diff options
Diffstat (limited to 'arch/powerpc')
32 files changed, 1277 insertions, 542 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2729c6663d8..cdf7a0a6440 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -134,6 +134,7 @@ config PPC select GENERIC_IRQ_SHOW_LEVEL select HAVE_RCU_TABLE_FREE if SMP select HAVE_SYSCALL_TRACEPOINTS + select HAVE_BPF_JIT if (PPC64 && NET) config EARLY_PRINTK bool diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index b7212b619c5..b94740f36b1 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -154,7 +154,8 @@ core-y += arch/powerpc/kernel/ \ arch/powerpc/lib/ \ arch/powerpc/sysdev/ \ arch/powerpc/platforms/ \ - arch/powerpc/math-emu/ + arch/powerpc/math-emu/ \ + arch/powerpc/net/ core-$(CONFIG_XMON) += arch/powerpc/xmon/ core-$(CONFIG_KVM) += arch/powerpc/kvm/ diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 3d80c3e9cf6..12da77ec022 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -1,5 +1,4 @@ addnote -dtc empty.c hack-coff infblock.c diff --git a/arch/powerpc/boot/dtc-src/.gitignore b/arch/powerpc/boot/dtc-src/.gitignore deleted file mode 100644 index a7c3f94e5e7..00000000000 --- a/arch/powerpc/boot/dtc-src/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -dtc-lexer.lex.c -dtc-parser.tab.c -dtc-parser.tab.h diff --git a/arch/powerpc/boot/dts/p1022ds.dts b/arch/powerpc/boot/dts/p1022ds.dts index 4f685a779f4..98d9426d4b8 100644 --- a/arch/powerpc/boot/dts/p1022ds.dts +++ b/arch/powerpc/boot/dts/p1022ds.dts @@ -209,8 +209,10 @@ wm8776:codec@1a { compatible = "wlf,wm8776"; reg = <0x1a>; - /* MCLK source is a stand-alone oscillator */ - clock-frequency = <12288000>; + /* + * clock-frequency will be set by U-Boot if + * the clock is enabled. + */ }; }; @@ -280,7 +282,8 @@ codec-handle = <&wm8776>; fsl,playback-dma = <&dma00>; fsl,capture-dma = <&dma01>; - fsl,fifo-depth = <16>; + fsl,fifo-depth = <15>; + fsl,ssi-asynchronous; }; dma@c300 { diff --git a/arch/powerpc/configs/52xx/pcm030_defconfig b/arch/powerpc/configs/52xx/pcm030_defconfig index 7f7e4a87860..22e719575c6 100644 --- a/arch/powerpc/configs/52xx/pcm030_defconfig +++ b/arch/powerpc/configs/52xx/pcm030_defconfig @@ -85,7 +85,7 @@ CONFIG_USB_OHCI_HCD=m CONFIG_USB_OHCI_HCD_PPC_OF_BE=y # CONFIG_USB_OHCI_HCD_PCI is not set CONFIG_USB_STORAGE=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PCF8563=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 6472322bf13..185c292b0f1 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -141,7 +141,7 @@ CONFIG_USB_EHCI_TT_NEWSCHED=y # CONFIG_USB_EHCI_HCD_PPC_OF is not set CONFIG_USB_OHCI_HCD=m CONFIG_USB_STORAGE=m -CONFIG_RTC_CLASS=m +CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_PS3=m CONFIG_EXT2_FS=m CONFIG_EXT3_FS=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index c9f212b5f3d..80bc5de7ee1 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -148,7 +148,6 @@ CONFIG_SCSI_SAS_ATTRS=m CONFIG_SCSI_CXGB3_ISCSI=m CONFIG_SCSI_CXGB4_ISCSI=m CONFIG_SCSI_BNX2_ISCSI=m -CONFIG_SCSI_BNX2_ISCSI=m CONFIG_BE2ISCSI=m CONFIG_SCSI_IBMVSCSI=y CONFIG_SCSI_IBMVFC=m diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index fd3fd58bad8..7b589178be4 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -38,13 +38,6 @@ u64 memory_hotplug_max(void); #define memory_hotplug_max() memblock_end_of_DRAM() #endif -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) - #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index e472659d906..e980faae422 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -71,6 +71,42 @@ #define PPC_INST_ERATSX 0x7c000126 #define PPC_INST_ERATSX_DOT 0x7c000127 +/* Misc instructions for BPF compiler */ +#define PPC_INST_LD 0xe8000000 +#define PPC_INST_LHZ 0xa0000000 +#define PPC_INST_LWZ 0x80000000 +#define PPC_INST_STD 0xf8000000 +#define PPC_INST_STDU 0xf8000001 +#define PPC_INST_MFLR 0x7c0802a6 +#define PPC_INST_MTLR 0x7c0803a6 +#define PPC_INST_CMPWI 0x2c000000 +#define PPC_INST_CMPDI 0x2c200000 +#define PPC_INST_CMPLW 0x7c000040 +#define PPC_INST_CMPLWI 0x28000000 +#define PPC_INST_ADDI 0x38000000 +#define PPC_INST_ADDIS 0x3c000000 +#define PPC_INST_ADD 0x7c000214 +#define PPC_INST_SUB 0x7c000050 +#define PPC_INST_BLR 0x4e800020 +#define PPC_INST_BLRL 0x4e800021 +#define PPC_INST_MULLW 0x7c0001d6 +#define PPC_INST_MULHWU 0x7c000016 +#define PPC_INST_MULLI 0x1c000000 +#define PPC_INST_DIVWU 0x7c0003d6 +#define PPC_INST_RLWINM 0x54000000 +#define PPC_INST_RLDICR 0x78000004 +#define PPC_INST_SLW 0x7c000030 +#define PPC_INST_SRW 0x7c000430 +#define PPC_INST_AND 0x7c000038 +#define PPC_INST_ANDDOT 0x7c000039 +#define PPC_INST_OR 0x7c000378 +#define PPC_INST_ANDI 0x70000000 +#define PPC_INST_ORI 0x60000000 +#define PPC_INST_ORIS 0x64000000 +#define PPC_INST_NEG 0x7c0000d0 +#define PPC_INST_BRANCH 0x48000000 +#define PPC_INST_BRANCH_COND 0x40800000 + /* macros to insert fields into opcodes */ #define __PPC_RA(a) (((a) & 0x1f) << 16) #define __PPC_RB(b) (((b) & 0x1f) << 11) @@ -83,6 +119,10 @@ #define __PPC_T_TLB(t) (((t) & 0x3) << 21) #define __PPC_WC(w) (((w) & 0x3) << 21) #define __PPC_WS(w) (((w) & 0x1f) << 11) +#define __PPC_SH(s) __PPC_WS(s) +#define __PPC_MB(s) (((s) & 0x1f) << 6) +#define __PPC_ME(s) (((s) & 0x1f) << 1) +#define __PPC_BI(s) (((s) & 0x1f) << 16) /* * Only use the larx hint bit on 64bit CPUs. e500v1/v2 based CPUs will treat a diff --git a/arch/powerpc/include/asm/rio.h b/arch/powerpc/include/asm/rio.h index d902abd3399..b1d2deceeed 100644 --- a/arch/powerpc/include/asm/rio.h +++ b/arch/powerpc/include/asm/rio.h @@ -14,7 +14,7 @@ #define ASM_PPC_RIO_H extern void platform_rio_init(void); -#ifdef CONFIG_RAPIDIO +#ifdef CONFIG_FSL_RIO extern int fsl_rio_mcheck_exception(struct pt_regs *); #else static inline int fsl_rio_mcheck_exception(struct pt_regs *regs) {return 0; } diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 34d2722b945..9fb933248ab 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1979,7 +1979,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .pvr_value = 0x80240000, .cpu_name = "e5500", .cpu_features = CPU_FTRS_E5500, - .cpu_user_features = COMMON_USER_BOOKE, + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .mmu_features = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS | MMU_FTR_USE_TLBILX, .icache_bsize = 64, diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index f2c906b1d8d..8c3112a57cf 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -82,11 +82,29 @@ static int __init early_parse_mem(char *p) } early_param("mem", early_parse_mem); +/* + * overlaps_initrd - check for overlap with page aligned extension of + * initrd. + */ +static inline int overlaps_initrd(unsigned long start, unsigned long size) +{ +#ifdef CONFIG_BLK_DEV_INITRD + if (!initrd_start) + return 0; + + return (start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) && + start <= _ALIGN_UP(initrd_end, PAGE_SIZE); +#else + return 0; +#endif +} + /** * move_device_tree - move tree to an unused area, if needed. * * The device tree may be allocated beyond our memory limit, or inside the - * crash kernel region for kdump. If so, move it out of the way. + * crash kernel region for kdump, or within the page aligned range of initrd. + * If so, move it out of the way. */ static void __init move_device_tree(void) { @@ -99,7 +117,8 @@ static void __init move_device_tree(void) size = be32_to_cpu(initial_boot_params->totalsize); if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || - overlaps_crashkernel(start, size)) { + overlaps_crashkernel(start, size) || + overlaps_initrd(start, size)) { p = __va(memblock_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); initial_boot_params = (struct boot_param_header *)p; @@ -555,7 +574,9 @@ static void __init early_reserve_mem(void) #ifdef CONFIG_BLK_DEV_INITRD /* then reserve the initrd, if any */ if (initrd_start && (initrd_end > initrd_start)) - memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); + memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE), + _ALIGN_UP(initrd_end, PAGE_SIZE) - + _ALIGN_DOWN(initrd_start, PAGE_SIZE)); #endif /* CONFIG_BLK_DEV_INITRD */ #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c index 77578c093dd..c57c19358a2 100644 --- a/arch/powerpc/kernel/rtas-rtc.c +++ b/arch/powerpc/kernel/rtas-rtc.c @@ -4,6 +4,7 @@ #include <linux/init.h> #include <linux/rtc.h> #include <linux/delay.h> +#include <linux/ratelimit.h> #include <asm/prom.h> #include <asm/rtas.h> #include <asm/time.h> @@ -29,9 +30,10 @@ unsigned long __init rtas_get_boot_time(void) } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) { - printk(KERN_WARNING "error: reading the clock failed (%d)\n", - error); + if (error != 0) { + printk_ratelimited(KERN_WARNING + "error: reading the clock failed (%d)\n", + error); return 0; } @@ -55,19 +57,21 @@ void rtas_get_rtc_time(struct rtc_time *rtc_tm) wait_time = rtas_busy_delay_time(error); if (wait_time) { - if (in_interrupt() && printk_ratelimit()) { + if (in_interrupt()) { memset(rtc_tm, 0, sizeof(struct rtc_time)); - printk(KERN_WARNING "error: reading clock" - " would delay interrupt\n"); + printk_ratelimited(KERN_WARNING + "error: reading clock " + "would delay interrupt\n"); return; /* delay not allowed */ } msleep(wait_time); } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) { - printk(KERN_WARNING "error: reading the clock failed (%d)\n", - error); + if (error != 0) { + printk_ratelimited(KERN_WARNING + "error: reading the clock failed (%d)\n", + error); return; } @@ -99,9 +103,10 @@ int rtas_set_rtc_time(struct rtc_time *tm) } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) - printk(KERN_WARNING "error: setting the clock failed (%d)\n", - error); + if (error != 0) + printk_ratelimited(KERN_WARNING + "error: setting the clock failed (%d)\n", + error); return 0; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b96a3a010c2..78b76dc54df 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -25,6 +25,7 @@ #include <linux/errno.h> #include <linux/elf.h> #include <linux/ptrace.h> +#include <linux/ratelimit.h> #ifdef CONFIG_PPC64 #include <linux/syscalls.h> #include <linux/compat.h> @@ -892,11 +893,12 @@ badframe: printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - addr, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in handle_rt_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); force_sigsegv(sig, current); return 0; @@ -1058,11 +1060,12 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; bad: - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in sys_rt_sigreturn: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - rt_sf, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in sys_rt_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + rt_sf, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; @@ -1149,12 +1152,12 @@ int sys_debug_setcontext(struct ucontext __user *ctx, * We kill the task with a SIGSEGV in this situation. */ if (do_setcontext(ctx, regs, 1)) { - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in " - "sys_debug_setcontext: %p nip %08lx " - "lr %08lx\n", - current->comm, current->pid, - ctx, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO "%s[%d]: bad frame in " + "sys_debug_setcontext: %p nip %08lx " + "lr %08lx\n", + current->comm, current->pid, + ctx, regs->nip, regs->link); force_sig(SIGSEGV, current); goto out; @@ -1236,11 +1239,12 @@ badframe: printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in handle_signal32: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - frame, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in handle_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + frame, regs->nip, regs->link); force_sigsegv(sig, current); return 0; @@ -1288,11 +1292,12 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; badframe: - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in sys_sigreturn: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - addr, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in sys_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index da989fff19c..e91c736cc84 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -24,6 +24,7 @@ #include <linux/elf.h> #include <linux/ptrace.h> #include <linux/module.h> +#include <linux/ratelimit.h> #include <asm/sigcontext.h> #include <asm/ucontext.h> @@ -380,10 +381,10 @@ badframe: printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n", regs, uc, &uc->uc_mcontext); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, "rt_sigreturn", - (long)uc, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, "rt_sigreturn", + (long)uc, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; @@ -468,10 +469,10 @@ badframe: printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, "setup_rt_frame", - (long)frame, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, "setup_rt_frame", + (long)frame, regs->nip, regs->link); force_sigsegv(signr, current); return 0; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0ff4ab98d50..1a0141426cd 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -34,6 +34,7 @@ #include <linux/bug.h> #include <linux/kdebug.h> #include <linux/debugfs.h> +#include <linux/ratelimit.h> #include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -197,12 +198,11 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (die("Exception in kernel mode", regs, signr)) return; } else if (show_unhandled_signals && - unhandled_signal(current, signr) && - printk_ratelimit()) { - printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, signr, - addr, regs->nip, regs->link, code); - } + unhandled_signal(current, signr)) { + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, signr, + addr, regs->nip, regs->link, code); + } memset(&info, 0, sizeof(info)); info.si_signo = signr; @@ -425,7 +425,7 @@ int machine_check_e500mc(struct pt_regs *regs) unsigned long reason = mcsr; int recoverable = 1; - if (reason & MCSR_BUS_RBERR) { + if (reason & MCSR_LD) { recoverable = fsl_rio_mcheck_exception(regs); if (recoverable == 1) goto silent_out; @@ -1342,9 +1342,8 @@ void altivec_assist_exception(struct pt_regs *regs) } else { /* didn't recognize the instruction */ /* XXX quick hack for now: set the non-Java bit in the VSCR */ - if (printk_ratelimit()) - printk(KERN_ERR "Unrecognized altivec instruction " - "in %s at %lx\n", current->comm, regs->nip); + printk_ratelimited(KERN_ERR "Unrecognized altivec instruction " + "in %s at %lx\n", current->comm, regs->nip); current->thread.vscr.u[3] |= 0x10000; } } @@ -1548,9 +1547,8 @@ u32 ppc_warn_emulated; void ppc_warn_emulated_print(const char *type) { - if (printk_ratelimit()) - pr_warning("%s used emulated %s instruction\n", current->comm, - type); + pr_warn_ratelimited("%s used emulated %s instruction\n", current->comm, + type); } static int __init ppc_warn_emulated_init(void) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 54f4fb994e9..ad35f66c69e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -31,6 +31,7 @@ #include <linux/kdebug.h> #include <linux/perf_event.h> #include <linux/magic.h> +#include <linux/ratelimit.h> #include <asm/firmware.h> #include <asm/page.h> @@ -346,11 +347,10 @@ bad_area_nosemaphore: return 0; } - if (is_exec && (error_code & DSISR_PROTFAULT) - && printk_ratelimit()) - printk(KERN_CRIT "kernel tried to execute NX-protected" - " page (%lx) - exploit attempt? (uid: %d)\n", - address, current_uid()); + if (is_exec && (error_code & DSISR_PROTFAULT)) + printk_ratelimited(KERN_CRIT "kernel tried to execute NX-protected" + " page (%lx) - exploit attempt? (uid: %d)\n", + address, current_uid()); return SIGSEGV; diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index d65b591e555..5de0f254dbb 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -223,21 +223,6 @@ void free_initmem(void) #undef FREESEC } -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - if (start < end) - printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } -} -#endif - - #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */ void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 6374b2196a1..f6dbb4c20e6 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -99,20 +99,6 @@ void free_initmem(void) ((unsigned long)__init_end - (unsigned long)__init_begin) >> 10); } -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - if (start < end) - printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - init_page_count(virt_to_page(start)); - free_page(start); - totalram_pages++; - } -} -#endif - static void pgd_ctor(void *addr) { memset(addr, 0, PGD_TABLE_SIZE); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 57e545b84bf..29d4dde65c4 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -382,6 +382,25 @@ void __init mem_init(void) mem_init_done = 1; } +#ifdef CONFIG_BLK_DEV_INITRD +void __init free_initrd_mem(unsigned long start, unsigned long end) +{ + if (start >= end) + return; + + start = _ALIGN_DOWN(start, PAGE_SIZE); + end = _ALIGN_UP(end, PAGE_SIZE); + pr_info("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + + for (; start < end; start += PAGE_SIZE) { + ClearPageReserved(virt_to_page(start)); + init_page_count(virt_to_page(start)); + free_page(start); + totalram_pages++; + } +} +#endif + /* * This is called when a page has been modified by the kernel. * It just marks the page as not i-cache clean. We do the i-cache diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile new file mode 100644 index 00000000000..266b3950c3a --- /dev/null +++ b/arch/powerpc/net/Makefile @@ -0,0 +1,4 @@ +# +# Arch-specific network modules +# +obj-$(CONFIG_BPF_JIT) += bpf_jit_64.o bpf_jit_comp.o diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h new file mode 100644 index 00000000000..af1ab5e9a69 --- /dev/null +++ b/arch/powerpc/net/bpf_jit.h @@ -0,0 +1,227 @@ +/* bpf_jit.h: BPF JIT compiler for PPC64 + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#define BPF_PPC_STACK_LOCALS 32 +#define BPF_PPC_STACK_BASIC (48+64) +#define BPF_PPC_STACK_SAVE (18*8) +#define BPF_PPC_STACKFRAME (BPF_PPC_STACK_BASIC+BPF_PPC_STACK_LOCALS+ \ + BPF_PPC_STACK_SAVE) +#define BPF_PPC_SLOWPATH_FRAME (48+64) + +/* + * Generated code register usage: + * + * As normal PPC C ABI (e.g. r1=sp, r2=TOC), with: + * + * skb r3 (Entry parameter) + * A register r4 + * X register r5 + * addr param r6 + * r7-r10 scratch + * skb->data r14 + * skb headlen r15 (skb->len - skb->data_len) + * m[0] r16 + * m[...] ... + * m[15] r31 + */ +#define r_skb 3 +#define r_ret 3 +#define r_A 4 +#define r_X 5 +#define r_addr 6 +#define r_scratch1 7 +#define r_D 14 +#define r_HL 15 +#define r_M 16 + +#ifndef __ASSEMBLY__ + +/* + * Assembly helpers from arch/powerpc/net/bpf_jit.S: + */ +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; + +#define FUNCTION_DESCR_SIZE 24 + +/* + * 16-bit immediate helper macros: HA() is for use with sign-extending instrs + * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the + * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). + */ +#define IMM_H(i) ((uintptr_t)(i)>>16) +#define IMM_HA(i) (((uintptr_t)(i)>>16) + \ + (((uintptr_t)(i) & 0x8000) >> 15)) +#define IMM_L(i) ((uintptr_t)(i) & 0xffff) + +#define PLANT_INSTR(d, idx, instr) \ + do { if (d) { (d)[idx] = instr; } idx++; } while (0) +#define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) + +#define PPC_NOP() EMIT(PPC_INST_NOP) +#define PPC_BLR() EMIT(PPC_INST_BLR) +#define PPC_BLRL() EMIT(PPC_INST_BLRL) +#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | __PPC_RT(r)) +#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | __PPC_RT(d) | \ + __PPC_RA(a) | IMM_L(i)) +#define PPC_MR(d, a) PPC_OR(d, a, a) +#define PPC_LI(r, i) PPC_ADDI(r, 0, i) +#define PPC_ADDIS(d, a, i) EMIT(PPC_INST_ADDIS | \ + __PPC_RS(d) | __PPC_RA(a) | IMM_L(i)) +#define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) +#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | __PPC_RS(r) | \ + __PPC_RA(base) | ((i) & 0xfffc)) + +#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | __PPC_RT(r) | \ + __PPC_RA(base) | IMM_L(i)) +/* Convenience helpers for the above with 'far' offsets: */ +#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LD(r, r, IMM_L(i)); } } while(0) + +#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LWZ(r, r, IMM_L(i)); } } while(0) + +#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i); \ + else { PPC_ADDIS(r, base, IMM_HA(i)); \ + PPC_LHZ(r, r, IMM_L(i)); } } while(0) + +#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | __PPC_RA(a) | IMM_L(i)) +#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | __PPC_RA(a) | __PPC_RB(b)) + +#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | __PPC_RT(d) | \ + __PPC_RB(a) | __PPC_RA(b)) +#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MUL(d, a, b) EMIT(PPC_INST_MULLW | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | __PPC_RT(d) | \ + __PPC_RA(a) | IMM_L(i)) +#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | __PPC_RT(d) | \ + __PPC_RA(a) | __PPC_RB(b)) +#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(b)) +#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | __PPC_RA(d) | \ + __PPC_RS(a) | IMM_L(i)) +#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(s)) +#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_RB(s)) +/* slwi = rlwinm Rx, Ry, n, 0, 31-n */ +#define PPC_SLWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(i) | \ + __PPC_MB(0) | __PPC_ME(31-(i))) +/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ +#define PPC_SRWI(d, a, i) EMIT(PPC_INST_RLWINM | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(32-(i)) | \ + __PPC_MB(i) | __PPC_ME(31)) +/* sldi = rldicr Rx, Ry, n, 63-n */ +#define PPC_SLDI(d, a, i) EMIT(PPC_INST_RLDICR | __PPC_RA(d) | \ + __PPC_RS(a) | __PPC_SH(i) | \ + __PPC_MB(63-(i)) | (((i) & 0x20) >> 4)) +#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | __PPC_RT(d) | __PPC_RA(a)) + +/* Long jump; (unconditional 'branch') */ +#define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ + (((dest) - (ctx->idx * 4)) & 0x03fffffc)) +/* "cond" here covers BO:BI fields. */ +#define PPC_BCC_SHORT(cond, dest) EMIT(PPC_INST_BRANCH_COND | \ + (((cond) & 0x3ff) << 16) | \ + (((dest) - (ctx->idx * 4)) & \ + 0xfffc)) +#define PPC_LI32(d, i) do { PPC_LI(d, IMM_L(i)); \ + if ((u32)(uintptr_t)(i) >= 32768) { \ + PPC_ADDIS(d, d, IMM_HA(i)); \ + } } while(0) +#define PPC_LI64(d, i) do { \ + if (!