diff options
Diffstat (limited to 'include/linux')
558 files changed, 16685 insertions, 9080 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b28f8790192a..d7136d13aa44 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -133,6 +133,7 @@ union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; struct acpi_prmt_module_header prmt; + struct acpi_cedt_header cedt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); @@ -140,6 +141,9 @@ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header, const unsigned long end); +typedef int (*acpi_tbl_entry_handler_arg)(union acpi_subtable_headers *header, + void *arg, const unsigned long end); + /* Debugger support */ struct acpi_debugger_ops { @@ -216,6 +220,8 @@ static inline int acpi_debugger_notify_command_complete(void) struct acpi_subtable_proc { int id; acpi_tbl_entry_handler handler; + acpi_tbl_entry_handler_arg handler_arg; + void *arg; int count; }; @@ -232,17 +238,31 @@ int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); + +#ifdef CONFIG_ACPI_TABLE_LIB +#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) +#define __init_or_acpilib +#define __initdata_or_acpilib +#else +#define EXPORT_SYMBOL_ACPI_LIB(x) +#define __init_or_acpilib __init +#define __initdata_or_acpilib __initdata +#endif + int acpi_table_parse(char *id, acpi_tbl_table_handler handler); -int __init acpi_table_parse_entries(char *id, unsigned long table_size, - int entry_id, - acpi_tbl_entry_handler handler, - unsigned int max_entries); -int __init acpi_table_parse_entries_array(char *id, unsigned long table_size, - struct acpi_subtable_proc *proc, int proc_num, - unsigned int max_entries); +int __init_or_acpilib acpi_table_parse_entries(char *id, + unsigned long table_size, int entry_id, + acpi_tbl_entry_handler handler, unsigned int max_entries); +int __init_or_acpilib acpi_table_parse_entries_array(char *id, + unsigned long table_size, struct acpi_subtable_proc *proc, + int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); +int __init_or_acpilib +acpi_table_parse_cedt(enum acpi_cedt_type id, + acpi_tbl_entry_handler_arg handler_arg, void *arg); + int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); @@ -506,7 +526,7 @@ acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -void __init acpi_no_s4_hw_signature(void); +extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP @@ -560,6 +580,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; +extern bool osc_sb_cppc_not_supported; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 @@ -671,7 +692,7 @@ int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, - struct property_entry *); + const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) @@ -910,7 +931,7 @@ static inline int acpi_device_modalias(struct device *dev, static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, - struct property_entry *properties) + const struct property_entry *properties) { return NULL; } @@ -1003,7 +1024,15 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); - +#ifdef CONFIG_X86 +struct acpi_s2idle_dev_ops { + struct list_head list_node; + void (*prepare)(void); + void (*restore)(void); +}; +int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); +void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); +#endif /* CONFIG_X86 */ #ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else @@ -1389,6 +1418,12 @@ static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) } #endif +#ifdef CONFIG_ACPI_PCC +void acpi_init_pcc(void); +#else +static inline void acpi_init_pcc(void) { } +#endif + #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); diff --git a/include/linux/acpi_agdi.h b/include/linux/acpi_agdi.h new file mode 100644 index 000000000000..f477f0b452fa --- /dev/null +++ b/include/linux/acpi_agdi.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ACPI_AGDI_H__ +#define __ACPI_AGDI_H__ + +#include <linux/acpi.h> + +#ifdef CONFIG_ACPI_AGDI +void __init acpi_agdi_init(void); +#else +static inline void acpi_agdi_init(void) {} +#endif +#endif /* __ACPI_AGDI_H__ */ diff --git a/include/linux/aio.h b/include/linux/aio.h index b83e68dd006f..86892a4fe7c8 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -20,8 +20,4 @@ static inline void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ -/* for sysctl: */ -extern unsigned long aio_nr; -extern unsigned long aio_max_nr; - #endif /* __LINUX__AIO_H */ diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index edfcf7a14dcd..6562f543c3e0 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -90,14 +90,8 @@ enum amba_vendor { AMBA_VENDOR_ST = 0x80, AMBA_VENDOR_QCOM = 0x51, AMBA_VENDOR_LSI = 0xb6, - AMBA_VENDOR_LINUX = 0xfe, /* This value is not official */ }; -/* This is used to generate pseudo-ID for AMBA device */ -#define AMBA_LINUX_ID(conf, rev, part) \ - (((conf) & 0xff) << 24 | ((rev) & 0xf) << 20 | \ - AMBA_VENDOR_LINUX << 12 | ((part) & 0xfff)) - extern struct bus_type amba_bustype; #define to_amba_device(d) container_of(d, struct amba_device, dev) @@ -123,30 +117,9 @@ void amba_device_put(struct amba_device *); int amba_device_add(struct amba_device *, struct resource *); int amba_device_register(struct amba_device *, struct resource *); void amba_device_unregister(struct amba_device *); -struct amba_device *amba_find_device(const char *, struct device *, unsigned int, unsigned int); int amba_request_regions(struct amba_device *, const char *); void amba_release_regions(struct amba_device *); -static inline int amba_pclk_enable(struct amba_device *dev) -{ - return clk_enable(dev->pclk); -} - -static inline void amba_pclk_disable(struct amba_device *dev) -{ - clk_disable(dev->pclk); -} - -static inline int amba_pclk_prepare(struct amba_device *dev) -{ - return clk_prepare(dev->pclk); -} - -static inline void amba_pclk_unprepare(struct amba_device *dev) -{ - clk_unprepare(dev->pclk); -} - /* Some drivers don't use the struct amba_device */ #define AMBA_CONFIG_BITS(a) (((a) >> 24) & 0xff) #define AMBA_REV_BITS(a) (((a) >> 20) & 0x0f) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index b97cea83b25e..58cbe18d825c 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -11,6 +11,10 @@ void topology_normalize_cpu_scale(void); int topology_update_cpu_topology(void); +#ifdef CONFIG_ACPI_CPPC_LIB +void topology_init_cpu_capacity_cppc(void); +#endif + struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); @@ -56,8 +60,8 @@ static inline unsigned long topology_get_thermal_pressure(int cpu) return per_cpu(thermal_pressure, cpu); } -void topology_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure); +void topology_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_freq); struct cpu_topology { int thread_id; diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 63ccb5252190..220c8c60e021 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -92,6 +92,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define ARM_SMCCC_ARCH_WORKAROUND_3 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x3fff) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 0a241c5c911d..14dc461b0e82 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -46,9 +46,11 @@ int sdei_unregister_ghes(struct ghes *ghes); /* For use by arch code when CPU hotplug notifiers are not appropriate. */ int sdei_mask_local_cpu(void); int sdei_unmask_local_cpu(void); +void __init sdei_init(void); #else static inline int sdei_mask_local_cpu(void) { return 0; } static inline int sdei_unmask_local_cpu(void) { return 0; } +static inline void sdei_init(void) { } #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/include/linux/ata.h b/include/linux/ata.h index 199e47e97d64..21292b5bbb55 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -324,12 +324,12 @@ enum { ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_IDENTIFY_DEVICE = 0x30, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, - ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, diff --git a/include/linux/atalk.h b/include/linux/atalk.h index f6034ba774be..a55bfc6567d0 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -113,7 +113,7 @@ extern int aarp_proto_init(void); /* Inter module exports */ /* Give a device find its atif control structure */ -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) static inline struct atalk_iface *atalk_find_dev(struct net_device *dev) { return dev->atalk_ptr; diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index a3dba31df01e..6db58d180866 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -151,7 +151,16 @@ static __always_inline int arch_atomic_read_acquire(const atomic_t *v) { - return smp_load_acquire(&(v)->counter); + int ret; + + if (__native_word(atomic_t)) { + ret = smp_load_acquire(&(v)->counter); + } else { + ret = arch_atomic_read(v); + __atomic_acquire_fence(); + } + + return ret; } #define arch_atomic_read_acquire arch_atomic_read_acquire #endif @@ -160,7 +169,12 @@ arch_atomic_read_acquire(const atomic_t *v) static __always_inline void arch_atomic_set_release(atomic_t *v, int i) { - smp_store_release(&(v)->counter, i); + if (__native_word(atomic_t)) { + smp_store_release(&(v)->counter, i); + } else { + __atomic_release_fence(); + arch_atomic_set(v, i); + } } #define arch_atomic_set_release arch_atomic_set_release #endif @@ -1258,7 +1272,16 @@ arch_atomic_dec_if_positive(atomic_t *v) static __always_inline s64 arch_atomic64_read_acquire(const atomic64_t *v) { - return smp_load_acquire(&(v)->counter); + s64 ret; + + if (__native_word(atomic64_t)) { + ret = smp_load_acquire(&(v)->counter); + } else { + ret = arch_atomic64_read(v); + __atomic_acquire_fence(); + } + + return ret; } #define arch_atomic64_read_acquire arch_atomic64_read_acquire #endif @@ -1267,7 +1290,12 @@ arch_atomic64_read_acquire(const atomic64_t *v) static __always_inline void arch_atomic64_set_release(atomic64_t *v, s64 i) { - smp_store_release(&(v)->counter, i); + if (__native_word(atomic64_t)) { + smp_store_release(&(v)->counter, i); + } else { + __atomic_release_fence(); + arch_atomic64_set(v, i); + } } #define arch_atomic64_set_release arch_atomic64_set_release #endif @@ -2358,4 +2386,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// cca554917d7ea73d5e3e7397dd70c484cad9b2c4 +// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index a0f654370da3..5d69b143c28e 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -45,6 +45,7 @@ atomic_set(atomic_t *v, int i) static __always_inline void atomic_set_release(atomic_t *v, int i) { + kcsan_release(); instrument_atomic_write(v, sizeof(*v)); arch_atomic_set_release(v, i); } @@ -59,6 +60,7 @@ atomic_add(int i, atomic_t *v) static __always_inline int atomic_add_return(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return(i, v); } @@ -73,6 +75,7 @@ atomic_add_return_acquire(int i, atomic_t *v) static __always_inline int atomic_add_return_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return_release(i, v); } @@ -87,6 +90,7 @@ atomic_add_return_relaxed(int i, atomic_t *v) static __always_inline int atomic_fetch_add(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add(i, v); } @@ -101,6 +105,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_release(i, v); } @@ -122,6 +127,7 @@ atomic_sub(int i, atomic_t *v) static __always_inline int atomic_sub_return(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return(i, v); } @@ -136,6 +142,7 @@ atomic_sub_return_acquire(int i, atomic_t *v) static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return_release(i, v); } @@ -150,6 +157,7 @@ atomic_sub_return_relaxed(int i, atomic_t *v) static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub(i, v); } @@ -164,6 +172,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub_release(i, v); } @@ -185,6 +194,7 @@ atomic_inc(atomic_t *v) static __always_inline int atomic_inc_return(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return(v); } @@ -199,6 +209,7 @@ atomic_inc_return_acquire(atomic_t *v) static __always_inline int atomic_inc_return_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return_release(v); } @@ -213,6 +224,7 @@ atomic_inc_return_relaxed(atomic_t *v) static __always_inline int atomic_fetch_inc(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc(v); } @@ -227,6 +239,7 @@ atomic_fetch_inc_acquire(atomic_t *v) static __always_inline int atomic_fetch_inc_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc_release(v); } @@ -248,6 +261,7 @@ atomic_dec(atomic_t *v) static __always_inline int atomic_dec_return(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return(v); } @@ -262,6 +276,7 @@ atomic_dec_return_acquire(atomic_t *v) static __always_inline int atomic_dec_return_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return_release(v); } @@ -276,6 +291,7 @@ atomic_dec_return_relaxed(atomic_t *v) static __always_inline int atomic_fetch_dec(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec(v); } @@ -290,6 +306,7 @@ atomic_fetch_dec_acquire(atomic_t *v) static __always_inline int atomic_fetch_dec_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec_release(v); } @@ -311,6 +328,7 @@ atomic_and(int i, atomic_t *v) static __always_inline int atomic_fetch_and(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and(i, v); } @@ -325,6 +343,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and_release(i, v); } @@ -346,6 +365,7 @@ atomic_andnot(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot(i, v); } @@ -360,6 +380,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot_release(i, v); } @@ -381,6 +402,7 @@ atomic_or(int i, atomic_t *v) static __always_inline int atomic_fetch_or(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or(i, v); } @@ -395,6 +417,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or_release(i, v); } @@ -416,6 +439,7 @@ atomic_xor(int i, atomic_t *v) static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor(i, v); } @@ -430,6 +454,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor_release(i, v); } @@ -444,6 +469,7 @@ atomic_fetch_xor_relaxed(int i, atomic_t *v) static __always_inline int atomic_xchg(atomic_t *v, int i) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg(v, i); } @@ -458,6 +484,7 @@ atomic_xchg_acquire(atomic_t *v, int i) static __always_inline int atomic_xchg_release(atomic_t *v, int i) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg_release(v, i); } @@ -472,6 +499,7 @@ atomic_xchg_relaxed(atomic_t *v, int i) static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg(v, old, new); } @@ -486,6 +514,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg_release(v, old, new); } @@ -500,6 +529,7 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg(v, old, new); @@ -516,6 +546,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg_release(v, old, new); @@ -532,6 +563,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_and_test(i, v); } @@ -539,6 +571,7 @@ atomic_sub_and_test(int i, atomic_t *v) static __always_inline bool atomic_dec_and_test(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_and_test(v); } @@ -546,6 +579,7 @@ atomic_dec_and_test(atomic_t *v) static __always_inline bool atomic_inc_and_test(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_and_test(v); } @@ -553,6 +587,7 @@ atomic_inc_and_test(atomic_t *v) static __always_inline bool atomic_add_negative(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_negative(i, v); } @@ -560,6 +595,7 @@ atomic_add_negative(int i, atomic_t *v) static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_unless(v, a, u); } @@ -567,6 +603,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_unless(v, a, u); } @@ -574,6 +611,7 @@ atomic_add_unless(atomic_t *v, int a, int u) static __always_inline bool atomic_inc_not_zero(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_not_zero(v); } @@ -581,6 +619,7 @@ atomic_inc_not_zero(atomic_t *v) static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_unless_negative(v); } @@ -588,6 +627,7 @@ atomic_inc_unless_negative(atomic_t *v) static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_unless_positive(v); } @@ -595,6 +635,7 @@ atomic_dec_unless_positive(atomic_t *v) static __always_inline int atomic_dec_if_positive(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_if_positive(v); } @@ -623,6 +664,7 @@ atomic64_set(atomic64_t *v, s64 i) static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { + kcsan_release(); instrument_atomic_write(v, sizeof(*v)); arch_atomic64_set_release(v, i); } @@ -637,6 +679,7 @@ atomic64_add(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return(i, v); } @@ -651,6 +694,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return_release(i, v); } @@ -665,6 +709,7 @@ atomic64_add_return_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add(i, v); } @@ -679,6 +724,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_release(i, v); } @@ -700,6 +746,7 @@ atomic64_sub(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return(i, v); } @@ -714,6 +761,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return_release(i, v); } @@ -728,6 +776,7 @@ atomic64_sub_return_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub(i, v); } @@ -742,6 +791,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub_release(i, v); } @@ -763,6 +813,7 @@ atomic64_inc(atomic64_t *v) static __always_inline s64 atomic64_inc_return(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return(v); } @@ -777,6 +828,7 @@ atomic64_inc_return_acquire(atomic64_t *v) static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return_release(v); } @@ -791,6 +843,7 @@ atomic64_inc_return_relaxed(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc(v); } @@ -805,6 +858,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc_release(v); } @@ -826,6 +880,7 @@ atomic64_dec(atomic64_t *v) static __always_inline s64 atomic64_dec_return(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return(v); } @@ -840,6 +895,7 @@ atomic64_dec_return_acquire(atomic64_t *v) static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return_release(v); } @@ -854,6 +910,7 @@ atomic64_dec_return_relaxed(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec(v); } @@ -868,6 +925,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec_release(v); } @@ -889,6 +947,7 @@ atomic64_and(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and(i, v); } @@ -903,6 +962,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and_release(i, v); } @@ -924,6 +984,7 @@ atomic64_andnot(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot(i, v); } @@ -938,6 +999,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot_release(i, v); } @@ -959,6 +1021,7 @@ atomic64_or(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or(i, v); } @@ -973,6 +1036,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or_release(i, v); } @@ -994,6 +1058,7 @@ atomic64_xor(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor(i, v); } @@ -1008,6 +1073,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor_release(i, v); } @@ -1022,6 +1088,7 @@ atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg(v, i); } @@ -1036,6 +1103,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i) static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 i) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg_release(v, i); } @@ -1050,6 +1118,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 i) static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg(v, old, new); } @@ -1064,6 +1133,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg_release(v, old, new); } @@ -1078,6 +1148,7 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg(v, old, new); @@ -1094,6 +1165,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg_release(v, old, new); @@ -1110,6 +1182,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } @@ -1117,6 +1190,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_and_test(v); } @@ -1124,6 +1198,7 @@ atomic64_dec_and_test(atomic64_t *v) static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_and_test(v); } @@ -1131,6 +1206,7 @@ atomic64_inc_and_test(atomic64_t *v) static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } @@ -1138,6 +1214,7 @@ atomic64_add_negative(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_unless(v, a, u); } @@ -1145,6 +1222,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_unless(v, a, u); } @@ -1152,6 +1230,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); } @@ -1159,6 +1238,7 @@ atomic64_inc_not_zero(atomic64_t *v) static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_unless_negative(v); } @@ -1166,6 +1246,7 @@ atomic64_inc_unless_negative(atomic64_t *v) static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_unless_positive(v); } @@ -1173,6 +1254,7 @@ atomic64_dec_unless_positive(atomic64_t *v) static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_if_positive(v); } @@ -1201,6 +1283,7 @@ atomic_long_set(atomic_long_t *v, long i) static __always_inline void atomic_long_set_release(atomic_long_t *v, long i) { + kcsan_release(); instrument_atomic_write(v, sizeof(*v)); arch_atomic_long_set_release(v, i); } @@ -1215,6 +1298,7 @@ atomic_long_add(long i, atomic_long_t *v) static __always_inline long atomic_long_add_return(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_return(i, v); } @@ -1229,6 +1313,7 @@ atomic_long_add_return_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_add_return_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_return_release(i, v); } @@ -1243,6 +1328,7 @@ atomic_long_add_return_relaxed(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_add(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_add(i, v); } @@ -1257,6 +1343,7 @@ atomic_long_fetch_add_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_add_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_add_release(i, v); } @@ -1278,6 +1365,7 @@ atomic_long_sub(long i, atomic_long_t *v) static __always_inline long atomic_long_sub_return(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_sub_return(i, v); } @@ -1292,6 +1380,7 @@ atomic_long_sub_return_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_sub_return_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_sub_return_release(i, v); } @@ -1306,6 +1395,7 @@ atomic_long_sub_return_relaxed(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_sub(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_sub(i, v); } @@ -1320,6 +1410,7 @@ atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_sub_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_sub_release(i, v); } @@ -1341,6 +1432,7 @@ atomic_long_inc(atomic_long_t *v) static __always_inline long atomic_long_inc_return(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_return(v); } @@ -1355,6 +1447,7 @@ atomic_long_inc_return_acquire(atomic_long_t *v) static __always_inline long atomic_long_inc_return_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_return_release(v); } @@ -1369,6 +1462,7 @@ atomic_long_inc_return_relaxed(atomic_long_t *v) static __always_inline long atomic_long_fetch_inc(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_inc(v); } @@ -1383,6 +1477,7 @@ atomic_long_fetch_inc_acquire(atomic_long_t *v) static __always_inline long atomic_long_fetch_inc_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_inc_release(v); } @@ -1404,6 +1499,7 @@ atomic_long_dec(atomic_long_t *v) static __always_inline long atomic_long_dec_return(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_return(v); } @@ -1418,6 +1514,7 @@ atomic_long_dec_return_acquire(atomic_long_t *v) static __always_inline long atomic_long_dec_return_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_return_release(v); } @@ -1432,6 +1529,7 @@ atomic_long_dec_return_relaxed(atomic_long_t *v) static __always_inline long atomic_long_fetch_dec(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_dec(v); } @@ -1446,6 +1544,7 @@ atomic_long_fetch_dec_acquire(atomic_long_t *v) static __always_inline long atomic_long_fetch_dec_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_dec_release(v); } @@ -1467,6 +1566,7 @@ atomic_long_and(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_and(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_and(i, v); } @@ -1481,6 +1581,7 @@ atomic_long_fetch_and_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_and_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_and_release(i, v); } @@ -1502,6 +1603,7 @@ atomic_long_andnot(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_andnot(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_andnot(i, v); } @@ -1516,6 +1618,7 @@ atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_andnot_release(i, v); } @@ -1537,6 +1640,7 @@ atomic_long_or(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_or(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_or(i, v); } @@ -1551,6 +1655,7 @@ atomic_long_fetch_or_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_or_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_or_release(i, v); } @@ -1572,6 +1677,7 @@ atomic_long_xor(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_xor(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_xor(i, v); } @@ -1586,6 +1692,7 @@ atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_xor_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_xor_release(i, v); } @@ -1600,6 +1707,7 @@ atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) static __always_inline long atomic_long_xchg(atomic_long_t *v, long i) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_xchg(v, i); } @@ -1614,6 +1722,7 @@ atomic_long_xchg_acquire(atomic_long_t *v, long i) static __always_inline long atomic_long_xchg_release(atomic_long_t *v, long i) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_xchg_release(v, i); } @@ -1628,6 +1737,7 @@ atomic_long_xchg_relaxed(atomic_long_t *v, long i) static __always_inline long atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_cmpxchg(v, old, new); } @@ -1642,6 +1752,7 @@ atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) static __always_inline long atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_cmpxchg_release(v, old, new); } @@ -1656,6 +1767,7 @@ atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) static __always_inline bool atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_long_try_cmpxchg(v, old, new); @@ -1672,6 +1784,7 @@ atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) static __always_inline bool atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_long_try_cmpxchg_release(v, old, new); @@ -1688,6 +1801,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) static __always_inline bool atomic_long_sub_and_test(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_sub_and_test(i, v); } @@ -1695,6 +1809,7 @@ atomic_long_sub_and_test(long i, atomic_long_t *v) static __always_inline bool atomic_long_dec_and_test(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_and_test(v); } @@ -1702,6 +1817,7 @@ atomic_long_dec_and_test(atomic_long_t *v) static __always_inline bool atomic_long_inc_and_test(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_and_test(v); } @@ -1709,6 +1825,7 @@ atomic_long_inc_and_test(atomic_long_t *v) static __always_inline bool atomic_long_add_negative(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_negative(i, v); } @@ -1716,6 +1833,7 @@ atomic_long_add_negative(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_add_unless(v, a, u); } @@ -1723,6 +1841,7 @@ atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) static __always_inline bool atomic_long_add_unless(atomic_long_t *v, long a, long u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_unless(v, a, u); } @@ -1730,6 +1849,7 @@ atomic_long_add_unless(atomic_long_t *v, long a, long u) static __always_inline bool atomic_long_inc_not_zero(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_not_zero(v); } @@ -1737,6 +1857,7 @@ atomic_long_inc_not_zero(atomic_long_t *v) static __always_inline bool atomic_long_inc_unless_negative(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_unless_negative(v); } @@ -1744,6 +1865,7 @@ atomic_long_inc_unless_negative(atomic_long_t *v) static __always_inline bool atomic_long_dec_unless_positive(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_unless_positive(v); } @@ -1751,6 +1873,7 @@ atomic_long_dec_unless_positive(atomic_long_t *v) static __always_inline long atomic_long_dec_if_positive(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_if_positive(v); } @@ -1758,6 +1881,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg(__ai_ptr, __VA_ARGS__); \ }) @@ -1772,6 +1896,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define xchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_release(__ai_ptr, __VA_ARGS__); \ }) @@ -1786,6 +1911,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) @@ -1800,6 +1926,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) @@ -1814,6 +1941,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg64(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) @@ -1828,6 +1956,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg64_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) @@ -1843,6 +1972,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ @@ -1861,6 +1991,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ @@ -1892,6 +2023,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define sync_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) @@ -1899,6 +2031,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_double(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ }) @@ -1912,4 +2045,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 2a9553f0a9d5619f19151092df5cabbbf16ce835 +// 87c974b93032afd42143613434d1a7788fa598f9 diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index fc51d45f106b..de21d9d24a95 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -11,12 +11,172 @@ #include <linux/device.h> #include <linux/mod_devicetable.h> +/** + * DOC: DEVICE_LIFESPAN + * + * The registering driver is the entity that allocates memory for the + * auxiliary_device and registers it on the auxiliary bus. It is important to + * note that, as opposed to the platform bus, the registering driver is wholly + * responsible for the management of the memory used for the device object. + * + * To be clear the memory for the auxiliary_device is freed in the release() + * callback defined by the registering driver. The registering driver should + * only call auxiliary_device_delete() and then auxiliary_device_uninit() when + * it is done with the device. The release() function is then automatically + * called if and when other code releases their reference to the devices. + * + * A parent object, defined in the shared header file, contains the + * auxiliary_device. It also contains a pointer to the shared object(s), which + * also is defined in the shared header. Both the parent object and the shared + * object(s) are allocated by the registering driver. This layout allows the + * auxiliary_driver's registering module to perform a container_of() call to go + * from the pointer to the auxiliary_device, that is passed during the call to + * the auxiliary_driver's probe function, up to the parent object, and then + * have access to the shared object(s). + * + * The memory for the shared object(s) must have a lifespan equal to, or + * greater than, the lifespan of the memory for the auxiliary_device. The + * auxiliary_driver should only consider that the shared object is valid as + * long as the auxiliary_device is still registered on the auxiliary bus. It + * is up to the registering driver to manage (e.g. free or keep available) the + * memory for the shared object beyond the life of the auxiliary_device. + * + * The registering driver must unregister all auxiliary devices before its own + * driver.remove() is completed. An easy way to ensure this is to use the + * devm_add_action_or_reset() call to register a function against the parent + * device which unregisters the auxiliary device object(s). + * + * Finally, any operations which operate on the auxiliary devices must continue + * to function (if only to return an error) after the registering driver + * unregisters the auxiliary device. + */ + +/** + * struct auxiliary_device - auxiliary device object. + * @dev: Device, + * The release and parent fields of the device structure must be filled + * in + * @name: Match name found by the auxiliary device driver, + * @id: unique identitier if multiple devices of the same name are exported, + * + * An auxiliary_device represents a part of its parent device's functionality. + * It is given a name that, combined with the registering drivers + * KBUILD_MODNAME, creates a match_name that is used for driver binding, and an + * id that combined with the match_name provide a unique name to register with + * the bus subsystem. For example, a driver registering an auxiliary device is + * named 'foo_mod.ko' and the subdevice is named 'foo_dev'. The match name is + * therefore 'foo_mod.foo_dev'. + * + * Registering an auxiliary_device is a three-step process. + * + * First, a 'struct auxiliary_device' needs to be defined or allocated for each + * sub-device desired. The name, id, dev.release, and dev.parent fields of + * this structure must be filled in as follows. + * + * The 'name' field is to be given a name that is recognized by the auxiliary + * driver. If two auxiliary_devices with the same match_name, eg + * "foo_mod.foo_dev", are registered onto the bus, they must have unique id + * values (e.g. "x" and "y") so that the registered devices names are + * "foo_mod.foo_dev.x" and "foo_mod.foo_dev.y". If match_name + id are not + * unique, then the device_add fails and generates an error message. + * + * The auxiliary_device.dev.type.release or auxiliary_device.dev.release must + * be populated with a non-NULL pointer to successfully register the + * auxiliary_device. This release call is where resources associated with the + * auxiliary device must be free'ed. Because once the device is placed on the + * bus the parent driver can not tell what other code may have a reference to + * this data. + * + * The auxiliary_device.dev.parent should be set. Typically to the registering + * drivers device. + * + * Second, call auxiliary_device_init(), which checks several aspects of the + * auxiliary_device struct and performs a device_initialize(). After this step + * completes, any error state must have a call to auxiliary_device_uninit() in + * its resolution path. + * + * The third and final step in registering an auxiliary_device is to perform a + * call to auxiliary_device_add(), which sets the name of the device and adds + * the device to the bus. + * + * .. code-block:: c + * + * #define MY_DEVICE_NAME "foo_dev" + * + * ... + * + * struct auxiliary_device *my_aux_dev = my_aux_dev_alloc(xxx); + * + * // Step 1: + * my_aux_dev->name = MY_DEVICE_NAME; + * my_aux_dev->id = my_unique_id_alloc(xxx); + * my_aux_dev->dev.release = my_aux_dev_release; + * my_aux_dev->dev.parent = my_dev; + * + * // Step 2: + * if (auxiliary_device_init(my_aux_dev)) + * goto fail; + * + * // Step 3: + * if (auxiliary_device_add(my_aux_dev)) { + * auxiliary_device_uninit(my_aux_dev); + * goto fail; + * } + * + * ... + * + * + * Unregistering an auxiliary_device is a two-step process to mirror the + * register process. First call auxiliary_device_delete(), then call + * auxiliary_device_uninit(). + * + * .. code-block:: c + * + * auxiliary_device_delete(my_dev->my_aux_dev); + * auxiliary_device_uninit(my_dev->my_aux_dev); + */ struct auxiliary_device { struct device dev; const char *name; u32 id; }; +/** + * struct auxiliary_driver - Definition of an auxiliary bus driver + * @probe: Called when a matching device is added to the bus. + * @remove: Called when device is removed from the bus. + * @shutdown: Called at shut-down time to quiesce the device. + * @suspend: Called to put the device to sleep mode. Usually to a power state. + * @resume: Called to bring a device from sleep mode. + * @name: Driver name. + * @driver: Core driver structure. + * @id_table: Table of devices this driver should match on the bus. + * + * Auxiliary drivers follow the standard driver model convention, where + * discovery/enumeration is handled by the core, and drivers provide probe() + * and remove() methods. They support power management and shutdown + * notifications using the standard conventions. + * + * Auxiliary drivers register themselves with the bus by calling + * auxiliary_driver_register(). The id_table contains the match_names of + * auxiliary devices that a driver can bind with. + * + * .. code-block:: c + * + * static const struct auxiliary_device_id my_auxiliary_id_table[] = { + * { .name = "foo_mod.foo_dev" }, + * {}, + * }; + * + * MODULE_DEVICE_TABLE(auxiliary, my_auxiliary_id_table); + * + * struct auxiliary_driver my_drv = { + * .name = "myauxiliarydrv", + * .id_table = my_auxiliary_id_table, + * .probe = my_drv_probe, + * .remove = my_drv_remove + * }; + */ struct auxiliary_driver { int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id); void (*remove)(struct auxiliary_device *auxdev); @@ -28,6 +188,16 @@ struct auxiliary_driver { const struct auxiliary_device_id *id_table; }; +static inline void *auxiliary_get_drvdata(struct auxiliary_device *auxdev) +{ + return dev_get_drvdata(&auxdev->dev); +} + +static inline void auxiliary_set_drvdata(struct auxiliary_device *auxdev, void *data) +{ + dev_set_drvdata(&auxdev->dev, data); +} + static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) { return container_of(dev, struct auxiliary_device, dev); @@ -66,6 +236,10 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); * Helper macro for auxiliary drivers which do not do anything special in * module init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() + * + * .. code-block:: c + * + * module_auxiliary_driver(my_drv); */ #define module_auxiliary_driver(__auxiliary_driver) \ module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister) diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b30a1bc74fc7..2ce27e8e4f19 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -141,6 +141,13 @@ enum virtchnl_ops { VIRTCHNL_OP_DEL_RSS_CFG = 46, VIRTCHNL_OP_ADD_FDIR_FILTER = 47, VIRTCHNL_OP_DEL_FDIR_FILTER = 48, + VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS = 51, + VIRTCHNL_OP_ADD_VLAN_V2 = 52, + VIRTCHNL_OP_DEL_VLAN_V2 = 53, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 = 54, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55, + VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56, + VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57, VIRTCHNL_OP_MAX, }; @@ -246,6 +253,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 BIT(18) @@ -475,6 +483,351 @@ struct virtchnl_vlan_filter_list { VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); +/* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related + * structures and opcodes. + * + * VIRTCHNL_VLAN_UNSUPPORTED - This field is not supported and if a VF driver + * populates it the PF should return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED. + * + * VIRTCHNL_VLAN_ETHERTYPE_8100 - This field supports 0x8100 ethertype. + * VIRTCHNL_VLAN_ETHERTYPE_88A8 - This field supports 0x88A8 ethertype. + * VIRTCHNL_VLAN_ETHERTYPE_9100 - This field supports 0x9100 ethertype. + * + * VIRTCHNL_VLAN_ETHERTYPE_AND - Used when multiple ethertypes can be supported + * by the PF concurrently. For example, if the PF can support + * VIRTCHNL_VLAN_ETHERTYPE_8100 AND VIRTCHNL_VLAN_ETHERTYPE_88A8 filters it + * would OR the following bits: + * + * VIRTHCNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * The VF would interpret this as VLAN filtering can be supported on both 0x8100 + * and 0x88A8 VLAN ethertypes. + * + * VIRTCHNL_ETHERTYPE_XOR - Used when only a single ethertype can be supported + * by the PF concurrently. For example if the PF can support + * VIRTCHNL_VLAN_ETHERTYPE_8100 XOR VIRTCHNL_VLAN_ETHERTYPE_88A8 stripping + * offload it would OR the following bits: + * + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * The VF would interpret this as VLAN stripping can be supported on either + * 0x8100 or 0x88a8 VLAN ethertypes. So when requesting VLAN stripping via + * VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 the specified ethertype will override + * the previously set value. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1 - Used to tell the VF to insert and/or + * strip the VLAN tag using the L2TAG1 field of the Tx/Rx descriptors. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 - Used to tell the VF to insert hardware + * offloaded VLAN tags using the L2TAG2 field of the Tx descriptor. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 - Used to tell the VF to strip hardware + * offloaded VLAN tags using the L2TAG2_2 field of the Rx descriptor. + * + * VIRTCHNL_VLAN_PRIO - This field supports VLAN priority bits. This is used for + * VLAN filtering if the underlying PF supports it. + * + * VIRTCHNL_VLAN_TOGGLE_ALLOWED - This field is used to say whether a + * certain VLAN capability can be toggled. For example if the underlying PF/CP + * allows the VF to toggle VLAN filtering, stripping, and/or insertion it should + * set this bit along with the supported ethertypes. + */ +enum virtchnl_vlan_support { + VIRTCHNL_VLAN_UNSUPPORTED = 0, + VIRTCHNL_VLAN_ETHERTYPE_8100 = BIT(0), + VIRTCHNL_VLAN_ETHERTYPE_88A8 = BIT(1), + VIRTCHNL_VLAN_ETHERTYPE_9100 = BIT(2), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1 = BIT(8), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 = BIT(9), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 = BIT(10), + VIRTCHNL_VLAN_PRIO = BIT(24), + VIRTCHNL_VLAN_FILTER_MASK = BIT(28), + VIRTCHNL_VLAN_ETHERTYPE_AND = BIT(29), + VIRTCHNL_VLAN_ETHERTYPE_XOR = BIT(30), + VIRTCHNL_VLAN_TOGGLE = BIT(31), +}; + +/* This structure is used as part of the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS + * for filtering, insertion, and stripping capabilities. + * + * If only outer capabilities are supported (for filtering, insertion, and/or + * stripping) then this refers to the outer most or single VLAN from the VF's + * perspective. + * + * If only inner capabilities are supported (for filtering, insertion, and/or + * stripping) then this refers to the outer most or single VLAN from the VF's + * perspective. Functionally this is the same as if only outer capabilities are + * supported. The VF driver is just forced to use the inner fields when + * adding/deleting filters and enabling/disabling offloads (if supported). + * + * If both outer and inner capabilities are supported (for filtering, insertion, + * and/or stripping) then outer refers to the outer most or single VLAN and + * inner refers to the second VLAN, if it exists, in the packet. + * + * There is no support for tunneled VLAN offloads, so outer or inner are never + * referring to a tunneled packet from the VF's perspective. + */ +struct virtchnl_vlan_supported_caps { + u32 outer; + u32 inner; +}; + +/* The PF populates these fields based on the supported VLAN filtering. If a + * field is VIRTCHNL_VLAN_UNSUPPORTED then it's not supported and the PF will + * reject any VIRTCHNL_OP_ADD_VLAN_V2 or VIRTCHNL_OP_DEL_VLAN_V2 messages using + * the unsupported fields. + * + * Also, a VF is only allowed to toggle its VLAN filtering setting if the + * VIRTCHNL_VLAN_TOGGLE bit is set. + * + * The ethertype(s) specified in the ethertype_init field are the ethertypes + * enabled for VLAN filtering. VLAN filtering in this case refers to the outer + * most VLAN from the VF's perspective. If both inner and outer filtering are + * allowed then ethertype_init only refers to the outer most VLAN as only + * VLAN ethertype supported for inner VLAN filtering is + * VIRTCHNL_VLAN_ETHERTYPE_8100. By default, inner VLAN filtering is disabled + * when both inner and outer filtering are allowed. + * + * The max_filters field tells the VF how many VLAN filters it's allowed to have + * at any one time. If it exceeds this amount and tries to add another filter, + * then the request will be rejected by the PF. To prevent failures, the VF + * should keep track of how many VLAN filters it has added and not attempt to + * add more than max_filters. + */ +struct virtchnl_vlan_filtering_caps { + struct virtchnl_vlan_supported_caps filtering_support; + u32 ethertype_init; + u16 max_filters; + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vlan_filtering_caps); + +/* This enum is used for the virtchnl_vlan_offload_caps structure to specify + * if the PF supports a different ethertype for stripping and insertion. + * + * VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION - The ethertype(s) specified + * for stripping affect the ethertype(s) specified for insertion and visa versa + * as well. If the VF tries to configure VLAN stripping via + * VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 with VIRTCHNL_VLAN_ETHERTYPE_8100 then + * that will be the ethertype for both stripping and insertion. + * + * VIRTCHNL_ETHERTYPE_MATCH_NOT_REQUIRED - The ethertype(s) specified for + * stripping do not affect the ethertype(s) specified for insertion and visa + * versa. + */ +enum virtchnl_vlan_ethertype_match { + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION = 0, + VIRTCHNL_ETHERTYPE_MATCH_NOT_REQUIRED = 1, +}; + +/* The PF populates these fields based on the supported VLAN offloads. If a + * field is VIRTCHNL_VLAN_UNSUPPORTED then it's not supported and the PF will + * reject any VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 or + * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 messages using the unsupported fields. + * + * Also, a VF is only allowed to toggle its VLAN offload setting if the + * VIRTCHNL_VLAN_TOGGLE_ALLOWED bit is set. + * + * The VF driver needs to be aware of how the tags are stripped by hardware and + * inserted by the VF driver based on the level of offload support. The PF will + * populate these fields based on where the VLAN tags are expected to be + * offloaded via the VIRTHCNL_VLAN_TAG_LOCATION_* bits. The VF will need to + * interpret these fields. See the definition of the + * VIRTCHNL_VLAN_TAG_LOCATION_* bits above the virtchnl_vlan_support + * enumeration. + */ +struct virtchnl_vlan_offload_caps { + struct virtchnl_vlan_supported_caps stripping_support; + struct virtchnl_vlan_supported_caps insertion_support; + u32 ethertype_init; + u8 ethertype_match; + u8 pad[3]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_vlan_offload_caps); + +/* VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS + * VF sends this message to determine its VLAN capabilities. + * + * PF will mark which capabilities it supports based on hardware support and + * current configuration. For example, if a port VLAN is configured the PF will + * not allow outer VLAN filtering, stripping, or insertion to be configured so + * it will block these features from the VF. + * + * The VF will need to cross reference its capabilities with the PFs + * capabilities in the response message from the PF to determine the VLAN + * support. + */ +struct virtchnl_vlan_caps { + struct virtchnl_vlan_filtering_caps filtering; + struct virtchnl_vlan_offload_caps offloads; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_caps); + +struct virtchnl_vlan { + u16 tci; /* tci[15:13] = PCP and tci[11:0] = VID */ + u16 tci_mask; /* only valid if VIRTCHNL_VLAN_FILTER_MASK set in + * filtering caps + */ + u16 tpid; /* 0x8100, 0x88a8, etc. and only type(s) set in + * filtering caps. Note that tpid here does not refer to + * VIRTCHNL_VLAN_ETHERTYPE_*, but it refers to the + * actual 2-byte VLAN TPID + */ + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan); + +struct virtchnl_vlan_filter { + struct virtchnl_vlan inner; + struct virtchnl_vlan outer; + u8 pad[16]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(32, virtchnl_vlan_filter); + +/* VIRTCHNL_OP_ADD_VLAN_V2 + * VIRTCHNL_OP_DEL_VLAN_V2 + * + * VF sends these messages to add/del one or more VLAN tag filters for Rx + * traffic. + * + * The PF attempts to add the filters and returns status. + * + * The VF should only ever attempt to add/del virtchnl_vlan_filter(s) using the + * supported fields negotiated via VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS. + */ +struct virtchnl_vlan_filter_list_v2 { + u16 vport_id; + u16 num_elements; + u8 pad[4]; + struct virtchnl_vlan_filter filters[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2); + +/* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 + * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 + * VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 + * VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 + * + * VF sends this message to enable or disable VLAN stripping or insertion. It + * also needs to specify an ethertype. The VF knows which VLAN ethertypes are + * allowed and whether or not it's allowed to enable/disable the specific + * offload via the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS message. The VF needs to + * parse the virtchnl_vlan_caps.offloads fields to determine which offload + * messages are allowed. + * + * For example, if the PF populates the virtchnl_vlan_caps.offloads in the + * following manner the VF will be allowed to enable and/or disable 0x8100 inner + * VLAN insertion and/or stripping via the opcodes listed above. Inner in this + * case means the outer most or single VLAN from the VF's perspective. This is + * because no outer offloads are supported. See the comments above the + * virtchnl_vlan_supported_caps structure for more details. + * + * virtchnl_vlan_caps.offloads.stripping_support.inner = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * virtchnl_vlan_caps.offloads.insertion_support.inner = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * In order to enable inner (again note that in this case inner is the outer + * most or single VLAN from the VF's perspective) VLAN stripping for 0x8100 + * VLANs, the VF would populate the virtchnl_vlan_setting structure in the + * following manner and send the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 message. + * + * virtchnl_vlan_setting.inner_ethertype_setting = + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + * + * The reason that VLAN TPID(s) are not being used for the + * outer_ethertype_setting and inner_ethertype_setting fields is because it's + * possible a device could support VLAN insertion and/or stripping offload on + * multiple ethertypes concurrently, so this method allows a VF to request + * multiple ethertypes in one message using the virtchnl_vlan_support + * enumeration. + * + * For example, if the PF populates the virtchnl_vlan_caps.offloads in the + * following manner the VF will be allowed to enable 0x8100 and 0x88a8 outer + * VLAN insertion and stripping simultaneously. The + * virtchnl_vlan_caps.offloads.ethertype_match field will also have to be + * populated based on what the PF can support. + * + * virtchnl_vlan_caps.offloads.stripping_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * virtchnl_vlan_caps.offloads.insertion_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * In order to enable outer VLAN stripping for 0x8100 and 0x88a8 VLANs, the VF + * would populate the virthcnl_vlan_offload_structure in the following manner + * and send the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 message. + * + * virtchnl_vlan_setting.outer_ethertype_setting = + * VIRTHCNL_VLAN_ETHERTYPE_8100 | + * VIRTHCNL_VLAN_ETHERTYPE_88A8; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + * + * There is also the case where a PF and the underlying hardware can support + * VLAN offloads on multiple ethertypes, but not concurrently. For example, if + * the PF populates the virtchnl_vlan_caps.offloads in the following manner the + * VF will be allowed to enable and/or disable 0x8100 XOR 0x88a8 outer VLAN + * offloads. The ethertypes must match for stripping and insertion. + * + * virtchnl_vlan_caps.offloads.stripping_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * virtchnl_vlan_caps.offloads.insertion_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * virtchnl_vlan_caps.offloads.ethertype_match = + * VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + * + * In order to enable outer VLAN stripping for 0x88a8 VLANs, the VF would + * populate the virtchnl_vlan_setting structure in the following manner and send + * the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2. Also, this will change the + * ethertype for VLAN insertion if it's enabled. So, for completeness, a + * VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 with the same ethertype should be sent. + * + * virtchnl_vlan_setting.outer_ethertype_setting = VIRTHCNL_VLAN_ETHERTYPE_88A8; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + */ +struct virtchnl_vlan_setting { + u32 outer_ethertype_setting; + u32 inner_ethertype_setting; + u16 vport_id; + u8 pad[6]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vlan_setting); + /* VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE * VF sends VSI id and flags. * PF returns status code in retval. @@ -1156,6 +1509,30 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_DEL_FDIR_FILTER: valid_len = sizeof(struct virtchnl_fdir_del); break; + case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: + break; + case VIRTCHNL_OP_ADD_VLAN_V2: + case VIRTCHNL_OP_DEL_VLAN_V2: + valid_len = sizeof(struct virtchnl_vlan_filter_list_v2); + if (msglen >= valid_len) { + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + + valid_len += (vfl->num_elements - 1) * + sizeof(struct virtchnl_vlan_filter); + + if (vfl->num_elements == 0) { + err_msg_format = true; + break; + } + } + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2: + case VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2: + case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: + valid_len = sizeof(struct virtchnl_vlan_setting); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 993c5628a726..e863c88df95f 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -207,14 +207,6 @@ struct backing_dev_info { #endif }; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; - -void clear_bdi_congested(struct backing_dev_info *bdi, int sync); -void set_bdi_congested(struct backing_dev_info *bdi, int sync); - struct wb_lock_cookie { bool locked; unsigned long flags; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 483979c1b9f4..87ce24d238f3 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -135,13 +135,6 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb) struct backing_dev_info *inode_to_bdi(struct inode *inode); -static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) -{ - return wb->congested & cong_bits; -} - -long congestion_wait(int sync, long timeout); - static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; @@ -162,7 +155,6 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct blkcg *blkcg); -int inode_congested(struct inode *inode, int cong_bits); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -390,50 +382,8 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg) { } -static inline int inode_congested(struct inode *inode, int cong_bits) -{ - return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); -} - #endif /* CONFIG_CGROUP_WRITEBACK */ -static inline int inode_read_congested(struct inode *inode) -{ - return inode_congested(inode, 1 << WB_sync_congested); -} - -static inline int inode_write_congested(struct inode *inode) -{ - return inode_congested(inode, 1 << WB_async_congested); -} - -static inline int inode_rw_congested(struct inode *inode) -{ - return inode_congested(inode, (1 << WB_sync_congested) | - (1 << WB_async_congested)); -} - -static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) -{ - return wb_congested(&bdi->wb, cong_bits); -} - -static inline int bdi_read_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << WB_sync_congested); -} - -static inline int bdi_write_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, 1 << WB_async_congested); -} - -static inline int bdi_rw_congested(struct backing_dev_info *bdi) -{ - return bdi_congested(bdi, (1 << WB_sync_congested) | - (1 << WB_async_congested)); -} - const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 338aa27e4773..edb7f6d41faa 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -80,12 +80,6 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) #ifdef CONFIG_BALLOON_COMPACTION extern const struct address_space_operations balloon_aops; -extern bool balloon_page_isolate(struct page *page, - isolate_mode_t mode); -extern void balloon_page_putback(struct page *page); -extern int balloon_page_migrate(struct address_space *mapping, - struct page *newpage, - struct page *page, enum migrate_mode mode); /* * balloon_page_insert - insert a page into the balloon's page list and make @@ -155,22 +149,6 @@ static inline void balloon_page_delete(struct page *page) list_del(&page->lru); } -static inline bool balloon_page_isolate(struct page *page) -{ - return false; -} - -static inline void balloon_page_putback(struct page *page) -{ - return; -} - -static inline int balloon_page_migrate(struct page *newpage, - struct page *page, enum migrate_mode mode) -{ - return 0; -} - static inline gfp_t balloon_mapping_gfp_mask(void) { return GFP_HIGHUSER; diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index d35b9206096d..e3314f746bfa 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -3,6 +3,7 @@ #define LINUX_BCMA_DRIVER_CC_H_ #include <linux/platform_device.h> +#include <linux/platform_data/brcmnand.h> #include <linux/gpio.h> /** ChipCommon core registers. **/ @@ -599,6 +600,10 @@ struct bcma_sflash { #ifdef CONFIG_BCMA_NFLASH struct bcma_nflash { + /* Must be the fist member for the brcmnand driver to + * de-reference that structure. + */ + struct brcmnand_platform_data brcmnand_info; bool present; bool boot; /* This is the flash the SoC boots from */ }; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 049cf9421d83..3dc20c4f394c 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -8,6 +8,7 @@ #include <uapi/linux/binfmts.h> struct filename; +struct coredump_params; #define CORENAME_MAX_SIZE 128 @@ -77,18 +78,6 @@ struct linux_binprm { #define BINPRM_FLAGS_PRESERVE_ARGV0_BIT 3 #define BINPRM_FLAGS_PRESERVE_ARGV0 (1 << BINPRM_FLAGS_PRESERVE_ARGV0_BIT) -/* Function parameter for binfmt->coredump */ -struct coredump_params { - const kernel_siginfo_t *siginfo; - struct pt_regs *regs; - struct file *file; - unsigned long limit; - unsigned long mm_flags; - loff_t written; - loff_t pos; - loff_t to_skip; -}; - /* * This structure defines the functions that are used to load the binary formats that * linux accepts. @@ -98,8 +87,10 @@ struct linux_binfmt { struct module *module; int (*load_binary)(struct linux_binprm *); int (*load_shlib)(struct file *); +#ifdef CONFIG_COREDUMP int (*core_dump)(struct coredump_params *cprm); unsigned long min_coredump; /* minimal dump size */ +#endif } __randomize_layout; extern void __register_binfmt(struct linux_binfmt *fmt, int insert); diff --git a/include/linux/bio.h b/include/linux/bio.h index fe6bdfbbef66..278cc81cc1e7 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -65,7 +65,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || - bio_op(bio) == REQ_OP_WRITE_SAME || bio_op(bio) == REQ_OP_WRITE_ZEROES; } @@ -124,7 +123,7 @@ void __bio_advance(struct bio *, unsigned bytes); /** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance - * @bytes: number of bytes to complete + * @nbytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will @@ -166,7 +165,7 @@ static inline void bio_advance(struct bio *bio, unsigned int nbytes) */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ - i < (bio)->bi_vcnt; i++, bvl++) \ + i < (bio)->bi_vcnt; i++, bvl++) #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) @@ -186,8 +185,6 @@ static inline unsigned bio_segments(struct bio *bio) case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; - case REQ_OP_WRITE_SAME: - return 1; default: break; } @@ -260,6 +257,57 @@ static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) return &bio->bi_io_vec[bio->bi_vcnt - 1]; } +/** + * struct folio_iter - State for iterating all folios in a bio. + * @folio: The current folio we're iterating. NULL after the last folio. + * @offset: The byte offset within the current folio. + * @length: The number of bytes in this iteration (will not cross folio + * boundary). + */ +struct folio_iter { + struct folio *folio; + size_t offset; + size_t length; + /* private: for use by the iterator */ + size_t _seg_count; + int _i; +}; + +static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, + int i) +{ + struct bio_vec *bvec = bio_first_bvec_all(bio) + i; + + fi->folio = page_folio(bvec->bv_page); + fi->offset = bvec->bv_offset + + PAGE_SIZE * (bvec->bv_page - &fi->folio->page); + fi->_seg_count = bvec->bv_len; + fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_i = i; +} + +static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) +{ + fi->_seg_count -= fi->length; + if (fi->_seg_count) { + fi->folio = folio_next(fi->folio); + fi->offset = 0; + fi->length = min(folio_size(fi->folio), fi->_seg_count); + } else if (fi->_i + 1 < bio->bi_vcnt) { + bio_first_folio(fi, bio, fi->_i + 1); + } else { + fi->folio = NULL; + } +} + +/** + * bio_for_each_folio_all - Iterate over each folio in a bio. + * @fi: struct folio_iter which is updated for each folio. + * @bio: struct bio to iterate over. + */ +#define bio_for_each_folio_all(fi, bio) \ + for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ @@ -332,7 +380,7 @@ extern struct bio *bio_split(struct bio *bio, int sectors, * @gfp: gfp mask * @bs: bio set to allocate from * - * Returns a bio representing the next @sectors of @bio - if the bio is smaller + * Return: a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, @@ -354,21 +402,25 @@ extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); -struct bio *bio_alloc_bioset(gfp_t gfp, unsigned short nr_iovecs, - struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs, - struct bio_set *bs); +struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, + unsigned int opf, gfp_t gfp_mask, + struct bio_set *bs); +struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, + unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); extern void bio_put(struct bio *); -extern void __bio_clone_fast(struct bio *, struct bio *); -extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); +struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, + gfp_t gfp, struct bio_set *bs); +int bio_init_clone(struct block_device *bdev, struct bio *bio, + struct bio *bio_src, gfp_t gfp); extern struct bio_set fs_bio_set; -static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs) +static inline struct bio *bio_alloc(struct block_device *bdev, + unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask) { - return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); + return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set); } void submit_bio(struct bio *bio); @@ -403,13 +455,14 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) struct request_queue; extern int submit_bio_wait(struct bio *bio); -extern void bio_init(struct bio *bio, struct bio_vec *table, - unsigned short max_vecs); +void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, + unsigned short max_vecs, unsigned int opf); extern void bio_uninit(struct bio *); -extern void bio_reset(struct bio *); +void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf); void bio_chain(struct bio *, struct bio *); -extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); +int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); +bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, @@ -435,8 +488,6 @@ static inline void bio_release_pages(struct bio *bio, bool mark_dirty) __bio_release_pages(bio, mark_dirty); } -extern const char *bio_devname(struct bio *bio, char *buffer); - #define bio_dev(bio) \ disk_devt((bio)->bi_bdev->bd_disk) @@ -463,13 +514,6 @@ static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) bio_associate_blkg(bio); } -static inline void bio_copy_dev(struct bio *dst, struct bio *src) -{ - bio_clear_flag(dst, BIO_REMAPPED); - dst->bi_bdev = src->bi_bdev; - bio_clone_blkg_association(dst, src); -} - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * @@ -738,6 +782,7 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } -struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); +struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, + unsigned int nr_pages, unsigned int opf, gfp_t gfp); #endif /* __LINUX_BIO_H */ diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 4e035aca6f7e..c9be1657f03d 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -19,6 +19,9 @@ * * Example: * + * #include <linux/bitfield.h> + * #include <linux/bits.h> + * * #define REG_FIELD_A GENMASK(6, 0) * #define REG_FIELD_B BIT(7) * #define REG_FIELD_C GENMASK(15, 8) @@ -41,6 +44,22 @@ #define __bf_shf(x) (__builtin_ffsll(x) - 1) +#define __scalar_type_to_unsigned_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (unsigned type)0 + +#define __unsigned_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (unsigned char)0, \ + __scalar_type_to_unsigned_cases(char), \ + __scalar_type_to_unsigned_cases(short), \ + __scalar_type_to_unsigned_cases(int), \ + __scalar_type_to_unsigned_cases(long), \ + __scalar_type_to_unsigned_cases(long long), \ + default: (x))) + +#define __bf_cast_unsigned(type, x) ((__unsigned_scalar_typeof(type))(x)) + #define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx) \ ({ \ BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ @@ -49,7 +68,8 @@ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ _pfx "value too large for the field"); \ - BUILD_BUG_ON_MSG((_mask) > (typeof(_reg))~0ull, \ + BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ + __bf_cast_unsigned(_reg, ~0ull), \ _pfx "type of reg too small for mask"); \ __BUILD_BUG_ON_NOT_POWER_OF_2((_mask) + \ (1ULL << __bf_shf(_mask))); \ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a241dcf50f39..7dba0847510c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -6,6 +6,7 @@ #include <linux/align.h> #include <linux/bitops.h> +#include <linux/find.h> #include <linux/limits.h> #include <linux/string.h> #include <linux/types.h> @@ -54,12 +55,6 @@ struct device; * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above - * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region - * bitmap_next_set_region(map, &start, &end, nbits) Find next set region - * bitmap_for_each_clear_region(map, rs, re, start, end) - * Iterate over all clear regions - * bitmap_for_each_set_region(map, rs, re, start, end) - * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest @@ -466,14 +461,6 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } -static inline void bitmap_next_clear_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) -{ - *rs = find_next_zero_bit(bitmap, end, *rs); - *re = find_next_bit(bitmap, end, *rs + 1); -} - static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) @@ -482,25 +469,6 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, *re = find_next_zero_bit(bitmap, end, *rs + 1); } -/* - * Bitmap region iterators. Iterates over the bitmap between [@start, @end). - * @rs and @re should be integer variables and will be set to start and end - * index of the current clear or set region. - */ -#define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) - -#define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end))) - /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 5e62e2383b7f..7aaed501f768 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -32,40 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w); */ #include <asm/bitops.h> -#define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -#define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_first_zero_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) - -/* same as for_each_clear_bit() but use bit as value to start with */ -#define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) - -/** - * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits - * @start: bit offset to start search and to store the current iteration offset - * @clump: location to store copy of current 8-bit clump - * @bits: bitmap address to base the search on - * @size: bitmap size in number of bits - */ -#define for_each_set_clump8(start, clump, bits, size) \ - for ((start) = find_first_clump8(&(clump), (bits), (size)); \ - (start) < (size); \ - (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) - static inline int get_bitmask_order(unsigned int count) { int order; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index b4de2010fba5..f2ad8ed8f777 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -25,14 +25,8 @@ #include <linux/kthread.h> #include <linux/fs.h> -/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ -#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) - -/* Max limits for throttle policy */ -#define THROTL_IOPS_MAX UINT_MAX #define FC_APPID_LEN 129 - #ifdef CONFIG_BLK_CGROUP enum blkg_iostat_type { @@ -44,6 +38,7 @@ enum blkg_iostat_type { }; struct blkcg_gq; +struct blkg_policy_data; struct blkcg { struct cgroup_subsys_state css; @@ -76,36 +71,6 @@ struct blkg_iostat_set { struct blkg_iostat last; }; -/* - * A blkcg_gq (blkg) is association between a block cgroup (blkcg) and a - * request_queue (q). This is used by blkcg policies which need to track - * information per blkcg - q pair. - * - * There can be multiple active blkcg policies and each blkg:policy pair is - * represented by a blkg_policy_data which is allocated and freed by each - * policy's pd_alloc/free_fn() methods. A policy can allocate private data - * area by allocating larger data structure which embeds blkg_policy_data - * at the beginning. - */ -struct blkg_policy_data { - /* the blkg and policy id this per-policy data belongs to */ - struct blkcg_gq *blkg; - int plid; -}; - -/* - * Policies that need to keep per-blkcg data which is independent from any - * request_queue associated to it should implement cpd_alloc/free_fn() - * methods. A policy can allocate private data area by allocating larger - * data structure which embeds blkcg_policy_data at the beginning. - * cpd_init() is invoked to let each policy handle per-blkcg data. - */ -struct blkcg_policy_data { - /* the blkcg and policy id this per-policy data belongs to */ - struct blkcg *blkcg; - int plid; -}; - /* association between a blk cgroup and a request queue */ struct blkcg_gq { /* Pointer to the associated request_queue */ @@ -141,93 +106,11 @@ struct blkcg_gq { struct rcu_head rcu_head; }; -typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); -typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); -typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); -typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); -typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, - struct request_queue *q, struct blkcg *blkcg); -typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); -typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); -typedef bool (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, - struct seq_file *s); - -struct blkcg_policy { - int plid; - /* cgroup files for the policy */ - struct cftype *dfl_cftypes; - struct cftype *legacy_cftypes; - - /* operations */ - blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; - blkcg_pol_init_cpd_fn *cpd_init_fn; - blkcg_pol_free_cpd_fn *cpd_free_fn; - blkcg_pol_bind_cpd_fn *cpd_bind_fn; - - blkcg_pol_alloc_pd_fn *pd_alloc_fn; - blkcg_pol_init_pd_fn *pd_init_fn; - blkcg_pol_online_pd_fn *pd_online_fn; - blkcg_pol_offline_pd_fn *pd_offline_fn; - blkcg_pol_free_pd_fn *pd_free_fn; - blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; - blkcg_pol_stat_pd_fn *pd_stat_fn; -}; - -extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; -extern bool blkcg_debug_stats; - -struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, - struct request_queue *q, bool update_hint); -int blkcg_init_queue(struct request_queue *q); -void blkcg_exit_queue(struct request_queue *q); - -/* Blkio controller policy registration */ -int blkcg_policy_register(struct blkcg_policy *pol); -void blkcg_policy_unregister(struct blkcg_policy *pol); -int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol); -void blkcg_deactivate_policy(struct request_queue *q, - const struct blkcg_policy *pol); - -const char *blkg_dev_name(struct blkcg_gq *blkg); -void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, - u64 (*prfill)(struct seq_file *, - struct blkg_policy_data *, int), - const struct blkcg_policy *pol, int data, - bool show_total); -u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); - -struct blkg_conf_ctx { - struct block_device *bdev; - struct blkcg_gq *blkg; - char *body; -}; - -struct block_device *blkcg_conf_open_bdev(char **inputp); -int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, - char *input, struct blkg_conf_ctx *ctx); -void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} +void blkcg_destroy_blkgs(struct blkcg *blkcg); +void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); +void blkcg_maybe_throttle_current(void); static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { @@ -235,27 +118,6 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) } /** - * __bio_blkcg - internal, inconsistent version to get blkcg - * - * DO NOT USE. - * This function is inconsistent and consequently is dangerous to use. The - * first part of the function returns a blkcg where a reference is owned by the - * bio. This means it does not need to be rcu protected as it cannot go away - * with the bio owning a reference to it. However, the latter potentially gets - * it from task_css(). This can race against task migration and the cgroup - * dying. It is also semantically different as it must be called rcu protected - * and is susceptible to failure when trying to get a reference to it. - * Therefore, it is not ok to assume that *_get() will always succeed on the - * blkcg returned here. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** * bio_blkcg - grab the blkcg associated with a bio * @bio: target bio * @@ -291,22 +153,6 @@ static inline bool blk_cgroup_congested(void) } /** - * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg - * @return: true if this bio needs to be submitted with the root blkg context. - * - * In order to avoid priority inversions we sometimes need to issue a bio as if - * it were attached to the root blkg, and then backcharge to the actual owning - * blkg. The idea is we do bio_blkcg() to look up the actual context for the - * bio and attach the appropriate blkg to the bio. Then we call this helper and - * if it is true run with the root blkg for that queue and then do any - * backcharging to the originating cgroup once the io is complete. - */ -static inline bool bio_issue_as_root_blkg(struct bio *bio) -{ - return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0; -} - -/** * blkcg_parent - get the parent of a blkcg * @blkcg: blkcg of interest * @@ -318,96 +164,6 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) } /** - * __blkg_lookup - internal version of blkg_lookup() - * @blkcg: blkcg of interest - * @q: request_queue of interest - * @update_hint: whether to update lookup hint with the result or not - * - * This is internal version and shouldn't be used by policy - * implementations. Looks up blkgs for the @blkcg - @q pair regardless of - * @q's bypass state. If @update_hint is %true, the caller should be - * holding @q->queue_lock and lookup hint is updated on success. - */ -static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, - struct request_queue *q, - bool update_hint) -{ - struct blkcg_gq *blkg; - - if (blkcg == &blkcg_root) - return q->root_blkg; - - blkg = rcu_dereference(blkcg->blkg_hint); - if (blkg && blkg->q == q) - return blkg; - - return blkg_lookup_slowpath(blkcg, q, update_hint); -} - -/** - * blkg_lookup - lookup blkg for the specified blkcg - q pair - * @blkcg: blkcg of interest - * @q: request_queue of interest - * - * Lookup blkg for the @blkcg - @q pair. This function should be called - * under RCU read lock. - */ -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, - struct request_queue *q) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return __blkg_lookup(blkcg, q, false); -} - -/** - * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair - * @q: request_queue of interest - * - * Lookup blkg for @q at the root level. See also blkg_lookup(). - */ -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ - return q->root_blkg; -} - -/** - * blkg_to_pdata - get policy private data - * @blkg: blkg of interest - * @pol: policy of interest - * - * Return pointer to private data associated with the @blkg-@pol pair. - */ -static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, - struct blkcg_policy *pol) -{ - return blkg ? blkg->pd[pol->plid] : NULL; -} - -static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, - struct blkcg_policy *pol) -{ - return blkcg ? blkcg->cpd[pol->plid] : NULL; -} - -/** - * pdata_to_blkg - get blkg associated with policy private data - * @pd: policy private data of interest - * - * @pd is policy private data. Determine the blkg it's associated with. - */ -static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) -{ - return pd ? pd->blkg : NULL; -} - -static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) -{ - return cpd ? cpd->blkcg : NULL; -} - -extern void blkcg_destroy_blkgs(struct blkcg *blkcg); - -/** * blkcg_pin_online - pin online state * @blkcg: blkcg of interest * @@ -439,231 +195,24 @@ static inline void blkcg_unpin_online(struct blkcg *blkcg) } while (blkcg); } -/** - * blkg_path - format cgroup path of blkg - * @blkg: blkg of interest - * @buf: target buffer - * @buflen: target buffer length - * - * Format the path of the cgroup of @blkg into @buf. - */ -static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) -{ - return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen); -} - -/** - * blkg_get - get a blkg reference - * @blkg: blkg to get - * - * The caller should be holding an existing reference. - */ -static inline void blkg_get(struct blkcg_gq *blkg) -{ - percpu_ref_get(&blkg->refcnt); -} - -/** - * blkg_tryget - try and get a blkg reference - * @blkg: blkg to get - * - * This is for use when doing an RCU lookup of the blkg. We may be in the midst - * of freeing this blkg, so we can only use it if the refcnt is not zero. - */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) -{ - return blkg && percpu_ref_tryget(&blkg->refcnt); -} - -/** - * blkg_put - put a blkg reference - * @blkg: blkg to put - */ -static inline void blkg_put(struct blkcg_gq *blkg) -{ - percpu_ref_put(&blkg->refcnt); -} - -/** - * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants - * @d_blkg: loop cursor pointing to the current descendant - * @pos_css: used for iteration - * @p_blkg: target blkg to walk descendants of - * - * Walk @c_blkg through the descendants of @p_blkg. Must be used with RCU - * read locked. If called under either blkcg or queue lock, the iteration - * is guaranteed to include all and only online blkgs. The caller may - * update @pos_css by calling css_rightmost_descendant() to skip subtree. - * @p_blkg is included in the iteration and the first node to be visited. - */ -#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg) \ - css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) - -/** - * blkg_for_each_descendant_post - post-order walk of a blkg's descendants - * @d_blkg: loop cursor pointing to the current descendant - * @pos_css: used for iteration - * @p_blkg: target blkg to walk descendants of - * - * Similar to blkg_for_each_descendant_pre() but performs post-order - * traversal instead. Synchronization rules are the same. @p_blkg is - * included in the iteration and the last node to be visited. - */ -#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg) \ - css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css) \ - if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ - (p_blkg)->q, false))) - -bool __blkcg_punt_bio_submit(struct bio *bio); - -static inline bool blkcg_punt_bio_submit(struct bio *bio) -{ - if (bio->bi_opf & REQ_CGROUP_PUNT) - return __blkcg_punt_bio_submit(bio); - else - return false; -} - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - -static inline void blkcg_use_delay(struct blkcg_gq *blkg) -{ - if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) - return; - if (atomic_add_return(1, &blkg->use_delay) == 1) - atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); -} - -static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) -{ - int old = atomic_read(&blkg->use_delay); - - if (WARN_ON_ONCE(old < 0)) - return 0; - if (old == 0) - return 0; - - /* - * We do this song and dance because we can race with somebody else - * adding or removing delay. If we just did an atomic_dec we'd end up - * negative and we'd already be in trouble. We need to subtract 1 and - * then check to see if we were the last delay so we can drop the - * congestion count on the cgroup. - */ - while (old) { - int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); - if (cur == old) - break; - old = cur; - } - - if (old == 0) - return 0; - if (old == 1) - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); - return 1; -} - -/** - * blkcg_set_delay - Enable allocator delay mechanism with the specified delay amount - * @blkg: target blkg - * @delay: delay duration in nsecs - * - * When enabled with this function, the delay is not decayed and must be - * explicitly cleared with blkcg_clear_delay(). Must not be mixed with - * blkcg_[un]use_delay() and blkcg_add_delay() usages. - */ -static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) -{ - int old = atomic_read(&blkg->use_delay); - - /* We only want 1 person setting the congestion count for this blkg. */ - if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) - atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); - - atomic64_set(&blkg->delay_nsec, delay); -} - -/** - * blkcg_clear_delay - Disable allocator delay mechanism - * @blkg: target blkg - * - * Disable use_delay mechanism. See blkcg_set_delay(). - */ -static inline void blkcg_clear_delay(struct blkcg_gq *blkg) -{ - int old = atomic_read(&blkg->use_delay); - - /* We only want 1 person clearing the congestion count for this blkg. */ - if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) - atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); -} - -void blk_cgroup_bio_start(struct bio *bio); -void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); -void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); -void blkcg_maybe_throttle_current(void); #else /* CONFIG_BLK_CGROUP */ struct blkcg { }; -struct blkg_policy_data { -}; - -struct blkcg_policy_data { -}; - struct blkcg_gq { }; -struct blkcg_policy { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } #ifdef CONFIG_BLOCK - static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } - -static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } -static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q) -{ return NULL; } -static inline int blkcg_init_queue(struct request_queue *q) { return 0; } -static inline void blkcg_exit_queue(struct request_queue *q) { } -static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; } -static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { } -static inline int blkcg_activate_policy(struct request_queue *q, - const struct blkcg_policy *pol) { return 0; } -static inline void blkcg_deactivate_policy(struct request_queue *q, - const struct blkcg_policy *pol) { } - -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } +#endif /* CONFIG_BLOCK */ -static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, - struct blkcg_policy *pol) { return NULL; } -static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; } -static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } -static inline void blkg_get(struct blkcg_gq *blkg) { } -static inline void blkg_put(struct blkcg_gq *blkg) { } - -static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } -static inline void blk_cgroup_bio_start(struct bio *bio) { } - -#define blk_queue_for_each_rl(rl, q) \ - for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) - -#endif /* CONFIG_BLOCK */ #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_BLK_CGROUP_FC_APPID diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index 8a038ea0717e..378b2459efe2 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -19,6 +19,7 @@ struct blk_integrity_iter { sector_t seed; unsigned int data_size; unsigned short interval; + unsigned char tuple_size; const char *disk_name; }; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2949d9ac7484..7aa5c54901a9 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -4,7 +4,6 @@ #include <linux/blkdev.h> #include <linux/sbitmap.h> -#include <linux/srcu.h> #include <linux/lockdep.h> #include <linux/scatterlist.h> #include <linux/prefetch.h> @@ -100,7 +99,6 @@ struct request { struct request *rq_next; }; - struct gendisk *rq_disk; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ @@ -140,7 +138,7 @@ struct request { unsigned short ioprio; enum mq_rq_state state; - refcount_t ref; + atomic_t ref; unsigned long deadline; @@ -218,6 +216,56 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) +#define rq_list_add(listptr, rq) do { \ + (rq)->rq_next = *(listptr); \ + *(listptr) = rq; \ +} while (0) + +#define rq_list_pop(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) { \ + __req = *(listptr); \ + *(listptr) = __req->rq_next; \ + } \ + __req; \ +}) + +#define rq_list_peek(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) \ + __req = *(listptr); \ + __req; \ +}) + +#define rq_list_for_each(listptr, pos) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) + +#define rq_list_for_each_safe(listptr, pos, nxt) \ + for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos); \ + pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL) + +#define rq_list_next(rq) (rq)->rq_next +#define rq_list_empty(list) ((list) == (struct request *) NULL) + +/** + * rq_list_move() - move a struct request from one list to another + * @src: The source list @rq is currently in + * @dst: The destination list that @rq will be appended to + * @rq: The request to move + * @prev: The request preceding @rq in @src (NULL if @rq is the head) + */ +static inline void rq_list_move(struct request **src, struct request **dst, + struct request *rq, struct request *prev) +{ + if (prev) + prev->rq_next = rq->rq_next; + else + *src = rq->rq_next; + rq_list_add(dst, rq); +} + enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ @@ -376,13 +424,6 @@ struct blk_mq_hw_ctx { * q->unused_hctx_list. */ struct list_head hctx_list; - - /** - * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is - * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also - * blk_mq_hw_ctx_size(). - */ - struct srcu_struct srcu[]; }; /** @@ -479,8 +520,6 @@ struct blk_mq_queue_data { bool last; }; -typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, - bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); /** @@ -504,6 +543,14 @@ struct blk_mq_ops { void (*commit_rqs)(struct blk_mq_hw_ctx *); /** + * @queue_rqs: Queue a list of new requests. Driver is guaranteed + * that each request belongs to the same queue. If the driver doesn't + * empty the @rqlist completely, then the rest will be queued + * individually by the block layer upon return. + */ + void (*queue_rqs)(struct request **rqlist); + + /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case @@ -752,6 +799,17 @@ static inline void blk_mq_set_request_complete(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } +/* + * Complete the request directly instead of deferring it to softirq or + * completing it another CPU. Useful in preemptible instead of an interrupt. + */ +static inline void blk_mq_complete_request_direct(struct request *rq, + void (*complete)(struct request *rq)) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); + complete(rq); +} + void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); @@ -859,8 +917,7 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) } #define queue_for_each_hw_ctx(q, hctx, i) \ - for ((i) = 0; (i) < (q)->nr_hw_queues && \ - ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) + xa_for_each(&(q)->hctx_table, (i), (hctx)) #define hctx_for_each_ctx(hctx, ctx, i) \ for ((i) = 0; (i) < (hctx)->nr_ctx && \ @@ -879,9 +936,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; rq->ioprio = bio_prio(bio); - - if (bio->bi_bdev) - rq->rq_disk = bio->bi_bdev->bd_disk; } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, @@ -897,8 +951,7 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); void blk_rq_unprep_clone(struct request *rq); -blk_status_t blk_insert_cloned_request(struct request_queue *q, - struct request *rq); +blk_status_t blk_insert_cloned_request(struct request *rq); struct rq_map_data { struct page **pages; @@ -917,10 +970,9 @@ int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); int blk_rq_append_bio(struct request *rq, struct bio *bio); -void blk_execute_rq_nowait(struct gendisk *, struct request *, int, - rq_end_io_fn *); -blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, - int at_head); +void blk_execute_rq_nowait(struct request *rq, bool at_head, + rq_end_io_fn *end_io); +blk_status_t blk_execute_rq(struct request *rq, bool at_head); struct req_iterator { struct bvec_iter iter; @@ -947,7 +999,6 @@ struct req_iterator { * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment - * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats @@ -971,8 +1022,6 @@ static inline int blk_rq_cur_bytes(const struct request *rq) return bio_iovec(rq->bio).bv_len; } -unsigned int blk_rq_err_bytes(const struct request *rq); - static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; @@ -1135,14 +1184,4 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) } #endif /* CONFIG_BLK_DEV_ZONED */ -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" -#endif -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -void rq_flush_dcache_pages(struct request *rq); -#else -static inline void rq_flush_dcache_pages(struct request *rq) -{ -} -#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ #endif /* BLK_MQ_H */ diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h index b80c65aba249..2580e05a8ab6 100644 --- a/include/linux/blk-pm.h +++ b/include/linux/blk-pm.h @@ -14,7 +14,7 @@ extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); extern int blk_pre_runtime_suspend(struct request_queue *q); extern void blk_post_runtime_suspend(struct request_queue *q, int err); extern void blk_pre_runtime_resume(struct request_queue *q); -extern void blk_post_runtime_resume(struct request_queue *q, int err); +extern void blk_post_runtime_resume(struct request_queue *q); extern void blk_set_runtime_active(struct request_queue *q); #else static inline void blk_pm_runtime_init(struct request_queue *q, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index fe065c394fff..dd0763a1c674 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -153,6 +153,13 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +/* + * BLK_STS_OFFLINE is returned from the driver when the target device is offline + * or is being taken offline. This could help differentiate the case where a + * device is intentionally being shut down from a real I/O error. + */ +#define BLK_STS_OFFLINE ((__force blk_status_t)17) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -243,7 +250,6 @@ struct bio { */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; - unsigned short bi_write_hint; blk_status_t bi_status; atomic_t __bi_remaining; @@ -317,7 +323,8 @@ enum { BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ - BIO_TRACKED, /* set if bio goes through the rq_qos path */ + BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ + BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ @@ -354,8 +361,6 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* write the same sector many times */ - REQ_OP_WRITE_SAME = 7, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bd4370baccca..60d016138997 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1,9 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Portions Copyright (C) 1992 Drew Eckhardt + */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H -#include <linux/sched.h> -#include <linux/genhd.h> +#include <linux/types.h> +#include <linux/blk_types.h> +#include <linux/device.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/minmax.h> @@ -12,10 +16,15 @@ #include <linux/wait.h> #include <linux/bio.h> #include <linux/gfp.h> +#include <linux/kdev_t.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/blkzoned.h> +#include <linux/sched.h> #include <linux/sbitmap.h> +#include <linux/srcu.h> +#include <linux/uuid.h> +#include <linux/xarray.h> struct module; struct request_queue; @@ -32,6 +41,10 @@ struct blk_queue_stats; struct blk_stat_callback; struct blk_crypto_profile; +extern const struct device_type disk_type; +extern struct device_type part_type; +extern struct class block_class; + /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 @@ -44,7 +57,146 @@ struct blk_crypto_profile; */ #define BLKCG_MAX_POLS 6 -static inline int blk_validate_block_size(unsigned int bsize) +#define DISK_MAX_PARTS 256 +#define DISK_NAME_LEN 32 + +#define PARTITION_META_INFO_VOLNAMELTH 64 +/* + * Enough for the string representation of any kind of UUID plus NULL. + * EFI UUID is 36 characters. MSDOS UUID is 11 characters. + */ +#define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) + +struct partition_meta_info { + char uuid[PARTITION_META_INFO_UUIDLTH]; + u8 volname[PARTITION_META_INFO_VOLNAMELTH]; +}; + +/** + * DOC: genhd capability flags + * + * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to + * removable media. When set, the device remains present even when media is not + * inserted. Shall not be set for devices which are removed entirely when the + * media is removed. + * + * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, + * doesn't appear in sysfs, and can't be opened from userspace or using + * blkdev_get*. Used for the underlying components of multipath devices. + * + * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not + * scan for partitions from add_disk, and users can't add partitions manually. + * + */ +enum { + GENHD_FL_REMOVABLE = 1 << 0, + GENHD_FL_HIDDEN = 1 << 1, + GENHD_FL_NO_PART = 1 << 2, +}; + +enum { + DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ + DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ +}; + +enum { + /* Poll even if events_poll_msecs is unset */ + DISK_EVENT_FLAG_POLL = 1 << 0, + /* Forward events to udev */ + DISK_EVENT_FLAG_UEVENT = 1 << 1, + /* Block event polling when open for exclusive write */ + DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, +}; + +struct disk_events; +struct badblocks; + +struct blk_integrity { + const struct blk_integrity_profile *profile; + unsigned char flags; + unsigned char tuple_size; + unsigned char interval_exp; + unsigned char tag_size; +}; + +struct gendisk { + /* + * major/first_minor/minors should not be set by any new driver, the + * block core will take care of allocating them automatically. + */ + int major; + int first_minor; + int minors; + + char disk_name[DISK_NAME_LEN]; /* name of major driver */ + + unsigned short events; /* supported events */ + unsigned short event_flags; /* flags related to event processing */ + + struct xarray part_tbl; + struct block_device *part0; + + const struct block_device_operations *fops; + struct request_queue *queue; + void *private_data; + + int flags; + unsigned long state; +#define GD_NEED_PART_SCAN 0 +#define GD_READ_ONLY 1 +#define GD_DEAD 2 +#define GD_NATIVE_CAPACITY 3 +#define GD_ADDED 4 + + struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ + + struct backing_dev_info *bdi; + struct kobject *slave_dir; +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED + struct list_head slave_bdevs; +#endif + struct timer_rand_state *random; + atomic_t sync_io; /* RAID */ + struct disk_events *ev; +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct kobject integrity_kobj; +#endif /* CONFIG_BLK_DEV_INTEGRITY */ +#if IS_ENABLED(CONFIG_CDROM) + struct cdrom_device_info *cdi; +#endif + int node_id; + struct badblocks *bb; + struct lockdep_map lockdep_map; + u64 diskseq; +}; + +static inline bool disk_live(struct gendisk *disk) +{ + return !inode_unhashed(disk->part0->bd_inode); +} + +/* + * The gendisk is refcounted by the part0 block_device, and the bd_device + * therein is also used for device model presentation in sysfs. + */ +#define dev_to_disk(device) \ + (dev_to_bdev(device)->bd_disk) +#define disk_to_dev(disk) \ + (&((disk)->part0->bd_device)) + +#if IS_REACHABLE(CONFIG_CDROM) +#define disk_to_cdi(disk) ((disk)->cdi) +#else +#define disk_to_cdi(disk) NULL +#endif + +static inline dev_t disk_devt(struct gendisk *disk) +{ + return MKDEV(disk->major, disk->first_minor); +} + +static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; @@ -96,7 +248,6 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; - unsigned int max_write_same_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -203,7 +354,7 @@ struct request_queue { unsigned int queue_depth; /* hw dispatch queues */ - struct blk_mq_hw_ctx **queue_hw_ctx; + struct xarray hctx_table; unsigned int nr_hw_queues; /* @@ -261,13 +412,14 @@ struct request_queue { #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; + struct kobject *crypto_kobject; #endif unsigned int rq_timeout; int poll_nsec; struct blk_stat_callback *poll_cb; - struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; + struct blk_rq_stat *poll_stat; struct timer_list timeout; struct work_struct timeout_work; @@ -365,19 +517,23 @@ struct request_queue { bool mq_sysfs_init_done; -#define BLK_MAX_WRITE_HINTS 5 - u64 write_hints[BLK_MAX_WRITE_HINTS]; - /* * Independent sector access ranges. This is always NULL for * devices that do not have multiple independent access ranges. */ struct blk_independent_access_ranges *ia_ranges; + + /** + * @srcu: Sleepable RCU. Use as lock when type of the request queue + * is blocking (BLK_MQ_F_BLOCKING). Must be the last member + */ + struct srcu_struct srcu[]; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ +#define QUEUE_FLAG_HAS_SRCU 2 /* SRCU is allocated */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ @@ -397,7 +553,6 @@ struct request_queue { #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ -#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ @@ -416,6 +571,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) +#define blk_queue_has_srcu(q) test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) @@ -588,6 +744,118 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int __must_check add_disk(struct gendisk *disk) +{ + return device_add_disk(NULL, disk, NULL); +} +void del_gendisk(struct gendisk *gp); +void invalidate_disk(struct gendisk *disk); +void set_disk_ro(struct gendisk *disk, bool read_only); +void disk_uevent(struct gendisk *disk, enum kobject_action action); + +static inline int get_disk_ro(struct gendisk *disk) +{ + return disk->part0->bd_read_only || + test_bit(GD_READ_ONLY, &disk->state); +} + +static inline int bdev_read_only(struct block_device *bdev) +{ + return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); +} + +bool set_capacity_and_notify(struct gendisk *disk, sector_t size); +bool disk_force_media_change(struct gendisk *disk, unsigned int events); + +void add_disk_randomness(struct gendisk *disk) __latent_entropy; +void rand_initialize_disk(struct gendisk *disk); + +static inline sector_t get_start_sect(struct block_device *bdev) +{ + return bdev->bd_start_sect; +} + +static inline sector_t bdev_nr_sectors(struct block_device *bdev) +{ + return bdev->bd_nr_sectors; +} + +static inline loff_t bdev_nr_bytes(struct block_device *bdev) +{ + return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; +} + +static inline sector_t get_capacity(struct gendisk *disk) +{ + return bdev_nr_sectors(disk->part0); +} + +static inline u64 sb_bdev_nr_blocks(struct super_block *sb) +{ + return bdev_nr_sectors(sb->s_bdev) >> + (sb->s_blocksize_bits - SECTOR_SHIFT); +} + +int bdev_disk_changed(struct gendisk *disk, bool invalidate); + +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass); +void put_disk(struct gendisk *disk); +struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); + +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + static struct lock_class_key __key; \ + \ + __blk_alloc_disk(node_id, &__key); \ +}) +void blk_cleanup_disk(struct gendisk *disk); + +int __register_blkdev(unsigned int major, const char *name, + void (*probe)(dev_t devt)); +#define register_blkdev(major, name) \ + __register_blkdev(major, name, NULL) +void unregister_blkdev(unsigned int major, const char *name); + +bool bdev_check_media_change(struct block_device *bdev); +int __invalidate_device(struct block_device *bdev, bool kill_dirty); +void set_capacity(struct gendisk *disk, sector_t size); + +#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +int bd_register_pending_holders(struct gendisk *disk); +#else +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} +static inline int bd_register_pending_holders(struct gendisk *disk) +{ + return 0; +} +#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ + +dev_t part_devt(struct gendisk *disk, u8 partno); +void inc_diskseq(struct gendisk *disk); +dev_t blk_lookup_devt(const char *name, int partno); +void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); @@ -643,9 +911,6 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); - if (unlikely(op == REQ_OP_WRITE_SAME)) - return q->limits.max_write_same_sectors; - if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; @@ -688,8 +953,6 @@ extern void blk_queue_max_discard_segments(struct request_queue *, extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); -extern void blk_queue_max_write_same_sectors(struct request_queue *q, - unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); @@ -740,7 +1003,8 @@ extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); -extern void blk_set_queue_dying(struct request_queue *); + +void blk_mark_disk_dead(struct gendisk *disk); #ifdef CONFIG_BLOCK /* @@ -783,14 +1047,11 @@ extern void blk_start_plug(struct blk_plug *); extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); -void blk_flush_plug(struct blk_plug *plug, bool from_schedule); - -static inline bool blk_needs_flush_plug(struct task_struct *tsk) +void __blk_flush_plug(struct blk_plug *plug, bool from_schedule); +static inline void blk_flush_plug(struct blk_plug *plug, bool async) { - struct blk_plug *plug = tsk->plug; - - return plug && - (plug->mq_list || !list_empty(&plug->cb_list)); + if (plug) + __blk_flush_plug(plug, async); } int blkdev_issue_flush(struct block_device *bdev); @@ -816,11 +1077,6 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } -static inline bool blk_needs_flush_plug(struct task_struct *tsk) -{ - return false; -} - static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; @@ -834,9 +1090,6 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, struct page *page); - #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, @@ -1063,16 +1316,6 @@ static inline int bdev_discard_alignment(struct block_device *bdev) return q->limits.discard_alignment; } -static inline unsigned int bdev_write_same(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_same_sectors; - - return 0; -} - static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1171,8 +1414,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q); -void blk_crypto_unregister(struct request_queue *q); - #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, @@ -1181,8 +1422,6 @@ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, return true; } -static inline void blk_crypto_unregister(struct request_queue *q) { } - #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ enum blk_unique_id { @@ -1196,6 +1435,8 @@ enum blk_unique_id { struct block_device_operations { void (*submit_bio)(struct bio *bio); + int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, + unsigned int flags); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); @@ -1206,6 +1447,7 @@ struct block_device_operations { void (*unlock_native_capacity) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); int (*set_read_only)(struct block_device *bdev, bool ro); + void (*free_disk)(struct gendisk *disk); /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, @@ -1254,6 +1496,7 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); +void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); @@ -1261,7 +1504,7 @@ void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, /** * bio_end_io_acct - end I/O accounting for bio based drivers * @bio: bio to end account for - * @start: start time returned by bio_start_io_acct() + * @start_time: start time returned by bio_start_io_acct() */ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { @@ -1306,6 +1549,7 @@ void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); +void printk_all_partitions(void); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1321,7 +1565,11 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -#endif +static inline void printk_all_partitions(void) +{ +} +#endif /* CONFIG_BLOCK */ + int fsync_bdev(struct block_device *bdev); int freeze_bdev(struct block_device *bdev); @@ -1335,33 +1583,4 @@ struct io_comp_batch { #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) - -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) - -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) - -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \ - -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) - #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index 2bc8b1f69c93..cc35d010fa94 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -30,7 +30,7 @@ void put_page_bootmem(struct page *page); */ static inline void free_bootmem_page(struct page *page) { - unsigned long magic = (unsigned long)page->freelist; + unsigned long magic = page->index; /* * The reserve_bootmem_region sets the reserved flag on bootmem diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h new file mode 100644 index 000000000000..695d1224a71b --- /dev/null +++ b/include/linux/bpf-cgroup-defs.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_CGROUP_DEFS_H +#define _BPF_CGROUP_DEFS_H + +#ifdef CONFIG_CGROUP_BPF + +#include <linux/list.h> +#include <linux/percpu-refcount.h> +#include <linux/workqueue.h> + +struct bpf_prog_array; + +enum cgroup_bpf_attach_type { + CGROUP_BPF_ATTACH_TYPE_INVALID = -1, + CGROUP_INET_INGRESS = 0, + CGROUP_INET_EGRESS, + CGROUP_INET_SOCK_CREATE, + CGROUP_SOCK_OPS, + CGROUP_DEVICE, + CGROUP_INET4_BIND, + CGROUP_INET6_BIND, + CGROUP_INET4_CONNECT, + CGROUP_INET6_CONNECT, + CGROUP_INET4_POST_BIND, + CGROUP_INET6_POST_BIND, + CGROUP_UDP4_SENDMSG, + CGROUP_UDP6_SENDMSG, + CGROUP_SYSCTL, + CGROUP_UDP4_RECVMSG, + CGROUP_UDP6_RECVMSG, + CGROUP_GETSOCKOPT, + CGROUP_SETSOCKOPT, + CGROUP_INET4_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, + CGROUP_INET4_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, + CGROUP_INET_SOCK_RELEASE, + MAX_CGROUP_BPF_ATTACH_TYPE +}; + +struct cgroup_bpf { + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS + */ + struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; + + /* list of cgroup shared storages */ + struct list_head storages; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array *inactive; + + /* reference counter used to detach bpf programs after cgroup removal */ + struct percpu_ref refcnt; + + /* cgroup_bpf is released using a work queue */ + struct work_struct release_work; +}; + +#else /* CONFIG_CGROUP_BPF */ +struct cgroup_bpf {}; +#endif /* CONFIG_CGROUP_BPF */ + +#endif diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 11820a430d6c..88a51b242adc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -3,11 +3,12 @@ #define _BPF_CGROUP_H #include <linux/bpf.h> +#include <linux/bpf-cgroup-defs.h> #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/percpu.h> -#include <linux/percpu-refcount.h> #include <linux/rbtree.h> +#include <net/sock.h> #include <uapi/linux/bpf.h> struct sock; @@ -23,33 +24,6 @@ struct ctl_table_header; struct task_struct; #ifdef CONFIG_CGROUP_BPF -enum cgroup_bpf_attach_type { - CGROUP_BPF_ATTACH_TYPE_INVALID = -1, - CGROUP_INET_INGRESS = 0, - CGROUP_INET_EGRESS, - CGROUP_INET_SOCK_CREATE, - CGROUP_SOCK_OPS, - CGROUP_DEVICE, - CGROUP_INET4_BIND, - CGROUP_INET6_BIND, - CGROUP_INET4_CONNECT, - CGROUP_INET6_CONNECT, - CGROUP_INET4_POST_BIND, - CGROUP_INET6_POST_BIND, - CGROUP_UDP4_SENDMSG, - CGROUP_UDP6_SENDMSG, - CGROUP_SYSCTL, - CGROUP_UDP4_RECVMSG, - CGROUP_UDP6_RECVMSG, - CGROUP_GETSOCKOPT, - CGROUP_SETSOCKOPT, - CGROUP_INET4_GETPEERNAME, - CGROUP_INET6_GETPEERNAME, - CGROUP_INET4_GETSOCKNAME, - CGROUP_INET6_GETSOCKNAME, - CGROUP_INET_SOCK_RELEASE, - MAX_CGROUP_BPF_ATTACH_TYPE -}; #define CGROUP_ATYPE(type) \ case BPF_##type: return type @@ -127,33 +101,6 @@ struct bpf_prog_list { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; -struct bpf_prog_array; - -struct cgroup_bpf { - /* array of effective progs in this cgroup */ - struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; - - /* attached progs to this cgroup and attach flags - * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will - * have either zero or one element - * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS - */ - struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; - u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; - - /* list of cgroup shared storages */ - struct list_head storages; - - /* temp storage for effective prog array used by prog_attach/detach */ - struct bpf_prog_array *inactive; - - /* reference counter used to detach bpf programs after cgroup removal */ - struct percpu_ref refcnt; - - /* cgroup_bpf is released using a work queue */ - struct work_struct release_work; -}; - int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); @@ -219,11 +166,23 @@ int bpf_percpu_cgroup_storage_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, void *value, u64 flags); +/* Opportunistic check to see whether we have any BPF program attached*/ +static inline bool cgroup_bpf_sock_enabled(struct sock *sk, + enum cgroup_bpf_attach_type type) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_prog_array *array; + + array = rcu_access_pointer(cgrp->bpf.effective[type]); + return array != &bpf_empty_prog_array.hdr; +} + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_INET_INGRESS)) \ + if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) && \ + cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(sk, skb, \ CGROUP_INET_INGRESS); \ \ @@ -235,7 +194,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, int __ret = 0; \ if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \ typeof(sk) __sk = sk_to_full_sk(sk); \ - if (sk_fullsock(__sk)) \ + if (sk_fullsock(__sk) && \ + cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS)) \ __ret = __cgroup_bpf_run_filter_skb(__sk, skb, \ CGROUP_INET_EGRESS); \ } \ @@ -401,7 +361,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, kernel_optval) \ ({ \ int __ret = 0; \ - if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_SETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_SETSOCKOPT)) \ __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ optname, optval, \ optlen, \ @@ -421,7 +382,8 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, max_optlen, retval) \ ({ \ int __ret = retval; \ - if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \ + if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT) && \ + cgroup_bpf_sock_enabled(sock, CGROUP_GETSOCKOPT)) \ if (!(sock)->sk_prot->bpf_bypass_getsockopt || \ !INDIRECT_CALL_INET_1((sock)->sk_prot->bpf_bypass_getsockopt, \ tcp_bpf_bypass_getsockopt, \ @@ -451,7 +413,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else -struct cgroup_bpf {}; static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 722f799c1a2e..413cfa5e4b07 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -3,15 +3,9 @@ #define _BPF_NETNS_H #include <linux/mutex.h> +#include <net/netns/bpf.h> #include <uapi/linux/bpf.h> -enum netns_bpf_attach_type { - NETNS_BPF_INVALID = -1, - NETNS_BPF_FLOW_DISSECTOR = 0, - NETNS_BPF_SK_LOOKUP, - MAX_NETNS_BPF_ATTACH_TYPE -}; - static inline enum netns_bpf_attach_type to_netns_bpf_attach_type(enum bpf_attach_type attach_type) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 755f38e893be..bdb5298735ce 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,6 +194,17 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -209,11 +220,9 @@ static inline bool map_value_has_timer(const struct bpf_map *map) static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) - *(struct bpf_timer *)(dst + map->timer_off) = - (struct bpf_timer){}; + memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); } /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ @@ -224,7 +233,8 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) if (unlikely(map_value_has_spin_lock(map))) { s_off = map->spin_lock_off; s_sz = sizeof(struct bpf_spin_lock); - } else if (unlikely(map_value_has_timer(map))) { + } + if (unlikely(map_value_has_timer(map))) { t_off = map->timer_off; t_sz = sizeof(struct bpf_timer); } @@ -297,6 +307,50 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, extern const struct bpf_map_ops bpf_map_offload_ops; +/* bpf_type_flag contains a set of flags that are applicable to the values of + * arg_type, ret_type and reg_type. For example, a pointer value may be null, + * or a memory is read-only. We classify types into two categories: base types + * and extended types. Extended types are base types combined with a type flag. + * + * Currently there are no more than 32 base types in arg_type, ret_type and + * reg_types. + */ +#define BPF_BASE_TYPE_BITS 8 + +enum bpf_type_flag { + /* PTR may be NULL. */ + PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), + + /* MEM is read-only. When applied on bpf_arg, it indicates the arg is + * compatible with both mutable and immutable memory. + */ + MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), + + /* MEM was "allocated" from a different helper, and cannot be mixed + * with regular non-MEM_ALLOC'ed MEM types. + */ + MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), + + /* MEM is in user address space. */ + MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), + + /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged + * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In + * order to drop this tag, it must be passed into bpf_per_cpu_ptr() + * or bpf_this_cpu_ptr(), which will return the pointer corresponding + * to the specified cpu. + */ + MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_PERCPU, +}; + +/* Max number of base types. */ +#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) + +/* Max number of all types. */ +#define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) + /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ @@ -308,13 +362,11 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */ ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, * helper function must fill all bytes or clear * them in error case. @@ -324,42 +376,65 @@ enum bpf_arg_type { ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ - ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ - ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ - ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ - ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ + ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, + + /* Extended arg_types. */ + ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, + ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, + ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, + ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, + ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, + ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ - RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ - RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ - RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ - RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ - RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ - RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ - RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ + RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ + RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ + RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ + RET_PTR_TO_ALLOC_MEM, /* returns a pointer to dynamically allocated memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ + __BPF_RET_TYPE_MAX, + + /* Extended ret_types. */ + RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, + RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, + RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, + RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, + RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL @@ -421,18 +496,15 @@ enum bpf_reg_type { PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ - PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ - PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ - PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need @@ -450,18 +522,24 @@ enum bpf_reg_type { * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ - PTR_TO_BTF_ID_OR_NULL, PTR_TO_MEM, /* reg points to valid memory region */ - PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ - PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ - PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ - PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ - PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ - PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ + PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ - PTR_TO_MAP_KEY, /* reg points to a map element key */ __BPF_REG_TYPE_MAX, + + /* Extended reg_types. */ + PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, + PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, + PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, + PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, + PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. @@ -519,8 +597,7 @@ struct bpf_verifier_ops { const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); + u32 *next_btf_id, enum bpf_type_flag *flag); }; struct bpf_prog_offload_ops { @@ -775,8 +852,9 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); -int bpf_jit_charge_modmem(u32 pages); -void bpf_jit_uncharge_modmem(u32 pages); +int bpf_jit_charge_modmem(u32 size); +void bpf_jit_uncharge_modmem(u32 size); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -805,6 +883,10 @@ static inline bool is_bpf_image_address(unsigned long address) { return false; } +static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + return false; +} #endif struct bpf_func_info_aux { @@ -876,6 +958,8 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; + bool use_bpf_prog_pack; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -936,16 +1020,6 @@ struct bpf_prog_aux { }; struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1082,7 +1156,7 @@ struct bpf_array { }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ -#define MAX_TAIL_CALL_CNT 32 +#define MAX_TAIL_CALL_CNT 33 #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ @@ -1120,7 +1194,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1162,6 +1243,19 @@ struct bpf_prog_array { struct bpf_prog_array_item items[]; }; +struct bpf_empty_prog_array { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +}; + +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'bpf_empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +extern struct bpf_empty_prog_array bpf_empty_prog_array; + struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); @@ -1188,6 +1282,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1220,19 +1315,19 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) + int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; u32 func_ret; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1241,27 +1336,29 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) + const void *ctx, bpf_prog_run_fn run_prog, + int retval) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1269,13 +1366,14 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - ret &= run_prog(prog, ctx); + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline u32 @@ -1328,19 +1426,21 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ + if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) @@ -1611,17 +1711,17 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ -struct xdp_buff; +struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(void); -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); @@ -1630,7 +1730,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, bool exclude_ingress); void __cpu_map_flush(void); -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); @@ -1661,7 +1761,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1691,7 +1790,7 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, - u32 *next_btf_id); + u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id); @@ -1722,6 +1821,19 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +struct bpf_core_ctx { + struct bpf_verifier_log *log; + const struct btf *btf; +}; + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn); + +static inline bool unprivileged_ebpf_enabled(void) +{ + return !sysctl_unprivileged_bpf_disabled; +} + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1791,35 +1903,30 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } -static inline bool dev_map_can_have_prog(struct bpf_map *map) -{ - return false; -} - static inline void __dev_flush(void) { } -struct xdp_buff; +struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; @@ -1847,7 +1954,7 @@ static inline void __cpu_map_flush(void) } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, - struct xdp_buff *xdp, + struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; @@ -1859,11 +1966,6 @@ static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, return -EOPNOTSUPP; } -static inline bool cpu_map_prog_allowed(struct bpf_map *map) -{ - return false; -} - static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { @@ -1905,12 +2007,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } @@ -1941,6 +2037,12 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, { return NULL; } + +static inline bool unprivileged_ebpf_enabled(void) +{ + return false; +} + #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -2005,6 +2107,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -2058,6 +2163,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ @@ -2153,6 +2264,10 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; +extern const struct bpf_func_proto bpf_find_vma_proto; +extern const struct bpf_func_proto bpf_loop_proto; +extern const struct bpf_func_proto bpf_strncmp_proto; +extern const struct bpf_func_proto bpf_copy_from_user_task_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2265,6 +2380,8 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void *bpf_arch_text_copy(void *dst, void *src, size_t len); + struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 24496bc28e7b..493e63258497 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -8,6 +8,7 @@ #define _BPF_LOCAL_STORAGE_H #include <linux/bpf.h> +#include <linux/filter.h> #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> @@ -16,6 +17,9 @@ #define BPF_LOCAL_STORAGE_CACHE_SIZE 16 +#define bpf_rcu_lock_held() \ + (rcu_read_lock_held() || rcu_read_lock_trace_held() || \ + rcu_read_lock_bh_held()) struct bpf_local_storage_map_bucket { struct hlist_head list; raw_spinlock_t lock; @@ -150,15 +154,18 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem); + bool charge_mem, gfp_t gfp_flags); int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem); + struct bpf_local_storage_elem *first_selem, + gfp_t gfp_flags); struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags); + void *value, u64 map_flags, gfp_t gfp_flags); + +void bpf_local_storage_free_rcu(struct rcu_head *rcu); #endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 48a91c51c015..3e24ad0c4b3c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -140,3 +140,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c8a78e830fca..c1fc4af47f69 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,6 +18,8 @@ * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) +/* size of type_str_buf in bpf_verifier. */ +#define TYPE_STR_BUF_LEN 64 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -388,6 +390,8 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ +#define BPF_LOG_MIN_ALIGNMENT 8U +#define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { @@ -396,6 +400,13 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) log->level == BPF_LOG_KERNEL); } +static inline bool +bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) +{ + return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && + log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); +} + #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { @@ -467,6 +478,16 @@ struct bpf_verifier_env { /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; bpfptr_t fd_array; + + /* bit mask to keep track of whether a register has been accessed + * since the last time the function state was printed + */ + u32 scratched_regs; + /* Same as scratched_regs but for stack slots */ + u64 scratched_stack_slots; + u32 prev_log_len, prev_insn_print_len; + /* buffer used in reg_type_str() to generate reg_type string */ + char type_str_buf[TYPE_STR_BUF_LEN]; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, @@ -498,8 +519,14 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno); +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno); +int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type, + bool is_release_func); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); @@ -529,5 +556,23 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); +#define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) + +/* extract base type from bpf_{arg, return, reg}_type. */ +static inline u32 base_type(u32 type) +{ + return type & BPF_BASE_TYPE_MASK; +} + +/* extract flags from an extended type. See bpf_type_flag in bpf.h. */ +static inline u32 type_flag(u32 type) +{ + return type & ~BPF_BASE_TYPE_MASK; +} + +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; +} #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 6b211323a489..9e97ced2896d 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -10,7 +10,6 @@ #define _BLK_BSG_ #include <linux/blkdev.h> -#include <scsi/scsi_request.h> struct bsg_job; struct request; diff --git a/include/linux/btf.h b/include/linux/btf.h index 0e1b6281fd8f..36bc09b8e890 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,33 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +enum btf_kfunc_type { + BTF_KFUNC_TYPE_CHECK, + BTF_KFUNC_TYPE_ACQUIRE, + BTF_KFUNC_TYPE_RELEASE, + BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_MAX, +}; + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + union { + struct { + struct btf_id_set *check_set; + struct btf_id_set *acquire_set; + struct btf_id_set *release_set; + struct btf_id_set *ret_null_set; + }; + struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; + }; +}; extern const struct file_operations btf_fops; @@ -144,6 +166,53 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +static inline u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(u32 *)(t + 1)); +} + +static inline u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(u32 *)(t + 1)); +} + static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); @@ -169,6 +238,11 @@ static inline bool btf_type_is_var(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_VAR; } +static inline bool btf_type_is_type_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG; +} + /* union is only a special case of struct: * all its offsetof(member) == 0 */ @@ -184,6 +258,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t) return BTF_INFO_VLEN(t->info); } +static inline u16 btf_vlen(const struct btf_type *t) +{ + return btf_type_vlen(t); +} + static inline u16 btf_func_linkage(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -194,31 +273,65 @@ static inline bool btf_type_kflag(const struct btf_type *t) return BTF_INFO_KFLAG(t->info); } -static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) : member->offset; } -static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) : 0; } +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bit_offset(t, m); +} + +static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bitfield_size(t, m); +} + static inline const struct btf_member *btf_type_member(const struct btf_type *t) { return (const struct btf_member *)(t + 1); } +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { return (const struct btf_var_secinfo *)(t + 1); } +static inline struct btf_param *btf_params(const struct btf_type *t) +{ + return (struct btf_param *)(t + 1); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; @@ -226,6 +339,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -237,50 +355,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } -#endif - -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static inline bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, + u32 kfunc_btf_id) { + return false; } -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) { - return false; + return 0; } - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } - #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 47d9abfbdb55..bc5d9cc34e4c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -11,6 +11,7 @@ struct btf_id_set { #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ +#include <linux/compiler_attributes.h> /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -73,7 +74,7 @@ asm( \ __BTF_ID_LIST(name, local) \ extern u32 name[]; -#define BTF_ID_LIST_GLOBAL(name) \ +#define BTF_ID_LIST_GLOBAL(name, n) \ __BTF_ID_LIST(name, globl) /* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with @@ -83,7 +84,7 @@ __BTF_ID_LIST(name, globl) BTF_ID_LIST(name) \ BTF_ID(prefix, typename) #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \ - BTF_ID_LIST_GLOBAL(name) \ + BTF_ID_LIST_GLOBAL(name, 1) \ BTF_ID(prefix, typename) /* @@ -146,14 +147,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ @@ -189,6 +190,18 @@ MAX_BTF_SOCK_TYPE, extern u32 btf_sock_ids[]; #endif -extern u32 btf_task_struct_ids[]; +#define BTF_TRACING_TYPE_xxx \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct) + +enum { +#define BTF_TRACING_TYPE(name, type) name, +BTF_TRACING_TYPE_xxx +#undef BTF_TRACING_TYPE +MAX_BTF_TRACING_TYPE, +}; + +extern u32 btf_tracing_ids[]; #endif diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 36f33685c8c0..bcb4fe9b8575 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -144,6 +144,7 @@ BUFFER_FNS(Defer_Completion, defer_completion) ((struct buffer_head *)page_private(page)); \ }) #define page_has_buffers(page) PagePrivate(page) +#define folio_buffers(folio) folio_get_private(folio) void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback); @@ -216,16 +217,14 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -void block_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); +void block_invalidate_folio(struct folio *folio, size_t offset, size_t length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler); int block_read_full_page(struct page*, get_block_t*); -int block_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count); +bool block_is_partially_uptodate(struct folio *, size_t from, size_t count); int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block); int __block_write_begin(struct page *page, loff_t pos, unsigned len, @@ -398,7 +397,7 @@ __bread(struct block_device *bdev, sector_t block, unsigned size) return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } -extern int __set_page_dirty_buffers(struct page *page); +bool block_dirty_folio(struct address_space *mapping, struct folio *folio); #else /* CONFIG_BLOCK */ diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 4b13e0a3e15b..c9a4c96c9943 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -190,7 +190,7 @@ static inline void be64_add_cpu(__be64 *var, u64 val) static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) { - int i; + size_t i; for (i = 0; i < len; i++) dst[i] = cpu_to_be32(src[i]); @@ -198,7 +198,7 @@ static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) { - int i; + size_t i; for (i = 0; i < len; i++) dst[i] = be32_to_cpu(src[i]); diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h index fef8b607f97e..a6189d21f2ba 100644 --- a/include/linux/cacheflush.h +++ b/include/linux/cacheflush.h @@ -4,6 +4,8 @@ #include <asm/cacheflush.h> +struct folio; + #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO void flush_dcache_folio(struct folio *folio); diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 20b50baf3a02..7ae21c0f7f23 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -12,13 +12,6 @@ #define CAN_SYNC_SEG 1 -/* Kilobits and Megabits per second */ -#define CAN_KBPS 1000UL -#define CAN_MBPS 1000000UL - -/* Megahertz */ -#define CAN_MHZ 1000000UL - #define CAN_CTRLMODE_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) @@ -120,7 +113,7 @@ struct can_tdc_const { }; #ifdef CONFIG_CAN_CALC_BITTIMING -int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, +int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc); void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, @@ -128,7 +121,7 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, u32 *ctrlmode, u32 ctrlmode_supported); #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int -can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, +can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc) { netdev_err(dev, "bit-timing calculation not available\n"); @@ -143,7 +136,7 @@ can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, } #endif /* CONFIG_CAN_CALC_BITTIMING */ -int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, +int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, const unsigned int bitrate_const_cnt); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 45f19d9db5ca..c2ea47f30046 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -64,12 +64,14 @@ struct can_priv { struct gpio_desc *termination_gpio; u16 termination_gpio_ohms[CAN_TERMINATION_GPIO_MAX]; + unsigned int echo_skb_max; + struct sk_buff **echo_skb; + enum can_state state; /* CAN controller features - see include/uapi/linux/can/netlink.h */ u32 ctrlmode; /* current options setting */ u32 ctrlmode_supported; /* options that can be modified by netlink */ - u32 ctrlmode_static; /* static enabled options for driver/hardware */ int restart_ms; struct delayed_work restart_work; @@ -84,9 +86,6 @@ struct can_priv { struct can_berr_counter *bec); int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); - unsigned int echo_skb_max; - struct sk_buff **echo_skb; - #ifdef CONFIG_CAN_LEDS struct led_trigger *tx_led_trig; char tx_led_trig_name[CAN_LED_NAME_SZ]; @@ -132,18 +131,29 @@ static inline s32 can_get_relative_tdco(const struct can_priv *priv) } /* helper to define static CAN controller features at device creation time */ -static inline void can_set_static_ctrlmode(struct net_device *dev, - u32 static_mode) +static inline int __must_check can_set_static_ctrlmode(struct net_device *dev, + u32 static_mode) { struct can_priv *priv = netdev_priv(dev); /* alloc_candev() succeeded => netdev_priv() is valid at this point */ + if (priv->ctrlmode_supported & static_mode) { + netdev_warn(dev, + "Controller features can not be supported and static at the same time\n"); + return -EINVAL; + } priv->ctrlmode = static_mode; - priv->ctrlmode_static = static_mode; /* override MTU which was set by default in can_setup()? */ if (static_mode & CAN_CTRLMODE_FD) dev->mtu = CANFD_MTU; + + return 0; +} + +static inline u32 can_get_static_ctrlmode(struct can_priv *priv) +{ + return priv->ctrlmode & ~priv->ctrlmode_supported; } void can_setup(struct net_device *dev); diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index d311bc369a39..fdb22b00674a 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -21,8 +21,9 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx, - unsigned int *frame_len_ptr); +unsigned int __must_check can_get_echo_skb(struct net_device *dev, + unsigned int idx, + unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index a075b70b9a70..efd8205282da 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -61,6 +61,17 @@ enum cc_attr { * Examples include SEV-ES. */ CC_ATTR_GUEST_STATE_ENCRYPT, + + /** + * @CC_ATTR_GUEST_UNROLL_STRING_IO: String I/O is implemented with + * IN/OUT instructions + * + * The platform/OS is running as a guest/virtual machine and uses + * IN/OUT instructions in place of string I/O. + * + * Examples include TDX guest & SEV. + */ + CC_ATTR_GUEST_UNROLL_STRING_IO, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 7ad6c3d0db7d..86bf82dbd8b8 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -28,8 +28,8 @@ #define CEPH_INO_ROOT 1 -#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ -#define CEPH_INO_DOTDOT 3 /* used by ceph fuse for parent (..) */ +#define CEPH_INO_CEPH 2 /* hidden .ceph dir */ +#define CEPH_INO_GLOBAL_SNAPREALM 3 /* global dummy snaprealm */ /* arbitrary limit on max # of monitors (cluster of 3 is typical) */ #define CEPH_MAX_MON 31 @@ -328,6 +328,7 @@ enum { CEPH_MDS_OP_LOOKUPPARENT = 0x00103, CEPH_MDS_OP_LOOKUPINO = 0x00104, CEPH_MDS_OP_LOOKUPNAME = 0x00105, + CEPH_MDS_OP_GETVXATTR = 0x00106, CEPH_MDS_OP_SETXATTR = 0x01105, CEPH_MDS_OP_RMXATTR = 0x01106, diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 409d8c29bc4f..00af2c98da75 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -35,6 +35,7 @@ #define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */ #define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */ #define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */ +#define CEPH_OPT_RXBOUNCE (1<<7) /* double-buffer read data */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) @@ -283,6 +284,7 @@ DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) extern struct kmem_cache *ceph_inode_cachep; extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_cap_snap_cachep; extern struct kmem_cache *ceph_cap_flush_cachep; extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; @@ -295,13 +297,13 @@ extern bool libceph_compatible(void *data); extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); -extern void *ceph_kvmalloc(size_t size, gfp_t flags); +extern int ceph_parse_fsid(const char *str, struct ceph_fsid *fsid); struct fs_parameter; struct fc_log; struct ceph_options *ceph_alloc_options(void); int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, - struct fc_log *l); + struct fc_log *l, char delim); int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, struct fc_log *l); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 0e6e9ad3c3bf..e7f2fb2fc207 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -383,6 +383,10 @@ struct ceph_connection_v2_info { struct ceph_gcm_nonce in_gcm_nonce; struct ceph_gcm_nonce out_gcm_nonce; + struct page **in_enc_pages; + int in_enc_page_cnt; + int in_enc_resid; + int in_enc_i; struct page **out_enc_pages; int out_enc_page_cnt; int out_enc_resid; @@ -457,6 +461,7 @@ struct ceph_connection { struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ + struct page *bounce_page; u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */ @@ -532,7 +537,7 @@ extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr); extern int ceph_parse_ips(const char *c, const char *end, struct ceph_entity_addr *addr, - int max_count, int *count); + int max_count, int *count, char delim); extern int ceph_msgr_init(void); extern void ceph_msgr_exit(void); diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 879744aaa6e0..c6dfc1ed0626 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -34,8 +34,17 @@ static inline void cfi_module_remove(struct module *mod, unsigned long base_addr #else /* !CONFIG_CFI_CLANG */ -#define __CFI_ADDRESSABLE(fn, __attr) +#ifdef CONFIG_X86_KERNEL_IBT + +#define __CFI_ADDRESSABLE(fn, __attr) \ + const void *__cfi_jt_ ## fn __visible __attr = (void *)&fn + +#endif /* CONFIG_X86_KERNEL_IBT */ #endif /* CONFIG_CFI_CLANG */ +#ifndef __CFI_ADDRESSABLE +#define __CFI_ADDRESSABLE(fn, __attr) +#endif + #endif /* _LINUX_CFI_H */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index db2e147e069f..1bfcfb1af352 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -19,7 +19,7 @@ #include <linux/percpu-rwsem.h> #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> -#include <linux/bpf-cgroup.h> +#include <linux/bpf-cgroup-defs.h> #include <linux/psi_types.h> #ifdef CONFIG_CGROUPS @@ -413,7 +413,7 @@ struct cgroup { /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_ss_mask is the effective + * "cgroup.subtree_control" while ->subtree_ss_mask is the effective * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 75c151413fda..0d1ada8968d7 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -450,6 +450,7 @@ extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ + rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) @@ -791,11 +792,9 @@ static inline void cgroup_account_cputime(struct task_struct *task, cpuacct_charge(task, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); - rcu_read_unlock(); } static inline void cgroup_account_cputime_field(struct task_struct *task, @@ -806,11 +805,9 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, cpuacct_account_field(task, index, delta_exec); - rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); - rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ diff --git a/include/linux/cgroup_api.h b/include/linux/cgroup_api.h new file mode 100644 index 000000000000..d0cfe8025111 --- /dev/null +++ b/include/linux/cgroup_api.h @@ -0,0 +1 @@ +#include <linux/cgroup.h> diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h deleted file mode 100644 index 5f5730c1d324..000000000000 --- a/include/linux/cleancache.h +++ /dev/null @@ -1,124 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_CLEANCACHE_H -#define _LINUX_CLEANCACHE_H - -#include <linux/fs.h> -#include <linux/exportfs.h> -#include <linux/mm.h> - -#define CLEANCACHE_NO_POOL -1 -#define CLEANCACHE_NO_BACKEND -2 -#define CLEANCACHE_NO_BACKEND_SHARED -3 - -#define CLEANCACHE_KEY_MAX 6 - -/* - * cleancache requires every file with a page in cleancache to have a - * unique key unless/until the file is removed/truncated. For some - * filesystems, the inode number is unique, but for "modern" filesystems - * an exportable filehandle is required (see exportfs.h) - */ -struct cleancache_filekey { - union { - ino_t ino; - __u32 fh[CLEANCACHE_KEY_MAX]; - u32 key[CLEANCACHE_KEY_MAX]; - } u; -}; - -struct cleancache_ops { - int (*init_fs)(size_t); - int (*init_shared_fs)(uuid_t *uuid, size_t); - int (*get_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*put_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); - void (*invalidate_inode)(int, struct cleancache_filekey); - void (*invalidate_fs)(int); -}; - -extern int cleancache_register_ops(const struct cleancache_ops *ops); -extern void __cleancache_init_fs(struct super_block *); -extern void __cleancache_init_shared_fs(struct super_block *); -extern int __cleancache_get_page(struct page *); -extern void __cleancache_put_page(struct page *); -extern void __cleancache_invalidate_page(struct address_space *, struct page *); -extern void __cleancache_invalidate_inode(struct address_space *); -extern void __cleancache_invalidate_fs(struct super_block *); - -#ifdef CONFIG_CLEANCACHE -#define cleancache_enabled (1) -static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) -{ - return mapping->host->i_sb->cleancache_poolid >= 0; -} -static inline bool cleancache_fs_enabled(struct page *page) -{ - return cleancache_fs_enabled_mapping(page->mapping); -} -#else -#define cleancache_enabled (0) -#define cleancache_fs_enabled(_page) (0) -#define cleancache_fs_enabled_mapping(_page) (0) -#endif - -/* - * The shim layer provided by these inline functions allows the compiler - * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE - * is disabled, to a single global variable check if CONFIG_CLEANCACHE - * is enabled but no cleancache "backend" has dynamically enabled it, - * and, for the most frequent cleancache ops, to a single global variable - * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled - * and a cleancache backend has dynamically enabled cleancache, but the - * filesystem referenced by that cleancache op has not enabled cleancache. - * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially - * no measurable performance impact. - */ - -static inline void cleancache_init_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_fs(sb); -} - -static inline void cleancache_init_shared_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_shared_fs(sb); -} - -static inline int cleancache_get_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - return __cleancache_get_page(page); - return -1; -} - -static inline void cleancache_put_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - __cleancache_put_page(page); -} - -static inline void cleancache_invalidate_page(struct address_space *mapping, - struct page *page) -{ - /* careful... page->mapping is NULL sometimes when this is called */ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_page(mapping, page); -} - -static inline void cleancache_invalidate_inode(struct address_space *mapping) -{ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_inode(mapping); -} - -static inline void cleancache_invalidate_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_invalidate_fs(sb); -} - -#endif /* _LINUX_CLEANCACHE_H */ diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index f59c875271a0..c10dc4c659e2 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -490,6 +490,13 @@ struct clk_hw *__clk_hw_register_gate(struct device *dev, unsigned long flags, void __iomem *reg, u8 bit_idx, u8 clk_gate_flags, spinlock_t *lock); +struct clk_hw *__devm_clk_hw_register_gate(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, + unsigned long flags, + void __iomem *reg, u8 bit_idx, + u8 clk_gate_flags, spinlock_t *lock); struct clk *clk_register_gate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 bit_idx, @@ -544,6 +551,22 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __clk_hw_register_gate((dev), NULL, (name), NULL, NULL, (parent_data), \ (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate - register a gate clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of this clock's parent + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate(dev, name, parent_name, flags, reg, bit_idx,\ + clk_gate_flags, lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); @@ -865,7 +888,7 @@ void clk_hw_unregister_divider(struct clk_hw *hw); struct clk_mux { struct clk_hw hw; void __iomem *reg; - u32 *table; + const u32 *table; u32 mask; u8 shift; u8 flags; @@ -890,18 +913,18 @@ struct clk_hw *__clk_hw_register_mux(struct device *dev, struct device_node *np, const struct clk_hw **parent_hws, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); struct clk_hw *__devm_clk_hw_register_mux(struct device *dev, struct device_node *np, const char *name, u8 num_parents, const char * const *parent_names, const struct clk_hw **parent_hws, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); struct clk *clk_register_mux_table(struct device *dev, const char *name, const char * const *parent_names, u8 num_parents, unsigned long flags, void __iomem *reg, u8 shift, u32 mask, - u8 clk_mux_flags, u32 *table, spinlock_t *lock); + u8 clk_mux_flags, const u32 *table, spinlock_t *lock); #define clk_register_mux(dev, name, parent_names, num_parents, flags, reg, \ shift, width, clk_mux_flags, lock) \ @@ -939,9 +962,9 @@ struct clk *clk_register_mux_table(struct device *dev, const char *name, (shift), BIT((width)) - 1, (clk_mux_flags), \ NULL, (lock)) -int clk_mux_val_to_index(struct clk_hw *hw, u32 *table, unsigned int flags, +int clk_mux_val_to_index(struct clk_hw *hw, const u32 *table, unsigned int flags, unsigned int val); -unsigned int clk_mux_index_to_val(u32 *table, unsigned int flags, u8 index); +unsigned int clk_mux_index_to_val(const u32 *table, unsigned int flags, u8 index); void clk_unregister_mux(struct clk *clk); void clk_hw_unregister_mux(struct clk_hw *hw); @@ -980,6 +1003,9 @@ void clk_hw_unregister_fixed_factor(struct clk_hw *hw); struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev, const char *name, const char *parent_name, unsigned long flags, unsigned int mult, unsigned int div); +struct clk_hw *devm_clk_hw_register_fixed_factor_index(struct device *dev, + const char *name, unsigned int index, unsigned long flags, + unsigned int mult, unsigned int div); /** * struct clk_fractional_divider - adjustable fractional divider clock * diff --git a/include/linux/clk.h b/include/linux/clk.h index 266e8de3cb51..39faa54efe88 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -987,6 +987,17 @@ static inline void clk_bulk_disable_unprepare(int num_clks, } /** + * clk_drop_range - Reset any range set on that clock + * @clk: clock source + * + * Returns success (0) or negative errno. + */ +static inline int clk_drop_range(struct clk *clk) +{ + return clk_set_rate_range(clk, 0, ULONG_MAX); +} + +/** * clk_get_optional - lookup and obtain a reference to an optional clock * producer. * @dev: device for clock "consumer" diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index ccb3f034bfa9..3484309b59bf 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -78,6 +78,10 @@ #define AT91_PMC_MAINRDY (1 << 16) /* Main Clock Ready */ #define AT91_CKGR_PLLAR 0x28 /* PLL A Register */ + +#define AT91_PMC_RATIO 0x2c /* Processor clock ratio register [SAMA7G5 only] */ +#define AT91_PMC_RATIO_RATIO (0xf) /* CPU clock ratio. */ + #define AT91_CKGR_PLLBR 0x2c /* PLL B Register */ #define AT91_PMC_DIV (0xff << 0) /* Divider */ #define AT91_PMC_PLLCOUNT (0x3f << 8) /* PLL Counter */ diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h index 3cd14acde0a1..cf32123b39f5 100644 --- a/include/linux/clk/sunxi-ng.h +++ b/include/linux/clk/sunxi-ng.h @@ -6,22 +6,7 @@ #ifndef _LINUX_CLK_SUNXI_NG_H_ #define _LINUX_CLK_SUNXI_NG_H_ -#include <linux/errno.h> - -#ifdef CONFIG_SUNXI_CCU int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); -#else -static inline int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, - bool new_mode) -{ - return -ENOTSUPP; -} - -static inline int sunxi_ccu_get_mmc_timing_mode(struct clk *clk) -{ - return -ENOTSUPP; -} -#endif #endif diff --git a/include/linux/cma.h b/include/linux/cma.h index bd801023504b..a6f637342740 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -12,14 +12,18 @@ */ #ifdef CONFIG_CMA_AREAS #define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) - -#else -#define MAX_CMA_AREAS (0) - #endif #define CMA_MAX_NAME 64 +/* + * TODO: once the buddy -- especially pageblock merging and alloc_contig_range() + * -- can deal with only some pageblocks of a higher-order page being + * MIGRATE_CMA, we can use pageblock_nr_pages. + */ +#define CMA_MIN_ALIGNMENT_PAGES MAX_ORDER_NR_PAGES +#define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) + struct cma; extern unsigned long totalcma_pages; @@ -50,4 +54,6 @@ extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); + +extern void cma_reserve_pages_on_error(struct cma *cma); #endif diff --git a/include/linux/comedi/comedi_8254.h b/include/linux/comedi/comedi_8254.h new file mode 100644 index 000000000000..d8264417e53c --- /dev/null +++ b/include/linux/comedi/comedi_8254.