From 8605c6844fb9bdf55471bb87c3ac62d44eb34e04 Mon Sep 17 00:00:00 2001 From: Tang Liang Date: Thu, 8 Dec 2011 17:36:39 +0800 Subject: xen: Utilize the restore_msi_irqs hook. to make a hypercall to restore the vectors in the MSI/MSI-X configuration space. Signed-off-by: Tang Liang Signed-off-by: Konrad Rzeszutek Wilk --- include/xen/interface/physdev.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h index c1080d9c705..0c28989007f 100644 --- a/include/xen/interface/physdev.h +++ b/include/xen/interface/physdev.h @@ -145,6 +145,13 @@ struct physdev_manage_pci { uint8_t devfn; }; +#define PHYSDEVOP_restore_msi 19 +struct physdev_restore_msi { + /* IN */ + uint8_t bus; + uint8_t devfn; +}; + #define PHYSDEVOP_manage_pci_add_ext 20 struct physdev_manage_pci_ext { /* IN */ -- cgit v1.2.3 From a96d627abaac899e8bfaf18fd0578b228c9c752f Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Wed, 4 Jan 2012 14:23:56 -0500 Subject: pci: Introduce __pci_reset_function_locked to be used when holding device_lock. The use case of this is when a driver wants to call FLR when a device is attached to it using the SysFS "bind" or "unbind" functionality. The call chain when a user does "bind" looks as so: echo "0000:01.07.0" > /sys/bus/pci/drivers/XXXX/bind and ends up calling: driver_bind: device_lock(dev); <=== TAKES LOCK XXXX_probe: .. pci_enable_device() ...__pci_reset_function(), which calls pci_dev_reset(dev, 0): if (!0) { device_lock(dev) <==== DEADLOCK The __pci_reset_function_locked function allows the the drivers 'probe' function to call the "pci_reset_function" while still holding the driver mutex lock. Signed-off-by: Konrad Rzeszutek Wilk --- drivers/pci/pci.c | 25 +++++++++++++++++++++++++ include/linux/pci.h | 1 + 2 files changed, 26 insertions(+) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 97fff785e97..192be5dbde5 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3162,6 +3162,31 @@ int __pci_reset_function(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(__pci_reset_function); +/** + * __pci_reset_function_locked - reset a PCI device function while holding + * the @dev mutex lock. + * @dev: PCI device to reset + * + * Some devices allow an individual function to be reset without affecting + * other functions in the same device. The PCI device must be responsive + * to PCI config space in order to use this function. + * + * The device function is presumed to be unused and the caller is holding + * the device mutex lock when this function is called. + * Resetting the device will make the contents of PCI configuration space + * random, so any caller of this must be prepared to reinitialise the + * device including MSI, bus mastering, BARs, decoding IO and memory spaces, + * etc. + * + * Returns 0 if the device function was successfully reset or negative if the + * device doesn't support resetting a single function. + */ +int __pci_reset_function_locked(struct pci_dev *dev) +{ + return pci_dev_reset(dev, 1); +} +EXPORT_SYMBOL_GPL(__pci_reset_function_locked); + /** * pci_probe_reset_function - check whether the device can be safely reset * @dev: PCI device to reset diff --git a/include/linux/pci.h b/include/linux/pci.h index a16b1df3def..65c2d8a32b2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -817,6 +817,7 @@ int pcie_set_readrq(struct pci_dev *dev, int rq); int pcie_get_mps(struct pci_dev *dev); int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); +int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); -- cgit v1.2.3 From 73c154c60be106b47f15d1111fc2d75cc7a436f2 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Mon, 13 Feb 2012 22:26:32 -0500 Subject: xen/enlighten: Expose MWAIT and MWAIT_LEAF if hypervisor OKs it. For the hypervisor to take advantage of the MWAIT support it needs to extract from the ACPI _CST the register address. But the hypervisor does not have the support to parse DSDT so it relies on the initial domain (dom0) to parse the ACPI Power Management information and push it up to the hypervisor. The pushing of the data is done by the processor_harveset_xen module which parses the information that the ACPI parser has graciously exposed in 'struct acpi_processor'. For the ACPI parser to also expose the Cx states for MWAIT, we need to expose the MWAIT capability (leaf 1). Furthermore we also need to expose the MWAIT_LEAF capability (leaf 5) for cstate.c to properly function. The hypervisor could expose these flags when it traps the XEN_EMULATE_PREFIX operations, but it can't do it since it needs to be backwards compatible. Instead we choose to use the native CPUID to figure out if the MWAIT