diff options
Diffstat (limited to 'arch')
491 files changed, 6940 insertions, 5179 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 4877a8c8ee16..53d7f619a1b9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -32,8 +32,9 @@ config HAVE_OPROFILE config KPROBES bool "Kprobes" - depends on KALLSYMS && MODULES + depends on MODULES depends on HAVE_KPROBES + select KALLSYMS help Kprobes allows you to trap at almost any kernel address and execute a callback function. register_kprobe() establishes @@ -45,7 +46,6 @@ config OPTPROBES def_bool y depends on KPROBES && HAVE_OPTPROBES depends on !PREEMPT - select KALLSYMS_ALL config HAVE_EFFICIENT_UNALIGNED_ACCESS bool @@ -158,4 +158,7 @@ config HAVE_PERF_EVENTS_NMI subsystem. Also has support for calculating CPU cycle events to determine how many clock cycles in a given period. +config HAVE_ARCH_JUMP_LABEL + bool + source "kernel/gcov/Kconfig" diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index b9647bb66d13..d04ccd73af45 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -9,6 +9,7 @@ config ALPHA select HAVE_IDE select HAVE_OPROFILE select HAVE_SYSCALL_WRAPPERS + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select HAVE_DMA_ATTRS help diff --git a/arch/alpha/include/asm/cache.h b/arch/alpha/include/asm/cache.h index f199e69a5d0b..ad368a93a46a 100644 --- a/arch/alpha/include/asm/cache.h +++ b/arch/alpha/include/asm/cache.h @@ -17,7 +17,6 @@ # define L1_CACHE_SHIFT 5 #endif -#define L1_CACHE_ALIGN(x) (((x)+(L1_CACHE_BYTES-1))&~(L1_CACHE_BYTES-1)) #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif diff --git a/arch/alpha/include/asm/cacheflush.h b/arch/alpha/include/asm/cacheflush.h index 01d71e1c8a9e..012f1243b1c1 100644 --- a/arch/alpha/include/asm/cacheflush.h +++ b/arch/alpha/include/asm/cacheflush.h @@ -43,6 +43,8 @@ extern void smp_imb(void); /* ??? Ought to use this in arch/alpha/kernel/signal.c too. */ #ifndef CONFIG_SMP +#include <linux/sched.h> + extern void __load_new_mm_context(struct mm_struct *); static inline void flush_icache_user_range(struct vm_area_struct *vma, struct page *page, diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h index 4157cd3c44a9..fe792ca818f6 100644 --- a/arch/alpha/include/asm/perf_event.h +++ b/arch/alpha/include/asm/perf_event.h @@ -1,11 +1,6 @@ #ifndef __ASM_ALPHA_PERF_EVENT_H #define __ASM_ALPHA_PERF_EVENT_H -/* Alpha only supports software events through this interface. */ -extern void set_perf_event_pending(void); - -#define PERF_EVENT_INDEX_OFFSET 0 - #ifdef CONFIG_PERF_EVENTS extern void init_hw_perf_events(void); #else diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h index 804e5311c841..058937bf5a77 100644 --- a/arch/alpha/include/asm/unistd.h +++ b/arch/alpha/include/asm/unistd.h @@ -449,10 +449,13 @@ #define __NR_pwritev 491 #define __NR_rt_tgsigqueueinfo 492 #define __NR_perf_event_open 493 +#define __NR_fanotify_init 494 +#define __NR_fanotify_mark 495 +#define __NR_prlimit64 496 #ifdef __KERNEL__ -#define NR_SYSCALLS 494 +#define NR_SYSCALLS 497 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR @@ -463,6 +466,7 @@ #define __ARCH_WANT_SYS_OLD_GETRLIMIT #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_SIGPENDING +#define __ARCH_WANT_SYS_RT_SIGSUSPEND /* "Conditional" syscalls. What we want is diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index b45d913a51c3..6d159cee5f2f 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -73,8 +73,6 @@ ldq $20, HAE_REG($19); \ stq $21, HAE_CACHE($19); \ stq $21, 0($20); \ - ldq $0, 0($sp); \ - ldq $1, 8($sp); \ 99:; \ ldq $19, 72($sp); \ ldq $20, 80($sp); \ @@ -316,19 +314,24 @@ ret_from_sys_call: cmovne $26, 0, $19 /* $19 = 0 => non-restartable */ ldq $0, SP_OFF($sp) and $0, 8, $0 - beq $0, restore_all -ret_from_reschedule: + beq $0, ret_to_kernel +ret_to_user: /* Make sure need_resched and sigpending don't change between sampling and the rti. */ lda $16, 7 call_pal PAL_swpipl ldl $5, TI_FLAGS($8) and $5, _TIF_WORK_MASK, $2 - bne $5, work_pending + bne $2, work_pending restore_all: RESTORE_ALL call_pal PAL_rti +ret_to_kernel: + lda $16, 7 + call_pal PAL_swpipl + br restore_all + .align 3 $syscall_error: /* @@ -363,7 +366,7 @@ $ret_success: * $8: current. * $19: The old syscall number, or zero if this is not a return * from a syscall that errored and is possibly restartable. - * $20: Error indication. + * $20: The old a3 value */ .align 4 @@ -392,12 +395,18 @@ $work_resched: $work_notifysig: mov $sp, $16 - br $1, do_switch_stack + bsr $1, do_switch_stack mov $sp, $17 mov $5, $18 + mov $19, $9 /* save old syscall number */ + mov $20, $10 /* save old a3 */ + and $5, _TIF_SIGPENDING, $2 + cmovne $2, 0, $9 /* we don't want double syscall restarts */ jsr $26, do_notify_resume + mov $9, $19 + mov $10, $20 bsr $1, undo_switch_stack - br restore_all + br ret_to_user .end work_pending /* @@ -430,6 +439,7 @@ strace: beq $1, 1f ldq $27, 0($2) 1: jsr $26, ($27), sys_gettimeofday +ret_from_straced: ldgp $gp, 0($26) /* check return.. */ @@ -650,7 +660,7 @@ kernel_thread: /* We don't actually care for a3 success widgetry in the kernel. Not for positive errno values. */ stq $0, 0($sp) /* $0 */ - br restore_all + br ret_to_kernel .end kernel_thread /* @@ -757,11 +767,15 @@ sys_vfork: .ent sys_sigreturn sys_sigreturn: .prologue 0 + lda $9, ret_from_straced + cmpult $26, $9, $9 mov $sp, $17 lda $18, -SWITCH_STACK_SIZE($sp) lda $sp, -SWITCH_STACK_SIZE($sp) jsr $26, do_sigreturn - br $1, undo_switch_stack + bne $9, 1f + jsr $26, syscall_trace +1: br $1, undo_switch_stack br ret_from_sys_call .end sys_sigreturn @@ -770,47 +784,19 @@ sys_sigreturn: .ent sys_rt_sigreturn sys_rt_sigreturn: .prologue 0 + lda $9, ret_from_straced + cmpult $26, $9, $9 mov $sp, $17 lda $18, -SWITCH_STACK_SIZE($sp) lda $sp, -SWITCH_STACK_SIZE($sp) jsr $26, do_rt_sigreturn - br $1, undo_switch_stack + bne $9, 1f + jsr $26, syscall_trace +1: br $1, undo_switch_stack br ret_from_sys_call .end sys_rt_sigreturn .align 4 - .globl sys_sigsuspend - .ent sys_sigsuspend -sys_sigsuspend: - .prologue 0 - mov $sp, $17 - br $1, do_switch_stack - mov $sp, $18 - subq $sp, 16, $sp - stq $26, 0($sp) - jsr $26, do_sigsuspend - ldq $26, 0($sp) - lda $sp, SWITCH_STACK_SIZE+16($sp) - ret -.end sys_sigsuspend - - .align 4 - .globl sys_rt_sigsuspend - .ent sys_rt_sigsuspend -sys_rt_sigsuspend: - .prologue 0 - mov $sp, $18 - br $1, do_switch_stack - mov $sp, $19 - subq $sp, 16, $sp - stq $26, 0($sp) - jsr $26, do_rt_sigsuspend - ldq $26, 0($sp) - lda $sp, SWITCH_STACK_SIZE+16($sp) - ret -.end sys_rt_sigsuspend - - .align 4 .globl sys_sethae .ent sys_sethae sys_sethae: @@ -929,15 +915,6 @@ sys_execve: .end sys_execve .align 4 - .globl osf_sigprocmask - .ent osf_sigprocmask -osf_sigprocmask: - .prologue 0 - mov $sp, $18 - jmp $31, sys_osf_sigprocmask -.end osf_sigprocmask - - .align 4 .globl alpha_ni_syscall .ent alpha_ni_syscall alpha_ni_syscall: diff --git a/arch/alpha/kernel/err_ev6.c b/arch/alpha/kernel/err_ev6.c index 8ca6345bf131..253cf1a87481 100644 --- a/arch/alpha/kernel/err_ev6.c +++ b/arch/alpha/kernel/err_ev6.c @@ -90,11 +90,13 @@ static int ev6_parse_cbox(u64 c_addr, u64 c1_syn, u64 c2_syn, u64 c_stat, u64 c_sts, int print) { - char *sourcename[] = { "UNKNOWN", "UNKNOWN", "UNKNOWN", - "MEMORY", "BCACHE", "DCACHE", - "BCACHE PROBE", "BCACHE PROBE" }; - char *streamname[] = { "D", "I" }; - char *bitsname[] = { "SINGLE", "DOUBLE" }; + static const char * const sourcename[] = { + "UNKNOWN", "UNKNOWN", "UNKNOWN", + "MEMORY", "BCACHE", "DCACHE", + "BCACHE PROBE", "BCACHE PROBE" + }; + static const char * const streamname[] = { "D", "I" }; + static const char * const bitsname[] = { "SINGLE", "DOUBLE" }; int status = MCHK_DISPOSITION_REPORT; int source = -1, stream = -1, bits = -1; diff --git a/arch/alpha/kernel/err_marvel.c b/arch/alpha/kernel/err_marvel.c index 52a79dfc13c6..648ae88aeb8a 100644 --- a/arch/alpha/kernel/err_marvel.c +++ b/arch/alpha/kernel/err_marvel.c @@ -109,7 +109,7 @@ marvel_print_err_cyc(u64 err_cyc) #define IO7__ERR_CYC__CYCLE__M (0x7) printk("%s Packet In Error: %s\n" - "%s Error in %s, cycle %ld%s%s\n", + "%s Error in %s, cycle %lld%s%s\n", err_print_prefix, packet_desc[EXTRACT(err_cyc, IO7__ERR_CYC__PACKET)], err_print_prefix, @@ -313,7 +313,7 @@ marvel_print_po7_ugbge_sym(u64 ugbge_sym) } printk("%s Up Hose Garbage Symptom:\n" - "%s Source Port: %ld - Dest PID: %ld - OpCode: %s\n", + "%s Source Port: %lld - Dest PID: %lld - OpCode: %s\n", err_print_prefix, err_print_prefix, EXTRACT(ugbge_sym, IO7__PO7_UGBGE_SYM__UPH_SRC_PORT), @@ -552,7 +552,7 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt) #define IO7__POX_SPLCMPLT__REM_BYTE_COUNT__M (0xfff) printk("%s Split Completion Error:\n" - "%s Source (Bus:Dev:Func): %ld:%ld:%ld\n", + "%s Source (Bus:Dev:Func): %lld:%lld:%lld\n", err_print_prefix, err_print_prefix, EXTRACT(spl_cmplt, IO7__POX_SPLCMPLT__SOURCE_BUS), @@ -589,22 +589,23 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt) static void marvel_print_pox_trans_sum(u64 trans_sum) { - char *pcix_cmd[] = { "Interrupt Acknowledge", - "Special Cycle", - "I/O Read", - "I/O Write", - "Reserved", - "Reserved / Device ID Message", - "Memory Read", - "Memory Write", - "Reserved / Alias to Memory Read Block", - "Reserved / Alias to Memory Write Block", - "Configuration Read", - "Configuration Write", - "Memory Read Multiple / Split Completion", - "Dual Address Cycle", - "Memory Read Line / Memory Read Block", - "Memory Write and Invalidate / Memory Write Block" + static const char * const pcix_cmd[] = { + "Interrupt Acknowledge", + "Special Cycle", + "I/O Read", + "I/O Write", + "Reserved", + "Reserved / Device ID Message", + "Memory Read", + "Memory Write", + "Reserved / Alias to Memory Read Block", + "Reserved / Alias to Memory Write Block", + "Configuration Read", + "Configuration Write", + "Memory Read Multiple / Split Completion", + "Dual Address Cycle", + "Memory Read Line / Memory Read Block", + "Memory Write and Invalidate / Memory Write Block" }; #define IO7__POX_TRANSUM__PCI_ADDR__S (0) diff --git a/arch/alpha/kernel/err_titan.c b/arch/alpha/kernel/err_titan.c index f7ed97ce0dfd..c3b3781a03de 100644 --- a/arch/alpha/kernel/err_titan.c +++ b/arch/alpha/kernel/err_titan.c @@ -75,8 +75,12 @@ titan_parse_p_serror(int which, u64 serror, int print) int status = MCHK_DISPOSITION_REPORT; #ifdef CONFIG_VERBOSE_MCHECK - char *serror_src[] = {"GPCI", "APCI", "AGP HP", "AGP LP"}; - char *serror_cmd[] = {"DMA Read", "DMA RMW", "SGTE Read", "Reserved"}; + static const char * const serror_src[] = { + "GPCI", "APCI", "AGP HP", "AGP LP" + }; + static const char * const serror_cmd[] = { + "DMA Read", "DMA RMW", "SGTE Read", "Reserved" + }; #endif /* CONFIG_VERBOSE_MCHECK */ #define TITAN__PCHIP_SERROR__LOST_UECC (1UL << 0) @@ -140,14 +144,15 @@ titan_parse_p_perror(int which, int port, u64 perror, int print) int status = MCHK_DISPOSITION_REPORT; #ifdef CONFIG_VERBOSE_MCHECK - char *perror_cmd[] = { "Interrupt Acknowledge", "Special Cycle", - "I/O Read", "I/O Write", - "Reserved", "Reserved", - "Memory Read", "Memory Write", - "Reserved", "Reserved", - "Configuration Read", "Configuration Write", - "Memory Read Multiple", "Dual Address Cycle", - "Memory Read Line","Memory Write and Invalidate" + static const char * const perror_cmd[] = { + "Interrupt Acknowledge", "Special Cycle", + "I/O Read", "I/O Write", + "Reserved", "Reserved", + "Memory Read", "Memory Write", + "Reserved", "Reserved", + "Configuration Read", "Configuration Write", + "Memory Read Multiple", "Dual Address Cycle", + "Memory Read Line", "Memory Write and Invalidate" }; #endif /* CONFIG_VERBOSE_MCHECK */ @@ -273,11 +278,11 @@ titan_parse_p_agperror(int which, u64 agperror, int print) int cmd, len; unsigned long addr; - char *agperror_cmd[] = { "Read (low-priority)", "Read (high-priority)", - "Write (low-priority)", - "Write (high-priority)", - "Reserved", "Reserved", - "Flush", "Fence" + static const char * const agperror_cmd[] = { + "Read (low-priority)", "Read (high-priority)", + "Write (low-priority)", "Write (high-priority)", + "Reserved", "Reserved", + "Flush", "Fence" }; #endif /* CONFIG_VERBOSE_MCHECK */ diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index fb58150a7e8f..547e8b84b2f7 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -15,7 +15,6 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/smp.h> -#include <linux/smp_lock.h> #include <linux/stddef.h> #include <linux/syscalls.h> #include <linux/unistd.h> @@ -69,7 +68,6 @@ SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start, { struct mm_struct *mm; - lock_kernel(); mm = current->mm; mm->end_code = bss_start + bss_len; mm->start_brk = bss_start + bss_len; @@ -78,7 +76,6 @@ SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start, printk("set_program_attributes(%lx %lx %lx %lx)\n", text_start, text_len, bss_start, bss_len); #endif - unlock_kernel(); return 0; } @@ -252,7 +249,7 @@ SYSCALL_DEFINE3(osf_statfs, const char __user *, pathname, retval = user_path(pathname, &path); if (!retval) { - retval = do_osf_statfs(&path buffer, bufsiz); + retval = do_osf_statfs(&path, buffer, bufsiz); path_put(&path); } return retval; @@ -517,7 +514,6 @@ SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code, long error; int __user *min_buf_size_ptr; - lock_kernel(); switch (code) { case PL_SET: if (get_user(error, &args->set.nbytes)) @@ -547,7 +543,6 @@ SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code, error = -EOPNOTSUPP; break; }; - unlock_kernel(); return error; } @@ -594,7 +589,7 @@ SYSCALL_DEFINE2(osf_sigstack, struct sigstack __user *, uss, SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) { - char *sysinfo_table[] = { + const char *sysinfo_table[] = { utsname()->sysname, utsname()->nodename, utsname()->release, @@ -606,7 +601,7 @@ SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) "dummy", /* secure RPC domain */ }; unsigned long offset; - char *res; + const char *res; long len, err = -EINVAL; offset = command-1; diff --git a/arch/alpha/kernel/pci-sysfs.c b/arch/alpha/kernel/pci-sysfs.c index 738fc824e2ea..b899e95f79fd 100644 --- a/arch/alpha/kernel/pci-sysfs.c +++ b/arch/alpha/kernel/pci-sysfs.c @@ -66,7 +66,7 @@ static int pci_mmap_resource(struct kobject *kobj, { struct pci_dev *pdev = to_pci_dev(container_of(kobj, struct device, kobj)); - struct resource *res = (struct resource *)attr->private; + struct resource *res = attr->private; enum pci_mmap_state mmap_type; struct pci_bus_region bar; int i; diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c index 51c39fa41693..1cc49683fb69 100644 --- a/arch/alpha/kernel/perf_event.c +++ b/arch/alpha/kernel/perf_event.c @@ -241,20 +241,20 @@ static inline unsigned long alpha_read_pmc(int idx) static int alpha_perf_event_set_period(struct perf_event *event, struct hw_perf_event *hwc, int idx) { - long left = atomic64_read(&hwc->period_left); + long left = local64_read(&hwc->period_left); long period = hwc->sample_period; int ret = 0; if (unlikely(left <= -period)) { left = period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } if (unlikely(left <= 0)) { left += period; - atomic64_set(&hwc->period_left, left); + local64_set(&hwc->period_left, left); hwc->last_period = period; ret = 1; } @@ -269,7 +269,7 @@ static int alpha_perf_event_set_period(struct perf_event *event, if (left > (long)alpha_pmu->pmc_max_period[idx]) left = alpha_pmu->pmc_max_period[idx]; - atomic64_set(&hwc->prev_count, (unsigned long)(-left)); + local64_set(&hwc->prev_count, (unsigned long)(-left)); alpha_write_pmc(idx, (unsigned long)(-left)); @@ -300,14 +300,14 @@ static unsigned long alpha_perf_event_update(struct perf_event *event, long delta; again: - prev_raw_count = atomic64_read(&hwc->prev_count); + prev_raw_count = local64_read(&hwc->prev_count); new_raw_count = alpha_read_pmc(idx); - if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count, + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, new_raw_count) != prev_raw_count) goto again; - delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf; + delta = (new_raw_count - (prev_raw_count & alpha_pmu->pmc_count_mask[idx])) + ovf; /* It is possible on very rare occasions that the PMC has overflowed * but the interrupt is yet to come. Detect and fix this situation. @@ -316,8 +316,8 @@ again: delta += alpha_pmu->pmc_max_period[idx] + 1; } - atomic64_add(delta, &event->count); - atomic64_sub(delta, &hwc->period_left); + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); return new_raw_count; } @@ -402,14 +402,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc) struct hw_perf_event *hwc = &pe->hw; int idx = hwc->idx; - if (cpuc->current_idx[j] != PMC_NO_INDEX) { - cpuc->idx_mask |= (1<<cpuc->current_idx[j]); - continue; + if (cpuc->current_idx[j] == PMC_NO_INDEX) { + alpha_perf_event_set_period(pe, hwc, idx); + cpuc->current_idx[j] = idx; } - alpha_perf_event_set_period(pe, hwc, idx); - cpuc->current_idx[j] = idx; - cpuc->idx_mask |= (1<<cpuc->current_idx[j]); + if (!(hwc->state & PERF_HES_STOPPED)) + cpuc->idx_mask |= (1<<cpuc->current_idx[j]); } cpuc->config = cpuc->event[0]->hw.config_base; } @@ -420,12 +419,13 @@ static void maybe_change_configuration(struct cpu_hw_events *cpuc) * - this function is called from outside this module via the pmu struct * returned from perf event initialisation. */ -static int alpha_pmu_enable(struct perf_event *event) +static int alpha_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; int n0; int ret; - unsigned long flags; + unsigned long irq_flags; /* * The Sparc code has the IRQ disable first followed by the perf @@ -435,8 +435,8 @@ static int alpha_pmu_enable(struct perf_event *event) * nevertheless we disable the PMCs first to enable a potential * final PMI to occur before we disable interrupts. */ - perf_disable(); - local_irq_save(flags); + perf_pmu_disable(event->pmu); + local_irq_save(irq_flags); /* Default to error to be returned */ ret = -EAGAIN; @@ -455,8 +455,12 @@ static int alpha_pmu_enable(struct perf_event *event) } } - local_irq_restore(flags); - perf_enable(); + hwc->state = PERF_HES_UPTODATE; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_STOPPED; + + local_irq_restore(irq_flags); + perf_pmu_enable(event->pmu); return ret; } @@ -467,15 +471,15 @@ static int alpha_pmu_enable(struct perf_event *event) * - this function is called from outside this module via the pmu struct * returned from perf event initialisation. */ -static void alpha_pmu_disable(struct perf_event *event) +static void alpha_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - unsigned long flags; + unsigned long irq_flags; int j; - perf_disable(); - local_irq_save(flags); + perf_pmu_disable(event->pmu); + local_irq_save(irq_flags); for (j = 0; j < cpuc->n_events; j++) { if (event == cpuc->event[j]) { @@ -501,8 +505,8 @@ static void alpha_pmu_disable(struct perf_event *event) } } - local_irq_restore(flags); - perf_enable(); + local_irq_restore(irq_flags); + perf_pmu_enable(event->pmu); } @@ -514,13 +518,44 @@ static void alpha_pmu_read(struct perf_event *event) } -static void alpha_pmu_unthrottle(struct perf_event *event) +static void alpha_pmu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + + if (!(hwc->state & PERF_HES_STOPPED)) { + cpuc->idx_mask &= ~(1UL<<hwc->idx); + hwc->state |= PERF_HES_STOPPED; + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + alpha_perf_event_update(event, hwc, hwc->idx, 0); + hwc->state |= PERF_HES_UPTODATE; + } + + if (cpuc->enabled) + wrperfmon(PERFMON_CMD_DISABLE, (1UL<<hwc->idx)); +} + + +static void alpha_pmu_start(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + if (flags & PERF_EF_RELOAD) { + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + alpha_perf_event_set_period(event, hwc, hwc->idx); + } + + hwc->state = 0; + cpuc->idx_mask |= 1UL<<hwc->idx; - wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx)); + if (cpuc->enabled) + wrperfmon(PERFMON_CMD_ENABLE, (1UL<<hwc->idx)); } @@ -636,45 +671,42 @@ static int __hw_perf_event_init(struct perf_event *event) if (!hwc->sample_period) { hwc->sample_period = alpha_pmu->pmc_max_period[0]; hwc->last_period = hwc->sample_period; - atomic64_set(&hwc->period_left, hwc->sample_period); + local64_set(&hwc->period_left, hwc->sample_period); } return 0; } -static const struct pmu pmu = { - .enable = alpha_pmu_enable, - .disable = alpha_pmu_disable, - .read = alpha_pmu_read, - .unthrottle = alpha_pmu_unthrottle, -}; - - /* * Main entry point to initialise a HW performance event. */ -const struct pmu *hw_perf_event_init(struct perf_event *event) +static int alpha_pmu_event_init(struct perf_event *event) { int err; + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + break; + + default: + return -ENOENT; + } + if (!alpha_pmu) - return ERR_PTR(-ENODEV); + return -ENODEV; /* Do the real initialisation work. */ err = __hw_perf_event_init(event); - if (err) - return ERR_PTR(err); - - return &pmu; + return err; } - - /* * Main entry point - enable HW performance counters. */ -void hw_perf_enable(void) +static void alpha_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -700,7 +732,7 @@ void hw_perf_enable(void) * Main entry point - disable HW performance counters. */ -void hw_perf_disable(void) +static void alpha_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -713,6 +745,17 @@ void hw_perf_disable(void) wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask); } +static struct pmu pmu = { + .pmu_enable = alpha_pmu_enable, + .pmu_disable = alpha_pmu_disable, + .event_init = alpha_pmu_event_init, + .add = alpha_pmu_add, + .del = alpha_pmu_del, + .start = alpha_pmu_start, + .stop = alpha_pmu_stop, + .read = alpha_pmu_read, +}; + /* * Main entry point - don't know when this is called but it @@ -766,7 +809,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, wrperfmon(PERFMON_CMD_DISABLE, cpuc->idx_mask); /* la_ptr is the counter that overflowed. */ - if (unlikely(la_ptr >= perf_max_events)) { + if (unlikely(la_ptr >= alpha_pmu->num_pmcs)) { /* This should never occur! */ irq_err_count++; pr_warning("PMI: silly index %ld\n", la_ptr); @@ -807,7 +850,7 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr, /* Interrupts coming too quickly; "throttle" the * counter, i.e., disable it for a little while. */ - cpuc->idx_mask &= ~(1UL<<idx); + alpha_pmu_stop(event, 0); } } wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask); @@ -837,6 +880,7 @@ void __init init_hw_perf_events(void) /* And set up PMU specification */ alpha_pmu = &ev67_pmu; - perf_max_events = alpha_pmu->num_pmcs; + + perf_pmu_register(&pmu); } diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index 842dba308eab..3ec35066f1dc 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -356,7 +356,7 @@ dump_elf_thread(elf_greg_t *dest, struct pt_regs *pt, struct thread_info *ti) dest[27] = pt->r27; dest[28] = pt->r28; dest[29] = pt->gp; - dest[30] = rdusp(); + dest[30] = ti == current_thread_info() ? rdusp() : ti->pcb.usp; dest[31] = pt->pc; /* Once upon a time this was the PS value. Which is stupid diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index 3d2627ec9860..d3e52d3fd592 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -156,9 +156,6 @@ extern void SMC669_Init(int); /* es1888.c */ extern void es1888_init(void); -/* ns87312.c */ -extern void ns87312_enable_ide(long ide_base); - /* ../lib/fpreg.c */ extern void alpha_write_fp_reg (unsigned long reg, unsigned long val); extern unsigned long alpha_read_fp_reg (unsigned long reg); diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 0932dbb1ef8e..6f7feb5db271 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -41,46 +41,20 @@ static void do_signal(struct pt_regs *, struct switch_stack *, /* * The OSF/1 sigprocmask calling sequence is different from the * C sigprocmask() sequence.. - * - * how: - * 1 - SIG_BLOCK - * 2 - SIG_UNBLOCK - * 3 - SIG_SETMASK - * - * We change the range to -1 .. 1 in order to let gcc easily - * use the conditional move instructions. - * - * Note that we don't need to acquire the kernel lock for SMP - * operation, as all of this is local to this thread. */ -SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask, - struct pt_regs *, regs) +SYSCALL_DEFINE2(osf_sigprocmask, int, how, unsigned long, newmask) { - unsigned long oldmask = -EINVAL; - - if ((unsigned long)how-1 <= 2) { - long sign = how-2; /* -1 .. 1 */ - unsigned long block, unblock; - - newmask &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); - oldmask = current->blocked.sig[0]; - - unblock = oldmask & ~newmask; - block = oldmask | newmask; - if (!sign) - block = unblock; - if (sign <= 0) - newmask = block; - if (_NSIG_WORDS > 1 && sign > 0) - sigemptyset(¤t->blocked); - current->blocked.sig[0] = newmask; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - regs->r0 = 0; /* special no error return */ + sigset_t oldmask; + sigset_t mask; + unsigned long res; + + siginitset(&mask, newmask & _BLOCKABLE); + res = sigprocmask(how, &mask, &oldmask); + if (!res) { + force_successful_syscall_return(); + res = oldmask.sig[0]; } - return oldmask; + return res; } SYSCALL_DEFINE3(osf_sigaction, int, sig, @@ -94,9 +68,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig, old_sigset_t mask; if (!access_ok(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_flags, &act->sa_flags)) + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); new_ka.ka_restorer = NULL; } @@ -106,9 +80,9 @@ SYSCALL_DEFINE3(osf_sigaction, int, sig, if (!ret && oact) { if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_flags, &oact->sa_flags)) + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; @@ -144,8 +118,7 @@ SYSCALL_DEFINE5(rt_sigaction, int, sig, const struct sigaction __user *, act, /* * Atomically swap in the new signal mask, and wait for a signal. */ -asmlinkage int -do_sigsuspend(old_sigset_t mask, struct pt_regs *regs, struct switch_stack *sw) +SYSCALL_DEFINE1(sigsuspend, old_sigset_t, mask) { mask &= _BLOCKABLE; spin_lock_irq(¤t->sighand->siglock); @@ -154,41 +127,6 @@ do_sigsuspend(old_sigset_t mask, struct pt_regs *regs, struct switch_stack *sw) recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - /* Indicate EINTR on return from any possible signal handler, - which will not come back through here, but via sigreturn. */ - regs->r0 = EINTR; - regs->r19 = 1; - - current->state = TASK_INTERRUPTIBLE; - schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); - return -ERESTARTNOHAND; -} - -asmlinkage int -do_rt_sigsuspend(sigset_t __user *uset, size_t sigsetsize, - struct pt_regs *regs, struct switch_stack *sw) -{ - sigset_t set; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - if (copy_from_user(&set, uset, sizeof(set))) - return -EFAULT; - - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->saved_sigmask = current->blocked; - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - /* Indicate EINTR on return from any possible signal handler, - which will not come back through here, but via sigreturn. */ - regs->r0 = EINTR; - regs->r19 = 1; - current->state = TASK_INTERRUPTIBLE; schedule(); set_thread_flag(TIF_RESTORE_SIGMASK); @@ -239,6 +177,8 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long usp; long i, err = __get_user(regs->pc, &sc->sc_pc); + current_thread_info()->restart_block.fn = do_no_restart_syscall; + sw->r26 = (unsigned long) ret_from_sys_call; err |= __get_user(regs->r0, sc->sc_regs+0); @@ -591,7 +531,6 @@ syscall_restart(unsigned long r0, unsigned long r19, regs->pc -= 4; break; case ERESTART_RESTARTBLOCK: - current_thread_info()->restart_block.fn = do_no_restart_syscall; regs->r0 = EINTR; break; } diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c index 4afc1a1e2e5a..f0df3fbd8402 100644 --- a/arch/alpha/kernel/srm_env.c +++ b/arch/alpha/kernel/srm_env.c @@ -87,7 +87,7 @@ static int srm_env_proc_show(struct seq_file *m, void *v) srm_env_t *entry; char *page; - entry = (srm_env_t *)m->private; + entry = m->private; page = (char *)__get_free_page(GFP_USER); if (!page) return -ENOMEM; diff --git a/arch/alpha/kernel/sys_cabriolet.c b/arch/alpha/kernel/sys_cabriolet.c index affd0f3f25df..14c8898d19ec 100644 --- a/arch/alpha/kernel/sys_cabriolet.c +++ b/arch/alpha/kernel/sys_cabriolet.c @@ -33,7 +33,7 @@ #include "irq_impl.h" #include "pci_impl.h" #include "machvec_impl.h" - +#include "pc873xx.h" /* Note mask bit is true for DISABLED irqs. */ static unsigned long cached_irq_mask = ~0UL; @@ -236,17 +236,30 @@ cabriolet_map_irq(struct pci_dev *dev, u8 slot, u8 pin) } static inline void __init +cabriolet_enable_ide(void) +{ + if (pc873xx_probe() == -1) { + printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n"); + } else { + printk(KERN_INFO "Found %s Super IO chip at 0x%x\n", + pc873xx_get_model(), pc873xx_get_base()); + + pc873xx_enable_ide(); + } +} + +static inline void __init cabriolet_init_pci(void) { common_init_pci(); - ns87312_enable_ide(0x398); + cabriolet_enable_ide(); } static inline void __init cia_cab_init_pci(void) { cia_init_pci(); - ns87312_enable_ide(0x398); + cabriolet_enable_ide(); } /* diff --git a/arch/alpha/kernel/sys_takara.c b/arch/alpha/kernel/sys_takara.c index 230464885b5c..4da596b6adbb 100644 --- a/arch/alpha/kernel/sys_takara.c +++ b/arch/alpha/kernel/sys_takara.c @@ -29,7 +29,7 @@ #include "irq_impl.h" #include "pci_impl.h" #include "machvec_impl.h" - +#include "pc873xx.h" /* Note mask bit is true for DISABLED irqs. */ static unsigned long cached_irq_mask[2] = { -1, -1 }; @@ -264,7 +264,14 @@ takara_init_pci(void) alpha_mv.pci_map_irq = takara_map_irq_srm; cia_init_pci(); - ns87312_enable_ide(0x26e); + + if (pc873xx_probe() == -1) { + printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n"); + } else { + printk(KERN_INFO "Found %s Super IO chip at 0x%x\n", + pc873xx_get_model(), pc873xx_get_base()); + pc873xx_enable_ide(); + } } diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index 09acb786e72b..a6a1de9db16f 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -58,7 +58,7 @@ sys_call_table: .quad sys_open /* 45 */ .quad alpha_ni_syscall .quad sys_getxgid - .quad osf_sigprocmask + .quad sys_osf_sigprocmask .quad alpha_ni_syscall .quad alpha_ni_syscall /* 50 */ .quad sys_acct @@ -512,6 +512,9 @@ sys_call_table: .quad sys_pwritev .quad sys_rt_tgsigqueueinfo .quad sys_perf_event_open + .quad sys_fanotify_init + .quad sys_fanotify_mark /* 495 */ + .quad sys_prlimit64 .size sys_call_table, . - sys_call_table .type sys_call_table, @object diff --git a/arch/alpha/kernel/time.c b/arch/alpha/kernel/time.c index eacceb26d9c8..0f1d8493cfca 100644 --- a/arch/alpha/kernel/time.c +++ b/arch/alpha/kernel/time.c @@ -41,7 +41,7 @@ #include <linux/init.h> #include <linux/bcd.h> #include <linux/profile.h> -#include <linux/perf_event.h> +#include <linux/irq_work.h> #include <asm/uaccess.h> #include <asm/io.h> @@ -83,25 +83,25 @@ static struct { unsigned long est_cycle_freq; -#ifdef CONFIG_PERF_EVENTS +#ifdef CONFIG_IRQ_WORK -DEFINE_PER_CPU(u8, perf_event_pending); +DEFINE_PER_CPU(u8, irq_work_pending); -#define set_perf_event_pending_flag() __get_cpu_var(perf_event_pending) = 1 -#define test_perf_event_pending() __get_cpu_var(perf_event_pending) -#define clear_perf_event_pending() __get_cpu_var(perf_event_pending) = 0 +#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 +#define test_irq_work_pending() __get_cpu_var(irq_work_pending) +#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 -void set_perf_event_pending(void) +void set_irq_work_pending(void) { - set_perf_event_pending_flag(); + set_irq_work_pending_flag(); } -#else /* CONFIG_PERF_EVENTS */ +#else /* CONFIG_IRQ_WORK */ -#define test_perf_event_pending() 0 -#define clear_perf_event_pending() +#define test_irq_work_pending() 0 +#define clear_irq_work_pending() -#endif /* CONFIG_PERF_EVENTS */ +#endif /* CONFIG_IRQ_WORK */ static inline __u32 rpcc(void) @@ -191,16 +191,16 @@ irqreturn_t timer_interrupt(int irq, void *dev) write_sequnlock(&xtime_lock); + if (test_irq_work_pending()) { + clear_irq_work_pending(); + irq_work_run(); + } + #ifndef CONFIG_SMP while (nticks--) update_process_times(user_mode(get_irq_regs())); #endif - if (test_perf_event_pending()) { - clear_perf_event_pending(); - perf_event_do_pending(); - } - return IRQ_HANDLED; } diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index b14f015008ad..0414e021a91c 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -13,7 +13,6 @@ #include <linux/sched.h> #include <linux/tty.h> #include <linux/delay.h> -#include <linux/smp_lock.h> #include <linux/module.h> #include <linux/init.h> #include <linux/kallsyms.h> @@ -623,7 +622,6 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, return; } - lock_kernel(); printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n", pc, va, opcode, reg); do_exit(SIGSEGV); @@ -646,7 +644,6 @@ got_exception: * Yikes! No one to forward the exception to. * Since the registers are in a weird format, dump them ourselves. */ - lock_kernel(); printk("%s(%d): unhandled unaligned exception\n", current->comm, task_pid_nr(current)); diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 92951103255a..9103904b3dab 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -23,6 +23,7 @@ config ARM select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZO select HAVE_KERNEL_LZMA + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC select HAVE_REGS_AND_STACK_ACCESS_API @@ -271,7 +272,6 @@ config ARCH_AT91 bool "Atmel AT91" select ARCH_REQUIRE_GPIOLIB select HAVE_CLK - select ARCH_USES_GETTIMEOFFSET help This enables support for systems based on the Atmel AT91RM9200, AT91SAM9 and AT91CAP9 processors. @@ -1051,6 +1051,32 @@ config ARM_ERRATA_460075 ACTLR register. Note that setting specific bits in the ACTLR register may not be available in non-secure mode. +config ARM_ERRATA_742230 + bool "ARM errata: DMB operation may be faulty" + depends on CPU_V7 && SMP + help + This option enables the workaround for the 742230 Cortex-A9 + (r1p0..r2p2) erratum. Under rare circumstances, a DMB instruction + between two write operations may not ensure the correct visibility + ordering of the two writes. This workaround sets a specific bit in + the diagnostic register of the Cortex-A9 which causes the DMB + instruction to behave as a DSB, ensuring the correct behaviour of + the two writes. + +config ARM_ERRATA_742231 + bool "ARM errata: Incorrect hazard handling in the SCU may lead to data corruption" + depends on CPU_V7 && SMP + help + This option enables the workaround for the 742231 Cortex-A9 + (r2p0..r2p2) erratum. Under certain conditions, specific to the + Cortex-A9 MPCore micro-architecture, two CPUs working in SMP mode, + accessing some data located in the same cache line, may get corrupted + data due to bad handling of the address hazard when the line gets + replaced from one of the CPUs at the same time as another CPU is + accessing it. This workaround sets specific bits in the diagnostic + register of the Cortex-A9 which reduces the linefill issuing + capabilities of the processor. + config PL310_ERRATA_588369 bool "Clean & Invalidate maintenance operations do not invalidate clean lines" depends on CACHE_L2X0 && ARCH_OMAP4 @@ -1076,6 +1102,20 @@ config ARM_ERRATA_720789 invalidated are not, resulting in an incoherency in the system page tables. The workaround changes the TLB flushing routines to invalidate entries regardless of the ASID. + +config ARM_ERRATA_743622 + bool "ARM errata: Faulty hazard checking in the Store Buffer may lead to data corruption" + depends on CPU_V7 + help + This option enables the workaround for the 743622 Cortex-A9 + (r2p0..r2p2) erratum. Under very rare conditions, a faulty + optimisation in the Cortex-A9 Store Buffer may lead to data + corruption. This workaround sets a specific bit in the diagnostic + register of the Cortex-A9 which disables the Store Buffer + optimisation, preventing the defect from occurring. This has no + visible impact on the overall performance or power consumption of the + processor. + endmenu source "arch/arm/common/Kconfig" @@ -1576,95 +1616,6 @@ config AUTO_ZRELADDR 0xf8000000. This assumes the zImage being placed in the first 128MB from start of memory. -config ZRELADDR - hex "Physical address of the decompressed kernel image" - depends on !AUTO_ZRELADDR - default 0x00008000 if ARCH_BCMRING ||\ - ARCH_CNS3XXX ||\ - ARCH_DOVE ||\ - ARCH_EBSA110 ||\ - ARCH_FOOTBRIDGE ||\ - ARCH_INTEGRATOR ||\ - ARCH_IOP13XX ||\ - ARCH_IOP33X ||\ - ARCH_IXP2000 ||\ - ARCH_IXP23XX ||\ - ARCH_IXP4XX ||\ - ARCH_KIRKWOOD ||\ - ARCH_KS8695 ||\ - ARCH_LOKI ||\ - ARCH_MMP ||\ - ARCH_MV78XX0 ||\ - ARCH_NOMADIK ||\ - ARCH_NUC93X ||\ - ARCH_NS9XXX ||\ - ARCH_ORION5X ||\ - ARCH_SPEAR3XX ||\ - ARCH_SPEAR6XX ||\ - ARCH_U8500 ||\ - ARCH_VERSATILE ||\ - ARCH_W90X900 - default 0x08008000 if ARCH_MX1 ||\ - ARCH_SHARK - default 0x10008000 if ARCH_MSM ||\ - ARCH_OMAP1 ||\ - ARCH_RPC - default 0x20008000 if ARCH_S5P6440 ||\ - ARCH_S5P6442 ||\ - ARCH_S5PC100 ||\ - ARCH_S5PV210 - default 0x30008000 if ARCH_S3C2410 ||\ - ARCH_S3C2400 ||\ - ARCH_S3C2412 ||\ - ARCH_S3C2416 ||\ - ARCH_S3C2440 ||\ - ARCH_S3C2443 - default 0x40008000 if ARCH_STMP378X ||\ - ARCH_STMP37XX ||\ - ARCH_SH7372 ||\ - ARCH_SH7377 - default 0x50008000 if ARCH_S3C64XX ||\ - ARCH_SH7367 - default 0x60008000 if ARCH_VEXPRESS - default 0x80008000 if ARCH_MX25 ||\ - ARCH_MX3 ||\ - ARCH_NETX ||\ - ARCH_OMAP2PLUS ||\ - ARCH_PNX4008 - default 0x90008000 if ARCH_MX5 ||\ - ARCH_MX91231 - default 0xa0008000 if ARCH_IOP32X ||\ - ARCH_PXA ||\ - MACH_MX27 - default 0xc0008000 if ARCH_LH7A40X ||\ - MACH_MX21 - default 0xf0008000 if ARCH_AAEC2000 ||\ - ARCH_L7200 - default 0xc0028000 if ARCH_CLPS711X - default 0x70008000 if ARCH_AT91 && (ARCH_AT91CAP9 || ARCH_AT91SAM9G45) - default 0x20008000 if ARCH_AT91 && !(ARCH_AT91CAP9 || ARCH_AT91SAM9G45) - default 0xc0008000 if ARCH_DAVINCI && ARCH_DAVINCI_DA8XX - default 0x80008000 if ARCH_DAVINCI && !ARCH_DAVINCI_DA8XX - default 0x00008000 if ARCH_EP93XX && EP93XX_SDCE3_SYNC_PHYS_OFFSET - default 0xc0008000 if ARCH_EP93XX && EP93XX_SDCE0_PHYS_OFFSET - default 0xd0008000 if ARCH_EP93XX && EP93XX_SDCE1_PHYS_OFFSET - default 0xe0008000 if ARCH_EP93XX && EP93XX_SDCE2_PHYS_OFFSET - default 0xf0008000 if ARCH_EP93XX && EP93XX_SDCE3_ASYNC_PHYS_OFFSET - default 0x00008000 if ARCH_GEMINI && GEMINI_MEM_SWAP - default 0x10008000 if ARCH_GEMINI && !GEMINI_MEM_SWAP - default 0x70008000 if ARCH_REALVIEW && REALVIEW_HIGH_PHYS_OFFSET - default 0x00008000 if ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET - default 0xc0208000 if ARCH_SA1100 && SA1111 - default 0xc0008000 if ARCH_SA1100 && !SA1111 - default 0x30108000 if ARCH_S3C2410 && PM_H1940 - default 0x28E08000 if ARCH_U300 && MACH_U300_SINGLE_RAM - default 0x48008000 if ARCH_U300 && !MACH_U300_SINGLE_RAM - help - ZRELADDR is the physical address where the decompressed kernel - image will be placed. ZRELADDR has to be specified when the - assumption of AUTO_ZRELADDR is not valid, or when ZBOOT_ROM is - selected. - endmenu menu "CPU Power Management" diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index f705213caa88..4a590f4113e2 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -14,16 +14,18 @@ MKIMAGE := $(srctree)/scripts/mkuboot.sh ifneq ($(MACHINE),) --include $(srctree)/$(MACHINE)/Makefile.boot +include $(srctree)/$(MACHINE)/Makefile.boot endif # Note: the following conditions must always be true: +# ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET) # PARAMS_PHYS must be within 4MB of ZRELADDR # INITRD_PHYS must be in RAM +ZRELADDR := $(zreladdr-y) PARAMS_PHYS := $(params_phys-y) INITRD_PHYS := $(initrd_phys-y) -export INITRD_PHYS PARAMS_PHYS +export ZRELADDR INITRD_PHYS PARAMS_PHYS targets := Image zImage xipImage bootpImage uImage @@ -65,7 +67,7 @@ quiet_cmd_uimage = UIMAGE $@ ifeq ($(CONFIG_ZBOOT_ROM),y) $(obj)/uImage: LOADADDR=$(CONFIG_ZBOOT_ROM_TEXT) else -$(obj)/uImage: LOADADDR=$(CONFIG_ZRELADDR) +$(obj)/uImage: LOADADDR=$(ZRELADDR) endif ifeq ($(CONFIG_THUMB2_KERNEL),y) diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 68775e33476c..65a7c1c588a9 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -79,6 +79,10 @@ endif EXTRA_CFLAGS := -fpic -fno-builtin EXTRA_AFLAGS := -Wa,-march=all +# Supply ZRELADDR to the decompressor via a linker symbol. +ifneq ($(CONFIG_AUTO_ZRELADDR),y) +LDFLAGS_vmlinux := --defsym zreladdr=$(ZRELADDR) +endif ifeq ($(CONFIG_CPU_ENDIAN_BE8),y) LDFLAGS_vmlinux += --be8 endif @@ -112,5 +116,5 @@ CFLAGS_font.o := -Dstatic= $(obj)/font.c: $(FONTC) $(call cmd,shipped) -$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile .config +$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG) @sed "$(SEDFLAGS)" < $< > $@ diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 6af9907c3b5c..6825c34646d4 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -177,7 +177,7 @@ not_angel: and r4, pc, #0xf8000000 add r4, r4, #TEXT_OFFSET #else - ldr r4, =CONFIG_ZRELADDR + ldr r4, =zreladdr #endif subs r0, r0, r1 @ calculate the delta offset diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c index 6c0913562455..1bec96e85196 100644 --- a/arch/arm/common/it8152.c +++ b/arch/arm/common/it8152.c @@ -263,6 +263,22 @@ static int it8152_pci_platform_notify_remove(struct device *dev) return 0; } +int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size) +{ + dev_dbg(dev, "%s: dma_addr %08x, size %08x\n", + __func__, dma_addr, size); + return (dev->bus == &pci_bus_type) && + ((dma_addr + size - PHYS_OFFSET) >= SZ_64M); +} + +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (mask >= PHYS_OFFSET + SZ_64M - 1) + return 0; + + return -EIO; +} + int __init it8152_pci_setup(int nr, struct pci_sys_data *sys) { it8152_io.start = IT8152_IO_BASE + 0x12000; diff --git a/arch/arm/configs/omap_4430sdp_defconfig b/arch/arm/configs/omap_4430sdp_defconfig index 63e0c2d50f32..14c1e18c648f 100644 --- a/arch/arm/configs/omap_4430sdp_defconfig +++ b/arch/arm/configs/omap_4430sdp_defconfig @@ -13,6 +13,9 @@ CONFIG_MODULE_SRCVERSION_ALL=y # CONFIG_BLK_DEV_BSG is not set CONFIG_ARCH_OMAP=y CONFIG_ARCH_OMAP4=y +# CONFIG_ARCH_OMAP2PLUS_TYPICAL is not set +# CONFIG_ARCH_OMAP2 is not set +# CONFIG_ARCH_OMAP3 is not set # CONFIG_OMAP_MUX is not set CONFIG_OMAP_32K_TIMER=y CONFIG_OMAP_DM_TIMER=y diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h index c226fe10553e..c568da7dcae4 100644 --- a/arch/arm/include/asm/dma-mapping.h +++ b/arch/arm/include/asm/dma-mapping.h @@ -288,15 +288,7 @@ extern void dmabounce_unregister_dev(struct device *); * DMA access and 1 if the buffer needs to be bounced. * */ -#ifdef CONFIG_SA1111 extern int dma_needs_bounce(struct device*, dma_addr_t, size_t); -#else -static inline int dma_needs_bounce(struct device *dev, dma_addr_t addr, - size_t size) -{ - return 0; -} -#endif /* * The DMA API, implemented by dmabounce.c. See below for descriptions. diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h index 48837e6d8887..c4aa4e8c6af9 100644 --- a/arch/arm/include/asm/perf_event.h +++ b/arch/arm/include/asm/perf_event.h @@ -12,18 +12,6 @@ #ifndef __ARM_PERF_EVENT_H__ #define __ARM_PERF_EVENT_H__ -/* - * NOP: on *most* (read: all supported) ARM platforms, the performance - * counter interrupts are regular interrupts and not an NMI. This - * means that when we receive the interrupt we can call - * perf_event_do_pending() that handles all of the work with - * interrupts enabled. - */ -static inline void -set_perf_event_pending(void) -{ -} - /* ARM performance counters start from 1 (in the cp15 accesses) so use the * same indexes here for consistency. */ #define PERF_EVENT_INDEX_OFFSET 1 diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index ab68cf1ef80f..e90b167ea848 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -317,6 +317,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE) +#define __HAVE_PHYS_MEM_ACCESS_PROT +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); #else #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED) diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h index d02cfb683487..c891eb76c0e3 100644 --- a/arch/arm/include/asm/unistd.h +++ b/arch/arm/include/asm/unistd.h @@ -393,6 +393,9 @@ #define __NR_perf_event_open (__NR_SYSCALL_BASE+364) #define __NR_recvmmsg (__NR_SYSCALL_BASE+365) #define __NR_accept4 (__NR_SYSCALL_BASE+366) +#define __NR_fanotify_init (__NR_SYSCALL_BASE+367) +#define __NR_fanotify_mark (__NR_SYSCALL_BASE+368) +#define __NR_prlimit64 (__NR_SYSCALL_BASE+369) /* * The following SWIs are ARM private. diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S index afeb71fa72cb..5c26eccef998 100644 --- a/arch/arm/kernel/calls.S +++ b/arch/arm/kernel/calls.S @@ -376,6 +376,9 @@ CALL(sys_perf_event_open) /* 365 */ CALL(sys_recvmmsg) CALL(sys_accept4) + CALL(sys_fanotify_init) + CALL(sys_fanotify_mark) + CALL(sys_prlimit64) #ifndef syscalls_counted .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls #define syscalls_counted diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index f05a35a59694..7885722bdf4e 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -48,6 +48,8 @@ work_pending: beq no_work_pending mov r0, sp @ 'regs' mov r2, why @ 'syscall' + tst r1, #_TIF_SIGPENDING @ delivering a signal? + movne why, #0 @ prevent further restarts bl do_notify_resume b ret_slow_syscall @ Check work again @@ -418,11 +420,13 @@ ENDPROC(sys_clone_wrapper) sys_sigreturn_wrapper: add r0, sp, #S_OFF + mov why, #0 @ prevent syscall restart handling b sys_sigreturn ENDPROC(sys_sigreturn_wrapper) sys_rt_sigreturn_wrapper: add r0, sp, #S_OFF + mov why, #0 @ prevent syscall restart handling b sys_rt_sigreturn ENDPROC(sys_rt_sigreturn_wrapper) diff --git a/arch/arm/kernel/etm.c b/arch/arm/kernel/etm.c index 56418f98cd01..33c7077174db 100644 --- a/arch/arm/kernel/etm.c +++ b/arch/arm/kernel/etm.c @@ -230,7 +230,7 @@ static void etm_dump(void) etb_lock(t); } -static void sysrq_etm_dump(int key, struct tty_struct *tty) +static void sysrq_etm_dump(int key) { dev_dbg(tracer.dev, "Dumping ETB buffer\n"); etm_dump(); diff --git a/arch/arm/kernel/kprobes-decode.c b/arch/arm/kernel/kprobes-decode.c index 8bccbfa693ff..2c1f0050c9c4 100644 --- a/arch/arm/kernel/kprobes-decode.c +++ b/arch/arm/kernel/kprobes-decode.c @@ -1162,11 +1162,12 @@ space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi) { /* * MSR : cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx - * Undef : cccc 0011 0x00 xxxx xxxx xxxx xxxx xxxx + * Undef : cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx * ALU op with S bit and Rd == 15 : * cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx */ - if ((insn & 0x0f900000) == 0x03200000 || /* MSR & Undef */ + if ((insn & 0x0fb00000) == 0x03200000 || /* MSR */ + (insn & 0x0ff00000) == 0x03400000 || /* Undef */ (insn & 0x0e10f000) == 0x0210f000) /* ALU s-bit, R15 */ return INSN_REJECTED; @@ -1177,7 +1178,7 @@ space_cccc_001x(kprobe_opcode_t insn, struct arch_specific_insn *asi) * *S (bit 20) updates condition codes * ADC/SBC/RSC reads the C flag */ - insn &= 0xfff00fff; /* Rn = r0, Rd = r0 */ + insn &= 0xffff0fff; /* Rd = r0 */ asi->insn[0] = insn; asi->insn_handler = (insn & (1 << 20)) ? /* S-bit */ emulate_alu_imm_rwflags : emulate_alu_imm_rflags; diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index 417c392ddf1c..49643b1467e6 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -123,6 +123,12 @@ armpmu_get_max_events(void) } EXPORT_SYMBOL_GPL(armpmu_get_max_events); +int perf_num_counters(void) +{ + return armpmu_get_max_events(); +} +EXPORT_SYMBOL_GPL(perf_num_counters); + #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) \ @@ -221,46 +227,56 @@ again: } static void -armpmu_disable(struct perf_event *event) +armpmu_read(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - - WARN_ON(idx < 0); - - clear_bit(idx, cpuc->active_mask); - armpmu->disable(hwc, idx); - - barrier(); - armpmu_event_update(event, hwc, idx); - cpuc->events[idx] = NULL; - clear_bit(idx, cpuc->used_mask); + /* Don't read disabled counters! */ + if (hwc->idx < 0) + return; - perf_event_update_userpage(event); + armpmu_event_update(event, hwc, hwc->idx); } static void -armpmu_read(struct perf_event *event) +armpmu_stop(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; - /* Don't read disabled counters! */ - if (hwc->idx < 0) + if (!armpmu) return; - armpmu_event_update(event, hwc, hwc->idx); + /* + * ARM pmu always has to update the counter, so ignore + * PERF_EF_UPDATE, see comments in armpmu_start(). + */ + if (!(hwc->state & PERF_HES_STOPPED)) { + armpmu->disable(hwc, hwc->idx); + barrier(); /* why? */ + armpmu_event_update(event, hwc, hwc->idx); + hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + } } static void -armpmu_unthrottle(struct perf_event *event) +armpmu_start(struct perf_event *event, int flags) { struct hw_perf_event *hwc = &event->hw; + if (!armpmu) + return; + + /* + * ARM pmu always has to reprogram the period, so ignore + * PERF_EF_RELOAD, see the comment below. + */ + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + + hwc->state = 0; /* * Set the period again. Some counters can't be stopped, so when we - * were throttled we simply disabled the IRQ source and the counter + * were stopped we simply disabled the IRQ source and the counter * may have been left counting. If we don't do this step then we may * get an interrupt too soon or *way* too late if the overflow has * happened since disabling. @@ -269,14 +285,33 @@ armpmu_unthrottle(struct perf_event *event) armpmu->enable(hwc, hwc->idx); } +static void +armpmu_del(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + WARN_ON(idx < 0); + + clear_bit(idx, cpuc->active_mask); + armpmu_stop(event, PERF_EF_UPDATE); + cpuc->events[idx] = NULL; + clear_bit(idx, cpuc->used_mask); + + perf_event_update_userpage(event); +} + static int -armpmu_enable(struct perf_event *event) +armpmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; int idx; int err = 0; + perf_pmu_disable(event->pmu); + /* If we don't have a space for the counter then finish early. */ idx = armpmu->get_event_idx(cpuc, hwc); if (idx < 0) { @@ -293,25 +328,19 @@ armpmu_enable(struct perf_event *event) cpuc->events[idx] = event; set_bit(idx, cpuc->active_mask); - /* Set the period for the event. */ - armpmu_event_set_period(event, hwc, idx); - - /* Enable the event. */ - armpmu->enable(hwc, idx); + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + if (flags & PERF_EF_START) + armpmu_start(event, PERF_EF_RELOAD); /* Propagate our changes to the userspace mapping. */ perf_event_update_userpage(event); out: + perf_pmu_enable(event->pmu); return err; } -static struct pmu pmu = { - .enable = armpmu_enable, - .disable = armpmu_disable, - .unthrottle = armpmu_unthrottle, - .read = armpmu_read, -}; +static struct pmu pmu; static int validate_event(struct cpu_hw_events *cpuc, @@ -319,8 +348,8 @@ validate_event(struct cpu_hw_events *cpuc, { struct hw_perf_event fake_event = event->hw; - if (event->pmu && event->pmu != &pmu) - return 0; + if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF) + return 1; return armpmu->get_event_idx(cpuc, &fake_event) >= 0; } @@ -491,20 +520,29 @@ __hw_perf_event_init(struct perf_event *event) return err; } -const struct pmu * -hw_perf_event_init(struct perf_event *event) +static int armpmu_event_init(struct perf_event *event) { int err = 0; + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + break; + + default: + return -ENOENT; + } + if (!armpmu) - return ERR_PTR(-ENODEV); + return -ENODEV; event->destroy = hw_perf_event_destroy; if (!atomic_inc_not_zero(&active_events)) { - if (atomic_read(&active_events) > perf_max_events) { + if (atomic_read(&active_events) > armpmu->num_events) { atomic_dec(&active_events); - return ERR_PTR(-ENOSPC); + return -ENOSPC; } mutex_lock(&pmu_reserve_mutex); @@ -518,17 +556,16 @@ hw_perf_event_init(struct perf_event *event) } if (err) - return ERR_PTR(err); + return err; err = __hw_perf_event_init(event); if (err) hw_perf_event_destroy(event); - return err ? ERR_PTR(err) : &pmu; + return err; } -void -hw_perf_enable(void) +static void armpmu_enable(struct pmu *pmu) { /* Enable all of the perf events on hardware. */ int idx; @@ -549,13 +586,23 @@ hw_perf_enable(void) armpmu->start(); } -void -hw_perf_disable(void) +static void armpmu_disable(struct pmu *pmu) { if (armpmu) armpmu->stop(); } +static struct pmu pmu = { + .pmu_enable = armpmu_enable, + .pmu_disable = armpmu_disable, + .event_init = armpmu_event_init, + .add = armpmu_add, + .del = armpmu_del, + .start = armpmu_start, + .stop = armpmu_stop, + .read = armpmu_read, +}; + /* * ARMv6 Performance counter handling code. * @@ -1041,11 +1088,11 @@ armv6pmu_handle_irq(int irq_num, /* * Handle the pending perf events. * - * Note: this call *must* be run with interrupts enabled. For - * platforms that can have the PMU interrupts raised as a PMI, this + * Note: this call *must* be run with interrupts disabled. For + * platforms that can have the PMU interrupts raised as an NMI, this * will not work. */ - perf_event_do_pending(); + irq_work_run(); return IRQ_HANDLED; } @@ -2017,11 +2064,11 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev) /* * Handle the pending perf events. * - * Note: this call *must* be run with interrupts enabled. For - * platforms that can have the PMU interrupts raised as a PMI, this + * Note: this call *must* be run with interrupts disabled. For + * platforms that can have the PMU interrupts raised as an NMI, this * will not work. */ - perf_event_do_pending(); + irq_work_run(); return IRQ_HANDLED; } @@ -2389,7 +2436,7 @@ xscale1pmu_handle_irq(int irq_num, void *dev) armpmu->disable(hwc, idx); } - perf_event_do_pending(); + irq_work_run(); /* * Re-enable the PMU. @@ -2716,7 +2763,7 @@ xscale2pmu_handle_irq(int irq_num, void *dev) armpmu->disable(hwc, idx); } - perf_event_do_pending(); + irq_work_run(); /* * Re-enable the PMU. @@ -2933,14 +2980,12 @@ init_hw_perf_events(void) armpmu = &armv6pmu; memcpy(armpmu_perf_cache_map, armv6_perf_cache_map, sizeof(armv6_perf_cache_map)); - perf_max_events = armv6pmu.num_events; break; case 0xB020: /* ARM11mpcore */ armpmu = &armv6mpcore_pmu; memcpy(armpmu_perf_cache_map, armv6mpcore_perf_cache_map, sizeof(armv6mpcore_perf_cache_map)); - perf_max_events = armv6mpcore_pmu.num_events; break; case 0xC080: /* Cortex-A8 */ armv7pmu.id = ARM_PERF_PMU_ID_CA8; @@ -2952,7 +2997,6 @@ init_hw_perf_events(void) /* Reset PMNC and read the nb of CNTx counters supported */ armv7pmu.num_events = armv7_reset_read_pmnc(); - perf_max_events = armv7pmu.num_events; break; case 0xC090: /* Cortex-A9 */ armv7pmu.id = ARM_PERF_PMU_ID_CA9; @@ -2964,7 +3008,6 @@ init_hw_perf_events(void) /* Reset PMNC and read the nb of CNTx counters supported */ armv7pmu.num_events = armv7_reset_read_pmnc(); - perf_max_events = armv7pmu.num_events; break; } /* Intel CPUs [xscale]. */ @@ -2975,13 +3018,11 @@ init_hw_perf_events(void) armpmu = &xscale1pmu; memcpy(armpmu_perf_cache_map, xscale_perf_cache_map, sizeof(xscale_perf_cache_map)); - perf_max_events = xscale1pmu.num_events; break; case 2: armpmu = &xscale2pmu; memcpy(armpmu_perf_cache_map, xscale_perf_cache_map, sizeof(xscale_perf_cache_map)); - perf_max_events = xscale2pmu.num_events; break; } } @@ -2991,9 +3032,10 @@ init_hw_perf_events(void) arm_pmu_names[armpmu->id], armpmu->num_events); } else { pr_info("no hardware support available\n"); - perf_max_events = -1; } + perf_pmu_register(&pmu); + return 0; } arch_initcall(init_hw_perf_events); @@ -3001,13 +3043,6 @@ arch_initcall(init_hw_perf_events); /* * Callchain handling code. */ -static inline void -callchain_store(struct perf_callchain_entry *entry, - u64 ip) -{ - if (entry->nr < PERF_MAX_STACK_DEPTH) - entry->ip[entry->nr++] = ip; -} /* * The registers we're interested in are at the end of the variable @@ -3039,7 +3074,7 @@ user_backtrace(struct frame_tail *tail, if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail))) return NULL; - callchain_store(entry, buftail.lr); + perf_callchain_store(entry, buftail.lr); /* * Frame pointers should strictly progress back up the stack @@ -3051,16 +3086,11 @@ user_backtrace(struct frame_tail *tail, return buftail.fp - 1; } -static void -perf_callchain_user(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void +perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { struct frame_tail *tail; - callchain_store(entry, PERF_CONTEXT_USER); - - if (!user_mode(regs)) - regs = task_pt_regs(current); tail = (struct frame_tail *)regs->ARM_fp - 1; @@ -3078,56 +3108,18 @@ callchain_trace(struct stackframe *fr, void *data) { struct perf_callchain_entry *entry = data; - callchain_store(entry, fr->pc); + perf_callchain_store(entry, fr->pc); return 0; } -static void -perf_callchain_kernel(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void +perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { struct stackframe fr; - callchain_store(entry, PERF_CONTEXT_KERNEL); fr.fp = regs->ARM_fp; fr.sp = regs->ARM_sp; fr.lr = regs->ARM_lr; fr.pc = regs->ARM_pc; walk_stackframe(&fr, callchain_trace, entry); } - -static void -perf_do_callchain(struct pt_regs *regs, - struct perf_callchain_entry *entry) -{ - int is_user; - - if (!regs) - return; - - is_user = user_mode(regs); - - if (!current || !current->pid) - return; - - if (is_user && current->state != TASK_RUNNING) - return; - - if (!is_user) - perf_callchain_kernel(regs, entry); - - if (current->mm) - perf_callchain_user(regs, entry); -} - -static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); - -struct perf_callchain_entry * -perf_callchain(struct pt_regs *regs) -{ - struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry); - - entry->nr = 0; - perf_do_callchain(regs, entry); - return entry; -} diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c index 753c0d31a3d3..c67b47f1c0fd 100644 --- a/arch/arm/mach-at91/at91sam9g45.c +++ b/arch/arm/mach-at91/at91sam9g45.c @@ -121,8 +121,8 @@ static struct clk ssc1_clk = { .pmc_mask = 1 << AT91SAM9G45_ID_SSC1, .type = CLK_TYPE_PERIPHERAL, }; -static struct clk tcb_clk = { - .name = "tcb_clk", +static struct clk tcb0_clk = { + .name = "tcb0_clk", .pmc_mask = 1 << AT91SAM9G45_ID_TCB, .type = CLK_TYPE_PERIPHERAL, }; @@ -192,6 +192,14 @@ static struct clk ohci_clk = { .parent = &uhphs_clk, }; +/* One additional fake clock for second TC block */ +static struct clk tcb1_clk = { + .name = "tcb1_clk", + .pmc_mask = 0, + .type = CLK_TYPE_PERIPHERAL, + .parent = &tcb0_clk, +}; + static struct clk *periph_clocks[] __initdata = { &pioA_clk, &pioB_clk, @@ -208,7 +216,7 @@ static struct clk *periph_clocks[] __initdata = { &spi1_clk, &ssc0_clk, &ssc1_clk, - &tcb_clk, + &tcb0_clk, &pwm_clk, &tsc_clk, &dma_clk, @@ -221,6 +229,7 @@ static struct clk *periph_clocks[] __initdata = { &mmc1_clk, // irq0 &ohci_clk, + &tcb1_clk, }; /* diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c index 809114d5a5a6..1276babf84d5 100644 --- a/arch/arm/mach-at91/at91sam9g45_devices.c +++ b/arch/arm/mach-at91/at91sam9g45_devices.c @@ -46,7 +46,7 @@ static struct resource hdmac_resources[] = { .end = AT91_BASE_SYS + AT91_DMA + SZ_512 - 1, .flags = IORESOURCE_MEM, }, - [2] = { + [1] = { .start = AT91SAM9G45_ID_DMA, .end = AT91SAM9G45_ID_DMA, .flags = IORESOURCE_IRQ, @@ -426,7 +426,7 @@ static struct i2c_gpio_platform_data pdata_i2c0 = { .sda_is_open_drain = 1, .scl_pin = AT91_PIN_PA21, .scl_is_open_drain = 1, - .udelay = 2, /* ~100 kHz */ + .udelay = 5, /* ~100 kHz */ }; static struct platform_device at91sam9g45_twi0_device = { @@ -440,7 +440,7 @@ static struct i2c_gpio_platform_data pdata_i2c1 = { .sda_is_open_drain = 1, .scl_pin = AT91_PIN_PB11, .scl_is_open_drain = 1, - .udelay = 2, /* ~100 kHz */ + .udelay = 5, /* ~100 kHz */ }; static struct platform_device at91sam9g45_twi1_device = { @@ -835,9 +835,9 @@ static struct platform_device at91sam9g45_tcb1_device = { static void __init at91_add_device_tc(void) { /* this chip has one clock and irq for all six TC channels */ - at91_clock_associate("tcb_clk", &at91sam9g45_tcb0_device.dev, "t0_clk"); + at91_clock_associate("tcb0_clk", &at91sam9g45_tcb0_device.dev, "t0_clk"); platform_device_register(&at91sam9g45_tcb0_device); - at91_clock_associate("tcb_clk", &at91sam9g45_tcb1_device.dev, "t0_clk"); + at91_clock_associate("tcb1_clk", &at91sam9g45_tcb1_device.dev, "t0_clk"); platform_device_register(&at91sam9g45_tcb1_device); } #else diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c index c4c8865d52d7..65eb0943194f 100644 --- a/arch/arm/mach-at91/board-sam9261ek.c +++ b/arch/arm/mach-at91/board-sam9261ek.c @@ -93,11 +93,12 @@ static struct resource dm9000_resource[] = { .start = AT91_PIN_PC11, .end = AT91_PIN_PC11, .flags = IORESOURCE_IRQ + | IORESOURCE_IRQ_LOWEDGE | IORESOURCE_IRQ_HIGHEDGE, } }; static struct dm9000_plat_data dm9000_platdata = { - .flags = DM9000_PLATF_16BITONLY, + .flags = DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM, }; static struct platform_device dm9000_device = { @@ -168,17 +169,6 @@ static struct at91_udc_data __initdata ek_udc_data = { /* - * MCI (SD/MMC) - */ -static struct at91_mmc_data __initdata ek_mmc_data = { - .wire4 = 1, -// .det_pin = ... not connected -// .wp_pin = ... not connected -// .vcc_pin = ... not connected -}; - - -/* * NAND flash */ static struct mtd_partition __initdata ek_nand_partition[] = { @@ -246,6 +236,10 @@ static void __init ek_add_device_nand(void) at91_add_device_nand(&ek_nand_data); } +/* + * SPI related devices + */ +#if defined(CONFIG_SPI_ATMEL) || defined(CONFIG_SPI_ATMEL_MODULE) /* * ADS7846 Touchscreen @@ -356,6 +350,19 @@ static struct spi_board_info ek_spi_devices[] = { #endif }; +#else /* CONFIG_SPI_ATMEL_* */ +/* spi0 and mmc/sd share the same PIO pins: cannot be used at the same time */ + +/* + * MCI (SD/MMC) + * det_pin, wp_pin and vcc_pin are not connected + */ +static struct at91_mmc_data __initdata ek_mmc_data = { + .wire4 = 1, +}; + +#endif /* CONFIG_SPI_ATMEL_* */ + /* * LCD Controller diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c index 7f7da439341f..7525cee3983f 100644 --- a/arch/arm/mach-at91/clock.c +++ b/arch/arm/mach-at91/clock.c @@ -501,7 +501,8 @@ postcore_initcall(at91_clk_debugfs_init); int __init clk_register(struct clk *clk) { if (clk_is_peripheral(clk)) { - clk->parent = &mck; + if (!clk->parent) + clk->parent = &mck; clk->mode = pmc_periph_mode; list_add_tail(&clk->node, &clocks); } diff --git a/arch/arm/mach-at91/include/mach/system.h b/arch/arm/mach-at91/include/mach/system.h index c80e090b3670..ee8db152592e 100644 --- a/arch/arm/mach-at91/include/mach/system.h +++ b/arch/arm/mach-at91/include/mach/system.h @@ -28,17 +28,16 @@ static inline void arch_idle(void) { -#ifndef CONFIG_DEBUG_KERNEL /* * Disable the processor clock. The processor will be automatically * re-enabled by an interrupt or by a reset. */ at91_sys_write(AT91_PMC_SCDR, AT91_PMC_PCK); -#else +#ifndef CONFIG_CPU_ARM920T /* * Set the processor (CP15) into 'Wait for Interrupt' mode. - * Unlike disabling the processor clock via the PMC (above) - * this allows the processor to be woken via JTAG. + * Post-RM9200 processors need this in conjunction with the above + * to save power when idle. */ cpu_do_idle(); #endif diff --git a/arch/arm/mach-bcmring/dma.c b/arch/arm/mach-bcmring/dma.c index 29c0a911df26..77eb35c89cd0 100644 --- a/arch/arm/mach-bcmring/dma.c +++ b/arch/arm/mach-bcmring/dma.c @@ -691,7 +691,7 @@ int dma_init(void) memset(&gDMA, 0, sizeof(gDMA)); - init_MUTEX_LOCKED(&gDMA.lock); + sema_init(&gDMA.lock, 0); init_waitqueue_head(&gDMA.freeChannelQ); /* Initialize the Hardware */ @@ -1574,7 +1574,7 @@ int dma_init_mem_map(DMA_MemMap_t *memMap) { memset(memMap, 0, sizeof(*memMap)); - init_MUTEX(&memMap->lock); + sema_init(&memMap->lock, 1); return 0; } diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c index 3d996b659ff4..9be261beae7d 100644 --- a/arch/arm/mach-davinci/dm355.c +++ b/arch/arm/mach-davinci/dm355.c @@ -769,8 +769,7 @@ static struct map_desc dm355_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00010000), .length = SZ_32K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index 6b6f4c643709..7781e35daec3 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -969,8 +969,7 @@ static struct map_desc dm365_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00010000), .length = SZ_32K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c index 40fec315c99a..5e5b0a7831fb 100644 --- a/arch/arm/mach-davinci/dm644x.c +++ b/arch/arm/mach-davinci/dm644x.c @@ -653,8 +653,7 @@ static struct map_desc dm644x_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00008000), .length = SZ_16K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c index e4a3df1872ac..26e8a9c7f50b 100644 --- a/arch/arm/mach-davinci/dm646x.c +++ b/arch/arm/mach-davinci/dm646x.c @@ -737,8 +737,7 @@ static struct map_desc dm646x_io_desc[] = { .virtual = SRAM_VIRT, .pfn = __phys_to_pfn(0x00010000), .length = SZ_32K, - /* MT_MEMORY_NONCACHED requires supersection alignment */ - .type = MT_DEVICE, + .type = MT_MEMORY_NONCACHED, }, }; diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h index 3b3e4721ce2e..eb4936ff90ad 100644 --- a/arch/arm/mach-dove/include/mach/io.h +++ b/arch/arm/mach-dove/include/mach/io.h @@ -13,8 +13,8 @@ #define IO_SPACE_LIMIT 0xffffffff -#define __io(a) ((void __iomem *)(((a) - DOVE_PCIE0_IO_PHYS_BASE) +\ - DOVE_PCIE0_IO_VIRT_BASE)) -#define __mem_pci(a) (a) +#define __io(a) ((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \ + DOVE_PCIE0_IO_VIRT_BASE)) +#define __mem_pci(a) (a) #endif diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index 8bf3cec98cfa..4566bd1c8660 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -560,4 +560,4 @@ static int __init ep93xx_clock_init(void) clkdev_add_table(clocks, ARRAY_SIZE(clocks)); return 0; } -arch_initcall(ep93xx_clock_init); +postcore_initcall(ep93xx_clock_init); diff --git a/arch/arm/mach-ep93xx/dma-m2p.c b/arch/arm/mach-ep93xx/dma-m2p.c index 8904ca4e2e24..a696d354b1f8 100644 --- a/arch/arm/mach-ep93xx/dma-m2p.c +++ b/arch/arm/mach-ep93xx/dma-m2p.c @@ -276,7 +276,7 @@ static void channel_disable(struct m2p_channel *ch) v &= ~(M2P_CONTROL_STALL_IRQ_EN | M2P_CONTROL_NFB_IRQ_EN); m2p_set_control(ch, v); - while (m2p_channel_state(ch) == STATE_ON) + while (m2p_channel_state(ch) >= STATE_ON) cpu_relax(); m2p_set_control(ch, 0x0); diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index c5c0369bb481..2f7e2728970d 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -122,6 +122,7 @@ config MACH_CPUIMX27 select IMX_HAVE_PLATFORM_IMX_I2C select IMX_HAVE_PLATFORM_IMX_UART select IMX_HAVE_PLATFORM_MXC_NAND + select MXC_ULPI if USB_ULPI help Include support for Eukrea CPUIMX27 platform. This includes specific configurations for the module and its peripherals. diff --git a/arch/arm/mach-imx/mach-cpuimx27.c b/arch/arm/mach-imx/mach-cpuimx27.c index 575ff1ae85a7..6830afd1d2ba 100644 --- a/arch/arm/mach-imx/mach-cpuimx27.c +++ b/arch/arm/mach-imx/mach-cpuimx27.c @@ -259,7 +259,7 @@ static void __init eukrea_cpuimx27_init(void) i2c_register_board_info(0, eukrea_cpuimx27_i2c_devices, ARRAY_SIZE(eukrea_cpuimx27_i2c_devices)); - imx27_add_i2c_imx1(&cpuimx27_i2c1_data); + imx27_add_i2c_imx0(&cpuimx27_i2c1_data); platform_add_devices(platform_devices, ARRAY_SIZE(platform_devices)); @@ -279,13 +279,13 @@ static void __init eukrea_cpuimx27_init(void) #if defined(CONFIG_USB_ULPI) if (otg_mode_host) { otg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops, - USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT); + ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT); mxc_register_device(&mxc_otg_host, &otg_pdata); } usbh2_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops, - USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT); + ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT); mxc_register_device(&mxc_usbh2, &usbh2_pdata); #endif diff --git a/arch/arm/mach-imx/mach-pca100.c b/arch/arm/mach-imx/mach-pca100.c index a389d1148f18..23c9e1f37b9c 100644 --- a/arch/arm/mach-imx/mach-pca100.c +++ b/arch/arm/mach-imx/mach-pca100.c @@ -419,13 +419,13 @@ static void __init pca100_init(void) #if defined(CONFIG_USB_ULPI) if (otg_mode_host) { otg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops, - USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT); + ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT); mxc_register_device(&mxc_otg_host, &otg_pdata); } usbh2_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops, - USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT); + ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT); mxc_register_device(&mxc_usbh2, &usbh2_pdata); #endif diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c index 61cd4d64b985..24498a932ba6 100644 --- a/arch/arm/mach-ixp4xx/common-pci.c +++ b/arch/arm/mach-ixp4xx/common-pci.c @@ -503,6 +503,14 @@ struct pci_bus * __devinit ixp4xx_scan_bus(int nr, struct pci_sys_data *sys) return pci_scan_bus(sys->busnr, &ixp4xx_ops, sys); } +int dma_set_coherent_mask(struct device *dev, u64 mask) +{ + if (mask >= SZ_64M - 1) + return 0; + + return -EIO; +} + EXPORT_SYMBOL(ixp4xx_pci_read); EXPORT_SYMBOL(ixp4xx_pci_write); diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h index f91ca6d4fbe8..8138371c406e 100644 --- a/arch/arm/mach-ixp4xx/include/mach/hardware.h +++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h @@ -26,6 +26,8 @@ #define PCIBIOS_MAX_MEM 0x4BFFFFFF #endif +#define ARCH_HAS_DMA_SET_COHERENT_MASK + #define pcibios_assign_all_busses() 1 /* Register locations and bits */ diff --git a/arch/arm/mach-kirkwood/include/mach/kirkwood.h b/arch/arm/mach-kirkwood/include/mach/kirkwood.h index 93fc2ec95e76..6e924b398919 100644 --- a/arch/arm/mach-kirkwood/include/mach/kirkwood.h +++ b/arch/arm/mach-kirkwood/include/mach/kirkwood.h @@ -38,7 +38,7 @@ #define KIRKWOOD_PCIE1_IO_PHYS_BASE 0xf3000000 #define KIRKWOOD_PCIE1_IO_VIRT_BASE 0xfef00000 -#define KIRKWOOD_PCIE1_IO_BUS_BASE 0x00000000 +#define KIRKWOOD_PCIE1_IO_BUS_BASE 0x00100000 #define KIRKWOOD_PCIE1_IO_SIZE SZ_1M #define KIRKWOOD_PCIE_IO_PHYS_BASE 0xf2000000 diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c index 55e7f00836b7..513ad3102d7c 100644 --- a/arch/arm/mach-kirkwood/pcie.c +++ b/arch/arm/mach-kirkwood/pcie.c @@ -117,7 +117,7 @@ static void __init pcie0_ioresources_init(struct pcie_port *pp) * IORESOURCE_IO */ pp->res[0].name = "PCIe 0 I/O Space"; - pp->res[0].start = KIRKWOOD_PCIE_IO_PHYS_BASE; + pp->res[0].start = KIRKWOOD_PCIE_IO_BUS_BASE; pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE_IO_SIZE - 1; pp->res[0].flags = IORESOURCE_IO; @@ -139,7 +139,7 @@ static void __init pcie1_ioresources_init(struct pcie_port *pp) * IORESOURCE_IO */ pp->res[0].name = "PCIe 1 I/O Space"; - pp->res[0].start = KIRKWOOD_PCIE1_IO_PHYS_BASE; + pp->res[0].start = KIRKWOOD_PCIE1_IO_BUS_BASE; pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE1_IO_SIZE - 1; pp->res[0].flags = IORESOURCE_IO; diff --git a/arch/arm/mach-mmp/include/mach/system.h b/arch/arm/mach-mmp/include/mach/system.h index 4f5b0e0ce6cf..1a8a25edb1b4 100644 --- a/arch/arm/mach-mmp/include/mach/system.h +++ b/arch/arm/mach-mmp/include/mach/system.h @@ -9,6 +9,8 @@ #ifndef __ASM_MACH_SYSTEM_H #define __ASM_MACH_SYSTEM_H +#include <mach/cputype.h> + static inline void arch_idle(void) { cpu_do_idle(); @@ -16,6 +18,9 @@ static inline void arch_idle(void) static inline void arch_reset(char mode, const char *cmd) { - cpu_reset(0); + if (cpu_is_pxa168()) + cpu_reset(0xffff0000); + else + cpu_reset(0); } #endif /* __ASM_MACH_SYSTEM_H */ diff --git a/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c b/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c index 91931dcb0689..4aaadc753d3e 100644 --- a/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c +++ b/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c @@ -215,7 +215,7 @@ struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = { * Add platform devices present on this baseboard and init * them from CPU side as far as required to use them later on */ -void __init eukrea_mbimxsd_baseboard_init(void) +void __init eukrea_mbimxsd25_baseboard_init(void) { if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads, ARRAY_SIZE(eukrea_mbimxsd_pads))) diff --git a/arch/arm/mach-mx25/mach-cpuimx25.c b/arch/arm/mach-mx25/mach-cpuimx25.c index 56b2e26d23b4..e064bb3d6919 100644 --- a/arch/arm/mach-mx25/mach-cpuimx25.c +++ b/arch/arm/mach-mx25/mach-cpuimx25.c @@ -138,7 +138,7 @@ static void __init eukrea_cpuimx25_init(void) #if defined(CONFIG_USB_ULPI) if (otg_mode_host) { otg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops, - USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT); + ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT); mxc_register_device(&mxc_otg, &otg_pdata); } @@ -147,8 +147,8 @@ static void __init eukrea_cpuimx25_init(void) if (!otg_mode_host) mxc_register_device(&otg_udc_device, &otg_device_pdata); -#ifdef CONFIG_MACH_EUKREA_MBIMXSD_BASEBOARD - eukrea_mbimxsd_baseboard_init(); +#ifdef CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD + eukrea_mbimxsd25_baseboard_init(); #endif } diff --git a/arch/arm/mach-mx3/clock-imx35.c b/arch/arm/mach-mx3/clock-imx35.c index d3af0fdf8475..7a62e744a8b0 100644 --- a/arch/arm/mach-mx3/clock-imx35.c +++ b/arch/arm/mach-mx3/clock-imx35.c @@ -155,7 +155,7 @@ static unsigned long get_rate_arm(void) aad = &clk_consumer[(pdr0 >> 16) & 0xf]; if (aad->sel) - fref = fref * 2 / 3; + fref = fref * 3 / 4; return fref / aad->arm; } @@ -164,7 +164,7 @@ static unsigned long get_rate_ahb(struct clk *clk) { unsigned long pdr0 = __raw_readl(CCM_BASE + CCM_PDR0); struct arm_ahb_div *aad; - unsigned long fref = get_rate_mpll(); + unsigned long fref = get_rate_arm(); aad = &clk_consumer[(pdr0 >> 16) & 0xf]; @@ -176,16 +176,11 @@ static unsigned long get_rate_ipg(struct clk *clk) return get_rate_ahb(NULL) >> 1; } -static unsigned long get_3_3_div(unsigned long in) -{ - return (((in >> 3) & 0x7) + 1) * ((in & 0x7) + 1); -} - static unsigned long get_rate_uart(struct clk *clk) { unsigned long pdr3 = __raw_readl(CCM_BASE + CCM_PDR3); unsigned long pdr4 = __raw_readl(CCM_BASE + CCM_PDR4); - unsigned long div = get_3_3_div(pdr4 >> 10); + unsigned long div = ((pdr4 >> 10) & 0x3f) + 1; if (pdr3 & (1 << 14)) return get_rate_arm() / div; @@ -216,7 +211,7 @@ static unsigned long get_rate_sdhc(struct clk *clk) break; } - return rate / get_3_3_div(div); + return rate / (div + 1); } static unsigned long get_rate_mshc(struct clk *clk) @@ -270,7 +265,7 @@ static unsigned long get_rate_csi(struct clk *clk) else rate = get_rate_ppll(); - return rate / get_3_3_div((pdr2 >> 16) & 0x3f); + return rate / (((pdr2 >> 16) & 0x3f) + 1); } static unsigned long get_rate_otg(struct clk *clk) @@ -283,25 +278,51 @@ static unsigned long get_rate_otg(struct clk *clk) else rate = get_rate_ppll(); - return rate / get_3_3_div((pdr4 >> 22) & 0x3f); + return rate / (((pdr4 >> 22) & 0x3f) + 1); } static unsigned long get_rate_ipg_per(struct clk *clk) { unsigned long pdr0 = __raw_readl(CCM_BASE + CCM_PDR0); unsigned long pdr4 = __raw_readl(CCM_BASE + CCM_PDR4); - unsigned long div1, div2; + unsigned long div; if (pdr0 & (1 << 26)) { - div1 = (pdr4 >> 19) & 0x7; - div2 = (pdr4 >> 16) & 0x7; - return get_rate_arm() / ((div1 + 1) * (div2 + 1)); + div = (pdr4 >> 16) & 0x3f; + return get_rate_arm() / (div + 1); } else { - div1 = (pdr0 >> 12) & 0x7; - return get_rate_ahb(NULL) / div1; + div = (pdr0 >> 12) & 0x7; + return get_rate_ahb(NULL) / (div + 1); } } +static unsigned long get_rate_hsp(struct clk *clk) +{ + unsigned long hsp_podf = (__raw_readl(CCM_BASE + CCM_PDR0) >> 20) & 0x03; + unsigned long fref = get_rate_mpll(); + + if (fref > 400 * 1000 * 1000) { + switch (hsp_podf) { + case 0: + return fref >> 2; + case 1: + return fref >> 3; + case 2: + return fref / 3; + } + } else { + switch (hsp_podf) { + case 0: + case 2: + return fref / 3; + case 1: + return fref / 6; + } + } + + return 0; +} + static int clk_cgr_enable(struct clk *clk) { u32 reg; @@ -359,7 +380,7 @@ DEFINE_CLOCK(i2c1_clk, 0, CCM_CGR1, 10, get_rate_ipg_per, NULL); DEFINE_CLOCK(i2c2_clk, 1, CCM_CGR1, 12, get_rate_ipg_per, NULL); DEFINE_CLOCK(i2c3_clk, 2, CCM_CGR1, 14, get_rate_ipg_per, NULL); DEFINE_CLOCK(iomuxc_clk, 0, CCM_CGR1, 16, NULL, NULL); -DEFINE_CLOCK(ipu_clk, 0, CCM_CGR1, 18, get_rate_ahb, NULL); +DEFINE_CLOCK(ipu_clk, 0, CCM_CGR1, 18, get_rate_hsp, NULL); DEFINE_CLOCK(kpp_clk, 0, CCM_CGR1, 20, get_rate_ipg, NULL); DEFINE_CLOCK(mlb_clk, 0, CCM_CGR1, 22, get_rate_ahb, NULL); DEFINE_CLOCK(mshc_clk, 0, CCM_CGR1, 24, get_rate_mshc, NULL); @@ -485,10 +506,10 @@ static struct clk_lookup lookups[] = { int __init mx35_clocks_init() { - unsigned int ll = 0; + unsigned int cgr2 = 3 << 26, cgr3 = 0; #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_ICEDCC) - ll = (3 << 16); + cgr2 |= 3 << 16; #endif clkdev_add_table(lookups, ARRAY_SIZE(lookups)); @@ -499,8 +520,20 @@ int __init mx35_clocks_init() __raw_writel((3 << 18), CCM_BASE + CCM_CGR0); __raw_writel((3 << 2) | (3 << 4) | (3 << 6) | (3 << 8) | (3 << 16), CCM_BASE + CCM_CGR1); - __raw_writel((3 << 26) | ll, CCM_BASE + CCM_CGR2); - __raw_writel(0, CCM_BASE + CCM_CGR3); + + /* + * Check if we came up in internal boot mode. If yes, we need some + * extra clocks turned on, otherwise the MX35 boot ROM code will + * hang after a watchdog reset. + */ + if (!(__raw_readl(CCM_BASE + CCM_RCSR) & (3 << 10))) { + /* Additionally turn on UART1, SCC, and IIM clocks */ + cgr2 |= 3 << 16 | 3 << 4; + cgr3 |= 3 << 2; + } + + __raw_writel(cgr2, CCM_BASE + CCM_CGR2); + __raw_writel(cgr3, CCM_BASE + CCM_CGR3); mxc_timer_init(&gpt_clk, MX35_IO_ADDRESS(MX35_GPT1_BASE_ADDR), MX35_INT_GPT); diff --git a/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c b/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c index 1dc5004df866..f8f15e3ac7a0 100644 --- a/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c +++ b/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c @@ -216,7 +216,7 @@ struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = { * Add platform devices present on this baseboard and init * them from CPU side as far as required to use them later on */ -void __init eukrea_mbimxsd_baseboard_init(void) +void __init eukrea_mbimxsd35_baseboard_init(void) { if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads, ARRAY_SIZE(eukrea_mbimxsd_pads))) diff --git a/arch/arm/mach-mx3/mach-cpuimx35.c b/arch/arm/mach-mx3/mach-cpuimx35.c index 63f970f340a2..2a4f8b781ba4 100644 --- a/arch/arm/mach-mx3/mach-cpuimx35.c +++ b/arch/arm/mach-mx3/mach-cpuimx35.c @@ -192,7 +192,7 @@ static void __init mxc_board_init(void) #if defined(CONFIG_USB_ULPI) if (otg_mode_host) { otg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops, - USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT); + ULPI_OTG_DRVVBUS | ULPI_OTG_DRVVBUS_EXT); mxc_register_device(&mxc_otg_host, &otg_pdata); } @@ -201,8 +201,8 @@ static void __init mxc_board_init(void) if (!otg_mode_host) mxc_register_device(&mxc_otg_udc_device, &otg_device_pdata); -#ifdef CONFIG_MACH_EUKREA_MBIMXSD_BASEBOARD - eukrea_mbimxsd_baseboard_init(); +#ifdef CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD + eukrea_mbimxsd35_baseboard_init(); #endif } diff --git a/arch/arm/mach-mx5/clock-mx51.c b/arch/arm/mach-mx5/clock-mx51.c index 6af69def357f..57c10a9926cc 100644 --- a/arch/arm/mach-mx5/clock-mx51.c +++ b/arch/arm/mach-mx5/clock-mx51.c @@ -56,7 +56,7 @@ static void _clk_ccgr_disable(struct clk *clk) { u32 reg; reg = __raw_readl(clk->enable_reg); - reg &= ~(MXC_CCM_CCGRx_MOD_OFF << clk->enable_shift); + reg &= ~(MXC_CCM_CCGRx_CG_MASK << clk->enable_shift); __raw_writel(reg, clk->enable_reg); } diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile index 63b2d8859c3c..88d3a1e920f5 100644 --- a/arch/arm/mach-omap2/Makefile +++ b/arch/arm/mach-omap2/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_LOCAL_TIMERS) += timer-mpu.o obj-$(CONFIG_HOTPLUG_CPU) += omap-hotplug.o obj-$(CONFIG_ARCH_OMAP4) += omap44xx-smc.o omap4-common.o +AFLAGS_omap-headsmp.o :=-Wa,-march=armv7-a AFLAGS_omap44xx-smc.o :=-Wa,-march=armv7-a # Functions loaded to SRAM diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c index 138646deac89..dfdce2d82779 100644 --- a/arch/arm/mach-omap2/clock3xxx_data.c +++ b/arch/arm/mach-omap2/clock3xxx_data.c @@ -3417,7 +3417,13 @@ int __init omap3xxx_clk_init(void) struct omap_clk *c; u32 cpu_clkflg = CK_3XXX; - if (cpu_is_omap34xx()) { + if (cpu_is_omap3517()) { + cpu_mask = RATE_IN_3XXX | RATE_IN_3430ES2PLUS; + cpu_clkflg |= CK_3517; + } else if (cpu_is_omap3505()) { + cpu_mask = RATE_IN_3XXX | RATE_IN_3430ES2PLUS; + cpu_clkflg |= CK_3505; + } else if (cpu_is_omap34xx()) { cpu_mask = RATE_IN_3XXX; cpu_clkflg |= CK_343X; @@ -3432,12 +3438,6 @@ int __init omap3xxx_clk_init(void) cpu_mask |= RATE_IN_3430ES2PLUS; cpu_clkflg |= CK_3430ES2; } - } else if (cpu_is_omap3517()) { - cpu_mask = RATE_IN_3XXX | RATE_IN_3430ES2PLUS; - cpu_clkflg |= CK_3517; - } else if (cpu_is_omap3505()) { - cpu_mask = RATE_IN_3XXX | RATE_IN_3430ES2PLUS; - cpu_clkflg |= CK_3505; } if (omap3_has_192mhz_clk()) diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index e8256a2ed8e7..9a879f959509 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -284,8 +284,8 @@ static void __init omap3_check_revision(void) default: omap_revision = OMAP3630_REV_ES1_2; omap_chip.oc |= CHIP_IS_OMAP3630ES1_2; - break; } + break; default: /* Unknown default to latest silicon rev as default*/ omap_revision = OMAP3630_REV_ES1_2; diff --git a/arch/arm/mach-omap2/include/mach/entry-macro.S b/arch/arm/mach-omap2/include/mach/entry-macro.S index 50fd74916643..06e64e1fc28a 100644 --- a/arch/arm/mach-omap2/include/mach/entry-macro.S +++ b/arch/arm/mach-omap2/include/mach/entry-macro.S @@ -177,7 +177,10 @@ omap_irq_base: .word 0 cmpne \irqnr, \tmp cmpcs \irqnr, \irqnr .endm +#endif +#endif /* MULTI_OMAP2 */ +#ifdef CONFIG_SMP /* We assume that irqstat (the raw value of the IRQ acknowledge * register) is preserved from the macro above. * If there is an IPI, we immediately signal end of interrupt @@ -205,8 +208,7 @@ omap_irq_base: .word 0 streq \irqstat, [\base, #GIC_CPU_EOI] cmp \tmp, #0 .endm -#endif -#endif /* MULTI_OMAP2 */ +#endif /* CONFIG_SMP */ .macro irq_prio_table .endm diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index af3c20c8d3f9..9e9f70e18e3c 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -102,8 +102,7 @@ static void __init wakeup_secondary(void) * Send a 'sev' to wake the secondary core from WFE. * Drain the outstanding writes to memory */ - dsb(); - set_event(); + dsb_sev(); mb(); } diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index fb4994ad622e..7b03426c72a3 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -480,7 +480,9 @@ void omap_sram_idle(void) } /* Disable IO-PAD and IO-CHAIN wakeup */ - if (omap3_has_io_wakeup() && core_next_state < PWRDM_POWER_ON) { + if (omap3_has_io_wakeup() && + (per_next_state < PWRDM_POWER_ON || + core_next_state < PWRDM_POWER_ON)) { prm_clear_mod_reg_bits(OMAP3430_EN_IO_MASK, WKUP_MOD, PM_WKEN); omap3_disable_io_chain(); } diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c index 268a9bc6be8a..58093d9e07be 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c @@ -312,8 +312,7 @@ static int pxa_set_target(struct cpufreq_policy *policy, freqs.cpu = policy->cpu; if (freq_debug) - pr_debug(KERN_INFO "Changing CPU frequency to %d Mhz, " - "(SDRAM %d Mhz)\n", + pr_debug("Changing CPU frequency to %d Mhz, (SDRAM %d Mhz)\n", freqs.new / 1000, (pxa_freq_settings[idx].div2) ? (new_freq_mem / 2000) : (new_freq_mem / 1000)); @@ -398,7 +397,7 @@ static int pxa_set_target(struct cpufreq_policy *policy, return 0; } -static __init int pxa_cpufreq_init(struct cpufreq_policy *policy) +static int pxa_cpufreq_init(struct cpufreq_policy *policy) { int i; unsigned int freq; diff --git a/arch/arm/mach-pxa/cpufreq-pxa3xx.c b/arch/arm/mach-pxa/cpufreq-pxa3xx.c index 27fa329d9a8b..0a0d0fe99220 100644 --- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c +++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c @@ -204,7 +204,7 @@ static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy, return 0; } -static __init int pxa3xx_cpufreq_init(struct cpufreq_policy *policy) +static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy) { int ret = -EINVAL; diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h index 7f64d24cd564..814f1458a06a 100644 --- a/arch/arm/mach-pxa/include/mach/hardware.h +++ b/arch/arm/mach-pxa/include/mach/hardware.h @@ -264,23 +264,35 @@ * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x * == 0x3 for pxa300/pxa310/pxa320 */ +#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x) #define __cpu_is_pxa2xx(id) \ ({ \ unsigned int _id = (id) >> 13 & 0x7; \ _id <= 0x2; \ }) +#else +#define __cpu_is_pxa2xx(id) (0) +#endif +#ifdef CONFIG_PXA3xx #define __cpu_is_pxa3xx(id) \ ({ \ unsigned int _id = (id) >> 13 & 0x7; \ _id == 0x3; \ }) +#else +#define __cpu_is_pxa3xx(id) (0) +#endif +#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935) #define __cpu_is_pxa93x(id) \ ({ \ unsigned int _id = (id) >> 4 & 0xfff; \ _id == 0x683 || _id == 0x693; \ }) +#else +#define __cpu_is_pxa93x(id) (0) +#endif #define cpu_is_pxa2xx() \ ({ \ @@ -309,7 +321,7 @@ extern unsigned long get_clock_tick_rate(void); #define PCIBIOS_MIN_IO 0 #define PCIBIOS_MIN_MEM 0 #define pcibios_assign_all_busses() 1 +#define ARCH_HAS_DMA_SET_COHERENT_MASK #endif - #endif /* _ASM_ARCH_HARDWARE_H */ diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h index 262691fb97d8..fdca3be47d9b 100644 --- a/arch/arm/mach-pxa/include/mach/io.h +++ b/arch/arm/mach-pxa/include/mach/io.h @@ -6,6 +6,8 @@ #ifndef __ASM_ARM_ARCH_IO_H #define __ASM_ARM_ARCH_IO_H +#include <mach/hardware.h> + #define IO_SPACE_LIMIT 0xffffffff /* diff --git a/arch/arm/mach-pxa/include/mach/mfp-pxa300.h b/arch/arm/mach-pxa/include/mach/mfp-pxa300.h index 7139e0dc26d1..4e1287070d21 100644 --- a/arch/arm/mach-pxa/include/mach/mfp-pxa300.h +++ b/arch/arm/mach-pxa/include/mach/mfp-pxa300.h @@ -71,10 +71,10 @@ #define GPIO46_CI_DD_7 MFP_CFG_DRV(GPIO46, AF0, DS04X) #define GPIO47_CI_DD_8 MFP_CFG_DRV(GPIO47, AF1, DS04X) #define GPIO48_CI_DD_9 MFP_CFG_DRV(GPIO48, AF1, DS04X) -#define GPIO52_CI_HSYNC MFP_CFG_DRV(GPIO52, AF0, DS04X) -#define GPIO51_CI_VSYNC MFP_CFG_DRV(GPIO51, AF0, DS04X) #define GPIO49_CI_MCLK MFP_CFG_DRV(GPIO49, AF0, DS04X) #define GPIO50_CI_PCLK MFP_CFG_DRV(GPIO50, AF0, DS04X) +#define GPIO51_CI_HSYNC MFP_CFG_DRV(GPIO51, AF0, DS04X) +#define GPIO52_CI_VSYNC MFP_CFG_DRV(GPIO52, AF0, DS04X) /* KEYPAD */ #define GPIO3_KP_DKIN_6 MFP_CFG_LPM(GPIO3, AF2, FLOAT) diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c index 77ad6d34ab5b..405b92a29793 100644 --- a/arch/arm/mach-pxa/palm27x.c +++ b/arch/arm/mach-pxa/palm27x.c @@ -469,9 +469,13 @@ static struct i2c_board_info __initdata palm27x_pi2c_board_info[] = { }, }; +static struct i2c_pxa_platform_data palm27x_i2c_power_info = { + .use_pio = 1, +}; + void __init palm27x_pmic_init(void) { i2c_register_board_info(1, ARRAY_AND_SIZE(palm27x_pi2c_board_info)); - pxa27x_set_i2c_power_info(NULL); + pxa27x_set_i2c_power_info(&palm27x_i2c_power_info); } #endif diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c index c9b747cedea8..37d6173bbb66 100644 --- a/arch/arm/mach-pxa/vpac270.c +++ b/arch/arm/mach-pxa/vpac270.c @@ -240,6 +240,7 @@ static void __init vpac270_onenand_init(void) {} #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE) static struct pxamci_platform_data vpac270_mci_platform_data = { .ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, + .gpio_power = -1, .gpio_card_detect = GPIO53_VPAC270_SD_DETECT_N, .gpio_card_ro = GPIO52_VPAC270_SD_READONLY, .detect_delay_ms = 200, diff --git a/arch/arm/mach-s3c2410/include/mach/vmalloc.h b/arch/arm/mach-s3c2410/include/mach/vmalloc.h index 315b0078a34d..54297eb0bf5e 100644 --- a/arch/arm/mach-s3c2410/include/mach/vmalloc.h +++ b/arch/arm/mach-s3c2410/include/mach/vmalloc.h @@ -15,6 +15,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H -#define VMALLOC_END (0xE0000000) +#define VMALLOC_END 0xE0000000UL #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-s3c64xx/dev-spi.c b/arch/arm/mach-s3c64xx/dev-spi.c index a492b982aa06..405e62128917 100644 --- a/arch/arm/mach-s3c64xx/dev-spi.c +++ b/arch/arm/mach-s3c64xx/dev-spi.c @@ -18,10 +18,11 @@ #include <mach/map.h> #include <mach/gpio-bank-c.h> #include <mach/spi-clocks.h> +#include <mach/irqs.h> #include <plat/s3c64xx-spi.h> #include <plat/gpio-cfg.h> -#include <plat/irqs.h> +#include <plat/devs.h> static char *spi_src_clks[] = { [S3C64XX_SPI_SRCCLK_PCLK] = "pclk", diff --git a/arch/arm/mach-s3c64xx/include/mach/vmalloc.h b/arch/arm/mach-s3c64xx/include/mach/vmalloc.h index 7411ef3711a6..bc0e91389864 100644 --- a/arch/arm/mach-s3c64xx/include/mach/vmalloc.h +++ b/arch/arm/mach-s3c64xx/include/mach/vmalloc.h @@ -15,6 +15,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H -#define VMALLOC_END (0xE0000000) +#define VMALLOC_END 0xE0000000UL #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-s3c64xx/mach-real6410.c b/arch/arm/mach-s3c64xx/mach-real6410.c index 5c07d013b23d..e130379ba0e8 100644 --- a/arch/arm/mach-s3c64xx/mach-real6410.c +++ b/arch/arm/mach-s3c64xx/mach-real6410.c @@ -30,73 +30,73 @@ #include <plat/devs.h> #include <plat/regs-serial.h> -#define UCON S3C2410_UCON_DEFAULT | S3C2410_UCON_UCLK -#define ULCON S3C2410_LCON_CS8 | S3C2410_LCON_PNONE | S3C2410_LCON_STOPB -#define UFCON S3C2410_UFCON_RXTRIG8 | S3C2410_UFCON_FIFOMODE +#define UCON (S3C2410_UCON_DEFAULT | S3C2410_UCON_UCLK) +#define ULCON (S3C2410_LCON_CS8 | S3C2410_LCON_PNONE | S3C2410_LCON_STOPB) +#define UFCON (S3C2410_UFCON_RXTRIG8 | S3C2410_UFCON_FIFOMODE) static struct s3c2410_uartcfg real6410_uartcfgs[] __initdata = { [0] = { - .hwport = 0, - .flags = 0, - .ucon = UCON, - .ulcon = ULCON, - .ufcon = UFCON, + .hwport = 0, + .flags = 0, + .ucon = UCON, + .ulcon = ULCON, + .ufcon = UFCON, }, [1] = { - .hwport = 1, - .flags = 0, - .ucon = UCON, - .ulcon = ULCON, - .ufcon = UFCON, + .hwport = 1, + .flags = 0, + .ucon = UCON, + .ulcon = ULCON, + .ufcon = UFCON, }, [2] = { - .hwport = 2, - .flags = 0, - .ucon = UCON, - .ulcon = ULCON, - .ufcon = UFCON, + .hwport = 2, + .flags = 0, + .ucon = UCON, + .ulcon = ULCON, + .ufcon = UFCON, }, [3] = { - .hwport = 3, - .flags = 0, - .ucon = UCON, - .ulcon = ULCON, - .ufcon = UFCON, + .hwport = 3, + .flags = 0, + .ucon = UCON, + .ulcon = ULCON, + .ufcon = UFCON, }, }; /* DM9000AEP 10/100 ethernet controller */ static struct resource real6410_dm9k_resource[] = { - [0] = { - .start = S3C64XX_PA_XM0CSN1, - .end = S3C64XX_PA_XM0CSN1 + 1, - .flags = IORESOURCE_MEM - }, - [1] = { - .start = S3C64XX_PA_XM0CSN1 + 4, - .end = S3C64XX_PA_XM0CSN1 + 5, - .flags = IORESOURCE_MEM - }, - [2] = { - .start = S3C_EINT(7), - .end = S3C_EINT(7), - .flags = IORESOURCE_IRQ, - } + [0] = { + .start = S3C64XX_PA_XM0CSN1, + .end = S3C64XX_PA_XM0CSN1 + 1, + .flags = IORESOURCE_MEM + }, + [1] = { + .start = S3C64XX_PA_XM0CSN1 + 4, + .end = S3C64XX_PA_XM0CSN1 + 5, + .flags = IORESOURCE_MEM + }, + [2] = { + .start = S3C_EINT(7), + .end = S3C_EINT(7), + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL + } }; static struct dm9000_plat_data real6410_dm9k_pdata = { - .flags = (DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM), + .flags = (DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM), }; static struct platform_device real6410_device_eth = { - .name = "dm9000", - .id = -1, - .num_resources = ARRAY_SIZE(real6410_dm9k_resource), - .resource = real6410_dm9k_resource, - .dev = { - .platform_data = &real6410_dm9k_pdata, - }, + .name = "dm9000", + .id = -1, + .num_resources = ARRAY_SIZE(real6410_dm9k_resource), + .resource = real6410_dm9k_resource, + .dev = { + .platform_data = &real6410_dm9k_pdata, + }, }; static struct platform_device *real6410_devices[] __initdata = { @@ -129,12 +129,12 @@ static void __init real6410_machine_init(void) /* set timing for nCS1 suitable for ethernet chip */ __raw_writel((0 << S3C64XX_SROM_BCX__PMC__SHIFT) | - (6 << S3C64XX_SROM_BCX__TACP__SHIFT) | - (4 << S3C64XX_SROM_BCX__TCAH__SHIFT) | - (1 << S3C64XX_SROM_BCX__TCOH__SHIFT) | - (13 << S3C64XX_SROM_BCX__TACC__SHIFT) | - (4 << S3C64XX_SROM_BCX__TCOS__SHIFT) | - (0 << S3C64XX_SROM_BCX__TACS__SHIFT), S3C64XX_SROM_BC1); + (6 << S3C64XX_SROM_BCX__TACP__SHIFT) | + (4 << S3C64XX_SROM_BCX__TCAH__SHIFT) | + (1 << S3C64XX_SROM_BCX__TCOH__SHIFT) | + (13 << S3C64XX_SROM_BCX__TACC__SHIFT) | + (4 << S3C64XX_SROM_BCX__TCOS__SHIFT) | + (0 << S3C64XX_SROM_BCX__TACS__SHIFT), S3C64XX_SROM_BC1); platform_add_devices(real6410_devices, ARRAY_SIZE(real6410_devices)); } diff --git a/arch/arm/mach-s5p6440/cpu.c b/arch/arm/mach-s5p6440/cpu.c index 526f33adb31d..ec592e866054 100644 --- a/arch/arm/mach-s5p6440/cpu.c +++ b/arch/arm/mach-s5p6440/cpu.c @@ -19,6 +19,7 @@ #include <linux/sysdev.h> #include <linux/serial_core.h> #include <linux/platform_device.h> +#include <linux/sched.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/mach-s5p6440/include/mach/vmalloc.h b/arch/arm/mach-s5p6440/include/mach/vmalloc.h index 16df257b1dce..e3f0eebf5205 100644 --- a/arch/arm/mach-s5p6440/include/mach/vmalloc.h +++ b/arch/arm/mach-s5p6440/include/mach/vmalloc.h @@ -12,6 +12,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H -#define VMALLOC_END (0xE0000000) +#define VMALLOC_END 0xE0000000UL #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-s5p6442/cpu.c b/arch/arm/mach-s5p6442/cpu.c index a48fb553fd01..70ac681af72b 100644 --- a/arch/arm/mach-s5p6442/cpu.c +++ b/arch/arm/mach-s5p6442/cpu.c @@ -19,6 +19,7 @@ #include <linux/sysdev.h> #include <linux/serial_core.h> #include <linux/platform_device.h> +#include <linux/sched.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/mach-s5p6442/include/mach/vmalloc.h b/arch/arm/mach-s5p6442/include/mach/vmalloc.h index be3333688c20..f5c83f02c18e 100644 --- a/arch/arm/mach-s5p6442/include/mach/vmalloc.h +++ b/arch/arm/mach-s5p6442/include/mach/vmalloc.h @@ -12,6 +12,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H -#define VMALLOC_END (0xE0000000) +#define VMALLOC_END 0xE0000000UL #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-s5pc100/cpu.c b/arch/arm/mach-s5pc100/cpu.c index 251c92ac5b22..cd1afbce83e2 100644 --- a/arch/arm/mach-s5pc100/cpu.c +++ b/arch/arm/mach-s5pc100/cpu.c @@ -21,6 +21,7 @@ #include <linux/sysdev.h> #include <linux/serial_core.h> #include <linux/platform_device.h> +#include <linux/sched.