((uintptr_t)(i) & 0xffffffff00000000ULL)) \ + PPC_LI32(d, i); \ + else { \ + PPC_LIS(d, ((uintptr_t)(i) >> 48)); \ + if ((uintptr_t)(i) & 0x0000ffff00000000ULL) \ + PPC_ORI(d, d, \ + ((uintptr_t)(i) >> 32) & 0xffff); \ + PPC_SLDI(d, d, 32); \ + if ((uintptr_t)(i) & 0x00000000ffff0000ULL) \ + PPC_ORIS(d, d, \ + ((uintptr_t)(i) >> 16) & 0xffff); \ + if ((uintptr_t)(i) & 0x000000000000ffffULL) \ + PPC_ORI(d, d, (uintptr_t)(i) & 0xffff); \ + } } while (0); + +static inline bool is_nearbranch(int offset) +{ + return (offset < 32768) && (offset >= -32768); +} + +/* + * The fly in the ointment of code size changing from pass to pass is + * avoided by padding the short branch case with a NOP. If code size differs + * with different branch reaches we will have the issue of code moving from + * one pass to the next and will need a few passes to converge on a stable + * state. + */ +#define PPC_BCC(cond, dest) do { \ + if (is_nearbranch((dest) - (ctx->idx * 4))) { \ + PPC_BCC_SHORT(cond, dest); \ + PPC_NOP(); \ + } else { \ + /* Flip the 'T or F' bit to invert comparison */ \ + PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \ + PPC_JMP(dest); \ + } } while(0) + +/* To create a branch condition, select a bit of cr0... */ +#define CR0_LT 0 +#define CR0_GT 1 +#define CR0_EQ 2 +/* ...and modify BO[3] */ +#define COND_CMP_TRUE 0x100 +#define COND_CMP_FALSE 0x000 +/* Together, they make all required comparisons: */ +#define COND_GT (CR0_GT | COND_CMP_TRUE) +#define COND_GE (CR0_LT | COND_CMP_FALSE) +#define COND_EQ (CR0_EQ | COND_CMP_TRUE) +#define COND_NE (CR0_EQ | COND_CMP_FALSE) +#define COND_LT (CR0_LT | COND_CMP_TRUE) + +#define SEEN_DATAREF 0x10000 /* might call external helpers */ +#define SEEN_XREG 0x20000 /* X reg is used */ +#define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary + * storage */ +#define SEEN_MEM_MSK 0x0ffff + +struct codegen_context { + unsigned int seen; + unsigned int idx; + int pc_ret0; /* bpf index of first RET #0 instruction (if any) */ +}; + +#endif + +#endif diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S new file mode 100644 index 00000000000..ff4506e85cc --- /dev/null +++ b/arch/powerpc/net/bpf_jit_64.S @@ -0,0 +1,138 @@ +/* bpf_jit.S: Packet/header access helper functions + * for PPC64 BPF compiler. + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <asm/ppc_asm.h> +#include "bpf_jit.h" + +/* + * All of these routines are called directly from generated code, + * whose register usage is: + * + * r3 skb + * r4,r5 A,X + * r6 *** address parameter to helper *** + * r7-r10 scratch + * r14 skb->data + * r15 skb headlen + * r16-31 M[] + */ + +/* + * To consider: These helpers are so small it could be better to just + * generate them inline. Inline code can do the simple headlen check + * then branch directly to slow_path_XXX if required. (In fact, could + * load a spare GPR with the address of slow_path_generic and pass size + * as an argument, making the call site a mtlr, li and bllr.) + * + * Technically, the "is addr < 0" check is unnecessary & slowing down + * the ABS path, as it's statically checked on generation. + */ + .globl sk_load_word +sk_load_word: + cmpdi r_addr, 0 + blt bpf_error + /* Are we accessing past headlen? */ + subi r_scratch1, r_HL, 4 + cmpd r_scratch1, r_addr + blt bpf_slow_path_word + /* Nope, just hitting the header. cr0 here is eq or gt! */ + lwzx r_A, r_D, r_addr + /* When big endian we don't need to byteswap. */ + blr /* Return success, cr0 != LT */ + + .globl sk_load_half +sk_load_half: + cmpdi r_addr, 0 + blt bpf_error + subi r_scratch1, r_HL, 2 + cmpd r_scratch1, r_addr + blt bpf_slow_path_half + lhzx r_A, r_D, r_addr + blr + + .globl sk_load_byte +sk_load_byte: + cmpdi r_addr, 0 + blt bpf_error + cmpd r_HL, r_addr + ble bpf_slow_path_byte + lbzx r_A, r_D, r_addr + blr + +/* + * BPF_S_LDX_B_MSH: ldxb 4*([offset]&0xf) + * r_addr is the offset value, already known positive + */ + .globl sk_load_byte_msh +sk_load_byte_msh: + cmpd r_HL, r_addr + ble bpf_slow_path_byte_msh + lbzx r_X, r_D, r_addr + rlwinm r_X, r_X, 2, 32-4-2, 31-2 + blr + +bpf_error: + /* Entered with cr0 = lt */ + li r3, 0 + /* Generated code will 'blt epilogue', returning 0. */ + blr + +/* Call out to skb_copy_bits: + * We'll need to back up our volatile regs first; we have + * local variable space at r1+(BPF_PPC_STACK_BASIC). + * Allocate a new stack frame here to remain ABI-compliant in + * stashing LR. + */ +#define bpf_slow_path_common(SIZE) \ + mflr r0; \ + std r0, 16(r1); \ + /* R3 goes in parameter space of caller's frame */ \ + std r_skb, (BPF_PPC_STACKFRAME+48)(r1); \ + std r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \ + std r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \ + addi r5, r1, BPF_PPC_STACK_BASIC+(2*8); \ + stdu r1, -BPF_PPC_SLOWPATH_FRAME(r1); \ + /* R3 = r_skb, as passed */ \ + mr r4, r_addr; \ + li r6, SIZE; \ + bl skb_copy_bits; \ + /* R3 = 0 on success */ \ + addi r1, r1, BPF_PPC_SLOWPATH_FRAME; \ + ld r0, 16(r1); \ + ld r_A, (BPF_PPC_STACK_BASIC+(0*8))(r1); \ + ld r_X, (BPF_PPC_STACK_BASIC+(1*8))(r1); \ + mtlr r0; \ + cmpdi r3, 0; \ + blt bpf_error; /* cr0 = LT */ \ + ld r_skb, (BPF_PPC_STACKFRAME+48)(r1); \ + /* Great success! */ + +bpf_slow_path_word: + bpf_slow_path_common(4) + /* Data value is on stack, and cr0 != LT */ + lwz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_half: + bpf_slow_path_common(2) + lhz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_byte: + bpf_slow_path_common(1) + lbz r_A, BPF_PPC_STACK_BASIC+(2*8)(r1) + blr + +bpf_slow_path_byte_msh: + bpf_slow_path_common(1) + lbz r_X, BPF_PPC_STACK_BASIC+(2*8)(r1) + rlwinm r_X, r_X, 2, 32-4-2, 31-2 + blr diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c new file mode 100644 index 00000000000..73619d3aeb6 --- /dev/null +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -0,0 +1,694 @@ +/* bpf_jit_comp.c: BPF JIT compiler for PPC64 + * + * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation + * + * Based on the x86 BPF compiler, by Eric Dumazet (eric.dumazet@gmail.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ +#include <linux/moduleloader.h> +#include <asm/cacheflush.h> +#include <linux/netdevice.h> +#include <linux/filter.h> +#include "bpf_jit.h" + +#ifndef __BIG_ENDIAN +/* There are endianness assumptions herein. */ +#error "Little-endian PPC not supported in BPF compiler" +#endif + +int bpf_jit_enable __read_mostly; + + +static inline void bpf_flush_icache(void *start, void *end) +{ + smp_wmb(); + flush_icache_range((unsigned long)start, (unsigned long)end); +} + +static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image, + struct codegen_context *ctx) +{ + int i; + const struct sock_filter *filter = fp->insns; + + if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { + /* Make stackframe */ + if (ctx->seen & SEEN_DATAREF) { + /* If we call any helpers (for loads), save LR */ + EMIT(PPC_INST_MFLR | __PPC_RT(0)); + PPC_STD(0, 1, 16); + + /* Back up non-volatile regs. */ + PPC_STD(r_D, 1, -(8*(32-r_D))); + PPC_STD(r_HL, 1, -(8*(32-r_HL))); + } + if (ctx->seen & SEEN_MEM) { + /* + * Conditionally save regs r15-r31 as some will be used + * for M[] data. + */ + for (i = r_M; i < (r_M+16); i++) { + if (ctx->seen & (1 << (i-r_M))) + PPC_STD(i, 1, -(8*(32-i))); + } + } + EMIT(PPC_INST_STDU | __PPC_RS(1) | __PPC_RA(1) | + (-BPF_PPC_STACKFRAME & 0xfffc)); + } + + if (ctx->seen & SEEN_DATAREF) { + /* + * If this filter needs to access skb data, + * prepare r_D and r_HL: + * r_HL = skb->len - skb->data_len + * r_D = skb->data + */ + PPC_LWZ_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, + data_len)); + PPC_LWZ_OFFS(r_HL, r_skb, offsetof(struct