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_8254.h + * Generic 8254 timer/counter support + * Copyright (C) 2014 H Hartley Sweeten <hsweeten@visionengravers.com> + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_8254_H +#define _COMEDI_8254_H + +#include <linux/types.h> + +struct comedi_device; +struct comedi_insn; +struct comedi_subdevice; + +/* + * Common oscillator base values in nanoseconds + */ +#define I8254_OSC_BASE_10MHZ 100 +#define I8254_OSC_BASE_5MHZ 200 +#define I8254_OSC_BASE_4MHZ 250 +#define I8254_OSC_BASE_2MHZ 500 +#define I8254_OSC_BASE_1MHZ 1000 +#define I8254_OSC_BASE_100KHZ 10000 +#define I8254_OSC_BASE_10KHZ 100000 +#define I8254_OSC_BASE_1KHZ 1000000 + +/* + * I/O access size used to read/write registers + */ +#define I8254_IO8 1 +#define I8254_IO16 2 +#define I8254_IO32 4 + +/* + * Register map for generic 8254 timer (I8254_IO8 with 0 regshift) + */ +#define I8254_COUNTER0_REG 0x00 +#define I8254_COUNTER1_REG 0x01 +#define I8254_COUNTER2_REG 0x02 +#define I8254_CTRL_REG 0x03 +#define I8254_CTRL_SEL_CTR(x) ((x) << 6) +#define I8254_CTRL_READBACK(x) (I8254_CTRL_SEL_CTR(3) | BIT(x)) +#define I8254_CTRL_READBACK_COUNT I8254_CTRL_READBACK(4) +#define I8254_CTRL_READBACK_STATUS I8254_CTRL_READBACK(5) +#define I8254_CTRL_READBACK_SEL_CTR(x) (2 << (x)) +#define I8254_CTRL_RW(x) (((x) & 0x3) << 4) +#define I8254_CTRL_LATCH I8254_CTRL_RW(0) +#define I8254_CTRL_LSB_ONLY I8254_CTRL_RW(1) +#define I8254_CTRL_MSB_ONLY I8254_CTRL_RW(2) +#define I8254_CTRL_LSB_MSB I8254_CTRL_RW(3) + +/* counter maps zero to 0x10000 */ +#define I8254_MAX_COUNT 0x10000 + +/** + * struct comedi_8254 - private data used by this module + * @iobase: PIO base address of the registers (in/out) + * @mmio: MMIO base address of the registers (read/write) + * @iosize: I/O size used to access the registers (b/w/l) + * @regshift: register gap shift + * @osc_base: cascaded oscillator speed in ns + * @divisor: divisor for single counter + * @divisor1: divisor loaded into first cascaded counter + * @divisor2: divisor loaded into second cascaded counter + * #next_div: next divisor for single counter + * @next_div1: next divisor to use for first cascaded counter + * @next_div2: next divisor to use for second cascaded counter + * @clock_src; current clock source for each counter (driver specific) + * @gate_src; current gate source for each counter (driver specific) + * @busy: flags used to indicate that a counter is "busy" + * @insn_config: driver specific (*insn_config) callback + */ +struct comedi_8254 { + unsigned long iobase; + void __iomem *mmio; + unsigned int iosize; + unsigned int regshift; + unsigned int osc_base; + unsigned int divisor; + unsigned int divisor1; + unsigned int divisor2; + unsigned int next_div; + unsigned int next_div1; + unsigned int next_div2; + unsigned int clock_src[3]; + unsigned int gate_src[3]; + bool busy[3]; + + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); +}; + +unsigned int comedi_8254_status(struct comedi_8254 *i8254, + unsigned int counter); +unsigned int comedi_8254_read(struct comedi_8254 *i8254, unsigned int counter); +void comedi_8254_write(struct comedi_8254 *i8254, + unsigned int counter, unsigned int val); + +int comedi_8254_set_mode(struct comedi_8254 *i8254, + unsigned int counter, unsigned int mode); +int comedi_8254_load(struct comedi_8254 *i8254, + unsigned int counter, unsigned int val, unsigned int mode); + +void comedi_8254_pacer_enable(struct comedi_8254 *i8254, + unsigned int counter1, unsigned int counter2, + bool enable); +void comedi_8254_update_divisors(struct comedi_8254 *i8254); +void comedi_8254_cascade_ns_to_timer(struct comedi_8254 *i8254, + unsigned int *nanosec, unsigned int flags); +void comedi_8254_ns_to_timer(struct comedi_8254 *i8254, + unsigned int *nanosec, unsigned int flags); + +void comedi_8254_set_busy(struct comedi_8254 *i8254, + unsigned int counter, bool busy); + +void comedi_8254_subdevice_init(struct comedi_subdevice *s, + struct comedi_8254 *i8254); + +struct comedi_8254 *comedi_8254_init(unsigned long iobase, + unsigned int osc_base, + unsigned int iosize, + unsigned int regshift); +struct comedi_8254 *comedi_8254_mm_init(void __iomem *mmio, + unsigned int osc_base, + unsigned int iosize, + unsigned int regshift); + +#endif /* _COMEDI_8254_H */ diff --git a/include/linux/comedi/comedi_8255.h b/include/linux/comedi/comedi_8255.h new file mode 100644 index 000000000000..b2a5bc6b3a49 --- /dev/null +++ b/include/linux/comedi/comedi_8255.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_8255.h + * Generic 8255 digital I/O subdevice support + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_8255_H +#define _COMEDI_8255_H + +#define I8255_SIZE 0x04 + +#define I8255_DATA_A_REG 0x00 +#define I8255_DATA_B_REG 0x01 +#define I8255_DATA_C_REG 0x02 +#define I8255_CTRL_REG 0x03 +#define I8255_CTRL_C_LO_IO BIT(0) +#define I8255_CTRL_B_IO BIT(1) +#define I8255_CTRL_B_MODE BIT(2) +#define I8255_CTRL_C_HI_IO BIT(3) +#define I8255_CTRL_A_IO BIT(4) +#define I8255_CTRL_A_MODE(x) ((x) << 5) +#define I8255_CTRL_CW BIT(7) + +struct comedi_device; +struct comedi_subdevice; + +int subdev_8255_init(struct comedi_device *dev, struct comedi_subdevice *s, + int (*io)(struct comedi_device *dev, int dir, int port, + int data, unsigned long regbase), + unsigned long regbase); + +int subdev_8255_mm_init(struct comedi_device *dev, struct comedi_subdevice *s, + int (*io)(struct comedi_device *dev, int dir, int port, + int data, unsigned long regbase), + unsigned long regbase); + +unsigned long subdev_8255_regbase(struct comedi_subdevice *s); + +#endif diff --git a/include/linux/comedi/comedi_isadma.h b/include/linux/comedi/comedi_isadma.h new file mode 100644 index 000000000000..9d2b12db7e6e --- /dev/null +++ b/include/linux/comedi/comedi_isadma.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * COMEDI ISA DMA support functions + * Copyright (c) 2014 H Hartley Sweeten <hsweeten@visionengravers.com> + */ + +#ifndef _COMEDI_ISADMA_H +#define _COMEDI_ISADMA_H + +#include <linux/types.h> + +struct comedi_device; +struct device; + +/* + * These are used to avoid issues when <asm/dma.h> and the DMA_MODE_ + * defines are not available. + */ +#define COMEDI_ISADMA_READ 0 +#define COMEDI_ISADMA_WRITE 1 + +/** + * struct comedi_isadma_desc - cookie for ISA DMA + * @virt_addr: virtual address of buffer + * @hw_addr: hardware (bus) address of buffer + * @chan: DMA channel + * @maxsize: allocated size of buffer (in bytes) + * @size: transfer size (in bytes) + * @mode: DMA_MODE_READ or DMA_MODE_WRITE + */ +struct comedi_isadma_desc { + void *virt_addr; + dma_addr_t hw_addr; + unsigned int chan; + unsigned int maxsize; + unsigned int size; + char mode; +}; + +/** + * struct comedi_isadma - ISA DMA data + * @dev: device to allocate non-coherent memory for + * @desc: cookie for each DMA buffer + * @n_desc: the number of cookies + * @cur_dma: the current cookie in use + * @chan: the first DMA channel requested + * @chan2: the second DMA channel requested + */ +struct comedi_isadma { + struct device *dev; + struct comedi_isadma_desc *desc; + int n_desc; + int cur_dma; + unsigned int chan; + unsigned int chan2; +}; + +#if IS_ENABLED(CONFIG_ISA_DMA_API) + +void comedi_isadma_program(struct comedi_isadma_desc *desc); +unsigned int comedi_isadma_disable(unsigned int dma_chan); +unsigned int comedi_isadma_disable_on_sample(unsigned int dma_chan, + unsigned int size); +unsigned int comedi_isadma_poll(struct comedi_isadma *dma); +void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, char dma_dir); + +struct comedi_isadma *comedi_isadma_alloc(struct comedi_device *dev, + int n_desc, unsigned int dma_chan1, + unsigned int dma_chan2, + unsigned int maxsize, char dma_dir); +void comedi_isadma_free(struct comedi_isadma *dma); + +#else /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ + +static inline void comedi_isadma_program(struct comedi_isadma_desc *desc) +{ +} + +static inline unsigned int comedi_isadma_disable(unsigned int dma_chan) +{ + return 0; +} + +static inline unsigned int +comedi_isadma_disable_on_sample(unsigned int dma_chan, unsigned int size) +{ + return 0; +} + +static inline unsigned int comedi_isadma_poll(struct comedi_isadma *dma) +{ + return 0; +} + +static inline void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, + char dma_dir) +{ +} + +static inline struct comedi_isadma * +comedi_isadma_alloc(struct comedi_device *dev, int n_desc, + unsigned int dma_chan1, unsigned int dma_chan2, + unsigned int maxsize, char dma_dir) +{ + return NULL; +} + +static inline void comedi_isadma_free(struct comedi_isadma *dma) +{ +} + +#endif /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ + +#endif /* #ifndef _COMEDI_ISADMA_H */ diff --git a/include/linux/comedi/comedi_pci.h b/include/linux/comedi/comedi_pci.h new file mode 100644 index 000000000000..2fb50663e3ed --- /dev/null +++ b/include/linux/comedi/comedi_pci.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pci.h + * header file for Comedi PCI drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_PCI_H +#define _COMEDI_PCI_H + +#include <linux/pci.h> +#include <linux/comedi/comedidev.h> + +/* + * PCI Vendor IDs not in <linux/pci_ids.h> + */ +#define PCI_VENDOR_ID_KOLTER 0x1001 +#define PCI_VENDOR_ID_ICP 0x104c +#define PCI_VENDOR_ID_DT 0x1116 +#define PCI_VENDOR_ID_IOTECH 0x1616 +#define PCI_VENDOR_ID_CONTEC 0x1221 +#define PCI_VENDOR_ID_RTD 0x1435 +#define PCI_VENDOR_ID_HUMUSOFT 0x186c + +struct pci_dev *comedi_to_pci_dev(struct comedi_device *dev); + +int comedi_pci_enable(struct comedi_device *dev); +void comedi_pci_disable(struct comedi_device *dev); +void comedi_pci_detach(struct comedi_device *dev); + +int comedi_pci_auto_config(struct pci_dev *pcidev, struct comedi_driver *driver, + unsigned long context); +void comedi_pci_auto_unconfig(struct pci_dev *pcidev); + +int comedi_pci_driver_register(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); +void comedi_pci_driver_unregister(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); + +/** + * module_comedi_pci_driver() - Helper macro for registering a comedi PCI driver + * @__comedi_driver: comedi_driver struct + * @__pci_driver: pci_driver struct + * + * Helper macro for comedi PCI drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pci_driver(__comedi_driver, __pci_driver) \ + module_driver(__comedi_driver, comedi_pci_driver_register, \ + comedi_pci_driver_unregister, &(__pci_driver)) + +#endif /* _COMEDI_PCI_H */ diff --git a/include/linux/comedi/comedi_pcmcia.h b/include/linux/comedi/comedi_pcmcia.h new file mode 100644 index 000000000000..a33dfb65b869 --- /dev/null +++ b/include/linux/comedi/comedi_pcmcia.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pcmcia.h + * header file for Comedi PCMCIA drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_PCMCIA_H +#define _COMEDI_PCMCIA_H + +#include <pcmcia/cistpl.h> +#include <pcmcia/ds.h> +#include <linux/comedi/comedidev.h> + +struct pcmcia_device *comedi_to_pcmcia_dev(struct comedi_device *dev); + +int comedi_pcmcia_enable(struct comedi_device *dev, + int (*conf_check)(struct pcmcia_device *p_dev, + void *priv_data)); +void comedi_pcmcia_disable(struct comedi_device *dev); + +int comedi_pcmcia_auto_config(struct pcmcia_device *link, + struct comedi_driver *driver); +void comedi_pcmcia_auto_unconfig(struct pcmcia_device *link); + +int comedi_pcmcia_driver_register(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); +void comedi_pcmcia_driver_unregister(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); + +/** + * module_comedi_pcmcia_driver() - Helper macro for registering a comedi + * PCMCIA driver + * @__comedi_driver: comedi_driver struct + * @__pcmcia_driver: pcmcia_driver struct + * + * Helper macro for comedi PCMCIA drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pcmcia_driver(__comedi_driver, __pcmcia_driver) \ + module_driver(__comedi_driver, comedi_pcmcia_driver_register, \ + comedi_pcmcia_driver_unregister, &(__pcmcia_driver)) + +#endif /* _COMEDI_PCMCIA_H */ diff --git a/include/linux/comedi/comedi_usb.h b/include/linux/comedi/comedi_usb.h new file mode 100644 index 000000000000..5d17dd425bd2 --- /dev/null +++ b/include/linux/comedi/comedi_usb.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* comedi_usb.h + * header file for USB Comedi drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDI_USB_H +#define _COMEDI_USB_H + +#include <linux/usb.h> +#include <linux/comedi/comedidev.h> + +struct usb_interface *comedi_to_usb_interface(struct comedi_device *dev); +struct usb_device *comedi_to_usb_dev(struct comedi_device *dev); + +int comedi_usb_auto_config(struct usb_interface *intf, + struct comedi_driver *driver, unsigned long context); +void comedi_usb_auto_unconfig(struct usb_interface *intf); + +int comedi_usb_driver_register(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); +void comedi_usb_driver_unregister(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); + +/** + * module_comedi_usb_driver() - Helper macro for registering a comedi USB driver + * @__comedi_driver: comedi_driver struct + * @__usb_driver: usb_driver struct + * + * Helper macro for comedi USB drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_usb_driver(__comedi_driver, __usb_driver) \ + module_driver(__comedi_driver, comedi_usb_driver_register, \ + comedi_usb_driver_unregister, &(__usb_driver)) + +#endif /* _COMEDI_USB_H */ diff --git a/include/linux/comedi/comedidev.h b/include/linux/comedi/comedidev.h new file mode 100644 index 000000000000..0a1150900ef3 --- /dev/null +++ b/include/linux/comedi/comedidev.h @@ -0,0 +1,1053 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedidev.h + * header file for kernel-only structures, variables, and constants + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef <ds@schleef.org> + */ + +#ifndef _COMEDIDEV_H +#define _COMEDIDEV_H + +#include <linux/dma-mapping.h> +#include <linux/mutex.h> +#include <linux/spinlock_types.h> +#include <linux/rwsem.h> +#include <linux/kref.h> +#include <linux/comedi.h> + +#define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) +#define COMEDI_VERSION_CODE COMEDI_VERSION(COMEDI_MAJORVERSION, \ + COMEDI_MINORVERSION, COMEDI_MICROVERSION) +#define COMEDI_RELEASE VERSION + +#define COMEDI_NUM_BOARD_MINORS 0x30 + +/** + * struct comedi_subdevice - Working data for a COMEDI subdevice + * @device: COMEDI device to which this subdevice belongs. (Initialized by + * comedi_alloc_subdevices().) + * @index: Index of this subdevice within device's array of subdevices. + * (Initialized by comedi_alloc_subdevices().) + * @type: Type of subdevice from &enum comedi_subdevice_type. (Initialized by + * the low-level driver.) + * @n_chan: Number of channels the subdevice supports. (Initialized by the + * low-level driver.) + * @subdev_flags: Various "SDF" flags indicating aspects of the subdevice to + * the COMEDI core and user application. (Initialized by the low-level + * driver.) + * @len_chanlist: Maximum length of a channel list if the subdevice supports + * asynchronous acquisition commands. (Optionally initialized by the + * low-level driver, or changed from 0 to 1 during post-configuration.) + * @private: Private data pointer which is either set by the low-level driver + * itself, or by a call to comedi_alloc_spriv() which allocates storage. + * In the latter case, the storage is automatically freed after the + * low-level driver's "detach" handler is called for the device. + * (Initialized by the low-level driver.) + * @async: Pointer to &struct comedi_async id the subdevice supports + * asynchronous acquisition commands. (Allocated and initialized during + * post-configuration if needed.) + * @lock: Pointer to a file object that performed a %COMEDI_LOCK ioctl on the + * subdevice. (Initially NULL.) + * @busy: Pointer to a file object that is performing an asynchronous + * acquisition command on the subdevice. (Initially NULL.) + * @runflags: Internal flags for use by COMEDI core, mostly indicating whether + * an asynchronous acquisition command is running. + * @spin_lock: Generic spin-lock for use by the COMEDI core and the low-level + * driver. (Initialized by comedi_alloc_subdevices().) + * @io_bits: Bit-mask indicating the channel directions for a DIO subdevice + * with no more than 32 channels. A '1' at a bit position indicates the + * corresponding channel is configured as an output. (Initialized by the + * low-level driver for a DIO subdevice. Forced to all-outputs during + * post-configuration for a digital output subdevice.) + * @maxdata: If non-zero, this is the maximum raw data value of each channel. + * If zero, the maximum data value is channel-specific. (Initialized by + * the low-level driver.) + * @maxdata_list: If the maximum data value is channel-specific, this points + * to an array of maximum data values indexed by channel index. + * (Initialized by the low-level driver.) + * @range_table: If non-NULL, this points to a COMEDI range table for the + * subdevice. If NULL, the range table is channel-specific. (Initialized + * by the low-level driver, will be set to an "invalid" range table during + * post-configuration if @range_table and @range_table_list are both + * NULL.) + * @range_table_list: If the COMEDI range table is channel-specific, this + * points to an array of pointers to COMEDI range tables indexed by + * channel number. (Initialized by the low-level driver.) + * @chanlist: Not used. + * @insn_read: Optional pointer to a handler for the %INSN_READ instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_write: Optional pointer to a handler for the %INSN_WRITE instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_bits: Optional pointer to a handler for the %INSN_BITS instruction + * for a digital input, digital output or digital input/output subdevice. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_config: Optional pointer to a handler for the %INSN_CONFIG + * instruction. (Initialized by the low-level driver, or set to a default + * handler during post-configuration.) + * @do_cmd: If the subdevice supports asynchronous acquisition commands, this + * points to a handler to set it up in hardware. (Initialized by the + * low-level driver.) + * @do_cmdtest: If the subdevice supports asynchronous acquisition commands, + * this points to a handler used to check and possibly tweak a prospective + * acquisition command without setting it up in hardware. (Initialized by + * the low-level driver.) + * @poll: If the subdevice supports asynchronous acquisition commands, this + * is an optional pointer to a handler for the %COMEDI_POLL ioctl which + * instructs the low-level driver to synchronize buffers. (Initialized by + * the low-level driver if needed.) + * @cancel: If the subdevice supports asynchronous acquisition commands, this + * points to a handler used to terminate a running command. (Initialized + * by the low-level driver.) + * @buf_change: If the subdevice supports asynchronous acquisition commands, + * this is an optional pointer to a handler that is called when the data + * buffer for handling asynchronous commands is allocated or reallocated. + * (Initialized by the low-level driver if needed.) + * @munge: If the subdevice supports asynchronous acquisition commands and + * uses DMA to transfer data from the hardware to the acquisition buffer, + * this points to a function used to "munge" the data values from the + * hardware into the format expected by COMEDI. (Initialized by the + * low-level driver if needed.) + * @async_dma_dir: If the subdevice supports asynchronous acquisition commands + * and uses DMA to transfer data from the hardware to the acquisition + * buffer, this sets the DMA direction for the buffer. (initialized to + * %DMA_NONE by comedi_alloc_subdevices() and changed by the low-level + * driver if necessary.) + * @state: Handy bit-mask indicating the output states for a DIO or digital + * output subdevice with no more than 32 channels. (Initialized by the + * low-level driver.) + * @class_dev: If the subdevice supports asynchronous acquisition commands, + * this points to a sysfs comediX_subdY device where X is the minor device + * number of the COMEDI device and Y is the subdevice number. The minor + * device number for the sysfs device is allocated dynamically in the + * range 48 to 255. This is used to allow the COMEDI device to be opened + * with a different default read or write subdevice. (Allocated during + * post-configuration if needed.) + * @minor: If @class_dev is set, this is its dynamically allocated minor + * device number. (Set during post-configuration if necessary.) + * @readback: Optional pointer to memory allocated by + * comedi_alloc_subdev_readback() used to hold the values written to + * analog output channels so they can be read back. The storage is + * automatically freed after the low-level driver's "detach" handler is + * called for the device. (Initialized by the low-level driver.) + * + * This is the main control structure for a COMEDI subdevice. If the subdevice + * supports asynchronous acquisition commands, additional information is stored + * in the &struct comedi_async pointed to by @async. + * + * Most of the subdevice is initialized by the low-level driver's "attach" or + * "auto_attach" handlers but parts of it are initialized by + * comedi_alloc_subdevices(), and other parts are initialized during + * post-configuration on return from that handler. + * + * A low-level driver that sets @insn_bits for a digital input, digital output, + * or DIO subdevice may leave @insn_read and @insn_write uninitialized, in + * which case they will be set to a default handler during post-configuration + * that uses @insn_bits to emulate the %INSN_READ and %INSN_WRITE instructions. + */ +struct comedi_subdevice { + struct comedi_device *device; + int index; + int type; + int n_chan; + int subdev_flags; + int len_chanlist; /* maximum length of channel/gain list */ + + void *private; + + struct comedi_async *async; + + void *lock; + void *busy; + unsigned int runflags; + spinlock_t spin_lock; /* generic spin-lock for COMEDI and drivers */ + + unsigned int io_bits; + + unsigned int maxdata; /* if maxdata==0, use list */ + const unsigned int *maxdata_list; /* list is channel specific */ + + const struct comedi_lrange *range_table; + const struct comedi_lrange *const *range_table_list; + + unsigned int *chanlist; /* driver-owned chanlist (not used) */ + + int (*insn_read)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_write)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_bits)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, + unsigned int *data); + + int (*do_cmd)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*do_cmdtest)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_cmd *cmd); + int (*poll)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*cancel)(struct comedi_device *dev, struct comedi_subdevice *s); + + /* called when the buffer changes */ + int (*buf_change)(struct comedi_device *dev, + struct comedi_subdevice *s); + + void (*munge)(struct comedi_device *dev, struct comedi_subdevice *s, + void *data, unsigned int num_bytes, + unsigned int start_chan_index); + enum dma_data_direction async_dma_dir; + + unsigned int state; + + struct device *class_dev; + int minor; + + unsigned int *readback; +}; + +/** + * struct comedi_buf_page - Describe a page of a COMEDI buffer + * @virt_addr: Kernel address of page. + * @dma_addr: DMA address of page if in DMA coherent memory. + */ +struct comedi_buf_page { + void *virt_addr; + dma_addr_t dma_addr; +}; + +/** + * struct comedi_buf_map - Describe pages in a COMEDI buffer + * @dma_hw_dev: Low-level hardware &struct device pointer copied from the + * COMEDI device's hw_dev member. + * @page_list: Pointer to array of &struct comedi_buf_page, one for each + * page in the buffer. + * @n_pages: Number of pages in the buffer. + * @dma_dir: DMA direction used to allocate pages of DMA coherent memory, + * or %DMA_NONE if pages allocated from regular memory. + * @refcount: &struct kref reference counter used to free the buffer. + * + * A COMEDI data buffer is allocated as individual pages, either in + * conventional memory or DMA coherent memory, depending on the attached, + * low-level hardware device. (The buffer pages also get mapped into the + * kernel's contiguous virtual address space pointed to by the 'prealloc_buf' + * member of &struct comedi_async.) + * + * The buffer is normally freed when the COMEDI device is detached from the + * low-level driver (which may happen due to device removal), but if it happens + * to be mmapped at the time, the pages cannot be freed until the buffer has + * been munmapped. That is what the reference counter is for. (The virtual + * address space pointed by 'prealloc_buf' is freed when the COMEDI device is + * detached.) + */ +struct comedi_buf_map { + struct device *dma_hw_dev; + struct comedi_buf_page *page_list; + unsigned int n_pages; + enum dma_data_direction dma_dir; + struct kref refcount; +}; + +/** + * struct comedi_async - Control data for asynchronous COMEDI commands + * @prealloc_buf: Kernel virtual address of allocated acquisition buffer. + * @prealloc_bufsz: Buffer size (in bytes). + * @buf_map: Map of buffer pages. + * @max_bufsize: Maximum allowed buffer size (in bytes). + * @buf_write_count: "Write completed" count (in bytes, modulo 2**32). + * @buf_write_alloc_count: "Allocated for writing" count (in bytes, + * modulo 2**32). + * @buf_read_count: "Read completed" count (in bytes, modulo 2**32). + * @buf_read_alloc_count: "Allocated for reading" count (in bytes, + * modulo 2**32). + * @buf_write_ptr: Buffer position for writer. + * @buf_read_ptr: Buffer position for reader. + * @cur_chan: Current position in chanlist for scan (for those drivers that + * use it). + * @scans_done: The number of scans completed. + * @scan_progress: Amount received or sent for current scan (in bytes). + * @munge_chan: Current position in chanlist for "munging". + * @munge_count: "Munge" count (in bytes, modulo 2**32). + * @munge_ptr: Buffer position for "munging". + * @events: Bit-vector of events that have occurred. + * @cmd: Details of comedi command in progress. + * @wait_head: Task wait queue for file reader or writer. + * @cb_mask: Bit-vector of events that should wake waiting tasks. + * @inttrig: Software trigger function for command, or NULL. + * + * Note about the ..._count and ..._ptr members: + * + * Think of the _Count values being integers of unlimited size, indexing + * into a buffer of infinite length (though only an advancing portion + * of the buffer of fixed length prealloc_bufsz is accessible at any + * time). Then: + * + * Buf_Read_Count <= Buf_Read_Alloc_Count <= Munge_Count <= + * Buf_Write_Count <= Buf_Write_Alloc_Count <= + * (Buf_Read_Count + prealloc_bufsz) + * + * (Those aren't the actual members, apart from prealloc_bufsz.) When the + * buffer is reset, those _Count values start at 0 and only increase in value, + * maintaining the above inequalities until the next time the buffer is + * reset. The buffer is divided into the following regions by the inequalities: + * + * [0, Buf_Read_Count): + * old region no longer accessible + * + * [Buf_Read_Count, Buf_Read_Alloc_Count): + * filled and munged region allocated for reading but not yet read + * + * [Buf_Read_Alloc_Count, Munge_Count): + * filled and munged region not yet allocated for reading + * + * [Munge_Count, Buf_Write_Count): + * filled region not yet munged + * + * [Buf_Write_Count, Buf_Write_Alloc_Count): + * unfilled region allocated for writing but not yet written + * + * [Buf_Write_Alloc_Count, Buf_Read_Count + prealloc_bufsz): + * unfilled region not yet allocated for writing + * + * [Buf_Read_Count + prealloc_bufsz, infinity): + * unfilled region not yet accessible + * + * Data needs to be written into the buffer before it can be read out, + * and may need to be converted (or "munged") between the two + * operations. Extra unfilled buffer space may need to allocated for + * writing (advancing Buf_Write_Alloc_Count) before new data is written. + * After writing new data, the newly filled space needs to be released + * (advancing Buf_Write_Count). This also results in the new data being + * "munged" (advancing Munge_Count). Before data is read out of the + * buffer, extra space may need to be allocated for reading (advancing + * Buf_Read_Alloc_Count). After the data has been read out, the space + * needs to be released (advancing Buf_Read_Count). + * + * The actual members, buf_read_count, buf_read_alloc_count, + * munge_count, buf_write_count, and buf_write_alloc_count take the + * value of the corresponding capitalized _Count values modulo 2^32 + * (UINT_MAX+1). Subtracting a "higher" _count value from a "lower" + * _count value gives the same answer as subtracting a "higher" _Count + * value from a lower _Count value because prealloc_bufsz < UINT_MAX+1. + * The modulo operation is done implicitly. + * + * The buf_read_ptr, munge_ptr, and buf_write_ptr members take the value + * of the corresponding capitalized _Count values modulo prealloc_bufsz. + * These correspond to byte indices in the physical buffer. The modulo + * operation is done by subtracting prealloc_bufsz when the value + * exceeds prealloc_bufsz (assuming prealloc_bufsz plus the increment is + * less than or equal to UINT_MAX). + */ +struct comedi_async { + void *prealloc_buf; + unsigned int prealloc_bufsz; + struct comedi_buf_map *buf_map; + unsigned int max_bufsize; + unsigned int buf_write_count; + unsigned int buf_write_alloc_count; + unsigned int buf_read_count; + unsigned int buf_read_alloc_count; + unsigned int buf_write_ptr; + unsigned int buf_read_ptr; + unsigned int cur_chan; + unsigned int scans_done; + unsigned int scan_progress; + unsigned int munge_chan; + unsigned int munge_count; + unsigned int munge_ptr; + unsigned int events; + struct comedi_cmd cmd; + wait_queue_head_t wait_head; + unsigned int cb_mask; + int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s, + unsigned int x); +}; + +/** + * enum comedi_cb - &struct comedi_async callback "events" + * @COMEDI_CB_EOS: end-of-scan + * @COMEDI_CB_EOA: end-of-acquisition/output + * @COMEDI_CB_BLOCK: data has arrived, wakes up read() / write() + * @COMEDI_CB_EOBUF: DEPRECATED: end of buffer + * @COMEDI_CB_ERROR: card error during acquisition + * @COMEDI_CB_OVERFLOW: buffer overflow/underflow + * @COMEDI_CB_ERROR_MASK: events that indicate an error has occurred + * @COMEDI_CB_CANCEL_MASK: events that will cancel an async command + */ +enum comedi_cb { + COMEDI_CB_EOS = BIT(0), + COMEDI_CB_EOA = BIT(1), + COMEDI_CB_BLOCK = BIT(2), + COMEDI_CB_EOBUF = BIT(3), + COMEDI_CB_ERROR = BIT(4), + COMEDI_CB_OVERFLOW = BIT(5), + /* masks */ + COMEDI_CB_ERROR_MASK = (COMEDI_CB_ERROR | COMEDI_CB_OVERFLOW), + COMEDI_CB_CANCEL_MASK = (COMEDI_CB_EOA | COMEDI_CB_ERROR_MASK) +}; + +/** + * struct comedi_driver - COMEDI driver registration + * @driver_name: Name of driver. + * @module: Owning module. + * @attach: The optional "attach" handler for manually configured COMEDI + * devices. + * @detach: The "detach" handler for deconfiguring COMEDI devices. + * @auto_attach: The optional "auto_attach" handler for automatically + * configured COMEDI devices. + * @num_names: Optional number of "board names" supported. + * @board_name: Optional pointer to a pointer to a board name. The pointer + * to a board name is embedded in an element of a driver-defined array + * of static, read-only board type information. + * @offset: Optional size of each element of the driver-defined array of + * static, read-only board type information, i.e. the offset between each + * pointer to a board name. + * + * This is used with comedi_driver_register() and comedi_driver_unregister() to + * register and unregister a low-level COMEDI driver with the COMEDI core. + * + * If @num_names is non-zero, @board_name should be non-NULL, and @offset + * should be at least sizeof(*board_name). These are used by the handler for + * the %COMEDI_DEVCONFIG ioctl to match a hardware device and its driver by + * board name. If @num_names is zero, the %COMEDI_DEVCONFIG ioctl matches a + * hardware device and its driver by driver name. This is only useful if the + * @attach handler is set. If @num_names is non-zero, the driver's @attach + * handler will be called with the COMEDI device structure's board_ptr member + * pointing to the matched pointer to a board name within the driver's private + * array of static, read-only board type information. + * + * The @detach handler has two roles. If a COMEDI device was successfully + * configured by the @attach or @auto_attach handler, it is called when the + * device is being deconfigured (by the %COMEDI_DEVCONFIG ioctl, or due to + * unloading of the driver, or due to device removal). It is also called when + * the @attach or @auto_attach handler returns an error. Therefore, the + * @attach or @auto_attach handlers can defer clean-up on error until the + * @detach handler is called. If the @attach or @auto_attach handlers free + * any resources themselves, they must prevent the @detach handler from + * freeing the same resources. The @detach handler must not assume that all + * resources requested by the @attach or @auto_attach handler were + * successfully allocated. + */ +struct comedi_driver { + /* private: */ + struct comedi_driver *next; /* Next in list of COMEDI drivers. */ + /* public: */ + const char *driver_name; + struct module *module; + int (*attach)(struct comedi_device *dev, struct comedi_devconfig *it); + void (*detach)(struct comedi_device *dev); + int (*auto_attach)(struct comedi_device *dev, unsigned long context); + unsigned int num_names; + const char *const *board_name; + int offset; +}; + +/** + * struct comedi_device - Working data for a COMEDI device + * @use_count: Number of open file objects. + * @driver: Low-level COMEDI driver attached to this COMEDI device. + * @pacer: Optional pointer to a dynamically allocated acquisition pacer + * control. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @private: Optional pointer to private data allocated by the low-level + * driver. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @class_dev: Sysfs comediX device. + * @minor: Minor device number of COMEDI char device (0-47). + * @detach_count: Counter incremented every time the COMEDI device is detached. + * Used for checking a previous attachment is still valid. + * @hw_dev: Optional pointer to the low-level hardware &struct device. It is + * required for automatically configured COMEDI devices and optional for + * COMEDI devices configured by the %COMEDI_DEVCONFIG ioctl, although + * the bus-specific COMEDI functions only work if it is set correctly. + * It is also passed to dma_alloc_coherent() for COMEDI subdevices that + * have their 'async_dma_dir' member set to something other than + * %DMA_NONE. + * @board_name: Pointer to a COMEDI board name or a COMEDI driver name. When + * the low-level driver's "attach" handler is called by the handler for + * the %COMEDI_DEVCONFIG ioctl, it either points to a matched board name + * string if the 'num_names' member of the &struct comedi_driver is + * non-zero, otherwise it points to the low-level driver name string. + * When the low-lever driver's "auto_attach" handler is called for an + * automatically configured COMEDI device, it points to the low-level + * driver name string. The low-level driver is free to change it in its + * "attach" or "auto_attach" handler if it wishes. + * @board_ptr: Optional pointer to private, read-only board type information in + * the low-level driver. If the 'num_names' member of the &struct + * comedi_driver is non-zero, the handler for the %COMEDI_DEVCONFIG ioctl + * will point it to a pointer to a matched board name string within the + * driver's private array of static, read-only board type information when + * calling the driver's "attach" handler. The low-level driver is free to + * change it. + * @attached: Flag indicating that the COMEDI device is attached to a low-level + * driver. + * @ioenabled: Flag used to indicate that a PCI device has been enabled and + * its regions requested. + * @spinlock: Generic spin-lock for use by the low-level driver. + * @mutex: Generic mutex for use by the COMEDI core module. + * @attach_lock: &struct rw_semaphore used to guard against the COMEDI device + * being detached while an operation is in progress. The down_write() + * operation is only allowed while @mutex is held and is used when + * changing @attached and @detach_count and calling the low-level driver's + * "detach" handler. The down_read() operation is generally used without + * holding @mutex. + * @refcount: &struct kref reference counter for freeing COMEDI device. + * @n_subdevices: Number of COMEDI subdevices allocated by the low-level + * driver for this device. + * @subdevices: Dynamically allocated array of COMEDI subdevices. + * @mmio: Optional pointer to a remapped MMIO region set by the low-level + * driver. + * @iobase: Optional base of an I/O port region requested by the low-level + * driver. + * @iolen: Length of I/O port region requested at @iobase. + * @irq: Optional IRQ number requested by the low-level driver. + * @read_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the read() file operation. Set by the low-level driver. + * @write_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the write() file operation. Set by the low-level driver. + * @async_queue: Storage for fasync_helper(). + * @open: Optional pointer to a function set by the low-level driver to be + * called when @use_count changes from 0 to 1. + * @close: Optional pointer to a function set by the low-level driver to be + * called when @use_count changed from 1 to 0. + * @insn_device_config: Optional pointer to a handler for all sub-instructions + * except %INSN_DEVICE_CONFIG_GET_ROUTES of the %INSN_DEVICE_CONFIG + * instruction. If this is not initialized by the low-level driver, a + * default handler will be set during post-configuration. + * @get_valid_routes: Optional pointer to a handler for the + * %INSN_DEVICE_CONFIG_GET_ROUTES sub-instruction of the + * %INSN_DEVICE_CONFIG instruction set. If this is not initialized by the + * low-level driver, a default handler that copies zero routes back to the + * user will be used. + * + * This is the main control data structure for a COMEDI device (as far as the + * COMEDI core is concerned). There are two groups of COMEDI devices - + * "legacy" devices that are configured by the handler for the + * %COMEDI_DEVCONFIG ioctl, and automatically configured devices resulting + * from a call to comedi_auto_config() as a result of a bus driver probe in + * a low-level COMEDI driver. The "legacy" COMEDI devices are allocated + * during module initialization if the "comedi_num_legacy_minors" module + * parameter is non-zero and use minor device numbers from 0 to + * comedi_num_legacy_minors minus one. The automatically configured COMEDI + * devices are allocated on demand and use minor device numbers from + * comedi_num_legacy_minors to 47. + */ +struct comedi_device { + int use_count; + struct comedi_driver *driver; + struct comedi_8254 *pacer; + void *private; + + struct device *class_dev; + int minor; + unsigned int detach_count; + struct device *hw_dev; + + const char *board_name; + const void *board_ptr; + unsigned int attached:1; + unsigned int ioenabled:1; + spinlock_t spinlock; /* generic spin-lock for low-level driver */ + struct mutex mutex; /* generic mutex for COMEDI core */ + struct rw_semaphore attach_lock; + struct kref refcount; + + int n_subdevices; + struct comedi_subdevice *subdevices; + + /* dumb */ + void __iomem *mmio; + unsigned long iobase; + unsigned long iolen; + unsigned int irq; + + struct comedi_subdevice *read_subdev; + struct comedi_subdevice *write_subdev; + + struct fasync_struct *async_queue; + + int (*open)(struct comedi_device *dev); + void (*close)(struct comedi_device *dev); + int (*insn_device_config)(struct comedi_device *dev, + struct comedi_insn *insn, unsigned int *data); + unsigned int (*get_valid_routes)(struct comedi_device *dev, + unsigned int n_pairs, + unsigned int *pair_data); +}; + +/* + * function prototypes + */ + +void comedi_event(struct comedi_device *dev, struct comedi_subdevice *s); + +struct comedi_device *comedi_dev_get_from_minor(unsigned int minor); +int comedi_dev_put(struct comedi_device *dev); + +bool comedi_is_subdevice_running(struct comedi_subdevice *s); + +void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size); +void comedi_set_spriv_auto_free(struct comedi_subdevice *s); + +int comedi_check_chanlist(struct comedi_subdevice *s, + int n, + unsigned int *chanlist); + +/* range stuff */ + +#define RANGE(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define RANGE_ext(a, b) {(a) * 1e6, (b) * 1e6, RF_EXTERNAL} +#define RANGE_mA(a, b) {(a) * 1e6, (b) * 1e6, UNIT_mA} +#define RANGE_unitless(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define BIP_RANGE(a) {-(a) * 1e6, (a) * 1e6, 0} +#define UNI_RANGE(a) {0, (a) * 1e6, 0} + +extern const struct comedi_lrange range_bipolar10; +extern const struct comedi_lrange range_bipolar5; +extern const struct comedi_lrange range_bipolar2_5; +extern const struct comedi_lrange range_unipolar10; +extern const struct comedi_lrange range_unipolar5; +extern const struct comedi_lrange range_unipolar2_5; +extern const struct comedi_lrange range_0_20mA; +extern const struct comedi_lrange range_4_20mA; +extern const struct comedi_lrange range_0_32mA; +extern const struct comedi_lrange range_unknown; + +#define range_digital range_unipolar5 + +/** + * struct comedi_lrange - Describes a COMEDI range table + * @length: Number of entries in the range table. + * @range: Array of &struct comedi_krange, one for each range. + * + * Each element of @range[] describes the minimum and maximum physical range + * and the type of units. Typically, the type of unit is %UNIT_volt + * (i.e. volts) and the minimum and maximum are in millionths of a volt. + * There may also be a flag that indicates the minimum and maximum are merely + * scale factors for an unknown, external reference. + */ +struct comedi_lrange { + int length; + struct comedi_krange range[]; +}; + +/** + * comedi_range_is_bipolar() - Test if subdevice range is bipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_range_is_bipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min < 0; +} + +/** + * comedi_range_is_unipolar() - Test if subdevice range is unipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_range_is_unipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min >= 0; +} + +/** + * comedi_range_is_external() - Test if subdevice range is external + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is external. + * %false if the range is internal. + */ +static inline bool comedi_range_is_external(struct comedi_subdevice *s, + unsigned int range) +{ + return !!(s->range_table->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_chan_range_is_bipolar() - Test if channel-specific range is bipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_bipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min < 0; +} + +/** + * comedi_chan_range_is_unipolar() - Test if channel-specific range is unipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_chan_range_is_unipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min >= 0; +} + +/** + * comedi_chan_range_is_external() - Test if channel-specific range is external + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_external(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return !!(s->range_table_list[chan]->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_offset_munge() - Convert between offset binary and 2's complement + * @s: COMEDI subdevice. + * @val: Value to be converted. + * + * Toggles the highest bit of a sample value to toggle between offset binary + * and 2's complement. Assumes that @s->maxdata is a power of 2 minus 1. + * + * Return: The converted value. + */ +static inline unsigned int comedi_offset_munge(struct comedi_subdevice *s, + unsigned int val) +{ + return val ^ s->maxdata ^ (s->maxdata >> 1); +} + +/** + * comedi_bytes_per_sample() - Determine subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. + * + * Return: The subdevice sample size. + */ +static inline unsigned int comedi_bytes_per_sample(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? sizeof(int) : sizeof(short); +} + +/** + * comedi_sample_shift() - Determine log2 of subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. The log2 of the + * sample size will be 2 or 1 and can be used as the right operand of a + * bit-shift operator to multiply or divide something by the sample size. + * + * Return: log2 of the subdevice sample size. + */ +static inline unsigned int comedi_sample_shift(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? 2 : 1; +} + +/** + * comedi_bytes_to_samples() - Convert a number of bytes to a number of samples + * @s: COMEDI subdevice. + * @nbytes: Number of bytes + * + * Return: The number of bytes divided by the subdevice sample size. + */ +static inline unsigned int comedi_bytes_to_samples(struct comedi_subdevice *s, + unsigned int nbytes) +{ + return nbytes >> comedi_sample_shift(s); +} + +/** + * comedi_samples_to_bytes() - Convert a number of samples to a number of bytes + * @s: COMEDI subdevice. + * @nsamples: Number of samples. + * + * Return: The number of samples multiplied by the subdevice sample size. + * (Does not check for arithmetic overflow.) + */ +static inline unsigned int comedi_samples_to_bytes(struct comedi_subdevice *s, + unsigned int nsamples) +{ + return nsamples << comedi_sample_shift(s); +} + +/** + * comedi_check_trigger_src() - Trivially validate a comedi_cmd trigger source + * @src: Pointer to the trigger source to validate. + * @flags: Bitmask of valid %TRIG_* for the trigger. + * + * This is used in "step 1" of the do_cmdtest functions of comedi drivers + * to validate the comedi_cmd triggers. The mask of the @src against the + * @flags allows the userspace comedilib to pass all the comedi_cmd + * triggers as %TRIG_ANY and get back a bitmask of the valid trigger sources. + * + * Return: + * 0 if trigger sources in *@src are all supported. + * -EINVAL if any trigger source in *@src is unsupported. + */ +static inline int comedi_check_trigger_src(unsigned int *src, + unsigned int flags) +{ + unsigned int orig_src = *src; + + *src = orig_src & flags; + if (*src == TRIG_INVALID || *src != orig_src) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_is_unique() - Make sure a trigger source is unique + * @src: The trigger source to check. + * + * Return: + * 0 if no more than one trigger source is set. + * -EINVAL if more than one trigger source is set. + */ +static inline int comedi_check_trigger_is_unique(unsigned int src) +{ + /* this test is true if more than one _src bit is set */ + if ((src & (src - 1)) != 0) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_arg_is() - Trivially validate a trigger argument + * @arg: Pointer to the trigger arg to validate. + * @val: The value the argument should be. + * + * Forces *@arg to be @val. + * + * Return: + * 0 if *@arg was already @val. + * -EINVAL if *@arg differed from @val. + */ +static inline int comedi_check_trigger_arg_is(unsigned int *arg, + unsigned int val) +{ + if (*arg != val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_min() - Trivially validate a trigger argument min + * @arg: Pointer to the trigger arg to validate. + * @val: The minimum value the argument should be. + * + * Forces *@arg to be at least @val, setting it to @val if necessary. + * + * Return: + * 0 if *@arg was already at least @val. + * -EINVAL if *@arg was less than @val. + */ +static inline int comedi_check_trigger_arg_min(unsigned int *arg, + unsigned int val) +{ + if (*arg < val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_max() - Trivially validate a trigger argument max + * @arg: Pointer to the trigger arg to validate. + * @val: The maximum value the argument should be. + * + * Forces *@arg to be no more than @val, setting it to @val if necessary. + * + * Return: + * 0 if*@arg was already no more than @val. + * -EINVAL if *@arg was greater than @val. + */ +static inline int comedi_check_trigger_arg_max(unsigned int *arg, + unsigned int val) +{ + if (*arg > val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/* + * Must set dev->hw_dev if you wish to dma directly into comedi's buffer. + * Also useful for retrieving a previously configured hardware device of + * known bus type. Set automatically for auto-configured devices. + * Automatically set to NULL when detaching hardware device. + */ +int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev); + +/** + * comedi_buf_n_bytes_ready - Determine amount of unread data in buffer + * @s: COMEDI subdevice. + * + * Determines the number of bytes of unread data in the asynchronous + * acquisition data buffer for a subdevice. The data in question might not + * have been fully "munged" yet. + * + * Returns: The amount of unread data in bytes. + */ +static inline unsigned int comedi_buf_n_bytes_ready(struct comedi_subdevice *s) +{ + return s->async->buf_write_count - s->async->buf_read_count; +} + +unsigned int comedi_buf_write_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_write_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_read_n_available(struct comedi_subdevice *s); +unsigned int comedi_buf_read_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_read_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_write_samples(struct comedi_subdevice *s, + const void *data, unsigned int nsamples); +unsigned int comedi_buf_read_samples(struct comedi_subdevice *s, + void *data, unsigned int nsamples); + +/* drivers.c - general comedi driver functions */ + +#define COMEDI_TIMEOUT_MS 1000 + +int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, + int (*cb)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned long context), + unsigned long context); + +unsigned int comedi_handle_events(struct comedi_device *dev, + struct comedi_subdevice *s); + +int comedi_dio_insn_config(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data, + unsigned int mask); +unsigned int comedi_dio_update_state(struct comedi_subdevice *s, + unsigned int *data); +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd); +unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); +unsigned int comedi_nscans_left(struct comedi_subdevice *s, + unsigned int nscans); +unsigned int comedi_nsamples_left(struct comedi_subdevice *s, + unsigned int nsamples); +void comedi_inc_scan_progress(struct comedi_subdevice *s, + unsigned int num_bytes); + +void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size); +int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices); +int comedi_alloc_subdev_readback(struct comedi_subdevice *s); + +int comedi_readback_insn_read(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + +int comedi_load_firmware(struct comedi_device *dev, struct device *hw_dev, + const char *name, + int (*cb)(struct comedi_device *dev, + const u8 *data, size_t size, + unsigned long context), + unsigned long context); + +int __comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +int comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +void comedi_legacy_detach(struct comedi_device *dev); + +int comedi_auto_config(struct device *hardware_device, + struct comedi_driver *driver, unsigned long context); +void comedi_auto_unconfig(struct device *hardware_device); + +int comedi_driver_register(struct comedi_driver *driver); +void comedi_driver_unregister(struct comedi_driver *driver); + +/** + * module_comedi_driver() - Helper macro for registering a comedi driver + * @__comedi_driver: comedi_driver struct + * + * Helper macro for comedi drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only use + * this macro once, and calling it replaces module_init() and module_exit(). + */ +#define module_comedi_driver(__comedi_driver) \ + module_driver(__comedi_driver, comedi_driver_register, \ + comedi_driver_unregister) + +#endif /* _COMEDIDEV_H */ diff --git a/include/linux/comedi/comedilib.h b/include/linux/comedi/comedilib.h new file mode 100644 index 000000000000..0223c9cd9215 --- /dev/null +++ b/include/linux/comedi/comedilib.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedilib.h + * Header file for kcomedilib + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998-2001 David A. Schleef <ds@schleef.org> + */ + +#ifndef _LINUX_COMEDILIB_H +#define _LINUX_COMEDILIB_H + +struct comedi_device *comedi_open(const char *path); +int comedi_close(struct comedi_device *dev); +int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int *io); +int comedi_dio_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int io); +int comedi_dio_bitfield2(struct comedi_device *dev, unsigned int subdev, + unsigned int mask, unsigned int *bits, + unsigned int base_channel); +int comedi_find_subdevice_by_type(struct comedi_device *dev, int type, + unsigned int subd); +int comedi_get_n_channels(struct comedi_device *dev, unsigned int subdevice); + +#endif diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 3c4de9b6c6e3..babb1347148c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -68,3 +68,28 @@ #define __nocfi __attribute__((__no_sanitize__("cfi"))) #define __cficanonical __attribute__((__cfi_canonical_jump_table__)) + +/* + * Turn individual warnings and errors on and off locally, depending + * on version. + */ +#define __diag_clang(version, severity, s) \ + __diag_clang_ ## version(__diag_clang_ ## severity s) + +/* Severity used in pragma directives */ +#define __diag_clang_ignore ignored +#define __diag_clang_warn warning +#define __diag_clang_error error + +#define __diag_str1(s) #s +#define __diag_str(s) __diag_str1(s) +#define __diag(s) _Pragma(__diag_str(clang diagnostic s)) + +#if CONFIG_CLANG_VERSION >= 110000 +#define __diag_clang_11(s) __diag(s) +#else +#define __diag_clang_11(s) +#endif + +#define __diag_ignore_all(option, comment) \ + __diag_clang(11, ignore, option) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index ccbbd31b3aae..52299c957c98 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -97,6 +97,10 @@ #define KASAN_ABI_VERSION 4 #endif +#ifdef CONFIG_SHADOW_CALL_STACK +#define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) +#endif + #if __has_attribute(__no_sanitize_address__) #define __no_sanitize_address __attribute__((no_sanitize_address)) #else @@ -151,6 +155,9 @@ #define __diag_GCC_8(s) #endif +#define __diag_ignore_all(option, comment) \ + __diag_GCC(8, ignore, option) + /* * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" * attribute) do not work, and must be disabled. diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 3d5af56337bd..219aa5ddbc73 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -117,40 +117,22 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define __stringify_label(n) #n -#define __annotate_reachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ -}) -#define annotate_reachable() __annotate_reachable(__COUNTER__) - #define __annotate_unreachable(c) ({ \ asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define annotate_unreachable() __annotate_unreachable(__COUNTER__) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" - /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") #else -#define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif -#ifndef ASM_UNREACHABLE -# define ASM_UNREACHABLE -#endif #ifndef unreachable # define unreachable() do { \ annotate_unreachable(); \ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index b9121afd8733..445e80517cab 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -101,6 +101,19 @@ #endif /* + * Optional: not supported by gcc + * Optional: only supported since clang >= 14.0 + * Optional: not supported by icc + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#diagnose_as_builtin + */ +#if __has_attribute(__diagnose_as_builtin__) +# define __diagnose_as(builtin...) __attribute__((__diagnose_as_builtin__(builtin))) +#else +# define __diagnose_as(builtin...) +#endif + +/* * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' * attribute warnings entirely and for good") for more information. * @@ -258,12 +271,38 @@ #define __noreturn __attribute__((__noreturn__)) /* + * Optional: not supported by gcc. + * Optional: not supported by icc. + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable + */ +#if __has_attribute(__overloadable__) +# define __overloadable __attribute__((__overloadable__)) +#else +# define __overloadable +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute */ #define __packed __attribute__((__packed__)) /* + * Note: the "type" argument should match any __builtin_object_size(p, type) usage. + * + * Optional: not supported by gcc. + * Optional: not supported by icc. + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#pass-object-size-pass-dynamic-object-size + */ +#if __has_attribute(__pass_object_size__) +# define __pass_object_size(type) __attribute__((__pass_object_size__(type))) +#else +# define __pass_object_size(type) +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute */ #define __pure __attribute__((__pure__)) @@ -309,6 +348,24 @@ #endif /* + * Optional: only supported since clang >= 14.0 + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#disable-sanitizer-instrumentation + * + * disable_sanitizer_instrumentation is not always similar to + * no_sanitize((<sanitizer-name>)): the latter may still let specific sanitizers + * insert code into functions to prevent false positives. Unlike that, + * disable_sanitizer_instrumentation prevents all kinds of instrumentation to + * functions with the attribute. + */ +#if __has_attribute(disable_sanitizer_instrumentation) +# define __disable_sanitizer_instrumentation \ + __attribute__((disable_sanitizer_instrumentation)) +#else +# define __disable_sanitizer_instrumentation +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 1d32f4c03c9e..1c2c33ae1b37 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -4,6 +4,14 @@ #ifndef __ASSEMBLY__ +#if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) +# define BTF_TYPE_TAG(value) __attribute__((btf_type_tag(#value))) +#else +# define BTF_TYPE_TAG(value) /* nothing */ +#endif + +/* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */ #ifdef __CHECKER__ /* address spaces */ # define __kernel __attribute__((address_space(0))) @@ -32,10 +40,10 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # ifdef STRUCTLEAK_PLUGIN # define __user __attribute__((user)) # else -# define __user +# define __user BTF_TYPE_TAG(user) # endif # define __iomem -# define __percpu +# define __percpu BTF_TYPE_TAG(percpu) # define __rcu # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 @@ -137,8 +145,6 @@ struct ftrace_likely_data { */ #define __naked __attribute__((__naked__)) notrace -#define __compiler_offsetof(a, b) __builtin_offsetof(a, b) - /* * Prefer gnu_inline, so that extern inline functions do not emit an * externally visible function. This makes extern inline behave as per gnu89 @@ -198,9 +204,20 @@ struct ftrace_likely_data { # define __no_kasan_or_inline __always_inline #endif -#define __no_kcsan __no_sanitize_thread #ifdef __SANITIZE_THREAD__ +/* + * Clang still emits instrumentation for __tsan_func_{entry,exit}() and builtin + * atomics even with __no_sanitize_thread (to avoid false positives in userspace + * ThreadSanitizer). The kernel's requirements are stricter and we really do not + * want any instrumentation with __no_kcsan. + * + * Therefore we add __disable_sanitizer_instrumentation where available to + * disable all instrumentation. See Kconfig.kcsan where this is mandatory. + */ +# define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused +#else +# define __no_kcsan #endif #ifndef __no_sanitize_or_inline @@ -357,4 +374,8 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) +#ifndef __diag_ignore_all +#define __diag_ignore_all(option, comment) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/include/linux/component.h b/include/linux/component.h index 16de18f473d7..df4aa75c9e7c 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -38,10 +38,10 @@ int component_add_typed(struct device *dev, const struct component_ops *ops, int subcomponent); void component_del(struct device *, const struct component_ops *); -int component_bind_all(struct device *master, void *master_data); -void component_unbind_all(struct device *master, void *master_data); +int component_bind_all(struct device *parent, void *data); +void component_unbind_all(struct device *parent, void *data); -struct master; +struct aggregate_device; /** * struct component_master_ops - callback for the aggregate driver @@ -82,6 +82,12 @@ struct component_master_ops { void (*unbind)(struct device *master); }; +/* A set helper functions for component compare/release */ +int component_compare_of(struct device *dev, void *data); +void component_release_of(struct device *dev, void *data); +int component_compare_dev(struct device *dev, void *data); +int component_compare_dev_name(struct device *dev, void *data); + void component_master_del(struct device *, const struct component_master_ops *); @@ -89,22 +95,22 @@ struct component_match; int component_master_add_with_match(struct device *, const struct component_master_ops *, struct component_match *); -void component_match_add_release(struct device *master, +void component_match_add_release(struct device *parent, struct component_match **matchptr, void (*release)(struct device *, void *), int (*compare)(struct device *, void *), void *compare_data); -void component_match_add_typed(struct device *master, +void component_match_add_typed(struct device *parent, struct component_match **matchptr, int (*compare_typed)(struct device *, int, void *), void *compare_data); /** * component_match_add - add a component match entry - * @master: device with the aggregate driver + * @parent: device with the aggregate driver * @matchptr: pointer to the list of component matches * @compare: compare function to match against all components * @compare_data: opaque pointer passed to the @compare function * - * Adds a new component match to the list stored in @matchptr, which the @master + * Adds a new component match to the list stored in @matchptr, which the @parent * aggregate driver needs to function. The list of component matches pointed to * by @matchptr must be initialized to NULL before adding the first match. This * only matches against components added with component_add(). @@ -114,11 +120,11 @@ void component_match_add_typed(struct device *master, * * See also component_match_add_release() and component_match_add_typed(). */ -static inline void component_match_add(struct device *master, +static inline void component_match_add(struct device *parent, struct component_match **matchptr, int (*compare)(struct device *, void *), void *compare_data) { - component_match_add_release(master, matchptr, NULL, compare, + component_match_add_release(parent, matchptr, NULL, compare, compare_data); } diff --git a/include/linux/console.h b/include/linux/console.h index a97f277cfdfa..7cd758a4f44e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -219,12 +219,6 @@ extern atomic_t ignore_console_lock_warning; #define VESA_HSYNC_SUSPEND 2 #define VESA_POWERDOWN 3 -#ifdef CONFIG_VGA_CONSOLE -extern bool vgacon_text_force(void); -#else -static inline bool vgacon_text_force(void) { return false; } -#endif - extern void console_init(void); /* For deferred console takeover */ diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 78fcd776b185..08a1d3e7e46d 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -12,29 +12,43 @@ struct core_vma_metadata { unsigned long start, end; unsigned long flags; unsigned long dump_size; + unsigned long pgoff; + struct file *file; }; -extern int core_uses_pid; -extern char core_pattern[]; -extern unsigned int core_pipe_limit; +struct coredump_params { + const kernel_siginfo_t *siginfo; + struct pt_regs *regs; + struct file *file; + unsigned long limit; + unsigned long mm_flags; + loff_t written; + loff_t pos; + loff_t to_skip; + int vma_count; + size_t vma_data_size; + struct core_vma_metadata *vma_meta; +}; /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. */ -struct coredump_params; extern void dump_skip_to(struct coredump_params *cprm, unsigned long to); extern void dump_skip(struct coredump_params *cprm, size_t nr); extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr); extern int dump_align(struct coredump_params *cprm, int align); int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len); -int dump_vma_snapshot(struct coredump_params *cprm, int *vma_count, - struct core_vma_metadata **vma_meta, - size_t *vma_data_size_ptr); extern void do_coredump(const kernel_siginfo_t *siginfo); #else static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif +#if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL) +extern void validate_coredump_safety(void); +#else +static inline void validate_coredump_safety(void) {} +#endif + #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 93a2922b7653..9f445f09fcfe 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -36,7 +36,6 @@ extern struct bus_type coresight_bustype; enum coresight_dev_type { - CORESIGHT_DEV_TYPE_NONE, CORESIGHT_DEV_TYPE_SINK, CORESIGHT_DEV_TYPE_LINK, CORESIGHT_DEV_TYPE_LINKSINK, @@ -46,7 +45,6 @@ enum coresight_dev_type { }; enum coresight_dev_subtype_sink { - CORESIGHT_DEV_SUBTYPE_SINK_NONE, CORESIGHT_DEV_SUBTYPE_SINK_PORT, CORESIGHT_DEV_SUBTYPE_SINK_BUFFER, CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM, @@ -54,21 +52,18 @@ enum coresight_dev_subtype_sink { }; enum coresight_dev_subtype_link { - CORESIGHT_DEV_SUBTYPE_LINK_NONE, CORESIGHT_DEV_SUBTYPE_LINK_MERG, CORESIGHT_DEV_SUBTYPE_LINK_SPLIT, CORESIGHT_DEV_SUBTYPE_LINK_FIFO, }; enum coresight_dev_subtype_source { - CORESIGHT_DEV_SUBTYPE_SOURCE_NONE, CORESIGHT_DEV_SUBTYPE_SOURCE_PROC, CORESIGHT_DEV_SUBTYPE_SOURCE_BUS, CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE, }; enum coresight_dev_subtype_helper { - CORESIGHT_DEV_SUBTYPE_HELPER_NONE, CORESIGHT_DEV_SUBTYPE_HELPER_CATU, }; diff --git a/include/linux/counter.h b/include/linux/counter.h index b7d0a00a61cf..1fe17f5adb09 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -38,64 +38,64 @@ enum counter_comp_type { * @type: Counter component data type * @name: device-specific component name * @priv: component-relevant data - * @action_read Synapse action mode read callback. The read value of the + * @action_read: Synapse action mode read callback. The read value of the * respective Synapse action mode should be passed back via * the action parameter. - * @device_u8_read Device u8 component read callback. The read value of the + * @device_u8_read: Device u8 component read callback. The read value of the * respective Device u8 component should be passed back via * the val parameter. - * @count_u8_read Count u8 component read callback. The read value of the + * @count_u8_read: Count u8 component read callback. The read value of the * respective Count u8 component should be passed back via * the val parameter. - * @signal_u8_read Signal u8 component read callback. The read value of the + * @signal_u8_read: Signal u8 component read callback. The read value of the * respective Signal u8 component should be passed back via * the val parameter. - * @device_u32_read Device u32 component read callback. The read value of + * @device_u32_read: Device u32 component read callback. The read value of * the respective Device u32 component should be passed * back via the val parameter. - * @count_u32_read Count u32 component read callback. The read value of the + * @count_u32_read: Count u32 component read callback. The read value of the * respective Count u32 component should be passed back via * the val parameter. - * @signal_u32_read Signal u32 component read callback. The read value of + * @signal_u32_read: Signal u32 component read callback. The read value of * the respective Signal u32 component should be passed * back via the val parameter. - * @device_u64_read Device u64 component read callback. The read value of + * @device_u64_read: Device u64 component read callback. The read value of * the respective Device u64 component should be passed * back via the val parameter. - * @count_u64_read Count u64 component read callback. The read value of the + * @count_u64_read: Count u64 component read callback. The read value of the * respective Count u64 component should be passed back via * the val parameter. - * @signal_u64_read Signal u64 component read callback. The read value of + * @signal_u64_read: Signal u64 component read callback. The read value of * the respective Signal u64 component should be passed * back via the val parameter. - * @action_write Synapse action mode write callback. The write value of + * @action_write: Synapse action mode write callback. The write value of * the respective Synapse action mode is passed via the * action parameter. - * @device_u8_write Device u8 component write callback. The write value of + * @device_u8_write: Device u8 component write callback. The write value of * the respective Device u8 component is passed via the val * parameter. - * @count_u8_write Count u8 component write callback. The write value of + * @count_u8_write: Count u8 component write callback. The write value of * the respective Count u8 component is passed via the val * parameter. - * @signal_u8_write Signal u8 component write callback. The write value of + * @signal_u8_write: Signal u8 component write callback. The write value of * the respective Signal u8 component is passed via the val * parameter. - * @device_u32_write Device u32 component write callback. The write value of + * @device_u32_write: Device u32 component write callback. The write value of * the respective Device u32 component is passed via the * val parameter. - * @count_u32_write Count u32 component write callback. The write value of + * @count_u32_write: Count u32 component write callback. The write value of * the respective Count u32 component is passed via the val * parameter. - * @signal_u32_write Signal u32 component write callback. The write value of + * @signal_u32_write: Signal u32 component write callback. The write value of * the respective Signal u32 component is passed via the * val parameter. - * @device_u64_write Device u64 component write callback. The write value of + * @device_u64_write: Device u64 component write callback. The write value of * the respective Device u64 component is passed via the * val parameter. - * @count_u64_write Count u64 component write callback. The write value of + * @count_u64_write: Count u64 component write callback. The write value of * the respective Count u64 component is passed via the val * parameter. - * @signal_u64_write Signal u64 component write callback. The write value of + * @signal_u64_write: Signal u64 component write callback. The write value of * the respective Signal u64 component is passed via the * val parameter. */ @@ -314,8 +314,6 @@ struct counter_device { struct counter_comp *ext; size_t num_ext; - void *priv; - struct device dev; struct cdev chrdev; struct list_head events_list; @@ -329,10 +327,17 @@ struct counter_device { struct mutex ops_exist_lock; }; -int counter_register(struct counter_device *const counter); +void *counter_priv(const struct counter_device *const counter); + +struct counter_device *counter_alloc(size_t sizeof_priv); +void counter_put(struct counter_device *const counter); +int counter_add(struct counter_device *const counter); + void counter_unregister(struct counter_device *const counter); -int devm_counter_register(struct device *dev, - struct counter_device *const counter); +struct counter_device *devm_counter_alloc(struct device *dev, + size_t sizeof_priv); +int devm_counter_add(struct device *dev, + struct counter_device *const counter); void counter_push_event(struct counter_device *const counter, const u8 event, const u8 channel); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1ab29e61b078..35c7d6db4139 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -382,6 +382,9 @@ struct cpufreq_driver { int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); + /* Will be called after the driver is fully initialized */ + void (*ready)(struct cpufreq_policy *policy); + struct freq_attr **attr; /* platform specific boost support code */ @@ -658,6 +661,11 @@ struct gov_attr_set { /* sysfs ops for cpufreq governors */ extern const struct sysfs_ops governor_sysfs_ops; +static inline struct gov_attr_set *to_gov_attr_set(struct kobject *kobj) +{ + return container_of(kobj, struct gov_attr_set, kobj); +} + void gov_attr_set_init(struct gov_attr_set *attr_set, struct list_head *list_node); void gov_attr_set_get(struct gov_attr_set *attr_set, struct list_head *list_node); unsigned int gov_attr_set_put(struct gov_attr_set *attr_set, struct list_head *list_node); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 773c83730906..82e33137f917 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -100,6 +100,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, CPUHP_PADATA_DEAD, CPUHP_AP_DTPM_CPU_DEAD, + CPUHP_RANDOM_PREPARE, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, @@ -165,6 +166,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, + CPUHP_AP_PERF_RISCV_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, @@ -225,11 +227,13 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE, + CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, @@ -239,6 +243,7 @@ enum cpuhp_state { CPUHP_AP_PERF_CSKY_ONLINE, CPUHP_AP_WATCHDOG_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, + CPUHP_AP_RANDOM_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1e7399fc69c0..fe29ac7cc469 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -102,7 +102,7 @@ extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; -static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) +static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); @@ -110,7 +110,7 @@ static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) } /* verify cpu argument to cpumask_* operators */ -static inline unsigned int cpumask_check(unsigned int cpu) +static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; @@ -123,6 +123,17 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return 0; } +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +{ + return 0; +} + +static inline unsigned int cpumask_first_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return 0; +} + static inline unsigned int cpumask_last(const struct cpumask *srcp) { return 0; @@ -167,7 +178,7 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) static inline int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { - return cpumask_next_and(-1, src1p, src2p); + return cpumask_first_and(src1p, src2p); } static inline int cpumask_any_distribute(const struct cpumask *srcp) @@ -196,6 +207,30 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) } /** + * cpumask_first_zero - get the first unset cpu in a cpumask + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if all cpus are set. + */ +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +{ + return find_first_zero_bit(cpumask_bits(srcp), nr_cpumask_bits); +} + +/** + * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 + * @src1p: the first input + * @src2p: the second input + * + * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). + */ +static inline +unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) +{ + return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + +/** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * @@ -306,12 +341,12 @@ extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) +static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -322,12 +357,12 @@ static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ -static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) +static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } -static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) +static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } @@ -339,7 +374,7 @@ static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) * * Returns 1 if @cpu is set in @cpumask, else returns 0 */ -static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -353,7 +388,7 @@ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) * * test_and_set_bit wrapper for cpumasks. */ -static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -367,7 +402,7 @@ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) * * test_and_clear_bit wrapper for cpumasks. */ -static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -586,15 +621,6 @@ static inline void cpumask_copy(struct cpumask *dstp, #define cpumask_any(srcp) cpumask_first(srcp) /** - * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 - * @src1p: the first input - * @src2p: the second input - * - * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). - */ -#define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) - -/** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask diff --git a/include/linux/cpumask_api.h b/include/linux/cpumask_api.h new file mode 100644 index 000000000000..83bd3ebe82b0 --- /dev/null +++ b/include/linux/cpumask_api.h @@ -0,0 +1 @@ +#include <linux/cpumask.h> diff --git a/include/linux/crc64.h b/include/linux/crc64.h index c756e65a1b58..e044c60d1e61 100644 --- a/include/linux/crc64.h +++ b/include/linux/crc64.h @@ -7,5 +7,12 @@ #include <linux/types.h> +#define CRC64_ROCKSOFT_STRING "crc64-rocksoft" + u64 __pure crc64_be(u64 crc, const void *p, size_t len); +u64 __pure crc64_rocksoft_generic(u64 crc, const void *p, size_t len); + +u64 crc64_rocksoft(const unsigned char *buffer, size_t len); +u64 crc64_rocksoft_update(u64 crc, const unsigned char *buffer, size_t len); + #endif /* _LINUX_CRC64_H */ diff --git a/include/linux/cred.h b/include/linux/cred.h index fcbc6885cc09..9ed9232af934 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -176,7 +176,7 @@ extern int set_cred_ucounts(struct cred *); * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS -extern void __invalid_creds(const struct cred *, const char *, unsigned); +extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 855869e1fd32..2324ab6f1846 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -133,6 +133,15 @@ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 /* + * Mark an algorithm as a service implementation only usable by a + * template and never by a normal user of the kernel crypto API. + * This is intended to be used by algorithms that are themselves + * not FIPS-approved but may instead be used to implement parts of + * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). + */ +#define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 + +/* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_NEED_KEY 0x00000001 diff --git a/include/linux/cuda.h b/include/linux/cuda.h index 45bfe9d61271..daf3e6f98444 100644 --- a/include/linux/cuda.h +++ b/include/linux/cuda.h @@ -12,7 +12,7 @@ #include <uapi/linux/cuda.h> -extern int find_via_cuda(void); +extern int __init find_via_cuda(void); extern int cuda_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); extern void cuda_poll(void); diff --git a/include/linux/damon.h b/include/linux/damon.h index b4d4be3cc987..f23cbfa4248d 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -11,12 +11,19 @@ #include <linux/mutex.h> #include <linux/time64.h> #include <linux/types.h> +#include <linux/random.h> /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE /* Max priority score for DAMON-based operation schemes */ #define DAMOS_MAX_SCORE (99) +/* Get a random number in [l, r) */ +static inline unsigned long damon_rand(unsigned long l, unsigned long r) +{ + return l + prandom_u32_max(r - l); +} + /** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). @@ -53,19 +60,18 @@ struct damon_region { /** * struct damon_target - Represents a monitoring target. - * @id: Unique identifier for this target. + * @pid: The PID of the virtual address space to monitor. * @nr_regions: Number of monitoring target regions of this target. * @regions_list: Head of the monitoring target regions of this target. * @list: List head for siblings. * * Each monitoring context could have multiple targets. For example, a context * for virtual memory address spaces could have multiple target processes. The - * @id of each target should be unique among the targets of the context. For - * example, in the virtual address monitoring context, it could be a pidfd or - * an address of an mm_struct. + * @pid should be set for appropriate &struct damon_operations including the + * virtual address spaces monitoring operations. */ struct damon_target { - unsigned long id; + struct pid *pid; unsigned int nr_regions; struct list_head regions_list; struct list_head list; @@ -81,6 +87,7 @@ struct damon_target { * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_STAT: Do nothing but count the stat. + * @NR_DAMOS_ACTIONS: Total number of DAMOS actions */ enum damos_action { DAMOS_WILLNEED, @@ -89,6 +96,7 @@ enum damos_action { DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, DAMOS_STAT, /* Do nothing but only record the stat */ + NR_DAMOS_ACTIONS, }; /** @@ -114,9 +122,9 @@ enum damos_action { * uses smaller one as the effective quota. * * For selecting regions within the quota, DAMON prioritizes current scheme's - * target memory regions using the &struct damon_primitive->get_scheme_score. + * target memory regions using the &struct damon_operations->get_scheme_score. * You could customize the prioritization logic by setting &weight_sz, - * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * &weight_nr_accesses, and &weight_age, because monitoring operations are * encouraged to respect those. */ struct damos_quota { @@ -151,10 +159,12 @@ struct damos_quota { * * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + * @NR_DAMOS_WMARK_METRICS: Total number of DAMOS watermark metrics */ enum damos_wmark_metric { DAMOS_WMARK_NONE, DAMOS_WMARK_FREE_MEM_RATE, + NR_DAMOS_WMARK_METRICS, }; /** @@ -186,6 +196,22 @@ struct damos_watermarks { }; /** + * struct damos_stat - Statistics on a given scheme. + * @nr_tried: Total number of regions that the scheme is tried to be applied. + * @sz_tried: Total size of regions that the scheme is tried to be applied. + * @nr_applied: Total number of regions that the scheme is applied. + * @sz_applied: Total size of regions that the scheme is applied. + * @qt_exceeds: Total number of times the quota of the scheme has exceeded. + */ +struct damos_stat { + unsigned long nr_tried; + unsigned long sz_tried; + unsigned long nr_applied; + unsigned long sz_applied; + unsigned long qt_exceeds; +}; + +/** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. * @max_sz_region: Maximum size of target regions. @@ -196,8 +222,7 @@ struct damos_watermarks { * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. - * @stat_count: Total number of regions that this scheme is applied. - * @stat_sz: Total size of regions that this scheme is applied. + * @stat: Statistics of this scheme. * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the @@ -228,18 +253,30 @@ struct damos { enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; - unsigned long stat_count; - unsigned long stat_sz; + struct damos_stat stat; struct list_head list; }; +/** + * enum damon_ops_id - Identifier for each monitoring operations implementation + * + * @DAMON_OPS_VADDR: Monitoring operations for virtual address spaces + * @DAMON_OPS_PADDR: Monitoring operations for the physical address space + */ +enum damon_ops_id { + DAMON_OPS_VADDR, + DAMON_OPS_PADDR, + NR_DAMON_OPS, +}; + struct damon_ctx; /** - * struct damon_primitive - Monitoring primitives for given use cases. + * struct damon_operations - Monitoring operations for given use cases. * - * @init: Initialize primitive-internal data structures. - * @update: Update primitive-internal data structures. + * @id: Identifier of this operations set. + * @init: Initialize operations-related data structures. + * @update: Update operations-related data structures. * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. @@ -249,18 +286,20 @@ struct damon_ctx; * @cleanup: Clean up the context. * * DAMON can be extended for various address spaces and usages. For this, - * users should register the low level primitives for their target address - * space and usecase via the &damon_ctx.primitive. Then, the monitoring thread + * users should register the low level operations for their target address + * space and usecase via the &damon_ctx.ops. Then, the monitoring thread * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting - * the monitoring, @update after each &damon_ctx.primitive_update_interval, and + * the monitoring, @update after each &damon_ctx.ops_update_interval, and * @check_accesses, @target_valid and @prepare_access_checks after each * &damon_ctx.sample_interval. Finally, @reset_aggregated is called after each * &damon_ctx.aggr_interval. * - * @init should initialize primitive-internal data structures. For example, + * Each &struct damon_operations instance having valid @id can be registered + * via damon_register_ops() and selected by damon_select_ops() later. + * @init should initialize operations-related data structures. For example, * this could be used to construct proper monitoring target regions and link * those to @damon_ctx.adaptive_targets. - * @update should update the primitive-internal data structures. For example, + * @update should update the operations-related data structures. For example, * this could be used to update monitoring target regions for current status. * @prepare_access_checks should manipulate the monitoring regions to be * prepared for the next access check. @@ -274,12 +313,14 @@ struct damon_ctx; * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action - * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. + * to the region and return bytes of the region that the action is successfully + * applied. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. */ -struct damon_primitive { +struct damon_operations { + enum damon_ops_id id; void (*init)(struct damon_ctx *context); void (*update)(struct damon_ctx *context); void (*prepare_access_checks)(struct damon_ctx *context); @@ -288,8 +329,9 @@ struct damon_primitive { int (*get_scheme_score)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); + unsigned long (*apply_scheme)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); }; @@ -332,15 +374,15 @@ struct damon_callback { * * @sample_interval: The time between access samplings. * @aggr_interval: The time between monitor results aggregations. - * @primitive_update_interval: The time between monitoring primitive updates. + * @ops_update_interval: The time between monitoring operations updates. * * For each @sample_interval, DAMON checks whether each region is accessed or * not. It aggregates and keeps the access information (number of accesses to * each region) for @aggr_interval time. DAMON also checks whether the target * memory regions need update (e.g., by ``mmap()`` calls from the application, * in case of virtual memory monitoring) and applies the changes for each - * @primitive_update_interval. All time intervals are in micro-seconds. - * Please refer to &struct damon_primitive and &struct damon_callback for more + * @ops_update_interval. All time intervals are in micro-seconds. + * Please refer to &struct damon_operations and &struct damon_callback for more * detail. * * @kdamond: Kernel thread who does the monitoring. @@ -352,7 +394,7 @@ struct damon_callback { * * Once started, the monitoring thread runs until explicitly required to be * terminated or every monitoring target is invalid. The validity of the - * targets is checked via the &damon_primitive.target_valid of @primitive. The + * targets is checked via the &damon_operations.target_valid of @ops. The * termination can also be explicitly requested by writing non-zero to * @kdamond_stop. The thread sets @kdamond to NULL when it terminates. * Therefore, users can know whether the monitoring is ongoing or terminated by @@ -362,7 +404,7 @@ struct damon_callback { * Note that the monitoring thread protects only @kdamond and @kdamond_stop via * @kdamond_lock. Accesses to other fields must be protected by themselves. * - * @primitive: Set of monitoring primitives for given use cases. + * @ops: Set of monitoring operations for given use cases. * @callback: Set of callbacks for monitoring events notifications. * * @min_nr_regions: The minimum number of adaptive monitoring regions. @@ -373,17 +415,17 @@ struct damon_callback { struct damon_ctx { unsigned long sample_interval; unsigned long aggr_interval; - unsigned long primitive_update_interval; + unsigned long ops_update_interval; /* private: internal use only */ struct timespec64 last_aggregation; - struct timespec64 last_primitive_update; + struct timespec64 last_ops_update; /* public: */ struct task_struct *kdamond; struct mutex kdamond_lock; - struct damon_primitive primitive; + struct damon_operations ops; struct damon_callback callback; unsigned long min_nr_regions; @@ -392,14 +434,20 @@ struct damon_ctx { struct list_head schemes; }; -#define damon_next_region(r) \ - (container_of(r->list.next, struct damon_region, list)) +static inline struct damon_region *damon_next_region(struct damon_region *r) +{ + return container_of(r->list.next, struct damon_region, list); +} -#define damon_prev_region(r) \ - (container_of(r->list.prev, struct damon_region, list)) +static inline struct damon_region *damon_prev_region(struct damon_region *r) +{ + return container_of(r->list.prev, struct damon_region, list); +} -#define damon_last_region(t) \ - (list_last_entry(&t->regions_list, struct damon_region, list)) +static inline struct damon_region *damon_last_region(struct damon_target *t) +{ + return list_last_entry(&t->regions_list, struct damon_region, list); +} #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) @@ -422,9 +470,18 @@ struct damon_ctx { #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); -inline void damon_insert_region(struct damon_region *r, + +/* + * Add a region between two other regions + */ +static inline void damon_insert_region(struct damon_region *r, struct damon_region *prev, struct damon_region *next, - struct damon_target *t); + struct damon_target *t) +{ + __list_add(&r->list, &prev->list, &next->list); + t->nr_regions++; +} + void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); @@ -437,7 +494,7 @@ struct damos *damon_new_scheme( void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); -struct damon_target *damon_new_target(unsigned long id); +struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); @@ -446,49 +503,18 @@ unsigned int damon_nr_regions(struct damon_target *t); struct damon_ctx *damon_new_ctx(void); void damon_destroy_ctx(struct damon_ctx *ctx); -int damon_set_targets(struct damon_ctx *ctx, - unsigned long *ids, ssize_t nr_ids); int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, - unsigned long aggr_int, unsigned long primitive_upd_int, + unsigned long aggr_int, unsigned long ops_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); +int damon_register_ops(struct damon_operations *ops); +int damon_select_ops(struct damon_ctx *ctx, enum damon_ops_id id); -int damon_start(struct damon_ctx **ctxs, int nr_ctxs); +int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ -#ifdef CONFIG_DAMON_VADDR - -/* Monitoring primitives for virtual memory address spaces */ -void damon_va_init(struct damon_ctx *ctx); -void damon_va_update(struct damon_ctx *ctx); -void damon_va_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_va_check_accesses(struct damon_ctx *ctx); -bool damon_va_target_valid(void *t); -void damon_va_cleanup(struct damon_ctx *ctx); -int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -void damon_va_set_primitives(struct damon_ctx *ctx); - -#endif /* CONFIG_DAMON_VADDR */ - -#ifdef CONFIG_DAMON_PADDR - -/* Monitoring primitives for the physical memory address space */ -void damon_pa_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); -bool damon_pa_target_valid(void *t); -int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -void damon_pa_set_primitives(struct damon_ctx *ctx); - -#endif /* CONFIG_DAMON_PADDR */ - #endif /* _DAMON_H */ diff --git a/include/linux/dax.h b/include/linux/dax.h index 8623caa67388..9fc5f99a0ae2 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -6,14 +6,14 @@ #include <linux/mm.h> #include <linux/radix-tree.h> -/* Flag for synchronous flush */ -#define DAXDEV_F_SYNC (1UL << 0) - typedef unsigned long dax_entry_t; +struct dax_device; +struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; -struct dax_device; + struct dax_operations { /* * direct_access: translate a device-relative @@ -28,33 +28,18 @@ struct dax_operations { */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); - /* copy_from_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); - /* copy_to_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops, unsigned long flags); +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); -bool __dax_synchronous(struct dax_device *dax_dev); -static inline bool dax_synchronous(struct dax_device *dax_dev) -{ - return __dax_synchronous(dax_dev); -} -void __set_dax_synchronous(struct dax_device *dax_dev); -static inline void set_dax_synchronous(struct dax_device *dax_dev) -{ - __set_dax_synchronous(dax_dev); -} +bool dax_synchronous(struct dax_device *dax_dev); +void set_dax_synchronous(struct dax_device *dax_dev); /* * Check if given mapping is supported by the file / underlying device. */ @@ -68,8 +53,8 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else -static inline struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops, unsigned long flags) +static inline struct dax_device *alloc_dax(void *private, + const struct dax_operations *ops) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this @@ -104,48 +89,46 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, } #endif -struct writeback_control; -int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); -#if IS_ENABLED(CONFIG_FS_DAX) -bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors); - -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); +void set_dax_nocache(struct dax_device *dax_dev); +void set_dax_nomc(struct dax_device *dax_dev); +struct writeback_control; +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); +void dax_remove_host(struct gendisk *disk); +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off); static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); } - -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); -int dax_writeback_mapping_range(struct address_space *mapping, - struct dax_device *dax_dev, struct writeback_control *wbc); - -struct page *dax_layout_busy_page(struct address_space *mapping); -struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); -dax_entry_t dax_lock_page(struct page *page); -void dax_unlock_page(struct page *page, dax_entry_t cookie); #else -#define generic_fsdax_supported NULL - -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) +static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { - return false; + return 0; } - -static inline void fs_put_dax(struct dax_device *dax_dev) +static inline void dax_remove_host(struct gendisk *disk) { } - -static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off) { return NULL; } +static inline void fs_put_dax(struct dax_device *dax_dev) +{ +} +#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ +#if IS_ENABLED(CONFIG_FS_DAX) +int dax_writeback_mapping_range(struct address_space *mapping, + struct dax_device *dax_dev, struct writeback_control *wbc); + +struct page *dax_layout_busy_page(struct address_space *mapping); +struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); +#else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; @@ -174,6 +157,11 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); + #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); @@ -208,7 +196,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9e23d33bb6f1..f5bba51480b2 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -61,16 +61,6 @@ extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; -struct dentry_stat_t { - long nr_dentry; - long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long nr_negative; /* # of unused negative dentries */ - long dummy; /* Reserved for future use */ -}; -extern struct dentry_stat_t dentry_stat; - /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index af7e6eb50283..3e03d010bd2e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -9,18 +9,9 @@ #include <uapi/linux/taskstats.h> -/* - * Per-task flags relevant to delay accounting - * maintained privately to avoid exhausting similar flags in sched.h:PF_* - * Used to set current->delays->flags - */ -#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ -#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ - #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; - unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately * @@ -37,13 +28,13 @@ struct task_delay_info { * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ - u64 blkio_start; /* Shared by blkio, swapin */ + u64 blkio_start; u64 blkio_delay; /* wait for sync block io completion */ - u64 swapin_delay; /* wait for swapin block io completion */ + u64 swapin_start; + u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ - u32 swapin_count; /* total count of the number of swapin block */ - /* io operations performed */ + u32 swapin_count; /* total count of swapin */ u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ @@ -51,8 +42,12 @@ struct task_delay_info { u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ + u64 compact_start; + u64 compact_delay; /* wait for memory compact */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ + u32 compact_count; /* total count of memory compact */ }; #endif @@ -79,26 +74,10 @@ extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); - -static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) -{ - if (p->delays) - return (p->delays->flags & DELAYACCT_PF_BLKIO); - else - return 0; -} - -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags |= flag; -} - -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags &= ~flag; -} +extern void __delayacct_swapin_start(void); +extern void __delayacct_swapin_end(void); +extern void __delayacct_compact_start(void); +extern void __delayacct_compact_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -123,7 +102,6 @@ static inline void delayacct_blkio_start(void) if (!static_branch_unlikely(&delayacct_key)) return; - delayacct_set_flag(current, DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } @@ -135,7 +113,6 @@ static inline void delayacct_blkio_end(struct task_struct *p) if (p->delays) __delayacct_blkio_end(p); - delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) @@ -147,33 +124,77 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) static inline void delayacct_freepages_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_end(); } static inline void delayacct_thrashing_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_thrashing_start(); } static inline void delayacct_thrashing_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_thrashing_end(); } +static inline void delayacct_swapin_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_swapin_start(); +} + +static inline void delayacct_swapin_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_swapin_end(); +} + +static inline void delayacct_compact_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_start(); +} + +static inline void delayacct_compact_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_end(); +} + #else -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{} -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{} static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) @@ -199,6 +220,14 @@ static inline void delayacct_thrashing_start(void) {} static inline void delayacct_thrashing_end(void) {} +static inline void delayacct_swapin_start(void) +{} +static inline void delayacct_swapin_end(void) +{} +static inline void delayacct_compact_start(void) +{} +static inline void delayacct_compact_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a7df155ea49b..c2a3758c4aaa 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -147,8 +147,6 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); @@ -200,8 +198,6 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; - dm_dax_copy_iter_fn dax_copy_from_iter; - dm_dax_copy_iter_fn dax_copy_to_iter; dm_dax_zero_page_range_fn dax_zero_page_range; /* For internal device-mapper use. */ @@ -321,12 +317,6 @@ struct dm_target { unsigned num_secure_erase_bios; /* - * The number of WRITE SAME bios that will be submitted to the target. - * The bio number can be accessed with dm_bio_get_target_bio_nr. - */ - unsigned num_write_same_bios; - - /* * The number of WRITE ZEROES bios that will be submitted to the target. * The bio number can be accessed with dm_bio_get_target_bio_nr. */ @@ -362,10 +352,16 @@ struct dm_target { bool limit_swap_bios:1; /* - * Set if this target implements a a zoned device and needs emulation of + * Set if this target implements a zoned device and needs emulation of * zone append operations using regular writes. */ bool emulate_zone_append:1; + + /* + * Set if the target will submit IO using dm_submit_bio_remap() + * after returning DM_MAPIO_SUBMITTED from its map function. + */ + bool accounts_remapped_io:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); @@ -469,6 +465,7 @@ int dm_suspended(struct dm_target *ti); int dm_post_suspending(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); +void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone); union map_info *dm_get_rq_mapinfo(struct request *rq); #ifdef CONFIG_BLK_DEV_ZONED diff --git a/include/linux/device.h b/include/linux/device.h index e270cb740b9e..93459724dcde 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -45,6 +45,7 @@ struct iommu_ops; struct iommu_group; struct dev_pin_info; struct dev_iommu; +struct msi_device_data; /** * struct subsys_interface - interfaces to device functions @@ -372,6 +373,20 @@ struct dev_links_info { }; /** + * struct dev_msi_info - Device data related to MSI + * @domain: The MSI interrupt domain associated to the device + * @data: Pointer to MSI device data + */ +struct dev_msi_info { +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + struct irq_domain *domain; +#endif +#ifdef CONFIG_GENERIC_MSI_IRQ + struct msi_device_data *data; +#endif +}; + +/** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host @@ -407,9 +422,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. - * @msi_lock: Lock to protect MSI mask cache and mask register - * @msi_list: Hosts MSI descriptors - * @msi_domain: The generic MSI domain this device is using. + * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). @@ -501,16 +514,10 @@ struct device { struct em_perf_domain *em_pd; #endif -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *msi_domain; -#endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif -#ifdef CONFIG_GENERIC_MSI_IRQ - raw_spinlock_t msi_lock; - struct list_head msi_list; -#endif + struct dev_msi_info msi; #ifdef CONFIG_DMA_OPS const struct dma_map_ops *dma_ops; #endif @@ -668,7 +675,7 @@ static inline void set_dev_node(struct device *dev, int node) static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - return dev->msi_domain; + return dev->msi.domain; #else return NULL; #endif @@ -677,7 +684,7 @@ static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - dev->msi_domain = d; + dev->msi.domain = d; #endif } diff --git a/include/linux/dma-buf-map.h b/include/linux/dma-buf-map.h index 278d489e4bdd..19fa0b5ae5ec 100644 --- a/include/linux/dma-buf-map.h +++ b/include/linux/dma-buf-map.h @@ -52,13 +52,13 @@ * * struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(0xdeadbeaf); * - * dma_buf_map_set_vaddr(&map. 0xdeadbeaf); + * dma_buf_map_set_vaddr(&map, 0xdeadbeaf); * * To set an address in I/O memory, use dma_buf_map_set_vaddr_iomem(). * * .. code-block:: c * - * dma_buf_map_set_vaddr_iomem(&map. 0xdeadbeaf); + * dma_buf_map_set_vaddr_iomem(&map, 0xdeadbeaf); * * Instances of struct dma_buf_map do not have to be cleaned up, but * can be cleared to NULL with dma_buf_map_clear(). Cleared mappings diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 42a323a73c61..2097760e8e95 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -13,7 +13,7 @@ #ifndef __DMA_BUF_H__ #define __DMA_BUF_H__ -#include <linux/dma-buf-map.h> +#include <linux/iosys-map.h> #include <linux/file.h> #include <linux/err.h> #include <linux/scatterlist.h> @@ -283,8 +283,8 @@ struct dma_buf_ops { */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); - int (*vmap)(struct dma_buf *dmabuf, struct dma_buf_map *map); - void (*vunmap)(struct dma_buf *dmabuf, struct dma_buf_map *map); + int (*vmap)(struct dma_buf *dmabuf, struct iosys_map *map); + void (*vunmap)(struct dma_buf *dmabuf, struct iosys_map *map); }; /** @@ -347,7 +347,7 @@ struct dma_buf { * @vmap_ptr: * The current vmap ptr if @vmapping_counter > 0. Protected by @lock. */ - struct dma_buf_map vmap_ptr; + struct iosys_map vmap_ptr; /** * @exp_name: @@ -433,8 +433,8 @@ struct dma_buf { /** @poll: for userspace poll support */ wait_queue_head_t poll; - /** @cb_excl: for userspace poll support */ - /** @cb_shared: for userspace poll support */ + /** @cb_in: for userspace poll support */ + /** @cb_out: for userspace poll support */ struct dma_buf_poll_cb_t { struct dma_fence_cb cb; wait_queue_head_t *poll; @@ -628,6 +628,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dma_buf, int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); -int dma_buf_vmap(struct dma_buf *dmabuf, struct dma_buf_map *map); -void dma_buf_vunmap(struct dma_buf *dmabuf, struct dma_buf_map *map); +int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map); +void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map); #endif /* __DMA_BUF_H__ */ diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index 303dd712220f..fec374f69e12 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -45,19 +45,6 @@ struct dma_fence_array { struct irq_work work; }; -extern const struct dma_fence_ops dma_fence_array_ops; - -/** - * dma_fence_is_array - check if a fence is from the array subsclass - * @fence: fence to test - * - * Return true if it is a dma_fence_array and false otherwise. - */ -static inline bool dma_fence_is_array(struct dma_fence *fence) -{ - return fence->ops == &dma_fence_array_ops; -} - /** * to_dma_fence_array - cast a fence to a dma_fence_array * @fence: fence to cast to a dma_fence_array @@ -68,7 +55,7 @@ static inline bool dma_fence_is_array(struct dma_fence *fence) static inline struct dma_fence_array * to_dma_fence_array(struct dma_fence *fence) { - if (fence->ops != &dma_fence_array_ops) + if (!fence || !dma_fence_is_array(fence)) return NULL; return container_of(fence, struct dma_fence_array, base); diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 54fe3443fd2c..10d51bcdf7b7 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -49,7 +49,6 @@ struct dma_fence_chain { spinlock_t lock; }; -extern const struct dma_fence_ops dma_fence_chain_ops; /** * to_dma_fence_chain - cast a fence to a dma_fence_chain @@ -61,13 +60,28 @@ extern const struct dma_fence_ops dma_fence_chain_ops; static inline struct dma_fence_chain * to_dma_fence_chain(struct dma_fence *fence) { - if (!fence || fence->ops != &dma_fence_chain_ops) + if (!fence || !dma_fence_is_chain(fence)) return NULL; return container_of(fence, struct dma_fence_chain, base); } /** + * dma_fence_chain_contained - return the contained fence + * @fence: the fence to test + * + * If the fence is a dma_fence_chain the function returns the fence contained + * inside the chain object, otherwise it returns the fence itself. + */ +static inline struct dma_fence * +dma_fence_chain_contained(struct dma_fence *fence) +{ + struct dma_fence_chain *chain = to_dma_fence_chain(fence); + + return chain ? chain->fence : fence; +} + +/** * dma_fence_chain_alloc * * Returns a new struct dma_fence_chain object or NULL on failure. diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index a706b7bf51d7..775cdc0b4f24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -264,6 +264,7 @@ void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, void dma_fence_release(struct kref *kref); void dma_fence_free(struct dma_fence *fence); +void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq); /** * dma_fence_put - decreases refcount of the fence @@ -586,4 +587,42 @@ struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); +extern const struct dma_fence_ops dma_fence_array_ops; +extern const struct dma_fence_ops dma_fence_chain_ops; + +/** + * dma_fence_is_array - check if a fence is from the array subclass + * @fence: the fence to test + * + * Return true if it is a dma_fence_array and false otherwise. + */ +static inline bool dma_fence_is_array(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_array_ops; +} + +/** + * dma_fence_is_chain - check if a fence is from the chain subclass + * @fence: the fence to test + * + * Return true if it is a dma_fence_chain and false otherwise. + */ +static inline bool dma_fence_is_chain(struct dma_fence *fence) +{ + return fence->ops == &dma_fence_chain_ops; +} + +/** + * dma_fence_is_container - check if a fence is a container for other fences + * @fence: the fence to test + * + * Return true if this fence is a container for other fences, false otherwise. + * This is important since we can't build up large fence structure or otherwise + * we run into recursion during operation on those fences. + */ +static inline bool dma_fence_is_container(struct dma_fence *fence) +{ + return dma_fence_is_array(fence) || dma_fence_is_chain(fence); +} + #endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index dbd235ab447f..afdfdfac729f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -153,6 +153,13 @@ struct dma_resv { * struct dma_resv_iter - current position into the dma_resv fences * * Don't touch this directly in the driver, use the accessor function instead. + * + * IMPORTANT + * + * When using the lockless iterators like dma_resv_iter_next_unlocked() or + * dma_resv_for_each_fence_unlocked() beware that the iterator can be restarted. + * Code which accumulates statistics or similar needs to check for this with + * dma_resv_iter_is_restarted(). */ struct dma_resv_iter { /** @obj: The dma_resv object we iterate over */ @@ -243,7 +250,11 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * &dma_resv.lock and using RCU instead. The cursor needs to be initialized * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside * the iterator a reference to the dma_fence is held and the RCU lock dropped. - * When the dma_resv is modified the iteration starts over again. + * + * Beware that the iterator can be restarted when the struct dma_resv for + * @cursor is modified. Code which accumulates statistics or similar needs to + * check for this with dma_resv_iter_is_restarted(). For this reason prefer the + * lock iterator dma_resv_for_each_fence() whenever possible. */ #define dma_resv_for_each_fence_unlocked(cursor, fence) \ for (fence = dma_resv_iter_first_unlocked(cursor); \ @@ -441,32 +452,6 @@ dma_resv_excl_fence(struct dma_resv *obj) } /** - * dma_resv_get_excl_unlocked - get the reservation object's - * exclusive fence, without lock held. - * @obj: the reservation object - * - * If there is an exclusive fence, this atomically increments it's - * reference count and returns it. - * - * RETURNS - * The exclusive fence or NULL if none - */ -static inline struct dma_fence * -dma_resv_get_excl_unlocked(struct dma_resv *obj) -{ - struct dma_fence *fence; - - if (!rcu_access_pointer(obj->fence_excl)) - return NULL; - - rcu_read_lock(); - fence = dma_fence_get_rcu_safe(&obj->fence_excl); - rcu_read_unlock(); - - return fence; -} - -/** * dma_resv_shared_list - get the reservation object's shared fence list * @obj: the reservation object * @@ -484,11 +469,12 @@ void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); -int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, - unsigned *pshared_count, struct dma_fence ***pshared); +int dma_resv_get_fences(struct dma_resv *obj, bool write, + unsigned int *num_fences, struct dma_fence ***fences); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, unsigned long timeout); bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); +void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq); #endif /* _LINUX_RESERVATION_H */ diff --git a/include/linux/dma/qcom_adm.h b/include/linux/dma/qcom_adm.h new file mode 100644 index 000000000000..af20df674f0c --- /dev/null +++ b/include/linux/dma/qcom_adm.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_DMA_QCOM_ADM_H +#define __LINUX_DMA_QCOM_ADM_H + +#include <linux/types.h> + +struct qcom_adm_peripheral_config { + u32 crci; + u32 mux; +}; + +#endif /* __LINUX_DMA_QCOM_ADM_H */ diff --git a/include/linux/dma/xilinx_dpdma.h b/include/linux/dma/xilinx_dpdma.h new file mode 100644 index 000000000000..02a4adf8921b --- /dev/null +++ b/include/linux/dma/xilinx_dpdma.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_DMA_XILINX_DPDMA_H +#define __LINUX_DMA_XILINX_DPDMA_H + +#include <linux/types.h> + +struct xilinx_dpdma_peripheral_config { + bool video_group; +}; + +#endif /* __LINUX_DMA_XILINX_DPDMA_H */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9000f3ffce8b..842d4f7ca752 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -50,6 +50,7 @@ enum dma_status { */ enum dma_transaction_type { DMA_MEMCPY, + DMA_MEMCPY_SG, DMA_XOR, DMA_PQ, DMA_XOR_VAL, @@ -418,9 +419,6 @@ enum dma_slave_buswidth { * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill * with 'true' if peripheral should be flow controller. Direction will be * selected at Runtime. - * @slave_id: Slave requester id. Only valid for slave channels. The dma - * slave peripheral will have unique id as dma requester which need to be - * pass as slave config. * @peripheral_config: peripheral configuration for programming peripheral * for dmaengine transfer * @peripheral_size: peripheral configuration buffer size @@ -448,7 +446,6 @@ struct dma_slave_config { u32 src_port_window_size; u32 dst_port_window_size; bool device_fc; - unsigned int slave_id; void *peripheral_config; size_t peripheral_size; }; @@ -891,6 +888,11 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)( struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memcpy_sg)( + struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_xor)( struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags); @@ -1051,6 +1053,20 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( len, flags); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy_sg( + struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy_sg) + return NULL; + + return chan->device->device_prep_dma_memcpy_sg(chan, dst_sg, dst_nents, + src_sg, src_nents, + flags); +} + static inline bool dmaengine_is_metadata_mode_supported(struct dma_chan *chan, enum dma_desc_metadata_mode mode) { diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index 0aad774beaec..b1d26f9f1c9f 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -26,10 +26,9 @@ struct dnotify_struct { FS_MODIFY | FS_MODIFY_CHILD |\ FS_ACCESS | FS_ACCESS_CHILD |\ FS_ATTRIB | FS_ATTRIB_CHILD |\ - FS_CREATE | FS_DN_RENAME |\ + FS_CREATE | FS_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) -extern int dir_notify_enable; extern void dnotify_flush(struct file *, fl_owner_t); extern int fcntl_dirnotify(int, struct file *, unsigned long); diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 254b165f2b44..3ed117e299ec 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -7,6 +7,7 @@ #include <linux/refcount.h> #include <linux/types.h> +#include <net/dsa.h> struct dsa_switch; struct dsa_port; @@ -31,33 +32,29 @@ int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci); +int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge); -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); +void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge); -int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num); +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); -void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid); -u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, + int vbid); -u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); +u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num); -u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp); +u16 dsa_tag_8021q_standalone_vid(const struct dsa_port *dp); int dsa_8021q_rx_switch_id(u16 vid); int dsa_8021q_rx_source_port(u16 vid); -bool vid_is_dsa_8021q_rxvlan(u16 vid); - -bool vid_is_dsa_8021q_txvlan(u16 vid); - bool vid_is_dsa_8021q(u16 vid); #endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h index 5a3470bcc8a7..b8fef35591aa 100644 --- a/include/linux/dsa/loop.h +++ b/include/linux/dsa/loop.h @@ -2,6 +2,7 @@ #ifndef DSA_LOOP_H #define DSA_LOOP_H +#include <linux/if_vlan.h> #include <linux/types.h> #include <linux/ethtool.h> #include <net/dsa.h> diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 7ee708ad7df2..dca2969015d8 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -8,6 +8,7 @@ #include <linux/kthread.h> #include <linux/packing.h> #include <linux/skbuff.h> +#include <net/dsa.h> struct ocelot_skb_cb { struct sk_buff *clone; @@ -168,11 +169,18 @@ struct felix_deferred_xmit_work { struct kthread_work work; }; -struct felix_port { +struct ocelot_8021q_tagger_data { void (*xmit_work_fn)(struct kthread_work *work); - struct kthread_worker *xmit_worker; }; +static inline struct ocelot_8021q_tagger_data * +ocelot_8021q_tagger_data(struct dsa_switch *ds) +{ + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_OCELOT_8021Q); + + return ds->tagger_data; +} + static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) { packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e6c78be40bde..159e43171ccc 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -35,23 +35,26 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull -#define SJA1105_HWTS_RX_EN 0 +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; -/* Global tagger data: each struct sja1105_port has a reference to - * the structure defined in struct sja1105_private. - */ +struct sja1105_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + +/* Global tagger data */ struct sja1105_tagger_data { - struct sk_buff *stampable_skb; - /* Protects concurrent access to the meta state machine - * from taggers running on multiple ports on SMP systems - */ - spinlock_t meta_lock; - unsigned long state; - u8 ts_id; - /* Used on SJA1110 where meta frames are generated only for - * 2-step TX timestamps - */ - struct sk_buff_head skb_txtstamp_queue; + /* Tagger to switch */ + void (*xmit_work_fn)(struct kthread_work *work); + void (*meta_tstamp_handler)(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + /* Switch to tagger */ + bool (*rxtstamp_get_state)(struct dsa_switch *ds); + void (*rxtstamp_set_state)(struct dsa_switch *ds, bool on); }; struct sja1105_skb_cb { @@ -64,32 +67,13 @@ struct sja1105_skb_cb { #define SJA1105_SKB_CB(skb) \ ((struct sja1105_skb_cb *)((skb)->cb)) -struct sja1105_port { - struct kthread_worker *xmit_worker; - struct kthread_work xmit_work; - struct sk_buff_head xmit_queue; - struct sja1105_tagger_data *data; - bool hwts_tx_en; -}; - -/* Timestamps are in units of 8 ns clock ticks (equivalent to - * a fixed 125 MHz clock). - */ -#define SJA1105_TICK_NS 8 - -static inline s64 ns_to_sja1105_ticks(s64 ns) +static inline struct sja1105_tagger_data * +sja1105_tagger_data(struct dsa_switch *ds) { - return ns / SJA1105_TICK_NS; -} + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1105 && + ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1110); -static inline s64 sja1105_ticks_to_ns(s64 ticks) -{ - return ticks * SJA1105_TICK_NS; -} - -static inline bool dsa_port_is_sja1105(struct dsa_port *dp) -{ - return true; + return ds->tagger_data; } #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h new file mode 100644 index 000000000000..4359fb0221cf --- /dev/null +++ b/include/linux/dsa/tag_qca.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __TAG_QCA_H +#define __TAG_QCA_H + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION GENMASK(15, 14) +#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11) +#define QCA_HDR_RECV_TYPE GENMASK(10, 6) +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) + +/* Packet type for recv */ +#define QCA_HDR_RECV_TYPE_NORMAL 0x0 +#define QCA_HDR_RECV_TYPE_MIB 0x1 +#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2 + +#define QCA_HDR_XMIT_VERSION GENMASK(15, 14) +#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) +#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) + +/* Packet type for xmit */ +#define QCA_HDR_XMIT_TYPE_NORMAL 0x0 +#define QCA_HDR_XMIT_TYPE_RW_REG 0x1 + +/* Check code for a valid mgmt packet. Switch will ignore the packet + * with this wrong. + */ +#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5 + +/* Specific define for in-band MDIO read/write with Ethernet packet */ +#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */ +#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */ +#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */ +#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \ + QCA_HDR_MGMT_COMMAND_LEN + \ + QCA_HDR_MGMT_DATA1_LEN) + +#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */ +#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */ + +#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \ + QCA_HDR_LEN + \ + QCA_HDR_MGMT_DATA2_LEN + \ + QCA_HDR_MGMT_PADDING_LEN) + +#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */ +#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */ +#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */ +#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */ +#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */ + +/* Special struct emulating a Ethernet header */ +struct qca_mgmt_ethhdr { + u32 command; /* command bit 31:0 */ + u32 seq; /* seq 63:32 */ + u32 mdio_data; /* first 4byte mdio */ + __be16 hdr; /* qca hdr */ +} __packed; + +enum mdio_cmd { + MDIO_WRITE = 0x0, + MDIO_READ +}; + +struct mib_ethhdr { + u32 data[3]; /* first 3 mib counter */ + __be16 hdr; /* qca hdr */ +} __packed; + +struct qca_tagger_data { + void (*rw_reg_ack_handler)(struct dsa_switch *ds, + struct sk_buff *skb); + void (*mib_autocast_handler)(struct dsa_switch *ds, + struct sk_buff *skb); +}; + +#endif /* __TAG_QCA_H */ diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 2890f6370eb9..a4a13514b730 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -32,28 +32,25 @@ struct dtpm_ops { void (*release)(struct dtpm *); }; -typedef int (*dtpm_init_t)(void); +struct device_node; -struct dtpm_descr { - dtpm_init_t init; +struct dtpm_subsys_ops { + const char *name; + int (*init)(void); + void (*exit)(void); + int (*setup)(struct dtpm *, struct device_node *); }; -/* Init section thermal table */ -extern struct dtpm_descr __dtpm_table[]; -extern struct dtpm_descr __dtpm_table_end[]; - -#define DTPM_TABLE_ENTRY(name, __init) \ - static struct dtpm_descr __dtpm_table_entry_##name \ - __used __section("__dtpm_table") = { \ - .init = __init, \ - } - -#define DTPM_DECLARE(name, init) DTPM_TABLE_ENTRY(name, init) +enum DTPM_NODE_TYPE { + DTPM_NODE_VIRTUAL = 0, + DTPM_NODE_DT, +}; -#define for_each_dtpm_table(__dtpm) \ - for (__dtpm = __dtpm_table; \ - __dtpm < __dtpm_table_end; \ - __dtpm++) +struct dtpm_node { + enum DTPM_NODE_TYPE type; + const char *name; + struct dtpm_node *parent; +}; static inline struct dtpm *to_dtpm(struct powercap_zone *zone) { @@ -70,6 +67,7 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); -int dtpm_register_cpu(struct dtpm *parent); +int dtpm_create_hierarchy(struct of_device_id *dtpm_match_table); +void dtpm_destroy_hierarchy(void); #endif diff --git a/include/linux/edac.h b/include/linux/edac.h index 4207d06996a4..e730b3468719 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -182,6 +182,8 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_LRDDR4: Load-Reduced DDR4 memory. * @MEM_LPDDR4: Low-Power DDR4 memory. * @MEM_DDR5: Unbuffered DDR5 RAM + * @MEM_RDDR5: Registered DDR5 RAM + * @MEM_LRDDR5: Load-Reduced DDR5 memory. * @MEM_NVDIMM: Non-volatile RAM * @MEM_WIO2: Wide I/O 2. * @MEM_HBM2: High bandwidth Memory Gen 2. @@ -211,6 +213,8 @@ enum mem_type { MEM_LRDDR4, MEM_LPDDR4, MEM_DDR5, + MEM_RDDR5, + MEM_LRDDR5, MEM_NVDIMM, MEM_WIO2, MEM_HBM2, @@ -239,6 +243,8 @@ enum mem_type { #define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) #define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4) #define MEM_FLAG_DDR5 BIT(MEM_DDR5) +#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) +#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) #define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) #define MEM_FLAG_HBM2 BIT(MEM_HBM2) diff --git a/include/linux/efi.h b/include/linux/efi.h index dbd39b20e034..ccd4d3f91c98 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -148,6 +148,52 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER */ +struct efi_manage_capsule_header { + u32 ver; + u16 emb_drv_cnt; + u16 payload_cnt; + /* + * Variable-size array of the size given by the sum of + * emb_drv_cnt and payload_cnt. + */ + u64 offset_list[]; +} __packed; + +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER */ +struct efi_manage_capsule_image_header { + u32 ver; + efi_guid_t image_type_id; + u8 image_index; + u8 reserved_bytes[3]; + u32 image_size; + u32 vendor_code_size; + /* hw_ins was introduced in version 2 */ + u64 hw_ins; + /* capsule_support was introduced in version 3 */ + u64 capsule_support; +} __packed; + +/* WIN_CERTIFICATE */ +struct win_cert { + u32 len; + u16 rev; + u16 cert_type; +}; + +/* WIN_CERTIFICATE_UEFI_GUID */ +struct win_cert_uefi_guid { + struct win_cert hdr; + efi_guid_t cert_type; + u8 cert_data[]; +}; + +/* EFI_FIRMWARE_IMAGE_AUTHENTICATION */ +struct efi_image_auth { + u64 mon_count; + struct win_cert_uefi_guid auth_info; +}; + /* * EFI capsule flags */ @@ -570,8 +616,8 @@ extern struct efi { unsigned long flags; } efi; -#define EFI_RT_SUPPORTED_GET_TIME 0x0001 -#define EFI_RT_SUPPORTED_SET_TIME 0x0002 +#define EFI_RT_SUPPORTED_GET_TIME 0x0001 +#define EFI_RT_SUPPORTED_SET_TIME 0x0002 #define EFI_RT_SUPPORTED_GET_WAKEUP_TIME 0x0004 #define EFI_RT_SUPPORTED_SET_WAKEUP_TIME 0x0008 #define EFI_RT_SUPPORTED_GET_VARIABLE 0x0010 @@ -838,7 +884,7 @@ extern int efi_status_to_err(efi_status_t status); #define EFI_VARIABLE_TIME_BASED_AUTHENTICATED_WRITE_ACCESS 0x0000000000000020 #define EFI_VARIABLE_APPEND_WRITE 0x0000000000000040 -#define EFI_VARIABLE_MASK (EFI_VARIABLE_NON_VOLATILE | \ +#define EFI_VARIABLE_MASK (EFI_VARIABLE_NON_VOLATILE | \ EFI_VARIABLE_BOOTSERVICE_ACCESS | \ EFI_VARIABLE_RUNTIME_ACCESS | \ EFI_VARIABLE_HARDWARE_ERROR_RECORD | \ @@ -1283,4 +1329,10 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( } #endif +#ifdef CONFIG_SYSFB +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); +#else +static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } +#endif + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index e272c3d452ce..54feb64e9b5d 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -43,6 +43,11 @@ struct compat_elf_prpsinfo __compat_uid_t pr_uid; __compat_gid_t pr_gid; compat_pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; char pr_psargs[ELF_PRARGSZ]; }; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 957ebec35aad..f8e206e82476 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -65,6 +65,11 @@ struct elf_prpsinfo __kernel_gid_t pr_gid; pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; /* Lots missing */ + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; /* filename of executable */ char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ }; @@ -109,7 +114,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg #endif } -#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64) +#ifdef CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS /* * These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out * extra segments containing the gate DSO contents. Dumping its @@ -144,6 +149,6 @@ static inline size_t elf_core_extra_data_size(void) { return 0; } -#endif +#endif /* CONFIG_ARCH_BINFMT_ELF_EXTRA_PHDRS */ #endif /* _LINUX_ELFCORE_H */ diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 6377adc3b78d..9f3c400bc52d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -116,6 +116,7 @@ struct em_data_callback { struct device *dev); }; #define EM_DATA_CB(_active_power_cb) { .active_power = &_active_power_cb } +#define EM_SET_ACTIVE_POWER_CB(em_cb, cb) ((em_cb).active_power = cb) struct em_perf_domain *em_cpu_get(int cpu); struct em_perf_domain *em_pd_get(struct device *dev); @@ -264,6 +265,7 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd) #else struct em_data_callback {}; #define EM_DATA_CB(_active_power_cb) { } +#define EM_SET_ACTIVE_POWER_CB(em_cb, cb) do { } while (0) static inline int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 2e2b8d6140ed..ab78bd4c2eb0 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -3,7 +3,7 @@ #define __LINUX_ENTRYCOMMON_H #include <linux/static_call_types.h> -#include <linux/tracehook.h> +#include <linux/ptrace.h> #include <linux/syscalls.h> #include <linux/seccomp.h> #include <linux/sched.h> @@ -80,26 +80,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} #endif /** - * arch_syscall_enter_tracehook - Wrapper around tracehook_report_syscall_entry() - * @regs: Pointer to currents pt_regs - * - * Returns: 0 on success or an error code to skip the syscall. - * - * Defaults to tracehook_report_syscall_entry(). Can be replaced by - * architecture specific code. - * - * Invoked from syscall_enter_from_user_mode() - */ -static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs); - -#ifndef arch_syscall_enter_tracehook -static inline __must_check int arch_syscall_enter_tracehook(struct pt_regs *regs) -{ - return tracehook_report_syscall_entry(regs); -} -#endif - -/** * enter_from_user_mode - Establish state when coming from user mode * * Syscall/interrupt entry disables interrupts, but user mode is traced as @@ -157,7 +137,7 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); * It handles the following work items: * * 1) syscall_work flag dependent invocations of - * arch_syscall_enter_tracehook(), __secure_computing(), trace_sys_enter() + * ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter() * 2) Invocation of audit_syscall_entry() */ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall); @@ -277,26 +257,7 @@ static __always_inline void arch_exit_to_user_mode(void) { } * * Invoked from exit_to_user_mode_loop(). */ -void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal); - -/** - * arch_syscall_exit_tracehook - Wrapper around tracehook_report_syscall_exit() - * @regs: Pointer to currents pt_regs - * @step: Indicator for single step - * - * Defaults to tracehook_report_syscall_exit(). Can be replaced by - * architecture specific code. - * - * Invoked from syscall_exit_to_user_mode() - */ -static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step); - -#ifndef arch_syscall_exit_tracehook -static inline void arch_syscall_exit_tracehook(struct pt_regs *regs, bool step) -{ - tracehook_report_syscall_exit(regs, step); -} -#endif +void arch_do_signal_or_restart(struct pt_regs *regs); /** * exit_to_user_mode - Fixup state when exiting to user mode @@ -347,7 +308,7 @@ void syscall_exit_to_user_mode_work(struct pt_regs *regs); * - rseq syscall exit * - audit * - syscall tracing - * - tracehook (single stepping) + * - ptrace (single stepping) * * 2) Preparatory work * - Exit to user mode loop (common TIF handling). Invokes @@ -454,10 +415,21 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * * Conditional reschedule with additional sanity checks. */ -void irqentry_exit_cond_resched(void); +void raw_irqentry_exit_cond_resched(void); #ifdef CONFIG_PREEMPT_DYNAMIC -DECLARE_STATIC_CALL(irqentry_exit_cond_resched, irqentry_exit_cond_resched); +#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +#define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched +#define irqentry_exit_cond_resched_dynamic_disabled NULL +DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); +#define irqentry_exit_cond_resched() static_call(irqentry_exit_cond_resched)() +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); +void dynamic_irqentry_exit_cond_resched(void); +#define irqentry_exit_cond_resched() dynamic_irqentry_exit_cond_resched() #endif +#else /* CONFIG_PREEMPT_DYNAMIC */ +#define irqentry_exit_cond_resched() raw_irqentry_exit_cond_resched() +#endif /* CONFIG_PREEMPT_DYNAMIC */ /** * irqentry_exit - Handle return from exception that used irqentry_enter() diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 0d7865a0731c..6813171afccb 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -3,7 +3,7 @@ #define __LINUX_ENTRYKVM_H #include <linux/static_call_types.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> #include <linux/syscalls.h> #include <linux/seccomp.h> #include <linux/sched.h> @@ -75,7 +75,7 @@ static inline void xfer_to_guest_mode_prepare(void) */ static inline bool __xfer_to_guest_mode_work_pending(void) { - unsigned long ti_work = READ_ONCE(current_thread_info()->flags); + unsigned long ti_work = read_thread_flags(); return !!(ti_work & XFER_TO_GUEST_MODE_WORK); } diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad71cc90b37..92b10e67d5f8 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -134,7 +134,7 @@ static inline bool is_multicast_ether_addr(const u8 *addr) #endif } -static inline bool is_multicast_ether_addr_64bits(const u8 addr[6+2]) +static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN @@ -372,8 +372,7 @@ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ -static inline bool ether_addr_equal_64bits(const u8 addr1[6+2], - const u8 addr2[6+2]) +static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 845a0ffc16ee..4af58459a1e7 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -67,6 +67,28 @@ enum { ETH_RSS_HASH_FUNCS_COUNT }; +/** + * struct kernel_ethtool_ringparam - RX/TX ring configuration + * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers + * @cqe_size: Size of TX/RX completion queue event + */ +struct kernel_ethtool_ringparam { + u32 rx_buf_len; + u8 tcp_data_split; + u32 cqe_size; +}; + +/** + * enum ethtool_supported_ring_param - indicator caps for setting ring params + * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + * @ETHTOOL_RING_USE_CQE_SIZE: capture for setting cqe_size + */ +enum ethtool_supported_ring_param { + ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), + ETHTOOL_RING_USE_CQE_SIZE = BIT(1), +}; + #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) #define __ETH_RSS_HASH(name) __ETH_RSS_HASH_BIT(ETH_RSS_HASH_##name##_BIT) @@ -95,7 +117,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; enum ethtool_link_ext_substate_module module; - u8 __link_ext_substate; + u32 __link_ext_substate; }; }; @@ -432,6 +454,7 @@ struct ethtool_module_power_mode_params { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. + * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -613,6 +636,7 @@ struct ethtool_module_power_mode_params { struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; + u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); @@ -638,9 +662,13 @@ struct ethtool_ops { struct kernel_ethtool_coalesce *, struct netlink_ext_ack *); void (*get_ringparam)(struct net_device *, - struct ethtool_ringparam *); + struct ethtool_ringparam *, + struct kernel_ethtool_ringparam *, + struct netlink_ext_ack *); int (*set_ringparam)(struct net_device *, - struct ethtool_ringparam *); + struct ethtool_ringparam *, + struct kernel_ethtool_ringparam *, + struct netlink_ext_ack *); void (*get_pause_stats)(struct net_device *dev, struct ethtool_pause_stats *pause_stats); void (*get_pauseparam)(struct net_device *, diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 3260fe714846..fe848901fcc3 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -221,8 +221,6 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ -#define EXPORT_OP_SYNC_LOCKS (0x20) /* Filesystem can't do - asychronous blocking locks */ unsigned long flags; }; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 616af2ea20f3..419cadcd7ff5 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,8 +5,6 @@ #include <linux/sysctl.h> #include <uapi/linux/fanotify.h> -extern struct ctl_table fanotify_table[]; /* for sysctl */ - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) @@ -25,7 +23,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FANOTIFY_PERM_CLASSES) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) #define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) @@ -82,7 +80,8 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. */ -#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ + FAN_RENAME) /* Events that can be reported with event->fd */ #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index e525f6957c49..2d04f6448cde 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -64,6 +64,8 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name, struct kmem_cache; +bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); + int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); diff --git a/include/linux/fb.h b/include/linux/fb.h index 6f3db99ab990..9a77ab615c36 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -204,6 +204,7 @@ struct fb_pixmap { struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; + bool sort_pagelist; /* sort pagelist by offset */ struct mutex lock; /* mutex that protects the page list */ struct list_head pagelist; /* list of touched pages */ /* callback */ @@ -262,7 +263,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another. Obsolete. */ + /* Copy data from area to another */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); @@ -502,6 +503,7 @@ struct fb_info { } *apertures; bool skip_vt_switch; /* no VT switch on suspend/resume required */ + bool forced_out; /* set when being removed by another driver */ }; static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { @@ -610,6 +612,7 @@ extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); +extern bool is_firmware_framebuffer(struct apertures_struct *a); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); diff --git a/include/linux/filter.h b/include/linux/filter.h index 7f1e88e3e2b5..ed0c0ff42ad5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -548,7 +548,7 @@ struct sock_fprog_kern { #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { - u32 pages; + u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; @@ -566,13 +566,15 @@ struct bpf_prog { gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ - call_get_func_ip:1; /* Do we call get_func_ip() */ + call_get_func_ip:1, /* Do we call get_func_ip() */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ @@ -886,17 +888,8 @@ static inline void bpf_prog_lock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_ro((unsigned long)hdr, hdr->pages); - set_memory_x((unsigned long)hdr, hdr->pages); -} - -static inline struct bpf_binary_header * -bpf_jit_binary_hdr(const struct bpf_prog *fp) -{ - unsigned long real_start = (unsigned long)fp->bpf_func; - unsigned long addr = real_start & PAGE_MASK; - - return (void *)addr; + set_memory_ro((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + set_memory_x((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -1019,6 +1012,10 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); +int xdp_do_redirect_frame(struct net_device *dev, + struct xdp_buff *xdp, + struct xdp_frame *xdpf, + struct bpf_prog *prog); void xdp_do_flush(void); /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as @@ -1027,7 +1024,7 @@ void xdp_do_flush(void); */ #define xdp_do_flush_map xdp_do_flush -void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, @@ -1064,6 +1061,18 @@ void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +struct bpf_binary_header * +bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, + unsigned int alignment, + struct bpf_binary_header **rw_hdr, + u8 **rw_image, + bpf_jit_fill_hole_t bpf_fill_ill_insns); +int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, + struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); +void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, + struct bpf_binary_header *rw_header); + int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); @@ -1352,7 +1361,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); @@ -1371,6 +1383,7 @@ struct bpf_sk_lookup_kern { const struct in6_addr *daddr; } v6; struct sock *selected_sk; + u32 ingress_ifindex; bool no_reuseport; }; @@ -1433,7 +1446,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1449,6 +1462,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, .v4.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; @@ -1471,7 +1485,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const __be16 sport, const struct in6_addr *daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1487,6 +1501,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, .v6.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; diff --git a/include/linux/find.h b/include/linux/find.h new file mode 100644 index 000000000000..5bb6db213bcb --- /dev/null +++ b/include/linux/find.h @@ -0,0 +1,372 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_FIND_H_ +#define __LINUX_FIND_H_ + +#ifndef __LINUX_BITMAP_H +#error only <linux/bitmap.h> can be included directly +#endif + +#include <linux/bitops.h> + +extern unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert, unsigned long le); +extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size); +extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); + +#ifndef find_next_bit +/** + * find_next_bit - find the next set bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); +} +#endif + +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & *addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); +} +#endif + +#ifndef find_next_zero_bit +/** + * find_next_zero_bit - find the next cleared bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number of the next zero bit + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); +} +#endif + +#ifndef find_first_bit +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first set bit. + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_bit(addr, size); +} +#endif + +#ifndef find_first_and_bit +/** + * find_first_and_bit - find the first set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_bit(addr1, addr2, size); +} +#endif + +#ifndef find_first_zero_bit +/** + * find_first_zero_bit - find the first cleared bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first cleared bit. + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit(addr, size); +} +#endif + +#ifndef find_last_bit +/** + * find_last_bit - find the last set bit in a memory region + * @addr: The address to start the search at + * @size: The number of bits to search + * + * Returns the bit number of the last set bit, or size. + */ +static inline +unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __fls(val) : size; + } + + return _find_last_bit(addr, size); +} +#endif + +/** + * find_next_clump8 - find next 8-bit clump with set bits in a memory region + * @clump: location to store copy of found clump + * @addr: address to base the search on + * @size: bitmap size in number of bits + * @offset: bit offset at which to start searching + * + * Returns the bit offset for the next set clump; the found clump value is + * copied to the location pointed by @clump. If no bits are set, returns @size. + */ +extern unsigned long find_next_clump8(unsigned long *clump, + const unsigned long *addr, + unsigned long size, unsigned long offset); + +#define find_first_clump8(clump, bits, size) \ + find_next_clump8((clump), (bits), (size), 0) + +#if defined(__LITTLE_ENDIAN) + +static inline unsigned long find_next_zero_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} + +static inline unsigned long find_next_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} + +static inline unsigned long find_first_zero_bit_le(const void *addr, + unsigned long size) +{ + return find_first_zero_bit(addr, size); +} + +#elif defined(__BIG_ENDIAN) + +#ifndef find_next_zero_bit_le +static inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); +} +#endif + +#ifndef find_next_bit_le +static inline +unsigned long find_next_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, NULL, size, offset, 0UL, 1); +} +#endif + +#ifndef find_first_zero_bit_le +#define find_first_zero_bit_le(addr, size) \ + find_next_zero_bit_le((addr), (size), 0) +#endif + +#else +#error "Please fix <asm/byteorder.h>" +#endif + +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), 0); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_from(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +#define for_each_clear_bit(bit, addr, size) \ + for ((bit) = find_next_zero_bit((addr), (size), 0); \ + (bit) < (size); \ + (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + +/* same as for_each_clear_bit() but use bit as value to start with */ +#define for_each_clear_bit_from(bit, addr, size) \ + for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + +/** + * for_each_set_bitrange - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit) + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange(b, e, addr, size) \ + for ((b) = find_next_bit((addr), (size), 0), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_bit((addr), (size), (e) + 1), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1)) + +/** + * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange_from(b, e, addr, size) \ + for ((b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_bit((addr), (size), (e) + 1), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1)) + +/** + * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first unset bit) + * @e: bit offset of end of current bitrange (first set bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange(b, e, addr, size) \ + for ((b) = find_next_zero_bit((addr), (size), 0), \ + (e) = find_next_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_zero_bit((addr), (size), (e) + 1), \ + (e) = find_next_bit((addr), (size), (b) + 1)) + +/** + * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange_from(b, e, addr, size) \ + for ((b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_zero_bit((addr), (size), (e) + 1), \ + (e) = find_next_bit((addr), (size), (b) + 1)) + +/** + * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits + * @start: bit offset to start search and to store the current iteration offset + * @clump: location to store copy of current 8-bit clump + * @bits: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_clump8(start, clump, bits, size) \ + for ((start) = find_first_clump8(&(clump), (bits), (size)); \ + (start) < (size); \ + (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) + +#endif /*__LINUX_FIND_H_ */ diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 3b057dfc8284..ec2ccfebef65 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -34,7 +34,7 @@ static inline bool firmware_request_builtin(struct firmware *fw, } #endif -#if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) +#if IS_REACHABLE(CONFIG_FW_LOADER) int request_firmware(const struct firmware **fw, const char *name, struct device *device); int firmware_request_nowarn(const struct firmware **fw, const char *name, diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 9ad9eaaaa552..38b4da3ddfe4 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -11,6 +11,11 @@ #ifndef __CS_DSP_H #define __CS_DSP_H +#include <linux/device.h> +#include <linux/firmware.h> +#include <linux/list.h> +#include <linux/regmap.h> + #define CS_ADSP2_REGION_0 BIT(0) #define CS_ADSP2_REGION_1 BIT(1) #define CS_ADSP2_REGION_2 BIT(2) @@ -49,12 +54,14 @@ struct cs_dsp_region { * struct cs_dsp_alg_region - Describes a logical algorithm region in DSP address space * @list: List node for internal use * @alg: Algorithm id + * @ver: Expected algorithm version * @type: Memory region type * @base: Address of region */ struct cs_dsp_alg_region { struct list_head list; unsigned int alg; + unsigned int ver; int type; unsigned int base; }; @@ -69,8 +76,8 @@ struct cs_dsp_alg_region { * @enabled: Flag indicating whether control is enabled * @list: List node for internal use * @cache: Cached value of the control - * @offset: Offset of control within alg_region - * @len: Length of the cached value + * @offset: Offset of control within alg_region in words + * @len: Length of the cached value in bytes * @set: Flag indicating the value has been written by the user * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h * @type: One of the WMFW_CTL_TYPE_ control types defined in wmfw.h @@ -180,7 +187,8 @@ struct cs_dsp { * struct cs_dsp_client_ops - client callbacks * @control_add: Called under the pwr_lock when a control is created * @control_remove: Called under the pwr_lock when a control is destroyed - * @post_run: Called under the pwr_lock by cs_dsp_run() + * @pre_run: Called under the pwr_lock by cs_dsp_run() before the core is started + * @post_run: Called under the pwr_lock by cs_dsp_run() after the core is started * @post_stop: Called under the pwr_lock by cs_dsp_stop() * @watchdog_expired: Called when a watchdog expiry is detected * @@ -190,6 +198,7 @@ struct cs_dsp { struct cs_dsp_client_ops { int (*control_add)(struct cs_dsp_coeff_ctl *ctl); void (*control_remove)(struct cs_dsp_coeff_ctl *ctl); + int (*pre_run)(struct cs_dsp *dsp); int (*post_run)(struct cs_dsp *dsp); void (*post_stop)(struct cs_dsp *dsp); void (*watchdog_expired)(struct cs_dsp *dsp); @@ -223,8 +232,10 @@ void cs_dsp_init_debugfs(struct cs_dsp *dsp, struct dentry *debugfs_root); void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); -int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_t len); -int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len); +int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + const void *buf, size_t len); +int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + void *buf, size_t len); struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg); diff --git a/include/linux/firmware/cirrus/wmfw.h b/include/linux/firmware/cirrus/wmfw.h index a19bf7c6fc8b..74e5a4f6c13a 100644 --- a/include/linux/firmware/cirrus/wmfw.h +++ b/include/linux/firmware/cirrus/wmfw.h @@ -29,6 +29,7 @@ #define WMFW_CTL_TYPE_ACKED 0x1000 /* acked control */ #define WMFW_CTL_TYPE_HOSTEVENT 0x1001 /* event control */ #define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */ +#define WMFW_CTL_TYPE_FWEVENT 0x1004 /* firmware event control */ struct wmfw_header { char magic[4]; diff --git a/include/linux/firmware/imx/svc/rm.h b/include/linux/firmware/imx/svc/rm.h index 456b6a59d29b..31456f897aa9 100644 --- a/include/linux/firmware/imx/svc/rm.h +++ b/include/linux/firmware/imx/svc/rm.h @@ -59,11 +59,16 @@ enum imx_sc_rm_func { #if IS_ENABLED(CONFIG_IMX_SCU) bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource); +int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt); #else static inline bool imx_sc_rm_is_resource_owned(struct imx_sc_ipc *ipc, u16 resource) { return true; } +static inline int imx_sc_rm_get_resource_owner(struct imx_sc_ipc *ipc, u16 resource, u8 *pt) +{ + return -EOPNOTSUPP; +} #endif #endif diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index c3e5ab014caf..aad497a9ad8b 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -321,8 +321,6 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_ECC_DBE \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE) -#endif - /** * Request INTEL_SIP_SMC_RSU_NOTIFY * @@ -404,3 +402,22 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY 18 #define INTEL_SIP_SMC_RSU_MAX_RETRY \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_MAX_RETRY) + +/** + * Request INTEL_SIP_SMC_FIRMWARE_VERSION + * + * Sync call used to query the version of running firmware + * + * Call register usage: + * a0 INTEL_SIP_SMC_FIRMWARE_VERSION + * a1-a7 not used + * + * Return status: + * a0 INTEL_SIP_SMC_STATUS_OK or INTEL_SIP_SMC_STATUS_ERROR + * a1 running firmware version + */ +#define INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION 31 +#define INTEL_SIP_SMC_FIRMWARE_VERSION \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION) + +#endif diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index 19781b0f6429..18c1841fdb1f 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -104,6 +104,9 @@ struct stratix10_svc_chan; * * @COMMAND_RSU_DCMF_VERSION: query firmware for the DCMF version, return status * is SVC_STATUS_OK or SVC_STATUS_ERROR + * + * @COMMAND_FIRMWARE_VERSION: query running firmware version, return status + * is SVC_STATUS_OK or SVC_STATUS_ERROR */ enum stratix10_svc_command_code { COMMAND_NOOP = 0, @@ -117,6 +120,7 @@ enum stratix10_svc_command_code { COMMAND_RSU_RETRY, COMMAND_RSU_MAX_RETRY, COMMAND_RSU_DCMF_VERSION, + COMMAND_FIRMWARE_VERSION, }; /** diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h new file mode 100644 index 000000000000..3f87c4929d21 --- /dev/null +++ b/include/linux/firmware/xlnx-event-manager.