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c index af91fefef2c6..d562670e1b0b 100644 --- a/arch/arm/mach-s5pv210/clock.c +++ b/arch/arm/mach-s5pv210/clock.c @@ -173,11 +173,6 @@ static int s5pv210_clk_ip3_ctrl(struct clk *clk, int enable) return s5p_gatectrl(S5P_CLKGATE_IP3, clk, enable); } -static int s5pv210_clk_ip4_ctrl(struct clk *clk, int enable) -{ - return s5p_gatectrl(S5P_CLKGATE_IP4, clk, enable); -} - static int s5pv210_clk_mask0_ctrl(struct clk *clk, int enable) { return s5p_gatectrl(S5P_CLK_SRC_MASK0, clk, enable); @@ -281,6 +276,24 @@ static struct clk init_clocks_disable[] = { .enable = s5pv210_clk_ip0_ctrl, .ctrlbit = (1<<29), }, { + .name = "fimc", + .id = 0, + .parent = &clk_hclk_dsys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 24), + }, { + .name = "fimc", + .id = 1, + .parent = &clk_hclk_dsys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 25), + }, { + .name = "fimc", + .id = 2, + .parent = &clk_hclk_dsys.clk, + .enable = s5pv210_clk_ip0_ctrl, + .ctrlbit = (1 << 26), + }, { .name = "otg", .id = -1, .parent = &clk_hclk_psys.clk, @@ -357,7 +370,7 @@ static struct clk init_clocks_disable[] = { .id = 1, .parent = &clk_pclk_psys.clk, .enable = s5pv210_clk_ip3_ctrl, - .ctrlbit = (1<<8), + .ctrlbit = (1 << 10), }, { .name = "i2c", .id = 2, diff --git a/arch/arm/mach-s5pv210/cpu.c b/arch/arm/mach-s5pv210/cpu.c index b9f4d677cf55..245b82b53df4 100644 --- a/arch/arm/mach-s5pv210/cpu.c +++ b/arch/arm/mach-s5pv210/cpu.c @@ -19,6 +19,7 @@ #include <linux/io.h> #include <linux/sysdev.h> #include <linux/platform_device.h> +#include <linux/sched.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> @@ -47,7 +48,7 @@ static struct map_desc s5pv210_iodesc[] __initdata = { { .virtual = (unsigned long)S5P_VA_SYSTIMER, .pfn = __phys_to_pfn(S5PV210_PA_SYSTIMER), - .length = SZ_1M, + .length = SZ_4K, .type = MT_DEVICE, }, { .virtual = (unsigned long)VA_VIC2, diff --git a/arch/arm/mach-s5pv210/include/mach/vmalloc.h b/arch/arm/mach-s5pv210/include/mach/vmalloc.h index 58f515e0747e..df9a28808323 100644 --- a/arch/arm/mach-s5pv210/include/mach/vmalloc.h +++ b/arch/arm/mach-s5pv210/include/mach/vmalloc.h @@ -17,6 +17,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H __FILE__ -#define VMALLOC_END (0xE0000000) +#define VMALLOC_END (0xE0000000UL) #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-s5pv310/clock.c b/arch/arm/mach-s5pv310/clock.c index 77f2b4d85e6b..26a0f03df8ea 100644 --- a/arch/arm/mach-s5pv310/clock.c +++ b/arch/arm/mach-s5pv310/clock.c @@ -30,6 +30,16 @@ static struct clk clk_sclk_hdmi27m = { .rate = 27000000, }; +static int s5pv310_clksrc_mask_peril0_ctrl(struct clk *clk, int enable) +{ + return s5p_gatectrl(S5P_CLKSRC_MASK_PERIL0, clk, enable); +} + +static int s5pv310_clk_ip_peril_ctrl(struct clk *clk, int enable) +{ + return s5p_gatectrl(S5P_CLKGATE_IP_PERIL, clk, enable); +} + /* Core list of CMU_CPU side */ static struct clksrc_clk clk_mout_apll = { @@ -39,6 +49,14 @@ static struct clksrc_clk clk_mout_apll = { }, .sources = &clk_src_apll, .reg_src = { .reg = S5P_CLKSRC_CPU, .shift = 0, .size = 1 }, +}; + +static struct clksrc_clk clk_sclk_apll = { + .clk = { + .name = "sclk_apll", + .id = -1, + .parent = &clk_mout_apll.clk, + }, .reg_div = { .reg = S5P_CLKDIV_CPU, .shift = 24, .size = 3 }, }; @@ -61,7 +79,7 @@ static struct clksrc_clk clk_mout_mpll = { }; static struct clk *clkset_moutcore_list[] = { - [0] = &clk_mout_apll.clk, + [0] = &clk_sclk_apll.clk, [1] = &clk_mout_mpll.clk, }; @@ -154,7 +172,7 @@ static struct clksrc_clk clk_pclk_dbg = { static struct clk *clkset_corebus_list[] = { [0] = &clk_mout_mpll.clk, - [1] = &clk_mout_apll.clk, + [1] = &clk_sclk_apll.clk, }; static struct clksrc_sources clkset_mout_corebus = { @@ -220,7 +238,7 @@ static struct clksrc_clk clk_pclk_acp = { static struct clk *clkset_aclk_top_list[] = { [0] = &clk_mout_mpll.clk, - [1] = &clk_mout_apll.clk, + [1] = &clk_sclk_apll.clk, }; static struct clksrc_sources clkset_aclk_200 = { @@ -321,11 +339,6 @@ static struct clksrc_clk clk_sclk_vpll = { .reg_src = { .reg = S5P_CLKSRC_TOP0, .shift = 8, .size = 1 }, }; -static int s5pv310_clk_ip_peril_ctrl(struct clk *clk, int enable) -{ - return s5p_gatectrl(S5P_CLKGATE_IP_PERIL, clk, enable); -} - static struct clk init_clocks_disable[] = { { .name = "timers", @@ -337,7 +350,37 @@ static struct clk init_clocks_disable[] = { }; static struct clk init_clocks[] = { - /* Nothing here yet */ + { + .name = "uart", + .id = 0, + .enable = s5pv310_clk_ip_peril_ctrl, + .ctrlbit = (1 << 0), + }, { + .name = "uart", + .id = 1, + .enable = s5pv310_clk_ip_peril_ctrl, + .ctrlbit = (1 << 1), + }, { + .name = "uart", + .id = 2, + .enable = s5pv310_clk_ip_peril_ctrl, + .ctrlbit = (1 << 2), + }, { + .name = "uart", + .id = 3, + .enable = s5pv310_clk_ip_peril_ctrl, + .ctrlbit = (1 << 3), + }, { + .name = "uart", + .id = 4, + .enable = s5pv310_clk_ip_peril_ctrl, + .ctrlbit = (1 << 4), + }, { + .name = "uart", + .id = 5, + .enable = s5pv310_clk_ip_peril_ctrl, + .ctrlbit = (1 << 5), + } }; static struct clk *clkset_group_list[] = { @@ -359,8 +402,8 @@ static struct clksrc_clk clksrcs[] = { .clk = { .name = "uclk1", .id = 0, + .enable = s5pv310_clksrc_mask_peril0_ctrl, .ctrlbit = (1 << 0), - .enable = s5pv310_clk_ip_peril_ctrl, }, .sources = &clkset_group, .reg_src = { .reg = S5P_CLKSRC_PERIL0, .shift = 0, .size = 4 }, @@ -369,8 +412,8 @@ static struct clksrc_clk clksrcs[] = { .clk = { .name = "uclk1", .id = 1, - .enable = s5pv310_clk_ip_peril_ctrl, - .ctrlbit = (1 << 1), + .enable = s5pv310_clksrc_mask_peril0_ctrl, + .ctrlbit = (1 << 4), }, .sources = &clkset_group, .reg_src = { .reg = S5P_CLKSRC_PERIL0, .shift = 4, .size = 4 }, @@ -379,8 +422,8 @@ static struct clksrc_clk clksrcs[] = { .clk = { .name = "uclk1", .id = 2, - .enable = s5pv310_clk_ip_peril_ctrl, - .ctrlbit = (1 << 2), + .enable = s5pv310_clksrc_mask_peril0_ctrl, + .ctrlbit = (1 << 8), }, .sources = &clkset_group, .reg_src = { .reg = S5P_CLKSRC_PERIL0, .shift = 8, .size = 4 }, @@ -389,8 +432,8 @@ static struct clksrc_clk clksrcs[] = { .clk = { .name = "uclk1", .id = 3, - .enable = s5pv310_clk_ip_peril_ctrl, - .ctrlbit = (1 << 3), + .enable = s5pv310_clksrc_mask_peril0_ctrl, + .ctrlbit = (1 << 12), }, .sources = &clkset_group, .reg_src = { .reg = S5P_CLKSRC_PERIL0, .shift = 12, .size = 4 }, @@ -399,7 +442,7 @@ static struct clksrc_clk clksrcs[] = { .clk = { .name = "sclk_pwm", .id = -1, - .enable = s5pv310_clk_ip_peril_ctrl, + .enable = s5pv310_clksrc_mask_peril0_ctrl, .ctrlbit = (1 << 24), }, .sources = &clkset_group, @@ -411,6 +454,7 @@ static struct clksrc_clk clksrcs[] = { /* Clock initialization code */ static struct clksrc_clk *sysclks[] = { &clk_mout_apll, + &clk_sclk_apll, &clk_mout_epll, &clk_mout_mpll, &clk_moutcore, @@ -470,11 +514,11 @@ void __init_or_cpufreq s5pv310_setup_clocks(void) apll = s5p_get_pll45xx(xtal, __raw_readl(S5P_APLL_CON0), pll_4508); mpll = s5p_get_pll45xx(xtal, __raw_readl(S5P_MPLL_CON0), pll_4508); epll = s5p_get_pll46xx(xtal, __raw_readl(S5P_EPLL_CON0), - __raw_readl(S5P_EPLL_CON1), pll_4500); + __raw_readl(S5P_EPLL_CON1), pll_4600); vpllsrc = clk_get_rate(&clk_vpllsrc.clk); vpll = s5p_get_pll46xx(vpllsrc, __raw_readl(S5P_VPLL_CON0), - __raw_readl(S5P_VPLL_CON1), pll_4502); + __raw_readl(S5P_VPLL_CON1), pll_4650); clk_fout_apll.rate = apll; clk_fout_mpll.rate = mpll; diff --git a/arch/arm/mach-s5pv310/cpu.c b/arch/arm/mach-s5pv310/cpu.c index 196c9f12ed85..e5b261a99ab2 100644 --- a/arch/arm/mach-s5pv310/cpu.c +++ b/arch/arm/mach-s5pv310/cpu.c @@ -45,6 +45,16 @@ static struct map_desc s5pv310_iodesc[] __initdata = { .pfn = __phys_to_pfn(S5PV310_PA_L2CC), .length = SZ_4K, .type = MT_DEVICE, + }, { + .virtual = (unsigned long)S5P_VA_SYSRAM, + .pfn = __phys_to_pfn(S5PV310_PA_SYSRAM), + .length = SZ_4K, + .type = MT_DEVICE, + }, { + .virtual = (unsigned long)S5P_VA_CMU, + .pfn = __phys_to_pfn(S5PV310_PA_CMU), + .length = SZ_128K, + .type = MT_DEVICE, }, }; diff --git a/arch/arm/mach-s5pv310/include/mach/irqs.h b/arch/arm/mach-s5pv310/include/mach/irqs.h index 56885ca3773c..4cdedda6e652 100644 --- a/arch/arm/mach-s5pv310/include/mach/irqs.h +++ b/arch/arm/mach-s5pv310/include/mach/irqs.h @@ -15,12 +15,14 @@ #include <plat/irqs.h> -/* Private Peripheral Interrupt */ +/* PPI: Private Peripheral Interrupt */ + #define IRQ_PPI(x) S5P_IRQ(x+16) #define IRQ_LOCALTIMER IRQ_PPI(13) -/* Shared Peripheral Interrupt */ +/* SPI: Shared Peripheral Interrupt */ + #define IRQ_SPI(x) S5P_IRQ(x+32) #define IRQ_EINT0 IRQ_SPI(40) @@ -36,7 +38,7 @@ #define IRQ_PCIE IRQ_SPI(50) #define IRQ_SYSTEM_TIMER IRQ_SPI(51) #define IRQ_MFC IRQ_SPI(52) -#define IRQ_WTD IRQ_SPI(53) +#define IRQ_WDT IRQ_SPI(53) #define IRQ_AUDIO_SS IRQ_SPI(54) #define IRQ_AC97 IRQ_SPI(55) #define IRQ_SPDIF IRQ_SPI(56) @@ -67,8 +69,9 @@ #define IRQ_IIC COMBINER_IRQ(27, 0) /* Set the default NR_IRQS */ + #define NR_IRQS COMBINER_IRQ(MAX_COMBINER_NR, 0) #define MAX_COMBINER_NR 39 -#endif /* ASM_ARCH_IRQS_H */ +#endif /* __ASM_ARCH_IRQS_H */ diff --git a/arch/arm/mach-s5pv310/include/mach/map.h b/arch/arm/mach-s5pv310/include/mach/map.h index 87697c9fca5b..213e1101a3b3 100644 --- a/arch/arm/mach-s5pv310/include/mach/map.h +++ b/arch/arm/mach-s5pv310/include/mach/map.h @@ -23,12 +23,16 @@ #include <plat/map-s5p.h> +#define S5PV310_PA_SYSRAM (0x02025000) + #define S5PV310_PA_CHIPID (0x10000000) #define S5P_PA_CHIPID S5PV310_PA_CHIPID #define S5PV310_PA_SYSCON (0x10020000) #define S5P_PA_SYSCON S5PV310_PA_SYSCON +#define S5PV310_PA_CMU (0x10030000) + #define S5PV310_PA_WATCHDOG (0x10060000) #define S5PV310_PA_COMBINER (0x10448000) @@ -39,8 +43,12 @@ #define S5PV310_PA_GIC_DIST (0x10501000) #define S5PV310_PA_L2CC (0x10502000) -#define S5PV310_PA_GPIO (0x11000000) -#define S5P_PA_GPIO S5PV310_PA_GPIO +#define S5PV310_PA_GPIO1 (0x11400000) +#define S5PV310_PA_GPIO2 (0x11000000) +#define S5PV310_PA_GPIO3 (0x03860000) +#define S5P_PA_GPIO S5PV310_PA_GPIO1 + +#define S5PV310_PA_HSMMC(x) (0x12510000 + ((x) * 0x10000)) #define S5PV310_PA_UART (0x13800000) @@ -63,6 +71,10 @@ /* compatibiltiy defines. */ #define S3C_PA_UART S5PV310_PA_UART +#define S3C_PA_HSMMC0 S5PV310_PA_HSMMC(0) +#define S3C_PA_HSMMC1 S5PV310_PA_HSMMC(1) +#define S3C_PA_HSMMC2 S5PV310_PA_HSMMC(2) +#define S3C_PA_HSMMC3 S5PV310_PA_HSMMC(3) #define S3C_PA_IIC S5PV310_PA_IIC0 #define S3C_PA_WDT S5PV310_PA_WATCHDOG diff --git a/arch/arm/mach-s5pv310/include/mach/regs-clock.h b/arch/arm/mach-s5pv310/include/mach/regs-clock.h index 59e3a7e94d80..4013553cd9be 100644 --- a/arch/arm/mach-s5pv310/include/mach/regs-clock.h +++ b/arch/arm/mach-s5pv310/include/mach/regs-clock.h @@ -15,48 +15,49 @@ #include <mach/map.h> -#define S5P_CLKREG(x) (S3C_VA_SYS + (x)) +#define S5P_CLKREG(x) (S5P_VA_CMU + (x)) #define S5P_INFORM0 S5P_CLKREG(0x800) -#define S5P_EPLL_CON0 S5P_CLKREG(0x1C110) -#define S5P_EPLL_CON1 S5P_CLKREG(0x1C114) -#define S5P_VPLL_CON0 S5P_CLKREG(0x1C120) -#define S5P_VPLL_CON1 S5P_CLKREG(0x1C124) +#define S5P_EPLL_CON0 S5P_CLKREG(0x0C110) +#define S5P_EPLL_CON1 S5P_CLKREG(0x0C114) +#define S5P_VPLL_CON0 S5P_CLKREG(0x0C120) +#define S5P_VPLL_CON1 S5P_CLKREG(0x0C124) -#define S5P_CLKSRC_TOP0 S5P_CLKREG(0x1C210) -#define S5P_CLKSRC_TOP1 S5P_CLKREG(0x1C214) +#define S5P_CLKSRC_TOP0 S5P_CLKREG(0x0C210) +#define S5P_CLKSRC_TOP1 S5P_CLKREG(0x0C214) -#define S5P_CLKSRC_PERIL0 S5P_CLKREG(0x1C250) +#define S5P_CLKSRC_PERIL0 S5P_CLKREG(0x0C250) -#define S5P_CLKDIV_TOP S5P_CLKREG(0x1C510) +#define S5P_CLKDIV_TOP S5P_CLKREG(0x0C510) -#define S5P_CLKDIV_PERIL0 S5P_CLKREG(0x1C550) -#define S5P_CLKDIV_PERIL1 S5P_CLKREG(0x1C554) -#define S5P_CLKDIV_PERIL2 S5P_CLKREG(0x1C558) -#define S5P_CLKDIV_PERIL3 S5P_CLKREG(0x1C55C) -#define S5P_CLKDIV_PERIL4 S5P_CLKREG(0x1C560) -#define S5P_CLKDIV_PERIL5 S5P_CLKREG(0x1C564) +#define S5P_CLKDIV_PERIL0 S5P_CLKREG(0x0C550) +#define S5P_CLKDIV_PERIL1 S5P_CLKREG(0x0C554) +#define S5P_CLKDIV_PERIL2 S5P_CLKREG(0x0C558) +#define S5P_CLKDIV_PERIL3 S5P_CLKREG(0x0C55C) +#define S5P_CLKDIV_PERIL4 S5P_CLKREG(0x0C560) +#define S5P_CLKDIV_PERIL5 S5P_CLKREG(0x0C564) -#define S5P_CLKGATE_IP_PERIL S5P_CLKREG(0x1C950) +#define S5P_CLKSRC_MASK_PERIL0 S5P_CLKREG(0x0C350) -#define S5P_CLKSRC_CORE S5P_CLKREG(0x20200) +#define S5P_CLKGATE_IP_PERIL S5P_CLKREG(0x0C950) -#define S5P_CLKDIV_CORE0 S5P_CLKREG(0x20500) +#define S5P_CLKSRC_CORE S5P_CLKREG(0x10200) +#define S5P_CLKDIV_CORE0 S5P_CLKREG(0x10500) -#define S5P_APLL_LOCK S5P_CLKREG(0x24000) -#define S5P_MPLL_LOCK S5P_CLKREG(0x24004) -#define S5P_APLL_CON0 S5P_CLKREG(0x24100) -#define S5P_APLL_CON1 S5P_CLKREG(0x24104) -#define S5P_MPLL_CON0 S5P_CLKREG(0x24108) -#define S5P_MPLL_CON1 S5P_CLKREG(0x2410C) +#define S5P_APLL_LOCK S5P_CLKREG(0x14000) +#define S5P_MPLL_LOCK S5P_CLKREG(0x14004) +#define S5P_APLL_CON0 S5P_CLKREG(0x14100) +#define S5P_APLL_CON1 S5P_CLKREG(0x14104) +#define S5P_MPLL_CON0 S5P_CLKREG(0x14108) +#define S5P_MPLL_CON1 S5P_CLKREG(0x1410C) -#define S5P_CLKSRC_CPU S5P_CLKREG(0x24200) -#define S5P_CLKMUX_STATCPU S5P_CLKREG(0x24400) +#define S5P_CLKSRC_CPU S5P_CLKREG(0x14200) +#define S5P_CLKMUX_STATCPU S5P_CLKREG(0x14400) -#define S5P_CLKDIV_CPU S5P_CLKREG(0x24500) -#define S5P_CLKDIV_STATCPU S5P_CLKREG(0x24600) +#define S5P_CLKDIV_CPU S5P_CLKREG(0x14500) +#define S5P_CLKDIV_STATCPU S5P_CLKREG(0x14600) -#define S5P_CLKGATE_SCLKCPU S5P_CLKREG(0x24800) +#define S5P_CLKGATE_SCLKCPU S5P_CLKREG(0x14800) #endif /* __ASM_ARCH_REGS_CLOCK_H */ diff --git a/arch/arm/mach-s5pv310/include/mach/vmalloc.h b/arch/arm/mach-s5pv310/include/mach/vmalloc.h index 3f565ebb7daa..256f221edf3a 100644 --- a/arch/arm/mach-s5pv310/include/mach/vmalloc.h +++ b/arch/arm/mach-s5pv310/include/mach/vmalloc.h @@ -17,6 +17,6 @@ #ifndef __ASM_ARCH_VMALLOC_H #define __ASM_ARCH_VMALLOC_H __FILE__ -#define VMALLOC_END (0xF0000000) +#define VMALLOC_END (0xF0000000UL) #endif /* __ASM_ARCH_VMALLOC_H */ diff --git a/arch/arm/mach-s5pv310/platsmp.c b/arch/arm/mach-s5pv310/platsmp.c index fe9469abd006..d357c198edee 100644 --- a/arch/arm/mach-s5pv310/platsmp.c +++ b/arch/arm/mach-s5pv310/platsmp.c @@ -187,6 +187,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) * until it receives a soft interrupt, and then the * secondary CPU branches to this address. */ - __raw_writel(BSYM(virt_to_phys(s5pv310_secondary_startup)), S5P_INFORM0); + __raw_writel(BSYM(virt_to_phys(s5pv310_secondary_startup)), S5P_VA_SYSRAM); } } diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile index 5e16b4c69222..ae416fe7daf2 100644 --- a/arch/arm/mach-shmobile/Makefile +++ b/arch/arm/mach-shmobile/Makefile @@ -3,7 +3,7 @@ # # Common objects -obj-y := timer.o console.o clock.o +obj-y := timer.o console.o clock.o pm_runtime.o # CPU objects obj-$(CONFIG_ARCH_SH7367) += setup-sh7367.o clock-sh7367.o intc-sh7367.o diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index 23d472f9525e..95935c83c306 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -25,6 +25,7 @@ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/mfd/sh_mobile_sdhi.h> +#include <linux/mfd/tmio.h> #include <linux/mmc/host.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> @@ -39,6 +40,7 @@ #include <linux/sh_clk.h> #include <linux/gpio.h> #include <linux/input.h> +#include <linux/leds.h> #include <linux/input/sh_keysc.h> #include <linux/usb/r8a66597.h> @@ -307,6 +309,7 @@ static struct sh_mobile_sdhi_info sdhi1_info = { .dma_slave_tx = SHDMA_SLAVE_SDHI1_TX, .dma_slave_rx = SHDMA_SLAVE_SDHI1_RX, .tmio_ocr_mask = MMC_VDD_165_195, + .tmio_flags = TMIO_MMC_WRPROTECT_DISABLE, }; static struct resource sdhi1_resources[] = { @@ -558,7 +561,7 @@ static struct resource fsi_resources[] = { static struct platform_device fsi_device = { .name = "sh_fsi2", - .id = 0, + .id = -1, .num_resources = ARRAY_SIZE(fsi_resources), .resource = fsi_resources, .dev = { @@ -650,7 +653,44 @@ static struct platform_device hdmi_device = { }, }; +static struct gpio_led ap4evb_leds[] = { + { + .name = "led4", + .gpio = GPIO_PORT185, + .default_state = LEDS_GPIO_DEFSTATE_ON, + }, + { + .name = "led2", + .gpio = GPIO_PORT186, + .default_state = LEDS_GPIO_DEFSTATE_ON, + }, + { + .name = "led3", + .gpio = GPIO_PORT187, + .default_state = LEDS_GPIO_DEFSTATE_ON, + }, + { + .name = "led1", + .gpio = GPIO_PORT188, + .default_state = LEDS_GPIO_DEFSTATE_ON, + } +}; + +static struct gpio_led_platform_data ap4evb_leds_pdata = { + .num_leds = ARRAY_SIZE(ap4evb_leds), + .leds = ap4evb_leds, +}; + +static struct platform_device leds_device = { + .name = "leds-gpio", + .id = 0, + .dev = { + .platform_data = &ap4evb_leds_pdata, + }, +}; + static struct platform_device *ap4evb_devices[] __initdata = { + &leds_device, &nor_flash_device, &smc911x_device, &sdhi0_device, @@ -840,20 +880,6 @@ static void __init ap4evb_init(void) gpio_request(GPIO_FN_CS5A, NULL); gpio_request(GPIO_FN_IRQ6_39, NULL); - /* enable LED 1 - 4 */ - gpio_request(GPIO_PORT185, NULL); - gpio_request(GPIO_PORT186, NULL); - gpio_request(GPIO_PORT187, NULL); - gpio_request(GPIO_PORT188, NULL); - gpio_direction_output(GPIO_PORT185, 1); - gpio_direction_output(GPIO_PORT186, 1); - gpio_direction_output(GPIO_PORT187, 1); - gpio_direction_output(GPIO_PORT188, 1); - gpio_export(GPIO_PORT185, 0); - gpio_export(GPIO_PORT186, 0); - gpio_export(GPIO_PORT187, 0); - gpio_export(GPIO_PORT188, 0); - /* enable Debug switch (S6) */ gpio_request(GPIO_PORT32, NULL); gpio_request(GPIO_PORT33, NULL); diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c index fb4e9b1d788e..759468992ad2 100644 --- a/arch/arm/mach-shmobile/clock-sh7372.c +++ b/arch/arm/mach-shmobile/clock-sh7372.c @@ -286,7 +286,6 @@ static struct clk_ops pllc2_clk_ops = { struct clk pllc2_clk = { .ops = &pllc2_clk_ops, - .flags = CLK_ENABLE_ON_INIT, .parent = &extal1_div2_clk, .freq_table = pllc2_freq_table, .parent_table = pllc2_parent, @@ -395,7 +394,7 @@ static struct clk div6_reparent_clks[DIV6_REPARENT_NR] = { enum { MSTP001, MSTP131, MSTP130, - MSTP129, MSTP128, + MSTP129, MSTP128, MSTP127, MSTP126, MSTP118, MSTP117, MSTP116, MSTP106, MSTP101, MSTP100, MSTP223, @@ -413,6 +412,8 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP130] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 30, 0), /* VEU2 */ [MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* VEU1 */ [MSTP128] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 28, 0), /* VEU0 */ + [MSTP127] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 27, 0), /* CEU */ + [MSTP126] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 26, 0), /* CSI2 */ [MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX */ [MSTP117] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 17, 0), /* LCDC1 */ [MSTP116] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 16, 0), /* IIC0 */ @@ -428,7 +429,7 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */ [MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */ [MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */ - [MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, CLK_ENABLE_ON_INIT), /* FSIA */ + [MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSIA */ [MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */ [MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */ [MSTP314] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 14, 0), /* SDHI0 */ @@ -498,6 +499,8 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("uio_pdrv_genirq.3", &mstp_clks[MSTP130]), /* VEU2 */ CLKDEV_DEV_ID("uio_pdrv_genirq.2", &mstp_clks[MSTP129]), /* VEU1 */ CLKDEV_DEV_ID("uio_pdrv_genirq.1", &mstp_clks[MSTP128]), /* VEU0 */ + CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[MSTP127]), /* CEU */ + CLKDEV_DEV_ID("sh-mobile-csi2.0", &mstp_clks[MSTP126]), /* CSI2 */ CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX */ CLKDEV_DEV_ID("sh_mobile_lcdc_fb.1", &mstp_clks[MSTP117]), /* LCDC1 */ CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* IIC0 */ diff --git a/arch/arm/mach-shmobile/clock.c b/arch/arm/mach-shmobile/clock.c index b7c705a213a2..6b7c7c42bc8f 100644 --- a/arch/arm/mach-shmobile/clock.c +++ b/arch/arm/mach-shmobile/clock.c @@ -1,8 +1,10 @@ /* - * SH-Mobile Timer + * SH-Mobile Clock Framework * * Copyright (C) 2010 Magnus Damm * + * Used together with arch/arm/common/clkdev.c and drivers/sh/clk.c. + * * 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. diff --git a/arch/arm/mach-shmobile/pm_runtime.c b/arch/arm/mach-shmobile/pm_runtime.c new file mode 100644 index 000000000000..94912d3944d3 --- /dev/null +++ b/arch/arm/mach-shmobile/pm_runtime.c @@ -0,0 +1,169 @@ +/* + * arch/arm/mach-shmobile/pm_runtime.c + * + * Runtime PM support code for SuperH Mobile ARM + * + * Copyright (C) 2009-2010 Magnus Damm + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/io.h> +#include <linux/pm_runtime.h> +#include <linux/platform_device.h> +#include <linux/clk.h> +#include <linux/sh_clk.h> +#include <linux/bitmap.h> + +#ifdef CONFIG_PM_RUNTIME +#define BIT_ONCE 0 +#define BIT_ACTIVE 1 +#define BIT_CLK_ENABLED 2 + +struct pm_runtime_data { + unsigned long flags; + struct clk *clk; +}; + +static void __devres_release(struct device *dev, void *res) +{ + struct pm_runtime_data *prd = res; + + dev_dbg(dev, "__devres_release()\n"); + + if (test_bit(BIT_CLK_ENABLED, &prd->flags)) + clk_disable(prd->clk); + + if (test_bit(BIT_ACTIVE, &prd->flags)) + clk_put(prd->clk); +} + +static struct pm_runtime_data *__to_prd(struct device *dev) +{ + return devres_find(dev, __devres_release, NULL, NULL); +} + +static void platform_pm_runtime_init(struct device *dev, + struct pm_runtime_data *prd) +{ + if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) { + prd->clk = clk_get(dev, NULL); + if (!IS_ERR(prd->clk)) { + set_bit(BIT_ACTIVE, &prd->flags); + dev_info(dev, "clocks managed by runtime pm\n"); + } + } +} + +static void platform_pm_runtime_bug(struct device *dev, + struct pm_runtime_data *prd) +{ + if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) + dev_err(dev, "runtime pm suspend before resume\n"); +} + +int platform_pm_runtime_suspend(struct device *dev) +{ + struct pm_runtime_data *prd = __to_prd(dev); + + dev_dbg(dev, "platform_pm_runtime_suspend()\n"); + + platform_pm_runtime_bug(dev, prd); + + if (prd && test_bit(BIT_ACTIVE, &prd->flags)) { + clk_disable(prd->clk); + clear_bit(BIT_CLK_ENABLED, &prd->flags); + } + + return 0; +} + +int platform_pm_runtime_resume(struct device *dev) +{ + struct pm_runtime_data *prd = __to_prd(dev); + + dev_dbg(dev, "platform_pm_runtime_resume()\n"); + + platform_pm_runtime_init(dev, prd); + + if (prd && test_bit(BIT_ACTIVE, &prd->flags)) { + clk_enable(prd->clk); + set_bit(BIT_CLK_ENABLED, &prd->flags); + } + + return 0; +} + +int platform_pm_runtime_idle(struct device *dev) +{ + /* suspend synchronously to disable clocks immediately */ + return pm_runtime_suspend(dev); +} + +static int platform_bus_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + struct pm_runtime_data *prd; + + dev_dbg(dev, "platform_bus_notify() %ld !\n", action); + + if (action == BUS_NOTIFY_BIND_DRIVER) { + prd = devres_alloc(__devres_release, sizeof(*prd), GFP_KERNEL); + if (prd) + devres_add(dev, prd); + else + dev_err(dev, "unable to alloc memory for runtime pm\n"); + } + + return 0; +} + +#else /* CONFIG_PM_RUNTIME */ + +static int platform_bus_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + struct clk *clk; + + dev_dbg(dev, "platform_bus_notify() %ld !\n", action); + + switch (action) { + case BUS_NOTIFY_BIND_DRIVER: + clk = clk_get(dev, NULL); + if (!IS_ERR(clk)) { + clk_enable(clk); + clk_put(clk); + dev_info(dev, "runtime pm disabled, clock forced on\n"); + } + break; + case BUS_NOTIFY_UNBOUND_DRIVER: + clk = clk_get(dev, NULL); + if (!IS_ERR(clk)) { + clk_disable(clk); + clk_put(clk); + dev_info(dev, "runtime pm disabled, clock forced off\n"); + } + break; + } + + return 0; +} + +#endif /* CONFIG_PM_RUNTIME */ + +static struct notifier_block platform_bus_notifier = { + .notifier_call = platform_bus_notify +}; + +static int __init sh_pm_runtime_init(void) +{ + bus_register_notifier(&platform_bus_type, &platform_bus_notifier); + return 0; +} +core_initcall(sh_pm_runtime_init); diff --git a/arch/arm/mach-tegra/board-harmony.c b/arch/arm/mach-tegra/board-harmony.c index 05e78dd9b50c..9e305de56be9 100644 --- a/arch/arm/mach-tegra/board-harmony.c +++ b/arch/arm/mach-tegra/board-harmony.c @@ -91,10 +91,8 @@ static void __init tegra_harmony_fixup(struct machine_desc *desc, { mi->nr_banks = 2; mi->bank[0].start = PHYS_OFFSET; - mi->bank[0].node = PHYS_TO_NID(PHYS_OFFSET); mi->bank[0].size = 448 * SZ_1M; mi->bank[1].start = SZ_512M; - mi->bank[1].node = PHYS_TO_NID(SZ_512M); mi->bank[1].size = SZ_512M; } diff --git a/arch/arm/mach-tegra/include/mach/vmalloc.h b/arch/arm/mach-tegra/include/mach/vmalloc.h index 267a141730d9..fd6aa65b2dc6 100644 --- a/arch/arm/mach-tegra/include/mach/vmalloc.h +++ b/arch/arm/mach-tegra/include/mach/vmalloc.h @@ -23,6 +23,6 @@ #include <asm/sizes.h> -#define VMALLOC_END 0xFE000000 +#define VMALLOC_END 0xFE000000UL #endif diff --git a/arch/arm/mach-u300/include/mach/gpio.h b/arch/arm/mach-u300/include/mach/gpio.h index 7b1fc984abb6..d5a71abcbaea 100644 --- a/arch/arm/mach-u300/include/mach/gpio.h +++ b/arch/arm/mach-u300/include/mach/gpio.h @@ -273,6 +273,9 @@ extern void gpio_pullup(unsigned gpio, int value); extern int gpio_get_value(unsigned gpio); extern void gpio_set_value(unsigned gpio, int value); +#define gpio_get_value_cansleep gpio_get_value +#define gpio_set_value_cansleep gpio_set_value + /* wrappers to sleep-enable the previous two functions */ static inline unsigned gpio_to_irq(unsigned gpio) { diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c index 577df6cccb08..71fb17349520 100644 --- a/arch/arm/mach-vexpress/ct-ca9x4.c +++ b/arch/arm/mach-vexpress/ct-ca9x4.c @@ -68,7 +68,7 @@ static void __init ct_ca9x4_init_irq(void) } #if 0 -static void ct_ca9x4_timer_init(void) +static void __init ct_ca9x4_timer_init(void) { writel(0, MMIO_P2V(CT_CA9X4_TIMER0) + TIMER_CTRL); writel(0, MMIO_P2V(CT_CA9X4_TIMER1) + TIMER_CTRL); @@ -222,12 +222,18 @@ static struct platform_device pmu_device = { .resource = pmu_resources, }; -static void ct_ca9x4_init(void) +static void __init ct_ca9x4_init(void) { int i; #ifdef CONFIG_CACHE_L2X0 - l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00000000, 0xfe0fffff); + void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC); + + /* set RAM latencies to 1 cycle for this core tile. */ + writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL); + writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL); + + l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff); #endif clkdev_add_table(lookups, ARRAY_SIZE(lookups)); diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c index 817f0ad38a0b..7eaa232180a5 100644 --- a/arch/arm/mach-vexpress/v2m.c +++ b/arch/arm/mach-vexpress/v2m.c @@ -48,7 +48,7 @@ void __init v2m_map_io(struct map_desc *tile, size_t num) } -static void v2m_timer_init(void) +static void __init v2m_timer_init(void) { writel(0, MMIO_P2V(V2M_TIMER0) + TIMER_CTRL); writel(0, MMIO_P2V(V2M_TIMER1) + TIMER_CTRL); diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 33c3f570aaa0..a0a2928ae4dd 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -398,7 +398,7 @@ config CPU_V6 # ARMv6k config CPU_32v6K bool "Support ARM V6K processor extensions" if !SMP - depends on CPU_V6 + depends on CPU_V6 || CPU_V7 default y if SMP && !(ARCH_MX3 || ARCH_OMAP2) help Say Y here if your ARMv6 processor supports the 'K' extension. diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index d073b64ae87e..724ba3bce72c 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if (ai_usermode & UM_SIGNAL) force_sig(SIGBUS, current); - else - set_cr(cr_no_alignment); + else { + /* + * We're about to disable the alignment trap and return to + * user space. But if an interrupt occurs before actually + * reaching user space, then the IRQ vector entry code will + * notice that we were still in kernel space and therefore + * the alignment trap won't be re-enabled in that case as it + * is presumed to be always on from kernel space. + * Let's prevent that race by disabling interrupts here (they + * are disabled on the way back to user space anyway in + * entry-common.S) and disable the alignment trap only if + * there is no work pending for this thread. + */ + raw_local_irq_disable(); + if (!(current_thread_info()->flags & _TIF_WORK_MASK)) + set_cr(cr_no_alignment); + } return 0; } diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c704eed63c5d..4bc43e535d3b 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -229,6 +229,8 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot) } } while (size -= PAGE_SIZE); + dsb(); + return (void *)c->vm_start; } return NULL; diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index ab506272b2d3..17e7b0b57e49 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -204,8 +204,12 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn, /* * Don't allow RAM to be mapped - this causes problems with ARMv6+ */ - if (WARN_ON(pfn_valid(pfn))) - return NULL; + if (pfn_valid(pfn)) { + printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory. This leads\n" + KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n" + KERN_WARNING "will fail in the next kernel release. Please fix your driver.\n"); + WARN_ON(1); + } type = get_mem_type(mtype); if (!type) diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 6e1c4f6a2b3f..e8ed9dc461fe 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -15,6 +15,7 @@ #include <linux/nodemask.h> #include <linux/memblock.h> #include <linux/sort.h> +#include <linux/fs.h> #include <asm/cputype.h> #include <asm/sections.h> @@ -246,6 +247,9 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_USER, }, [MT_MEMORY] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_WRITE | L_PTE_EXEC, + .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, @@ -254,6 +258,9 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_KERNEL, }, [MT_MEMORY_NONCACHED] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_WRITE | L_PTE_EXEC | L_PTE_MT_BUFFERABLE, + .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, @@ -411,9 +418,12 @@ static void __init build_mem_type_table(void) * Enable CPU-specific coherency if supported. * (Only available on XSC3 at the moment.) */ - if (arch_is_coherent() && cpu_is_xsc3()) + if (arch_is_coherent() && cpu_is_xsc3()) { mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; - + mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; + } /* * ARMv6 and above have extended page tables. */ @@ -438,7 +448,9 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; #endif } @@ -475,6 +487,8 @@ static void __init build_mem_type_table(void) mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; switch (cp->pmd) { @@ -498,6 +512,19 @@ static void __init build_mem_type_table(void) } } +#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + if (!pfn_valid(pfn)) + return pgprot_noncached(vma_prot); + else if (file->f_flags & O_SYNC) + return pgprot_writecombine(vma_prot); + return vma_prot; +} +EXPORT_SYMBOL(phys_mem_access_prot); +#endif + #define vectors_base() (vectors_high() ? 