sk_buff, len)); + PPC_SUB(r_HL, r_HL, r_scratch1); + PPC_LD_OFFS(r_D, r_skb, offsetof(struct sk_buff, data)); + } + + if (ctx->seen & SEEN_XREG) { + /* + * TODO: Could also detect whether first instr. sets X and + * avoid this (as below, with A). + */ + PPC_LI(r_X, 0); + } + + switch (filter[0].code) { + case BPF_S_RET_K: + case BPF_S_LD_W_LEN: + case BPF_S_ANC_PROTOCOL: + case BPF_S_ANC_IFINDEX: + case BPF_S_ANC_MARK: + case BPF_S_ANC_RXHASH: + case BPF_S_ANC_CPU: + case BPF_S_ANC_QUEUE: + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: + /* first instruction sets A register (or is RET 'constant') */ + break; + default: + /* make sure we dont leak kernel information to user */ + PPC_LI(r_A, 0); + } +} + +static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +{ + int i; + + if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { + PPC_ADDI(1, 1, BPF_PPC_STACKFRAME); + if (ctx->seen & SEEN_DATAREF) { + PPC_LD(0, 1, 16); + PPC_MTLR(0); + PPC_LD(r_D, 1, -(8*(32-r_D))); + PPC_LD(r_HL, 1, -(8*(32-r_HL))); + } + if (ctx->seen & SEEN_MEM) { + /* Restore any saved non-vol registers */ + for (i = r_M; i < (r_M+16); i++) { + if (ctx->seen & (1 << (i-r_M))) + PPC_LD(i, 1, -(8*(32-i))); + } + } + } + /* The RETs have left a return value in R3. */ + + PPC_BLR(); +} + +/* Assemble the body code between the prologue & epilogue. */ +static int bpf_jit_build_body(struct sk_filter *fp, u32 *image, + struct codegen_context *ctx, + unsigned int *addrs) +{ + const struct sock_filter *filter = fp->insns; + int flen = fp->len; + u8 *func; + unsigned int true_cond; + int i; + + /* Start of epilogue code */ + unsigned int exit_addr = addrs[flen]; + + for (i = 0; i < flen; i++) { + unsigned int K = filter[i].k; + + /* + * addrs[] maps a BPF bytecode address into a real offset from + * the start of the body code. + */ + addrs[i] = ctx->idx * 4; + + switch (filter[i].code) { + /*** ALU ops ***/ + case BPF_S_ALU_ADD_X: /* A += X; */ + ctx->seen |= SEEN_XREG; + PPC_ADD(r_A, r_A, r_X); + break; + case BPF_S_ALU_ADD_K: /* A += K; */ + if (!K) + break; + PPC_ADDI(r_A, r_A, IMM_L(K)); + if (K >= 32768) + PPC_ADDIS(r_A, r_A, IMM_HA(K)); + break; + case BPF_S_ALU_SUB_X: /* A -= X; */ + ctx->seen |= SEEN_XREG; + PPC_SUB(r_A, r_A, r_X); + break; + case BPF_S_ALU_SUB_K: /* A -= K */ + if (!K) + break; + PPC_ADDI(r_A, r_A, IMM_L(-K)); + if (K >= 32768) + PPC_ADDIS(r_A, r_A, IMM_HA(-K)); + break; + case BPF_S_ALU_MUL_X: /* A *= X; */ + ctx->seen |= SEEN_XREG; + PPC_MUL(r_A, r_A, r_X); + break; + case BPF_S_ALU_MUL_K: /* A *= K */ + if (K < 32768) + PPC_MULI(r_A, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_MUL(r_A, r_A, r_scratch1); + } + break; + case BPF_S_ALU_DIV_X: /* A /= X; */ + ctx->seen |= SEEN_XREG; + PPC_CMPWI(r_X, 0); + if (ctx->pc_ret0 != -1) { + PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); + } else { + /* + * Exit, returning 0; first pass hits here + * (longer worst-case code size). + */ + PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); + PPC_LI(r_ret, 0); + PPC_JMP(exit_addr); + } + PPC_DIVWU(r_A, r_A, r_X); + break; + case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ + PPC_LI32(r_scratch1, K); + /* Top 32 bits of 64bit result -> A */ + PPC_MULHWU(r_A, r_A, r_scratch1); + break; + case BPF_S_ALU_AND_X: + ctx->seen |= SEEN_XREG; + PPC_AND(r_A, r_A, r_X); + break; + case BPF_S_ALU_AND_K: + if (!IMM_H(K)) + PPC_ANDI(r_A, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_AND(r_A, r_A, r_scratch1); + } + break; + case BPF_S_ALU_OR_X: + ctx->seen |= SEEN_XREG; + PPC_OR(r_A, r_A, r_X); + break; + case BPF_S_ALU_OR_K: + if (IMM_L(K)) + PPC_ORI(r_A, r_A, IMM_L(K)); + if (K >= 65536) + PPC_ORIS(r_A, r_A, IMM_H(K)); + break; + case BPF_S_ALU_LSH_X: /* A <<= X; */ + ctx->seen |= SEEN_XREG; + PPC_SLW(r_A, r_A, r_X); + break; + case BPF_S_ALU_LSH_K: + if (K == 0) + break; + else + PPC_SLWI(r_A, r_A, K); + break; + case BPF_S_ALU_RSH_X: /* A >>= X; */ + ctx->seen |= SEEN_XREG; + PPC_SRW(r_A, r_A, r_X); + break; + case BPF_S_ALU_RSH_K: /* A >>= K; */ + if (K == 0) + break; + else + PPC_SRWI(r_A, r_A, K); + break; + case BPF_S_ALU_NEG: + PPC_NEG(r_A, r_A); + break; + case BPF_S_RET_K: + PPC_LI32(r_ret, K); + if (!K) { + if (ctx->pc_ret0 == -1) + ctx->pc_ret0 = i; + } + /* + * If this isn't the very last instruction, branch to + * the epilogue if we've stuff to clean up. Otherwise, + * if there's nothing to tidy, just return. If we /are/ + * the last instruction, we're about to fall through to + * the epilogue to return. + */ + if (i != flen - 1) { + /* + * Note: 'seen' is properly valid only on pass + * #2. Both parts of this conditional are the + * same instruction size though, meaning the + * first pass will still correctly determine the + * code size/addresses. + */ + if (ctx->seen) + PPC_JMP(exit_addr); + else + PPC_BLR(); + } + break; + case BPF_S_RET_A: + PPC_MR(r_ret, r_A); + if (i != flen - 1) { + if (ctx->seen) + PPC_JMP(exit_addr); + else + PPC_BLR(); + } + break; + case BPF_S_MISC_TAX: /* X = A */ + PPC_MR(r_X, r_A); + break; + case BPF_S_MISC_TXA: /* A = X */ + ctx->seen |= SEEN_XREG; + PPC_MR(r_A, r_X); + break; + + /*** Constant loads/M[] access ***/ + case BPF_S_LD_IMM: /* A = K */ + PPC_LI32(r_A, K); + break; + case BPF_S_LDX_IMM: /* X = K */ + PPC_LI32(r_X, K); + break; + case BPF_S_LD_MEM: /* A = mem[K] */ + PPC_MR(r_A, r_M + (K & 0xf)); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_LDX_MEM: /* X = mem[K] */ + PPC_MR(r_X, r_M + (K & 0xf)); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_ST: /* mem[K] = A */ + PPC_MR(r_M + (K & 0xf), r_A); + ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_STX: /* mem[K] = X */ + PPC_MR(r_M + (K & 0xf), r_X); + ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); + break; + case BPF_S_LD_W_LEN: /* A = skb->len; */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, len)); + break; + case BPF_S_LDX_W_LEN: /* X = skb->len; */ + PPC_LWZ_OFFS(r_X, r_skb, offsetof(struct sk_buff, len)); + break; + + /*** Ancillary info loads ***/ + + /* None of the BPF_S_ANC* codes appear to be passed by + * sk_chk_filter(). The interpreter and the x86 BPF + * compiler implement them so we do too -- they may be + * planted in future. + */ + case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + protocol) != 2); + PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + protocol)); + /* ntohs is a NOP with BE loads. */ + break; + case BPF_S_ANC_IFINDEX: + PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, + dev)); + PPC_CMPDI(r_scratch1, 0); + if (ctx->pc_ret0 != -1) { + PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); + } else { + /* Exit, returning 0; first pass hits here. */ + PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); + PPC_LI(r_ret, 0); + PPC_JMP(exit_addr); + } + BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, + ifindex) != 4); + PPC_LWZ_OFFS(r_A, r_scratch1, + offsetof(struct net_device, ifindex)); + break; + case BPF_S_ANC_MARK: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + mark)); + break; + case BPF_S_ANC_RXHASH: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4); + PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + rxhash)); + break; + case BPF_S_ANC_QUEUE: + BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, + queue_mapping) != 2); + PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff, + queue_mapping)); + break; + case BPF_S_ANC_CPU: +#ifdef CONFIG_SMP + /* + * PACA ptr is r13: + * raw_smp_processor_id() = local_paca->paca_index + */ + BUILD_BUG_ON(FIELD_SIZEOF(struct paca_struct, + paca_index) != 2); + PPC_LHZ_OFFS(r_A, 13, + offsetof(struct paca_struct, paca_index)); +#else + PPC_LI(r_A, 0); +#endif + break; + + /*** Absolute loads from packet header/data ***/ + case BPF_S_LD_W_ABS: + func = sk_load_word; + goto common_load; + case BPF_S_LD_H_ABS: + func = sk_load_half; + goto common_load; + case BPF_S_LD_B_ABS: + func = sk_load_byte; + common_load: + /* + * Load from [K]. Reference with the (negative) + * SKF_NET_OFF/SKF_LL_OFF offsets is unsupported. + */ + ctx->seen |= SEEN_DATAREF; + if ((int)K < 0) + return -ENOTSUPP; + PPC_LI64(r_scratch1, func); + PPC_MTLR(r_scratch1); + PPC_LI32(r_addr, K); + PPC_BLRL(); + /* + * Helper returns 'lt' condition on error, and an + * appropriate return value in r3 + */ + PPC_BCC(COND_LT, exit_addr); + break; + + /*** Indirect loads from packet header/data ***/ + case BPF_S_LD_W_IND: + func = sk_load_word; + goto common_load_ind; + case BPF_S_LD_H_IND: + func = sk_load_half; + goto common_load_ind; + case BPF_S_LD_B_IND: + func = sk_load_byte; + common_load_ind: + /* + * Load from [X + K]. Negative offsets are tested for + * in the helper functions, and result in a 'ret 0'. + */ + ctx->seen |= SEEN_DATAREF | SEEN_XREG; + PPC_LI64(r_scratch1, func); + PPC_MTLR(r_scratch1); + PPC_ADDI(r_addr, r_X, IMM_L(K)); + if (K >= 32768) + PPC_ADDIS(r_addr, r_addr, IMM_HA(K)); + PPC_BLRL(); + /* If error, cr0.LT set */ + PPC_BCC(COND_LT, exit_addr); + break; + + case BPF_S_LDX_B_MSH: + /* + * x86 version drops packet (RET 0) when K<0, whereas + * interpreter does allow K<0 (__load_pointer, special + * ancillary data). common_load returns ENOTSUPP if K<0, + * so we fall back to interpreter & filter works. + */ + func = sk_load_byte_msh; + goto common_load; + break; + + /*** Jump and branches ***/ + case BPF_S_JMP_JA: + if (K != 0) + PPC_JMP(addrs[i + 1 + K]); + break; + + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGT_X: + true_cond = COND_GT; + goto cond_branch; + case BPF_S_JMP_JGE_K: + case BPF_S_JMP_JGE_X: + true_cond = COND_GE; + goto cond_branch; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JEQ_X: + true_cond = COND_EQ; + goto cond_branch; + case BPF_S_JMP_JSET_K: + case BPF_S_JMP_JSET_X: + true_cond = COND_NE; + /* Fall through */ + cond_branch: + /* same targets, can avoid doing the test :) */ + if (filter[i].jt == filter[i].jf) { + if (filter[i].jt > 0) + PPC_JMP(addrs[i + 1 + filter[i].jt]); + break; + } + + switch (filter[i].code) { + case BPF_S_JMP_JGT_X: + case BPF_S_JMP_JGE_X: + case BPF_S_JMP_JEQ_X: + ctx->seen |= SEEN_XREG; + PPC_CMPLW(r_A, r_X); + break; + case BPF_S_JMP_JSET_X: + ctx->seen |= SEEN_XREG; + PPC_AND_DOT(r_scratch1, r_A, r_X); + break; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGE_K: + if (K < 32768) + PPC_CMPLWI(r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_CMPLW(r_A, r_scratch1); + } + break; + case BPF_S_JMP_JSET_K: + if (K < 32768) + /* PPC_ANDI is /only/ dot-form */ + PPC_ANDI(r_scratch1, r_A, K); + else { + PPC_LI32(r_scratch1, K); + PPC_AND_DOT(r_scratch1, r_A, + r_scratch1); + } + break; + } + /* Sometimes branches are constructed "backward", with + * the false path being the branch and true path being + * a fallthrough to the next instruction. + */ + if (filter[i].jt == 0) + /* Swap the sense of the branch */ + PPC_BCC(true_cond ^ COND_CMP_TRUE, + addrs[i + 1 + filter[i].jf]); + else { + PPC_BCC(true_cond, addrs[i + 1 + filter[i].jt]); + if (filter[i].jf != 0) + PPC_JMP(addrs[i + 1 + filter[i].jf]); + } + break; + default: + /* The filter contains something cruel & unusual. + * We don't handle it, but also there shouldn't be + * anything missing from our list. + */ + if (printk_ratelimit()) + pr_err("BPF filter opcode %04x (@%d) unsupported\n", + filter[i].code, i); + return -ENOTSUPP; + } + + } + /* Set end-of-body-code address for exit. */ + addrs[i] = ctx->idx * 4; + + return 0; +} + +void bpf_jit_compile(struct sk_filter *fp) +{ + unsigned int proglen; + unsigned int alloclen; + u32 *image = NULL; + u32 *code_base; + unsigned int *addrs; + struct codegen_context cgctx; + int pass; + int flen = fp->len; + + if (!bpf_jit_enable) + return; + + addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL); + if (addrs == NULL) + return; + + /* + * There are multiple assembly passes as the generated code will change + * size as it settles down, figuring out the max branch offsets/exit + * paths required. + * + * The range of standard conditional branches is +/- 32Kbytes. Since + * BPF_MAXINSNS = 4096, we can only jump from (worst case) start to + * finish with 8 bytes/instruction. Not feasible, so long jumps are + * used, distinct from short branches. + * + * Current: + * + * For now, both branch types assemble to 2 words (short branches padded + * with a NOP); this is less efficient, but assembly will always complete + * after exactly 3 passes: + * + * First pass: No code buffer; Program is "faux-generated" -- no code + * emitted but maximum size of output determined (and addrs[] filled + * in). Also, we note whether we use M[], whether we use skb data, etc. + * All generation choices assumed to be 'worst-case', e.g. branches all + * far (2 instructions), return path code reduction not available, etc. + * + * Second pass: Code buffer allocated with size determined previously. + * Prologue generated to support features we have seen used. Exit paths + * determined and addrs[] is filled in again, as code may be slightly + * smaller as a result. + * + * Third pass: Code generated 'for real', and branch destinations + * determined from now-accurate addrs[] map. + * + * Ideal: + * + * If we optimise this, near branches will be shorter. On the + * first assembly pass, we should err on the side of caution and + * generate the biggest code. On subsequent passes, branches will be + * generated short or long and code size will reduce. With smaller + * code, more branches may fall into the short category, and code will + * reduce more. + * + * Finally, if we see one pass generate code the same size as the + * previous pass we have converged and should now generate code for + * real. Allocating at the end will also save the memory that would + * otherwise be wasted by the (small) current code shrinkage. + * Preferably, we should do a small number of passes (e.g. 5) and if we + * haven't converged by then, get impatient and force code to generate + * as-is, even if the odd branch would be left long. The chances of a + * long jump are tiny with all but the most enormous of BPF filter + * inputs, so we should usually converge on the third pass. + */ + + cgctx.idx = 0; + cgctx.seen = 0; + cgctx.pc_ret0 = -1; + /* Scouting faux-generate pass 0 */ + if (bpf_jit_build_body(fp, 0, &cgctx, addrs)) + /* We hit something illegal or unsupported. */ + goto out; + + /* + * Pretend to build prologue, given the features we've seen. This will + * update ctgtx.idx as it pretends to output instructions, then we can + * calculate total size from idx. + */ + bpf_jit_build_prologue(fp, 0, &cgctx); + bpf_jit_build_epilogue(0, &cgctx); + + proglen = cgctx.idx * 4; + alloclen = proglen + FUNCTION_DESCR_SIZE; + image = module_alloc(max_t(unsigned int, alloclen, + sizeof(struct work_struct))); + if (!image) + goto out; + + code_base = image + (FUNCTION_DESCR_SIZE/4); + + /* Code generation passes 1-2 */ + for (pass = 1; pass < 3; pass++) { + /* Now build the prologue, body code & epilogue for real. */ + cgctx.idx = 0; + bpf_jit_build_prologue(fp, code_base, &cgctx); + bpf_jit_build_body(fp, code_base, &cgctx, addrs); + bpf_jit_build_epilogue(code_base, &cgctx); + + if (bpf_jit_enable > 1) + pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass, + proglen - (cgctx.idx * 4), cgctx.seen); + } + + if (bpf_jit_enable > 1) + pr_info("flen=%d proglen=%u pass=%d image=%p\n", + flen, proglen, pass, image); + + if (image) { + if (bpf_jit_enable > 1) + print_hex_dump(KERN_ERR, "JIT code: ", + DUMP_PREFIX_ADDRESS, + 16, 1, code_base, + proglen, false); + + bpf_flush_icache(code_base, code_base + (proglen/4)); + /* Function descriptor nastiness: Address + TOC */ + ((u64 *)image)[0] = (u64)code_base; + ((u64 *)image)[1] = local_paca->kernel_toc; + fp->bpf_func = (void *)image; + } +out: + kfree(addrs); + return; +} + +static void jit_free_defer(struct work_struct *arg) +{ + module_free(NULL, arg); +} + +/* run from softirq, we must use a work_struct to call + * module_free() from process context + */ +void bpf_jit_free(struct sk_filter *fp) +{ + if (fp->bpf_func != sk_run_filter) { + struct work_struct *work = (struct work_struct *)fp->bpf_func; + + INIT_WORK(work, jit_free_defer); + schedule_work(work); + } +} diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 47ea1be1481..90f4496017e 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -55,14 +55,6 @@ config PPC_MPC5200_BUGFIX It is safe to say 'Y' here -config PPC_MPC5200_GPIO - bool "MPC5200 GPIO support" - depends on PPC_MPC52xx - select ARCH_REQUIRE_GPIOLIB - select GENERIC_GPIO - help - Enable gpiolib support for mpc5200 based boards - config PPC_MPC5200_LPBFIFO tristate "MPC5200 LocalPlus bus FIFO driver" depends on PPC_MPC52xx diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile index 2bc8cd0c5cf..4e62486791e 100644 --- a/arch/powerpc/platforms/52xx/Makefile +++ b/arch/powerpc/platforms/52xx/Makefile @@ -14,5 +14,4 @@ ifeq ($(CONFIG_PPC_LITE5200),y) obj-$(CONFIG_PM) += lite5200_sleep.o lite5200_pm.o endif -obj-$(CONFIG_PPC_MPC5200_GPIO) += mpc52xx_gpio.o obj-$(CONFIG_PPC_MPC5200_LPBFIFO) += mpc52xx_lpbfifo.o diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c b/arch/powerpc/platforms/52xx/mpc52xx_gpio.c deleted file mode 100644 index 1757d1db4b5..00000000000 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpio.c +++ /dev/null @@ -1,380 +0,0 @@ -/* - * MPC52xx gpio driver - * - * Copyright (c) 2008 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/of.h> -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/of_gpio.h> -#include <linux/io.h> -#include <linux/of_platform.h> - -#include <asm/gpio.h> -#include <asm/mpc52xx.h> -#include <sysdev/fsl_soc.h> - -static DEFINE_SPINLOCK(gpio_lock); - -struct mpc52xx_gpiochip { - struct of_mm_gpio_chip mmchip; - unsigned int shadow_dvo; - unsigned int shadow_gpioe; - unsigned int shadow_ddr; -}; - -/* - * GPIO LIB API implementation for wakeup GPIOs. - * - * There's a maximum of 8 wakeup GPIOs. Which of these are available - * for use depends on your board setup. - * - * 0 -> GPIO_WKUP_7 - * 1 -> GPIO_WKUP_6 - * 2 -> PSC6_1 - * 3 -> PSC6_0 - * 4 -> ETH_17 - * 5 -> PSC3_9 - * 6 -> PSC2_4 - * 7 -> PSC1_4 - * - */ -static int mpc52xx_wkup_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - unsigned int ret; - - ret = (in_8(®s->wkup_ival) >> (7 - gpio)) & 1; - - pr_debug("%s: gpio: %d ret: %d\n", __func__, gpio, ret); - - return ret; -} - -static inline void -__mpc52xx_wkup_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - - if (val) - chip->shadow_dvo |= 1 << (7 - gpio); - else - chip->shadow_dvo &= ~(1 << (7 - gpio)); - - out_8(®s->wkup_dvo, chip->shadow_dvo); -} - -static void -mpc52xx_wkup_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_wkup_gpio_set(gc, gpio, val); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); -} - -static int mpc52xx_wkup_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* set the direction */ - chip->shadow_ddr &= ~(1 << (7 - gpio)); - out_8(®s->wkup_ddr, chip->shadow_ddr); - - /* and enable the pin */ - chip->shadow_gpioe |= 1 << (7 - gpio); - out_8(®s->wkup_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -} - -static int -mpc52xx_wkup_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio_wkup __iomem *regs = mm_gc->regs; - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_wkup_gpio_set(gc, gpio, val); - - /* Then set direction */ - chip->shadow_ddr |= 1 << (7 - gpio); - out_8(®s->wkup_ddr, chip->shadow_ddr); - - /* Finally enable the pin */ - chip->shadow_gpioe |= 1 << (7 - gpio); - out_8(®s->wkup_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); - - return 0; -} - -static int __devinit mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev) -{ - struct mpc52xx_gpiochip *chip; - struct mpc52xx_gpio_wkup __iomem *regs; - struct gpio_chip *gc; - int ret; - - chip = kzalloc(sizeof(*chip), GFP_KERNEL); - if (!chip) - return -ENOMEM; - - gc = &chip->mmchip.gc; - - gc->ngpio = 8; - gc->direction_input = mpc52xx_wkup_gpio_dir_in; - gc->direction_output = mpc52xx_wkup_gpio_dir_out; - gc->get = mpc52xx_wkup_gpio_get; - gc->set = mpc52xx_wkup_gpio_set; - - ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); - if (ret) - return ret; - - regs = chip->mmchip.regs; - chip->shadow_gpioe = in_8(®s->wkup_gpioe); - chip->shadow_ddr = in_8(®s->wkup_ddr); - chip->shadow_dvo = in_8(®s->wkup_dvo); - - return 0; -} - -static int mpc52xx_gpiochip_remove(struct platform_device *ofdev) -{ - return -EBUSY; -} - -static const struct of_device_id mpc52xx_wkup_gpiochip_match[] = { - { - .compatible = "fsl,mpc5200-gpio-wkup", - }, - {} -}; - -static struct platform_driver mpc52xx_wkup_gpiochip_driver = { - .driver = { - .name = "gpio_wkup", - .owner = THIS_MODULE, - .of_match_table = mpc52xx_wkup_gpiochip_match, - }, - .probe = mpc52xx_wkup_gpiochip_probe, - .remove = mpc52xx_gpiochip_remove, -}; - -/* - * GPIO LIB API implementation for simple GPIOs - * - * There's a maximum of 32 simple GPIOs. Which of these are available - * for use depends on your board setup. - * The numbering reflects the bit numbering in the port registers: - * - * 0..1 > reserved - * 2..3 > IRDA - * 4..7 > ETHR - * 8..11 > reserved - * 12..15 > USB - * 16..17 > reserved - * 18..23 > PSC3 - * 24..27 > PSC2 - * 28..31 > PSC1 - */ -static int mpc52xx_simple_gpio_get(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned int ret; - - ret = (in_be32(®s->simple_ival) >> (31 - gpio)) & 1; - - return ret; -} - -static inline void -__mpc52xx_simple_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - - if (val) - chip->shadow_dvo |= 1 << (31 - gpio); - else - chip->shadow_dvo &= ~(1 << (31 - gpio)); - out_be32(®s->simple_dvo, chip->shadow_dvo); -} - -static void -mpc52xx_simple_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) -{ - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - __mpc52xx_simple_gpio_set(gc, gpio, val); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); -} - -static int mpc52xx_simple_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* set the direction */ - chip->shadow_ddr &= ~(1 << (31 - gpio)); - out_be32(®s->simple_ddr, chip->shadow_ddr); - - /* and enable the pin */ - chip->shadow_gpioe |= 1 << (31 - gpio); - out_be32(®s->simple_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - return 0; -} - -static int -mpc52xx_simple_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) -{ - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct mpc52xx_gpiochip *chip = container_of(mm_gc, - struct