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _FIRMWARE_XLNX_EVENT_MANAGER_H_ +#define _FIRMWARE_XLNX_EVENT_MANAGER_H_ + +#include <linux/firmware/xlnx-zynqmp.h> + +#define CB_MAX_PAYLOAD_SIZE (4U) /*In payload maximum 32bytes */ + +/************************** Exported Function *****************************/ + +typedef void (*event_cb_func_t)(const u32 *payload, void *data); + +#if IS_REACHABLE(CONFIG_XLNX_EVENT_MANAGER) +int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data); + +int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, event_cb_func_t cb_fun); +#else +static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data) +{ + return -ENODEV; +} + +static inline int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, event_cb_func_t cb_fun) +{ + return -ENODEV; +} +#endif + +#endif /* _FIRMWARE_XLNX_EVENT_MANAGER_H_ */ diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 47fd4e52a423..14f00a7672d1 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -2,7 +2,7 @@ /* * Xilinx Zynq MPSoC Firmware layer * - * Copyright (C) 2014-2019 Xilinx + * Copyright (C) 2014-2021 Xilinx * * Michal Simek <michal.simek@xilinx.com> * Davorin Mista <davorin.mista@aggios.com> @@ -64,8 +64,23 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* + * Node IDs for the Error Events. + */ +#define EVENT_ERROR_PMC_ERR1 (0x28100000U) +#define EVENT_ERROR_PMC_ERR2 (0x28104000U) +#define EVENT_ERROR_PSM_ERR1 (0x28108000U) +#define EVENT_ERROR_PSM_ERR2 (0x2810C000U) + +enum pm_api_cb_id { + PM_INIT_SUSPEND_CB = 30, + PM_ACKNOWLEDGE_CB = 31, + PM_NOTIFY_CB = 32, +}; + enum pm_api_id { PM_GET_API_VERSION = 1, + PM_REGISTER_NOTIFIER = 5, PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, PM_RELEASE_NODE = 14, @@ -78,6 +93,7 @@ enum pm_api_id { PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, PM_GET_CHIPID = 24, + PM_SECURE_SHA = 26, PM_PINCTRL_REQUEST = 28, PM_PINCTRL_RELEASE = 29, PM_PINCTRL_GET_FUNCTION = 30, @@ -126,6 +142,11 @@ enum pm_ioctl_id { /* Set healthy bit value */ IOCTL_SET_BOOT_HEALTH_STATUS = 17, IOCTL_OSPI_MUX_SELECT = 21, + /* Register SGI to ATF */ + IOCTL_REGISTER_SGI = 25, + /* Runtime feature configuration */ + IOCTL_SET_FEATURE_CONFIG = 26, + IOCTL_GET_FEATURE_CONFIG = 27, }; enum pm_query_id { @@ -359,6 +380,14 @@ enum ospi_mux_select_type { PM_OSPI_MUX_SEL_LINEAR = 1, }; +enum pm_feature_config_id { + PM_FEATURE_INVALID = 0, + PM_FEATURE_OVERTEMP_STATUS = 1, + PM_FEATURE_OVERTEMP_VALUE = 2, + PM_FEATURE_EXTWDT_STATUS = 3, + PM_FEATURE_EXTWDT_VALUE = 4, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID @@ -410,6 +439,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities, const u32 qos, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_aes_engine(const u64 address, u32 *out); +int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); @@ -427,6 +457,11 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param, int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, u32 value); int zynqmp_pm_load_pdi(const u32 src, const u64 address); +int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable); +int zynqmp_pm_feature(const u32 api_id); +int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value); +int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -581,6 +616,12 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out) return -ENODEV; } +static inline int zynqmp_pm_sha_hash(const u64 address, const u32 size, + const u32 flags) +{ + return -ENODEV; +} + static inline int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags) { @@ -658,6 +699,29 @@ static inline int zynqmp_pm_load_pdi(const u32 src, const u64 address) { return -ENODEV; } + +static inline int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_feature(const u32 api_id) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, + u32 value) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, + u32 *payload) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index a6cd6815f249..295637a66c46 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -2,13 +2,17 @@ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ -#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#include <linux/const.h> + +#define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); +void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); +void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("detected write beyond size of field (1st parameter); maybe use struct_group()?"); #define __compiletime_strlen(p) \ ({ \ @@ -48,7 +52,17 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strncpy __builtin_strncpy #endif -__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +/* + * Clang's use of __builtin_object_size() within inlines needs hinting via + * __pass_object_size(). The preference is to only ever use type 1 (member + * size, rather than struct size), but there remain some stragglers using + * type 0 that will be converted in the future. + */ +#define POS __pass_object_size(1) +#define POS0 __pass_object_size(0) + +__FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3) +char *strncpy(char * const POS p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 1); @@ -59,7 +73,8 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) return __underlying_strncpy(p, q, size); } -__FORTIFY_INLINE char *strcat(char *p, const char *q) +__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2) +char *strcat(char * const POS p, const char *q) { size_t p_size = __builtin_object_size(p, 1); @@ -71,7 +86,7 @@ __FORTIFY_INLINE char *strcat(char *p, const char *q) } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +__FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 1); size_t p_len = __compiletime_strlen(p); @@ -91,8 +106,16 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) return ret; } -/* defined after fortified strnlen to reuse it. */ -__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +/* + * Defined after fortified strnlen to reuse it. However, it must still be + * possible for strlen() to be used on compile-time strings for use in + * static initializers (i.e. as a constant expression). + */ +#define strlen(p) \ + __builtin_choose_expr(__is_constexpr(__builtin_strlen(p)), \ + __builtin_strlen(p), __fortify_strlen(p)) +__FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1) +__kernel_size_t __fortify_strlen(const char * const POS p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 1); @@ -108,7 +131,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); -__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); @@ -135,7 +158,7 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) /* defined after fortified strnlen to reuse it */ extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy); -__FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) +__FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, size_t size) { size_t len; /* Use string size rather than possible enclosing struct size. */ @@ -181,7 +204,8 @@ __FORTIFY_INLINE ssize_t strscpy(char *p, const char *q, size_t size) } /* defined after fortified strlen and strnlen to reuse them */ -__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +__FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3) +char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 1); @@ -198,51 +222,161 @@ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) return p; } -__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size, + const size_t p_size, + const size_t p_size_field) { - size_t p_size = __builtin_object_size(p, 0); - - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) - fortify_panic(__func__); - return __underlying_memset(p, c, size); -} - -__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); - if (__builtin_constant_p(size)) { - if (p_size < size) + /* + * Length argument is a constant expression, so we + * can perform compile-time bounds checking where + * buffer sizes are known. + */ + + /* Error when size is larger than enclosing struct. */ + if (p_size > p_size_field && p_size < size) __write_overflow(); - if (q_size < size) - __read_overflow2(); + + /* Warn when write size is larger than dest field. */ + if (p_size_field < size) + __write_overflow_field(p_size_field, size); } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memcpy(p, q, size); + /* + * At this point, length argument may not be a constant expression, + * so run-time bounds checking can be done where buffer sizes are + * known. (This is not an "else" because the above checks may only + * be compile-time warnings, and we want to still warn for run-time + * overflows.) + */ + + /* + * Always stop accesses beyond the struct that contains the + * field, when the buffer's remaining size is known. + * (The -1 test is to optimize away checks where the buffer + * lengths are unknown.) + */ + if (p_size != (size_t)(-1) && p_size < size) + fortify_panic("memset"); } -__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) -{ - size_t p_size = __builtin_object_size(p, 0); - size_t q_size = __builtin_object_size(q, 0); +#define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({ \ + size_t __fortify_size = (size_t)(size); \ + fortify_memset_chk(__fortify_size, p_size, p_size_field), \ + __underlying_memset(p, c, __fortify_size); \ +}) +/* + * __builtin_object_size() must be captured here to avoid evaluating argument + * side-effects further into the macro layers. + */ +#define memset(p, c, s) __fortify_memset_chk(p, c, s, \ + __builtin_object_size(p, 0), __builtin_object_size(p, 1)) + +/* + * To make sure the compiler can enforce protection against buffer overflows, + * memcpy(), memmove(), and memset() must not be used beyond individual + * struct members. If you need to copy across multiple members, please use + * struct_group() to create a named mirror of an anonymous struct union. + * (e.g. see struct sk_buff.) Read overflow checking is currently only + * done when a write overflow is also present, or when building with W=1. + * + * Mitigation coverage matrix + * Bounds checking at: + * +-------+-------+-------+-------+ + * | Compile time | Run time | + * memcpy() argument sizes: | write | read | write | read | + * dest source length +-------+-------+-------+-------+ + * memcpy(known, known, constant) | y | y | n/a | n/a | + * memcpy(known, unknown, constant) | y | n | n/a | V | + * memcpy(known, known, dynamic) | n | n | B | B | + * memcpy(known, unknown, dynamic) | n | n | B | V | + * memcpy(unknown, known, constant) | n | y | V | n/a | + * memcpy(unknown, unknown, constant) | n | n | V | V | + * memcpy(unknown, known, dynamic) | n | n | V | B | + * memcpy(unknown, unknown, dynamic) | n | n | V | V | + * +-------+-------+-------+-------+ + * + * y = perform deterministic compile-time bounds checking + * n = cannot perform deterministic compile-time bounds checking + * n/a = no run-time bounds checking needed since compile-time deterministic + * B = can perform run-time bounds checking (currently unimplemented) + * V = vulnerable to run-time overflow (will need refactoring to solve) + * + */ +__FORTIFY_INLINE void fortify_memcpy_chk(__kernel_size_t size, + const size_t p_size, + const size_t q_size, + const size_t p_size_field, + const size_t q_size_field, + const char *func) +{ if (__builtin_constant_p(size)) { - if (p_size < size) + /* + * Length argument is a constant expression, so we + * can perform compile-time bounds checking where + * buffer sizes are known. + */ + + /* Error when size is larger than enclosing struct. */ + if (p_size > p_size_field && p_size < size) __write_overflow(); - if (q_size < size) + if (q_size > q_size_field && q_size < size) __read_overflow2(); + + /* Warn when write size argument larger than dest field. */ + if (p_size_field < size) + __write_overflow_field(p_size_field, size); + /* + * Warn for source field over-read when building with W=1 + * or when an over-write happened, so both can be fixed at + * the same time. + */ + if ((IS_ENABLED(KBUILD_EXTRA_WARN1) || p_size_field < size) && + q_size_field < size) + __read_overflow2_field(q_size_field, size); } - if (p_size < size || q_size < size) - fortify_panic(__func__); - return __underlying_memmove(p, q, size); + /* + * At this point, length argument may not be a constant expression, + * so run-time bounds checking can be done where buffer sizes are + * known. (This is not an "else" because the above checks may only + * be compile-time warnings, and we want to still warn for run-time + * overflows.) + */ + + /* + * Always stop accesses beyond the struct that contains the + * field, when the buffer's remaining size is known. + * (The -1 test is to optimize away checks where the buffer + * lengths are unknown.) + */ + if ((p_size != (size_t)(-1) && p_size < size) || + (q_size != (size_t)(-1) && q_size < size)) + fortify_panic(func); } +#define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ + p_size_field, q_size_field, op) ({ \ + size_t __fortify_size = (size_t)(size); \ + fortify_memcpy_chk(__fortify_size, p_size, q_size, \ + p_size_field, q_size_field, #op); \ + __underlying_##op(p, q, __fortify_size); \ +}) + +/* + * __builtin_object_size() must be captured here to avoid evaluating argument + * side-effects further into the macro layers. + */ +#define memcpy(p, q, s) __fortify_memcpy_chk(p, q, s, \ + __builtin_object_size(p, 0), __builtin_object_size(q, 0), \ + __builtin_object_size(p, 1), __builtin_object_size(q, 1), \ + memcpy) +#define memmove(p, q, s) __fortify_memcpy_chk(p, q, s, \ + __builtin_object_size(p, 0), __builtin_object_size(q, 0), \ + __builtin_object_size(p, 1), __builtin_object_size(q, 1), \ + memmove) + extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); -__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -253,7 +387,8 @@ __FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) return __real_memscan(p, c, size); } -__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3) +int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); @@ -269,7 +404,8 @@ __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) return __underlying_memcmp(p, q, size); } -__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +__FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3) +void *memchr(const void * const POS0 p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -281,7 +417,7 @@ __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); -__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +__FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) { size_t p_size = __builtin_object_size(p, 0); @@ -293,7 +429,7 @@ __FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); -__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) { size_t p_size = __builtin_object_size(p, 0); @@ -304,13 +440,15 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) return __real_kmemdup(p, size, gfp); } -/* defined after fortified strlen and memcpy to reuse them */ -__FORTIFY_INLINE char *strcpy(char *p, const char *q) +/* Defined after fortified strlen to reuse it. */ +__FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2) +char *strcpy(char * const POS p, const char * const POS q) { size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); size_t size; + /* If neither buffer size is known, immediately give up. */ if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strcpy(p, q); size = strlen(q) + 1; @@ -320,20 +458,20 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(__func__); - memcpy(p, q, size); + __underlying_memcpy(p, q, size); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp -#undef __underlying_memcpy -#undef __underlying_memmove -#undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy +#undef POS +#undef POS0 + #endif /* _LINUX_FORTIFY_STRING_H_ */ diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 6c3c28806ff1..223da48a6d18 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -23,6 +23,23 @@ struct fpga_bridge_ops { }; /** + * struct fpga_bridge_info - collection of parameters an FPGA Bridge + * @name: fpga bridge name + * @br_ops: pointer to structure of fpga bridge ops + * @priv: fpga bridge private data + * + * fpga_bridge_info contains parameters for the register function. These + * are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_bridge_info { + const char *name; + const struct fpga_bridge_ops *br_ops; + void *priv; +}; + +/** * struct fpga_bridge - FPGA bridge structure * @name: name of low level FPGA bridge * @dev: FPGA bridge device @@ -62,15 +79,10 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); -struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv); -void fpga_bridge_free(struct fpga_bridge *br); -int fpga_bridge_register(struct fpga_bridge *br); +struct fpga_bridge * +fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv); void fpga_bridge_unregister(struct fpga_bridge *br); -struct fpga_bridge -*devm_fpga_bridge_create(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, void *priv); - #endif /* _LINUX_FPGA_BRIDGE_H */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 474c1f506307..0f9468771bb9 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -106,6 +106,36 @@ struct fpga_image_info { }; /** + * struct fpga_compat_id - id for compatibility check + * + * @id_h: high 64bit of the compat_id + * @id_l: low 64bit of the compat_id + */ +struct fpga_compat_id { + u64 id_h; + u64 id_l; +}; + +/** + * struct fpga_manager_info - collection of parameters for an FPGA Manager + * @name: fpga manager name + * @compat_id: FPGA manager id for compatibility check. + * @mops: pointer to structure of fpga manager ops + * @priv: fpga manager private data + * + * fpga_manager_info contains parameters for the register_full function. + * These are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_manager_info { + const char *name; + struct fpga_compat_id *compat_id; + const struct fpga_manager_ops *mops; + void *priv; +}; + +/** * struct fpga_manager_ops - ops for low level fpga manager drivers * @initial_header_size: Maximum number of bytes that should be passed into write_init * @state: returns an enum value of the FPGA's state @@ -144,17 +174,6 @@ struct fpga_manager_ops { #define FPGA_MGR_STATUS_FIFO_OVERFLOW_ERR BIT(4) /** - * struct fpga_compat_id - id for compatibility check - * - * @id_h: high 64bit of the compat_id - * @id_l: low 64bit of the compat_id - */ -struct fpga_compat_id { - u64 id_h; - u64 id_l; -}; - -/** * struct fpga_manager - fpga manager structure * @name: name of low level fpga manager * @dev: fpga manager device @@ -191,17 +210,18 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); -struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, - void *priv); -void fpga_mgr_free(struct fpga_manager *mgr); -int fpga_mgr_register(struct fpga_manager *mgr); -void fpga_mgr_unregister(struct fpga_manager *mgr); +struct fpga_manager * +fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); -int devm_fpga_mgr_register(struct device *dev, struct fpga_manager *mgr); +struct fpga_manager * +fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv); +void fpga_mgr_unregister(struct fpga_manager *mgr); -struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, - void *priv); +struct fpga_manager * +devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +struct fpga_manager * +devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv); #endif /*_LINUX_FPGA_MGR_H */ diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 27cb706275db..3b87f232425c 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -7,6 +7,27 @@ #include <linux/fpga/fpga-mgr.h> #include <linux/fpga/fpga-bridge.h> +struct fpga_region; + +/** + * struct fpga_region_info - collection of parameters an FPGA Region + * @mgr: fpga region manager + * @compat_id: FPGA region id for compatibility check. + * @priv: fpga region private data + * @get_bridges: optional function to get bridges to a list + * + * fpga_region_info contains parameters for the register_full function. + * These are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_region_info { + struct fpga_manager *mgr; + struct fpga_compat_id *compat_id; + void *priv; + int (*get_bridges)(struct fpga_region *region); +}; + /** * struct fpga_region - FPGA Region structure * @dev: FPGA Region device @@ -37,15 +58,12 @@ struct fpga_region *fpga_region_class_find( int fpga_region_program_fpga(struct fpga_region *region); -struct fpga_region -*fpga_region_create(struct device *dev, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); -void fpga_region_free(struct fpga_region *region); -int fpga_region_register(struct fpga_region *region); -void fpga_region_unregister(struct fpga_region *region); +struct fpga_region * +fpga_region_register_full(struct device *parent, const struct fpga_region_info *info); -struct fpga_region -*devm_fpga_region_create(struct device *dev, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); +struct fpga_region * +fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); +void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h new file mode 100644 index 000000000000..1c2bde0ead73 --- /dev/null +++ b/include/linux/fprobe.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Simple ftrace probe wrapper */ +#ifndef _LINUX_FPROBE_H +#define _LINUX_FPROBE_H + +#include <linux/compiler.h> +#include <linux/ftrace.h> +#include <linux/rethook.h> + +/** + * struct fprobe - ftrace based probe. + * @ops: The ftrace_ops. + * @nmissed: The counter for missing events. + * @flags: The status flag. + * @rethook: The rethook data structure. (internal data) + * @entry_handler: The callback function for function entry. + * @exit_handler: The callback function for function exit. + */ +struct fprobe { +#ifdef CONFIG_FUNCTION_TRACER + /* + * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. + * But user of fprobe may keep embedding the struct fprobe on their own + * code. To avoid build error, this will keep the fprobe data structure + * defined here, but remove ftrace_ops data structure. + */ + struct ftrace_ops ops; +#endif + unsigned long nmissed; + unsigned int flags; + struct rethook *rethook; + + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); +}; + +/* This fprobe is soft-disabled. */ +#define FPROBE_FL_DISABLED 1 + +/* + * This fprobe handler will be shared with kprobes. + * This flag must be set before registering. + */ +#define FPROBE_FL_KPROBE_SHARED 2 + +static inline bool fprobe_disabled(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_DISABLED : false; +} + +static inline bool fprobe_shared_with_kprobes(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_KPROBE_SHARED : false; +} + +#ifdef CONFIG_FPROBE +int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter); +int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); +int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); +int unregister_fprobe(struct fprobe *fp); +#else +static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_syms(struct fprobe *fp, const char **syms, int num) +{ + return -EOPNOTSUPP; +} +static inline int unregister_fprobe(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} +#endif + +/** + * disable_fprobe() - Disable fprobe + * @fp: The fprobe to be disabled. + * + * This will soft-disable @fp. Note that this doesn't remove the ftrace + * hooks from the function entry. + */ +static inline void disable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags |= FPROBE_FL_DISABLED; +} + +/** + * enable_fprobe() - Enable fprobe + * @fp: The fprobe to be enabled. + * + * This will soft-enable @fp. + */ +static inline void enable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags &= ~FPROBE_FL_DISABLED; +} + +#endif diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index b07d88c92bb2..a631bac12220 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -7,31 +7,17 @@ #include <linux/bitops.h> #include <linux/jump_label.h> -/* - * Return code to denote that requested number of - * frontswap pages are unused(moved to page cache). - * Used in shmem_unuse and try_to_unuse. - */ -#define FRONTSWAP_PAGES_UNUSED 2 - struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ - struct frontswap_ops *next; /* private pointer to next ops */ }; -extern void frontswap_register_ops(struct frontswap_ops *ops); -extern void frontswap_shrink(unsigned long); -extern unsigned long frontswap_curr_pages(void); -extern void frontswap_writethrough(bool); -#define FRONTSWAP_HAS_EXCLUSIVE_GETS -extern void frontswap_tmem_exclusive_gets(bool); +int frontswap_register_ops(const struct frontswap_ops *ops); -extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); -extern void __frontswap_init(unsigned type, unsigned long *map); +extern void frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); extern void __frontswap_invalidate_page(unsigned, pgoff_t); @@ -45,11 +31,6 @@ static inline bool frontswap_enabled(void) return static_branch_unlikely(&frontswap_enabled_key); } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return __frontswap_test(sis, offset); -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -68,11 +49,6 @@ static inline bool frontswap_enabled(void) return false; } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return false; -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -112,11 +88,4 @@ static inline void frontswap_invalidate_area(unsigned type) __frontswap_invalidate_area(type); } -static inline void frontswap_init(unsigned type, unsigned long *map) -{ -#ifdef CONFIG_FRONTSWAP - __frontswap_init(type, map); -#endif -} - #endif /* _LINUX_FRONTSWAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..183160872133 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -41,6 +41,8 @@ #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> +#include <linux/mnt_idmapping.h> +#include <linux/slab.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -78,15 +80,8 @@ extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); -extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; -extern struct inodes_stat_t inodes_stat; -extern int leases_enable, lease_break_time; -extern int sysctl_protected_symlinks; -extern int sysctl_protected_hardlinks; -extern int sysctl_protected_fifos; -extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; @@ -333,7 +328,6 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; - u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ randomized_struct_fields_end @@ -373,8 +367,8 @@ struct address_space_operations { /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); - /* Set a page dirty. Return true if this dirtied it */ - int (*set_page_dirty)(struct page *page); + /* Mark a folio dirty. Return true if this dirtied it */ + bool (*dirty_folio)(struct address_space *, struct folio *); /* * Reads in the requested pages. Unlike ->readpage(), this is @@ -393,7 +387,7 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - void (*invalidatepage) (struct page *, unsigned int, unsigned int); + void (*invalidate_folio) (struct folio *, size_t offset, size_t len); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); @@ -405,9 +399,9 @@ struct address_space_operations { struct page *, struct page *, enum migrate_mode); bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); - int (*launder_page) (struct page *); - int (*is_partially_uptodate) (struct page *, unsigned long, - unsigned long); + int (*launder_folio)(struct folio *); + bool (*is_partially_uptodate) (struct folio *, size_t from, + size_t count); void (*is_dirty_writeback) (struct page *, bool *, bool *); int (*error_remove_page)(struct address_space *, struct page *); @@ -936,10 +930,15 @@ struct fown_struct { * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. - * @async_size: Start next readahead when this many pages are left. - * @ra_pages: Maximum size of a readahead request. + * @async_size: Numer of pages that were/are not needed immediately + * and so were/are genuinely "ahead". Start next readahead when + * the first of these pages is accessed. + * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. + * + * When this structure is passed to ->readahead(), the "most recent" + * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; @@ -973,7 +972,6 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; - enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -1220,13 +1218,13 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file, #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 __user *user) + struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 __user *user) + unsigned int cmd, struct flock64 *user) { return -EACCES; } @@ -1441,6 +1439,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ +#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ /* Possible states of 'frozen' field */ enum { @@ -1489,7 +1488,7 @@ struct super_block { #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif @@ -1541,11 +1540,6 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - /* - * Saved pool identifier for cleancache (-1 means none) - */ - int cleancache_poolid; - struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ @@ -1599,6 +1593,11 @@ struct super_block { struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; +static inline struct user_namespace *i_user_ns(const struct inode *inode) +{ + return inode->i_sb->s_user_ns; +} + /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored @@ -1606,50 +1605,22 @@ struct super_block { */ static inline uid_t i_uid_read(const struct inode *inode) { - return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); + return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { - return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); + return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { - inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); + inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { - inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); -} - -/** - * kuid_into_mnt - map a kuid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return make_kuid(mnt_userns, __kuid_val(kuid)); -} - -/** - * kgid_into_mnt - map a kgid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return make_kgid(mnt_userns, __kgid_val(kgid)); + inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** @@ -1663,7 +1634,7 @@ static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kuid_into_mnt(mnt_userns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid); } /** @@ -1677,69 +1648,7 @@ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kgid_into_mnt(mnt_userns, inode->i_gid); -} - -/** - * kuid_from_mnt - map a kuid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped up according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return KUIDT_INIT(from_kuid(mnt_userns, kuid)); -} - -/** - * kgid_from_mnt - map a kgid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped up according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return KGIDT_INIT(from_kgid(mnt_userns, kgid)); -} - -/** - * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsuid. A common example is initializing the i_uid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsuid mapped up according to @mnt_userns. - */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) -{ - return kuid_from_mnt(mnt_userns, current_fsuid()); -} - -/** - * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsgid. A common example is initializing the i_gid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsgid mapped up according to @mnt_userns. - */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) -{ - return kgid_from_mnt(mnt_userns, current_fsgid()); + return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid); } /** @@ -1753,7 +1662,7 @@ static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns); + inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); } /** @@ -1767,7 +1676,7 @@ static inline void inode_fsuid_set(struct inode *inode, static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns); + inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); } /** @@ -1784,10 +1693,18 @@ static inline void inode_fsgid_set(struct inode *inode, static inline bool fsuidgid_has_mapping(struct super_block *sb, struct user_namespace *mnt_userns) { - struct user_namespace *s_user_ns = sb->s_user_ns; + struct user_namespace *fs_userns = sb->s_user_ns; + kuid_t kuid; + kgid_t kgid; - return kuid_has_mapping(s_user_ns, mapped_fsuid(mnt_userns)) && - kgid_has_mapping(s_user_ns, mapped_fsgid(mnt_userns)); + kuid = mapped_fsuid(mnt_userns, fs_userns); + if (!uid_valid(kuid)) + return false; + kgid = mapped_fsgid(mnt_userns, fs_userns); + if (!gid_valid(kgid)) + return false; + return kuid_has_mapping(fs_userns, kuid) && + kgid_has_mapping(fs_userns, kgid); } extern struct timespec64 current_time(struct inode *inode); @@ -2249,6 +2166,7 @@ struct super_operations { #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ +#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -2302,31 +2220,13 @@ static inline bool HAS_UNMAPPED_ID(struct user_namespace *mnt_userns, !gid_valid(i_gid_into_mnt(mnt_userns, inode)); } -static inline enum rw_hint file_write_hint(struct file *file) -{ - if (file->f_write_hint != WRITE_LIFE_NOT_SET) - return file->f_write_hint; - - return file_inode(file)->i_write_hint; -} - static inline int iocb_flags(struct file *file); -static inline u16 ki_hint_validate(enum rw_hint hint) -{ - typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; - - if (hint <= max_hint) - return hint; - return 0; -} - static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = iocb_flags(filp), - .ki_hint = ki_hint_validate(file_write_hint(filp)), .ki_ioprio = get_current_ioprio(), }; } @@ -2337,7 +2237,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, - .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; @@ -2418,6 +2317,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2440,6 +2341,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) +#define I_PINNING_FSCACHE_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2724,6 +2626,21 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) { return mnt_user_ns(file->f_path.mnt); } + +/** + * is_idmapped_mnt - check whether a mount is mapped + * @mnt: the mount to check + * + * If @mnt has an idmapping attached different from the + * filesystem's idmapping then @mnt is mapped. + * + * Return: true if mount is mapped, false if not. + */ +static inline bool is_idmapped_mnt(const struct vfsmount *mnt) +{ + return mnt_user_ns(mnt) != mnt->mnt_sb->s_user_ns; +} + extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct user_namespace *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); @@ -2815,56 +2732,6 @@ extern void init_special_inode(struct inode *, umode_t, dev_t); extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -unsigned long invalidate_mapping_pages(struct address_space *mapping, - pgoff_t start, pgoff_t end); - -void invalidate_mapping_pagevec(struct address_space *mapping, - pgoff_t start, pgoff_t end, - unsigned long *nr_pagevec); - -static inline void invalidate_remote_inode(struct inode *inode) -{ - if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) - invalidate_mapping_pages(inode->i_mapping, 0, -1); -} -extern int invalidate_inode_pages2(struct address_space *mapping); -extern int invalidate_inode_pages2_range(struct address_space *mapping, - pgoff_t start, pgoff_t end); -extern int write_inode_now(struct inode *, int); -extern int filemap_fdatawrite(struct address_space *); -extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait_keep_errors(struct address_space *mapping); -extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, - loff_t lend); -extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, - loff_t start_byte, loff_t end_byte); - -static inline int filemap_fdatawait(struct address_space *mapping) -{ - return filemap_fdatawait_range(mapping, 0, LLONG_MAX); -} - -extern bool filemap_range_has_page(struct address_space *, loff_t lstart, - loff_t lend); -extern bool filemap_range_needs_writeback(struct address_space *, - loff_t lstart, loff_t lend); -extern int filemap_write_and_wait_range(struct address_space *mapping, - loff_t lstart, loff_t lend); -extern int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); -extern int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end); -extern int filemap_check_errors(struct address_space *mapping); -extern void __filemap_set_wb_err(struct address_space *mapping, int err); -int filemap_fdatawrite_wbc(struct address_space *mapping, - struct writeback_control *wbc); - -static inline int filemap_write_and_wait(struct address_space *mapping) -{ - return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); -} - extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); @@ -2876,67 +2743,6 @@ static inline int file_write_and_wait(struct file *file) return file_write_and_wait_range(file, 0, LLONG_MAX); } -/** - * filemap_set_wb_err - set a writeback error on an address_space - * @mapping: mapping in which to set writeback error - * @err: error to be set in mapping - * - * When writeback fails in some way, we must record that error so that - * userspace can be informed when fsync and the like are called. We endeavor - * to report errors on any file that was open at the time of the error. Some - * internal callers also need to know when writeback errors have occurred. - * - * When a writeback error occurs, most filesystems will want to call - * filemap_set_wb_err to record the error in the mapping so that it will be - * automatically reported whenever fsync is called on the file. - */ -static inline void filemap_set_wb_err(struct address_space *mapping, int err) -{ - /* Fastpath for common case of no error */ - if (unlikely(err)) - __filemap_set_wb_err(mapping, err); -} - -/** - * filemap_check_wb_err - has an error occurred since the mark was sampled? - * @mapping: mapping to check for writeback errors - * @since: previously-sampled errseq_t - * - * Grab the errseq_t value from the mapping, and see if it has changed "since" - * the given value was sampled. - * - * If it has then report the latest error set, otherwise return 0. - */ -static inline int filemap_check_wb_err(struct address_space *mapping, - errseq_t since) -{ - return errseq_check(&mapping->wb_err, since); -} - -/** - * filemap_sample_wb_err - sample the current errseq_t to test for later errors - * @mapping: mapping to be sampled - * - * Writeback errors are always reported relative to a particular sample point - * in the past. This function provides those sample points. - */ -static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) -{ - return errseq_sample(&mapping->wb_err); -} - -/** - * file_sample_sb_err - sample the current errseq_t to test for later errors - * @file: file pointer to be sampled - * - * Grab the most current superblock-level errseq_t value for the given - * struct file. - */ -static inline errseq_t file_sample_sb_err(struct file *file) -{ - return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); -} - extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); @@ -3152,6 +2958,7 @@ extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +void dump_mapping(const struct address_space *); /* * Userspace may rely on the the inode number being non-zero. For example, glibc @@ -3178,6 +2985,16 @@ extern void free_inode_nonrcu(struct inode *inode); extern int should_remove_suid(struct dentry *); extern int file_remove_privs(struct file *); +/* + * This must be used for allocating filesystems specific inodes to set + * up the inode reclaim context correctly. + */ +static inline void * +alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) +{ + return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); +} + extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { @@ -3200,6 +3017,7 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); @@ -3243,6 +3061,7 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); +int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); @@ -3392,8 +3211,6 @@ extern int simple_rename(struct user_namespace *, struct inode *, extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); -extern void noop_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, @@ -3591,12 +3408,6 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_dentry(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_inodes(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) @@ -3684,15 +3495,4 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); -/* - * Flush file data before changing attributes. Caller must hold any locks - * required to prevent further writes to this file until we're done setting - * flags. - */ -static inline int inode_drain_writes(struct inode *inode) -{ - inode_dio_wait(inode); - return filemap_write_and_wait(inode->i_mapping); -} - #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_api.h b/include/linux/fs_api.h new file mode 100644 index 000000000000..83be38d6d413 --- /dev/null +++ b/include/linux/fs_api.h @@ -0,0 +1 @@ +#include <linux/fs.h> diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 6b54982fc5f3..13fa6f3df8e4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -142,6 +142,8 @@ extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); +int reconfigure_single(struct super_block *s, + int flags, void *data); /* * sget() wrappers to be called from the ->get_tree() op. diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index aab0ffc6bac6..f103c91139d4 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -42,7 +42,7 @@ struct fs_parameter_spec { u8 opt; /* Option number (returned by fs_parse()) */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ -#define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ +#define fs_param_can_be_empty 0x0004 /* "xxx=" is allowed */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ const void *data; }; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 8d39491c5f9f..a174cedf4d90 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching backing cache interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -15,207 +15,34 @@ #define _LINUX_FSCACHE_CACHE_H #include <linux/fscache.h> -#include <linux/sched.h> -#include <linux/workqueue.h> -#define NR_MAXCACHES BITS_PER_LONG - -struct fscache_cache; -struct fscache_cache_ops; -struct fscache_object; -struct fscache_operation; - -enum fscache_obj_ref_trace { - fscache_obj_get_add_to_deps, - fscache_obj_get_queue, - fscache_obj_put_alloc_fail, - fscache_obj_put_attach_fail, - fscache_obj_put_drop_obj, - fscache_obj_put_enq_dep, - fscache_obj_put_queue, - fscache_obj_put_work, - fscache_obj_ref__nr_traces +enum fscache_cache_trace; +enum fscache_cookie_trace; +enum fscache_access_trace; + +enum fscache_cache_state { + FSCACHE_CACHE_IS_NOT_PRESENT, /* No cache is present for this name */ + FSCACHE_CACHE_IS_PREPARING, /* A cache is preparing to come live */ + FSCACHE_CACHE_IS_ACTIVE, /* Attached cache is active and can be used */ + FSCACHE_CACHE_GOT_IOERROR, /* Attached cache stopped on I/O error */ + FSCACHE_CACHE_IS_WITHDRAWN, /* Attached cache is being withdrawn */ +#define NR__FSCACHE_CACHE_STATE (FSCACHE_CACHE_IS_WITHDRAWN + 1) }; /* - * cache tag definition - */ -struct fscache_cache_tag { - struct list_head link; - struct fscache_cache *cache; /* cache referred to by this tag */ - unsigned long flags; -#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ - atomic_t usage; - char name[]; /* tag name */ -}; - -/* - * cache definition + * Cache cookie. */ struct fscache_cache { const struct fscache_cache_ops *ops; - struct fscache_cache_tag *tag; /* tag representing this cache */ - struct kobject *kobj; /* system representation of this cache */ - struct list_head link; /* link in list of caches */ - size_t max_index_size; /* maximum size of index data */ - char identifier[36]; /* cache label */ - - /* node management */ - struct work_struct op_gc; /* operation garbage collector */ - struct list_head object_list; /* list of data/index objects */ - struct list_head op_gc_list; /* list of ops to be deleted */ - spinlock_t object_list_lock; - spinlock_t op_gc_list_lock; + struct list_head cache_link; /* Link in cache list */ + void *cache_priv; /* Private cache data (or NULL) */ + refcount_t ref; + atomic_t n_volumes; /* Number of active volumes; */ + atomic_t n_accesses; /* Number of in-progress accesses on the cache */ atomic_t object_count; /* no. of live objects in this cache */ - struct fscache_object *fsdef; /* object for the fsdef index */ - unsigned long flags; -#define FSCACHE_IOERROR 0 /* cache stopped on I/O error */ -#define FSCACHE_CACHE_WITHDRAWN 1 /* cache has been withdrawn */ -}; - -extern wait_queue_head_t fscache_cache_cleared_wq; - -/* - * operation to be applied to a cache object - * - retrieval initiation operations are done in the context of the process - * that issued them, and not in an async thread pool - */ -typedef void (*fscache_operation_release_t)(struct fscache_operation *op); -typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); -typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op); - -enum fscache_operation_state { - FSCACHE_OP_ST_BLANK, /* Op is not yet submitted */ - FSCACHE_OP_ST_INITIALISED, /* Op is initialised */ - FSCACHE_OP_ST_PENDING, /* Op is blocked from running */ - FSCACHE_OP_ST_IN_PROGRESS, /* Op is in progress */ - FSCACHE_OP_ST_COMPLETE, /* Op is complete */ - FSCACHE_OP_ST_CANCELLED, /* Op has been cancelled */ - FSCACHE_OP_ST_DEAD /* Op is now dead */ -}; - -struct fscache_operation { - struct work_struct work; /* record for async ops */ - struct list_head pend_link; /* link in object->pending_ops */ - struct fscache_object *object; /* object to be operated upon */ - - unsigned long flags; -#define FSCACHE_OP_TYPE 0x000f /* operation type */ -#define FSCACHE_OP_ASYNC 0x0001 /* - async op, processor may sleep for disk */ -#define FSCACHE_OP_MYTHREAD 0x0002 /* - processing is done be issuing thread, not pool */ -#define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ -#define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ -#define FSCACHE_OP_DEC_READ_CNT 6 /* decrement object->n_reads on destruction */ -#define FSCACHE_OP_UNUSE_COOKIE 7 /* call fscache_unuse_cookie() on completion */ -#define FSCACHE_OP_KEEP_FLAGS 0x00f0 /* flags to keep when repurposing an op */ - - enum fscache_operation_state state; - atomic_t usage; - unsigned debug_id; /* debugging ID */ - - /* operation processor callback - * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform - * the op in a non-pool thread */ - fscache_operation_processor_t processor; - - /* Operation cancellation cleanup (optional) */ - fscache_operation_cancel_t cancel; - - /* operation releaser */ - fscache_operation_release_t release; -}; - -extern atomic_t fscache_op_debug_id; -extern void fscache_op_work_func(struct work_struct *work); - -extern void fscache_enqueue_operation(struct fscache_operation *); -extern void fscache_op_complete(struct fscache_operation *, bool); -extern void fscache_put_operation(struct fscache_operation *); -extern void fscache_operation_init(struct fscache_cookie *, - struct fscache_operation *, - fscache_operation_processor_t, - fscache_operation_cancel_t, - fscache_operation_release_t); - -/* - * data read operation - */ -struct fscache_retrieval { - struct fscache_operation op; - struct fscache_cookie *cookie; /* The netfs cookie */ - struct address_space *mapping; /* netfs pages */ - fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ - void *context; /* netfs read context (pinned) */ - struct list_head to_do; /* list of things to be done by the backend */ - atomic_t n_pages; /* number of pages to be retrieved */ -}; - -typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op, - struct page *page, - gfp_t gfp); - -typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op, - struct list_head *pages, - unsigned *nr_pages, - gfp_t gfp); - -/** - * fscache_get_retrieval - Get an extra reference on a retrieval operation - * @op: The retrieval operation to get a reference on - * - * Get an extra reference on a retrieval operation. - */ -static inline -struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op) -{ - atomic_inc(&op->op.usage); - return op; -} - -/** - * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing - * @op: The retrieval operation affected - * - * Enqueue a retrieval operation for processing by the FS-Cache thread pool. - */ -static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) -{ - fscache_enqueue_operation(&op->op); -} - -/** - * fscache_retrieval_complete - Record (partial) completion of a retrieval - * @op: The retrieval operation affected - * @n_pages: The number of pages to account for - */ -static inline void fscache_retrieval_complete(struct fscache_retrieval *op, - int n_pages) -{ - if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) - fscache_op_complete(&op->op, false); -} - -/** - * fscache_put_retrieval - Drop a reference to a retrieval operation - * @op: The retrieval operation affected - * - * Drop a reference to a retrieval operation. - */ -static inline void fscache_put_retrieval(struct fscache_retrieval *op) -{ - fscache_put_operation(&op->op); -} - -/* - * cached page storage work item - * - used to do three things: - * - batch writes to the cache - * - do cache writes asynchronously - * - defer writes until cache object lookup completion - */ -struct fscache_storage { - struct fscache_operation op; - pgoff_t store_limit; /* don't write more than this */ + unsigned int debug_id; + enum fscache_cache_state state; + char *name; }; /* @@ -225,341 +52,154 @@ struct fscache_cache_ops { /* name of cache provider */ const char *name; - /* allocate an object record for a cookie */ - struct fscache_object *(*alloc_object)(struct fscache_cache *cache, - struct fscache_cookie *cookie); - - /* look up the object for a cookie - * - return -ETIMEDOUT to be requeued - */ - int (*lookup_object)(struct fscache_object *object); - - /* finished looking up */ - void (*lookup_complete)(struct fscache_object *object); - - /* increment the usage count on this object (may fail if unmounting) */ - struct fscache_object *(*grab_object)(struct fscache_object *object, - enum fscache_obj_ref_trace why); + /* Acquire a volume */ + void (*acquire_volume)(struct fscache_volume *volume); - /* pin an object in the cache */ - int (*pin_object)(struct fscache_object *object); + /* Free the cache's data attached to a volume */ + void (*free_volume)(struct fscache_volume *volume); - /* unpin an object in the cache */ - void (*unpin_object)(struct fscache_object *object); + /* Look up a cookie in the cache */ + bool (*lookup_cookie)(struct fscache_cookie *cookie); - /* check the consistency between the backing cache and the FS-Cache - * cookie */ - int (*check_consistency)(struct fscache_operation *op); + /* Withdraw an object without any cookie access counts held */ + void (*withdraw_cookie)(struct fscache_cookie *cookie); - /* store the updated auxiliary data on an object */ - void (*update_object)(struct fscache_object *object); + /* Change the size of a data object */ + void (*resize_cookie)(struct netfs_cache_resources *cres, + loff_t new_size); /* Invalidate an object */ - void (*invalidate_object)(struct fscache_operation *op); - - /* discard the resources pinned by an object and effect retirement if - * necessary */ - void (*drop_object)(struct fscache_object *object); - - /* dispose of a reference to an object */ - void (*put_object)(struct fscache_object *object, - enum fscache_obj_ref_trace why); - - /* sync a cache */ - void (*sync_cache)(struct fscache_cache *cache); - - /* notification that the attributes of a non-index object (such as - * i_size) have changed */ - int (*attr_changed)(struct fscache_object *object); - - /* reserve space for an object's data and associated metadata */ - int (*reserve_space)(struct fscache_object *object, loff_t i_size); - - /* request a backing block for a page be read or allocated in the - * cache */ - fscache_page_retrieval_func_t read_or_alloc_page; - - /* request backing blocks for a list of pages be read or allocated in - * the cache */ - fscache_pages_retrieval_func_t read_or_alloc_pages; - - /* request a backing block for a page be allocated in the cache so that - * it can be written directly */ - fscache_page_retrieval_func_t allocate_page; - - /* request backing blocks for pages be allocated in the cache so that - * they can be written directly */ - fscache_pages_retrieval_func_t allocate_pages; - - /* write a page to its backing block in the cache */ - int (*write_page)(struct fscache_storage *op, struct page *page); - - /* detach backing block from a page (optional) - * - must release the cookie lock before returning - * - may sleep - */ - void (*uncache_page)(struct fscache_object *object, - struct page *page); - - /* dissociate a cache from all the pages it was backing */ - void (*dissociate_pages)(struct fscache_cache *cache); + bool (*invalidate_cookie)(struct fscache_cookie *cookie); - /* Begin a read operation for the netfs lib */ - int (*begin_read_operation)(struct netfs_read_request *rreq, - struct fscache_retrieval *op); -}; - -extern struct fscache_cookie fscache_fsdef_index; + /* Begin an operation for the netfs lib */ + bool (*begin_operation)(struct netfs_cache_resources *cres, + enum fscache_want_state want_state); -/* - * Event list for fscache_object::{event_mask,events} - */ -enum { - FSCACHE_OBJECT_EV_NEW_CHILD, /* T if object has a new child */ - FSCACHE_OBJECT_EV_PARENT_READY, /* T if object's parent is ready */ - FSCACHE_OBJECT_EV_UPDATE, /* T if object should be updated */ - FSCACHE_OBJECT_EV_INVALIDATE, /* T if cache requested object invalidation */ - FSCACHE_OBJECT_EV_CLEARED, /* T if accessors all gone */ - FSCACHE_OBJECT_EV_ERROR, /* T if fatal error occurred during processing */ - FSCACHE_OBJECT_EV_KILL, /* T if netfs relinquished or cache withdrew object */ - NR_FSCACHE_OBJECT_EVENTS -}; - -#define FSCACHE_OBJECT_EVENTS_MASK ((1UL << NR_FSCACHE_OBJECT_EVENTS) - 1) - -/* - * States for object state machine. - */ -struct fscache_transition { - unsigned long events; - const struct fscache_state *transit_to; + /* Prepare to write to a live cache object */ + void (*prepare_to_write)(struct fscache_cookie *cookie); }; -struct fscache_state { - char name[24]; - char short_name[8]; - const struct fscache_state *(*work)(struct fscache_object *object, - int event); - const struct fscache_transition transitions[]; -}; +extern struct workqueue_struct *fscache_wq; +extern wait_queue_head_t fscache_clearance_waiters; /* - * on-disk cache file or index handle + * out-of-line cache backend functions */ -struct fscache_object { - const struct fscache_state *state; /* Object state machine state */ - const struct fscache_transition *oob_table; /* OOB state transition table */ - int debug_id; /* debugging ID */ - int n_children; /* number of child objects */ - int n_ops; /* number of extant ops on object */ - int n_obj_ops; /* number of object ops outstanding on object */ - int n_in_progress; /* number of ops in progress */ - int n_exclusive; /* number of exclusive ops queued or in progress */ - atomic_t n_reads; /* number of read ops in progress */ - spinlock_t lock; /* state and operations lock */ - - unsigned long lookup_jif; /* time at which lookup started */ - unsigned long oob_event_mask; /* OOB events this object is interested in */ - unsigned long event_mask; /* events this object is interested in */ - unsigned long events; /* events to be processed by this object - * (order is important - using fls) */ - - unsigned long flags; -#define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ -#define FSCACHE_OBJECT_PENDING_WRITE 1 /* T if object has pending write */ -#define FSCACHE_OBJECT_WAITING 2 /* T if object is waiting on its parent */ -#define FSCACHE_OBJECT_IS_LIVE 3 /* T if object is not withdrawn or relinquished */ -#define FSCACHE_OBJECT_IS_LOOKED_UP 4 /* T if object has been looked up */ -#define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ -#define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ -#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ -#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */ - - struct list_head cache_link; /* link in cache->object_list */ - struct hlist_node cookie_link; /* link in cookie->backing_objects */ - struct fscache_cache *cache; /* cache that supplied this object */ - struct fscache_cookie *cookie; /* netfs's file/index object */ - struct fscache_object *parent; /* parent object */ - struct work_struct work; /* attention scheduling record */ - struct list_head dependents; /* FIFO of dependent objects */ - struct list_head dep_link; /* link in parent's dependents list */ - struct list_head pending_ops; /* unstarted operations on this object */ - pgoff_t store_limit; /* current storage limit */ - loff_t store_limit_l; /* current storage limit */ -}; - -extern void fscache_object_init(struct fscache_object *, struct fscache_cookie *, - struct fscache_cache *); -extern void fscache_object_destroy(struct fscache_object *); - -extern void fscache_object_lookup_negative(struct fscache_object *object); -extern void fscache_obtained_object(struct fscache_object *object); - -static inline bool fscache_object_is_live(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); -} - -static inline bool fscache_object_is_dying(struct fscache_object *object) -{ - return !fscache_object_is_live(object); -} - -static inline bool fscache_object_is_available(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); -} +extern struct rw_semaphore fscache_addremove_sem; +extern struct fscache_cache *fscache_acquire_cache(const char *name); +extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern int fscache_add_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + void *cache_priv); +extern void fscache_withdraw_cache(struct fscache_cache *cache); +extern void fscache_withdraw_volume(struct fscache_volume *volume); +extern void fscache_withdraw_cookie(struct fscache_cookie *cookie); -static inline bool fscache_cache_is_broken(struct fscache_object *object) -{ - return test_bit(FSCACHE_IOERROR, &object->cache->flags); -} +extern void fscache_io_error(struct fscache_cache *cache); -static inline bool fscache_object_is_active(struct fscache_object *object) -{ - return fscache_object_is_available(object) && - fscache_object_is_live(object) && - !fscache_cache_is_broken(object); -} +extern void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); + +extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); +extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); +extern void fscache_resume_after_invalidation(struct fscache_cookie *cookie); +extern void fscache_caching_failed(struct fscache_cookie *cookie); +extern bool fscache_wait_for_operation(struct netfs_cache_resources *cred, + enum fscache_want_state state); /** - * fscache_object_destroyed - Note destruction of an object in a cache - * @cache: The cache from which the object came + * fscache_cookie_state - Read the state of a cookie + * @cookie: The cookie to query * - * Note the destruction and deallocation of an object record in a cache. + * Get the state of a cookie, imposing an ordering between the cookie contents + * and the state value. Paired with fscache_set_cookie_state(). */ -static inline void fscache_object_destroyed(struct fscache_cache *cache) +static inline +enum fscache_cookie_state fscache_cookie_state(struct fscache_cookie *cookie) { - if (atomic_dec_and_test(&cache->object_count)) - wake_up_all(&fscache_cache_cleared_wq); + return smp_load_acquire(&cookie->state); } /** - * fscache_object_lookup_error - Note an object encountered an error - * @object: The object on which the error was encountered + * fscache_get_key - Get a pointer to the cookie key + * @cookie: The cookie to query * - * Note that an object encountered a fatal error (usually an I/O error) and - * that it should be withdrawn as soon as possible. + * Return a pointer to the where a cookie's key is stored. */ -static inline void fscache_object_lookup_error(struct fscache_object *object) +static inline void *fscache_get_key(struct fscache_cookie *cookie) { - set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events); + if (cookie->key_len <= sizeof(cookie->inline_key)) + return cookie->inline_key; + else + return cookie->key; } -/** - * fscache_set_store_limit - Set the maximum size to be stored in an object - * @object: The object to set the maximum on - * @i_size: The limit to set in bytes - * - * Set the maximum size an object is permitted to reach, implying the highest - * byte that may be written. Intended to be called by the attr_changed() op. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -static inline -void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) +static inline struct fscache_cookie *fscache_cres_cookie(struct netfs_cache_resources *cres) { - object->store_limit_l = i_size; - object->store_limit = i_size >> PAGE_SHIFT; - if (i_size & ~PAGE_MASK) - object->store_limit++; + return cres->cache_priv; } /** - * fscache_end_io - End a retrieval operation on a page - * @op: The FS-Cache operation covering the retrieval - * @page: The page that was to be fetched - * @error: The error code (0 if successful) + * fscache_count_object - Tell fscache that an object has been added + * @cache: The cache to account to * - * Note the end of an operation to retrieve a page, as covered by a particular - * operation record. + * Tell fscache that an object has been added to the cache. This prevents the + * cache from tearing down the cache structure until the object is uncounted. */ -static inline void fscache_end_io(struct fscache_retrieval *op, - struct page *page, int error) +static inline void fscache_count_object(struct fscache_cache *cache) { - op->end_io_func(page, op->context, error); -} - -static inline void __fscache_use_cookie(struct fscache_cookie *cookie) -{ - atomic_inc(&cookie->n_active); + atomic_inc(&cache->object_count); } /** - * fscache_use_cookie - Request usage of cookie attached to an object - * @object: Object description - * - * Request usage of the cookie attached to an object. NULL is returned if the - * relinquishment had reduced the cookie usage count to 0. + * fscache_uncount_object - Tell fscache that an object has been removed + * @cache: The cache to account to + * + * Tell fscache that an object has been removed from the cache and will no + * longer be accessed. After this point, the cache cookie may be destroyed. */ -static inline bool fscache_use_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - return atomic_inc_not_zero(&cookie->n_active) != 0; -} - -static inline bool __fscache_unuse_cookie(struct fscache_cookie *cookie) -{ - return atomic_dec_and_test(&cookie->n_active); -} - -static inline void __fscache_wake_unused_cookie(struct fscache_cookie *cookie) +static inline void fscache_uncount_object(struct fscache_cache *cache) { - wake_up_var(&cookie->n_active); + if (atomic_dec_and_test(&cache->object_count)) + wake_up_all(&fscache_clearance_waiters); } /** - * fscache_unuse_cookie - Cease usage of cookie attached to an object - * @object: Object description - * - * Cease usage of the cookie attached to an object. When the users count - * reaches zero then the cookie relinquishment will be permitted to proceed. - */ -static inline void fscache_unuse_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - if (__fscache_unuse_cookie(cookie)) - __fscache_wake_unused_cookie(cookie); -} - -/* - * out-of-line cache backend functions - */ -extern __printf(3, 4) -void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, ...); - -extern int fscache_add_cache(struct fscache_cache *cache, - struct fscache_object *fsdef, - const char *tagname); -extern void fscache_withdraw_cache(struct fscache_cache *cache); - -extern void fscache_io_error(struct fscache_cache *cache); - -extern void fscache_mark_page_cached(struct fscache_retrieval *op, - struct page *page); - -extern void fscache_mark_pages_cached(struct fscache_retrieval *op, - struct pagevec *pagevec); - -extern bool fscache_object_sleep_till_congested(signed long *timeoutp); - -extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, - const void *data, - uint16_t datalen, - loff_t object_size); - -extern void fscache_object_retrying_stale(struct fscache_object *object); - -enum fscache_why_object_killed { - FSCACHE_OBJECT_IS_STALE, - FSCACHE_OBJECT_NO_SPACE, - FSCACHE_OBJECT_WAS_RETIRED, - FSCACHE_OBJECT_WAS_CULLED, -}; -extern void fscache_object_mark_killed(struct fscache_object *object, - enum fscache_why_object_killed why); + * fscache_wait_for_objects - Wait for all objects to be withdrawn + * @cache: The cache to query + * + * Wait for all extant objects in a cache to finish being withdrawn + * and go away. + */ +static inline void fscache_wait_for_objects(struct fscache_cache *cache) +{ + wait_event(fscache_clearance_waiters, + atomic_read(&cache->object_count) == 0); +} + +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_read; +extern atomic_t fscache_n_write; +extern atomic_t fscache_n_no_write_space; +extern atomic_t fscache_n_no_create_space; +extern atomic_t fscache_n_culled; +#define fscache_count_read() atomic_inc(&fscache_n_read) +#define fscache_count_write() atomic_inc(&fscache_n_write) +#define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) +#define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) +#define fscache_count_culled() atomic_inc(&fscache_n_culled) +#else +#define fscache_count_read() do {} while(0) +#define fscache_count_write() do {} while(0) +#define fscache_count_no_write_space() do {} while(0) +#define fscache_count_no_create_space() do {} while(0) +#define fscache_count_culled() do {} while(0) +#endif #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 3b2282c157f7..6727fb0db619 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -15,146 +15,126 @@ #define _LINUX_FSCACHE_H #include <linux/fs.h> -#include <linux/list.h> -#include <linux/pagemap.h> -#include <linux/pagevec.h> -#include <linux/list_bl.h> #include <linux/netfs.h> +#include <linux/writeback.h> #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) +#define __fscache_available (1) #define fscache_available() (1) +#define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) +#define fscache_resources_valid(cres) ((cres)->cache_priv) +#define fscache_cookie_enabled(cookie) (cookie && !test_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) #else +#define __fscache_available (0) #define fscache_available() (0) +#define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) +#define fscache_resources_valid(cres) (false) +#define fscache_cookie_enabled(cookie) (0) #endif - -/* pattern used to fill dead space in an index entry */ -#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79 - -struct pagevec; -struct fscache_cache_tag; struct fscache_cookie; -struct fscache_netfs; -struct netfs_read_request; - -typedef void (*fscache_rw_complete_t)(struct page *page, - void *context, - int error); - -/* result of index entry consultation */ -enum fscache_checkaux { - FSCACHE_CHECKAUX_OKAY, /* entry okay as is */ - FSCACHE_CHECKAUX_NEEDS_UPDATE, /* entry requires update */ - FSCACHE_CHECKAUX_OBSOLETE, /* entry requires deletion */ -}; -/* - * fscache cookie definition - */ -struct fscache_cookie_def { - /* name of cookie type */ - char name[16]; - - /* cookie type */ - uint8_t type; -#define FSCACHE_COOKIE_TYPE_INDEX 0 -#define FSCACHE_COOKIE_TYPE_DATAFILE 1 - - /* select the cache into which to insert an entry in this index - * - optional - * - should return a cache identifier or NULL to cause the cache to be - * inherited from the parent if possible or the first cache picked - * for a non-index file if not - */ - struct fscache_cache_tag *(*select_cache)( - const void *parent_netfs_data, - const void *cookie_netfs_data); - - /* consult the netfs about the state of an object - * - this function can be absent if the index carries no state data - * - the netfs data from the cookie being used as the target is - * presented, as is the auxiliary data and the object size - */ - enum fscache_checkaux (*check_aux)(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size); - - /* get an extra reference on a read context - * - this function can be absent if the completion function doesn't - * require a context - */ - void (*get_context)(void *cookie_netfs_data, void *context); +#define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ +#define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ +#define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ - /* release an extra reference on a read context - * - this function can be absent if the completion function doesn't - * require a context - */ - void (*put_context)(void *cookie_netfs_data, void *context); +#define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ - /* indicate page that now have cache metadata retained - * - this function should mark the specified page as now being cached - * - the page will have been marked with PG_fscache before this is - * called, so this is optional - */ - void (*mark_page_cached)(void *cookie_netfs_data, - struct address_space *mapping, - struct page *page); +enum fscache_want_state { + FSCACHE_WANT_PARAMS, + FSCACHE_WANT_WRITE, + FSCACHE_WANT_READ, }; /* - * fscache cached network filesystem type - * - name, version and ops must be filled in before registration - * - all other fields will be set during registration + * Data object state. + */ +enum fscache_cookie_state { + FSCACHE_COOKIE_STATE_QUIESCENT, /* The cookie is uncached */ + FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ + FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ + FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ + FSCACHE_COOKIE_STATE_INVALIDATING, /* The cache is being invalidated */ + FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ + FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ + FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ + FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ + FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ +#define FSCACHE_COOKIE_STATE__NR (FSCACHE_COOKIE_STATE_DROPPED + 1) +} __attribute__((mode(byte))); + +/* + * Volume representation cookie. */ -struct fscache_netfs { - uint32_t version; /* indexing version */ - const char *name; /* filesystem name */ - struct fscache_cookie *primary_index; +struct fscache_volume { + refcount_t ref; + atomic_t n_cookies; /* Number of data cookies in volume */ + atomic_t n_accesses; /* Number of cache accesses in progress */ + unsigned int debug_id; + unsigned int key_hash; /* Hash of key string */ + char *key; /* Volume ID, eg. "afs@example.com@1234" */ + struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ + struct hlist_bl_node hash_link; /* Link in hash table */ + struct work_struct work; + struct fscache_cache *cache; /* The cache in which this resides */ + void *cache_priv; /* Cache private data */ + spinlock_t lock; + unsigned long flags; +#define FSCACHE_VOLUME_RELINQUISHED 0 /* Volume is being cleaned up */ +#define FSCACHE_VOLUME_INVALIDATE 1 /* Volume was invalidated */ +#define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ +#define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ +#define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ + u8 coherency_len; /* Length of the coherency data */ + u8 coherency[]; /* Coherency data */ }; /* - * data file or index object cookie + * Data file representation cookie. * - a file will only appear in one cache * - a request to cache a file may or may not be honoured, subject to * constraints such as disk space * - indices are created on disk just-in-time */ struct fscache_cookie { - refcount_t ref; /* number of users of this cookie */ - atomic_t n_children; /* number of children of this cookie */ - atomic_t n_active; /* number of active users of netfs ptrs */ + refcount_t ref; + atomic_t n_active; /* number of active users of cookie */ + atomic_t n_accesses; /* Number of cache accesses in progress */ unsigned int debug_id; + unsigned int inval_counter; /* Number of invalidations made */ spinlock_t lock; - spinlock_t stores_lock; /* lock on page store tree */ - struct hlist_head backing_objects; /* object(s) backing this file/index */ - const struct fscache_cookie_def *def; /* definition */ - struct fscache_cookie *parent; /* parent of this entry */ + struct fscache_volume *volume; /* Parent volume of this file. */ + void *cache_priv; /* Cache-side representation */ struct hlist_bl_node hash_link; /* Link in hash table */ struct list_head proc_link; /* Link in proc list */ - void *netfs_data; /* back pointer to netfs */ - struct radix_tree_root stores; /* pages to be stored on this cookie */ -#define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ -#define FSCACHE_COOKIE_STORING_TAG 1 /* pages tag: writing to cache */ - + struct list_head commit_link; /* Link in commit queue */ + struct work_struct work; /* Commit/relinq/withdraw work */ + loff_t object_size; /* Size of the netfs object */ + unsigned long unused_at; /* Time at which unused (jiffies) */ unsigned long flags; -#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ -#define FSCACHE_COOKIE_NO_DATA_YET 1 /* T if new object with no cached data yet */ -#define FSCACHE_COOKIE_UNAVAILABLE 2 /* T if cookie is unavailable (error, etc) */ -#define FSCACHE_COOKIE_INVALIDATING 3 /* T if cookie is being invalidated */ -#define FSCACHE_COOKIE_RELINQUISHED 4 /* T if cookie has been relinquished */ -#define FSCACHE_COOKIE_ENABLED 5 /* T if cookie is enabled */ -#define FSCACHE_COOKIE_ENABLEMENT_LOCK 6 /* T if cookie is being en/disabled */ -#define FSCACHE_COOKIE_AUX_UPDATED 8 /* T if the auxiliary data was updated */ -#define FSCACHE_COOKIE_ACQUIRED 9 /* T if cookie is in use */ -#define FSCACHE_COOKIE_RELINQUISHING 10 /* T if cookie is being relinquished */ - - u8 type; /* Type of object */ +#define FSCACHE_COOKIE_RELINQUISHED 0 /* T if cookie has been relinquished */ +#define FSCACHE_COOKIE_RETIRED 1 /* T if this cookie has retired on relinq */ +#define FSCACHE_COOKIE_IS_CACHING 2 /* T if this cookie is cached */ +#define FSCACHE_COOKIE_NO_DATA_TO_READ 3 /* T if this cookie has nothing to read */ +#define FSCACHE_COOKIE_NEEDS_UPDATE 4 /* T if attrs have been updated */ +#define FSCACHE_COOKIE_HAS_BEEN_CACHED 5 /* T if cookie needs withdraw-on-relinq */ +#define FSCACHE_COOKIE_DISABLED 6 /* T if cookie has been disabled */ +#define FSCACHE_COOKIE_LOCAL_WRITE 7 /* T if cookie has been modified locally */ +#define FSCACHE_COOKIE_NO_ACCESS_WAKE 8 /* T if no wake when n_accesses goes 0 */ +#define FSCACHE_COOKIE_DO_RELINQUISH 9 /* T if this cookie needs relinquishment */ +#define FSCACHE_COOKIE_DO_WITHDRAW 10 /* T if this cookie needs withdrawing */ +#define FSCACHE_COOKIE_DO_LRU_DISCARD 11 /* T if this cookie needs LRU discard */ +#define FSCACHE_COOKIE_DO_PREP_TO_WRITE 12 /* T if cookie needs write preparation */ +#define FSCACHE_COOKIE_HAVE_DATA 13 /* T if this cookie has data stored */ +#define FSCACHE_COOKIE_IS_HASHED 14 /* T if this cookie is hashed */ + + enum fscache_cookie_state state; + u8 advice; /* FSCACHE_ADV_* */ u8 key_len; /* Length of index key */ u8 aux_len; /* Length of auxiliary data */ - u32 key_hash; /* Hash of parent, type, key, len */ + u32 key_hash; /* Hash of volume, key, len */ union { void *key; /* Index key */ u8 inline_key[16]; /* - If the key is short enough */ @@ -165,11 +145,6 @@ struct fscache_cookie { }; }; -static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) -{ - return fscache_cookie_valid(cookie) && test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); -} - /* * slow-path functions for when there is actually caching available, and the * netfs does actually have a valid token @@ -177,699 +152,544 @@ static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) * - these are undefined symbols when FS-Cache is not configured and the * optimiser takes care of not using them */ -extern int __fscache_register_netfs(struct fscache_netfs *); -extern void __fscache_unregister_netfs(struct fscache_netfs *); -extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); -extern void __fscache_release_cache_tag(struct fscache_cache_tag *); +extern struct fscache_volume *__fscache_acquire_volume(const char *, const char *, + const void *, size_t); +extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); extern struct fscache_cookie *__fscache_acquire_cookie( - struct fscache_cookie *, - const struct fscache_cookie_def *, + struct fscache_volume *, + u8, const void *, size_t, const void *, size_t, - void *, loff_t, bool); -extern void __fscache_relinquish_cookie(struct fscache_cookie *, const void *, bool); -extern int __fscache_check_consistency(struct fscache_cookie *, const void *); -extern void __fscache_update_cookie(struct fscache_cookie *, const void *); -extern int __fscache_attr_changed(struct fscache_cookie *); -extern void __fscache_invalidate(struct fscache_cookie *); -extern void __fscache_wait_on_invalidate(struct fscache_cookie *); - -#ifdef FSCACHE_USE_NEW_IO_API -extern int __fscache_begin_read_operation(struct netfs_read_request *, struct fscache_cookie *); -#else -extern int __fscache_read_or_alloc_page(struct fscache_cookie *, - struct page *, - fscache_rw_complete_t, - void *, - gfp_t); -extern int __fscache_read_or_alloc_pages(struct fscache_cookie *, - struct address_space *, - struct list_head *, - unsigned *, - fscache_rw_complete_t, - void *, - gfp_t); -extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t); -extern int __fscache_write_page(struct fscache_cookie *, struct page *, loff_t, gfp_t); -extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); -extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); -extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); -extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, - gfp_t); -extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, - struct inode *); -extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages); -#endif /* FSCACHE_USE_NEW_IO_API */ - -extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); -extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, - bool (*)(void *), void *); + loff_t); +extern void __fscache_use_cookie(struct fscache_cookie *, bool); +extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); +extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); +extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); +extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); +extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); +extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); + +extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, + loff_t, size_t, loff_t, netfs_io_terminated_t, void *, + bool); +extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** - * fscache_register_netfs - Register a filesystem as desiring caching services - * @netfs: The description of the filesystem + * fscache_acquire_volume - Register a volume as desiring caching services + * @volume_key: An identification string for the volume + * @cache_name: The name of the cache to use (or NULL for the default) + * @coherency_data: Piece of arbitrary coherency data to check (or NULL) + * @coherency_len: The size of the coherency data * - * Register a filesystem as desiring caching services if they're available. + * Register a volume as desiring caching services if they're available. The + * caller must provide an identifier for the volume and may also indicate which + * cache it should be in. If a preexisting volume entry is found in the cache, + * the coherency data must match otherwise the entry will be invalidated. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Returns a cookie pointer on success, -ENOMEM if out of memory or -EBUSY if a + * cache volume of that name is already acquired. Note that "NULL" is a valid + * cookie pointer and can be returned if caching is refused. */ static inline -int fscache_register_netfs(struct fscache_netfs *netfs) +struct fscache_volume *fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) { - if (fscache_available()) - return __fscache_register_netfs(netfs); - else - return 0; + if (!fscache_available()) + return NULL; + return __fscache_acquire_volume(volume_key, cache_name, + coherency_data, coherency_len); } /** - * fscache_unregister_netfs - Indicate that a filesystem no longer desires - * caching services - * @netfs: The description of the filesystem + * fscache_relinquish_volume - Cease caching a volume + * @volume: The volume cookie + * @coherency_data: Piece of arbitrary coherency data to set (or NULL) + * @invalidate: True if the volume should be invalidated * - * Indicate that a filesystem no longer desires caching services for the - * moment. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Indicate that a filesystem no longer desires caching services for a volume. + * The caller must have relinquished all file cookies prior to calling this. + * The stored coherency data is updated. */ static inline -void fscache_unregister_netfs(struct fscache_netfs *netfs) +void fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) { - if (fscache_available()) - __fscache_unregister_netfs(netfs); + if (fscache_volume_valid(volume)) + __fscache_relinquish_volume(volume, coherency_data, invalidate); } /** - * fscache_lookup_cache_tag - Look up a cache tag - * @name: The name of the tag to search for + * fscache_acquire_cookie - Acquire a cookie to represent a cache object + * @volume: The volume in which to locate/create this cookie + * @advice: Advice flags (FSCACHE_COOKIE_ADV_*) + * @index_key: The index key for this cookie + * @index_key_len: Size of the index key + * @aux_data: The auxiliary data for the cookie (may be NULL) + * @aux_data_len: Size of the auxiliary data buffer + * @object_size: The initial size of object * - * Acquire a specific cache referral tag that can be used to select a specific - * cache in which to cache an index. + * Acquire a cookie to represent a data file within the given cache volume. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) +struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, + u8 advice, + const void *index_key, + size_t index_key_len, + const void *aux_data, + size_t aux_data_len, + loff_t object_size) { - if (fscache_available()) - return __fscache_lookup_cache_tag(name); - else + if (!fscache_volume_valid(volume)) return NULL; + return __fscache_acquire_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); } /** - * fscache_release_cache_tag - Release a cache tag - * @tag: The tag to release - * - * Release a reference to a cache referral tag previously looked up. + * fscache_use_cookie - Request usage of cookie attached to an object + * @object: Object description + * @will_modify: If cache is expected to be modified locally * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Request usage of the cookie attached to an object. The caller should tell + * the cache if the object's contents are about to be modified locally and then + * the cache can apply the policy that has been set to handle this case. */ -static inline -void fscache_release_cache_tag(struct fscache_cache_tag *tag) +static inline void fscache_use_cookie(struct fscache_cookie *cookie, + bool will_modify) { - if (fscache_available()) - __fscache_release_cache_tag(tag); + if (fscache_cookie_valid(cookie)) + __fscache_use_cookie(cookie, will_modify); } /** - * fscache_acquire_cookie - Acquire a cookie to represent a cache object - * @parent: The cookie that's to be the parent of this one - * @def: A description of the cache object, including callback operations - * @index_key: The index key for this cookie - * @index_key_len: Size of the index key - * @aux_data: The auxiliary data for the cookie (may be NULL) - * @aux_data_len: Size of the auxiliary data buffer - * @netfs_data: An arbitrary piece of data to be kept in the cookie to - * represent the cache object to the netfs - * @object_size: The initial size of object - * @enable: Whether or not to enable a data cookie immediately + * fscache_unuse_cookie - Cease usage of cookie attached to an object + * @object: Object description + * @aux_data: Updated auxiliary data (or NULL) + * @object_size: Revised size of the object (or NULL) * - * This function is used to inform FS-Cache about part of an index hierarchy - * that can be used to locate files. This is done by requesting a cookie for - * each index in the path to the file. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Cease usage of the cookie attached to an object. When the users count + * reaches zero then the cookie relinquishment will be permitted to proceed. */ -static inline -struct fscache_cookie *fscache_acquire_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, - const void *index_key, - size_t index_key_len, - const void *aux_data, - size_t aux_data_len, - void *netfs_data, - loff_t object_size, - bool enable) +static inline void fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, + const loff_t *object_size) { - if (fscache_cookie_valid(parent) && fscache_cookie_enabled(parent)) - return __fscache_acquire_cookie(parent, def, - index_key, index_key_len, - aux_data, aux_data_len, - netfs_data, object_size, enable); - else - return NULL; + if (fscache_cookie_valid(cookie)) + __fscache_unuse_cookie(cookie, aux_data, object_size); } /** * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding * it * @cookie: The cookie being returned - * @aux_data: The updated auxiliary data for the cookie (may be NULL) * @retire: True if the cache object the cookie represents is to be discarded * * This function returns a cookie to the cache, forcibly discarding the - * associated cache object if retire is set to true. The opportunity is - * provided to update the auxiliary data in the cache before the object is - * disconnected. + * associated cache object if retire is set to true. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -void fscache_relinquish_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool retire) +void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) { if (fscache_cookie_valid(cookie)) - __fscache_relinquish_cookie(cookie, aux_data, retire); + __fscache_relinquish_cookie(cookie, retire); } -/** - * fscache_check_consistency - Request validation of a cache's auxiliary data - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an consistency check from fscache, which passes the request to the - * backing cache. The auxiliary data on the cookie will be updated first if - * @aux_data is set. - * - * Returns 0 if consistent and -ESTALE if inconsistent. May also - * return -ENOMEM and -ERESTARTSYS. +/* + * Find the auxiliary data on a cookie. */ -static inline -int fscache_check_consistency(struct fscache_cookie *cookie, - const void *aux_data) +static inline void *fscache_get_aux(struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_check_consistency(cookie, aux_data); + if (cookie->aux_len <= sizeof(cookie->inline_aux)) + return cookie->inline_aux; else - return 0; + return cookie->aux; } -/** - * fscache_update_cookie - Request that a cache object be updated - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an update of the index data for the cache object associated with the - * cookie. The auxiliary data on the cookie will be updated first if @aux_data - * is set. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. +/* + * Update the auxiliary data on a cookie. */ static inline -void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) +void fscache_update_aux(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_update_cookie(cookie, aux_data); + void *p = fscache_get_aux(cookie); + + if (aux_data && p) + memcpy(p, aux_data, cookie->aux_len); + if (object_size) + cookie->object_size = *object_size; } -/** - * fscache_pin_cookie - Pin a data-storage cache object in its cache - * @cookie: The cookie representing the cache object - * - * Permit data-storage cache objects to be pinned in the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_updates; +#endif + static inline -int fscache_pin_cookie(struct fscache_cookie *cookie) +void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) { - return -ENOBUFS; +#ifdef CONFIG_FSCACHE_STATS + atomic_inc(&fscache_n_updates); +#endif + fscache_update_aux(cookie, aux_data, object_size); + smp_wmb(); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } /** - * fscache_pin_cookie - Unpin a data-storage cache object in its cache + * fscache_update_cookie - Request that a cache object be updated * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @object_size: The current size of the object (may be NULL) * - * Permit data-storage cache objects to be unpinned from the cache. + * Request an update of the index data for the cache object associated with the + * cookie. The auxiliary data on the cookie will be updated first if @aux_data + * is set and the object size will be updated and the object possibly trimmed + * if @object_size is set. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -void fscache_unpin_cookie(struct fscache_cookie *cookie) +void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) { + if (fscache_cookie_enabled(cookie)) + __fscache_update_cookie(cookie, aux_data, object_size); } /** - * fscache_attr_changed - Notify cache that an object's attributes changed + * fscache_resize_cookie - Request that a cache object be resized * @cookie: The cookie representing the cache object + * @new_size: The new size of the object (may be NULL) * - * Send a notification to the cache indicating that an object's attributes have - * changed. This includes the data size. These attributes will be obtained - * through the get_attr() cookie definition op. + * Request that the size of an object be changed. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete + * See Documentation/filesystems/caching/netfs-api.txt for a complete * description. */ static inline -int fscache_attr_changed(struct fscache_cookie *cookie) +void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_attr_changed(cookie); - else - return -ENOBUFS; + if (fscache_cookie_enabled(cookie)) + __fscache_resize_cookie(cookie, new_size); } /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @size: The revised size of the object. + * @flags: Invalidation flags (FSCACHE_INVAL_*) * * Notify the cache that an object is needs to be invalidated and that it - * should abort any retrievals or stores it is doing on the cache. The object - * is then marked non-caching until such time as the invalidation is complete. + * should abort any retrievals or stores it is doing on the cache. This + * increments inval_counter on the cookie which can be used by the caller to + * reconsider I/O requests as they complete. * - * This can be called with spinlocks held. + * If @flags has FSCACHE_INVAL_DIO_WRITE set, this indicates that this is due + * to a direct I/O write and will cause caching to be disabled on this cookie + * until it is completely unused. * * See Documentation/filesystems/caching/netfs-api.rst for a complete * description. */ static inline -void fscache_invalidate(struct fscache_cookie *cookie) +void fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t size, unsigned int flags) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_invalidate(cookie); + if (fscache_cookie_enabled(cookie)) + __fscache_invalidate(cookie, aux_data, size, flags); } /** - * fscache_wait_on_invalidate - Wait for invalidation to complete - * @cookie: The cookie representing the cache object - * - * Wait for the invalidation of an object to complete. + * fscache_operation_valid - Return true if operations resources are usable + * @cres: The resources to check. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Returns a pointer to the operations table if usable or NULL if not. */ static inline -void fscache_wait_on_invalidate(struct fscache_cookie *cookie) +const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_resources *cres) { - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_invalidate(cookie); + return fscache_resources_valid(cres) ? cres->ops : NULL; } /** - * fscache_reserve_space - Reserve data space for a cached object - * @cookie: The cookie representing the cache object - * @i_size: The amount of space to be reserved - * - * Reserve an amount of space in the cache for the cache object attached to a - * cookie so that a write to that object within the space can always be - * honoured. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) -{ - return -ENOBUFS; -} - -#ifdef FSCACHE_USE_NEW_IO_API - -/** * fscache_begin_read_operation - Begin a read operation for the netfs lib - * @rreq: The read request being undertaken + * @cres: The cache resources for the read being performed * @cookie: The cookie representing the cache object * - * Begin a read operation on behalf of the netfs helper library. @rreq - * indicates the read request to which the operation state should be attached; - * @cookie indicates the cache object that will be accessed. + * Begin a read operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. * * This is intended to be called from the ->begin_cache_operation() netfs lib * operation as implemented by the network filesystem. * + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. + * * Returns: * * 0 - Success * * -ENOBUFS - No caching available * * Other error code from the cache, such as -ENOMEM. */ static inline -int fscache_begin_read_operation(struct netfs_read_request *rreq, +int fscache_begin_read_operation(struct netfs_cache_resources *cres, struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_begin_read_operation(rreq, cookie); + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_read_operation(cres, cookie); return -ENOBUFS; } -#else /* FSCACHE_USE_NEW_IO_API */ - /** - * fscache_read_or_alloc_page - Read a page from the cache or allocate a block - * in which to store it - * @cookie: The cookie representing the cache object - * @page: The netfs page to fill if possible - * @end_io_func: The callback to invoke when and if the page is filled - * @context: An arbitrary piece of data to pass on to end_io_func() - * @gfp: The conditions under which memory allocation should be made - * - * Read a page from the cache, or if that's not possible make a potential - * one-block reservation in the cache into which the page may be stored once - * fetched from the server. - * - * If the page is not backed by the cache object, or if it there's some reason - * it can't be, -ENOBUFS will be returned and nothing more will be done for - * that page. - * - * Else, if that page is backed by the cache, a read will be initiated directly - * to the netfs's page and 0 will be returned by this function. The - * end_io_func() callback will be invoked when the operation terminates on a - * completion or failure. Note that the callback may be invoked before the - * return. + * fscache_end_operation - End the read operation for the netfs lib + * @cres: The cache resources for the read operation * - * Else, if the page is unbacked, -ENODATA is returned and a block may have - * been allocated in the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Clean up the resources at the end of the read request. */ -static inline -int fscache_read_or_alloc_page(struct fscache_cookie *cookie, - struct page *page, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) +static inline void fscache_end_operation(struct netfs_cache_resources *cres) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_page(cookie, page, end_io_func, - context, gfp); - else - return -ENOBUFS; -} + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); -/** - * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate - * blocks in which to store them - * @cookie: The cookie representing the cache object - * @mapping: The netfs inode mapping to which the pages will be attached - * @pages: A list of potential netfs pages to be filled - * @nr_pages: Number of pages to be read and/or allocated - * @end_io_func: The callback to invoke when and if each page is filled - * @context: An arbitrary piece of data to pass on to end_io_func() - * @gfp: The conditions under which memory allocation should be made - * - * Read a set of pages from the cache, or if that's not possible, attempt to - * make a potential one-block reservation for each page in the cache into which - * that page may be stored once fetched from the server. - * - * If some pages are not backed by the cache object, or if it there's some - * reason they can't be, -ENOBUFS will be returned and nothing more will be - * done for that pages. - * - * Else, if some of the pages are backed by the cache, a read will be initiated - * directly to the netfs's page and 0 will be returned by this function. The - * end_io_func() callback will be invoked when the operation terminates on a - * completion or failure. Note that the callback may be invoked before the - * return. - * - * Else, if a page is unbacked, -ENODATA is returned and a block may have - * been allocated in the cache. - * - * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in - * regard to different pages, the return values are prioritised in that order. - * Any pages submitted for reading are removed from the pages list. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_pages(cookie, mapping, pages, - nr_pages, end_io_func, - context, gfp); - else - return -ENOBUFS; + if (ops) + ops->end_operation(cres); } /** - * fscache_alloc_page - Allocate a block in which to store a page - * @cookie: The cookie representing the cache object - * @page: The netfs page to allocate a page for - * @gfp: The conditions under which memory allocation should be made + * fscache_read - Start a read from the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The buffer to fill - and also the length + * @read_hole: How to handle a hole in the data. + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func * - * Request Allocation a block in the cache in which to store a netfs page - * without retrieving any contents from the cache. + * Start a read from the cache. @cres indicates the cache object to read from + * and must be obtained by a call to fscache_begin_operation() beforehand. * - * If the page is not backed by a file then -ENOBUFS will be returned and - * nothing more will be done, and no reservation will be made. + * The data is read into the iterator, @iter, and that also indicates the size + * of the operation. @start_pos is the start position in the file, though if + * @seek_data is set appropriately, the cache can use SEEK_DATA to find the + * next piece of data, writing zeros for the hole into the iterator. * - * Else, a block will be allocated if one wasn't already, and 0 will be - * returned + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_alloc_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_alloc_page(cookie, page, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_readpages_cancel - Cancel read/alloc on pages - * @cookie: The cookie representing the inode's cache object. - * @pages: The netfs pages that we canceled write on in readpages() + * @read_hole indicates how a partially populated region in the cache should be + * handled. It can be one of a number of settings: + * + * NETFS_READ_HOLE_IGNORE - Just try to read (may return a short read). * - * Uncache/unreserve the pages reserved earlier in readpages() via - * fscache_readpages_or_alloc() and similar. In most successful caches in - * readpages() this doesn't do anything. In cases when the underlying netfs's - * readahead failed we need to clean up the pagelist (unmark and uncache). + * NETFS_READ_HOLE_CLEAR - Seek for data, clearing the part of the buffer + * skipped over, then do as for IGNORE. * - * This function may sleep as it may have to clean up disk state. + * NETFS_READ_HOLE_FAIL - Give ENODATA if we encounter a hole. */ static inline -void fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages) +int fscache_read(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + enum netfs_read_from_hole read_hole, + netfs_io_terminated_t term_func, + void *term_func_priv) { - if (fscache_cookie_valid(cookie)) - __fscache_readpages_cancel(cookie, pages); + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->read(cres, start_pos, iter, read_hole, + term_func, term_func_priv); } /** - * fscache_write_page - Request storage of a page in the cache + * fscache_begin_write_operation - Begin a write operation for the netfs lib + * @cres: The cache resources for the write being performed * @cookie: The cookie representing the cache object - * @page: The netfs page to store - * @object_size: Updated size of object - * @gfp: The conditions under which memory allocation should be made * - * Request the contents of the netfs page be written into the cache. This - * request may be ignored if no cache block is currently allocated, in which - * case it will return -ENOBUFS. + * Begin a write operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. * - * If a cache block was already allocated, a write will be initiated and 0 will - * be returned. The PG_fscache_write page bit is set immediately and will then - * be cleared at the completion of the write to indicate the success or failure - * of the operation. Note that the completion may happen before the return. + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Returns: + * * 0 - Success + * * -ENOBUFS - No caching available + * * Other error code from the cache, such as -ENOMEM. */ static inline -int fscache_write_page(struct fscache_cookie *cookie, - struct page *page, - loff_t object_size, - gfp_t gfp) +int fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_write_page(cookie, page, object_size, gfp); - else - return -ENOBUFS; + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_write_operation(cres, cookie); + return -ENOBUFS; } /** - * fscache_uncache_page - Indicate that caching is no longer required on a page - * @cookie: The cookie representing the cache object - * @page: The netfs page that was being cached. + * fscache_write - Start a write to the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The data to write - and also the length + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func * - * Tell the cache that we no longer want a page to be cached and that it should - * remove any knowledge of the netfs page it may have. + * Start a write to the cache. @cres indicates the cache object to write to and + * must be obtained by a call to fscache_begin_operation() beforehand. * - * Note that this cannot cancel any outstanding I/O operations between this - * page and the cache. + * The data to be written is obtained from the iterator, @iter, and that also + * indicates the size of the operation. @start_pos is the start position in + * the file. * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. */ static inline -void fscache_uncache_page(struct fscache_cookie *cookie, - struct page *page) +int fscache_write(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) { - if (fscache_cookie_valid(cookie)) - __fscache_uncache_page(cookie, page); + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->write(cres, start_pos, iter, term_func, term_func_priv); } /** - * fscache_check_page_write - Ask if a page is being writing to the cache + * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * - * Ask the cache if a page is being written to the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -bool fscache_check_page_write(struct fscache_cookie *cookie, - struct page *page) + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to unlock + * @caching: If PG_fscache has been set + * + * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's + * waiting. + */ +static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, + bool caching) { - if (fscache_cookie_valid(cookie)) - return __fscache_check_page_write(cookie, page); - return false; + if (caching) + __fscache_clear_page_bits(mapping, start, len); } /** - * fscache_wait_on_page_write - Wait for a page to complete writing to the cache + * fscache_write_to_cache - Save a write to the cache and clear PG_fscache * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * - * Ask the cache to wake us up when a page is no longer being written to the - * cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_wait_on_page_write(struct fscache_cookie *cookie, - struct page *page) + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to write back + * @i_size: The new size of the inode + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * @caching: If PG_fscache has been set + * + * Helper function for a netfs to write dirty data from an inode into the cache + * object that's backing it. + * + * @start and @len describe the range of the data. This does not need to be + * page-aligned, but to satisfy DIO requirements, the cache may expand it up to + * the page boundaries on either end. All the pages covering the range must be + * marked with PG_fscache. + * + * If given, @term_func will be called upon completion and supplied with + * @term_func_priv. Note that the PG_fscache flags will have been cleared by + * this point, so the netfs must retain its own pin on the mapping. + */ +static inline void fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool caching) { - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_page_write(cookie, page); -} + if (caching) + __fscache_write_to_cache(cookie, mapping, start, len, i_size, + term_func, term_func_priv, caching); + else if (term_func) + term_func(term_func_priv, -ENOBUFS, false); -/** - * fscache_maybe_release_page - Consider releasing a page, cancelling a store - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * @gfp: The gfp flags passed to releasepage() - * - * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's - * releasepage() call. A storage request on the page may cancelled if it is - * not currently being processed. - * - * The function returns true if the page no longer has a storage request on it, - * and false if a storage request is left in place. If true is returned, the - * page will have been passed to fscache_uncache_page(). If false is returned - * the page cannot be freed yet. - */ -static inline -bool fscache_maybe_release_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && PageFsCache(page)) - return __fscache_maybe_release_page(cookie, page, gfp); - return true; } +#if __fscache_available +bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio, + struct fscache_cookie *cookie); +#else +#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \ + filemap_dirty_folio(MAPPING, FOLIO) +#endif + /** - * fscache_uncache_all_inode_pages - Uncache all an inode's pages - * @cookie: The cookie representing the inode's cache object. - * @inode: The inode to uncache pages from. - * - * Uncache all the pages in an inode that are marked PG_fscache, assuming them - * to be associated with the given cookie. + * fscache_unpin_writeback - Unpin writeback resources + * @wbc: The writeback control + * @cookie: The cookie referring to the cache object * - * This function may sleep. It will wait for pages that are being written out - * and will wait whilst the PG_fscache mark is removed by the cache. + * Unpin the writeback resources pinned by fscache_dirty_folio(). This is + * intended to be called by the netfs's ->write_inode() method. */ -static inline -void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, - struct inode *inode) +static inline void fscache_unpin_writeback(struct writeback_control *wbc, + struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie)) - __fscache_uncache_all_inode_pages(cookie, inode); + if (wbc->unpinned_fscache_wb) + fscache_unuse_cookie(cookie, NULL, NULL); } -#endif /* FSCACHE_USE_NEW_IO_API */ - /** - * fscache_disable_cookie - Disable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @invalidate: Invalidate the backing object - * - * Disable a cookie from accepting further alloc, read, write, invalidate, - * update or acquire operations. Outstanding operations can still be waited - * upon and pages can still be uncached and the cookie relinquished. - * - * This will not return until all outstanding operations have completed. + * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode + * @cookie: The cookie referring to the cache object + * @inode: The inode to clean up + * @aux: Auxiliary data to apply to the inode * - * If @invalidate is set, then the backing object will be invalidated and - * detached, otherwise it will just be detached. - * - * If @aux_data is set, then auxiliary data will be updated from that. + * Clear any writeback resources held by an inode when the inode is evicted. + * This must be called before clear_inode() is called. */ -static inline -void fscache_disable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool invalidate) +static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, + struct inode *inode, + const void *aux) { - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_disable_cookie(cookie, aux_data, invalidate); + if (inode->i_state & I_PINNING_FSCACHE_WB) { + loff_t i_size = i_size_read(inode); + fscache_unuse_cookie(cookie, aux, &i_size); + } } /** - * fscache_enable_cookie - Reenable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @object_size: Current size of object - * @can_enable: A function to permit enablement once lock is held - * @data: Data for can_enable() - * - * Reenable a previously disabled cookie, allowing it to accept further alloc, - * read, write, invalidate, update or acquire operations. An attempt will be - * made to immediately reattach the cookie to a backing object. If @aux_data - * is set, the auxiliary data attached to the cookie will be updated. + * fscache_note_page_release - Note that a netfs page got released + * @cookie: The cookie corresponding to the file * - * The can_enable() function is called (if not NULL) once the enablement lock - * is held to rule on whether enablement is still permitted to go ahead. + * Note that a page that has been copied to the cache has been released. This + * means that future reads will need to look in the cache to see if it's there. */ static inline -void fscache_enable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - loff_t object_size, - bool (*can_enable)(void *data), - void *data) +void fscache_note_page_release(struct fscache_cookie *cookie) { - if (fscache_cookie_valid(cookie) && !fscache_cookie_enabled(cookie)) - __fscache_enable_cookie(cookie, aux_data, object_size, - can_enable, data); + /* If we've written data to the cache (HAVE_DATA) and there wasn't any + * data in the cache when we started (NO_DATA_TO_READ), it may no + * longer be true that we can skip reading from the cache - so clear + * the flag that causes reads to be skipped. + */ + if (cookie && + test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && + test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); } #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 91ea9477e9bd..50d92d805bd8 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -714,6 +714,10 @@ bool fscrypt_mergeable_bio(struct bio *bio, const struct inode *inode, bool fscrypt_mergeable_bio_bh(struct bio *bio, const struct buffer_head *next_bh); +bool fscrypt_dio_supported(struct kiocb *iocb, struct iov_iter *iter); + +u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, u64 nr_blocks); + #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ static inline bool __fscrypt_inode_uses_inline_crypto(const struct inode *inode) @@ -742,6 +746,20 @@ static inline bool fscrypt_mergeable_bio_bh(struct bio *bio, { return true; } + +static inline bool fscrypt_dio_supported(struct kiocb *iocb, + struct iov_iter *iter) +{ + const struct inode *inode = file_inode(iocb->ki_filp); + + return !fscrypt_needs_contents_encryption(inode); +} + +static inline u64 fscrypt_limit_io_blocks(const struct inode *inode, u64 lblk, + u64 nr_blocks) +{ + return nr_blocks; +} #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ /** diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index e026f6c48b49..7b6c42bfb660 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -91,13 +91,13 @@ struct fsl_mc_resource { /** * struct fsl_mc_device_irq - MC object device message-based interrupt - * @msi_desc: pointer to MSI descriptor allocated by fsl_mc_msi_alloc_descs() + * @virq: Linux virtual interrupt number * @mc_dev: MC object device that owns this interrupt * @dev_irq_index: device-relative IRQ index * @resource: MC generic resource associated with the interrupt */ struct fsl_mc_device_irq { - struct msi_desc *msi_desc; + unsigned int virq; struct fsl_mc_device *mc_dev; u8 dev_irq_index; struct fsl_mc_resource resource; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 787545e87eeb..bb8467cd11ae 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -144,16 +144,19 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; + __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; - if (old_dir == new_dir) - old_dir_mask |= FS_DN_RENAME; - if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; + rename_mask |= FS_ISDIR; } + /* Event with information about both old and new parent+name */ + fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, + old_dir, old_name, 0); + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, @@ -222,16 +225,53 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, } /* + * fsnotify_delete - @dentry was unlinked and unhashed + * + * Caller must make sure that dentry->d_name is stable. + * + * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode + * as this may be called after d_delete() and old_dentry may be negative. + */ +static inline void fsnotify_delete(struct inode *dir, struct inode *inode, + struct dentry *dentry) +{ + __u32 mask = FS_DELETE; + + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + + fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, + 0); +} + +/** + * d_delete_notify - delete a dentry and call fsnotify_delete() + * @dentry: The dentry to delete + * + * This helper is used to guaranty that the unlinked inode cannot be found + * by lookup of this name after fsnotify_delete() event has been delivered. + */ +static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + ihold(inode); + d_delete(dentry); + fsnotify_delete(dir, inode, dentry); + iput(inode); +} + +/* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* @@ -255,10 +295,10 @@ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 51ef2b079bfa..0805b74cae44 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -63,7 +63,7 @@ */ #define FS_EVENT_ON_CHILD 0x08000000 -#define FS_DN_RENAME 0x10000000 /* file renamed */ +#define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_IN_ONESHOT 0x80000000 /* only send event once */ @@ -76,7 +76,7 @@ * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ -#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) +#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) @@ -101,7 +101,7 @@ /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ - FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ + FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) @@ -337,58 +337,69 @@ static inline struct fs_error_report *fsnotify_data_error_report( } } +/* + * Index to merged marks iterator array that correlates to a type of watch. + * The type of watched object can be deduced from the iterator type, but not + * the other way around, because an event can match different watched objects + * of the same object type. + * For example, both parent and child are watching an object of type inode. + */ +enum fsnotify_iter_type { + FSNOTIFY_ITER_TYPE_INODE, + FSNOTIFY_ITER_TYPE_VFSMOUNT, + FSNOTIFY_ITER_TYPE_SB, + FSNOTIFY_ITER_TYPE_PARENT, + FSNOTIFY_ITER_TYPE_INODE2, + FSNOTIFY_ITER_TYPE_COUNT +}; + +/* The type of object that a mark is attached to */ enum fsnotify_obj_type { + FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, - FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; -#define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) -#define FSNOTIFY_OBJ_TYPE_PARENT_FL (1U << FSNOTIFY_OBJ_TYPE_PARENT) -#define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) -#define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) -#define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) - -static inline bool fsnotify_valid_obj_type(unsigned int type) +static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { - return (type < FSNOTIFY_OBJ_TYPE_COUNT); + return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { - struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; + struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) { - return (iter_info->report_mask & (1U << type)); + return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) { - iter_info->report_mask |= (1U << type); + iter_info->report_mask |= (1U << iter_type); } static inline void fsnotify_iter_set_report_type_mark( - struct fsnotify_iter_info *iter_info, int type, + struct fsnotify_iter_info *iter_info, int iter_type, struct fsnotify_mark *mark) { - iter_info->marks[type] = mark; - iter_info->report_mask |= (1U << type); + iter_info->marks[iter_type] = mark; + iter_info->report_mask |= (1U << iter_type); } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ - iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ + return (iter_info->report_mask & (1U << FSNOTIFY_ITER_TYPE_##NAME)) ? \ + iter_info->marks[FSNOTIFY_ITER_TYPE_##NAME] : NULL; \ } FSNOTIFY_ITER_FUNCS(inode, INODE) @@ -396,8 +407,8 @@ FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) -#define fsnotify_foreach_obj_type(type) \ - for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_type(type) \ + for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached @@ -590,6 +601,25 @@ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, /* functions used to manipulate the marks attached to inodes */ +/* Get mask for calculating object interest taking ignored mask into account */ +static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) +{ + __u32 mask = mark->mask; + + if (!mark->ignored_mask) + return mask; + + /* Interest in FS_MODIFY may be needed for clearing ignored mask */ + if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) + mask |= FS_MODIFY; + + /* + * If mark is interested in ignoring events on children, the object must + * show interest in those events for fsnotify_parent() to notice it. + */ + return mask | (mark->ignored_mask & ALL_FSNOTIFY_EVENTS); +} + /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ @@ -604,11 +634,11 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, + fsnotify_connp_t *connp, unsigned int obj_type, int allow_dups, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups, + unsigned int obj_type, int allow_dups, __kernel_fsid_t *fsid); /* attach the mark to the inode */ @@ -637,22 +667,23 @@ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); -/* run all the marks in a group, and clear all of the marks attached to given object type */ -extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); +/* Clear all of the marks of a group attached to a given object type */ +extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, + unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9999e29187de..ed8cf433a46a 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -30,6 +30,12 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +#ifdef CONFIG_TRACING +extern void ftrace_boot_snapshot(void); +#else +static inline void ftrace_boot_snapshot(void) { } +#endif + #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops; struct ftrace_regs; @@ -215,7 +221,10 @@ struct ftrace_ops_hash { void ftrace_free_init_mem(void); void ftrace_free_mem(struct module *mod, void *start, void *end); #else -static inline void ftrace_free_init_mem(void) { } +static inline void ftrace_free_init_mem(void) +{ + ftrace_boot_snapshot(); +} static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif @@ -512,6 +521,8 @@ struct dyn_ftrace { int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); +int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, + unsigned int cnt, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -802,6 +813,7 @@ static inline unsigned long ftrace_location(unsigned long ip) #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) #define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) +#define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) diff --git a/include/linux/genhd.h b/include/linux/genhd.h deleted file mode 100644 index 74c410263113..000000000000 --- a/include/linux/genhd.h +++ /dev/null @@ -1,334 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_GENHD_H -#define _LINUX_GENHD_H - -/* - * genhd.h Copyright (C) 1992 Drew Eckhardt - * Generic hard disk header file by - * Drew Eckhardt - * - * <drew@colorado.edu> - */ - -#include <linux/types.h> -#include <linux/kdev_t.h> -#include <linux/uuid.h> -#include <linux/blk_types.h> -#include <linux/device.h> -#include <linux/xarray.h> - -extern const struct device_type disk_type; -extern struct device_type part_type; -extern struct class block_class; - -#define DISK_MAX_PARTS 256 -#define DISK_NAME_LEN 32 - -#define PARTITION_META_INFO_VOLNAMELTH 64 -/* - * Enough for the string representation of any kind of UUID plus NULL. - * EFI UUID is 36 characters. MSDOS UUID is 11 characters. - */ -#define PARTITION_META_INFO_UUIDLTH (UUID_STRING_LEN + 1) - -struct partition_meta_info { - char uuid[PARTITION_META_INFO_UUIDLTH]; - u8 volname[PARTITION_META_INFO_VOLNAMELTH]; -}; - -/** - * DOC: genhd capability flags - * - * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device - * gives access to removable media. - * When set, the device remains present even when media is not - * inserted. - * Must not be set for devices which are removed entirely when the - * media is removed. - * - * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style - * device. - * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. - * - * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include - * partition information in ``/proc/partitions`` or in the output of - * printk_all_partitions(). - * Used for the null block device and some MMC devices. - * - * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended - * dynamic ``dev_t``, i.e. it wants extended device numbers - * (``BLOCK_EXT_MAJOR``). - * This affects the maximum number of partitions. - * - * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the - * partition table, the device's capacity has been extended to its - * native capacity; i.e. the device has hidden capacity used by one - * of the partitions (this is a flag used so that native capacity is - * only ever unlocked once). - * - * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is - * blocked whenever a writer holds an exclusive lock. - * - * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled. - * Used for loop devices in their default settings and some MMC - * devices. - * - * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it - * doesn't produce events, doesn't appear in sysfs, and doesn't have - * an associated ``bdev``. - * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and - * ``GENHD_FL_NO_PART_SCAN``. - * Used for multipath devices. - */ -#define GENHD_FL_REMOVABLE 0x0001 -/* 2 is unused (used to be GENHD_FL_DRIVERFS) */ -/* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ -#define GENHD_FL_CD 0x0008 -#define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 -#define GENHD_FL_EXT_DEVT 0x0040 -#define GENHD_FL_NATIVE_CAPACITY 0x0080 -#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100 -#define GENHD_FL_NO_PART_SCAN 0x0200 -#define GENHD_FL_HIDDEN 0x0400 - -enum { - DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ - DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */ -}; - -enum { - /* Poll even if events_poll_msecs is unset */ - DISK_EVENT_FLAG_POLL = 1 << 0, - /* Forward events to udev */ - DISK_EVENT_FLAG_UEVENT = 1 << 1, -}; - -struct disk_events; -struct badblocks; - -struct blk_integrity { - const struct blk_integrity_profile *profile; - unsigned char flags; - unsigned char tuple_size; - unsigned char interval_exp; - unsigned char tag_size; -}; - -struct gendisk { - /* major, first_minor and minors are input parameters only, - * don't use directly. Use disk_devt() and disk_max_parts(). - */ - int major; /* major number of driver */ - int first_minor; - int minors; /* maximum number of minors, =1 for - * disks that can't be partitioned. */ - - char disk_name[DISK_NAME_LEN]; /* name of major driver */ - - unsigned short events; /* supported events */ - unsigned short event_flags; /* flags related to event processing */ - - struct xarray part_tbl; - struct block_device *part0; - - const struct block_device_operations *fops; - struct request_queue *queue; - void *private_data; - - int flags; - unsigned long state; -#define GD_NEED_PART_SCAN 0 -#define GD_READ_ONLY 1 -#define GD_DEAD 2 - - struct mutex open_mutex; /* open/close mutex */ - unsigned open_partitions; /* number of open partitions */ - - struct backing_dev_info *bdi; - struct kobject *slave_dir; -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED - struct list_head slave_bdevs; -#endif - struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ - struct disk_events *ev; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct kobject integrity_kobj; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ -#if IS_ENABLED(CONFIG_CDROM) - struct cdrom_device_info *cdi; -#endif - int node_id; - struct badblocks *bb; - struct lockdep_map lockdep_map; - u64 diskseq; -}; - -static inline bool disk_live(struct gendisk *disk) -{ - return !inode_unhashed(disk->part0->bd_inode); -} - -/* - * The gendisk is refcounted by the part0 block_device, and the bd_device - * therein is also used for device model presentation in sysfs. - */ -#define dev_to_disk(device) \ - (dev_to_bdev(device)->bd_disk) -#define disk_to_dev(disk) \ - (&((disk)->part0->bd_device)) - -#if IS_REACHABLE(CONFIG_CDROM) -#define disk_to_cdi(disk) ((disk)->cdi) -#else -#define disk_to_cdi(disk) NULL -#endif - -static inline int disk_max_parts(struct gendisk *disk) -{ - if (disk->flags & GENHD_FL_EXT_DEVT) - return DISK_MAX_PARTS; - return disk->minors; -} - -static inline bool disk_part_scan_enabled(struct gendisk *disk) -{ - return disk_max_parts(disk) > 1 && - !(disk->flags & GENHD_FL_NO_PART_SCAN); -} - -static inline dev_t disk_devt(struct gendisk *disk) -{ - return MKDEV(disk->major, disk->first_minor); -} - -void disk_uevent(struct gendisk *disk, enum kobject_action action); - -/* block/genhd.c */ -int __must_check device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline int __must_check add_disk(struct gendisk *disk) -{ - return device_add_disk(NULL, disk, NULL); -} -extern void del_gendisk(struct gendisk *gp); - -void invalidate_disk(struct gendisk *disk); - -void set_disk_ro(struct gendisk *disk, bool read_only); - -static inline int get_disk_ro(struct gendisk *disk) -{ - return disk->part0->bd_read_only || - test_bit(GD_READ_ONLY, &disk->state); -} - -static inline int bdev_read_only(struct block_device *bdev) -{ - return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); -} - -extern void disk_block_events(struct gendisk *disk); -extern void disk_unblock_events(struct gendisk *disk); -extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -bool set_capacity_and_notify(struct gendisk *disk, sector_t size); -bool disk_force_media_change(struct gendisk *disk, unsigned int events); - -/* drivers/char/random.c */ -extern void add_disk_randomness(struct gendisk *disk) __latent_entropy; -extern void rand_initialize_disk(struct gendisk *disk); - -static inline sector_t get_start_sect(struct block_device *bdev) -{ - return bdev->bd_start_sect; -} - -static inline sector_t bdev_nr_sectors(struct block_device *bdev) -{ - return bdev->bd_nr_sectors; -} - -static inline loff_t bdev_nr_bytes(struct block_device *bdev) -{ - return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; -} - -static inline sector_t get_capacity(struct gendisk *disk) -{ - return bdev_nr_sectors(disk->part0); -} - -static inline u64 sb_bdev_nr_blocks(struct super_block *sb) -{ - return bdev_nr_sectors(sb->s_bdev) >> - (sb->s_blocksize_bits - SECTOR_SHIFT); -} - -int bdev_disk_changed(struct gendisk *disk, bool invalidate); -void blk_drop_partitions(struct gendisk *disk); - -struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, - struct lock_class_key *lkclass); -extern void put_disk(struct gendisk *disk); -struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); - -/** - * blk_alloc_disk - allocate a gendisk structure - * @node_id: numa node to allocate on - * - * Allocate and pre-initialize a gendisk structure for use with BIO based - * drivers. - * - * Context: can sleep - */ -#define blk_alloc_disk(node_id) \ -({ \ - static struct lock_class_key __key; \ - \ - __blk_alloc_disk(node_id, &__key); \ -}) -void blk_cleanup_disk(struct gendisk *disk); - -int __register_blkdev(unsigned int major, const char *name, - void (*probe)(dev_t devt)); -#define register_blkdev(major, name) \ - __register_blkdev(major, name, NULL) -void unregister_blkdev(unsigned int major, const char *name); - -bool bdev_check_media_change(struct block_device *bdev); -int __invalidate_device(struct block_device *bdev, bool kill_dirty); -void set_capacity(struct gendisk *disk, sector_t size); - -#ifdef CONFIG_BLOCK_HOLDER_DEPRECATED -int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); -int bd_register_pending_holders(struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -static inline int bd_register_pending_holders(struct gendisk *disk) -{ - return 0; -} -#endif /* CONFIG_BLOCK_HOLDER_DEPRECATED */ - -dev_t part_devt(struct gendisk *disk, u8 partno); -void inc_diskseq(struct gendisk *disk); -dev_t blk_lookup_devt(const char *name, int partno); -void blk_request_module(dev_t devt); -#ifdef CONFIG_BLOCK -void printk_all_partitions(void); -#else /* CONFIG_BLOCK */ -static inline void printk_all_partitions(void) -{ -} -#endif /* CONFIG_BLOCK */ - -#endif /* _LINUX_GENHD_H */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b976c4177299..0fa17fb85de5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -54,9 +54,17 @@ struct vm_area_struct; #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u -#define ___GFP_SKIP_KASAN_POISON 0x1000000u +#ifdef CONFIG_KASAN_HW_TAGS +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u +#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#else +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN_UNPOISON 0 +#define ___GFP_SKIP_KASAN_POISON 0 +#endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x2000000u +#define ___GFP_NOLOCKDEP 0x8000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -79,7 +87,7 @@ struct vm_area_struct; * DOC: Page mobility and placement hints * * Page mobility and placement hints - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * --------------------------------- * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due @@ -112,7 +120,7 @@ struct vm_area_struct; * DOC: Watermark modifiers * * Watermark modifiers -- controls access to emergency reserves - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * ------------------------------------------------------------ * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. @@ -144,7 +152,7 @@ struct vm_area_struct; * DOC: Reclaim modifiers * * Reclaim modifiers - * ~~~~~~~~~~~~~~~~~ + * ----------------- * Please note that all the following flags are only applicable to sleepable * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). * @@ -224,7 +232,7 @@ struct vm_area_struct; * DOC: Action modifiers * * Action modifiers - * ~~~~~~~~~~~~~~~~ + * ---------------- * * %__GFP_NOWARN suppresses allocation failure reports. * @@ -232,31 +240,40 @@ struct vm_area_struct; * * %__GFP_ZERO returns a zeroed page on success. * - * %__GFP_ZEROTAGS returns a page with zeroed memory tags on success, if - * __GFP_ZERO is set. + * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself + * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that + * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting + * memory tags at the same time as zeroing memory has minimal additional + * performace impact. + * + * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. + * Only effective in HW_TAGS mode. * - * %__GFP_SKIP_KASAN_POISON returns a page which does not need to be poisoned - * on deallocation. Typically used for userspace pages. Currently only has an - * effect in HW tags mode. + * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. + * Typically, used for userspace pages. Only effective in HW_TAGS mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) +#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) +#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) +#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (25 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (24 + \ + 3 * IS_ENABLED(CONFIG_KASAN_HW_TAGS) + \ + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** * DOC: Useful GFP flag combinations * * Useful GFP flag combinations - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * ---------------------------- * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear @@ -302,7 +319,9 @@ struct vm_area_struct; * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit - * address. + * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory + * because the DMA32 kmalloc cache array is not implemented. + * (Reason: there is no such user in kernel). * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot @@ -598,9 +617,9 @@ struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); + bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + alloc_pages_vma(gfp_mask, order, vma, addr, true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -610,21 +629,21 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1); +__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) diff --git a/include/linux/gfp_api.h b/include/linux/gfp_api.h new file mode 100644 index 000000000000..5a05a2764a86 --- /dev/null +++ b/include/linux/gfp_api.h @@ -0,0 +1 @@ +#include <linux/gfp.h> diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 97a28ad3393b..c3aa8b330e1c 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -8,27 +8,16 @@ #include <linux/err.h> struct device; - -/** - * Opaque descriptor for a GPIO. These are obtained using gpiod_get() and are - * preferable to the old integer-based handles. - * - * Contrary to integers, a pointer to a gpio_desc is guaranteed to be valid - * until the GPIO is released. - */ struct gpio_desc; - -/** - * Opaque descriptor for a structure of GPIO array attributes. This structure - * is attached to struct gpiod_descs obtained from gpiod_get_array() and can be - * passed back to get/set array functions in order to activate fast processing - * path if applicable. - */ struct gpio_array; /** - * Struct containing an array of descriptors that can be obtained using - * gpiod_get_array(). + * struct gpio_descs - Struct containing an array of descriptors that can be + * obtained using gpiod_get_array() + * + * @info: Pointer to the opaque gpio_array structure + * @ndescs: Number of held descriptors + * @desc: Array of pointers to GPIO descriptors */ struct gpio_descs { struct gpio_array *info; @@ -43,8 +32,16 @@ struct gpio_descs { #define GPIOD_FLAGS_BIT_NONEXCLUSIVE BIT(4) /** - * Optional flags that can be passed to one of gpiod_* to configure direction - * and output value. These values cannot be OR'd. + * enum gpiod_flags - Optional flags that can be passed to one of gpiod_* to + * configure direction and output value. These values + * cannot be OR'd. + * + * @GPIOD_ASIS: Don't change anything + * @GPIOD_IN: Set lines to input mode + * @GPIOD_OUT_LOW: Set lines to output and drive them low + * @GPIOD_OUT_HIGH: Set lines to output and drive them high + * @GPIOD_OUT_LOW_OPEN_DRAIN: Set lines to open-drain output and drive them low + * @GPIOD_OUT_HIGH_OPEN_DRAIN: Set lines to open-drain output and drive them high */ enum gpiod_flags { GPIOD_ASIS = 0, @@ -690,7 +687,6 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -void devm_acpi_dev_remove_driver_gpios(struct device *dev); struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); @@ -708,7 +704,6 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, { return -ENXIO; } -static inline void devm_acpi_dev_remove_driver_gpios(struct device *dev) {} #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index a673a359e20b..b0728c8ad90c 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -289,6 +289,7 @@ struct gpio_irq_chip { * number or the name of the SoC IP-block implementing it. * @gpiodev: the internal state holder, opaque struct * @parent: optional parent device providing the GPIOs + * @fwnode: optional fwnode providing this controller's properties * @owner: helps prevent removal of modules exporting active GPIOs * @request: optional hook for chip-specific activation, such as * enabling module power and clock; may sleep @@ -377,6 +378,7 @@ struct gpio_chip { const char *label; struct gpio_device *gpiodev; struct device *parent; + struct fwnode_handle *fwnode; struct module *owner; int (*request)(struct gpio_chip *gc, diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index d755e529c1e3..2647dd10b541 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -100,6 +100,7 @@ void gpiod_add_lookup_table(struct gpiod_lookup_table *table); void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n); void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); void gpiod_add_hogs(struct gpiod_hog *hogs); +void gpiod_remove_hogs(struct gpiod_hog *hogs); #else /* ! CONFIG_GPIOLIB */ static inline void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {} @@ -108,6 +109,7 @@ void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n) {} static inline void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {} static inline void gpiod_add_hogs(struct gpiod_hog *hogs) {} +static inline void gpiod_remove_hogs(struct gpiod_hog *hogs) {} #endif /* CONFIG_GPIOLIB */ #endif /* __LINUX_GPIO_MACHINE_H */ diff --git a/include/linux/greybus/greybus_manifest.h b/include/linux/greybus/greybus_manifest.h index 6e62fe478712..bef9eb2093e9 100644 --- a/include/linux/greybus/greybus_manifest.h +++ b/include/linux/greybus/greybus_manifest.h @@ -100,7 +100,7 @@ enum { struct greybus_descriptor_string { __u8 length; __u8 id; - __u8 string[0]; + __u8 string[]; } __packed; /* @@ -175,7 +175,7 @@ struct greybus_manifest_header { struct greybus_manifest { struct greybus_manifest_header header; - struct greybus_descriptor descriptors[0]; + struct greybus_descriptor descriptors[]; } __packed; #endif /* __GREYBUS_MANIFEST_H */ diff --git a/include/linux/greybus/hd.h b/include/linux/greybus/hd.h index d3faf0c1a569..718e2857054e 100644 --- a/include/linux/greybus/hd.h +++ b/include/linux/greybus/hd.h @@ -58,7 +58,7 @@ struct gb_host_device { struct gb_svc *svc; /* Private data for the host driver */ - unsigned long hd_priv[0] __aligned(sizeof(s64)); + unsigned long hd_priv[] __aligned(sizeof(s64)); }; #define to_gb_host_device(d) container_of(d, struct gb_host_device, dev) diff --git a/include/linux/greybus/module.h b/include/linux/greybus/module.h index 47b839af145d..3efe2133acfd 100644 --- a/include/linux/greybus/module.h +++ b/include/linux/greybus/module.h @@ -23,7 +23,7 @@ struct gb_module { bool disconnected; - struct gb_interface *interfaces[0]; + struct gb_interface *interfaces[]; }; #define to_gb_module(d) container_of(d, struct gb_module, dev) diff --git a/include/linux/hash.h b/include/linux/hash.h index ad6fa21d977b..38edaa08f862 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val) return val * GOLDEN_RATIO_32; } -#ifndef HAVE_ARCH_HASH_32 -#define hash_32 hash_32_generic -#endif -static inline u32 hash_32_generic(u32 val, unsigned int bits) +static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); diff --git a/include/linux/hashtable_api.h b/include/linux/hashtable_api.h new file mode 100644 index 000000000000..c268ac2c5c0e --- /dev/null +++ b/include/linux/hashtable_api.h @@ -0,0 +1 @@ +#include <linux/hashtable.h> diff --git a/include/linux/hid.h b/include/linux/hid.h index f453be385bd4..4363a63b9775 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -241,6 +241,7 @@ struct hid_item { #define HID_DG_TOUCH 0x000d0033 #define HID_DG_UNTOUCH 0x000d0034 #define HID_DG_TAP 0x000d0035 +#define HID_DG_TRANSDUCER_INDEX 0x000d0038 #define HID_DG_TABLETFUNCTIONKEY 0x000d0039 #define HID_DG_PROGRAMCHANGEKEY 0x000d003a #define HID_DG_BATTERYSTRENGTH 0x000d003b @@ -253,6 +254,15 @@ struct hid_item { #define HID_DG_BARRELSWITCH 0x000d0044 #define HID_DG_ERASER 0x000d0045 #define HID_DG_TABLETPICK 0x000d0046 +#define HID_DG_PEN_COLOR 0x000d005c +#define HID_DG_PEN_LINE_WIDTH 0x000d005e +#define HID_DG_PEN_LINE_STYLE 0x000d0070 +#define HID_DG_PEN_LINE_STYLE_INK 0x000d0072 +#define HID_DG_PEN_LINE_STYLE_PENCIL 0x000d0073 +#define HID_DG_PEN_LINE_STYLE_HIGHLIGHTER 0x000d0074 +#define HID_DG_PEN_LINE_STYLE_CHISEL_MARKER 0x000d0075 +#define HID_DG_PEN_LINE_STYLE_BRUSH 0x000d0076 +#define HID_DG_PEN_LINE_STYLE_NO_PREFERENCE 0x000d0077 #define HID_CP_CONSUMERCONTROL 0x000c0001 #define HID_CP_NUMERICKEYPAD 0x000c0002 @@ -332,12 +342,12 @@ struct hid_item { * HID device quirks. */ -/* +/* * Increase this if you need to configure more HID quirks at module load time */ #define MAX_USBHID_BOOT_QUIRKS 4 -#define HID_QUIRK_INVERT BIT(0) +/* BIT(0) reserved for backward compatibility, was HID_QUIRK_INVERT */ #define HID_QUIRK_NOTOUCH BIT(1) #define HID_QUIRK_IGNORE BIT(2) #define HID_QUIRK_NOGET BIT(3) @@ -349,6 +359,8 @@ struct hid_item { /* BIT(9) reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */ #define HID_QUIRK_ALWAYS_POLL BIT(10) #define HID_QUIRK_INPUT_PER_APP BIT(11) +#define HID_QUIRK_X_INVERT BIT(12) +#define HID_QUIRK_Y_INVERT BIT(13) #define HID_QUIRK_SKIP_OUTPUT_REPORTS BIT(16) #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID BIT(17) #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP BIT(18) @@ -464,31 +476,50 @@ struct hid_field { unsigned report_count; /* number of this field in the report */ unsigned report_type; /* (input,output,feature) */ __s32 *value; /* last known value(s) */ + __s32 *new_value; /* newly read value(s) */ + __s32 *usages_priorities; /* priority of each usage when reading the report + * bits 8-16 are reserved for hid-input usage + */ __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; __s32 physical_maximum; __s32 unit_exponent; unsigned unit; + bool ignored; /* this field is ignored in this event */ struct hid_report *report; /* associated report */ unsigned index; /* index into report->field[] */ /* hidinput data */ struct hid_input *hidinput; /* associated input structure */ __u16 dpad; /* dpad input code */ + unsigned int slot_idx; /* slot index in a report */ }; #define HID_MAX_FIELDS 256 +struct hid_field_entry { + struct list_head list; + struct hid_field *field; + unsigned int index; + __s32 priority; +}; + struct hid_report { struct list_head list; struct list_head hidinput_list; + struct list_head field_entry_list; /* ordered list of input fields */ unsigned int id; /* id of this report */ unsigned int type; /* report type */ unsigned int application; /* application usage for this report */ struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ + struct hid_field_entry *field_entries; /* allocated memory of input field_entry */ unsigned maxfield; /* maximum valid field index */ unsigned size; /* size of the report (bits) */ struct hid_device *device; /* associated device */ + + /* tool related state */ + bool tool_active; /* whether the current tool is active */ + unsigned int tool; /* BTN_TOOL_* */ }; #define HID_MAX_IDS 256 @@ -788,7 +819,7 @@ struct hid_driver { container_of(pdrv, struct hid_driver, driver) /** - * hid_ll_driver - low level driver callbacks + * struct hid_ll_driver - low level driver callbacks * @start: called on probe to start the device * @stop: called on remove * @open: called by input layer on open @@ -894,7 +925,6 @@ extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, u32, int); -int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); @@ -928,6 +958,16 @@ s32 hid_snto32(__u32 value, unsigned n); __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, unsigned offset, unsigned n); +#ifdef CONFIG_PM +int hid_driver_suspend(struct hid_device *hdev, pm_message_t state); +int hid_driver_reset_resume(struct hid_device *hdev); +int hid_driver_resume(struct hid_device *hdev); +#else +static inline int hid_driver_suspend(struct hid_device *hdev, pm_message_t state) { return 0; } +static inline int hid_driver_reset_resume(struct hid_device *hdev) { return 0; } +static inline int hid_driver_resume(struct hid_device *hdev) { return 0; } +#endif + /** * hid_device_io_start - enable HID input during probe, remove * @@ -1005,6 +1045,10 @@ static inline void hid_map_usage(struct hid_input *hidinput, bmap = input->ledbit; limit = LED_MAX; break; + case EV_MSC: + bmap = input->mscbit; + limit = MSC_MAX; + break; } if (unlikely(c > limit || !bmap)) { @@ -1061,6 +1105,12 @@ int __must_check hid_hw_start(struct hid_device *hdev, void hid_hw_stop(struct hid_device *hdev); int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); +void hid_hw_request(struct hid_device *hdev, + struct hid_report *report, int reqtype); +int hid_hw_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + size_t len, unsigned char rtype, int reqtype); +int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len); /** * hid_hw_power - requests underlying HW to go into given power mode @@ -1079,68 +1129,6 @@ static inline int hid_hw_power(struct hid_device *hdev, int level) /** - * hid_hw_request - send report request to device - * - * @hdev: hid device - * @report: report to send - * @reqtype: hid request type - */ -static inline void hid_hw_request(struct hid_device *hdev, - struct hid_report *report, int reqtype) -{ - if (hdev->ll_driver->request) - return hdev->ll_driver->request(hdev, report, reqtype); - - __hid_request(hdev, report, reqtype); -} - -/** - * hid_hw_raw_request - send report request to device - * - * @hdev: hid device - * @reportnum: report ID - * @buf: in/out data to transfer - * @len: length of buf - * @rtype: HID report type - * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT - * - * Return: count of data transferred, negative if error - * - * Same behavior as hid_hw_request, but with raw buffers instead. - */ -static inline int hid_hw_raw_request(struct hid_device *hdev, - unsigned char reportnum, __u8 *buf, - size_t len, unsigned char rtype, int reqtype) -{ - if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) - return -EINVAL; - - return hdev->ll_driver->raw_request(hdev, reportnum, buf, len, - rtype, reqtype); -} - -/** - * hid_hw_output_report - send output report to device - * - * @hdev: hid device - * @buf: raw data to transfer - * @len: length of buf - * - * Return: count of data transferred, negative if error - */ -static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, - size_t len) -{ - if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) - return -EINVAL; - - if (hdev->ll_driver->output_report) - return hdev->ll_driver->output_report(hdev, buf, len); - - return -ENOSYS; -} - -/** * hid_hw_idle - send idle request to device * * @hdev: hid device @@ -1158,7 +1146,7 @@ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, } /** - * hid_may_wakeup - return if the hid device may act as a wakeup source during system-suspend + * hid_hw_may_wakeup - return if the hid device may act as a wakeup source during system-suspend * * @hdev: hid device */ diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 0a0b2b09b1b8..a77be5630209 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -246,6 +246,16 @@ do { \ __kunmap_atomic(__addr); \ } while (0) +/** + * kunmap_local - Unmap a page mapped via kmap_local_page(). + * @__addr: An address within the page mapped + * + * @__addr can be any address within the mapped page. Commonly it is the + * address return from kmap_local_page(), but it can also include offsets. + * + * Unmapping should be done in the reverse order of the mapping. See + * kmap_local_page() for details. + */ #define kunmap_local(__addr) \ do { \ BUILD_BUG_ON(__same_type((__addr), struct page *)); \ diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h new file mode 100644 index 000000000000..177f7b7cd414 --- /dev/null +++ b/include/linux/hisi_acc_qm.h @@ -0,0 +1,490 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 HiSilicon Limited. */ +#ifndef HISI_ACC_QM_H +#define HISI_ACC_QM_H + +#include <linux/bitfield.h> +#include <linux/debugfs.