0xffff0000 : 0) static void __init *early_alloc(unsigned long sz) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 6a8506d99ee9..197f21bed5e9 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -186,13 +186,14 @@ cpu_v7_name: * It is assumed that: * - cache type register is implemented */ -__v7_setup: +__v7_ca9mp_setup: #ifdef CONFIG_SMP mrc p15, 0, r0, c1, c0, 1 tst r0, #(1 << 6) @ SMP/nAMP mode enabled? orreq r0, r0, #(1 << 6) | (1 << 0) @ Enable SMP/nAMP mode and mcreq p15, 0, r0, c1, c0, 1 @ TLB ops broadcasting #endif +__v7_setup: adr r12, __v7_setup_stack @ the local stack stmia r12, {r0-r5, r7, r9, r11, lr} bl v7_flush_dcache_all @@ -201,11 +202,16 @@ __v7_setup: mrc p15, 0, r0, c0, c0, 0 @ read main ID register and r10, r0, #0xff000000 @ ARM? teq r10, #0x41000000 - bne 2f + bne 3f and r5, r0, #0x00f00000 @ variant and r6, r0, #0x0000000f @ revision - orr r0, r6, r5, lsr #20-4 @ combine variant and revision + orr r6, r6, r5, lsr #20-4 @ combine variant and revision + ubfx r0, r0, #4, #12 @ primary part number + /* Cortex-A8 Errata */ + ldr r10, =0x00000c08 @ Cortex-A8 primary part number + teq r0, r10 + bne 2f #ifdef CONFIG_ARM_ERRATA_430973 teq r5, #0x00100000 @ only present in r1p* mrceq p15, 0, r10, c1, c0, 1 @ read aux control register @@ -213,21 +219,50 @@ __v7_setup: mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_458693 - teq r0, #0x20 @ only present in r2p0 + teq r6, #0x20 @ only present in r2p0 mrceq p15, 0, r10, c1, c0, 1 @ read aux control register orreq r10, r10, #(1 << 5) @ set L1NEON to 1 orreq r10, r10, #(1 << 9) @ set PLDNOP to 1 mcreq p15, 0, r10, c1, c0, 1 @ write aux control register #endif #ifdef CONFIG_ARM_ERRATA_460075 - teq r0, #0x20 @ only present in r2p0 + teq r6, #0x20 @ only present in r2p0 mrceq p15, 1, r10, c9, c0, 2 @ read L2 cache aux ctrl register tsteq r10, #1 << 22 orreq r10, r10, #(1 << 22) @ set the Write Allocate disable bit mcreq p15, 1, r10, c9, c0, 2 @ write the L2 cache aux ctrl register #endif + b 3f -2: mov r10, #0 + /* Cortex-A9 Errata */ +2: ldr r10, =0x00000c09 @ Cortex-A9 primary part number + teq r0, r10 + bne 3f +#ifdef CONFIG_ARM_ERRATA_742230 + cmp r6, #0x22 @ only present up to r2p2 + mrcle p15, 0, r10, c15, c0, 1 @ read diagnostic register + orrle r10, r10, #1 << 4 @ set bit #4 + mcrle p15, 0, r10, c15, c0, 1 @ write diagnostic register +#endif +#ifdef CONFIG_ARM_ERRATA_742231 + teq r6, #0x20 @ present in r2p0 + teqne r6, #0x21 @ present in r2p1 + teqne r6, #0x22 @ present in r2p2 + mrceq p15, 0, r10, c15, c0, 1 @ read diagnostic register + orreq r10, r10, #1 << 12 @ set bit #12 + orreq r10, r10, #1 << 22 @ set bit #22 + mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register +#endif +#ifdef CONFIG_ARM_ERRATA_743622 + teq r6, #0x20 @ present in r2p0 + teqne r6, #0x21 @ present in r2p1 + teqne r6, #0x22 @ present in r2p2 + mrceq p15, 0, r10, c15, c0, 1 @ read diagnostic register + orreq r10, r10, #1 << 6 @ set bit #6 + mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register +#endif + +3: mov r10, #0 #ifdef HARVARD_CACHE mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate #endif @@ -323,6 +358,29 @@ cpu_elf_name: .section ".proc.info.init", #alloc, #execinstr + .type __v7_ca9mp_proc_info, #object +__v7_ca9mp_proc_info: + .long 0x410fc090 @ Required ID value + .long 0xff0ffff0 @ Mask for ID + .long PMD_TYPE_SECT | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ | \ + PMD_FLAGS + .long PMD_TYPE_SECT | \ + PMD_SECT_XN | \ + PMD_SECT_AP_WRITE | \ + PMD_SECT_AP_READ + b __v7_ca9mp_setup + .long cpu_arch_name + .long cpu_elf_name + .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS + .long cpu_v7_name + .long v7_processor_functions + .long v7wbi_tlb_fns + .long v6_user_fns + .long v7_cache_fns + .size __v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info + /* * Match any ARMv7 processor core. */ diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile index e666eafed152..b2215c61cdf0 100644 --- a/arch/arm/oprofile/Makefile +++ b/arch/arm/oprofile/Makefile @@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ oprofilefs.o oprofile_stats.o \ timer_int.o ) +ifeq ($(CONFIG_HW_PERF_EVENTS),y) +DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o) +endif + oprofile-y := $(DRIVER_OBJS) common.o diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index 0691176899ff..8aa974491dfc 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -25,138 +25,10 @@ #include <asm/ptrace.h> #ifdef CONFIG_HW_PERF_EVENTS -/* - * Per performance monitor configuration as set via oprofilefs. - */ -struct op_counter_config { - unsigned long count; - unsigned long enabled; - unsigned long event; - unsigned long unit_mask; - unsigned long kernel; - unsigned long user; - struct perf_event_attr attr; -}; - -static int op_arm_enabled; -static DEFINE_MUTEX(op_arm_mutex); - -static struct op_counter_config *counter_config; -static struct perf_event **perf_events[nr_cpumask_bits]; -static int perf_num_counters; - -/* - * Overflow callback for oprofile. - */ -static void op_overflow_handler(struct perf_event *event, int unused, - struct perf_sample_data *data, struct pt_regs *regs) -{ - int id; - u32 cpu = smp_processor_id(); - - for (id = 0; id < perf_num_counters; ++id) - if (perf_events[cpu][id] == event) - break; - - if (id != perf_num_counters) - oprofile_add_sample(regs, id); - else - pr_warning("oprofile: ignoring spurious overflow " - "on cpu %u\n", cpu); -} - -/* - * Called by op_arm_setup to create perf attributes to mirror the oprofile - * settings in counter_config. Attributes are created as `pinned' events and - * so are permanently scheduled on the PMU. - */ -static void op_perf_setup(void) -{ - int i; - u32 size = sizeof(struct perf_event_attr); - struct perf_event_attr *attr; - - for (i = 0; i < perf_num_counters; ++i) { - attr = &counter_config[i].attr; - memset(attr, 0, size); - attr->type = PERF_TYPE_RAW; - attr->size = size; - attr->config = counter_config[i].event; - attr->sample_period = counter_config[i].count; - attr->pinned = 1; - } -} - -static int op_create_counter(int cpu, int event) -{ - int ret = 0; - struct perf_event *pevent; - - if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL)) - return ret; - - pevent = perf_event_create_kernel_counter(&counter_config[event].attr, - cpu, -1, - op_overflow_handler); - - if (IS_ERR(pevent)) { - ret = PTR_ERR(pevent); - } else if (pevent->state != PERF_EVENT_STATE_ACTIVE) { - pr_warning("oprofile: failed to enable event %d " - "on CPU %d\n", event, cpu); - ret = -EBUSY; - } else { - perf_events[cpu][event] = pevent; - } - - return ret; -} - -static void op_destroy_counter(int cpu, int event) -{ - struct perf_event *pevent = perf_events[cpu][event]; - - if (pevent) { - perf_event_release_kernel(pevent); - perf_events[cpu][event] = NULL; - } -} - -/* - * Called by op_arm_start to create active perf events based on the - * perviously configured attributes. - */ -static int op_perf_start(void) -{ - int cpu, event, ret = 0; - - for_each_online_cpu(cpu) { - for (event = 0; event < perf_num_counters; ++event) { - ret = op_create_counter(cpu, event); - if (ret) - goto out; - } - } - -out: - return ret; -} - -/* - * Called by op_arm_stop at the end of a profiling run. - */ -static void op_perf_stop(void) +char *op_name_from_perf_id(void) { - int cpu, event; + enum arm_perf_pmu_ids id = armpmu_get_pmu_id(); - for_each_online_cpu(cpu) - for (event = 0; event < perf_num_counters; ++event) - op_destroy_counter(cpu, event); -} - - -static char *op_name_from_perf_id(enum arm_perf_pmu_ids id) -{ switch (id) { case ARM_PERF_PMU_ID_XSCALE1: return "arm/xscale1"; @@ -175,116 +47,6 @@ static char *op_name_from_perf_id(enum arm_perf_pmu_ids id) } } -static int op_arm_create_files(struct super_block *sb, struct dentry *root) -{ - unsigned int i; - - for (i = 0; i < perf_num_counters; i++) { - struct dentry *dir; - char buf[4]; - - snprintf(buf, sizeof buf, "%d", i); - dir = oprofilefs_mkdir(sb, root, buf); - oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); - oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event); - oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count); - oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask); - oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel); - oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user); - } - - return 0; -} - -static int op_arm_setup(void) -{ - spin_lock(&oprofilefs_lock); - op_perf_setup(); - spin_unlock(&oprofilefs_lock); - return 0; -} - -static int op_arm_start(void) -{ - int ret = -EBUSY; - - mutex_lock(&op_arm_mutex); - if (!op_arm_enabled) { - ret = 0; - op_perf_start(); - op_arm_enabled = 1; - } - mutex_unlock(&op_arm_mutex); - return ret; -} - -static void op_arm_stop(void) -{ - mutex_lock(&op_arm_mutex); - if (op_arm_enabled) - op_perf_stop(); - op_arm_enabled = 0; - mutex_unlock(&op_arm_mutex); -} - -#ifdef CONFIG_PM -static int op_arm_suspend(struct platform_device *dev, pm_message_t state) -{ - mutex_lock(&op_arm_mutex); - if (op_arm_enabled) - op_perf_stop(); - mutex_unlock(&op_arm_mutex); - return 0; -} - -static int op_arm_resume(struct platform_device *dev) -{ - mutex_lock(&op_arm_mutex); - if (op_arm_enabled && op_perf_start()) - op_arm_enabled = 0; - mutex_unlock(&op_arm_mutex); - return 0; -} - -static struct platform_driver oprofile_driver = { - .driver = { - .name = "arm-oprofile", - }, - .resume = op_arm_resume, - .suspend = op_arm_suspend, -}; - -static struct platform_device *oprofile_pdev; - -static int __init init_driverfs(void) -{ - int ret; - - ret = platform_driver_register(&oprofile_driver); - if (ret) - goto out; - - oprofile_pdev = platform_device_register_simple( - oprofile_driver.driver.name, 0, NULL, 0); - if (IS_ERR(oprofile_pdev)) { - ret = PTR_ERR(oprofile_pdev); - platform_driver_unregister(&oprofile_driver); - } - -out: - return ret; -} - -static void exit_driverfs(void) -{ - platform_device_unregister(oprofile_pdev); - platform_driver_unregister(&oprofile_driver); -} -#else -static int __init init_driverfs(void) { return 0; } -#define exit_driverfs() do { } while (0) -#endif /* CONFIG_PM */ - static int report_trace(struct stackframe *frame, void *d) { unsigned int *depth = d; @@ -349,72 +111,14 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth) int __init oprofile_arch_init(struct oprofile_operations *ops) { - int cpu, ret = 0; - - perf_num_counters = armpmu_get_max_events(); - - counter_config = kcalloc(perf_num_counters, - sizeof(struct op_counter_config), GFP_KERNEL); - - if (!counter_config) { - pr_info("oprofile: failed to allocate %d " - "counters\n", perf_num_counters); - return -ENOMEM; - } - - ret = init_driverfs(); - if (ret) { - kfree(counter_config); - return ret; - } - - for_each_possible_cpu(cpu) { - perf_events[cpu] = kcalloc(perf_num_counters, - sizeof(struct perf_event *), GFP_KERNEL); - if (!perf_events[cpu]) { - pr_info("oprofile: failed to allocate %d perf events " - "for cpu %d\n", perf_num_counters, cpu); - while (--cpu >= 0) - kfree(perf_events[cpu]); - return -ENOMEM; - } - } - ops->backtrace = arm_backtrace; - ops->create_files = op_arm_create_files; - ops->setup = op_arm_setup; - ops->start = op_arm_start; - ops->stop = op_arm_stop; - ops->shutdown = op_arm_stop; - ops->cpu_type = op_name_from_perf_id(armpmu_get_pmu_id()); - - if (!ops->cpu_type) - ret = -ENODEV; - else - pr_info("oprofile: using %s\n", ops->cpu_type); - return ret; + return oprofile_perf_init(ops); } -void oprofile_arch_exit(void) +void __exit oprofile_arch_exit(void) { - int cpu, id; - struct perf_event *event; - - if (*perf_events) { - exit_driverfs(); - for_each_possible_cpu(cpu) { - for (id = 0; id < perf_num_counters; ++id) { - event = perf_events[cpu][id]; - if (event != NULL) - perf_event_release_kernel(event); - } - kfree(perf_events[cpu]); - } - } - - if (counter_config) - kfree(counter_config); + oprofile_perf_exit(); } #else int __init oprofile_arch_init(struct oprofile_operations *ops) @@ -422,5 +126,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) pr_info("oprofile: hardware counters not available\n"); return -ENODEV; } -void oprofile_arch_exit(void) {} +void __exit oprofile_arch_exit(void) {} #endif /* CONFIG_HW_PERF_EVENTS */ diff --git a/arch/arm/plat-mxc/Kconfig b/arch/arm/plat-mxc/Kconfig index 0527e65318f4..6785db4179b8 100644 --- a/arch/arm/plat-mxc/Kconfig +++ b/arch/arm/plat-mxc/Kconfig @@ -43,6 +43,7 @@ config ARCH_MXC91231 config ARCH_MX5 bool "MX5-based" select CPU_V7 + select ARM_L1_CACHE_SHIFT_6 help This enables support for systems based on the Freescale i.MX51 family diff --git a/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h b/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h index 634e3f4c454d..656acb45d434 100644 --- a/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h +++ b/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h @@ -37,9 +37,9 @@ * mach-mx5/eukrea_mbimx51-baseboard.c for cpuimx51 */ -extern void eukrea_mbimx25_baseboard_init(void); +extern void eukrea_mbimxsd25_baseboard_init(void); extern void eukrea_mbimx27_baseboard_init(void); -extern void eukrea_mbimx35_baseboard_init(void); +extern void eukrea_mbimxsd35_baseboard_init(void); extern void eukrea_mbimx51_baseboard_init(void); #endif diff --git a/arch/arm/plat-mxc/tzic.c b/arch/arm/plat-mxc/tzic.c index b3da9aad4295..3703ab28257f 100644 --- a/arch/arm/plat-mxc/tzic.c +++ b/arch/arm/plat-mxc/tzic.c @@ -164,8 +164,9 @@ int tzic_enable_wake(int is_idle) return -EAGAIN; for (i = 0; i < 4; i++) { - v = is_idle ? __raw_readl(TZIC_ENSET0(i)) : wakeup_intr[i]; - __raw_writel(v, TZIC_WAKEUP0(i)); + v = is_idle ? __raw_readl(tzic_base + TZIC_ENSET0(i)) : + wakeup_intr[i]; + __raw_writel(v, tzic_base + TZIC_WAKEUP0(i)); } return 0; diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c index ea3ca86c5283..aedf9c1d645e 100644 --- a/arch/arm/plat-nomadik/timer.c +++ b/arch/arm/plat-nomadik/timer.c @@ -1,5 +1,5 @@ /* - * linux/arch/arm/mach-nomadik/timer.c + * linux/arch/arm/plat-nomadik/timer.c * * Copyright (C) 2008 STMicroelectronics * Copyright (C) 2010 Alessandro Rubini @@ -75,7 +75,7 @@ static void nmdk_clkevt_mode(enum clock_event_mode mode, cr = readl(mtu_base + MTU_CR(1)); writel(0, mtu_base + MTU_LR(1)); writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(1)); - writel(0x2, mtu_base + MTU_IMSC); + writel(1 << 1, mtu_base + MTU_IMSC); break; case CLOCK_EVT_MODE_SHUTDOWN: case CLOCK_EVT_MODE_UNUSED: @@ -131,25 +131,23 @@ void __init nmdk_timer_init(void) { unsigned long rate; struct clk *clk0; - struct clk *clk1; - u32 cr; + u32 cr = MTU_CRn_32BITS; clk0 = clk_get_sys("mtu0", NULL); BUG_ON(IS_ERR(clk0)); - clk1 = clk_get_sys("mtu1", NULL); - BUG_ON(IS_ERR(clk1)); - clk_enable(clk0); - clk_enable(clk1); /* - * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500: - * use a divide-by-16 counter if it's more than 16MHz + * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz + * for ux500. + * Use a divide-by-16 counter if the tick rate is more than 32MHz. + * At 32 MHz, the timer (with 32 bit counter) can be programmed + * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer + * with 16 gives too low timer resolution. */ - cr = MTU_CRn_32BITS;; rate = clk_get_rate(clk0); - if (rate > 16 << 20) { + if (rate > 32000000) { rate /= 16; cr |= MTU_CRn_PRESCALE_16; } else { @@ -170,15 +168,8 @@ void __init nmdk_timer_init(void) pr_err("timer: failed to initialize clock source %s\n", nmdk_clksrc.name); - /* Timer 1 is used for events, fix according to rate */ - cr = MTU_CRn_32BITS; - rate = clk_get_rate(clk1); - if (rate > 16 << 20) { - rate /= 16; - cr |= MTU_CRn_PRESCALE_16; - } else { - cr |= MTU_CRn_PRESCALE_1; - } + /* Timer 1 is used for events */ + clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE); writel(cr | MTU_CRn_ONESHOT, mtu_base + MTU_CR(1)); /* off, currently */ diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig index e39a417a368d..a92cb499313f 100644 --- a/arch/arm/plat-omap/Kconfig +++ b/arch/arm/plat-omap/Kconfig @@ -33,7 +33,7 @@ config OMAP_DEBUG_DEVICES config OMAP_DEBUG_LEDS bool depends on OMAP_DEBUG_DEVICES - default y if LEDS + default y if LEDS_CLASS config OMAP_RESET_CLOCKS bool "Reset unused clocks during boot" diff --git a/arch/arm/plat-omap/include/plat/smp.h b/arch/arm/plat-omap/include/plat/smp.h index 6a3ff65c0303..5177a9c5a25a 100644 --- a/arch/arm/plat-omap/include/plat/smp.h +++ b/arch/arm/plat-omap/include/plat/smp.h @@ -19,13 +19,6 @@ #include <asm/hardware/gic.h> -/* - * set_event() is used to wake up secondary core from wfe using sev. ROM - * code puts the second core into wfe(standby). - * - */ -#define set_event() __asm__ __volatile__ ("sev" : : : "memory") - /* Needed for secondary core boot */ extern void omap_secondary_startup(void); extern u32 omap_modify_auxcoreboot0(u32 set_mask, u32 clear_mask); diff --git a/arch/arm/plat-omap/iommu.c b/arch/arm/plat-omap/iommu.c index a202a2ce6e3d..6cd151b31bc5 100644 --- a/arch/arm/plat-omap/iommu.c +++ b/arch/arm/plat-omap/iommu.c @@ -320,6 +320,7 @@ void flush_iotlb_page(struct iommu *obj, u32 da) if ((start <= da) && (da < start + bytes)) { dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n", __func__, start, da, bytes); + iotlb_load_cr(obj, &cr); iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY); } } diff --git a/arch/arm/plat-omap/mcbsp.c b/arch/arm/plat-omap/mcbsp.c index e31496e35b0f..0c8612fd8312 100644 --- a/arch/arm/plat-omap/mcbsp.c +++ b/arch/arm/plat-omap/mcbsp.c @@ -156,7 +156,7 @@ static irqreturn_t omap_mcbsp_rx_irq_handler(int irq, void *dev_id) /* Writing zero to RSYNC_ERR clears the IRQ */ MCBSP_WRITE(mcbsp_rx, SPCR1, MCBSP_READ_CACHE(mcbsp_rx, SPCR1)); } else { - complete(&mcbsp_rx->tx_irq_completion); + complete(&mcbsp_rx->rx_irq_completion); } return IRQ_HANDLED; diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c index 226b2e858d6c..10b3b4c63372 100644 --- a/arch/arm/plat-omap/sram.c +++ b/arch/arm/plat-omap/sram.c @@ -220,20 +220,7 @@ void __init omap_map_sram(void) if (omap_sram_size == 0) return; - if (cpu_is_omap24xx()) { - omap_sram_io_desc[0].virtual = OMAP2_SRAM_VA; - - base = OMAP2_SRAM_PA; - base = ROUND_DOWN(base, PAGE_SIZE); - omap_sram_io_desc[0].pfn = __phys_to_pfn(base); - } - if (cpu_is_omap34xx()) { - omap_sram_io_desc[0].virtual = OMAP3_SRAM_VA; - base = OMAP3_SRAM_PA; - base = ROUND_DOWN(base, PAGE_SIZE); - omap_sram_io_desc[0].pfn = __phys_to_pfn(base); - /* * SRAM must be marked as non-cached on OMAP3 since the * CORE DPLL M2 divider change code (in SRAM) runs with the @@ -244,13 +231,11 @@ void __init omap_map_sram(void) omap_sram_io_desc[0].type = MT_MEMORY_NONCACHED; } - if (cpu_is_omap44xx()) { - omap_sram_io_desc[0].virtual = OMAP4_SRAM_VA; - base = OMAP4_SRAM_PA; - base = ROUND_DOWN(base, PAGE_SIZE); - omap_sram_io_desc[0].pfn = __phys_to_pfn(base); - } - omap_sram_io_desc[0].length = 1024 * 1024; /* Use section desc */ + omap_sram_io_desc[0].virtual = omap_sram_base; + base = omap_sram_start; + base = ROUND_DOWN(base, PAGE_SIZE); + omap_sram_io_desc[0].pfn = __phys_to_pfn(base); + omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE); iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc)); printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n", diff --git a/arch/arm/plat-pxa/pwm.c b/arch/arm/plat-pxa/pwm.c index 0732c6c8d511..ef32686feef9 100644 --- a/arch/arm/plat-pxa/pwm.c +++ b/arch/arm/plat-pxa/pwm.c @@ -176,7 +176,7 @@ static inline void __add_pwm(struct pwm_device *pwm) static int __devinit pwm_probe(struct platform_device *pdev) { - struct platform_device_id *id = platform_get_device_id(pdev); + const struct platform_device_id *id = platform_get_device_id(pdev); struct pwm_device *pwm, *secondary = NULL; struct resource *r; int ret = 0; diff --git a/arch/arm/plat-s5p/dev-fimc0.c b/arch/arm/plat-s5p/dev-fimc0.c index d3f1a9b5d2b5..608770fc1531 100644 --- a/arch/arm/plat-s5p/dev-fimc0.c +++ b/arch/arm/plat-s5p/dev-fimc0.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> +#include <linux/dma-mapping.h> #include <linux/platform_device.h> #include <linux/interrupt.h> #include <linux/ioport.h> @@ -18,7 +19,7 @@ static struct resource s5p_fimc0_resource[] = { [0] = { .start = S5P_PA_FIMC0, - .end = S5P_PA_FIMC0 + SZ_1M - 1, + .end = S5P_PA_FIMC0 + SZ_4K - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -28,9 +29,15 @@ static struct resource s5p_fimc0_resource[] = { }, }; +static u64 s5p_fimc0_dma_mask = DMA_BIT_MASK(32); + struct platform_device s5p_device_fimc0 = { .name = "s5p-fimc", .id = 0, .num_resources = ARRAY_SIZE(s5p_fimc0_resource), .resource = s5p_fimc0_resource, + .dev = { + .dma_mask = &s5p_fimc0_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + }, }; diff --git a/arch/arm/plat-s5p/dev-fimc1.c b/arch/arm/plat-s5p/dev-fimc1.c index 41bd6986d0ad..76e3a97a87d3 100644 --- a/arch/arm/plat-s5p/dev-fimc1.c +++ b/arch/arm/plat-s5p/dev-fimc1.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> +#include <linux/dma-mapping.h> #include <linux/platform_device.h> #include <linux/interrupt.h> #include <linux/ioport.h> @@ -18,7 +19,7 @@ static struct resource s5p_fimc1_resource[] = { [0] = { .start = S5P_PA_FIMC1, - .end = S5P_PA_FIMC1 + SZ_1M - 1, + .end = S5P_PA_FIMC1 + SZ_4K - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -28,9 +29,15 @@ static struct resource s5p_fimc1_resource[] = { }, }; +static u64 s5p_fimc1_dma_mask = DMA_BIT_MASK(32); + struct platform_device s5p_device_fimc1 = { .name = "s5p-fimc", .id = 1, .num_resources = ARRAY_SIZE(s5p_fimc1_resource), .resource = s5p_fimc1_resource, + .dev = { + .dma_mask = &s5p_fimc1_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + }, }; diff --git a/arch/arm/plat-s5p/dev-fimc2.c b/arch/arm/plat-s5p/dev-fimc2.c index dfddeda6d4a3..24d29816fa2c 100644 --- a/arch/arm/plat-s5p/dev-fimc2.c +++ b/arch/arm/plat-s5p/dev-fimc2.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> +#include <linux/dma-mapping.h> #include <linux/platform_device.h> #include <linux/interrupt.h> #include <linux/ioport.h> @@ -18,7 +19,7 @@ static struct resource s5p_fimc2_resource[] = { [0] = { .start = S5P_PA_FIMC2, - .end = S5P_PA_FIMC2 + SZ_1M - 1, + .end = S5P_PA_FIMC2 + SZ_4K - 1, .flags = IORESOURCE_MEM, }, [1] = { @@ -28,9 +29,15 @@ static struct resource s5p_fimc2_resource[] = { }, }; +static u64 s5p_fimc2_dma_mask = DMA_BIT_MASK(32); + struct platform_device s5p_device_fimc2 = { .name = "s5p-fimc", .id = 2, .num_resources = ARRAY_SIZE(s5p_fimc2_resource), .resource = s5p_fimc2_resource, + .dev = { + .dma_mask = &s5p_fimc2_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + }, }; diff --git a/arch/arm/plat-s5p/include/plat/map-s5p.h b/arch/arm/plat-s5p/include/plat/map-s5p.h index 54e9fb9d315e..c4ff88bf6477 100644 --- a/arch/arm/plat-s5p/include/plat/map-s5p.h +++ b/arch/arm/plat-s5p/include/plat/map-s5p.h @@ -17,6 +17,7 @@ #define S5P_VA_GPIO S3C_ADDR(0x00500000) #define S5P_VA_SYSTIMER S3C_ADDR(0x01200000) #define S5P_VA_SROMC S3C_ADDR(0x01100000) +#define S5P_VA_SYSRAM S3C_ADDR(0x01180000) #define S5P_VA_COMBINER_BASE S3C_ADDR(0x00600000) #define S5P_VA_COMBINER(x) (S5P_VA_COMBINER_BASE + ((x) >> 2) * 0x10) @@ -29,6 +30,7 @@ #define S5P_VA_GIC_DIST S5P_VA_COREPERI(0x1000) #define S5P_VA_L2CC S3C_ADDR(0x00900000) +#define S5P_VA_CMU S3C_ADDR(0x00920000) #define S5P_VA_UART(x) (S3C_VA_UART + ((x) * S3C_UART_OFFSET)) #define S5P_VA_UART0 S5P_VA_UART(0) diff --git a/arch/arm/plat-samsung/adc.c b/arch/arm/plat-samsung/adc.c index 04d9521ddc9f..e8f2be2d67f2 100644 --- a/arch/arm/plat-samsung/adc.c +++ b/arch/arm/plat-samsung/adc.c @@ -435,7 +435,6 @@ static int s3c_adc_suspend(struct platform_device *pdev, pm_message_t state) static int s3c_adc_resume(struct platform_device *pdev) { struct adc_device *adc = platform_get_drvdata(pdev); - unsigned long flags; clk_enable(adc->clk); enable_irq(adc->irq); diff --git a/arch/arm/plat-samsung/clock.c b/arch/arm/plat-samsung/clock.c index 90a20512d68d..e8d20b0bc50e 100644 --- a/arch/arm/plat-samsung/clock.c +++ b/arch/arm/plat-samsung/clock.c @@ -48,6 +48,9 @@ #include <plat/clock.h> #include <plat/cpu.h> +#include <linux/serial_core.h> +#include <plat/regs-serial.h> /* for s3c24xx_uart_devs */ + /* clock information */ static LIST_HEAD(clocks); @@ -65,6 +68,28 @@ static int clk_null_enable(struct clk *clk, int enable) return 0; } +static int dev_is_s3c_uart(struct device *dev) +{ + struct platform_device **pdev = s3c24xx_uart_devs; + int i; + for (i = 0; i < ARRAY_SIZE(s3c24xx_uart_devs); i++, pdev++) + if (*pdev && dev == &(*pdev)->dev) + return 1; + return 0; +} + +/* + * Serial drivers call get_clock() very early, before platform bus + * has been set up, this requires a special check to let them get + * a proper clock + */ + +static int dev_is_platform_device(struct device *dev) +{ + return dev->bus == &platform_bus_type || + (dev->bus == NULL && dev_is_s3c_uart(dev)); +} + /* Clock API calls */ struct clk *clk_get(struct device *dev, const char *id) @@ -73,7 +98,7 @@ struct clk *clk_get(struct device *dev, const char *id) struct clk *clk = ERR_PTR(-ENOENT); int idno; - if (dev == NULL || dev->bus != &platform_bus_type) + if (dev == NULL || !dev_is_platform_device(dev)) idno = -1; else idno = to_platform_device(dev)->id; diff --git a/arch/arm/plat-samsung/gpio-config.c b/arch/arm/plat-samsung/gpio-config.c index 57b68a50f45e..e3d41eaed1ff 100644 --- a/arch/arm/plat-samsung/gpio-config.c +++ b/arch/arm/plat-samsung/gpio-config.c @@ -273,13 +273,13 @@ s5p_gpio_drvstr_t s5p_gpio_get_drvstr(unsigned int pin) if (!chip) return -EINVAL; - off = chip->chip.base - pin; + off = pin - chip->chip.base; shift = off * 2; reg = chip->base + 0x0C; drvstr = __raw_readl(reg); - drvstr = 0xffff & (0x3 << shift); drvstr = drvstr >> shift; + drvstr &= 0x3; return (__force s5p_gpio_drvstr_t)drvstr; } @@ -296,11 +296,12 @@ int s5p_gpio_set_drvstr(unsigned int pin, s5p_gpio_drvstr_t drvstr) if (!chip) return -EINVAL; - off = chip->chip.base - pin; + off = pin - chip->chip.base; shift = off * 2; reg = chip->base + 0x0C; tmp = __raw_readl(reg); + tmp &= ~(0x3 << shift); tmp |= drvstr << shift; __raw_writel(tmp, reg); diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h index db4112c6f2be..1c6b92947c5d 100644 --- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h +++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h @@ -143,12 +143,12 @@ extern s3c_gpio_pull_t s3c_gpio_getpull(unsigned int pin); /* Define values for the drvstr available for each gpio pin. * * These values control the value of the output signal driver strength, - * configurable on most pins on the S5C series. + * configurable on most pins on the S5P series. */ -#define S5P_GPIO_DRVSTR_LV1 ((__force s5p_gpio_drvstr_t)0x00) -#define S5P_GPIO_DRVSTR_LV2 ((__force s5p_gpio_drvstr_t)0x01) -#define S5P_GPIO_DRVSTR_LV3 ((__force s5p_gpio_drvstr_t)0x10) -#define S5P_GPIO_DRVSTR_LV4 ((__force s5p_gpio_drvstr_t)0x11) +#define S5P_GPIO_DRVSTR_LV1 ((__force s5p_gpio_drvstr_t)0x0) +#define S5P_GPIO_DRVSTR_LV2 ((__force s5p_gpio_drvstr_t)0x2) +#define S5P_GPIO_DRVSTR_LV3 ((__force s5p_gpio_drvstr_t)0x1) +#define S5P_GPIO_DRVSTR_LV4 ((__force s5p_gpio_drvstr_t)0x3) /** * s5c_gpio_get_drvstr() - get the driver streght value of a gpio pin diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types index 48cbdcb6bbd4..55590a4d87c9 100644 --- a/arch/arm/tools/mach-types +++ b/arch/arm/tools/mach-types @@ -12,7 +12,7 @@ # # http://www.arm.linux.org.uk/developer/machines/?action=new # -# Last update: Mon Jul 12 21:10:14 2010 +# Last update: Thu Sep 9 22:43:01 2010 # # machine_is_xxx CONFIG_xxxx MACH_TYPE_xxx number # @@ -2622,7 +2622,7 @@ kraken MACH_KRAKEN KRAKEN 2634 gw2388 MACH_GW2388 GW2388 2635 jadecpu MACH_JADECPU JADECPU 2636 carlisle MACH_CARLISLE CARLISLE 2637 -lux_sf9 MACH_LUX_SFT9 LUX_SFT9 2638 +lux_sf9 MACH_LUX_SF9 LUX_SF9 2638 nemid_tb MACH_NEMID_TB NEMID_TB 2639 terrier MACH_TERRIER TERRIER 2640 turbot MACH_TURBOT TURBOT 2641 @@ -2950,3 +2950,97 @@ davinci_dm365_dvr MACH_DAVINCI_DM365_DVR DAVINCI_DM365_DVR 2963 netviz MACH_NETVIZ NETVIZ 2964 flexibity MACH_FLEXIBITY FLEXIBITY 2965 wlan_computer MACH_WLAN_COMPUTER WLAN_COMPUTER 2966 +lpc24xx MACH_LPC24XX LPC24XX 2967 +spica MACH_SPICA SPICA 2968 +gpsdisplay MACH_GPSDISPLAY GPSDISPLAY 2969 +bipnet MACH_BIPNET BIPNET 2970 +overo_ctu_inertial MACH_OVERO_CTU_INERTIAL OVERO_CTU_INERTIAL 2971 +davinci_dm355_mmm MACH_DAVINCI_DM355_MMM DAVINCI_DM355_MMM 2972 +pc9260_v2 MACH_PC9260_V2 PC9260_V2 2973 +ptx7545 MACH_PTX7545 PTX7545 2974 +tm_efdc MACH_TM_EFDC TM_EFDC 2975 +omap3_waldo1 MACH_OMAP3_WALDO1 OMAP3_WALDO1 2977 +flyer MACH_FLYER FLYER 2978 +tornado3240 MACH_TORNADO3240 TORNADO3240 2979 +soli_01 MACH_SOLI_01 SOLI_01 2980 +omapl138_europalc MACH_OMAPL138_EUROPALC OMAPL138_EUROPALC 2981 +helios_v1 MACH_HELIOS_V1 HELIOS_V1 2982 +netspace_lite_v2 MACH_NETSPACE_LITE_V2 NETSPACE_LITE_V2 2983 +ssc MACH_SSC SSC 2984 +premierwave_en MACH_PREMIERWAVE_EN PREMIERWAVE_EN 2985 +wasabi MACH_WASABI WASABI 2986 +vivow MACH_VIVOW VIVOW 2987 +mx50_rdp MACH_MX50_RDP MX50_RDP 2988 +universal MACH_UNIVERSAL UNIVERSAL 2989 +real6410 MACH_REAL6410 REAL6410 2990 +spx_sakura MACH_SPX_SAKURA SPX_SAKURA 2991 +ij3k_2440 MACH_IJ3K_2440 IJ3K_2440 2992 +omap3_bc10 MACH_OMAP3_BC10 OMAP3_BC10 2993 +thebe MACH_THEBE THEBE 2994 +rv082 MACH_RV082 RV082 2995 +armlguest MACH_ARMLGUEST ARMLGUEST 2996 +tjinc1000 MACH_TJINC1000 TJINC1000 2997 +dockstar MACH_DOCKSTAR DOCKSTAR 2998 +ax8008 MACH_AX8008 AX8008 2999 +gnet_sgce MACH_GNET_SGCE GNET_SGCE 3000 +pxwnas_500_1000 MACH_PXWNAS_500_1000 PXWNAS_500_1000 3001 +ea20 MACH_EA20 EA20 3002 +awm2 MACH_AWM2 AWM2 3003 +ti8148evm MACH_TI8148EVM TI8148EVM 3004 +tegra_seaboard MACH_TEGRA_SEABOARD TEGRA_SEABOARD 3005 +linkstation_chlv2 MACH_LINKSTATION_CHLV2 LINKSTATION_CHLV2 3006 +tera_pro2_rack MACH_TERA_PRO2_RACK TERA_PRO2_RACK 3007 +rubys MACH_RUBYS RUBYS 3008 +aquarius MACH_AQUARIUS AQUARIUS 3009 +mx53_ard MACH_MX53_ARD MX53_ARD 3010 +mx53_smd MACH_MX53_SMD MX53_SMD 3011 +lswxl MACH_LSWXL LSWXL 3012 +dove_avng_v3 MACH_DOVE_AVNG_V3 DOVE_AVNG_V3 3013 +sdi_ess_9263 MACH_SDI_ESS_9263 SDI_ESS_9263 3014 +jocpu550 MACH_JOCPU550 JOCPU550 3015 +msm8x60_rumi3 MACH_MSM8X60_RUMI3 MSM8X60_RUMI3 3016 +msm8x60_ffa MACH_MSM8X60_FFA MSM8X60_FFA 3017 +yanomami MACH_YANOMAMI YANOMAMI 3018 +gta04 MACH_GTA04 GTA04 3019 +cm_a510 MACH_CM_A510 CM_A510 3020 +omap3_rfs200 MACH_OMAP3_RFS200 OMAP3_RFS200 3021 +kx33xx MACH_KX33XX KX33XX 3022 +ptx7510 MACH_PTX7510 PTX7510 3023 +top9000 MACH_TOP9000 TOP9000 3024 +teenote MACH_TEENOTE TEENOTE 3025 +ts3 MACH_TS3 TS3 3026 +a0 MACH_A0 A0 3027 +fsm9xxx_surf MACH_FSM9XXX_SURF FSM9XXX_SURF 3028 +fsm9xxx_ffa MACH_FSM9XXX_FFA FSM9XXX_FFA 3029 +frrhwcdma60w MACH_FRRHWCDMA60W FRRHWCDMA60W 3030 +remus MACH_REMUS REMUS 3031 +at91cap7xdk MACH_AT91CAP7XDK AT91CAP7XDK 3032 +at91cap7stk MACH_AT91CAP7STK AT91CAP7STK 3033 +kt_sbc_sam9_1 MACH_KT_SBC_SAM9_1 KT_SBC_SAM9_1 3034 +oratisrouter MACH_ORATISROUTER ORATISROUTER 3035 +armada_xp_db MACH_ARMADA_XP_DB ARMADA_XP_DB 3036 +spdm MACH_SPDM SPDM 3037 +gtib MACH_GTIB GTIB 3038 +dgm3240 MACH_DGM3240 DGM3240 3039 +atlas_i_lpe MACH_ATLAS_I_LPE ATLAS_I_LPE 3040 +htcmega MACH_HTCMEGA HTCMEGA 3041 +tricorder MACH_TRICORDER TRICORDER 3042 +tx28 MACH_TX28 TX28 3043 +bstbrd MACH_BSTBRD BSTBRD 3044 +pwb3090 MACH_PWB3090 PWB3090 3045 +idea6410 MACH_IDEA6410 