capability exists and use the XEN_SET_PDC query hypercall to figure out if the hypervisor wants us to expose the MWAIT_LEAF capability or not. Note: The XEN_SET_PDC query was implemented in c/s 23783: "ACPI: add _PDC input override mechanism". With this in place, instead of C3 ACPI IOPORT 415 we get now C3:ACPI FFH INTEL MWAIT 0x20 Note: The cpu_idle which would be calling the mwait variants for idling never gets set b/c we set the default pm_idle to be the hypercall variant. Acked-by: Jan Beulich [v2: Fix missing header file include and #ifdef] Signed-off-by: Konrad Rzeszutek Wilk --- arch/ia64/include/asm/xen/interface.h | 1 + arch/x86/include/asm/xen/interface.h | 1 + arch/x86/xen/enlighten.c | 93 ++++++++++++++++++++++++++++++++++- include/xen/interface/platform.h | 3 +- 4 files changed, 96 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/arch/ia64/include/asm/xen/interface.h b/arch/ia64/include/asm/xen/interface.h index fbb519828aa..09d5f7fd9db 100644 --- a/arch/ia64/include/asm/xen/interface.h +++ b/arch/ia64/include/asm/xen/interface.h @@ -77,6 +77,7 @@ DEFINE_GUEST_HANDLE(int); DEFINE_GUEST_HANDLE(long); DEFINE_GUEST_HANDLE(void); DEFINE_GUEST_HANDLE(uint64_t); +DEFINE_GUEST_HANDLE(uint32_t); typedef unsigned long xen_pfn_t; DEFINE_GUEST_HANDLE(xen_pfn_t); diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index a1f2db5f117..cbf0c9d50b9 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -56,6 +56,7 @@ DEFINE_GUEST_HANDLE(int); DEFINE_GUEST_HANDLE(long); DEFINE_GUEST_HANDLE(void); DEFINE_GUEST_HANDLE(uint64_t); +DEFINE_GUEST_HANDLE(uint32_t); #endif #ifndef HYPERVISOR_VIRT_START diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 312c9e3cb63..fe06bf4ef0e 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -62,6 +62,15 @@ #include #include #include +#include + +#ifdef CONFIG_ACPI +#include +#include +#include +#include +#include +#endif #include "xen-ops.h" #include "mmu.h" @@ -200,13 +209,17 @@ static void __init xen_banner(void) static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; +static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask; +static __read_mostly unsigned int cpuid_leaf5_ecx_val; +static __read_mostly unsigned int cpuid_leaf5_edx_val; + static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { unsigned maskebx = ~0; unsigned maskecx = ~0; unsigned maskedx = ~0; - + unsigned setecx = 0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. @@ -214,9 +227,18 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, switch (*ax) { case 1: maskecx = cpuid_leaf1_ecx_mask; + setecx = cpuid_leaf1_ecx_set_mask; maskedx = cpuid_leaf1_edx_mask; break; + case CPUID_MWAIT_LEAF: + /* Synthesize the values.. */ + *ax = 0; + *bx = 0; + *cx = cpuid_leaf5_ecx_val; + *dx = cpuid_leaf5_edx_val; + return; + case 0xb: /* Suppress extended topology stuff */ maskebx = 0; @@ -232,9 +254,75 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, *bx &= maskebx; *cx &= maskecx; + *cx |= setecx; *dx &= maskedx; + } +static bool __init xen_check_mwait(void) +{ +#ifdef CONFIG_ACPI + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .u.set_pminfo.id = -1, + .u.set_pminfo.type = XEN_PM_PDC, + }; + uint32_t buf[3]; + unsigned int ax, bx, cx, dx; + unsigned int mwait_mask; + + /* We need to determine whether it is OK to expose the MWAIT + * capability to the kernel to harvest deeper than C3 states from ACPI + * _CST using the processor_harvest_xen.c module. For this to work, we + * need to gather the MWAIT_LEAF values (which the cstate.c code + * checks against). The hypervisor won't expose the MWAIT flag because + * it would break backwards compatibility; so we will find out directly + * from the hardware and hypercall. + */ + if (!xen_initial_domain()) + return false; + + ax = 1; + cx = 0; + + native_cpuid(&ax, &bx, &cx, &dx); + + mwait_mask = (1 << (X86_FEATURE_EST % 32)) | + (1 << (X86_FEATURE_MWAIT % 32)); + + if ((cx & mwait_mask) != mwait_mask) + return false; + + /* We need to emulate the MWAIT_LEAF and for that we need both + * ecx and edx. The hypercall provides only partial information. + */ + + ax = CPUID_MWAIT_LEAF; + bx = 0; + cx = 0; + dx = 0; + + native_cpuid(&ax, &bx, &cx, &dx); + + /* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so, + * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3. + */ + buf[0] = ACPI_PDC_REVISION_ID; + buf[1] = 1; + buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP); + + set_xen_guest_handle(op.u.set_pminfo.pdc, buf); + + if ((HYPERVISOR_dom0_op(&op) == 0) && + (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) { + cpuid_leaf5_ecx_val = cx; + cpuid_leaf5_edx_val = dx; + } + return true; +#else + return false; +#endif +} static void __init xen_init_cpuid_mask(void) { unsigned int ax, bx, cx, dx; @@ -261,6 +349,9 @@ static void __init xen_init_cpuid_mask(void) /* Xen will set CR4.OSXSAVE if supported and not disabled by force */ if ((cx & xsave_mask) != xsave_mask) cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */ + + if (xen_check_mwait()) + cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32)); } static void xen_set_debugreg(int reg, unsigned long val) diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h index c1684680431..861b359b44a 100644 --- a/include/xen/interface/platform.h +++ b/include/xen/interface/platform.h @@ -200,7 +200,7 @@ DEFINE_GUEST_HANDLE_STRUCT(xenpf_getidletime_t); #define XEN_PM_CX 0 #define XEN_PM_PX 1 #define XEN_PM_TX 2 - +#define XEN_PM_PDC 3 /* Px sub info type */ #define XEN_PX_PCT 1 #define XEN_PX_PSS 2 @@ -293,6 +293,7 @@ struct xenpf_set_processor_pminfo { union { struct xen_processor_power power;/* Cx: _CST/_CSD */ struct xen_processor_performance perf; /* Px: _PPC/_PCT/_PSS/_PSD */ + GUEST_HANDLE(uint32_t) pdc; }; }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_set_processor_pminfo); -- cgit v1.2.3 From eb5ef07151ba3c3cb4bcef0c8f146ff1115eaa55 Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Fri, 27 Jan 2012 18:31:36 +0000 Subject: hvc_xen: support PV on HVM consoles Signed-off-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/tty/hvc/hvc_xen.c | 84 ++++++++++++++++++++++++++++++-------- include/xen/interface/hvm/params.h | 6 ++- 2 files changed, 73 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 52fdf60bdbe..d5000aa0286 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -24,9 +24,12 @@ #include #include +#include #include #include +#include +#include #include #include #include @@ -42,9 +45,13 @@ static int xencons_irq; /* ------------------------------------------------------------------ */ static unsigned long console_pfn = ~0ul; +static unsigned int console_evtchn = ~0ul; +static struct xencons_interface *xencons_if = NULL; static inline struct xencons_interface *xencons_interface(void) { + if (xencons_if != NULL) + return xencons_if; if (console_pfn == ~0ul) return mfn_to_virt(xen_start_info->console.domU.mfn); else @@ -54,7 +61,10 @@ static inline struct xencons_interface *xencons_interface(void) static inline void notify_daemon(void) { /* Use evtchn: this is called early, before irq is set up. */ - notify_remote_via_evtchn(xen_start_info->console.domU.evtchn); + if (console_evtchn == ~0ul) + notify_remote_via_evtchn(xen_start_info->console.domU.evtchn); + else + notify_remote_via_evtchn(console_evtchn); } static int __write_console(const char *data, int len) @@ -157,28 +167,63 @@ static struct hv_ops dom0_hvc_ops = { .notifier_hangup = notifier_hangup_irq, }; +static int xen_hvm_console_init(void) +{ + int r; + uint64_t v = 0; + unsigned long mfn; + + if (!xen_hvm_domain()) + return -ENODEV; + + if (xencons_if != NULL) + return -EBUSY; + + r = hvm_get_parameter(HVM_PARAM_CONSOLE_EVTCHN, &v); + if (r < 0) + return -ENODEV; + console_evtchn = v; + hvm_get_parameter(HVM_PARAM_CONSOLE_PFN, &v); + if (r < 0) + return -ENODEV; + mfn = v; + xencons_if = ioremap(mfn << PAGE_SHIFT, PAGE_SIZE); + if (xencons_if == NULL) + return -ENODEV; + + return 0; +} + static int __init xen_hvc_init(void) { struct hvc_struct *hp; struct hv_ops *ops; + int r; - if (!xen_pv_domain()) + if (!xen_domain()) return -ENODEV; if (xen_initial_domain()) { ops = &dom0_hvc_ops; xencons_irq = bind_virq_to_irq(VIRQ_CONSOLE, 0); } else { - if (!xen_start_info->console.domU.evtchn) - return -ENODEV; - ops = &domU_hvc_ops; - xencons_irq = bind_evtchn_to_irq(xen_start_info->console.domU.evtchn); + if (xen_pv_domain()) { + if (!xen_start_info->console.domU.evtchn) + return -ENODEV; + console_pfn = mfn_to_pfn(xen_start_info->console.domU.mfn); + console_evtchn = xen_start_info->console.domU.evtchn; + } else { + r = xen_hvm_console_init(); + if (r < 0) + return r; + } + xencons_irq = bind_evtchn_to_irq(console_evtchn); + if (xencons_irq < 0) + xencons_irq = 0; /* NO_IRQ */ + else + irq_set_noprobe(xencons_irq); } - if (xencons_irq < 0) - xencons_irq = 0; /* NO_IRQ */ - else - irq_set_noprobe(xencons_irq); hp = hvc_alloc(HVC_COOKIE, xencons_irq, ops, 256); if (IS_ERR(hp)) @@ -186,15 +231,13 @@ static int __init xen_hvc_init(void) hvc = hp; - console_pfn = mfn_to_pfn(xen_start_info->console.domU.mfn); - return 0; } void xen_console_resume(void) { if (xencons_irq) - rebind_evtchn_irq(xen_start_info->console.domU.evtchn, xencons_irq); + rebind_evtchn_irq(console_evtchn, xencons_irq); } static