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/pci.h> + +#define QM_QNUM_V1 4096 +#define QM_QNUM_V2 1024 +#define QM_MAX_VFS_NUM_V2 63 + +/* qm user domain */ +#define QM_ARUSER_M_CFG_1 0x100088 +#define AXUSER_SNOOP_ENABLE BIT(30) +#define AXUSER_CMD_TYPE GENMASK(14, 12) +#define AXUSER_CMD_SMMU_NORMAL 1 +#define AXUSER_NS BIT(6) +#define AXUSER_NO BIT(5) +#define AXUSER_FP BIT(4) +#define AXUSER_SSV BIT(0) +#define AXUSER_BASE (AXUSER_SNOOP_ENABLE | \ + FIELD_PREP(AXUSER_CMD_TYPE, \ + AXUSER_CMD_SMMU_NORMAL) | \ + AXUSER_NS | AXUSER_NO | AXUSER_FP) +#define QM_ARUSER_M_CFG_ENABLE 0x100090 +#define ARUSER_M_CFG_ENABLE 0xfffffffe +#define QM_AWUSER_M_CFG_1 0x100098 +#define QM_AWUSER_M_CFG_ENABLE 0x1000a0 +#define AWUSER_M_CFG_ENABLE 0xfffffffe +#define QM_WUSER_M_CFG_ENABLE 0x1000a8 +#define WUSER_M_CFG_ENABLE 0xffffffff + +/* mailbox */ +#define QM_MB_CMD_SQC 0x0 +#define QM_MB_CMD_CQC 0x1 +#define QM_MB_CMD_EQC 0x2 +#define QM_MB_CMD_AEQC 0x3 +#define QM_MB_CMD_SQC_BT 0x4 +#define QM_MB_CMD_CQC_BT 0x5 +#define QM_MB_CMD_SQC_VFT_V2 0x6 +#define QM_MB_CMD_STOP_QP 0x8 +#define QM_MB_CMD_SRC 0xc +#define QM_MB_CMD_DST 0xd + +#define QM_MB_CMD_SEND_BASE 0x300 +#define QM_MB_EVENT_SHIFT 8 +#define QM_MB_BUSY_SHIFT 13 +#define QM_MB_OP_SHIFT 14 +#define QM_MB_CMD_DATA_ADDR_L 0x304 +#define QM_MB_CMD_DATA_ADDR_H 0x308 +#define QM_MB_MAX_WAIT_CNT 6000 + +/* doorbell */ +#define QM_DOORBELL_CMD_SQ 0 +#define QM_DOORBELL_CMD_CQ 1 +#define QM_DOORBELL_CMD_EQ 2 +#define QM_DOORBELL_CMD_AEQ 3 + +#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 +#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 +#define QM_QP_MAX_NUM_SHIFT 11 +#define QM_DB_CMD_SHIFT_V2 12 +#define QM_DB_RAND_SHIFT_V2 16 +#define QM_DB_INDEX_SHIFT_V2 32 +#define QM_DB_PRIORITY_SHIFT_V2 48 +#define QM_VF_STATE 0x60 + +/* qm cache */ +#define QM_CACHE_CTL 0x100050 +#define SQC_CACHE_ENABLE BIT(0) +#define CQC_CACHE_ENABLE BIT(1) +#define SQC_CACHE_WB_ENABLE BIT(4) +#define SQC_CACHE_WB_THRD GENMASK(10, 5) +#define CQC_CACHE_WB_ENABLE BIT(11) +#define CQC_CACHE_WB_THRD GENMASK(17, 12) +#define QM_AXI_M_CFG 0x1000ac +#define AXI_M_CFG 0xffff +#define QM_AXI_M_CFG_ENABLE 0x1000b0 +#define AM_CFG_SINGLE_PORT_MAX_TRANS 0x300014 +#define AXI_M_CFG_ENABLE 0xffffffff +#define QM_PEH_AXUSER_CFG 0x1000cc +#define QM_PEH_AXUSER_CFG_ENABLE 0x1000d0 +#define PEH_AXUSER_CFG 0x401001 +#define PEH_AXUSER_CFG_ENABLE 0xffffffff + +#define QM_AXI_RRESP BIT(0) +#define QM_AXI_BRESP BIT(1) +#define QM_ECC_MBIT BIT(2) +#define QM_ECC_1BIT BIT(3) +#define QM_ACC_GET_TASK_TIMEOUT BIT(4) +#define QM_ACC_DO_TASK_TIMEOUT BIT(5) +#define QM_ACC_WB_NOT_READY_TIMEOUT BIT(6) +#define QM_SQ_CQ_VF_INVALID BIT(7) +#define QM_CQ_VF_INVALID BIT(8) +#define QM_SQ_VF_INVALID BIT(9) +#define QM_DB_TIMEOUT BIT(10) +#define QM_OF_FIFO_OF BIT(11) +#define QM_DB_RANDOM_INVALID BIT(12) +#define QM_MAILBOX_TIMEOUT BIT(13) +#define QM_FLR_TIMEOUT BIT(14) + +#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ + QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ + QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ + QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) +#define QM_BASE_CE QM_ECC_1BIT + +#define QM_Q_DEPTH 1024 +#define QM_MIN_QNUM 2 +#define HISI_ACC_SGL_SGE_NR_MAX 255 +#define QM_SHAPER_CFG 0x100164 +#define QM_SHAPER_ENABLE BIT(30) +#define QM_SHAPER_TYPE1_OFFSET 10 + +/* page number for queue file region */ +#define QM_DOORBELL_PAGE_NR 1 + +/* uacce mode of the driver */ +#define UACCE_MODE_NOUACCE 0 /* don't use uacce */ +#define UACCE_MODE_SVA 1 /* use uacce sva mode */ +#define UACCE_MODE_DESC "0(default) means only register to crypto, 1 means both register to crypto and uacce" + +enum qm_stop_reason { + QM_NORMAL, + QM_SOFT_RESET, + QM_FLR, +}; + +enum qm_state { + QM_INIT = 0, + QM_START, + QM_CLOSE, + QM_STOP, +}; + +enum qp_state { + QP_INIT = 1, + QP_START, + QP_STOP, + QP_CLOSE, +}; + +enum qm_hw_ver { + QM_HW_UNKNOWN = -1, + QM_HW_V1 = 0x20, + QM_HW_V2 = 0x21, + QM_HW_V3 = 0x30, +}; + +enum qm_fun_type { + QM_HW_PF, + QM_HW_VF, +}; + +enum qm_debug_file { + CURRENT_QM, + CURRENT_Q, + CLEAR_ENABLE, + DEBUG_FILE_NUM, +}; + +enum qm_vf_state { + QM_READY = 0, + QM_NOT_READY, +}; + +struct qm_dfx { + atomic64_t err_irq_cnt; + atomic64_t aeq_irq_cnt; + atomic64_t abnormal_irq_cnt; + atomic64_t create_qp_err_cnt; + atomic64_t mb_err_cnt; +}; + +struct debugfs_file { + enum qm_debug_file index; + struct mutex lock; + struct qm_debug *debug; +}; + +struct qm_debug { + u32 curr_qm_qp_num; + u32 sqe_mask_offset; + u32 sqe_mask_len; + struct qm_dfx dfx; + struct dentry *debug_root; + struct dentry *qm_d; + struct debugfs_file files[DEBUG_FILE_NUM]; +}; + +struct qm_shaper_factor { + u32 func_qos; + u64 cir_b; + u64 cir_u; + u64 cir_s; + u64 cbs_s; +}; + +struct qm_dma { + void *va; + dma_addr_t dma; + size_t size; +}; + +struct hisi_qm_status { + u32 eq_head; + bool eqc_phase; + u32 aeq_head; + bool aeqc_phase; + atomic_t flags; + int stop_reason; +}; + +struct hisi_qm; + +struct hisi_qm_err_info { + char *acpi_rst; + u32 msi_wr_port; + u32 ecc_2bits_mask; + u32 dev_ce_mask; + u32 ce; + u32 nfe; + u32 fe; +}; + +struct hisi_qm_err_status { + u32 is_qm_ecc_mbit; + u32 is_dev_ecc_mbit; +}; + +struct hisi_qm_err_ini { + int (*hw_init)(struct hisi_qm *qm); + void (*hw_err_enable)(struct hisi_qm *qm); + void (*hw_err_disable)(struct hisi_qm *qm); + u32 (*get_dev_hw_err_status)(struct hisi_qm *qm); + void (*clear_dev_hw_err_status)(struct hisi_qm *qm, u32 err_sts); + void (*open_axi_master_ooo)(struct hisi_qm *qm); + void (*close_axi_master_ooo)(struct hisi_qm *qm); + void (*open_sva_prefetch)(struct hisi_qm *qm); + void (*close_sva_prefetch)(struct hisi_qm *qm); + void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); + void (*err_info_init)(struct hisi_qm *qm); +}; + +struct hisi_qm_list { + struct mutex lock; + struct list_head list; + int (*register_to_crypto)(struct hisi_qm *qm); + void (*unregister_from_crypto)(struct hisi_qm *qm); +}; + +struct hisi_qm { + enum qm_hw_ver ver; + enum qm_fun_type fun_type; + const char *dev_name; + struct pci_dev *pdev; + void __iomem *io_base; + void __iomem *db_io_base; + u32 sqe_size; + u32 qp_base; + u32 qp_num; + u32 qp_in_used; + u32 ctrl_qp_num; + u32 max_qp_num; + u32 vfs_num; + u32 db_interval; + struct list_head list; + struct hisi_qm_list *qm_list; + + struct qm_dma qdma; + struct qm_sqc *sqc; + struct qm_cqc *cqc; + struct qm_eqe *eqe; + struct qm_aeqe *aeqe; + dma_addr_t sqc_dma; + dma_addr_t cqc_dma; + dma_addr_t eqe_dma; + dma_addr_t aeqe_dma; + + struct hisi_qm_status status; + const struct hisi_qm_err_ini *err_ini; + struct hisi_qm_err_info err_info; + struct hisi_qm_err_status err_status; + unsigned long misc_ctl; /* driver removing and reset sched */ + + struct rw_semaphore qps_lock; + struct idr qp_idr; + struct hisi_qp *qp_array; + + struct mutex mailbox_lock; + + const struct hisi_qm_hw_ops *ops; + + struct qm_debug debug; + + u32 error_mask; + + struct workqueue_struct *wq; + struct work_struct work; + struct work_struct rst_work; + struct work_struct cmd_process; + + const char *algs; + bool use_sva; + bool is_frozen; + + /* doorbell isolation enable */ + bool use_db_isolation; + resource_size_t phys_base; + resource_size_t db_phys_base; + struct uacce_device *uacce; + int mode; + struct qm_shaper_factor *factor; + u32 mb_qos; + u32 type_rate; +}; + +struct hisi_qp_status { + atomic_t used; + u16 sq_tail; + u16 cq_head; + bool cqc_phase; + atomic_t flags; +}; + +struct hisi_qp_ops { + int (*fill_sqe)(void *sqe, void *q_parm, void *d_parm); +}; + +struct hisi_qp { + u32 qp_id; + u8 alg_type; + u8 req_type; + + struct qm_dma qdma; + void *sqe; + struct qm_cqe *cqe; + dma_addr_t sqe_dma; + dma_addr_t cqe_dma; + + struct hisi_qp_status qp_status; + struct hisi_qp_ops *hw_ops; + void *qp_ctx; + void (*req_cb)(struct hisi_qp *qp, void *data); + void (*event_cb)(struct hisi_qp *qp); + + struct hisi_qm *qm; + bool is_resetting; + bool is_in_kernel; + u16 pasid; + struct uacce_queue *uacce_q; +}; + +static inline int q_num_set(const char *val, const struct kernel_param *kp, + unsigned int device) +{ + struct pci_dev *pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, + device, NULL); + u32 n, q_num; + int ret; + + if (!val) + return -EINVAL; + + if (!pdev) { + q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2); + pr_info("No device found currently, suppose queue number is %u\n", + q_num); + } else { + if (pdev->revision == QM_HW_V1) + q_num = QM_QNUM_V1; + else + q_num = QM_QNUM_V2; + } + + ret = kstrtou32(val, 10, &n); + if (ret || n < QM_MIN_QNUM || n > q_num) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int vfs_num_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret < 0) + return ret; + + if (n > QM_MAX_VFS_NUM_V2) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int mode_set(const char *val, const struct kernel_param *kp) +{ + u32 n; + int ret; + + if (!val) + return -EINVAL; + + ret = kstrtou32(val, 10, &n); + if (ret != 0 || (n != UACCE_MODE_SVA && + n != UACCE_MODE_NOUACCE)) + return -EINVAL; + + return param_set_int(val, kp); +} + +static inline int uacce_mode_set(const char *val, const struct kernel_param *kp) +{ + return mode_set(val, kp); +} + +static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list) +{ + INIT_LIST_HEAD(&qm_list->list); + mutex_init(&qm_list->lock); +} + +int hisi_qm_init(struct hisi_qm *qm); +void hisi_qm_uninit(struct hisi_qm *qm); +int hisi_qm_start(struct hisi_qm *qm); +int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r); +struct hisi_qp *hisi_qm_create_qp(struct hisi_qm *qm, u8 alg_type); +int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg); +int hisi_qm_stop_qp(struct hisi_qp *qp); +void hisi_qm_release_qp(struct hisi_qp *qp); +int hisi_qp_send(struct hisi_qp *qp, const void *msg); +int hisi_qm_get_free_qp_num(struct hisi_qm *qm); +int hisi_qm_get_vft(struct hisi_qm *qm, u32 *base, u32 *number); +void hisi_qm_debug_init(struct hisi_qm *qm); +enum qm_hw_ver hisi_qm_get_hw_version(struct pci_dev *pdev); +void hisi_qm_debug_regs_clear(struct hisi_qm *qm); +int hisi_qm_sriov_enable(struct pci_dev *pdev, int max_vfs); +int hisi_qm_sriov_disable(struct pci_dev *pdev, bool is_frozen); +int hisi_qm_sriov_configure(struct pci_dev *pdev, int num_vfs); +void hisi_qm_dev_err_init(struct hisi_qm *qm); +void hisi_qm_dev_err_uninit(struct hisi_qm *qm); +pci_ers_result_t hisi_qm_dev_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); +pci_ers_result_t hisi_qm_dev_slot_reset(struct pci_dev *pdev); +void hisi_qm_reset_prepare(struct pci_dev *pdev); +void hisi_qm_reset_done(struct pci_dev *pdev); + +int hisi_qm_wait_mb_ready(struct hisi_qm *qm); +int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue, + bool op); + +struct hisi_acc_sgl_pool; +struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, + struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool, + u32 index, dma_addr_t *hw_sgl_dma); +void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, + struct hisi_acc_hw_sgl *hw_sgl); +struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, + u32 count, u32 sge_nr); +void hisi_acc_free_sgl_pool(struct device *dev, + struct hisi_acc_sgl_pool *pool); +int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num, + u8 alg_type, int node, struct hisi_qp **qps); +void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num); +void hisi_qm_dev_shutdown(struct pci_dev *pdev); +void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list); +int hisi_qm_resume(struct device *dev); +int hisi_qm_suspend(struct device *dev); +void hisi_qm_pm_uninit(struct hisi_qm *qm); +void hisi_qm_pm_init(struct hisi_qm *qm); +int hisi_qm_get_dfx_access(struct hisi_qm *qm); +void hisi_qm_put_dfx_access(struct hisi_qm *qm); +void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset); + +/* Used by VFIO ACC live migration driver */ +struct pci_driver *hisi_sec_get_pf_driver(void); +struct pci_driver *hisi_hpre_get_pf_driver(void); +struct pci_driver *hisi_zip_get_pf_driver(void); +#endif diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 2fd2e91d5107..d5a6f101f843 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -9,14 +9,9 @@ #ifndef LINUX_HMM_H #define LINUX_HMM_H -#include <linux/kconfig.h> -#include <linux/pgtable.h> +#include <linux/mm.h> -#include <linux/device.h> -#include <linux/migrate.h> -#include <linux/memremap.h> -#include <linux/completion.h> -#include <linux/mmu_notifier.h> +struct mmu_interval_notifier; /* * On output: diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 7bccf589aba7..e8dc5bc41f79 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -7,6 +7,8 @@ #define __LINUX_HOST1X_H #include <linux/device.h> +#include <linux/dma-direction.h> +#include <linux/spinlock.h> #include <linux/types.h> enum host1x_class { @@ -15,6 +17,8 @@ enum host1x_class { HOST1X_CLASS_GR2D_SB = 0x52, HOST1X_CLASS_VIC = 0x5D, HOST1X_CLASS_GR3D = 0x60, + HOST1X_CLASS_NVDEC = 0xF0, + HOST1X_CLASS_NVDEC1 = 0xF5, }; struct host1x; @@ -24,6 +28,28 @@ struct iommu_group; u64 host1x_get_dma_mask(struct host1x *host1x); /** + * struct host1x_bo_cache - host1x buffer object cache + * @mappings: list of mappings + * @lock: synchronizes accesses to the list of mappings + */ +struct host1x_bo_cache { + struct list_head mappings; + struct mutex lock; +}; + +static inline void host1x_bo_cache_init(struct host1x_bo_cache *cache) +{ + INIT_LIST_HEAD(&cache->mappings); + mutex_init(&cache->lock); +} + +static inline void host1x_bo_cache_destroy(struct host1x_bo_cache *cache) +{ + /* XXX warn if not empty? */ + mutex_destroy(&cache->lock); +} + +/** * struct host1x_client_ops - host1x client operations * @early_init: host1x client early initialization code * @init: host1x client initialization code @@ -73,6 +99,8 @@ struct host1x_client { struct host1x_client *parent; unsigned int usecount; struct mutex lock; + + struct host1x_bo_cache cache; }; /* @@ -82,23 +110,48 @@ struct host1x_client { struct host1x_bo; struct sg_table; +struct host1x_bo_mapping { + struct kref ref; + struct dma_buf_attachment *attach; + enum dma_data_direction direction; + struct list_head list; + struct host1x_bo *bo; + struct sg_table *sgt; + unsigned int chunks; + struct device *dev; + dma_addr_t phys; + size_t size; + + struct host1x_bo_cache *cache; + struct list_head entry; +}; + +static inline struct host1x_bo_mapping *to_host1x_bo_mapping(struct kref *ref) +{ + return container_of(ref, struct host1x_bo_mapping, ref); +} + struct host1x_bo_ops { struct host1x_bo *(*get)(struct host1x_bo *bo); void (*put)(struct host1x_bo *bo); - struct sg_table *(*pin)(struct device *dev, struct host1x_bo *bo, - dma_addr_t *phys); - void (*unpin)(struct device *dev, struct sg_table *sgt); + struct host1x_bo_mapping *(*pin)(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction dir); + void (*unpin)(struct host1x_bo_mapping *map); void *(*mmap)(struct host1x_bo *bo); void (*munmap)(struct host1x_bo *bo, void *addr); }; struct host1x_bo { const struct host1x_bo_ops *ops; + struct list_head mappings; + spinlock_t lock; }; static inline void host1x_bo_init(struct host1x_bo *bo, const struct host1x_bo_ops *ops) { + INIT_LIST_HEAD(&bo->mappings); + spin_lock_init(&bo->lock); bo->ops = ops; } @@ -112,18 +165,10 @@ static inline void host1x_bo_put(struct host1x_bo *bo) bo->ops->put(bo); } -static inline struct sg_table *host1x_bo_pin(struct device *dev, - struct host1x_bo *bo, - dma_addr_t *phys) -{ - return bo->ops->pin(dev, bo, phys); -} - -static inline void host1x_bo_unpin(struct device *dev, struct host1x_bo *bo, - struct sg_table *sgt) -{ - bo->ops->unpin(dev, sgt); -} +struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction dir, + struct host1x_bo_cache *cache); +void host1x_bo_unpin(struct host1x_bo_mapping *map); static inline void *host1x_bo_mmap(struct host1x_bo *bo) { @@ -181,6 +226,7 @@ struct host1x_job; struct host1x_channel *host1x_channel_request(struct host1x_client *client); struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); +void host1x_channel_stop(struct host1x_channel *channel); void host1x_channel_put(struct host1x_channel *channel); int host1x_job_submit(struct host1x_job *job); diff --git a/include/linux/hrtimer_api.h b/include/linux/hrtimer_api.h new file mode 100644 index 000000000000..8d9700894468 --- /dev/null +++ b/include/linux/hrtimer_api.h @@ -0,0 +1 @@ +#include <linux/hrtimer.h> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f280f33ff223..2999190adc22 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -183,9 +183,8 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, void prep_transhuge_page(struct page *page); void free_transhuge_page(struct page *page); -bool is_transparent_hugepage(struct page *page); -bool can_split_huge_page(struct page *page, int *pextra_pins); +bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { @@ -194,7 +193,7 @@ static inline int split_huge_page(struct page *page) void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page); + unsigned long address, bool freeze, struct folio *folio); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ @@ -207,7 +206,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, - bool freeze, struct page *page); + bool freeze, struct folio *folio); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); @@ -251,27 +250,12 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, } /** - * thp_order - Order of a transparent huge page. - * @page: Head page of a transparent huge page. + * folio_test_pmd_mappable - Can we map this folio with a PMD? + * @folio: The folio to test */ -static inline unsigned int thp_order(struct page *page) +static inline bool folio_test_pmd_mappable(struct folio *folio) { - VM_BUG_ON_PGFLAGS(PageTail(page), page); - if (PageHead(page)) - return HPAGE_PMD_ORDER; - return 0; -} - -/** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline int thp_nr_pages(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - if (PageHead(page)) - return HPAGE_PMD_NR; - return 1; + return folio_order(folio) >= HPAGE_PMD_ORDER; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -327,16 +311,9 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) -static inline unsigned int thp_order(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return 0; -} - -static inline int thp_nr_pages(struct page *page) +static inline bool folio_test_pmd_mappable(struct folio *folio) { - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return 1; + return false; } static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) @@ -363,17 +340,12 @@ static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, static inline void prep_transhuge_page(struct page *page) {} -static inline bool is_transparent_hugepage(struct page *page) -{ - return false; -} - #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool -can_split_huge_page(struct page *page, int *pextra_pins) +can_split_folio(struct folio *folio, int *pextra_pins) { BUILD_BUG(); return false; @@ -392,9 +364,9 @@ static inline void deferred_split_huge_page(struct page *page) {} do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, - unsigned long address, bool freeze, struct page *page) {} + unsigned long address, bool freeze, struct folio *folio) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) @@ -469,15 +441,10 @@ static inline bool thp_migration_supported(void) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -/** - * thp_size - Size of a transparent huge page. - * @page: Head page of a transparent huge page. - * - * Return: Number of bytes in this page. - */ -static inline unsigned long thp_size(struct page *page) +static inline int split_folio_to_list(struct folio *folio, + struct list_head *list) { - return PAGE_SIZE << thp_order(page); + return split_huge_page_to_list(&folio->page, list); } #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 00351ccb49a3..53c1b6082a4c 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -622,8 +622,8 @@ struct hstate { #endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[7]; - struct cftype cgroup_files_legacy[9]; + struct cftype cgroup_files_dfl[8]; + struct cftype cgroup_files_legacy[10]; #endif char name[HSTATE_NAME_LEN]; }; @@ -754,7 +754,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { - return entry; + return pte_mkhuge(entry); } #endif @@ -970,6 +970,11 @@ static inline struct hstate *page_hstate(struct page *page) return NULL; } +static inline struct hstate *size_to_hstate(unsigned long size) +{ + return NULL; +} + static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; @@ -1075,12 +1080,6 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr } #endif /* CONFIG_HUGETLB_PAGE */ -#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP -extern bool hugetlb_free_vmemmap_enabled; -#else -#define hugetlb_free_vmemmap_enabled false -#endif - static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index ba025ae27882..379344828e78 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -36,6 +36,11 @@ enum hugetlb_memory_event { HUGETLB_NR_MEMORY_EVENTS, }; +struct hugetlb_cgroup_per_node { + /* hugetlb usage in pages over all hstates. */ + unsigned long usage[HUGE_MAX_HSTATE]; +}; + struct hugetlb_cgroup { struct cgroup_subsys_state css; @@ -57,6 +62,8 @@ struct hugetlb_cgroup { /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; + + struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 8e6dd908da21..aa1d4da03538 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -60,7 +60,5 @@ extern int devm_hwrng_register(struct device *dev, struct hwrng *rng); /** Unregister a Hardware Random Number Generator driver. */ extern void hwrng_unregister(struct hwrng *rng); extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng); -/** Feed random bits into the pool. */ -extern void add_hwgenerator_randomness(const char *buffer, size_t count, size_t entropy); #endif /* LINUX_HWRANDOM_H_ */ diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 1e8d6ea8992e..eba380b76d15 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -332,12 +332,14 @@ enum hwmon_pwm_attributes { hwmon_pwm_enable, hwmon_pwm_mode, hwmon_pwm_freq, + hwmon_pwm_auto_channels_temp, }; #define HWMON_PWM_INPUT BIT(hwmon_pwm_input) #define HWMON_PWM_ENABLE BIT(hwmon_pwm_enable) #define HWMON_PWM_MODE BIT(hwmon_pwm_mode) #define HWMON_PWM_FREQ BIT(hwmon_pwm_freq) +#define HWMON_PWM_AUTO_CHANNELS_TEMP BIT(hwmon_pwm_auto_channels_temp) enum hwmon_intrusion_attributes { hwmon_intrusion_alarm, @@ -403,7 +405,7 @@ struct hwmon_ops { }; /** - * Channel information + * struct hwmon_channel_info - Channel information * @type: Channel type. * @config: Pointer to NULL-terminated list of channel parameters. * Use for per-channel attributes. @@ -422,7 +424,7 @@ struct hwmon_channel_info { }) /** - * Chip configuration + * struct hwmon_chip_info - Chip configuration * @ops: Pointer to hwmon operations. * @info: Null-terminated list of channel information. */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b823311eac79..fe2e0179ed51 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1261,6 +1261,8 @@ struct hv_device { struct vmbus_channel *channel; struct kset *channels_kset; + struct device_dma_parameters dma_parms; + u64 dma_mask; /* place holder to keep track of the dir for hv device in debugfs */ struct dentry *debug_dir; @@ -1583,6 +1585,11 @@ struct hyperv_service_callback { void (*callback)(void *context); }; +struct hv_dma_range { + dma_addr_t dma; + u32 mapping_size; +}; + #define MAX_SRV_VER 0x7ffffff extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen, const int *fw_version, int fw_vercnt, diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 1ef421818d3a..ced1c6ead52a 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -30,14 +30,6 @@ struct i2c_client *i2c_new_smbus_alert_device(struct i2c_adapter *adapter, struct i2c_smbus_alert_setup *setup); int i2c_handle_smbus_alert(struct i2c_client *ara); -#if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_OF) -int of_i2c_setup_smbus_alert(struct i2c_adapter *adap); -#else -static inline int of_i2c_setup_smbus_alert(struct i2c_adapter *adap) -{ - return 0; -} -#endif #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_I2C_SLAVE) struct i2c_client *i2c_new_slave_host_notify_device(struct i2c_adapter *adapter); void i2c_free_slave_host_notify_device(struct i2c_client *client); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 16119ac1aa97..fbda5ada2afc 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -392,12 +392,8 @@ enum i2c_slave_event { int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); bool i2c_detect_slave_mode(struct device *dev); - -static inline int i2c_slave_event(struct i2c_client *client, - enum i2c_slave_event event, u8 *val) -{ - return client->slave_cb(client, event, val); -} +int i2c_slave_event(struct i2c_client *client, + enum i2c_slave_event event, u8 *val); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif @@ -1025,8 +1021,9 @@ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); u32 i2c_acpi_find_bus_speed(struct device *dev); -struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, - struct i2c_board_info *info); +struct i2c_client *i2c_acpi_new_device_by_fwnode(struct fwnode_handle *fwnode, + int index, + struct i2c_board_info *info); struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); bool i2c_acpi_waive_d0_probe(struct device *dev); #else @@ -1043,8 +1040,9 @@ static inline u32 i2c_acpi_find_bus_speed(struct device *dev) { return 0; } -static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, - int index, struct i2c_board_info *info) +static inline struct i2c_client *i2c_acpi_new_device_by_fwnode( + struct fwnode_handle *fwnode, int index, + struct i2c_board_info *info) { return ERR_PTR(-ENODEV); } @@ -1058,4 +1056,11 @@ static inline bool i2c_acpi_waive_d0_probe(struct device *dev) } #endif /* CONFIG_ACPI */ +static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, + int index, + struct i2c_board_info *info) +{ + return i2c_acpi_new_device_by_fwnode(dev_fwnode(dev), index, info); +} + #endif /* _LINUX_I2C_H */ diff --git a/include/linux/i3c/ccc.h b/include/linux/i3c/ccc.h index 73b0982cc519..ad59a4ae60d1 100644 --- a/include/linux/i3c/ccc.h +++ b/include/linux/i3c/ccc.h @@ -132,7 +132,7 @@ struct i3c_ccc_dev_desc { struct i3c_ccc_defslvs { u8 count; struct i3c_ccc_dev_desc master; - struct i3c_ccc_dev_desc slaves[0]; + struct i3c_ccc_dev_desc slaves[]; } __packed; /** @@ -240,7 +240,7 @@ struct i3c_ccc_bridged_slave_desc { */ struct i3c_ccc_setbrgtgt { u8 count; - struct i3c_ccc_bridged_slave_desc bslaves[0]; + struct i3c_ccc_bridged_slave_desc bslaves[]; } __packed; /** @@ -318,7 +318,7 @@ enum i3c_ccc_setxtime_subcmd { */ struct i3c_ccc_setxtime { u8 subcmd; - u8 data[0]; + u8 data[]; } __packed; #define I3C_CCC_GETXTIME_SYNC_MODE BIT(0) diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 9cb39d901cd5..604a126b78c8 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -85,7 +85,6 @@ struct i2c_dev_boardinfo { */ struct i2c_dev_desc { struct i3c_i2c_dev_desc common; - const struct i2c_dev_boardinfo *boardinfo; struct i2c_client *dev; u16 addr; u8 lvr; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 11d7af260f20..75d40acb60c1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2021 Intel Corporation + * Copyright (c) 2018 - 2022 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -18,6 +18,7 @@ #include <linux/types.h> #include <linux/if_ether.h> #include <linux/etherdevice.h> +#include <linux/bitfield.h> #include <asm/byteorder.h> #include <asm/unaligned.h> @@ -1023,6 +1024,8 @@ struct ieee80211_tpc_report_ie { #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_MASK GENMASK(2, 1) #define IEEE80211_ADDBA_EXT_FRAG_LEVEL_SHIFT 1 #define IEEE80211_ADDBA_EXT_NO_FRAG BIT(0) +#define IEEE80211_ADDBA_EXT_BUF_SIZE_MASK GENMASK(7, 5) +#define IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT 10 struct ieee80211_addba_ext_ie { u8 data; @@ -1697,10 +1700,12 @@ struct ieee80211_ht_operation { * A-MPDU buffer sizes * According to HT size varies from 8 to 64 frames * HE adds the ability to have up to 256 frames. + * EHT adds the ability to have up to 1K frames. */ #define IEEE80211_MIN_AMPDU_BUF 0x8 #define IEEE80211_MAX_AMPDU_BUF_HT 0x40 -#define IEEE80211_MAX_AMPDU_BUF 0x100 +#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 +#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 /* Spatial Multiplexing Power Save Modes (for capability) */ @@ -1925,6 +1930,111 @@ struct ieee80211_mu_edca_param_set { struct ieee80211_he_mu_edca_param_ac_rec ac_vo; } __packed; +#define IEEE80211_EHT_MCS_NSS_RX 0x0f +#define IEEE80211_EHT_MCS_NSS_TX 0xf0 + +/** + * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max + * supported NSS for per MCS. + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 7. + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 8 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + */ +struct ieee80211_eht_mcs_nss_supp_20mhz_only { + u8 rx_tx_mcs7_max_nss; + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; +}; + +/** + * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except + * 20MHz only stations). + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + */ +struct ieee80211_eht_mcs_nss_supp_bw { + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; +}; + +/** + * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data + * + * This structure is the "EHT Capabilities element" fixed fields as + * described in P802.11be_D1.4 section 9.4.2.313. + * + * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* + * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* + */ +struct ieee80211_eht_cap_elem_fixed { + u8 mac_cap_info[2]; + u8 phy_cap_info[9]; +} __packed; + +/** + * struct ieee80211_eht_cap_elem - EHT capabilities element + * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed + * @optional: optional parts + */ +struct ieee80211_eht_cap_elem { + struct ieee80211_eht_cap_elem_fixed fixed; + + /* + * Followed by: + * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. + * EHT PPE Thresholds field: variable length. + */ + u8 optional[]; +} __packed; + +/** + * struct ieee80211_eht_operation - eht operation element + * + * This structure is the "EHT Operation Element" fields as + * described in P802.11be_D1.4 section 9.4.2.311 + * + * FIXME: The spec is unclear how big the fields are, and doesn't + * indicate the "Disabled Subchannel Bitmap Present" in the + * structure (Figure 9-1002a) at all ... + */ +struct ieee80211_eht_operation { + u8 chan_width; + u8 ccfs; + u8 present_bm; + + u8 disable_subchannel_bitmap[]; +} __packed; + +#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x1 + /* 802.11ac VHT Capabilities */ #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 @@ -2129,6 +2239,8 @@ enum ieee80211_client_reg_power { #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e + #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe @@ -2258,11 +2370,12 @@ enum ieee80211_client_reg_power { #define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US 0x00 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US 0x40 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US 0x80 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 #define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 @@ -2308,6 +2421,7 @@ ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 #define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) #define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) +#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) /* * Calculate 802.11ax HE capabilities IE PPE field size @@ -2337,6 +2451,29 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) return n; } +static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; + u8 needed = sizeof(*he_cap_ie_elem); + + if (len < needed) + return false; + + needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); + if (len < needed) + return false; + + if (he_cap_ie_elem->phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { + if (len < needed + 1) + return false; + needed += ieee80211_he_ppe_size(data[needed], + he_cap_ie_elem->phy_cap_info); + } + + return len >= needed; +} + /* HE Operation defines */ #define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 @@ -2426,7 +2563,7 @@ struct ieee80211_tx_pwr_env { static inline u8 ieee80211_he_oper_size(const u8 *he_oper_ie) { - struct ieee80211_he_operation *he_oper = (void *)he_oper_ie; + const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; u8 oper_len = sizeof(struct ieee80211_he_operation); u32 he_oper_params; @@ -2459,7 +2596,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) static inline const struct ieee80211_he_6ghz_oper * ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) { - const u8 *ret = (void *)&he_oper->optional; + const u8 *ret = (const void *)&he_oper->optional; u32 he_oper_params; if (!he_oper) @@ -2474,7 +2611,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) ret++; - return (void *)ret; + return (const void *)ret; } /* HE Spatial Reuse defines */ @@ -2495,7 +2632,7 @@ ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) static inline u8 ieee80211_he_spr_size(const u8 *he_spr_ie) { - struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; + const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); u8 he_spr_params; @@ -2598,6 +2735,194 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) #define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ BIT(0) #define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) +/* EHT MAC capabilities as defined in P802.11be_D1.4 section 9.4.2.313.2 */ +#define IEEE80211_EHT_MAC_CAP0_NSEP_PRIO_ACCESS 0x01 +#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 +#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 +#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_MASK 0xc0 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_3895 0 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_7991 1 +#define IEEE80211_EHT_MAC_CAP0_MAX_AMPDU_LEN_11454 2 + +/* EHT PHY capabilities as defined in P802.11be_D1.4 section 9.4.2.313.3 */ +#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 +#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 +#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 + +/* EHT beamformee number of spatial streams <= 80MHz is split */ +#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 + +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 + +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 + +/* EHT number of sounding dimensions for 320MHz is split */ +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 +#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 +#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 +#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 +#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 +#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 + +#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 +#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 +#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 + +#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 +#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 + +/* Maximum number of supported EHT LTF is split */ +#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 + +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 +#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 + +#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 + +#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 +#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 + +/* + * EHT operation channel width as defined in P802.11be_D1.4 section 9.4.2.311 + */ +#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 + +/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ +static inline u8 +ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, + const struct ieee80211_eht_cap_elem_fixed *eht_cap) +{ + u8 count = 0; + + /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return 3; + + /* on 2.4 GHz, these three bits are reserved, so should be 0 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + count += 3; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 3; + + if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + count += 3; + + return count ? count : 4; +} + +/* 802.11be EHT PPE Thresholds */ +#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 +#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf +#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 +#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 +#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 + +/* + * Calculate 802.11be EHT capabilities IE EHT field size + */ +static inline u8 +ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u32 n; + + if (!(phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) + return 0; + + n = hweight16(ppe_thres_hdr & + IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); + + /* + * Each pair is 6 bits, and we need to add the 9 "header" bits to the + * total size. + */ + n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + + IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; + return DIV_ROUND_UP(n, 8); +} + +static inline bool +ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len) +{ + const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; + u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); + + if (len < needed || !he_capa) + return false; + + needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, + (const void *)data); + if (len < needed) + return false; + + if (elem->phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { + u16 ppe_thres_hdr; + + if (len < needed + sizeof(ppe_thres_hdr)) + return false; + + ppe_thres_hdr = get_unaligned_le16(data + needed); + needed += ieee80211_eht_ppe_size(ppe_thres_hdr, + elem->phy_cap_info); + } + + return len >= needed; +} + +static inline bool +ieee80211_eht_oper_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_eht_operation *elem = (const void *)data; + u8 needed = sizeof(*elem); + + if (len < needed) + return false; + + if (elem->present_bm & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) + needed += 2; + + return len >= needed; +} #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) @@ -3053,6 +3378,9 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_SHORT_SSID_LIST = 58, WLAN_EID_EXT_HE_6GHZ_CAPA = 59, WLAN_EID_EXT_UL_MU_POWER_CAPA = 60, + WLAN_EID_EXT_EHT_OPERATION = 106, + WLAN_EID_EXT_EHT_MULTI_LINK = 107, + WLAN_EID_EXT_EHT_CAPABILITY = 108, }; /* Action category code */ @@ -4004,10 +4332,10 @@ static inline bool for_each_element_completed(const struct element *element, #define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP 0x40 struct ieee80211_neighbor_ap_info { - u8 tbtt_info_hdr; - u8 tbtt_info_len; - u8 op_class; - u8 channel; + u8 tbtt_info_hdr; + u8 tbtt_info_len; + u8 op_class; + u8 channel; } __packed; enum ieee80211_range_params_max_total_ltf { diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index b712217f7030..1ed52441972f 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -52,6 +52,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: + case ARPHRD_PIMREG: return false; default: return true; diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 509e18c7e740..d62ef428e3aa 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -58,6 +58,7 @@ struct br_ip_list { #define BR_MRP_LOST_CONT BIT(18) #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) +#define BR_PORT_LOCKED BIT(21) #define BR_DEFAULT_AGEING_TIME (300 * HZ) @@ -118,6 +119,9 @@ int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); +bool br_mst_enabled(const struct net_device *dev); +int br_mst_get_info(const struct net_device *dev, u16 msti, unsigned long *vids); +int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -150,6 +154,22 @@ static inline int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, { return -EINVAL; } + +static inline bool br_mst_enabled(const struct net_device *dev) +{ + return false; +} + +static inline int br_mst_get_info(const struct net_device *dev, u16 msti, + unsigned long *vids) +{ + return -EINVAL; +} +static inline int br_mst_get_state(const struct net_device *dev, u16 msti, + u8 *state) +{ + return -EINVAL; +} #endif #if IS_ENABLED(CONFIG_BRIDGE) diff --git a/include/linux/if_eql.h b/include/linux/if_eql.h index d984694c384d..d75601d613cc 100644 --- a/include/linux/if_eql.h +++ b/include/linux/if_eql.h @@ -26,6 +26,7 @@ typedef struct slave { struct list_head list; struct net_device *dev; + netdevice_tracker dev_tracker; long priority; long priority_bps; long priority_Bps; diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index 38bbc537d4e4..408539d5ea5f 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -9,6 +9,22 @@ enum hsr_version { PRP_V1, }; +/* HSR Tag. + * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, + * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, + * h_source, h_proto = 0x88FB }, and add { path, LSDU_size, sequence Nr, + * encapsulated protocol } instead. + * + * Field names as defined in the IEC:2010 standard for HSR. + */ +struct hsr_tag { + __be16 path_and_LSDU_size; + __be16 sequence_nr; + __be16 encap_proto; +} __packed; + +#define HSR_HLEN 6 + #if IS_ENABLED(CONFIG_HSR) extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 10c94a3936ca..b42294739063 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -21,6 +21,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; + netdevice_tracker dev_tracker; void *accel_priv; struct vlan_pcpu_stats __percpu *pcpu_stats; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 41a518336673..2be4dd7e90a9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -46,8 +46,10 @@ struct vlan_hdr { * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + struct_group(addrs, + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; @@ -162,6 +164,7 @@ struct netpoll; * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice + * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats @@ -177,6 +180,8 @@ struct vlan_dev_priv { u16 flags; struct net_device *real_dev; + netdevice_tracker dev_tracker; + unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h index 33f60f43e1aa..ce78d4804994 100644 --- a/include/linux/iio/adc/qcom-vadc-common.h +++ b/include/linux/iio/adc/qcom-vadc-common.h @@ -6,6 +6,7 @@ #ifndef QCOM_VADC_COMMON_H #define QCOM_VADC_COMMON_H +#include <linux/math.h> #include <linux/types.h> #define VADC_CONV_TIME_MIN_US 2000 @@ -80,16 +81,6 @@ struct vadc_linear_graph { }; /** - * struct vadc_prescale_ratio - Represent scaling ratio for ADC input. - * @num: the inverse numerator of the gain applied to the input channel. - * @den: the inverse denominator of the gain applied to the input channel. - */ -struct vadc_prescale_ratio { - u32 num; - u32 den; -}; - -/** * enum vadc_scale_fn_type - Scaling function to convert ADC code to * physical scaled units for the channel. * SCALE_DEFAULT: Default scaling to convert raw adc code to voltage (uV). @@ -144,12 +135,12 @@ struct adc5_data { int qcom_vadc_scale(enum vadc_scale_fn_type scaletype, const struct vadc_linear_graph *calib_graph, - const struct vadc_prescale_ratio *prescale, + const struct u32_fract *prescale, bool absolute, u16 adc_code, int *result_mdec); struct qcom_adc5_scale_type { - int (*scale_fn)(const struct vadc_prescale_ratio *prescale, + int (*scale_fn)(const struct u32_fract *prescale, const struct adc5_data *data, u16 adc_code, int *result); }; diff --git a/include/linux/iio/afe/rescale.h b/include/linux/iio/afe/rescale.h new file mode 100644 index 000000000000..6eecb435488f --- /dev/null +++ b/include/linux/iio/afe/rescale.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2018 Axentia Technologies AB + */ + +#ifndef __IIO_RESCALE_H__ +#define __IIO_RESCALE_H__ + +#include <linux/types.h> +#include <linux/iio/iio.h> + +struct device; +struct rescale; + +struct rescale_cfg { + enum iio_chan_type type; + int (*props)(struct device *dev, struct rescale *rescale); +}; + +struct rescale { + const struct rescale_cfg *cfg; + struct iio_channel *source; + struct iio_chan_spec chan; + struct iio_chan_spec_ext_info *ext_info; + bool chan_processed; + s32 numerator; + s32 denominator; + s32 offset; +}; + +int rescale_process_scale(struct rescale *rescale, int scale_type, + int *val, int *val2); +int rescale_process_offset(struct rescale *rescale, int scale_type, + int scale, int scale2, int schan_off, + int *val, int *val2); +#endif /* __IIO_RESCALE_H__ */ diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index ff15c61bf319..6564bdcdac66 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -17,11 +17,6 @@ struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; struct device; -struct iio_buffer_block { - u32 size; - u32 bytes_used; -}; - /** * enum iio_block_state - State of a struct iio_dma_buffer_block * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 324561b7a5e8..faf00f2c0be6 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -103,15 +103,16 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev, /** * IIO_ENUM_AVAILABLE() - Initialize enum available extended channel attribute * @_name: Attribute name ("_available" will be appended to the name) + * @_shared: Whether the attribute is shared between all channels * @_e: Pointer to an iio_enum struct * * Creates a read only attribute which lists all the available enum items in a * space separated list. This should usually be used together with IIO_ENUM() */ -#define IIO_ENUM_AVAILABLE(_name, _e) \ +#define IIO_ENUM_AVAILABLE(_name, _shared, _e) \ { \ .name = (_name "_available"), \ - .shared = IIO_SHARED_BY_TYPE, \ + .shared = _shared, \ .read = iio_enum_available_read, \ .private = (uintptr_t)(_e), \ } @@ -488,7 +489,7 @@ struct iio_buffer_setup_ops { /** * struct iio_dev - industrial I/O device * @modes: [DRIVER] operating modes supported by device - * @currentmode: [DRIVER] current operating mode + * @currentmode: [INTERN] current operating mode * @dev: [DRIVER] device structure, should be assigned a parent * and owner * @buffer: [DRIVER] any buffer present diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 7c02f5292eea..515ca09764fe 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -32,6 +32,7 @@ struct adis_timeout { u16 sw_reset_ms; u16 self_test_ms; }; + /** * struct adis_data - ADIS chip variant specific data * @read_delay: SPI delay for read operations in us @@ -45,7 +46,7 @@ struct adis_timeout { * @self_test_mask: Bitmask of supported self-test operations * @self_test_reg: Register address to request self test command * @self_test_no_autoclear: True if device's self-test needs clear of ctrl reg - * @status_error_msgs: Array of error messgaes + * @status_error_msgs: Array of error messages * @status_error_mask: Bitmask of errors supported by the device * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable @@ -130,12 +131,12 @@ struct adis { unsigned long irq_flag; void *buffer; - uint8_t tx[10] ____cacheline_aligned; - uint8_t rx[4]; + u8 tx[10] ____cacheline_aligned; + u8 rx[4]; }; int adis_init(struct adis *adis, struct iio_dev *indio_dev, - struct spi_device *spi, const struct adis_data *data); + struct spi_device *spi, const struct adis_data *data); int __adis_reset(struct adis *adis); /** @@ -156,9 +157,9 @@ static inline int adis_reset(struct adis *adis) } int __adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size); + unsigned int val, unsigned int size); int __adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size); + unsigned int *val, unsigned int size); /** * __adis_write_reg_8() - Write single byte to a register (unlocked) @@ -167,7 +168,7 @@ int __adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return __adis_write_reg(adis, reg, val, 1); } @@ -179,7 +180,7 @@ static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return __adis_write_reg(adis, reg, val, 2); } @@ -191,7 +192,7 @@ static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return __adis_write_reg(adis, reg, val, 4); } @@ -203,7 +204,7 @@ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -222,7 +223,7 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -242,7 +243,7 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, * @size: The size of the @value (in bytes) */ static inline int adis_write_reg(struct adis *adis, unsigned int reg, - unsigned int val, unsigned int size) + unsigned int val, unsigned int size) { int ret; @@ -261,7 +262,7 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, * @size: The size of the @val buffer */ static int adis_read_reg(struct adis *adis, unsigned int reg, - unsigned int *val, unsigned int size) + unsigned int *val, unsigned int size) { int ret; @@ -279,7 +280,7 @@ static int adis_read_reg(struct adis *adis, unsigned int reg, * @value: The value to write */ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, - uint8_t val) + u8 val) { return adis_write_reg(adis, reg, val, 1); } @@ -291,7 +292,7 @@ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, - uint16_t val) + u16 val) { return adis_write_reg(adis, reg, val, 2); } @@ -303,7 +304,7 @@ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg, * @value: Value to be written */ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, - uint32_t val) + u32 val) { return adis_write_reg(adis, reg, val, 4); } @@ -315,7 +316,7 @@ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, - uint16_t *val) + u16 *val) { unsigned int tmp; int ret; @@ -334,7 +335,7 @@ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg, * @val: The value read back from the device */ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, - uint32_t *val) + u32 *val) { unsigned int tmp; int ret; @@ -381,10 +382,8 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, * @val can lead to undesired behavior if the register to update is 16bit. */ #define adis_update_bits(adis, reg, mask, val) ({ \ - BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ - __builtin_choose_expr(sizeof(val) == 4, \ - adis_update_bits_base(adis, reg, mask, val, 4), \ - adis_update_bits_base(adis, reg, mask, val, 2)); \ + BUILD_BUG_ON(sizeof(val) != 2 && sizeof(val) != 4); \ + adis_update_bits_base(adis, reg, mask, val, sizeof(val)); \ }) /** @@ -399,10 +398,8 @@ static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, * @val can lead to undesired behavior if the register to update is 16bit. */ #define __adis_update_bits(adis, reg, mask, val) ({ \ - BUILD_BUG_ON(sizeof(val) == 1 || sizeof(val) == 8); \ - __builtin_choose_expr(sizeof(val) == 4, \ - __adis_update_bits_base(adis, reg, mask, val, 4), \ - __adis_update_bits_base(adis, reg, mask, val, 2)); \ + BUILD_BUG_ON(sizeof(val) != 2 && sizeof(val) != 4); \ + __adis_update_bits_base(adis, reg, mask, val, sizeof(val)); \ }) int adis_enable_irq(struct adis *adis, bool enable); @@ -443,8 +440,8 @@ static inline void adis_dev_unlock(struct adis *adis) } int adis_single_conversion(struct iio_dev *indio_dev, - const struct iio_chan_spec *chan, unsigned int error_mask, - int *val); + const struct iio_chan_spec *chan, + unsigned int error_mask, int *val); #define ADIS_VOLTAGE_CHAN(addr, si, chan, name, info_all, bits) { \ .type = IIO_VOLTAGE, \ @@ -493,7 +490,7 @@ int adis_single_conversion(struct iio_dev *indio_dev, .modified = 1, \ .channel2 = IIO_MOD_ ## mod, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ - info_sep, \ + (info_sep), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .info_mask_shared_by_all = info_all, \ .address = (addr), \ @@ -527,7 +524,7 @@ devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); int adis_update_scan_mode(struct iio_dev *indio_dev, - const unsigned long *scan_mask); + const unsigned long *scan_mask); #else /* CONFIG_IIO_BUFFER */ @@ -551,7 +548,8 @@ static inline int devm_adis_probe_trigger(struct adis *adis, #ifdef CONFIG_DEBUG_FS int adis_debugfs_reg_access(struct iio_dev *indio_dev, - unsigned int reg, unsigned int writeval, unsigned int *readval); + unsigned int reg, unsigned int writeval, + unsigned int *readval); #else diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 096f68dd2e0c..4c69b144677b 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -55,6 +55,7 @@ struct iio_trigger_ops { * @attached_own_device:[INTERN] if we are using our own device as trigger, * i.e. if we registered a poll function to the same * device as the one providing the trigger. + * @reenable_work: [INTERN] work item used to ensure reenable can sleep. **/ struct iio_trigger { const struct iio_trigger_ops *ops; @@ -74,6 +75,7 @@ struct iio_trigger { unsigned long pool[BITS_TO_LONGS(CONFIG_IIO_CONSUMERS_PER_TRIGGER)]; struct mutex pool_lock; bool attached_own_device; + struct work_struct reenable_work; }; diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 84b3f8175cc6..a7aa91f3a8dc 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -24,6 +24,7 @@ enum iio_event_info { #define IIO_VAL_INT_PLUS_NANO 3 #define IIO_VAL_INT_PLUS_MICRO_DB 4 #define IIO_VAL_INT_MULTIPLE 5 +#define IIO_VAL_INT_64 6 /* 64-bit data, val is lower 32 bits */ #define IIO_VAL_FRACTIONAL 10 #define IIO_VAL_FRACTIONAL_LOG2 11 #define IIO_VAL_CHAR 12 diff --git a/include/linux/ima.h b/include/linux/ima.h index b6ab66a546ae..426b1744215e 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -50,21 +50,6 @@ static inline void ima_appraise_parse_cmdline(void) {} extern void ima_add_kexec_buffer(struct kimage *image); #endif -#ifdef CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT -extern bool arch_ima_get_secureboot(void); -extern const char * const *arch_get_ima_policy(void); -#else -static inline bool arch_ima_get_secureboot(void) -{ - return false; -} - -static inline const char * const *arch_get_ima_policy(void) -{ - return NULL; -} -#endif - #else static inline enum hash_algo ima_get_current_hash_algo(void) { @@ -155,6 +140,21 @@ static inline int ima_measure_critical_data(const char *event_label, #endif /* CONFIG_IMA */ +#ifdef CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT +extern bool arch_ima_get_secureboot(void); +extern const char * const *arch_get_ima_policy(void); +#else +static inline bool arch_ima_get_secureboot(void) +{ + return false; +} + +static inline const char * const *arch_get_ima_policy(void) +{ + return NULL; +} +#endif + #ifndef CONFIG_IMA_KEXEC struct kimage; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 518b484a7f07..ead323243e7b 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -24,6 +24,8 @@ struct ipv4_devconf { struct in_device { struct net_device *dev; + netdevice_tracker dev_tracker; + refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ @@ -148,6 +150,7 @@ struct in_ifaddr { __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; + unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; diff --git a/include/linux/init.h b/include/linux/init.h index d82b4b2e1d25..baf0b29a7010 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -320,12 +320,19 @@ struct obs_kernel_param { __aligned(__alignof__(struct obs_kernel_param)) \ = { __setup_str_##unique_id, fn, early } +/* + * NOTE: __setup functions return values: + * @fn returns 1 (or non-zero) if the option argument is "handled" + * and returns 0 if the option argument is "not handled". + */ #define __setup(str, fn) \ __setup_param(str, fn, fn, 0) /* - * NOTE: fn is as per module_param, not __setup! - * Emits warning if fn returns non-zero. + * NOTE: @fn is as per module_param, not __setup! + * I.e., @fn returns 0 for no error or non-zero for error + * (possibly @fn returns a -errno value, but it does not matter). + * Emits warning if @fn returns non-zero. */ #define early_param(str, fn) \ __setup_param(str, fn, fn, 1) diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 6a24905f6e1e..8d20caa1b268 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,11 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H -#include <linux/sysctl.h> #include <uapi/linux/inotify.h> -extern struct ctl_table inotify_table[]; /* for sysctl */ - #define ALL_INOTIFY_BITS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \ IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \ IN_MOVED_TO | IN_CREATE | IN_DELETE | \ diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index fa2cd8c63dcc..24359b4a9605 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -11,7 +11,7 @@ asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_begin\n\t" \ ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_begin() __instrumentation_begin(__COUNTER__) @@ -50,7 +50,7 @@ asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_end\n\t" \ ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) #else diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 69230fd695ea..2f9891cb3d00 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -525,12 +525,6 @@ struct context_entry { */ #define DOMAIN_FLAG_USE_FIRST_LEVEL BIT(1) -/* - * Domain represents a virtual machine which demands iommu nested - * translation mode support. - */ -#define DOMAIN_FLAG_NESTING_MODE BIT(2) - struct dmar_domain { int nid; /* node id */ @@ -548,7 +542,6 @@ struct dmar_domain { u8 iommu_snooping: 1; /* indicate snooping control feature */ struct list_head devices; /* all devices' list */ - struct list_head subdevices; /* all subdevices' list */ struct iova_domain iovad; /* iova's that belong to this domain */ struct dma_pte *pgd; /* virtual address */ @@ -563,11 +556,6 @@ struct dmar_domain { 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ u64 max_addr; /* maximum mapped address */ - u32 default_pasid; /* - * The default pasid used for non-SVM - * traffic on mediated devices. - */ - struct iommu_domain domain; /* generic domain data structure for iommu core */ }; @@ -590,7 +578,6 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ - struct dmar_domain ***domains; /* ptr to domains */ spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ @@ -620,21 +607,11 @@ struct intel_iommu { void *perf_statistic; }; -/* Per subdevice private data */ -struct subdev_domain_info { - struct list_head link_phys; /* link to phys device siblings */ - struct list_head link_domain; /* link to domain siblings */ - struct device *pdev; /* physical device derived from */ - struct dmar_domain *domain; /* aux-domain */ - int users; /* user count */ -}; - /* PCI domain-device relationship */ struct device_domain_info { struct list_head link; /* link to domain siblings */ struct list_head global; /* link to global list */ struct list_head table; /* link to pasid table */ - struct list_head subdevices; /* subdevices sibling */ u32 segment; /* PCI segment number */ u8 bus; /* PCI bus number */ u8 devfn; /* PCI devfn number */ @@ -645,7 +622,6 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; - u8 auxd_enabled:1; /* Multiple domains per device */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ @@ -717,7 +693,6 @@ static inline int nr_pte_to_next_page(struct dma_pte *pte) } extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); -extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); extern int dmar_enable_qi(struct intel_iommu *iommu); extern void dmar_disable_qi(struct intel_iommu *iommu); @@ -757,17 +732,12 @@ int for_each_device_domain(int (*fn)(struct device_domain_info *info, void *data), void *data); void iommu_flush_write_buffer(struct intel_iommu *iommu); int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct device *dev); -struct dmar_domain *find_domain(struct device *dev); -struct device_domain_info *get_domain_info(struct device *dev); struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); #ifdef CONFIG_INTEL_IOMMU_SVM extern void intel_svm_check(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); -int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev, - struct iommu_gpasid_bind_data *data); -int intel_svm_unbind_gpasid(struct device *dev, u32 pasid); struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata); void intel_svm_unbind(struct iommu_sva *handle); @@ -795,7 +765,6 @@ struct intel_svm { unsigned int flags; u32 pasid; - int gpasid; /* In case that guest PASID is different from host PASID */ struct list_head devs; }; #else @@ -813,6 +782,8 @@ bool context_present(struct context_entry *context); struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, u8 devfn, int alloc); +extern const struct iommu_ops intel_iommu_ops; + #ifdef CONFIG_INTEL_IOMMU extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 57cceecbe37f..b3b125b332aa 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -8,12 +8,6 @@ #ifndef __INTEL_SVM_H__ #define __INTEL_SVM_H__ -/* Values for rxwp in fault_cb callback */ -#define SVM_REQ_READ (1<<3) -#define SVM_REQ_WRITE (1<<2) -#define SVM_REQ_EXEC (1<<1) -#define SVM_REQ_PRIV (1<<0) - /* Page Request Queue depth */ #define PRQ_ORDER 2 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) @@ -31,17 +25,5 @@ * do such IOTLB flushes automatically. */ #define SVM_FLAG_SUPERVISOR_MODE BIT(0) -/* - * The SVM_FLAG_GUEST_MODE flag is used when a PASID bind is for guest - * processes. Compared to the host bind, the primary differences are: - * 1. mm life cycle management - * 2. fault reporting - */ -#define SVM_FLAG_GUEST_MODE BIT(1) -/* - * The SVM_FLAG_GUEST_PASID flag is used when a guest has its own PASID space, - * which requires guest and host PASID translation at both directions. - */ -#define SVM_FLAG_GUEST_PASID BIT(2) #endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 93780834fc8f..9f4b6f5b822f 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -58,6 +58,12 @@ enum rapl_primitives { THROTTLED_TIME, PRIORITY_LEVEL, + PSYS_POWER_LIMIT1, + PSYS_POWER_LIMIT2, + PSYS_PL1_ENABLE, + PSYS_PL2_ENABLE, + PSYS_TIME_WINDOW1, + PSYS_TIME_WINDOW2, /* below are not raw primitive data */ AVERAGE_POWER, NR_RAPL_PRIMITIVES, diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index f2dd2fc8d3cd..f685777b875e 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -38,13 +38,6 @@ struct icc_bulk_data { u32 peak_bw; }; -int __must_check of_icc_bulk_get(struct device *dev, int num_paths, - struct icc_bulk_data *paths); -void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); -int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); -int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); -void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); - #if IS_ENABLED(CONFIG_INTERCONNECT) struct icc_path *icc_get(struct device *dev, const int src_id, @@ -58,6 +51,12 @@ int icc_disable(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); const char *icc_get_name(struct icc_path *path); +int __must_check of_icc_bulk_get(struct device *dev, int num_paths, + struct icc_bulk_data *paths); +void icc_bulk_put(int num_paths, struct icc_bulk_data *paths); +int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths); +int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths); +void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths); #else @@ -112,6 +111,29 @@ static inline const char *icc_get_name(struct icc_path *path) return NULL; } +static inline int of_icc_bulk_get(struct device *dev, int num_paths, struct icc_bulk_data *paths) +{ + return 0; +} + +static inline void icc_bulk_put(int num_paths, struct icc_bulk_data *paths) +{ +} + +static inline int icc_bulk_set_bw(int num_paths, const struct icc_bulk_data *paths) +{ + return 0; +} + +static inline int icc_bulk_enable(int num_paths, const struct icc_bulk_data *paths) +{ + return 0; +} + +static inline void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths) +{ +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_H */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 1f22a30c0963..f40754caaefa 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -329,7 +329,46 @@ extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); -extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); +extern int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, + bool setaffinity); + +/** + * irq_update_affinity_hint - Update the affinity hint + * @irq: Interrupt to update + * @m: cpumask pointer (NULL to clear the hint) + * + * Updates the affinity hint, but does not change the affinity of the interrupt. + */ +static inline int +irq_update_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + return __irq_apply_affinity_hint(irq, m, false); +} + +/** + * irq_set_affinity_and_hint - Update the affinity hint and apply the provided + * cpumask to the interrupt + * @irq: Interrupt to update + * @m: cpumask pointer (NULL to clear the hint) + * + * Updates the affinity hint and if @m is not NULL it applies it as the + * affinity of that interrupt. + */ +static inline int +irq_set_affinity_and_hint(unsigned int irq, const struct cpumask *m) +{ + return __irq_apply_affinity_hint(irq, m, true); +} + +/* + * Deprecated. Use irq_update_affinity_hint() or irq_set_affinity_and_hint() + * instead. + */ +static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + return irq_set_affinity_and_hint(irq, m); +} + extern int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity); @@ -361,6 +400,18 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } +static inline int irq_update_affinity_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} + +static inline int irq_set_affinity_and_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} + static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) { @@ -528,7 +579,16 @@ enum NR_SOFTIRQS }; -#define SOFTIRQ_STOP_IDLE_MASK (~(1 << RCU_SOFTIRQ)) +/* + * The following vectors can be safely ignored after ksoftirqd is parked: + * + * _ RCU: + * 1) rcutree_migrate_callbacks() migrates the queue. + * 2) rcu_report_dead() reports the final quiescent states. + * + * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue + */ +#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ)) /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 649a4d7c241b..1814e698d861 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -9,11 +9,14 @@ struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); +void io_uring_unreg_ringfd(void); static inline void io_uring_files_cancel(void) { - if (current->io_uring) + if (current->io_uring) { + io_uring_unreg_ringfd(); __io_uring_cancel(false); + } } static inline void io_uring_task_cancel(void) { diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h index e9dacd4b9f6b..af1c9d62e642 100644 --- a/include/linux/ioasid.h +++ b/include/linux/ioasid.h @@ -34,13 +34,16 @@ struct ioasid_allocator_ops { #if IS_ENABLED(CONFIG_IOASID) ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, void *private); -void ioasid_get(ioasid_t ioasid); -bool ioasid_put(ioasid_t ioasid); +void ioasid_free(ioasid_t ioasid); void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)); int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); int ioasid_set_data(ioasid_t ioasid, void *data); +static inline bool pasid_valid(ioasid_t ioasid) +{ + return ioasid != INVALID_IOASID; +} #else /* !CONFIG_IOASID */ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, @@ -49,14 +52,7 @@ static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, return INVALID_IOASID; } -static inline void ioasid_get(ioasid_t ioasid) -{ -} - -static inline bool ioasid_put(ioasid_t ioasid) -{ - return false; -} +static inline void ioasid_free(ioasid_t ioasid) { } static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, bool (*getter)(void *)) @@ -78,5 +74,10 @@ static inline int ioasid_set_data(ioasid_t ioasid, void *data) return -ENOTSUPP; } +static inline bool pasid_valid(ioasid_t ioasid) +{ + return false; +} + #endif /* CONFIG_IOASID */ #endif /* __LINUX_IOASID_H */ diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 0a9dc40b7be8..14f7eaf1b443 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -99,55 +99,40 @@ struct io_cq { struct io_context { atomic_long_t refcount; atomic_t active_ref; - atomic_t nr_tasks; + unsigned short ioprio; + +#ifdef CONFIG_BLK_ICQ /* all the fields below are protected by this lock */ spinlock_t lock; - unsigned short ioprio; - struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; struct work_struct release_work; +#endif /* CONFIG_BLK_ICQ */ }; -/** - * get_io_context_active - get active reference on ioc - * @ioc: ioc of interest - * - * Only iocs with active reference can issue new IOs. This function - * acquires an active reference on @ioc. The caller must already have an - * active reference on @ioc. - */ -static inline void get_io_context_active(struct io_context *ioc) -{ - WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0); - WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0); - atomic_long_inc(&ioc->refcount); - atomic_inc(&ioc->active_ref); -} - -static inline void ioc_task_link(struct io_context *ioc) -{ - get_io_context_active(ioc); - - WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); - atomic_inc(&ioc->nr_tasks); -} - struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); -void put_io_context_active(struct io_context *ioc); void exit_io_context(struct task_struct *task); -struct io_context *get_task_io_context(struct task_struct *task, - gfp_t gfp_flags, int node); +int __copy_io(unsigned long clone_flags, struct task_struct *tsk); +static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + if (!current->io_context) + return 0; + return __copy_io(clone_flags, tsk); +} #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } -#endif +static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + return 0; +} +#endif /* CONFIG_BLOCK */ -#endif +#endif /* IOCONTEXT_H */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6d1b08d0ae93..b76f0dd149fb 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -141,6 +141,11 @@ struct iomap_page_ops { #define IOMAP_NOWAIT (1 << 5) /* do not block */ #define IOMAP_OVERWRITE_ONLY (1 << 6) /* only pure overwrites allowed */ #define IOMAP_UNSHARE (1 << 7) /* unshare_file_range */ +#ifdef CONFIG_FS_DAX +#define IOMAP_DAX (1 << 8) /* DAX mapping */ +#else +#define IOMAP_DAX 0 +#endif /* CONFIG_FS_DAX */ struct iomap_ops { /* @@ -222,11 +227,9 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); -int iomap_is_partially_uptodate(struct page *page, unsigned long from, - unsigned long count); +bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); -void iomap_invalidatepage(struct page *page, unsigned int offset, - unsigned int len); +void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); #ifdef CONFIG_MIGRATION int iomap_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); @@ -257,9 +260,11 @@ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ u16 io_type; u16 io_flags; /* IOMAP_F_* */ + u32 io_folios; /* folios added to ioend */ struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ loff_t io_offset; /* offset in the file */ + sector_t io_sector; /* start sector of ioend */ struct bio *io_bio; /* bio being built */ struct bio io_inline_bio; /* MUST BE LAST! */ }; @@ -284,7 +289,7 @@ struct iomap_writeback_ops { * Optional, allows the file system to discard state on a page where * we failed to submit any I/O. */ - void (*discard_page)(struct page *page, loff_t fileoff); + void (*discard_folio)(struct folio *folio, loff_t pos); }; struct iomap_writepage_ctx { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d2f3435e7d17..9208eca4b0d1 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -37,6 +37,7 @@ struct iommu_group; struct bus_type; struct device; struct iommu_domain; +struct iommu_domain_ops; struct notifier_block; struct iommu_sva; struct iommu_fault_event; @@ -88,7 +89,7 @@ struct iommu_domain_geometry { struct iommu_domain { unsigned type; - const struct iommu_ops *ops; + const struct iommu_domain_ops *ops; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ iommu_fault_handler_t handler; void *handler_token; @@ -144,7 +145,6 @@ struct iommu_resv_region { /** * enum iommu_dev_features - Per device IOMMU features - * @IOMMU_DEV_FEAT_AUX: Auxiliary domain feature * @IOMMU_DEV_FEAT_SVA: Shared Virtual Addresses * @IOMMU_DEV_FEAT_IOPF: I/O Page Faults such as PRI or Stall. Generally * enabling %IOMMU_DEV_FEAT_SVA requires @@ -157,7 +157,6 @@ struct iommu_resv_region { * iommu_dev_has_feature(), and enable it using iommu_dev_enable_feature(). */ enum iommu_dev_features { - IOMMU_DEV_FEAT_AUX, IOMMU_DEV_FEAT_SVA, IOMMU_DEV_FEAT_IOPF, }; @@ -186,7 +185,7 @@ struct iommu_iotlb_gather { unsigned long start; unsigned long end; size_t pgsize; - struct page *freelist; + struct list_head freelist; bool queued; }; @@ -194,48 +193,28 @@ struct iommu_iotlb_gather { * struct iommu_ops - iommu ops and capabilities * @capable: check capability * @domain_alloc: allocate iommu domain - * @domain_free: free iommu domain - * @attach_dev: attach device to an iommu domain - * @detach_dev: detach device from an iommu domain - * @map: map a physically contiguous memory region to an iommu domain - * @map_pages: map a physically contiguous set of pages of the same size to - * an iommu domain. - * @unmap: unmap a physically contiguous memory region from an iommu domain - * @unmap_pages: unmap a number of pages of the same size from an iommu domain - * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain - * @iotlb_sync_map: Sync mappings created recently using @map to the hardware - * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush - * queue - * @iova_to_phys: translate iova to physical address * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU * group and attached to the groups domain * @device_group: find iommu group for a particular device - * @enable_nesting: Enable nesting - * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @get_resv_regions: Request list of reserved regions for a device * @put_resv_regions: Free list of reserved regions for a device - * @apply_resv_region: Temporary helper call-back for iova reserved ranges * @of_xlate: add OF master IDs to iommu grouping * @is_attach_deferred: Check if domain attach should be deferred from iommu * driver init to device driver init (default no) * @dev_has/enable/disable_feat: per device entries to check/enable/disable * iommu specific features. * @dev_feat_enabled: check enabled feature - * @aux_attach/detach_dev: aux-domain specific attach/detach entries. - * @aux_get_pasid: get the pasid given an aux-domain * @sva_bind: Bind process address space to device * @sva_unbind: Unbind process address space from device * @sva_get_pasid: Get PASID associated to a SVA handle * @page_response: handle page request response - * @cache_invalidate: invalidate translation caches - * @sva_bind_gpasid: bind guest pasid and mm - * @sva_unbind_gpasid: unbind guest pasid and mm * @def_domain_type: device default domain type, return value: * - IOMMU_DOMAIN_IDENTITY: must use an identity domain * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting + * @default_domain_ops: the default ops for domains * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ @@ -244,43 +223,18 @@ struct iommu_ops { /* Domain allocation and freeing by the iommu driver */ struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type); - void (*domain_free)(struct iommu_domain *); - int (*attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*detach_dev)(struct iommu_domain *domain, struct device *dev); - int (*map)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp); - int (*map_pages)(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t pgsize, size_t pgcount, - int prot, gfp_t gfp, size_t *mapped); - size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, - size_t size, struct iommu_iotlb_gather *iotlb_gather); - size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, - size_t pgsize, size_t pgcount, - struct iommu_iotlb_gather *iotlb_gather); - void (*flush_iotlb_all)(struct iommu_domain *domain); - void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, - size_t size); - void (*iotlb_sync)(struct iommu_domain *domain, - struct iommu_iotlb_gather *iotlb_gather); - phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); void (*probe_finalize)(struct device *dev); struct iommu_group *(*device_group)(struct device *dev); - int (*enable_nesting)(struct iommu_domain *domain); - int (*set_pgtable_quirks)(struct iommu_domain *domain, - unsigned long quirks); /* Request/Free a list of reserved regions for a device */ void (*get_resv_regions)(struct device *dev, struct list_head *list); void (*put_resv_regions)(struct device *dev, struct list_head *list); - void (*apply_resv_region)(struct device *dev, - struct iommu_domain *domain, - struct iommu_resv_region *region); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); - bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); + bool (*is_attach_deferred)(struct device *dev); /* Per device IOMMU features */ bool (*dev_has_feat)(struct device *dev, enum iommu_dev_features f); @@ -288,11 +242,6 @@ struct iommu_ops { int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); - /* Aux-domain specific attach/detach entries */ - int (*aux_attach_dev)(struct iommu_domain *domain, struct device *dev); - void (*aux_detach_dev)(struct iommu_domain *domain, struct device *dev); - int (*aux_get_pasid)(struct iommu_domain *domain, struct device *dev); - struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, void *drvdata); void (*sva_unbind)(struct iommu_sva *handle); @@ -301,20 +250,64 @@ struct iommu_ops { int (*page_response)(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg); - int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev, - struct iommu_cache_invalidate_info *inv_info); - int (*sva_bind_gpasid)(struct iommu_domain *domain, - struct device *dev, struct iommu_gpasid_bind_data *data); - - int (*sva_unbind_gpasid)(struct device *dev, u32 pasid); int (*def_domain_type)(struct device *dev); + const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; struct module *owner; }; /** + * struct iommu_domain_ops - domain specific operations + * @attach_dev: attach an iommu domain to a device + * @detach_dev: detach an iommu domain from a device + * @map: map a physically contiguous memory region to an iommu domain + * @map_pages: map a physically contiguous set of pages of the same size to + * an iommu domain. + * @unmap: unmap a physically contiguous memory region from an iommu domain + * @unmap_pages: unmap a number of pages of the same size from an iommu domain + * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain + * @iotlb_sync_map: Sync mappings created recently using @map to the hardware + * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * queue + * @iova_to_phys: translate iova to physical address + * @enable_nesting: Enable nesting + * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) + * @free: Release the domain after use. + */ +struct iommu_domain_ops { + int (*attach_dev)(struct iommu_domain *domain, struct device *dev); + void (*detach_dev)(struct iommu_domain *domain, struct device *dev); + + int (*map)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp); + int (*map_pages)(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t pgsize, size_t pgcount, + int prot, gfp_t gfp, size_t *mapped); + size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, + size_t size, struct iommu_iotlb_gather *iotlb_gather); + size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova, + size_t pgsize, size_t pgcount, + struct iommu_iotlb_gather *iotlb_gather); + + void (*flush_iotlb_all)(struct iommu_domain *domain); + void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova, + size_t size); + void (*iotlb_sync)(struct iommu_domain *domain, + struct iommu_iotlb_gather *iotlb_gather); + + phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, + dma_addr_t iova); + + int (*enable_nesting)(struct iommu_domain *domain); + int (*set_pgtable_quirks)(struct iommu_domain *domain, + unsigned long quirks); + + void (*free)(struct iommu_domain *domain); +}; + +/** * struct iommu_device - IOMMU core representation of one IOMMU hardware * instance * @list: Used by the iommu-core to keep a list of registered iommus @@ -399,9 +392,21 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) { *gather = (struct iommu_iotlb_gather) { .start = ULONG_MAX, + .freelist = LIST_HEAD_INIT(gather->freelist), }; } +static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) +{ + /* + * Assume that valid ops must be installed if iommu_probe_device() + * has succeeded. The device ops are essentially for internal use + * within the IOMMU subsystem itself, so we should be able to trust + * ourselves not to misuse the helper. + */ + return dev->iommu->iommu_dev->ops; +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ @@ -420,14 +425,6 @@ extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - void __user *uinfo); - -extern int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata); -extern int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata); extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); @@ -671,9 +668,6 @@ void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features f); -int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev); -void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev); -int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, @@ -1018,23 +1012,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) return -ENODEV; } -static inline int -iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) -{ - return -ENODEV; -} - -static inline void -iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev) -{ -} - -static inline int -iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) -{ - return -ENODEV; -} - static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) { @@ -1050,33 +1027,6 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) return IOMMU_PASID_INVALID; } -static inline int -iommu_uapi_cache_invalidate(struct iommu_domain *domain, - struct device *dev, - struct iommu_cache_invalidate_info *inv_info) -{ - return -ENODEV; -} - -static inline int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata) -{ - return -ENODEV; -} - -static inline int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, void __user *udata) -{ - return -ENODEV; -} - -static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, - ioasid_t pasid) -{ - return -ENODEV; -} - static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 8359c50f9988..ec5f71f7135b 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -262,6 +262,8 @@ resource_union(struct resource *r1, struct resource *r2, struct resource *r) #define request_muxed_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED) #define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl) #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0) +#define request_mem_region_muxed(start, n, name) \ + __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_MUXED) #define request_mem_region_exclusive(start,n,name) \ __request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE) #define rename_region(region, newname) do { (region)->name = (newname); } while (0) diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h new file mode 100644 index 000000000000..e69a002d5aa4 --- /dev/null +++ b/include/linux/iosys-map.h @@ -0,0 +1,459 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Pointer abstraction for IO/system memory + */ + +#ifndef __IOSYS_MAP_H__ +#define __IOSYS_MAP_H__ + +#include <linux/io.h> +#include <linux/string.h> + +/** + * DOC: overview + * + * When accessing a memory region, depending on its location, users may have to + * access it with I/O operations or memory load/store operations. For example, + * copying to system memory could be done with memcpy(), copying to I/O memory + * would be done with memcpy_toio(). + * + * .. code-block:: c + * + * void *vaddr = ...; // pointer to system memory + * memcpy(vaddr, src, len); + * + * void *vaddr_iomem = ...; // pointer to I/O memory + * memcpy_toio(vaddr, _iomem, src, len); + * + * The user of such pointer may not have information about the mapping of that + * region or may want to have a single code path to handle operations on that + * buffer, regardless if it's located in system or IO memory. The type + * :c:type:`struct iosys_map <iosys_map>` and its helpers abstract that so the + * buffer can be passed around to other drivers or have separate duties inside + * the same driver for allocation, read and write operations. + * + * Open-coding access to :c:type:`struct iosys_map <iosys_map>` is considered + * bad style. Rather then accessing its fields directly, use one of the provided + * helper functions, or implement your own. For example, instances of + * :c:type:`struct iosys_map <iosys_map>` can be initialized statically with + * IOSYS_MAP_INIT_VADDR(), or at runtime with iosys_map_set_vaddr(). These + * helpers will set an address in system memory. + * + * .. code-block:: c + * + * struct iosys_map map = IOSYS_MAP_INIT_VADDR(0xdeadbeaf); + * + * iosys_map_set_vaddr(&map, 0xdeadbeaf); + * + * To set an address in I/O memory, use iosys_map_set_vaddr_iomem(). + * + * .. code-block:: c + * + * iosys_map_set_vaddr_iomem(&map, 0xdeadbeaf); + * + * Instances of struct iosys_map do not have to be cleaned up, but + * can be cleared to NULL with iosys_map_clear(). Cleared mappings + * always refer to system memory. + * + * .. code-block:: c + * + * iosys_map_clear(&map); + * + * Test if a mapping is valid with either iosys_map_is_set() or + * iosys_map_is_null(). + * + * .. code-block:: c + * + * if (iosys_map_is_set(&map) != iosys_map_is_null(&map)) + * // always true + * + * Instances of :c:type:`struct iosys_map <iosys_map>` can be compared for + * equality with iosys_map_is_equal(). Mappings that point to different memory + * spaces, system or I/O, are never equal. That's even true if both spaces are + * located in the same address space, both mappings contain the same address + * value, or both mappings refer to NULL. + * + * .. code-block:: c + * + * struct iosys_map sys_map; // refers to system memory + * struct iosys_map io_map; // refers to I/O memory + * + * if (iosys_map_is_equal(&sys_map, &io_map)) + * // always false + * + * A set up instance of struct iosys_map can be used to access or manipulate the + * buffer memory. Depending on the location of the memory, the provided helpers + * will pick the correct operations. Data can be copied into the memory with + * iosys_map_memcpy_to(). The address can be manipulated with iosys_map_incr(). + * + * .. code-block:: c + * + * const void *src = ...; // source buffer + * size_t len = ...; // length of src + * + * iosys_map_memcpy_to(&map, src, len); + * iosys_map_incr(&map, len); // go to first byte after the memcpy + */ + +/** + * struct iosys_map - Pointer to IO/system memory + * @vaddr_iomem: The buffer's address if in I/O memory + * @vaddr: The buffer's address if in system memory + * @is_iomem: True if the buffer is located in I/O memory, or false + * otherwise. + */ +struct iosys_map { + union { + void __iomem *vaddr_iomem; + void *vaddr; + }; + bool is_iomem; +}; + +/** + * IOSYS_MAP_INIT_VADDR - Initializes struct iosys_map to an address in system memory + * @vaddr_: A system-memory address + */ +#define IOSYS_MAP_INIT_VADDR(vaddr_) \ + { \ + .vaddr = (vaddr_), \ + .is_iomem = false, \ + } + +/** + * IOSYS_MAP_INIT_OFFSET - Initializes struct iosys_map from another iosys_map + * @map_: The dma-buf mapping structure to copy from + * @offset_: Offset to add to the other mapping + * + * Initializes a new iosys_map struct based on another passed as argument. It + * does a shallow copy of the struct so it's possible to update the back storage + * without changing where the original map points to. It is the equivalent of + * doing: + * + * .. code-block:: c + * + * iosys_map map = other_map; + * iosys_map_incr(&map, &offset); + * + * Example usage: + * + * .. code-block:: c + * + * void foo(struct device *dev, struct iosys_map *base_map) + * { + * ... + * struct iosys_map map = IOSYS_MAP_INIT_OFFSET(base_map, FIELD_OFFSET); + * ... + * } + * + * The advantage of using the initializer over just increasing the offset with + * iosys_map_incr() like above is that the new map will always point to the + * right place of the buffer during its scope. It reduces the risk of updating + * the wrong part of the buffer and having no compiler warning about that. If + * the assignment to IOSYS_MAP_INIT_OFFSET() is forgotten, the compiler can warn + * about the use of uninitialized variable. + */ +#define IOSYS_MAP_INIT_OFFSET(map_, offset_) ({ \ + struct iosys_map copy = *map_; \ + iosys_map_incr(©, offset_); \ + copy; \ +}) + +/** + * iosys_map_set_vaddr - Sets a iosys mapping structure to an address in system memory + * @map: The iosys_map structure + * @vaddr: A system-memory address + * + * Sets the address and clears the I/O-memory flag. + */ +static inline void iosys_map_set_vaddr(struct iosys_map *map, void *vaddr) +{ + map->vaddr = vaddr; + map->is_iomem = false; +} + +/** + * iosys_map_set_vaddr_iomem - Sets a iosys mapping structure to an address in I/O memory + * @map: The iosys_map structure + * @vaddr_iomem: An I/O-memory address + * + * Sets the address and the I/O-memory flag. + */ +static inline void iosys_map_set_vaddr_iomem(struct iosys_map *map, + void __iomem *vaddr_iomem) +{ + map->vaddr_iomem = vaddr_iomem; + map->is_iomem = true; +} + +/** + * iosys_map_is_equal - Compares two iosys mapping structures for equality + * @lhs: The iosys_map structure + * @rhs: A iosys_map structure to compare with + * + * Two iosys mapping structures are equal if they both refer to the same type of memory + * and to the same address within that memory. + * + * Returns: + * True is both structures are equal, or false otherwise. + */ +static inline bool iosys_map_is_equal(const struct iosys_map *lhs, + const struct iosys_map *rhs) +{ + if (lhs->is_iomem != rhs->is_iomem) + return false; + else if (lhs->is_iomem) + return lhs->vaddr_iomem == rhs->vaddr_iomem; + else + return lhs->vaddr == rhs->vaddr; +} + +/** + * iosys_map_is_null - Tests for a iosys mapping to be NULL + * @map: The iosys_map structure + * + * Depending on the state of struct iosys_map.is_iomem, tests if the + * mapping is NULL. + * + * Returns: + * True if the mapping is NULL, or false otherwise. + */ +static inline bool iosys_map_is_null(const struct iosys_map *map) +{ + if (map->is_iomem) + return !map->vaddr_iomem; + return !map->vaddr; +} + +/** + * iosys_map_is_set - Tests if the iosys mapping has been set + * @map: The iosys_map structure + * + * Depending on the state of struct iosys_map.is_iomem, tests if the + * mapping has been set. + * + * Returns: + * True if the mapping is been set, or false otherwise. + */ +static inline bool iosys_map_is_set(const struct iosys_map *map) +{ + return !iosys_map_is_null(map); +} + +/** + * iosys_map_clear - Clears a iosys mapping structure + * @map: The iosys_map structure + * + * Clears all fields to zero, including struct iosys_map.is_iomem, so + * mapping structures that were set to point to I/O memory are reset for + * system memory. Pointers are cleared to NULL. This is the default. + */ +static inline void iosys_map_clear(struct iosys_map *map) +{ + if (map->is_iomem) { + map->vaddr_iomem = NULL; + map->is_iomem = false; + } else { + map->vaddr = NULL; + } +} + +/** + * iosys_map_memcpy_to - Memcpy into offset of iosys_map + * @dst: The iosys_map structure + * @dst_offset: The offset from which to copy + * @src: The source buffer + * @len: The number of byte in src + * + * Copies data into a iosys_map with an offset. The source buffer is in + * system memory. Depending on the buffer's location, the helper picks the + * correct method of accessing the memory. + */ +static inline void iosys_map_memcpy_to(struct iosys_map *dst, size_t dst_offset, + const void *src, size_t len) +{ + if (dst->is_iomem) + memcpy_toio(dst->vaddr_iomem + dst_offset, src, len); + else + memcpy(dst->vaddr + dst_offset, src, len); +} + +/** + * iosys_map_memcpy_from - Memcpy from iosys_map into system memory + * @dst: Destination in system memory + * @src: The iosys_map structure + * @src_offset: The offset from which to copy + * @len: The number of byte in src + * + * Copies data from a iosys_map with an offset. The dest buffer is in + * system memory. Depending on the mapping location, the helper picks the + * correct method of accessing the memory. + */ +static inline void iosys_map_memcpy_from(void *dst, const struct iosys_map *src, + size_t src_offset, size_t len) +{ + if (src->is_iomem) + memcpy_fromio(dst, src->vaddr_iomem + src_offset, len); + else + memcpy(dst, src->vaddr + src_offset, len); +} + +/** + * iosys_map_incr - Increments the address stored in a iosys mapping + * @map: The iosys_map structure + * @incr: The number of bytes to increment + * + * Increments the address stored in a iosys mapping. Depending on the + * buffer's location, the correct value will be updated. + */ +static inline void iosys_map_incr(struct iosys_map *map, size_t incr) +{ + if (map->is_iomem) + map->vaddr_iomem += incr; + else + map->vaddr += incr; +} + +/** + * iosys_map_memset - Memset iosys_map + * @dst: The iosys_map structure + * @offset: Offset from dst where to start setting value + * @value: The value to set + * @len: The number of bytes to set in dst + * + * Set value in iosys_map. Depending on the buffer's location, the helper + * picks the correct method of accessing the memory. + */ +static inline void iosys_map_memset(struct iosys_map *dst, size_t offset, + int value, size_t len) +{ + if (dst->is_iomem) + memset_io(dst->vaddr_iomem + offset, value, len); + else + memset(dst->vaddr + offset, value, len); +} + +/** + * iosys_map_rd - Read a C-type value from the iosys_map + * + * @map__: The iosys_map structure + * @offset__: The offset from which to read + * @type__: Type of the value being read + * + * Read a C type value from iosys_map, handling possible un-aligned accesses to + * the mapping. + * + * Returns: + * The value read from the mapping. + */ +#define iosys_map_rd(map__, offset__, type__) ({ \ + type__ val; \ + iosys_map_memcpy_from(&val, map__, offset__, sizeof(val)); \ + val; \ +}) + +/** + * iosys_map_wr - Write a C-type value to the iosys_map + * + * @map__: The iosys_map structure + * @offset__: The offset from the mapping to write to + * @type__: Type of the value being written + * @val__: Value to write + * + * Write a C-type value to the iosys_map, handling possible un-aligned accesses + * to the mapping. + */ +#define iosys_map_wr(map__, offset__, type__, val__) ({ \ + type__ val = (val__); \ + iosys_map_memcpy_to(map__, offset__, &val, sizeof(val)); \ +}) + +/** + * iosys_map_rd_field - Read a member from a struct in the iosys_map + * + * @map__: The iosys_map structure + * @struct_offset__: Offset from the beggining of the map, where the struct + * is located + * @struct_type__: The struct describing the layout of the mapping + * @field__: Member of the struct to read + * + * Read a value from iosys_map considering its layout is described by a C struct + * starting at @struct_offset__. The field offset and size is calculated and its + * value read handling possible un-aligned memory accesses. For example: suppose + * there is a @struct foo defined as below and the value ``foo.field2.inner2`` + * needs to be read from the iosys_map: + * + * .. code-block:: c + * + * struct foo { + * int field1; + * struct { + * int inner1; + * int inner2; + * } field2; + * int field3; + * } __packed; + * + * This is the expected memory layout of a buffer using iosys_map_rd_field(): + * + * +------------------------------+--------------------------+ + * | Address | Content | + * +==============================+==========================+ + * | buffer + 0000 | start of mmapped buffer | + * | | pointed by iosys_map | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + ``struct_offset__`` | start of ``struct foo`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + wwww | ``foo.field2.inner2`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + yyyy | end of ``struct foo`` | + * +------------------------------+--------------------------+ + * | ... | ... | + * +------------------------------+--------------------------+ + * | buffer + zzzz | end of mmaped buffer | + * +------------------------------+--------------------------+ + * + * Values automatically calculated by this macro or not needed are denoted by + * wwww, yyyy and zzzz. This is the code to read that value: + * + * .. code-block:: c + * + * x = iosys_map_rd_field(&map, offset, struct foo, field2.inner2); + * + * Returns: + * The value read from the mapping. + */ +#define iosys_map_rd_field(map__, struct_offset__, struct_type__, field__) ({ \ + struct_type__ *s; \ + iosys_map_rd(map__, struct_offset__ + offsetof(struct_type__, field__), \ + typeof(s->field__)); \ +}) + +/** + * iosys_map_wr_field - Write to a member of a struct in the iosys_map + * + * @map__: The iosys_map structure + * @struct_offset__: Offset from the beggining of the map, where the struct + * is located + * @struct_type__: The struct describing the layout of the mapping + * @field__: Member of the struct to read + * @val__: Value to write + * + * Write a value to the iosys_map considering its layout is described by a C struct + * starting at @struct_offset__. The field offset and size is calculated and the + * @val__ is written handling possible un-aligned memory accesses. Refer to + * iosys_map_rd_field() for expected usage and memory layout. + */ +#define iosys_map_wr_field(map__, struct_offset__, struct_type__, field__, val__) ({ \ + struct_type__ *s; \ + iosys_map_wr(map__, struct_offset__ + offsetof(struct_type__, field__), \ + typeof(s->field__), val__); \ +}) + +#endif /* __IOSYS_MAP_H__ */ diff --git a/include/linux/iova.h b/include/linux/iova.h index 71d8a2de6635..320a70e40233 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -12,7 +12,6 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/rbtree.h> -#include <linux/atomic.h> #include <linux/dma-mapping.h> /* iova structure */ @@ -22,47 +21,8 @@ struct iova { unsigned long pfn_lo; /* Lowest allocated pfn */ }; -struct iova_magazine; -struct iova_cpu_rcache; -#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */ -#define MAX_GLOBAL_MAGS 32 /* magazines per bin */ - -struct iova_rcache { - spinlock_t lock; - unsigned long depot_size; - struct iova_magazine *depot[MAX_GLOBAL_MAGS]; - struct iova_cpu_rcache __percpu *cpu_rcaches; -}; - -struct iova_domain; - -/* Call-Back from IOVA code into IOMMU drivers */ -typedef void (* iova_flush_cb)(struct iova_domain *domain); - -/* Destructor for per-entry data */ -typedef void (* iova_entry_dtor)(unsigned long data); - -/* Number of entries per Flush Queue */ -#define IOVA_FQ_SIZE 256 - -/* Timeout (in ms) after which entries are flushed from the Flush-Queue */ -#define IOVA_FQ_TIMEOUT 10 - -/* Flush Queue entry for defered flushing */ -struct iova_fq_entry { - unsigned long iova_pfn; - unsigned long pages; - unsigned long data; - u64 counter; /* Flush counter when this entrie was added */ -}; - -/* Per-CPU Flush Queue structure */ -struct iova_fq { - struct iova_fq_entry entries[IOVA_FQ_SIZE]; - unsigned head, tail; - spinlock_t lock; -}; +struct iova_rcache; /* holds all the iova translations for a domain */ struct iova_domain { @@ -74,27 +34,9 @@ struct iova_domain { unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; unsigned long max32_alloc_size; /* Size of last failed allocation */ - struct iova_fq __percpu *fq; /* Flush Queue */ - - atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that - have been started */ - - atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that - have been finished */ - struct iova anchor; /* rbtree lookup anchor */ - struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ - iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU - TLBs */ - - iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for - iova entry */ - - struct timer_list fq_timer; /* Timer to regularily empty the - flush-queues */ - atomic_t fq_timer_on; /* 1 when timer is active, 0 - when not */ + struct iova_rcache *rcaches; struct hlist_node cpuhp_dead; }; @@ -144,17 +86,13 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, bool size_aligned); void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); -void queue_iova(struct iova_domain *iovad, - unsigned long pfn, unsigned long pages, - unsigned long data); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); +int iova_domain_init_rcaches(struct iova_domain *iovad); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else @@ -189,12 +127,6 @@ static inline void free_iova_fast(struct iova_domain *iovad, { } -static inline void queue_iova(struct iova_domain *iovad, - unsigned long pfn, unsigned long pages, - unsigned long data) -{ -} - static inline unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, @@ -216,13 +148,6 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } -static inline int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, - iova_entry_dtor entry_dtor) -{ - return -ENODEV; -} - static inline struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) { diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 20c1f968da7c..16870f86c74d 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -51,7 +51,7 @@ struct ipv6_devconf { __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - __s32 mc_forwarding; + atomic_t mc_forwarding; #endif __s32 disable_ipv6; __s32 drop_unicast_in_l2_multicast; @@ -133,6 +133,7 @@ struct inet6_skb_parm { __u16 dsthao; #endif __u16 frag_max_size; + __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 @@ -142,6 +143,7 @@ struct inet6_skb_parm { #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 +#define IP6SKB_SEG6 256 }; #if defined(CONFIG_NET_L3_MASTER_DEV) @@ -369,19 +371,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) return NULL; } -static inline struct inet6_request_sock * - inet6_rsk(const struct request_sock *rsk) -{ - return NULL; -} - static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL -#define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ diff --git a/include/linux/irq.h b/include/linux/irq.h index 848e1e12c5c6..f92788ccdba2 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -456,7 +456,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) /** * struct irq_chip - hardware interrupt chip descriptor * - * @parent_device: pointer to parent device for irqchip * @name: name for /proc/interrupts * @irq_startup: start up the interrupt (defaults to ->enable if NULL) * @irq_shutdown: shut down the interrupt (defaults to ->disable if NULL) @@ -503,7 +502,6 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * @flags: chip specific flags */ struct irq_chip { - struct device *parent_device; const char *name; unsigned int (*irq_startup)(struct irq_data *data); void (*irq_shutdown)(struct irq_data *data); @@ -712,10 +710,11 @@ extern struct irq_chip no_irq_chip; extern struct irq_chip dummy_irq_chip; extern void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name); -static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *chip, +static inline void irq_set_chip_and_handler(unsigned int irq, + const struct irq_chip *chip, irq_flow_handler_t handle) { irq_set_chip_and_handler_name(irq, chip, handle, NULL); @@ -805,7 +804,7 @@ static inline void irq_set_percpu_devid_flags(unsigned int irq) } /* Set/get chip/data for an IRQ: */ -extern int irq_set_chip(unsigned int irq, struct irq_chip *chip); +extern int irq_set_chip(unsigned int irq, const struct irq_chip *chip); extern int irq_set_handler_data(unsigned int irq, void *data); extern int irq_set_chip_data(unsigned int irq, void *data); extern int irq_set_irq_type(unsigned int irq, unsigned int type); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 81cbf85f73de..12d91f0dedf9 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -615,7 +615,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; - bool lpi_enabled; + u64 flags; cpumask_t *vpe_table_mask; void *vpe_l1_base; } __percpu *rdist; @@ -624,6 +624,7 @@ struct rdists { u64 flags; u32 gicd_typer; u32 gicd_typer2; + int cpuhp_memreserve_state; bool has_vlpis; bool has_rvpeid; bool has_direct_lpi; @@ -632,6 +633,7 @@ struct rdists { struct irq_domain; struct fwnode_handle; +int __init its_lpi_memreserve_init(void); int its_cpu_init(void); int its_init(struct fwnode_handle *handle, struct rdists *rdists, struct irq_domain *domain); diff --git a/include/linux/irqchip/versatile-fpga.h b/include/linux/irqchip/versatile-fpga.h deleted file mode 100644 index a978fc8c7996..000000000000 --- a/include/linux/irqchip/versatile-fpga.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef PLAT_FPGA_IRQ_H -#define PLAT_FPGA_IRQ_H - -struct device_node; -struct pt_regs; - -void fpga_handle_irq(struct pt_regs *regs); -void fpga_irq_init(void __iomem *, const char *, int, int, u32, - struct device_node *node); -int fpga_irq_of_init(struct device_node *node, - struct device_node *parent); - -#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 93d270ca0c56..a77584593f7d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -160,6 +160,7 @@ static inline void generic_handle_irq_desc(struct irq_desc *desc) int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); +int generic_handle_irq_safe(unsigned int irq); #ifdef CONFIG_IRQ_DOMAIN /* diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 553da4899f55..00d577f90883 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -131,7 +131,7 @@ struct irq_domain_ops { #endif }; -extern struct irq_domain_ops irq_generic_chip_ops; +extern const struct irq_domain_ops irq_generic_chip_ops; struct irq_domain_chip_generic; @@ -151,6 +151,8 @@ struct irq_domain_chip_generic; * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. + * @dev: Pointer to a device that the domain represent, and that will be + * used for power management purposes. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * * Revmap data, used internally by irq_domain @@ -171,6 +173,7 @@ struct irq_domain { struct fwnode_handle *fwnode; enum irq_domain_bus_token bus_token; struct irq_domain_chip_generic *gc; + struct device *dev; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif @@ -226,6 +229,13 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d) return to_of_node(d->fwnode); } +static inline void irq_domain_set_pm_device(struct irq_domain *d, + struct device *dev) +{ + if (d) + d->dev = dev; +} + #ifdef CONFIG_IRQ_DOMAIN struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id, const char *name, phys_addr_t *pa); @@ -469,7 +479,8 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest); extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq); extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, + const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name); extern void irq_domain_reset_irq_data(struct irq_data *irq_data); @@ -512,7 +523,7 @@ extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq, - struct irq_chip *chip, + const struct irq_chip *chip, void *chip_data); extern void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 600c10da321a..4b140938b03e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -71,14 +71,6 @@ do { \ do { \ __this_cpu_dec(hardirq_context); \ } while (0) -# define lockdep_softirq_enter() \ -do { \ - current->softirq_context++; \ -} while (0) -# define lockdep_softirq_exit() \ -do { \ - current->softirq_context--; \ -} while (0) # define lockdep_hrtimer_enter(__hrtimer) \ ({ \ @@ -140,6 +132,21 @@ do { \ # define lockdep_irq_work_exit(__work) do { } while (0) #endif +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ +} while (0) + +#else +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) +#endif + #if defined(CONFIG_IRQSOFF_TRACER) || \ defined(CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fd933c45281a..de9536680b2b 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -554,9 +554,6 @@ struct transaction_chp_stats_s { * ->j_list_lock * * j_state_lock - * ->t_handle_lock - * - * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ @@ -594,7 +591,7 @@ struct transaction_s */ unsigned long t_log_start; - /* + /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ @@ -1295,7 +1292,7 @@ struct journal_s * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ - void (*j_fc_cleanup_callback)(struct journal_s *journal, int); + void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: @@ -1419,9 +1416,7 @@ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); @@ -1486,9 +1481,6 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct buffer_head **bh_out, sector_t blocknr); -/* Transaction locking */ -extern void __wait_on_journal (journal_t *); - /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); @@ -1535,14 +1527,16 @@ void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); -extern int jbd2_journal_invalidatepage(journal_t *, - struct page *, unsigned int, unsigned int); +int jbd2_journal_invalidate_folio(journal_t *, struct folio *, + size_t offset, size_t length); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); +void jbd2_journal_wait_updates(journal_t *); + extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); @@ -1774,8 +1768,6 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -extern int jbd_blocks_per_page(struct inode *inode); - /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 48b9b2a82767..107751cc047b 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -82,10 +82,9 @@ extern bool static_key_initialized; "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) -#ifdef CONFIG_JUMP_LABEL - struct static_key { atomic_t enabled; +#ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static @@ -104,13 +103,9 @@ struct static_key { struct jump_entry *entries; struct static_key_mod *next; }; +#endif /* CONFIG_JUMP_LABEL */ }; -#else -struct static_key { - atomic_t enabled; -}; -#endif /* CONFIG_JUMP_LABEL */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL @@ -251,10 +246,10 @@ extern void static_key_disable_cpuslocked(struct static_key *key); */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ - { .entries = (void *)JUMP_TYPE_TRUE } } + { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ - { .entries = (void *)JUMP_TYPE_FALSE } } + { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 4176c7eca7b5..ce1bd2fbf23e 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -48,7 +48,7 @@ static inline int is_ksym_addr(unsigned long addr) static inline void *dereference_symbol_descriptor(void *ptr) { -#ifdef HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS struct module *mod; ptr = dereference_kernel_function_descriptor(ptr); diff --git a/include/linux/kasan-enabled.h b/include/linux/kasan-enabled.h new file mode 100644 index 000000000000..6f612d69ea0c --- /dev/null +++ b/include/linux/kasan-enabled.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KASAN_ENABLED_H +#define _LINUX_KASAN_ENABLED_H + +#include <linux/static_key.h> + +#ifdef CONFIG_KASAN_HW_TAGS + +DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); + +static __always_inline bool kasan_enabled(void) +{ + return static_branch_likely(&kasan_flag_enabled); +} + +static inline bool kasan_hw_tags_enabled(void) +{ + return kasan_enabled(); +} + +#else /* CONFIG_KASAN_HW_TAGS */ + +static inline bool kasan_enabled(void) +{ + return IS_ENABLED(CONFIG_KASAN); +} + +static inline bool kasan_hw_tags_enabled(void) +{ + return false; +} + +#endif /* CONFIG_KASAN_HW_TAGS */ + +#endif /* LINUX_KASAN_ENABLED_H */ diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d8783b682669..ceebcb9de7bf 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -3,12 +3,14 @@ #define _LINUX_KASAN_H #include <linux/bug.h> +#include <linux/kasan-enabled.h> #include <linux/kernel.h> #include <linux/static_key.h> #include <linux/types.h> struct kmem_cache; struct page; +struct slab; struct vm_struct; struct task_struct; @@ -17,13 +19,15 @@ struct task_struct; #include <linux/linkage.h> #include <asm/kasan.h> -/* kasan_data struct is used in KUnit tests for KASAN expected failures */ -struct kunit_kasan_expectation { - bool report_found; -}; - #endif +typedef unsigned int __bitwise kasan_vmalloc_flags_t; + +#define KASAN_VMALLOC_NONE 0x00u +#define KASAN_VMALLOC_INIT 0x01u +#define KASAN_VMALLOC_VM_ALLOC 0x02u +#define KASAN_VMALLOC_PROT_NORMAL 0x04u + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #include <linux/pgtable.h> @@ -82,47 +86,8 @@ static inline void kasan_disable_current(void) {} #ifdef CONFIG_KASAN_HW_TAGS -DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled); - -static __always_inline bool kasan_enabled(void) -{ - return static_branch_likely(&kasan_flag_enabled); -} - -static inline bool kasan_hw_tags_enabled(void) -{ - return kasan_enabled(); -} - -void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags); -void kasan_free_pages(struct page *page, unsigned int order); - #else /* CONFIG_KASAN_HW_TAGS */ -static inline bool kasan_enabled(void) -{ - return IS_ENABLED(CONFIG_KASAN); -} - -static inline bool kasan_hw_tags_enabled(void) -{ - return false; -} - -static __always_inline void kasan_alloc_pages(struct page *page, - unsigned int order, gfp_t flags) -{ - /* Only available for integrated init. */ - BUILD_BUG(); -} - -static __always_inline void kasan_free_pages(struct page *page, - unsigned int order) -{ - /* Only available for integrated init. */ - BUILD_BUG(); -} - #endif /* CONFIG_KASAN_HW_TAGS */ static inline bool kasan_has_integrated_init(void) @@ -193,11 +158,11 @@ static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) return 0; } -void __kasan_poison_slab(struct page *page); -static __always_inline void kasan_poison_slab(struct page *page) +void __kasan_poison_slab(struct slab *slab); +static __always_inline void kasan_poison_slab(struct slab *slab) { if (kasan_enabled()) - __kasan_poison_slab(page); + __kasan_poison_slab(slab); } void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object); @@ -302,10 +267,6 @@ static __always_inline bool kasan_check_byte(const void *addr) return true; } - -bool kasan_save_enable_multi_shot(void); -void kasan_restore_multi_shot(bool enabled); - #else /* CONFIG_KASAN */ static inline slab_flags_t kasan_never_merge(void) @@ -322,7 +283,7 @@ static inline void kasan_cache_create(struct kmem_cache *cache, slab_flags_t *flags) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } -static inline void kasan_poison_slab(struct page *page) {} +static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} static inline void kasan_poison_object_data(struct kmem_cache *cache, @@ -434,34 +395,71 @@ static inline void kasan_init_hw_tags(void) { } #ifdef CONFIG_KASAN_VMALLOC +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) + +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); int kasan_populate_vmalloc(unsigned long addr, unsigned long size); -void kasan_poison_vmalloc(const void *start, unsigned long size); -void kasan_unpoison_vmalloc(const void *start, unsigned long size); void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); -void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); +#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } +static inline int kasan_populate_vmalloc(unsigned long start, + unsigned long size) +{ + return 0; +} +static inline void kasan_release_vmalloc(unsigned long start, + unsigned long end, + unsigned long free_region_start, + unsigned long free_region_end) { } + +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ + +void *__kasan_unpoison_vmalloc(const void *start, unsigned long size, + kasan_vmalloc_flags_t flags); +static __always_inline void *kasan_unpoison_vmalloc(const void *start, + unsigned long size, + kasan_vmalloc_flags_t flags) +{ + if (kasan_enabled()) + return __kasan_unpoison_vmalloc(start, size, flags); + return (void *)start; +} + +void __kasan_poison_vmalloc(const void *start, unsigned long size); +static __always_inline void kasan_poison_vmalloc(const void *start, + unsigned long size) +{ + if (kasan_enabled()) + __kasan_poison_vmalloc(start, size); +} #else /* CONFIG_KASAN_VMALLOC */ +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) { } static inline int kasan_populate_vmalloc(unsigned long start, unsigned long size) { return 0; } - -static inline void kasan_poison_vmalloc(const void *start, unsigned long size) -{ } -static inline void kasan_unpoison_vmalloc(const void *start, unsigned long size) -{ } static inline void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, - unsigned long free_region_end) {} + unsigned long free_region_end) { } -static inline void kasan_populate_early_vm_area_shadow(void *start, - unsigned long size) +static inline void *kasan_unpoison_vmalloc(const void *start, + unsigned long size, + kasan_vmalloc_flags_t flags) +{ + return (void *)start; +} +static inline void kasan_poison_vmalloc(const void *start, unsigned long size) { } #endif /* CONFIG_KASAN_VMALLOC */ @@ -470,17 +468,17 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, !defined(CONFIG_KASAN_VMALLOC) /* - * These functions provide a special case to support backing module - * allocations with real shadow memory. With KASAN vmalloc, the special - * case is unnecessary, as the work is handled in the generic case. + * These functions allocate and free shadow memory for kernel modules. + * They are only required when KASAN_VMALLOC is not supported, as otherwise + * shadow memory is allocated by the generic vmalloc handlers. */ -int kasan_module_alloc(void *addr, size_t size); -void kasan_free_shadow(const struct vm_struct *vm); +int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask); +void kasan_free_module_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } -static inline void kasan_free_shadow(const struct vm_struct *vm) {} +static inline int kasan_alloc_module_shadow(void *addr, size_t size, gfp_t gfp_mask) { return 0; } +static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 5f5965246877..92f3843d9ebb 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -36,6 +36,36 @@ */ void __kcsan_check_access(const volatile void *ptr, size_t size, int type); +/* + * See definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c. + * Note: The mappings are arbitrary, and do not reflect any real mappings of C11 + * memory orders to the LKMM memory orders and vice-versa! + */ +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb __ATOMIC_SEQ_CST +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb __ATOMIC_ACQ_REL +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb __ATOMIC_ACQUIRE +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_release __ATOMIC_RELEASE + +/** + * __kcsan_mb - full memory barrier instrumentation + */ +void __kcsan_mb(void); + +/** + * __kcsan_wmb - write memory barrier instrumentation + */ +void __kcsan_wmb(void); + +/** + * __kcsan_rmb - read memory barrier instrumentation + */ +void __kcsan_rmb(void); + +/** + * __kcsan_release - release barrier instrumentation + */ +void __kcsan_release(void); + /** * kcsan_disable_current - disable KCSAN for the current context * @@ -99,7 +129,15 @@ void kcsan_set_access_mask(unsigned long mask); /* Scoped access information. */ struct kcsan_scoped_access { - struct list_head list; + union { + struct list_head list; /* scoped_accesses list */ + /* + * Not an entry in scoped_accesses list; stack depth from where + * the access was initialized. + */ + int stack_depth; + }; + /* Access information. */ const volatile void *ptr; size_t size; @@ -151,6 +189,10 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa); static inline void __kcsan_check_access(const volatile void *ptr, size_t size, int type) { } +static inline void __kcsan_mb(void) { } +static inline void __kcsan_wmb(void) { } +static inline void __kcsan_rmb(void) { } +static inline void __kcsan_release(void) { } static inline void kcsan_disable_current(void) { } static inline void kcsan_enable_current(void) { } static inline void kcsan_enable_current_nowarn(void) { } @@ -183,12 +225,47 @@ static inline void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) { } */ #define __kcsan_disable_current kcsan_disable_current #define __kcsan_enable_current kcsan_enable_current_nowarn -#else +#else /* __SANITIZE_THREAD__ */ static inline void kcsan_check_access(const volatile void *ptr, size_t size, int type) { } static inline void __kcsan_enable_current(void) { } static inline void __kcsan_disable_current(void) { } -#endif +#endif /* __SANITIZE_THREAD__ */ + +#if defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__SANITIZE_THREAD__) +/* + * Normal barrier instrumentation is not done via explicit calls, but by mapping + * to a repurposed __atomic_signal_fence(), which normally does not generate any + * real instructions, but is still intercepted by fsanitize=thread. This means, + * like any other compile-time instrumentation, barrier instrumentation can be + * disabled with the __no_kcsan function attribute. + * + * Also see definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c. + * + * These are all macros, like <asm/barrier.h>, since some architectures use them + * in non-static inline functions. + */ +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE(name) \ + do { \ + barrier(); \ + __atomic_signal_fence(__KCSAN_BARRIER_TO_SIGNAL_FENCE_##name); \ + barrier(); \ + } while (0) +#define kcsan_mb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(mb) +#define kcsan_wmb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(wmb) +#define kcsan_rmb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(rmb) +#define kcsan_release() __KCSAN_BARRIER_TO_SIGNAL_FENCE(release) +#elif defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__KCSAN_INSTRUMENT_BARRIERS__) +#define kcsan_mb __kcsan_mb +#define kcsan_wmb __kcsan_wmb +#define kcsan_rmb __kcsan_rmb +#define kcsan_release __kcsan_release +#else /* CONFIG_KCSAN_WEAK_MEMORY && ... */ +#define kcsan_mb() do { } while (0) +#define kcsan_wmb() do { } while (0) +#define kcsan_rmb() do { } while (0) +#define kcsan_release() do { } while (0) +#endif /* CONFIG_KCSAN_WEAK_MEMORY && ... */ /** * __kcsan_check_read - check regular read access for races diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index fc266ecb2a4d..c07c71f5ba4f 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -21,6 +21,7 @@ */ struct kcsan_ctx { int disable_count; /* disable counter */ + int disable_scoped; /* disable scoped access counter */ int atomic_next; /* number of following atomic ops */ /* @@ -48,8 +49,16 @@ struct kcsan_ctx { */ unsigned long access_mask; - /* List of scoped accesses. */ + /* List of scoped accesses; likely to be empty. */ struct list_head scoped_accesses; + +#ifdef CONFIG_KCSAN_WEAK_MEMORY + /* + * Scoped access for modeling access reordering to detect missing memory + * barriers; only keep 1 to keep fast-path complexity manageable. + */ + struct kcsan_scoped_access reorder_access; +#endif }; /** diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..08ba5995aa8b 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -1,4 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * NOTE: + * + * This header has combined a lot of unrelated to each other stuff. + * The process of splitting its content is in progress while keeping + * backward compatibility. That's why it's highly recommended NOT to + * include this header inside another header file, especially under + * generic or architectural include/ directory. + */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H @@ -55,6 +64,15 @@ ) /** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + +/** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing * @@ -90,7 +108,7 @@ struct user; extern int __cond_resched(void); # define might_resched() __cond_resched() -#elif defined(CONFIG_PREEMPT_DYNAMIC) +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) extern int __cond_resched(void); @@ -101,6 +119,11 @@ static __always_inline void might_resched(void) static_call_mod(might_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + +extern int dynamic_might_resched(void); +# define might_resched() dynamic_might_resched() + #else # define might_resched() do { } while (0) @@ -187,7 +210,6 @@ static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; -void complete_and_exit(struct completion *, long) __noreturn; extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 3ccce6f24548..e2ae15a6225e 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -6,7 +6,6 @@ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H -#include <linux/kernel.h> #include <linux/err.h> #include <linux/list.h> #include <linux/mutex.h> @@ -14,14 +13,18 @@ #include <linux/lockdep.h> #include <linux/rbtree.h> #include <linux/atomic.h> +#include <linux/bug.h> +#include <linux/types.h> #include <linux/uidgid.h> #include <linux/wait.h> +#include <linux/rwsem.h> struct file; struct dentry; struct iattr; struct seq_file; struct vm_area_struct; +struct vm_operations_struct; struct super_block; struct file_system_type; struct poll_table_struct; @@ -182,22 +185,7 @@ struct kernfs_syscall_ops { struct kernfs_root *root); }; -struct kernfs_root { - /* published fields */ - struct kernfs_node *kn; - unsigned int flags; /* KERNFS_ROOT_* flags */ - - /* private fields, do not use outside kernfs proper */ - struct idr ino_idr; - u32 last_id_lowbits; - u32 id_highbits; - struct kernfs_syscall_ops *syscall_ops; - - /* list of kernfs_super_info of this root, protected by kernfs_rwsem */ - struct list_head supers; - - wait_queue_head_t deactivate_waitq; -}; +struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root); struct kernfs_open_file { /* published fields */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 0c994ae37729..58d1b58a971e 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -20,6 +20,12 @@ #include <uapi/linux/kexec.h> +/* Location of a reserved region to hold the crash kernel. + */ +extern struct resource crashk_res; +extern struct resource crashk_low_res; +extern note_buf_t __percpu *crash_notes; + #ifdef CONFIG_KEXEC_CORE #include <linux/list.h> #include <linux/compat.h> @@ -350,12 +356,6 @@ extern int kexec_load_disabled; #define KEXEC_FILE_FLAGS (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \ KEXEC_FILE_NO_INITRAMFS) -/* Location of a reserved region to hold the crash kernel. - */ -extern struct resource crashk_res; -extern struct resource crashk_low_res; -extern note_buf_t __percpu *crash_notes; - /* flag to track if kexec reboot is in progress */ extern bool kexec_in_progress; diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 4b5e3679a72c..f49e64222628 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -17,6 +17,8 @@ #include <linux/atomic.h> #include <linux/static_key.h> +extern unsigned long kfence_sample_interval; + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an diff --git a/include/linux/kobject.h b/include/linux/kobject.h index efd56f990a46..c7b47399b36a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -19,10 +19,10 @@ #include <linux/list.h> #include <linux/sysfs.h> #include <linux/compiler.h> +#include <linux/container_of.h> #include <linux/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> -#include <linux/kernel.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> @@ -66,7 +66,7 @@ struct kobject { struct list_head entry; struct kobject *parent; struct kset *kset; - struct kobj_type *ktype; + const struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE @@ -90,13 +90,13 @@ static inline const char *kobject_name(const struct kobject *kobj) return kobj->name; } -extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); +extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, - struct kobj_type *ktype, struct kobject *parent, + const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); @@ -117,23 +117,6 @@ extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); -/** - * kobject_has_children - Returns whether a kobject has children. - * @kobj: the object to test - * - * This will return whether a kobject has other kobjects as children. - * - * It does NOT account for the presence of attribute files, only sub - * directories. It also assumes there is no concurrent addition or - * removal of such children, and thus relies on external locking. - */ -static inline bool kobject_has_children(struct kobject *kobj) -{ - WARN_ON_ONCE(kref_read(&kobj->kref) == 0); - - return kobj->sd && kobj->sd->dir.subdirs; -} - struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; @@ -153,10 +136,9 @@ struct kobj_uevent_env { }; struct kset_uevent_ops { - int (* const filter)(struct kset *kset, struct kobject *kobj); - const char *(* const name)(struct kset *kset, struct kobject *kobj); - int (* const uevent)(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env); + int (* const filter)(struct kobject *kobj); + const char *(* const name)(struct kobject *kobj); + int (* const uevent)(struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { @@ -217,7 +199,7 @@ static inline void kset_put(struct kset *k) kobject_put(&k->kobj); } -static inline struct kobj_type *get_ktype(struct kobject *kobj) +static inline const struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } diff --git a/include/linux/kobject_api.h b/include/linux/kobject_api.h new file mode 100644 index 000000000000..6e36a054c2d6 --- /dev/null +++ b/include/linux/kobject_api.h @@ -0,0 +1 @@ +#include <linux/kobject.h> diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8c8f7a4d93af..157168769fc2 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -28,6 +28,7 @@ #include <linux/ftrace.h> #include <linux/refcount.h> #include <linux/freelist.h> +#include <linux/rethook.h> #include <asm/kprobes.h> #ifdef CONFIG_KPROBES @@ -149,13 +150,20 @@ struct kretprobe { int maxactive; int nmissed; size_t data_size; +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + struct rethook *rh; +#else struct freelist_head freelist; struct kretprobe_holder *rph; +#endif }; #define KRETPROBE_MAX_DATA_SIZE 4096 struct kretprobe_instance { +#ifdef CONFIG_KRETPROBE_ON_RETHOOK + struct rethook_node node; +#else union { struct freelist_node freelist; struct rcu_head rcu; @@ -164,6 +172,7 @@ struct kretprobe_instance { struct kretprobe_holder *rph; kprobe_opcode_t *ret_addr; void *fp; +#endif char data[]; }; @@ -186,10 +195,24 @@ extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); #ifdef CONFIG_KRETPROBES -extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs); +/* Check whether @p is used for implementing a trampoline. */ extern int arch_trampoline_kprobe(struct kprobe *p); +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) +{ + RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), + "Kretprobe is accessed from instance under preemptive context"); + + return (struct kretprobe *)READ_ONCE(ri->node.rethook->data); +} +static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) +{ + return ri->node.ret_addr; +} +#else +extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs); void arch_kretprobe_fixup_return(struct pt_regs *regs, kprobe_opcode_t *correct_ret_addr); @@ -232,6 +255,12 @@ static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance return READ_ONCE(ri->rph->rp); } +static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) +{ + return (unsigned long)ri->ret_addr; +} +#endif /* CONFIG_KRETPROBE_ON_RETHOOK */ + #else /* !CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) @@ -265,7 +294,6 @@ extern int arch_init_kprobes(void); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); -extern bool arch_kprobe_on_func_entry(unsigned long offset); extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); @@ -348,12 +376,6 @@ extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); -#ifdef CONFIG_SYSCTL -extern int sysctl_kprobes_optimization; -extern int proc_kprobes_optimization_handler(struct ctl_table *table, - int write, void *buffer, - size_t *length, loff_t *ppos); -#endif /* CONFIG_SYSCTL */ extern void wait_for_kprobe_optimizer(void); #else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } @@ -390,6 +412,8 @@ static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) } kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); +kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset, bool *on_func_entry); + int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); @@ -400,7 +424,11 @@ void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +#define kprobe_flush_task(tk) do {} while (0) +#else void kprobe_flush_task(struct task_struct *tk); +#endif void kprobe_free_init_mem(void); @@ -433,6 +461,9 @@ static inline struct kprobe *kprobe_running(void) { return NULL; } +#define kprobe_busy_begin() do {} while (0) +#define kprobe_busy_end() do {} while (0) + static inline int register_kprobe(struct kprobe *p) { return -EOPNOTSUPP; @@ -511,6 +542,19 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) #endif /* !CONFIG_OPTPROBES */ #ifdef CONFIG_KRETPROBES +#ifdef CONFIG_KRETPROBE_ON_RETHOOK +static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) +{ + return is_rethook_trampoline(addr); +} + +static nokprobe_inline +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur) +{ + return rethook_find_ret_addr(tsk, (unsigned long)fp, cur); +} +#else static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) { return (void *)addr == kretprobe_trampoline_addr(); @@ -518,6 +562,7 @@ static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, struct llist_node **cur); +#endif #else static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) { diff --git a/include/linux/kref_api.h b/include/linux/kref_api.h new file mode 100644 index 000000000000..d67e554721d2 --- /dev/null +++ b/include/linux/kref_api.h @@ -0,0 +1 @@ +#include <linux/kref.h> diff --git a/include/linux/ksm.h b/include/linux/ksm.h index a38a5bca1ba5..0630e545f4cb 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -51,7 +51,7 @@ static inline void ksm_exit(struct mm_struct *mm) struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); -void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk_ksm(struct folio *folio, const struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -78,8 +78,8 @@ static inline struct page *ksm_might_need_to_copy(struct page *page, return page; } -static inline void rmap_walk_ksm(struct page *page, - struct rmap_walk_control *rwc) +static inline void rmap_walk_ksm(struct folio *folio, + const struct rmap_walk_control *rwc) { } diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 346b0f269161..de5d75bafd66 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,7 +33,8 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); -void set_kthread_struct(struct task_struct *p); +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk); +bool set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); bool kthread_is_per_cpu(struct task_struct *k); @@ -56,6 +57,31 @@ bool kthread_is_per_cpu(struct task_struct *k); __k; \ }) +/** + * kthread_run_on_cpu - create and wake a cpu bound thread. + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: Convenient wrapper for kthread_create_on_cpu() + * followed by wake_up_process(). Returns the kthread or + * ERR_PTR(-ENOMEM). + */ +static inline struct task_struct * +kthread_run_on_cpu(int (*threadfn)(void *data), void *data, + unsigned int cpu, const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_cpu(threadfn, data, cpu, namefmt); + if (!IS_ERR(p)) + wake_up_process(p); + + return p; +} + void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); @@ -70,6 +96,8 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); +void kthread_exit(long result) __noreturn; +void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; @@ -113,12 +141,6 @@ struct kthread_delayed_work { struct timer_list timer; }; -#define KTHREAD_WORKER_INIT(worker) { \ - .lock = __RAW_SPIN_LOCK_UNLOCKED((worker).lock), \ - .work_list = LIST_HEAD_INIT((worker).work_list), \ - .delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\ - } - #define KTHREAD_WORK_INIT(work, fn) { \ .node = LIST_HEAD_INIT((work).node), \ .func = (fn), \ @@ -130,9 +152,6 @@ struct kthread_delayed_work { TIMER_IRQSAFE), \ } -#define DEFINE_KTHREAD_WORKER(worker) \ - struct kthread_worker worker = KTHREAD_WORKER_INIT(worker) - #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) @@ -140,19 +159,6 @@ struct kthread_delayed_work { struct kthread_delayed_work dwork = \ KTHREAD_DELAYED_WORK_INIT(dwork, fn) -/* - * kthread_worker.lock needs its own lockdep class key when defined on - * stack with lockdep enabled. Use the following macros in such cases. - */ -#ifdef CONFIG_LOCKDEP -# define KTHREAD_WORKER_INIT_ONSTACK(worker) \ - ({ kthread_init_worker(&worker); worker; }) -# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ - struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) -#else -# define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) -#endif - extern void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key); diff --git a/include/linux/ktime_api.h b/include/linux/ktime_api.h new file mode 100644 index 000000000000..f697d493960f --- /dev/null +++ b/include/linux/ktime_api.h @@ -0,0 +1 @@ +#include <linux/ktime.h> diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 120e5e90fa1d..906f899813dc 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -27,9 +27,9 @@ struct kvm_dirty_ring { int index; }; -#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +#ifndef CONFIG_HAVE_KVM_DIRTY_RING /* - * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should * not be included as well, so define these nop functions for the arch. */ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) @@ -43,11 +43,6 @@ static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, return 0; } -static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) -{ - return NULL; -} - static inline int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) { @@ -74,11 +69,10 @@ static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) return true; } -#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#else /* CONFIG_HAVE_KVM_DIRTY_RING */ u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); -struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm); /* * called with kvm->slots_lock held, returns the number of @@ -98,6 +92,6 @@ struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); -#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#endif /* CONFIG_HAVE_KVM_DIRTY_RING */ #endif /* KVM_DIRTY_RING_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..9536ffa0473b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,12 @@ #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> +#include <linux/ftrace.h> +#include <linux/hashtable.h> +#include <linux/instrumentation.h> +#include <linux/interval_tree.h> +#include <linux/rbtree.h> +#include <linux/xarray.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -147,10 +153,10 @@ static inline bool is_error_page(struct page *page) * Bits 4-7 are reserved for more arch-independent bits. */ #define KVM_REQ_TLB_FLUSH (0 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_GPC_INVALIDATE (5 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -304,13 +310,12 @@ struct kvm_vcpu { u64 requests; unsigned long guest_debug; - int pre_pcpu; - struct list_head blocked_vcpu_list; - struct mutex mutex; struct kvm_run *run; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -355,15 +360,20 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; /* - * The index of the most recently used memslot by this vCPU. It's ok - * if this becomes stale due to memslot changes since we always check - * it is a valid slot. + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. */ - int last_used_slot; + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) +/* + * Start accounting time towards a guest. + * Must be called before entering guest context. + */ +static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the @@ -372,7 +382,18 @@ static __always_inline void guest_enter_irqoff(void) instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); +} +/* + * Enter guest context and enter an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_enter_irqoff(void) +{ /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode @@ -388,16 +409,79 @@ static __always_inline void guest_enter_irqoff(void) } } -static __always_inline void guest_exit_irqoff(void) +/* + * Deprecated. Architectures should move to guest_timing_enter_irqoff() and + * guest_state_enter_irqoff(). + */ +static __always_inline void guest_enter_irqoff(void) +{ + guest_timing_enter_irqoff(); + guest_context_enter_irqoff(); +} + +/** + * guest_state_enter_irqoff - Fixup state when entering a guest + * + * Entry to a guest will enable interrupts, but the kernel state is interrupts + * disabled when this is invoked. Also tell RCU about it. + * + * 1) Trace interrupts on state + * 2) Invoke context tracking if enabled to adjust RCU state + * 3) Tell lockdep that interrupts are enabled + * + * Invoked from architecture specific code before entering a guest. + * Must be called with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_enter_irqoff() before this. + * + * Note: this is analogous to exit_to_user_mode(). + */ +static __always_inline void guest_state_enter_irqoff(void) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + instrumentation_end(); + + guest_context_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +/* + * Exit guest context and exit an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_exit_irqoff(void) { context_tracking_guest_exit(); +} +/* + * Stop accounting time towards a guest. + * Must be called after exiting guest context. + */ +static __always_inline void guest_timing_exit_irqoff(void) +{ instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } +/* + * Deprecated. Architectures should move to guest_state_exit_irqoff() and + * guest_timing_exit_irqoff(). + */ +static __always_inline void guest_exit_irqoff(void) +{ + guest_context_exit_irqoff(); + guest_timing_exit_irqoff(); +} + static inline void guest_exit(void) { unsigned long flags; @@ -407,6 +491,33 @@ static inline void guest_exit(void) local_irq_restore(flags); } +/** + * guest_state_exit_irqoff - Establish state when returning from guest mode + * + * Entry from a guest disables interrupts, but guest mode is traced as + * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + * + * Invoked from architecture specific code after exiting a guest. + * Must be invoked with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_exit_irqoff() after this. + * + * Note: this is analogous to enter_from_user_mode(). + */ +static __always_inline void guest_state_exit_irqoff(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + guest_context_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* @@ -424,7 +535,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * Since at idle each memslot belongs to two memslot sets it has to contain + * two embedded nodes for each data structure that it forms a part of. + * + * Two memslot sets (one active and one inactive) are necessary so the VM + * continues to run on one memslot set while the other is being modified. + * + * These two memslot sets normally point to the same set of memslots. + * They can, however, be desynchronized when performing a memslot management + * operation by replacing the memslot to be modified by its copy. + * After the operation is complete, both memslot sets once again point to + * the same, common set of memslot data. + * + * The memslots themselves are independent of each other so they can be + * individually added or deleted. + */ struct kvm_memory_slot { + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -435,7 +565,7 @@ struct kvm_memory_slot { u16 as_id; }; -static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } @@ -469,6 +599,12 @@ struct kvm_hv_sint { u32 sint; }; +struct kvm_xen_evtchn { + u32 port; + u32 vcpu; + u32 priority; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -489,6 +625,7 @@ struct kvm_kernel_irq_routing_entry { } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; + struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; @@ -519,18 +656,21 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -/* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. - */ struct kvm_memslots { u64 generation; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; - atomic_t last_used_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + atomic_long_t last_used_slot; + struct rb_root_cached hva_tree; + struct rb_root gfn_tree; + /* + * The mapping table from slot id to memslot. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); + int node_idx; }; struct kvm { @@ -551,14 +691,22 @@ struct kvm { */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ + unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; unsigned long mn_active_invalidate_count; struct rcuwait mn_memslots_update_rcuwait; + /* For management / invalidation of gfn_to_pfn_caches */ + spinlock_t gpc_lock; + struct list_head gpc_list; + /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only @@ -701,19 +849,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; @@ -727,13 +873,12 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else +static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); @@ -793,21 +938,124 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; + int idx = slots->node_idx; - if (index < 0) - return NULL; + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { + if (slot->id == id) + return slot; + } + + return NULL; +} + +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; + +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; + + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); +} + +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } - slot = &slots->memslots[index]; + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } - WARN_ON(slot->id != id); - return slot; + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); + + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } +} + +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; } +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot @@ -833,11 +1081,10 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); @@ -863,9 +1110,9 @@ void kvm_set_page_accessed(struct page *page); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva); @@ -942,7 +1189,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); @@ -966,10 +1213,109 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); +/** + * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a + * given guest physical address. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @vcpu: vCPU to be used for marking pages dirty and to be woken on + * invalidation. + * @guest_uses_pa: indicates that the resulting host physical PFN is used while + * @vcpu is IN_GUEST_MODE so invalidations should wake it. + * @kernel_map: requests a kernel virtual mapping (kmap / memremap). + * @gpa: guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * @dirty: mark the cache dirty immediately. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This primes a gfn_to_pfn_cache and links it into the @kvm's list for + * invalidations to be processed. Invalidation callbacks to @vcpu using + * %KVM_REQ_GPC_INVALIDATE will occur only for MMU notifiers, not for KVM + * memslot changes. Callers are required to use kvm_gfn_to_pfn_cache_check() + * to ensure that the cache is valid before accessing the target page. + */ +int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, bool guest_uses_pa, + bool kernel_map, gpa_t gpa, unsigned long len, + bool dirty); + +/** + * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: current guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * @dirty: mark the cache dirty immediately. + * + * @return: %true if the cache is still valid and the address matches. + * %false if the cache is not valid. + * + * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock + * while calling this function, and then continue to hold the lock until the + * access is complete. + * + * Callers in IN_GUEST_MODE may do so without locking, although they should + * still hold a read lock on kvm->scru for the memslot checks. + */ +bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_refresh - update a previously initialized cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: updated guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * @dirty: mark the cache dirty immediately. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful + * returm from this function does not mean the page can be immediately + * accessed because it may have raced with an invalidation. Callers must + * still lock and check the cache status, as this function does not return + * with the lock still held to permit access. + */ +int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len, bool dirty); + +/** + * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This unmaps the referenced page and marks it dirty, if appropriate. The + * cache is left in the invalid state but at least the mapping from GPA to + * userspace HVA will remain cached and can be reused on a subsequent + * refresh. + */ +void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This removes a cache from the @kvm's list to be processed on MMU notifier + * invocation. + */ +void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); -void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_halt(struct kvm_vcpu *vcpu); +bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); @@ -978,7 +1324,6 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_flush_remote_tlbs(struct kvm *kvm); -void kvm_reload_remote_mmus(struct kvm *kvm); #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min); @@ -1152,6 +1497,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #endif } +/* + * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns + * true if the vCPU was blocking and was awakened, false otherwise. + */ +static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and @@ -1166,6 +1525,16 @@ static inline bool kvm_arch_intc_initialized(struct kvm *kvm) } #endif +#ifdef CONFIG_GUEST_PERF_EVENTS +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); +void kvm_unregister_perf_callbacks(void); +#else +static inline void kvm_register_perf_callbacks(void *ign) {} +static inline void kvm_unregister_perf_callbacks(void) {} +#endif /* CONFIG_GUEST_PERF_EVENTS */ + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); @@ -1174,7 +1543,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -1205,25 +1573,15 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * Returns a pointer to the memslot at slot_index if it contains gfn. + * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - struct kvm_memory_slot *slot; - - if (slot_index < 0 || slot_index >= slots->used_slots) + if (!slot) return NULL; - /* - * slot_index can come from vcpu->last_used_slot which is not kept - * in sync with userspace-controllable memslot deletion. So use nospec - * to prevent the CPU from speculating past the end of memslots[]. - */ - slot_index = array_index_nospec(slot_index, slots->used_slots); - slot = &slots->memslots[slot_index]; - if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else @@ -1231,63 +1589,63 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) } /* - * Returns a pointer to the memslot that contains gfn and records the index of - * the slot in index. Otherwise returns NULL. + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! + * With "approx" set returns the memslot also when the address falls + * in a hole. In that case one of the memslots bordering the hole is + * returned. */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { - int start = 0, end = slots->used_slots; - struct kvm_memory_slot *memslots = slots->memslots; struct kvm_memory_slot *slot; - - if (unlikely(!slots->used_slots)) - return NULL; - - while (start < end) { - int slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - slot = try_get_memslot(slots, start, gfn); - if (slot) { - *index = start; - return slot; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; } - return NULL; + return approx ? slot : NULL; } -/* - * __gfn_to_memslot() and its descendants are here because it is called from - * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. gfn_to_memslot() - * itself isn't here as an inline because that would bloat other code too much. - */ static inline struct kvm_memory_slot * -__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; - int slot_index = atomic_read(&slots->last_used_slot); - slot = try_get_memslot(slots, slot_index, gfn); + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); if (slot) return slot; - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, approx); if (slot) { - atomic_set(&slots->last_used_slot, slot_index); + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } return NULL; } +/* + * __gfn_to_memslot() and its descendants are here to allow arch code to inline + * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline + * because that would bloat other code too much. + */ +static inline struct kvm_memory_slot * +__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, false); +} + static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { @@ -1463,7 +1821,8 @@ struct _kvm_stats_desc { STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ - HALT_POLL_HIST_COUNT) + HALT_POLL_HIST_COUNT), \ + STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 234eab059839..dceac12c1ce5 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -19,6 +19,7 @@ struct kvm_memslots; enum kvm_mr_change; #include <linux/types.h> +#include <linux/spinlock_types.h> #include <asm/kvm_types.h> @@ -53,6 +54,23 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; +struct gfn_to_pfn_cache { + u64 generation; + gpa_t gpa; + unsigned long uhva; + struct kvm_memory_slot *memslot; + struct kvm_vcpu *vcpu; + struct list_head list; + rwlock_t lock; + void *khva; + kvm_pfn_t pfn; + bool active; + bool valid; + bool dirty; + bool kernel_map; + bool guest_uses_pa; +}; + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, @@ -87,6 +105,7 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT]; u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT]; u64 halt_wait_hist[HALT_POLL_HIST_COUNT]; + u64 blocking; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/include/linux/libata.h b/include/linux/libata.h index 2a8404b26083..9b1d3d8b1252 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -39,25 +39,9 @@ * compile-time options: to be removed as soon as all the drivers are * converted to the new debugging mechanism */ -#undef ATA_DEBUG /* debugging output */ -#undef ATA_VERBOSE_DEBUG /* yet more debugging output */ #undef ATA_IRQ_TRAP /* define to ack screaming irqs */ -#undef ATA_NDEBUG /* define to disable quick runtime checks */ -/* note: prints function name for you */ -#ifdef ATA_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#ifdef ATA_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define VPRINTK(fmt, args...) -#endif /* ATA_VERBOSE_DEBUG */ -#else -#define DPRINTK(fmt, args...) -#define VPRINTK(fmt, args...) -#endif /* ATA_DEBUG */ - #define ata_print_version_once(dev, version) \ ({ \ static bool __print_once; \ @@ -68,38 +52,6 @@ } \ }) -/* NEW: debug levels */ -#define HAVE_LIBATA_MSG 1 - -enum { - ATA_MSG_DRV = 0x0001, - ATA_MSG_INFO = 0x0002, - ATA_MSG_PROBE = 0x0004, - ATA_MSG_WARN = 0x0008, - ATA_MSG_MALLOC = 0x0010, - ATA_MSG_CTL = 0x0020, - ATA_MSG_INTR = 0x0040, - ATA_MSG_ERR = 0x0080, -}; - -#define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) -#define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) -#define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) -#define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) -#define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) -#define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL) -#define ata_msg_intr(p) ((p)->msg_enable & ATA_MSG_INTR) -#define ata_msg_err(p) ((p)->msg_enable & ATA_MSG_ERR) - -static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) -{ - if (dval < 0 || dval >= (sizeof(u32) * 8)) - return default_msg_enable_bits; /* should be 0x1 - only driver info msgs */ - if (!dval) - return 0; - return (1 << dval) - 1; -} - /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU @@ -191,7 +143,7 @@ enum { ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ - ATA_LFLAG_NO_DB_DELAY = (1 << 11), /* no debounce delay on link resume */ + ATA_LFLAG_NO_DEBOUNCE_DELAY = (1 << 11), /* no debounce delay on link resume */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ @@ -428,6 +380,7 @@ enum { ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ + ATA_HORKAGE_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ @@ -566,7 +519,10 @@ struct ata_taskfile { u8 hob_lbam; u8 hob_lbah; - u8 feature; + union { + u8 error; + u8 feature; + }; u8 nsect; u8 lbal; u8 lbam; @@ -574,7 +530,10 @@ struct ata_taskfile { u8 device; - u8 command; /* IO operation */ + union { + u8 status; + u8 command; + }; u32 auxiliary; /* auxiliary field */ /* from SATA 3.1 and */ @@ -884,7 +843,6 @@ struct ata_port { unsigned int hsm_task_state; - u32 msg_enable; struct list_head eh_done_q; wait_queue_head_t eh_wait_q; int eh_tries; @@ -933,7 +891,8 @@ struct ata_port_operations { void (*set_piomode)(struct ata_port *ap, struct ata_device *dev); void (*set_dmamode)(struct ata_port *ap, struct ata_device *dev); int (*set_mode)(struct ata_link *link, struct ata_device **r_failed_dev); - unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); + unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, + __le16 *id); void (*dev_config)(struct ata_device *dev); @@ -1128,7 +1087,7 @@ extern int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *dev, extern bool ata_link_online(struct ata_link *link); extern bool ata_link_offline(struct ata_link *link); #ifdef CONFIG_PM -extern int ata_host_suspend(struct ata_host *host, pm_message_t mesg); +extern void ata_host_suspend(struct ata_host *host, pm_message_t mesg); extern void ata_host_resume(struct ata_host *host); extern void ata_sas_port_suspend(struct ata_port *ap); extern void ata_sas_port_resume(struct ata_port *ap); @@ -1160,13 +1119,15 @@ extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); +extern unsigned int ata_port_classify(struct ata_port *ap, + const struct ata_taskfile *tf); extern void ata_dev_disable(struct ata_device *adev); extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern unsigned int ata_do_dev_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id); + struct ata_taskfile *tf, __le16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); @@ -1432,6 +1393,12 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .slave_configure = ata_scsi_slave_config +#define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ + __ATA_BASE_SHT(drv_name), \ + .can_queue = drv_qd, \ + .