mpc52xx_gpiochip, mmchip); - struct mpc52xx_gpio __iomem *regs = mm_gc->regs; - unsigned long flags; - - spin_lock_irqsave(&gpio_lock, flags); - - /* First set initial value */ - __mpc52xx_simple_gpio_set(gc, gpio, val); - - /* Then set direction */ - chip->shadow_ddr |= 1 << (31 - gpio); - out_be32(®s->simple_ddr, chip->shadow_ddr); - - /* Finally enable the pin */ - chip->shadow_gpioe |= 1 << (31 - gpio); - out_be32(®s->simple_gpioe, chip->shadow_gpioe); - - spin_unlock_irqrestore(&gpio_lock, flags); - - pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val); - - return 0; -} - -static int __devinit mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev) -{ - struct mpc52xx_gpiochip *chip; - struct gpio_chip *gc; - struct mpc52xx_gpio __iomem *regs; - int ret; - - chip = kzalloc(sizeof(*chip), GFP_KERNEL); - if (!chip) - return -ENOMEM; - - gc = &chip->mmchip.gc; - - gc->ngpio = 32; - gc->direction_input = mpc52xx_simple_gpio_dir_in; - gc->direction_output = mpc52xx_simple_gpio_dir_out; - gc->get = mpc52xx_simple_gpio_get; - gc->set = mpc52xx_simple_gpio_set; - - ret = of_mm_gpiochip_add(ofdev->dev.of_node, &chip->mmchip); - if (ret) - return ret; - - regs = chip->mmchip.regs; - chip->shadow_gpioe = in_be32(®s->simple_gpioe); - chip->shadow_ddr = in_be32(®s->simple_ddr); - chip->shadow_dvo = in_be32(®s->simple_dvo); - - return 0; -} - -static const struct of_device_id mpc52xx_simple_gpiochip_match[] = { - { - .compatible = "fsl,mpc5200-gpio", - }, - {} -}; - -static struct platform_driver mpc52xx_simple_gpiochip_driver = { - .driver = { - .name = "gpio", - .owner = THIS_MODULE, - .of_match_table = mpc52xx_simple_gpiochip_match, - }, - .probe = mpc52xx_simple_gpiochip_probe, - .remove = mpc52xx_gpiochip_remove, -}; - -static int __init mpc52xx_gpio_init(void) -{ - if (platform_driver_register(&mpc52xx_wkup_gpiochip_driver)) - printk(KERN_ERR "Unable to register wakeup GPIO driver\n"); - - if (platform_driver_register(&mpc52xx_simple_gpiochip_driver)) - printk(KERN_ERR "Unable to register simple GPIO driver\n"); - - return 0; -} - - -/* Make sure we get initialised before anyone else tries to use us */ -subsys_initcall(mpc52xx_gpio_init); - -/* No exit call at the moment as we cannot unregister of gpio chips */ - -MODULE_DESCRIPTION("Freescale MPC52xx gpio driver"); -MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de"); -MODULE_LICENSE("GPL v2"); - diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 33867ec4a23..9d6a8effeda 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -12,6 +12,8 @@ #include <linux/of.h> #include <linux/memblock.h> #include <linux/vmalloc.h> +#include <linux/memory.h> + #include <asm/firmware.h> #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> @@ -20,24 +22,25 @@ static unsigned long get_memblock_size(void) { struct device_node *np; - unsigned int memblock_size = 0; + unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (np) { - const unsigned long *size; + const __be64 *size; size = of_get_property(np, "ibm,lmb-size", NULL); - memblock_size = size ? *size : 0; - + if (size) + memblock_size = be64_to_cpup(size); of_node_put(np); - } else { + } else if (machine_is(pseries)) { + /* This fallback really only applies to pseries */ unsigned int memzero_size = 0; - const unsigned int *regs; np = of_find_node_by_path("/memory@0"); if (np) { - regs = of_get_property(np, "reg", NULL); - memzero_size = regs ? regs[3] : 0; + if (!of_address_to_resource(np, 0, &r)) + memzero_size = resource_size(&r); of_node_put(np); } @@ -50,16 +53,21 @@ static unsigned long get_memblock_size(void) sprintf(buf, "/memory@%x", memzero_size); np = of_find_node_by_path(buf); if (np) { - regs = of_get_property(np, "reg", NULL); - memblock_size = regs ? regs[3] : 0; + if (!of_address_to_resource(np, 0, &r)) + memblock_size = resource_size(&r); of_node_put(np); } } } - return memblock_size; } +/* WARNING: This is going to override the generic definition whenever + * pseries is built-in regardless of what platform is active at boot + * time. This is fine for now as this is the only "option" and it + * should work everywhere. If not, we'll have to turn this into a + * ppc_md. callback + */ unsigned long memory_block_size_bytes(void) { return get_memblock_size(); diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c index 0608b1657da..d917573cf1a 100644 --- a/arch/powerpc/sysdev/fsl_lbc.c +++ b/arch/powerpc/sysdev/fsl_lbc.c @@ -196,9 +196,6 @@ static int __devinit fsl_lbc_ctrl_init(struct fsl_lbc_ctrl *ctrl, out_be32(&lbc->lteccr, LTECCR_CLEAR); out_be32(&lbc->ltedr, LTEDR_ENABLE); - /* Enable interrupts for any detected events */ - out_be32(&lbc->lteir, LTEIR_ENABLE); - /* Set the monitor timeout value to the maximum for erratum A001 */ if (of_device_is_compatible(node, "fsl,elbc")) clrsetbits_be32(&lbc->lbcr, LBCR_BMT, LBCR_BMTPS); @@ -322,6 +319,9 @@ static int __devinit fsl_lbc_ctrl_probe(struct platform_device *dev) goto err; } + /* Enable interrupts for any detected events */ + out_be32(&fsl_lbc_ctrl_dev->regs->lteir, LTEIR_ENABLE); + return 0; err: diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 5b206a2fe17..b3fd081d56f 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -283,23 +283,24 @@ static void __iomem *rio_regs_win; #ifdef CONFIG_E500 int fsl_rio_mcheck_exception(struct pt_regs *regs) { - const struct exception_table_entry *entry = NULL; - unsigned long reason = mfspr(SPRN_MCSR); - - if (reason & MCSR_BUS_RBERR) { - reason = in_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR)); - if (reason & (RIO_LTLEDCSR_IER | RIO_LTLEDCSR_PRT)) { - /* Check if we are prepared to handle this fault */ - entry = search_exception_tables(regs->nip); - if (entry) { - pr_debug("RIO: %s - MC Exception handled\n", - __func__); - out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), - 0); - regs->msr |= MSR_RI; - regs->nip = entry->fixup; - return 1; - } + const struct exception_table_entry *entry; + unsigned long reason; + + if (!rio_regs_win) + return 0; + + reason = in_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR)); + if (reason & (RIO_LTLEDCSR_IER | RIO_LTLEDCSR_PRT)) { + /* Check if we are prepared to handle this fault */ + entry = search_exception_tables(regs->nip); + if (entry) { + pr_debug("RIO: %s - MC Exception handled\n", + __func__); + out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), + 0); + regs->msr |= MSR_RI; + regs->nip = entry->fixup; + return 1; } } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 3a8de5bb628..58d7a534f87 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -29,6 +29,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/syscore_ops.h> +#include <linux/ratelimit.h> #include <asm/ptrace.h> #include <asm/signal.h> @@ -1648,9 +1649,8 @@ static unsigned int _mpic_get_one_irq(struct mpic *mpic, int reg) return NO_IRQ; } if (unlikely(mpic->protected && test_bit(src, mpic->protected))) { - if (printk_ratelimit()) - printk(KERN_WARNING "%s: Got protected source %d !\n", - mpic->name, (int)src); + printk_ratelimited(KERN_WARNING "%s: Got protected source %d !\n", + mpic->name, (int)src); mpic_eoi(mpic); return NO_IRQ; } @@ -1688,9 +1688,8 @@ unsigned int mpic_get_coreint_irq(void) return NO_IRQ; } if (unlikely(mpic->protected && test_bit(src, mpic->protected))) { - if (printk_ratelimit()) - printk(KERN_WARNING "%s: Got protected source %d !\n", - mpic->name, (int)src); + printk_ratelimited(KERN_WARNING "%s: Got protected source %d !\n", + mpic->name, (int)src); return NO_IRQ; } |