void __exit xen_hvc_fini(void) @@ -205,16 +248,22 @@ static void __exit xen_hvc_fini(void) static int xen_cons_init(void) { - struct hv_ops *ops; + const struct hv_ops *ops; - if (!xen_pv_domain()) + if (!xen_domain()) return 0; if (xen_initial_domain()) ops = &dom0_hvc_ops; - else + else { ops = &domU_hvc_ops; + if (xen_pv_domain()) + console_evtchn = xen_start_info->console.domU.evtchn; + else + xen_hvm_console_init(); + } + hvc_instantiate(HVC_COOKIE, 0, ops); return 0; } @@ -230,6 +279,9 @@ static void xenboot_write_console(struct console *console, const char *string, unsigned int linelen, off = 0; const char *pos; + if (!xen_pv_domain()) + return; + dom0_write_console(0, string, len); if (xen_initial_domain()) diff --git a/include/xen/interface/hvm/params.h b/include/xen/interface/hvm/params.h index 1888d8c157e..1b4f923d708 100644 --- a/include/xen/interface/hvm/params.h +++ b/include/xen/interface/hvm/params.h @@ -90,6 +90,10 @@ /* Boolean: Enable aligning all periodic vpts to reduce interrupts */ #define HVM_PARAM_VPT_ALIGN 16 -#define HVM_NR_PARAMS 17 +/* Console debug shared memory ring and event channel */ +#define HVM_PARAM_CONSOLE_PFN 17 +#define HVM_PARAM_CONSOLE_EVTCHN 18 + +#define HVM_NR_PARAMS 19 #endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */ -- cgit v1.2.3 From 59a56802918100c1e39e68c30a2e5ae9f7d837f0 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 3 Feb 2012 16:03:20 -0500 Subject: xen/acpi-processor: C and P-state driver that uploads said data to hypervisor. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This driver solves three problems: 1). Parse and upload ACPI0007 (or PROCESSOR_TYPE) information to the hypervisor - aka P-states (cpufreq data). 2). Upload the the Cx state information (cpuidle data). 3). Inhibit CPU frequency scaling drivers from loading. The reason for wanting to solve 1) and 2) is such that the Xen hypervisor is the only one that knows the CPU usage of different guests and can make the proper decision of when to put CPUs and packages in proper states. Unfortunately the hypervisor has no support to parse ACPI DSDT tables, hence it needs help from the initial domain to provide this information. The reason for 3) is that we do not want the initial domain to change P-states while the hypervisor is doing it as well - it causes rather some funny cases of P-states transitions. For this to work, the driver parses the Power Management data and uploads said information to the Xen hypervisor. It also calls acpi_processor_notify_smm() to inhibit the other CPU frequency scaling drivers from being loaded. Everything revolves around the 'struct acpi_processor' structure which gets updated during the bootup cycle in different stages. At the startup, when the ACPI parser starts, the C-state information is processed (processor_idle) and saved in said structure as 'power' element. Later on, the CPU frequency scaling driver (powernow-k8 or acpi_cpufreq), would call the the acpi_processor_* (processor_perflib functions) to parse P-states information and populate in the said structure the 'performance' element. Since we do not want the CPU frequency scaling drivers from loading we have to call the acpi_processor_* functions to parse the P-states and call "acpi_processor_notify_smm" to stop them from loading. There is also one oddity in this driver which is that under Xen, the physical online CPU count can be different from the virtual online CPU count. Meaning that the macros 'for_[online|possible]_cpu' would process only up to virtual online CPU count. We on the other hand want to process the full amount of physical CPUs. For that, the driver checks if the ACPI IDs count is different from the APIC ID count - which can happen if the user choose to use dom0_max_vcpu argument. In such a case a backup of the PM structure is used and uploaded to the hypervisor. [v1-v2: Initial RFC implementations that were posted] [v3: Changed the name to passthru suggested by Pasi Kärkkäinen ] [v4: Added vCPU != pCPU support - aka dom0_max_vcpus support] [v5: Cleaned up the driver, fix bug under Athlon XP] [v6: Changed the driver to a CPU frequency governor] [v7: Jan Beulich suggestion to make it a cpufreq scaling driver made me rework it as driver that inhibits cpufreq scaling driver] [v8: Per Jan's review comments, fixed up the driver] [v9: Allow to continue even if acpi_processor_preregister_perf.. fails] Signed-off-by: Konrad Rzeszutek Wilk --- drivers/xen/Kconfig | 17 ++ drivers/xen/Makefile | 2 +- drivers/xen/xen-acpi-processor.c | 562 +++++++++++++++++++++++++++++++++++++++ include/xen/interface/platform.h | 17 ++ 4 files changed, 597 insertions(+), 1 deletion(-) create mode 100644 drivers/xen/xen-acpi-processor.c (limited to 'include') diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index a1ced521cf7..648bcd4195c 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -178,4 +178,21 @@ config XEN_PRIVCMD depends on XEN default m +config XEN_ACPI_PROCESSOR + tristate "Xen ACPI processor" + depends on XEN && X86 && ACPI_PROCESSOR + default y if (X86_ACPI_CPUFREQ = y || X86_POWERNOW_K8 = y) + default m if (X86_ACPI_CPUFREQ = m || X86_POWERNOW_K8 = m) + help + This ACPI processor uploads Power Management information to the Xen hypervisor. + + To do that the driver parses the Power Management data and uploads said + information to the Xen hypervisor. Then the Xen hypervisor can select the + proper Cx and Pxx states. It also registers itslef as the SMM so that + other drivers (such as ACPI cpufreq scaling driver) will not load. + + To compile this driver as a module, choose M here: the + module will be called xen_acpi_processor If you do not know what to choose, + select M here. If the CPUFREQ drivers are built in, select Y here. + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index aa31337192c..9adc5be57b1 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -20,7 +20,7 @@ obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o obj-$(CONFIG_XEN_DOM0) += pci.o obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/ obj-$(CONFIG_XEN_PRIVCMD) += xen-privcmd.o - +obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c new file mode 100644 index 00000000000..5c2be963aa1 --- /dev/null +++ b/drivers/xen/xen-acpi-processor.c @@ -0,0 +1,562 @@ +/* + * Copyright 2012 by Oracle Inc + * Author: Konrad Rzeszutek Wilk + * + * This code borrows ideas from https://lkml.org/lkml/2011/11/30/249 + * so many thanks go to Kevin Tian + * and Yu Ke . + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define DRV_NAME "xen-acpi-processor: " + +static int no_hypercall; +MODULE_PARM_DESC(off, "Inhibit the hypercall."); +module_param_named(off, no_hypercall, int, 0400); + +/* + * Note: Do not convert the acpi_id* below to cpumask_var_t or use cpumask_bit + * - as those shrink to nr_cpu_bits (which is dependent on possible_cpu), which + * can be less than what we want to put in. Instead use the 'nr_acpi_bits' + * which is dynamically computed based on the MADT or x2APIC table. + */ +static unsigned int nr_acpi_bits; +/* Mutex to protect the acpi_ids_done - for CPU hotplug use. */ +static DEFINE_MUTEX(acpi_ids_mutex); +/* Which ACPI ID we have processed from 'struct acpi_processor'. */ +static unsigned long *acpi_ids_done; +/* Which ACPI ID exist in the SSDT/DSDT processor definitions. */ +static unsigned long __initdata *acpi_id_present; +/* And if there is an _CST definition (or a PBLK) for the ACPI IDs */ +static unsigned long __initdata *acpi_id_cst_present; + +static int push_cxx_to_hypervisor(struct acpi_processor *_pr) +{ + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.set_pminfo.id = _pr->acpi_id, + .u.set_pminfo.type = XEN_PM_CX, + }; + struct xen_processor_cx *dst_cx, *dst_cx_states = NULL; + struct acpi_processor_cx *cx; + unsigned int i, ok; + int ret = 0; + + dst_cx_states = kcalloc(_pr->power.count, + sizeof(struct xen_processor_cx), GFP_KERNEL); + if (!dst_cx_states) + return -ENOMEM; + + for (ok = 0, i = 1; i <= _pr->power.count; i++) { + cx = &_pr->power.states[i]; + if (!cx->valid) + continue; + + dst_cx = &(dst_cx_states[ok++]); + + dst_cx->reg.space_id = ACPI_ADR_SPACE_SYSTEM_IO; + if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) { + dst_cx->reg.bit_width = 8; + dst_cx->reg.bit_offset = 0; + dst_cx->reg.access_size = 1; + } else { + dst_cx->reg.space_id = ACPI_ADR_SPACE_FIXED_HARDWARE; + if (cx->entry_method == ACPI_CSTATE_FFH) { + /* NATIVE_CSTATE_BEYOND_HALT */ + dst_cx->reg.bit_offset = 2; + dst_cx->reg.bit_width = 1; /* VENDOR_INTEL */ + } + dst_cx->reg.access_size = 0; + } + dst_cx->reg.address = cx->address; + + dst_cx->type = cx->type; + dst_cx->latency = cx->latency; + dst_cx->power = cx->power; + + dst_cx->dpcnt = 0; + set_xen_guest_handle(dst_cx->dp, NULL); + } + if (!ok) { + pr_debug(DRV_NAME "No _Cx for ACPI CPU %u\n", _pr->acpi_id); + kfree(dst_cx_states); + return -EINVAL; + } + op.u.set_pminfo.power.count = ok; + op.u.set_pminfo.power.flags.bm_control = _pr->flags.bm_control; + op.u.set_pminfo.power.flags.bm_check = _pr->flags.bm_check; + op.u.set_pminfo.power.flags.has_cst = _pr->flags.has_cst; + op.u.set_pminfo.power.flags.power_setup_done = + _pr->flags.power_setup_done; + + set_xen_guest_handle(op.u.set_pminfo.power.states, dst_cx_states); + + if (!no_hypercall) + ret = HYPERVISOR_dom0_op(&op); + + if (!ret) { + pr_debug("ACPI CPU%u - C-states uploaded.