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ + .slave_configure = ata_scsi_slave_config + #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_common_sdev_groups @@ -1443,6 +1410,11 @@ extern const struct attribute_group *ata_ncq_sdev_groups[]; ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_ncq_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth + +#define ATA_NCQ_SHT_QD(drv_name, drv_qd) \ + ATA_SUBBASE_SHT_QD(drv_name, drv_qd), \ + .sdev_groups = ata_ncq_sdev_groups, \ + .change_queue_depth = ata_scsi_change_queue_depth #endif /* @@ -1487,51 +1459,61 @@ static inline int sata_srst_pmp(struct ata_link *link) return link->pmp; } -/* - * printk helpers - */ -__printf(3, 4) -void ata_port_printk(const struct ata_port *ap, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_link_printk(const struct ata_link *link, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_dev_printk(const struct ata_device *dev, const char *level, - const char *fmt, ...); +#define ata_port_printk(level, ap, fmt, ...) \ + pr_ ## level ("ata%u: " fmt, (ap)->print_id, ##__VA_ARGS__) #define ata_port_err(ap, fmt, ...) \ - ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__) + ata_port_printk(err, ap, fmt, ##__VA_ARGS__) #define ata_port_warn(ap, fmt, ...) \ - ata_port_printk(ap, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_port_printk(warn, ap, fmt, ##__VA_ARGS__) #define ata_port_notice(ap, fmt, ...) \ - ata_port_printk(ap, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_port_printk(notice, ap, fmt, ##__VA_ARGS__) #define ata_port_info(ap, fmt, ...) \ - ata_port_printk(ap, KERN_INFO, fmt, ##__VA_ARGS__) + ata_port_printk(info, ap, fmt, ##__VA_ARGS__) #define ata_port_dbg(ap, fmt, ...) \ - ata_port_printk(ap, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_port_printk(debug, ap, fmt, ##__VA_ARGS__) + +#define ata_link_printk(level, link, fmt, ...) \ +do { \ + if (sata_pmp_attached((link)->ap) || \ + (link)->ap->slave_link) \ + pr_ ## level ("ata%u.%02u: " fmt, \ + (link)->ap->print_id, \ + (link)->pmp, \ + ##__VA_ARGS__); \ + else \ + pr_ ## level ("ata%u: " fmt, \ + (link)->ap->print_id, \ + ##__VA_ARGS__); \ +} while (0) #define ata_link_err(link, fmt, ...) \ - ata_link_printk(link, KERN_ERR, fmt, ##__VA_ARGS__) + ata_link_printk(err, link, fmt, ##__VA_ARGS__) #define ata_link_warn(link, fmt, ...) \ - ata_link_printk(link, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_link_printk(warn, link, fmt, ##__VA_ARGS__) #define ata_link_notice(link, fmt, ...) \ - ata_link_printk(link, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_link_printk(notice, link, fmt, ##__VA_ARGS__) #define ata_link_info(link, fmt, ...) \ - ata_link_printk(link, KERN_INFO, fmt, ##__VA_ARGS__) + ata_link_printk(info, link, fmt, ##__VA_ARGS__) #define ata_link_dbg(link, fmt, ...) \ - ata_link_printk(link, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_link_printk(debug, link, fmt, ##__VA_ARGS__) + +#define ata_dev_printk(level, dev, fmt, ...) \ + pr_ ## level("ata%u.%02u: " fmt, \ + (dev)->link->ap->print_id, \ + (dev)->link->pmp + (dev)->devno, \ + ##__VA_ARGS__) #define ata_dev_err(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_ERR, fmt, ##__VA_ARGS__) + ata_dev_printk(err, dev, fmt, ##__VA_ARGS__) #define ata_dev_warn(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_dev_printk(warn, dev, fmt, ##__VA_ARGS__) #define ata_dev_notice(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_dev_printk(notice, dev, fmt, ##__VA_ARGS__) #define ata_dev_info(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) + ata_dev_printk(info, dev, fmt, ##__VA_ARGS__) #define ata_dev_dbg(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__) void ata_print_version(const struct device *dev, const char *version); @@ -2065,11 +2047,8 @@ static inline u8 ata_wait_idle(struct ata_port *ap) { u8 status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); -#ifdef ATA_DEBUG if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ))) - ata_port_printk(ap, KERN_DEBUG, "abnormal Status 0x%X\n", - status); -#endif + ata_port_dbg(ap, "abnormal Status 0x%X\n", status); return status; } diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7074aa9af525..0d61e07b6827 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -25,8 +25,6 @@ struct badrange { }; enum { - /* when a dimm supports both PMEM and BLK access a label is required */ - NDD_ALIASING = 0, /* unarmed memory devices may not persist writes */ NDD_UNARMED = 1, /* locked memory devices should not be accessed */ @@ -35,8 +33,6 @@ enum { NDD_SECURITY_OVERWRITE = 3, /* tracking whether or not there is a pending device reference */ NDD_WORK_PENDING = 4, - /* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */ - NDD_NOBLK = 5, /* dimm supports namespace labels */ NDD_LABELING = 6, @@ -140,21 +136,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, } struct nvdimm_bus; -struct module; -struct nd_blk_region; -struct nd_blk_region_desc { - int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); - int (*do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, - void *iobuf, u64 len, int rw); - struct nd_region_desc ndr_desc; -}; - -static inline struct nd_blk_region_desc *to_blk_region_desc( - struct nd_region_desc *ndr_desc) -{ - return container_of(ndr_desc, struct nd_blk_region_desc, ndr_desc); - -} /* * Note that separate bits for locked + unlocked are defined so that @@ -257,7 +238,6 @@ struct nvdimm_bus *nvdimm_to_bus(struct nvdimm *nvdimm); struct nvdimm *to_nvdimm(struct device *dev); struct nd_region *to_nd_region(struct device *dev); struct device *nd_region_dev(struct nd_region *nd_region); -struct nd_blk_region *to_nd_blk_region(struct device *dev); struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus); const char *nvdimm_name(struct nvdimm *nvdimm); @@ -295,10 +275,6 @@ struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc); void *nd_region_provider_data(struct nd_region *nd_region); -void *nd_blk_region_provider_data(struct nd_blk_region *ndbr); -void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data); -struct nvdimm *nd_blk_region_to_dimm(struct nd_blk_region *ndbr); -unsigned long nd_blk_memremap_flags(struct nd_blk_region *ndbr); unsigned int nd_region_acquire_lane(struct nd_region *nd_region); void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane); u64 nd_fletcher64(void *addr, size_t len, bool le); diff --git a/include/linux/linkage.h b/include/linux/linkage.h index dbf8506decca..acb1ad2356f1 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -165,7 +165,18 @@ #ifndef SYM_END #define SYM_END(name, sym_type) \ .type name sym_type ASM_NL \ - .size name, .-name + .set .L__sym_size_##name, .-name ASM_NL \ + .size name, .L__sym_size_##name +#endif + +/* SYM_ALIAS -- use only if you have to */ +#ifndef SYM_ALIAS +#define SYM_ALIAS(alias, name, sym_type, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL \ + .type alias sym_type ASM_NL \ + .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ + .size alias, .L__sym_size_##alias #endif /* === code annotations === */ @@ -200,30 +211,8 @@ SYM_ENTRY(name, linkage, SYM_A_NONE) #endif -/* - * SYM_FUNC_START_LOCAL_ALIAS -- use where there are two local names for one - * function - */ -#ifndef SYM_FUNC_START_LOCAL_ALIAS -#define SYM_FUNC_START_LOCAL_ALIAS(name) \ - SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) -#endif - -/* - * SYM_FUNC_START_ALIAS -- use where there are two global names for one - * function - */ -#ifndef SYM_FUNC_START_ALIAS -#define SYM_FUNC_START_ALIAS(name) \ - SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) -#endif - /* SYM_FUNC_START -- use for global functions */ #ifndef SYM_FUNC_START -/* - * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two - * later. - */ #define SYM_FUNC_START(name) \ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) #endif @@ -236,7 +225,6 @@ /* SYM_FUNC_START_LOCAL -- use for local functions */ #ifndef SYM_FUNC_START_LOCAL -/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_START_LOCAL(name) \ SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) #endif @@ -259,22 +247,39 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) #endif -/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */ -#ifndef SYM_FUNC_END_ALIAS -#define SYM_FUNC_END_ALIAS(name) \ - SYM_END(name, SYM_T_FUNC) -#endif - /* * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START, * SYM_FUNC_START_WEAK, ... */ #ifndef SYM_FUNC_END -/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */ #define SYM_FUNC_END(name) \ SYM_END(name, SYM_T_FUNC) #endif +/* + * SYM_FUNC_ALIAS -- define a global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS +#define SYM_FUNC_ALIAS(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) +#endif + +/* + * SYM_FUNC_ALIAS_LOCAL -- define a local alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_LOCAL +#define SYM_FUNC_ALIAS_LOCAL(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) +#endif + +/* + * SYM_FUNC_ALIAS_WEAK -- define a weak global alias for an existing function + */ +#ifndef SYM_FUNC_ALIAS_WEAK +#define SYM_FUNC_ALIAS_WEAK(alias, name) \ + SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) +#endif + /* SYM_CODE_START -- use for non-C (special) functions */ #ifndef SYM_CODE_START #define SYM_CODE_START(name) \ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index f8397f300fcd..15e0e0209da4 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -66,11 +66,6 @@ static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, linkmode_clear_bit(nr, addr); } -static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) -{ - __change_bit(nr, addr); -} - static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); diff --git a/include/linux/list.h b/include/linux/list.h index 6636fc07f918..dd6c2041d09c 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -258,8 +258,7 @@ static inline void list_bulk_move_tail(struct list_head *head, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_first(const struct list_head *list, - const struct list_head *head) +static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } @@ -269,13 +268,22 @@ static inline int list_is_first(const struct list_head *list, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_last(const struct list_head *list, - const struct list_head *head) +static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** + * list_is_head - tests whether @list is the list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_head(const struct list_head *list, const struct list_head *head) +{ + return list == head; +} + +/** * list_empty - tests whether a list is empty * @head: the list to test. */ @@ -318,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return (next == head) && (next == head->prev); + return list_is_head(next, head) && (next == head->prev); } /** @@ -393,10 +401,9 @@ static inline void list_cut_position(struct list_head *list, { if (list_empty(head)) return; - if (list_is_singular(head) && - (head->next != entry && head != entry)) + if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; - if (entry == head) + if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); @@ -570,7 +577,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each(pos, head) \ - for (pos = (head)->next; pos != (head); pos = pos->next) + for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_continue - continue iteration over a list @@ -580,7 +587,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ - for (pos = pos->next; pos != (head); pos = pos->next) + for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards @@ -588,7 +595,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ - for (pos = (head)->prev; pos != (head); pos = pos->prev) + for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry @@ -597,8 +604,9 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = n, n = pos->next) + for (pos = (head)->next, n = pos->next; \ + !list_is_head(pos, (head)); \ + pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry @@ -608,7 +616,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ - pos != (head); \ + !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 1b5fceb565df..b35968ee9fb5 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/nodemask.h> #include <linux/shrinker.h> +#include <linux/xarray.h> struct mem_cgroup; @@ -33,8 +34,8 @@ struct list_lru_one { struct list_lru_memcg { struct rcu_head rcu; - /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_one *lru[]; + /* array of per cgroup per node lists, indexed by node id */ + struct list_lru_one node[]; }; struct list_lru_node { @@ -42,11 +43,7 @@ struct list_lru_node { spinlock_t lock; /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; -#ifdef CONFIG_MEMCG_KMEM - /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ - struct list_lru_memcg __rcu *memcg_lrus; -#endif - long nr_items; + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { @@ -55,6 +52,7 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; + struct xarray xa; #endif }; @@ -69,8 +67,9 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, NULL, shrinker) -int memcg_update_all_list_lrus(int num_memcgs); -void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); +int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, + gfp_t gfp); +void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** * list_lru_add: add an element to the lru list's tail diff --git a/include/linux/llist_api.h b/include/linux/llist_api.h new file mode 100644 index 000000000000..625bec0393a1 --- /dev/null +++ b/include/linux/llist_api.h @@ -0,0 +1 @@ +#include <linux/llist.h> diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 975e33b793a7..6d635e8306d6 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -static inline void local_lock_acquire(local_lock_t *l) { } -static inline void local_lock_release(local_lock_t *l) { } -static inline void local_lock_debug_init(local_lock_t *l) { } +# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c4ae6506b8b3..fcef192e5e45 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -303,10 +303,15 @@ void nlmsvc_invalidate_all(void); int nlmsvc_unlock_all_by_sb(struct super_block *sb); int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); +static inline struct file *nlmsvc_file_file(struct nlm_file *file) +{ + return file->f_file[O_RDONLY] ? + file->f_file[O_RDONLY] : file->f_file[O_WRONLY]; +} + static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(file->f_file[O_RDONLY] ? - file->f_file[O_RDONLY] : file->f_file[O_WRONLY]); + return locks_inode(nlmsvc_file_file(file)); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) diff --git a/include/linux/lockdep_api.h b/include/linux/lockdep_api.h new file mode 100644 index 000000000000..907e66979ab2 --- /dev/null +++ b/include/linux/lockdep_api.h @@ -0,0 +1 @@ +#include <linux/lockdep.h> diff --git a/include/linux/log2.h b/include/linux/log2.h index df0b155c2141..9f30d087a128 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -18,7 +18,7 @@ * - the arch is not required to handle n==0 if implementing the fallback */ #ifndef CONFIG_ARCH_HAS_ILOG2_U32 -static inline __attribute__((const)) +static __always_inline __attribute__((const)) int __ilog2_u32(u32 n) { return fls(n) - 1; @@ -26,7 +26,7 @@ int __ilog2_u32(u32 n) #endif #ifndef CONFIG_ARCH_HAS_ILOG2_U64 -static inline __attribute__((const)) +static __always_inline __attribute__((const)) int __ilog2_u64(u64 n) { return fls64(n) - 1; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index df8de62f4710..db924fe379c9 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -78,11 +78,9 @@ LSM_HOOK(int, 0, sb_set_mnt_opts, struct super_block *sb, void *mnt_opts, LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) -LSM_HOOK(int, 0, sb_add_mnt_opt, const char *option, const char *val, - int len, void **mnt_opts) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) -LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, +LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, @@ -206,8 +204,7 @@ LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) -LSM_HOOK(void, LSM_RET_VOID, task_getsecid_subj, - struct task_struct *p, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj, struct task_struct *p, u32 *secid) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) @@ -335,6 +332,8 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) +LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc, + struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d45b6f6e27fd..419b5febc3ca 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -180,8 +180,6 @@ * Copy all security options from a given superblock to another * @oldsb old superblock which contain information to clone * @newsb new superblock which needs filled in - * @sb_add_mnt_opt: - * Add one mount @option to @mnt_opts. * @sb_parse_opts_str: * Parse a string of security data filling in the opts structure * @options string containing all mount options known by the LSM @@ -719,11 +717,9 @@ * @p. * @p contains the task_struct for the process. * Return 0 if permission is granted. - * @task_getsecid_subj: - * Retrieve the subjective security identifier of the task_struct in @p - * and return it in @secid. Special care must be taken to ensure that @p - * is the either the "current" task, or the caller has exclusive access - * to @p. + * @current_getsecid_subj: + * Retrieve the subjective security identifier of the current task and + * return it in @secid. * In case of failure, @secid will be set to zero. * @task_getsecid_obj: * Retrieve the objective security identifier of the task_struct in @p @@ -1050,6 +1046,11 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. + * @sctp_assoc_established: + * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet + * to the security module. + * @asoc pointer to sctp association structure. + * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h new file mode 100644 index 000000000000..62674c83bde4 --- /dev/null +++ b/include/linux/map_benchmark.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 HiSilicon Limited. + */ + +#ifndef _KERNEL_DMA_BENCHMARK_H +#define _KERNEL_DMA_BENCHMARK_H + +#define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) +#define DMA_MAP_MAX_THREADS 1024 +#define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) + +#define DMA_MAP_BIDIRECTIONAL 0 +#define DMA_MAP_TO_DEVICE 1 +#define DMA_MAP_FROM_DEVICE 2 + +struct map_benchmark { + __u64 avg_map_100ns; /* average map latency in 100ns */ + __u64 map_stddev; /* standard deviation of map latency */ + __u64 avg_unmap_100ns; /* as above */ + __u64 unmap_stddev; + __u32 threads; /* how many threads will do map/unmap in parallel */ + __u32 seconds; /* how long the test will last */ + __s32 node; /* which numa node this benchmark will run on */ + __u32 dma_bits; /* DMA addressing capability */ + __u32 dma_dir; /* DMA data direction */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ +}; +#endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/include/linux/math.h b/include/linux/math.h index 53674a327e39..439b8f0b9ebd 100644 --- a/include/linux/math.h +++ b/include/linux/math.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MATH_H #define _LINUX_MATH_H +#include <linux/types.h> #include <asm/div64.h> #include <uapi/linux/kernel.h> @@ -106,6 +107,17 @@ } \ ) +#define __STRUCT_FRACT(type) \ +struct type##_fract { \ + __##type numerator; \ + __##type denominator; \ +}; +__STRUCT_FRACT(s16) +__STRUCT_FRACT(u16) +__STRUCT_FRACT(s32) +__STRUCT_FRACT(u32) +#undef __STRUCT_FRACT + /* * Multiplies an integer by a fraction, while avoiding unnecessary * overflow or loss of precision. diff --git a/include/linux/math64.h b/include/linux/math64.h index 2928f03d6d46..a14f40de1dca 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -301,6 +301,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); ({ u64 _tmp = (divisor); div64_u64((dividend) + _tmp / 2, _tmp); }) /* + * DIV_U64_ROUND_CLOSEST - unsigned 64bit divide with 32bit divisor rounded to nearest integer + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 32bit divisor + * + * Divide unsigned 64bit dividend by unsigned 32bit divisor + * and round to closest integer. + * + * Return: dividend / divisor rounded to nearest integer + */ +#define DIV_U64_ROUND_CLOSEST(dividend, divisor) \ + ({ u32 _tmp = (divisor); div_u64((u64)(dividend) + _tmp / 2, _tmp); }) + +/* * DIV_S64_ROUND_CLOSEST - signed 64bit divide with 32bit divisor rounded to nearest integer * @dividend: signed 64bit dividend * @divisor: signed 32bit divisor diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 0661af17a758..808bb4cee230 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -123,7 +123,11 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ -unsigned int mc146818_get_time(struct rtc_time *time); +bool mc146818_does_rtc_work(void); +int mc146818_get_time(struct rtc_time *time); int mc146818_set_time(struct rtc_time *time); +bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + void *param); + #endif /* _MC146818RTC_H */ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 9f3587a61e14..ecac96d52e01 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -7,6 +7,7 @@ #define __LINUX_MDIO_H__ #include <uapi/linux/mdio.h> +#include <linux/bitfield.h> #include <linux/mod_devicetable.h> /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit @@ -14,6 +15,7 @@ */ #define MII_ADDR_C45 (1<<30) #define MII_DEVADDR_C45_SHIFT 16 +#define MII_DEVADDR_C45_MASK GENMASK(20, 16) #define MII_REGADDR_C45_MASK GENMASK(15, 0) struct gpio_desc; @@ -381,6 +383,16 @@ static inline u32 mdiobus_c45_addr(int devad, u16 regnum) return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; } +static inline u16 mdiobus_c45_regad(u32 regnum) +{ + return FIELD_GET(MII_REGADDR_C45_MASK, regnum); +} + +static inline u16 mdiobus_c45_devad(u32 regnum) +{ + return FIELD_GET(MII_DEVADDR_C45_MASK, regnum); +} + static inline int __mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, u16 regnum) { diff --git a/include/linux/mdio/mdio-mscc-miim.h b/include/linux/mdio/mdio-mscc-miim.h new file mode 100644 index 000000000000..5b4ed2c3cbb9 --- /dev/null +++ b/include/linux/mdio/mdio-mscc-miim.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Driver for the MDIO interface of Microsemi network switches. + * + * Author: Colin Foster <colin.foster@in-advantage.com> + * Copyright (C) 2021 Innovative Advantage + */ +#ifndef MDIO_MSCC_MIIM_H +#define MDIO_MSCC_MIIM_H + +#include <linux/device.h> +#include <linux/phy.h> +#include <linux/regmap.h> + +int mscc_miim_setup(struct device *device, struct mii_bus **bus, + const char *name, struct regmap *mii_regmap, + int status_offset); + +#endif diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index c6786c12b207..df1fab44ea5c 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -117,4 +117,7 @@ int mei_cldev_enable(struct mei_cl_device *cldev); int mei_cldev_disable(struct mei_cl_device *cldev); bool mei_cldev_enabled(const struct mei_cl_device *cldev); +void *mei_cldev_dma_map(struct mei_cl_device *cldev, u8 buffer_id, size_t size); +int mei_cldev_dma_unmap(struct mei_cl_device *cldev); + #endif /* _LINUX_MEI_CL_BUS_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8adcf1fa8096..50ad19662a32 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _LINUX_MEMBLOCK_H #define _LINUX_MEMBLOCK_H -#ifdef __KERNEL__ /* * Logical memory blocks. @@ -405,8 +404,8 @@ phys_addr_t memblock_alloc_range_nid(phys_addr_t size, phys_addr_t end, int nid, bool exact_nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -static inline phys_addr_t memblock_phys_alloc(phys_addr_t size, - phys_addr_t align) +static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size, + phys_addr_t align) { return memblock_phys_alloc_range(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE); @@ -605,6 +604,5 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif -#endif /* __KERNEL__ */ #endif /* _LINUX_MEMBLOCK_H */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c5c403f4be6..a68dce3873fc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -33,6 +33,8 @@ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, + MEMCG_VMALLOC, + MEMCG_KMEM, MEMCG_NR_STAT, }; @@ -42,6 +44,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, @@ -217,7 +220,7 @@ struct obj_cgroup { struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { - struct list_head list; + struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; @@ -313,7 +316,8 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; struct obj_cgroup __rcu *objcg; - struct list_head objcg_list; /* list of inherited objcgs */ + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif MEMCG_PADDING(_pad2_); @@ -520,6 +524,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(objcg); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + return memcg; +} + #ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. @@ -536,45 +554,6 @@ static inline bool folio_memcg_kmem(struct folio *folio) return folio->memcg_data & MEMCG_DATA_KMEM; } -/* - * page_objcgs - get the object cgroups vector associated with a page - * @page: a pointer to the page struct - * - * Returns a pointer to the object cgroups vector associated with the page, - * or NULL. This function assumes that the page is known to have an - * associated object cgroups vector. It's not safe to call this function - * against pages, which might have an associated memory cgroup: e.g. - * kernel stack pages. - */ -static inline struct obj_cgroup **page_objcgs(struct page *page) -{ - unsigned long memcg_data = READ_ONCE(page->memcg_data); - - VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); - - return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); -} - -/* - * page_objcgs_check - get the object cgroups vector associated with a page - * @page: a pointer to the page struct - * - * Returns a pointer to the object cgroups vector associated with the page, - * or NULL. This function is safe to use if the page can be directly associated - * with a memory cgroup. - */ -static inline struct obj_cgroup **page_objcgs_check(struct page *page) -{ - unsigned long memcg_data = READ_ONCE(page->memcg_data); - - if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS)) - return NULL; - - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); - - return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); -} #else static inline bool folio_memcg_kmem(struct folio *folio) @@ -582,15 +561,6 @@ static inline bool folio_memcg_kmem(struct folio *folio) return false; } -static inline struct obj_cgroup **page_objcgs(struct page *page) -{ - return NULL; -} - -static inline struct obj_cgroup **page_objcgs_check(struct page *page) -{ - return NULL; -} #endif static inline bool PageMemcgKmem(struct page *page) @@ -886,9 +856,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); + return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, @@ -991,6 +959,21 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + rcu_read_lock(); + memcg = page_memcg(page); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return READ_ONCE(memcg->vmstats.state[idx]); @@ -1446,6 +1429,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; @@ -1697,18 +1685,6 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; -extern int memcg_nr_cache_ids; -void memcg_get_cache_ids(void); -void memcg_put_cache_ids(void); - -/* - * Helper macro to loop through all memcg-specific caches. Callers must still - * check if the cache is valid (it is either valid or NULL). - * the slab_mutex must be held when looping through those caches - */ -#define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) - static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); @@ -1732,7 +1708,7 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order) * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } @@ -1765,27 +1741,16 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } -#define for_each_memcg_cache_index(_idx) \ - for (; NULL; ) - static inline bool memcg_kmem_enabled(void) { return false; } -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } -static inline void memcg_get_cache_ids(void) -{ -} - -static inline void memcg_put_cache_ids(void) -{ -} - static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; diff --git a/include/linux/memory.h b/include/linux/memory.h index 88eb587b5143..aa619464a1df 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -70,6 +70,13 @@ struct memory_block { unsigned long state; /* serialized by the dev->lock */ int online_type; /* for passing data to online routine */ int nid; /* NID for this memory block */ + /* + * The single zone of this memory block if all PFNs of this memory block + * that are System RAM (not a memory hole, not ZONE_DEVICE ranges) are + * managed by a single zone. NULL if multiple zones (including nodes) + * apply. + */ + struct zone *zone; struct device dev; /* * Number of vmemmap pages. These pages @@ -161,6 +168,11 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) + +#ifdef CONFIG_NUMA +void memory_block_add_nid(struct memory_block *mem, int nid, + enum meminit_context context); +#endif /* CONFIG_NUMA */ #endif /* CONFIG_MEMORY_HOTPLUG */ /* diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index be48e003a518..1ce6f8044f1e 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -16,6 +16,62 @@ struct memory_group; struct resource; struct vmem_altmap; +#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION +/* + * For supporting node-hotadd, we have to allocate a new pgdat. + * + * If an arch has generic style NODE_DATA(), + * node_data[nid] = kzalloc() works well. But it depends on the architecture. + * + * In general, generic_alloc_nodedata() is used. + * + */ +extern pg_data_t *arch_alloc_nodedata(int nid); +extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); + +#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + +#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) + +#ifdef CONFIG_NUMA +/* + * XXX: node aware allocation can't work well to get new node's memory at this time. + * Because, pgdat for the new node is not allocated/initialized yet itself. + * To use new node's memory, more consideration will be necessary. + */ +#define generic_alloc_nodedata(nid) \ +({ \ + memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES); \ +}) +/* + * This definition is just for error path in node hotadd. + * For node hotremove, we have to replace this. + */ +#define generic_free_nodedata(pgdat) kfree(pgdat) + +extern pg_data_t *node_data[]; +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ + node_data[nid] = pgdat; +} + +#else /* !CONFIG_NUMA */ + +/* never called */ +static inline pg_data_t *generic_alloc_nodedata(int nid) +{ + BUG(); + return NULL; +} +static inline void generic_free_nodedata(pg_data_t *pgdat) +{ +} +static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) +{ +} +#endif /* CONFIG_NUMA */ +#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ + #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); @@ -107,8 +163,6 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern struct zone *test_pages_in_a_zone(unsigned long start_pfn, - unsigned long end_pfn); extern void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -154,66 +208,6 @@ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params); #endif /* ARCH_HAS_ADD_PAGES */ -#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION -/* - * For supporting node-hotadd, we have to allocate a new pgdat. - * - * If an arch has generic style NODE_DATA(), - * node_data[nid] = kzalloc() works well. But it depends on the architecture. - * - * In general, generic_alloc_nodedata() is used. - * Now, arch_free_nodedata() is just defined for error path of node_hot_add. - * - */ -extern pg_data_t *arch_alloc_nodedata(int nid); -extern void arch_free_nodedata(pg_data_t *pgdat); -extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat); - -#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - -#define arch_alloc_nodedata(nid) generic_alloc_nodedata(nid) -#define arch_free_nodedata(pgdat) generic_free_nodedata(pgdat) - -#ifdef CONFIG_NUMA -/* - * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat. - * XXX: kmalloc_node() can't work well to get new node's memory at this time. - * Because, pgdat for the new node is not allocated/initialized yet itself. - * To use new node's memory, more consideration will be necessary. - */ -#define generic_alloc_nodedata(nid) \ -({ \ - kzalloc(sizeof(pg_data_t), GFP_KERNEL); \ -}) -/* - * This definition is just for error path in node hotadd. - * For node hotremove, we have to replace this. - */ -#define generic_free_nodedata(pgdat) kfree(pgdat) - -extern pg_data_t *node_data[]; -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ - node_data[nid] = pgdat; -} - -#else /* !CONFIG_NUMA */ - -/* never called */ -static inline pg_data_t *generic_alloc_nodedata(int nid) -{ - BUG(); - return NULL; -} -static inline void generic_free_nodedata(pg_data_t *pgdat) -{ -} -static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) -{ -} -#endif /* CONFIG_NUMA */ -#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ - void get_online_mems(void); void put_online_mems(void); @@ -297,7 +291,7 @@ static inline void pgdat_resize_init(struct pglist_data *pgdat) {} extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group); + struct zone *zone, struct memory_group *group); extern int remove_memory(u64 start, u64 size); extern void __remove_memory(u64 start, u64 size); extern int offline_and_remove_memory(u64 start, u64 size); @@ -306,7 +300,7 @@ extern int offline_and_remove_memory(u64 start, u64 size); static inline void try_offline_node(int nid) {} static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages, - struct memory_group *group) + struct zone *zone, struct memory_group *group) { return -EINVAL; } @@ -323,7 +317,7 @@ extern void set_zone_contiguous(struct zone *zone); extern void clear_zone_contiguous(struct zone *zone); #ifdef CONFIG_MEMORY_HOTPLUG -extern void __ref free_area_init_core_hotplug(int nid); +extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory_resource(int nid, struct resource *resource, diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3c7595e81150..668389b4b53d 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,6 +46,7 @@ struct mempolicy { unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ + int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..8af304f6b504 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MEMREMAP_H_ #define _LINUX_MEMREMAP_H_ + +#include <linux/mm.h> #include <linux/range.h> #include <linux/ioport.h> #include <linux/percpu-refcount.h> @@ -66,23 +68,13 @@ enum memory_type { struct dev_pagemap_ops { /* - * Called once the page refcount reaches 1. (ZONE_DEVICE pages never - * reach 0 refcount unless there is a refcount bug. This allows the - * device driver to implement its own memory management.) + * Called once the page refcount reaches 0. The reference count will be + * reset to one by the core code after the method is called to prepare + * for handing out the page again. */ void (*page_free)(struct page *page); /* - * Transition the refcount in struct dev_pagemap to the dead state. - */ - void (*kill)(struct dev_pagemap *pgmap); - - /* - * Wait for refcount in struct dev_pagemap to be idle and reap it. - */ - void (*cleanup)(struct dev_pagemap *pgmap); - - /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. */ @@ -95,10 +87,14 @@ struct dev_pagemap_ops { * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping - * @internal_ref: internal reference if @ref is not provided by the caller - * @done: completion for @internal_ref + * @done: completion for @ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior + * @vmemmap_shift: structural definition of how the vmemmap page metadata + * is populated, specifically the metadata page order. + * A zero value (default) uses base pages as the vmemmap metadata + * representation. A bigger value will set up compound struct pages + * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no @@ -109,11 +105,11 @@ struct dev_pagemap_ops { */ struct dev_pagemap { struct vmem_altmap altmap; - struct percpu_ref *ref; - struct percpu_ref internal_ref; + struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; + unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; @@ -130,6 +126,30 @@ static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) return NULL; } +static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) +{ + return 1 << pgmap->vmemmap_shift; +} + +static inline bool is_device_private_page(const struct page *page) +{ + return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; +} + +static inline bool folio_is_device_private(const struct folio *folio) +{ + return is_device_private_page(&folio->page); +} + +static inline bool is_pci_p2pdma_page(const struct page *page) +{ + return IS_ENABLED(CONFIG_PCI_P2PDMA) && + is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; +} + #ifdef CONFIG_ZONE_DEVICE void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); @@ -191,7 +211,7 @@ static inline unsigned long memremap_compat_align(void) static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) - percpu_ref_put(pgmap->ref); + percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h index cbf9d7619493..e7a7e70fdb38 100644 --- a/include/linux/mfd/dbx500-prcmu.h +++ b/include/linux/mfd/dbx500-prcmu.h @@ -556,31 +556,11 @@ static inline void prcmu_clear(unsigned int reg, u32 bits) #define PRCMU_QOS_ARM_OPP 3 #define PRCMU_QOS_DEFAULT_VALUE -1 -#ifdef CONFIG_DBX500_PRCMU_QOS_POWER - -unsigned long prcmu_qos_get_cpufreq_opp_delay(void); -void prcmu_qos_set_cpufreq_opp_delay(unsigned long); -void prcmu_qos_force_opp(int, s32); -int prcmu_qos_requirement(int pm_qos_class); -int prcmu_qos_add_requirement(int pm_qos_class, char *name, s32 value); -int prcmu_qos_update_requirement(int pm_qos_class, char *name, s32 new_value); -void prcmu_qos_remove_requirement(int pm_qos_class, char *name); -int prcmu_qos_add_notifier(int prcmu_qos_class, - struct notifier_block *notifier); -int prcmu_qos_remove_notifier(int prcmu_qos_class, - struct notifier_block *notifier); - -#else - static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void) { return 0; } -static inline void prcmu_qos_set_cpufreq_opp_delay(unsigned long n) {} - -static inline void prcmu_qos_force_opp(int prcmu_qos_class, s32 i) {} - static inline int prcmu_qos_requirement(int prcmu_qos_class) { return 0; @@ -613,6 +593,4 @@ static inline int prcmu_qos_remove_notifier(int prcmu_qos_class, return 0; } -#endif - #endif /* __MACH_PRCMU_H */ diff --git a/include/linux/mfd/idt82p33_reg.h b/include/linux/mfd/idt82p33_reg.h index 129a6c078221..1db532feeb91 100644 --- a/include/linux/mfd/idt82p33_reg.h +++ b/include/linux/mfd/idt82p33_reg.h @@ -7,6 +7,8 @@ #ifndef HAVE_IDT82P33_REG #define HAVE_IDT82P33_REG +#define REG_ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) + /* Register address */ #define DPLL1_TOD_CNFG 0x134 #define DPLL2_TOD_CNFG 0x1B4 @@ -41,6 +43,7 @@ #define REG_SOFT_RESET 0X381 #define OUT_MUX_CNFG(outn) REG_ADDR(0x6, (0xC * (outn))) +#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) /* Register bit definitions */ #define SYNC_TOD BIT(1) diff --git a/include/linux/mfd/intel_soc_pmic.h b/include/linux/mfd/intel_soc_pmic.h index 6a88e34cb955..945bde1fe55c 100644 --- a/include/linux/mfd/intel_soc_pmic.h +++ b/include/linux/mfd/intel_soc_pmic.h @@ -13,6 +13,13 @@ #include <linux/regmap.h> +enum intel_cht_wc_models { + INTEL_CHT_WC_UNKNOWN, + INTEL_CHT_WC_GPD_WIN_POCKET, + INTEL_CHT_WC_XIAOMI_MIPAD2, + INTEL_CHT_WC_LENOVO_YOGABOOK1, +}; + /** * struct intel_soc_pmic - Intel SoC PMIC data * @irq: Master interrupt number of the parent PMIC device @@ -39,6 +46,7 @@ struct intel_soc_pmic { struct regmap_irq_chip_data *irq_chip_data_crit; struct device *dev; struct intel_scu_ipc_dev *scu; + enum intel_cht_wc_models cht_wc_model; }; int intel_soc_pmic_exec_mipi_pmic_seq_element(u16 i2c_address, u32 reg_address, diff --git a/include/linux/mfd/iqs62x.h b/include/linux/mfd/iqs62x.h index 5ced55eae11b..ffc86010af74 100644 --- a/include/linux/mfd/iqs62x.h +++ b/include/linux/mfd/iqs62x.h @@ -14,6 +14,11 @@ #define IQS624_PROD_NUM 0x43 #define IQS625_PROD_NUM 0x4E +#define IQS620_HW_NUM_V0 0x82 +#define IQS620_HW_NUM_V1 IQS620_HW_NUM_V0 +#define IQS620_HW_NUM_V2 IQS620_HW_NUM_V0 +#define IQS620_HW_NUM_V3 0x92 + #define IQS621_ALS_FLAGS 0x16 #define IQS622_ALS_FLAGS 0x14 @@ -129,6 +134,8 @@ struct iqs62x_core { struct completion fw_done; enum iqs62x_ui_sel ui_sel; unsigned long event_cache; + u8 sw_num; + u8 hw_num; }; extern const struct iqs62x_event_desc iqs62x_events[IQS62X_NUM_EVENTS]; diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h index 39967a5eca6d..ea4a4b1b246a 100644 --- a/include/linux/mfd/lpc_ich.h +++ b/include/linux/mfd/lpc_ich.h @@ -8,7 +8,7 @@ #ifndef LPC_ICH_H #define LPC_ICH_H -#include <linux/platform_data/x86/intel-spi.h> +#include <linux/platform_data/x86/spi-intel.h> /* GPIO resources */ #define ICH_RES_GPIO 0 diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index b1482b3cf353..3acceeedbaba 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -152,7 +152,7 @@ enum max77686_rtc_reg { MAX77686_RTC_WEEKDAY = 0x0A, MAX77686_RTC_MONTH = 0x0B, MAX77686_RTC_YEAR = 0x0C, - MAX77686_RTC_DATE = 0x0D, + MAX77686_RTC_MONTHDAY = 0x0D, MAX77686_ALARM1_SEC = 0x0E, MAX77686_ALARM1_MIN = 0x0F, MAX77686_ALARM1_HOUR = 0x10, @@ -352,7 +352,7 @@ enum max77802_rtc_reg { MAX77802_RTC_WEEKDAY = 0xCA, MAX77802_RTC_MONTH = 0xCB, MAX77802_RTC_YEAR = 0xCC, - MAX77802_RTC_DATE = 0xCD, + MAX77802_RTC_MONTHDAY = 0xCD, MAX77802_RTC_AE1 = 0xCE, MAX77802_ALARM1_SEC = 0xCF, MAX77802_ALARM1_MIN = 0xD0, diff --git a/include/linux/mfd/max77714.h b/include/linux/mfd/max77714.h new file mode 100644 index 000000000000..a970dc455426 --- /dev/null +++ b/include/linux/mfd/max77714.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Maxim MAX77714 Register and data structures definition. + * + * Copyright (C) 2022 Luca Ceresoli + * Author: Luca Ceresoli <luca@lucaceresoli.net> + */ + +#ifndef __LINUX_MFD_MAX77714_H_ +#define __LINUX_MFD_MAX77714_H_ + +#include <linux/bits.h> + +#define MAX77714_INT_TOP 0x00 +#define MAX77714_INT_TOPM 0x07 /* Datasheet says "read only", but it is RW */ + +#define MAX77714_INT_TOP_ONOFF BIT(1) +#define MAX77714_INT_TOP_RTC BIT(3) +#define MAX77714_INT_TOP_GPIO BIT(4) +#define MAX77714_INT_TOP_LDO BIT(5) +#define MAX77714_INT_TOP_SD BIT(6) +#define MAX77714_INT_TOP_GLBL BIT(7) + +#define MAX77714_32K_STATUS 0x30 +#define MAX77714_32K_STATUS_SIOSCOK BIT(5) +#define MAX77714_32K_STATUS_XOSCOK BIT(4) +#define MAX77714_32K_STATUS_32KSOURCE BIT(3) +#define MAX77714_32K_STATUS_32KLOAD_MSK 0x3 +#define MAX77714_32K_STATUS_32KLOAD_SHF 1 +#define MAX77714_32K_STATUS_CRYSTAL_CFG BIT(0) + +#define MAX77714_32K_CONFIG 0x31 +#define MAX77714_32K_CONFIG_XOSC_RETRY BIT(4) + +#define MAX77714_CNFG_GLBL2 0x91 +#define MAX77714_WDTEN BIT(2) +#define MAX77714_WDTSLPC BIT(3) +#define MAX77714_TWD_MASK 0x3 +#define MAX77714_TWD_2s 0x0 +#define MAX77714_TWD_16s 0x1 +#define MAX77714_TWD_64s 0x2 +#define MAX77714_TWD_128s 0x3 + +#define MAX77714_CNFG_GLBL3 0x92 +#define MAX77714_WDTC BIT(0) + +#define MAX77714_CNFG2_ONOFF 0x94 +#define MAX77714_WD_RST_WK BIT(5) + +/* Interrupts */ +enum { + MAX77714_IRQ_TOP_ONOFF, + MAX77714_IRQ_TOP_RTC, /* Real-time clock */ + MAX77714_IRQ_TOP_GPIO, /* GPIOs */ + MAX77714_IRQ_TOP_LDO, /* Low-dropout regulators */ + MAX77714_IRQ_TOP_SD, /* Step-down regulators */ + MAX77714_IRQ_TOP_GLBL, /* "Global resources": Low-Battery, overtemp... */ +}; + +#endif /* __LINUX_MFD_MAX77714_H_ */ diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h index 201139b12140..3d33517f178c 100644 --- a/include/linux/mfd/mt6358/registers.h +++ b/include/linux/mfd/mt6358/registers.h @@ -94,6 +94,10 @@ #define MT6358_BUCK_VCORE_CON0 0x1488 #define MT6358_BUCK_VCORE_DBG0 0x149e #define MT6358_BUCK_VCORE_DBG1 0x14a0 +#define MT6358_BUCK_VCORE_SSHUB_CON0 0x14a4 +#define MT6358_BUCK_VCORE_SSHUB_CON1 0x14a6 +#define MT6358_BUCK_VCORE_SSHUB_ELR0 MT6358_BUCK_VCORE_SSHUB_CON1 +#define MT6358_BUCK_VCORE_SSHUB_DBG1 MT6358_BUCK_VCORE_DBG1 #define MT6358_BUCK_VCORE_ELR0 0x14aa #define MT6358_BUCK_VGPU_CON0 0x1508 #define MT6358_BUCK_VGPU_DBG0 0x151e @@ -169,6 +173,9 @@ #define MT6358_LDO_VSRAM_OTHERS_CON0 0x1ba6 #define MT6358_LDO_VSRAM_OTHERS_DBG0 0x1bc0 #define MT6358_LDO_VSRAM_OTHERS_DBG1 0x1bc2 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_CON0 0x1bc4 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_CON1 0x1bc6 +#define MT6358_LDO_VSRAM_OTHERS_SSHUB_DBG1 MT6358_LDO_VSRAM_OTHERS_DBG1 #define MT6358_LDO_VSRAM_GPU_CON0 0x1bc8 #define MT6358_LDO_VSRAM_GPU_DBG0 0x1be2 #define MT6358_LDO_VSRAM_GPU_DBG1 0x1be4 diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h index 56f210eebc54..1cf78726503b 100644 --- a/include/linux/mfd/mt6397/core.h +++ b/include/linux/mfd/mt6397/core.h @@ -14,6 +14,7 @@ enum chip_id { MT6323_CHIP_ID = 0x23, MT6358_CHIP_ID = 0x58, MT6359_CHIP_ID = 0x59, + MT6366_CHIP_ID = 0x66, MT6391_CHIP_ID = 0x91, MT6397_CHIP_ID = 0x97, }; diff --git a/include/linux/mfd/ntxec.h b/include/linux/mfd/ntxec.h index 26ab3b8eb612..cc6f07bfa2b3 100644 --- a/include/linux/mfd/ntxec.h +++ b/include/linux/mfd/ntxec.h @@ -26,7 +26,7 @@ struct ntxec { * This convenience function converts an 8-bit value to 16-bit for use in the * second kind of register. */ -static inline __be16 ntxec_reg8(u8 value) +static inline u16 ntxec_reg8(u8 value) { return value << 8; } diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index a96e6d43ca06..58602032e642 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -373,6 +373,7 @@ enum rk805_reg { #define SWITCH2_EN BIT(6) #define SWITCH1_EN BIT(5) #define DEV_OFF_RST BIT(3) +#define DEV_RST BIT(2) #define DEV_OFF BIT(0) #define RTC_STOP BIT(0) diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h deleted file mode 100644 index 4a5966475a35..000000000000 --- a/include/linux/mfd/rohm-bd70528.h +++ /dev/null @@ -1,389 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Copyright (C) 2018 ROHM Semiconductors */ - -#ifndef __LINUX_MFD_BD70528_H__ -#define __LINUX_MFD_BD70528_H__ - -#include <linux/bits.h> -#include <linux/device.h> -#include <linux/mfd/rohm-generic.h> -#include <linux/mfd/rohm-shared.h> -#include <linux/regmap.h> - -enum { - BD70528_BUCK1, - BD70528_BUCK2, - BD70528_BUCK3, - BD70528_LDO1, - BD70528_LDO2, - BD70528_LDO3, - BD70528_LED1, - BD70528_LED2, -}; - -struct bd70528_data { - struct rohm_regmap_dev chip; - struct mutex rtc_timer_lock; -}; - -#define BD70528_BUCK_VOLTS 0x10 -#define BD70528_LDO_VOLTS 0x20 - -#define BD70528_REG_BUCK1_EN 0x0F -#define BD70528_REG_BUCK1_VOLT 0x15 -#define BD70528_REG_BUCK2_EN 0x10 -#define BD70528_REG_BUCK2_VOLT 0x16 -#define BD70528_REG_BUCK3_EN 0x11 -#define BD70528_REG_BUCK3_VOLT 0x17 -#define BD70528_REG_LDO1_EN 0x1b -#define BD70528_REG_LDO1_VOLT 0x1e -#define BD70528_REG_LDO2_EN 0x1c -#define BD70528_REG_LDO2_VOLT 0x1f -#define BD70528_REG_LDO3_EN 0x1d -#define BD70528_REG_LDO3_VOLT 0x20 -#define BD70528_REG_LED_CTRL 0x2b -#define BD70528_REG_LED_VOLT 0x29 -#define BD70528_REG_LED_EN 0x2a - -/* main irq registers */ -#define BD70528_REG_INT_MAIN 0x7E -#define BD70528_REG_INT_MAIN_MASK 0x74 - -/* 'sub irq' registers */ -#define BD70528_REG_INT_SHDN 0x7F -#define BD70528_REG_INT_PWR_FLT 0x80 -#define BD70528_REG_INT_VR_FLT 0x81 -#define BD70528_REG_INT_MISC 0x82 -#define BD70528_REG_INT_BAT1 0x83 -#define BD70528_REG_INT_BAT2 0x84 -#define BD70528_REG_INT_RTC 0x85 -#define BD70528_REG_INT_GPIO 0x86 -#define BD70528_REG_INT_OP_FAIL 0x87 - -#define BD70528_REG_INT_SHDN_MASK 0x75 -#define BD70528_REG_INT_PWR_FLT_MASK 0x76 -#define BD70528_REG_INT_VR_FLT_MASK 0x77 -#define BD70528_REG_INT_MISC_MASK 0x78 -#define BD70528_REG_INT_BAT1_MASK 0x79 -#define BD70528_REG_INT_BAT2_MASK 0x7a -#define BD70528_REG_INT_RTC_MASK 0x7b -#define BD70528_REG_INT_GPIO_MASK 0x7c -#define BD70528_REG_INT_OP_FAIL_MASK 0x7d - -/* Reset related 'magic' registers */ -#define BD70528_REG_SHIPMODE 0x03 -#define BD70528_REG_HWRESET 0x04 -#define BD70528_REG_WARMRESET 0x05 -#define BD70528_REG_STANDBY 0x06 - -/* GPIO registers */ -#define BD70528_REG_GPIO_STATE 0x8F - -#define BD70528_REG_GPIO1_IN 0x4d -#define BD70528_REG_GPIO2_IN 0x4f -#define BD70528_REG_GPIO3_IN 0x51 -#define BD70528_REG_GPIO4_IN 0x53 -#define BD70528_REG_GPIO1_OUT 0x4e -#define BD70528_REG_GPIO2_OUT 0x50 -#define BD70528_REG_GPIO3_OUT 0x52 -#define BD70528_REG_GPIO4_OUT 0x54 - -/* RTC */ - -#define BD70528_REG_RTC_COUNT_H 0x2d -#define BD70528_REG_RTC_COUNT_L 0x2e -#define BD70528_REG_RTC_SEC 0x2f -#define BD70528_REG_RTC_MINUTE 0x30 -#define BD70528_REG_RTC_HOUR 0x31 -#define BD70528_REG_RTC_WEEK 0x32 -#define BD70528_REG_RTC_DAY 0x33 -#define BD70528_REG_RTC_MONTH 0x34 -#define BD70528_REG_RTC_YEAR 0x35 - -#define BD70528_REG_RTC_ALM_SEC 0x36 -#define BD70528_REG_RTC_ALM_START BD70528_REG_RTC_ALM_SEC -#define BD70528_REG_RTC_ALM_MINUTE 0x37 -#define BD70528_REG_RTC_ALM_HOUR 0x38 -#define BD70528_REG_RTC_ALM_WEEK 0x39 -#define BD70528_REG_RTC_ALM_DAY 0x3a -#define BD70528_REG_RTC_ALM_MONTH 0x3b -#define BD70528_REG_RTC_ALM_YEAR 0x3c -#define BD70528_REG_RTC_ALM_MASK 0x3d -#define BD70528_REG_RTC_ALM_REPEAT 0x3e -#define BD70528_REG_RTC_START BD70528_REG_RTC_SEC - -#define BD70528_REG_RTC_WAKE_SEC 0x43 -#define BD70528_REG_RTC_WAKE_START BD70528_REG_RTC_WAKE_SEC -#define BD70528_REG_RTC_WAKE_MIN 0x44 -#define BD70528_REG_RTC_WAKE_HOUR 0x45 -#define BD70528_REG_RTC_WAKE_CTRL 0x46 - -#define BD70528_REG_ELAPSED_TIMER_EN 0x42 -#define BD70528_REG_WAKE_EN 0x46 - -/* WDT registers */ -#define BD70528_REG_WDT_CTRL 0x4A -#define BD70528_REG_WDT_HOUR 0x49 -#define BD70528_REG_WDT_MINUTE 0x48 -#define BD70528_REG_WDT_SEC 0x47 - -/* Charger / Battery */ -#define BD70528_REG_CHG_CURR_STAT 0x59 -#define BD70528_REG_CHG_BAT_STAT 0x57 -#define BD70528_REG_CHG_BAT_TEMP 0x58 -#define BD70528_REG_CHG_IN_STAT 0x56 -#define BD70528_REG_CHG_DCIN_ILIM 0x5d -#define BD70528_REG_CHG_CHG_CURR_WARM 0x61 -#define BD70528_REG_CHG_CHG_CURR_COLD 0x62 - -/* Masks for main IRQ register bits */ -enum { - BD70528_INT_SHDN, -#define BD70528_INT_SHDN_MASK BIT(BD70528_INT_SHDN) - BD70528_INT_PWR_FLT, -#define BD70528_INT_PWR_FLT_MASK BIT(BD70528_INT_PWR_FLT) - BD70528_INT_VR_FLT, -#define BD70528_INT_VR_FLT_MASK BIT(BD70528_INT_VR_FLT) - BD70528_INT_MISC, -#define BD70528_INT_MISC_MASK BIT(BD70528_INT_MISC) - BD70528_INT_BAT1, -#define BD70528_INT_BAT1_MASK BIT(BD70528_INT_BAT1) - BD70528_INT_RTC, -#define BD70528_INT_RTC_MASK BIT(BD70528_INT_RTC) - BD70528_INT_GPIO, -#define BD70528_INT_GPIO_MASK BIT(BD70528_INT_GPIO) - BD70528_INT_OP_FAIL, -#define BD70528_INT_OP_FAIL_MASK BIT(BD70528_INT_OP_FAIL) -}; - -/* IRQs */ -enum { - /* Shutdown register IRQs */ - BD70528_INT_LONGPUSH, - BD70528_INT_WDT, - BD70528_INT_HWRESET, - BD70528_INT_RSTB_FAULT, - BD70528_INT_VBAT_UVLO, - BD70528_INT_TSD, - BD70528_INT_RSTIN, - /* Power failure register IRQs */ - BD70528_INT_BUCK1_FAULT, - BD70528_INT_BUCK2_FAULT, - BD70528_INT_BUCK3_FAULT, - BD70528_INT_LDO1_FAULT, - BD70528_INT_LDO2_FAULT, - BD70528_INT_LDO3_FAULT, - BD70528_INT_LED1_FAULT, - BD70528_INT_LED2_FAULT, - /* VR FAULT register IRQs */ - BD70528_INT_BUCK1_OCP, - BD70528_INT_BUCK2_OCP, - BD70528_INT_BUCK3_OCP, - BD70528_INT_LED1_OCP, - BD70528_INT_LED2_OCP, - BD70528_INT_BUCK1_FULLON, - BD70528_INT_BUCK2_FULLON, - /* PMU register interrupts */ - BD70528_INT_SHORTPUSH, - BD70528_INT_AUTO_WAKEUP, - BD70528_INT_STATE_CHANGE, - /* Charger 1 register IRQs */ - BD70528_INT_BAT_OV_RES, - BD70528_INT_BAT_OV_DET, - BD70528_INT_DBAT_DET, - BD70528_INT_BATTSD_COLD_RES, - BD70528_INT_BATTSD_COLD_DET, - BD70528_INT_BATTSD_HOT_RES, - BD70528_INT_BATTSD_HOT_DET, - BD70528_INT_CHG_TSD, - /* Charger 2 register IRQs */ - BD70528_INT_BAT_RMV, - BD70528_INT_BAT_DET, - BD70528_INT_DCIN2_OV_RES, - BD70528_INT_DCIN2_OV_DET, - BD70528_INT_DCIN2_RMV, - BD70528_INT_DCIN2_DET, - BD70528_INT_DCIN1_RMV, - BD70528_INT_DCIN1_DET, - /* RTC register IRQs */ - BD70528_INT_RTC_ALARM, - BD70528_INT_ELPS_TIM, - /* GPIO register IRQs */ - BD70528_INT_GPIO0, - BD70528_INT_GPIO1, - BD70528_INT_GPIO2, - BD70528_INT_GPIO3, - /* Invalid operation register IRQs */ - BD70528_INT_BUCK1_DVS_OPFAIL, - BD70528_INT_BUCK2_DVS_OPFAIL, - BD70528_INT_BUCK3_DVS_OPFAIL, - BD70528_INT_LED1_VOLT_OPFAIL, - BD70528_INT_LED2_VOLT_OPFAIL, -}; - -/* Masks */ -#define BD70528_INT_LONGPUSH_MASK 0x1 -#define BD70528_INT_WDT_MASK 0x2 -#define BD70528_INT_HWRESET_MASK 0x4 -#define BD70528_INT_RSTB_FAULT_MASK 0x8 -#define BD70528_INT_VBAT_UVLO_MASK 0x10 -#define BD70528_INT_TSD_MASK 0x20 -#define BD70528_INT_RSTIN_MASK 0x40 - -#define BD70528_INT_BUCK1_FAULT_MASK 0x1 -#define BD70528_INT_BUCK2_FAULT_MASK 0x2 -#define BD70528_INT_BUCK3_FAULT_MASK 0x4 -#define BD70528_INT_LDO1_FAULT_MASK 0x8 -#define BD70528_INT_LDO2_FAULT_MASK 0x10 -#define BD70528_INT_LDO3_FAULT_MASK 0x20 -#define BD70528_INT_LED1_FAULT_MASK 0x40 -#define BD70528_INT_LED2_FAULT_MASK 0x80 - -#define BD70528_INT_BUCK1_OCP_MASK 0x1 -#define BD70528_INT_BUCK2_OCP_MASK 0x2 -#define BD70528_INT_BUCK3_OCP_MASK 0x4 -#define BD70528_INT_LED1_OCP_MASK 0x8 -#define BD70528_INT_LED2_OCP_MASK 0x10 -#define BD70528_INT_BUCK1_FULLON_MASK 0x20 -#define BD70528_INT_BUCK2_FULLON_MASK 0x40 - -#define BD70528_INT_SHORTPUSH_MASK 0x1 -#define BD70528_INT_AUTO_WAKEUP_MASK 0x2 -#define BD70528_INT_STATE_CHANGE_MASK 0x10 - -#define BD70528_INT_BAT_OV_RES_MASK 0x1 -#define BD70528_INT_BAT_OV_DET_MASK 0x2 -#define BD70528_INT_DBAT_DET_MASK 0x4 -#define BD70528_INT_BATTSD_COLD_RES_MASK 0x8 -#define BD70528_INT_BATTSD_COLD_DET_MASK 0x10 -#define BD70528_INT_BATTSD_HOT_RES_MASK 0x20 -#define BD70528_INT_BATTSD_HOT_DET_MASK 0x40 -#define BD70528_INT_CHG_TSD_MASK 0x80 - -#define BD70528_INT_BAT_RMV_MASK 0x1 -#define BD70528_INT_BAT_DET_MASK 0x2 -#define BD70528_INT_DCIN2_OV_RES_MASK 0x4 -#define BD70528_INT_DCIN2_OV_DET_MASK 0x8 -#define BD70528_INT_DCIN2_RMV_MASK 0x10 -#define BD70528_INT_DCIN2_DET_MASK 0x20 -#define BD70528_INT_DCIN1_RMV_MASK 0x40 -#define BD70528_INT_DCIN1_DET_MASK 0x80 - -#define BD70528_INT_RTC_ALARM_MASK 0x1 -#define BD70528_INT_ELPS_TIM_MASK 0x2 - -#define BD70528_INT_GPIO0_MASK 0x1 -#define BD70528_INT_GPIO1_MASK 0x2 -#define BD70528_INT_GPIO2_MASK 0x4 -#define BD70528_INT_GPIO3_MASK 0x8 - -#define BD70528_INT_BUCK1_DVS_OPFAIL_MASK 0x1 -#define BD70528_INT_BUCK2_DVS_OPFAIL_MASK 0x2 -#define BD70528_INT_BUCK3_DVS_OPFAIL_MASK 0x4 -#define BD70528_INT_LED1_VOLT_OPFAIL_MASK 0x10 -#define BD70528_INT_LED2_VOLT_OPFAIL_MASK 0x20 - -#define BD70528_DEBOUNCE_MASK 0x3 - -#define BD70528_DEBOUNCE_DISABLE 0 -#define BD70528_DEBOUNCE_15MS 1 -#define BD70528_DEBOUNCE_30MS 2 -#define BD70528_DEBOUNCE_50MS 3 - -#define BD70528_GPIO_DRIVE_MASK 0x2 -#define BD70528_GPIO_PUSH_PULL 0x0 -#define BD70528_GPIO_OPEN_DRAIN 0x2 - -#define BD70528_GPIO_OUT_EN_MASK 0x80 -#define BD70528_GPIO_OUT_ENABLE 0x80 -#define BD70528_GPIO_OUT_DISABLE 0x0 - -#define BD70528_GPIO_OUT_HI 0x1 -#define BD70528_GPIO_OUT_LO 0x0 -#define BD70528_GPIO_OUT_MASK 0x1 - -#define BD70528_GPIO_IN_STATE_BASE 1 - -/* RTC masks to mask out reserved bits */ - -#define BD70528_MASK_ELAPSED_TIMER_EN 0x1 -/* Mask second, min and hour fields - * HW would support ALM irq for over 24h - * (by setting day, month and year too) - * but as we wish to keep this same as for - * wake-up we limit ALM to 24H and only - * unmask sec, min and hour - */ -#define BD70528_MASK_WAKE_EN 0x1 - -/* WDT masks */ -#define BD70528_MASK_WDT_EN 0x1 -#define BD70528_MASK_WDT_HOUR 0x1 -#define BD70528_MASK_WDT_MINUTE 0x7f -#define BD70528_MASK_WDT_SEC 0x7f - -#define BD70528_WDT_STATE_BIT 0x1 -#define BD70528_ELAPSED_STATE_BIT 0x2 -#define BD70528_WAKE_STATE_BIT 0x4 - -/* Charger masks */ -#define BD70528_MASK_CHG_STAT 0x7f -#define BD70528_MASK_CHG_BAT_TIMER 0x20 -#define BD70528_MASK_CHG_BAT_OVERVOLT 0x10 -#define BD70528_MASK_CHG_BAT_DETECT 0x1 -#define BD70528_MASK_CHG_DCIN1_UVLO 0x1 -#define BD70528_MASK_CHG_DCIN_ILIM 0x3f -#define BD70528_MASK_CHG_CHG_CURR 0x1f -#define BD70528_MASK_CHG_TRICKLE_CURR 0x10 - -/* - * Note, external battery register is the lonely rider at - * address 0xc5. See how to stuff that in the regmap - */ -#define BD70528_MAX_REGISTER 0x94 - -/* Buck control masks */ -#define BD70528_MASK_RUN_EN 0x4 -#define BD70528_MASK_STBY_EN 0x2 -#define BD70528_MASK_IDLE_EN 0x1 -#define BD70528_MASK_LED1_EN 0x1 -#define BD70528_MASK_LED2_EN 0x10 - -#define BD70528_MASK_BUCK_VOLT 0xf -#define BD70528_MASK_LDO_VOLT 0x1f -#define BD70528_MASK_LED1_VOLT 0x1 -#define BD70528_MASK_LED2_VOLT 0x10 - -/* Misc irq masks */ -#define BD70528_INT_MASK_SHORT_PUSH 1 -#define BD70528_INT_MASK_AUTO_WAKE 2 -#define BD70528_INT_MASK_POWER_STATE 4 - -#define BD70528_MASK_BUCK_RAMP 0x10 -#define BD70528_SIFT_BUCK_RAMP 4 - -#if IS_ENABLED(CONFIG_BD70528_WATCHDOG) - -int bd70528_wdt_set(struct rohm_regmap_dev *data, int enable, int *old_state); -void bd70528_wdt_lock(struct rohm_regmap_dev *data); -void bd70528_wdt_unlock(struct rohm_regmap_dev *data); - -#else /* CONFIG_BD70528_WATCHDOG */ - -static inline int bd70528_wdt_set(struct rohm_regmap_dev *data, int enable, - int *old_state) -{ - return 0; -} - -static inline void bd70528_wdt_lock(struct rohm_regmap_dev *data) -{ -} - -static inline void bd70528_wdt_unlock(struct rohm_regmap_dev *data) -{ -} - -#endif /* CONFIG_BD70528_WATCHDOG */ - -#endif /* __LINUX_MFD_BD70528_H__ */ diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 35b392a0d73a..4eeb22876bad 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -12,7 +12,6 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD9573, ROHM_CHIP_TYPE_BD9574, ROHM_CHIP_TYPE_BD9576, - ROHM_CHIP_TYPE_BD70528, ROHM_CHIP_TYPE_BD71815, ROHM_CHIP_TYPE_BD71828, ROHM_CHIP_TYPE_BD71837, @@ -80,14 +79,8 @@ int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, const struct regulator_desc *desc, struct regmap *regmap); -#else -static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, - struct device_node *np, - const struct regulator_desc *desc, - struct regmap *regmap) -{ - return 0; -} +int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, + unsigned int sel); #endif #endif diff --git a/include/linux/mfd/sy7636a.h b/include/linux/mfd/sy7636a.h new file mode 100644 index 000000000000..22f03b2f851e --- /dev/null +++ b/include/linux/mfd/sy7636a.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Functions to access SY3686A power management chip. + * + * Copyright (C) 2021 reMarkable AS - http://www.remarkable.com/ + */ + +#ifndef __MFD_SY7636A_H +#define __MFD_SY7636A_H + +#define SY7636A_REG_OPERATION_MODE_CRL 0x00 +/* It is set if a gpio is used to control the regulator */ +#define SY7636A_OPERATION_MODE_CRL_VCOMCTL BIT(6) +#define SY7636A_OPERATION_MODE_CRL_ONOFF BIT(7) +#define SY7636A_REG_VCOM_ADJUST_CTRL_L 0x01 +#define SY7636A_REG_VCOM_ADJUST_CTRL_H 0x02 +#define SY7636A_REG_VCOM_ADJUST_CTRL_MASK 0x01ff +#define SY7636A_REG_VLDO_VOLTAGE_ADJULST_CTRL 0x03 +#define SY7636A_REG_POWER_ON_DELAY_TIME 0x06 +#define SY7636A_REG_FAULT_FLAG 0x07 +#define SY7636A_FAULT_FLAG_PG BIT(0) +#define SY7636A_REG_TERMISTOR_READOUT 0x08 + +#define SY7636A_REG_MAX 0x08 + +#define VCOM_ADJUST_CTRL_MASK 0x1ff +// Used to shift the high byte +#define VCOM_ADJUST_CTRL_SHIFT 8 +// Used to scale from VCOM_ADJUST_CTRL to mv +#define VCOM_ADJUST_CTRL_SCAL 10000 + +#define FAULT_FLAG_SHIFT 1 + +#endif /* __LINUX_MFD_SY7636A_H */ diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ba13e043d910..4063b0614d90 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -103,7 +103,6 @@ #define CNTRLREG_TSC_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) #define CNTRLREG_TSC_4WIRE CNTRLREG_TSC_AFE_CTRL(1) #define CNTRLREG_TSC_5WIRE CNTRLREG_TSC_AFE_CTRL(2) -#define CNTRLREG_TSC_8WIRE CNTRLREG_TSC_AFE_CTRL(3) #define CNTRLREG_TSC_ENB BIT(7) /*Control registers bitfields for MAGADC IP */ diff --git a/include/linux/mfd/tps68470.h b/include/linux/mfd/tps68470.h index ffe81127d91c..7807fa329db0 100644 --- a/include/linux/mfd/tps68470.h +++ b/include/linux/mfd/tps68470.h @@ -75,6 +75,17 @@ #define TPS68470_CLKCFG1_MODE_A_MASK GENMASK(1, 0) #define TPS68470_CLKCFG1_MODE_B_MASK GENMASK(3, 2) +#define TPS68470_CLKCFG2_DRV_STR_2MA 0x05 +#define TPS68470_PLL_OUTPUT_ENABLE 0x02 +#define TPS68470_CLK_SRC_XTAL BIT(0) +#define TPS68470_PLLSWR_DEFAULT GENMASK(1, 0) +#define TPS68470_OSC_EXT_CAP_DEFAULT 0x05 + +#define TPS68470_OUTPUT_A_SHIFT 0x00 +#define TPS68470_OUTPUT_B_SHIFT 0x02 +#define TPS68470_CLK_SRC_SHIFT GENMASK(2, 0) +#define TPS68470_OSC_EXT_CAP_SHIFT BIT(2) + #define TPS68470_GPIO_CTL_REG_A(x) (TPS68470_REG_GPCTL0A + (x) * 2) #define TPS68470_GPIO_CTL_REG_B(x) (TPS68470_REG_GPCTL0B + (x) * 2) #define TPS68470_GPIO_MODE_MASK GENMASK(1, 0) diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5cc4cdf9cc8..a5441ad33c74 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -730,16 +730,27 @@ void mhi_device_put(struct mhi_device *mhi_dev); /** * mhi_prepare_for_transfer - Setup UL and DL channels for data transfer. - * Allocate and initialize the channel context and - * also issue the START channel command to both - * channels. Channels can be started only if both - * host and device execution environments match and - * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * + * Allocate and initialize the channel context and also issue the START channel + * command to both channels. Channels can be started only if both host and + * device execution environments match and channels are in a DISABLED state. */ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); /** + * mhi_prepare_for_transfer_autoqueue - Setup UL and DL channels with auto queue + * buffers for DL traffic + * @mhi_dev: Device associated with the channels + * + * Allocate and initialize the channel context and also issue the START channel + * command to both channels. Channels can be started only if both host and + * device execution environments match and channels are in a DISABLED state. + * The MHI core will automatically allocate and queue buffers for the DL traffic. + */ +int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); + +/** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. * Issue the RESET channel command and let the * device clean-up the context so no incoming diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4850cc5bf813..90e75d5a54d6 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,13 +40,23 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); extern bool numa_demotion_enabled; +extern void migrate_on_reclaim_init(void); +#ifdef CONFIG_HOTPLUG_CPU +extern void set_migration_target_nodes(void); #else +static inline void set_migration_target_nodes(void) {} +#endif +#else + +static inline void set_migration_target_nodes(void) {} static inline void putback_movable_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t new, diff --git a/include/linux/mii.h b/include/linux/mii.h index 12ea29e04293..5ee13083cec7 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -355,56 +355,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) } /** - * mii_lpa_mod_linkmode_adv_sgmii - * @lp_advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_LPA bits to - * linkmode advertisement settings for SGMII. - * Leaves other bits unchanged. - */ -static inline void -mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) -{ - u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10FULL); -} - -/** - * mii_lpa_to_linkmode_adv_sgmii - * @advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings when in SGMII mode. - * Clears the old value of advertising. - */ -static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, - u32 lpa) -{ - linkmode_zero(lp_advertising); - - mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); -} - -/** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. * @adv: value of the MII_ADVERTISE register diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7bfb67363434..cb15308b5cb0 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -183,6 +183,8 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) complete(&cq->free); } +int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, + u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 9c25edfd59a6..604b85dd770a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1117,6 +1117,7 @@ enum { MLX5_MATCH_MISC_PARAMETERS_2 = 1 << 3, MLX5_MATCH_MISC_PARAMETERS_3 = 1 << 4, MLX5_MATCH_MISC_PARAMETERS_4 = 1 << 5, + MLX5_MATCH_MISC_PARAMETERS_5 = 1 << 6, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a623ec635947..9424503eb8d3 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -264,6 +264,14 @@ enum { struct mlx5_cmd_stats { u64 sum; u64 n; + /* number of times command failed */ + u64 failed; + /* number of times command failed on bad status returned by FW */ + u64 failed_mbox_status; + /* last command failed returned errno */ + u32 last_failed_errno; + /* last bad status returned by FW */ + u8 last_failed_mbox_status; struct dentry *root; /* protect command average calculations */ spinlock_t lock; @@ -478,6 +486,10 @@ struct mlx5_fc_stats { unsigned long next_query; unsigned long sampling_interval; /* jiffies */ u32 *bulk_query_out; + int bulk_query_len; + size_t num_counters; + bool bulk_query_alloc_failed; + unsigned long next_bulk_query_alloc; struct mlx5_fc_pool fc_pool; }; @@ -539,6 +551,15 @@ struct mlx5_adev { int idx; }; +struct mlx5_debugfs_entries { + struct dentry *dbg_root; + struct dentry *qp_debugfs; + struct dentry *eq_debugfs; + struct dentry *cq_debugfs; + struct dentry *cmdif_debugfs; + struct dentry *pages_debugfs; +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -549,21 +570,19 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - int fw_pages; + u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - int vfs_pages; - int host_pf_pages; + u32 vfs_pages; + u32 host_pf_pages; + u32 fw_pages_alloc_failed; + u32 give_pages_dropped; + u32 reclaim_pages_discard; struct mlx5_core_health health; struct list_head traps; - /* start: qp staff */ - struct dentry *qp_debugfs; - struct dentry *eq_debugfs; - struct dentry *cq_debugfs; - struct dentry *cmdif_debugfs; - /* end: qp staff */ + struct mlx5_debugfs_entries dbg; /* start: alloc staff */ /* protect buffer allocation according to numa node */ @@ -573,7 +592,6 @@ struct mlx5_priv { struct mutex pgdir_mutex; struct list_head pgdir_list; /* end: alloc staff */ - struct dentry *dbg_root; struct list_head ctx_list; spinlock_t ctx_lock; @@ -859,20 +877,10 @@ struct mlx5_hca_vport_context { bool grh_required; }; -static inline void *mlx5_buf_offset(struct mlx5_frag_buf *buf, int offset) -{ - return buf->frags->buf + offset; -} - #define STRUCT_FIELD(header, field) \ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \ .struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field -static inline struct mlx5_core_dev *pci2mlx5_core_dev(struct pci_dev *pdev) -{ - return pci_get_drvdata(pdev); -} - extern struct dentry *mlx5_debugfs_root; static inline u16 fw_rev_maj(struct mlx5_core_dev *dev) @@ -961,6 +969,8 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; + u16 opcode; /* cmd opcode */ + void *out; /* pointer to the cmd output buffer */ }; void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, @@ -969,7 +979,9 @@ void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx); int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, void *out, int out_size, mlx5_async_cbk_t callback, struct mlx5_async_work *work); - +void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out); +int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); +int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out); int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); @@ -987,7 +999,6 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); -void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); @@ -998,9 +1009,6 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); -int mlx5_buf_alloc(struct mlx5_core_dev *dev, - int size, struct mlx5_frag_buf *buf); -void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); @@ -1019,6 +1027,8 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); @@ -1026,15 +1036,18 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); void mlx5_unregister_debugfs(void); -void mlx5_fill_page_array(struct mlx5_frag_buf *buf, __be64 *pas); void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm); void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); +struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); +int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, + void *data_out, int size_out, u16 reg_id, int arg, + int write, bool verbose); int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, void *data_out, int size_out, u16 reg_num, int arg, int write); @@ -1139,6 +1152,9 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, u64 length, u16 uid, phys_addr_t addr, u32 obj_id); +struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev); +void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev); + #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, struct ib_device *ibdev, diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index ea3ff5a8ced3..3705a382276b 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -9,13 +9,13 @@ #define MLX5_NUM_SPARE_EQE (0x80) struct mlx5_eq; +struct mlx5_irq; struct mlx5_core_dev; struct mlx5_eq_param { - u8 irq_index; int nent; u64 mask[4]; - cpumask_var_t affinity; + struct mlx5_irq *irq; }; struct mlx5_eq * diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index cd2d4c572367..e3bfed68b08a 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_ANCHOR, + MLX5_FLOW_NAMESPACE_FDB_BYPASS, MLX5_FLOW_NAMESPACE_FDB, MLX5_FLOW_NAMESPACE_ESW_EGRESS, MLX5_FLOW_NAMESPACE_ESW_INGRESS, @@ -223,6 +224,7 @@ struct mlx5_flow_act { u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; + struct mlx5_flow_group *fg; }; #define MLX5_DECLARE_FLOW_ACT(name) \ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fbaab440a484..7d2d0ba82144 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -64,13 +64,6 @@ enum { }; enum { - MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, - MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, - MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, - MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 -}; - -enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, @@ -127,6 +120,11 @@ enum { MLX5_CMD_OP_QUERY_SF_PARTITION = 0x111, MLX5_CMD_OP_ALLOC_SF = 0x113, MLX5_CMD_OP_DEALLOC_SF = 0x114, + MLX5_CMD_OP_SUSPEND_VHCA = 0x115, + MLX5_CMD_OP_RESUME_VHCA = 0x116, + MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE = 0x117, + MLX5_CMD_OP_SAVE_VHCA_STATE = 0x118, + MLX5_CMD_OP_LOAD_VHCA_STATE = 0x119, MLX5_CMD_OP_CREATE_MKEY = 0x200, MLX5_CMD_OP_QUERY_MKEY = 0x201, MLX5_CMD_OP_DESTROY_MKEY = 0x202, @@ -372,7 +370,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 reserved_at_37[0x9]; u8 geneve_tlv_option_0_data[0x1]; - u8 reserved_at_41[0x4]; + u8 geneve_tlv_option_0_exist[0x1]; + u8 reserved_at_42[0x3]; u8 outer_first_mpls_over_udp[0x4]; u8 outer_first_mpls_over_gre[0x4]; u8 inner_first_mpls[0x4]; @@ -499,7 +498,10 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x18]; + u8 reserved_at_c0[0x10]; + u8 ipv4_ihl[0x4]; + u8 reserved_at_c4[0x4]; + u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; @@ -551,7 +553,8 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 bth_opcode[0x8]; u8 geneve_vni[0x18]; - u8 reserved_at_d8[0x7]; + u8 reserved_at_d8[0x6]; + u8 geneve_tlv_option_0_exist[0x1]; u8 geneve_oam[0x1]; u8 reserved_at_e0[0xc]; @@ -670,6 +673,26 @@ struct mlx5_ifc_fte_match_set_misc4_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_fte_match_set_misc5_bits { + u8 macsec_tag_0[0x20]; + + u8 macsec_tag_1[0x20]; + + u8 macsec_tag_2[0x20]; + + u8 macsec_tag_3[0x20]; + + u8 tunnel_header_0[0x20]; + + u8 tunnel_header_1[0x20]; + + u8 tunnel_header_2[0x20]; + + u8 tunnel_header_3[0x20]; + + u8 reserved_at_100[0x100]; +}; + struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; @@ -811,7 +834,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_to_vport_reg_c_id[0x8]; u8 reserved_at_8[0xd]; u8 fdb_modify_header_fwd_to_table[0x1]; - u8 reserved_at_16[0x1]; + u8 fdb_ipv4_ttl_modify[0x1]; u8 flow_source[0x1]; u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; @@ -1291,7 +1314,7 @@ enum { enum { MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED = 1 << 4, - mlx5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, + MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, @@ -1328,6 +1351,7 @@ enum mlx5_fc_bulk_alloc_bitmask { enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, + MLX5_STEERING_FORMAT_CONNECTX_7 = 2, }; struct mlx5_ifc_cmd_hca_cap_bits { @@ -1404,8 +1428,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0x6]; + u8 reserved_at_140[0x5]; u8 release_all_pages[0x1]; + u8 must_not_use[0x1]; u8 reserved_at_147[0x2]; u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; @@ -1621,7 +1646,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ext_stride_num_range[0x1]; u8 roce_rw_supported[0x1]; - u8 reserved_at_3a2[0x1]; + u8 log_max_current_uc_list_wr_supported[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; @@ -1735,7 +1760,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_682[0x1]; u8 log_max_sf[0x5]; u8 apu[0x1]; - u8 reserved_at_689[0x7]; + u8 reserved_at_689[0x4]; + u8 migration[0x1]; + u8 reserved_at_68e[0x2]; u8 log_min_sf_size[0x8]; u8 max_num_sf_partitions[0x8]; @@ -1839,7 +1866,9 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_misc4_bits misc_parameters_4; - u8 reserved_at_c00[0x400]; + struct mlx5_ifc_fte_match_set_misc5_bits misc_parameters_5; + + u8 reserved_at_e00[0x200]; }; enum { @@ -3410,7 +3439,6 @@ enum { enum { MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO = BIT(0), MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO = BIT(1), - MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO = BIT(2), }; enum { @@ -5977,6 +6005,7 @@ enum { MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_4 = 0x5, + MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_5 = 0x6, }; struct mlx5_ifc_query_flow_group_out_bits { @@ -9669,7 +9698,10 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x6b]; + u8 reserved_at_0[0x5d]; + u8 mcia_32dwords[0x1]; + u8 reserved_at_5e[0xc]; + u8 reset_state[0x1]; u8 ptpcyc2realtime_modify[0x1]; u8 reserved_at_6c[0x2]; u8 pci_status_and_power[0x1]; @@ -9863,10 +9895,10 @@ struct mlx5_ifc_pcmr_reg_bits { }; struct mlx5_ifc_lane_2_module_mapping_bits { - u8 reserved_at_0[0x6]; - u8 rx_lane[0x2]; - u8 reserved_at_8[0x6]; - u8 tx_lane[0x2]; + u8 reserved_at_0[0x4]; + u8 rx_lane[0x4]; + u8 reserved_at_8[0x4]; + u8 tx_lane[0x4]; u8 reserved_at_10[0x8]; u8 module[0x8]; }; @@ -9875,8 +9907,8 @@ struct mlx5_ifc_bufferx_reg_bits { u8 reserved_at_0[0x6]; u8 lossy[0x1]; u8 epsb[0x1]; - u8 reserved_at_8[0xc]; - u8 size[0xc]; + u8 reserved_at_8[0x8]; + u8 size[0x10]; u8 xoff_threshold[0x10]; u8 xon_threshold[0x10]; @@ -10351,6 +10383,14 @@ struct mlx5_ifc_mcda_reg_bits { }; enum { + MLX5_MFRL_REG_RESET_STATE_IDLE = 0, + MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1, + MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2, + MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3, + MLX5_MFRL_REG_RESET_STATE_NACK = 4, +}; + +enum { MLX5_MFRL_REG_RESET_TYPE_FULL_CHIP = BIT(0), MLX5_MFRL_REG_RESET_TYPE_NET_PORT_ALIVE = BIT(1), }; @@ -10368,7 +10408,8 @@ struct mlx5_ifc_mfrl_reg_bits { u8 pci_sync_for_fw_update_start[0x1]; u8 pci_sync_for_fw_update_resp[0x2]; u8 rst_type_sel[0x3]; - u8 reserved_at_28[0x8]; + u8 reserved_at_28[0x4]; + u8 reset_state[0x4]; u8 reset_type[0x8]; u8 reset_level[0x8]; }; @@ -11494,4 +11535,142 @@ enum { MLX5_MTT_PERM_RW = MLX5_MTT_PERM_READ | MLX5_MTT_PERM_WRITE, }; +enum { + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR = 0x0, + MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER = 0x1, +}; + +struct mlx5_ifc_suspend_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_suspend_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +enum { + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_RESPONDER = 0x0, + MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR = 0x1, +}; + +struct mlx5_ifc_resume_vhca_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_resume_vhca_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_query_vhca_migration_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_query_vhca_migration_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + u8 required_umem_size[0x20]; + + u8 reserved_at_a0[0x160]; +}; + +struct mlx5_ifc_save_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_save_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 actual_image_size[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x10]; + u8 vhca_id[0x10]; + + u8 reserved_at_60[0x20]; + + u8 va[0x40]; + + u8 mkey[0x20]; + + u8 size[0x20]; +}; + +struct mlx5_ifc_load_vhca_state_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 77ea4f9c5265..28a928b0684b 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -56,8 +56,6 @@ enum mlx5_an_status { MLX5_AN_LINK_DOWN = 4, }; -#define MLX5_EEPROM_MAX_BYTES 32 -#define MLX5_EEPROM_IDENTIFIER_BYTE_MASK 0x000000ff #define MLX5_I2C_ADDR_LOW 0x50 #define MLX5_I2C_ADDR_HIGH 0x51 #define MLX5_EEPROM_PAGE_LENGTH 256 diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 61e48d459b23..8bda3ba5b109 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -202,6 +202,9 @@ struct mlx5_wqe_fmr_seg { struct mlx5_wqe_ctrl_seg { __be32 opmod_idx_opcode; __be32 qpn_ds; + + struct_group(trailer, + u8 signature; u8 rsvd[2]; u8 fm_ce_se; @@ -211,6 +214,8 @@ struct mlx5_wqe_ctrl_seg { __be32 umr_mkey; __be32 tis_tir_num; }; + + ); /* end of trailer group */ }; #define MLX5_WQE_CTRL_DS_MASK 0x3f diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..e34edb775334 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3,9 +3,6 @@ #define _LINUX_MM_H #include <linux/errno.h> - -#ifdef __KERNEL__ - #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/bug.h> @@ -26,7 +23,6 @@ #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> -#include <linux/memremap.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> @@ -216,8 +212,10 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +#define folio_page_idx(folio, p) (page_to_pfn(p) - folio_pfn(folio)) #else #define nth_page(page,n) ((page) + (n)) +#define folio_page_idx(folio, p) ((p) - &(folio)->page) #endif /* to align the pointer to the (next) page boundary */ @@ -227,6 +225,10 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +static inline struct folio *lru_to_folio(struct list_head *head) +{ + return list_entry((head)->prev, struct folio, lru); +} void setup_initial_init_mm(void *start_code, void *end_code, void *end_data, void *brk); @@ -424,51 +426,6 @@ extern unsigned int kobjsize(const void *objp); */ extern pgprot_t protection_map[16]; -/** - * enum fault_flag - Fault flag definitions. - * @FAULT_FLAG_WRITE: Fault was a write fault. - * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. - * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. - * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. - * @FAULT_FLAG_TRIED: The fault has been tried once. - * @FAULT_FLAG_USER: The fault originated in userspace. - * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. - * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. - * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. - * - * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify - * whether we would allow page faults to retry by specifying these two - * fault flags correctly. Currently there can be three legal combinations: - * - * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and - * this is the first try - * - * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and - * we've already tried at least once - * - * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry - * - * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never - * be used. Note that page faults can be allowed to retry for multiple times, - * in which case we'll have an initial fault with flags (a) then later on - * continuous faults with flags (b). We should always try to detect pending - * signals before a retry to make sure the continuous page faults can still be - * interrupted if necessary. - */ -enum fault_flag { - FAULT_FLAG_WRITE = 1 << 0, - FAULT_FLAG_MKWRITE = 1 << 1, - FAULT_FLAG_ALLOW_RETRY = 1 << 2, - FAULT_FLAG_RETRY_NOWAIT = 1 << 3, - FAULT_FLAG_KILLABLE = 1 << 4, - FAULT_FLAG_TRIED = 1 << 5, - FAULT_FLAG_USER = 1 << 6, - FAULT_FLAG_REMOTE = 1 << 7, - FAULT_FLAG_INSTRUCTION = 1 << 8, - FAULT_FLAG_INTERRUPTIBLE = 1 << 9, -}; - /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. @@ -523,7 +480,8 @@ struct vm_fault { struct vm_area_struct *vma; /* Target VMA */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ - unsigned long address; /* Faulting virtual address */ + unsigned long address; /* Faulting virtual address - masked */ + unsigned long real_address; /* Faulting virtual address - unmasked */ }; enum fault_flag flags; /* FAULT_FLAG_xxx flags * XXX: should really be 'const' */ @@ -577,6 +535,10 @@ enum page_entry_size { */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); + /** + * @close: Called when the VMA is being removed from the MM. + * Context: User context. May sleep. Caller holds mmap_lock. + */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); @@ -714,6 +676,27 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +static inline unsigned int compound_order(struct page *page) +{ + if (!PageHead(page)) + return 0; + return page[1].compound_order; +} + +/** + * folio_order - The allocation order of a folio. + * @folio: The folio. + * + * A folio is composed of 2^order pages. See get_order() for the definition + * of order. + * + * Return: The order of the folio. + */ +static inline unsigned int folio_order(struct folio *folio) +{ + return compound_order(&folio->page); +} + #include <linux/huge_mm.h> /* @@ -794,21 +777,26 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif -static inline int head_compound_mapcount(struct page *head) +/* + * How many times the entire folio is mapped as a single unit (eg by a + * PMD or PUD entry). This is probably not what you want, except for + * debugging purposes; look at folio_mapcount() or page_mapcount() + * instead. + */ +static inline int folio_entire_mapcount(struct folio *folio) { - return atomic_read(compound_mapcount_ptr(head)) + 1; + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(folio_mapcount_ptr(folio)) + 1; } /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * - * Must be called only for compound pages or any their tail sub-pages. + * Must be called only for compound pages. */ static inline int compound_mapcount(struct page *page) { - VM_BUG_ON_PAGE(!PageCompound(page), page); - page = compound_head(page); - return head_compound_mapcount(page); + return folio_entire_mapcount(page_folio(page)); } /* @@ -838,21 +826,18 @@ static inline int page_mapcount(struct page *page) return atomic_read(&page->_mapcount) + 1; } +int folio_mapcount(struct folio *folio); + #ifdef CONFIG_TRANSPARENT_HUGEPAGE -int total_mapcount(struct page *page); -int page_trans_huge_mapcount(struct page *page, int *total_mapcount); -#else static inline int total_mapcount(struct page *page) { - return page_mapcount(page); + return folio_mapcount(page_folio(page)); } -static inline int page_trans_huge_mapcount(struct page *page, - int *total_mapcount) + +#else +static inline int total_mapcount(struct page *page) { - int mapcount = page_mapcount(page); - if (total_mapcount) - *total_mapcount = mapcount; - return mapcount; + return page_mapcount(page); } #endif @@ -863,6 +848,13 @@ static inline struct page *virt_to_head_page(const void *x) return compound_head(page); } +static inline struct folio *virt_to_folio(const void *x) +{ + struct page *page = virt_to_page(x); + + return page_folio(page); +} + void __put_page(struct page *page); void put_pages_list(struct list_head *pages); @@ -906,54 +898,17 @@ static inline void destroy_compound_page(struct page *page) compound_page_dtors[page[1].compound_dtor](page); } -static inline unsigned int compound_order(struct page *page) -{ - if (!PageHead(page)) - return 0; - return page[1].compound_order; -} - -/** - * folio_order - The allocation order of a folio. - * @folio: The folio. - * - * A folio is composed of 2^order pages. See get_order() for the definition - * of order. - * - * Return: The order of the folio. - */ -static inline unsigned int folio_order(struct folio *folio) -{ - return compound_order(&folio->page); -} - -static inline bool hpage_pincount_available(struct page *page) -{ - /* - * Can the page->hpage_pinned_refcount field be used? That field is in - * the 3rd page of the compound page, so the smallest (2-page) compound - * pages cannot support it. - */ - page = compound_head(page); - return PageCompound(page) && compound_order(page) > 1; -} - static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); } -static inline int compound_pincount(struct page *page) -{ - VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); - page = compound_head(page); - return head_compound_pincount(page); -} - static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; +#ifdef CONFIG_64BIT page[1].compound_nr = 1U << order; +#endif } /* Returns the number of pages in this potentially compound page. */ @@ -961,7 +916,11 @@ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; +#ifdef CONFIG_64BIT return page[1].compound_nr; +#else + return 1UL << compound_order(page); +#endif } /* Returns the number of bytes in this potentially compound page. */ @@ -976,6 +935,37 @@ static inline unsigned int page_shift(struct page *page) return PAGE_SHIFT + compound_order(page); } +/** + * thp_order - Order of a transparent huge page. + * @page: Head page of a transparent huge page. + */ +static inline unsigned int thp_order(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return compound_order(page); +} + +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) +{ + VM_BUG_ON_PGFLAGS(PageTail(page), page); + return compound_nr(page); +} + +/** + * thp_size - Size of a transparent huge page. + * @page: Head page of a transparent huge page. + * + * Return: Number of bytes in this page. + */ +static inline unsigned long thp_size(struct page *page) +{ + return PAGE_SIZE << thp_order(page); +} + void free_compound_page(struct page *page); #ifdef CONFIG_MMU @@ -1127,59 +1117,35 @@ static inline bool is_zone_device_page(const struct page *page) } #endif +static inline bool folio_is_zone_device(const struct folio *folio) +{ + return is_zone_device_page(&folio->page); +} + static inline bool is_zone_movable_page(const struct page *page) { return page_zonenum(page) == ZONE_MOVABLE; } -#ifdef CONFIG_DEV_PAGEMAP_OPS -void free_devmap_managed_page(struct page *page); +#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool page_is_devmap_managed(struct page *page) +bool __put_devmap_managed_page(struct page *page); +static inline bool put_devmap_managed_page(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; - switch (page->pgmap->type) { - case MEMORY_DEVICE_PRIVATE: - case MEMORY_DEVICE_FS_DAX: - return true; - default: - break; - } - return false; + return __put_devmap_managed_page(page); } -void put_devmap_managed_page(struct page *page); - -#else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool page_is_devmap_managed(struct page *page) +#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ +static inline bool put_devmap_managed_page(struct page *page) { return false; } - -static inline void put_devmap_managed_page(struct page *page) -{ -} -#endif /* CONFIG_DEV_PAGEMAP_OPS */ - -static inline bool is_device_private_page(const struct page *page) -{ - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_DEVICE_PRIVATE) && - is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -static inline bool is_pci_p2pdma_page(const struct page *page) -{ - return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && - IS_ENABLED(CONFIG_PCI_P2PDMA) && - is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; -} +#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ @@ -1205,9 +1171,6 @@ static inline void get_page(struct page *page) } bool __must_check try_grab_page(struct page *page, unsigned int flags); -struct page *try_grab_compound_head(struct page *page, int refs, - unsigned int flags); - static inline __must_check bool try_get_page(struct page *page) { @@ -1237,21 +1200,36 @@ static inline void folio_put(struct folio *folio) __put_page(&folio->page); } +/** + * folio_put_refs - Reduce the reference count on a folio. + * @folio: The folio. + * @refs: The amount to subtract from the folio's reference count. + * + * If the folio's reference count reaches zero, the memory will be + * released back to the page allocator and may be used by another + * allocation immediately. Do not access the memory or the struct folio + * after calling folio_put_refs() unless you can be sure that these weren't + * the last references. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folio_put_refs(struct folio *folio, int refs) +{ + if (folio_ref_sub_and_test(folio, refs)) + __put_page(&folio->page); +} + static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); /* - * For devmap managed pages we need to catch refcount transition from - * 2 to 1, when refcount reach one it means the page is free and we - * need to inform the device driver through callback. See - * include/linux/memremap.h and HMM for details. + * For some devmap managed pages we need to catch refcount transition + * from 2 to 1: */ - if (page_is_devmap_managed(&folio->page)) { - put_devmap_managed_page(&folio->page); + if (put_devmap_managed_page(&folio->page)) return; - } - folio_put(folio); } @@ -1281,10 +1259,9 @@ static inline void put_page(struct page *page) * applications that don't have huge page reference counts, this won't be an * issue. * - * Locking: the lockless algorithm described in page_cache_get_speculative() - * and page_cache_gup_pin_speculative() provides safe operation for - * get_user_pages and page_mkclean and other calls that race to set up page - * table entries. + * Locking: the lockless algorithm described in folio_try_get_rcu() + * provides safe operation for get_user_pages(), page_mkclean() and + * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) @@ -1295,70 +1272,11 @@ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); -/** - * page_maybe_dma_pinned - Report if a page is pinned for DMA. - * @page: The page. - * - * This function checks if a page has been pinned via a call to - * a function in the pin_user_pages() family. - * - * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, - * because it means "definitely not pinned for DMA", but true means "probably - * pinned for DMA, but possibly a false positive due to having at least - * GUP_PIN_COUNTING_BIAS worth of normal page references". - * - * False positives are OK, because: a) it's unlikely for a page to get that many - * refcounts, and b) all the callers of this routine are expected to be able to - * deal gracefully with a false positive. - * - * For huge pages, the result will be exactly correct. That's because we have - * more tracking data available: the 3rd struct page in the compound page is - * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS - * scheme). - * - * For more information, please see Documentation/core-api/pin_user_pages.rst. - * - * Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. - */ -static inline bool page_maybe_dma_pinned(struct page *page) -{ - if (hpage_pincount_available(page)) - return compound_pincount(page) > 0; - - /* - * page_ref_count() is signed. If that refcount overflows, then - * page_ref_count() returns a negative value, and callers will avoid - * further incrementing the refcount. - * - * Here, for that overflow case, use the signed bit to count a little - * bit higher via unsigned math, and thus still get an accurate result. - */ - return ((unsigned int)page_ref_count(compound_head(page))) >= - GUP_PIN_COUNTING_BIAS; -} - static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } -/* - * This should most likely only be called during fork() to see whether we - * should break the cow immediately for a page on the src mm. - */ -static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, - struct page *page) -{ - if (!is_cow_mapping(vma->vm_flags)) - return false; - - if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) - return false; - - return page_maybe_dma_pinned(page); -} - #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1524,11 +1442,18 @@ static inline u8 page_kasan_tag(const struct page *page) static inline void page_kasan_tag_set(struct page *page, u8 tag) { - if (kasan_enabled()) { - tag ^= 0xff; - page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); - page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; - } + unsigned long old_flags, flags; + + if (!kasan_enabled()) + return; + + tag ^= 0xff; + old_flags = READ_ONCE(page->flags); + do { + flags = old_flags; + flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); + flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) @@ -1596,6 +1521,74 @@ static inline unsigned long folio_pfn(struct folio *folio) return page_to_pfn(&folio->page); } +static inline atomic_t *folio_pincount_ptr(struct folio *folio) +{ + return &folio_page(folio, 1)->compound_pincount; +} + +/** + * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. + * @folio: The folio. + * + * This function checks if a folio has been pinned via a call to + * a function in the pin_user_pages() family. + * + * For small folios, the return value is partially fuzzy: false is not fuzzy, + * because it means "definitely not pinned for DMA", but true means "probably + * pinned for DMA, but possibly a false positive due to having at least + * GUP_PIN_COUNTING_BIAS worth of normal folio references". + * + * False positives are OK, because: a) it's unlikely for a folio to + * get that many refcounts, and b) all the callers of this routine are + * expected to be able to deal gracefully with a false positive. + * + * For large folios, the result will be exactly correct. That's because + * we have more tracking data available: the compound_pincount is used + * instead of the GUP_PIN_COUNTING_BIAS scheme. + * + * For more information, please see Documentation/core-api/pin_user_pages.rst. + * + * Return: True, if it is likely that the page has been "dma-pinned". + * False, if the page is definitely not dma-pinned. + */ +static inline bool folio_maybe_dma_pinned(struct folio *folio) +{ + if (folio_test_large(folio)) + return atomic_read(folio_pincount_ptr(folio)) > 0; + + /* + * folio_ref_count() is signed. If that refcount overflows, then + * folio_ref_count() returns a negative value, and callers will avoid + * further incrementing the refcount. + * + * Here, for that overflow case, use the sign bit to count a little + * bit higher via unsigned math, and thus still get an accurate result. + */ + return ((unsigned int)folio_ref_count(folio)) >= + GUP_PIN_COUNTING_BIAS; +} + +static inline bool page_maybe_dma_pinned(struct page *page) +{ + return folio_maybe_dma_pinned(page_folio(page)); +} + +/* + * This should most likely only be called during fork() to see whether we + * should break the cow immediately for a page on the src mm. + */ +static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, + struct page *page) +{ + if (!is_cow_mapping(vma->vm_flags)) + return false; + + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) + return false; + + return page_maybe_dma_pinned(page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) @@ -1610,6 +1603,11 @@ static inline bool is_pinnable_page(struct page *page) } #endif +static inline bool folio_is_pinnable(struct folio *folio) +{ + return is_pinnable_page(&folio->page); +} + static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); @@ -1753,8 +1751,12 @@ void page_address_init(void); #define page_address_init() do { } while(0) #endif +static inline void *folio_address(const struct folio *folio) +{ + return page_address(&folio->page); +} + extern void *page_rmapping(struct page *page); -extern struct anon_vma *page_anon_vma(struct page *page); extern pgoff_t __page_file_index(struct page *page); /* @@ -1825,28 +1827,6 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); -/* - * Parameter block passed down to zap_pte_range in exceptional cases. - */ -struct zap_details { - struct address_space *zap_mapping; /* Check page->mapping if set */ - struct page *single_page; /* Locked page to be unmapped */ -}; - -/* - * We set details->zap_mappings when we want to unmap shared but keep private - * pages. Return true if skip zapping this page, false otherwise. - */ -static inline bool -zap_skip_check_mapping(struct zap_details *details, struct page *page) -{ - if (!details || !page) - return false; - - return details->zap_mapping && - (details->zap_mapping != page_rmapping(page)); -} - struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1881,9 +1861,7 @@ extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); -int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); -int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, @@ -1892,7 +1870,6 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); -void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1913,7 +1890,6 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } -static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, @@ -1947,10 +1923,6 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); -long get_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, int *locked); -long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1970,10 +1942,6 @@ int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); -extern int try_to_release_page(struct page * page, gfp_t gfp_mask); -extern void do_invalidatepage(struct page *page, unsigned int offset, - unsigned int length); - bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); @@ -2485,7 +2453,6 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) } extern void __init pagecache_init(void); -extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* @@ -2658,7 +2625,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); @@ -2957,13 +2924,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ -#define FOLL_POPULATE 0x40 /* fault in pages (with FOLL_MLOCK) */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ -#define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ @@ -3167,7 +3132,6 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, #endif void drop_slab(void); -void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 @@ -3184,10 +3148,12 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP int vmemmap_remap_free(unsigned long start, unsigned long end, unsigned long reuse); int vmemmap_remap_alloc(unsigned long start, unsigned long end, unsigned long reuse, gfp_t gfp_mask); +#endif void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, @@ -3220,6 +3186,7 @@ enum mf_flags { MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, + MF_UNPOISON = 1 << 4, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); @@ -3231,6 +3198,19 @@ extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifndef arch_memory_failure +static inline int arch_memory_failure(unsigned long pfn, int flags) +{ + return -ENXIO; +} +#endif + +#ifndef arch_is_platform_page +static inline bool arch_is_platform_page(u64 paddr) +{ + return false; +} +#endif /* * Error handlers for various types of pages. @@ -3247,7 +3227,6 @@ enum mf_action_page_type { MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, - MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_NON_PMD_HUGE, @@ -3262,9 +3241,9 @@ enum mf_action_page_type { MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, - MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, + MF_MSG_DIFFERENT_PAGE_SIZE, MF_MSG_UNKNOWN, }; @@ -3391,5 +3370,16 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) return 0; } -#endif /* __KERNEL__ */ +#ifdef CONFIG_ANON_VMA_NAME +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, + struct anon_vma_name *anon_name); +#else +static inline int +madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, struct anon_vma_name *anon_name) { + return 0; +} +#endif + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_api.h b/include/linux/mm_api.h new file mode 100644 index 000000000000..a5ace2b198b8 --- /dev/null +++ b/include/linux/mm_api.h @@ -0,0 +1 @@ +#include <linux/mm.h> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e2ec68b0515c..ac32125745ab 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,8 +2,10 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/swap.h> +#include <linux/string.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -97,7 +99,8 @@ void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); - list_add(&folio->lru, &lruvec->lists[lru]); + if (lru != LRU_UNEVICTABLE) + list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list(struct page *page, @@ -113,6 +116,7 @@ void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); + /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } @@ -125,8 +129,11 @@ static __always_inline void add_page_to_lru_list_tail(struct page *page, static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { - list_del(&folio->lru); - update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio), + enum lru_list lru = folio_lru_list(folio); + + if (lru != LRU_UNEVICTABLE) + list_del(&folio->lru); + update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } @@ -135,4 +142,179 @@ static __always_inline void del_page_from_lru_list(struct page *page, { lruvec_del_folio(lruvec, page_folio(page)); } + +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling anon_vma_name(). Caller should + * either keep holding the lock while using the returned pointer or it should + * raise anon_vma_name refcount before releasing the lock. + */ +extern struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); +extern struct anon_vma_name *anon_vma_name_alloc(const char *name); +extern void anon_vma_name_free(struct kref *kref); + +/* mmap_lock should be read-locked */ +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) +{ + if (anon_name) + kref_get(&anon_name->kref); +} + +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) +{ + if (anon_name) + kref_put(&anon_name->kref, anon_vma_name_free); +} + +static inline +struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) +{ + /* Prevent anon_name refcount saturation early on */ + if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { + anon_vma_name_get(anon_name); + return anon_name; + + } + return anon_vma_name_alloc(anon_name->name); +} + +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + struct anon_vma_name *anon_name = anon_vma_name(orig_vma); + + if (anon_name) + new_vma->anon_name = anon_vma_name_reuse(anon_name); +} + +static inline void free_anon_vma_name(struct vm_area_struct *vma) +{ + /* + * Not using anon_vma_name because it generates a warning if mmap_lock + * is not held, which might be the case here. + */ + if (!vma->vm_file) + anon_vma_name_put(vma->anon_name); +} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + if (anon_name1 == anon_name2) + return true; + + return anon_name1 && anon_name2 && + !strcmp(anon_name1->name, anon_name2->name); +} + +#else /* CONFIG_ANON_VMA_NAME */ +static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) +{ + return NULL; +} + +static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + return NULL; +} + +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_anon_vma_name(struct vm_area_struct *vma) {} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + return true; +} + +#endif /* CONFIG_ANON_VMA_NAME */ + +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); + /* + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. + */ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c3a6e6209600..8834e38c06a4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -5,6 +5,7 @@ #include <linux/mm_types_task.h> #include <linux/auxvec.h> +#include <linux/kref.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> @@ -56,11 +57,11 @@ struct mem_cgroup; * in each subpage, but you may need to restore some of their values * afterwards. * - * SLUB uses cmpxchg_double() to atomically update its freelist and - * counters. That requires that freelist & counters be adjacent and - * double-word aligned. We align all struct pages to double-word - * boundaries, and ensure that 'freelist' is aligned within the - * struct. + * SLUB uses cmpxchg_double() to atomically update its freelist and counters. + * That requires that freelist & counters in struct slab be adjacent and + * double-word aligned. Because struct slab currently just reinterprets the + * bits of struct page, we align all struct pages to double-word boundaries, + * and ensure that 'freelist' is aligned within struct slab. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) @@ -84,7 +85,16 @@ struct page { * lruvec->lru_lock. Sometimes used as a generic list * by the page owner. */ - struct list_head lru; + union { + struct list_head lru; + /* Or, for the Unevictable "LRU list" slot */ + struct { + /* Always even, to negate PageTail */ + void *__filler; + /* Count page's or folio's mlocks */ + unsigned int mlock_count; + }; + }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ @@ -118,31 +128,6 @@ struct page { atomic_long_t pp_frag_count; }; }; - struct { /* slab, slob and slub */ - union { - struct list_head slab_list; - struct { /* Partial pages */ - struct page *next; -#ifdef CONFIG_64BIT - int pages; /* Nr of pages left */ -#else - short int pages; -#endif - }; - }; - struct kmem_cache *slab_cache; /* not slob */ - /* Double-word boundary */ - void *freelist; /* first free object */ - union { - void *s_mem; /* slab: first object */ - unsigned long counters; /* SLUB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; - }; - }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ @@ -150,11 +135,14 @@ struct page { unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; + atomic_t compound_pincount; +#ifdef CONFIG_64BIT unsigned int compound_nr; /* 1 << compound_order */ +#endif }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ - atomic_t hpage_pinned_refcount; + unsigned long _compound_pad_2; /* For both global and memcg */ struct list_head deferred_list; }; @@ -206,9 +194,6 @@ struct page { * which are currently stored here. */ unsigned int page_type; - - unsigned int active; /* SLAB */ - int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ @@ -268,7 +253,13 @@ struct folio { struct { /* public: */ unsigned long flags; - struct list_head lru; + union { + struct list_head lru; + struct { + void *__filler; + unsigned int mlock_count; + }; + }; struct address_space *mapping; pgoff_t index; void *private; @@ -288,6 +279,7 @@ static_assert(sizeof(struct page) == sizeof(struct folio)); static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); +FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); @@ -311,7 +303,7 @@ static inline atomic_t *compound_mapcount_ptr(struct page *page) static inline atomic_t *compound_pincount_ptr(struct page *page) { - return &page[2].hpage_pinned_refcount; + return &page[1].compound_pincount; } /* @@ -386,6 +378,12 @@ struct vm_userfaultfd_ctx { struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ +struct anon_vma_name { + struct kref kref; + /* The name needs to be at the end because it is dynamically sized. */ + char name[]; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -426,11 +424,22 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * containing the name given to the vma, or NULL if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* + * Serialized by mmap_sem. Never use directly because it is + * valid only when vm_file is NULL. Use anon_vma_name instead. + */ + struct anon_vma_name *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -632,7 +641,7 @@ struct mm_struct { atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT @@ -643,7 +652,7 @@ struct mm_struct { #endif struct work_struct async_put_work; -#ifdef CONFIG_IOMMU_SUPPORT +#ifdef CONFIG_IOMMU_SVA u32 pasid; #endif } __randomize_layout; @@ -677,90 +686,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); -static inline void init_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_set(&mm->tlb_flush_pending, 0); -} - -static inline void inc_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_inc(&mm->tlb_flush_pending); - /* - * The only time this value is relevant is when there are indeed pages - * to flush. And we'll only flush pages after changing them, which - * requires the PTL. - * - * So the ordering here is: - * - * atomic_inc(&mm->tlb_flush_pending); - * spin_lock(&ptl); - * ... - * set_pte_at(); - * spin_unlock(&ptl); - * - * spin_lock(&ptl) - * mm_tlb_flush_pending(); - * .... - * spin_unlock(&ptl); - * - * flush_tlb_range(); - * atomic_dec(&mm->tlb_flush_pending); - * - * Where the increment if constrained by the PTL unlock, it thus - * ensures that the increment is visible if the PTE modification is - * visible. After all, if there is no PTE modification, nobody cares - * about TLB flushes either. - * - * This very much relies on users (mm_tlb_flush_pending() and - * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and - * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc - * locks (PPC) the unlock of one doesn't order against the lock of - * another PTL. - * - * The decrement is ordered by the flush_tlb_range(), such that - * mm_tlb_flush_pending() will not return false unless all flushes have - * completed. - */ -} - -static inline void dec_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * See inc_tlb_flush_pending(). - * - * This cannot be smp_mb__before_atomic() because smp_mb() simply does - * not order against TLB invalidate completion, which is what we need. - * - * Therefore we must rely on tlb_flush_*() to guarantee order. - */ - atomic_dec(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * Must be called after having acquired the PTL; orders against that - * PTLs release and therefore ensures that if we observe the modified - * PTE we must also observe the increment from inc_tlb_flush_pending(). - * - * That is, it only guarantees to return true if there is a flush - * pending for _this_ PTL. - */ - return atomic_read(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) -{ - /* - * Similar to mm_tlb_flush_pending(), we must have acquired the PTL - * for which there is a TLB flush pending in order to guarantee - * we've seen both that PTE modification and the increment. - * - * (no requirement on actually still holding the PTL, that is irrelevant) - */ - return atomic_read(&mm->tlb_flush_pending) > 1; -} - struct vm_fault; /** @@ -875,4 +800,49 @@ typedef struct { unsigned long val; } swp_entry_t; +/** + * enum fault_flag - Fault flag definitions. + * @FAULT_FLAG_WRITE: Fault was a write fault. + * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. + * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. + * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. + * @FAULT_FLAG_TRIED: The fault has been tried once. + * @FAULT_FLAG_USER: The fault originated in userspace. + * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. + * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. + * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * + * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify + * whether we would allow page faults to retry by specifying these two + * fault flags correctly. Currently there can be three legal combinations: + * + * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and + * this is the first try + * + * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and + * we've already tried at least once + * + * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry + * + * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never + * be used. Note that page faults can be allowed to retry for multiple times, + * in which case we'll have an initial fault with flags (a) then later on + * continuous faults with flags (b). We should always try to detect pending + * signals before a retry to make sure the continuous page faults can still be + * interrupted if necessary. + */ +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index a85c9f0bd470..53f0efa0bccf 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -105,6 +105,7 @@ #define SDIO_VENDOR_ID_MEDIATEK 0x037a #define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 #define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 +#define SDIO_DEVICE_ID_MEDIATEK_MT7961 0x7961 #define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 #define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 58e744b78c2c..962b14d403e8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -83,6 +83,17 @@ static inline bool is_migrate_movable(int mt) return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } +/* + * Check whether a migratetype can be merged with another migratetype. + * + * It is only mergeable when it can fall back to other migratetypes for + * allocation. See fallbacks[MIGRATE_TYPES][3] in page_alloc.c. + */ +static inline bool migratetype_is_mergeable(int mt) +{ + return mt < MIGRATE_PCPTYPES; +} + #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) @@ -211,6 +222,9 @@ enum node_stat_item { #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif +#ifdef CONFIG_NUMA_BALANCING + PGPROMOTE_SUCCESS, /* promote successfully */ +#endif NR_VM_NODE_STAT_ITEMS }; @@ -277,6 +291,7 @@ enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, + VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; @@ -338,6 +353,7 @@ enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, + WMARK_PROMO, NR_WMARK }; @@ -919,12 +935,6 @@ typedef struct pglist_data { #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) -#ifdef CONFIG_FLATMEM -#define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) -#else -#define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) -#endif -#define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) @@ -1046,6 +1056,15 @@ static inline int is_highmem_idx(enum zone_type idx) #endif } +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); +#else +static inline bool has_managed_dma(void) +{ + return false; +} +#endif + /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references @@ -1091,7 +1110,6 @@ static inline struct pglist_data *NODE_DATA(int nid) { return &contig_page_data; } -#define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NUMA */ diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h new file mode 100644 index 000000000000..ee5a217de2a8 --- /dev/null +++ b/include/linux/mnt_idmapping.h @@ -0,0 +1,234 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MNT_IDMAPPING_H +#define _LINUX_MNT_IDMAPPING_H + +#include <linux/types.h> +#include <linux/uidgid.h> + +struct user_namespace; +/* + * Carries the initial idmapping of 0:0:4294967295 which is an identity + * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is + * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. + */ +extern struct user_namespace init_user_ns; + +/** + * initial_idmapping - check whether this is the initial mapping + * @ns: idmapping to check + * + * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, + * [...], 1000 to 1000 [...]. + * + * Return: true if this is the initial mapping, false if not. + */ +static inline bool initial_idmapping(const struct user_namespace *ns) +{ + return ns == &init_user_ns; +} + +/** + * no_idmapping - check whether we can skip remapping a kuid/gid + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * This function can be used to check whether a remapping between two + * idmappings is required. + * An idmapped mount is a mount that has an idmapping attached to it that + * is different from the filsystem's idmapping and the initial idmapping. + * If the initial mapping is used or the idmapping of the mount and the + * filesystem are identical no remapping is required. + * + * Return: true if remapping can be skipped, false if not. + */ +static inline bool no_idmapping(const struct user_namespace *mnt_userns, + const struct user_namespace *fs_userns) +{ + return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; +} + +/** + * mapped_kuid_fs - map a filesystem kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kuid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * from_kuid() so we can simply retrieve the value via __kuid_val() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + if (initial_idmapping(fs_userns)) + uid = __kuid_val(kuid); + else + uid = from_kuid(fs_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + return make_kuid(mnt_userns, uid); +} + +/** + * mapped_kgid_fs - map a filesystem kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kgid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * from_kgid() so we can simply retrieve the value via __kgid_val() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + if (initial_idmapping(fs_userns)) + gid = __kgid_val(kgid); + else + gid = from_kgid(fs_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + return make_kgid(mnt_userns, gid); +} + +/** + * mapped_kuid_user - map a user kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kuid into @fs_userns. Use this + * function when preparing a @kuid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * make_kuid() so we can simply retrieve the value via KUIDT_INIT() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + uid = from_kuid(mnt_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + if (initial_idmapping(fs_userns)) + return KUIDT_INIT(uid); + return make_kuid(fs_userns, uid); +} + +/** + * mapped_kgid_user - map a user kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kgid into @fs_userns. Use this + * function when preparing a @kgid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * make_kgid() so we can simply retrieve the value via KGIDT_INIT() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + gid = from_kgid(mnt_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + if (initial_idmapping(fs_userns)) + return KGIDT_INIT(gid); + return make_kgid(fs_userns, gid); +} + +/** + * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsuid. A common example is initializing the i_uid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsuid mapped up according to @mnt_userns. + */ +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) +{ + return mapped_kuid_user(mnt_userns, fs_userns, current_fsuid()); +} + +/** + * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsgid. A common example is initializing the i_gid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsgid mapped up according to @mnt_userns. + */ +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) +{ + return mapped_kgid_user(mnt_userns, fs_userns, current_fsgid()); +} + +#endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 4bb71979a8fd..5da5d990ff58 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -211,7 +211,7 @@ struct css_device_id { kernel_ulong_t driver_data; }; -#define ACPI_ID_LEN 9 +#define ACPI_ID_LEN 16 struct acpi_device_id { __u8 id[ACPI_ID_LEN]; diff --git a/include/linux/module.h b/include/linux/module.h index c9f1200b2312..1e135fd5c076 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -290,7 +290,8 @@ extern typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) +#define _MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) +#define MODULE_IMPORT_NS(ns) _MODULE_IMPORT_NS(ns) struct notifier_block; @@ -595,9 +596,9 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -extern void __noreturn __module_put_and_exit(struct module *mod, +extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); -#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) +#define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); @@ -790,7 +791,7 @@ static inline int unregister_module_notifier(struct notifier_block *nb) return 0; } -#define module_put_and_exit(code) do_exit(code) +#define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { diff --git a/include/linux/mount.h b/include/linux/mount.h index 5d92a7e1a742..7f18a7555dff 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -113,9 +113,6 @@ extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); - -extern unsigned int sysctl_mount_max; - extern bool path_is_mountpoint(const struct path *path); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 8071148f29a6..e05ee9f001ff 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -12,6 +12,7 @@ /** * struct vif_device - interface representor for multicast routing * @dev: network device being used + * @dev_tracker: refcount tracker for @dev reference * @bytes_in: statistic; bytes ingressing * @bytes_out: statistic; bytes egresing * @pkt_in: statistic; packets ingressing @@ -26,6 +27,7 @@ */ struct vif_device { struct net_device *dev; + netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; unsigned long rate_limit; diff --git a/include/linux/msi.h b/include/linux/msi.h index e616f94c7c58..fc918a658d48 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -2,7 +2,23 @@ #ifndef LINUX_MSI_H #define LINUX_MSI_H -#include <linux/kobject.h> +/* + * This header file contains MSI data structures and functions which are + * only relevant for: + * - Interrupt core code + * - PCI/MSI core code + * - MSI interrupt domain implementations + * - IOMMU, low level VFIO, NTB and other justified exceptions + * dealing with low level MSI details. + * + * Regular device drivers have no business with any of these functions and + * especially storing MSI descriptor pointers in random code is considered + * abuse. The only function which is relevant for drivers is msi_get_virq(). + */ + +#include <linux/cpumask.h> +#include <linux/xarray.h> +#include <linux/mutex.h> #include <linux/list.h> #include <asm/msi.h> @@ -56,6 +72,8 @@ struct irq_data; struct msi_desc; struct pci_dev; struct platform_msi_priv_data; +struct device_attribute; + void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); @@ -69,62 +87,59 @@ typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, struct msi_msg *msg); /** - * platform_msi_desc - Platform device specific msi descriptor data - * @msi_priv_data: Pointer to platform private data - * @msi_index: The index of the MSI descriptor for multi MSI - */ -struct platform_msi_desc { - struct platform_msi_priv_data *msi_priv_data; - u16 msi_index; -}; - -/** - * fsl_mc_msi_desc - FSL-MC device specific msi descriptor data - * @msi_index: The index of the MSI descriptor + * pci_msi_desc - PCI/MSI specific MSI descriptor data + * + * @msi_mask: [PCI MSI] MSI cached mask bits + * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits + * @is_msix: [PCI MSI/X] True if MSI-X + * @multiple: [PCI MSI/X] log2 num of messages allocated + * @multi_cap: [PCI MSI/X] log2 num of messages supported + * @can_mask: [PCI MSI/X] Masking supported? + * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit + * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq + * @mask_pos: [PCI MSI] Mask register position + * @mask_base: [PCI MSI-X] Mask register base address */ -struct fsl_mc_msi_desc { - u16 msi_index; +struct pci_msi_desc { + union { + u32 msi_mask; + u32 msix_ctrl; + }; + struct { + u8 is_msix : 1; + u8 multiple : 3; + u8 multi_cap : 3; + u8 can_mask : 1; + u8 is_64 : 1; + u8 is_virtual : 1; + unsigned default_irq; + } msi_attrib; + union { + u8 mask_pos; + void __iomem *mask_base; + }; }; -/** - * ti_sci_inta_msi_desc - TISCI based INTA specific msi descriptor data - * @dev_index: TISCI device index - */ -struct ti_sci_inta_msi_desc { - u16 dev_index; -}; +#define MSI_MAX_INDEX ((unsigned int)USHRT_MAX) /** * struct msi_desc - Descriptor structure for MSI based interrupts - * @list: List head for management * @irq: The base interrupt number * @nvec_used: The number of vectors used * @dev: Pointer to the device which uses this descriptor * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor + * @sysfs_attr: Pointer to sysfs device attribute * * @write_msi_msg: Callback that may be called when the MSI message * address or data changes * @write_msi_msg_data: Data parameter for the callback. * - * @msi_mask: [PCI MSI] MSI cached mask bits - * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits - * @is_msix: [PCI MSI/X] True if MSI-X - * @multiple: [PCI MSI/X] log2 num of messages allocated - * @multi_cap: [PCI MSI/X] log2 num of messages supported - * @maskbit: [PCI MSI/X] Mask-Pending bit supported? - * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit - * @entry_nr: [PCI MSI/X] Entry which is described by this descriptor - * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq - * @mask_pos: [PCI MSI] Mask register position - * @mask_base: [PCI MSI-X] Mask register base address - * @platform: [platform] Platform device specific msi descriptor data - * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data - * @inta: [INTA] TISCI based INTA specific msi descriptor data + * @msi_index: Index of the msi descriptor + * @pci: PCI specific msi descriptor data */ struct msi_desc { /* Shared device/bus type independent data */ - struct list_head list; unsigned int irq; unsigned int nvec_used; struct device *dev; @@ -133,61 +148,71 @@ struct msi_desc { #ifdef CONFIG_IRQ_MSI_IOMMU const void *iommu_cookie; #endif +#ifdef CONFIG_SYSFS + struct device_attribute *sysfs_attrs; +#endif void (*write_msi_msg)(struct msi_desc *entry, void *data); void *write_msi_msg_data; - union { - /* PCI MSI/X specific data */ - struct { - union { - u32 msi_mask; - u32 msix_ctrl; - }; - struct { - u8 is_msix : 1; - u8 multiple : 3; - u8 multi_cap : 3; - u8 can_mask : 1; - u8 is_64 : 1; - u8 is_virtual : 1; - u16 entry_nr; - unsigned default_irq; - } msi_attrib; - union { - u8 mask_pos; - void __iomem *mask_base; - }; - }; - - /* - * Non PCI variants add their data structure here. New - * entries need to use a named structure. We want - * proper name spaces for this. The PCI part is - * anonymous for now as it would require an immediate - * tree wide cleanup. - */ - struct platform_msi_desc platform; - struct fsl_mc_msi_desc fsl_mc; - struct ti_sci_inta_msi_desc inta; - }; + u16 msi_index; + struct pci_msi_desc pci; +}; + +/* + * Filter values for the MSI descriptor iterators and accessor functions. + */ +enum msi_desc_filter { + /* All descriptors */ + MSI_DESC_ALL, + /* Descriptors which have no interrupt associated */ + MSI_DESC_NOTASSOCIATED, + /* Descriptors which have an interrupt associated */ + MSI_DESC_ASSOCIATED, }; -/* Helpers to hide struct msi_desc implementation details */ +/** + * msi_device_data - MSI per device data + * @properties: MSI properties which are interesting to drivers + * @platform_data: Platform-MSI specific data + * @mutex: Mutex protecting the MSI descriptor store + * @__store: Xarray for storing MSI descriptor pointers + * @__iter_idx: Index to search the next entry for iterators + */ +struct msi_device_data { + unsigned long properties; + struct platform_msi_priv_data *platform_data; + struct mutex mutex; + struct xarray __store; + unsigned long __iter_idx; +}; + +int msi_setup_device_data(struct device *dev); + +unsigned int msi_get_virq(struct device *dev, unsigned int index); +void msi_lock_descs(struct device *dev); +void msi_unlock_descs(struct device *dev); + +struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter); +struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); + +/** + * msi_for_each_desc - Iterate the MSI descriptors + * + * @desc: struct msi_desc pointer used as iterator + * @dev: struct device pointer - device to iterate + * @filter: Filter for descriptor selection + * + * Notes: + * - The loop must be protected with a msi_lock_descs()/msi_unlock_descs() + * pair. + * - It is safe to remove a retrieved MSI descriptor in the loop. + */ +#define msi_for_each_desc(desc, dev, filter) \ + for ((desc) = msi_first_desc((dev), (filter)); (desc); \ + (desc) = msi_next_desc((dev), (filter))) + #define msi_desc_to_dev(desc) ((desc)->dev) -#define dev_to_msi_list(dev) (&(dev)->msi_list) -#define first_msi_entry(dev) \ - list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list) -#define for_each_msi_entry(desc, dev) \ - list_for_each_entry((desc), dev_to_msi_list((dev)), list) -#define for_each_msi_entry_safe(desc, tmp, dev) \ - list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list) -#define for_each_msi_vector(desc, __irq, dev) \ - for_each_msi_entry((desc), (dev)) \ - if ((desc)->irq) \ - for (__irq = (desc)->irq; \ - __irq < ((desc)->irq + (desc)->nvec_used); \ - __irq++) #ifdef CONFIG_IRQ_MSI_IOMMU static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) @@ -213,36 +238,33 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, #endif #ifdef CONFIG_PCI_MSI -#define first_pci_msi_entry(pdev) first_msi_entry(&(pdev)->dev) -#define for_each_pci_msi_entry(desc, pdev) \ - for_each_msi_entry((desc), &(pdev)->dev) - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); -void *msi_desc_to_pci_sysdata(struct msi_desc *desc); void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); #else /* CONFIG_PCI_MSI */ -static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc) -{ - return NULL; -} static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) { } #endif /* CONFIG_PCI_MSI */ -struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, - const struct irq_affinity_desc *affinity); -void free_msi_entry(struct msi_desc *entry); +int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); +void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, + unsigned int first_index, unsigned int last_index); + +/** + * msi_free_msi_descs - Free MSI descriptors of a device + * @dev: Device to free the descriptors + */ +static inline void msi_free_msi_descs(struct device *dev) +{ + msi_free_msi_descs_range(dev, MSI_DESC_ALL, 0, MSI_MAX_INDEX); +} + void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -const struct attribute_group **msi_populate_sysfs(struct device *dev); -void msi_destroy_sysfs(struct device *dev, - const struct attribute_group **msi_irq_groups); - /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific @@ -256,25 +278,20 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -#else -static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - WARN_ON_ONCE(1); - return -ENODEV; -} - -static inline void arch_teardown_msi_irqs(struct pci_dev *dev) -{ - WARN_ON_ONCE(1); -} -#endif +#ifdef CONFIG_SYSFS +int msi_device_populate_sysfs(struct device *dev); +void msi_device_destroy_sysfs(struct device *dev); +#else /* CONFIG_SYSFS */ +static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } +static inline void msi_device_destroy_sysfs(struct device *dev) { } +#endif /* !CONFIG_SYSFS */ +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* - * The restore hooks are still available as they are useful even - * for fully irq domain based setups. Courtesy to XEN/X86. + * The restore hook is still available even for fully irq domain based + * setups. Courtesy to XEN/X86. */ -void arch_restore_msi_irqs(struct pci_dev *dev); -void default_restore_msi_irqs(struct pci_dev *dev); +bool arch_restore_msi_irqs(struct pci_dev *dev); #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN @@ -294,20 +311,17 @@ struct msi_domain_info; * @msi_free: Domain specific function to free a MSI interrupts * @msi_check: Callback for verification of the domain/info/dev data * @msi_prepare: Prepare the allocation of the interrupts in the domain - * @msi_finish: Optional callback to finalize the allocation * @set_desc: Set the msi descriptor for an interrupt - * @handle_error: Optional error handler if the allocation fails * @domain_alloc_irqs: Optional function to override the default allocation * function. * @domain_free_irqs: Optional function to override the default free * function. * - * @get_hwirq, @msi_init and @msi_free are callbacks used by - * msi_create_irq_domain() and related interfaces + * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying + * irqdomain. * - * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error - * are callbacks used by msi_domain_alloc_irqs() and related - * interfaces which are based on msi_desc. + * @msi_check, @msi_prepare and @set_desc are callbacks used by + * msi_domain_alloc/free_irqs(). * * @domain_alloc_irqs, @domain_free_irqs can be used to override the * default allocation/free functions (__msi_domain_alloc/free_irqs). This @@ -341,11 +355,8 @@ struct msi_domain_ops { int (*msi_prepare)(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg); - void (*msi_finish)(msi_alloc_info_t *arg, int retval); void (*set_desc)(msi_alloc_info_t *arg, struct msi_desc *desc); - int (*handle_error)(struct irq_domain *domain, - struct msi_desc *desc, int error); int (*domain_alloc_irqs)(struct irq_domain *domain, struct device *dev, int nvec); void (*domain_free_irqs)(struct irq_domain *domain, @@ -399,6 +410,14 @@ enum { MSI_FLAG_MUST_REACTIVATE = (1 << 5), /* Is level-triggered capable, using two messages */ MSI_FLAG_LEVEL_CAPABLE = (1 << 6), + /* Populate sysfs on alloc() and destroy it on free() */ + MSI_FLAG_DEV_SYSFS = (1 << 7), + /* MSI-X entries must be contiguous */ + MSI_FLAG_MSIX_CONTIGUOUS = (1 << 8), + /* Allocate simple MSI descriptors */ + MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 9), + /* Free MSI descriptors */ + MSI_FLAG_FREE_MSI_DESCS = (1 << 10), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, @@ -409,9 +428,12 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct irq_domain *parent); int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); +int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, + int nvec); int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); +void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev); void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); @@ -440,20 +462,17 @@ __platform_msi_create_device_domain(struct device *dev, #define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) -int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs); -void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nvec); +int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, struct device *dev); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); diff --git a/include/linux/mtd/latch-addr-flash.h b/include/linux/mtd/latch-addr-flash.h deleted file mode 100644 index e94b8e128074..000000000000 --- a/include/linux/mtd/latch-addr-flash.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Interface for NOR flash driver whose high address lines are latched - * - * Copyright © 2008 MontaVista Software, Inc. <source@mvista.com> - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ -#ifndef __LATCH_ADDR_FLASH__ -#define __LATCH_ADDR_FLASH__ - -struct map_info; -struct mtd_partition; - -struct latch_addr_flash_data { - unsigned int width; - unsigned int size; - - int (*init)(void *data, int cs); - void (*done)(void *data); - void (*set_window)(unsigned long offset, void *data); - void *data; - - unsigned int nr_parts; - struct mtd_partition *parts; -}; - -#endif diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f5e7dfc2e4e9..151607e9d64a 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -188,9 +188,6 @@ struct module; /* only needed for owner field in mtd_info */ */ struct mtd_debug_info { struct dentry *dfs_dir; - - const char *partname; - const char *partid; }; /** @@ -711,4 +708,11 @@ static inline int mtd_is_bitflip_or_eccerr(int err) { unsigned mtd_mmap_capabilities(struct mtd_info *mtd); +#ifdef CONFIG_DEBUG_FS +bool mtd_check_expert_analysis_mode(void); +#else +static inline bool mtd_check_expert_analysis_mode(void) { return false; } +#endif + + #endif /* __MTD_MTD_H__ */ diff --git a/include/linux/mtd/nand-ecc-mxic.h b/include/linux/mtd/nand-ecc-mxic.h new file mode 100644 index 000000000000..b125926e458c --- /dev/null +++ b/include/linux/mtd/nand-ecc-mxic.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright © 2019 Macronix + * Author: Miquèl Raynal <miquel.raynal@bootlin.com> + * + * Header for the Macronix external ECC engine. + */ + +#ifndef __MTD_NAND_ECC_MXIC_H__ +#define __MTD_NAND_ECC_MXIC_H__ + +#include <linux/platform_device.h> +#include <linux/device.h> + +struct mxic_ecc_engine; + +#if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) && IS_REACHABLE(CONFIG_MTD_NAND_CORE) + +struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void); +struct nand_ecc_engine *mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev); +void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng); +int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, + unsigned int direction, dma_addr_t dirmap); + +#else /* !CONFIG_MTD_NAND_ECC_MXIC */ + +static inline struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void) +{ + return NULL; +} + +static inline struct nand_ecc_engine * +mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng) {} + +static inline int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng, + unsigned int direction, + dma_addr_t dirmap) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_MTD_NAND_ECC_MXIC */ + +#endif /* __MTD_NAND_ECC_MXIC_H__ */ diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 32fc7edf65b3..c3693bb87b4c 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -264,11 +264,35 @@ struct nand_ecc_engine_ops { }; /** + * enum nand_ecc_engine_integration - How the NAND ECC engine is integrated + * @NAND_ECC_ENGINE_INTEGRATION_INVALID: Invalid value + * @NAND_ECC_ENGINE_INTEGRATION_PIPELINED: Pipelined engine, performs on-the-fly + * correction, does not need to copy + * data around + * @NAND_ECC_ENGINE_INTEGRATION_EXTERNAL: External engine, needs to bring the + * data into its own area before use + */ +enum nand_ecc_engine_integration { + NAND_ECC_ENGINE_INTEGRATION_INVALID, + NAND_ECC_ENGINE_INTEGRATION_PIPELINED, + NAND_ECC_ENGINE_INTEGRATION_EXTERNAL, +}; + +/** * struct nand_ecc_engine - ECC engine abstraction for NAND devices + * @dev: Host device + * @node: Private field for registration time * @ops: ECC engine operations + * @integration: How the engine is integrated with the host + * (only relevant on %NAND_ECC_ENGINE_TYPE_ON_HOST engines) + * @priv: Private data */ struct nand_ecc_engine { + struct device *dev; + struct list_head node; struct nand_ecc_engine_ops *ops; + enum nand_ecc_engine_integration integration; + void *priv; }; void of_get_nand_ecc_user_config(struct nand_device *nand); @@ -279,8 +303,28 @@ int nand_ecc_prepare_io_req(struct nand_device *nand, int nand_ecc_finish_io_req(struct nand_device *nand, struct nand_page_io_req *req); bool nand_ecc_is_strong_enough(struct nand_device *nand); + +#if IS_REACHABLE(CONFIG_MTD_NAND_CORE) +int nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine); +int nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine); +#else +static inline int +nand_ecc_register_on_host_hw_engine(struct nand_ecc_engine *engine) +{ + return -ENOTSUPP; +} +static inline int +nand_ecc_unregister_on_host_hw_engine(struct nand_ecc_engine *engine) +{ + return -ENOTSUPP; +} +#endif + struct nand_ecc_engine *nand_ecc_get_sw_engine(struct nand_device *nand); struct nand_ecc_engine *nand_ecc_get_on_die_hw_engine(struct nand_device *nand); +struct nand_ecc_engine *nand_ecc_get_on_host_hw_engine(struct nand_device *nand); +void nand_ecc_put_on_host_hw_engine(struct nand_device *nand); +struct device *nand_ecc_get_engine_dev(struct device *host); #if IS_ENABLED(CONFIG_MTD_NAND_ECC_SW_HAMMING) struct nand_ecc_engine *nand_ecc_sw_hamming_get_engine(void); @@ -962,6 +1006,11 @@ int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos); int nanddev_ecc_engine_init(struct nand_device *nand); void nanddev_ecc_engine_cleanup(struct nand_device *nand); +static inline void *nand_to_ecc_ctx(struct nand_device *nand) +{ + return nand->ecc.ctx.priv; +} + /* BBT related functions */ enum nand_bbt_block_status { NAND_BBT_BLOCK_STATUS_UNKNOWN, diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b2f9dd3cbd69..dcf90144d70b 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1240,6 +1240,7 @@ struct nand_secure_region { * @lock: Lock protecting the suspended field. Also used to serialize accesses * to the NAND device * @suspended: Set to 1 when the device is suspended, 0 when it's not + * @resume_wq: wait queue to sleep if rawnand is in suspended state. * @cur_cs: Currently selected target. -1 means no target selected, otherwise we * should always have cur_cs >= 0 && cur_cs < nanddev_ntargets(). * NAND Controller drivers should not modify this value, but they're @@ -1294,6 +1295,7 @@ struct nand_chip { /* Internals */ struct mutex lock; unsigned int suspended : 1; + wait_queue_head_t resume_wq; int cur_cs; int read_retries; struct nand_secure_region *secure_regions; @@ -1539,6 +1541,8 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit, bool check_only); int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); +int nand_read_page_hwecc_oob_first(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); /* Scan and identify a NAND device */ int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index f67457748ed8..5e25a7b75ae2 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -47,8 +47,6 @@ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ #define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ -#define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ -#define SPINOR_OP_CLFSR 0x50 /* Clear flag status register */ #define SPINOR_OP_RDEAR 0xc8 /* Read Extended Address Register */ #define SPINOR_OP_WREAR 0xc5 /* Write Extended Address Register */ #define SPINOR_OP_SRSTEN 0x66 /* Software Reset Enable */ @@ -86,22 +84,12 @@ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ -/* Used for S3AN flashes only */ -#define SPINOR_OP_XSE 0x50 /* Sector erase */ -#define SPINOR_OP_XPP 0x82 /* Page program */ -#define SPINOR_OP_XRDSR 0xd7 /* Read status register */ - -#define XSR_PAGESIZE BIT(0) /* Page size in Po2 or Linear */ -#define XSR_RDY BIT(7) /* Ready */ - - /* Used for Macronix and Winbond flashes. */ #define SPINOR_OP_EN4B 0xb7 /* Enter 4-byte mode */ #define SPINOR_OP_EX4B 0xe9 /* Exit 4-byte mode */ /* Used for Spansion flashes only. */ #define SPINOR_OP_BRWR 0x17 /* Bank register write */ -#define SPINOR_OP_CLSR 0x30 /* Clear status register 1 */ /* Used for Micron flashes only. */ #define SPINOR_OP_RD_EVCR 0x65 /* Read EVCR register */ @@ -135,12 +123,6 @@ /* Enhanced Volatile Configuration Register bits */ #define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ -/* Flag Status Register bits */ -#define FSR_READY BIT(7) /* Device status, 0 = Busy, 1 = Ready */ -#define FSR_E_ERR BIT(5) /* Erase operation status */ -#define FSR_P_ERR BIT(4) /* Program operation status */ -#define FSR_PT_ERR BIT(1) /* Protection error bit */ - /* Status Register 2 bits. */ #define SR2_QUAD_EN_BIT1 BIT(1) #define SR2_LB1 BIT(3) /* Security Register Lock Bit 1 */ @@ -371,7 +353,6 @@ struct spi_nor_flash_parameter; * @bouncebuf_size: size of the bounce buffer * @info: SPI NOR part JEDEC MFR ID and other info * @manufacturer: SPI NOR manufacturer - * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector * @read_opcode: the read opcode @@ -401,7 +382,6 @@ struct spi_nor { size_t bouncebuf_size; const struct flash_info *info; const struct spi_nor_manufacturer *manufacturer; - u32 page_size; u8 addr_width; u8 erase_opcode; u8 read_opcode; diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h index 6988956b8492..3aa28240a77f 100644 --- a/include/linux/mtd/spinand.h +++ b/include/linux/mtd/spinand.h @@ -389,6 +389,8 @@ struct spinand_info { struct spinand_dirmap { struct spi_mem_dirmap_desc *wdesc; struct spi_mem_dirmap_desc *rdesc; + struct spi_mem_dirmap_desc *wdesc_ecc; + struct spi_mem_dirmap_desc *rdesc_ecc; }; /** diff --git a/include/linux/mutex_api.h b/include/linux/mutex_api.h new file mode 100644 index 000000000000..85ab9491e13e --- /dev/null +++ b/include/linux/mutex_api.h @@ -0,0 +1 @@ +#include <linux/mutex.h> diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h index 7a09b040ac39..2e25c838f831 100644 --- a/include/linux/mux/consumer.h +++ b/include/linux/mux/consumer.h @@ -14,14 +14,19 @@ struct device; struct mux_control; +struct mux_state; unsigned int mux_control_states(struct mux_control *mux); int __must_check mux_control_select_delay(struct mux_control *mux, unsigned int state, unsigned int delay_us); +int __must_check mux_state_select_delay(struct mux_state *mstate, + unsigned int delay_us); int __must_check mux_control_try_select_delay(struct mux_control *mux, unsigned int state, unsigned int delay_us); +int __must_check mux_state_try_select_delay(struct mux_state *mstate, + unsigned int delay_us); static inline int __must_check mux_control_select(struct mux_control *mux, unsigned int state) @@ -29,18 +34,31 @@ static inline int __must_check mux_control_select(struct mux_control *mux, return mux_control_select_delay(mux, state, 0); } +static inline int __must_check mux_state_select(struct mux_state *mstate) +{ + return mux_state_select_delay(mstate, 0); +} + static inline int __must_check mux_control_try_select(struct mux_control *mux, unsigned int state) { return mux_control_try_select_delay(mux, state, 0); } +static inline int __must_check mux_state_try_select(struct mux_state *mstate) +{ + return mux_state_try_select_delay(mstate, 0); +} + int mux_control_deselect(struct mux_control *mux); +int mux_state_deselect(struct mux_state *mstate); struct mux_control *mux_control_get(struct device *dev, const char *mux_name); void mux_control_put(struct mux_control *mux); struct mux_control *devm_mux_control_get(struct device *dev, const char *mux_name); +struct mux_state *devm_mux_state_get(struct device *dev, + const char *mux_name); #endif /* _LINUX_MUX_CONSUMER_H */ diff --git a/include/linux/nd.h b/include/linux/nd.h index 8a8c63edb1b2..b9771ba1ef87 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -8,6 +8,7 @@ #include <linux/ndctl.h> #include <linux/device.h> #include <linux/badblocks.h> +#include <linux/perf_event.h> enum nvdimm_event { NVDIMM_REVALIDATE_POISON, @@ -23,6 +24,57 @@ enum nvdimm_claim_class { NVDIMM_CCLASS_UNKNOWN, }; +#define NVDIMM_EVENT_VAR(_id) event_attr_##_id +#define NVDIMM_EVENT_PTR(_id) (&event_attr_##_id.attr.attr) + +#define NVDIMM_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR(_name, NVDIMM_EVENT_VAR(_id), _id, \ + nvdimm_events_sysfs_show) + +/* Event attribute array index */ +#define NVDIMM_PMU_FORMAT_ATTR 0 +#define NVDIMM_PMU_EVENT_ATTR 1 +#define NVDIMM_PMU_CPUMASK_ATTR 2 +#define NVDIMM_PMU_NULL_ATTR 3 + +/** + * struct nvdimm_pmu - data structure for nvdimm perf driver + * @pmu: pmu data structure for nvdimm performance stats. + * @dev: nvdimm device pointer. + * @cpu: designated cpu for counter access. + * @node: node for cpu hotplug notifier link. + * @cpuhp_state: state for cpu hotplug notification. + * @arch_cpumask: cpumask to get designated cpu for counter access. + */ +struct nvdimm_pmu { + struct pmu pmu; + struct device *dev; + int cpu; + struct hlist_node node; + enum cpuhp_state cpuhp_state; + /* cpumask provided by arch/platform specific code */ + struct cpumask arch_cpumask; +}; + +struct platform_device; + +#ifdef CONFIG_PERF_EVENTS +extern ssize_t nvdimm_events_sysfs_show(struct device *dev, + struct device_attribute *attr, + char *page); + +int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev); +void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu); + +#else +static inline int register_nvdimm_pmu(struct nvdimm_pmu *nvdimm, struct platform_device *pdev) +{ + return -ENXIO; +} + +static inline void unregister_nvdimm_pmu(struct nvdimm_pmu *nd_pmu) { } +#endif + struct nd_device_driver { struct device_driver drv; unsigned long type; @@ -92,27 +144,6 @@ struct nd_namespace_pmem { int id; }; -/** - * struct nd_namespace_blk - namespace for dimm-bounded persistent memory - * @alt_name: namespace name supplied in the dimm label - * @uuid: namespace name supplied in the dimm label - * @id: ida allocated id - * @lbasize: blk namespaces have a native sector size when btt not present - * @size: sum of all the resource ranges allocated to this namespace - * @num_resources: number of dpa extents to claim - * @res: discontiguous dpa extents for given dimm - */ -struct nd_namespace_blk { - struct nd_namespace_common common; - char *alt_name; - uuid_t *uuid; - int id; - unsigned long lbasize; - resource_size_t size; - int num_resources; - struct resource **res; -}; - static inline struct nd_namespace_io *to_nd_namespace_io(const struct device *dev) { return container_of(dev, struct nd_namespace_io, common.dev); @@ -125,11 +156,6 @@ static inline struct nd_namespace_pmem *to_nd_namespace_pmem(const struct device return container_of(nsio, struct nd_namespace_pmem, nsio); } -static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device *dev) -{ - return container_of(dev, struct nd_namespace_blk, common.dev); -} - /** * nvdimm_read_bytes() - synchronously read bytes from an nvdimm namespace * @ndns: device to read diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 6b3267b49755..ed42bd5f639f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -26,11 +26,6 @@ struct i40e_client_version { u8 rsvd; }; -enum i40e_client_state { - __I40E_CLIENT_NULL, - __I40E_CLIENT_REGISTERED -}; - enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_NONE, __I40E_CLIENT_INSTANCE_OPENED, @@ -190,11 +185,6 @@ struct i40e_client { const struct i40e_client_ops *ops; /* client ops provided by the client */ }; -static inline bool i40e_client_is_registered(struct i40e_client *client) -{ - return test_bit(__I40E_CLIENT_REGISTERED, &client->state); -} - void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); void i40e_client_device_unregister(struct i40e_info *ldev); diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index e32f6712aee0..1c1332e4df26 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -26,7 +26,14 @@ enum iidc_reset_type { IIDC_GLOBR, }; +enum iidc_rdma_protocol { + IIDC_RDMA_PROTOCOL_IWARP = BIT(0), + IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1), +}; + #define IIDC_MAX_USER_PRIORITY 8 +#define IIDC_MAX_DSCP_MAPPING 64 +#define IIDC_DSCP_PFC_MODE 0x1 /* Struct to hold per RDMA Qset info */ struct iidc_rdma_qset_params { @@ -55,6 +62,8 @@ struct iidc_qos_params { u8 vport_relative_bw; u8 vport_priority_type; u8 num_tc; + u8 pfc_mode; + u8 dscp_map[IIDC_MAX_DSCP_MAPPING]; }; struct iidc_event { @@ -70,8 +79,6 @@ int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); -#define IIDC_RDMA_ROCE_NAME "roce" - /* Structure representing auxiliary driver tailored information about the core * PCI dev, each auxiliary driver using the IIDC interface will have an * instance of this struct dedicated to it. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be5cb3360b94..59e27a2b7bf0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -28,6 +28,7 @@ #include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> +#include <asm/local.h> #include <linux/percpu.h> #include <linux/rculist.h> @@ -48,6 +49,7 @@ #include <uapi/linux/pkt_cls.h> #include <linux/hashtable.h> #include <linux/rbtree.h> +#include <net/net_trackers.h> struct netpoll_info; struct device; @@ -193,6 +195,14 @@ struct net_device_stats { unsigned long tx_compressed; }; +/* per-cpu stats, allocated on demand. + * Try to fit them in a single cache line, for dev_get_stats() sake. + */ +struct net_device_core_stats { + local_t rx_dropped; + local_t tx_dropped; + local_t rx_nohandler; +} __aligned(4 * sizeof(local_t)); #include <linux/cache.h> #include <linux/skbuff.h> @@ -299,7 +309,6 @@ enum netdev_state_t { __LINK_STATE_TESTING, }; - struct gro_list { struct list_head list; int count; @@ -579,6 +588,8 @@ struct netdev_queue { * read-mostly part */ struct net_device *dev; + netdevice_tracker dev_tracker; + struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS @@ -592,7 +603,7 @@ struct netdev_queue { * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ - unsigned long trans_timeout; + atomic_long_t trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; @@ -734,6 +745,8 @@ struct netdev_rx_queue { #endif struct kobject kobj; struct net_device *dev; + netdevice_tracker dev_tracker; + #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif @@ -916,6 +929,7 @@ enum tc_setup_type { TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, TC_SETUP_QDISC_HTB, + TC_SETUP_ACT, }; /* These structures hold the attributes of bpf state that are being passed @@ -1297,11 +1311,6 @@ struct netdev_net_notifier { * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. - * void (*ndo_change_proto_down)(struct net_device *dev, - * bool proto_down); - * This function is used to pass protocol port error state information - * to the switch driver. The switch driver can react to the proto_down - * by doing a phys down on the associated switch port. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while @@ -1542,8 +1551,6 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); - int (*ndo_change_proto_down)(struct net_device *dev, - bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, @@ -1612,6 +1619,7 @@ struct net_device_ops { * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) + * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1646,6 +1654,7 @@ enum netdev_priv_flags { IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, IFF_TX_SKB_NO_LINEAR = 1<<31, + IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1735,12 +1744,8 @@ enum netdev_ml_priv_type { * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * - * @rx_dropped: Dropped packets by core network, - * do not use this in drivers - * @tx_dropped: Dropped packets by core network, + * @core_stats: core networking counters, * do not use this in drivers - * @rx_nohandler: nohandler dropped packets by core network on - * inactive devices, do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * @@ -1870,6 +1875,7 @@ enum netdev_ml_priv_type { * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @dev_refcnt: Number of references to this device + * @refcnt_tracker: Tracker directory for tracked references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * @@ -1893,6 +1899,8 @@ enum netdev_ml_priv_type { * @garp_port: GARP * @mrp_port: MRP * + * @dm_private: Drop monitor private + * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups @@ -1937,10 +1945,19 @@ enum netdev_ml_priv_type { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * - * @nested_level: Used as as a parameter of spin_lock_nested() of + * @nested_level: Used as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. + * @gro_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO) + * + * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. + * @linkwatch_dev_tracker: refcount tracker used by linkwatch. + * @watchdog_dev_tracker: refcount tracker used by watchdog. + * @dev_registered_tracker: tracker for reference held while + * registered + * @offload_xstats_l3: L3 HW stats for this netdevice. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -1980,7 +1997,7 @@ struct net_device { /* Read-mostly cache-line for fast-path access */ unsigned int flags; - unsigned int priv_flags; + unsigned long long priv_flags; const struct net_device_ops *netdev_ops; int ifindex; unsigned short gflags; @@ -2013,9 +2030,7 @@ struct net_device { struct net_device_stats stats; /* not used by modern drivers */ - atomic_long_t rx_dropped; - atomic_long_t tx_dropped; - atomic_long_t rx_nohandler; + struct net_device_core_stats __percpu *core_stats; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; @@ -2093,7 +2108,7 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif struct in_device __rcu *ip_ptr; @@ -2117,7 +2132,7 @@ struct net_device { * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ - unsigned char *dev_addr; + const unsigned char *dev_addr; struct netdev_rx_queue *_rx; unsigned int num_rx_queues; @@ -2126,6 +2141,8 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; +#define GRO_MAX_SIZE 65536 + unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -2149,7 +2166,7 @@ struct net_device { struct netdev_queue *_tx ____cacheline_aligned_in_smp; unsigned int num_tx_queues; unsigned int real_num_tx_queues; - struct Qdisc *qdisc; + struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; @@ -2181,6 +2198,7 @@ struct net_device { #else refcount_t dev_refcnt; #endif + struct ref_tracker_dir refcnt_tracker; struct list_head link_watch_list; @@ -2224,7 +2242,9 @@ struct net_device { #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif - +#if IS_ENABLED(CONFIG_NET_DROP_MONITOR) + struct dm_hw_stat_delta __rcu *dm_private; +#endif struct device dev; const struct attribute_group *sysfs_groups[4]; const struct attribute_group *sysfs_rx_queue_group; @@ -2268,6 +2288,12 @@ struct net_device { /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; + + u8 dev_addr_shadow[MAX_ADDR_LEN]; + netdevice_tracker linkwatch_dev_tracker; + netdevice_tracker watchdog_dev_tracker; + netdevice_tracker dev_registered_tracker; + struct rtnl_hw_stats64 *offload_xstats_l3; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2520,113 +2546,11 @@ static inline void netif_napi_del(struct napi_struct *napi) synchronize_net(); } -struct napi_gro_cb { - /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; - - /* Length of frag0. */ - unsigned int frag0_len; - - /* This indicates where we are processing relative to skb->data. */ - int data_offset; - - /* This is non-zero if the packet cannot be merged with the new skb. */ - u16 flush; - - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - - /* Number of segments aggregated. */ - u16 count; - - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; - - /* jiffies when first packet was created/queued */ - unsigned long age; - - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; - - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; - - /* Used in tunnel GRO receive */ - u8 encap_mark:1; - - /* GRO checksum is valid */ - u8 csum_valid:1; - - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; - - /* Free the skb? */ - u8 free:2; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 - - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; - - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; - - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; - - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; - - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; - - /* used to support CHECKSUM_COMPLETE for tunneling protocols */ - __wsum csum; - - /* used in skb_gro_receive() slow path */ - struct sk_buff *last; -}; - -#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) - -#define GRO_RECURSION_LIMIT 15 -static inline int gro_recursion_inc_test(struct sk_buff *skb) -{ - return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; -} - -typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); -static inline struct sk_buff *call_gro_receive(gro_receive_t cb, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(head, skb); -} - -typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, - struct sk_buff *); -static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(sk, head, skb); -} - struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ + netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, @@ -2636,6 +2560,7 @@ struct packet_type { struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); + struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; @@ -2809,6 +2734,10 @@ enum netdev_cmd { NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, + NETDEV_OFFLOAD_XSTATS_ENABLE, + NETDEV_OFFLOAD_XSTATS_DISABLE, + NETDEV_OFFLOAD_XSTATS_REPORT_USED, + NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); @@ -2859,6 +2788,42 @@ struct netdev_notifier_pre_changeaddr_info { const unsigned char *dev_addr; }; +enum netdev_offload_xstats_type { + NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, +}; + +struct netdev_notifier_offload_xstats_info { + struct netdev_notifier_info info; /* must be first */ + enum netdev_offload_xstats_type type; + + union { + /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ + struct netdev_notifier_offload_xstats_rd *report_delta; + /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ + struct netdev_notifier_offload_xstats_ru *report_used; + }; +}; + +int netdev_offload_xstats_enable(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct netlink_ext_ack *extack); +int netdev_offload_xstats_disable(struct net_device *dev, + enum netdev_offload_xstats_type type); +bool netdev_offload_xstats_enabled(const struct net_device *dev, + enum netdev_offload_xstats_type type); +int netdev_offload_xstats_get(struct net_device *dev, + enum netdev_offload_xstats_type type, + struct rtnl_hw_stats64 *stats, bool *used, + struct netlink_ext_ack *extack); +void +netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, + const struct rtnl_hw_stats64 *stats); +void +netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); +void netdev_offload_xstats_push_delta(struct net_device *dev, + enum netdev_offload_xstats_type type, + const struct rtnl_hw_stats64 *stats); + static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { @@ -3005,254 +2970,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); -int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); - -static inline unsigned int skb_gro_offset(const struct sk_buff *skb) -{ - return NAPI_GRO_CB(skb)->data_offset; -} - -static inline unsigned int skb_gro_len(const struct sk_buff *skb) -{ - return skb->len - NAPI_GRO_CB(skb)->data_offset; -} - -static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) -{ - NAPI_GRO_CB(skb)->data_offset += len; -} - -static inline void *skb_gro_header_fast(struct sk_buff *skb, - unsigned int offset) -{ - return NAPI_GRO_CB(skb)->frag0 + offset; -} - -static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) -{ - return NAPI_GRO_CB(skb)->frag0_len < hlen; -} - -static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; -} - -static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, - unsigned int offset) -{ - if (!pskb_may_pull(skb, hlen)) - return NULL; - - skb_gro_frag0_invalidate(skb); - return skb->data + offset; -} - -static inline void *skb_gro_network_header(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + - skb_network_offset(skb); -} - -static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) -{ - if (NAPI_GRO_CB(skb)->csum_valid) - NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, - csum_partial(start, len, 0)); -} - -/* GRO checksum functions. These are logical equivalents of the normal - * checksum functions (in skbuff.h) except that they operate on the GRO - * offsets and fields in sk_buff. - */ - -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); - -static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); -} - -static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, - bool zero_okay, - __sum16 check) -{ - return ((skb->ip_summed != CHECKSUM_PARTIAL || - skb_checksum_start_offset(skb) < - skb_gro_offset(skb)) && - !skb_at_gro_remcsum_start(skb) && - NAPI_GRO_CB(skb)->csum_cnt == 0 && - (!zero_okay || check)); -} - -static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, - __wsum psum) -{ - if (NAPI_GRO_CB(skb)->csum_valid && - !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) - return 0; - - NAPI_GRO_CB(skb)->csum = psum; - - return __skb_gro_checksum_complete(skb); -} - -static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) -{ - if (NAPI_GRO_CB(skb)->csum_cnt > 0) { - /* Consume a checksum from CHECKSUM_UNNECESSARY */ - NAPI_GRO_CB(skb)->csum_cnt--; - } else { - /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we - * verified a new top level checksum or an encapsulated one - * during GRO. This saves work if we fallback to normal path. - */ - __skb_incr_checksum_unnecessary(skb); - } -} - -#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ - compute_pseudo) \ -({ \ - __sum16 __ret = 0; \ - if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ - __ret = __skb_gro_checksum_validate_complete(skb, \ - compute_pseudo(skb, proto)); \ - if (!__ret) \ - skb_gro_incr_csum_unnecessary(skb); \ - __ret; \ -}) - -#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) - -#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ - compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) - -#define skb_gro_checksum_simple_validate(skb) \ - __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) - -static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->csum_cnt == 0 && - !NAPI_GRO_CB(skb)->csum_valid); -} - -static inline void __skb_gro_checksum_convert(struct sk_buff *skb, - __wsum pseudo) -{ - NAPI_GRO_CB(skb)->csum = ~pseudo; - NAPI_GRO_CB(skb)->csum_valid = 1; -} - -#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ -do { \ - if (__skb_gro_checksum_convert_check(skb)) \ - __skb_gro_checksum_convert(skb, \ - compute_pseudo(skb, proto)); \ -} while (0) - -struct gro_remcsum { - int offset; - __wsum delta; -}; - -static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) -{ - grc->offset = 0; - grc->delta = 0; -} - -static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - unsigned int off, size_t hdrlen, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) -{ - __wsum delta; - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - - BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); - - if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; - return ptr; - } - - ptr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, off + plen)) { - ptr = skb_gro_header_slow(skb, off + plen, off); - if (!ptr) - return NULL; - } - - delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, - start, offset); - - /* Adjust skb->csum since we changed the packet */ - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - - grc->offset = off + hdrlen + offset; - grc->delta = delta; - - return ptr; -} -static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, - struct gro_remcsum *grc) -{ - void *ptr; - size_t plen = grc->offset + sizeof(u16); - - if (!grc->delta) - return; - - ptr = skb_gro_header_fast(skb, grc->offset); - if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { - ptr = skb_gro_header_slow(skb, plen, grc->offset); - if (!ptr) - return; - } - - remcsum_unadjust((__sum16 *)ptr, grc->delta); -} - -#ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - if (PTR_ERR(pp) != -EINPROGRESS) - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - if (PTR_ERR(pp) != -EINPROGRESS) { - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; - } -} -#else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; -} -#endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -3948,7 +3666,6 @@ static inline unsigned int get_netdev_rx_queue_index( } #endif -#define DEFAULT_MAX_NUM_RSS_QUEUES (8) int netif_get_num_default_rss_queues(void); enum skb_free_reason { @@ -4003,10 +3720,11 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); -int netif_rx_ni(struct sk_buff *skb); -int netif_rx_any_context(struct sk_buff *skb); +int __netif_rx(struct sk_buff *skb); + int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); @@ -4080,7 +3798,6 @@ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); @@ -4126,13 +3843,42 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } +struct net_device_core_stats *netdev_core_stats_alloc(struct net_device *dev); + +static inline struct net_device_core_stats *dev_core_stats(struct net_device *dev) +{ + /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ + struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); + + if (likely(p)) + return this_cpu_ptr(p); + + return netdev_core_stats_alloc(dev); +} + +#define DEV_CORE_STATS_INC(FIELD) \ +static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ +{ \ + struct net_device_core_stats *p; \ + \ + preempt_disable(); \ + p = dev_core_stats(dev); \ + \ + if (p) \ + local_inc(&p->FIELD); \ + preempt_enable(); \ +} +DEV_CORE_STATS_INC(rx_dropped) +DEV_CORE_STATS_INC(tx_dropped) +DEV_CORE_STATS_INC(rx_nohandler) + static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { - atomic_long_inc(&dev->rx_dropped); + dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); return NET_RX_DROP; } @@ -4151,13 +3897,7 @@ extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); -/** - * dev_put - release reference to device - * @dev: network device - * - * Release reference to device to allow it to be freed. - */ -static inline void dev_put(struct net_device *dev) +static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -4168,13 +3908,7 @@ static inline void dev_put(struct net_device *dev) } } -/** - * dev_hold - get reference to device - * @dev: network device - * - * Hold reference to device to keep it from being freed. - */ -static inline void dev_hold(struct net_device *dev) +static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -4185,6 +3919,92 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void __netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +/* netdev_tracker_alloc() can upgrade a prior untracked reference + * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. + */ +static inline void netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + refcount_dec(&dev->refcnt_tracker.no_tracker); + __netdev_tracker_alloc(dev, tracker, gfp); +#endif +} + +static inline void netdev_tracker_free(struct net_device *dev, + netdevice_tracker *tracker) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_free(&dev->refcnt_tracker, tracker); +#endif +} + +static inline void dev_hold_track(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ + if (dev) { + __dev_hold(dev); + __netdev_tracker_alloc(dev, tracker, gfp); + } +} + +static inline void dev_put_track(struct net_device *dev, + netdevice_tracker *tracker) +{ + if (dev) { + netdev_tracker_free(dev, tracker); + __dev_put(dev); + } +} + +/** + * dev_hold - get reference to device + * @dev: network device + * + * Hold reference to device to keep it from being freed. + * Try using dev_hold_track() instead. + */ +static inline void dev_hold(struct net_device *dev) +{ + dev_hold_track(dev, NULL, GFP_ATOMIC); +} + +/** + * dev_put - release reference to device + * @dev: network device + * + * Release reference to device to allow it to be freed. + * Try using dev_put_track() instead. + */ +static inline void dev_put(struct net_device *dev) +{ + dev_put_track(dev, NULL); +} + +static inline void dev_replace_track(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) +{ + if (odev) + netdev_tracker_free(odev, tracker); + + __dev_hold(ndev); + __dev_put(odev); + + if (ndev) + __netdev_tracker_alloc(ndev, tracker, gfp); +} + /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. @@ -4451,10 +4271,21 @@ static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) spin_unlock_bh(&txq->_xmit_lock); } +/* + * txq->trans_start can be read locklessly from dev_watchdog() + */ static inline void txq_trans_update(struct netdev_queue *txq) { if (txq->xmit_lock_owner != -1) - txq->trans_start = jiffies; + WRITE_ONCE(txq->trans_start, jiffies); +} + +static inline void txq_trans_cond_update(struct netdev_queue *txq) +{ + unsigned long now = jiffies; + + if (READ_ONCE(txq->trans_start) != now) + WRITE_ONCE(txq->trans_start, now); } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ @@ -4462,8 +4293,7 @@ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); - if (txq->trans_start != jiffies) - txq->trans_start = jiffies; + txq_trans_cond_update(txq); } /** @@ -4472,27 +4302,7 @@ static inline void netif_trans_update(struct net_device *dev) * * Get network device transmit lock */ -static inline void netif_tx_lock(struct net_device *dev) -{ - unsigned int i; - int cpu; - - spin_lock(&dev->tx_global_lock); - cpu = smp_processor_id(); - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* We are the only thread of execution doing a - * freeze, but we have to grab the _xmit_lock in - * order to synchronize with threads which are in - * the ->hard_start_xmit() handler and already - * checked the frozen bit. - */ - __netif_tx_lock(txq, cpu); - set_bit(__QUEUE_STATE_FROZEN, &txq->state); - __netif_tx_unlock(txq); - } -} +void netif_tx_lock(struct net_device *dev); static inline void netif_tx_lock_bh(struct net_device *dev) { @@ -4500,22 +4310,7 @@ static inline void netif_tx_lock_bh(struct net_device *dev) netif_tx_lock(dev); } -static inline void netif_tx_unlock(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* No need to grab the _xmit_lock here. If the - * queue is not stopped for another reason, we - * force a schedule. - */ - clear_bit(__QUEUE_STATE_FROZEN, &txq->state); - netif_schedule_queue(txq); - } - spin_unlock(&dev->tx_global_lock); -} +void netif_tx_unlock(struct net_device *dev); static inline void netif_tx_unlock_bh(struct net_device *dev) { @@ -4649,10 +4444,13 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ +void dev_addr_mod(struct net_device *dev, unsigned int offset, + const void *addr, size_t len); + static inline void __dev_addr_set(struct net_device *dev, const void *addr, size_t len) { - memcpy(dev->dev_addr, addr, len); + dev_addr_mod(dev, 0, addr, len); } static inline void dev_addr_set(struct net_device *dev, const u8 *addr) @@ -4660,19 +4458,13 @@ static inline void dev_addr_set(struct net_device *dev, const u8 *addr) __dev_addr_set(dev, addr, dev->addr_len); } -static inline void -dev_addr_mod(struct net_device *dev, unsigned int offset, - const void *addr, size_t len) -{ - memcpy(&dev->dev_addr[offset], addr, len); -} - int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); void dev_addr_flush(struct net_device *dev); int dev_addr_init(struct net_device *dev); +void dev_addr_check(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); @@ -4809,16 +4601,6 @@ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); -#ifdef CONFIG_LOCKDEP -static LIST_HEAD(net_unlink_list); - -static inline void net_unlink_todo(struct net_device *dev) -{ - if (list_empty(&dev->unlink_list)) - list_add_tail(&dev->unlink_list, &net_unlink_list); -} -#endif - /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ @@ -4913,6 +4695,8 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); +struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, + netdev_features_t features, __be16 type); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); @@ -5111,7 +4895,22 @@ static inline bool netif_needs_gso(struct sk_buff *skb, static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { - dev->gso_max_size = size; + /* dev->gso_max_size is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_max_size, size); +} + +static inline void netif_set_gso_max_segs(struct net_device *dev, + unsigned int segs) +{ + /* dev->gso_max_segs is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_max_segs, segs); +} + +static inline void netif_set_gro_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_max_size, size); } static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, @@ -5298,7 +5097,7 @@ void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ do { \ - static bool __print_once __read_mostly; \ + static bool __section(".data.once") __print_once; \ \ if (!__print_once) { \ __print_once = true; \ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 3fda1a508733..c2c6f332fb90 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -379,15 +379,16 @@ struct nf_nat_hook { unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct, enum nf_nat_manip_type mtype, enum ip_conntrack_dir dir); + void (*remove_nat_bysrc)(struct nf_conn *ct); }; -extern struct nf_nat_hook __rcu *nf_nat_hook; +extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #if IS_ENABLED(CONFIG_NF_NAT) - struct nf_nat_hook *nat_hook; + const struct nf_nat_hook *nat_hook; rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); @@ -440,7 +441,6 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_zones_common.h> -extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, @@ -463,8 +463,9 @@ struct nf_ct_hook { void (*destroy)(struct nf_conntrack *); bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); + void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); }; -extern struct nf_ct_hook __rcu *nf_ct_hook; +extern const struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; @@ -479,7 +480,7 @@ struct nfnl_ct_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfnl_ct_hook __rcu *nfnl_ct_hook; +extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; /** * nf_skb_duplicated - TEE target has sent a packet diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 700ea077ce2d..2770db2fa080 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -2,7 +2,7 @@ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { @@ -25,19 +25,21 @@ struct ip_conntrack_stat { #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { - atomic_t use; + refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); + +/* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { - if (nfct && atomic_dec_and_test(&nfct->use)) + if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) - atomic_inc(&nfct->use); + refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index a28aa289afdc..c3bdb4370938 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -300,26 +300,22 @@ union pptp_ctrl_union { struct PptpSetLinkInfo setlink; }; -extern int -(*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern int -(*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, - struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned int protoff, - struct PptpControlHeader *ctlh, - union pptp_ctrl_union *pptpReq); - -extern void -(*nf_nat_pptp_hook_exp_gre)(struct nf_conntrack_expect *exp_orig, - struct nf_conntrack_expect *exp_reply); - -extern void -(*nf_nat_pptp_hook_expectfn)(struct nf_conn *ct, - struct nf_conntrack_expect *exp); +struct nf_nat_pptp_hook { + int (*outbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + int (*inbound)(struct sk_buff *skb, + struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, + struct PptpControlHeader *ctlh, + union pptp_ctrl_union *pptpReq); + void (*exp_gre)(struct nf_conntrack_expect *exp_orig, + struct nf_conntrack_expect *exp_reply); + void (*expectfn)(struct nf_conn *ct, + struct nf_conntrack_expect *exp); +}; +extern const struct nf_nat_pptp_hook __rcu *nf_nat_pptp_hook; #endif /* _NF_CONNTRACK_PPTP_H */ diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index b71b57a83bb4..8676316547cc 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -94,14 +94,18 @@ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, return skb; #endif - e = rcu_dereference(dev->nf_hooks_egress); + e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, - NFPROTO_NETDEV, dev, NULL, NULL, + NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); + + /* nf assumes rcu_read_lock, not just read_lock_bh */ + rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); + rcu_read_unlock(); if (ret == 1) { return skb; diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ca0683b9e3d1..c7bf1eaf51d5 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -18,6 +18,8 @@ #include <linux/fs.h> #include <linux/pagemap.h> +enum netfs_sreq_ref_trace; + /* * Overload PG_private_2 to give us PG_fscache - this is used to indicate that * a page is currently backed by a local disk cache @@ -106,7 +108,7 @@ static inline int wait_on_page_fscache_killable(struct page *page) return folio_wait_private_2_killable(page_folio(page)); } -enum netfs_read_source { +enum netfs_io_source { NETFS_FILL_WITH_ZEROES, NETFS_DOWNLOAD_FROM_SERVER, NETFS_READ_FROM_CACHE, @@ -117,6 +119,17 @@ typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error, bool was_async); /* + * Per-inode description. This must be directly after the inode struct. + */ +struct netfs_i_context { + const struct netfs_request_ops *ops; +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cache; +#endif + loff_t remote_i_size; /* Size of the remote file */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -124,78 +137,94 @@ struct netfs_cache_resources { void *cache_priv; void *cache_priv2; unsigned int debug_id; /* Cookie debug ID */ + unsigned int inval_counter; /* object->inval_counter at begin_op */ }; /* * Descriptor for a single component subrequest. */ -struct netfs_read_subrequest { - struct netfs_read_request *rreq; /* Supervising read request */ +struct netfs_io_subrequest { + struct netfs_io_request *rreq; /* Supervising I/O request */ struct list_head rreq_link; /* Link in rreq->subrequests */ loff_t start; /* Where to start the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ - refcount_t usage; + refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ - enum netfs_read_source source; /* Where to read from */ + enum netfs_io_source source; /* Where to read from/write to */ unsigned long flags; -#define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ +#define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ -#define NETFS_SREQ_SHORT_READ 2 /* Set if there was a short read from the cache */ +#define NETFS_SREQ_SHORT_IO 2 /* Set if the I/O was short */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ }; +enum netfs_io_origin { + NETFS_READAHEAD, /* This read was triggered by readahead */ + NETFS_READPAGE, /* This read is a synchronous read */ + NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ +} __mode(byte); + /* - * Descriptor for a read helper request. This is used to make multiple I/O - * requests on a variety of sources and then stitch the result together. + * Descriptor for an I/O helper request. This is used to make multiple I/O + * operations to a variety of data stores and then stitch the result together. */ -struct netfs_read_request { +struct netfs_io_request { struct work_struct work; struct inode *inode; /* The file being accessed */ struct address_space *mapping; /* The mapping being accessed */ struct netfs_cache_resources cache_resources; - struct list_head subrequests; /* Requests to fetch I/O from disk or net */ + struct list_head subrequests; /* Contributory I/O operations */ void *netfs_priv; /* Private data for the netfs */ unsigned int debug_id; - atomic_t nr_rd_ops; /* Number of read ops in progress */ - atomic_t nr_wr_ops; /* Number of write ops in progress */ + atomic_t nr_outstanding; /* Number of ops in progress */ + atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ size_t submitted; /* Amount submitted for I/O so far */ size_t len; /* Length of the request */ short error; /* 0 or error that occurred */ + enum netfs_io_origin origin; /* Origin of the request */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ - refcount_t usage; + refcount_t ref; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ -#define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ - const struct netfs_read_request_ops *netfs_ops; + const struct netfs_request_ops *netfs_ops; }; /* * Operations the network filesystem can/must provide to the helpers. */ -struct netfs_read_request_ops { - bool (*is_cache_enabled)(struct inode *inode); - void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); - int (*begin_cache_operation)(struct netfs_read_request *rreq); - void (*expand_readahead)(struct netfs_read_request *rreq); - bool (*clamp_length)(struct netfs_read_subrequest *subreq); - void (*issue_op)(struct netfs_read_subrequest *subreq); - bool (*is_still_valid)(struct netfs_read_request *rreq); +struct netfs_request_ops { + int (*init_request)(struct netfs_io_request *rreq, struct file *file); + int (*begin_cache_operation)(struct netfs_io_request *rreq); + void (*expand_readahead)(struct netfs_io_request *rreq); + bool (*clamp_length)(struct netfs_io_subrequest *subreq); + void (*issue_read)(struct netfs_io_subrequest *subreq); + bool (*is_still_valid)(struct netfs_io_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, struct folio *folio, void **_fsdata); - void (*done)(struct netfs_read_request *rreq); + void (*done)(struct netfs_io_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; /* + * How to handle reading from a hole. + */ +enum netfs_read_from_hole { + NETFS_READ_HOLE_IGNORE, + NETFS_READ_HOLE_CLEAR, + NETFS_READ_HOLE_FAIL, +}; + +/* * Table of operations for access to a cache. This is obtained by * rreq->ops->begin_cache_operation(). */ @@ -207,7 +236,7 @@ struct netfs_cache_ops { int (*read)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, - bool seek_data, + enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); @@ -225,31 +254,108 @@ struct netfs_cache_ops { /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ - enum netfs_read_source (*prepare_read)(struct netfs_read_subrequest *subreq, + enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, loff_t i_size); /* Prepare a write operation, working out what part of the write we can * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + loff_t *_start, size_t *_len, loff_t i_size, + bool no_space_allocated_yet); + + /* Query the occupancy of the cache in a region, returning where the + * next chunk of data starts and how long it is. + */ + int (*query_occupancy)(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len); }; struct readahead_control; -extern void netfs_readahead(struct readahead_control *, - const struct netfs_read_request_ops *, - void *); -extern int netfs_readpage(struct file *, - struct folio *, - const struct netfs_read_request_ops *, - void *); +extern void netfs_readahead(struct readahead_control *); +extern int netfs_readpage(struct file *, struct page *); extern int netfs_write_begin(struct file *, struct address_space *, loff_t, unsigned int, unsigned int, struct folio **, - void **, - const struct netfs_read_request_ops *, - void *); + void **); -extern void netfs_subreq_terminated(struct netfs_read_subrequest *, ssize_t, bool); +extern void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool); +extern void netfs_get_subrequest(struct netfs_io_subrequest *subreq, + enum netfs_sreq_ref_trace what); +extern void netfs_put_subrequest(struct netfs_io_subrequest *subreq, + bool was_async, enum netfs_sreq_ref_trace what); extern void netfs_stats_show(struct seq_file *); +/** + * netfs_i_context - Get the netfs inode context from the inode + * @inode: The inode to query + * + * Get the netfs lib inode context from the network filesystem's inode. The + * context struct is expected to directly follow on from the VFS inode struct. + */ +static inline struct netfs_i_context *netfs_i_context(struct inode *inode) +{ + return (struct netfs_i_context *)(inode + 1); +} + +/** + * netfs_inode - Get the netfs inode from the inode context + * @ctx: The context to query + * + * Get the netfs inode from the netfs library's inode context. The VFS inode + * is expected to directly precede the context struct. + */ +static inline struct inode *netfs_inode(struct netfs_i_context *ctx) +{ + return ((struct inode *)ctx) - 1; +} + +/** + * netfs_i_context_init - Initialise a netfs lib context + * @inode: The inode with which the context is associated + * @ops: The netfs's operations list + * + * Initialise the netfs library context struct. This is expected to follow on + * directly from the VFS inode struct. + */ +static inline void netfs_i_context_init(struct inode *inode, + const struct netfs_request_ops *ops) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + memset(ctx, 0, sizeof(*ctx)); + ctx->ops = ops; + ctx->remote_i_size = i_size_read(inode); +} + +/** + * netfs_resize_file - Note that a file got resized + * @inode: The inode being resized + * @new_i_size: The new file size + * + * Inform the netfs lib that a file got resized so that it can adjust its state. + */ +static inline void netfs_resize_file(struct inode *inode, loff_t new_i_size) +{ + struct netfs_i_context *ctx = netfs_i_context(inode); + + ctx->remote_i_size = new_i_size; +} + +/** + * netfs_i_cookie - Get the cache cookie from the inode + * @inode: The inode to query + * + * Get the caching cookie (if enabled) from the network filesystem's inode. + */ +static inline struct fscache_cookie *netfs_i_cookie(struct inode *inode) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct netfs_i_context *ctx = netfs_i_context(inode); + return ctx->cache; +#else + return NULL; +#endif +} + #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1ec631838af9..bda1c385cffb 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -135,15 +135,6 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(cookie); } -static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, - u32 cookie) -{ - if (!extack) - return; - memcpy(extack->cookie, &cookie, sizeof(cookie)); - extack->cookie_len = sizeof(cookie); -} - void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e6a2d72e0dc7..bd19c4b91e31 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -24,6 +24,7 @@ union inet_addr { struct netpoll { struct net_device *dev; + netdevice_tracker dev_tracker; char dev_name[IFNAMSIZ]; const char *name; diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 0dc7ad38a0da..b06375e88e58 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -36,14 +36,6 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc memcpy(target->data, source->data, source->size); } - -/* - * This is really a general kernel constant, but since nothing like - * this is defined in the kernel headers, I have to do it here. - */ -#define NFS_OFFSET_MAX ((__s64)((~(__u64)0) >> 1)) - - enum nfs3_stable_how { NFS_UNSTABLE = 0, NFS_DATA_SYNC = 1, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 05f249f20f55..b48b9259e02c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -46,11 +46,6 @@ #define NFS_MAX_TRANSPORTS 16 /* - * These are the default flags for swap requests - */ -#define NFS_RPC_SWAPFLAGS (RPC_TASK_SWAPPER|RPC_TASK_ROOTCREDS) - -/* * Size of the NFS directory verifier */ #define NFS_DIR_VERIFIER_SIZE 2 @@ -61,7 +56,9 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - const struct cred * cred; + kuid_t fsuid; + kgid_t fsgid; + struct group_info *group_info; __u32 mask; struct rcu_head rcu_head; }; @@ -99,12 +96,17 @@ struct nfs_open_context { struct nfs_open_dir_context { struct list_head list; + atomic_t cache_hits; + atomic_t cache_misses; unsigned long attr_gencount; __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; - __u64 dup_cookie; + __u64 last_cookie; pgoff_t page_index; - signed char duped; + unsigned int dtsize; + bool force_clear; + bool eof; + struct rcu_head rcu_head; }; /* @@ -244,7 +246,6 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ #define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ #define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ #define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ #define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ #define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ @@ -270,13 +271,11 @@ struct nfs4_copy_state { /* * Bit offsets in flags field */ -#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ +#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ -#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -353,17 +352,15 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_INVALID_CHANGE - | NFS_INO_INVALID_CTIME; + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | + NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | + NFS_INO_INVALID_SIZE; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } -static inline int nfs_server_capable(struct inode *inode, int cap) +static inline int nfs_server_capable(const struct inode *inode, int cap) { return NFS_SERVER(inode)->caps & cap; } @@ -396,7 +393,7 @@ extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fa extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); @@ -511,10 +508,10 @@ static inline const struct cred *nfs_file_cred(struct file *file) * linux/fs/nfs/direct.c */ extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *); -extern ssize_t nfs_file_direct_read(struct kiocb *iocb, - struct iov_iter *iter); -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, - struct iov_iter *iter); +ssize_t nfs_file_direct_read(struct kiocb *iocb, + struct iov_iter *iter, bool swap); +ssize_t nfs_file_direct_write(struct kiocb *iocb, + struct iov_iter *iter, bool swap); /* * linux/fs/nfs/dir.c @@ -533,8 +530,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, - bool may_block); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block); /* * linux/fs/nfs/symlink.c @@ -581,26 +578,24 @@ extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned extern int nfs_sync_inode(struct inode *inode); extern int nfs_wb_all(struct inode *inode); extern int nfs_wb_page(struct inode *inode, struct page *page); -extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); +int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio); extern int nfs_commit_inode(struct inode *, int); -extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); +extern struct nfs_commit_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_commit_data *data); bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); -static inline int -nfs_have_writebacks(struct inode *inode) +static inline bool nfs_have_writebacks(const struct inode *inode) { if (S_ISREG(inode->i_mode)) return atomic_long_read(&NFS_I(inode)->nrequests) != 0; - return 0; + return false; } /* * linux/fs/nfs/read.c */ extern int nfs_readpage(struct file *, struct page *); -extern int nfs_readpages(struct file *, struct address_space *, - struct list_head *, unsigned); +void nfs_readahead(struct readahead_control *); /* * inline functions diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2a9acbfe00f0..157d2bd6b241 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -120,11 +120,6 @@ struct nfs_client { * This is used to generate the mv0 callback address. */ char cl_ipaddr[48]; - -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; /* client index cache cookie */ -#endif - struct net *cl_net; struct list_head pending_cb_stateids; }; @@ -143,6 +138,7 @@ struct nfs_server { struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ atomic_long_t writeback; /* number of writeback pages */ + unsigned int write_congested;/* flag set when writeback gets too high */ unsigned int flags; /* various flags */ /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */ @@ -156,6 +152,7 @@ struct nfs_server { #define NFS_MOUNT_SOFTREVAL 0x800000 #define NFS_MOUNT_WRITE_EAGER 0x01000000 #define NFS_MOUNT_WRITE_WAIT 0x02000000 +#define NFS_MOUNT_TRUNK_DISCOVERY 0x04000000 unsigned int fattr_valid; /* Valid attributes */ unsigned int caps; /* server capabilities */ @@ -194,8 +191,8 @@ struct nfs_server { struct nfs_auth_info auth_info; /* parsed auth flavors */ #ifdef CONFIG_NFS_FSCACHE - struct nfs_fscache_key *fscache_key; /* unique key for superblock */ - struct fscache_cookie *fscache; /* superblock cookie */ + struct fscache_volume *fscache; /* superblock cookie */ + char *fscache_uniq; /* Uniquifier (or NULL) */ #endif u32 pnfs_blksize; /* layout_blksize attr */ @@ -271,6 +268,8 @@ struct nfs_server { #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) #define NFS_CAP_LGOPEN (1U << 5) +#define NFS_CAP_CASE_INSENSITIVE (1U << 6) +#define NFS_CAP_CASE_PRESERVING (1U << 7) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) @@ -287,5 +286,5 @@ struct nfs_server { #define NFS_CAP_COPY_NOTIFY (1U << 27) #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) - +#define NFS_CAP_FS_LOCATIONS (1U << 30) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 967a0098f0a9..49ba486aea5f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -745,8 +745,7 @@ struct nfs_auth_info { */ struct nfs_entry { __u64 ino; - __u64 cookie, - prev_cookie; + __u64 cookie; const char * name; unsigned int len; int eof; @@ -1194,6 +1193,8 @@ struct nfs4_server_caps_res { u32 has_links; u32 has_symlinks; u32 fh_expire_type; + u32 case_insensitive; + u32 case_preserving; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1737,7 +1738,7 @@ struct nfs_rpc_ops { struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); - int (*access) (struct inode *, struct nfs_access_entry *); + int (*access) (struct inode *, struct nfs_access_entry *, const struct cred *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*create) (struct inode *, struct dentry *, @@ -1795,6 +1796,9 @@ struct nfs_rpc_ops { struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); + int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); + void (*enable_swap)(struct inode *inode); + void (*disable_swap)(struct inode *inode); }; /* diff --git a/include/linux/node.h b/include/linux/node.h index bb21fd631b16..40d641a8bfb0 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,19 +99,20 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) -void link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context); +void register_memory_blocks_under_node(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else -static inline void link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn, - enum meminit_context context) +static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context) { } #endif extern void unregister_node(struct node *node); #ifdef CONFIG_NUMA +extern void node_dev_init(void); /* Core of the node registration - only memory hotplug should use this */ extern int __register_one_node(int nid); @@ -128,8 +129,8 @@ static inline int register_one_node(int nid) error = __register_one_node(nid); if (error) return error; - /* link memory sections under this node */ - link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY); + register_memory_blocks_under_node(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; @@ -149,6 +150,9 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister, node_registration_func_t unregister); #endif #else +static inline void node_dev_init(void) +{ +} static inline int __register_one_node(int nid) { return 0; @@ -181,4 +185,9 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg, #define to_node(device) container_of(device, struct node, dev) +static inline bool node_is_toptier(int node) +{ + return node_state(node, N_CPU); +} + #endif /* _LINUX_NODE_H_ */ diff --git a/include/linux/numa.h b/include/linux/numa.h index cb44cfe2b725..59df211d051f 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -58,4 +58,8 @@ static inline int phys_to_target_node(u64 start) } #endif +#ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP +extern const struct attribute_group arch_node_dev_group; +#endif + #endif /* _LINUX_NUMA_H */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index cb909edb76c4..5358a5facdee 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -721,7 +721,7 @@ enum { * * Fields with static values for the port. Initialized by the * port_info struct supplied to the registration call. - * @port_num: NVME-FC transport subsytem port number + * @port_num: NVME-FC transport subsystem port number * @node_name: FC WWNN for the port * @port_name: FC WWPN for the port * @private: pointer to memory allocated alongside the local port diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 959e0bd9a913..75470159a194 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -12,6 +12,7 @@ #define NVME_TCP_DISC_PORT 8009 #define NVME_TCP_ADMIN_CCSZ SZ_8K #define NVME_TCP_DIGEST_LENGTH 4 +#define NVME_TCP_MIN_MAXH2CDATA 4096 enum nvme_tcp_pfv { NVME_TCP_PFV_1_0 = 0x0, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 855dd9b3e84b..4f44f83817a9 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -43,6 +43,12 @@ enum nvme_ctrl_type { NVME_CTRL_ADMIN = 3, /* Administrative controller */ }; +enum nvme_dctype { + NVME_DCTYPE_NOT_REPORTED = 0, + NVME_DCTYPE_DDC = 1, /* Direct Discovery Controller */ + NVME_DCTYPE_CDC = 2, /* Central Discovery Controller */ +}; + /* Address Family codes for Discovery Log Page entry ADRFAM field */ enum { NVMF_ADDR_FAMILY_PCI = 0, /* PCIe */ @@ -238,6 +244,7 @@ enum { enum nvme_ctrl_attr { NVME_CTRL_ATTR_HID_128_BIT = (1 << 0), NVME_CTRL_ATTR_TBKAS = (1 << 6), + NVME_CTRL_ATTR_ELBAS = (1 << 15), }; struct nvme_id_ctrl { @@ -320,7 +327,9 @@ struct nvme_id_ctrl { __le16 icdoff; __u8 ctrattr; __u8 msdbd; - __u8 rsvd1804[244]; + __u8 rsvd1804[2]; + __u8 dctype; + __u8 rsvd1807[241]; struct nvme_id_power_state psd[32]; __u8 vs[1024]; }; @@ -391,8 +400,7 @@ struct nvme_id_ns { __le16 endgid; __u8 nguid[16]; __u8 eui64[8]; - struct nvme_lbaf lbaf[16]; - __u8 rsvd192[192]; + struct nvme_lbaf lbaf[64]; __u8 vs[3712]; }; @@ -410,8 +418,7 @@ struct nvme_id_ns_zns { __le32 rrl; __le32 frl; __u8 rsvd20[2796]; - struct nvme_zns_lbafe lbafe[16]; - __u8 rsvd3072[768]; + struct nvme_zns_lbafe lbafe[64]; __u8 vs[256]; }; @@ -420,6 +427,30 @@ struct nvme_id_ctrl_zns { __u8 rsvd1[4095]; }; +struct nvme_id_ns_nvm { + __le64 lbstm; + __u8 pic; + __u8 rsvd9[3]; + __le32 elbaf[64]; + __u8 rsvd268[3828]; +}; + +enum { + NVME_ID_NS_NVM_STS_MASK = 0x3f, + NVME_ID_NS_NVM_GUARD_SHIFT = 7, + NVME_ID_NS_NVM_GUARD_MASK = 0x3, +}; + +static inline __u8 nvme_elbaf_sts(__u32 elbaf) +{ + return elbaf & NVME_ID_NS_NVM_STS_MASK; +} + +static inline __u8 nvme_elbaf_guard_type(__u32 elbaf) +{ + return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK; +} + struct nvme_id_ctrl_nvm { __u8 vsl; __u8 wzsl; @@ -470,6 +501,8 @@ enum { NVME_NS_FEAT_IO_OPT = 1 << 4, NVME_NS_ATTR_RO = 1 << 0, NVME_NS_FLBAS_LBA_MASK = 0xf, + NVME_NS_FLBAS_LBA_UMASK = 0x60, + NVME_NS_FLBAS_LBA_SHIFT = 1, NVME_NS_FLBAS_META_EXT = 0x10, NVME_NS_NMIC_SHARED = 1 << 0, NVME_LBAF_RP_BEST = 0, @@ -488,6 +521,18 @@ enum { NVME_NS_DPS_PI_TYPE3 = 3, }; +enum { + NVME_NVM_NS_16B_GUARD = 0, + NVME_NVM_NS_32B_GUARD = 1, + NVME_NVM_NS_64B_GUARD = 2, +}; + +static inline __u8 nvme_lbaf_index(__u8 flbas) +{ + return (flbas & NVME_NS_FLBAS_LBA_MASK) | + ((flbas & NVME_NS_FLBAS_LBA_UMASK) >> NVME_NS_FLBAS_LBA_SHIFT); +} + /* Identify Namespace Metadata Capabilities (MC): */ enum { NVME_MC_EXTENDED_LBA = (1 << 0), @@ -834,7 +879,8 @@ struct nvme_rw_command { __u8 flags; __u16 command_id; __le32 nsid; - __u64 rsvd2; + __le32 cdw2; + __le32 cdw3; __le64 metadata; union nvme_data_ptr dptr; __le64 slba; @@ -988,11 +1034,14 @@ enum { struct nvme_feat_host_behavior { __u8 acre; - __u8 resv1[511]; + __u8 etdas; + __u8 lbafee; + __u8 resv1[509]; }; enum { NVME_ENABLE_ACRE = 1, + NVME_ENABLE_LBAFEE = 1, }; /* Admin commands */ @@ -1636,6 +1685,7 @@ enum { NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, + NVME_SC_MORE = 0x2000, NVME_SC_DNR = 0x4000, }; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 98efb7b5660d..50caa117cb62 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,8 @@ struct nvmem_keepout { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin + * @wp-gpio: Write protect pin + * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is @@ -92,6 +93,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool ignore_wp; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; @@ -133,8 +135,6 @@ void nvmem_unregister(struct nvmem_device *nvmem); struct nvmem_device *devm_nvmem_register(struct device *dev, const struct nvmem_config *cfg); -int devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem); - void nvmem_add_cell_table(struct nvmem_cell_table *table); void nvmem_del_cell_table(struct nvmem_cell_table *table); @@ -153,12 +153,6 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c) return nvmem_register(c); } -static inline int -devm_nvmem_unregister(struct device *dev, struct nvmem_device *nvmem) -{ - return -EOPNOTSUPP; -} - static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {} static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {} diff --git a/include/linux/objtool.h b/include/linux/objtool.h index aca52db2f3f3..586d35720f13 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -77,6 +77,18 @@ struct unwind_hint { #define STACK_FRAME_NON_STANDARD_FP(func) #endif +#define ANNOTATE_NOENDBR \ + "986: \n\t" \ + ".pushsection .discard.noendbr\n\t" \ + _ASM_PTR " 986b\n\t" \ + ".popsection\n\t" + +#define ASM_REACHABLE \ + "998:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long 998b - .\n\t" \ + ".popsection\n\t" + #else /* __ASSEMBLY__ */ /* @@ -129,6 +141,20 @@ struct unwind_hint { .popsection .endm +.macro ANNOTATE_NOENDBR +.Lhere_\@: + .pushsection .discard.noendbr + .quad .Lhere_\@ + .popsection +.endm + +.macro REACHABLE +.Lhere_\@: + .pushsection .discard.reachable + .long .Lhere_\@ - . + .popsection +.endm + #endif /* __ASSEMBLY__ */ #else /* !CONFIG_STACK_VALIDATION */ @@ -139,12 +165,18 @@ struct unwind_hint { "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) +#define ANNOTATE_NOENDBR +#define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm +.macro ANNOTATE_NOENDBR +.endm +.macro REACHABLE +.endm #endif #endif /* CONFIG_STACK_VALIDATION */ diff --git a/include/linux/of.h b/include/linux/of.h index ff143a027abc..04971e85fbc9 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -364,18 +364,12 @@ extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); extern int of_modalias_node(struct device_node *node, char *modalias, int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); -extern struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, - int index); -extern int of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, const char *cells_name, int index, - struct of_phandle_args *out_args); +extern int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, const char *cells_name, int cell_count, + int index, struct of_phandle_args *out_args); extern int of_parse_phandle_with_args_map(const struct device_node *np, const char *list_name, const char *stem_name, int index, struct of_phandle_args *out_args); -extern int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cells_count, int index, - struct of_phandle_args *out_args); extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); @@ -394,9 +388,6 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it, extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align)); extern int of_alias_get_id(struct device_node *np, const char *stem); extern int of_alias_get_highest_id(const char *stem); -extern int of_alias_get_alias_list(const struct of_device_id *matches, - const char *stem, unsigned long *bitmap, - unsigned int nbits); extern int of_machine_is_compatible(const char *compat); @@ -416,130 +407,6 @@ extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) -/** - * of_property_read_u8_array - Find and read an array of u8 from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 8-bit value(s) from - * it. - * - * dts entry of array should be like: - * ``property = /bits/ 8 <0x50 0x60 0x70>;`` - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u8 value can be decoded. - */ -static inline int of_property_read_u8_array(const struct device_node *np, - const char *propname, - u8 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u8_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u16_array - Find and read an array of u16 from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 16-bit value(s) from - * it. - * - * dts entry of array should be like: - * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;`` - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u16 value can be decoded. - */ -static inline int of_property_read_u16_array(const struct device_node *np, - const char *propname, - u16 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u16_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u32_array - Find and read an array of 32 bit integers - * from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 32-bit value(s) from - * it. - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u32 value can be decoded. - */ -static inline int of_property_read_u32_array(const struct device_node *np, - const char *propname, - u32 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u32_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u64_array - Find and read an array of 64 bit integers - * from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 64-bit value(s) from - * it. - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u64 value can be decoded. - */ -static inline int of_property_read_u64_array(const struct device_node *np, - const char *propname, - u64 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u64_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - /* * struct property *prop; * const __be32 *p; @@ -734,32 +601,6 @@ static inline int of_property_count_elems_of_size(const struct device_node *np, return -ENOSYS; } -static inline int of_property_read_u8_array(const struct device_node *np, - const char *propname, u8 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u16_array(const struct device_node *np, - const char *propname, u16 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u32_array(const struct device_node *np, - const char *propname, - u32 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u64_array(const struct device_node *np, - const char *propname, - u64 *out_values, size_t sz) -{ - return -ENOSYS; -} - static inline int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value) { @@ -865,18 +706,12 @@ static inline int of_property_read_string_helper(const struct device_node *np, return -ENOSYS; } -static inline struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, - int index) -{ - return NULL; -} - -static inline int of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, - const char *cells_name, - int index, - struct of_phandle_args *out_args) +static inline int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int cell_count, + int index, + struct of_phandle_args *out_args) { return -ENOSYS; } @@ -890,13 +725,6 @@ static inline int of_parse_phandle_with_args_map(const struct device_node *np, return -ENOSYS; } -static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cells_count, int index, - struct of_phandle_args *out_args) -{ - return -ENOSYS; -} - static inline int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name) @@ -935,13 +763,6 @@ static inline int of_alias_get_highest_id(const char *stem) return -ENOSYS; } -static inline int of_alias_get_alias_list(const struct of_device_id *matches, - const char *stem, unsigned long *bitmap, - unsigned int nbits) -{ - return -ENOSYS; -} - static inline int of_machine_is_compatible(const char *compat) { return 0; @@ -1078,6 +899,117 @@ static inline bool of_node_is_type(const struct device_node *np, const char *typ } /** + * of_parse_phandle - Resolve a phandle property to a device_node pointer + * @np: Pointer to device node holding phandle property + * @phandle_name: Name of property holding a phandle value + * @index: For properties holding a table of phandles, this is the index into + * the table + * + * Return: The device_node pointer with refcount incremented. Use + * of_node_put() on it when done. + */ +static inline struct device_node *of_parse_phandle(const struct device_node *np, + const char *phandle_name, + int index) +{ + struct of_phandle_args args; + + if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0, + index, &args)) + return NULL; + + return args.np; +} + +/** + * of_parse_phandle_with_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cells_name: property name that specifies phandles' arguments count + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * This function is useful to parse lists of phandles and their arguments. + * Returns 0 on success and fills out_args, on error returns appropriate + * errno value. + * + * Caller is responsible to call of_node_put() on the returned out_args->np + * pointer. + * + * Example:: + * + * phandle1: node1 { + * #list-cells = <2>; + * }; + * + * phandle2: node2 { + * #list-cells = <1>; + * }; + * + * node3 { + * list = <&phandle1 1 2 &phandle2 3>; + * }; + * + * To get a device_node of the ``node2`` node you may call this: + * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args); + */ +static inline int of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int index, + struct of_phandle_args *out_args) +{ + int cell_count = -1; + + /* If cells_name is NULL we assume a cell count of 0 */ + if (!cells_name) + cell_count = 0; + + return __of_parse_phandle_with_args(np, list_name, cells_name, + cell_count, index, out_args); +} + +/** + * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cell_count: number of argument cells following the phandle + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * This function is useful to parse lists of phandles and their arguments. + * Returns 0 on success and fills out_args, on error returns appropriate + * errno value. + * + * Caller is responsible to call of_node_put() on the returned out_args->np + * pointer. + * + * Example:: + * + * phandle1: node1 { + * }; + * + * phandle2: node2 { + * }; + * + * node3 { + * list = <&phandle1 0 2 &phandle2 2 3>; + * }; + * + * To get a device_node of the ``node2`` node you may call this: + * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args); + */ +static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, + const char *list_name, + int cell_count, + int index, + struct of_phandle_args *out_args) +{ + return __of_parse_phandle_with_args(np, list_name, NULL, cell_count, + index, out_args); +} + +/** * of_property_count_u8_elems - Count the number of u8 elements in a property * * @np: device node from which the property value is to be read. @@ -1236,6 +1168,130 @@ static inline bool of_property_read_bool(const struct device_node *np, return prop ? true : false; } +/** + * of_property_read_u8_array - Find and read an array of u8 from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 8-bit value(s) from + * it. + * + * dts entry of array should be like: + * ``property = /bits/ 8 <0x50 0x60 0x70>;`` + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u8 value can be decoded. + */ +static inline int of_property_read_u8_array(const struct device_node *np, + const char *propname, + u8 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u8_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u16_array - Find and read an array of u16 from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 16-bit value(s) from + * it. + * + * dts entry of array should be like: + * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;`` + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u16 value can be decoded. + */ +static inline int of_property_read_u16_array(const struct device_node *np, + const char *propname, + u16 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u16_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u32_array - Find and read an array of 32 bit integers + * from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 32-bit value(s) from + * it. + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u32 value can be decoded. + */ +static inline int of_property_read_u32_array(const struct device_node *np, + const char *propname, + u32 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u32_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u64_array - Find and read an array of 64 bit integers + * from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 64-bit value(s) from + * it. + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u64 value can be decoded. + */ +static inline int of_property_read_u64_array(const struct device_node *np, + const char *propname, + u64 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u64_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + static inline int of_property_read_u8(const struct device_node *np, const char *propname, u8 *out_value) diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index cf48983d3c86..d69ad5bb1eb1 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -58,10 +58,9 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); extern uint32_t of_get_flat_dt_phandle(unsigned long node); -extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, - int depth, void *data); -extern int early_init_dt_scan_memory(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_chosen(char *cmdline); +extern int early_init_dt_scan_memory(void); +extern void early_init_dt_check_for_usable_mem_range(void); extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); @@ -69,8 +68,7 @@ extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ -extern int early_init_dt_scan_root(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_root(void); extern bool early_init_dt_scan(void *params); extern bool early_init_dt_verify(void *params); @@ -86,6 +84,7 @@ extern void unflatten_and_copy_device_tree(void); extern void early_init_devtree(void *); extern void early_get_first_memblock_info(void *, phys_addr_t *); #else /* CONFIG_OF_EARLY_FLATTREE */ +static inline void early_init_dt_check_for_usable_mem_range(void) {} static inline int early_init_dt_scan_chosen_stdout(void) { return -ENODEV; } static inline void early_init_fdt_scan_reserved_mem(void) {} static inline void early_init_fdt_reserve_self(void) {} diff --git a/include/linux/once.h b/include/linux/once.h index d361fb14ac3a..f54523052bbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -38,7 +38,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, #define DO_ONCE(func, ...) \ ({ \ bool ___ret = false; \ - static bool ___done = false; \ + static bool __section(".data.once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 4669632bd72b..f1221d11f8e5 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -4,6 +4,7 @@ #include <linux/compiler.h> #include <linux/limits.h> +#include <linux/const.h> /* * We need to compute the minimum and maximum values representable in a given @@ -118,81 +119,94 @@ static inline bool __must_check __must_check_overflow(bool overflow) })) /** - * array_size() - Calculate size of 2-dimensional array. - * - * @a: dimension one - * @b: dimension two + * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX * - * Calculates size of 2-dimensional array: @a * @b. + * @factor1: first factor + * @factor2: second factor * - * Returns: number of bytes needed to represent the array or SIZE_MAX on - * overflow. + * Returns: calculate @factor1 * @factor2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t array_size(size_t a, size_t b) +static inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) + if (check_mul_overflow(factor1, factor2, &bytes)) return SIZE_MAX; return bytes; } /** - * array3_size() - Calculate size of 3-dimensional array. + * size_add() - Calculate size_t addition with saturation at SIZE_MAX * - * @a: dimension one - * @b: dimension two - * @c: dimension three - * - * Calculates size of 3-dimensional array: @a * @b * @c. + * @addend1: first addend + * @addend2: second addend * - * Returns: number of bytes needed to represent the array or SIZE_MAX on - * overflow. + * Returns: calculate @addend1 + @addend2, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. The + * lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +static inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) - return SIZE_MAX; - if (check_mul_overflow(bytes, c, &bytes)) + if (check_add_overflow(addend1, addend2, &bytes)) return SIZE_MAX; return bytes; } -/* - * Compute a*b+c, returning SIZE_MAX on overflow. Internal helper for - * struct_size() below. +/** + * size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX + * + * @minuend: value to subtract from + * @subtrahend: value to subtract from @minuend + * + * Returns: calculate @minuend - @subtrahend, both promoted to size_t, + * with any overflow causing the return value to be SIZE_MAX. For + * composition with the size_add() and size_mul() helpers, neither + * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). + * The lvalue must be size_t to avoid implicit type conversion. */ -static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) +static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; - if (check_mul_overflow(a, b, &bytes)) - return SIZE_MAX; - if (check_add_overflow(bytes, c, &bytes)) + if (minuend == SIZE_MAX || subtrahend == SIZE_MAX || + check_sub_overflow(minuend, subtrahend, &bytes)) return SIZE_MAX; return bytes; } /** - * struct_size() - Calculate size of structure with trailing array. - * @p: Pointer to the structure. - * @member: Name of the array member. - * @count: Number of elements in the array. + * array_size() - Calculate size of 2-dimensional array. * - * Calculates size of memory needed for structure @p followed by an - * array of @count number of @member elements. + * @a: dimension one + * @b: dimension two * - * Return: number of bytes needed or SIZE_MAX on overflow. + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. */ -#define struct_size(p, member, count) \ - __ab_c_size(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member),\ - sizeof(*(p))) +#define array_size(a, b) size_mul(a, b) + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +#define array3_size(a, b, c) size_mul(size_mul(a, b), c) /** * flex_array_size() - Calculate size of a flexible array member @@ -208,7 +222,25 @@ static inline __must_check size_t __ab_c_size(size_t a, size_t b, size_t c) * Return: number of bytes needed or SIZE_MAX on overflow. */ #define flex_array_size(p, member, count) \ - array_size(count, \ - sizeof(*(p)->member) + __must_be_array((p)->member)) + __builtin_choose_expr(__is_constexpr(count), \ + (count) * sizeof(*(p)->member) + __must_be_array((p)->member), \ + size_mul(count, sizeof(*(p)->member) + __must_be_array((p)->member))) + +/** + * struct_size() - Calculate size of structure with trailing flexible array. + * + * @p: Pointer to the structure. + * @member: Name of the array member. + * @count: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @count number of @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, count) \ + __builtin_choose_expr(__is_constexpr(count), \ + sizeof(*(p)) + flex_array_size(p, member, count), \ + size_add(sizeof(*(p)), flex_array_size(p, member, count))) #endif /* __LINUX_OVERFLOW_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..9d8eeaa67d05 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -68,9 +68,6 @@ * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * - * PG_uptodate tells whether the page's contents is valid. When a read - * completes, the page becomes uptodate, unless a disk I/O error happened. - * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * @@ -193,13 +190,81 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +DECLARE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, + hugetlb_free_vmemmap_enabled_key); + +static __always_inline bool hugetlb_free_vmemmap_enabled(void) +{ + return static_branch_maybe(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, + &hugetlb_free_vmemmap_enabled_key); +} + +/* + * If the feature of freeing some vmemmap pages associated with each HugeTLB + * page is enabled, the head vmemmap page frame is reused and all of the tail + * vmemmap addresses map to the head vmemmap page frame (furture details can + * refer to the figure at the head of the mm/hugetlb_vmemmap.c). In other + * words, there are more than one page struct with PG_head associated with each + * HugeTLB page. We __know__ that there is only one head page struct, the tail + * page structs with PG_head are fake head page structs. We need an approach + * to distinguish between those two different types of page structs so that + * compound_head() can return the real head page struct when the parameter is + * the tail page struct but with PG_head. + * + * The page_fixed_fake_head() returns the real head page struct if the @page is + * fake page head, otherwise, returns @page which can either be a true page + * head or tail. + */ +static __always_inline const struct page *page_fixed_fake_head(const struct page *page) +{ + if (!hugetlb_free_vmemmap_enabled()) + return page; + + /* + * Only addresses aligned with PAGE_SIZE of struct page may be fake head + * struct page. The alignment check aims to avoid access the fields ( + * e.g. compound_head) of the @page[1]. It can avoid touch a (possibly) + * cold cacheline in some cases. + */ + if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) && + test_bit(PG_head, &page->flags)) { + /* + * We can safely access the field of the @page[1] with PG_head + * because the @page is a compound page composed with at least + * two contiguous pages. + */ + unsigned long head = READ_ONCE(page[1].compound_head); + + if (likely(head & 1)) + return (const struct page *)(head - 1); + } + return page; +} +#else +static inline const struct page *page_fixed_fake_head(const struct page *page) +{ + return page; +} + +static inline bool hugetlb_free_vmemmap_enabled(void) +{ + return false; +} +#endif + +static __always_inline int page_is_fake_head(struct page *page) +{ + return page_fixed_fake_head(page) != page; +} + static inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return head - 1; - return (unsigned long)page; + return (unsigned long)page_fixed_fake_head(page); } #define compound_head(page) ((typeof(page))_compound_head(page)) @@ -234,12 +299,13 @@ static inline unsigned long _compound_head(const struct page *page) static __always_inline int PageTail(struct page *page) { - return READ_ONCE(page->compound_head) & 1; + return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page); } static __always_inline int PageCompound(struct page *page) { - return test_bit(PG_head, &page->flags) || PageTail(page); + return test_bit(PG_head, &page->flags) || + READ_ONCE(page->compound_head) & 1; } #define PAGE_POISON_PATTERN -1l @@ -383,7 +449,7 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \ +static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ @@ -415,7 +481,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) -PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) +PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) @@ -522,7 +588,11 @@ PAGEFLAG_FALSE(Uncached, uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) +#define MAGIC_HWPOISON 0x48575053U /* HWPS */ +extern void SetPageHWPoisonTakenOff(struct page *page); +extern void ClearPageHWPoisonTakenOff(struct page *page); extern bool take_page_off_buddy(struct page *page); +extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 @@ -615,6 +685,16 @@ TESTPAGEFLAG_FALSE(Ksm, ksm) u64 stable_page_flags(struct page *page); +/** + * folio_test_uptodate - Is this folio up to date? + * @folio: The folio. + * + * The uptodate flag is set on a folio when every byte in the folio is + * at least as new as the corresponding bytes on storage. Anonymous + * and CoW folios are always uptodate. If the folio is not uptodate, + * some of the bytes in it may be; see the is_partially_uptodate() + * address_space operation. + */ static inline bool folio_test_uptodate(struct folio *folio) { bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); @@ -684,7 +764,20 @@ static inline bool test_set_page_writeback(struct page *page) return set_page_writeback(page); } -__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) +static __always_inline bool folio_test_head(struct folio *folio) +{ + return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY)); +} + +static __always_inline int PageHead(struct page *page) +{ + PF_POISONED_CHECK(page); + return test_bit(PG_head, &page->flags) && !page_is_fake_head(page); +} + +__SETPAGEFLAG(Head, head, PF_ANY) +__CLEARPAGEFLAG(Head, head, PF_ANY) +CLEARPAGEFLAG(Head, head, PF_ANY) /** * folio_test_large() - Does this folio contain more than one page? @@ -907,44 +1000,7 @@ PAGE_TYPE_OPS(Guard, guard) extern bool is_free_buddy_page(struct page *page); -__PAGEFLAG(Isolated, isolated, PF_ANY); - -/* - * If network-based swap is enabled, sl*b must keep track of whether pages - * were allocated from pfmemalloc reserves. - */ -static inline int PageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - return PageActive(page); -} - -/* - * A version of PageSlabPfmemalloc() for opportunistic checks where the page - * might have been freed under us and not be a PageSlab anymore. - */ -static inline int __PageSlabPfmemalloc(struct page *page) -{ - return PageActive(page); -} - -static inline void SetPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - SetPageActive(page); -} - -static inline void __ClearPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - __ClearPageActive(page); -} - -static inline void ClearPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - ClearPageActive(page); -} +PAGEFLAG(Isolated, isolated, PF_ANY); #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 83abf95e9fa7..4663dfed1293 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -13,7 +13,6 @@ * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -extern struct page_ext_operations page_idle_ops; static inline bool folio_test_young(struct folio *folio) { diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h new file mode 100644 index 000000000000..01e16c7696ec --- /dev/null +++ b/include/linux/page_table_check.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2021, Google LLC. + * Pasha Tatashin <pasha.tatashin@soleen.com> + */ +#ifndef __LINUX_PAGE_TABLE_CHECK_H +#define __LINUX_PAGE_TABLE_CHECK_H + +#ifdef CONFIG_PAGE_TABLE_CHECK +#include <linux/jump_label.h> + +extern struct static_key_true page_table_check_disabled; +extern struct page_ext_operations page_table_check_ops; + +void __page_table_check_zero(struct page *page, unsigned int order); +void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t pte); +void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, + pmd_t pmd); +void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, + pud_t pud); +void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd); + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear(mm, addr, pte); +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_clear(mm, addr, pmd); +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_clear(mm, addr, pud); +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_set(mm, addr, ptep, pte); +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_set(mm, addr, pmdp, pmd); +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_set(mm, addr, pudp, pud); +} + +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear_range(mm, addr, pmd); +} + +#else + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ +} + +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ +} + +#endif /* CONFIG_PAGE_TABLE_CHECK */ +#endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 973fd731a520..83c7248053a1 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -37,8 +37,11 @@ extern unsigned int pageblock_order; #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -/* Huge pages are a constant size */ -#define pageblock_order HUGETLB_PAGE_ORDER +/* + * Huge pages are a constant size, but don't exceed the maximum allocation + * granularity. + */ +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 605246452305..a8d0b327b066 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -16,7 +16,121 @@ #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> -struct pagevec; +struct folio_batch; + +unsigned long invalidate_mapping_pages(struct address_space *mapping, + pgoff_t start, pgoff_t end); + +static inline void invalidate_remote_inode(struct inode *inode) +{ + if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode)) + invalidate_mapping_pages(inode->i_mapping, 0, -1); +} +int invalidate_inode_pages2(struct address_space *mapping); +int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end); +int write_inode_now(struct inode *, int sync); +int filemap_fdatawrite(struct address_space *); +int filemap_flush(struct address_space *); +int filemap_fdatawait_keep_errors(struct address_space *mapping); +int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); +int filemap_fdatawait_range_keep_errors(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + +bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); +int filemap_write_and_wait_range(struct address_space *mapping, + loff_t lstart, loff_t lend); +int __filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end, int sync_mode); +int filemap_fdatawrite_range(struct address_space *mapping, + loff_t start, loff_t end); +int filemap_check_errors(struct address_space *mapping); +void __filemap_set_wb_err(struct address_space *mapping, int err); +int filemap_fdatawrite_wbc(struct address_space *mapping, + struct writeback_control *wbc); + +static inline int filemap_write_and_wait(struct address_space *mapping) +{ + return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); +} + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_err - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} + +/** + * file_sample_sb_err - sample the current errseq_t to test for later errors + * @file: file pointer to be sampled + * + * Grab the most current superblock-level errseq_t value for the given + * struct file. + */ +static inline errseq_t file_sample_sb_err(struct file *file) +{ + return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); +} + +/* + * Flush file data before changing attributes. Caller must hold any locks + * required to prevent further writes to this file until we're done setting + * flags. + */ +static inline int inode_drain_writes(struct inode *inode) +{ + inode_dio_wait(inode); + return filemap_write_and_wait(inode->i_mapping); +} static inline bool mapping_empty(struct address_space *mapping) { @@ -192,9 +306,14 @@ static inline void mapping_set_large_folios(struct address_space *mapping) __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* + * Large folio support currently depends on THP. These dependencies are + * being worked on but are not yet fixed. + */ static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && + test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -212,7 +331,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } @@ -222,7 +341,7 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else - WARN_ON_ONCE(1); + WARN_ON_ONCE(mapping_large_folio_support(mapping) == 0); #endif } @@ -283,17 +402,6 @@ static inline struct inode *folio_inode(struct folio *folio) return folio->mapping->host; } -static inline bool page_cache_add_speculative(struct page *page, int count) -{ - VM_BUG_ON_PAGE(PageTail(page), page); - return folio_ref_try_add_rcu((struct folio *)page, count); -} - -static inline bool page_cache_get_speculative(struct page *page) -{ - return page_cache_add_speculative(page, 1); -} - /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. @@ -424,6 +532,24 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, } /** + * filemap_lock_folio - Find and lock a folio. + * @mapping: The address_space to search. + * @index: The page index. + * + * Looks up the page cache entry at @mapping & @index. If a folio is + * present, it is returned locked with an increased refcount. + * + * Context: May sleep. + * Return: A folio or %NULL if there is no folio in the cache for this + * index. Will not return a shadow, swap or DAX entry. + */ +static inline struct folio *filemap_lock_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, FGP_LOCK, 0); +} + +/** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index @@ -512,15 +638,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -/* Does this page contain this index? */ -static inline bool thp_contains(struct page *head, pgoff_t index) -{ - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (PageHuge(head)) - return head->index == index; - return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); -} - #define swapcache_index(folio) __page_file_index(&(folio)->page) /** @@ -601,18 +718,9 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) return head + (index & (thp_nr_pages(head) - 1)); } -unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); -static inline unsigned find_get_pages(struct address_space *mapping, - pgoff_t *start, unsigned int nr_pages, - struct page **pages) -{ - return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, - pages); -} unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, @@ -638,17 +746,25 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); +struct folio *read_cache_folio(struct address_space *, pgoff_t index, + filler_t *filler, void *data); +struct page *read_cache_page(struct address_space *, pgoff_t index, + filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, - pgoff_t index, void *data) + pgoff_t index, struct file *file) { - return read_cache_page(mapping, index, NULL, data); + return read_cache_page(mapping, index, NULL, file); +} + +static inline struct folio *read_mapping_folio(struct address_space *mapping, + pgoff_t index, struct file *file) +{ + return read_cache_folio(mapping, index, NULL, file); } /* @@ -717,6 +833,17 @@ static inline loff_t folio_file_pos(struct folio *folio) return page_file_offset(&folio->page); } +/* + * Get the offset in PAGE_SIZE (even for hugetlb folios). + * (TODO: hugetlb folios should have ->index in PAGE_SIZE) + */ +static inline pgoff_t folio_pgoff(struct folio *folio) +{ + if (unlikely(folio_test_hugetlb(folio))) + return hugetlb_basepage_index(&folio->page); + return folio->index; +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); @@ -868,7 +995,7 @@ static inline int wait_on_page_locked_killable(struct page *page) return folio_wait_locked_killable(page_folio(page)); } -int put_and_wait_on_page_locked(struct page *page, int state); +int folio_put_wait_locked(struct folio *folio, int state); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); @@ -882,13 +1009,7 @@ static inline void __set_page_dirty(struct page *page, { __folio_mark_dirty(page_folio(page), mapping, warn); } -void folio_account_cleaned(struct folio *folio, struct address_space *mapping, - struct bdi_writeback *wb); -static inline void account_page_cleaned(struct page *page, - struct address_space *mapping, struct bdi_writeback *wb) -{ - return folio_account_cleaned(page_folio(page), mapping, wb); -} +void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { @@ -902,6 +1023,7 @@ static inline void cancel_dirty_page(struct page *page) } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); +void folio_invalidate(struct folio *folio, size_t offset, size_t length); int __must_check folio_write_one(struct folio *folio); static inline int __must_check write_one_page(struct page *page) { @@ -909,7 +1031,7 @@ static inline int __must_check write_one_page(struct page *page) } int __set_page_dirty_nobuffers(struct page *page); -int __set_page_dirty_no_writeback(struct page *page); +bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); void page_endio(struct page *page, bool is_write, int err); @@ -935,11 +1057,18 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); -extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +void filemap_remove_folio(struct folio *folio); +void delete_from_page_cache(struct page *page); +void __filemap_remove_folio(struct folio *folio, void *shadow); +static inline void __delete_from_page_cache(struct page *page, void *shadow) +{ + __filemap_remove_folio(page_folio(page), shadow); +} void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec); + struct folio_batch *fbatch); +int try_to_release_page(struct page *page, gfp_t gfp); +bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); @@ -963,6 +1092,35 @@ static inline int add_to_page_cache(struct page *page, int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); +bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +/** + * filemap_range_needs_writeback - check if range potentially needs writeback + * @mapping: address space within which to check + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Find at least one page in the range supplied, usually used to check if + * direct writing in this range will trigger a writeback. Used by O_DIRECT + * read/write with IOCB_NOWAIT, to see if the caller needs to do + * filemap_write_and_wait_range() before proceeding. + * + * Return: %true if the caller should do filemap_write_and_wait_range() before + * doing O_DIRECT to a page in this range, %false otherwise. + */ +static inline bool filemap_range_needs_writeback(struct address_space *mapping, + loff_t start_byte, + loff_t end_byte) +{ + if (!mapping->nrpages) + return false; + if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && + !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + return false; + return filemap_range_has_writeback(mapping, start_byte, end_byte); +} + /** * struct readahead_control - Describes a readahead request. * @@ -1002,7 +1160,7 @@ struct readahead_control { void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); -void page_cache_async_ra(struct readahead_control *, struct page *, +void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); @@ -1049,7 +1207,7 @@ void page_cache_async_readahead(struct address_space *mapping, struct page *page, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page, req_count); + page_cache_async_ra(&ractl, page_folio(page), req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) @@ -1126,16 +1284,6 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); - - /* - * The page cache isn't using multi-index entries yet, - * so the xas cursor needs to be manually moved to the - * next index. This can be removed once the page cache - * is converted. - */ - if (PageHead(page)) - xas_set(&xas, rac->_index + rac->_batch_count); - if (i == array_sz) break; } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 7f3f19065a9f..67b1246f136b 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -15,8 +15,10 @@ #define PAGEVEC_SIZE 15 struct page; +struct folio; struct address_space; +/* Layout must match folio_batch */ struct pagevec { unsigned char nr; bool percpu_pvec_drained; @@ -25,7 +27,6 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); -void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); @@ -81,4 +82,69 @@ static inline void pagevec_release(struct pagevec *pvec) __pagevec_release(pvec); } +/** + * struct folio_batch - A collection of folios. + * + * The folio_batch is used to amortise the cost of retrieving and + * operating on a set of folios. The order of folios in the batch may be + * significant (eg delete_from_page_cache_batch()). Some users of the + * folio_batch store "exceptional" entries in it which can be removed + * by calling folio_batch_remove_exceptionals(). + */ +struct folio_batch { + unsigned char nr; + bool percpu_pvec_drained; + struct folio *folios[PAGEVEC_SIZE]; +}; + +/* Layout must match pagevec */ +static_assert(sizeof(struct pagevec) == sizeof(struct folio_batch)); +static_assert(offsetof(struct pagevec, pages) == + offsetof(struct folio_batch, folios)); + +/** + * folio_batch_init() - Initialise a batch of folios + * @fbatch: The folio batch. + * + * A freshly initialised folio_batch contains zero folios. + */ +static inline void folio_batch_init(struct folio_batch *fbatch) +{ + fbatch->nr = 0; + fbatch->percpu_pvec_drained = false; +} + +static inline unsigned int folio_batch_count(struct folio_batch *fbatch) +{ + return fbatch->nr; +} + +static inline unsigned int fbatch_space(struct folio_batch *fbatch) +{ + return PAGEVEC_SIZE - fbatch->nr; +} + +/** + * folio_batch_add() - Add a folio to a batch. + * @fbatch: The folio batch. + * @folio: The folio to add. + * + * The folio is added to the end of the batch. + * The batch must have previously been initialised using folio_batch_init(). + * + * Return: The number of slots still available. + */ +static inline unsigned folio_batch_add(struct folio_batch *fbatch, + struct folio *folio) +{ + fbatch->folios[fbatch->nr++] = folio; + return fbatch_space(fbatch); +} + +static inline void folio_batch_release(struct folio_batch *fbatch) +{ + pagevec_release((struct pagevec *)fbatch); +} + +void folio_batch_remove_exceptionals(struct folio_batch *fbatch); #endif /* _LINUX_PAGEVEC_H */ diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index 6f7949b2fd8d..abeba356bc3f 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -2,7 +2,7 @@ #ifndef _LINUX_PART_STAT_H #define _LINUX_PART_STAT_H -#include <linux/genhd.h> +#include <linux/blkdev.h> #include <asm/local.h> struct disk_stats { diff --git a/include/linux/pci.h b/include/linux/pci.h index 18a75c8e615c..b957eeb89c7a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -155,6 +155,15 @@ enum pci_interrupt_pin { #define PCI_NUM_INTX 4 /* + * Reading from a device that doesn't respond typically returns ~0. A + * successful read from a device may also return ~0, so you need additional + * information to reliably identify errors. + */ +#define PCI_ERROR_RESPONSE (~0ULL) +#define PCI_SET_ERROR_RESPONSE(val) (*(val) = ((typeof(*(val))) PCI_ERROR_RESPONSE)) +#define PCI_POSSIBLE_ERROR(val) ((val) == ((typeof(val)) PCI_ERROR_RESPONSE)) + +/* * pci_power_t values must match the bits in the Capabilities PME_Support * and Control/Status PowerState fields in the Power Management capability. */ @@ -425,7 +434,8 @@ struct pci_dev { unsigned int ats_enabled:1; /* Address Translation Svc */ unsigned int pasid_enabled:1; /* Process Address Space ID */ unsigned int pri_enabled:1; /* Page Request Interface */ - unsigned int is_managed:1; + unsigned int is_managed:1; /* Managed via devres */ + unsigned int is_msi_managed:1; /* MSI release via devres installed */ unsigned int needs_freset:1; /* Requires fundamental reset */ unsigned int state_saved:1; unsigned int is_physfn:1; @@ -455,6 +465,7 @@ struct pci_dev { unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ + unsigned int rom_bar_overlap:1; /* ROM BAR disable broken */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ @@ -473,7 +484,8 @@ struct pci_dev { u8 ptm_granularity; #endif #ifdef CONFIG_PCI_MSI - const struct attribute_group **msi_irq_groups; + void __iomem *msix_base; + raw_spinlock_t msi_lock; #endif struct pci_vpd vpd; #ifdef CONFIG_PCIE_DPC @@ -656,6 +668,7 @@ struct pci_bus { struct bin_attribute *legacy_io; /* Legacy I/O for this bus */ struct bin_attribute *legacy_mem; /* Legacy mem */ unsigned int is_added:1; + unsigned int unsafe_warn:1; /* warned about RW1C config write */ }; #define to_pci_bus(n) container_of(n, struct pci_bus, dev) @@ -1775,7 +1788,10 @@ static inline struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from) { return NULL; } -#define pci_dev_present(ids) (0) + +static inline int pci_dev_present(const struct pci_device_id *ids) +{ return 0; } + #define no_pci_devices() (1) #define pci_dev_put(dev) do { } while (0) @@ -2151,7 +2167,8 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar); #ifdef CONFIG_PCI_IOV int pci_iov_virtfn_bus(struct pci_dev *dev, int id); int pci_iov_virtfn_devfn(struct pci_dev *dev, int id); - +int pci_iov_vf_id(struct pci_dev *dev); +void *pci_iov_get_pf_drvdata(struct pci_dev *dev, struct pci_driver *pf_driver); int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn); void pci_disable_sriov(struct pci_dev *dev); @@ -2179,6 +2196,18 @@ static inline int pci_iov_virtfn_devfn(struct pci_dev *dev, int id) { return -ENOSYS; } + +static inline int pci_iov_vf_id(struct pci_dev *dev) +{ + return -ENOSYS; +} + +static inline void *pci_iov_get_pf_drvdata(struct pci_dev *dev, + struct pci_driver *pf_driver) +{ + return ERR_PTR(-EINVAL); +} + static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn) { return -ENODEV; } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 011f2f1ea5bb..0178823ce8c2 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -60,6 +60,8 @@ #define PCI_CLASS_BRIDGE_EISA 0x0602 #define PCI_CLASS_BRIDGE_MC 0x0603 #define PCI_CLASS_BRIDGE_PCI 0x0604 +#define PCI_CLASS_BRIDGE_PCI_NORMAL 0x060400 +#define PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE 0x060401 #define PCI_CLASS_BRIDGE_PCMCIA 0x0605 #define PCI_CLASS_BRIDGE_NUBUS 0x0606 #define PCI_CLASS_BRIDGE_CARDBUS 0x0607 @@ -555,6 +557,7 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F3 0x14b0 #define PCI_DEVICE_ID_AMD_19H_M40H_DF_F3 0x167c #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 @@ -1964,24 +1967,6 @@ #define PCI_DEVICE_ID_APPLICOM_PCI2000PFB 0x0003 #define PCI_VENDOR_ID_MOXA 0x1393 -#define PCI_DEVICE_ID_MOXA_RC7000 0x0001 -#define PCI_DEVICE_ID_MOXA_CP102 0x1020 -#define PCI_DEVICE_ID_MOXA_CP102UL 0x1021 -#define PCI_DEVICE_ID_MOXA_CP102U 0x1022 -#define PCI_DEVICE_ID_MOXA_C104 0x1040 -#define PCI_DEVICE_ID_MOXA_CP104U 0x1041 -#define PCI_DEVICE_ID_MOXA_CP104JU 0x1042 -#define PCI_DEVICE_ID_MOXA_CP104EL 0x1043 -#define PCI_DEVICE_ID_MOXA_CT114 0x1140 -#define PCI_DEVICE_ID_MOXA_CP114 0x1141 -#define PCI_DEVICE_ID_MOXA_CP118U 0x1180 -#define PCI_DEVICE_ID_MOXA_CP118EL 0x1181 -#define PCI_DEVICE_ID_MOXA_CP132 0x1320 -#define PCI_DEVICE_ID_MOXA_CP132U 0x1321 -#define PCI_DEVICE_ID_MOXA_CP134U 0x1340 -#define PCI_DEVICE_ID_MOXA_C168 0x1680 -#define PCI_DEVICE_ID_MOXA_CP168U 0x1681 -#define PCI_DEVICE_ID_MOXA_CP168EL 0x1682 #define PCI_DEVICE_ID_MOXA_CP204J 0x2040 #define PCI_DEVICE_ID_MOXA_C218 0x2180 #define PCI_DEVICE_ID_MOXA_C320 0x3200 @@ -2546,11 +2531,16 @@ #define PCI_DEVICE_ID_KORENIX_JETCARDF3 0x17ff #define PCI_VENDOR_ID_HUAWEI 0x19e5 +#define PCI_DEVICE_ID_HUAWEI_ZIP_VF 0xa251 +#define PCI_DEVICE_ID_HUAWEI_SEC_VF 0xa256 +#define PCI_DEVICE_ID_HUAWEI_HPRE_VF 0xa259 #define PCI_VENDOR_ID_NETRONOME 0x19ee +#define PCI_DEVICE_ID_NETRONOME_NFP3800 0x3800 #define PCI_DEVICE_ID_NETRONOME_NFP4000 0x4000 #define PCI_DEVICE_ID_NETRONOME_NFP5000 0x5000 #define PCI_DEVICE_ID_NETRONOME_NFP6000 0x6000 +#define PCI_DEVICE_ID_NETRONOME_NFP3800_VF 0x3803 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF 0x6003 #define PCI_VENDOR_ID_QMI 0x1a32 @@ -2578,6 +2568,8 @@ #define PCI_VENDOR_ID_HYGON 0x1d94 +#define PCI_VENDOR_ID_FUNGIBLE 0x1dad + #define PCI_VENDOR_ID_HXT 0x1dbf #define PCI_VENDOR_ID_TEKRAM 0x1de1 @@ -2635,8 +2627,8 @@ #define PCI_DEVICE_ID_INTEL_PXHD_0 0x0320 #define PCI_DEVICE_ID_INTEL_PXHD_1 0x0321 #define PCI_DEVICE_ID_INTEL_PXH_0 0x0329 -#define PCI_DEVICE_ID_INTEL_PXH_1 0x032A -#define PCI_DEVICE_ID_INTEL_PXHV 0x032C +#define PCI_DEVICE_ID_INTEL_PXH_1 0x032a +#define PCI_DEVICE_ID_INTEL_PXHV 0x032c #define PCI_DEVICE_ID_INTEL_80332_0 0x0330 #define PCI_DEVICE_ID_INTEL_80332_1 0x0332 #define PCI_DEVICE_ID_INTEL_80333_0 0x0370 @@ -2654,14 +2646,14 @@ #define PCI_DEVICE_ID_INTEL_MFD_SDIO2 0x0822 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 -#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F -#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E +#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084f +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095e #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 #define PCI_DEVICE_ID_INTEL_8257X_SOL 0x1062 #define PCI_DEVICE_ID_INTEL_82573E_SOL 0x1085 -#define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108F +#define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108f #define PCI_DEVICE_ID_INTEL_82815_MC 0x1130 #define PCI_DEVICE_ID_INTEL_82815_CGC 0x1132 #define PCI_DEVICE_ID_INTEL_82092AA_0 0x1221 @@ -2755,12 +2747,6 @@ #define PCI_DEVICE_ID_INTEL_82801EB_11 0x24db #define PCI_DEVICE_ID_INTEL_82801EB_12 0x24dc #define PCI_DEVICE_ID_INTEL_82801EB_13 0x24dd -#define PCI_DEVICE_ID_INTEL_ESB_1 0x25a1 -#define PCI_DEVICE_ID_INTEL_ESB_2 0x25a2 -#define PCI_DEVICE_ID_INTEL_ESB_4 0x25a4 -#define PCI_DEVICE_ID_INTEL_ESB_5 0x25a6 -#define PCI_DEVICE_ID_INTEL_ESB_9 0x25ab -#define PCI_DEVICE_ID_INTEL_ESB_10 0x25ac #define PCI_DEVICE_ID_INTEL_82820_HB 0x2500 #define PCI_DEVICE_ID_INTEL_82820_UP_HB 0x2501 #define PCI_DEVICE_ID_INTEL_82850_HB 0x2530 @@ -2775,14 +2761,15 @@ #define PCI_DEVICE_ID_INTEL_82915G_IG 0x2582 #define PCI_DEVICE_ID_INTEL_82915GM_HB 0x2590 #define PCI_DEVICE_ID_INTEL_82915GM_IG 0x2592 -#define PCI_DEVICE_ID_INTEL_5000_ERR 0x25F0 -#define PCI_DEVICE_ID_INTEL_5000_FBD0 0x25F5 -#define PCI_DEVICE_ID_INTEL_5000_FBD1 0x25F6 -#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 -#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 -#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 -#define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27A0 -#define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27A2 +#define PCI_DEVICE_ID_INTEL_ESB_1 0x25a1 +#define PCI_DEVICE_ID_INTEL_ESB_2 0x25a2 +#define PCI_DEVICE_ID_INTEL_ESB_4 0x25a4 +#define PCI_DEVICE_ID_INTEL_ESB_5 0x25a6 +#define PCI_DEVICE_ID_INTEL_ESB_9 0x25ab +#define PCI_DEVICE_ID_INTEL_ESB_10 0x25ac +#define PCI_DEVICE_ID_INTEL_5000_ERR 0x25f0 +#define PCI_DEVICE_ID_INTEL_5000_FBD0 0x25f5 +#define PCI_DEVICE_ID_INTEL_5000_FBD1 0x25f6 #define PCI_DEVICE_ID_INTEL_ICH6_0 0x2640 #define PCI_DEVICE_ID_INTEL_ICH6_1 0x2641 #define PCI_DEVICE_ID_INTEL_ICH6_2 0x2642 @@ -2794,6 +2781,11 @@ #define PCI_DEVICE_ID_INTEL_ESB2_14 0x2698 #define PCI_DEVICE_ID_INTEL_ESB2_17 0x269b #define PCI_DEVICE_ID_INTEL_ESB2_18 0x269e +#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 +#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 +#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 +#define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27a0 +#define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27a2 #define PCI_DEVICE_ID_INTEL_ICH7_0 0x27b8 #define PCI_DEVICE_ID_INTEL_ICH7_1 0x27b9 #define PCI_DEVICE_ID_INTEL_ICH7_30 0x27b0 @@ -2846,7 +2838,7 @@ #define PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_PHY0 0x2c91 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MCR 0x2c98 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TAD 0x2c99 -#define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST 0x2c9C +#define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST 0x2c9c #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_CTRL 0x2ca0 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_ADDR 0x2ca1 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_RANK 0x2ca2 @@ -2958,16 +2950,16 @@ #define PCI_DEVICE_ID_INTEL_SBRIDGE_BR 0x3cf5 /* 13.6 */ #define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1 0x3cf6 /* 12.7 */ #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f -#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 -#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 -#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 -#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 #define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030 #define PCI_DEVICE_ID_INTEL_5400_FBD0 0x4035 #define PCI_DEVICE_ID_INTEL_5400_FBD1 0x4036 -#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_EP80579_0 0x5031 #define PCI_DEVICE_ID_INTEL_EP80579_1 0x5032 +#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 +#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 +#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 +#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 +#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_82371SB_0 0x7000 #define PCI_DEVICE_ID_INTEL_82371SB_1 0x7010 #define PCI_DEVICE_ID_INTEL_82371SB_2 0x7020 diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h index a6440d6ebe95..5712cc2ce775 100644 --- a/include/linux/pcs-lynx.h +++ b/include/linux/pcs-lynx.h @@ -9,13 +9,10 @@ #include <linux/mdio.h> #include <linux/phylink.h> -struct lynx_pcs { - struct phylink_pcs pcs; - struct mdio_device *mdio; -}; +struct mdio_device *lynx_get_mdio_device(struct phylink_pcs *pcs); -struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); +struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio); -void lynx_pcs_destroy(struct lynx_pcs *pcs); +void lynx_pcs_destroy(struct phylink_pcs *pcs); #endif /* __LINUX_PCS_LYNX_H */ diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index add077a81b21..266eb26fb029 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -31,8 +31,7 @@ void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, unsigned int mode); -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state); +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, diff --git a/include/linux/peci-cpu.h b/include/linux/peci-cpu.h new file mode 100644 index 000000000000..ff8ae9c26c80 --- /dev/null +++ b/include/linux/peci-cpu.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Intel Corporation */ + +#ifndef __LINUX_PECI_CPU_H +#define __LINUX_PECI_CPU_H + +#include <linux/types.h> + +#include "../../arch/x86/include/asm/intel-family.h" + +#define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ +#define PECI_PKG_ID_CPU_ID 0x0000 /* CPUID Info */ +#define PECI_PKG_ID_PLATFORM_ID 0x0001 /* Platform ID */ +#define PECI_PKG_ID_DEVICE_ID 0x0002 /* Uncore Device ID */ +#define PECI_PKG_ID_MAX_THREAD_ID 0x0003 /* Max Thread ID */ +#define PECI_PKG_ID_MICROCODE_REV 0x0004 /* CPU Microcode Update Revision */ +#define PECI_PKG_ID_MCA_ERROR_LOG 0x0005 /* Machine Check Status */ +#define PECI_PCS_MODULE_TEMP 9 /* Per Core DTS Temperature Read */ +#define PECI_PCS_THERMAL_MARGIN 10 /* DTS thermal margin */ +#define PECI_PCS_DDR_DIMM_TEMP 14 /* DDR DIMM Temperature */ +#define PECI_PCS_TEMP_TARGET 16 /* Temperature Target Read */ +#define PECI_PCS_TDP_UNITS 30 /* Units for power/energy registers */ + +struct peci_device; + +int peci_temp_read(struct peci_device *device, s16 *temp_raw); + +int peci_pcs_read(struct peci_device *device, u8 index, + u16 param, u32 *data); + +int peci_pci_local_read(struct peci_device *device, u8 bus, u8 dev, + u8 func, u16 reg, u32 *data); + +int peci_ep_pci_local_read(struct peci_device *device, u8 seg, + u8 bus, u8 dev, u8 func, u16 reg, u32 *data); + +int peci_mmio_read(struct peci_device *device, u8 bar, u8 seg, + u8 bus, u8 dev, u8 func, u64 address, u32 *data); + +#endif /* __LINUX_PECI_CPU_H */ diff --git a/include/linux/peci.h b/include/linux/peci.h new file mode 100644 index 000000000000..06e6ef935297 --- /dev/null +++ b/include/linux/peci.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2018-2021 Intel Corporation */ + +#ifndef __LINUX_PECI_H +#define __LINUX_PECI_H + +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/types.h> + +/* + * Currently we don't support any PECI command over 32 bytes. + */ +#define PECI_REQUEST_MAX_BUF_SIZE 32 + +struct peci_controller; +struct peci_request; + +/** + * struct peci_controller_ops - PECI controller specific methods + * @xfer: PECI transfer function + * + * PECI controllers may have different hardware interfaces - the drivers + * implementing PECI controllers can use this structure to abstract away those + * differences by exposing a common interface for PECI core. + */ +struct peci_controller_ops { + int (*xfer)(struct peci_controller *controller, u8 addr, struct peci_request *req); +}; + +/** + * struct peci_controller - PECI controller + * @dev: device object to register PECI controller to the device model + * @ops: pointer to device specific controller operations + * @bus_lock: lock used to protect multiple callers + * @id: PECI controller ID + * + * PECI controllers usually connect to their drivers using non-PECI bus, + * such as the platform bus. + * Each PECI controller can communicate with one or more PECI devices. + */ +struct peci_controller { + struct device dev; + struct peci_controller_ops *ops; + struct mutex bus_lock; /* held for the duration of xfer */ + u8 id; +}; + +struct peci_controller *devm_peci_controller_add(struct device *parent, + struct peci_controller_ops *ops); + +static inline struct peci_controller *to_peci_controller(void *d) +{ + return container_of(d, struct peci_controller, dev); +} + +/** + * struct peci_device - PECI device + * @dev: device object to register PECI device to the device model + * @controller: manages the bus segment hosting this PECI device + * @info: PECI device characteristics + * @info.family: device family + * @info.model: device model + * @info.peci_revision: PECI revision supported by the PECI device + * @info.socket_id: the socket ID represented by the PECI device + * @addr: address used on the PECI bus connected to the parent controller + * @deleted: indicates that PECI device was already deleted + * + * A peci_device identifies a single device (i.e. CPU) connected to a PECI bus. + * The behaviour exposed to the rest of the system is defined by the PECI driver + * managing the device. + */ +struct peci_device { + struct device dev; + struct { + u16 family; + u8 model; + u8 peci_revision; + u8 socket_id; + } info; + u8 addr; + bool deleted; +}; + +static inline struct peci_device *to_peci_device(struct device *d) +{ + return container_of(d, struct peci_device, dev); +} + +/** + * struct peci_request - PECI request + * @device: PECI device to which the request is sent + * @tx: TX buffer specific data + * @tx.buf: TX buffer + * @tx.len: transfer data length in bytes + * @rx: RX buffer specific data + * @rx.buf: RX buffer + * @rx.len: received data length in bytes + * + * A peci_request represents a request issued by PECI originator (TX) and + * a response received from PECI responder (RX). + */ +struct peci_request { + struct peci_device *device; + struct { + u8 buf[PECI_REQUEST_MAX_BUF_SIZE]; + u8 len; + } rx, tx; +}; + +#endif /* __LINUX_PECI_H */ diff --git a/include/linux/percpu.h b/include/linux/percpu.h index ae4004e7957e..f1ec5ad1351c 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -94,10 +94,7 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; -typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, - size_t align); -typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); -typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); +typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, @@ -111,15 +108,13 @@ extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +void __init pcpu_populate_pte(unsigned long addr); extern int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 2512e2f9cd4e..0407a38b470a 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -26,6 +26,8 @@ */ /* Event uses a 64bit counter */ #define ARMPMU_EVT_64BIT 1 +/* Event uses a 47bit counter */ +#define ARMPMU_EVT_47BIT 2 #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h new file mode 100644 index 000000000000..46f9b6fe306e --- /dev/null +++ b/include/linux/perf/riscv_pmu.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 SiFive + * Copyright (C) 2018 Andes Technology Corporation + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * + */ + +#ifndef _ASM_RISCV_PERF_EVENT_H +#define _ASM_RISCV_PERF_EVENT_H + +#include <linux/perf_event.h> +#include <linux/ptrace.h> +#include <linux/interrupt.h> + +#ifdef CONFIG_RISCV_PMU + +/* + * The RISCV_MAX_COUNTERS parameter should be specified. + */ + +#define RISCV_MAX_COUNTERS 64 +#define RISCV_OP_UNSUPP (-EOPNOTSUPP) +#define RISCV_PMU_PDEV_NAME "riscv-pmu" +#define RISCV_PMU_LEGACY_PDEV_NAME "riscv-pmu-legacy" + +#define RISCV_PMU_STOP_FLAG_RESET 1 + +struct cpu_hw_events { + /* currently enabled events */ + int n_events; + /* Counter overflow interrupt */ + int irq; + /* currently enabled events */ + struct perf_event *events[RISCV_MAX_COUNTERS]; + /* currently enabled hardware counters */ + DECLARE_BITMAP(used_hw_ctrs, RISCV_MAX_COUNTERS); + /* currently enabled firmware counters */ + DECLARE_BITMAP(used_fw_ctrs, RISCV_MAX_COUNTERS); +}; + +struct riscv_pmu { + struct pmu pmu; + char *name; + + irqreturn_t (*handle_irq)(int irq_num, void *dev); + + int num_counters; + u64 (*ctr_read)(struct perf_event *event); + int (*ctr_get_idx)(struct perf_event *event); + int (*ctr_get_width)(int idx); + void (*ctr_clear_idx)(struct perf_event *event); + void (*ctr_start)(struct perf_event *event, u64 init_val); + void (*ctr_stop)(struct perf_event *event, unsigned long flag); + int (*event_map)(struct perf_event *event, u64 *config); + + struct cpu_hw_events __percpu *hw_events; + struct hlist_node node; +}; + +#define to_riscv_pmu(p) (container_of(p, struct riscv_pmu, pmu)) +unsigned long riscv_pmu_ctr_read_csr(unsigned long csr); +int riscv_pmu_event_set_period(struct perf_event *event); +uint64_t riscv_pmu_ctr_get_width_mask(struct perf_event *event); +u64 riscv_pmu_event_update(struct perf_event *event); +#ifdef CONFIG_RISCV_PMU_LEGACY +void riscv_pmu_legacy_skip_init(void); +#else +static inline void riscv_pmu_legacy_skip_init(void) {}; +#endif +struct riscv_pmu *riscv_pmu_alloc(void); + +#endif /* CONFIG_RISCV_PMU */ + +#endif /* _ASM_RISCV_PERF_EVENT_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0dcfd265beed..af97dd427501 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -26,11 +26,13 @@ # include <asm/local64.h> #endif +#define PERF_GUEST_ACTIVE 0x01 +#define PERF_GUEST_USER 0x02 + struct perf_guest_info_callbacks { - int (*is_in_guest)(void); - int (*is_user_mode)(void); - unsigned long (*get_guest_ip)(void); - void (*handle_intel_pt_intr)(void); + unsigned int (*state)(void); + unsigned long (*get_ip)(void); + unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -130,6 +132,15 @@ struct hw_perf_event_extra { }; /** + * hw_perf_event::flag values + * + * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific + * usage. + */ +#define PERF_EVENT_FLAG_ARCH 0x0000ffff +#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 + +/** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { @@ -611,6 +622,7 @@ struct swevent_hlist { #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 +struct bpf_prog; struct perf_cgroup; struct perf_buffer; @@ -681,18 +693,6 @@ struct perf_event { u64 total_time_running; u64 tstamp; - /* - * timestamp shadows the actual context timing but it can - * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in, - * or when ctx_sched_in failed to schedule the event because we - * run out of PMC. - * - * ctx_time already accounts for ctx->timestamp. Therefore to - * compute ctx_time for a sample, simply add perf_clock(). - */ - u64 shadow_ctx_time; - struct perf_event_attr attr; u16 header_size; u16 id_header_size; @@ -822,6 +822,7 @@ struct perf_event_context { int nr_events; int nr_active; + int nr_user; int is_active; int nr_stat; int nr_freq; @@ -839,6 +840,7 @@ struct perf_event_context { */ u64 time; u64 timestamp; + u64 timeoffset; /* * These fields let us detect when two contexts have both @@ -862,7 +864,7 @@ struct perf_event_context { #define PERF_NR_CONTEXTS 4 /** - * struct perf_event_cpu_context - per cpu event context structure + * struct perf_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; @@ -921,6 +923,8 @@ struct bpf_perf_event_data_kern { struct perf_cgroup_info { u64 time; u64 timestamp; + u64 timeoffset; + int active; }; struct perf_cgroup { @@ -1240,9 +1244,32 @@ extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); -extern struct perf_guest_info_callbacks *perf_guest_cbs; -extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); -extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); +#ifdef CONFIG_GUEST_PERF_EVENTS +extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; + +DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); +DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); +DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); + +static inline unsigned int perf_guest_state(void) +{ + return static_call(__perf_guest_state)(); +} +static inline unsigned long perf_guest_get_ip(void) +{ + return static_call(__perf_guest_get_ip)(); +} +static inline unsigned int perf_guest_handle_intel_pt_intr(void) +{ + return static_call(__perf_guest_handle_intel_pt_intr)(); +} +extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); +extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); +#else +static inline unsigned int perf_guest_state(void) { return 0; } +static inline unsigned long perf_guest_get_ip(void) { return 0; } +static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } +#endif /* CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); @@ -1486,11 +1513,6 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } -static inline int perf_register_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } -static inline int perf_unregister_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } - static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); diff --git a/include/linux/perf_event_api.h b/include/linux/perf_event_api.h new file mode 100644 index 000000000000..c2fd6048b790 --- /dev/null +++ b/include/linux/perf_event_api.h @@ -0,0 +1 @@ +#include <linux/perf_event.h> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e24d2c992b11..f4f4077b97aa 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -62,6 +62,7 @@ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } +#define pte_index pte_index #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) @@ -258,6 +259,14 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef __HAVE_ARCH_PTEP_CLEAR +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_clear(mm, addr, ptep); +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, diff --git a/include/linux/pgtable_api.h b/include/linux/pgtable_api.h new file mode 100644 index 000000000000..ff367a4ba8c4 --- /dev/null +++ b/include/linux/pgtable_api.h @@ -0,0 +1 @@ +#include <linux/pgtable.h> diff --git a/include/linux/phy.h b/include/linux/phy.h index cbf03a5f9cf5..36ca2b5c2253 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -87,8 +87,8 @@ extern const int phy_10gbit_features_array[1]; * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined - * @PHY_INTERFACE_MODE_MII: Median-independent interface - * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface + * @PHY_INTERFACE_MODE_MII: Media-independent interface + * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface @@ -99,7 +99,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI - * @PHY_INTERFACE_MODE_SMII: ??? MII + * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax @@ -1578,6 +1578,7 @@ int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status_fixed(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); +int genphy_read_master_slave(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); @@ -1661,7 +1662,7 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index f037470b6fb3..223781622b33 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -20,6 +20,29 @@ enum { MLO_AN_PHY = 0, /* Conventional PHY */ MLO_AN_FIXED, /* Fixed-link mode */ MLO_AN_INBAND, /* In-band protocol */ + + MAC_SYM_PAUSE = BIT(0), + MAC_ASYM_PAUSE = BIT(1), + MAC_10HD = BIT(2), + MAC_10FD = BIT(3), + MAC_10 = MAC_10HD | MAC_10FD, + MAC_100HD = BIT(4), + MAC_100FD = BIT(5), + MAC_100 = MAC_100HD | MAC_100FD, + MAC_1000HD = BIT(6), + MAC_1000FD = BIT(7), + MAC_1000 = MAC_1000HD | MAC_1000FD, + MAC_2500FD = BIT(8), + MAC_5000FD = BIT(9), + MAC_10000FD = BIT(10), + MAC_20000FD = BIT(11), + MAC_25000FD = BIT(12), + MAC_40000FD = BIT(13), + MAC_50000FD = BIT(14), + MAC_56000FD = BIT(15), + MAC_100000FD = BIT(16), + MAC_200000FD = BIT(17), + MAC_400000FD = BIT(18), }; static inline bool phylink_autoneg_inband(unsigned int mode) @@ -61,7 +84,8 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance - * @pcs_poll: MAC PCS cannot provide link change interrupt + * @legacy_pre_march2020: driver has not been updated for March 2020 updates + * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND @@ -69,21 +93,24 @@ enum phylink_op_type { * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx * are supported by the MAC/PCS. + * @mac_capabilities: MAC pause/speed/duplex capabilities. */ struct phylink_config { struct device *dev; enum phylink_op_type type; - bool pcs_poll; + bool legacy_pre_march2020; bool poll_fixed_state; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + unsigned long mac_capabilities; }; /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. + * @mac_select_pcs: Select a PCS for the interface mode. * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. @@ -98,6 +125,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); + struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, + phy_interface_t interface); void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, @@ -150,6 +179,21 @@ struct phylink_mac_ops { */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); +/** + * mac_select_pcs: Select a PCS for the interface mode. + * @config: a pointer to a &struct phylink_config. + * @interface: PHY interface mode for PCS + * + * Return the &struct phylink_pcs for the specified interface mode, or + * NULL if none is required, or an error pointer on error. + * + * This must not modify any state. It is used to query which PCS should + * be used. Phylink will use this during validation to ensure that the + * configuration is valid, and when setting a configuration to internally + * set the PCS that will be used. + */ +struct phylink_pcs *mac_select_pcs(struct phylink_config *config, + phy_interface_t interface); /** * mac_pcs_get_state() - Read the current inband link state from the hardware @@ -162,6 +206,10 @@ void validate(struct phylink_config *config, unsigned long *supported, * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_pcs_get_state(struct phylink_config *config, struct phylink_link_state *state); @@ -202,6 +250,15 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set + * in their &phylnk_config and which don't have a PCS), this function will be + * called on each link up event, and to also change the in-band advert. For + * non-legacy drivers, it will only be called to reconfigure the MAC for a + * "major" change in e.g. interface mode. It will not be called for changes + * in speed, duplex or pause modes or to change the in-band advertisement. + * In any case, it is strongly preferred that speed, duplex and pause settings + * are handled in the mac_link_up() method and not in this method. + * * (this requires a rewrite - please refer to mac_link_up() for situations * where the PCS and MAC are not tightly integrated.) * @@ -286,6 +343,10 @@ int mac_finish(struct phylink_config *config, unsigned int mode, /** * mac_an_restart() - restart 802.3z BaseX autonegotiation * @config: a pointer to a &struct phylink_config. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_an_restart(struct phylink_config *config); @@ -353,6 +414,7 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. + * @pcs_validate: validate the link configuration. * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -360,6 +422,8 @@ struct phylink_pcs { * (where necessary). */ struct phylink_pcs_ops { + int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode, @@ -373,6 +437,23 @@ struct phylink_pcs_ops { #if 0 /* For kernel-doc purposes only. */ /** + * pcs_validate() - validate the link configuration. + * @pcs: a pointer to a &struct phylink_pcs. + * @supported: ethtool bitmask for supported link modes. + * @state: a const pointer to a &struct phylink_link_state. + * + * Validate the interface mode, and advertising's autoneg bit, removing any + * media ethtool link modes that would not be supportable from the supported + * mask. Phylink will propagate the changes to the advertising mask. See the + * &struct phylink_mac_ops validate() method. + * + * Returns -EINVAL if the interface mode/autoneg mode is not supported. + * Returns non-zero positive if the link state can be supported. + */ +int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); + +/** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. * @state: a pointer to a &struct phylink_link_state. @@ -442,10 +523,15 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); #endif +void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, + unsigned long mac_capabilities); +void phylink_generic_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state); + struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); -void phylink_set_pcs(struct phylink *, struct phylink_pcs *pcs); void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); @@ -493,14 +579,14 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); +void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, + u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); -int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, - phy_interface_t interface, - const unsigned long *advertising); +int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, + const unsigned long *advertising); int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c7e627503d2..07481bb87d4e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -86,4 +86,9 @@ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) +{ + return task_active_pid_ns(tsk) == &init_pid_ns; +} + #endif /* _LINUX_PID_NS_H */ diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index eee0e3948537..2422211d6a5a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -91,6 +91,8 @@ struct pinctrl_map; * configuration (eg. the currently selected mux function) drive values on * the line. Use argument 1 to enable output mode, argument 0 to disable * it. + * @PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS: this will configure the output impedance + * of the pin with the value passed as argument. The argument is in ohms. * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells @@ -129,6 +131,7 @@ enum pin_config_param { PIN_CONFIG_MODE_PWM, PIN_CONFIG_OUTPUT, PIN_CONFIG_OUTPUT_ENABLE, + PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS, PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_POWER_SOURCE, PIN_CONFIG_SKEW_DELAY, diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index fc5642431b92..c00c618ef290 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -238,10 +238,6 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); -extern unsigned int pipe_max_size; -extern unsigned long pipe_user_pages_hard; -extern unsigned long pipe_user_pages_soft; - /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 174601554b06..f9c5ac80d59b 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -152,14 +152,6 @@ struct packet_stacked_data }; #define PSD_POOL_SIZE 64 -struct pktcdvd_kobj -{ - struct kobject kobj; - struct pktcdvd_device *pd; -}; -#define to_pktcdvdkobj(_k) \ - ((struct pktcdvd_kobj*)container_of(_k,struct pktcdvd_kobj,kobj)) - struct pktcdvd_device { struct block_device *bdev; /* dev attached */ @@ -183,6 +175,8 @@ struct pktcdvd_device spinlock_t lock; /* Serialize access to bio_queue */ struct rb_root bio_queue; /* Work queue of bios we need to handle */ int bio_queue_size; /* Number of nodes in bio_queue */ + bool congested; /* Someone is waiting for bio_queue_size + * to drop. */ sector_t current_sector; /* Keep track of where the elevator is */ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ /* needs to be run. */ @@ -195,8 +189,6 @@ struct pktcdvd_device int write_congestion_on; struct device *dev; /* sysfs pktcdvd[0-7] dev */ - struct pktcdvd_kobj *kobj_stat; /* sysfs pktcdvd[0-7]/stat/ */ - struct pktcdvd_kobj *kobj_wqueue; /* sysfs pktcdvd[0-7]/write_queue/ */ struct dentry *dfs_d_root; /* debugfs: devname directory */ struct dentry *dfs_f_info; /* debugfs: info file */ diff --git a/include/linux/platform_data/ad5755.h b/include/linux/platform_data/ad5755.h deleted file mode 100644 index e371e08f04bc..000000000000 --- a/include/linux/platform_data/ad5755.h +++ /dev/null @@ -1,102 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2012 Analog Devices Inc. - */ -#ifndef __LINUX_PLATFORM_DATA_AD5755_H__ -#define __LINUX_PLATFORM_DATA_AD5755_H__ - -enum ad5755_mode { - AD5755_MODE_VOLTAGE_0V_5V = 0, - AD5755_MODE_VOLTAGE_0V_10V = 1, - AD5755_MODE_VOLTAGE_PLUSMINUS_5V = 2, - AD5755_MODE_VOLTAGE_PLUSMINUS_10V = 3, - AD5755_MODE_CURRENT_4mA_20mA = 4, - AD5755_MODE_CURRENT_0mA_20mA = 5, - AD5755_MODE_CURRENT_0mA_24mA = 6, -}; - -enum ad5755_dc_dc_phase { - AD5755_DC_DC_PHASE_ALL_SAME_EDGE = 0, - AD5755_DC_DC_PHASE_A_B_SAME_EDGE_C_D_OPP_EDGE = 1, - AD5755_DC_DC_PHASE_A_C_SAME_EDGE_B_D_OPP_EDGE = 2, - AD5755_DC_DC_PHASE_90_DEGREE = 3, -}; - -enum ad5755_dc_dc_freq { - AD5755_DC_DC_FREQ_250kHZ = 0, - AD5755_DC_DC_FREQ_410kHZ = 1, - AD5755_DC_DC_FREQ_650kHZ = 2, -}; - -enum ad5755_dc_dc_maxv { - AD5755_DC_DC_MAXV_23V = 0, - AD5755_DC_DC_MAXV_24V5 = 1, - AD5755_DC_DC_MAXV_27V = 2, - AD5755_DC_DC_MAXV_29V5 = 3, -}; - -enum ad5755_slew_rate { - AD5755_SLEW_RATE_64k = 0, - AD5755_SLEW_RATE_32k = 1, - AD5755_SLEW_RATE_16k = 2, - AD5755_SLEW_RATE_8k = 3, - AD5755_SLEW_RATE_4k = 4, - AD5755_SLEW_RATE_2k = 5, - AD5755_SLEW_RATE_1k = 6, - AD5755_SLEW_RATE_500 = 7, - AD5755_SLEW_RATE_250 = 8, - AD5755_SLEW_RATE_125 = 9, - AD5755_SLEW_RATE_64 = 10, - AD5755_SLEW_RATE_32 = 11, - AD5755_SLEW_RATE_16 = 12, - AD5755_SLEW_RATE_8 = 13, - AD5755_SLEW_RATE_4 = 14, - AD5755_SLEW_RATE_0_5 = 15, -}; - -enum ad5755_slew_step_size { - AD5755_SLEW_STEP_SIZE_1 = 0, - AD5755_SLEW_STEP_SIZE_2 = 1, - AD5755_SLEW_STEP_SIZE_4 = 2, - AD5755_SLEW_STEP_SIZE_8 = 3, - AD5755_SLEW_STEP_SIZE_16 = 4, - AD5755_SLEW_STEP_SIZE_32 = 5, - AD5755_SLEW_STEP_SIZE_64 = 6, - AD5755_SLEW_STEP_SIZE_128 = 7, - AD5755_SLEW_STEP_SIZE_256 = 8, -}; - -/** - * struct ad5755_platform_data - AD5755 DAC driver platform data - * @ext_dc_dc_compenstation_resistor: Whether an external DC-DC converter - * compensation register is used. - * @dc_dc_phase: DC-DC converter phase. - * @dc_dc_freq: DC-DC converter frequency. - * @dc_dc_maxv: DC-DC maximum allowed boost voltage. - * @dac.mode: The mode to be used for the DAC output. - * @dac.ext_current_sense_resistor: Whether an external current sense resistor - * is used. - * @dac.enable_voltage_overrange: Whether to enable 20% voltage output overrange. - * @dac.slew.enable: Whether to enable digital slew. - * @dac.slew.rate: Slew rate of the digital slew. - * @dac.slew.step_size: Slew step size of the digital slew. - **/ -struct ad5755_platform_data { - bool ext_dc_dc_compenstation_resistor; - enum ad5755_dc_dc_phase dc_dc_phase; - enum ad5755_dc_dc_freq dc_dc_freq; - enum ad5755_dc_dc_maxv dc_dc_maxv; - - struct { - enum ad5755_mode mode; - bool ext_current_sense_resistor; - bool enable_voltage_overrange; - struct { - bool enable; - enum ad5755_slew_rate rate; - enum ad5755_slew_step_size step_size; - } slew; - } dac[4]; -}; - -#endif diff --git a/include/linux/platform_data/bcm7038_wdt.h b/include/linux/platform_data/bcm7038_wdt.h new file mode 100644 index 000000000000..e18cfd9ec8f9 --- /dev/null +++ b/include/linux/platform_data/bcm7038_wdt.h @@ -0,0 +1,8 @@ +#ifndef __BCM7038_WDT_PDATA_H +#define __BCM7038_WDT_PDATA_H + +struct bcm7038_wdt_platform_data { + const char *clk_name; +}; + +#endif /* __BCM7038_WDT_PDATA_H */ diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h index 2b5676ff35be..f922a192fe58 100644 --- a/include/linux/platform_data/brcmfmac.h +++ b/include/linux/platform_data/brcmfmac.h @@ -178,7 +178,7 @@ struct brcmfmac_platform_data { void (*power_off)(void); char *fw_alternative_path; int device_count; - struct brcmfmac_pd_device devices[0]; + struct brcmfmac_pd_device devices[]; }; diff --git a/include/linux/platform_data/brcmnand.h b/include/linux/platform_data/brcmnand.h new file mode 100644 index 000000000000..8b8777985dce --- /dev/null +++ b/include/linux/platform_data/brcmnand.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef BRCMNAND_PLAT_DATA_H +#define BRCMNAND_PLAT_DATA_H + +struct brcmnand_platform_data { + int chip_select; + const char * const *part_probe_types; + unsigned int ecc_stepsize; + unsigned int ecc_strength; +}; + +#endif /* BRCMNAND_PLAT_DATA_H */ diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h index b9f682459f08..11a2a23fd9b2 100644 --- a/include/linux/platform_data/clk-fch.h +++ b/include/linux/platform_data/clk-fch.h @@ -12,7 +12,7 @@ struct fch_clk_data { void __iomem *base; - u32 is_rv; + char *name; }; #endif /* __CLK_FCH_H */ diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 271bd87bff0a..c23554531961 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -3386,6 +3386,9 @@ enum ec_mkbp_event { /* Send an incoming CEC message to the AP */ EC_MKBP_EVENT_CEC_MESSAGE = 9, + /* Peripheral device charger event */ + EC_MKBP_EVENT_PCHG = 12, + /* Number of MKBP events */ EC_MKBP_EVENT_COUNT, }; @@ -5527,6 +5530,67 @@ enum pchg_state { [PCHG_STATE_CONNECTED] = "CONNECTED", \ } +/* + * Update firmware of peripheral chip + */ +#define EC_CMD_PCHG_UPDATE 0x0136 + +/* Port number is encoded in bit[28:31]. */ +#define EC_MKBP_PCHG_PORT_SHIFT 28 +/* Utility macro for converting MKBP event to port number. */ +#define EC_MKBP_PCHG_EVENT_TO_PORT(e) (((e) >> EC_MKBP_PCHG_PORT_SHIFT) & 0xf) +/* Utility macro for extracting event bits. */ +#define EC_MKBP_PCHG_EVENT_MASK(e) ((e) \ + & GENMASK(EC_MKBP_PCHG_PORT_SHIFT-1, 0)) + +#define EC_MKBP_PCHG_UPDATE_OPENED BIT(0) +#define EC_MKBP_PCHG_WRITE_COMPLETE BIT(1) +#define EC_MKBP_PCHG_UPDATE_CLOSED BIT(2) +#define EC_MKBP_PCHG_UPDATE_ERROR BIT(3) +#define EC_MKBP_PCHG_DEVICE_EVENT BIT(4) + +enum ec_pchg_update_cmd { + /* Reset chip to normal mode. */ + EC_PCHG_UPDATE_CMD_RESET_TO_NORMAL = 0, + /* Reset and put a chip in update (a.k.a. download) mode. */ + EC_PCHG_UPDATE_CMD_OPEN, + /* Write a block of data containing FW image. */ + EC_PCHG_UPDATE_CMD_WRITE, + /* Close update session. */ + EC_PCHG_UPDATE_CMD_CLOSE, + /* End of commands */ + EC_PCHG_UPDATE_CMD_COUNT, +}; + +struct ec_params_pchg_update { + /* PCHG port number */ + uint8_t port; + /* enum ec_pchg_update_cmd */ + uint8_t cmd; + /* Padding */ + uint8_t reserved0; + uint8_t reserved1; + /* Version of new firmware */ + uint32_t version; + /* CRC32 of new firmware */ + uint32_t crc32; + /* Address in chip memory where <data> is written to */ + uint32_t addr; + /* Size of <data> */ + uint32_t size; + /* Partial data of new firmware */ + uint8_t data[]; +} __ec_align4; + +BUILD_ASSERT(EC_PCHG_UPDATE_CMD_COUNT + < BIT(sizeof(((struct ec_params_pchg_update *)0)->cmd)*8)); + +struct ec_response_pchg_update { + /* Block size */ + uint32_t block_size; +} __ec_align4; + + /*****************************************************************************/ /* Voltage regulator controls */ @@ -5644,7 +5708,7 @@ struct ec_response_typec_discovery { uint8_t svid_count; /* Number of SVIDs partner sent */ uint16_t reserved; uint32_t discovery_vdo[6]; /* Max VDOs allowed after VDM header is 6 */ - struct svid_mode_info svids[0]; + struct svid_mode_info svids[]; } __ec_align1; /* USB Type-C commands for AP-controlled device policy. */ diff --git a/include/linux/platform_data/eth_ixp4xx.h b/include/linux/platform_data/eth_ixp4xx.h deleted file mode 100644 index 114b0940729f..000000000000 --- a/include/linux/platform_data/eth_ixp4xx.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_ETH_IXP4XX -#define __PLATFORM_DATA_ETH_IXP4XX - -#include <linux/types.h> - -#define IXP4XX_ETH_NPEA 0x00 -#define IXP4XX_ETH_NPEB 0x10 -#define IXP4XX_ETH_NPEC 0x20 - -/* Information about built-in Ethernet MAC interfaces */ -struct eth_plat_info { - u8 phy; /* MII PHY ID, 0 - 31 */ - u8 rxq; /* configurable, currently 0 - 31 only */ - u8 txreadyq; - u8 hwaddr[6]; - u8 npe; /* NPE instance used by this interface */ - bool has_mdio; /* If this instance has an MDIO bus */ -}; - -#endif diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h index de6ada739121..8c2f1f185353 100644 --- a/include/linux/platform_data/mtd-nand-omap2.h +++ b/include/linux/platform_data/mtd-nand-omap2.h @@ -7,6 +7,7 @@ #define _MTD_NAND_OMAP2_H #include <linux/mtd/partitions.h> +#include <linux/mod_devicetable.h> #define GPMC_BCH_NUM_REMAINDER 8 @@ -61,4 +62,11 @@ struct gpmc_nand_regs { void __iomem *gpmc_bch_result5[GPMC_BCH_NUM_REMAINDER]; void __iomem *gpmc_bch_result6[GPMC_BCH_NUM_REMAINDER]; }; -#endif + +static const struct of_device_id omap_nand_ids[] = { + { .compatible = "ti,omap2-nand", }, + { .compatible = "ti,am64-nand", }, + {}, +}; + +#endif /* _MTD_NAND_OMAP2_H */ diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h deleted file mode 100644 index b324d03e580c..000000000000 --- a/include/linux/platform_data/ntc_thermistor.h +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * ntc_thermistor.h - NTC Thermistors - * - * Copyright (C) 2010 Samsung Electronics - * MyungJoo Ham <myungjoo.ham@samsung.com> - */ -#ifndef _LINUX_NTC_H -#define _LINUX_NTC_H - -struct iio_channel; - -enum ntc_thermistor_type { - TYPE_B57330V2103, - TYPE_B57891S0103, - TYPE_NCPXXWB473, - TYPE_NCPXXWF104, - TYPE_NCPXXWL333, - TYPE_NCPXXXH103, -}; - -struct ntc_thermistor_platform_data { - /* - * One (not both) of read_uV and read_ohm should be provided and only - * one of the two should be provided. - * Both functions should return negative value for an error case. - * - * pullup_uV, pullup_ohm, pulldown_ohm, and connect are required to use - * read_uV() - * - * How to setup pullup_ohm, pulldown_ohm, and connect is - * described at Documentation/hwmon/ntc_thermistor.rst - * - * pullup/down_ohm: 0 for infinite / not-connected - * - * chan: iio_channel pointer to communicate with the ADC which the - * thermistor is using for conversion of the analog values. - */ - int (*read_uv)(struct ntc_thermistor_platform_data *); - unsigned int pullup_uv; - - unsigned int pullup_ohm; - unsigned int pulldown_ohm; - enum { NTC_CONNECTED_POSITIVE, NTC_CONNECTED_GROUND } connect; - struct iio_channel *chan; - - int (*read_ohm)(void); -}; - -#endif /* _LINUX_NTC_H */ diff --git a/include/linux/platform_data/pata_ixp4xx_cf.h b/include/linux/platform_data/pata_ixp4xx_cf.h deleted file mode 100644 index e60fa41da4a5..000000000000 --- a/include/linux/platform_data/pata_ixp4xx_cf.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_PATA_IXP4XX_H -#define __PLATFORM_DATA_PATA_IXP4XX_H - -#include <linux/types.h> - -/* - * This structure provide a means for the board setup code - * to give information to th pata_ixp4xx driver. It is - * passed as platform_data. - */ -struct ixp4xx_pata_data { - volatile u32 *cs0_cfg; - volatile u32 *cs1_cfg; - unsigned long cs0_bits; - unsigned long cs1_bits; - void __iomem *cmd; - void __iomem *ctl; -}; - -#endif diff --git a/include/linux/platform_data/spi-clps711x.h b/include/linux/platform_data/spi-clps711x.h deleted file mode 100644 index efaa596848c9..000000000000 --- a/include/linux/platform_data/spi-clps711x.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * CLPS711X SPI bus driver definitions - * - * Copyright (C) 2012 Alexander Shiyan <shc_work@mail.ru> - */ - -#ifndef ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H -#define ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H - -/* Board specific platform_data */ -struct spi_clps711x_pdata { - int *chipselect; /* Array of GPIO-numbers */ - int num_chipselect; /* Total count of GPIOs */ -}; - -#endif diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 773daf7915a3..5df1ace6d2c9 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -16,7 +16,6 @@ struct platform_device; * struct s3c64xx_spi_csinfo - ChipSelect description * @fb_delay: Slave specific feedback delay. * Refer to FB_CLK_SEL register definition in SPI chapter. - * @line: Custom 'identity' of the CS line. * * This is per SPI-Slave Chipselect information. * Allocate and initialize one in machine init code and make the @@ -24,7 +23,6 @@ struct platform_device; */ struct s3c64xx_spi_csinfo { u8 fb_delay; - unsigned line; }; /** @@ -43,26 +41,16 @@ struct s3c64xx_spi_info { /** * s3c64xx_spi_set_platdata - SPI Controller configure callback by the board * initialization code. - * @cfg_gpio: Pointer to gpio setup function. * @src_clk_nr: Clock the SPI controller is to use to generate SPI clocks. * @num_cs: Number of elements in the 'cs' array. * * Call this from machine init code for each SPI Controller that * has some chips attached to it. */ -extern void s3c64xx_spi0_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); -extern void s3c64xx_spi1_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); -extern void s3c64xx_spi2_set_platdata(int (*cfg_gpio)(void), int src_clk_nr, - int num_cs); +extern void s3c64xx_spi0_set_platdata(int src_clk_nr, int num_cs); /* defined by architecture to configure gpio */ extern int s3c64xx_spi0_cfg_gpio(void); -extern int s3c64xx_spi1_cfg_gpio(void); -extern int s3c64xx_spi2_cfg_gpio(void); extern struct s3c64xx_spi_info s3c64xx_spi0_pdata; -extern struct s3c64xx_spi_info s3c64xx_spi1_pdata; -extern struct s3c64xx_spi_info s3c64xx_spi2_pdata; #endif /*__SPI_S3C64XX_H */ diff --git a/include/linux/platform_data/tps68470.h b/include/linux/platform_data/tps68470.h new file mode 100644 index 000000000000..126d082c3f2e --- /dev/null +++ b/include/linux/platform_data/tps68470.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * TI TPS68470 PMIC platform data definition. + * + * Copyright (c) 2021 Red Hat Inc. + * + * Red Hat authors: + * Hans de Goede <hdegoede@redhat.com> + */ +#ifndef __PDATA_TPS68470_H +#define __PDATA_TPS68470_H + +enum tps68470_regulators { + TPS68470_CORE, + TPS68470_ANA, + TPS68470_VCM, + TPS68470_VIO, + TPS68470_VSIO, + TPS68470_AUX1, + TPS68470_AUX2, + TPS68470_NUM_REGULATORS +}; + +struct regulator_init_data; + +struct tps68470_regulator_platform_data { + const struct regulator_init_data *reg_init_data[TPS68470_NUM_REGULATORS]; +}; + +struct tps68470_clk_platform_data { + const char *consumer_dev_name; + const char *consumer_con_id; +}; + +#endif diff --git a/include/linux/platform_data/wan_ixp4xx_hss.h b/include/linux/platform_data/wan_ixp4xx_hss.h deleted file mode 100644 index d525a0feb9e1..000000000000 --- a/include/linux/platform_data/wan_ixp4xx_hss.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_WAN_IXP4XX_HSS_H -#define __PLATFORM_DATA_WAN_IXP4XX_HSS_H - -#include <linux/types.h> - -/* Information about built-in HSS (synchronous serial) interfaces */ -struct hss_plat_info { - int (*set_clock)(int port, unsigned int clock_type); - int (*open)(int port, void *pdev, - void (*set_carrier_cb)(void *pdev, int carrier)); - void (*close)(int port, void *pdev); - u8 txreadyq; - u32 timer_freq; -}; - -#endif diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 17dc5cb6f3f2..a571b47ff362 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -77,6 +77,8 @@ #define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 #define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 /* deprecated */ #define ASUS_WMI_DEVID_CPU_FAN_CTRL 0x00110013 +#define ASUS_WMI_DEVID_CPU_FAN_CURVE 0x00110024 +#define ASUS_WMI_DEVID_GPU_FAN_CURVE 0x00110025 /* Power */ #define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 diff --git a/include/linux/platform_data/x86/simatic-ipc-base.h b/include/linux/platform_data/x86/simatic-ipc-base.h new file mode 100644 index 000000000000..62d2bc774067 --- /dev/null +++ b/include/linux/platform_data/x86/simatic-ipc-base.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Siemens SIMATIC IPC drivers + * + * Copyright (c) Siemens AG, 2018-2021 + * + * Authors: + * Henning Schild <henning.schild@siemens.com> + * Gerd Haeussler <gerd.haeussler.ext@siemens.com> + */ + +#ifndef __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H +#define __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H + +#include <linux/types.h> + +#define SIMATIC_IPC_DEVICE_NONE 0 +#define SIMATIC_IPC_DEVICE_227D 1 +#define SIMATIC_IPC_DEVICE_427E 2 +#define SIMATIC_IPC_DEVICE_127E 3 +#define SIMATIC_IPC_DEVICE_227E 4 + +struct simatic_ipc_platform { + u8 devmode; +}; + +u32 simatic_ipc_get_membase0(unsigned int p2sb); + +#endif /* __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H */ diff --git a/include/linux/platform_data/x86/simatic-ipc.h b/include/linux/platform_data/x86/simatic-ipc.h new file mode 100644 index 000000000000..f3b76b39776b --- /dev/null +++ b/include/linux/platform_data/x86/simatic-ipc.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Siemens SIMATIC IPC drivers + * + * Copyright (c) Siemens AG, 2018-2021 + * + * Authors: + * Henning Schild <henning.schild@siemens.com> + * Gerd Haeussler <gerd.haeussler.ext@siemens.com> + */ + +#ifndef __PLATFORM_DATA_X86_SIMATIC_IPC_H +#define __PLATFORM_DATA_X86_SIMATIC_IPC_H + +#include <linux/dmi.h> +#include <linux/platform_data/x86/simatic-ipc-base.h> + +#define SIMATIC_IPC_DMI_ENTRY_OEM 129 +/* binary type */ +#define SIMATIC_IPC_DMI_TYPE 0xff +#define SIMATIC_IPC_DMI_GROUP 0x05 +#define SIMATIC_IPC_DMI_ENTRY 0x02 +#define SIMATIC_IPC_DMI_TID 0x02 + +enum simatic_ipc_station_ids { + SIMATIC_IPC_INVALID_STATION_ID = 0, + SIMATIC_IPC_IPC227D = 0x00000501, + SIMATIC_IPC_IPC427D = 0x00000701, + SIMATIC_IPC_IPC227E = 0x00000901, + SIMATIC_IPC_IPC277E = 0x00000902, + SIMATIC_IPC_IPC427E = 0x00000A01, + SIMATIC_IPC_IPC477E = 0x00000A02, + SIMATIC_IPC_IPC127E = 0x00000D01, +}; + +static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len) +{ + struct { + u8 type; /* type (0xff = binary) */ + u8 len; /* len of data entry */ + u8 group; + u8 entry; + u8 tid; + __le32 station_id; /* station id (LE) */ + } __packed * data_entry = (void *)data + sizeof(struct dmi_header); + + while ((u8 *)data_entry < data + max_len) { + if (data_entry->type == SIMATIC_IPC_DMI_TYPE && + data_entry->len == sizeof(*data_entry) && + data_entry->group == SIMATIC_IPC_DMI_GROUP && + data_entry->entry == SIMATIC_IPC_DMI_ENTRY && + data_entry->tid == SIMATIC_IPC_DMI_TID) { + return le32_to_cpu(data_entry->station_id); + } + data_entry = (void *)((u8 *)(data_entry) + data_entry->len); + } + + return SIMATIC_IPC_INVALID_STATION_ID; +} + +static inline void +simatic_ipc_find_dmi_entry_helper(const struct dmi_header *dh, void *_data) +{ + u32 *id = _data; + + if (dh->type != SIMATIC_IPC_DMI_ENTRY_OEM) + return; + + *id = simatic_ipc_get_station_id((u8 *)dh, dh->length); +} + +#endif /* __PLATFORM_DATA_X86_SIMATIC_IPC_H */ diff --git a/include/linux/platform_data/x86/intel-spi.h b/include/linux/platform_data/x86/spi-intel.h index 7f53a5c6f35e..a512ec37abbb 100644 --- a/include/linux/platform_data/x86/intel-spi.h +++ b/include/linux/platform_data/x86/spi-intel.h @@ -6,8 +6,8 @@ * Author: Mika Westerberg <mika.westerberg@linux.intel.com> */ -#ifndef INTEL_SPI_PDATA_H -#define INTEL_SPI_PDATA_H +#ifndef SPI_INTEL_PDATA_H +#define SPI_INTEL_PDATA_H enum intel_spi_type { INTEL_SPI_BYT = 1, @@ -19,11 +19,13 @@ enum intel_spi_type { /** * struct intel_spi_boardinfo - Board specific data for Intel SPI driver * @type: Type which this controller is compatible with - * @writeable: The chip is writeable + * @set_writeable: Try to make the chip writeable (optional) + * @data: Data to be passed to @set_writeable can be %NULL */ struct intel_spi_boardinfo { enum intel_spi_type type; - bool writeable; + bool (*set_writeable)(void __iomem *base, void *data); + void *data; }; -#endif /* INTEL_SPI_PDATA_H */ +#endif /* SPI_INTEL_PDATA_H */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 1d8209c09686..e65b3ab28377 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -8,6 +8,7 @@ #ifndef _LINUX_PM_H #define _LINUX_PM_H +#include <linux/export.h> #include <linux/list.h> #include <linux/workqueue.h> #include <linux/spinlock.h> @@ -300,55 +301,101 @@ struct dev_pm_ops { int (*runtime_idle)(struct device *dev); }; +#define SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend = pm_sleep_ptr(suspend_fn), \ + .resume = pm_sleep_ptr(resume_fn), \ + .freeze = pm_sleep_ptr(suspend_fn), \ + .thaw = pm_sleep_ptr(resume_fn), \ + .poweroff = pm_sleep_ptr(suspend_fn), \ + .restore = pm_sleep_ptr(resume_fn), + +#define LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_late = pm_sleep_ptr(suspend_fn), \ + .resume_early = pm_sleep_ptr(resume_fn), \ + .freeze_late = pm_sleep_ptr(suspend_fn), \ + .thaw_early = pm_sleep_ptr(resume_fn), \ + .poweroff_late = pm_sleep_ptr(suspend_fn), \ + .restore_early = pm_sleep_ptr(resume_fn), + +#define NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_noirq = pm_sleep_ptr(suspend_fn), \ + .resume_noirq = pm_sleep_ptr(resume_fn), \ + .freeze_noirq = pm_sleep_ptr(suspend_fn), \ + .thaw_noirq = pm_sleep_ptr(resume_fn), \ + .poweroff_noirq = pm_sleep_ptr(suspend_fn), \ + .restore_noirq = pm_sleep_ptr(resume_fn), + +#define RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + .runtime_suspend = suspend_fn, \ + .runtime_resume = resume_fn, \ + .runtime_idle = idle_fn, + #ifdef CONFIG_PM_SLEEP #define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend = suspend_fn, \ - .resume = resume_fn, \ - .freeze = suspend_fn, \ - .thaw = resume_fn, \ - .poweroff = suspend_fn, \ - .restore = resume_fn, + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM_SLEEP #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend_late = suspend_fn, \ - .resume_early = resume_fn, \ - .freeze_late = suspend_fn, \ - .thaw_early = resume_fn, \ - .poweroff_late = suspend_fn, \ - .restore_early = resume_fn, + LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM_SLEEP #define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend_noirq = suspend_fn, \ - .resume_noirq = resume_fn, \ - .freeze_noirq = suspend_fn, \ - .thaw_noirq = resume_fn, \ - .poweroff_noirq = suspend_fn, \ - .restore_noirq = resume_fn, + NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ - .runtime_suspend = suspend_fn, \ - .runtime_resume = resume_fn, \ - .runtime_idle = idle_fn, + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #else #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #endif +#define _DEFINE_DEV_PM_OPS(name, \ + suspend_fn, resume_fn, \ + runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + RUNTIME_PM_OPS(runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +} + +#ifdef CONFIG_PM +#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn, sec) \ + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn); \ + _EXPORT_SYMBOL(name, sec) +#else +#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn, sec) \ +static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ + resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn) +#endif + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_SIMPLE_DEV_PM_OPS() or EXPORT_GPL_SIMPLE_DEV_PM_OPS() instead. */ +#define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) + +#define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "") +#define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl") + +/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ @@ -366,6 +413,9 @@ const struct dev_pm_ops __maybe_unused name = { \ * suspend and "early" resume callback pointers, .suspend_late() and * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). + * + * Deprecated. You most likely don't want this macro. Use + * DEFINE_RUNTIME_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ @@ -373,11 +423,8 @@ const struct dev_pm_ops __maybe_unused name = { \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } -#ifdef CONFIG_PM -#define pm_ptr(_ptr) (_ptr) -#else -#define pm_ptr(_ptr) NULL -#endif +#define pm_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM), (_ptr)) +#define pm_sleep_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM_SLEEP), (_ptr)) /* * PM_EVENT_ messages @@ -499,6 +546,7 @@ const struct dev_pm_ops __maybe_unused name = { \ */ enum rpm_status { + RPM_INVALID = -1, RPM_ACTIVE = 0, RPM_RESUMING, RPM_SUSPENDED, @@ -612,6 +660,7 @@ struct dev_pm_info { unsigned int links_count; enum rpm_request request; enum rpm_status runtime_status; + enum rpm_status last_status; int runtime_error; int autosuspend_delay; u64 last_busy; @@ -721,11 +770,11 @@ extern int dpm_suspend_late(pm_message_t state); extern int dpm_suspend(pm_message_t state); extern int dpm_prepare(pm_message_t state); -extern void __suspend_report_result(const char *function, void *fn, int ret); +extern void __suspend_report_result(const char *function, struct device *dev, void *fn, int ret); -#define suspend_report_result(fn, ret) \ +#define suspend_report_result(dev, fn, ret) \ do { \ - __suspend_report_result(__func__, fn, ret); \ + __suspend_report_result(__func__, dev, fn, ret); \ } while (0) extern int device_pm_wait_for_dev(struct device *sub, struct device *dev); @@ -765,7 +814,7 @@ static inline int dpm_suspend_start(pm_message_t state) return 0; } -#define suspend_report_result(fn, ret) do {} while (0) +#define suspend_report_result(dev, fn, ret) do {} while (0) static inline int device_pm_wait_for_dev(struct device *a, struct device *b) { diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 879c138c7b8e..0d85a63a1f78 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -32,14 +32,17 @@ enum dev_pm_opp_event { * @u_volt_min: Minimum voltage in microvolts corresponding to this OPP * @u_volt_max: Maximum voltage in microvolts corresponding to this OPP * @u_amp: Maximum current drawn by the device in microamperes + * @u_watt: Power used by the device in microwatts * - * This structure stores the voltage/current values for a single power supply. + * This structure stores the voltage/current/power values for a single power + * supply. */ struct dev_pm_opp_supply { unsigned long u_volt; unsigned long u_volt_min; unsigned long u_volt_max; unsigned long u_amp; + unsigned long u_watt; }; /** @@ -94,6 +97,8 @@ void dev_pm_opp_put_opp_table(struct opp_table *opp_table); unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp); +unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp); + unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp); unsigned int dev_pm_opp_get_level(struct dev_pm_opp *opp); @@ -186,6 +191,11 @@ static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp) return 0; } +static inline unsigned long dev_pm_opp_get_power(struct dev_pm_opp *opp) +{ + return 0; +} + static inline unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp) { return 0; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index eddd66d426ca..2bff6a10095d 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -22,6 +22,30 @@ usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ +/* + * Use this for defining a set of PM operations to be used in all situations + * (system suspend, hibernation or runtime PM). + * + * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() + * macro, which uses the provided callbacks for both runtime PM and system + * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() + * and pm_runtime_force_resume() for its system sleep callbacks. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. + */ +#define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ + pm_runtime_force_resume, suspend_fn, \ + resume_fn, idle_fn) + +#define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "") +#define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "_gpl") + #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; @@ -58,6 +82,7 @@ extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); +extern void pm_runtime_release_supplier(struct device_link *link, bool check_idle); extern int devm_pm_runtime_enable(struct device *dev); @@ -283,6 +308,8 @@ static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} +static inline void pm_runtime_release_supplier(struct device_link *link, + bool check_idle) {} #endif /* !CONFIG_PM */ @@ -540,6 +567,10 @@ static inline void pm_runtime_disable(struct device *dev) * Allow the runtime PM autosuspend mechanism to be used for @dev whenever * requested (or "autosuspend" will be handled as direct runtime-suspend for * it). + * + * NOTE: It's important to undo this with pm_runtime_dont_use_autosuspend() + * at driver exit time unless your driver initially enabled pm_runtime + * with devm_pm_runtime_enable() (which handles it for you). */ static inline void pm_runtime_use_autosuspend(struct device *dev) { diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 52453a24a24f..c677442d007c 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -13,7 +13,7 @@ #include <uapi/linux/pmu.h> -extern int find_via_pmu(void); +extern int __init find_via_pmu(void); extern int pmu_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); diff --git a/include/linux/poll.h b/include/linux/poll.h index 1cdc32b1f1b0..a9e0e1c2d1f2 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -8,12 +8,10 @@ #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> -#include <linux/sysctl.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> -extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #ifdef __clang__ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 5bbcd280bfd2..2c6e99ca48af 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -6,7 +6,6 @@ #include <linux/list.h> #include <linux/alarmtimer.h> #include <linux/timerqueue.h> -#include <linux/task_work.h> struct kernel_siginfo; struct task_struct; @@ -253,7 +252,7 @@ void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); -void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/include/linux/power/bq25890_charger.h b/include/linux/power/bq25890_charger.h new file mode 100644 index 000000000000..c706ddb77a08 --- /dev/null +++ b/include/linux/power/bq25890_charger.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Platform data for the TI bq25890 battery charger driver. + */ + +#ifndef _BQ25890_CHARGER_H_ +#define _BQ25890_CHARGER_H_ + +struct regulator_init_data; + +struct bq25890_platform_data { + const struct regulator_init_data *regulator_init_data; +}; + +#endif diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 9ca1f120a211..cb380c1d9459 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -49,6 +49,7 @@ enum { POWER_SUPPLY_CHARGE_TYPE_ADAPTIVE, /* dynamically adjusted speed */ POWER_SUPPLY_CHARGE_TYPE_CUSTOM, /* use CHARGE_CONTROL_* props */ POWER_SUPPLY_CHARGE_TYPE_LONGLIFE, /* slow speed, longer life */ + POWER_SUPPLY_CHARGE_TYPE_BYPASS, /* bypassing the charger */ }; enum { @@ -66,6 +67,7 @@ enum { POWER_SUPPLY_HEALTH_WARM, POWER_SUPPLY_HEALTH_COOL, POWER_SUPPLY_HEALTH_HOT, + POWER_SUPPLY_HEALTH_NO_BATTERY, }; enum { @@ -132,6 +134,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD, /* in percents! */ POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD, /* in percents! */ + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, POWER_SUPPLY_PROP_INPUT_VOLTAGE_LIMIT, POWER_SUPPLY_PROP_INPUT_POWER_LIMIT, @@ -202,6 +205,12 @@ enum power_supply_usb_type { POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ }; +enum power_supply_charge_behaviour { + POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO = 0, + POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE, + POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE, +}; + enum power_supply_notifier_events { PSY_EVENT_PROP_CHANGED, }; @@ -340,43 +349,385 @@ struct power_supply_resistance_temp_table { int resistance; /* internal resistance percent */ }; +struct power_supply_vbat_ri_table { + int vbat_uv; /* Battery voltage in microvolt */ + int ri_uohm; /* Internal resistance in microohm */ +}; + +/** + * struct power_supply_maintenance_charge_table - setting for maintenace charging + * @charge_current_max_ua: maintenance charging current that is used to keep + * the charge of the battery full as current is consumed after full charging. + * The corresponding charge_voltage_max_uv is used as a safeguard: when we + * reach this voltage the maintenance charging current is turned off. It is + * turned back on if we fall below this voltage. + * @charge_voltage_max_uv: maintenance charging voltage that is usually a bit + * lower than the constant_charge_voltage_max_uv. We can apply this settings + * charge_current_max_ua until we get back up to this voltage. + * @safety_timer_minutes: maintenance charging safety timer, with an expiry + * time in minutes. We will only use maintenance charging in this setting + * for a certain amount of time, then we will first move to the next + * maintenance charge current and voltage pair in respective array and wait + * for the next safety timer timeout, or, if we reached the last maintencance + * charging setting, disable charging until we reach + * charge_restart_voltage_uv and restart ordinary CC/CV charging from there. + * These timers should be chosen to align with the typical discharge curve + * for the battery. + * + * When the main CC/CV charging is complete the battery can optionally be + * maintenance charged at the voltages from this table: a table of settings is + * traversed using a slightly lower current and voltage than what is used for + * CC/CV charging. The maintenance charging will for safety reasons not go on + * indefinately: we lower the current and voltage with successive maintenance + * settings, then disable charging completely after we reach the last one, + * and after that we do not restart charging until we reach + * charge_restart_voltage_uv (see struct power_supply_battery_info) and restart + * ordinary CC/CV charging from there. + * + * As an example, a Samsung EB425161LA Lithium-Ion battery is CC/CV charged + * at 900mA to 4340mV, then maintenance charged at 600mA and 4150mV for + * 60 hours, then maintenance charged at 600mA and 4100mV for 200 hours. + * After this the charge cycle is restarted waiting for + * charge_restart_voltage_uv. + * + * For most mobile electronics this type of maintenance charging is enough for + * the user to disconnect the device and make use of it before both maintenance + * charging cycles are complete. + */ +struct power_supply_maintenance_charge_table { + int charge_current_max_ua; + int charge_voltage_max_uv; + int charge_safety_timer_minutes; +}; + #define POWER_SUPPLY_OCV_TEMP_MAX 20 -/* +/** + * struct power_supply_battery_info - information about batteries + * @technology: from the POWER_SUPPLY_TECHNOLOGY_* enum + * @energy_full_design_uwh: energy content when fully charged in microwatt + * hours + * @charge_full_design_uah: charge content when fully charged in microampere + * hours + * @voltage_min_design_uv: minimum voltage across the poles when the battery + * is at minimum voltage level in microvolts. If the voltage drops below this + * level the battery will need precharging when using CC/CV charging. + * @voltage_max_design_uv: voltage across the poles when the battery is fully + * charged in microvolts. This is the "nominal voltage" i.e. the voltage + * printed on the label of the battery. + * @tricklecharge_current_ua: the tricklecharge current used when trickle + * charging the battery in microamperes. This is the charging phase when the + * battery is completely empty and we need to carefully trickle in some + * charge until we reach the precharging voltage. + * @precharge_current_ua: current to use in the precharge phase in microamperes, + * the precharge rate is limited by limiting the current to this value. + * @precharge_voltage_max_uv: the maximum voltage allowed when precharging in + * microvolts. When we pass this voltage we will nominally switch over to the + * CC (constant current) charging phase defined by constant_charge_current_ua + * and constant_charge_voltage_max_uv. + * @charge_term_current_ua: when the current in the CV (constant voltage) + * charging phase drops below this value in microamperes the charging will + * terminate completely and not restart until the voltage over the battery + * poles reach charge_restart_voltage_uv unless we use maintenance charging. + * @charge_restart_voltage_uv: when the battery has been fully charged by + * CC/CV charging and charging has been disabled, and the voltage subsequently + * drops below this value in microvolts, the charging will be restarted + * (typically using CV charging). + * @overvoltage_limit_uv: If the voltage exceeds the nominal voltage + * voltage_max_design_uv and we reach this voltage level, all charging must + * stop and emergency procedures take place, such as shutting down the system + * in some cases. + * @constant_charge_current_max_ua: current in microamperes to use in the CC + * (constant current) charging phase. The charging rate is limited + * by this current. This is the main charging phase and as the current is + * constant into the battery the voltage slowly ascends to + * constant_charge_voltage_max_uv. + * @constant_charge_voltage_max_uv: voltage in microvolts signifying the end of + * the CC (constant current) charging phase and the beginning of the CV + * (constant voltage) charging phase. + * @maintenance_charge: an array of maintenance charging settings to be used + * after the main CC/CV charging phase is complete. + * @maintenance_charge_size: the number of maintenance charging settings in + * maintenance_charge. + * @alert_low_temp_charge_current_ua: The charging current to use if the battery + * enters low alert temperature, i.e. if the internal temperature is between + * temp_alert_min and temp_min. No matter the charging phase, this + * and alert_high_temp_charge_voltage_uv will be applied. + * @alert_low_temp_charge_voltage_uv: Same as alert_low_temp_charge_current_ua, + * but for the charging voltage. + * @alert_high_temp_charge_current_ua: The charging current to use if the + * battery enters high alert temperature, i.e. if the internal temperature is + * between temp_alert_max and temp_max. No matter the charging phase, this + * and alert_high_temp_charge_voltage_uv will be applied, usually lowering + * the charging current as an evasive manouver. + * @alert_high_temp_charge_voltage_uv: Same as + * alert_high_temp_charge_current_ua, but for the charging voltage. + * @factory_internal_resistance_uohm: the internal resistance of the battery + * at fabrication time, expressed in microohms. This resistance will vary + * depending on the lifetime and charge of the battery, so this is just a + * nominal ballpark figure. This internal resistance is given for the state + * when the battery is discharging. + * @factory_internal_resistance_charging_uohm: the internal resistance of the + * battery at fabrication time while charging, expressed in microohms. + * The charging process will affect the internal resistance of the battery + * so this value provides a better resistance under these circumstances. + * This resistance will vary depending on the lifetime and charge of the + * battery, so this is just a nominal ballpark figure. + * @ocv_temp: array indicating the open circuit voltage (OCV) capacity + * temperature indices. This is an array of temperatures in degrees Celsius + * indicating which capacity table to use for a certain temperature, since + * the capacity for reasons of chemistry will be different at different + * temperatures. Determining capacity is a multivariate problem and the + * temperature is the first variable we determine. + * @temp_ambient_alert_min: the battery will go outside of operating conditions + * when the ambient temperature goes below this temperature in degrees + * Celsius. + * @temp_ambient_alert_max: the battery will go outside of operating conditions + * when the ambient temperature goes above this temperature in degrees + * Celsius. + * @temp_alert_min: the battery should issue an alert if the internal + * temperature goes below this temperature in degrees Celsius. + * @temp_alert_max: the battery should issue an alert if the internal + * temperature goes above this temperature in degrees Celsius. + * @temp_min: the battery will go outside of operating conditions when + * the internal temperature goes below this temperature in degrees Celsius. + * Normally this means the system should shut down. + * @temp_max: the battery will go outside of operating conditions when + * the internal temperature goes above this temperature in degrees Celsius. + * Normally this means the system should shut down. + * @ocv_table: for each entry in ocv_temp there is a corresponding entry in + * ocv_table and a size for each entry in ocv_table_size. These arrays + * determine the capacity in percent in relation to the voltage in microvolts + * at the indexed temperature. + * @ocv_table_size: for each entry in ocv_temp this array is giving the size of + * each entry in the array of capacity arrays in ocv_table. + * @resist_table: this is a table that correlates a battery temperature to the + * expected internal resistance at this temperature. The resistance is given + * as a percentage of factory_internal_resistance_uohm. Knowing the + * resistance of the battery is usually necessary for calculating the open + * circuit voltage (OCV) that is then used with the ocv_table to calculate + * the capacity of the battery. The resist_table must be ordered descending + * by temperature: highest temperature with lowest resistance first, lowest + * temperature with highest resistance last. + * @resist_table_size: the number of items in the resist_table. + * @vbat2ri_discharging: this is a table that correlates Battery voltage (VBAT) + * to internal resistance (Ri). The resistance is given in microohm for the + * corresponding voltage in microvolts. The internal resistance is used to + * determine the open circuit voltage so that we can determine the capacity + * of the battery. These voltages to resistance tables apply when the battery + * is discharging. The table must be ordered descending by voltage: highest + * voltage first. + * @vbat2ri_discharging_size: the number of items in the vbat2ri_discharging + * table. + * @vbat2ri_charging: same function as vbat2ri_discharging but for the state + * when the battery is charging. Being under charge changes the battery's + * internal resistance characteristics so a separate table is needed.* + * The table must be ordered descending by voltage: highest voltage first. + * @vbat2ri_charging_size: the number of items in the vbat2ri_charging + * table. + * @bti_resistance_ohm: The Battery Type Indicator (BIT) nominal resistance + * in ohms for this battery, if an identification resistor is mounted + * between a third battery terminal and ground. This scheme is used by a lot + * of mobile device batteries. + * @bti_resistance_tolerance: The tolerance in percent of the BTI resistance, + * for example 10 for +/- 10%, if the bti_resistance is set to 7000 and the + * tolerance is 10% we will detect a proper battery if the BTI resistance + * is between 6300 and 7700 Ohm. + * * This is the recommended struct to manage static battery parameters, * populated by power_supply_get_battery_info(). Most platform drivers should * use these for consistency. + * * Its field names must correspond to elements in enum power_supply_property. - * The default field value is -EINVAL. - * Power supply class itself doesn't use this. + * The default field value is -EINVAL or NULL for pointers. + * + * CC/CV CHARGING: + * + * The charging parameters here assume a CC/CV charging scheme. This method + * is most common with Lithium Ion batteries (other methods are possible) and + * looks as follows: + * + * ^ Battery voltage + * | --- overvoltage_limit_uv + * | + * | ................................................... + * | .. constant_charge_voltage_max_uv + * | .. + * | . + * | . + * | . + * | . + * | . + * | .. precharge_voltage_max_uv + * | .. + * |. (trickle charging) + * +------------------------------------------------------------------> time + * + * ^ Current into the battery + * | + * | ............. constant_charge_current_max_ua + * | . . + * | . . + * | . . + * | . . + * | . .. + * | . .... + * | . ..... + * | ... precharge_current_ua ....... charge_term_current_ua + * | . . + * | . . + * |.... tricklecharge_current_ua . + * | . + * +-----------------------------------------------------------------> time + * + * These diagrams are synchronized on time and the voltage and current + * follow each other. + * + * With CC/CV charging commence over time like this for an empty battery: + * + * 1. When the battery is completely empty it may need to be charged with + * an especially small current so that electrons just "trickle in", + * this is the tricklecharge_current_ua. + * + * 2. Next a small initial pre-charge current (precharge_current_ua) + * is applied if the voltage is below precharge_voltage_max_uv until we + * reach precharge_voltage_max_uv. CAUTION: in some texts this is referred + * to as "trickle charging" but the use in the Linux kernel is different + * see below! + * + * 3. Then the main charging current is applied, which is called the constant + * current (CC) phase. A current regulator is set up to allow + * constant_charge_current_max_ua of current to flow into the battery. + * The chemical reaction in the battery will make the voltage go up as + * charge goes into the battery. This current is applied until we reach + * the constant_charge_voltage_max_uv voltage. + * + * 4. At this voltage we switch over to the constant voltage (CV) phase. This + * means we allow current to go into the battery, but we keep the voltage + * fixed. This current will continue to charge the battery while keeping + * the voltage the same. A chemical reaction in the battery goes on + * storing energy without affecting the voltage. Over time the current + * will slowly drop and when we reach charge_term_current_ua we will + * end the constant voltage phase. + * + * After this the battery is fully charged, and if we do not support maintenance + * charging, the charging will not restart until power dissipation makes the + * voltage fall so that we reach charge_restart_voltage_uv and at this point + * we restart charging at the appropriate phase, usually this will be inside + * the CV phase. + * + * If we support maintenance charging the voltage is however kept high after + * the CV phase with a very low current. This is meant to let the same charge + * go in for usage while the charger is still connected, mainly for + * dissipation for the power consuming entity while connected to the + * charger. + * + * All charging MUST terminate if the overvoltage_limit_uv is ever reached. + * Overcharging Lithium Ion cells can be DANGEROUS and lead to fire or + * explosions. + * + * DETERMINING BATTERY CAPACITY: + * + * Several members of the struct deal with trying to determine the remaining + * capacity in the battery, usually as a percentage of charge. In practice + * many chargers uses a so-called fuel gauge or coloumb counter that measure + * how much charge goes into the battery and how much goes out (+/- leak + * consumption). This does not help if we do not know how much capacity the + * battery has to begin with, such as when it is first used or was taken out + * and charged in a separate charger. Therefore many capacity algorithms use + * the open circuit voltage with a look-up table to determine the rough + * capacity of the battery. The open circuit voltage can be conceptualized + * with an ideal voltage source (V) in series with an internal resistance (Ri) + * like this: + * + * +-------> IBAT >----------------+ + * | ^ | + * [ ] Ri | | + * | | VBAT | + * o <---------- | | + * +| ^ | [ ] Rload + * .---. | | | + * | V | | OCV | | + * '---' | | | + * | | | | + * GND +-------------------------------+ + * + * If we disconnect the load (here simplified as a fixed resistance Rload) + * and measure VBAT with a infinite impedance voltage meter we will get + * VBAT = OCV and this assumption is sometimes made even under load, assuming + * Rload is insignificant. However this will be of dubious quality because the + * load is rarely that small and Ri is strongly nonlinear depending on + * temperature and how much capacity is left in the battery due to the + * chemistry involved. + * + * In many practical applications we cannot just disconnect the battery from + * the load, so instead we often try to measure the instantaneous IBAT (the + * current out from the battery), estimate the Ri and thus calculate the + * voltage drop over Ri and compensate like this: + * + * OCV = VBAT - (IBAT * Ri) + * + * The tables vbat2ri_discharging and vbat2ri_charging are used to determine + * (by interpolation) the Ri from the VBAT under load. These curves are highly + * nonlinear and may need many datapoints but can be found in datasheets for + * some batteries. This gives the compensated open circuit voltage (OCV) for + * the battery even under load. Using this method will also compensate for + * temperature changes in the environment: this will also make the internal + * resistance change, and it will affect the VBAT under load, so correlating + * VBAT to Ri takes both remaining capacity and temperature into consideration. + * + * Alternatively a manufacturer can specify how the capacity of the battery + * is dependent on the battery temperature which is the main factor affecting + * Ri. As we know all checmical reactions are faster when it is warm and slower + * when it is cold. You can put in 1500mAh and only get 800mAh out before the + * voltage drops too low for example. This effect is also highly nonlinear and + * the purpose of the table resist_table: this will take a temperature and + * tell us how big percentage of Ri the specified temperature correlates to. + * Usually we have 100% of the factory_internal_resistance_uohm at 25 degrees + * Celsius. + * + * The power supply class itself doesn't use this struct as of now. */ struct power_supply_battery_info { - unsigned int technology; /* from the enum above */ - int energy_full_design_uwh; /* microWatt-hours */ - int charge_full_design_uah; /* microAmp-hours */ - int voltage_min_design_uv; /* microVolts */ - int voltage_max_design_uv; /* microVolts */ - int tricklecharge_current_ua; /* microAmps */ - int precharge_current_ua; /* microAmps */ - int precharge_voltage_max_uv; /* microVolts */ - int charge_term_current_ua; /* microAmps */ - int charge_restart_voltage_uv; /* microVolts */ - int overvoltage_limit_uv; /* microVolts */ - int constant_charge_current_max_ua; /* microAmps */ - int constant_charge_voltage_max_uv; /* microVolts */ - int factory_internal_resistance_uohm; /* microOhms */ - int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX];/* celsius */ - int temp_ambient_alert_min; /* celsius */ - int temp_ambient_alert_max; /* celsius */ - int temp_alert_min; /* celsius */ - int temp_alert_max; /* celsius */ - int temp_min; /* celsius */ - int temp_max; /* celsius */ + unsigned int technology; + int energy_full_design_uwh; + int charge_full_design_uah; + int voltage_min_design_uv; + int voltage_max_design_uv; + int tricklecharge_current_ua; + int precharge_current_ua; + int precharge_voltage_max_uv; + int charge_term_current_ua; + int charge_restart_voltage_uv; + int overvoltage_limit_uv; + int constant_charge_current_max_ua; + int constant_charge_voltage_max_uv; + struct power_supply_maintenance_charge_table *maintenance_charge; + int maintenance_charge_size; + int alert_low_temp_charge_current_ua; + int alert_low_temp_charge_voltage_uv; + int alert_high_temp_charge_current_ua; + int alert_high_temp_charge_voltage_uv; + int factory_internal_resistance_uohm; + int factory_internal_resistance_charging_uohm; + int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX]; + int temp_ambient_alert_min; + int temp_ambient_alert_max; + int temp_alert_min; + int temp_alert_max; + int temp_min; + int temp_max; struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX]; int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; int resist_table_size; + struct power_supply_vbat_ri_table *vbat2ri_discharging; + int vbat2ri_discharging_size; + struct power_supply_vbat_ri_table *vbat2ri_charging; + int vbat2ri_charging_size; + int bti_resistance_ohm; + int bti_resistance_tolerance; }; extern struct atomic_notifier_head power_supply_notifier; @@ -405,7 +756,7 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) #endif /* CONFIG_OF */ extern int power_supply_get_battery_info(struct power_supply *psy, - struct power_supply_battery_info *info); + struct power_supply_battery_info **info_out); extern void power_supply_put_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, @@ -418,12 +769,43 @@ extern int power_supply_batinfo_ocv2cap(struct power_supply_battery_info *info, extern int power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table, int table_len, int temp); +extern int power_supply_vbat2ri(struct power_supply_battery_info *info, + int vbat_uv, bool charging); +extern struct power_supply_maintenance_charge_table * +power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); +extern bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, + int resistance); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); -extern int power_supply_set_input_current_limit_from_supplier( - struct power_supply *psy); +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_set_battery_charged(struct power_supply *psy); +static inline bool +power_supply_supports_maintenance_charging(struct power_supply_battery_info *info) +{ + struct power_supply_maintenance_charge_table *mt; + + mt = power_supply_get_maintenance_charging_setting(info, 0); + + return (mt != NULL); +} + +static inline bool +power_supply_supports_vbat2ri(struct power_supply_battery_info *info) +{ + return ((info->vbat2ri_discharging != NULL) && + info->vbat2ri_discharging_size > 0); +} + +static inline bool +power_supply_supports_temp2ri(struct power_supply_battery_info *info) +{ + return ((info->resist_table != NULL) && + info->resist_table_size > 0); +} + #ifdef CONFIG_POWER_SUPPLY extern int power_supply_is_system_supplied(void); #else @@ -539,4 +921,28 @@ static inline void power_supply_remove_hwmon_sysfs(struct power_supply *psy) {} #endif +#ifdef CONFIG_SYSFS +ssize_t power_supply_charge_behaviour_show(struct device *dev, + unsigned int available_behaviours, + enum power_supply_charge_behaviour behaviour, + char *buf); + +int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf); +#else +static inline +ssize_t power_supply_charge_behaviour_show(struct device *dev, + unsigned int available_behaviours, + enum power_supply_charge_behaviour behaviour, + char *buf) +{ + return -EOPNOTSUPP; +} + +static inline int power_supply_charge_behaviour_parse(unsigned int available_behaviours, + const char *buf) +{ + return -EOPNOTSUPP; +} +#endif + #endif /* __LINUX_POWER_SUPPLY_H__ */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 9497f6b98339..1522df223c0f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -183,10 +183,6 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, extern int printk_delay_msec; extern int dmesg_restrict; -extern int -devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, - size_t *lenp, loff_t *ppos); - extern void wake_up_klogd(void); char *log_buf_addr_get(void); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 069c7fd95396..81d6e4ec2294 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -110,7 +110,16 @@ extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); -extern void *PDE_DATA(const struct inode *); + +/* + * Obtain the private data passed by user through proc_create_data() or + * related. + */ +static inline void *pde_data(const struct inode *inode) +{ + return inode->i_private; +} + extern void *proc_get_parent_data(const struct inode *); extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); @@ -178,12 +187,20 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) -#define proc_create(name, mode, parent, proc_ops) ({NULL;}) -#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;}) + +static inline struct proc_dir_entry * +proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops) +{ return NULL; } + +static inline struct proc_dir_entry * +proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops, void *data) +{ return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;} +static inline void *pde_data(const struct inode *inode) {BUG(); return NULL;} static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; } static inline void proc_remove(struct proc_dir_entry *de) {} diff --git a/include/linux/profile.h b/include/linux/profile.h index fd18ca96f557..11db1ec516e2 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -31,11 +31,6 @@ static inline int create_proc_profile(void) } #endif -enum profile_type { - PROFILE_TASK_EXIT, - PROFILE_MUNMAP -}; - #ifdef CONFIG_PROFILING extern int prof_on __read_mostly; @@ -66,23 +61,6 @@ static inline void profile_hit(int type, void *ip) struct task_struct; struct mm_struct; -/* task is in do_exit() */ -void profile_task_exit(struct task_struct * task); - -/* task is dead, free task struct ? Returns 1 if - * the task was taken, 0 if the task should be freed. - */ -int profile_handoff_task(struct task_struct * task); - -/* sys_munmap */ -void profile_munmap(unsigned long addr); - -int task_handoff_register(struct notifier_block * n); -int task_handoff_unregister(struct notifier_block * n); - -int profile_event_register(enum profile_type, struct notifier_block * n); -int profile_event_unregister(enum profile_type, struct notifier_block * n); - #else #define prof_on 0 @@ -107,29 +85,6 @@ static inline void profile_hit(int type, void *ip) return; } -static inline int task_handoff_register(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int task_handoff_unregister(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_register(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_unregister(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -#define profile_task_exit(a) do { } while (0) -#define profile_handoff_task(a) (0) -#define profile_munmap(a) do { } while (0) #endif /* CONFIG_PROFILING */ diff --git a/include/linux/property.h b/include/linux/property.h index 88fa726a76df..4cd4b326941f 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -121,6 +121,7 @@ struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); void fwnode_handle_put(struct fwnode_handle *fwnode); int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); +int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(struct device *dev); @@ -378,10 +379,6 @@ property_entries_dup(const struct property_entry *properties); void property_entries_free(const struct property_entry *properties); -int device_add_properties(struct device *dev, - const struct property_entry *properties); -void device_remove_properties(struct device *dev); - bool device_dma_supported(struct device *dev); enum dev_dma_attr device_get_dma_attr(struct device *dev); @@ -389,8 +386,10 @@ enum dev_dma_attr device_get_dma_attr(struct device *dev); const void *device_get_match_data(struct device *dev); int device_get_phy_mode(struct device *dev); - int fwnode_get_phy_mode(struct fwnode_handle *fwnode); + +void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); + struct fwnode_handle *fwnode_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * @@ -401,9 +400,6 @@ struct fwnode_handle *fwnode_graph_get_remote_port( const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_endpoint( const struct fwnode_handle *fwnode); -struct fwnode_handle * -fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, - u32 endpoint); static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) { @@ -418,7 +414,8 @@ static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) * one. * @FWNODE_GRAPH_DEVICE_DISABLED: That the device to which the remote * endpoint of the given endpoint belongs to, - * may be disabled. + * may be disabled, or that the endpoint is not + * connected. */ #define FWNODE_GRAPH_ENDPOINT_NEXT BIT(0) #define FWNODE_GRAPH_DEVICE_DISABLED BIT(1) @@ -426,6 +423,8 @@ static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); +unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, + unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ for (child = NULL; \ diff --git a/include/linux/psi.h b/include/linux/psi.h index 65eb1476ac70..89784763d19e 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H @@ -5,6 +6,7 @@ #include <linux/psi_types.h> #include <linux/sched.h> #include <linux/poll.h> +#include <linux/cgroup-defs.h> struct seq_file; struct css_set; @@ -24,18 +26,17 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); - -#ifdef CONFIG_CGROUPS -int psi_cgroup_alloc(struct cgroup *cgrp); -void psi_cgroup_free(struct cgroup *cgrp); -void cgroup_move_task(struct task_struct *p, struct css_set *to); - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); +void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); #endif #else /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 0a23300d49af..c7fe7c089718 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_TYPES_H #define _LINUX_PSI_TYPES_H @@ -21,7 +22,17 @@ enum psi_task_count { * don't have to special case any state tracking for it. */ NR_ONCPU, - NR_PSI_TASK_COUNTS = 4, + /* + * For IO and CPU stalls the presence of running/oncpu tasks + * in the domain means a partial rather than a full stall. + * For memory it's not so simple because of page reclaimers: + * they are running/oncpu while representing a stall. To tell + * whether a domain has productivity left or not, we need to + * distinguish between regular running (i.e. productive) + * threads and memstall ones. + */ + NR_MEMSTALL_RUNNING, + NR_PSI_TASK_COUNTS = 5, }; /* Task state bitmasks */ @@ -29,6 +40,7 @@ enum psi_task_count { #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) #define TSK_ONCPU (1 << NR_ONCPU) +#define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) /* Resources that workloads could be stalled on */ enum psi_res { @@ -130,8 +142,8 @@ struct psi_trigger { */ u64 last_event_time; - /* Refcounting to prevent premature destruction */ - struct kref refcount; + /* Deferred event(s) from previous ratelimit window */ + bool pending_event; }; struct psi_group { diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index d48a7192e881..1595088c428b 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -52,6 +52,7 @@ enum sev_cmd { SEV_CMD_DF_FLUSH = 0x00A, SEV_CMD_DOWNLOAD_FIRMWARE = 0x00B, SEV_CMD_GET_ID = 0x00C, + SEV_CMD_INIT_EX = 0x00D, /* Guest commands */ SEV_CMD_DECOMMISSION = 0x020, @@ -102,6 +103,26 @@ struct sev_data_init { u32 tmr_len; /* In */ } __packed; +/** + * struct sev_data_init_ex - INIT_EX command parameters + * + * @length: len of the command buffer read by the PSP + * @flags: processing flags + * @tmr_address: system physical address used for SEV-ES + * @tmr_len: len of tmr_address + * @nv_address: system physical address used for PSP NV storage + * @nv_len: len of nv_address + */ +struct sev_data_init_ex { + u32 length; /* In */ + u32 flags; /* In */ + u64 tmr_address; /* In */ + u32 tmr_len; /* In */ + u32 reserved; /* In */ + u64 nv_address; /* In/Out */ + u32 nv_len; /* In */ +} __packed; + #define SEV_INIT_FLAGS_SEV_ES 0x01 /** diff --git a/include/linux/pstore.h b/include/linux/pstore.h index eb93a54cff31..e97a8188f0fd 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/kmsg_dump.h> #include <linux/mutex.h> -#include <linux/semaphore.h> +#include <linux/spinlock.h> #include <linux/time.h> #include <linux/types.h> @@ -87,7 +87,7 @@ struct pstore_record { * @owner: module which is responsible for this backend driver * @name: name of the backend driver * - * @buf_lock: semaphore to serialize access to @buf + * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer * @bufsize: size of @buf available for crash dump bytes (must match * smallest number of bytes available for writing to a @@ -178,7 +178,7 @@ struct pstore_info { struct module *owner; const char *name; - struct semaphore buf_lock; + spinlock_t buf_lock; char *buf; size_t bufsize; diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index 9afd34a2d36c..fefa7790dc46 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -126,6 +126,17 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, return msgtype; } +/** + * ptp_msg_is_sync - Evaluates whether the given skb is a PTP Sync message + * @skb: packet buffer + * @type: type of the packet (see ptp_classify_raw()) + * + * This function evaluates whether the given skb is a PTP Sync message. + * + * Return: true if sync message, false otherwise + */ +bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type); + void __init ptp_classifier_init(void); #else static inline void ptp_classifier_init(void) @@ -148,5 +159,9 @@ static inline u8 ptp_get_msgtype(const struct ptp_header *hdr, */ return PTP_MSGTYPE_SYNC; } +static inline bool ptp_msg_is_sync(struct sk_buff *skb, unsigned int type) +{ + return false; +} #endif #endif /* _PTP_CLASSIFY_H_ */ diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 2e5565067355..554454cb8693 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -351,15 +351,17 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); * * @hwtstamps: skb_shared_hwtstamps structure pointer * @vclock_index: phc index of ptp vclock. + * + * Returns converted timestamp, or 0 on error. */ -void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index); +ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index); #else static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } -static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index) -{ } +static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ return 0; } #endif diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 8aee2945ff08..15b3d176b6b4 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -60,7 +60,7 @@ extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned extern void ptrace_disable(struct task_struct *); extern int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data); -extern void ptrace_notify(int exit_code); +extern int ptrace_notify(int exit_code, unsigned long message); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred); @@ -155,8 +155,7 @@ static inline bool ptrace_event_enabled(struct task_struct *task, int event) static inline void ptrace_event(int event, unsigned long message) { if (unlikely(ptrace_event_enabled(current, event))) { - current->ptrace_message = message; - ptrace_notify((event << 8) | SIGTRAP); + ptrace_notify((event << 8) | SIGTRAP, message); } else if (event == PTRACE_EVENT_EXEC) { /* legacy EXEC report via SIGTRAP */ if ((current->ptrace & (PT_PTRACED|PT_SEIZED)) == PT_PTRACED) @@ -413,4 +412,80 @@ static inline void user_single_step_report(struct pt_regs *regs) extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); + +/* + * ptrace report for syscall entry and exit looks identical. + */ +static inline int ptrace_report_syscall(unsigned long message) +{ + int ptrace = current->ptrace; + int signr; + + if (!(ptrace & PT_PTRACED)) + return 0; + + signr = ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0), + message); + + /* + * this isn't the same as continuing with a signal, but it will do + * for normal use. strace only continues with a signal if the + * stopping signal is not SIGTRAP. -brl + */ + if (signr) + send_sig(signr, current, 1); + + return fatal_signal_pending(current); +} + +/** + * ptrace_report_syscall_entry - task is about to attempt a system call + * @regs: user register state of current task + * + * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or + * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just + * entered the kernel for a system call. Full user register state is + * available here. Changing the values in @regs can affect the system + * call number and arguments to be tried. It is safe to block here, + * preventing the system call from beginning. + * + * Returns zero normally, or nonzero if the calling arch code should abort + * the system call. That must prevent normal entry so no system call is + * made. If @task ever returns to user mode after this, its register state + * is unspecified, but should be something harmless like an %ENOSYS error + * return. It should preserve enough information so that syscall_rollback() + * can work (see asm-generic/syscall.h). + * + * Called without locks, just after entering kernel mode. + */ +static inline __must_check int ptrace_report_syscall_entry( + struct pt_regs *regs) +{ + return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); +} + +/** + * ptrace_report_syscall_exit - task has just finished a system call + * @regs: user register state of current task + * @step: nonzero if simulating single-step or block-step + * + * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when + * the current task has just finished an attempted system call. Full + * user register state is available here. It is safe to block here, + * preventing signals from being processed. + * + * If @step is nonzero, this report is also in lieu of the normal + * trap that would follow the system call instruction because + * user_enable_block_step() or user_enable_single_step() was used. + * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. + * + * Called without locks, just before checking for pending signals. + */ +static inline void ptrace_report_syscall_exit(struct pt_regs *regs, int step) +{ + if (step) + user_single_step_report(regs); + else + ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); +} #endif diff --git a/include/linux/ptrace_api.h b/include/linux/ptrace_api.h new file mode 100644 index 000000000000..26e7d275ad8d --- /dev/null +++ b/include/linux/ptrace_api.h @@ -0,0 +1 @@ +#include <linux/ptrace.h> diff --git a/include/linux/pwm.h b/include/linux/pwm.h index e6dac95e4960..9771a0761a40 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -414,6 +414,8 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args); +struct pwm_device *of_pwm_single_xlate(struct pwm_chip *pc, + const struct of_phandle_args *args); struct pwm_device *pwm_get(struct device *dev, const char *con_id); struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index 81cad9e1e412..f8335644a01a 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -63,13 +63,21 @@ enum qcom_scm_ice_cipher { extern bool qcom_scm_is_available(void); -extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); -extern int qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus); +extern int qcom_scm_set_cold_boot_addr(void *entry); +extern int qcom_scm_set_warm_boot_addr(void *entry); extern void qcom_scm_cpu_power_down(u32 flags); extern int qcom_scm_set_remote_state(u32 state, u32 id); +struct qcom_scm_pas_metadata { + void *ptr; + dma_addr_t phys; + ssize_t size; +}; + extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size); + size_t size, + struct qcom_scm_pas_metadata *ctx); +void qcom_scm_pas_metadata_release(struct qcom_scm_pas_metadata *ctx); extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size); extern int qcom_scm_pas_auth_and_reset(u32 peripheral); @@ -83,6 +91,7 @@ extern bool qcom_scm_restore_sec_cfg_available(void); extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare); extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size); extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare); +extern int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size); extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, u32 cp_nonpixel_start, u32 cp_nonpixel_size); @@ -107,6 +116,7 @@ extern bool qcom_scm_hdcp_available(void); extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp); +extern int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt); extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en); extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 0dae7fcc5ef2..6dc4943d8aec 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -652,6 +652,7 @@ struct qed_dev_info { bool wol_support; bool smart_an; + bool esl; /* MBI version */ u32 mbi_version; @@ -807,6 +808,12 @@ struct qed_devlink { struct devlink_health_reporter *fw_reporter; }; +struct qed_sb_info_dbg { + u32 igu_prod; + u32 igu_cons; + u16 pi[PIS_PER_SB]; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -1194,6 +1201,13 @@ struct qed_common_ops { struct devlink* (*devlink_register)(struct qed_dev *cdev); void (*devlink_unregister)(struct devlink *devlink); + + __printf(2, 3) void (*mfw_report)(struct qed_dev *cdev, char *fmt, ...); + + int (*get_sb_info)(struct qed_dev *cdev, struct qed_sb_info *sb, + u16 qid, struct qed_sb_info_dbg *sb_dbg); + + int (*get_esl_status)(struct qed_dev *cdev, bool *esl_active); }; #define MASK_FIELD(_name, _value) \ diff --git a/include/linux/quota.h b/include/linux/quota.h index 18ebd39c9487..fd692b4a41d5 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -91,7 +91,7 @@ extern bool qid_valid(struct kqid qid); * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to - * test for and handle handle invalid kqids being returned. + * test for and handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 154e954b711d..d6e5a1feb947 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -81,7 +81,7 @@ struct raid6_calls { void (*xor_syndrome)(int, int, int, size_t, void **); int (*valid)(void); /* Returns 1 if this routine set is usable */ const char *name; /* Name of this routine set */ - int prefer; /* Has special performance attribute */ + int priority; /* Relative priority ranking if non-zero */ }; /* Selected algorithm */ diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h index 2a9fee8ddae3..51b811b62322 100644 --- a/include/linux/raid/xor.h +++ b/include/linux/raid/xor.h @@ -11,13 +11,20 @@ struct xor_block_template { struct xor_block_template *next; const char *name; int speed; - void (*do_2)(unsigned long, unsigned long *, unsigned long *); - void (*do_3)(unsigned long, unsigned long *, unsigned long *, - unsigned long *); - void (*do_4)(unsigned long, unsigned long *, unsigned long *, - unsigned long *, unsigned long *); - void (*do_5)(unsigned long, unsigned long *, unsigned long *, - unsigned long *, unsigned long *, unsigned long *); + void (*do_2)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_3)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_4)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); + void (*do_5)(unsigned long, unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict, + const unsigned long * __restrict); }; #endif diff --git a/include/linux/random.h b/include/linux/random.h index f45b8be3e3c4..f673fbb838b3 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -1,9 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * include/linux/random.h - * - * Include file for the random number generator. - */ + #ifndef _LINUX_RANDOM_H #define _LINUX_RANDOM_H @@ -14,14 +10,10 @@ #include <uapi/linux/random.h> -struct random_ready_callback { - struct list_head list; - void (*func)(struct random_ready_callback *rdy); - struct module *owner; -}; +struct notifier_block; -extern void add_device_randomness(const void *, unsigned int); -extern void add_bootloader_randomness(const void *, unsigned int); +extern void add_device_randomness(const void *, size_t); +extern void add_bootloader_randomness(const void *, size_t); #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) static inline void add_latent_entropy(void) @@ -35,15 +27,25 @@ static inline void add_latent_entropy(void) {} extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; +extern void add_interrupt_randomness(int irq) __latent_entropy; +extern void add_hwgenerator_randomness(const void *buffer, size_t count, + size_t entropy); +#if IS_ENABLED(CONFIG_VMGENID) +extern void add_vmfork_randomness(const void *unique_vm_id, size_t size); +extern int register_random_vmfork_notifier(struct notifier_block *nb); +extern int unregister_random_vmfork_notifier(struct notifier_block *nb); +#else +static inline int register_random_vmfork_notifier(struct notifier_block *nb) { return 0; } +static inline int unregister_random_vmfork_notifier(struct notifier_block *nb) { return 0; } +#endif -extern void get_random_bytes(void *buf, int nbytes); +extern void get_random_bytes(void *buf, size_t nbytes); extern int wait_for_random_bytes(void); extern int __init rand_initialize(void); extern bool rng_is_initialized(void); -extern int add_random_ready_callback(struct random_ready_callback *rdy); -extern void del_random_ready_callback(struct random_ready_callback *rdy); -extern int __must_check get_random_bytes_arch(void *buf, int nbytes); +extern int register_random_ready_notifier(struct notifier_block *nb); +extern int unregister_random_ready_notifier(struct notifier_block *nb); +extern size_t __must_check get_random_bytes_arch(void *buf, size_t nbytes); #ifndef MODULE extern const struct file_operations random_fops, urandom_fops; @@ -87,7 +89,7 @@ static inline unsigned long get_random_canary(void) /* Calls wait_for_random_bytes() and then calls get_random_bytes(buf, nbytes). * Returns the result of the call to wait_for_random_bytes. */ -static inline int get_random_bytes_wait(void *buf, int nbytes) +static inline int get_random_bytes_wait(void *buf, size_t nbytes) { int ret = wait_for_random_bytes(); get_random_bytes(buf, nbytes); @@ -158,4 +160,9 @@ static inline bool __init arch_get_random_long_early(unsigned long *v) } #endif +#ifdef CONFIG_SMP +extern int random_prepare_cpu(unsigned int cpu); +extern int random_online_cpu(unsigned int cpu); +#endif + #endif /* _LINUX_RANDOM_H */ diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index bebc911161b6..1468caf001c0 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -2,6 +2,7 @@ #ifndef _LINUX_RANDOMIZE_KSTACK_H #define _LINUX_RANDOMIZE_KSTACK_H +#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET #include <linux/kernel.h> #include <linux/jump_label.h> #include <linux/percpu-defs.h> @@ -16,8 +17,20 @@ DECLARE_PER_CPU(u32, kstack_offset); * alignment. Also, since this use is being explicitly masked to a max of * 10 bits, stack-clash style attacks are unlikely. For more details see * "VLAs" in Documentation/process/deprecated.rst + * + * The normal __builtin_alloca() is initialized with INIT_STACK_ALL (currently + * only with Clang and not GCC). Initializing the unused area on each syscall + * entry is expensive, and generating an implicit call to memset() may also be + * problematic (such as in noinstr functions). Therefore, if the compiler + * supports it (which it should if it initializes allocas), always use the + * "uninitialized" variant of the builtin. */ -void *__builtin_alloca(size_t size); +#if __has_builtin(__builtin_alloca_uninitialized) +#define __kstack_alloca __builtin_alloca_uninitialized +#else +#define __kstack_alloca __builtin_alloca +#endif + /* * Use, at most, 10 bits of entropy. We explicitly cap this to keep the * "VLA" from being unbounded (see above). 10 bits leaves enough room for @@ -36,7 +49,7 @@ void *__builtin_alloca(size_t size); if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \ &randomize_kstack_offset)) { \ u32 offset = raw_cpu_read(kstack_offset); \ - u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ + u8 *ptr = __kstack_alloca(KSTACK_OFFSET_MAX(offset)); \ /* Keep allocation even after "ptr" loses scope. */ \ asm volatile("" :: "r"(ptr) : "memory"); \ } \ @@ -50,5 +63,9 @@ void *__builtin_alloca(size_t size); raw_cpu_write(kstack_offset, offset); \ } \ } while (0) +#else /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ +#define add_random_kstack_offset() do { } while (0) +#define choose_random_kstack_offset(rand) do { } while (0) +#endif /* CONFIG_RANDOMIZE_KSTACK_OFFSET */ #endif diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index b676aa419eef..c21c7f8103e2 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -4,7 +4,7 @@ #include <linux/bits.h> #include <linux/param.h> -#include <linux/spinlock_types.h> +#include <linux/spinlock_types_raw.h> #define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) #define DEFAULT_RATELIMIT_BURST 10 diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 3db96c4f45fd..659d13a7ddaa 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -69,7 +69,7 @@ struct rcu_cblist { * * * ---------------------------------------------------------------------------- - * | SEGCBLIST_SOFTIRQ_ONLY | + * | SEGCBLIST_RCU_CORE | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, without holding nocb_lock. | @@ -77,7 +77,7 @@ struct rcu_cblist { * | * v * ---------------------------------------------------------------------------- - * | SEGCBLIST_OFFLOADED | + * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads, | @@ -89,7 +89,9 @@ struct rcu_cblist { * | | * v v * --------------------------------------- ----------------------------------| - * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_RCU_CORE | | | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | * | SEGCBLIST_KTHREAD_CB | | SEGCBLIST_KTHREAD_GP | * | | | | * | | | | @@ -104,9 +106,10 @@ struct rcu_cblist { * | * v * |--------------------------------------------------------------------------| - * | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | - * | SEGCBLIST_KTHREAD_GP | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_GP | | + * | SEGCBLIST_KTHREAD_CB | * | | * | Kthreads handle callbacks holding nocb_lock, local rcu_core() stops | * | handling callbacks. Enable bypass queueing. | @@ -120,7 +123,8 @@ struct rcu_cblist { * * * |--------------------------------------------------------------------------| - * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | * | | @@ -130,6 +134,22 @@ struct rcu_cblist { * | * v * |--------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | + * | handles callbacks concurrently. Bypass enqueue is enabled. | + * | Invoke RCU core so we make sure not to preempt it in the middle with | + * | leaving some urgent work unattended within a jiffy. | + * ---------------------------------------------------------------------------- + * | + * v + * |--------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | * | | @@ -143,7 +163,9 @@ struct rcu_cblist { * | | * v v * ---------------------------------------------------------------------------| - * | | + * | | | + * | SEGCBLIST_RCU_CORE | | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | SEGCBLIST_LOCKING | | * | SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | * | | | * | GP kthread woke up and | CB kthread woke up and | @@ -159,7 +181,7 @@ struct rcu_cblist { * | * v * ---------------------------------------------------------------------------- - * | 0 | + * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed. | @@ -168,17 +190,18 @@ struct rcu_cblist { * | * v * ---------------------------------------------------------------------------- - * | SEGCBLIST_SOFTIRQ_ONLY | + * | SEGCBLIST_RCU_CORE | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, without holding nocb_lock. | * ---------------------------------------------------------------------------- */ #define SEGCBLIST_ENABLED BIT(0) -#define SEGCBLIST_SOFTIRQ_ONLY BIT(1) -#define SEGCBLIST_KTHREAD_CB BIT(2) -#define SEGCBLIST_KTHREAD_GP BIT(3) -#define SEGCBLIST_OFFLOADED BIT(4) +#define SEGCBLIST_RCU_CORE BIT(1) +#define SEGCBLIST_LOCKING BIT(2) +#define SEGCBLIST_KTHREAD_CB BIT(3) +#define SEGCBLIST_KTHREAD_GP BIT(4) +#define SEGCBLIST_OFFLOADED BIT(5) struct rcu_segcblist { struct rcu_head *head; diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5e0beb5c5659..e7c39c200e2b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -84,7 +84,7 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); @@ -364,6 +364,12 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +#define __unrcu_pointer(p, local) \ +({ \ + typeof(*p) *local = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(local)); \ +}) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property @@ -371,39 +377,35 @@ static inline void rcu_preempt_sleep_check(void) { } * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ -#define unrcu_pointer(p) \ -({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ - rcu_check_sparse(p, __rcu); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ -}) +#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) -#define __rcu_access_pointer(p, space) \ +#define __rcu_access_pointer(p, local, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ + typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ + ((typeof(*p) __force __kernel *)(local)); \ }) -#define __rcu_dereference_check(p, c, space) \ +#define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ + typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(________p1)); \ + ((typeof(*p) __force __kernel *)(local)); \ }) -#define __rcu_dereference_protected(p, c, space) \ +#define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) -#define rcu_dereference_raw(p) \ +#define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(p) ________p1 = READ_ONCE(p); \ - ((typeof(*p) __force __kernel *)(________p1)); \ + typeof(p) local = READ_ONCE(p); \ + ((typeof(*p) __force __kernel *)(local)); \ }) +#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable @@ -490,7 +492,7 @@ do { \ * when tearing down multi-linked structures after a grace period * has elapsed. */ -#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) +#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking @@ -526,7 +528,8 @@ do { \ * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking @@ -541,7 +544,8 @@ do { \ * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking @@ -556,7 +560,8 @@ do { \ * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_sched_held(), \ __rcu) /* @@ -566,7 +571,8 @@ do { \ * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ -#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) +#define rcu_dereference_raw_check(p) \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented @@ -585,7 +591,7 @@ do { \ * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) + __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** @@ -918,7 +924,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * * kvfree_rcu(ptr); * - * where @ptr is a pointer to kvfree(). + * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 9be015305f9f..5fed476f977f 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -64,9 +64,8 @@ static inline void rcu_softirq_qs(void) rcu_tasks_qs(current, (preempt)); \ } while (0) -static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt) +static inline int rcu_needs_cpu(void) { - *nextevt = KTIME_MAX; return 0; } @@ -85,7 +84,7 @@ static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } static inline void rcu_irq_exit_check_preempt(void) { } #define rcu_is_idle_cpu(cpu) \ - (is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq()) + (is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq()) static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 53209d669400..9c6cfb742504 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -19,7 +19,7 @@ void rcu_softirq_qs(void); void rcu_note_context_switch(bool preempt); -int rcu_needs_cpu(u64 basem, u64 *nextevt); +int rcu_needs_cpu(void); void rcu_cpu_stall_reset(void); /* @@ -62,7 +62,7 @@ static inline void rcu_irq_exit_check_preempt(void) { } void exit_rcu(void); void rcu_scheduler_starting(void); -extern int rcu_scheduler_active __read_mostly; +extern int rcu_scheduler_active; void rcu_end_inkernel_boot(void); bool rcu_inkernel_boot_has_ended(void); bool rcu_is_watching(void); diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 61c56cca95c4..8052d34da782 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -47,11 +47,7 @@ static inline void prepare_to_rcuwait(struct rcuwait *w) rcu_assign_pointer(w->task, current); } -static inline void finish_rcuwait(struct rcuwait *w) -{ - rcu_assign_pointer(w->task, NULL); - __set_current_state(TASK_RUNNING); -} +extern void finish_rcuwait(struct rcuwait *w); #define rcuwait_wait_event(w, condition, state) \ ({ \ diff --git a/include/linux/rcuwait_api.h b/include/linux/rcuwait_api.h new file mode 100644 index 000000000000..f962e28544dd --- /dev/null +++ b/include/linux/rcuwait_api.h @@ -0,0 +1 @@ +#include <linux/rcuwait.h> diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h new file mode 100644 index 000000000000..9ca353ab712b --- /dev/null +++ b/include/linux/ref_tracker.h @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#ifndef _LINUX_REF_TRACKER_H +#define _LINUX_REF_TRACKER_H +#include <linux/refcount.h> +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/stackdepot.h> + +struct ref_tracker; + +struct ref_tracker_dir { +#ifdef CONFIG_REF_TRACKER + spinlock_t lock; + unsigned int quarantine_avail; + refcount_t untracked; + refcount_t no_tracker; + bool dead; + struct list_head list; /* List of active trackers */ + struct list_head quarantine; /* List of dead trackers */ +#endif +}; + +#ifdef CONFIG_REF_TRACKER +static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, + unsigned int quarantine_count) +{ + INIT_LIST_HEAD(&dir->list); + INIT_LIST_HEAD(&dir->quarantine); + spin_lock_init(&dir->lock); + dir->quarantine_avail = quarantine_count; + dir->dead = false; + refcount_set(&dir->untracked, 1); + refcount_set(&dir->no_tracker, 1); + stack_depot_init(); +} + +void ref_tracker_dir_exit(struct ref_tracker_dir *dir); + +void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit); + +int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, gfp_t gfp); + +int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp); + +#else /* CONFIG_REF_TRACKER */ + +static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, + unsigned int quarantine_count) +{ +} + +static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir) +{ +} + +static inline void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ +} + +static inline int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, + gfp_t gfp) +{ + return 0; +} + +static inline int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp) +{ + return 0; +} + +#endif + +#endif /* _LINUX_REF_TRACKER_H */ diff --git a/include/linux/refcount_api.h b/include/linux/refcount_api.h new file mode 100644 index 000000000000..5f032589f568 --- /dev/null +++ b/include/linux/refcount_api.h @@ -0,0 +1 @@ +#include <linux/refcount.h> diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e3c9a25a853a..de81a94d7b30 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -237,6 +237,10 @@ typedef void (*regmap_unlock)(void *); * @reg_stride: The register address stride. Valid register addresses are a * multiple of this value. If set to 0, a value of 1 will be * used. + * @reg_downshift: The number of bits to downshift the register before + * performing any operations. + * @reg_base: Value to be added to every register address before performing any + * operation. * @pad_bits: Number of bits of padding between register and value. * @val_bits: Number of bits in a register value, mandatory. * @@ -290,6 +294,11 @@ typedef void (*regmap_unlock)(void *); * read operation on a bus such as SPI, I2C, etc. Most of the * devices do not need this. * @reg_write: Same as above for writing. + * @reg_update_bits: Optional callback that if filled will be used to perform + * all the update_bits(rmw) operation. Should only be provided + * if the function require special handling with lock and reg + * handling and the operation cannot be represented as a simple + * update_bits operation on a bus such as SPI, I2C, etc. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -355,6 +364,8 @@ struct regmap_config { int reg_bits; int reg_stride; + int reg_downshift; + unsigned int reg_base; int pad_bits; int val_bits; @@ -372,6 +383,8 @@ struct regmap_config { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); + int (*reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); bool fast_io; diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 54cf566616ae..0228caaa6741 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -90,22 +90,28 @@ enum regulator_detection_severity { * @set_over_current_protection: Support enabling of and setting limits for over * current situation detection. Detection can be configured for three * levels of severity. - * REGULATOR_SEVERITY_PROT should automatically shut down the regulator(s). - * REGULATOR_SEVERITY_ERR should indicate that over-current situation is - * caused by an unrecoverable error but HW does not perform - * automatic shut down. - * REGULATOR_SEVERITY_WARN should indicate situation where hardware is - * still believed to not be damaged but that a board sepcific - * recovery action is needed. If lim_uA is 0 the limit should not - * be changed but the detection should just be enabled/disabled as - * is requested. + * + * - REGULATOR_SEVERITY_PROT should automatically shut down the regulator(s). + * + * - REGULATOR_SEVERITY_ERR should indicate that over-current situation is + * caused by an unrecoverable error but HW does not perform + * automatic shut down. + * + * - REGULATOR_SEVERITY_WARN should indicate situation where hardware is + * still believed to not be damaged but that a board sepcific + * recovery action is needed. If lim_uA is 0 the limit should not + * be changed but the detection should just be enabled/disabled as + * is requested. + * * @set_over_voltage_protection: Support enabling of and setting limits for over * voltage situation detection. Detection can be configured for same - * severities as over current protection. + * severities as over current protection. Units of uV. * @set_under_voltage_protection: Support enabling of and setting limits for - * under situation detection. + * under voltage situation detection. Detection can be configured for same + * severities as over current protection. Units of uV. * @set_thermal_protection: Support enabling of and setting limits for over - * temperature situation detection. + * temperature situation detection.Detection can be configured for same + * severities as over current protection. Units of degree Kelvin. * * @set_active_discharge: Set active discharge enable/disable of regulators. * @@ -554,7 +560,6 @@ struct regulator_irq_data { */ struct regulator_irq_desc { const char *name; - int irq_flags; int fatal_cnt; int reread_ms; int irq_off_ms; @@ -646,6 +651,40 @@ struct regulator_dev { spinlock_t err_lock; }; +/* + * Convert error flags to corresponding notifications. + * + * Can be used by drivers which use the notification helpers to + * find out correct notification flags based on the error flags. Drivers + * can avoid storing both supported notification and error flags which + * may save few bytes. + */ +static inline int regulator_err2notif(int err) +{ + switch (err) { + case REGULATOR_ERROR_UNDER_VOLTAGE: + return REGULATOR_EVENT_UNDER_VOLTAGE; + case REGULATOR_ERROR_OVER_CURRENT: + return REGULATOR_EVENT_OVER_CURRENT; + case REGULATOR_ERROR_REGULATION_OUT: + return REGULATOR_EVENT_REGULATION_OUT; + case REGULATOR_ERROR_FAIL: + return REGULATOR_EVENT_FAIL; + case REGULATOR_ERROR_OVER_TEMP: + return REGULATOR_EVENT_OVER_TEMP; + case REGULATOR_ERROR_UNDER_VOLTAGE_WARN: + return REGULATOR_EVENT_UNDER_VOLTAGE_WARN; + case REGULATOR_ERROR_OVER_CURRENT_WARN: + return REGULATOR_EVENT_OVER_CURRENT_WARN; + case REGULATOR_ERROR_OVER_VOLTAGE_WARN: + return REGULATOR_EVENT_OVER_VOLTAGE_WARN; + case REGULATOR_ERROR_OVER_TEMP_WARN: + return REGULATOR_EVENT_OVER_TEMP_WARN; + } + return 0; +} + + struct regulator_dev * regulator_register(const struct regulator_desc *regulator_desc, const struct regulator_config *config); @@ -667,6 +706,8 @@ void *regulator_irq_helper(struct device *dev, int irq_flags, int common_errs, int *per_rdev_errs, struct regulator_dev **rdev, int rdev_amount); void regulator_irq_helper_cancel(void **handle); +int regulator_irq_map_event_simple(int irq, struct regulator_irq_data *rid, + unsigned long *dev_mask); void *rdev_get_drvdata(struct regulator_dev *rdev); struct device *rdev_get_dev(struct regulator_dev *rdev); diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index e0600e1e5c17..7c943f0a2fc4 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -523,6 +523,7 @@ struct rproc_dump_segment { * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU * @auto_boot: flag to indicate if remote processor should be auto-started + * @sysfs_read_only: flag to make remoteproc sysfs files read only * @dump_segments: list of segments in the firmware * @nb_vdev: number of vdev currently handled by rproc * @elf_class: firmware ELF class @@ -562,6 +563,7 @@ struct rproc { size_t table_sz; bool has_iommu; bool auto_boot; + bool sysfs_read_only; struct list_head dump_segments; int nb_vdev; u8 elf_class; @@ -669,10 +671,11 @@ rproc_of_resm_mem_entry_init(struct device *dev, u32 of_resm_idx, size_t len, u32 da, const char *name, ...); int rproc_boot(struct rproc *rproc); -void rproc_shutdown(struct rproc *rproc); +int rproc_shutdown(struct rproc *rproc); int rproc_detach(struct rproc *rproc); int rproc_set_firmware(struct rproc *rproc, const char *fw_name); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); +void *rproc_da_to_va(struct rproc *rproc, u64 da, size_t len, bool *is_iomem); void rproc_coredump_using_sections(struct rproc *rproc); int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); int rproc_coredump_add_custom_segment(struct rproc *rproc, diff --git a/include/linux/reset.h b/include/linux/reset.h index db0e6115a2f6..8a21b5756c3e 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -455,6 +455,26 @@ static inline struct reset_control *of_reset_control_get_exclusive( } /** + * of_reset_control_get_optional_exclusive - Lookup and obtain an optional exclusive + * reference to a reset controller. + * @node: device to be reset by the controller + * @id: reset line name + * + * Optional variant of of_reset_control_get_exclusive(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * Returns a struct reset_control or IS_ERR() condition containing errno. + * + * Use of id names is optional. + */ +static inline struct reset_control *of_reset_control_get_optional_exclusive( + struct device_node *node, const char *id) +{ + return __of_reset_control_get(node, id, 0, false, true, true); +} + +/** * of_reset_control_get_shared - Lookup and obtain a shared reference * to a reset controller. * @node: device to be reset by the controller diff --git a/include/linux/resource.h b/include/linux/resource.h index bdf491cbcab7..4fdbc0c3f315 100644 --- a/include/linux/resource.h +++ b/include/linux/resource.h @@ -8,7 +8,5 @@ struct task_struct; void getrusage(struct task_struct *p, int who, struct rusage *ru); -int do_prlimit(struct task_struct *tsk, unsigned int resource, - struct rlimit *new_rlim, struct rlimit *old_rlim); #endif diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h new file mode 100644 index 000000000000..285189454449 --- /dev/null +++ b/include/linux/resume_user_mode.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef LINUX_RESUME_USER_MODE_H +#define LINUX_RESUME_USER_MODE_H + +#include <linux/sched.h> +#include <linux/task_work.h> +#include <linux/memcontrol.h> +#include <linux/blk-cgroup.h> + +/** + * set_notify_resume - cause resume_user_mode_work() to be called + * @task: task that will call resume_user_mode_work() + * + * Calling this arranges that @task will call resume_user_mode_work() + * before returning to user mode. If it's already running in user mode, + * it will enter the kernel and call resume_user_mode_work() soon. + * If it's blocked, it will not be woken. + */ +static inline void set_notify_resume(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) + kick_process(task); +} + + +/** + * resume_user_mode_work - Perform work before returning to user mode + * @regs: user-mode registers of @current task + * + * This is called when %TIF_NOTIFY_RESUME has been set. Now we are + * about to return to user mode, and the user state in @regs can be + * inspected or adjusted. The caller in arch code has cleared + * %TIF_NOTIFY_RESUME before the call. If the flag gets set again + * asynchronously, this will be called again before we return to + * user mode. + * + * Called without locks. + */ +static inline void resume_user_mode_work(struct pt_regs *regs) +{ + clear_thread_flag(TIF_NOTIFY_RESUME); + /* + * This barrier pairs with task_work_add()->set_notify_resume() after + * hlist_add_head(task->task_works); + */ + smp_mb__after_atomic(); + if (unlikely(task_work_pending(current))) + task_work_run(); + +#ifdef CONFIG_KEYS_REQUEST_CACHE + if (unlikely(current->cached_requested_key)) { + key_put(current->cached_requested_key); + current->cached_requested_key = NULL; + } +#endif + + mem_cgroup_handle_over_high(); + blkcg_maybe_throttle_current(); + + rseq_handle_notify_resume(NULL, regs); +} + +#endif /* LINUX_RESUME_USER_MODE_H */ diff --git a/include/linux/rethook.h b/include/linux/rethook.h new file mode 100644 index 000000000000..c8ac1e5afcd1 --- /dev/null +++ b/include/linux/rethook.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Return hooking with list-based shadow stack. + */ +#ifndef _LINUX_RETHOOK_H +#define _LINUX_RETHOOK_H + +#include <linux/compiler.h> +#include <linux/freelist.h> +#include <linux/kallsyms.h> +#include <linux/llist.h> +#include <linux/rcupdate.h> +#include <linux/refcount.h> + +struct rethook_node; + +typedef void (*rethook_handler_t) (struct rethook_node *, void *, struct pt_regs *); + +/** + * struct rethook - The rethook management data structure. + * @data: The user-defined data storage. + * @handler: The user-defined return hook handler. + * @pool: The pool of struct rethook_node. + * @ref: The reference counter. + * @rcu: The rcu_head for deferred freeing. + * + * Don't embed to another data structure, because this is a self-destructive + * data structure when all rethook_node are freed. + */ +struct rethook { + void *data; + rethook_handler_t handler; + struct freelist_head pool; + refcount_t ref; + struct rcu_head rcu; +}; + +/** + * struct rethook_node - The rethook shadow-stack entry node. + * @freelist: The freelist, linked to struct rethook::pool. + * @rcu: The rcu_head for deferred freeing. + * @llist: The llist, linked to a struct task_struct::rethooks. + * @rethook: The pointer to the struct rethook. + * @ret_addr: The storage for the real return address. + * @frame: The storage for the frame pointer. + * + * You can embed this to your extended data structure to store any data + * on each entry of the shadow stack. + */ +struct rethook_node { + union { + struct freelist_node freelist; + struct rcu_head rcu; + }; + struct llist_node llist; + struct rethook *rethook; + unsigned long ret_addr; + unsigned long frame; +}; + +struct rethook *rethook_alloc(void *data, rethook_handler_t handler); +void rethook_free(struct rethook *rh); +void rethook_add_node(struct rethook *rh, struct rethook_node *node); +struct rethook_node *rethook_try_get(struct rethook *rh); +void rethook_recycle(struct rethook_node *node); +void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount); +unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame, + struct llist_node **cur); + +/* Arch dependent code must implement arch_* and trampoline code */ +void arch_rethook_prepare(struct rethook_node *node, struct pt_regs *regs, bool mcount); +void arch_rethook_trampoline(void); + +/** + * is_rethook_trampoline() - Check whether the address is rethook trampoline + * @addr: The address to be checked + * + * Return true if the @addr is the rethook trampoline address. + */ +static inline bool is_rethook_trampoline(unsigned long addr) +{ + return addr == (unsigned long)dereference_symbol_descriptor(arch_rethook_trampoline); +} + +/* If the architecture needs to fixup the return address, implement it. */ +void arch_rethook_fixup_return(struct pt_regs *regs, + unsigned long correct_ret_addr); + +/* Generic trampoline handler, arch code must prepare asm stub */ +unsigned long rethook_trampoline_handler(struct pt_regs *regs, + unsigned long frame); + +#ifdef CONFIG_RETHOOK +void rethook_flush_task(struct task_struct *tk); +#else +#define rethook_flush_task(tsk) do { } while (0) +#endif + +#endif + diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 231e06b74b50..373003ace639 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -230,6 +230,13 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); bool rfkill_blocked(struct rfkill *rfkill); /** + * rfkill_soft_blocked - Query soft rfkill block state + * + * @rfkill: rfkill struct to query + */ +bool rfkill_soft_blocked(struct rfkill *rfkill); + +/** * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * @@ -301,6 +308,11 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) return false; } +static inline bool rfkill_soft_blocked(struct rfkill *rfkill) +{ + return false; +} + static inline enum rfkill_type rfkill_find_type(const char *name) { return RFKILL_TYPE_ALL; diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index 4846f72759b2..c7e2f21dd5c1 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -9,18 +9,6 @@ #ifndef LINUX_RIO_IDS_H #define LINUX_RIO_IDS_H -#define RIO_VID_FREESCALE 0x0002 -#define RIO_DID_MPC8560 0x0003 - -#define RIO_VID_TUNDRA 0x000d -#define RIO_DID_TSI500 0x0500 -#define RIO_DID_TSI568 0x0568 -#define RIO_DID_TSI572 0x0572 -#define RIO_DID_TSI574 0x0574 -#define RIO_DID_TSI576 0x0578 /* Same ID as Tsi578 */ -#define RIO_DID_TSI577 0x0577 -#define RIO_DID_TSI578 0x0578 - #define RIO_VID_IDT 0x0038 #define RIO_DID_IDT70K200 0x0310 #define RIO_DID_IDTCPS8 0x035c @@ -33,7 +21,6 @@ #define RIO_DID_IDTCPS1616 0x0379 #define RIO_DID_IDTVPS1616 0x0377 #define RIO_DID_IDTSPS1616 0x0378 -#define RIO_DID_TSI721 0x80ab #define RIO_DID_IDTRXS1632 0x80e5 #define RIO_DID_IDTRXS2448 0x80e6 diff --git a/include/linux/rmap.h b/include/linux/rmap.h index e704b1a4c06c..17230c458341 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -11,6 +11,7 @@ #include <linux/rwsem.h> #include <linux/memcontrol.h> #include <linux/highmem.h> +#include <linux/pagemap.h> /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -167,18 +168,19 @@ struct anon_vma *page_get_anon_vma(struct page *page); */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); + unsigned long address, bool compound); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, int); + unsigned long address, int flags); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long, bool); -void page_add_file_rmap(struct page *, bool); -void page_remove_rmap(struct page *, bool); - + unsigned long address, bool compound); +void page_add_file_rmap(struct page *, struct vm_area_struct *, + bool compound); +void page_remove_rmap(struct page *, struct vm_area_struct *, + bool compound); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, - unsigned long); + unsigned long address); static inline void page_dup_rmap(struct page *page, bool compound) { @@ -188,11 +190,11 @@ static inline void page_dup_rmap(struct page *page, bool compound) /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked, +int folio_referenced(struct folio *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -void try_to_migrate(struct page *page, enum ttu_flags flags); -void try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_migrate(struct folio *folio, enum ttu_flags flags); +void try_to_unmap(struct folio *, enum ttu_flags flags); int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, @@ -200,11 +202,13 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) -/* Look for migarion entries rather than present PTEs */ +/* Look for migration entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { - struct page *page; + unsigned long pfn; + unsigned long nr_pages; + pgoff_t pgoff; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; @@ -213,10 +217,30 @@ struct page_vma_mapped_walk { unsigned int flags; }; +#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .pfn = page_to_pfn(_page), \ + .nr_pages = compound_nr(page), \ + .pgoff = page_to_pgoff(page), \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + +#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ + struct page_vma_mapped_walk name = { \ + .pfn = folio_pfn(_folio), \ + .nr_pages = folio_nr_pages(_folio), \ + .pgoff = folio_pgoff(_folio), \ + .vma = _vma, \ + .address = _address, \ + .flags = _flags, \ + } + static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ - if (pvmw->pte && !PageHuge(pvmw->page)) + if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); @@ -237,18 +261,12 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int folio_mkclean(struct folio *); -/* - * called in munlock()/munmap() path to check for other vmas holding - * the page mlocked. - */ -void page_mlock(struct page *page); - -void remove_migration_ptes(struct page *old, struct page *new, bool locked); +void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); /* * Called by memory-failure.c to kill processes. */ -struct anon_vma *page_lock_anon_vma_read(struct page *page); +struct anon_vma *folio_lock_anon_vma_read(struct folio *folio); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); @@ -267,15 +285,15 @@ struct rmap_walk_control { * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ - bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, + bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma, unsigned long addr, void *arg); - int (*done)(struct page *page); - struct anon_vma *(*anon_lock)(struct page *page); + int (*done)(struct folio *folio); + struct anon_vma *(*anon_lock)(struct folio *folio); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; -void rmap_walk(struct page *page, struct rmap_walk_control *rwc); -void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); +void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc); +void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ @@ -283,7 +301,7 @@ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -static inline int page_referenced(struct page *page, int is_locked, +static inline int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { @@ -291,7 +309,7 @@ static inline int page_referenced(struct page *page, int is_locked, return 0; } -static inline void try_to_unmap(struct page *page, enum ttu_flags flags) +static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags) { } diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 9deedfeec2b1..7d049883a08a 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -99,13 +99,22 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +extern void _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock); #define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#define rt_mutex_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _rt_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) + #else extern void rt_mutex_lock(struct rt_mutex *lock); #define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#define rt_mutex_lock_nest_lock(lock, nest_lock) rt_mutex_lock(lock) #endif extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); +extern int rt_mutex_lock_killable(struct rt_mutex *lock); extern int rt_mutex_trylock(struct rt_mutex *lock); extern void rt_mutex_unlock(struct rt_mutex *lock); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index bb9cb84114c1..7f970b16da3a 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -134,4 +134,7 @@ extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int (*vlan_fill)(struct sk_buff *skb, struct net_device *dev, u32 filter_mask)); + +extern void rtnl_offload_xstats_notify(struct net_device *dev); + #endif /* __LINUX_RTNETLINK_H */ diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 4ab7bfc675f1..3d780b44e678 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1095,7 +1095,7 @@ struct pcr_ops { unsigned int (*cd_deglitch)(struct rtsx_pcr *pcr); int (*conv_clk_and_div_n)(int clk, int dir); void (*fetch_vendor_settings)(struct rtsx_pcr *pcr); - void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state); + void (*force_power_down)(struct rtsx_pcr *pcr, u8 pm_state, bool runtime); void (*stop_cmd)(struct rtsx_pcr *pcr); void (*set_aspm)(struct rtsx_pcr *pcr, bool enable); @@ -1201,8 +1201,6 @@ struct rtsx_pcr { unsigned int card_exist; struct delayed_work carddet_work; - struct delayed_work idle_work; - struct delayed_work rtd3_work; spinlock_t lock; struct mutex pcr_mutex; @@ -1212,7 +1210,6 @@ struct rtsx_pcr { unsigned int cur_clock; bool remove_pci; bool msi_en; - bool is_runtime_suspended; #define EXTRA_CAPS_SD_SDR50 (1 << 0) #define EXTRA_CAPS_SD_SDR104 (1 << 1) diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 2c0ad417ce3c..8f416c5e929e 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -55,6 +55,12 @@ do { \ #define write_lock(lock) _raw_write_lock(lock) #define read_lock(lock) _raw_read_lock(lock) +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define write_lock_nested(lock, subclass) _raw_write_lock_nested(lock, subclass) +#else +#define write_lock_nested(lock, subclass) _raw_write_lock(lock) +#endif + #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define read_lock_irqsave(lock, flags) \ diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index f1db6f17c4fb..dceb0a59b692 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -17,6 +17,7 @@ void __lockfunc _raw_read_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock(rwlock_t *lock) __acquires(lock); +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) __acquires(lock); void __lockfunc _raw_read_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_read_lock_irq(rwlock_t *lock) __acquires(lock); @@ -209,6 +210,13 @@ static inline void __raw_write_lock(rwlock_t *lock) LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); } +static inline void __raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + preempt_disable(); + rwlock_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); +} + #endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */ static inline void __raw_write_unlock(rwlock_t *lock) diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h index 49c1f3842ed5..8544ff05e594 100644 --- a/include/linux/rwlock_rt.h +++ b/include/linux/rwlock_rt.h @@ -28,6 +28,7 @@ extern void rt_read_lock(rwlock_t *rwlock); extern int rt_read_trylock(rwlock_t *rwlock); extern void rt_read_unlock(rwlock_t *rwlock); extern void rt_write_lock(rwlock_t *rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); extern int rt_write_trylock(rwlock_t *rwlock); extern void rt_write_unlock(rwlock_t *rwlock); @@ -83,6 +84,15 @@ static __always_inline void write_lock(rwlock_t *rwlock) rt_write_lock(rwlock); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static __always_inline void write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rt_write_lock_nested(rwlock, subclass); +} +#else +#define write_lock_nested(lock, subclass) rt_write_lock(((void)(subclass), (lock))) +#endif + static __always_inline void write_lock_bh(rwlock_t *rwlock) { local_bh_disable(); diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index f9348769e558..efa5c324369a 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -230,7 +230,7 @@ extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map * do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ -} while (0); +} while (0) /* * Take/release a lock when not the owner will release it. diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index fc0357a6e19b..dffeb8281c2d 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -28,14 +28,9 @@ struct seq_file; */ struct sbitmap_word { /** - * @depth: Number of bits being used in @word/@cleared - */ - unsigned long depth; - - /** * @word: word holding free bits */ - unsigned long word ____cacheline_aligned_in_smp; + unsigned long word; /** * @cleared: word holding cleared bits @@ -140,7 +135,7 @@ struct sbitmap_queue { /** * @min_shallow_depth: The minimum shallow depth which may be passed to - * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow(). + * sbitmap_queue_get_shallow() */ unsigned int min_shallow_depth; }; @@ -164,6 +159,14 @@ struct sbitmap_queue { int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, gfp_t flags, int node, bool round_robin, bool alloc_hint); +/* sbitmap internal helper */ +static inline unsigned int __map_depth(const struct sbitmap *sb, int index) +{ + if (index == sb->map_nr - 1) + return sb->depth - (index << sb->shift); + return 1U << sb->shift; +} + /** * sbitmap_free() - Free memory used by a &struct sbitmap. * @sb: Bitmap to free. @@ -251,7 +254,7 @@ static inline void __sbitmap_for_each_set(struct sbitmap *sb, while (scanned < sb->depth) { unsigned long word; unsigned int depth = min_t(unsigned int, - sb->map[index].depth - nr, + __map_depth(sb, index) - nr, sb->depth - scanned); scanned += depth; @@ -416,6 +419,17 @@ static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) } /** + * sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch + * @sbq: Bitmap queue to recalculate wake batch. + * @users: Number of shares. + * + * Like sbitmap_queue_update_wake_batch(), this will calculate wake batch + * by depth. This interface is for HCTX shared tags or queue shared tags. + */ +void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, + unsigned int users); + +/** * sbitmap_queue_resize() - Resize a &struct sbitmap_queue. * @sbq: Bitmap queue to resize. * @depth: New number of bits to resize to. @@ -449,7 +463,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, unsigned int *offset); /** - * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct + * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word, with preemption * already disabled. * @sbq: Bitmap queue to allocate from. @@ -461,8 +475,8 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, - unsigned int shallow_depth); +int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, + unsigned int shallow_depth); /** * sbitmap_queue_get() - Try to allocate a free bit from a &struct @@ -485,32 +499,6 @@ static inline int sbitmap_queue_get(struct sbitmap_queue *sbq, } /** - * sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct - * sbitmap_queue, limiting the depth used from each word. - * @sbq: Bitmap queue to allocate from. - * @cpu: Output parameter; will contain the CPU we ran on (e.g., to be passed to - * sbitmap_queue_clear()). - * @shallow_depth: The maximum number of bits to allocate from a single word. - * See sbitmap_get_shallow(). - * - * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after - * initializing @sbq. - * - * Return: Non-negative allocated bit number if successful, -1 otherwise. - */ -static inline int sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, - unsigned int *cpu, - unsigned int shallow_depth) -{ - int nr; - - *cpu = get_cpu(); - nr = __sbitmap_queue_get_shallow(sbq, shallow_depth); - put_cpu(); - return nr; -} - -/** * sbitmap_queue_min_shallow_depth() - Inform a &struct sbitmap_queue of the * minimum shallow depth that will be used. * @sbq: Bitmap queue in question. diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 266754a55327..7ff9d6386c12 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -69,10 +69,27 @@ struct sg_append_table { * a valid sg entry, or whether it points to the start of a new scatterlist. * Those low bits are there for everyone! (thanks mason :-) */ -#define sg_is_chain(sg) ((sg)->page_link & SG_CHAIN) -#define sg_is_last(sg) ((sg)->page_link & SG_END) -#define sg_chain_ptr(sg) \ - ((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END))) +#define SG_PAGE_LINK_MASK (SG_CHAIN | SG_END) + +static inline unsigned int __sg_flags(struct scatterlist *sg) +{ + return sg->page_link & SG_PAGE_LINK_MASK; +} + +static inline struct scatterlist *sg_chain_ptr(struct scatterlist *sg) +{ + return (struct scatterlist *)(sg->page_link & ~SG_PAGE_LINK_MASK); +} + +static inline bool sg_is_chain(struct scatterlist *sg) +{ + return __sg_flags(sg) & SG_CHAIN; +} + +static inline bool sg_is_last(struct scatterlist *sg) +{ + return __sg_flags(sg) & SG_END; +} /** * sg_assign_page - Assign a given page to an SG entry @@ -92,7 +109,7 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) * In order for the low bit stealing approach to work, pages * must be aligned at a 32-bit boundary as a minimum. */ - BUG_ON((unsigned long) page & (SG_CHAIN | SG_END)); + BUG_ON((unsigned long)page & SG_PAGE_LINK_MASK); #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif @@ -126,7 +143,7 @@ static inline struct page *sg_page(struct scatterlist *sg) #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif - return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END)); + return (struct page *)((sg)->page_link & ~SG_PAGE_LINK_MASK); } /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..4a6fdd2a679f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -274,8 +274,13 @@ struct task_group; #define get_current_state() READ_ONCE(current->__state) -/* Task command name length: */ -#define TASK_COMM_LEN 16 +/* + * Define the task command name length as enum, then it can be visible to + * BPF programs. + */ +enum { + TASK_COMM_LEN = 16, +}; extern void scheduler_tick(void); @@ -523,7 +528,11 @@ struct sched_statistics { u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; + +#ifdef CONFIG_SCHED_CORE + u64 core_forceidle_sum; #endif +#endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { @@ -610,10 +619,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * @@ -933,6 +938,9 @@ struct task_struct { /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd_signal:1; #endif +#ifdef CONFIG_IOMMU_SVA + unsigned pasid_activated:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ @@ -987,8 +995,8 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; - /* PF_IO_WORKER */ - void *pf_io_worker; + /* PF_KTHREAD | PF_IO_WORKER */ + void *worker_private; u64 utime; u64 stime; @@ -1082,6 +1090,9 @@ struct task_struct { /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; +#ifdef CONFIG_RT_DELAYED_SIGNALS + struct kernel_siginfo forced_info; +#endif unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; @@ -1339,6 +1350,9 @@ struct task_struct { #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif +#ifdef CONFIG_KCSAN_WEAK_MEMORY + int kcsan_stack_depth; +#endif #endif #if IS_ENABLED(CONFIG_KUNIT) @@ -1473,6 +1487,9 @@ struct task_struct { #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_RETHOOK + struct llist_head rethooks; +#endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* @@ -1612,19 +1629,32 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) -static inline unsigned int task_state_index(struct task_struct *tsk) +static inline unsigned int __task_state_index(unsigned int tsk_state, + unsigned int tsk_exit_state) { - unsigned int tsk_state = READ_ONCE(tsk->__state); - unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT; + unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if (tsk_state == TASK_IDLE) state = TASK_REPORT_IDLE; + /* + * We're lying here, but rather than expose a completely new task state + * to userspace, we can make this appear as if the task has gone through + * a regular rt_mutex_lock() call. + */ + if (tsk_state == TASK_RTLOCK_WAIT) + state = TASK_UNINTERRUPTIBLE; + return fls(state); } +static inline unsigned int task_state_index(struct task_struct *tsk) +{ + return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); +} + static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; @@ -1672,7 +1702,6 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_FROZEN 0x00010000 /* Frozen for system suspend */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ @@ -1682,7 +1711,6 @@ extern struct pid *cad_pid; * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ -#define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */ @@ -2008,7 +2036,7 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); -#ifdef CONFIG_PREEMPT_DYNAMIC +#if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) DECLARE_STATIC_CALL(cond_resched, __cond_resched); @@ -2017,6 +2045,14 @@ static __always_inline int _cond_resched(void) return static_call_mod(cond_resched)(); } +#elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +extern int dynamic_cond_resched(void); + +static __always_inline int _cond_resched(void) +{ + return dynamic_cond_resched(); +} + #else static inline int _cond_resched(void) @@ -2171,6 +2207,15 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #endif #ifdef CONFIG_SMP +static inline bool owner_on_cpu(struct task_struct *owner) +{ + /* + * As lock holder preemption issue, we both skip spinning if + * task is not on cpu or its cpu is preempted + */ + return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); +} + /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu, unsigned long max); #endif /* CONFIG_SMP */ diff --git a/include/linux/sched/affinity.h b/include/linux/sched/affinity.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/affinity.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/cond_resched.h b/include/linux/sched/cond_resched.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/cond_resched.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index 1aff00b65f3c..7c83d4d5a971 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -6,6 +6,8 @@ * NORMAL/BATCH tasks. */ +#include <linux/sched.h> + #define MAX_DL_PRIO 0 static inline int dl_prio(int prio) diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index cc9f393e2a70..8c15abd67aed 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -5,54 +5,55 @@ #include <linux/init.h> #include <linux/tick.h> -enum hk_flags { - HK_FLAG_TIMER = 1, - HK_FLAG_RCU = (1 << 1), - HK_FLAG_MISC = (1 << 2), - HK_FLAG_SCHED = (1 << 3), - HK_FLAG_TICK = (1 << 4), - HK_FLAG_DOMAIN = (1 << 5), - HK_FLAG_WQ = (1 << 6), - HK_FLAG_MANAGED_IRQ = (1 << 7), - HK_FLAG_KTHREAD = (1 << 8), +enum hk_type { + HK_TYPE_TIMER, + HK_TYPE_RCU, + HK_TYPE_MISC, + HK_TYPE_SCHED, + HK_TYPE_TICK, + HK_TYPE_DOMAIN, + HK_TYPE_WQ, + HK_TYPE_MANAGED_IRQ, + HK_TYPE_KTHREAD, + HK_TYPE_MAX }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overridden); -extern int housekeeping_any_cpu(enum hk_flags flags); -extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); -extern bool housekeeping_enabled(enum hk_flags flags); -extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); -extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); +extern int housekeeping_any_cpu(enum hk_type type); +extern const struct cpumask *housekeeping_cpumask(enum hk_type type); +extern bool housekeeping_enabled(enum hk_type type); +extern void housekeeping_affine(struct task_struct *t, enum hk_type type); +extern bool housekeeping_test_cpu(int cpu, enum hk_type type); extern void __init housekeeping_init(void); #else -static inline int housekeeping_any_cpu(enum hk_flags flags) +static inline int housekeeping_any_cpu(enum hk_type type) { return smp_processor_id(); } -static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) +static inline const struct cpumask *housekeeping_cpumask(enum hk_type type) { return cpu_possible_mask; } -static inline bool housekeeping_enabled(enum hk_flags flags) +static inline bool housekeeping_enabled(enum hk_type type) { return false; } static inline void housekeeping_affine(struct task_struct *t, - enum hk_flags flags) { } + enum hk_type type) { } static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ -static inline bool housekeeping_cpu(int cpu, enum hk_flags flags) +static inline bool housekeeping_cpu(int cpu, enum hk_type type) { #ifdef CONFIG_CPU_ISOLATION if (static_branch_unlikely(&housekeeping_overridden)) - return housekeeping_test_cpu(cpu, flags); + return housekeeping_test_cpu(cpu, type); #endif return true; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aca874d33fe6..a80356e9dc69 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> +#include <linux/ioasid.h> /* * Routines for handling mm_structs @@ -214,6 +215,32 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif +/* Any memory-allocation retry loop should use + * memalloc_retry_wait(), and pass the flags for the most + * constrained allocation attempt that might have failed. + * This provides useful documentation of where loops are, + * and a central place to fine tune the waiting as the MM + * implementation changes. + */ +static inline void memalloc_retry_wait(gfp_t gfp_flags) +{ + /* We use io_schedule_timeout because waiting for memory + * typically included waiting for dirty pages to be + * written out, which requires IO. + */ + __set_current_state(TASK_UNINTERRUPTIBLE); + gfp_flags = current_gfp_context(gfp_flags); + if (gfpflags_allow_blocking(gfp_flags) && + !(gfp_flags & __GFP_NORETRY)) + /* Probably waited already, no need for much more */ + io_schedule_timeout(1); + else + /* Probably didn't wait, and has now released a lock, + * so now is a good time to wait + */ + io_schedule_timeout(HZ/50); +} + /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate @@ -407,4 +434,29 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif +#ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = INVALID_IOASID; +} + +/* Associate a PASID with an mm_struct: */ +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) +{ + mm->pasid = pasid; +} + +static inline void mm_pasid_drop(struct mm_struct *mm) +{ + if (pasid_valid(mm->pasid)) { + ioasid_free(mm->pasid); + mm->pasid = INVALID_IOASID; + } +} +#else +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} +static inline void mm_pasid_drop(struct mm_struct *mm) {} +#endif + #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/posix-timers.h b/include/linux/sched/posix-timers.h new file mode 100644 index 000000000000..523a381d6c88 --- /dev/null +++ b/include/linux/sched/posix-timers.h @@ -0,0 +1 @@ +#include <linux/posix-timers.h> diff --git a/include/linux/sched/rseq_api.h b/include/linux/sched/rseq_api.h new file mode 100644 index 000000000000..cf2af72693e1 --- /dev/null +++ b/include/linux/sched/rseq_api.h @@ -0,0 +1 @@ +#include <linux/rseq.h> diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 33a50642cf41..3c8b34876744 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -109,13 +109,9 @@ struct signal_struct { /* thread group exit support */ int group_exit_code; - /* overloaded: - * - notify group_exit_task when ->count is equal to notify_count - * - everyone except group_exit_task is stopped during signal delivery - * of fatal signals, group_exit_task processes the signal. - */ + /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; - struct task_struct *group_exit_task; + struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; @@ -256,7 +252,6 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ -#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ @@ -272,31 +267,25 @@ struct signal_struct { static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { - WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } -/* If true, all threads except ->group_exit_task have pending SIGKILL */ -static inline int signal_group_exit(const struct signal_struct *sig) -{ - return (sig->flags & SIGNAL_GROUP_EXIT) || - (sig->group_exit_task != NULL); -} - extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, - sigset_t *mask, kernel_siginfo_t *info); +extern int dequeue_signal(struct task_struct *task, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; + enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info); + ret = dequeue_signal(task, &task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; @@ -360,6 +349,23 @@ extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); +static inline void clear_notify_signal(void) +{ + clear_thread_flag(TIF_NOTIFY_SIGNAL); + smp_mb__after_atomic(); +} + +/* + * Called to break out of interruptible wait loops, and enter the + * exit_to_user_mode_loop(). + */ +static inline void set_notify_signal(struct task_struct *task) +{ + if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE)) + kick_process(task); +} + static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 304f431178fd..c1076b5e17fb 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -7,20 +7,8 @@ struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK - -#ifdef CONFIG_SMP -extern unsigned int sysctl_hung_task_all_cpu_backtrace; -#else -#define sysctl_hung_task_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - -extern int sysctl_hung_task_check_count; -extern unsigned int sysctl_hung_task_panic; +/* used for hung_task and block/ */ extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_check_interval_secs; -extern int sysctl_hung_task_warnings; -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #else /* Avoid need for ifdefs elsewhere in the code */ enum { sysctl_hung_task_timeout_secs = 0 }; @@ -35,6 +23,16 @@ enum sched_tunable_scaling { SCHED_TUNABLESCALING_END, }; +#define NUMA_BALANCING_DISABLED 0x0 +#define NUMA_BALANCING_NORMAL 0x1 +#define NUMA_BALANCING_MEMORY_TIERING 0x2 + +#ifdef CONFIG_NUMA_BALANCING +extern int sysctl_numa_balancing_mode; +#else +#define sysctl_numa_balancing_mode 0 +#endif + /* * control realtime throttling: * @@ -57,10 +55,6 @@ extern unsigned int sysctl_sched_uclamp_util_min_rt_default; extern unsigned int sysctl_sched_cfs_bandwidth_slice; #endif -#ifdef CONFIG_SCHED_AUTOGROUP -extern unsigned int sysctl_sched_autogroup_enabled; -#endif - extern int sysctl_sched_rr_timeslice; extern int sched_rr_timeslice; diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 058d7f371e25..719c9a6cac8d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -54,11 +54,12 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_post_fork(struct task_struct *p, - struct kernel_clone_args *kargs); +extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); +extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); +void __noreturn make_task_dead(int signr); extern void proc_caches_init(void); @@ -78,7 +79,7 @@ static inline void exit_thread(struct task_struct *tsk) { } #endif -extern void do_group_exit(int); +extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); diff --git a/include/linux/sched/task_flags.h b/include/linux/sched/task_flags.h new file mode 100644 index 000000000000..227f5be81bcd --- /dev/null +++ b/include/linux/sched/task_flags.h @@ -0,0 +1 @@ +#include <linux/sched.h> diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index d10150587d81..892562ebbd3a 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -79,6 +79,8 @@ static inline void *try_get_task_stack(struct task_struct *tsk) static inline void put_task_stack(struct task_struct *tsk) {} #endif +void exit_task_stack_account(struct task_struct *tsk); + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) diff --git a/include/linux/sched/thread_info_api.h b/include/linux/sched/thread_info_api.h new file mode 100644 index 000000000000..2c60fbc16c08 --- /dev/null +++ b/include/linux/sched/thread_info_api.h @@ -0,0 +1 @@ +#include <linux/thread_info.h> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index c07bfa2d80f2..56cffe42abbc 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -93,6 +93,7 @@ struct sched_domain { unsigned int busy_factor; /* less balancing by factor if busy */ unsigned int imbalance_pct; /* No balance until over watermark */ unsigned int cache_nice_tries; /* Leave cache hot tasks for # tries */ + unsigned int imb_numa_nr; /* Nr running tasks that allows a NUMA imbalance */ int nohz_idle; /* NOHZ IDLE status */ int flags; /* See SD_* */ @@ -266,10 +267,10 @@ unsigned long arch_scale_thermal_pressure(int cpu) } #endif -#ifndef arch_set_thermal_pressure +#ifndef arch_update_thermal_pressure static __always_inline -void arch_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure) +void arch_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_frequency) { } #endif diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h index 835ee87ed792..cb41c5edb4d4 100644 --- a/include/linux/sched_clock.h +++ b/include/linux/sched_clock.h @@ -5,6 +5,8 @@ #ifndef LINUX_SCHED_CLOCK #define LINUX_SCHED_CLOCK +#include <linux/types.h> + #ifdef CONFIG_GENERIC_SCHED_CLOCK /** * struct clock_read_data - data required to read from sched_clock() diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index 80e781c51ddc..b87551f41f9f 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -42,6 +42,7 @@ struct scmi_revision_info { struct scmi_clock_info { char name[SCMI_MAX_STR_SIZE]; + unsigned int enable_latency; bool rate_discrete; union { struct { @@ -82,6 +83,9 @@ struct scmi_clk_proto_ops { u64 rate); int (*enable)(const struct scmi_protocol_handle *ph, u32 clk_id); int (*disable)(const struct scmi_protocol_handle *ph, u32 clk_id); + int (*enable_atomic)(const struct scmi_protocol_handle *ph, u32 clk_id); + int (*disable_atomic)(const struct scmi_protocol_handle *ph, + u32 clk_id); }; /** @@ -612,6 +616,15 @@ struct scmi_notify_ops { * @devm_protocol_get: devres managed method to acquire a protocol and get specific * operations and a dedicated protocol handler * @devm_protocol_put: devres managed method to release a protocol + * @is_transport_atomic: method to check if the underlying transport for this + * instance handle is configured to support atomic + * transactions for commands. + * Some users of the SCMI stack in the upper layers could + * be interested to know if they can assume SCMI + * command transactions associated to this handle will + * never sleep and act accordingly. + * An optional atomic threshold value could be returned + * where configured. * @notify_ops: pointer to set of notifications related operations */ struct scmi_handle { @@ -622,6 +635,8 @@ struct scmi_handle { (*devm_protocol_get)(struct scmi_device *sdev, u8 proto, struct scmi_protocol_handle **ph); void (*devm_protocol_put)(struct scmi_device *sdev, u8 proto); + bool (*is_transport_atomic)(const struct scmi_handle *handle, + unsigned int *atomic_threshold); const struct scmi_notify_ops *notify_ops; }; diff --git a/include/linux/security.h b/include/linux/security.h index bbf44a466832..25b3ef71f495 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -313,8 +313,6 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags); -int security_add_mnt_opt(const char *option, const char *val, - int len, void **mnt_opts); int security_move_mount(const struct path *from_path, const struct path *to_path); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, @@ -418,7 +416,7 @@ int security_task_fix_setgid(struct cred *new, const struct cred *old, int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); -void security_task_getsecid_subj(struct task_struct *p, u32 *secid); +void security_current_getsecid_subj(u32 *secid); void security_task_getsecid_obj(struct task_struct *p, u32 *secid); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); @@ -711,12 +709,6 @@ static inline int security_sb_clone_mnt_opts(const struct super_block *oldsb, return 0; } -static inline int security_add_mnt_opt(const char *option, const char *val, - int len, void **mnt_opts) -{ - return 0; -} - static inline int security_move_mount(const struct path *from_path, const struct path *to_path) { @@ -1119,7 +1111,7 @@ static inline int security_task_getsid(struct task_struct *p) return 0; } -static inline void security_task_getsecid_subj(struct task_struct *p, u32 *secid) +static inline void security_current_getsecid_subj(u32 *secid) { *secid = 0; } @@ -1430,6 +1422,8 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); +int security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1649,6 +1643,12 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } + +static inline int security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb) +{ + return 0; +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 72dbb44a4573..88cc16444b43 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -209,7 +209,7 @@ static const struct file_operations __name ## _fops = { \ #define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ - return single_open(file, __name ## _show, PDE_DATA(inode)); \ + return single_open(file, __name ## _show, pde_data(inode)); \ } \ \ static const struct proc_ops __name ## _proc_ops = { \ diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index 0fdbe1ddd8d1..b97912fdbae7 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -9,7 +9,8 @@ extern struct net init_net; struct seq_net_private { #ifdef CONFIG_NET_NS - struct net *net; + struct net *net; + netns_tracker ns_tracker; #endif }; diff --git a/include/linux/seqlock_api.h b/include/linux/seqlock_api.h new file mode 100644 index 000000000000..be91e7d3b826 --- /dev/null +++ b/include/linux/seqlock_api.h @@ -0,0 +1 @@ +#include <linux/seqlock.h> diff --git a/include/linux/serial.h b/include/linux/serial.h index 0916107c77f9..0b8b7d7c8f33 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -12,6 +12,8 @@ #include <asm/page.h> #include <uapi/linux/serial.h> +/* Helper for dealing with UART_LCR_WLEN* defines */ +#define UART_LCR_WLEN(x) ((x) - 5) /* * Counters of the input lines (CTS, DSR, RI, CD) interrupts diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 5db211f43b29..ff84a3ed10ea 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -104,8 +104,6 @@ struct uart_8250_port { unsigned char ier; unsigned char lcr; unsigned char mcr; - unsigned char mcr_mask; /* mask of user bits */ - unsigned char mcr_force; /* mask of forced bits */ unsigned char cur_iotype; /* Running I/O type */ unsigned int rpm_tx_active; unsigned char canary; /* non-zero during system sleep diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index c58cc142d23f..d4828e69087a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -171,7 +171,7 @@ struct uart_port { * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * - * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable + * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ @@ -399,7 +399,7 @@ int uart_set_options(struct uart_port *port, struct console *co, int baud, struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, - void (*putchar)(struct uart_port *, int)); + void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal @@ -458,6 +458,8 @@ extern void uart_handle_cts_change(struct uart_port *uport, extern void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_xchar_out(struct uart_port *uport, int offset); + #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index cf0de4a86640..f6c3323fc4c5 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -27,15 +27,6 @@ #define S3C2410_UERSTAT (0x14) #define S3C2410_UFSTAT (0x18) #define S3C2410_UMSTAT (0x1C) -#define USI_CON (0xC4) -#define USI_OPTION (0xC8) - -#define USI_CON_RESET (1<<0) -#define USI_CON_RESET_MASK (1<<0) - -#define USI_OPTION_HWACG_CLKREQ_ON (1<<1) -#define USI_OPTION_HWACG_CLKSTOP_ON (1<<2) -#define USI_OPTION_HWACG_MASK (3<<1) #define S3C2410_LCON_CFGMASK ((0xF<<3)|(0x3)) diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 166158b6e917..ab51d3cd39bd 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -24,6 +24,7 @@ struct shmem_inode_info { struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ atomic_t stop_eviction; /* hold when working on inode */ + struct timespec64 i_crtime; /* file creation time */ struct inode vfs_inode; }; @@ -83,8 +84,7 @@ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); -extern int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse); +int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, pgoff_t index); diff --git a/include/linux/siphash.h b/include/linux/siphash.h index 0cda61855d90..cce8a9acc76c 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -21,6 +21,8 @@ typedef struct { u64 key[2]; } siphash_key_t; +#define siphash_aligned_key_t siphash_key_t __aligned(16) + static inline bool siphash_key_is_zero(const siphash_key_t *key) { return !(key->key[0] | key->key[1]); diff --git a/include/linux/sizes.h b/include/linux/sizes.h index 1ac79bcee2bb..84aa448d8bb3 100644 --- a/include/linux/sizes.h +++ b/include/linux/sizes.h @@ -47,6 +47,8 @@ #define SZ_8G _AC(0x200000000, ULL) #define SZ_16G _AC(0x400000000, ULL) #define SZ_32G _AC(0x800000000, ULL) + +#define SZ_1T _AC(0x10000000000, ULL) #define SZ_64T _AC(0x400000000000, ULL) #endif /* __LINUX_SIZES_H__ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c8cb7e697d47..3a30cae8b0a5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -36,6 +36,7 @@ #include <linux/splice.h> #include <linux/in6.h> #include <linux/if_packet.h> +#include <linux/llist.h> #include <net/flow.h> #include <net/page_pool.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) @@ -286,14 +287,19 @@ struct nf_bridge_info { struct tc_skb_ext { __u32 chain; __u16 mru; - bool post_ct; + __u16 zone; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; }; #endif struct sk_buff_head { - /* These two members must be first. */ - struct sk_buff *next; - struct sk_buff *prev; + /* These two members must be first to match sk_buff. */ + struct_group_tagged(sk_buff_list, list, + struct sk_buff *next; + struct sk_buff *prev; + ); __u32 qlen; spinlock_t lock; @@ -301,6 +307,146 @@ struct sk_buff_head { struct sk_buff; +/* The reason of skb drop, which is used in kfree_skb_reason(). + * en...maybe they should be splited by group? + * + * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is + * used to translate the reason to string. + */ +enum skb_drop_reason { + SKB_NOT_DROPPED_YET = 0, + SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ + SKB_DROP_REASON_NO_SOCKET, /* socket not found */ + SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ + SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ + SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ + SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ + SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ + SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current + * host (interface is in promisc + * mode) + */ + SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ + SKB_DROP_REASON_IP_INHDR, /* there is something wrong with + * IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. + * see the document for rp_filter + * in ip-sysctl.rst for more + * information + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 + * is multicast, but L3 is + * unicast. + */ + SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ + SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ + SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ + SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as + * udp packet drop out of + * udp_memory_allocated. + */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one + * expected, corresponding + * to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not + * expecting one, corresponding + * to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, + * corresponding to + * LINUX_MIB_TCPMD5FAILURE + */ + SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket + * backlog (see + * LINUX_MIB_TCPBACKLOGDROP) + */ + SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ + SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already + * received before (spurious retrans + * may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, + * the seq of the first byte exceed + * the right edges of receive + * window + */ + SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in + * the ofo queue, corresponding to + * LINUX_MIB_TCPOFOMERGE + */ + SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ + SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by + * BPF_PROG_TYPE_CGROUP_SKB + * eBPF program + */ + SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ + SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh + * entry + */ + SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ + SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh + * entry is full + */ + SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ + SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ + SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet + * outputting (failed to enqueue to + * current qdisc) + */ + SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to + * the per CPU backlog queue. This + * can be caused by backlog queue + * full (see netdev_max_backlog in + * net.rst) or RPS flow limit + */ + SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ + SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ + SKB_DROP_REASON_PTYPE_ABSENT, /* not packet_type found to handle + * the skb. For an etner packet, + * this means that L3 protocol is + * not supported + */ + SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation + * error + */ + SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ + SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from + * user space, e.g., via + * zerocopy_sg_from_iter() + * or skb_orphan_frags_rx() + */ + SKB_DROP_REASON_DEV_HDR, /* device driver specific + * header/metadata is invalid + */ + /* the device is not ready to xmit/recv due to any of its data + * structure that is not up/ready/initialized, e.g., the IFF_UP is + * not set, or driver specific tun->tfiles[txq] is not initialized + */ + SKB_DROP_REASON_DEV_READY, + SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ + SKB_DROP_REASON_NOMEM, /* error due to OOM */ + SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header + * from networking data, e.g., failed + * to pull the protocol header from + * frags via pskb_may_pull() + */ + SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly + * attached to tun/tap, e.g., via + * TUNSETFILTEREBPF + */ + SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented + * at tun/tap, e.g., check_filter() + */ + SKB_DROP_REASON_MAX, +}; + /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. @@ -535,6 +681,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ @@ -626,6 +773,7 @@ typedef unsigned char *sk_buff_data_t; * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head + * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in * fragmentation management @@ -697,6 +845,10 @@ typedef unsigned char *sk_buff_data_t; * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required + * @mono_delivery_time: When set, skb->tstamp has the + * delivery_time in mono clock base (i.e. EDT). Otherwise, the + * skb->tstamp has the (rcv) timestamp at ingress and + * delivery_time at egress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking @@ -728,7 +880,7 @@ typedef unsigned char *sk_buff_data_t; struct sk_buff { union { struct { - /* These two members must be first. */ + /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; @@ -743,6 +895,7 @@ struct sk_buff { }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; + struct llist_node ll_node; }; union { @@ -792,7 +945,7 @@ struct sk_buff { #else #define CLONED_MASK 1 #endif -#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) +#define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; @@ -808,25 +961,15 @@ struct sk_buff { __u8 active_extensions; #endif - /* fields enclosed in headers_start/headers_end are copied + /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ - /* private: */ - __u32 headers_start[0]; - /* public: */ - -/* if you move pkt_type around you also must adapt those constants */ -#ifdef __BIG_ENDIAN_BITFIELD -#define PKT_TYPE_MAX (7 << 5) -#else -#define PKT_TYPE_MAX 7 -#endif -#define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) + struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ - __u8 pkt_type:3; + __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 nf_trace:1; __u8 ip_summed:2; @@ -842,20 +985,18 @@ struct sk_buff { __u8 encap_hdr_csum:1; __u8 csum_valid:1; -#ifdef __BIG_ENDIAN_BITFIELD -#define PKT_VLAN_PRESENT_BIT 7 -#else -#define PKT_VLAN_PRESENT_BIT 0 -#endif -#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) /* private: */ __u8 __pkt_vlan_present_offset[0]; /* public: */ - __u8 vlan_present:1; + __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ __u8 csum_complete_sw:1; __u8 csum_level:2; - __u8 csum_not_inet:1; __u8 dst_pending_confirm:1; + __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ +#ifdef CONFIG_NET_CLS_ACT + __u8 tc_skip_classify:1; + __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ +#endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif @@ -867,10 +1008,6 @@ struct sk_buff { __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif -#ifdef CONFIG_NET_CLS_ACT - __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; -#endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; @@ -882,6 +1019,7 @@ struct sk_buff { __u8 decrypted:1; #endif __u8 slow_gro:1; + __u8 csum_not_inet:1; #ifdef CONFIG_NET_SCHED __u16 tc_index; /* traffic control index */ @@ -932,9 +1070,7 @@ struct sk_buff { u64 kcov_handle; #endif - /* private: */ - __u32 headers_end[0]; - /* public: */ + ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; @@ -950,6 +1086,28 @@ struct sk_buff { #endif }; +/* if you move pkt_type around you also must adapt those constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_TYPE_MAX (7 << 5) +#else +#define PKT_TYPE_MAX 7 +#endif +#define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) + +/* if you move pkt_vlan_present, tc_at_ingress, or mono_delivery_time + * around, you also must adapt these constants. + */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_VLAN_PRESENT_BIT 7 +#define TC_AT_INGRESS_MASK (1 << 0) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) +#else +#define PKT_VLAN_PRESENT_BIT 0 +#define TC_AT_INGRESS_MASK (1 << 7) +#define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) +#endif +#define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) + #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel @@ -1081,12 +1239,28 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } +void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); + +/** + * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason + * @skb: buffer to free + */ +static inline void kfree_skb(struct sk_buff *skb) +{ + kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); +} + void skb_release_head_state(struct sk_buff *skb); -void kfree_skb(struct sk_buff *skb); -void kfree_skb_list(struct sk_buff *segs); +void kfree_skb_list_reason(struct sk_buff *segs, + enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); +static inline void kfree_skb_list(struct sk_buff *segs) +{ + kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); +} + #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else @@ -1380,7 +1554,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, - bool post_ct); + bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, @@ -1443,6 +1617,11 @@ static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } + +static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) +{ + skb->end = offset; +} #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { @@ -1453,6 +1632,11 @@ static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } + +static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) +{ + skb->end = skb->head + offset; +} #endif /* Internal */ @@ -1692,19 +1876,19 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) return 0; } -/* This variant of skb_unclone() makes sure skb->truesize is not changed */ +/* This variant of skb_unclone() makes sure skb->truesize + * and skb_end_offset() are not changed, whenever a new skb->head is needed. + * + * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) + * when various debugging features are in place. + */ +int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); - if (skb_cloned(skb)) { - unsigned int save = skb->truesize; - int res; - - res = pskb_expand_head(skb, 0, 0, pri); - skb->truesize = save; - return res; - } + if (skb_cloned(skb)) + return __skb_unclone_keeptruesize(skb, pri); return 0; } @@ -1975,8 +2159,8 @@ static inline void __skb_insert(struct sk_buff *newsk, */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); - WRITE_ONCE(next->prev, newsk); - WRITE_ONCE(prev->next, newsk); + WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); + WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } @@ -2072,7 +2256,7 @@ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { - __skb_insert(newsk, prev, prev->next, list); + __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, @@ -2082,7 +2266,7 @@ static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { - __skb_insert(newsk, next->prev, next, list); + __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** @@ -2372,6 +2556,8 @@ static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } +void *skb_pull_data(struct sk_buff *skb, size_t len); + void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) @@ -3484,7 +3670,12 @@ __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - __skb_postpull_rcsum(skb, start, len, 0); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = wsum_negate(csum_partial(start, len, + wsum_negate(skb->csum))); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; } static __always_inline void @@ -3852,6 +4043,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); + skb->mono_delivery_time = 0; } static inline ktime_t net_timedelta(ktime_t t) @@ -3859,8 +4051,53 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } -static inline ktime_t net_invalid_timestamp(void) +static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, + bool mono) { + skb->tstamp = kt; + skb->mono_delivery_time = kt && mono; +} + +DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); + +/* It is used in the ingress path to clear the delivery_time. + * If needed, set the skb->tstamp to the (rcv) timestamp. + */ +static inline void skb_clear_delivery_time(struct sk_buff *skb) +{ + if (skb->mono_delivery_time) { + skb->mono_delivery_time = 0; + if (static_branch_unlikely(&netstamp_needed_key)) + skb->tstamp = ktime_get_real(); + else + skb->tstamp = 0; + } +} + +static inline void skb_clear_tstamp(struct sk_buff *skb) +{ + if (skb->mono_delivery_time) + return; + + skb->tstamp = 0; +} + +static inline ktime_t skb_tstamp(const struct sk_buff *skb) +{ + if (skb->mono_delivery_time) + return 0; + + return skb->tstamp; +} + +static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) +{ + if (!skb->mono_delivery_time && skb->tstamp) + return skb->tstamp; + + if (static_branch_unlikely(&netstamp_needed_key) || cond) + return ktime_get_real(); + return 0; } @@ -4720,7 +4957,7 @@ static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) - skb->tstamp = 0; + skb_clear_tstamp(skb); #endif } diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 584d94be9c8b..c5a2d6f50f25 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,7 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - unsigned long copy; + DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the @@ -38,7 +38,6 @@ struct sk_msg_sg { */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -171,11 +170,6 @@ static inline u32 sk_msg_iter_dist(u32 start, u32 end) #define sk_msg_iter_next(msg, which) \ sk_msg_iter_var_next(msg->sg.which) -static inline void sk_msg_clear_meta(struct sk_msg *msg) -{ - memset(&msg->sg, 0, offsetofend(struct sk_msg_sg, copy)); -} - static inline void sk_msg_init(struct sk_msg *msg) { BUILD_BUG_ON(ARRAY_SIZE(msg->sg.data) - 1 != NR_MSG_FRAG_IDS); @@ -234,7 +228,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (test_bit(msg->sg.start, &msg->sg.copy)) { + if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -253,7 +247,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - __set_bit(msg->sg.end, &msg->sg.copy); + __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -262,9 +256,9 @@ static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) - __set_bit(i, &msg->sg.copy); + __set_bit(i, msg->sg.copy); else - __clear_bit(i, &msg->sg.copy); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; @@ -310,21 +304,16 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) -{ - if (msg->skb) - sock_drop(psock->sk, msg->skb); - kfree(msg); -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) list_add_tail(&msg->list, &psock->ingress_msg); - else - drop_sk_msg(psock, msg); + else { + sk_msg_free(psock->sk, msg); + kfree(msg); + } spin_unlock_bh(&psock->ingress_lock); } @@ -507,12 +496,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } -static inline bool sk_is_tcp(const struct sock *sk) -{ - return sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP; -} - static inline bool sk_is_udp(const struct sock *sk) { return sk->sk_type == SOCK_DGRAM && diff --git a/include/linux/slab.h b/include/linux/slab.h index 181045148b06..373b3ef99f4e 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -117,9 +117,6 @@ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ -/* Slab deactivation flag */ -#define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) - /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -135,6 +132,7 @@ #include <linux/kasan.h> +struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes @@ -189,14 +187,6 @@ bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); #endif -#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR -void __check_heap_object(const void *ptr, unsigned long n, struct page *page, - bool to_user); -#else -static inline void __check_heap_object(const void *ptr, unsigned long n, - struct page *page, bool to_user) { } -#endif - /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. @@ -411,8 +401,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; - if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000) - && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); @@ -425,6 +414,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); /* @@ -669,8 +660,7 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) - __alloc_size(1); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 3aa5e1e73ab6..e24c9aff6fed 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -87,11 +87,11 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, +static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab, void *x) { - void *object = x - (x - page->s_mem) % cache->size; - void *last_object = page->s_mem + (cache->num - 1) * cache->size; + void *object = x - (x - slab->s_mem) % cache->size; + void *last_object = slab->s_mem + (cache->num - 1) * cache->size; if (unlikely(object > last_object)) return last_object; @@ -106,16 +106,16 @@ static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, * reciprocal_divide(offset, cache->reciprocal_buffer_size) */ static inline unsigned int obj_to_index(const struct kmem_cache *cache, - const struct page *page, void *obj) + const struct slab *slab, void *obj) { - u32 offset = (obj - page->s_mem); + u32 offset = (obj - slab->s_mem); return reciprocal_divide(offset, cache->reciprocal_buffer_size); } -static inline int objs_per_slab_page(const struct kmem_cache *cache, - const struct page *page) +static inline int objs_per_slab(const struct kmem_cache *cache, + const struct slab *slab) { - if (is_kfence_address(page_address(page))) + if (is_kfence_address(slab_address(slab))) return 1; return cache->num; } diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 0fa751b946fa..33c5c0e3bd8d 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -48,9 +48,9 @@ enum stat_item { struct kmem_cache_cpu { void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ - struct page *page; /* The slab from which we are allocating */ + struct slab *slab; /* The slab from which we are allocating */ #ifdef CONFIG_SLUB_CPU_PARTIAL - struct page *partial; /* Partially allocated frozen slabs */ + struct slab *partial; /* Partially allocated frozen slabs */ #endif local_lock_t lock; /* Protects the fields above */ #ifdef CONFIG_SLUB_STATS @@ -99,8 +99,8 @@ struct kmem_cache { #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; - /* Number of per cpu partial pages to keep around */ - unsigned int cpu_partial_pages; + /* Number of per cpu partial slabs to keep around */ + unsigned int cpu_partial_slabs; #endif struct kmem_cache_order_objects oo; @@ -156,16 +156,13 @@ static inline void sysfs_slab_release(struct kmem_cache *s) } #endif -void object_err(struct kmem_cache *s, struct page *page, - u8 *object, char *reason); - void *fixup_red_left(struct kmem_cache *s, void *p); -static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, +static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab, void *x) { - void *object = x - (x - page_address(page)) % cache->size; - void *last_object = page_address(page) + - (page->objects - 1) * cache->size; + void *object = x - (x - slab_address(slab)) % cache->size; + void *last_object = slab_address(slab) + + (slab->objects - 1) * cache->size; void *result = (unlikely(object > last_object)) ? last_object : object; result = fixup_red_left(cache, result); @@ -181,16 +178,16 @@ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, } static inline unsigned int obj_to_index(const struct kmem_cache *cache, - const struct page *page, void *obj) + const struct slab *slab, void *obj) { if (is_kfence_address(obj)) return 0; - return __obj_to_index(cache, page_address(page), obj); + return __obj_to_index(cache, slab_address(slab), obj); } -static inline int objs_per_slab_page(const struct kmem_cache *cache, - const struct page *page) +static inline int objs_per_slab(const struct kmem_cache *cache, + const struct slab *slab) { - return page->objects; + return slab->objects; } #endif /* _LINUX_SLUB_DEF_H */ diff --git a/include/linux/soc/ixp4xx/cpu.h b/include/linux/soc/ixp4xx/cpu.h index 88bd8de0e803..f526ac33afea 100644 --- a/include/linux/soc/ixp4xx/cpu.h +++ b/include/linux/soc/ixp4xx/cpu.h @@ -9,6 +9,7 @@ #define __SOC_IXP4XX_CPU_H__ #include <linux/io.h> +#include <linux/regmap.h> #ifdef CONFIG_ARM #include <asm/cputype.h> #endif @@ -23,6 +24,9 @@ #define IXP46X_PROCESSOR_ID_VALUE 0x69054200 /* including IXP455 */ #define IXP46X_PROCESSOR_ID_MASK 0xfffffff0 +/* Feature register in the expansion bus controller */ +#define IXP4XX_EXP_CNFG2 0x2c + /* "fuse" bits of IXP_EXP_CFG2 */ /* All IXP4xx CPUs */ #define IXP4XX_FEATURE_RCOMP (1 << 0) @@ -86,21 +90,31 @@ IXP43X_PROCESSOR_ID_VALUE) #define cpu_is_ixp46x() ((read_cpuid_id() & IXP46X_PROCESSOR_ID_MASK) == \ IXP46X_PROCESSOR_ID_VALUE) +static inline u32 cpu_ixp4xx_features(struct regmap *rmap) +{ + u32 val; -u32 ixp4xx_read_feature_bits(void); -void ixp4xx_write_feature_bits(u32 value); + regmap_read(rmap, IXP4XX_EXP_CNFG2, &val); + /* For some reason this register is inverted */ + val = ~val; + if (cpu_is_ixp42x_rev_a0()) + return IXP42X_FEATURE_MASK & ~(IXP4XX_FEATURE_RCOMP | + IXP4XX_FEATURE_AES); + if (cpu_is_ixp42x()) + return val & IXP42X_FEATURE_MASK; + if (cpu_is_ixp43x()) + return val & IXP43X_FEATURE_MASK; + return val & IXP46X_FEATURE_MASK; +} #else #define cpu_is_ixp42x_rev_a0() 0 #define cpu_is_ixp42x() 0 #define cpu_is_ixp43x() 0 #define cpu_is_ixp46x() 0 -static inline u32 ixp4xx_read_feature_bits(void) +static inline u32 cpu_ixp4xx_features(struct regmap *rmap) { return 0; } -static inline void ixp4xx_write_feature_bits(u32 value) -{ -} #endif #endif /* _ASM_ARCH_CPU_H */ diff --git a/include/linux/soc/ixp4xx/npe.h b/include/linux/soc/ixp4xx/npe.h index 2a91f465d456..9efeac777da1 100644 --- a/include/linux/soc/ixp4xx/npe.h +++ b/include/linux/soc/ixp4xx/npe.h @@ -3,6 +3,7 @@ #define __IXP4XX_NPE_H #include <linux/kernel.h> +#include <linux/regmap.h> extern const char *npe_names[]; @@ -17,6 +18,7 @@ struct npe_regs { struct npe { struct npe_regs __iomem *regs; + struct regmap *rmap; int id; int valid; }; diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index 4615a228da51..50804ac748bd 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -2,6 +2,88 @@ #ifndef __SOC_MEDIATEK_INFRACFG_H #define __SOC_MEDIATEK_INFRACFG_H +#define MT8195_TOP_AXI_PROT_EN_STA1 0x228 +#define MT8195_TOP_AXI_PROT_EN_1_STA1 0x258 +#define MT8195_TOP_AXI_PROT_EN_SET 0x2a0 +#define MT8195_TOP_AXI_PROT_EN_CLR 0x2a4 +#define MT8195_TOP_AXI_PROT_EN_1_SET 0x2a8 +#define MT8195_TOP_AXI_PROT_EN_1_CLR 0x2ac +#define MT8195_TOP_AXI_PROT_EN_MM_SET 0x2d4 +#define MT8195_TOP_AXI_PROT_EN_MM_CLR 0x2d8 +#define MT8195_TOP_AXI_PROT_EN_MM_STA1 0x2ec +#define MT8195_TOP_AXI_PROT_EN_2_SET 0x714 +#define MT8195_TOP_AXI_PROT_EN_2_CLR 0x718 +#define MT8195_TOP_AXI_PROT_EN_2_STA1 0x724 +#define MT8195_TOP_AXI_PROT_EN_VDNR_SET 0xb84 +#define MT8195_TOP_AXI_PROT_EN_VDNR_CLR 0xb88 +#define MT8195_TOP_AXI_PROT_EN_VDNR_STA1 0xb90 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_SET 0xba4 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_CLR 0xba8 +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_STA1 0xbb0 +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_SET 0xbb8 +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_CLR 0xbbc +#define MT8195_TOP_AXI_PROT_EN_VDNR_2_STA1 0xbc4 +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_SET 0xbcc +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_CLR 0xbd0 +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_STA1 0xbd8 +#define MT8195_TOP_AXI_PROT_EN_MM_2_SET 0xdcc +#define MT8195_TOP_AXI_PROT_EN_MM_2_CLR 0xdd0 +#define MT8195_TOP_AXI_PROT_EN_MM_2_STA1 0xdd8 + +#define MT8195_TOP_AXI_PROT_EN_VDOSYS0 BIT(6) +#define MT8195_TOP_AXI_PROT_EN_VPPSYS0 BIT(10) +#define MT8195_TOP_AXI_PROT_EN_MFG1 BIT(11) +#define MT8195_TOP_AXI_PROT_EN_MFG1_2ND GENMASK(22, 21) +#define MT8195_TOP_AXI_PROT_EN_VPPSYS0_2ND BIT(23) +#define MT8195_TOP_AXI_PROT_EN_1_MFG1 GENMASK(20, 19) +#define MT8195_TOP_AXI_PROT_EN_1_CAM BIT(22) +#define MT8195_TOP_AXI_PROT_EN_2_CAM BIT(0) +#define MT8195_TOP_AXI_PROT_EN_2_MFG1_2ND GENMASK(6, 5) +#define MT8195_TOP_AXI_PROT_EN_2_MFG1 BIT(7) +#define MT8195_TOP_AXI_PROT_EN_2_AUDIO (BIT(9) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_2_ADSP (BIT(12) | GENMASK(16, 14)) +#define MT8195_TOP_AXI_PROT_EN_MM_CAM (BIT(0) | BIT(2) | BIT(4)) +#define MT8195_TOP_AXI_PROT_EN_MM_IPE BIT(1) +#define MT8195_TOP_AXI_PROT_EN_MM_IMG BIT(3) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS0 GENMASK(21, 17) +#define MT8195_TOP_AXI_PROT_EN_MM_VPPSYS1 GENMASK(8, 5) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC (BIT(9) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC_CORE1 (BIT(10) | BIT(12)) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC0 BIT(13) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC1 BIT(14) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS1_2ND BIT(22) +#define MT8195_TOP_AXI_PROT_EN_MM_VPPSYS1_2ND BIT(23) +#define MT8195_TOP_AXI_PROT_EN_MM_CAM_2ND BIT(24) +#define MT8195_TOP_AXI_PROT_EN_MM_IMG_2ND BIT(25) +#define MT8195_TOP_AXI_PROT_EN_MM_VENC_2ND BIT(26) +#define MT8195_TOP_AXI_PROT_EN_MM_WPESYS BIT(27) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC0_2ND BIT(28) +#define MT8195_TOP_AXI_PROT_EN_MM_VDEC1_2ND BIT(29) +#define MT8195_TOP_AXI_PROT_EN_MM_VDOSYS1 GENMASK(31, 30) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS0_2ND (GENMASK(1, 0) | BIT(4) | BIT(11)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VENC BIT(2) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VENC_CORE1 (BIT(3) | BIT(15)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_CAM (BIT(5) | BIT(17)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS1 (GENMASK(7, 6) | BIT(18)) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VPPSYS0 GENMASK(9, 8) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDOSYS1 BIT(10) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC2_2ND BIT(12) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC0_2ND BIT(13) +#define MT8195_TOP_AXI_PROT_EN_MM_2_WPESYS_2ND BIT(14) +#define MT8195_TOP_AXI_PROT_EN_MM_2_IPE BIT(16) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC2 BIT(21) +#define MT8195_TOP_AXI_PROT_EN_MM_2_VDEC0 BIT(22) +#define MT8195_TOP_AXI_PROT_EN_MM_2_WPESYS GENMASK(24, 23) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_EPD_TX BIT(1) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_DP_TX BIT(2) +#define MT8195_TOP_AXI_PROT_EN_VDNR_PCIE_MAC_P0 (BIT(11) | BIT(28)) +#define MT8195_TOP_AXI_PROT_EN_VDNR_PCIE_MAC_P1 (BIT(12) | BIT(29)) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_PCIE_MAC_P0 BIT(13) +#define MT8195_TOP_AXI_PROT_EN_VDNR_1_PCIE_MAC_P1 BIT(14) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_MFG1 (BIT(17) | BIT(19)) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VPPSYS0 BIT(20) +#define MT8195_TOP_AXI_PROT_EN_SUB_INFRA_VDNR_VDOSYS0 BIT(21) + #define MT8192_TOP_AXI_PROT_EN_STA1 0x228 #define MT8192_TOP_AXI_PROT_EN_1_STA1 0x258 #define MT8192_TOP_AXI_PROT_EN_SET 0x2a0 @@ -58,6 +140,54 @@ #define MT8192_TOP_AXI_PROT_EN_MM_2_MDP_2ND BIT(13) #define MT8192_TOP_AXI_PROT_EN_VDNR_CAM BIT(21) +#define MT8186_TOP_AXI_PROT_EN_SET (0x2A0) +#define MT8186_TOP_AXI_PROT_EN_CLR (0x2A4) +#define MT8186_TOP_AXI_PROT_EN_STA (0x228) +#define MT8186_TOP_AXI_PROT_EN_1_SET (0x2A8) +#define MT8186_TOP_AXI_PROT_EN_1_CLR (0x2AC) +#define MT8186_TOP_AXI_PROT_EN_1_STA (0x258) +#define MT8186_TOP_AXI_PROT_EN_2_SET (0x2B0) +#define MT8186_TOP_AXI_PROT_EN_2_CLR (0x2B4) +#define MT8186_TOP_AXI_PROT_EN_2_STA (0x26C) +#define MT8186_TOP_AXI_PROT_EN_3_SET (0x2B8) +#define MT8186_TOP_AXI_PROT_EN_3_CLR (0x2BC) +#define MT8186_TOP_AXI_PROT_EN_3_STA (0x2C8) + +/* MFG1 */ +#define MT8186_TOP_AXI_PROT_EN_1_MFG1_STEP1 (GENMASK(28, 27)) +#define MT8186_TOP_AXI_PROT_EN_MFG1_STEP2 (GENMASK(22, 21)) +#define MT8186_TOP_AXI_PROT_EN_MFG1_STEP3 (BIT(25)) +#define MT8186_TOP_AXI_PROT_EN_1_MFG1_STEP4 (BIT(29)) +/* DIS */ +#define MT8186_TOP_AXI_PROT_EN_1_DIS_STEP1 (GENMASK(12, 11)) +#define MT8186_TOP_AXI_PROT_EN_DIS_STEP2 (GENMASK(2, 1) | GENMASK(11, 10)) +/* IMG */ +#define MT8186_TOP_AXI_PROT_EN_1_IMG_STEP1 (BIT(23)) +#define MT8186_TOP_AXI_PROT_EN_1_IMG_STEP2 (BIT(15)) +/* IPE */ +#define MT8186_TOP_AXI_PROT_EN_1_IPE_STEP1 (BIT(24)) +#define MT8186_TOP_AXI_PROT_EN_1_IPE_STEP2 (BIT(16)) +/* CAM */ +#define MT8186_TOP_AXI_PROT_EN_1_CAM_STEP1 (GENMASK(22, 21)) +#define MT8186_TOP_AXI_PROT_EN_1_CAM_STEP2 (GENMASK(14, 13)) +/* VENC */ +#define MT8186_TOP_AXI_PROT_EN_1_VENC_STEP1 (BIT(31)) +#define MT8186_TOP_AXI_PROT_EN_1_VENC_STEP2 (BIT(19)) +/* VDEC */ +#define MT8186_TOP_AXI_PROT_EN_1_VDEC_STEP1 (BIT(30)) +#define MT8186_TOP_AXI_PROT_EN_1_VDEC_STEP2 (BIT(17)) +/* WPE */ +#define MT8186_TOP_AXI_PROT_EN_2_WPE_STEP1 (BIT(17)) +#define MT8186_TOP_AXI_PROT_EN_2_WPE_STEP2 (BIT(16)) +/* CONN_ON */ +#define MT8186_TOP_AXI_PROT_EN_1_CONN_ON_STEP1 (BIT(18)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP2 (BIT(14)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP3 (BIT(13)) +#define MT8186_TOP_AXI_PROT_EN_CONN_ON_STEP4 (BIT(16)) +/* ADSP_TOP */ +#define MT8186_TOP_AXI_PROT_EN_3_ADSP_TOP_STEP1 (GENMASK(12, 11)) +#define MT8186_TOP_AXI_PROT_EN_3_ADSP_TOP_STEP2 (GENMASK(1, 0)) + #define MT8183_TOP_AXI_PROT_EN_STA1 0x228 #define MT8183_TOP_AXI_PROT_EN_STA1_1 0x258 #define MT8183_TOP_AXI_PROT_EN_SET 0x2a0 @@ -147,6 +277,9 @@ #define INFRA_TOPAXI_PROTECTEN_SET 0x0260 #define INFRA_TOPAXI_PROTECTEN_CLR 0x0264 +#define MT8192_INFRA_CTRL 0x290 +#define MT8192_INFRA_CTRL_DISABLE_MFG2ACP BIT(9) + #define REG_INFRA_MISC 0xf00 #define F_DDR_4GB_SUPPORT_EN BIT(13) diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 437c9df13229..0bc21ee58fac 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -33,6 +33,14 @@ #define LLCC_MODPE 29 #define LLCC_APTCM 30 #define LLCC_WRCACHE 31 +#define LLCC_CVPFW 32 +#define LLCC_CPUSS1 33 +#define LLCC_CAMEXP0 34 +#define LLCC_CPUMTE 35 +#define LLCC_CPUHWT 36 +#define LLCC_MDMCLAD2 37 +#define LLCC_CAMEXP1 38 +#define LLCC_AENPU 45 /** * struct llcc_slice_desc - Cache slice descriptor @@ -80,7 +88,7 @@ struct llcc_edac_reg_data { * @bitmap: Bit map to track the active slice ids * @offsets: Pointer to the bank offsets array * @ecc_irq: interrupt for llcc cache error detection and reporting - * @major_version: Indicates the LLCC major version + * @version: Indicates the LLCC version */ struct llcc_drv_data { struct regmap *regmap; @@ -93,7 +101,7 @@ struct llcc_drv_data { unsigned long *bitmap; u32 *offsets; int ecc_irq; - u32 major_version; + u32 version; }; #if IS_ENABLED(CONFIG_QCOM_LLCC) diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index afd47217996b..9e8e60421192 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -10,10 +10,14 @@ struct device; struct firmware; +struct qcom_scm_pas_metadata; #if IS_ENABLED(CONFIG_QCOM_MDT_LOADER) ssize_t qcom_mdt_get_size(const struct firmware *fw); +int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, phys_addr_t mem_phys, + struct qcom_scm_pas_metadata *pas_metadata_ctx); int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, @@ -23,7 +27,8 @@ int qcom_mdt_load_no_init(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, size_t mem_size, phys_addr_t *reloc_base); -void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len); +void *qcom_mdt_read_metadata(const struct firmware *fw, size_t *data_len, + const char *fw_name, struct device *dev); #else /* !IS_ENABLED(CONFIG_QCOM_MDT_LOADER) */ @@ -32,6 +37,13 @@ static inline ssize_t qcom_mdt_get_size(const struct firmware *fw) return -ENODEV; } +static inline int qcom_mdt_pas_init(struct device *dev, const struct firmware *fw, + const char *fw_name, int pas_id, phys_addr_t mem_phys, + struct qcom_scm_pas_metadata *pas_metadata_ctx) +{ + return -ENODEV; +} + static inline int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, phys_addr_t mem_phys, @@ -51,7 +63,8 @@ static inline int qcom_mdt_load_no_init(struct device *dev, } static inline void *qcom_mdt_read_metadata(const struct firmware *fw, - size_t *data_len) + size_t *data_len, const char *fw_name, + struct device *dev) { return ERR_PTR(-ENODEV); } diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index 860dd8cdf9f3..82c9d489833a 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -40,6 +40,7 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_AGGR_CLK 0x72676761 #define QCOM_SMD_RPM_HWKM_CLK 0x6d6b7768 #define QCOM_SMD_RPM_PKA_CLK 0x616b70 +#define QCOM_SMD_RPM_MCFG_CLK 0x6766636d int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm, int state, diff --git a/include/linux/soc/renesas/rcar-rst.h b/include/linux/soc/renesas/rcar-rst.h index 7899a5b8c247..1f1fe8bfaa76 100644 --- a/include/linux/soc/renesas/rcar-rst.h +++ b/include/linux/soc/renesas/rcar-rst.h @@ -4,8 +4,10 @@ #ifdef CONFIG_RST_RCAR int rcar_rst_read_mode_pins(u32 *mode); +int rcar_rst_set_rproc_boot_addr(u64 boot_addr); #else static inline int rcar_rst_read_mode_pins(u32 *mode) { return -ENODEV; } +static inline int rcar_rst_set_rproc_boot_addr(u64 boot_addr) { return -ENODEV; } #endif #endif /* __LINUX_SOC_RENESAS_RCAR_RST_H__ */ diff --git a/include/linux/soc/ti/ti-msgmgr.h b/include/linux/soc/ti/ti-msgmgr.h index 1f6e76d423cf..69a8d7682c4b 100644 --- a/include/linux/soc/ti/ti-msgmgr.h +++ b/include/linux/soc/ti/ti-msgmgr.h @@ -1,7 +1,7 @@ /* * Texas Instruments' Message Manager * - * Copyright (C) 2015-2016 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (C) 2015-2022 Texas Instruments Incorporated - https://www.ti.com/ * Nishanth Menon * * This program is free software; you can redistribute it and/or modify @@ -17,10 +17,14 @@ #ifndef TI_MSGMGR_H #define TI_MSGMGR_H +struct mbox_chan; + /** * struct ti_msgmgr_message - Message Manager structure * @len: Length of data in the Buffer * @buf: Buffer pointer + * @chan_rx: Expected channel for response, must be provided to use polled rx + * @timeout_rx_ms: Timeout value to use if polling for response * * This is the structure for data used in mbox_send_message * the length of data buffer used depends on the SoC integration @@ -30,6 +34,8 @@ struct ti_msgmgr_message { size_t len; u8 *buf; + struct mbox_chan *chan_rx; + int timeout_rx_ms; }; #endif /* TI_MSGMGR_H */ diff --git a/include/linux/soc/ti/ti_sci_inta_msi.h b/include/linux/soc/ti/ti_sci_inta_msi.h index e3aa8b14612e..4dba2f2aff6f 100644 --- a/include/linux/soc/ti/ti_sci_inta_msi.h +++ b/include/linux/soc/ti/ti_sci_inta_msi.h @@ -18,6 +18,4 @@ struct irq_domain struct irq_domain *parent); int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev, struct ti_sci_resource *res); -unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 index); -void ti_sci_inta_msi_domain_free_irqs(struct device *dev); #endif /* __INCLUDE_LINUX_IRQCHIP_TI_SCI_INTA_H */ diff --git a/include/linux/soc/ti/ti_sci_protocol.h b/include/linux/soc/ti/ti_sci_protocol.h index 0aad7009b50e..bd0d11af76c5 100644 --- a/include/linux/soc/ti/ti_sci_protocol.h +++ b/include/linux/soc/ti/ti_sci_protocol.h @@ -645,7 +645,7 @@ devm_ti_sci_get_of_resource(const struct ti_sci_handle *handle, static inline struct ti_sci_resource * devm_ti_sci_get_resource(const struct ti_sci_handle *handle, struct device *dev, - u32 dev_id, u32 sub_type); + u32 dev_id, u32 sub_type) { return ERR_PTR(-EINVAL); } diff --git a/include/linux/socket.h b/include/linux/socket.h index 8ef26d89ef49..6f85f5d957ef 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -366,6 +366,7 @@ struct ucred { #define SOL_XDP 283 #define SOL_MPTCP 284 #define SOL_MCTP 285 +#define SOL_SMC 286 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/softirq.h b/include/linux/softirq.h new file mode 100644 index 000000000000..c73d7dcb4cb5 --- /dev/null +++ b/include/linux/softirq.h @@ -0,0 +1 @@ +#include <linux/interrupt.h> diff --git a/include/linux/sort.h b/include/linux/sort.h index b5898725fe9d..e163287ac6c1 100644 --- a/include/linux/sort.h +++ b/include/linux/sort.h @@ -6,7 +6,7 @@ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, - swap_func_t swap_func, + swap_r_func_t swap_func, const void *priv); void sort(void *base, size_t num, size_t size, diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 8a463b8fc12a..67e0d3e750b5 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -92,7 +92,7 @@ * firmware. */ struct sdw_intel_stream_params_data { - struct snd_pcm_substream *substream; + int stream; struct snd_soc_dai *dai; struct snd_pcm_hw_params *hw_params; int link_id; @@ -105,7 +105,7 @@ struct sdw_intel_stream_params_data { * firmware. */ struct sdw_intel_stream_free_data { - struct snd_pcm_substream *substream; + int stream; struct snd_soc_dai *dai; int link_id; }; diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index eaab121ee575..4658e7801b42 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -9,9 +9,6 @@ #include <linux/pxa2xx_ssp.h> -#define PXA2XX_CS_ASSERT (0x01) -#define PXA2XX_CS_DEASSERT (0x02) - struct dma_chan; /* @@ -45,9 +42,6 @@ struct pxa2xx_spi_chip { u8 rx_threshold; u8 dma_burst_size; u32 timeout; - u8 enable_loopback; - int gpio_cs; - void (*cs_control)(u32 command); }; #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) diff --git a/include/linux/spi/s3c24xx.h b/include/linux/spi/s3c24xx.h index 440a71593162..9b8bb22d5b0c 100644 --- a/include/linux/spi/s3c24xx.h +++ b/include/linux/spi/s3c24xx.h @@ -10,14 +10,9 @@ #define __LINUX_SPI_S3C24XX_H __FILE__ struct s3c2410_spi_info { - int pin_cs; /* simple gpio cs */ unsigned int num_cs; /* total chipselects */ int bus_num; /* bus number to use. */ - unsigned int use_fiq:1; /* use fiq */ - - void (*gpio_setup)(struct s3c2410_spi_info *spi, int enable); - void (*set_cs)(struct s3c2410_spi_info *spi, int cs, int pol); }; extern int s3c24xx_set_fiq(unsigned int irq, u32 *ack_ptr, bool on); diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h index 85e2ff7b840d..2ba044d0d5e5 100644 --- a/include/linux/spi/spi-mem.h +++ b/include/linux/spi/spi-mem.h @@ -89,6 +89,7 @@ enum spi_mem_data_dir { * @dummy.dtr: whether the dummy bytes should be sent in DTR mode or not * @data.buswidth: number of IO lanes used to send/receive the data * @data.dtr: whether the data should be sent in DTR mode or not + * @data.ecc: whether error correction is required or not * @data.dir: direction of the transfer * @data.nbytes: number of data bytes to send/receive. Can be zero if the * operation does not involve transferring data @@ -119,6 +120,7 @@ struct spi_mem_op { struct { u8 buswidth; u8 dtr : 1; + u8 ecc : 1; enum spi_mem_data_dir dir; unsigned int nbytes; union { @@ -286,6 +288,19 @@ struct spi_controller_mem_ops { }; /** + * struct spi_controller_mem_caps - SPI memory controller capabilities + * @dtr: Supports DTR operations + * @ecc: Supports operations with error correction + */ +struct spi_controller_mem_caps { + bool dtr; + bool ecc; +}; + +#define spi_mem_controller_is_capable(ctlr, cap) \ + ((ctlr)->mem_caps && (ctlr)->mem_caps->cap) + +/** * struct spi_mem_driver - SPI memory driver * @spidrv: inherit from a SPI driver * @probe: probe a SPI memory. Usually where detection/initialization takes @@ -319,10 +334,6 @@ void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr, bool spi_mem_default_supports_op(struct spi_mem *mem, const struct spi_mem_op *op); - -bool spi_mem_dtr_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op); - #else static inline int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr, @@ -345,13 +356,6 @@ bool spi_mem_default_supports_op(struct spi_mem *mem, { return false; } - -static inline -bool spi_mem_dtr_supports_op(struct spi_mem *mem, - const struct spi_mem_op *op) -{ - return false; -} #endif /* CONFIG_SPI_MEM */ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index eb7ac8a1e03c..5f8c063ddff4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -14,15 +14,17 @@ #include <linux/completion.h> #include <linux/scatterlist.h> #include <linux/gpio/consumer.h> -#include <linux/ptp_clock_kernel.h> #include <uapi/linux/spi/spi.h> +#include <linux/acpi.h> struct dma_chan; struct software_node; +struct ptp_system_timestamp; struct spi_controller; struct spi_transfer; struct spi_controller_mem_ops; +struct spi_controller_mem_caps; /* * INTERFACES between SPI master-side drivers and SPI slave protocol handlers, @@ -136,9 +138,6 @@ extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); * for driver coldplugging, and in uevents used for hotplugging * @driver_override: If the name of a driver is written to this attribute, then * the device will bind to the named driver and only the named driver. - * @cs_gpio: LEGACY: gpio number of the chipselect line (optional, -ENOENT when - * not using a GPIO line) use cs_gpiod in new drivers by opting in on - * the spi_master. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) * @word_delay: delay to be inserted between consecutive @@ -185,7 +184,6 @@ struct spi_device { void *controller_data; char modalias[SPI_NAME_SIZE]; const char *driver_override; - int cs_gpio; /* LEGACY: chip select gpio */ struct gpio_desc *cs_gpiod; /* chip select gpio desc */ struct spi_delay word_delay; /* inter-word delay */ /* CS delays */ @@ -280,7 +278,7 @@ struct spi_message; struct spi_driver { const struct spi_device_id *id_table; int (*probe)(struct spi_device *spi); - int (*remove)(struct spi_device *spi); + void (*remove)(struct spi_device *spi); void (*shutdown)(struct spi_device *spi); struct device_driver driver; }; @@ -373,7 +371,8 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @cur_msg_prepared: spi_prepare_message was called for the currently * in-flight message * @cur_msg_mapped: message has been mapped for DMA - * @last_cs_enable: was enable true on the last call to set_cs. + * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip + * selected * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy @@ -415,19 +414,15 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @mem_ops: optimized/dedicated operations for interactions with SPI memory. * This field is optional and should only be implemented if the * controller has native support for memory like operations. + * @mem_caps: controller capabilities for the handling of memory operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller - * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per - * CS number. Any individual value may be -ENOENT for CS lines that - * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods - * in new drivers. * @cs_gpiods: Array of GPIO descs to use as chip select lines; one per CS * number. Any individual value may be NULL for CS lines that * are not GPIOs (driven by the SPI controller itself). * @use_gpio_descriptors: Turns on the code in the SPI core to parse and grab - * GPIO descriptors rather than using global GPIO numbers grabbed by the - * driver. This will fill in @cs_gpiods and @cs_gpios should not be used, - * and SPI devices will have the cs_gpiod assigned rather than cs_gpio. + * GPIO descriptors. This will fill in @cs_gpiods and SPI devices will have + * the cs_gpiod assigned if a GPIO line is found for the chipselect. * @unused_native_cs: When cs_gpiods is used, spi_register_controller() will * fill in this field with the first unused native CS, to be used by SPI * controller drivers that need to drive a native CS when using GPIO CS. @@ -611,7 +606,7 @@ struct spi_controller { bool auto_runtime_pm; bool cur_msg_prepared; bool cur_msg_mapped; - bool last_cs_enable; + char last_cs; bool last_cs_mode_high; bool fallback; struct completion xfer_completion; @@ -639,9 +634,9 @@ struct spi_controller { /* Optimized handlers for SPI memory-like operations. */ const struct spi_controller_mem_ops *mem_ops; + const struct spi_controller_mem_caps *mem_caps; /* gpio chip select */ - int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; s8 unused_native_cs; @@ -759,6 +754,13 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); +#if IS_ENABLED(CONFIG_ACPI) +extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index); +int acpi_spi_count_resources(struct acpi_device *adev); +#endif + /* * SPI resource management while processing a SPI message */ @@ -1452,8 +1454,20 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but * normally that would be handled by spi_unregister_controller(). + * + * You can also use spi_alloc_device() and spi_add_device() to use a two + * stage registration sequence for each spi_device. This gives the caller + * some more control over the spi_device structure before it is registered, + * but requires that caller to initialize fields that would otherwise + * be defined using the board info. */ extern struct spi_device * +spi_alloc_device(struct spi_controller *ctlr); + +extern int +spi_add_device(struct spi_device *spi); + +extern struct spi_device * spi_new_device(struct spi_controller *, struct spi_board_info *); extern void spi_unregister_device(struct spi_device *spi); diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index b4e5ca23f840..5c0c5174155d 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -171,7 +171,7 @@ do { \ * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock -#define smp_mb__after_spinlock() do { } while (0) +#define smp_mb__after_spinlock() kcsan_mb() #endif #ifdef CONFIG_DEBUG_SPINLOCK diff --git a/include/linux/spinlock_api.h b/include/linux/spinlock_api.h new file mode 100644 index 000000000000..6338b27f98df --- /dev/null +++ b/include/linux/spinlock_api.h @@ -0,0 +1 @@ +#include <linux/spinlock.h> diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d0d188861ad6..b8ba00ccccde 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -59,6 +59,7 @@ #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) +#define _raw_write_lock_nested(lock, subclass) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) #define _raw_read_lock_bh(lock) __LOCK_BH(lock) #define _raw_write_lock_bh(lock) __LOCK_BH(lock) diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index c09b6407ae1b..7f86a2016ac5 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_TYPES_UP_H #define __LINUX_SPINLOCK_TYPES_UP_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/include/linux/srcu.h b/include/linux/srcu.h index e6011a9975af..01226e4d960a 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -117,7 +117,8 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ - __rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h index 15ba0df1ee0d..28c145a51e57 100644 --- a/include/linux/ssb/ssb_driver_gige.h +++ b/include/linux/ssb/ssb_driver_gige.h @@ -95,7 +95,7 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev) struct ssb_gige *dev = pdev_to_ssb_gige(pdev); if (dev) return (dev->dev->bus->chip_id == 0x4785); - return 0; + return false; } /* Get the device MAC address */ diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index c34b55a6e554..17f992fe6355 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -19,6 +19,22 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags, bool can_alloc); +/* + * Every user of stack depot has to call this during its own init when it's + * decided that it will be calling stack_depot_save() later. + * + * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot + * enabled as part of mm_init(), for subsystems where it's known at compile time + * that stack depot will be used. + */ +int stack_depot_init(void); + +#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT +static inline int stack_depot_early_init(void) { return stack_depot_init(); } +#else +static inline int stack_depot_early_init(void) { return 0; } +#endif + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); @@ -30,13 +46,4 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, void stack_depot_print(depot_stack_handle_t stack); -#ifdef CONFIG_STACKDEPOT -int stack_depot_init(void); -#else -static inline int stack_depot_init(void) -{ - return 0; -} -#endif /* CONFIG_STACKDEPOT */ - #endif diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index a59db2f08e76..ccaab2043fcd 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -23,11 +23,6 @@ static inline void stackleak_task_init(struct task_struct *t) # endif } -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index bef158815e83..97455880ac41 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -8,22 +8,6 @@ struct task_struct; struct pt_regs; -#ifdef CONFIG_STACKTRACE -void stack_trace_print(const unsigned long *trace, unsigned int nr_entries, - int spaces); -int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, - unsigned int nr_entries, int spaces); -unsigned int stack_trace_save(unsigned long *store, unsigned int size, - unsigned int skipnr); -unsigned int stack_trace_save_tsk(struct task_struct *task, - unsigned long *store, unsigned int size, - unsigned int skipnr); -unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, - unsigned int size, unsigned int skipnr); -unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); -unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); - -/* Internal interfaces. Do not use in generic code */ #ifdef CONFIG_ARCH_STACKWALK /** @@ -76,8 +60,25 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, const struct pt_regs *regs); +#endif /* CONFIG_ARCH_STACKWALK */ -#else /* CONFIG_ARCH_STACKWALK */ +#ifdef CONFIG_STACKTRACE +void stack_trace_print(const unsigned long *trace, unsigned int nr_entries, + int spaces); +int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, + unsigned int nr_entries, int spaces); +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr); +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); + +#ifndef CONFIG_ARCH_STACKWALK +/* Internal interfaces. Do not use in generic code */ struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; diff --git a/include/linux/stddef.h b/include/linux/stddef.h index ca507bd5f808..929d67710cc5 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -13,11 +13,7 @@ enum { }; #undef offsetof -#ifdef __compiler_offsetof -#define offsetof(TYPE, MEMBER) __compiler_offsetof(TYPE, MEMBER) -#else -#define offsetof(TYPE, MEMBER) ((size_t)&((TYPE *)0)->MEMBER) -#endif +#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) /** * sizeof_field() - Report the size of a struct field in bytes diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a6f03b36fc4f..24eea1b05ca2 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -233,6 +233,7 @@ struct plat_stmmacenet_data { int (*clks_config)(void *priv, bool enabled); int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); + void (*dump_debug_regs)(void *priv); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; @@ -241,6 +242,7 @@ struct plat_stmmacenet_data { unsigned int clk_ref_rate; unsigned int mult_fact_100ns; s32 ptp_max_adj; + u32 cdc_error_adj; struct reset_control *stmmac_rst; struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 4ba39e1403b2..4d72258d42fd 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -7,6 +7,7 @@ #include <linux/string.h> #include <linux/types.h> +struct device; struct file; struct task_struct; @@ -100,6 +101,29 @@ char *kstrdup_quotable(const char *src, gfp_t gfp); char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp); char *kstrdup_quotable_file(struct file *file, gfp_t gfp); +char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n); void kfree_strarray(char **array, size_t n); +char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n); + +static inline const char *str_yes_no(bool v) +{ + return v ? "yes" : "no"; +} + +static inline const char *str_on_off(bool v) +{ + return v ? "on" : "off"; +} + +static inline const char *str_enable_disable(bool v) +{ + return v ? "enable" : "disable"; +} + +static inline const char *str_enabled_disabled(bool v) +{ + return v ? "enabled" : "disabled"; +} + #endif diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 98da816b5fc2..3e6ce288a7fc 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -99,6 +99,7 @@ struct rpc_auth_create_args { /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ +#define RPCAUTH_LOOKUP_ASYNC 0x02 /* Don't block waiting for memory */ /* * Client authentication ops diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index db964bb63912..1d7a3e51b795 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -124,7 +124,6 @@ struct rpc_task_setup { #define RPC_TASK_MOVEABLE 0x0004 /* nfs4.1+ rpc tasks */ #define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ -#define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ #define RPC_TASK_NO_ROUND_ROBIN 0x0100 /* send requests on "main" xprt */ #define RPC_TASK_SOFT 0x0200 /* Use soft timeouts */ @@ -263,6 +262,7 @@ void rpc_destroy_mempool(void); extern struct workqueue_struct *rpciod_workqueue; extern struct workqueue_struct *xprtiod_workqueue; void rpc_prepare_task(struct rpc_task *task); +gfp_t rpc_task_gfp_mask(void); static inline int rpc_wait_for_completion_task(struct rpc_task *task) { diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 0ae28ae6caf2..a5dda4987e8b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -52,25 +52,6 @@ struct svc_pool { unsigned long sp_flags; } ____cacheline_aligned_in_smp; -struct svc_serv; - -struct svc_serv_ops { - /* Callback to use when last thread exits. */ - void (*svo_shutdown)(struct svc_serv *, struct net *); - - /* function for service threads to run */ - int (*svo_function)(void *); - - /* queue up a transport for servicing */ - void (*svo_enqueue_xprt)(struct svc_xprt *); - - /* set up thread (or whatever) execution context */ - int (*svo_setup)(struct svc_serv *, struct svc_pool *, int); - - /* optional module to count when adding threads (pooled svcs only) */ - struct module *svo_module; -}; - /* * RPC service. * @@ -85,6 +66,7 @@ struct svc_serv { struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + struct kref sv_refcnt; unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -102,7 +84,8 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - const struct svc_serv_ops *sv_ops; /* server operations */ + int (*sv_threadfn)(void *data); + #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -114,15 +97,43 @@ struct svc_serv { #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; -/* - * We use sv_nrthreads as a reference count. svc_destroy() drops - * this refcount, so we need to bump it up around operations that - * change the number of threads. Horrible, but there it is. - * Should be called with the "service mutex" held. +/** + * svc_get() - increment reference count on a SUNRPC serv + * @serv: the svc_serv to have count incremented + * + * Returns: the svc_serv that was passed in. */ -static inline void svc_get(struct svc_serv *serv) +static inline struct svc_serv *svc_get(struct svc_serv *serv) { - serv->sv_nrthreads++; + kref_get(&serv->sv_refcnt); + return serv; +} + +void svc_destroy(struct kref *); + +/** + * svc_put - decrement reference count on a SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * When the reference count reaches zero, svc_destroy() + * is called to clean up and free the serv. + */ +static inline void svc_put(struct svc_serv *serv) +{ + kref_put(&serv->sv_refcnt, svc_destroy); +} + +/** + * svc_put_not_last - decrement non-final reference count on SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * Returns: %true is refcount was decremented. + * + * If the refcount is 1, it is not decremented and instead failure is reported. + */ +static inline bool svc_put_not_last(struct svc_serv *serv) +{ + return refcount_dec_not_one(&serv->sv_refcnt.refcount); } /* @@ -469,53 +480,23 @@ struct svc_procedure { }; /* - * Mode for mapping cpus to pools. - */ -enum { - SVC_POOL_AUTO = -1, /* choose one of the others */ - SVC_POOL_GLOBAL, /* no mapping, just a single global pool - * (legacy & UP mode) */ - SVC_POOL_PERCPU, /* one pool per cpu */ - SVC_POOL_PERNODE /* one pool per numa node */ -}; - -struct svc_pool_map { - int count; /* How many svc_servs use us */ - int mode; /* Note: int not enum to avoid - * warnings about "enumeration value - * not handled in switch" */ - unsigned int npools; - unsigned int *pool_to; /* maps pool id to cpu or node */ - unsigned int *to_pool; /* maps cpu or node to pool id */ -}; - -extern struct svc_pool_map svc_pool_map; - -/* * Function prototypes. */ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, - struct svc_pool *pool, int node); void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); -unsigned int svc_pool_map_get(void); -void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - const struct svc_serv_ops *); + int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); -int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -void svc_destroy(struct svc_serv *); -void svc_shutdown_net(struct svc_serv *, struct net *); int svc_process(struct svc_rqst *); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..d42a75b3be10 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -28,6 +28,7 @@ struct svc_xprt_ops { void (*xpo_free)(struct svc_xprt *); void (*xpo_secure_port)(struct svc_rqst *rqstp); void (*xpo_kill_temp_xprt)(struct svc_xprt *); + void (*xpo_start_tls)(struct svc_xprt *); }; struct svc_xprt_class { @@ -88,6 +89,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ @@ -127,15 +129,16 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); -int svc_create_xprt(struct svc_serv *, const char *, struct net *, - const int, const unsigned short, int, - const struct cred *); +int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, + struct net *net, const int family, + const unsigned short port, int flags, + const struct cred *cred); +void svc_xprt_destroy_all(struct svc_serv *serv, struct net *net); void svc_xprt_received(struct svc_xprt *xprt); -void svc_xprt_do_enqueue(struct svc_xprt *xprt); void svc_xprt_enqueue(struct svc_xprt *xprt); void svc_xprt_put(struct svc_xprt *xprt); void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); -void svc_close_xprt(struct svc_xprt *xprt); +void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index b519609af1d0..4417f667c757 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -731,6 +731,8 @@ xdr_stream_decode_uint32_array(struct xdr_stream *xdr, if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) return -EBADMSG; + if (len > SIZE_MAX / sizeof(*p)) + return -EBADMSG; p = xdr_inline_decode(xdr, len * sizeof(*p)); if (unlikely(!p)) return -EBADMSG; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..45a9530d3839 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -139,6 +139,9 @@ struct rpc_xprt_ops { void (*rpcbind)(struct rpc_task *task); void (*set_port)(struct rpc_xprt *xprt, unsigned short port); void (*connect)(struct rpc_xprt *xprt, struct rpc_task *task); + int (*get_srcaddr)(struct rpc_xprt *xprt, char *buf, + size_t buflen); + unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); void (*prepare_request)(struct rpc_rqst *req); @@ -284,6 +287,7 @@ struct rpc_xprt { } stat; struct net *xprt_net; + netns_tracker ns_tracker; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 8c2a712cb242..38284f25eddf 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,7 +10,6 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); -unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) @@ -89,5 +88,7 @@ struct sock_xprt { #define XPRT_SOCK_WAKE_WRITE (5) #define XPRT_SOCK_WAKE_PENDING (6) #define XPRT_SOCK_WAKE_DISCONNECT (7) +#define XPRT_SOCK_CONNECT_SENT (8) +#define XPRT_SOCK_NOSPACE (9) #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index f636c5310321..cc257097eb05 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -319,6 +319,15 @@ void ssam_device_driver_unregister(struct ssam_device_driver *d); ssam_device_driver_unregister) +/* -- Helpers for controller and hub devices. ------------------------------- */ + +#ifdef CONFIG_SURFACE_AGGREGATOR_BUS +void ssam_remove_clients(struct device *dev); +#else /* CONFIG_SURFACE_AGGREGATOR_BUS */ +static inline void ssam_remove_clients(struct device *dev) {} +#endif /* CONFIG_SURFACE_AGGREGATOR_BUS */ + + /* -- Helpers for client-device requests. ----------------------------------- */ /** diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8af13ba60c7e..300273ff40cc 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -430,15 +430,7 @@ struct platform_hibernation_ops { #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ -extern void __register_nosave_region(unsigned long b, unsigned long e, int km); -static inline void __init register_nosave_region(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 0); -} -static inline void __init register_nosave_region_late(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 1); -} +extern void register_nosave_region(unsigned long b, unsigned long e); extern int swsusp_page_is_forbidden(struct page *); extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); @@ -446,6 +438,7 @@ extern unsigned long get_safe_page(gfp_t gfp_mask); extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); +extern u32 swsusp_hardware_signature; extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); @@ -457,7 +450,6 @@ int pfn_is_nosave(unsigned long pfn); int hibernate_quiet_exec(int (*func)(void *data), void *data); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} @@ -505,14 +497,14 @@ extern void ksys_sync_helper(void); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; -extern unsigned int pm_wakeup_irq; extern suspend_state_t pm_suspend_target_state; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); extern void pm_system_cancel_wakeup(void); -extern void pm_wakeup_clear(bool reset); +extern void pm_wakeup_clear(unsigned int irq_number); extern void pm_system_irq_wakeup(unsigned int irq_number); +extern unsigned int pm_wakeup_irq(void); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); diff --git a/include/linux/swait_api.h b/include/linux/swait_api.h new file mode 100644 index 000000000000..1eeaaaaa5ea7 --- /dev/null +++ b/include/linux/swait_api.h @@ -0,0 +1 @@ +#include <linux/swait.h> diff --git a/include/linux/swap.h b/include/linux/swap.h index d1ea44b31f19..27093b477c5f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -328,15 +328,18 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); -void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); +void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); +extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ - if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ } while (0) /* linux/mm/page_alloc.c */ @@ -372,7 +375,6 @@ extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void deactivate_file_page(struct page *page); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); extern void swap_setup(void); @@ -384,7 +386,6 @@ extern void lru_cache_add_inactive_or_unevictable(struct page *page, extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); -extern bool __isolate_lru_page_prepare(struct page *page, isolate_mode_t mode); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, @@ -395,7 +396,7 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; -extern int remove_mapping(struct address_space *mapping, struct page *page); +long remove_mapping(struct address_space *mapping, struct folio *folio); extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA @@ -427,7 +428,7 @@ extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func); -extern int swap_set_page_dirty(struct page *page); +bool swap_dirty_folio(struct address_space *mapping, struct folio *folio); int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); @@ -514,7 +515,6 @@ extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern bool reuse_swap_page(struct page *, int *); extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); @@ -680,9 +680,6 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_map_swapcount) \ - (page_trans_huge_mapcount(page, total_map_swapcount) == 1) - static inline int try_to_free_swap(struct page *page) { return 0; @@ -741,7 +738,7 @@ static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) #endif #ifdef CONFIG_MEMCG_SWAP -extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry); +void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); extern int __mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) { @@ -761,7 +758,7 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_p extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct page *page); #else -static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e06febf62978..54078542134c 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,10 +6,7 @@ * these were static in swapfile.c but frontswap.c needs them and we don't * want to expose them to the dozens of source files that include swap.h */ -extern spinlock_t swap_lock; -extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; -extern int try_to_unuse(unsigned int, bool, unsigned long); extern unsigned long generic_max_swapfile_size(void); extern unsigned long max_swapfile_size(void); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 569272871375..f6c3638255d5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -73,6 +73,9 @@ extern enum swiotlb_force swiotlb_force; * @end: The end address of the swiotlb memory pool. Used to do a quick * range check to see if the memory was in fact allocated by this * API. + * @vaddr: The vaddr of the swiotlb memory pool. The swiotlb memory pool + * may be remapped in the memory encrypted case and store virtual + * address for bounce buffer operation. * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and * @end. For default swiotlb, this is command line adjustable via * setup_io_tlb_npages. @@ -92,6 +95,7 @@ extern enum swiotlb_force swiotlb_force; struct io_tlb_mem { phys_addr_t start; phys_addr_t end; + void *vaddr; unsigned long nslabs; unsigned long used; unsigned int index; @@ -186,4 +190,6 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ +extern phys_addr_t swiotlb_unencrypted_base; + #endif /* __LINUX_SWIOTLB_H */ diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index be24056ac00f..48fabe36509e 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -337,8 +337,6 @@ enum { NTB_CTRL_REQ_ID_EN = 1 << 0, NTB_CTRL_LUT_EN = 1 << 0, - - NTB_PART_CTRL_ID_PROT_DIS = 1 << 0, }; struct ntb_ctrl_regs { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 528a478dbda8..a34b0f9a9972 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -290,10 +290,6 @@ static inline void addr_limit_user_check(void) return; #endif - if (CHECK_DATA_CORRUPTION(uaccess_kernel(), - "Invalid address limit on user-mode return")) - force_sig(SIGKILL); - #ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); #endif @@ -1057,6 +1053,9 @@ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type ru const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); asmlinkage long sys_memfd_secret(unsigned int flags); +asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); /* * Architecture-specific system calls diff --git a/include/linux/syscalls_api.h b/include/linux/syscalls_api.h new file mode 100644 index 000000000000..23e012b04db4 --- /dev/null +++ b/include/linux/syscalls_api.h @@ -0,0 +1 @@ +#include <linux/syscalls.h> diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1fa2b69c6fc3..6353d6db69b2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,12 +38,28 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) -#define SYSCTL_ONE ((void *)&sysctl_vals[1]) -#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) +#define SYSCTL_ONE ((void *)&sysctl_vals[2]) +#define SYSCTL_TWO ((void *)&sysctl_vals[3]) +#define SYSCTL_FOUR ((void *)&sysctl_vals[4]) +#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) +#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) +#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) +#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) +#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) + +/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ +#define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) extern const int sysctl_vals[]; +#define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0]) +#define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1]) +#define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2]) + +extern const unsigned long sysctl_long_vals[]; + typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); @@ -178,6 +194,20 @@ struct ctl_path { #ifdef CONFIG_SYSCTL +#define DECLARE_SYSCTL_BASE(_name, _table) \ +static struct ctl_table _name##_base_table[] = { \ + { \ + .procname = #_name, \ + .mode = 0555, \ + .child = _table, \ + }, \ + { }, \ +} + +extern int __register_sysctl_base(struct ctl_table *base_table); + +#define register_sysctl_base(_name) __register_sysctl_base(_name##_base_table) + void proc_sys_poll_notify(struct ctl_table_poll *poll); extern void setup_sysctl_set(struct ctl_table_set *p, @@ -198,8 +228,19 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); -extern int sysctl_init(void); +extern int sysctl_init_bases(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) +extern struct ctl_table_header *register_sysctl_mount_point(const char *path); + void do_sysctl_args(void); +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data); extern int pwrsw_enabled; extern int unaligned_enabled; @@ -207,16 +248,28 @@ extern int unaligned_dump_stack; extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; -extern struct ctl_table random_table[]; -extern struct ctl_table firmware_config_table[]; -extern struct ctl_table epoll_table[]; #else /* CONFIG_SYSCTL */ + +#define DECLARE_SYSCTL_BASE(_name, _table) + +static inline int __register_sysctl_base(struct ctl_table *base_table) +{ + return 0; +} + +#define register_sysctl_base(table) __register_sysctl_base(table) + static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) { return NULL; } +static inline struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return NULL; +} + static inline struct ctl_table_header *register_sysctl_paths( const struct ctl_path *path, struct ctl_table *table) { diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index c635c2e014e3..a4b1af581f69 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -53,4 +53,24 @@ extern const struct blk_integrity_profile t10_pi_type1_ip; extern const struct blk_integrity_profile t10_pi_type3_crc; extern const struct blk_integrity_profile t10_pi_type3_ip; +struct crc64_pi_tuple { + __be64 guard_tag; + __be16 app_tag; + __u8 ref_tag[6]; +}; + +static inline u64 ext_pi_ref_tag(struct request *rq) +{ + unsigned int shift = ilog2(queue_logical_block_size(rq->q)); + +#ifdef CONFIG_BLK_DEV_INTEGRITY + if (rq->q->integrity.interval_exp) + shift = rq->q->integrity.interval_exp; +#endif + return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT)); +} + +extern const struct blk_integrity_profile ext_pi_type1_crc64; +extern const struct blk_integrity_profile ext_pi_type3_crc64; + #endif diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 5b8a93f288bb..897494b597ba 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -19,6 +19,11 @@ enum task_work_notify_mode { TWA_SIGNAL, }; +static inline bool task_work_pending(struct task_struct *task) +{ + return READ_ONCE(task->task_works); +} + int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 48d8a363319e..1168302b7927 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -394,6 +394,7 @@ struct tcp_sock { bool is_mptcp; #endif #if IS_ENABLED(CONFIG_SMC) + bool (*smc_hs_congested)(const struct sock *sk); bool syn_smc; /* SYN includes SMC */ #endif @@ -512,11 +513,13 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); +void __tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepcnt(struct sock *sk, int val); int tcp_sock_set_keepidle_locked(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); +void __tcp_sock_set_nodelay(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a1f03461369b..911cad324acc 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2016, Linaro Limited + * Copyright (c) 2015-2022 Linaro Limited */ #ifndef __TEE_DRV_H @@ -20,14 +20,11 @@ * specific TEE driver. */ -#define TEE_SHM_MAPPED BIT(0) /* Memory mapped by the kernel */ -#define TEE_SHM_DMA_BUF BIT(1) /* Memory with dma-buf handle */ -#define TEE_SHM_EXT_DMA_BUF BIT(2) /* Memory with dma-buf handle */ -#define TEE_SHM_REGISTER BIT(3) /* Memory registered in secure world */ -#define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */ -#define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */ -#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */ +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ struct device; struct tee_device; @@ -195,7 +192,7 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @offset: offset of buffer in user space * @pages: locked pages from userspace * @num_pages: number of locked pages - * @dmabuf: dmabuf used to for exporting to user space + * @refcount: reference counter * @flags: defined by TEE_SHM_* in tee_drv.h * @id: unique id of a shared memory object on this device, shared * with user space @@ -214,99 +211,46 @@ struct tee_shm { unsigned int offset; struct page **pages; size_t num_pages; - struct dma_buf *dmabuf; + refcount_t refcount; u32 flags; int id; u64 sec_world_id; }; /** - * struct tee_shm_pool_mgr - shared memory manager + * struct tee_shm_pool - shared memory pool * @ops: operations * @private_data: private data for the shared memory manager */ -struct tee_shm_pool_mgr { - const struct tee_shm_pool_mgr_ops *ops; +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; void *private_data; }; /** - * struct tee_shm_pool_mgr_ops - shared memory pool manager operations + * struct tee_shm_pool_ops - shared memory pool operations * @alloc: called when allocating shared memory * @free: called when freeing shared memory - * @destroy_poolmgr: called when destroying the pool manager + * @destroy_pool: called when destroying the pool */ -struct tee_shm_pool_mgr_ops { - int (*alloc)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm, - size_t size); - void (*free)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm); - void (*destroy_poolmgr)(struct tee_shm_pool_mgr *poolmgr); +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); }; -/** - * tee_shm_pool_alloc() - Create a shared memory pool from shm managers - * @priv_mgr: manager for driver private shared memory allocations - * @dmabuf_mgr: manager for dma-buf shared memory allocations - * - * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied - * in @dmabuf, others will use the range provided by @priv. - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc(struct tee_shm_pool_mgr *priv_mgr, - struct tee_shm_pool_mgr *dmabuf_mgr); - /* - * tee_shm_pool_mgr_alloc_res_mem() - Create a shm manager for reserved - * memory + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory * @vaddr: Virtual address of start of pool * @paddr: Physical address of start of pool * @size: Size in bytes of the pool * - * @returns pointer to a 'struct tee_shm_pool_mgr' or an ERR_PTR on failure. - */ -struct tee_shm_pool_mgr *tee_shm_pool_mgr_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, - size_t size, - int min_alloc_order); - -/** - * tee_shm_pool_mgr_destroy() - Free a shared memory manager - */ -static inline void tee_shm_pool_mgr_destroy(struct tee_shm_pool_mgr *poolm) -{ - poolm->ops->destroy_poolmgr(poolm); -} - -/** - * struct tee_shm_pool_mem_info - holds information needed to create a shared - * memory pool - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - */ -struct tee_shm_pool_mem_info { - unsigned long vaddr; - phys_addr_t paddr; - size_t size; -}; - -/** - * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved - * memory range - * @priv_info: Information for driver private shared memory pool - * @dmabuf_info: Information for dma-buf shared memory pool - * - * Start and end of pools will must be page aligned. - * - * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied - * in @dmabuf, others will use the range provided by @priv. - * * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. */ -struct tee_shm_pool * -tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, - struct tee_shm_pool_mem_info *dmabuf_info); +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); /** * tee_shm_pool_free() - Free a shared memory pool @@ -315,7 +259,10 @@ tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info, * The must be no remaining shared memory allocated from this pool when * this function is called. */ -void tee_shm_pool_free(struct tee_shm_pool *pool); +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} /** * tee_get_drvdata() - Return driver_data pointer @@ -323,43 +270,20 @@ void tee_shm_pool_free(struct tee_shm_pool *pool); */ void *tee_get_drvdata(struct tee_device *teedev); -/** - * tee_shm_alloc() - Allocate shared memory - * @ctx: Context that allocates the shared memory - * @size: Requested size of shared memory - * @flags: Flags setting properties for the requested shared memory. - * - * Memory allocated as global shared memory is automatically freed when the - * TEE file pointer is closed. The @flags field uses the bits defined by - * TEE_SHM_* above. TEE_SHM_MAPPED must currently always be set. If - * TEE_SHM_DMA_BUF global shared memory will be allocated and associated - * with a dma-buf handle, else driver private memory. - * - * @returns a pointer to 'struct tee_shm' - */ -struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags); +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); -/** - * tee_shm_register() - Register shared memory buffer - * @ctx: Context that registers the shared memory - * @addr: Address is userspace of the shared buffer - * @length: Length of the shared buffer - * @flags: Flags setting properties for the requested shared memory. - * - * @returns a pointer to 'struct tee_shm' - */ -struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, - size_t length, u32 flags); +struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, + void *addr, size_t length); /** - * tee_shm_is_registered() - Check if shared memory object in registered in TEE + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind * @shm: Shared memory handle - * @returns true if object is registered in TEE + * @returns true if object is dynamic shared memory */ -static inline bool tee_shm_is_registered(struct tee_shm *shm) +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) { - return shm && (shm->flags & TEE_SHM_REGISTER); + return shm && (shm->flags & TEE_SHM_DYNAMIC); } /** @@ -587,4 +511,18 @@ struct tee_client_driver { #define to_tee_client_driver(d) \ container_of(d, struct tee_client_driver, driver) +/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + #endif /*__TEE_DRV_H*/ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ad0c4e041030..9f392ec76f2b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -118,6 +118,15 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) return test_bit(flag, (unsigned long *)&ti->flags); } +/* + * This may be used in noinstr code, and needs to be __always_inline to prevent + * inadvertent instrumentation. + */ +static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) +{ + return READ_ONCE(ti->flags); +} + #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ @@ -130,6 +139,11 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) +#define read_thread_flags() \ + read_ti_thread_flags(current_thread_info()) + +#define read_task_thread_flags(t) \ + read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ @@ -195,9 +209,12 @@ __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); +void __copy_overflow(int size, unsigned long count); + static inline void copy_overflow(int size, unsigned long count) { - WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); + if (IS_ENABLED(CONFIG_BUG)) + __copy_overflow(size, count); } static __always_inline __must_check bool diff --git a/include/linux/topology.h b/include/linux/topology.h index 0b3704ad13c8..f19bc3626297 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -180,6 +180,19 @@ static inline int cpu_to_mem(int cpu) #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ +#if defined(topology_die_id) && defined(topology_die_cpumask) +#define TOPOLOGY_DIE_SYSFS +#endif +#if defined(topology_cluster_id) && defined(topology_cluster_cpumask) +#define TOPOLOGY_CLUSTER_SYSFS +#endif +#if defined(topology_book_id) && defined(topology_book_cpumask) +#define TOPOLOGY_BOOK_SYSFS +#endif +#if defined(topology_drawer_id) && defined(topology_drawer_cpumask) +#define TOPOLOGY_DRAWER_SYSFS +#endif + #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif @@ -192,6 +205,15 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif +#ifndef topology_book_id +#define topology_book_id(cpu) ((void)(cpu), -1) +#endif +#ifndef topology_drawer_id +#define topology_drawer_id(cpu) ((void)(cpu), -1) +#endif +#ifndef topology_ppin +#define topology_ppin(cpu) ((void)(cpu), 0ull) +#endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif @@ -204,6 +226,12 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif +#ifndef topology_book_cpumask +#define topology_book_cpumask(cpu) cpumask_of(cpu) +#endif +#ifndef topology_drawer_cpumask +#define topology_drawer_cpumask(cpu) cpumask_of(cpu) +#endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) diff --git a/include/linux/torture.h b/include/linux/torture.h index 24f58e50a94b..63fa4196e51c 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -38,13 +38,8 @@ do { \ pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); \ } \ } while (0) -#define VERBOSE_TOROUT_ERRSTRING(s) \ -do { \ - if (verbose) { \ - verbose_torout_sleep(); \ - pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); \ - } \ -} while (0) +#define TOROUT_ERRSTRING(s) \ + pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s) void verbose_torout_sleep(void); #define torture_init_error(firsterr) \ diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 12d827734686..dfeb25a0362d 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -207,6 +207,7 @@ enum tpm2_return_codes { TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ TPM2_RC_FAILURE = 0x0101, TPM2_RC_DISABLED = 0x0120, + TPM2_RC_UPGRADE = 0x012D, TPM2_RC_COMMAND_CODE = 0x0143, TPM2_RC_TESTING = 0x090A, /* RC_WARN */ TPM2_RC_REFERENCE_H0 = 0x0910, @@ -278,6 +279,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), + TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) @@ -399,6 +401,14 @@ static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) tpm_buf_append(buf, (u8 *) &value2, 4); } +/* + * Check if TPM device is in the firmware upgrade mode. + */ +static inline bool tpm_is_firmware_upgrade(struct tpm_chip *chip) +{ + return chip->flags & TPM_CHIP_FLAG_FIRMWARE_UPGRADE; +} + static inline u32 tpm2_rc_value(u32 rc) { return (rc & BIT(7)) ? rc & 0xff : rc; diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2d167ac3452c..e6e95a9f07a5 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -15,6 +15,7 @@ struct array_buffer; struct tracer; struct dentry; struct bpf_prog; +union bpf_attr; const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, @@ -172,6 +173,7 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, + TRACE_FLAG_BH_OFF = 0x80, }; #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT @@ -314,6 +316,7 @@ enum { TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, TRACE_EVENT_FL_EPROBE_BIT, + TRACE_EVENT_FL_CUSTOM_BIT, }; /* @@ -327,6 +330,9 @@ enum { * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe * EPROBE - Event is an event probe + * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) + * This is set when the custom event has not been attached + * to a tracepoint yet, then it is cleared when it is. */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -338,6 +344,7 @@ enum { TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), + TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -439,7 +446,9 @@ static inline bool bpf_prog_array_valid(struct trace_event_call *call) static inline const char * trace_event_name(struct trace_event_call *call) { - if (call->flags & TRACE_EVENT_FL_TRACEPOINT) + if (call->flags & TRACE_EVENT_FL_CUSTOM) + return call->name; + else if (call->flags & TRACE_EVENT_FL_TRACEPOINT) return call->tp ? call->tp->name : NULL; else return call->name; @@ -698,6 +707,8 @@ event_triggers_post_call(struct trace_event_file *file, bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); +bool __trace_trigger_soft_disabled(struct trace_event_file *file); + /** * trace_trigger_soft_disabled - do triggers and test if soft disabled * @file: The file pointer of the event to test @@ -707,20 +718,20 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); * triggers that require testing the fields, it will return true, * otherwise false. */ -static inline bool +static __always_inline bool trace_trigger_soft_disabled(struct trace_event_file *file) { unsigned long eflags = file->flags; - if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { - if (eflags & EVENT_FILE_FL_TRIGGER_MODE) - event_triggers_call(file, NULL, NULL, NULL); - if (eflags & EVENT_FILE_FL_SOFT_DISABLED) - return true; - if (eflags & EVENT_FILE_FL_PID_FILTER) - return trace_event_ignore_this_pid(file); - } - return false; + if (likely(!(eflags & (EVENT_FILE_FL_TRIGGER_MODE | + EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (likely(eflags & EVENT_FILE_FL_TRIGGER_COND)) + return false; + + return __trace_trigger_soft_disabled(file); } #ifdef CONFIG_BPF_EVENTS @@ -735,6 +746,7 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -776,12 +788,18 @@ static inline int bpf_get_perf_event_info(const struct perf_event *event, { return -EOPNOTSUPP; } +static inline int +bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { FILTER_OTHER = 0, FILTER_STATIC_STRING, FILTER_DYN_STRING, + FILTER_RDYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, FILTER_COMM, @@ -899,3 +917,18 @@ perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, #endif #endif /* _LINUX_TRACE_EVENT_H */ + +/* + * Note: we keep the TRACE_CUSTOM_EVENT outside the include file ifdef protection. + * This is due to the way trace custom events work. If a file includes two + * trace event headers under one "CREATE_CUSTOM_TRACE_EVENTS" the first include + * will override the TRACE_CUSTOM_EVENT and break the second include. + */ + +#ifndef TRACE_CUSTOM_EVENT + +#define DECLARE_CUSTOM_EVENT_CLASS(name, proto, args, tstruct, assign, print) +#define DEFINE_CUSTOM_EVENT(template, name, proto, args) +#define TRACE_CUSTOM_EVENT(name, proto, args, struct, assign, print) + +#endif /* ifdef TRACE_CUSTOM_EVENT (see note above) */ diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h deleted file mode 100644 index 2564b7434b4d..000000000000 --- a/include/linux/tracehook.h +++ /dev/null @@ -1,227 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Tracing hooks - * - * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. - * - * This file defines hook entry points called by core code where - * user tracing/debugging support might need to do something. These - * entry points are called tracehook_*(). Each hook declared below - * has a detailed kerneldoc comment giving the context (locking et - * al) from which it is called, and the meaning of its return value. - * - * Each function here typically has only one call site, so it is ok - * to have some nontrivial tracehook_*() inlines. In all cases, the - * fast path when no tracing is enabled should be very short. - * - * The purpose of this file and the tracehook_* layer is to consolidate - * the interface that the kernel core and arch code uses to enable any - * user debugging or tracing facility (such as ptrace). The interfaces - * here are carefully documented so that maintainers of core and arch - * code do not need to think about the implementation details of the - * tracing facilities. Likewise, maintainers of the tracing code do not - * need to understand all the calling core or arch code in detail, just - * documented circumstances of each call, such as locking conditions. - * - * If the calling core code changes so that locking is different, then - * it is ok to change the interface documented here. The maintainer of - * core code changing should notify the maintainers of the tracing code - * that they need to work out the change. - * - * Some tracehook_*() inlines take arguments that the current tracing - * implementations might not necessarily use. These function signatures - * are chosen to pass in all the information that is on hand in the - * caller and might conceivably be relevant to a tracer, so that the - * core code won't have to be updated when tracing adds more features. - * If a call site changes so that some of those parameters are no longer - * already on hand without extra work, then the tracehook_* interface - * can change so there is no make-work burden on the core code. The - * maintainer of core code changing should notify the maintainers of the - * tracing code that they need to work out the change. - */ - -#ifndef _LINUX_TRACEHOOK_H -#define _LINUX_TRACEHOOK_H 1 - -#include <linux/sched.h> -#include <linux/ptrace.h> -#include <linux/security.h> -#include <linux/task_work.h> -#include <linux/memcontrol.h> -#include <linux/blk-cgroup.h> -struct linux_binprm; - -/* - * ptrace report for syscall entry and exit looks identical. - */ -static inline int ptrace_report_syscall(struct pt_regs *regs, - unsigned long message) -{ - int ptrace = current->ptrace; - - if (!(ptrace & PT_PTRACED)) - return 0; - - current->ptrace_message = message; - ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); - - /* - * this isn't the same as continuing with a signal, but it will do - * for normal use. strace only continues with a signal if the - * stopping signal is not SIGTRAP. -brl - */ - if (current->exit_code) { - send_sig(current->exit_code, current, 1); - current->exit_code = 0; - } - - current->ptrace_message = 0; - return fatal_signal_pending(current); -} - -/** - * tracehook_report_syscall_entry - task is about to attempt a system call - * @regs: user register state of current task - * - * This will be called if %SYSCALL_WORK_SYSCALL_TRACE or - * %SYSCALL_WORK_SYSCALL_EMU have been set, when the current task has just - * entered the kernel for a system call. Full user register state is - * available here. Changing the values in @regs can affect the system - * call number and arguments to be tried. It is safe to block here, - * preventing the system call from beginning. - * - * Returns zero normally, or nonzero if the calling arch code should abort - * the system call. That must prevent normal entry so no system call is - * made. If @task ever returns to user mode after this, its register state - * is unspecified, but should be something harmless like an %ENOSYS error - * return. It should preserve enough information so that syscall_rollback() - * can work (see asm-generic/syscall.h). - * - * Called without locks, just after entering kernel mode. - */ -static inline __must_check int tracehook_report_syscall_entry( - struct pt_regs *regs) -{ - return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); -} - -/** - * tracehook_report_syscall_exit - task has just finished a system call - * @regs: user register state of current task - * @step: nonzero if simulating single-step or block-step - * - * This will be called if %SYSCALL_WORK_SYSCALL_TRACE has been set, when - * the current task has just finished an attempted system call. Full - * user register state is available here. It is safe to block here, - * preventing signals from being processed. - * - * If @step is nonzero, this report is also in lieu of the normal - * trap that would follow the system call instruction because - * user_enable_block_step() or user_enable_single_step() was used. - * In this case, %SYSCALL_WORK_SYSCALL_TRACE might not be set. - * - * Called without locks, just before checking for pending signals. - */ -static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) -{ - if (step) - user_single_step_report(regs); - else - ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); -} - -/** - * tracehook_signal_handler - signal handler setup is complete - * @stepping: nonzero if debugger single-step or block-step in use - * - * Called by the arch code after a signal handler has been set up. - * Register and stack state reflects the user handler about to run. - * Signal mask changes have already been made. - * - * Called without locks, shortly before returning to user mode - * (or handling more signals). - */ -static inline void tracehook_signal_handler(int stepping) -{ - if (stepping) - ptrace_notify(SIGTRAP); -} - -/** - * set_notify_resume - cause tracehook_notify_resume() to be called - * @task: task that will call tracehook_notify_resume() - * - * Calling this arranges that @task will call tracehook_notify_resume() - * before returning to user mode. If it's already running in user mode, - * it will enter the kernel and call tracehook_notify_resume() soon. - * If it's blocked, it will not be woken. - */ -static inline void set_notify_resume(struct task_struct *task) -{ -#ifdef TIF_NOTIFY_RESUME - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) - kick_process(task); -#endif -} - -/** - * tracehook_notify_resume - report when about to return to user mode - * @regs: user-mode registers of @current task - * - * This is called when %TIF_NOTIFY_RESUME has been set. Now we are - * about to return to user mode, and the user state in @regs can be - * inspected or adjusted. The caller in arch code has cleared - * %TIF_NOTIFY_RESUME before the call. If the flag gets set again - * asynchronously, this will be called again before we return to - * user mode. - * - * Called without locks. - */ -static inline void tracehook_notify_resume(struct pt_regs *regs) -{ - clear_thread_flag(TIF_NOTIFY_RESUME); - /* - * This barrier pairs with task_work_add()->set_notify_resume() after - * hlist_add_head(task->task_works); - */ - smp_mb__after_atomic(); - if (unlikely(current->task_works)) - task_work_run(); - -#ifdef CONFIG_KEYS_REQUEST_CACHE - if (unlikely(current->cached_requested_key)) { - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; - } -#endif - - mem_cgroup_handle_over_high(); - blkcg_maybe_throttle_current(); - - rseq_handle_notify_resume(NULL, regs); -} - -/* - * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This - * is currently used by TWA_SIGNAL based task_work, which requires breaking - * wait loops to ensure that task_work is noticed and run. - */ -static inline void tracehook_notify_signal(void) -{ - clear_thread_flag(TIF_NOTIFY_SIGNAL); - smp_mb__after_atomic(); - if (current->task_works) - task_work_run(); -} - -/* - * Called when we have work to process from exit_to_user_mode_loop() - */ -static inline void set_notify_signal(struct task_struct *task) -{ - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) - kick_process(task); -} - -#endif /* <linux/tracehook.h> */ diff --git a/include/linux/tty.h b/include/linux/tty.h index 5dbd7c5afac7..7b0a5d478ef6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -122,33 +122,84 @@ struct tty_operations; /** * struct tty_struct - state associated with a tty while open * - * @flow.lock: lock for flow members - * @flow.stopped: tty stopped/started by tty_stop/tty_start - * @flow.tco_stopped: tty stopped/started by TCOOFF/TCOON ioctls (it has - * precedense over @flow.stopped) + * @magic: magic value set early in @alloc_tty_struct to %TTY_MAGIC, for + * debugging purposes + * @kref: reference counting by tty_kref_get() and tty_kref_put(), reaching zero + * frees the structure + * @dev: class device or %NULL (e.g. ptys, serdev) + * @driver: &struct tty_driver operating this tty + * @ops: &struct tty_operations of @driver for this tty (open, close, etc.) + * @index: index of this tty (e.g. to construct @name like tty12) + * @ldisc_sem: protects line discipline changes (@ldisc) -- lock tty not pty + * @ldisc: the current line discipline for this tty (n_tty by default) + * @atomic_write_lock: protects against concurrent writers, i.e. locks + * @write_cnt, @write_buf and similar + * @legacy_mutex: leftover from history (BKL -> BTM -> @legacy_mutex), + * protecting several operations on this tty + * @throttle_mutex: protects against concurrent tty_throttle_safe() and + * tty_unthrottle_safe() (but not tty_unthrottle()) + * @termios_rwsem: protects @termios and @termios_locked + * @winsize_mutex: protects @winsize + * @termios: termios for the current tty, copied from/to @driver.termios + * @termios_locked: locked termios (by %TIOCGLCKTRMIOS and %TIOCSLCKTRMIOS + * ioctls) + * @name: name of the tty constructed by tty_line_name() (e.g. ttyS3) + * @flags: bitwise OR of %TTY_THROTTLED, %TTY_IO_ERROR, ... + * @count: count of open processes, reaching zero cancels all the work for + * this tty and drops a @kref too (but does not free this tty) + * @winsize: size of the terminal "window" (cf. @winsize_mutex) + * @flow: flow settings grouped together, see also @flow.unused + * @flow.lock: lock for @flow members + * @flow.stopped: tty stopped/started by stop_tty()/start_tty() + * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has + * precedence over @flow.stopped) * @flow.unused: alignment for Alpha, so that no members other than @flow.* are * modified by the same 64b word store. The @flow's __aligned is * there for the very same reason. - * @ctrl.lock: lock for ctrl members + * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both - * @ctrl.lock and legacy mutex, readers must use at least one of + * @ctrl.lock and @legacy_mutex, readers must use at least one of * them. - * @ctrl.pktstatus: packet mode status (bitwise OR of TIOCPKT_* constants) + * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled + * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation + * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS + * handling + * @receive_room: bytes permitted to feed to @ldisc without any being lost + * @flow_change: controls behavior of throttling, see tty_throttle_safe() and + * tty_unthrottle_safe() + * @link: link to another pty (master -> slave and vice versa) + * @fasync: state for %O_ASYNC (for %SIGIO); managed by fasync_helper() + * @write_wait: concurrent writers are waiting in this queue until they are + * allowed to write + * @read_wait: readers wait for data in this queue + * @hangup_work: normally a work to perform a hangup (do_tty_hangup()); while + * freeing the tty, (re)used to release_one_tty() + * @disc_data: pointer to @ldisc's private data (e.g. to &struct n_tty_data) + * @driver_data: pointer to @driver's private data (e.g. &struct uart_state) + * @files_lock: protects @tty_files list + * @tty_files: list of (re)openers of this tty (i.e. linked &struct + * tty_file_private) + * @closing: when set during close, n_tty processes only START & STOP chars + * @write_buf: temporary buffer used during tty_write() to copy user data to + * @write_cnt: count of bytes written in tty_write() to @write_buf + * @SAK_work: if the tty has a pending do_SAK, it is queued here + * @port: persistent storage for this device (i.e. &struct tty_port) * * All of the state associated with a tty while the tty is open. Persistent - * storage for tty devices is referenced here as @port in struct tty_port. + * storage for tty devices is referenced here as @port and is documented in + * &struct tty_port. */ struct tty_struct { int magic; struct kref kref; - struct device *dev; /* class device or NULL (e.g. ptys, serdev) */ + struct device *dev; struct tty_driver *driver; const struct tty_operations *ops; int index; - /* Protects ldisc changes: Lock tty not pty */ struct ld_semaphore ldisc_sem; struct tty_ldisc *ldisc; @@ -157,12 +208,11 @@ struct tty_struct { struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; struct mutex winsize_mutex; - /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; char name[64]; unsigned long flags; int count; - struct winsize winsize; /* winsize_mutex */ + struct winsize winsize; struct { spinlock_t lock; @@ -181,7 +231,7 @@ struct tty_struct { } __aligned(sizeof(unsigned long)) ctrl; int hw_stopped; - unsigned int receive_room; /* Bytes free for queue */ + unsigned int receive_room; int flow_change; struct tty_struct *link; @@ -191,7 +241,7 @@ struct tty_struct { struct work_struct hangup_work; void *disc_data; void *driver_data; - spinlock_t files_lock; /* protects tty_files list */ + spinlock_t files_lock; struct list_head tty_files; #define N_TTY_BUF_SIZE 4096 @@ -199,7 +249,6 @@ struct tty_struct { int closing; unsigned char *write_buf; int write_cnt; - /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; } __randomize_layout; @@ -214,26 +263,72 @@ struct tty_file_private { /* tty magic number */ #define TTY_MAGIC 0x5401 -/* - * These bits are used in the flags field of the tty structure. +/** + * DOC: TTY Struct Flags + * + * These bits are used in the :c:member:`tty_struct.flags` field. * * So that interrupts won't be able to mess up the queues, * copy_to_cooked must be atomic with respect to itself, as must * tty->write. Thus, you must use the inline functions set_bit() and * clear_bit() to make things atomic. + * + * TTY_THROTTLED + * Driver input is throttled. The ldisc should call + * :c:member:`tty_driver.unthrottle()` in order to resume reception when + * it is ready to process more data (at threshold min). + * + * TTY_IO_ERROR + * If set, causes all subsequent userspace read/write calls on the tty to + * fail, returning -%EIO. (May be no ldisc too.) + * + * TTY_OTHER_CLOSED + * Device is a pty and the other side has closed. + * + * TTY_EXCLUSIVE + * Exclusive open mode (a single opener). + * + * TTY_DO_WRITE_WAKEUP + * If set, causes the driver to call the + * :c:member:`tty_ldisc_ops.write_wakeup()` method in order to resume + * transmission when it can accept more data to transmit. + * + * TTY_LDISC_OPEN + * Indicates that a line discipline is open. For debugging purposes only. + * + * TTY_PTY_LOCK + * A flag private to pty code to implement %TIOCSPTLCK/%TIOCGPTLCK logic. + * + * TTY_NO_WRITE_SPLIT + * Prevent driver from splitting up writes into smaller chunks (preserve + * write boundaries to driver). + * + * TTY_HUPPED + * The TTY was hung up. This is set post :c:member:`tty_driver.hangup()`. + * + * TTY_HUPPING + * The TTY is in the process of hanging up to abort potential readers. + * + * TTY_LDISC_CHANGING + * Line discipline for this TTY is being changed. I/O should not block + * when this is set. Use tty_io_nonblock() to check. + * + * TTY_LDISC_HALTED + * Line discipline for this TTY was stopped. No work should be queued to + * this ldisc. */ -#define TTY_THROTTLED 0 /* Call unthrottle() at threshold min */ -#define TTY_IO_ERROR 1 /* Cause an I/O error (may be no ldisc too) */ -#define TTY_OTHER_CLOSED 2 /* Other side (if any) has closed */ -#define TTY_EXCLUSIVE 3 /* Exclusive open mode */ -#define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -#define TTY_LDISC_OPEN 11 /* Line discipline is open */ -#define TTY_PTY_LOCK 16 /* pty private */ -#define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ -#define TTY_HUPPED 18 /* Post driver->hangup() */ -#define TTY_HUPPING 19 /* Hangup in progress */ -#define TTY_LDISC_CHANGING 20 /* Change pending - non-block IO */ -#define TTY_LDISC_HALTED 22 /* Line discipline is halted */ +#define TTY_THROTTLED 0 +#define TTY_IO_ERROR 1 +#define TTY_OTHER_CLOSED 2 +#define TTY_EXCLUSIVE 3 +#define TTY_DO_WRITE_WAKEUP 5 +#define TTY_LDISC_OPEN 11 +#define TTY_PTY_LOCK 16 +#define TTY_NO_WRITE_SPLIT 17 +#define TTY_HUPPED 18 +#define TTY_HUPPING 19 +#define TTY_LDISC_CHANGING 20 +#define TTY_LDISC_HALTED 22 static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) { diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 795b94ccdeb6..4841d8069c07 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -2,248 +2,350 @@ #ifndef _LINUX_TTY_DRIVER_H #define _LINUX_TTY_DRIVER_H -/* - * This structure defines the interface between the low-level tty - * driver and the tty routines. The following routines can be - * defined; unless noted otherwise, they are optional, and can be - * filled in with a null pointer. +#include <linux/export.h> +#include <linux/fs.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/cdev.h> +#include <linux/termios.h> +#include <linux/seq_file.h> + +struct tty_struct; +struct tty_driver; +struct serial_icounter_struct; +struct serial_struct; + +/** + * struct tty_operations -- interface between driver and tty + * + * @lookup: ``struct tty_struct *()(struct tty_driver *self, struct file *, + * int idx)`` * - * struct tty_struct * (*lookup)(struct tty_driver *self, struct file *, int idx) + * Return the tty device corresponding to @idx, %NULL if there is not + * one currently in use and an %ERR_PTR value on error. Called under + * %tty_mutex (for now!) * - * Return the tty device corresponding to idx, NULL if there is not - * one currently in use and an ERR_PTR value on error. Called under - * tty_mutex (for now!) + * Optional method. Default behaviour is to use the @self->ttys array. * - * Optional method. Default behaviour is to use the ttys array + * @install: ``int ()(struct tty_driver *self, struct tty_struct *tty)`` * - * int (*install)(struct tty_driver *self, struct tty_struct *tty) + * Install a new @tty into the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. * - * Install a new tty into the tty driver internal tables. Used in - * conjunction with lookup and remove methods. + * Optional method. Default behaviour is to use the @self->ttys array. * - * Optional method. Default behaviour is to use the ttys array + * @remove: ``void ()(struct tty_driver *self, struct tty_struct *tty)`` * - * void (*remove)(struct tty_driver *self, struct tty_struct *tty) + * Remove a closed @tty from the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. * - * Remove a closed tty from the tty driver internal tables. Used in - * conjunction with lookup and remove methods. + * Optional method. Default behaviour is to use the @self->ttys array. * - * Optional method. Default behaviour is to use the ttys array + * @open: ``int ()(struct tty_struct *tty, struct file *)`` * - * int (*open)(struct tty_struct * tty, struct file * filp); + * This routine is called when a particular @tty device is opened. This + * routine is mandatory; if this routine is not filled in, the attempted + * open will fail with %ENODEV. * - * This routine is called when a particular tty device is opened. - * This routine is mandatory; if this routine is not filled in, - * the attempted open will fail with ENODEV. + * Required method. Called with tty lock held. May sleep. * - * Required method. Called with tty lock held. + * @close: ``void ()(struct tty_struct *tty, struct file *)`` * - * void (*close)(struct tty_struct * tty, struct file * filp); + * This routine is called when a particular @tty device is closed. At the + * point of return from this call the driver must make no further ldisc + * calls of any kind. * - * This routine is called when a particular tty device is closed. - * Note: called even if the corresponding open() failed. + * Remark: called even if the corresponding @open() failed. * - * Required method. Called with tty lock held. + * Required method. Called with tty lock held. May sleep. * - * void (*shutdown)(struct tty_struct * tty); + * @shutdown: ``void ()(struct tty_struct *tty)`` * - * This routine is called under the tty lock when a particular tty device - * is closed for the last time. It executes before the tty resources - * are freed so may execute while another function holds a tty kref. + * This routine is called under the tty lock when a particular @tty device + * is closed for the last time. It executes before the @tty resources + * are freed so may execute while another function holds a @tty kref. * - * void (*cleanup)(struct tty_struct * tty); + * @cleanup: ``void ()(struct tty_struct *tty)`` * - * This routine is called asynchronously when a particular tty device + * This routine is called asynchronously when a particular @tty device * is closed for the last time freeing up the resources. This is * actually the second part of shutdown for routines that might sleep. * + * @write: ``int ()(struct tty_struct *tty, const unsigned char *buf, + * int count)`` * - * int (*write)(struct tty_struct * tty, - * const unsigned char *buf, int count); - * - * This routine is called by the kernel to write a series of - * characters to the tty device. The characters may come from - * user space or kernel space. This routine will return the + * This routine is called by the kernel to write a series (@count) of + * characters (@buf) to the @tty device. The characters may come from + * user space or kernel space. This routine will return the * number of characters actually accepted for writing. * - * Optional: Required for writable devices. + * May occur in parallel in special cases. Because this includes panic + * paths drivers generally shouldn't try and do clever locking here. * - * int (*put_char)(struct tty_struct *tty, unsigned char ch); + * Optional: Required for writable devices. May not sleep. * - * This routine is called by the kernel to write a single - * character to the tty device. If the kernel uses this routine, - * it must call the flush_chars() routine (if defined) when it is - * done stuffing characters into the driver. If there is no room - * in the queue, the character is ignored. + * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)`` * - * Optional: Kernel will use the write method if not provided. + * This routine is called by the kernel to write a single character @ch to + * the @tty device. If the kernel uses this routine, it must call the + * @flush_chars() routine (if defined) when it is done stuffing characters + * into the driver. If there is no room in the queue, the character is + * ignored. * - * Note: Do not call this function directly, call tty_put_char + * Optional: Kernel will use the @write method if not provided. Do not + * call this function directly, call tty_put_char(). * - * void (*flush_chars)(struct tty_struct *tty); + * @flush_chars: ``void ()(struct tty_struct *tty)`` * - * This routine is called by the kernel after it has written a - * series of characters to the tty device using put_char(). + * This routine is called by the kernel after it has written a + * series of characters to the tty device using @put_char(). * - * Optional: + * Optional. Do not call this function directly, call + * tty_driver_flush_chars(). * - * Note: Do not call this function directly, call tty_driver_flush_chars - * - * unsigned int (*write_room)(struct tty_struct *tty); + * @write_room: ``unsigned int ()(struct tty_struct *tty)`` * - * This routine returns the numbers of characters the tty driver - * will accept for queuing to be written. This number is subject - * to change as output buffers get emptied, or if the output flow + * This routine returns the numbers of characters the @tty driver + * will accept for queuing to be written. This number is subject + * to change as output buffers get emptied, or if the output flow * control is acted. * - * Required if write method is provided else not needed. + * The ldisc is responsible for being intelligent about multi-threading of + * write_room/write calls + * + * Required if @write method is provided else not needed. Do not call this + * function directly, call tty_write_room() + * + * @chars_in_buffer: ``unsigned int ()(struct tty_struct *tty)`` + * + * This routine returns the number of characters in the device private + * output queue. Used in tty_wait_until_sent() and for poll() + * implementation. * - * Note: Do not call this function directly, call tty_write_room - * - * int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call tty_chars_in_buffer(). * - * This routine allows the tty driver to implement - * device-specific ioctls. If the ioctl number passed in cmd - * is not recognized by the driver, it should return ENOIOCTLCMD. + * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` * - * Optional + * This routine allows the @tty driver to implement device-specific + * ioctls. If the ioctl number passed in @cmd is not recognized by the + * driver, it should return %ENOIOCTLCMD. * - * long (*compat_ioctl)(struct tty_struct *tty,, - * unsigned int cmd, unsigned long arg); + * Optional. * - * implement ioctl processing for 32 bit process on 64 bit system + * @compat_ioctl: ``long ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` * - * Optional - * - * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); + * Implement ioctl processing for 32 bit process on 64 bit system. * - * This routine allows the tty driver to be notified when - * device's termios settings have changed. + * Optional. * - * Optional: Called under the termios lock + * @set_termios: ``void ()(struct tty_struct *tty, struct ktermios *old)`` * + * This routine allows the @tty driver to be notified when device's + * termios settings have changed. New settings are in @tty->termios. + * Previous settings are passed in the @old argument. * - * void (*set_ldisc)(struct tty_struct *tty); + * The API is defined such that the driver should return the actual modes + * selected. This means that the driver is responsible for modifying any + * bits in @tty->termios it cannot fulfill to indicate the actual modes + * being used. * - * This routine allows the tty driver to be notified when the - * device's termios settings have changed. + * Optional. Called under the @tty->termios_rwsem. May sleep. * - * Optional: Called under BKL (currently) - * - * void (*throttle)(struct tty_struct * tty); + * @set_ldisc: ``void ()(struct tty_struct *tty)`` * - * This routine notifies the tty driver that input buffers for - * the line discipline are close to full, and it should somehow - * signal that no more characters should be sent to the tty. + * This routine allows the @tty driver to be notified when the device's + * line discipline is being changed. At the point this is done the + * discipline is not yet usable. * - * Optional: Always invoke via tty_throttle_safe(), called under the - * termios lock. - * - * void (*unthrottle)(struct tty_struct * tty); + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. * - * This routine notifies the tty drivers that it should signals - * that characters can now be sent to the tty without fear of - * overrunning the input buffers of the line disciplines. - * - * Optional: Always invoke via tty_unthrottle(), called under the - * termios lock. + * @throttle: ``void ()(struct tty_struct *tty)`` * - * void (*stop)(struct tty_struct *tty); + * This routine notifies the @tty driver that input buffers for the line + * discipline are close to full, and it should somehow signal that no more + * characters should be sent to the @tty. * - * This routine notifies the tty driver that it should stop - * outputting characters to the tty device. + * Serialization including with @unthrottle() is the job of the ldisc + * layer. * - * Called with ->flow.lock held. Serialized with start() method. + * Optional: Always invoke via tty_throttle_safe(). Called under the + * @tty->termios_rwsem. * - * Optional: + * @unthrottle: ``void ()(struct tty_struct *tty)`` * - * Note: Call stop_tty not this method. - * - * void (*start)(struct tty_struct *tty); + * This routine notifies the @tty driver that it should signal that + * characters can now be sent to the @tty without fear of overrunning the + * input buffers of the line disciplines. * - * This routine notifies the tty driver that it resume sending + * Optional. Always invoke via tty_unthrottle(). Called under the + * @tty->termios_rwsem. + * + * @stop: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should stop outputting * characters to the tty device. * - * Called with ->flow.lock held. Serialized with stop() method. + * Called with @tty->flow.lock held. Serialized with @start() method. + * + * Optional. Always invoke via stop_tty(). + * + * @start: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it resumed sending + * characters to the @tty device. + * + * Called with @tty->flow.lock held. Serialized with stop() method. + * + * Optional. Always invoke via start_tty(). + * + * @hangup: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should hang up the @tty + * device. * - * Optional: + * Optional. Called with tty lock held. * - * Note: Call start_tty not this method. - * - * void (*hangup)(struct tty_struct *tty); + * @break_ctl: ``int ()(struct tty_struct *tty, int state)`` * - * This routine notifies the tty driver that it should hang up the - * tty device. + * This optional routine requests the @tty driver to turn on or off BREAK + * status on the RS-232 port. If @state is -1, then the BREAK status + * should be turned on; if @state is 0, then BREAK should be turned off. * - * Optional: + * If this routine is implemented, the high-level tty driver will handle + * the following ioctls: %TCSBRK, %TCSBRKP, %TIOCSBRK, %TIOCCBRK. * - * Called with tty lock held. + * If the driver sets %TTY_DRIVER_HARDWARE_BREAK in tty_alloc_driver(), + * then the interface will also be called with actual times and the + * hardware is expected to do the delay work itself. 0 and -1 are still + * used for on/off. * - * int (*break_ctl)(struct tty_struct *tty, int state); + * Optional: Required for %TCSBRK/%BRKP/etc. handling. May sleep. * - * This optional routine requests the tty driver to turn on or - * off BREAK status on the RS-232 port. If state is -1, - * then the BREAK status should be turned on; if state is 0, then - * BREAK should be turned off. + * @flush_buffer: ``void ()(struct tty_struct *tty)`` * - * If this routine is implemented, the high-level tty driver will - * handle the following ioctls: TCSBRK, TCSBRKP, TIOCSBRK, - * TIOCCBRK. + * This routine discards device private output buffer. Invoked on close, + * hangup, to implement %TCOFLUSH ioctl and similar. * - * If the driver sets TTY_DRIVER_HARDWARE_BREAK then the interface - * will also be called with actual times and the hardware is expected - * to do the delay work itself. 0 and -1 are still used for on/off. + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call + * tty_driver_flush_buffer(). * - * Optional: Required for TCSBRK/BRKP/etc handling. + * @wait_until_sent: ``void ()(struct tty_struct *tty, int timeout)`` * - * void (*wait_until_sent)(struct tty_struct *tty, int timeout); - * - * This routine waits until the device has written out all of the - * characters in its transmitter FIFO. + * This routine waits until the device has written out all of the + * characters in its transmitter FIFO. Or until @timeout (in jiffies) is + * reached. * - * Optional: If not provided the device is assumed to have no FIFO + * Optional: If not provided, the device is assumed to have no FIFO. + * Usually correct to invoke via tty_wait_until_sent(). May sleep. * - * Note: Usually correct to call tty_wait_until_sent + * @send_xchar: ``void ()(struct tty_struct *tty, char ch)`` * - * void (*send_xchar)(struct tty_struct *tty, char ch); + * This routine is used to send a high-priority XON/XOFF character (@ch) + * to the @tty device. * - * This routine is used to send a high-priority XON/XOFF - * character to the device. + * Optional: If not provided, then the @write method is called under + * the @tty->atomic_write_lock to keep it serialized with the ldisc. * - * Optional: If not provided then the write method is called under - * the atomic write lock to keep it serialized with the ldisc. + * @tiocmget: ``int ()(struct tty_struct *tty)`` * - * int (*resize)(struct tty_struct *tty, struct winsize *ws) + * This routine is used to obtain the modem status bits from the @tty + * driver. * - * Called when a termios request is issued which changes the - * requested terminal geometry. + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMGET + * ioctl. Do not call this function directly, call tty_tiocmget(). + * + * @tiocmset: ``int ()(struct tty_struct *tty, + * unsigned int set, unsigned int clear)`` + * + * This routine is used to set the modem status bits to the @tty driver. + * First, @clear bits should be cleared, then @set bits set. + * + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMSET + * ioctl. Do not call this function directly, call tty_tiocmset(). + * + * @resize: ``int ()(struct tty_struct *tty, struct winsize *ws)`` + * + * Called when a termios request is issued which changes the requested + * terminal geometry to @ws. * * Optional: the default action is to update the termios structure * without error. This is usually the correct behaviour. Drivers should - * not force errors here if they are not resizable objects (eg a serial + * not force errors here if they are not resizable objects (e.g. a serial * line). See tty_do_resize() if you need to wrap the standard method - * in your own logic - the usual case. + * in your own logic -- the usual case. + * + * @get_icount: ``int ()(struct tty_struct *tty, + * struct serial_icounter *icount)`` + * + * Called when the @tty device receives a %TIOCGICOUNT ioctl. Passed a + * kernel structure @icount to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. * - * int (*get_icount)(struct tty_struct *tty, struct serial_icounter *icount); + * @get_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` * - * Called when the device receives a TIOCGICOUNT ioctl. Passed a kernel - * structure to complete. This method is optional and will only be called - * if provided (otherwise ENOTTY will be returned). + * Called when the @tty device receives a %TIOCGSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocgserial(). + * + * @set_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` + * + * Called when the @tty device receives a %TIOCSSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to set the values from. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocsserial(). + * + * @show_fdinfo: ``void ()(struct tty_struct *tty, struct seq_file *m)`` + * + * Called when the @tty device file descriptor receives a fdinfo request + * from VFS (to show in /proc/<pid>/fdinfo/). @m should be filled with + * information. + * + * Optional: called only if provided, otherwise nothing is written to @m. + * Do not call this function directly, call tty_show_fdinfo(). + * + * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` + * + * kgdboc support (Documentation/dev-tools/kgdb.rst). This routine is + * called to initialize the HW for later use by calling @poll_get_char or + * @poll_put_char. + * + * Optional: called only if provided, otherwise skipped as a non-polling + * driver. + * + * @poll_get_char: ``int ()(struct tty_driver *driver, int line)`` + * + * kgdboc support (see @poll_init). @driver should read a character from a + * tty identified by @line and return it. + * + * Optional: called only if @poll_init provided. + * + * @poll_put_char: ``void ()(struct tty_driver *driver, int line, char ch)`` + * + * kgdboc support (see @poll_init). @driver should write character @ch to + * a tty identified by @line. + * + * Optional: called only if @poll_init provided. + * + * @proc_show: ``int ()(struct seq_file *m, void *driver)`` + * + * Driver @driver (cast to &struct tty_driver) can show additional info in + * /proc/tty/driver/<driver_name>. It is enough to fill in the information + * into @m. + * + * Optional: called only if provided, otherwise no /proc entry created. + * + * This structure defines the interface between the low-level tty driver and + * the tty routines. These routines can be defined. Unless noted otherwise, + * they are optional, and can be filled in with a %NULL pointer. */ - -#include <linux/export.h> -#include <linux/fs.h> -#include <linux/kref.h> -#include <linux/list.h> -#include <linux/cdev.h> -#include <linux/termios.h> -#include <linux/seq_file.h> - -struct tty_struct; -struct tty_driver; -struct serial_icounter_struct; -struct serial_struct; - struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, struct file *filp, int idx); @@ -288,26 +390,64 @@ struct tty_operations { int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif - int (*proc_show)(struct seq_file *, void *); + int (*proc_show)(struct seq_file *m, void *driver); } __randomize_layout; +/** + * struct tty_driver -- driver for TTY devices + * + * @magic: set to %TTY_DRIVER_MAGIC in __tty_alloc_driver() + * @kref: reference counting. Reaching zero frees all the internals and the + * driver. + * @cdevs: allocated/registered character /dev devices + * @owner: modules owning this driver. Used drivers cannot be rmmod'ed. + * Automatically set by tty_alloc_driver(). + * @driver_name: name of the driver used in /proc/tty + * @name: used for constructing /dev node name + * @name_base: used as a number base for constructing /dev node name + * @major: major /dev device number (zero for autoassignment) + * @minor_start: the first minor /dev device number + * @num: number of devices allocated + * @type: type of tty driver (%TTY_DRIVER_TYPE_) + * @subtype: subtype of tty driver (%SYSTEM_TYPE_, %PTY_TYPE_, %SERIAL_TYPE_) + * @init_termios: termios to set to each tty initially (e.g. %tty_std_termios) + * @flags: tty driver flags (%TTY_DRIVER_) + * @proc_entry: proc fs entry, used internally + * @other: driver of the linked tty; only used for the PTY driver + * @ttys: array of active &struct tty_struct, set by tty_standard_install() + * @ports: array of &struct tty_port; can be set during initialization by + * tty_port_link_device() and similar + * @termios: storage for termios at each TTY close for the next open + * @driver_state: pointer to driver's arbitrary data + * @ops: driver hooks for TTYs. Set them using tty_set_operations(). Use &struct + * tty_port helpers in them as much as possible. + * @tty_drivers: used internally to link tty_drivers together + * + * The usual handling of &struct tty_driver is to allocate it by + * tty_alloc_driver(), set up all the necessary members, and register it by + * tty_register_driver(). At last, the driver is torn down by calling + * tty_unregister_driver() followed by tty_driver_kref_put(). + * + * The fields required to be set before calling tty_register_driver() include + * @driver_name, @name, @type, @subtype, @init_termios, and @ops. + */ struct tty_driver { - int magic; /* magic number for this structure */ - struct kref kref; /* Reference management */ + int magic; + struct kref kref; struct cdev **cdevs; struct module *owner; const char *driver_name; const char *name; - int name_base; /* offset of printed name */ - int major; /* major device number */ - int minor_start; /* start of minor device number */ - unsigned int num; /* number of devices allocated */ - short type; /* type of tty driver */ - short subtype; /* subtype of tty driver */ - struct ktermios init_termios; /* Initial termios */ - unsigned long flags; /* tty driver flags */ - struct proc_dir_entry *proc_entry; /* /proc fs entry */ - struct tty_driver *other; /* only used for the PTY driver */ + int name_base; + int major; + int minor_start; + unsigned int num; + short type; + short subtype; + struct ktermios init_termios; + unsigned long flags; + struct proc_dir_entry *proc_entry; + struct tty_driver *other; /* * Pointer to the tty data structures @@ -352,49 +492,53 @@ static inline void tty_set_operations(struct tty_driver *driver, /* tty driver magic number */ #define TTY_DRIVER_MAGIC 0x5402 -/* - * tty driver flags - * - * TTY_DRIVER_RESET_TERMIOS --- requests the tty layer to reset the - * termios setting when the last process has closed the device. - * Used for PTY's, in particular. - * - * TTY_DRIVER_REAL_RAW --- if set, indicates that the driver will - * guarantee never to set any special character handling - * flags if ((IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || - * !INPCK)). That is, if there is no reason for the driver to - * send notifications of parity and break characters up to the - * line driver, it won't do so. This allows the line driver to - * optimize for this case if this flag is set. (Note that there - * is also a promise, if the above case is true, not to signal - * overruns, either.) - * - * TTY_DRIVER_DYNAMIC_DEV --- if set, the individual tty devices need - * to be registered with a call to tty_register_device() when the - * device is found in the system and unregistered with a call to - * tty_unregister_device() so the devices will be show up - * properly in sysfs. If not set, driver->num entries will be - * created by the tty core in sysfs when tty_register_driver() is - * called. This is to be used by drivers that have tty devices - * that can appear and disappear while the main tty driver is - * registered with the tty core. - * - * TTY_DRIVER_DEVPTS_MEM -- don't use the standard arrays, instead - * use dynamic memory keyed through the devpts filesystem. This - * is only applicable to the pty driver. - * - * TTY_DRIVER_HARDWARE_BREAK -- hardware handles break signals. Pass - * the requested timeout to the caller instead of using a simple - * on/off interface. - * - * TTY_DRIVER_DYNAMIC_ALLOC -- do not allocate structures which are - * needed per line for this driver as it would waste memory. - * The driver will take care. - * - * TTY_DRIVER_UNNUMBERED_NODE -- do not create numbered /dev nodes. In - * other words create /dev/ttyprintk and not /dev/ttyprintk0. - * Applicable only when a driver for a single tty device is - * being allocated. +/** + * DOC: TTY Driver Flags + * + * TTY_DRIVER_RESET_TERMIOS + * Requests the tty layer to reset the termios setting when the last + * process has closed the device. Used for PTYs, in particular. + * + * TTY_DRIVER_REAL_RAW + * Indicates that the driver will guarantee not to set any special + * character handling flags if this is set for the tty: + * + * ``(IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || !INPCK)`` + * + * That is, if there is no reason for the driver to + * send notifications of parity and break characters up to the line + * driver, it won't do so. This allows the line driver to optimize for + * this case if this flag is set. (Note that there is also a promise, if + * the above case is true, not to signal overruns, either.) + * + * TTY_DRIVER_DYNAMIC_DEV + * The individual tty devices need to be registered with a call to + * tty_register_device() when the device is found in the system and + * unregistered with a call to tty_unregister_device() so the devices will + * be show up properly in sysfs. If not set, all &tty_driver.num entries + * will be created by the tty core in sysfs when tty_register_driver() is + * called. This is to be used by drivers that have tty devices that can + * appear and disappear while the main tty driver is registered with the + * tty core. + * + * TTY_DRIVER_DEVPTS_MEM + * Don't use the standard arrays (&tty_driver.ttys and + * &tty_driver.termios), instead use dynamic memory keyed through the + * devpts filesystem. This is only applicable to the PTY driver. + * + * TTY_DRIVER_HARDWARE_BREAK + * Hardware handles break signals. Pass the requested timeout to the + * &tty_operations.break_ctl instead of using a simple on/off interface. + * + * TTY_DRIVER_DYNAMIC_ALLOC + * Do not allocate structures which are needed per line for this driver + * (&tty_driver.ports) as it would waste memory. The driver will take + * care. This is only applicable to the PTY driver. + * + * TTY_DRIVER_UNNUMBERED_NODE + * Do not create numbered ``/dev`` nodes. For example, create + * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a + * driver for a single tty device is being allocated. */ #define TTY_DRIVER_INSTALLED 0x0001 #define TTY_DRIVER_RESET_TERMIOS 0x0002 diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 9916acb5de49..483d41cbcbb7 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -17,7 +17,6 @@ int tty_insert_flip_string_fixed_flag(struct tty_port *port, int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); void tty_flip_buffer_push(struct tty_port *port); -void tty_schedule_flip(struct tty_port *port); int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index b85d84fb5f49..e85002b56752 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -4,127 +4,6 @@ struct tty_struct; -/* - * This structure defines the interface between the tty line discipline - * implementation and the tty routines. The following routines can be - * defined; unless noted otherwise, they are optional, and can be - * filled in with a null pointer. - * - * int (*open)(struct tty_struct *); - * - * This function is called when the line discipline is associated - * with the tty. The line discipline can use this as an - * opportunity to initialize any state needed by the ldisc routines. - * - * void (*close)(struct tty_struct *); - * - * This function is called when the line discipline is being - * shutdown, either because the tty is being closed or because - * the tty is being changed to use a new line discipline - * - * void (*flush_buffer)(struct tty_struct *tty); - * - * This function instructs the line discipline to clear its - * buffers of any input characters it may have queued to be - * delivered to the user mode process. - * - * ssize_t (*read)(struct tty_struct * tty, struct file * file, - * unsigned char * buf, size_t nr); - * - * This function is called when the user requests to read from - * the tty. The line discipline will return whatever characters - * it has buffered up for the user. If this function is not - * defined, the user will receive an EIO error. - * - * ssize_t (*write)(struct tty_struct * tty, struct file * file, - * const unsigned char * buf, size_t nr); - * - * This function is called when the user requests to write to the - * tty. The line discipline will deliver the characters to the - * low-level tty device for transmission, optionally performing - * some processing on the characters first. If this function is - * not defined, the user will receive an EIO error. - * - * int (*ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); - * - * This function is called when the user requests an ioctl which - * is not handled by the tty layer or the low-level tty driver. - * It is intended for ioctls which affect line discpline - * operation. Note that the search order for ioctls is (1) tty - * layer, (2) tty low-level driver, (3) line discpline. So a - * low-level driver can "grab" an ioctl request before the line - * discpline has a chance to see it. - * - * int (*compat_ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); - * - * Process ioctl calls from 32-bit process on 64-bit system - * - * NOTE: only ioctls that are neither "pointer to compatible - * structure" nor tty-generic. Something private that takes - * an integer or a pointer to wordsize-sensitive structure - * belongs here, but most of ldiscs will happily leave - * it NULL. - * - * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); - * - * This function notifies the line discpline that a change has - * been made to the termios structure. - * - * int (*poll)(struct tty_struct * tty, struct file * file, - * poll_table *wait); - * - * This function is called when a user attempts to select/poll on a - * tty device. It is solely the responsibility of the line - * discipline to handle poll requests. - * - * void (*receive_buf)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. <cp> is a pointer to the buffer of input - * character received by the device. <fp> is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. <fp> may be NULL to indicate - * all data received is TTY_NORMAL. - * - * void (*write_wakeup)(struct tty_struct *); - * - * This function is called by the low-level tty driver to signal - * that line discpline should try to send more characters to the - * low-level driver for transmission. If the line discpline does - * not have any more data to send, it can just return. If the line - * discipline does have some data to send, please arise a tasklet - * or workqueue to do the real data transfer. Do not send data in - * this hook, it may leads to a deadlock. - * - * int (*hangup)(struct tty_struct *) - * - * Called on a hangup. Tells the discipline that it should - * cease I/O to the tty driver. Can sleep. The driver should - * seek to perform this action quickly but should wait until - * any pending driver I/O is completed. - * - * void (*dcd_change)(struct tty_struct *tty, unsigned int status) - * - * Tells the discipline that the DCD pin has changed its status. - * Used exclusively by the N_PPS (Pulse-Per-Second) line discipline. - * - * int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. <cp> is a pointer to the buffer of input - * character received by the device. <fp> is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. <fp> may be NULL to indicate - * all data received is TTY_NORMAL. - * If assigned, prefer this function for automatic flow control. - */ - #include <linux/fs.h> #include <linux/wait.h> #include <linux/atomic.h> @@ -176,7 +55,147 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, ldsem_down_write(sem, timeout) #endif - +/** + * struct tty_ldisc_ops - ldisc operations + * + * @name: name of this ldisc rendered in /proc/tty/ldiscs + * @num: ``N_*`` number (%N_TTY, %N_HDLC, ...) reserved to this ldisc + * + * @open: [TTY] ``int ()(struct tty_struct *tty)`` + * + * This function is called when the line discipline is associated with the + * @tty. No other call into the line discipline for this tty will occur + * until it completes successfully. It should initialize any state needed + * by the ldisc, and set @tty->receive_room to the maximum amount of data + * the line discipline is willing to accept from the driver with a single + * call to @receive_buf(). Returning an error will prevent the ldisc from + * being attached. + * + * Can sleep. + * + * @close: [TTY] ``void ()(struct tty_struct *tty)`` + * + * This function is called when the line discipline is being shutdown, + * either because the @tty is being closed or because the @tty is being + * changed to use a new line discipline. At the point of execution no + * further users will enter the ldisc code for this tty. + * + * Can sleep. + * + * @flush_buffer: [TTY] ``void ()(struct tty_struct *tty)`` + * + * This function instructs the line discipline to clear its buffers of any + * input characters it may have queued to be delivered to the user mode + * process. It may be called at any point between open and close. + * + * @read: [TTY] ``ssize_t ()(struct tty_struct *tty, struct file *file, + * unsigned char *buf, size_t nr)`` + * + * This function is called when the user requests to read from the @tty. + * The line discipline will return whatever characters it has buffered up + * for the user. If this function is not defined, the user will receive + * an %EIO error. Multiple read calls may occur in parallel and the ldisc + * must deal with serialization issues. + * + * Can sleep. + * + * @write: [TTY] ``ssize_t ()(struct tty_struct *tty, struct file *file, + * const unsigned char *buf, size_t nr)`` + * + * This function is called when the user requests to write to the @tty. + * The line discipline will deliver the characters to the low-level tty + * device for transmission, optionally performing some processing on the + * characters first. If this function is not defined, the user will + * receive an %EIO error. + * + * Can sleep. + * + * @ioctl: [TTY] ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * This function is called when the user requests an ioctl which is not + * handled by the tty layer or the low-level tty driver. It is intended + * for ioctls which affect line discpline operation. Note that the search + * order for ioctls is (1) tty layer, (2) tty low-level driver, (3) line + * discpline. So a low-level driver can "grab" an ioctl request before + * the line discpline has a chance to see it. + * + * @compat_ioctl: [TTY] ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * Process ioctl calls from 32-bit process on 64-bit system. + * + * Note that only ioctls that are neither "pointer to compatible + * structure" nor tty-generic. Something private that takes an integer or + * a pointer to wordsize-sensitive structure belongs here, but most of + * ldiscs will happily leave it %NULL. + * + * @set_termios: [TTY] ``void ()(struct tty_struct *tty, struct ktermios *old)`` + * + * This function notifies the line discpline that a change has been made + * to the termios structure. + * + * @poll: [TTY] ``int ()(struct tty_struct *tty, struct file *file, + * struct poll_table_struct *wait)`` + * + * This function is called when a user attempts to select/poll on a @tty + * device. It is solely the responsibility of the line discipline to + * handle poll requests. + * + * @hangup: [TTY] ``void ()(struct tty_struct *tty)`` + * + * Called on a hangup. Tells the discipline that it should cease I/O to + * the tty driver. The driver should seek to perform this action quickly + * but should wait until any pending driver I/O is completed. No further + * calls into the ldisc code will occur. + * + * Can sleep. + * + * @receive_buf: [DRV] ``void ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` + * + * This function is called by the low-level tty driver to send characters + * received by the hardware to the line discpline for processing. @cp is + * a pointer to the buffer of input character received by the device. @fp + * is a pointer to an array of flag bytes which indicate whether a + * character was received with a parity error, etc. @fp may be %NULL to + * indicate all data received is %TTY_NORMAL. + * + * @write_wakeup: [DRV] ``void ()(struct tty_struct *tty)`` + * + * This function is called by the low-level tty driver to signal that line + * discpline should try to send more characters to the low-level driver + * for transmission. If the line discpline does not have any more data to + * send, it can just return. If the line discipline does have some data to + * send, please arise a tasklet or workqueue to do the real data transfer. + * Do not send data in this hook, it may lead to a deadlock. + * + * @dcd_change: [DRV] ``void ()(struct tty_struct *tty, unsigned int status)`` + * + * Tells the discipline that the DCD pin has changed its status. Used + * exclusively by the %N_PPS (Pulse-Per-Second) line discipline. + * + * @receive_buf2: [DRV] ``int ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` + * + * This function is called by the low-level tty driver to send characters + * received by the hardware to the line discpline for processing. @cp is a + * pointer to the buffer of input character received by the device. @fp + * is a pointer to an array of flag bytes which indicate whether a + * character was received with a parity error, etc. @fp may be %NULL to + * indicate all data received is %TTY_NORMAL. If assigned, prefer this + * function for automatic flow control. + * + * @owner: module containting this ldisc (for reference counting) + * + * This structure defines the interface between the tty line discipline + * implementation and the tty routines. The above routines can be defined. + * Unless noted otherwise, they are optional, and can be filled in with a %NULL + * pointer. + * + * Hooks marked [TTY] are invoked from the TTY core, the [DRV] ones from the + * tty_driver side. + */ struct tty_ldisc_ops { char *name; int num; @@ -184,31 +203,31 @@ struct tty_ldisc_ops { /* * The following routines are called from above. */ - int (*open)(struct tty_struct *); - void (*close)(struct tty_struct *); + int (*open)(struct tty_struct *tty); + void (*close)(struct tty_struct *tty); void (*flush_buffer)(struct tty_struct *tty); ssize_t (*read)(struct tty_struct *tty, struct file *file, unsigned char *buf, size_t nr, void **cookie, unsigned long offset); ssize_t (*write)(struct tty_struct *tty, struct file *file, const unsigned char *buf, size_t nr); - int (*ioctl)(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); - int (*compat_ioctl)(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); + int (*ioctl)(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); + int (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); void (*set_termios)(struct tty_struct *tty, struct ktermios *old); - __poll_t (*poll)(struct tty_struct *, struct file *, - struct poll_table_struct *); + __poll_t (*poll)(struct tty_struct *tty, struct file *file, + struct poll_table_struct *wait); void (*hangup)(struct tty_struct *tty); /* * The following routines are called from below. */ - void (*receive_buf)(struct tty_struct *, const unsigned char *cp, + void (*receive_buf)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); - void (*write_wakeup)(struct tty_struct *); - void (*dcd_change)(struct tty_struct *, unsigned int); - int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + void (*write_wakeup)(struct tty_struct *tty); + void (*dcd_change)(struct tty_struct *tty, unsigned int status); + int (*receive_buf2)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); struct module *owner; diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index 6e86e9e118b6..58e9619116b7 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -2,42 +2,39 @@ #ifndef _LINUX_TTY_PORT_H #define _LINUX_TTY_PORT_H +#include <linux/kfifo.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/tty_buffer.h> #include <linux/wait.h> -/* - * Port level information. Each device keeps its own port level information - * so provide a common structure for those ports wanting to use common support - * routines. - * - * The tty port has a different lifetime to the tty so must be kept apart. - * In addition be careful as tty -> port mappings are valid for the life - * of the tty object but in many cases port -> tty mappings are valid only - * until a hangup so don't use the wrong path. - */ - struct attribute_group; struct tty_driver; struct tty_port; struct tty_struct; +/** + * struct tty_port_operations -- operations on tty_port + * @carrier_raised: return 1 if the carrier is raised on @port + * @dtr_rts: raise the DTR line if @raise is nonzero, otherwise lower DTR + * @shutdown: called when the last close completes or a hangup finishes IFF the + * port was initialized. Do not use to free resources. Turn off the device + * only. Called under the port mutex to serialize against @activate and + * @shutdown. + * @activate: called under the port mutex from tty_port_open(), serialized using + * the port mutex. Supposed to turn on the device. + * + * FIXME: long term getting the tty argument *out* of this would be good + * for consoles. + * + * @destruct: called on the final put of a port. Free resources, possibly incl. + * the port itself. + */ struct tty_port_operations { - /* Return 1 if the carrier is raised */ int (*carrier_raised)(struct tty_port *port); - /* Control the DTR line */ void (*dtr_rts)(struct tty_port *port, int raise); - /* Called when the last close completes or a hangup finishes - IFF the port was initialized. Do not use to free resources. Called - under the port mutex to serialize against activate/shutdowns */ void (*shutdown)(struct tty_port *port); - /* Called under the port mutex from tty_port_open, serialized using - the port mutex */ - /* FIXME: long term getting the tty argument *out* of this would be - good for consoles */ int (*activate)(struct tty_port *port, struct tty_struct *tty); - /* Called on the final put of a port */ void (*destruct)(struct tty_port *port); }; @@ -48,30 +45,79 @@ struct tty_port_client_operations { extern const struct tty_port_client_operations tty_port_default_client_ops; +/** + * struct tty_port -- port level information + * + * @buf: buffer for this port, locked internally + * @tty: back pointer to &struct tty_struct, valid only if the tty is open. Use + * tty_port_tty_get() to obtain it (and tty_kref_put() to release). + * @itty: internal back pointer to &struct tty_struct. Avoid this. It should be + * eliminated in the long term. + * @ops: tty port operations (like activate, shutdown), see &struct + * tty_port_operations + * @client_ops: tty port client operations (like receive_buf, write_wakeup). + * By default, tty_port_default_client_ops is used. + * @lock: lock protecting @tty + * @blocked_open: # of procs waiting for open in tty_port_block_til_ready() + * @count: usage count + * @open_wait: open waiters queue (waiting e.g. for a carrier) + * @delta_msr_wait: modem status change queue (waiting for MSR changes) + * @flags: user TTY flags (%ASYNC_) + * @iflags: internal flags (%TTY_PORT_) + * @console: when set, the port is a console + * @mutex: locking, for open, shutdown and other port operations + * @buf_mutex: @xmit_buf alloc lock + * @xmit_buf: optional xmit buffer used by some drivers + * @xmit_fifo: optional xmit buffer used by some drivers + * @close_delay: delay in jiffies to wait when closing the port + * @closing_wait: delay in jiffies for output to be sent before closing + * @drain_delay: set to zero if no pure time based drain is needed else set to + * size of fifo + * @kref: references counter. Reaching zero calls @ops->destruct() if non-%NULL + * or frees the port otherwise. + * @client_data: pointer to private data, for @client_ops + * + * Each device keeps its own port level information. &struct tty_port was + * introduced as a common structure for such information. As every TTY device + * shall have a backing tty_port structure, every driver can use these members. + * + * The tty port has a different lifetime to the tty so must be kept apart. + * In addition be careful as tty -> port mappings are valid for the life + * of the tty object but in many cases port -> tty mappings are valid only + * until a hangup so don't use the wrong path. + * + * Tty port shall be initialized by tty_port_init() and shut down either by + * tty_port_destroy() (refcounting not used), or tty_port_put() (refcounting). + * + * There is a lot of helpers around &struct tty_port too. To name the most + * significant ones: tty_port_open(), tty_port_close() (or + * tty_port_close_start() and tty_port_close_end() separately if need be), and + * tty_port_hangup(). These call @ops->activate() and @ops->shutdown() as + * needed. + */ struct tty_port { - struct tty_bufhead buf; /* Locked internally */ - struct tty_struct *tty; /* Back pointer */ - struct tty_struct *itty; /* internal back ptr */ - const struct tty_port_operations *ops; /* Port operations */ - const struct tty_port_client_operations *client_ops; /* Port client operations */ - spinlock_t lock; /* Lock protecting tty field */ - int blocked_open; /* Waiting to open */ - int count; /* Usage count */ - wait_queue_head_t open_wait; /* Open waiters */ - wait_queue_head_t delta_msr_wait; /* Modem status change */ - unsigned long flags; /* User TTY flags ASYNC_ */ - unsigned long iflags; /* Internal flags TTY_PORT_ */ - unsigned char console:1; /* port is a console */ - struct mutex mutex; /* Locking */ - struct mutex buf_mutex; /* Buffer alloc lock */ - unsigned char *xmit_buf; /* Optional buffer */ - unsigned int close_delay; /* Close port delay */ - unsigned int closing_wait; /* Delay for output */ - int drain_delay; /* Set to zero if no pure time - based drain is needed else - set to size of fifo */ - struct kref kref; /* Ref counter */ - void *client_data; + struct tty_bufhead buf; + struct tty_struct *tty; + struct tty_struct *itty; + const struct tty_port_operations *ops; + const struct tty_port_client_operations *client_ops; + spinlock_t lock; + int blocked_open; + int count; + wait_queue_head_t open_wait; + wait_queue_head_t delta_msr_wait; + unsigned long flags; + unsigned long iflags; + unsigned char console:1; + struct mutex mutex; + struct mutex buf_mutex; + unsigned char *xmit_buf; + DECLARE_KFIFO_PTR(xmit_fifo, unsigned char); + unsigned int close_delay; + unsigned int closing_wait; + int drain_delay; + struct kref kref; + void *client_data; }; /* tty_port::iflags bits -- use atomic bit ops */ diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..ea8cf60a8a79 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -226,6 +226,7 @@ struct callback_head { typedef void (*rcu_callback_t)(struct rcu_head *head); typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); +typedef void (*swap_r_func_t)(void *a, void *b, int size, const void *priv); typedef void (*swap_func_t)(void *a, void *b, int size); typedef int (*cmp_r_func_t)(const void *a, const void *b, const void *priv); diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e8ec116c916b..6ad4e9032d53 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -66,7 +66,7 @@ #include <linux/seqlock.h> struct u64_stats_sync { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) seqcount_t seq; #endif }; @@ -125,7 +125,7 @@ static inline void u64_stats_inc(u64_stats_t *p) } #endif -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) #define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) #else static inline void u64_stats_init(struct u64_stats_sync *syncp) @@ -135,15 +135,19 @@ static inline void u64_stats_init(struct u64_stats_sync *syncp) static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); write_seqcount_begin(&syncp->seq); #endif } static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); #endif } @@ -152,8 +156,11 @@ u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) { unsigned long flags = 0; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - local_irq_save(flags); +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_irq_save(flags); write_seqcount_begin(&syncp->seq); #endif return flags; @@ -163,15 +170,18 @@ static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, unsigned long flags) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - local_irq_restore(flags); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_irq_restore(flags); #endif } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); #else return 0; @@ -180,7 +190,7 @@ static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync * static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -189,7 +199,7 @@ static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *sy static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_retry(&syncp->seq, start); #else return false; @@ -199,7 +209,7 @@ static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_enable(); #endif return __u64_stats_fetch_retry(syncp, start); @@ -213,7 +223,9 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_disable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -222,7 +234,9 @@ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_enable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_enable(); #endif return __u64_stats_fetch_retry(syncp, start); diff --git a/include/linux/u64_stats_sync_api.h b/include/linux/u64_stats_sync_api.h new file mode 100644 index 000000000000..c72ca63da44b --- /dev/null +++ b/include/linux/u64_stats_sync_api.h @@ -0,0 +1 @@ +#include <linux/u64_stats_sync.h> diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ac0394087f7d..546179418ffa 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -10,46 +10,6 @@ #include <asm/uaccess.h> -#ifdef CONFIG_SET_FS -/* - * Force the uaccess routines to be wired up for actual userspace access, - * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone - * using force_uaccess_end below. - */ -static inline mm_segment_t force_uaccess_begin(void) -{ - mm_segment_t fs = get_fs(); - - set_fs(USER_DS); - return fs; -} - -static inline void force_uaccess_end(mm_segment_t oldfs) -{ - set_fs(oldfs); -} -#else /* CONFIG_SET_FS */ -typedef struct { - /* empty dummy */ -} mm_segment_t; - -#ifndef TASK_SIZE_MAX -#define TASK_SIZE_MAX TASK_SIZE -#endif - -#define uaccess_kernel() (false) -#define user_addr_max() (TASK_SIZE_MAX) - -static inline mm_segment_t force_uaccess_begin(void) -{ - return (mm_segment_t) { }; -} - -static inline void force_uaccess_end(mm_segment_t oldfs) -{ -} -#endif /* CONFIG_SET_FS */ - /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and @@ -368,6 +328,25 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); +#ifndef __get_kernel_nofault +#define __get_kernel_nofault(dst, src, type, label) \ +do { \ + type __user *p = (type __force __user *)(src); \ + type data; \ + if (__get_user(data, p)) \ + goto label; \ + *(type *)dst = data; \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, label) \ +do { \ + type __user *p = (type __force __user *)(dst); \ + type data = *(type *)src; \ + if (__put_user(data, p)) \ + goto label; \ +} while (0) +#endif + /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable @@ -401,8 +380,6 @@ static inline void user_access_restore(unsigned long flags) { } #endif #ifdef CONFIG_HARDENED_USERCOPY -void usercopy_warn(const char *name, const char *detail, bool to_user, - unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); diff --git a/include/linux/udp.h b/include/linux/udp.h index ae66dadd8543..254a2654400f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,11 +23,6 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } -static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) -{ - return (struct udphdr *)skb_inner_transport_header(skb); -} - #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) diff --git a/include/linux/uio.h b/include/linux/uio.h index 6350354f97e9..739285fe5a2f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/thread_info.h> +#include <linux/mm_types.h> #include <uapi/linux/uio.h> struct page; @@ -146,6 +147,12 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) +{ + return copy_page_to_iter(&folio->page, offset, bytes, i); +} + static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { @@ -196,7 +203,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of - * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for + * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ @@ -211,24 +218,6 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #define _copy_mc_to_iter _copy_to_iter #endif -static __always_inline __must_check -size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, false))) - return 0; - else - return _copy_from_iter_flushcache(addr, bytes, i); -} - -static __always_inline __must_check -size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, true))) - return 0; - else - return _copy_mc_to_iter(addr, bytes, i); -} - size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); @@ -284,6 +273,23 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) i->count = count; } +static inline int +iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) +{ + size_t shorted = 0; + int npages; + + if (iov_iter_count(i) > max_bytes) { + shorted = iov_iter_count(i) - max_bytes; + iov_iter_truncate(i, max_bytes); + } + npages = iov_iter_npages(i, INT_MAX); + if (shorted) + iov_iter_reexpand(i, iov_iter_count(i) + shorted); + + return npages; +} + struct csum_state { __wsum csum; size_t off; diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index c0d817de4df2..f4c8eaf4d012 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H -#include <linux/kernel.h> +#include <linux/types.h> struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 74484d44c755..4d39e6e11a95 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -5,9 +5,52 @@ #include <linux/init.h> #include <linux/dcache.h> +struct utf8data; +struct utf8data_table; + +#define UNICODE_MAJ_SHIFT 16 +#define UNICODE_MIN_SHIFT 8 + +#define UNICODE_AGE(MAJ, MIN, REV) \ + (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \ + ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ + ((unsigned int)(REV))) + +static inline u8 unicode_major(unsigned int age) +{ + return (age >> UNICODE_MAJ_SHIFT) & 0xff; +} + +static inline u8 unicode_minor(unsigned int age) +{ + return (age >> UNICODE_MIN_SHIFT) & 0xff; +} + +static inline u8 unicode_rev(unsigned int age) +{ + return age & 0xff; +} + +/* + * Two normalization forms are supported: + * 1) NFDI + * - Apply unicode normalization form NFD. + * - Remove any Default_Ignorable_Code_Point. + * 2) NFDICF + * - Apply unicode normalization form NFD. + * - Remove any Default_Ignorable_Code_Point. + * - Apply a full casefold (C + F). + */ +enum utf8_normalization { + UTF8_NFDI = 0, + UTF8_NFDICF, + UTF8_NMAX, +}; + struct unicode_map { - const char *charset; - int version; + unsigned int version; + const struct utf8data *ntab[UTF8_NMAX]; + const struct utf8data_table *tables; }; int utf8_validate(const struct unicode_map *um, const struct qstr *str); @@ -30,7 +73,7 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str, int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct qstr *str); -struct unicode_map *utf8_load(const char *version); +struct unicode_map *utf8_load(unsigned int version); void utf8_unload(struct unicode_map *um); #endif /* _LINUX_UNICODE_H */ diff --git a/include/linux/usb.h b/include/linux/usb.h index 7ccaa76a9a96..200b7b79acb5 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -875,15 +875,6 @@ extern struct usb_host_interface *usb_find_alt_setting( unsigned int iface_num, unsigned int alt_num); -#if IS_REACHABLE(CONFIG_USB) -int usb_for_each_port(void *data, int (*fn)(struct device *, void *)); -#else -static inline int usb_for_each_port(void *data, int (*fn)(struct device *, void *)) -{ - return 0; -} -#endif - /* port claiming functions */ int usb_hub_claim_port(struct usb_device *hdev, unsigned port1, struct usb_dev_state *owner); diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 1cffa34740b0..969e7dba6358 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -33,7 +33,6 @@ #ifndef __LINUX_USB_CH9_H #define __LINUX_USB_CH9_H -#include <linux/device.h> #include <uapi/linux/usb/ch9.h> /* USB 3.2 SuperSpeed Plus phy signaling rate generation and lane count */ @@ -45,6 +44,8 @@ enum usb_ssp_rate { USB_SSP_GEN_2x2, }; +struct device; + extern const char *usb_ep_type_string(int ep_type); extern const char *usb_speed_string(enum usb_device_speed speed); extern enum usb_device_speed usb_get_maximum_speed(struct device *dev); diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 031f148ab373..b5deafd91f67 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -92,6 +92,12 @@ fwnode_usb_role_switch_get(struct fwnode_handle *node) static inline void usb_role_switch_put(struct usb_role_switch *sw) { } static inline struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct usb_role_switch * usb_role_switch_register(struct device *parent, const struct usb_role_switch_desc *desc) { diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index e2e44bb1dad8..fdf737d48b3b 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -295,6 +295,9 @@ int typec_set_mode(struct typec_port *port, int mode); void *typec_get_drvdata(struct typec_port *port); +int typec_get_fw_cap(struct typec_capability *cap, + struct fwnode_handle *fwnode); + int typec_find_pwr_opmode(const char *name); int typec_find_orientation(const char *name); int typec_find_port_power_role(const char *name); @@ -305,16 +308,4 @@ void typec_partner_set_svdm_version(struct typec_partner *partner, enum usb_pd_svdm_ver svdm_version); int typec_get_negotiated_svdm_version(struct typec_port *port); -#if IS_REACHABLE(CONFIG_TYPEC) -int typec_link_port(struct device *port); -void typec_unlink_port(struct device *port); -#else -static inline int typec_link_port(struct device *port) -{ - return 0; -} - -static inline void typec_unlink_port(struct device *port) { } -#endif - #endif /* __LINUX_USB_TYPEC_H */ diff --git a/include/linux/usb/xhci-dbgp.h b/include/linux/usb/xhci-dbgp.h index 0a37f1283bf0..01fe768873f9 100644 --- a/include/linux/usb/xhci-dbgp.h +++ b/include/linux/usb/xhci-dbgp.h @@ -15,7 +15,7 @@ #define __LINUX_XHCI_DBGP_H #ifdef CONFIG_EARLY_PRINTK_USB_XDBC -int __init early_xdbc_parse_parameter(char *s); +int __init early_xdbc_parse_parameter(char *s, int keep_early); int __init early_xdbc_setup_hardware(void); void __init early_xdbc_register_console(void); #else diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index c3011ccda430..8943a209202e 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -64,6 +64,7 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA + * @driver_override: driver name to force a match * @config: the configuration ops for this device. * @cf_mutex: Protects get and set access to configuration layout. * @index: device index @@ -76,12 +77,13 @@ struct vdpa_mgmt_dev; struct vdpa_device { struct device dev; struct device *dma_dev; + const char *driver_override; const struct vdpa_config_ops *config; struct mutex cf_mutex; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; - int nvqs; + u32 nvqs; struct vdpa_mgmt_dev *mdev; }; @@ -99,6 +101,7 @@ struct vdpa_dev_set_config { struct { u8 mac[ETH_ALEN]; u16 mtu; + u16 max_vq_pairs; } net; u64 mask; }; @@ -155,7 +158,7 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) - * @get_vq_notification: Get the notification area for a virtqueue + * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area @@ -169,14 +172,17 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_features: Get virtio features supported by the device + * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the * device - * @set_features: Set virtio features supported by the driver + * @set_driver_features: Set virtio features supported by the driver * @vdev: vdpa device * @features: feature support by the driver * Returns integer: success (0) or error (< 0) + * @get_driver_features: Get the virtio driver features in action + * @vdev: vdpa device + * Returns the virtio features accepted * @set_config_cb: Set the config interrupt callback * @vdev: vdpa device * @cb: virtio-vdev interrupt callback structure @@ -201,7 +207,8 @@ struct vdpa_map_file { * @reset: Reset device * @vdev: vdpa device * Returns integer: success (0) or error (< 0) - * @get_config_size: Get the size of the configuration space + * @get_config_size: Get the size of the configuration space includes + * fields that are conditional on feature bits. * @vdev: vdpa device * Returns size_t: configuration size * @get_config: Read from device specific configuration space @@ -276,8 +283,9 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); - u64 (*get_features)(struct vdpa_device *vdev); - int (*set_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_device_features)(struct vdpa_device *vdev); + int (*set_driver_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_driver_features)(struct vdpa_device *vdev); void (*set_config_cb)(struct vdpa_device *vdev, struct vdpa_callback *cb); u16 (*get_vq_num_max)(struct vdpa_device *vdev); @@ -330,10 +338,10 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, dev_struct, member)), name, use_va), \ dev_struct, member) -int vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void vdpa_unregister_device(struct vdpa_device *vdev); -int _vdpa_register_device(struct vdpa_device *vdev, int nvqs); +int _vdpa_register_device(struct vdpa_device *vdev, u32 nvqs); void _vdpa_unregister_device(struct vdpa_device *vdev); /** @@ -385,23 +393,43 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) static inline int vdpa_reset(struct vdpa_device *vdev) { const struct vdpa_config_ops *ops = vdev->config; + int ret; + mutex_lock(&vdev->cf_mutex); vdev->features_valid = false; - return ops->reset(vdev); + ret = ops->reset(vdev); + mutex_unlock(&vdev->cf_mutex); + return ret; } -static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +static inline int vdpa_set_features_unlocked(struct vdpa_device *vdev, u64 features) { const struct vdpa_config_ops *ops = vdev->config; + int ret; vdev->features_valid = true; - return ops->set_features(vdev, features); + ret = ops->set_driver_features(vdev, features); + + return ret; +} + +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +{ + int ret; + + mutex_lock(&vdev->cf_mutex); + ret = vdpa_set_features_unlocked(vdev, features); + mutex_unlock(&vdev->cf_mutex); + + return ret; } void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, const void *buf, unsigned int length); +void vdpa_set_status(struct vdpa_device *vdev, u8 status); + /** * struct vdpa_mgmtdev_ops - vdpa device ops * @dev_add: Add a vdpa device using alloc and register @@ -438,6 +466,8 @@ struct vdpa_mgmt_dev { const struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; + u64 supported_features; + u32 max_supported_vqs; }; int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 76191d7abed1..66dda06ec42d 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -33,6 +33,7 @@ struct vfio_device { struct vfio_group *group; struct vfio_device_set *dev_set; struct list_head dev_set_list; + unsigned int migration_flags; /* Members below here are private, not for driver use */ refcount_t refcount; @@ -55,6 +56,17 @@ struct vfio_device { * @match: Optional device name match callback (return: 0 for no-match, >0 for * match, -errno for abort (ex. match with insufficient or incorrect * additional args) + * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl + * @migration_set_state: Optional callback to change the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. + * The returned FD is used for data transfer according to the FSM + * definition. The driver is responsible to ensure that FD reaches end + * of stream or error whenever the migration FSM leaves a data transfer + * state or before close_device() returns. + * @migration_get_state: Optional callback to get the migration state for + * devices that support migration. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. */ struct vfio_device_ops { char *name; @@ -69,8 +81,44 @@ struct vfio_device_ops { int (*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma); void (*request)(struct vfio_device *vdev, unsigned int count); int (*match)(struct vfio_device *vdev, char *buf); + int (*device_feature)(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); + struct file *(*migration_set_state)( + struct vfio_device *device, + enum vfio_device_mig_state new_state); + int (*migration_get_state)(struct vfio_device *device, + enum vfio_device_mig_state *curr_state); }; +/** + * vfio_check_feature - Validate user input for the VFIO_DEVICE_FEATURE ioctl + * @flags: Arg from the device_feature op + * @argsz: Arg from the device_feature op + * @supported_ops: Combination of VFIO_DEVICE_FEATURE_GET and SET the driver + * supports + * @minsz: Minimum data size the driver accepts + * + * For use in a driver's device_feature op. Checks that the inputs to the + * VFIO_DEVICE_FEATURE ioctl are correct for the driver's feature. Returns 1 if + * the driver should execute the get or set, otherwise the relevant + * value should be returned. + */ +static inline int vfio_check_feature(u32 flags, size_t argsz, u32 supported_ops, + size_t minsz) +{ + if ((flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET)) & + ~supported_ops) + return -EINVAL; + if (flags & VFIO_DEVICE_FEATURE_PROBE) + return 0; + /* Without PROBE one of GET or SET must be requested */ + if (!(flags & (VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_SET))) + return -EINVAL; + if (argsz < minsz) + return -EINVAL; + return 1; +} + void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_uninit_group_dev(struct vfio_device *device); @@ -82,6 +130,11 @@ extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); +int vfio_mig_get_next_state(struct vfio_device *device, + enum vfio_device_mig_state cur_fsm, + enum vfio_device_mig_state new_fsm, + enum vfio_device_mig_state *next_fsm); + /* * External user API */ diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index ef9a44b6cf5d..74a4a0f17b28 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -159,8 +159,17 @@ extern ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, extern ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); +#ifdef CONFIG_VFIO_PCI_VGA extern ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite); +#else +static inline ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, + char __user *buf, size_t count, + loff_t *ppos, bool iswrite) +{ + return -EINVAL; +} +#endif extern long vfio_pci_ioeventfd(struct vfio_pci_core_device *vdev, loff_t offset, uint64_t data, int count, int fd); @@ -220,6 +229,8 @@ int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn); extern const struct pci_error_handlers vfio_pci_core_err_handlers; long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, unsigned long arg); +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz); ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos); ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *buf, @@ -230,6 +241,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf); int vfio_pci_core_enable(struct vfio_pci_core_device *vdev); void vfio_pci_core_disable(struct vfio_pci_core_device *vdev); void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state); static inline bool vfio_pci_is_vga(struct pci_dev *pdev) { diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 41edbc01ffa4..5464f398912a 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -133,11 +133,11 @@ bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); void virtio_config_changed(struct virtio_device *dev); -int virtio_finalize_features(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif +void virtio_reset_device(struct virtio_device *dev); size_t virtio_max_dma_size(struct virtio_device *vdev); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 4d107ad31149..dafdc7f48c01 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -64,8 +64,9 @@ struct virtio_shm_region { * Returns the first 64 feature bits (all we currently need). * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device - * This gives the final feature bits for the device: it can change + * This sends the driver feature bits to the device: it can change * the dev->feature bits if it wants. + * Note: despite the name this can be called any number of times. * Returns 0 on success or error status * @bus_name: return the bus name associated with the device (optional) * vdev: the virtio_device diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 04e87f4b9417..a960de68ac69 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -7,9 +7,27 @@ #include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> +static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) +{ + switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + return protocol == cpu_to_be16(ETH_P_IP); + case VIRTIO_NET_HDR_GSO_TCPV6: + return protocol == cpu_to_be16(ETH_P_IPV6); + case VIRTIO_NET_HDR_GSO_UDP: + return protocol == cpu_to_be16(ETH_P_IP) || + protocol == cpu_to_be16(ETH_P_IPV6); + default: + return false; + } +} + static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { + if (skb->protocol) + return 0; + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: @@ -88,9 +106,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); - virtio_net_hdr_set_proto(skb, hdr); - if (protocol && protocol != skb->protocol) + if (!protocol) + virtio_net_hdr_set_proto(skb, hdr); + else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; + else + skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index a185cc75ff52..16a0a4fd000b 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -98,6 +98,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, + THP_SCAN_EXCEED_NONE_PTE, + THP_SCAN_EXCEED_SWAP_PTE, + THP_SCAN_EXCEED_SHARED_PTE, #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD THP_SPLIT_PUD, #endif @@ -126,6 +129,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_SWAP SWAP_RA, SWAP_RA_HIT, +#ifdef CONFIG_KSM + KSM_SWPIN_COPY, +#endif #endif #ifdef CONFIG_X86 DIRECT_MAP_LEVEL2_SPLIT, diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 6e022cc712e6..3b1df7da402d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -28,16 +28,12 @@ struct notifier_block; /* in notifier.h */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ -/* - * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC. - * - * If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after - * shadow memory has been mapped. It's used to handle allocation errors so that - * we don't try to poison shadow on free if it was never allocated. - * - * Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to - * determine which allocations need the module shadow freed. - */ +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(CONFIG_KASAN_VMALLOC) +#define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ +#else +#define VM_DEFER_KMEMLEAK 0 +#endif /* bits [20..32] reserved for arch specific ioremap internals */ @@ -73,8 +69,8 @@ struct vmap_area { /* * The following two variables can be packed, because * a vmap_area object can be either: - * 1) in "free" tree (root is vmap_area_root) - * 2) or "busy" tree (root is free_vmap_area_root) + * 1) in "free" tree (root is free_vmap_area_root) + * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ @@ -119,6 +115,13 @@ static inline int arch_vmap_pte_supported_shift(unsigned long size) } #endif +#ifndef arch_vmap_pgprot_tagged +static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) +{ + return prot; +} +#endif + /* * Highlevel APIs for driver use */ @@ -152,6 +155,11 @@ void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); +extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2); + extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index e36cb114c188..6fb663b36f72 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -12,15 +12,20 @@ #include <linux/bits.h> /* Register offsets. */ -#define VMCI_STATUS_ADDR 0x00 -#define VMCI_CONTROL_ADDR 0x04 -#define VMCI_ICR_ADDR 0x08 -#define VMCI_IMR_ADDR 0x0c -#define VMCI_DATA_OUT_ADDR 0x10 -#define VMCI_DATA_IN_ADDR 0x14 -#define VMCI_CAPS_ADDR 0x18 -#define VMCI_RESULT_LOW_ADDR 0x1c -#define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_STATUS_ADDR 0x00 +#define VMCI_CONTROL_ADDR 0x04 +#define VMCI_ICR_ADDR 0x08 +#define VMCI_IMR_ADDR 0x0c +#define VMCI_DATA_OUT_ADDR 0x10 +#define VMCI_DATA_IN_ADDR 0x14 +#define VMCI_CAPS_ADDR 0x18 +#define VMCI_RESULT_LOW_ADDR 0x1c +#define VMCI_RESULT_HIGH_ADDR 0x20 +#define VMCI_DATA_OUT_LOW_ADDR 0x24 +#define VMCI_DATA_OUT_HIGH_ADDR 0x28 +#define VMCI_DATA_IN_LOW_ADDR 0x2c +#define VMCI_DATA_IN_HIGH_ADDR 0x30 +#define VMCI_GUEST_PAGE_SHIFT 0x34 /* Max number of devices. */ #define VMCI_MAX_DEVICES 1 @@ -39,17 +44,27 @@ #define VMCI_CAPS_DATAGRAM BIT(2) #define VMCI_CAPS_NOTIFICATIONS BIT(3) #define VMCI_CAPS_PPN64 BIT(4) +#define VMCI_CAPS_DMA_DATAGRAM BIT(5) /* Interrupt Cause register bits. */ #define VMCI_ICR_DATAGRAM BIT(0) #define VMCI_ICR_NOTIFICATION BIT(1) +#define VMCI_ICR_DMA_DATAGRAM BIT(2) /* Interrupt Mask register bits. */ #define VMCI_IMR_DATAGRAM BIT(0) #define VMCI_IMR_NOTIFICATION BIT(1) +#define VMCI_IMR_DMA_DATAGRAM BIT(2) -/* Maximum MSI/MSI-X interrupt vectors in the device. */ -#define VMCI_MAX_INTRS 2 +/* + * Maximum MSI/MSI-X interrupt vectors in the device. + * If VMCI_CAPS_DMA_DATAGRAM is supported by the device, + * VMCI_MAX_INTRS_DMA_DATAGRAM vectors are available, + * otherwise only VMCI_MAX_INTRS_NOTIFICATION. + */ +#define VMCI_MAX_INTRS_NOTIFICATION 2 +#define VMCI_MAX_INTRS_DMA_DATAGRAM 3 +#define VMCI_MAX_INTRS VMCI_MAX_INTRS_DMA_DATAGRAM /* * Supported interrupt vectors. There is one for each ICR value above, @@ -58,6 +73,7 @@ enum { VMCI_INTR_DATAGRAM = 0, VMCI_INTR_NOTIFICATION = 1, + VMCI_INTR_DMA_DATAGRAM = 2, }; /* @@ -83,6 +99,52 @@ enum { #define VMCI_MAX_PINNED_QP_MEMORY ((size_t)(32 * 1024)) /* + * The version of the VMCI device that supports MMIO access to registers + * requests 256KB for BAR1 whereas the version of VMCI that supports + * MSI/MSI-X only requests 8KB. The layout of the larger 256KB region is: + * - the first 128KB are used for MSI/MSI-X. + * - the following 64KB are used for MMIO register access. + * - the remaining 64KB are unused. + */ +#define VMCI_WITH_MMIO_ACCESS_BAR_SIZE ((size_t)(256 * 1024)) +#define VMCI_MMIO_ACCESS_OFFSET ((size_t)(128 * 1024)) +#define VMCI_MMIO_ACCESS_SIZE ((size_t)(64 * 1024)) + +/* + * For VMCI devices supporting the VMCI_CAPS_DMA_DATAGRAM capability, the + * sending and receiving of datagrams can be performed using DMA to/from + * a driver allocated buffer. + * Sending and receiving will be handled as follows: + * - when sending datagrams, the driver initializes the buffer where the + * data part will refer to the outgoing VMCI datagram, sets the busy flag + * to 1 and writes the address of the buffer to VMCI_DATA_OUT_HIGH_ADDR + * and VMCI_DATA_OUT_LOW_ADDR. Writing to VMCI_DATA_OUT_LOW_ADDR triggers + * the device processing of the buffer. When the device has processed the + * buffer, it will write the result value to the buffer and then clear the + * busy flag. + * - when receiving datagrams, the driver initializes the buffer where the + * data part will describe the receive buffer, clears the busy flag and + * writes the address of the buffer to VMCI_DATA_IN_HIGH_ADDR and + * VMCI_DATA_IN_LOW_ADDR. Writing to VMCI_DATA_IN_LOW_ADDR triggers the + * device processing of the buffer. The device will copy as many available + * datagrams into the buffer as possible, and then sets the busy flag. + * When the busy flag is set, the driver will process the datagrams in the + * buffer. + */ +struct vmci_data_in_out_header { + uint32_t busy; + uint32_t opcode; + uint32_t size; + uint32_t rsvd; + uint64_t result; +}; + +struct vmci_sg_elem { + uint64_t addr; + uint64_t size; +}; + +/* * We have a fixed set of resource IDs available in the VMX. * This allows us to have a very simple implementation since we statically * know how many will create datagram handles. If a new caller arrives and diff --git a/include/linux/wait_api.h b/include/linux/wait_api.h new file mode 100644 index 000000000000..4e930548935a --- /dev/null +++ b/include/linux/wait_api.h @@ -0,0 +1 @@ +#include <linux/wait.h> diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index c994d1b2cdba..3b9a40ae8bdb 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -28,7 +28,8 @@ struct watch_type_filter { struct watch_filter { union { struct rcu_head rcu; - unsigned long type_filter[2]; /* Bitmask of accepted types */ + /* Bitmask of accepted types */ + DECLARE_BITMAP(type_filter, WATCH_TYPE__NR); }; u32 nr_filters; /* Number of filters */ struct watch_type_filter filters[]; diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 2cb3913c1f50..b88d7b58e61e 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -35,6 +35,7 @@ extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); struct wmi_driver { struct device_driver driver; const struct wmi_device_id *id_table; + bool no_notify_data; int (*probe)(struct wmi_device *wdev, const void *context); void (*remove)(struct wmi_device *wdev); diff --git a/include/linux/workqueue_api.h b/include/linux/workqueue_api.h new file mode 100644 index 000000000000..77debb5d2760 --- /dev/null +++ b/include/linux/workqueue_api.h @@ -0,0 +1 @@ +#include <linux/workqueue.h> diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3bfd487d1dd2..fec248ab1fec 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,6 +68,7 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned unpinned_fscache_wb:1; /* Cleared I_PINNING_FSCACHE_WB */ /* * When writeback IOs are bounced through async layers, only the diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 9fac819f92e3..5ce2acf444fb 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -4,12 +4,9 @@ #ifndef __WWAN_H #define __WWAN_H -#include <linux/device.h> -#include <linux/kernel.h> #include <linux/poll.h> -#include <linux/skbuff.h> -#include <linux/netlink.h> #include <linux/netdevice.h> +#include <linux/types.h> /** * enum wwan_port_type - WWAN port types @@ -37,6 +34,10 @@ enum wwan_port_type { WWAN_PORT_UNKNOWN, }; +struct device; +struct file; +struct netlink_ext_ack; +struct sk_buff; struct wwan_port; /** struct wwan_port_ops - The WWAN port operations @@ -171,4 +172,15 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, void wwan_unregister_ops(struct device *parent); +#ifdef CONFIG_WWAN_DEBUGFS +struct dentry *wwan_get_debugfs_dir(struct device *parent); +void wwan_put_debugfs_dir(struct dentry *dir); +#else +static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) +{ + return ERR_PTR(-ENODEV); +} +static inline void wwan_put_debugfs_dir(struct dentry *dir) {} +#endif + #endif /* __WWAN_H */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a91e3d90df8a..bb52b786be1b 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1317,6 +1317,7 @@ struct xa_state { struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; + struct list_lru *xa_lru; }; /* @@ -1336,7 +1337,8 @@ struct xa_state { .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ - .xa_update = NULL \ + .xa_update = NULL, \ + .xa_lru = NULL, \ } /** @@ -1581,6 +1583,24 @@ static inline void xas_set(struct xa_state *xas, unsigned long index) } /** + * xas_advance() - Skip over sibling entries. + * @xas: XArray operation state. + * @index: Index of last sibling entry. + * + * Move the operation state to refer to the last sibling entry. + * This is useful for loops that normally want to see sibling + * entries but sometimes want to skip them. Use xas_set() if you + * want to move to an index which is not part of this entry. + */ +static inline void xas_advance(struct xa_state *xas, unsigned long index) +{ + unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; + + xas->xa_index = index; + xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; +} + +/** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. @@ -1613,6 +1633,11 @@ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) xas->xa_update = update; } +static inline void xas_set_lru(struct xa_state *xas, struct list_lru *lru) +{ + xas->xa_lru = lru; +} + /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. |