IDEA6410 3046 +qbc9263 MACH_QBC9263 QBC9263 3047 +borabora MACH_BORABORA BORABORA 3048 +valdez MACH_VALDEZ VALDEZ 3049 +ls9g20 MACH_LS9G20 LS9G20 3050 +mios_v1 MACH_MIOS_V1 MIOS_V1 3051 +s5pc110_crespo MACH_S5PC110_CRESPO S5PC110_CRESPO 3052 +controltek9g20 MACH_CONTROLTEK9G20 CONTROLTEK9G20 3053 +tin307 MACH_TIN307 TIN307 3054 +tin510 MACH_TIN510 TIN510 3055 +bluecheese MACH_BLUECHEESE BLUECHEESE 3057 +tem3x30 MACH_TEM3X30 TEM3X30 3058 +harvest_desoto MACH_HARVEST_DESOTO HARVEST_DESOTO 3059 +msm8x60_qrdc MACH_MSM8X60_QRDC MSM8X60_QRDC 3060 +spear900 MACH_SPEAR900 SPEAR900 3061 +pcontrol_g20 MACH_PCONTROL_G20 PCONTROL_G20 3062 diff --git a/arch/avr32/kernel/module.c b/arch/avr32/kernel/module.c index 98f94d041d9c..a727f54d64d6 100644 --- a/arch/avr32/kernel/module.c +++ b/arch/avr32/kernel/module.c @@ -314,10 +314,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, vfree(module->arch.syminfo); module->arch.syminfo = NULL; - return module_bug_finalize(hdr, sechdrs, module); + return 0; } void module_arch_cleanup(struct module *module) { - module_bug_cleanup(module); } diff --git a/arch/blackfin/include/asm/bfin_sport.h b/arch/blackfin/include/asm/bfin_sport.h index 9626cf7e4251..d27600c262c2 100644 --- a/arch/blackfin/include/asm/bfin_sport.h +++ b/arch/blackfin/include/asm/bfin_sport.h @@ -115,12 +115,6 @@ struct sport_register { #endif -/* Workaround defBF*.h SPORT MMRs till they get cleansed */ -#undef DTYPE_NORM -#undef SLEN -#undef SP_WOFF -#undef SP_WSIZE - /* SPORT_TCR1 Masks */ #define TSPEN 0x0001 /* TX enable */ #define ITCLK 0x0002 /* Internal TX Clock Select */ diff --git a/arch/blackfin/include/asm/bitops.h b/arch/blackfin/include/asm/bitops.h index d5872cd967ab..3f7ef4d97791 100644 --- a/arch/blackfin/include/asm/bitops.h +++ b/arch/blackfin/include/asm/bitops.h @@ -22,7 +22,9 @@ #include <asm-generic/bitops/sched.h> #include <asm-generic/bitops/ffs.h> +#include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/lock.h> + #include <asm-generic/bitops/ext2-non-atomic.h> #include <asm-generic/bitops/ext2-atomic.h> #include <asm-generic/bitops/minix.h> @@ -115,7 +117,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) * of bits set) of a N-bit word */ -static inline unsigned int hweight32(unsigned int w) +static inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; @@ -125,19 +127,20 @@ static inline unsigned int hweight32(unsigned int w) return res; } -static inline unsigned int hweight64(__u64 w) +static inline unsigned int __arch_hweight64(__u64 w) { - return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w); + return __arch_hweight32((unsigned int)(w >> 32)) + + __arch_hweight32((unsigned int)w); } -static inline unsigned int hweight16(unsigned int w) +static inline unsigned int __arch_hweight16(unsigned int w) { - return hweight32(w & 0xffff); + return __arch_hweight32(w & 0xffff); } -static inline unsigned int hweight8(unsigned int w) +static inline unsigned int __arch_hweight8(unsigned int w) { - return hweight32(w & 0xff); + return __arch_hweight32(w & 0xff); } #endif /* _BLACKFIN_BITOPS_H */ diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h index 22886cbdae7a..14fcd254b185 100644 --- a/arch/blackfin/include/asm/unistd.h +++ b/arch/blackfin/include/asm/unistd.h @@ -389,8 +389,11 @@ #define __NR_rt_tgsigqueueinfo 368 #define __NR_perf_event_open 369 #define __NR_recvmmsg 370 +#define __NR_fanotify_init 371 +#define __NR_fanotify_mark 372 +#define __NR_prlimit64 373 -#define __NR_syscall 371 +#define __NR_syscall 374 #define NR_syscalls __NR_syscall /* Old optional stuff no one actually uses */ diff --git a/arch/blackfin/mach-bf518/include/mach/defBF51x_base.h b/arch/blackfin/mach-bf518/include/mach/defBF51x_base.h index 2bc8f4f98011..037a51fd8e93 100644 --- a/arch/blackfin/mach-bf518/include/mach/defBF51x_base.h +++ b/arch/blackfin/mach-bf518/include/mach/defBF51x_base.h @@ -913,88 +913,6 @@ #define PH6 0x0040 #define PH7 0x0080 - -/* ******************* SERIAL PORT MASKS **************************************/ -/* SPORTx_TCR1 Masks */ -#define TSPEN 0x0001 /* Transmit Enable */ -#define ITCLK 0x0002 /* Internal Transmit Clock Select */ -#define DTYPE_NORM 0x0004 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define TLSBIT 0x0010 /* Transmit Bit Order */ -#define ITFS 0x0200 /* Internal Transmit Frame Sync Select */ -#define TFSR 0x0400 /* Transmit Frame Sync Required Select */ -#define DITFS 0x0800 /* Data-Independent Transmit Frame Sync Select */ -#define LTFS 0x1000 /* Low Transmit Frame Sync Select */ -#define LATFS 0x2000 /* Late Transmit Frame Sync Select */ -#define TCKFE 0x4000 /* Clock Falling Edge Select */ - -/* SPORTx_TCR2 Masks and Macro */ -#define SLEN(x) ((x)&0x1F) /* SPORT TX Word Length (2 - 31) */ -#define TXSE 0x0100 /* TX Secondary Enable */ -#define TSFSE 0x0200 /* Transmit Stereo Frame Sync Enable */ -#define TRFST 0x0400 /* Left/Right Order (1 = Right Channel 1st) */ - -/* SPORTx_RCR1 Masks */ -#define RSPEN 0x0001 /* Receive Enable */ -#define IRCLK 0x0002 /* Internal Receive Clock Select */ -#define DTYPE_NORM 0x0004 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define RLSBIT 0x0010 /* Receive Bit Order */ -#define IRFS 0x0200 /* Internal Receive Frame Sync Select */ -#define RFSR 0x0400 /* Receive Frame Sync Required Select */ -#define LRFS 0x1000 /* Low Receive Frame Sync Select */ -#define LARFS 0x2000 /* Late Receive Frame Sync Select */ -#define RCKFE 0x4000 /* Clock Falling Edge Select */ - -/* SPORTx_RCR2 Masks */ -#define SLEN(x) ((x)&0x1F) /* SPORT RX Word Length (2 - 31) */ -#define RXSE 0x0100 /* RX Secondary Enable */ -#define RSFSE 0x0200 /* RX Stereo Frame Sync Enable */ -#define RRFST 0x0400 /* Right-First Data Order */ - -/* SPORTx_STAT Masks */ -#define RXNE 0x0001 /* Receive FIFO Not Empty Status */ -#define RUVF 0x0002 /* Sticky Receive Underflow Status */ -#define ROVF 0x0004 /* Sticky Receive Overflow Status */ -#define TXF 0x0008 /* Transmit FIFO Full Status */ -#define TUVF 0x0010 /* Sticky Transmit Underflow Status */ -#define TOVF 0x0020 /* Sticky Transmit Overflow Status */ -#define TXHRE 0x0040 /* Transmit Hold Register Empty */ - -/* SPORTx_MCMC1 Macros */ -#define SP_WOFF(x) ((x) & 0x3FF) /* Multichannel Window Offset Field */ - -/* Only use WSIZE Macro With Logic OR While Setting Lower Order Bits */ -#define SP_WSIZE(x) (((((x)>>0x3)-1)&0xF) << 0xC) /* Multichannel Window Size = (x/8)-1 */ - -/* SPORTx_MCMC2 Masks */ -#define REC_BYPASS 0x0000 /* Bypass Mode (No Clock Recovery) */ -#define REC_2FROM4 0x0002 /* Recover 2 MHz Clock from 4 MHz Clock */ -#define REC_8FROM16 0x0003 /* Recover 8 MHz Clock from 16 MHz Clock */ -#define MCDTXPE 0x0004 /* Multichannel DMA Transmit Packing */ -#define MCDRXPE 0x0008 /* Multichannel DMA Receive Packing */ -#define MCMEN 0x0010 /* Multichannel Frame Mode Enable */ -#define FSDR 0x0080 /* Multichannel Frame Sync to Data Relationship */ -#define MFD_0 0x0000 /* Multichannel Frame Delay = 0 */ -#define MFD_1 0x1000 /* Multichannel Frame Delay = 1 */ -#define MFD_2 0x2000 /* Multichannel Frame Delay = 2 */ -#define MFD_3 0x3000 /* Multichannel Frame Delay = 3 */ -#define MFD_4 0x4000 /* Multichannel Frame Delay = 4 */ -#define MFD_5 0x5000 /* Multichannel Frame Delay = 5 */ -#define MFD_6 0x6000 /* Multichannel Frame Delay = 6 */ -#define MFD_7 0x7000 /* Multichannel Frame Delay = 7 */ -#define MFD_8 0x8000 /* Multichannel Frame Delay = 8 */ -#define MFD_9 0x9000 /* Multichannel Frame Delay = 9 */ -#define MFD_10 0xA000 /* Multichannel Frame Delay = 10 */ -#define MFD_11 0xB000 /* Multichannel Frame Delay = 11 */ -#define MFD_12 0xC000 /* Multichannel Frame Delay = 12 */ -#define MFD_13 0xD000 /* Multichannel Frame Delay = 13 */ -#define MFD_14 0xE000 /* Multichannel Frame Delay = 14 */ -#define MFD_15 0xF000 /* Multichannel Frame Delay = 15 */ - - /* ********************* ASYNCHRONOUS MEMORY CONTROLLER MASKS *************************/ /* EBIU_AMGCTL Masks */ #define AMCKEN 0x0001 /* Enable CLKOUT */ diff --git a/arch/blackfin/mach-bf527/boards/cm_bf527.c b/arch/blackfin/mach-bf527/boards/cm_bf527.c index f392af641657..645ba5c8077b 100644 --- a/arch/blackfin/mach-bf527/boards/cm_bf527.c +++ b/arch/blackfin/mach-bf527/boards/cm_bf527.c @@ -145,7 +145,6 @@ static struct mtd_partition partition_info[] = { }; static struct bf5xx_nand_platform bf5xx_nand_platform = { - .page_size = NFC_PG_SIZE_256, .data_width = NFC_NWIDTH_8, .partitions = partition_info, .nr_partitions = ARRAY_SIZE(partition_info), diff --git a/arch/blackfin/mach-bf527/boards/ezbrd.c b/arch/blackfin/mach-bf527/boards/ezbrd.c index 606eb36b9d6e..c975fe88eba3 100644 --- a/arch/blackfin/mach-bf527/boards/ezbrd.c +++ b/arch/blackfin/mach-bf527/boards/ezbrd.c @@ -149,7 +149,6 @@ static struct mtd_partition partition_info[] = { }; static struct bf5xx_nand_platform bf5xx_nand_platform = { - .page_size = NFC_PG_SIZE_256, .data_width = NFC_NWIDTH_8, .partitions = partition_info, .nr_partitions = ARRAY_SIZE(partition_info), diff --git a/arch/blackfin/mach-bf527/boards/ezkit.c b/arch/blackfin/mach-bf527/boards/ezkit.c index a05c967a24cf..87b41e994ba3 100644 --- a/arch/blackfin/mach-bf527/boards/ezkit.c +++ b/arch/blackfin/mach-bf527/boards/ezkit.c @@ -234,7 +234,6 @@ static struct mtd_partition partition_info[] = { }; static struct bf5xx_nand_platform bf5xx_nand_platform = { - .page_size = NFC_PG_SIZE_256, .data_width = NFC_NWIDTH_8, .partitions = partition_info, .nr_partitions = ARRAY_SIZE(partition_info), diff --git a/arch/blackfin/mach-bf527/include/mach/defBF52x_base.h b/arch/blackfin/mach-bf527/include/mach/defBF52x_base.h index 5f97f01fcda6..3e000756aacd 100644 --- a/arch/blackfin/mach-bf527/include/mach/defBF52x_base.h +++ b/arch/blackfin/mach-bf527/include/mach/defBF52x_base.h @@ -922,88 +922,6 @@ #define PH14 0x4000 #define PH15 0x8000 - -/* ******************* SERIAL PORT MASKS **************************************/ -/* SPORTx_TCR1 Masks */ -#define TSPEN 0x0001 /* Transmit Enable */ -#define ITCLK 0x0002 /* Internal Transmit Clock Select */ -#define DTYPE_NORM 0x0004 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define TLSBIT 0x0010 /* Transmit Bit Order */ -#define ITFS 0x0200 /* Internal Transmit Frame Sync Select */ -#define TFSR 0x0400 /* Transmit Frame Sync Required Select */ -#define DITFS 0x0800 /* Data-Independent Transmit Frame Sync Select */ -#define LTFS 0x1000 /* Low Transmit Frame Sync Select */ -#define LATFS 0x2000 /* Late Transmit Frame Sync Select */ -#define TCKFE 0x4000 /* Clock Falling Edge Select */ - -/* SPORTx_TCR2 Masks and Macro */ -#define SLEN(x) ((x)&0x1F) /* SPORT TX Word Length (2 - 31) */ -#define TXSE 0x0100 /* TX Secondary Enable */ -#define TSFSE 0x0200 /* Transmit Stereo Frame Sync Enable */ -#define TRFST 0x0400 /* Left/Right Order (1 = Right Channel 1st) */ - -/* SPORTx_RCR1 Masks */ -#define RSPEN 0x0001 /* Receive Enable */ -#define IRCLK 0x0002 /* Internal Receive Clock Select */ -#define DTYPE_NORM 0x0004 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define RLSBIT 0x0010 /* Receive Bit Order */ -#define IRFS 0x0200 /* Internal Receive Frame Sync Select */ -#define RFSR 0x0400 /* Receive Frame Sync Required Select */ -#define LRFS 0x1000 /* Low Receive Frame Sync Select */ -#define LARFS 0x2000 /* Late Receive Frame Sync Select */ -#define RCKFE 0x4000 /* Clock Falling Edge Select */ - -/* SPORTx_RCR2 Masks */ -#define SLEN(x) ((x)&0x1F) /* SPORT RX Word Length (2 - 31) */ -#define RXSE 0x0100 /* RX Secondary Enable */ -#define RSFSE 0x0200 /* RX Stereo Frame Sync Enable */ -#define RRFST 0x0400 /* Right-First Data Order */ - -/* SPORTx_STAT Masks */ -#define RXNE 0x0001 /* Receive FIFO Not Empty Status */ -#define RUVF 0x0002 /* Sticky Receive Underflow Status */ -#define ROVF 0x0004 /* Sticky Receive Overflow Status */ -#define TXF 0x0008 /* Transmit FIFO Full Status */ -#define TUVF 0x0010 /* Sticky Transmit Underflow Status */ -#define TOVF 0x0020 /* Sticky Transmit Overflow Status */ -#define TXHRE 0x0040 /* Transmit Hold Register Empty */ - -/* SPORTx_MCMC1 Macros */ -#define SP_WOFF(x) ((x) & 0x3FF) /* Multichannel Window Offset Field */ - -/* Only use WSIZE Macro With Logic OR While Setting Lower Order Bits */ -#define SP_WSIZE(x) (((((x)>>0x3)-1)&0xF) << 0xC) /* Multichannel Window Size = (x/8)-1 */ - -/* SPORTx_MCMC2 Masks */ -#define REC_BYPASS 0x0000 /* Bypass Mode (No Clock Recovery) */ -#define REC_2FROM4 0x0002 /* Recover 2 MHz Clock from 4 MHz Clock */ -#define REC_8FROM16 0x0003 /* Recover 8 MHz Clock from 16 MHz Clock */ -#define MCDTXPE 0x0004 /* Multichannel DMA Transmit Packing */ -#define MCDRXPE 0x0008 /* Multichannel DMA Receive Packing */ -#define MCMEN 0x0010 /* Multichannel Frame Mode Enable */ -#define FSDR 0x0080 /* Multichannel Frame Sync to Data Relationship */ -#define MFD_0 0x0000 /* Multichannel Frame Delay = 0 */ -#define MFD_1 0x1000 /* Multichannel Frame Delay = 1 */ -#define MFD_2 0x2000 /* Multichannel Frame Delay = 2 */ -#define MFD_3 0x3000 /* Multichannel Frame Delay = 3 */ -#define MFD_4 0x4000 /* Multichannel Frame Delay = 4 */ -#define MFD_5 0x5000 /* Multichannel Frame Delay = 5 */ -#define MFD_6 0x6000 /* Multichannel Frame Delay = 6 */ -#define MFD_7 0x7000 /* Multichannel Frame Delay = 7 */ -#define MFD_8 0x8000 /* Multichannel Frame Delay = 8 */ -#define MFD_9 0x9000 /* Multichannel Frame Delay = 9 */ -#define MFD_10 0xA000 /* Multichannel Frame Delay = 10 */ -#define MFD_11 0xB000 /* Multichannel Frame Delay = 11 */ -#define MFD_12 0xC000 /* Multichannel Frame Delay = 12 */ -#define MFD_13 0xD000 /* Multichannel Frame Delay = 13 */ -#define MFD_14 0xE000 /* Multichannel Frame Delay = 14 */ -#define MFD_15 0xF000 /* Multichannel Frame Delay = 15 */ - - /* ********************* ASYNCHRONOUS MEMORY CONTROLLER MASKS *************************/ /* EBIU_AMGCTL Masks */ #define AMCKEN 0x0001 /* Enable CLKOUT */ diff --git a/arch/blackfin/mach-bf533/include/mach/defBF532.h b/arch/blackfin/mach-bf533/include/mach/defBF532.h index e9ff491c0953..04acf1ed10f9 100644 --- a/arch/blackfin/mach-bf533/include/mach/defBF532.h +++ b/arch/blackfin/mach-bf533/include/mach/defBF532.h @@ -509,98 +509,6 @@ #define IREN_P 0x01 #define UCEN_P 0x00 -/* ********** SERIAL PORT MASKS ********************** */ - -/* SPORTx_TCR1 Masks */ -#define TSPEN 0x0001 /* TX enable */ -#define ITCLK 0x0002 /* Internal TX Clock Select */ -#define TDTYPE 0x000C /* TX Data Formatting Select */ -#define DTYPE_NORM 0x0000 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define TLSBIT 0x0010 /* TX Bit Order */ -#define ITFS 0x0200 /* Internal TX Frame Sync Select */ -#define TFSR 0x0400 /* TX Frame Sync Required Select */ -#define DITFS 0x0800 /* Data Independent TX Frame Sync Select */ -#define LTFS 0x1000 /* Low TX Frame Sync Select */ -#define LATFS 0x2000 /* Late TX Frame Sync Select */ -#define TCKFE 0x4000 /* TX Clock Falling Edge Select */ - -/* SPORTx_TCR2 Masks */ -#if defined(__ADSPBF531__) || defined(__ADSPBF532__) || \ - defined(__ADSPBF533__) -# define SLEN 0x001F /*TX Word Length */ -#else -# define SLEN(x) ((x)&0x1F) /* SPORT TX Word Length (2 - 31) */ -#endif -#define TXSE 0x0100 /*TX Secondary Enable */ -#define TSFSE 0x0200 /*TX Stereo Frame Sync Enable */ -#define TRFST 0x0400 /*TX Right-First Data Order */ - -/* SPORTx_RCR1 Masks */ -#define RSPEN 0x0001 /* RX enable */ -#define IRCLK 0x0002 /* Internal RX Clock Select */ -#define RDTYPE 0x000C /* RX Data Formatting Select */ -#define DTYPE_NORM 0x0000 /* no companding */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define RLSBIT 0x0010 /* RX Bit Order */ -#define IRFS 0x0200 /* Internal RX Frame Sync Select */ -#define RFSR 0x0400 /* RX Frame Sync Required Select */ -#define LRFS 0x1000 /* Low RX Frame Sync Select */ -#define LARFS 0x2000 /* Late RX Frame Sync Select */ -#define RCKFE 0x4000 /* RX Clock Falling Edge Select */ - -/* SPORTx_RCR2 Masks */ -/* SLEN defined above */ -#define RXSE 0x0100 /*RX Secondary Enable */ -#define RSFSE 0x0200 /*RX Stereo Frame Sync Enable */ -#define RRFST 0x0400 /*Right-First Data Order */ - -/*SPORTx_STAT Masks */ -#define RXNE 0x0001 /*RX FIFO Not Empty Status */ -#define RUVF 0x0002 /*RX Underflow Status */ -#define ROVF 0x0004 /*RX Overflow Status */ -#define TXF 0x0008 /*TX FIFO Full Status */ -#define TUVF 0x0010 /*TX Underflow Status */ -#define TOVF 0x0020 /*TX Overflow Status */ -#define TXHRE 0x0040 /*TX Hold Register Empty */ - -/*SPORTx_MCMC1 Masks */ -#define SP_WSIZE 0x0000F000 /*Multichannel Window Size Field */ -#define SP_WOFF 0x000003FF /*Multichannel Window Offset Field */ -/* SPORTx_MCMC1 Macros */ -#define SET_SP_WOFF(x) ((x) & 0x3FF) /* Multichannel Window Offset Field */ -/* Only use SET_WSIZE Macro With Logic OR While Setting Lower Order Bits */ -#define SET_SP_WSIZE(x) (((((x)>>0x3)-1)&0xF) << 0xC) /* Multichannel Window Size = (x/8)-1 */ - -/*SPORTx_MCMC2 Masks */ -#define MCCRM 0x00000003 /*Multichannel Clock Recovery Mode */ -#define REC_BYPASS 0x0000 /* Bypass Mode (No Clock Recovery) */ -#define REC_2FROM4 0x0002 /* Recover 2 MHz Clock from 4 MHz Clock */ -#define REC_8FROM16 0x0003 /* Recover 8 MHz Clock from 16 MHz Clock */ -#define MCDTXPE 0x00000004 /*Multichannel DMA Transmit Packing */ -#define MCDRXPE 0x00000008 /*Multichannel DMA Receive Packing */ -#define MCMEN 0x00000010 /*Multichannel Frame Mode Enable */ -#define FSDR 0x00000080 /*Multichannel Frame Sync to Data Relationship */ -#define MFD 0x0000F000 /*Multichannel Frame Delay */ -#define MFD_0 0x0000 /* Multichannel Frame Delay = 0 */ -#define MFD_1 0x1000 /* Multichannel Frame Delay = 1 */ -#define MFD_2 0x2000 /* Multichannel Frame Delay = 2 */ -#define MFD_3 0x3000 /* Multichannel Frame Delay = 3 */ -#define MFD_4 0x4000 /* Multichannel Frame Delay = 4 */ -#define MFD_5 0x5000 /* Multichannel Frame Delay = 5 */ -#define MFD_6 0x6000 /* Multichannel Frame Delay = 6 */ -#define MFD_7 0x7000 /* Multichannel Frame Delay = 7 */ -#define MFD_8 0x8000 /* Multichannel Frame Delay = 8 */ -#define MFD_9 0x9000 /* Multichannel Frame Delay = 9 */ -#define MFD_10 0xA000 /* Multichannel Frame Delay = 10 */ -#define MFD_11 0xB000 /* Multichannel Frame Delay = 11 */ -#define MFD_12 0xC000 /* Multichannel Frame Delay = 12 */ -#define MFD_13 0xD000 /* Multichannel Frame Delay = 13 */ -#define MFD_14 0xE000 /* Multichannel Frame Delay = 14 */ -#define MFD_15 0xF000 /* Multichannel Frame Delay = 15 */ - /* ********* PARALLEL PERIPHERAL INTERFACE (PPI) MASKS **************** */ /* PPI_CONTROL Masks */ diff --git a/arch/blackfin/mach-bf537/include/mach/defBF534.h b/arch/blackfin/mach-bf537/include/mach/defBF534.h index aad61b887373..6f56907a18c0 100644 --- a/arch/blackfin/mach-bf537/include/mach/defBF534.h +++ b/arch/blackfin/mach-bf537/include/mach/defBF534.h @@ -1241,86 +1241,6 @@ #define PH14 0x4000 #define PH15 0x8000 -/* ******************* SERIAL PORT MASKS **************************************/ -/* SPORTx_TCR1 Masks */ -#define TSPEN 0x0001 /* Transmit Enable */ -#define ITCLK 0x0002 /* Internal Transmit Clock Select */ -#define DTYPE_NORM 0x0004 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define TLSBIT 0x0010 /* Transmit Bit Order */ -#define ITFS 0x0200 /* Internal Transmit Frame Sync Select */ -#define TFSR 0x0400 /* Transmit Frame Sync Required Select */ -#define DITFS 0x0800 /* Data-Independent Transmit Frame Sync Select */ -#define LTFS 0x1000 /* Low Transmit Frame Sync Select */ -#define LATFS 0x2000 /* Late Transmit Frame Sync Select */ -#define TCKFE 0x4000 /* Clock Falling Edge Select */ - -/* SPORTx_TCR2 Masks and Macro */ -#define SLEN(x) ((x)&0x1F) /* SPORT TX Word Length (2 - 31) */ -#define TXSE 0x0100 /* TX Secondary Enable */ -#define TSFSE 0x0200 /* Transmit Stereo Frame Sync Enable */ -#define TRFST 0x0400 /* Left/Right Order (1 = Right Channel 1st) */ - -/* SPORTx_RCR1 Masks */ -#define RSPEN 0x0001 /* Receive Enable */ -#define IRCLK 0x0002 /* Internal Receive Clock Select */ -#define DTYPE_NORM 0x0004 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define RLSBIT 0x0010 /* Receive Bit Order */ -#define IRFS 0x0200 /* Internal Receive Frame Sync Select */ -#define RFSR 0x0400 /* Receive Frame Sync Required Select */ -#define LRFS 0x1000 /* Low Receive Frame Sync Select */ -#define LARFS 0x2000 /* Late Receive Frame Sync Select */ -#define RCKFE 0x4000 /* Clock Falling Edge Select */ - -/* SPORTx_RCR2 Masks */ -#define SLEN(x) ((x)&0x1F) /* SPORT RX Word Length (2 - 31) */ -#define RXSE 0x0100 /* RX Secondary Enable */ -#define RSFSE 0x0200 /* RX Stereo Frame Sync Enable */ -#define RRFST 0x0400 /* Right-First Data Order */ - -/* SPORTx_STAT Masks */ -#define RXNE 0x0001 /* Receive FIFO Not Empty Status */ -#define RUVF 0x0002 /* Sticky Receive Underflow Status */ -#define ROVF 0x0004 /* Sticky Receive Overflow Status */ -#define TXF 0x0008 /* Transmit FIFO Full Status */ -#define TUVF 0x0010 /* Sticky Transmit Underflow Status */ -#define TOVF 0x0020 /* Sticky Transmit Overflow Status */ -#define TXHRE 0x0040 /* Transmit Hold Register Empty */ - -/* SPORTx_MCMC1 Macros */ -#define SP_WOFF(x) ((x) & 0x3FF) /* Multichannel Window Offset Field */ - -/* Only use WSIZE Macro With Logic OR While Setting Lower Order Bits */ -#define SP_WSIZE(x) (((((x)>>0x3)-1)&0xF) << 0xC) /* Multichannel Window Size = (x/8)-1 */ - -/* SPORTx_MCMC2 Masks */ -#define REC_BYPASS 0x0000 /* Bypass Mode (No Clock Recovery) */ -#define REC_2FROM4 0x0002 /* Recover 2 MHz Clock from 4 MHz Clock */ -#define REC_8FROM16 0x0003 /* Recover 8 MHz Clock from 16 MHz Clock */ -#define MCDTXPE 0x0004 /* Multichannel DMA Transmit Packing */ -#define MCDRXPE 0x0008 /* Multichannel DMA Receive Packing */ -#define MCMEN 0x0010 /* Multichannel Frame Mode Enable */ -#define FSDR 0x0080 /* Multichannel Frame Sync to Data Relationship */ -#define MFD_0 0x0000 /* Multichannel Frame Delay = 0 */ -#define MFD_1 0x1000 /* Multichannel Frame Delay = 1 */ -#define MFD_2 0x2000 /* Multichannel Frame Delay = 2 */ -#define MFD_3 0x3000 /* Multichannel Frame Delay = 3 */ -#define MFD_4 0x4000 /* Multichannel Frame Delay = 4 */ -#define MFD_5 0x5000 /* Multichannel Frame Delay = 5 */ -#define MFD_6 0x6000 /* Multichannel Frame Delay = 6 */ -#define MFD_7 0x7000 /* Multichannel Frame Delay = 7 */ -#define MFD_8 0x8000 /* Multichannel Frame Delay = 8 */ -#define MFD_9 0x9000 /* Multichannel Frame Delay = 9 */ -#define MFD_10 0xA000 /* Multichannel Frame Delay = 10 */ -#define MFD_11 0xB000 /* Multichannel Frame Delay = 11 */ -#define MFD_12 0xC000 /* Multichannel Frame Delay = 12 */ -#define MFD_13 0xD000 /* Multichannel Frame Delay = 13 */ -#define MFD_14 0xE000 /* Multichannel Frame Delay = 14 */ -#define MFD_15 0xF000 /* Multichannel Frame Delay = 15 */ - /* ********************* ASYNCHRONOUS MEMORY CONTROLLER MASKS *************************/ /* EBIU_AMGCTL Masks */ #define AMCKEN 0x0001 /* Enable CLKOUT */ diff --git a/arch/blackfin/mach-bf538/include/mach/defBF539.h b/arch/blackfin/mach-bf538/include/mach/defBF539.h index b674a1c4aef1..fe43062b4975 100644 --- a/arch/blackfin/mach-bf538/include/mach/defBF539.h +++ b/arch/blackfin/mach-bf538/include/mach/defBF539.h @@ -1610,113 +1610,6 @@ #define UCEN_P 0x00 -/* ********** SERIAL PORT MASKS ********************** */ -/* SPORTx_TCR1 Masks */ -#define TSPEN 0x0001 /* TX enable */ -#define ITCLK 0x0002 /* Internal TX Clock Select */ -#define TDTYPE 0x000C /* TX Data Formatting Select */ -#define DTYPE_NORM 0x0000 /* Data Format Normal */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define TLSBIT 0x0010 /* TX Bit Order */ -#define ITFS 0x0200 /* Internal TX Frame Sync Select */ -#define TFSR 0x0400 /* TX Frame Sync Required Select */ -#define DITFS 0x0800 /* Data Independent TX Frame Sync Select */ -#define LTFS 0x1000 /* Low TX Frame Sync Select */ -#define LATFS 0x2000 /* Late TX Frame Sync Select */ -#define TCKFE 0x4000 /* TX Clock Falling Edge Select */ -/* SPORTx_RCR1 Deprecated Masks */ -#define TULAW DTYPE_ULAW /* Compand Using u-Law */ -#define TALAW DTYPE_ALAW /* Compand Using A-Law */ - -/* SPORTx_TCR2 Masks */ -#ifdef _MISRA_RULES -#define SLEN(x) ((x)&0x1Fu) /* SPORT TX Word Length (2 - 31) */ -#else -#define SLEN(x) ((x)&0x1F) /* SPORT TX Word Length (2 - 31) */ -#endif /* _MISRA_RULES */ -#define TXSE 0x0100 /*TX Secondary Enable */ -#define TSFSE 0x0200 /*TX Stereo Frame Sync Enable */ -#define TRFST 0x0400 /*TX Right-First Data Order */ - -/* SPORTx_RCR1 Masks */ -#define RSPEN 0x0001 /* RX enable */ -#define IRCLK 0x0002 /* Internal RX Clock Select */ -#define RDTYPE 0x000C /* RX Data Formatting Select */ -#define DTYPE_NORM 0x0000 /* no companding */ -#define DTYPE_ULAW 0x0008 /* Compand Using u-Law */ -#define DTYPE_ALAW 0x000C /* Compand Using A-Law */ -#define RLSBIT 0x0010 /* RX Bit Order */ -#define IRFS 0x0200 /* Internal RX Frame Sync Select */ -#define RFSR 0x0400 /* RX Frame Sync Required Select */ -#define LRFS 0x1000 /* Low RX Frame Sync Select */ -#define LARFS 0x2000 /* Late RX Frame Sync Select */ -#define RCKFE 0x4000 /* RX Clock Falling Edge Select */ -/* SPORTx_RCR1 Deprecated Masks */ -#define RULAW DTYPE_ULAW /* Compand Using u-Law */ -#define RALAW DTYPE_ALAW /* Compand Using A-Law */ - -/* SPORTx_RCR2 Masks */ -#ifdef _MISRA_RULES -#define SLEN(x) ((x)&0x1Fu) /* SPORT RX Word Length (2 - 31) */ -#else -#define SLEN(x) ((x)&0x1F) /* SPORT RX Word Length (2 - 31) */ -#endif /* _MISRA_RULES */ -#define RXSE 0x0100 /*RX Secondary Enable */ -#define RSFSE 0x0200 /*RX Stereo Frame Sync Enable */ -#define RRFST 0x0400 /*Right-First Data Order */ - -/*SPORTx_STAT Masks */ -#define RXNE 0x0001 /*RX FIFO Not Empty Status */ -#define RUVF 0x0002 /*RX Underflow Status */ -#define ROVF 0x0004 /*RX Overflow Status */ -#define TXF 0x0008 /*TX FIFO Full Status */ -#define TUVF 0x0010 /*TX Underflow Status */ -#define TOVF 0x0020 /*TX Overflow Status */ -#define TXHRE 0x0040 /*TX Hold Register Empty */ - -/*SPORTx_MCMC1 Masks */ -#define WOFF 0x000003FF /*Multichannel Window Offset Field */ -/* SPORTx_MCMC1 Macros */ -#ifdef _MISRA_RULES -#define SET_WOFF(x) ((x) & 0x3FFu) /* Multichannel Window Offset Field */ -/* Only use SET_WSIZE Macro With Logic OR While Setting Lower Order Bits */ -#define SET_WSIZE(x) (((((x)>>0x3)-1u)&0xFu) << 0xC) /* Multichannel Window Size = (x/8)-1 */ -#else -#define SET_WOFF(x) ((x) & 0x3FF) /* Multichannel Window Offset Field */ -/* Only use SET_WSIZE Macro With Logic OR While Setting Lower Order Bits */ -#define SET_WSIZE(x) (((((x)>>0x3)-1)&0xF) << 0xC) /* Multichannel Window Size = (x/8)-1 */ -#endif /* _MISRA_RULES */ - - -/*SPORTx_MCMC2 Masks */ -#define MCCRM 0x0003 /*Multichannel Clock Recovery Mode */ -#define REC_BYPASS 0x0000 /* Bypass Mode (No Clock Recovery) */ -#define REC_2FROM4 0x0002 /* Recover 2 MHz Clock from 4 MHz Clock */ -#define REC_8FROM16 0x0003 /* Recover 8 MHz Clock from 16 MHz Clock */ -#define MCDTXPE 0x0004 /*Multichannel DMA Transmit Packing */ -#define MCDRXPE 0x0008 /*Multichannel DMA Receive Packing */ -#define MCMEN 0x0010 /*Multichannel Frame Mode Enable */ -#define FSDR 0x0080 /*Multichannel Frame Sync to Data Relationship */ -#define MFD 0xF000 /*Multichannel Frame Delay */ -#define MFD_0 0x0000 /* Multichannel Frame Delay = 0 */ -#define MFD_1 0x1000 /* Multichannel Frame Delay = 1 */ -#define MFD_2 0x2000 /* Multichannel Frame Delay = 2 */ -#define MFD_3 0x3000 /* Multichannel Frame Delay = 3 */ -#define MFD_4 0x4000 /* Multichannel Frame Delay = 4 */ -#define MFD_5 0x5000 /* Multichannel Frame Delay = 5 */ -#define MFD_6 0x6000 /* Multichannel Frame Delay = 6 */ -#define MFD_7 0x7000 /* Multichannel Frame Delay = 7 */ -#define MFD_8 0x8000 /* Multichannel Frame Delay = 8 */ -#define MFD_9 0x9000 /* Multichannel Frame Delay = 9 */ -#define MFD_10 0xA000 /* Multichannel Frame Delay = 10 */ -#define MFD_11 0xB000 /* Multichannel Frame Delay = 11 */ -#define MFD_12 0xC000 /* Multichannel Frame Delay = 12 */ -#define MFD_13 0xD000 /* Multichannel Frame Delay = 13 */ -#define MFD_14 0xE000 /* Multichannel Frame Delay = 14 */ -#define MFD_15 0xF000 /* Multichannel Frame Delay = 15 */ - - /* ********* PARALLEL PERIPHERAL INTERFACE (PPI) MASKS **************** */ /* PPI_CONTROL Masks */ #define PORT_EN 0x0001 /* PPI Port Enable */ diff --git a/arch/blackfin/mach-bf548/boards/cm_bf548.c b/arch/blackfin/mach-bf548/boards/cm_bf548.c index dbb6b1d83f6d..0c38eec9ade1 100644 --- a/arch/blackfin/mach-bf548/boards/cm_bf548.c +++ b/arch/blackfin/mach-bf548/boards/cm_bf548.c @@ -706,7 +706,6 @@ static struct mtd_partition partition_info[] = { }; static struct bf5xx_nand_platform bf5xx_nand_platform = { - .page_size = NFC_PG_SIZE_256, .data_width = NFC_NWIDTH_8, .partitions = partition_info, .nr_partitions = ARRAY_SIZE(partition_info), diff --git a/arch/blackfin/mach-bf548/boards/ezkit.c b/arch/blackfin/mach-bf548/boards/ezkit.c index 6fcfb9187c35..56682a36e42d 100644 --- a/arch/blackfin/mach-bf548/boards/ezkit.c +++ b/arch/blackfin/mach-bf548/boards/ezkit.c @@ -849,7 +849,6 @@ static struct mtd_partition partition_info[] = { }; static struct bf5xx_nand_platform bf5xx_nand_platform = { - .page_size = NFC_PG_SIZE_256, .data_width = NFC_NWIDTH_8, .partitions = partition_info, .nr_partitions = ARRAY_SIZE(partition_info), diff --git a/arch/blackfin/mach-bf548/include/mach/defBF54x_base.h b/arch/blackfin/mach-bf548/include/mach/defBF54x_base.h index 95ff44601fd1..7866197f5485 100644 --- a/arch/blackfin/mach-bf548/include/mach/defBF54x_base.h +++ b/arch/blackfin/mach-bf548/include/mach/defBF54x_base.h @@ -2221,73 +2221,6 @@ #define RCVDATA16 0xffff /* Receive FIFO 16-Bit Data */ -/* Bit masks for SPORTx_TCR1 */ - -#define TCKFE 0x4000 /* Clock Falling Edge Select */ -#define LATFS 0x2000 /* Late Transmit Frame Sync */ -#define LTFS 0x1000 /* Low Transmit Frame Sync Select */ -#define DITFS 0x800 /* Data-Independent Transmit Frame Sync Select */ -#define TFSR 0x400 /* Transmit Frame Sync Required Select */ -#define ITFS 0x200 /* Internal Transmit Frame Sync Select */ -#define TLSBIT 0x10 /* Transmit Bit Order */ -#define TDTYPE 0xc /* Data Formatting Type Select */ -#define ITCLK 0x2 /* Internal Transmit Clock Select */ -#define TSPEN 0x1 /* Transmit Enable */ - -/* Bit masks for SPORTx_TCR2 */ - -#define TRFST 0x400 /* Left/Right Order */ -#define TSFSE 0x200 /* Transmit Stereo Frame Sync Enable */ -#define TXSE 0x100 /* TxSEC Enable */ -#define SLEN_T 0x1f /* SPORT Word Length */ - -/* Bit masks for SPORTx_RCR1 */ - -#define RCKFE 0x4000 /* Clock Falling Edge Select */ -#define LARFS 0x2000 /* Late Receive Frame Sync */ -#define LRFS 0x1000 /* Low Receive Frame Sync Select */ -#define RFSR 0x400 /* Receive Frame Sync Required Select */ -#define IRFS 0x200 /* Internal Receive Frame Sync Select */ -#define RLSBIT 0x10 /* Receive Bit Order */ -#define RDTYPE 0xc /* Data Formatting Type Select */ -#define IRCLK 0x2 /* Internal Receive Clock Select */ -#define RSPEN 0x1 /* Receive Enable */ - -/* Bit masks for SPORTx_RCR2 */ - -#define RRFST 0x400 /* Left/Right Order */ -#define RSFSE 0x200 /* Receive Stereo Frame Sync Enable */ -#define RXSE 0x100 /* RxSEC Enable */ -#define SLEN_R 0x1f /* SPORT Word Length */ - -/* Bit masks for SPORTx_STAT */ - -#define TXHRE 0x40 /* Transmit Hold Register Empty */ -#define TOVF 0x20 /* Sticky Transmit Overflow Status */ -#define TUVF 0x10 /* Sticky Transmit Underflow Status */ -#define TXF 0x8 /* Transmit FIFO Full Status */ -#define ROVF 0x4 /* Sticky Receive Overflow Status */ -#define RUVF 0x2 /* Sticky Receive Underflow Status */ -#define RXNE 0x1 /* Receive FIFO Not Empty Status */ - -/* Bit masks for SPORTx_MCMC1 */ - -#define SP_WSIZE 0xf000 /* Window Size */ -#define SP_WOFF 0x3ff /* Windows Offset */ - -/* Bit masks for SPORTx_MCMC2 */ - -#define MFD 0xf000 /* Multi channel Frame Delay */ -#define FSDR 0x80 /* Frame Sync to Data Relationship */ -#define MCMEN 0x10 /* Multi channel Frame Mode Enable */ -#define MCDRXPE 0x8 /* Multi channel DMA Receive Packing */ -#define MCDTXPE 0x4 /* Multi channel DMA Transmit Packing */ -#define MCCRM 0x3 /* 2X Clock Recovery Mode */ - -/* Bit masks for SPORTx_CHNL */ - -#define CUR_CHNL 0x3ff /* Current Channel Indicator */ - /* Bit masks for UARTx_LCR */ #if 0 diff --git a/arch/blackfin/mach-bf561/include/mach/defBF561.h b/arch/blackfin/mach-bf561/include/mach/defBF561.h index 4c8e36b7fb33..2674f0097576 100644 --- a/arch/blackfin/mach-bf561/include/mach/defBF561.h +++ b/arch/blackfin/mach-bf561/include/mach/defBF561.h @@ -1007,66 +1007,6 @@ #define IREN_P 0x01 #define UCEN_P 0x00 -/* ********** SERIAL PORT MASKS ********************** */ - -/* SPORTx_TCR1 Masks */ -#define TSPEN 0x0001 /* TX enable */ -#define ITCLK 0x0002 /* Internal TX Clock Select */ -#define TDTYPE 0x000C /* TX Data Formatting Select */ -#define TLSBIT 0x0010 /* TX Bit Order */ -#define ITFS 0x0200 /* Internal TX Frame Sync Select */ -#define TFSR 0x0400 /* TX Frame Sync Required Select */ -#define DITFS 0x0800 /* Data Independent TX Frame Sync Select */ -#define LTFS 0x1000 /* Low TX Frame Sync Select */ -#define LATFS 0x2000 /* Late TX Frame Sync Select */ -#define TCKFE 0x4000 /* TX Clock Falling Edge Select */ - -/* SPORTx_TCR2 Masks */ -#define SLEN 0x001F /*TX Word Length */ -#define TXSE 0x0100 /*TX Secondary Enable */ -#define TSFSE 0x0200 /*TX Stereo Frame Sync Enable */ -#define TRFST 0x0400 /*TX Right-First Data Order */ - -/* SPORTx_RCR1 Masks */ -#define RSPEN 0x0001 /* RX enable */ -#define IRCLK 0x0002 /* Internal RX Clock Select */ -#define RDTYPE 0x000C /* RX Data Formatting Select */ -#define RULAW 0x0008 /* u-Law enable */ -#define RALAW 0x000C /* A-Law enable */ -#define RLSBIT 0x0010 /* RX Bit Order */ -#define IRFS 0x0200 /* Internal RX Frame Sync Select */ -#define RFSR 0x0400 /* RX Frame Sync Required Select */ -#define LRFS 0x1000 /* Low RX Frame Sync Select */ -#define LARFS 0x2000 /* Late RX Frame Sync Select */ -#define RCKFE 0x4000 /* RX Clock Falling Edge Select */ - -/* SPORTx_RCR2 Masks */ -#define SLEN 0x001F /*RX Word Length */ -#define RXSE 0x0100 /*RX Secondary Enable */ -#define RSFSE 0x0200 /*RX Stereo Frame Sync Enable */ -#define RRFST 0x0400 /*Right-First Data Order */ - -/*SPORTx_STAT Masks */ -#define RXNE 0x0001 /*RX FIFO Not Empty Status */ -#define RUVF 0x0002 /*RX Underflow Status */ -#define ROVF 0x0004 /*RX Overflow Status */ -#define TXF 0x0008 /*TX FIFO Full Status */ -#define TUVF 0x0010 /*TX Underflow Status */ -#define TOVF 0x0020 /*TX Overflow Status */ -#define TXHRE 0x0040 /*TX Hold Register Empty */ - -/*SPORTx_MCMC1 Masks */ -#define SP_WSIZE 0x0000F000 /*Multichannel Window Size Field */ -#define SP_WOFF 0x000003FF /*Multichannel Window Offset Field */ - -/*SPORTx_MCMC2 Masks */ -#define MCCRM 0x00000003 /*Multichannel Clock Recovery Mode */ -#define MCDTXPE 0x00000004 /*Multichannel DMA Transmit Packing */ -#define MCDRXPE 0x00000008 /*Multichannel DMA Receive Packing */ -#define MCMEN 0x00000010 /*Multichannel Frame Mode Enable */ -#define FSDR 0x00000080 /*Multichannel Frame Sync to Data Relationship */ -#define MFD 0x0000F000 /*Multichannel Frame Delay */ - /* ********* PARALLEL PERIPHERAL INTERFACE (PPI) MASKS **************** */ /* PPI_CONTROL Masks */ diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S index a5847f5d67c7..af1bffa21dc1 100644 --- a/arch/blackfin/mach-common/entry.S +++ b/arch/blackfin/mach-common/entry.S @@ -1628,6 +1628,9 @@ ENTRY(_sys_call_table) .long _sys_rt_tgsigqueueinfo .long _sys_perf_event_open .long _sys_recvmmsg /* 370 */ + .long _sys_fanotify_init + .long _sys_fanotify_mark + .long _sys_prlimit64 .rept NR_syscalls-(.