\n", _pr->acpi_id); + for (i = 1; i <= _pr->power.count; i++) { + cx = &_pr->power.states[i]; + if (!cx->valid) + continue; + pr_debug(" C%d: %s %d uS\n", + cx->type, cx->desc, (u32)cx->latency); + } + } else + pr_err(DRV_NAME "(CX): Hypervisor error (%d) for ACPI CPU%u\n", + ret, _pr->acpi_id); + + kfree(dst_cx_states); + + return ret; +} +static struct xen_processor_px * +xen_copy_pss_data(struct acpi_processor *_pr, + struct xen_processor_performance *dst_perf) +{ + struct xen_processor_px *dst_states = NULL; + unsigned int i; + + BUILD_BUG_ON(sizeof(struct xen_processor_px) != + sizeof(struct acpi_processor_px)); + + dst_states = kcalloc(_pr->performance->state_count, + sizeof(struct xen_processor_px), GFP_KERNEL); + if (!dst_states) + return ERR_PTR(-ENOMEM); + + dst_perf->state_count = _pr->performance->state_count; + for (i = 0; i < _pr->performance->state_count; i++) { + /* Fortunatly for us, they are both the same size */ + memcpy(&(dst_states[i]), &(_pr->performance->states[i]), + sizeof(struct acpi_processor_px)); + } + return dst_states; +} +static int xen_copy_psd_data(struct acpi_processor *_pr, + struct xen_processor_performance *dst) +{ + struct acpi_psd_package *pdomain; + + BUILD_BUG_ON(sizeof(struct xen_psd_package) != + sizeof(struct acpi_psd_package)); + + /* This information is enumerated only if acpi_processor_preregister_performance + * has been called. + */ + dst->shared_type = _pr->performance->shared_type; + + pdomain = &(_pr->performance->domain_info); + + /* 'acpi_processor_preregister_performance' does not parse if the + * num_processors <= 1, but Xen still requires it. Do it manually here. + */ + if (pdomain->num_processors <= 1) { + if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL) + dst->shared_type = CPUFREQ_SHARED_TYPE_ALL; + else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL) + dst->shared_type = CPUFREQ_SHARED_TYPE_HW; + else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY) + dst->shared_type = CPUFREQ_SHARED_TYPE_ANY; + + } + memcpy(&(dst->domain_info), pdomain, sizeof(struct acpi_psd_package)); + return 0; +} +static int xen_copy_pct_data(struct acpi_pct_register *pct, + struct xen_pct_register *dst_pct) +{ + /* It would be nice if you could just do 'memcpy(pct, dst_pct') but + * sadly the Xen structure did not have the proper padding so the + * descriptor field takes two (dst_pct) bytes instead of one (pct). + */ + dst_pct->descriptor = pct->descriptor; + dst_pct->length = pct->length; + dst_pct->space_id = pct->space_id; + dst_pct->bit_width = pct->bit_width; + dst_pct->bit_offset = pct->bit_offset; + dst_pct->reserved = pct->reserved; + dst_pct->address = pct->address; + return 0; +} +static int push_pxx_to_hypervisor(struct acpi_processor *_pr) +{ + int ret = 0; + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.set_pminfo.id = _pr->acpi_id, + .u.set_pminfo.type = XEN_PM_PX, + }; + struct xen_processor_performance *dst_perf; + struct xen_processor_px *dst_states = NULL; + + dst_perf = &op.u.set_pminfo.perf; + + dst_perf->platform_limit = _pr->performance_platform_limit; + dst_perf->flags |= XEN_PX_PPC; + xen_copy_pct_data(&(_pr->performance->control_register), + &dst_perf->control_register); + xen_copy_pct_data(&(_pr->performance->status_register), + &dst_perf->status_register); + dst_perf->flags |= XEN_PX_PCT; + dst_states = xen_copy_pss_data(_pr, dst_perf); + if (!IS_ERR_OR_NULL(dst_states)) { + set_xen_guest_handle(dst_perf->states, dst_states); + dst_perf->flags |= XEN_PX_PSS; + } + if (!xen_copy_psd_data(_pr, dst_perf)) + dst_perf->flags |= XEN_PX_PSD; + + if (dst_perf->flags != (XEN_PX_PSD | XEN_PX_PSS | XEN_PX_PCT | XEN_PX_PPC)) { + pr_warn(DRV_NAME "ACPI CPU%u missing some P-state data (%x), skipping.\n", + _pr->acpi_id, dst_perf->flags); + ret = -ENODEV; + goto err_free; + } + + if (!no_hypercall) + ret = HYPERVISOR_dom0_op(&op); + + if (!ret) { + struct acpi_processor_performance *perf; + unsigned int i; + + perf = _pr->performance; + pr_debug("ACPI CPU%u - P-states uploaded.\n", _pr->acpi_id); + for (i = 0; i < perf->state_count; i++) { + pr_debug(" %cP%d: %d MHz, %d mW, %d uS\n", + (i == perf->state ? '*' : ' '), i, + (u32) perf->states[i].core_frequency, + (u32) perf->states[i].power, + (u32) perf->states[i].transition_latency); + } + } else if (ret != -EINVAL) + /* EINVAL means the ACPI ID is incorrect - meaning the ACPI + * table is referencing a non-existing CPU - which can happen + * with broken ACPI tables. */ + pr_warn(DRV_NAME "(_PXX): Hypervisor error (%d) for ACPI CPU%u\n", + ret, _pr->acpi_id); +err_free: + if (!IS_ERR_OR_NULL(dst_states)) + kfree(dst_states); + + return ret; +} +static int upload_pm_data(struct acpi_processor *_pr) +{ + int err = 0; + + mutex_lock(&acpi_ids_mutex); + if (__test_and_set_bit(_pr->acpi_id, acpi_ids_done)) { + mutex_unlock(&acpi_ids_mutex); + return -EBUSY; + } + if (_pr->flags.power) + err = push_cxx_to_hypervisor(_pr); + + if (_pr->performance && _pr->performance->states) + err |= push_pxx_to_hypervisor(_pr); + + mutex_unlock(&acpi_ids_mutex); + return err; +} +static unsigned int __init get_max_acpi_id(void) +{ + struct xenpf_pcpuinfo *info; + struct xen_platform_op op = { + .cmd = XENPF_get_cpuinfo, + .interface_version = XENPF_INTERFACE_VERSION, + }; + int ret = 0; + unsigned int i, last_cpu, max_acpi_id = 0; + + info = &op.u.pcpu_info; + info->xen_cpuid = 0; + + ret = HYPERVISOR_dom0_op(&op); + if (ret) + return NR_CPUS; + + /* The max_present is the same irregardless of the xen_cpuid */ + last_cpu = op.u.pcpu_info.max_present; + for (i = 0; i <= last_cpu; i++) { + info->xen_cpuid = i; + ret = HYPERVISOR_dom0_op(&op); + if (ret) + continue; + max_acpi_id = max(info->acpi_id, max_acpi_id); + } + max_acpi_id *= 2; /* Slack for CPU hotplug support. */ + pr_debug(DRV_NAME "Max ACPI ID: %u\n", max_acpi_id); + return max_acpi_id; +} +/* + * The read_acpi_id and check_acpi_ids are there to support the Xen + * oddity of virtual CPUs != physical CPUs in the initial domain. + * The user can supply 'xen_max_vcpus=X' on the Xen hypervisor line + * which will band the amount of CPUs the initial domain can see. + * In general that is OK, except it plays havoc with any of the + * for_each_[present|online]_cpu macros which are banded to the virtual + * CPU amount. + */ +static acpi_status __init +read_acpi_id(acpi_handle handle, u32 lvl, void *context, void **rv) +{ + u32 acpi_id; + acpi_status status; + acpi_object_type acpi_type; + unsigned long long tmp; + union acpi_object object = { 0 }; + struct acpi_buffer buffer = { sizeof(union acpi_object), &object }; + acpi_io_address pblk = 0; + + status = acpi_get_type(handle, &acpi_type); + if (ACPI_FAILURE(status)) + return AE_OK; + + switch (acpi_type) { + case ACPI_TYPE_PROCESSOR: + status = acpi_evaluate_object(handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) + return AE_OK; + acpi_id = object.processor.proc_id; + pblk = object.processor.pblk_address; + break; + case ACPI_TYPE_DEVICE: + status = acpi_evaluate_integer(handle, "_UID", NULL, &tmp); + if (ACPI_FAILURE(status)) + return AE_OK; + acpi_id = tmp; + break; + default: + return AE_OK; + } + /* There are more ACPI Processor objects than in x2APIC or MADT. + * This can happen with incorrect ACPI SSDT declerations. */ + if (acpi_id > nr_acpi_bits) { + pr_debug(DRV_NAME "We only have %u, trying to set %u\n", + nr_acpi_bits, acpi_id); + return AE_OK; + } + /* OK, There is a ACPI Processor object */ + __set_bit(acpi_id, acpi_id_present); + + pr_debug(DRV_NAME "ACPI CPU%u w/ PBLK:0x%lx\n", acpi_id, + (unsigned long)pblk); + + status = acpi_evaluate_object(handle, "_CST", NULL, &buffer); + if (ACPI_FAILURE(status)) { + if (!pblk) + return AE_OK; + } + /* .. and it has a C-state */ + __set_bit(acpi_id, acpi_id_cst_present); + + return AE_OK; +} +static int __init check_acpi_ids(struct acpi_processor *pr_backup) +{ + + if (!pr_backup) + return -ENODEV; + + /* All online CPUs have been processed at this stage. Now verify + * whether in fact "online CPUs" == physical CPUs. + */ + acpi_id_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); + if (!acpi_id_present) + return -ENOMEM; + + acpi_id_cst_present = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); + if (!acpi_id_cst_present) { + kfree(acpi_id_present); + return -ENOMEM; + } + + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, + read_acpi_id, NULL, NULL, NULL); + acpi_get_devices("ACPI0007", read_acpi_id, NULL, NULL); + + if (!bitmap_equal(acpi_id_present, acpi_ids_done, nr_acpi_bits)) { + unsigned int i; + for_each_set_bit(i, acpi_id_present, nr_acpi_bits) { + pr_backup->acpi_id = i; + /* Mask out C-states if there are no _CST or PBLK */ + pr_backup->flags.power = test_bit(i, acpi_id_cst_present); + (void)upload_pm_data(pr_backup); + } + } + kfree(acpi_id_present); + acpi_id_present = NULL; + kfree(acpi_id_cst_present); + acpi_id_cst_present = NULL; + return 0; +} +static int __init check_prereq(void) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + if (!xen_initial_domain()) + return -ENODEV; + + if (!acpi_gbl_FADT.smi_command) + return -ENODEV; + + if (c->x86_vendor == X86_VENDOR_INTEL) { + if (!cpu_has(c, X86_FEATURE_EST)) + return -ENODEV; + + return 0; + } + if (c->x86_vendor == X86_VENDOR_AMD) { + /* Copied from powernow-k8.h, can't include ../cpufreq/powernow + * as we get compile warnings for the static functions. + */ +#define CPUID_FREQ_VOLT_CAPABILITIES 0x80000007 +#define USE_HW_PSTATE 0x00000080 + u32 eax, ebx, ecx, edx; + cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); + if ((edx & USE_HW_PSTATE) != USE_HW_PSTATE) + return -ENODEV; + return 0; + } + return -ENODEV; +} +/* acpi_perf_data is a pointer to percpu data. */ +static struct acpi_processor_performance __percpu *acpi_perf_data; + +static void free_acpi_perf_data(void) +{ + unsigned int i; + + /* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */ + for_each_possible_cpu(i) + free_cpumask_var(per_cpu_ptr(acpi_perf_data, i) + ->shared_cpu_map); + free_percpu(acpi_perf_data); +} + +static int __init xen_acpi_processor_init(void) +{ + struct acpi_processor *pr_backup = NULL; + unsigned int i; + int rc = check_prereq(); + + if (rc) + return rc; + + nr_acpi_bits = get_max_acpi_id() + 1; + acpi_ids_done = kcalloc(BITS_TO_LONGS(nr_acpi_bits), sizeof(unsigned long), GFP_KERNEL); + if (!acpi_ids_done) + return -ENOMEM; + + acpi_perf_data = alloc_percpu(struct acpi_processor_performance); + if (!acpi_perf_data) { + pr_debug(DRV_NAME "Memory allocation error for acpi_perf_data.\n"); + kfree(acpi_ids_done); + return -ENOMEM; + } + for_each_possible_cpu(i) { + if (!zalloc_cpumask_var_node( + &per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map, + GFP_KERNEL, cpu_to_node(i))) { + rc = -ENOMEM; + goto err_out; + } + } + + /* Do initialization in ACPI core. It is OK to fail here. */ + (void)acpi_processor_preregister_performance(acpi_perf_data); + + for_each_possible_cpu(i) { + struct acpi_processor_performance *perf; + + perf = per_cpu_ptr(acpi_perf_data, i); + rc = acpi_processor_register_performance(perf, i); + if (WARN_ON(rc)) + goto err_out; + } + rc = acpi_processor_notify_smm(THIS_MODULE); + if (WARN_ON(rc)) + goto err_unregister; + + for_each_possible_cpu(i) { + struct acpi_processor *_pr; + _pr = per_cpu(processors, i /* APIC ID */); + if (!_pr) + continue; + + if (!pr_backup) { + pr_backup = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL); + memcpy(pr_backup, _pr, sizeof(struct acpi_processor)); + } + (void)upload_pm_data(_pr); + } + rc = check_acpi_ids(pr_backup); + if (rc) + goto err_unregister; + + kfree(pr_backup); + + return 0; +err_unregister: + for_each_possible_cpu(i) { + struct acpi_processor_performance *perf; + perf = per_cpu_ptr(acpi_perf_data, i); + acpi_processor_unregister_performance(perf, i); + } +err_out: + /* Freeing a NULL pointer is OK: alloc_percpu zeroes. */ + free_acpi_perf_data(); + kfree(acpi_ids_done); + return rc; +} +static void __exit xen_acpi_processor_exit(void) +{ + int i; + + kfree(acpi_ids_done); + for_each_possible_cpu(i) { + struct acpi_processor_performance *perf; + perf = per_cpu_ptr(acpi_perf_data, i); + acpi_processor_unregister_performance(perf, i); + } + free_acpi_perf_data(); +} + +MODULE_AUTHOR("Konrad Rzeszutek Wilk "); +MODULE_DESCRIPTION("Xen ACPI Processor P-states (and Cx) driver which uploads PM data to Xen hypervisor"); +MODULE_LICENSE("GPL"); + +/* We want to be loaded before the CPU freq scaling drivers are loaded. + * They are loaded in late_initcall. */ +device_initcall(xen_acpi_processor_init); +module_exit(xen_acpi_processor_exit); diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h index 861b359b44a..486653f0dd8 100644 --- a/include/xen/interface/platform.h +++ b/include/xen/interface/platform.h @@ -298,6 +298,22 @@ struct xenpf_set_processor_pminfo { }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_set_processor_pminfo); +#define XENPF_get_cpuinfo 55 +struct xenpf_pcpuinfo { + /* IN */ + uint32_t xen_cpuid; + /* OUT */ + /* The maxium cpu_id that is present */ + uint32_t max_present; +#define XEN_PCPU_FLAGS_ONLINE 1 + /* Correponding xen_cpuid is not present*/ +#define XEN_PCPU_FLAGS_INVALID 2 + uint32_t flags; + uint32_t apic_id; + uint32_t acpi_id; +}; +DEFINE_GUEST_HANDLE_STRUCT(xenpf_pcpuinfo); + struct xen_platform_op { uint32_t cmd; uint32_t interface_version; /* XENPF_INTERFACE_VERSION */ @@ -313,6 +329,7 @@ struct xen_platform_op { struct xenpf_change_freq change_freq; struct xenpf_getidletime getidletime; struct xenpf_set_processor_pminfo set_pminfo; + struct xenpf_pcpuinfo pcpu_info; uint8_t pad[128]; } u; }; -- cgit v1.2.3