-_sys_call_table)/4 .long _sys_ni_syscall diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig index 16399bd24993..0f2417df6323 100644 --- a/arch/frv/Kconfig +++ b/arch/frv/Kconfig @@ -7,6 +7,7 @@ config FRV default y select HAVE_IDE select HAVE_ARCH_TRACEHOOK + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS config ZONE_DMA diff --git a/arch/frv/kernel/signal.c b/arch/frv/kernel/signal.c index 0974c0ecc594..bab01298b58e 100644 --- a/arch/frv/kernel/signal.c +++ b/arch/frv/kernel/signal.c @@ -121,6 +121,9 @@ static int restore_sigcontext(struct sigcontext __user *sc, int *_gr8) struct user_context *user = current->thread.user; unsigned long tbr, psr; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + tbr = user->i.tbr; psr = user->i.psr; if (copy_from_user(user, &sc->sc_context, sizeof(sc->sc_context))) @@ -250,6 +253,8 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set) struct sigframe __user *frame; int rsig; + set_fs(USER_DS); + frame = get_sigframe(ka, sizeof(*frame)); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) @@ -293,22 +298,23 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set) (unsigned long) (frame->retcode + 2)); } - /* set up registers for signal handler */ - __frame->sp = (unsigned long) frame; - __frame->lr = (unsigned long) &frame->retcode; - __frame->gr8 = sig; - + /* Set up registers for the signal handler */ if (current->personality & FDPIC_FUNCPTRS) { struct fdpic_func_descriptor __user *funcptr = (struct fdpic_func_descriptor __user *) ka->sa.sa_handler; - __get_user(__frame->pc, &funcptr->text); - __get_user(__frame->gr15, &funcptr->GOT); + struct fdpic_func_descriptor desc; + if (copy_from_user(&desc, funcptr, sizeof(desc))) + goto give_sigsegv; + __frame->pc = desc.text; + __frame->gr15 = desc.GOT; } else { __frame->pc = (unsigned long) ka->sa.sa_handler; __frame->gr15 = 0; } - set_fs(USER_DS); + __frame->sp = (unsigned long) frame; + __frame->lr = (unsigned long) &frame->retcode; + __frame->gr8 = sig; /* the tracer may want to single-step inside the handler */ if (test_thread_flag(TIF_SINGLESTEP)) @@ -323,7 +329,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set) return 0; give_sigsegv: - force_sig(SIGSEGV, current); + force_sigsegv(sig, current); return -EFAULT; } /* end setup_frame() */ @@ -338,6 +344,8 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, struct rt_sigframe __user *frame; int rsig; + set_fs(USER_DS); + frame = get_sigframe(ka, sizeof(*frame)); if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) @@ -392,22 +400,23 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, } /* Set up registers for signal handler */ - __frame->sp = (unsigned long) frame; - __frame->lr = (unsigned long) &frame->retcode; - __frame->gr8 = sig; - __frame->gr9 = (unsigned long) &frame->info; - if (current->personality & FDPIC_FUNCPTRS) { struct fdpic_func_descriptor __user *funcptr = (struct fdpic_func_descriptor __user *) ka->sa.sa_handler; - __get_user(__frame->pc, &funcptr->text); - __get_user(__frame->gr15, &funcptr->GOT); + struct fdpic_func_descriptor desc; + if (copy_from_user(&desc, funcptr, sizeof(desc))) + goto give_sigsegv; + __frame->pc = desc.text; + __frame->gr15 = desc.GOT; } else { __frame->pc = (unsigned long) ka->sa.sa_handler; __frame->gr15 = 0; } - set_fs(USER_DS); + __frame->sp = (unsigned long) frame; + __frame->lr = (unsigned long) &frame->retcode; + __frame->gr8 = sig; + __frame->gr9 = (unsigned long) &frame->info; /* the tracer may want to single-step inside the handler */ if (test_thread_flag(TIF_SINGLESTEP)) @@ -422,7 +431,7 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return 0; give_sigsegv: - force_sig(SIGSEGV, current); + force_sigsegv(sig, current); return -EFAULT; } /* end setup_rt_frame() */ @@ -437,7 +446,7 @@ static int handle_signal(unsigned long sig, siginfo_t *info, int ret; /* Are we from a system call? */ - if (in_syscall(__frame)) { + if (__frame->syscallno != -1) { /* If so, check system call restarting.. */ switch (__frame->gr8) { case -ERESTART_RESTARTBLOCK: @@ -456,6 +465,7 @@ static int handle_signal(unsigned long sig, siginfo_t *info, __frame->gr8 = __frame->orig_gr8; __frame->pc -= 4; } + __frame->syscallno = -1; } /* Set up the stack frame */ @@ -538,10 +548,11 @@ no_signal: break; case -ERESTART_RESTARTBLOCK: - __frame->gr8 = __NR_restart_syscall; + __frame->gr7 = __NR_restart_syscall; __frame->pc -= 4; break; } + __frame->syscallno = -1; } /* if there's no signal to deliver, we just put the saved sigmask diff --git a/arch/frv/lib/Makefile b/arch/frv/lib/Makefile index f4709756d0d9..4ff2fb1e6b16 100644 --- a/arch/frv/lib/Makefile +++ b/arch/frv/lib/Makefile @@ -5,4 +5,4 @@ lib-y := \ __ashldi3.o __lshrdi3.o __muldi3.o __ashrdi3.o __negdi2.o __ucmpdi2.o \ checksum.o memcpy.o memset.o atomic-ops.o atomic64-ops.o \ - outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o perf_event.o + outsl_ns.o outsl_sw.o insl_ns.o insl_sw.o cache.o diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h index e936804b7508..984221abb66d 100644 --- a/arch/h8300/include/asm/atomic.h +++ b/arch/h8300/include/asm/atomic.h @@ -18,7 +18,8 @@ static __inline__ int atomic_add_return(int i, atomic_t *v) { - int ret,flags; + unsigned long flags; + int ret; local_irq_save(flags); ret = v->counter += i; local_irq_restore(flags); @@ -30,7 +31,8 @@ static __inline__ int atomic_add_return(int i, atomic_t *v) static __inline__ int atomic_sub_return(int i, atomic_t *v) { - int ret,flags; + unsigned long flags; + int ret; local_irq_save(flags); ret = v->counter -= i; local_irq_restore(flags); @@ -42,7 +44,8 @@ static __inline__ int atomic_sub_return(int i, atomic_t *v) static __inline__ int atomic_inc_return(atomic_t *v) { - int ret,flags; + unsigned long flags; + int ret; local_irq_save(flags); v->counter++; ret = v->counter; @@ -64,7 +67,8 @@ static __inline__ int atomic_inc_return(atomic_t *v) static __inline__ int atomic_dec_return(atomic_t *v) { - int ret,flags; + unsigned long flags; + int ret; local_irq_save(flags); --v->counter; ret = v->counter; @@ -76,7 +80,8 @@ static __inline__ int atomic_dec_return(atomic_t *v) static __inline__ int atomic_dec_and_test(atomic_t *v) { - int ret,flags; + unsigned long flags; + int ret; local_irq_save(flags); --v->counter; ret = v->counter; diff --git a/arch/h8300/include/asm/system.h b/arch/h8300/include/asm/system.h index d98d97685f06..16bf1560ff68 100644 --- a/arch/h8300/include/asm/system.h +++ b/arch/h8300/include/asm/system.h @@ -3,6 +3,8 @@ #include <linux/linkage.h> +struct pt_regs; + /* * switch_to(n) should switch tasks to task ptr, first checking that * ptr isn't the current task, in which case it does nothing. This @@ -155,6 +157,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz #define arch_align_stack(x) (x) -void die(char *str, struct pt_regs *fp, unsigned long err); +extern void die(const char *str, struct pt_regs *fp, unsigned long err); #endif /* _H8300_SYSTEM_H */ diff --git a/arch/h8300/kernel/module.c b/arch/h8300/kernel/module.c index 0865e291c20d..db4953dc4e1b 100644 --- a/arch/h8300/kernel/module.c +++ b/arch/h8300/kernel/module.c @@ -112,10 +112,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/h8300/kernel/sys_h8300.c b/arch/h8300/kernel/sys_h8300.c index dc1ac0243b78..aaf5e5a48f93 100644 --- a/arch/h8300/kernel/sys_h8300.c +++ b/arch/h8300/kernel/sys_h8300.c @@ -56,8 +56,8 @@ int kernel_execve(const char *filename, const char *const envp[]) { register long res __asm__("er0"); - register char *const *_c __asm__("er3") = envp; - register char *const *_b __asm__("er2") = argv; + register const char *const *_c __asm__("er3") = envp; + register const char *const *_b __asm__("er2") = argv; register const char * _a __asm__("er1") = filename; __asm__ __volatile__ ("mov.l %1,er0\n\t" "trapa #0\n\t" diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index 3c0b66bc669e..dfa05bd908b6 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -96,7 +96,7 @@ static void dump(struct pt_regs *fp) printk("\n\n"); } -void die(char *str, struct pt_regs *fp, unsigned long err) +void die(const char *str, struct pt_regs *fp, unsigned long err) { static int diecount; diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index 2bef5261d96d..1e8d71ad93ef 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -149,7 +149,7 @@ static void receive_chars(struct tty_struct *tty) ch = ia64_ssc(0, 0, 0, 0, SSC_GETCHAR); while (!ch); - handle_sysrq(ch, NULL); + handle_sysrq(ch); } #endif seen_esc = 0; diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h index f90edc85b509..9301a2821615 100644 --- a/arch/ia64/include/asm/compat.h +++ b/arch/ia64/include/asm/compat.h @@ -199,7 +199,7 @@ ptr_to_compat(void __user *uptr) } static __inline__ void __user * -compat_alloc_user_space (long len) +arch_compat_alloc_user_space (long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *) (((regs->r12 & 0xffffffff) & -16) - len); diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h index d514cd9edb49..8fb7d33a661f 100644 --- a/arch/ia64/include/asm/hardirq.h +++ b/arch/ia64/include/asm/hardirq.h @@ -6,12 +6,6 @@ * David Mosberger-Tang <davidm@hpl.hp.com> */ - -#include <linux/threads.h> -#include <linux/irq.h> - -#include <asm/processor.h> - /* * No irq_cpustat_t for IA-64. The data is held in the per-CPU data structure. */ @@ -20,6 +14,11 @@ #define local_softirq_pending() (local_cpu_data->softirq_pending) +#include <linux/threads.h> +#include <linux/irq.h> + +#include <asm/processor.h> + extern void __iomem *ipi_base_addr; void ack_bad_irq(unsigned int irq); diff --git a/arch/ia64/include/asm/system.h b/arch/ia64/include/asm/system.h index 9f342a574ce8..dd028f2b13b3 100644 --- a/arch/ia64/include/asm/system.h +++ b/arch/ia64/include/asm/system.h @@ -272,10 +272,6 @@ void cpu_idle_wait(void); void default_idle(void); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void account_system_vtime(struct task_struct *); -#endif - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index 3567d54f8cee..331d42bda77a 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -420,22 +420,31 @@ EX(.fail_efault, ld8 r14=[r33]) // r14 <- *set ;; RSM_PSR_I(p0, r18, r19) // mask interrupt delivery - mov ar.ccv=0 andcm r14=r14,r17 // filter out SIGKILL & SIGSTOP + mov r8=EINVAL // default to EINVAL #ifdef CONFIG_SMP - mov r17=1 + // __ticket_spin_trylock(r31) + ld4 r17=[r31] ;; - cmpxchg4.acq r18=[r31],r17,ar.ccv // try to acquire the lock - mov r8=EINVAL // default to EINVAL + mov.m ar.ccv=r17 + extr.u r9=r17,17,15 + adds r19=1,r17 + extr.u r18=r17,0,15 + ;; + cmp.eq p6,p7=r9,r18 ;; +(p6) cmpxchg4.acq r9=[r31],r19,ar.ccv +(p6) dep.z r20=r19,1,15 // next serving ticket for unlock +(p7) br.cond.spnt.many .lock_contention + ;; + cmp4.eq p0,p7=r9,r17 + adds r31=2,r31 +(p7) br.cond.spnt.many .lock_contention ld8 r3=[r2] // re-read current->blocked now that we hold the lock - cmp4.ne p6,p0=r18,r0 -(p6) br.cond.spnt.many .lock_contention ;; #else ld8 r3=[r2] // re-read current->blocked now that we hold the lock - mov r8=EINVAL // default to EINVAL #endif add r18=IA64_TASK_PENDING_OFFSET+IA64_SIGPENDING_SIGNAL_OFFSET,r16 add r19=IA64_TASK_SIGNAL_OFFSET,r16 @@ -490,7 +499,9 @@ EX(.fail_efault, ld8 r14=[r33]) // r14 <- *set (p6) br.cond.spnt.few 1b // yes -> retry #ifdef CONFIG_SMP - st4.rel [r31]=r0 // release the lock + // __ticket_spin_unlock(r31) + st2.rel [r31]=r20 + mov r20=0 // i must not leak kernel bits... #endif SSM_PSR_I(p0, p9, r31) ;; @@ -512,7 +523,8 @@ EX(.fail_efault, (p15) st8 [r34]=r3) .sig_pending: #ifdef CONFIG_SMP - st4.rel [r31]=r0 // release the lock + // __ticket_spin_unlock(r31) + st2.rel [r31]=r20 // release the lock #endif SSM_PSR_I(p0, p9, r17) ;; diff --git a/arch/m32r/include/asm/elf.h b/arch/m32r/include/asm/elf.h index 2f85412ef730..b8da7d0574d2 100644 --- a/arch/m32r/include/asm/elf.h +++ b/arch/m32r/include/asm/elf.h @@ -82,9 +82,9 @@ typedef elf_fpreg_t elf_fpregset_t; * These are used to set parameters in the core dumps. */ #define ELF_CLASS ELFCLASS32 -#if defined(__LITTLE_ENDIAN) +#if defined(__LITTLE_ENDIAN__) #define ELF_DATA ELFDATA2LSB -#elif defined(__BIG_ENDIAN) +#elif defined(__BIG_ENDIAN__) #define ELF_DATA ELFDATA2MSB #else #error no endian defined diff --git a/arch/m32r/include/asm/signal.h b/arch/m32r/include/asm/signal.h index 9c1acb2b1a92..b2eeb0de1c8d 100644 --- a/arch/m32r/include/asm/signal.h +++ b/arch/m32r/include/asm/signal.h @@ -157,7 +157,6 @@ typedef struct sigaltstack { #undef __HAVE_ARCH_SIG_BITOPS struct pt_regs; -extern int do_signal(struct pt_regs *regs, sigset_t *oldset); #define ptrace_signal_deliver(regs, cookie) do { } while (0) diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h index 76125777483c..c70545689da8 100644 --- a/arch/m32r/include/asm/unistd.h +++ b/arch/m32r/include/asm/unistd.h @@ -351,6 +351,7 @@ #define __ARCH_WANT_SYS_OLD_GETRLIMIT /*will be unused*/ #define __ARCH_WANT_SYS_OLDUMOUNT #define __ARCH_WANT_SYS_RT_SIGACTION +#define __ARCH_WANT_SYS_RT_SIGSUSPEND #define __IGNORE_lchown #define __IGNORE_setuid diff --git a/arch/m32r/kernel/.gitignore b/arch/m32r/kernel/.gitignore new file mode 100644 index 000000000000..c5f676c3c224 --- /dev/null +++ b/arch/m32r/kernel/.gitignore @@ -0,0 +1 @@ +vmlinux.lds diff --git a/arch/m32r/kernel/entry.S b/arch/m32r/kernel/entry.S index 403869833b98..225412bc227e 100644 --- a/arch/m32r/kernel/entry.S +++ b/arch/m32r/kernel/entry.S @@ -235,10 +235,9 @@ work_resched: work_notifysig: ; deal with pending signals and ; notify-resume requests mv r0, sp ; arg1 : struct pt_regs *regs - ldi r1, #0 ; arg2 : sigset_t *oldset - mv r2, r9 ; arg3 : __u32 thread_info_flags + mv r1, r9 ; arg2 : __u32 thread_info_flags bl do_notify_resume - bra restore_all + bra resume_userspace ; perform syscall exit tracing ALIGN diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c index e555091eb97c..0021ade4cba8 100644 --- a/arch/m32r/kernel/ptrace.c +++ b/arch/m32r/kernel/ptrace.c @@ -592,16 +592,17 @@ void user_enable_single_step(struct task_struct *child) if (access_process_vm(child, pc&~3, &insn, sizeof(insn), 0) != sizeof(insn)) - break; + return -EIO; compute_next_pc(insn, pc, &next_pc, child); if (next_pc & 0x80000000) - break; + return -EIO; if (embed_debug_trap(child, next_pc)) - break; + return -EIO; invalidate_cache(); + return 0; } void user_disable_single_step(struct task_struct *child) diff --git a/arch/m32r/kernel/signal.c b/arch/m32r/kernel/signal.c index 144b0f124fc7..a08697f0886d 100644 --- a/arch/m32r/kernel/signal.c +++ b/arch/m32r/kernel/signal.c @@ -30,35 +30,6 @@ #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) -int do_signal(struct pt_regs *, sigset_t *); - -asmlinkage int -sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, - unsigned long r2, unsigned long r3, unsigned long r4, - unsigned long r5, unsigned long r6, struct pt_regs *regs) -{ - sigset_t newset; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - - if (copy_from_user(&newset, unewset, sizeof(newset))) - return -EFAULT; - sigdelsetmask(&newset, sigmask(SIGKILL)|sigmask(SIGSTOP)); - - spin_lock_irq(¤t->sighand->siglock); - current->saved_sigmask = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - current->state = TASK_INTERRUPTIBLE; - schedule(); - set_thread_flag(TIF_RESTORE_SIGMASK); - return -ERESTARTNOHAND; -} - asmlinkage int sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, unsigned long r2, unsigned long r3, unsigned long r4, @@ -218,7 +189,7 @@ get_sigframe(struct k_sigaction *ka, unsigned long sp, size_t frame_size) return (void __user *)((sp - frame_size) & -8ul); } -static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, +static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe __user *frame; @@ -275,22 +246,34 @@ static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, current->comm, current->pid, frame, regs->pc); #endif - return; + return 0; give_sigsegv: force_sigsegv(sig, current); + return -EFAULT; +} + +static int prev_insn(struct pt_regs *regs) +{ + u16 inst; + if (get_user(inst, (u16 __user *)(regs->bpc - 2))) + return -EFAULT; + if ((inst & 0xfff0) == 0x10f0) /* trap ? */ + regs->bpc -= 2; + else + regs->bpc -= 4; + regs->syscall_nr = -1; + return 0; } /* * OK, we're invoking a handler */ -static void +static int handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { - unsigned short inst; - /* Are we from a system call? */ if (regs->syscall_nr >= 0) { /* If so, check system call restarting.. */ @@ -308,16 +291,14 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, /* fallthrough */ case -ERESTARTNOINTR: regs->r0 = regs->orig_r0; - inst = *(unsigned short *)(regs->bpc - 2); - if ((inst & 0xfff0) == 0x10f0) /* trap ? */ - regs->bpc -= 2; - else - regs->bpc -= 4; + if (prev_insn(regs) < 0) + return -EFAULT; } } /* Set up the stack frame */ - setup_rt_frame(sig, ka, info, oldset, regs); + if (setup_rt_frame(sig, ka, info, oldset, regs)) + return -EFAULT; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); @@ -325,6 +306,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigaddset(¤t->blocked,sig); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + return 0; } /* @@ -332,12 +314,12 @@ handle_signal(unsigned long sig, struct k_sigaction *ka, siginfo_t *info, * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -int do_signal(struct pt_regs *regs, sigset_t *oldset) +static void do_signal(struct pt_regs *regs) { siginfo_t info; int signr; struct k_sigaction ka; - unsigned short inst; + sigset_t *oldset; /* * We want the common case to go fast, which @@ -346,12 +328,14 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) * if so. */ if (!user_mode(regs)) - return 1; + return; if (try_to_freeze()) goto no_signal; - if (!oldset) + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + oldset = ¤t->saved_sigmask; + else oldset = ¤t->blocked; signr = get_signal_to_deliver(&info, &ka, regs, NULL); @@ -363,8 +347,10 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) */ /* Whee! Actually deliver the signal. */ - handle_signal(signr, &ka, &info, oldset, regs); - return 1; + if (handle_signal(signr, &ka, &info, oldset, regs) == 0) + clear_thread_flag(TIF_RESTORE_SIGMASK); + + return; } no_signal: @@ -375,31 +361,24 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset) regs->r0 == -ERESTARTSYS || regs->r0 == -ERESTARTNOINTR) { regs->r0 = regs->orig_r0; - inst = *(unsigned short *)(regs->bpc - 2); - if ((inst & 0xfff0) == 0x10f0) /* trap ? */ - regs->bpc -= 2; - else - regs->bpc -= 4; - } - if (regs->r0 == -ERESTART_RESTARTBLOCK){ + prev_insn(regs); + } else if (regs->r0 == -ERESTART_RESTARTBLOCK){ regs->r0 = regs->orig_r0; regs->r7 = __NR_restart_syscall; - inst = *(unsigned short *)(regs->bpc - 2); - if ((inst & 0xfff0) == 0x10f0) /* trap ? */ - regs->bpc -= 2; - else - regs->bpc -= 4; + prev_insn(regs); } } - return 0; + if (test_thread_flag(TIF_RESTORE_SIGMASK)) { + clear_thread_flag(TIF_RESTORE_SIGMASK); + sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + } } /* * notification of userspace execution resumption * - triggered by current->work.notify_resume */ -void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, - __u32 thread_info_flags) +void do_notify_resume(struct pt_regs *regs, __u32 thread_info_flags) { /* Pending single-step? */ if (thread_info_flags & _TIF_SINGLESTEP) @@ -407,7 +386,7 @@ void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, /* deal with pending signal delivery */ if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs,oldset); + do_signal(regs); if (thread_info_flags & _TIF_NOTIFY_RESUME) { clear_thread_flag(TIF_NOTIFY_RESUME); diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 60b15d0aa072..b43b36beafe3 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -340,10 +340,13 @@ #define __NR_set_thread_area 334 #define __NR_atomic_cmpxchg_32 335 #define __NR_atomic_barrier 336 +#define __NR_fanotify_init 337 +#define __NR_fanotify_mark 338 +#define __NR_prlimit64 339 #ifdef __KERNEL__ -#define NR_syscalls 337 +#define NR_syscalls 340 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 2391bdff0996..6360c437dcf5 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -765,4 +765,7 @@ sys_call_table: .long sys_set_thread_area .long sys_atomic_cmpxchg_32 /* 335 */ .long sys_atomic_barrier + .long sys_fanotify_init + .long sys_fanotify_mark + .long sys_prlimit64 diff --git a/arch/m68k/mac/macboing.c b/arch/m68k/mac/macboing.c index 8f0640847ad2..05285d08e547 100644 --- a/arch/m68k/mac/macboing.c +++ b/arch/m68k/mac/macboing.c @@ -162,7 +162,7 @@ static void mac_init_asc( void ) void mac_mksound( unsigned int freq, unsigned int length ) { __u32 cfreq = ( freq << 5 ) / 468; - __u32 flags; + unsigned long flags; int i; if ( mac_special_bell == NULL ) @@ -224,7 +224,7 @@ static void mac_nosound( unsigned long ignored ) */ static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsigned int volume ) { - __u32 flags; + unsigned long flags; /* if the bell is already ringing, ring longer */ if ( mac_bell_duration > 0 ) @@ -271,7 +271,7 @@ static void mac_quadra_start_bell( unsigned int freq, unsigned int length, unsig static void mac_quadra_ring_bell( unsigned long ignored ) { int i, count = mac_asc_samplespersec / HZ; - __u32 flags; + unsigned long flags; /* * we neither want a sound buffer overflow nor underflow, so we need to match diff --git a/arch/m68knommu/kernel/syscalltable.S b/arch/m68knommu/kernel/syscalltable.S index b30b3eb197a5..79b1ed198c07 100644 --- a/arch/m68knommu/kernel/syscalltable.S +++ b/arch/m68knommu/kernel/syscalltable.S @@ -355,6 +355,9 @@ ENTRY(sys_call_table) .long sys_set_thread_area .long sys_atomic_cmpxchg_32 /* 335 */ .long sys_atomic_barrier + .long sys_fanotify_init + .long sys_fanotify_mark + .long sys_prlimit64 .rept NR_syscalls-(.-sys_call_table)/4 .long sys_ni_syscall diff --git a/arch/m68knommu/kernel/vmlinux.lds.S b/arch/m68knommu/kernel/vmlinux.lds.S index a91b2713451d..ef332136f96d 100644 --- a/arch/m68knommu/kernel/vmlinux.lds.S +++ b/arch/m68knommu/kernel/vmlinux.lds.S @@ -150,6 +150,8 @@ SECTIONS { _sdata = . ; DATA_DATA CACHELINE_ALIGNED_DATA(32) + PAGE_ALIGNED_DATA(PAGE_SIZE) + *(.data..shared_aligned) INIT_TASK_DATA(THREAD_SIZE) _edata = . ; } > DATA diff --git a/arch/mips/Kbuild b/arch/mips/Kbuild index e322d65f33a4..7dd65cfae837 100644 --- a/arch/mips/Kbuild +++ b/arch/mips/Kbuild @@ -7,6 +7,10 @@ subdir-ccflags-y := -Werror include arch/mips/Kbuild.platforms obj-y := $(platform-y) +# make clean traverses $(obj-) without having included .config, so +# everything ends up here +obj- := $(platform-) + # mips object files # The object files are linked as core-y files would be linked diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 3ad59dde4852..4c9f402295dd 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -13,6 +13,7 @@ config MIPS select HAVE_KPROBES select HAVE_KRETPROBES select RTC_LIB if !MACH_LOONGSON + select GENERIC_ATOMIC64 if !64BIT mainmenu "Linux/MIPS Kernel Configuration" @@ -880,11 +881,15 @@ config NO_IOPORT config GENERIC_ISA_DMA bool select ZONE_DMA if GENERIC_ISA_DMA_SUPPORT_BROKEN=n + select ISA_DMA_API config GENERIC_ISA_DMA_SUPPORT_BROKEN bool select GENERIC_ISA_DMA +config ISA_DMA_API + bool + config GENERIC_GPIO bool @@ -1646,8 +1651,16 @@ config MIPS_MT_SMP select SYS_SUPPORTS_SMP select SMP_UP help - This is a kernel model which is also known a VSMP or lately - has been marketesed into SMVP. + This is a kernel model which is known a VSMP but lately has been + marketesed into SMVP. + Virtual SMP uses the processor's VPEs to implement virtual + processors. In currently available configuration of the 34K processor + this allows for a dual processor. Both processors will share the same + primary caches; each will obtain the half of the TLB for it's own + exclusive use. For a layman this model can be described as similar to + what Intel calls Hyperthreading. + + For further information see http://www.linux-mips.org/wiki/34K#VSMP config MIPS_MT_SMTC bool "SMTC: Use all TCs on all VPEs for SMP" @@ -1664,6 +1677,14 @@ config MIPS_MT_SMTC help This is a kernel model which is known a SMTC or lately has been marketesed into SMVP. + is presenting the available TC's of the core as processors to Linux. + On currently available 34K processors this means a Linux system will + see up to 5 processors. The implementation of the SMTC kernel differs + significantly from VSMP and cannot efficiently coexist in the same + kernel binary so the choice between VSMP and SMTC is a compile time + decision. + + For further information see http://www.linux-mips.org/wiki/34K#SMTC endchoice diff --git a/arch/mips/alchemy/common/prom.c b/arch/mips/alchemy/common/prom.c index c29511b11d44..534021059629 100644 --- a/arch/mips/alchemy/common/prom.c +++ b/arch/mips/alchemy/common/prom.c @@ -43,7 +43,7 @@ int prom_argc; char **prom_argv; char **prom_envp; -void prom_init_cmdline(void) +void __init prom_init_cmdline(void) { int i; @@ -104,7 +104,7 @@ static inline void str2eaddr(unsigned char *ea, unsigned char *str) } } -int prom_get_ethernet_addr(char *ethernet_addr) +int __init prom_get_ethernet_addr(char *ethernet_addr) { char *ethaddr_str; @@ -123,7 +123,6 @@ int prom_get_ethernet_addr(char *ethernet_addr) return 0; } -EXPORT_SYMBOL(prom_get_ethernet_addr); void __init prom_free_prom_memory(void) { diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile index ed9bb709c9a3..5042d51b0512 100644 --- a/arch/mips/boot/compressed/Makefile +++ b/arch/mips/boot/compressed/Makefile @@ -59,7 +59,7 @@ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE hostprogs-y := calc_vmlinuz_load_addr VMLINUZ_LOAD_ADDRESS = $(shell $(obj)/calc_vmlinuz_load_addr \ - $(objtree)/$(KBUILD_IMAGE) $(VMLINUX_LOAD_ADDRESS)) + $(obj)/vmlinux.bin $(VMLINUX_LOAD_ADDRESS)) vmlinuzobjs-y += $(obj)/piggy.o @@ -105,4 +105,4 @@ OBJCOPYFLAGS_vmlinuz.srec := $(OBJCOPYFLAGS) -S -O srec vmlinuz.srec: vmlinuz $(call cmd,objcopy) -clean-files := $(objtree)/vmlinuz.* +clean-files := $(objtree)/vmlinuz $(objtree)/vmlinuz.{32,ecoff,bin,srec} diff --git a/arch/mips/cavium-octeon/Kconfig b/arch/mips/cavium-octeon/Kconfig index 094c17e38e16..47323ca452dc 100644 --- a/arch/mips/cavium-octeon/Kconfig +++ b/arch/mips/cavium-octeon/Kconfig @@ -83,3 +83,7 @@ config ARCH_SPARSEMEM_ENABLE def_bool y select SPARSEMEM_STATIC depends on CPU_CAVIUM_OCTEON + +config CAVIUM_OCTEON_HELPER + def_bool y + depends on OCTEON_ETHERNET || PCI diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c index c664c8cc2b42..a5b427909b5c 100644 --- a/arch/mips/cavium-octeon/cpu.c +++ b/arch/mips/cavium-octeon/cpu.c @@ -41,7 +41,7 @@ static int cnmips_cu2_call(struct notifier_block *nfb, unsigned long action, return NOTIFY_OK; /* Let default notifier send signals */ } -static int cnmips_cu2_setup(void) +static int __init cnmips_cu2_setup(void) { return cu2_notifier(cnmips_cu2_call, 0); } diff --git a/arch/mips/cavium-octeon/executive/Makefile b/arch/mips/cavium-octeon/executive/Makefile index 2fd66db6939e..7f41c5be2190 100644 --- a/arch/mips/cavium-octeon/executive/Makefile +++ b/arch/mips/cavium-octeon/executive/Makefile @@ -11,4 +11,4 @@ obj-y += cvmx-bootmem.o cvmx-l2c.o cvmx-sysinfo.o octeon-model.o -obj-$(CONFIG_PCI) += cvmx-helper-errata.o cvmx-helper-jtag.o +obj-$(CONFIG_CAVIUM_OCTEON_HELPER) += cvmx-helper-errata.o cvmx-helper-jtag.o diff --git a/arch/mips/dec/Platform b/arch/mips/dec/Platform index 3adbcbd95db1..cf55a6f4e720 100644 --- a/arch/mips/dec/Platform +++ b/arch/mips/dec/Platform @@ -1,7 +1,7 @@ # # DECstation family # -platform-$(CONFIG_MACH_DECSTATION) = dec/ +platform-$(CONFIG_MACH_DECSTATION) += dec/ cflags-$(CONFIG_MACH_DECSTATION) += \ -I$(srctree)/arch/mips/include/asm/mach-dec libs-$(CONFIG_MACH_DECSTATION) += arch/mips/dec/prom/ diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index c63c56bfd184..47d87da379f9 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -782,6 +782,10 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u) */ #define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0) +#else /* !CONFIG_64BIT */ + +#include <asm-generic/atomic64.h> + #endif /* CONFIG_64BIT */ /* diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 613f6912dfc1..dbc51065df5b 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -145,7 +145,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = (struct pt_regs *) ((unsigned long) current_thread_info() + THREAD_SIZE - 32) - 1; diff --git a/arch/mips/include/asm/cop2.h b/arch/mips/include/asm/cop2.h index 2cb2f0c2c4f8..3532e2c5f098 100644 --- a/arch/mips/include/asm/cop2.h +++ b/arch/mips/include/asm/cop2.h @@ -24,7 +24,7 @@ extern int cu2_notifier_call_chain(unsigned long val, void *v); #define cu2_notifier(fn, pri) \ ({ \ - static struct notifier_block fn##_nb __cpuinitdata = { \ + static struct notifier_block fn##_nb = { \ .notifier_call = fn, \ .priority = pri \ }; \ diff --git a/arch/mips/include/asm/fcntl.h b/arch/mips/include/asm/fcntl.h index e482fe90fe88..75eddedcfc3e 100644 --- a/arch/mips/include/asm/fcntl.h +++ b/arch/mips/include/asm/fcntl.h @@ -56,6 +56,7 @@ */ #ifdef CONFIG_32BIT +#include <linux/types.h> struct flock { short l_type; diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h index 9b9436a4d816..86548da650e7 100644 --- a/arch/mips/include/asm/gic.h +++ b/arch/mips/include/asm/gic.h @@ -321,6 +321,7 @@ struct gic_intrmask_regs { */ struct gic_intr_map { unsigned int cpunum; /* Directed to this CPU */ +#define GIC_UNUSED 0xdead /* Dummy data */ unsigned int pin; /* Directed to this Pin */ unsigned int polarity; /* Polarity : +/- */ unsigned int trigtype; /* Trigger : Edge/Levl */ diff --git a/arch/mips/include/asm/mach-tx49xx/kmalloc.h b/arch/mips/include/asm/mach-tx49xx/kmalloc.h index b74caf65482b..ff9a8b86cb93 100644 --- a/arch/mips/include/asm/mach-tx49xx/kmalloc.h +++ b/arch/mips/include/asm/mach-tx49xx/kmalloc.h @@ -1,6 +1,6 @@ #ifndef __ASM_MACH_TX49XX_KMALLOC_H #define __ASM_MACH_TX49XX_KMALLOC_H -#define ARCH_KMALLOC_MINALIGN L1_CACHE_BYTES +#define ARCH_DMA_MINALIGN L1_CACHE_BYTES #endif /* __ASM_MACH_TX49XX_KMALLOC_H */ diff --git a/arch/mips/include/asm/mips-boards/maltaint.h b/arch/mips/include/asm/mips-boards/maltaint.h index cea872fc6f5c..d11aa02a956a 100644 --- a/arch/mips/include/asm/mips-boards/maltaint.h +++ b/arch/mips/include/asm/mips-boards/maltaint.h @@ -88,9 +88,6 @@ #define GIC_EXT_INTR(x) x -/* Dummy data */ -#define X 0xdead - /* External Interrupts used for IPI */ #define GIC_IPI_EXT_INTR_RESCHED_VPE0 16 #define GIC_IPI_EXT_INTR_CALLFNC_VPE0 17 diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index a16beafcea91..e59cd1ac09c2 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -150,6 +150,20 @@ typedef struct { unsigned long pgprot; } pgprot_t; ((unsigned long)(x) - PAGE_OFFSET + PHYS_OFFSET) #endif #define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET)) + +/* + * RELOC_HIDE was originally added by 6007b903dfe5f1d13e0c711ac2894bdd4a61b1ad + * (lmo) rsp. 8431fd094d625b94d364fe393076ccef88e6ce18 (kernel.org). The + * discussion can be found in lkml posting + * <a2ebde260608230500o3407b108hc03debb9da6e62c@mail.gmail.com> which is + * archived at http://lists.linuxcoding.com/kernel/2006-q3/msg17360.html + * + * It is unclear if the misscompilations mentioned in + * http://lkml.org/lkml/2010/8/8/138 also affect MIPS so we keep this one + * until GCC 3.x has been retired before we can apply + * https://patchwork.linux-mips.org/patch/1541/ + */ + #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) diff --git a/arch/mips/include/asm/siginfo.h b/arch/mips/include/asm/siginfo.h index 96e28f18dad1..1ca64b4d33d9 100644 --- a/arch/mips/include/asm/siginfo.h +++ b/arch/mips/include/asm/siginfo.h @@ -88,6 +88,7 @@ typedef struct siginfo { #ifdef __ARCH_SI_TRAPNO int _trapno; /* TRAP # which caused the signal */ #endif + short _addr_lsb; } _sigfault; /* SIGPOLL, SIGXFSZ (To do ...) */ diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h index 2376f2e06e47..70df9c0d3c5b 100644 --- a/arch/mips/include/asm/thread_info.h +++ b/arch/mips/include/asm/thread_info.h @@ -146,7 +146,8 @@ register struct thread_info *__current_thread_info __asm__("$28"); #define _TIF_LOAD_WATCH (1<<TIF_LOAD_WATCH) /* work to do on interrupt/exception return */ -#define _TIF_WORK_MASK (0x0000ffef & ~_TIF_SECCOMP) +#define _TIF_WORK_MASK (0x0000ffef & \ + ~(_TIF_SECCOMP | _TIF_SYSCALL_AUDIT)) /* work to do on any return to u-space */ #define _TIF_ALLWORK_MASK (0x8000ffff & ~_TIF_SECCOMP) diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index baa318a59c97..550725b881d5 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -356,16 +356,19 @@ #define __NR_perf_event_open (__NR_Linux + 333) #define __NR_accept4 (__NR_Linux + 334) #define __NR_recvmmsg (__NR_Linux + 335) +#define __NR_fanotify_init (__NR_Linux + 336) +#define __NR_fanotify_mark (__NR_Linux + 337) +#define __NR_prlimit64 (__NR_Linux + 338) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 335 +#define __NR_Linux_syscalls 338 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 335 +#define __NR_O32_Linux_syscalls 338 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -668,16 +671,19 @@ #define __NR_perf_event_open (__NR_Linux + 292) #define __NR_accept4 (__NR_Linux + 293) #define __NR_recvmmsg (__NR_Linux + 294) +#define __NR_fanotify_init (__NR_Linux + 295) +#define __NR_fanotify_mark (__NR_Linux + 296) +#define __NR_prlimit64 (__NR_Linux + 297) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 294 +#define __NR_Linux_syscalls 297 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 294 +#define __NR_64_Linux_syscalls 297 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -985,16 +991,19 @@ #define __NR_accept4 (__NR_Linux + 297) #define __NR_recvmmsg (__NR_Linux + 298) #define __NR_getdents64 (__NR_Linux + 299) +#define __NR_fanotify_init (__NR_Linux + 300) +#define __NR_fanotify_mark (__NR_Linux + 301) +#define __NR_prlimit64 (__NR_Linux + 302) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 299 +#define __NR_Linux_syscalls 302 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 299 +#define __NR_N32_Linux_syscalls 302 #ifdef __KERNEL__ diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform index 6a97230e3d05..ba91be9c21ef 100644 --- a/arch/mips/jz4740/Platform +++ b/arch/mips/jz4740/Platform @@ -1,3 +1,3 @@ -core-$(CONFIG_MACH_JZ4740) += arch/mips/jz4740/ +platform-$(CONFIG_MACH_JZ4740) += jz4740/ cflags-$(CONFIG_MACH_JZ4740) += -I$(srctree)/arch/mips/include/asm/mach-jz4740 load-$(CONFIG_MACH_JZ4740) += 0xffffffff80010000 diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index 0176ed015c89..32103cc2a257 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -40,7 +40,6 @@ int __compute_return_epc(struct pt_regs *regs) return -EFAULT; } - regs->regs[0] = 0; switch (insn.i_format.opcode) { /* * jr and jalr are in r_format format. diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c index b181f2f0ea8e..82ba9f62f49e 100644 --- a/arch/mips/kernel/irq-gic.c +++ b/arch/mips/kernel/irq-gic.c @@ -7,7 +7,6 @@ #include <asm/io.h> #include <asm/gic.h> #include <asm/gcmpregs.h> -#include <asm/mips-boards/maltaint.h> #include <asm/irq.h> #include <linux/hardirq.h> #include <asm-generic/bitops/find.h> @@ -131,7 +130,7 @@ static int gic_set_affinity(unsigned int irq, const struct cpumask *cpumask) int i; irq -= _irqbase; - pr_debug(KERN_DEBUG "%s(%d) called\n", __func__, irq); + pr_debug("%s(%d) called\n", __func__, irq); cpumask_and(&tmp, cpumask, cpu_online_mask); if (cpus_empty(tmp)) return -1; @@ -222,7 +221,7 @@ static void __init gic_basic_init(int numintrs, int numvpes, /* Setup specifics */ for (i = 0; i < mapsize; i++) { cpu = intrmap[i].cpunum; - if (cpu == X) + if (cpu == GIC_UNUSED) continue; if (cpu == 0 && i != 0 && intrmap[i].flags == 0) continue; diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c index 1f4e2fa64140..f4546e97c60d 100644 --- a/arch/mips/kernel/kgdb.c +++ b/arch/mips/kernel/kgdb.c @@ -283,7 +283,7 @@ static int kgdb_mips_notify(struct notifier_block *self, unsigned long cmd, struct pt_regs *regs = args->regs; int trap = (regs->cp0_cause & 0x7c) >> 2; - /* Userpace events, ignore. */ + /* Userspace events, ignore. */ if (user_mode(regs)) return NOTIFY_DONE; diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c index 80e2ba694bab..29811f043399 100644 --- a/arch/mips/kernel/kspd.c +++ b/arch/mips/kernel/kspd.c @@ -251,7 +251,7 @@ void sp_work_handle_request(void) memset(&tz, 0, sizeof(tz)); if ((ret.retval = sp_syscall(__NR_gettimeofday, (int)&tv, (int)&tz, 0, 0)) == 0) - ret.retval = tv.tv_sec; + ret.retval = tv.tv_sec; break; case MTSP_SYSCALL_EXIT: diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index c2dab140dc98..6343b4a5b835 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -341,3 +341,10 @@ asmlinkage long sys32_lookup_dcookie(u32 a0, u32 a1, char __user *buf, { return sys_lookup_dcookie(merge_64(a0, a1), buf, len); } + +SYSCALL_DEFINE6(32_fanotify_mark, int, fanotify_fd, unsigned int, flags, + u64, a3, u64, a4, int, dfd, const char __user *, pathname) +{ + return sys_fanotify_mark(fanotify_fd, flags, merge_64(a3, a4), + dfd, pathname); +} diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index 2340f11dc29c..9a526ba6f257 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -103,7 +103,7 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len, if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) goto out_unlock; - retval = security_task_setscheduler(p, 0, NULL); + retval = security_task_setscheduler(p) if (retval) goto out_unlock; diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index c51b95ff8644..c8777333e198 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -536,7 +536,7 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit) { /* do the secure computing check first */ if (!entryexit) - secure_computing(regs->regs[0]); + secure_computing(regs->regs[2]); if (unlikely(current->audit_context) && entryexit) audit_syscall_exit(AUDITSC_RESULT(regs->regs[2]), @@ -565,7 +565,7 @@ asmlinkage void do_syscall_trace(struct pt_regs *regs, int entryexit) out: if (unlikely(current->audit_context) && !entryexit) - audit_syscall_entry(audit_arch(), regs->regs[0], + audit_syscall_entry(audit_arch(), regs->regs[2], regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); } diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 17202bbe843f..fbaabad0e6e2 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -63,9 +63,9 @@ stack_done: sw t0, PT_R7(sp) # set error flag beqz t0, 1f + lw t1, PT_R2(sp) # syscall number negu v0 # error - sw v0, PT_R0(sp) # set flag for syscall - # restarting + sw t1, PT_R0(sp) # save it for syscall restarting 1: sw v0, PT_R2(sp) # result o32_syscall_exit: @@ -104,9 +104,9 @@ syscall_trace_entry: sw t0, PT_R7(sp) # set error flag beqz t0, 1f + lw t1, PT_R2(sp) # syscall number negu v0 # error - sw v0, PT_R0(sp) # set flag for syscall - # restarting + sw t1, PT_R0(sp) # save it for syscall restarting 1: sw v0, PT_R2(sp) # result j syscall_exit @@ -169,8 +169,7 @@ stackargs: * We probably should handle this case a bit more drastic. */ bad_stack: - negu v0 # error - sw v0, PT_R0(sp) + li v0, EFAULT sw v0, PT_R2(sp) li t0, 1 # set error flag sw t0, PT_R7(sp) @@ -583,7 +582,10 @@ einval: li v0, -ENOSYS sys sys_rt_tgsigqueueinfo 4 sys sys_perf_event_open 5 sys sys_accept4 4 - sys sys_recvmmsg 5 + sys sys_recvmmsg 5 /* 4335 */ + sys sys_fanotify_init 2 + sys sys_fanotify_mark 6 + sys sys_prlimit64 4 .endm /* We pre-compute the number of _instruction_ bytes needed to diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index a8a6c596eb04..3f4179283207 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -66,9 +66,9 @@ NESTED(handle_sys64, PT_SIZE, sp) sd t0, PT_R7(sp) # set error flag beqz t0, 1f + ld t1, PT_R2(sp) # syscall number dnegu v0 # error - sd v0, PT_R0(sp) # set flag for syscall - # restarting + sd t1, PT_R0(sp) # save it for syscall restarting 1: sd v0, PT_R2(sp) # result n64_syscall_exit: @@ -109,8 +109,9 @@ syscall_trace_entry: sd t0, PT_R7(sp) # set error flag beqz t0, 1f + ld t1, PT_R2(sp) # syscall number dnegu v0 # error - sd v0, PT_R0(sp) # set flag for syscall restarting + sd t1, PT_R0(sp) # save it for syscall restarting 1: sd v0, PT_R2(sp) # result j syscall_exit @@ -416,9 +417,12 @@ sys_call_table: PTR sys_pipe2 PTR sys_inotify_init1 PTR sys_preadv - PTR sys_pwritev /* 5390 */ + PTR sys_pwritev /* 5290 */ PTR sys_rt_tgsigqueueinfo PTR sys_perf_event_open PTR sys_accept4 - PTR sys_recvmmsg + PTR sys_recvmmsg + PTR sys_fanotify_init /* 5295 */ + PTR sys_fanotify_mark + PTR sys_prlimit64 .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index a3d66137731a..f08ece6d8acc 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -65,8 +65,9 @@ NESTED(handle_sysn32, PT_SIZE, sp) sd t0, PT_R7(sp) # set error flag beqz t0, 1f + ld t1, PT_R2(sp) # syscall number dnegu v0 # error - sd v0, PT_R0(sp) # set flag for syscall restarting + sd t1, PT_R0(sp) # save it for syscall restarting 1: sd v0, PT_R2(sp) # result local_irq_disable # make sure need_resched and @@ -106,8 +107,9 @@ n32_syscall_trace_entry: sd t0, PT_R7(sp) # set error flag beqz t0, 1f + ld t1, PT_R2(sp) # syscall number dnegu v0 # error - sd v0, PT_R0(sp) # set flag for syscall restarting + sd t1, PT_R0(sp) # save it for syscall restarting 1: sd v0, PT_R2(sp) # result j syscall_exit @@ -320,10 +322,10 @@ EXPORT(sysn32_call_table) PTR sys_cacheflush PTR sys_cachectl PTR sys_sysmips - PTR sys_io_setup /* 6200 */ + PTR compat_sys_io_setup /* 6200 */ PTR sys_io_destroy - PTR sys_io_getevents - PTR sys_io_submit + PTR compat_sys_io_getevents + PTR compat_sys_io_submit PTR sys_io_cancel PTR sys_exit_group /* 6205 */ PTR sys_lookup_dcookie @@ -419,5 +421,8 @@ EXPORT(sysn32_call_table) PTR sys_perf_event_open PTR sys_accept4 PTR compat_sys_recvmmsg - PTR sys_getdents + PTR sys_getdents64 + PTR sys_fanotify_init /* 6300 */ + PTR sys_fanotify_mark + PTR sys_prlimit64 .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 813689ef2384..78d768a3e19d 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -93,8 +93,9 @@ NESTED(handle_sys, PT_SIZE, sp) sd t0, PT_R7(sp) # set error flag beqz t0, 1f + ld t1, PT_R2(sp) # syscall number dnegu v0 # error - sd v0, PT_R0(sp) # flag for syscall restarting + sd t1, PT_R0(sp) # save it for syscall restarting 1: sd v0, PT_R2(sp) # result o32_syscall_exit: @@ -142,8 +143,9 @@ trace_a_syscall: sd t0, PT_R7(sp) # set error flag beqz t0, 1f + ld t1, PT_R2(sp) # syscall number dnegu v0 # error - sd v0, PT_R0(sp) # set flag for syscall restarting + sd t1, PT_R0(sp) # save it for syscall restarting 1: sd v0, PT_R2(sp) # result j syscall_exit @@ -154,8 +156,7 @@ trace_a_syscall: * The stackpointer for a call with more than 4 arguments is bad. */ bad_stack: - dnegu v0 # error - sd v0, PT_R0(sp) + li v0, EFAULT sd v0, PT_R2(sp) li t0, 1 # set error flag sd t0, PT_R7(sp) @@ -444,10 +445,10 @@ sys_call_table: PTR compat_sys_futex PTR compat_sys_sched_setaffinity PTR compat_sys_sched_getaffinity /* 4240 */ - PTR sys_io_setup + PTR compat_sys_io_setup PTR sys_io_destroy - PTR sys_io_getevents - PTR sys_io_submit + PTR compat_sys_io_getevents + PTR compat_sys_io_submit PTR sys_io_cancel /* 4245 */ PTR sys_exit_group PTR sys32_lookup_dcookie @@ -538,5 +539,8 @@ sys_call_table: PTR compat_sys_rt_tgsigqueueinfo PTR sys_perf_event_open PTR sys_accept4 - PTR compat_sys_recvmmsg + PTR compat_sys_recvmmsg /* 4335 */ + PTR sys_fanotify_init + PTR sys_32_fanotify_mark + PTR sys_prlimit64 .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index 2099d5a4c4b7..5922342bca39 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -390,7 +390,6 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs) { struct rt_sigframe __user *frame; sigset_t set; - stack_t st; int sig; frame = (struct rt_sigframe __user *) regs.regs[29]; @@ -411,11 +410,9 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs) else if (sig) force_sig(sig, current); - if (__copy_from_user(&st, &frame->rs_uc.uc_stack, sizeof(st))) - goto badframe; /* It is more difficult to avoid calling this function than to call it and ignore errors. */ - do_sigaltstack((stack_t __user *)&st, NULL, regs.regs[29]); + do_sigaltstack(&frame->rs_uc.uc_stack, NULL, regs.regs[29]); /* * Don't let your children do this ... @@ -550,23 +547,26 @@ static int handle_signal(unsigned long sig, siginfo_t *info, struct mips_abi *abi = current->thread.abi; void *vdso = current->mm->context.vdso; - switch(regs->regs[0]) { - case ERESTART_RESTARTBLOCK: - case ERESTARTNOHAND: - regs->regs[2] = EINTR; - break; - case ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) { + if (regs->regs[0]) { + switch(regs->regs[2]) { + case ERESTART_RESTARTBLOCK: + case ERESTARTNOHAND: regs->regs[2] = EINTR; break; + case ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { + regs->regs[2] = EINTR; + break; + } + /* fallthrough */ + case ERESTARTNOINTR: + regs->regs[7] = regs->regs[26]; + regs->regs[2] = regs->regs[0]; + regs->cp0_epc -= 4; } - /* fallthrough */ - case ERESTARTNOINTR: /* Userland will reload $v0. */ - regs->regs[7] = regs->regs[26]; - regs->cp0_epc -= 8; - } - regs->regs[0] = 0; /* Don't deal with this again. */ + regs->regs[0] = 0; /* Don't deal with this again. */ + } if (sig_uses_siginfo(ka)) ret = abi->setup_rt_frame(vdso + abi->rt_signal_return_offset, @@ -575,6 +575,9 @@ static int handle_signal(unsigned long sig, siginfo_t *info, ret = abi->setup_frame(vdso + abi->signal_return_offset, ka, regs, sig, oldset); + if (ret) + return ret; + spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NODEFER)) @@ -622,17 +625,13 @@ static void do_signal(struct pt_regs *regs) return; } - /* - * Who's code doesn't conform to the restartable syscall convention - * dies here!!! The li instruction, a single machine instruction, - * must directly be followed by the syscall instruction. - */ if (regs->regs[0]) { if (regs->regs[2] == ERESTARTNOHAND || regs->regs[2] == ERESTARTSYS || regs->regs[2] == ERESTARTNOINTR) { + regs->regs[2] = regs->regs[0]; regs->regs[7] = regs->regs[26]; - regs->cp0_epc -= 8; + regs->cp0_epc -= 4; } if (regs->regs[2] == ERESTART_RESTARTBLOCK) { regs->regs[2] = current->thread.abi->restart; diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c index 2c5df818c65a..ee24d814d5b9 100644 --- a/arch/mips/kernel/signal_n32.c +++ b/arch/mips/kernel/signal_n32.c @@ -109,6 +109,7 @@ asmlinkage int sysn32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs) asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) { struct rt_sigframe_n32 __user *frame; + mm_segment_t old_fs; sigset_t set; stack_t st; s32 sp; @@ -143,7 +144,11 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs) /* It is more difficult to avoid calling this function than to call it and ignore errors. */ + old_fs = get_fs(); + set_fs(KERNEL_DS); do_sigaltstack((stack_t __user *)&st, NULL, regs.regs[29]); + set_fs(old_fs); + /* * Don't let your children do this ... diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 69b039ca8d83..33d5a5ce4a29 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -109,8 +109,6 @@ static void emulate_load_store_insn(struct pt_regs *regs, unsigned long value; unsigned int res; - regs->regs[0] = 0; - /* * This load never faults. */ diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index 7ba890860d98..469d4019f795 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -44,27 +44,39 @@ static inline int cpu_is_noncoherent_r10000(struct device *dev) static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp) { + gfp_t dma_flag; + /* ignore region specifiers */ gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM); -#ifdef CONFIG_ZONE_DMA +#ifdef CONFIG_ISA if (dev == NULL) - gfp |= __GFP_DMA; - else if (dev->coherent_dma_mask < DMA_BIT_MASK(24)) - gfp |= __GFP_DMA; + dma_flag = __GFP_DMA; else #endif -#ifdef CONFIG_ZONE_DMA32 +#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA) if (dev->coherent_dma_mask < DMA_BIT_MASK(32)) - gfp |= __GFP_DMA32; + dma_flag = __GFP_DMA; + else if (dev->coherent_dma_mask < DMA_BIT_MASK(64)) + dma_flag = __GFP_DMA32; + else +#endif +#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA) + if (dev->coherent_dma_mask < DMA_BIT_MASK(64)) + dma_flag = __GFP_DMA32; + else +#endif +#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32) + if (dev->coherent_dma_mask < DMA_BIT_MASK(64)) + dma_flag = __GFP_DMA; else #endif - ; + dma_flag = 0; /* Don't invoke OOM killer */ gfp |= __GFP_NORETRY; - return gfp; + return gfp | dma_flag; } void *dma_alloc_noncoherent(struct device *dev, size_t size, diff --git a/arch/mips/mm/sc-rm7k.c b/arch/mips/mm/sc-rm7k.c index 1ef75cd80a0d..274af3be1442 100644 --- a/arch/mips/mm/sc-rm7k.c +++ b/arch/mips/mm/sc-rm7k.c @@ -30,7 +30,7 @@ #define tc_lsize 32 extern unsigned long icache_way_size, dcache_way_size; -unsigned long tcache_size; +static unsigned long tcache_size; #include <asm/r4kcache.h> diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index 15949b0be811..b79b24afe3a2 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -385,6 +385,8 @@ static int __initdata msc_nr_eicirqs = ARRAY_SIZE(msc_eicirqmap); */ #define GIC_CPU_NMI GIC_MAP_TO_NMI_MSK +#define X GIC_UNUSED + static struct gic_intr_map gic_intr_map[GIC_NUM_INTRS] = { { X, X, X, X, 0 }, { X, X, X, X, 0 }, @@ -404,6 +406,7 @@ static struct gic_intr_map gic_intr_map[GIC_NUM_INTRS] = { { X, X, X, X, 0 }, /* The remainder of this table is initialised by fill_ipi_map */ }; +#undef X /* * GCMP needs to be detected before any SMP initialisation diff --git a/arch/mips/pci/pci-rc32434.c b/arch/mips/pci/pci-rc32434.c index 71f7d27b0d4c..f31218e17d3c 100644 --- a/arch/mips/pci/pci-rc32434.c +++ b/arch/mips/pci/pci-rc32434.c @@ -118,7 +118,7 @@ static int __init rc32434_pcibridge_init(void) if (!((pcicvalue == PCIM_H_EA) || (pcicvalue == PCIM_H_IA_FIX) || (pcicvalue == PCIM_H_IA_RR))) { - pr_err(KERN_ERR "PCI init error!!!\n"); + pr_err("PCI init error!!!\n"); /* Not in Host Mode, return ERROR */ return -1; } diff --git a/arch/mips/pnx8550/common/reset.c b/arch/mips/pnx8550/common/reset.c index fadd8744a6bc..e7a12ff304b9 100644 --- a/arch/mips/pnx8550/common/reset.c +++ b/arch/mips/pnx8550/common/reset.c @@ -22,29 +22,19 @@ */ #include <linux/kernel.h> +#include <asm/processor.h> #include <asm/reboot.h> #include <glb.h> void pnx8550_machine_restart(char *command) { - char head[] = "************* Machine restart *************"; - char foot[] = "*******************************************"; - - printk("\n\n"); - printk("%s\n", head); - if (command != NULL) - printk("* %s\n", command); - printk("%s\n", foot); - PNX8550_RST_CTL = PNX8550_RST_DO_SW_RST; } void pnx8550_machine_halt(void) { - printk("*** Machine halt. (Not implemented) ***\n"); -} - -void pnx8550_machine_power_off(void) -{ - printk("*** Machine power off. (Not implemented) ***\n"); + while (1) { + if (cpu_wait) + cpu_wait(); + } } diff --git a/arch/mips/pnx8550/common/setup.c b/arch/mips/pnx8550/common/setup.c index 64246c9c875c..43cb3945fdbf 100644 --- a/arch/mips/pnx8550/common/setup.c +++ b/arch/mips/pnx8550/common/setup.c @@ -44,7 +44,6 @@ extern void __init board_setup(void); extern void pnx8550_machine_restart(char *); extern void pnx8550_machine_halt(void); -extern void pnx8550_machine_power_off(void); extern struct resource ioport_resource; extern struct resource iomem_resource; extern char *prom_getcmdline(void); @@ -100,7 +99,7 @@ void __init plat_mem_setup(void) _machine_restart = pnx8550_machine_restart; _machine_halt = pnx8550_machine_halt; - pm_power_off = pnx8550_machine_power_off; + pm_power_off = pnx8550_machine_halt; /* Clear the Global 2 Register, PCI Inta Output Enable Registers Bit 1:Enable DAC Powerdown diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig index 444b9f918fdf..7c2a2f7f8dc1 100644 --- a/arch/mn10300/Kconfig +++ b/arch/mn10300/Kconfig @@ -8,7 +8,6 @@ mainmenu "Linux Kernel Configuration" config MN10300 def_bool y select HAVE_OPROFILE - select HAVE_ARCH_TRACEHOOK config AM33 def_bool y diff --git a/arch/mn10300/Kconfig.debug b/arch/mn10300/Kconfig.debug index ff80e86b9bd2..ce83c74b3fd7 100644 --- a/arch/mn10300/Kconfig.debug +++ b/arch/mn10300/Kconfig.debug @@ -101,7 +101,7 @@ config GDBSTUB_DEBUG_BREAKPOINT choice prompt "GDB stub port" - default GDBSTUB_TTYSM0 + default GDBSTUB_ON_TTYSM0 depends on GDBSTUB help Select the serial port used for GDB-stub. diff --git a/arch/mn10300/include/asm/bitops.h b/arch/mn10300/include/asm/bitops.h index f49ac49e09ad..3f50e9661076 100644 --- a/arch/mn10300/include/asm/bitops.h +++ b/arch/mn10300/include/asm/bitops.h @@ -229,9 +229,9 @@ int ffs(int x) #include <asm-generic/bitops/hweight.h> #define ext2_set_bit_atomic(lock, nr, addr) \ - test_and_set_bit((nr) ^ 0x18, (addr)) + test_and_set_bit((nr), (addr)) #define ext2_clear_bit_atomic(lock, nr, addr) \ - test_and_clear_bit((nr) ^ 0x18, (addr)) + test_and_clear_bit((nr), (addr)) #include <asm-generic/bitops/ext2-non-atomic.h> #include <asm-generic/bitops/minix-le.h> diff --git a/arch/mn10300/include/asm/signal.h b/arch/mn10300/include/asm/signal.h index 7e891fce2370..1865d72a86ff 100644 --- a/arch/mn10300/include/asm/signal.h +++ b/arch/mn10300/include/asm/signal.h @@ -78,7 +78,7 @@ typedef unsigned long sigset_t; /* These should not be considered constants from userland. */ #define SIGRTMIN 32 -#define SIGRTMAX (_NSIG-1) +#define SIGRTMAX _NSIG /* * SA_FLAGS values: diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c index 9d49073e827a..db509dd80565 100644 --- a/arch/mn10300/kernel/mn10300-serial.c +++ b/arch/mn10300/kernel/mn10300-serial.c @@ -156,17 +156,17 @@ struct mn10300_serial_port mn10300_serial_port_sif0 = { ._intr = &SC0ICR, ._rxb = &SC0RXB, ._txb = &SC0TXB, - .rx_name = "ttySM0/Rx", - .tx_name = "ttySM0/Tx", + .rx_name = "ttySM0:Rx", + .tx_name = "ttySM0:Tx", #ifdef CONFIG_MN10300_TTYSM0_TIMER8 - .tm_name = "ttySM0/Timer8", + .tm_name = "ttySM0:Timer8", ._tmxmd = &TM8MD, ._tmxbr = &TM8BR, ._tmicr = &TM8ICR, .tm_irq = TM8IRQ, .div_timer = MNSCx_DIV_TIMER_16BIT, #else /* CONFIG_MN10300_TTYSM0_TIMER2 */ - .tm_name = "ttySM0/Timer2", + .tm_name = "ttySM0:Timer2", ._tmxmd = &TM2MD, ._tmxbr = (volatile u16 *) &TM2BR, ._tmicr = &TM2ICR, @@ -209,17 +209,17 @@ struct mn10300_serial_port mn10300_serial_port_sif1 = { ._intr = &SC1ICR, ._rxb = &SC1RXB, ._txb = &SC1TXB, - .rx_name = "ttySM1/Rx", - .tx_name = "ttySM1/Tx", + .rx_name = "ttySM1:Rx", + .tx_name = "ttySM1:Tx", #ifdef CONFIG_MN10300_TTYSM1_TIMER9 - .tm_name = "ttySM1/Timer9", + .tm_name = "ttySM1:Timer9", ._tmxmd = &TM9MD, ._tmxbr = &TM9BR, ._tmicr = &TM9ICR, .tm_irq = TM9IRQ, .div_timer = MNSCx_DIV_TIMER_16BIT, #else /* CONFIG_MN10300_TTYSM1_TIMER3 */ - .tm_name = "ttySM1/Timer3", + .tm_name = "ttySM1:Timer3", ._tmxmd = &TM3MD, ._tmxbr = (volatile u16 *) &TM3BR, ._tmicr = &TM3ICR, @@ -260,9 +260,9 @@ struct mn10300_serial_port mn10300_serial_port_sif2 = { .uart.lock = __SPIN_LOCK_UNLOCKED(mn10300_serial_port_sif2.uart.lock), .name = "ttySM2", - .rx_name = "ttySM2/Rx", - .tx_name = "ttySM2/Tx", - .tm_name = "ttySM2/Timer10", + .rx_name = "ttySM2:Rx", + .tx_name = "ttySM2:Tx", + .tm_name = "ttySM2:Timer10", ._iobase = &SC2CTR, ._control = &SC2CTR, ._status = &SC2STR, diff --git a/arch/mn10300/kernel/module.c b/arch/mn10300/kernel/module.c index 6aea7fd76993..196a111e2e29 100644 --- a/arch/mn10300/kernel/module.c +++ b/arch/mn10300/kernel/module.c @@ -206,7 +206,7 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - return module_bug_finalize(hdr, sechdrs, me); + return 0; } /* @@ -214,5 +214,4 @@ int module_finalize(const Elf_Ehdr *hdr, */ void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c index 717db14c2cc3..d4de05ab7864 100644 --- a/arch/mn10300/kernel/signal.c +++ b/arch/mn10300/kernel/signal.c @@ -65,10 +65,10 @@ asmlinkage long sys_sigaction(int sig, old_sigset_t mask; if (verify_area(VERIFY_READ, act, sizeof(*act)) || __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer) || + __get_user(new_ka.sa.sa_flags, &act->sa_flags) || + __get_user(mask, &act->sa_mask)) return -EFAULT; - __get_user(new_ka.sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); siginitset(&new_ka.sa.sa_mask, mask); } @@ -77,10 +77,10 @@ asmlinkage long sys_sigaction(int sig, if (!ret && oact) { if (verify_area(VERIFY_WRITE, oact, sizeof(*oact)) || __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer) || + __put_user(old_ka.sa.sa_flags, &oact->sa_flags) || + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask)) return -EFAULT; - __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); } return ret; @@ -102,6 +102,9 @@ static int restore_sigcontext(struct pt_regs *regs, { unsigned int err = 0; + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + if (is_using_fpu(current)) fpu_kill_state(current); @@ -330,8 +333,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, regs->d0 = sig; regs->d1 = (unsigned long) &frame->sc; - set_fs(USER_DS); - /* the tracer may want to single-step inside the handler */ if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); @@ -345,7 +346,7 @@ static int setup_frame(int sig, struct k_sigaction *ka, sigset_t *set, return 0; give_sigsegv: - force_sig(SIGSEGV, current); + force_sigsegv(sig, current); return -EFAULT; } @@ -413,8 +414,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->d0 = sig; regs->d1 = (long) &frame->info; - set_fs(USER_DS); - /* the tracer may want to single-step inside the handler */ if (test_thread_flag(TIF_SINGLESTEP)) ptrace_notify(SIGTRAP); @@ -428,10 +427,16 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, return 0; give_sigsegv: - force_sig(SIGSEGV, current); + force_sigsegv(sig, current); return -EFAULT; } +static inline void stepback(struct pt_regs *regs) +{ + regs->pc -= 2; + regs->orig_d0 = -1; +} + /* * handle the actual delivery of a signal to userspace */ @@ -459,7 +464,7 @@ static int handle_signal(int sig, /* fallthrough */ case -ERESTARTNOINTR: regs->d0 = regs->orig_d0; - regs->pc -= 2; + stepback(regs); } } @@ -527,12 +532,12 @@ static void do_signal(struct pt_regs *regs) case -ERESTARTSYS: case -ERESTARTNOINTR: regs->d0 = regs->orig_d0; - regs->pc -= 2; + stepback(regs); break; case -ERESTART_RESTARTBLOCK: regs->d0 = __NR_restart_syscall; - regs->pc -= 2; + stepback(regs); break; } } diff --git a/arch/mn10300/mm/Makefile b/arch/mn10300/mm/Makefile index 28b9d983db0c..1557277fbc5c 100644 --- a/arch/mn10300/mm/Makefile +++ b/arch/mn10300/mm/Makefile @@ -2,13 +2,11 @@ # Makefile for the MN10300-specific memory management code # +cacheflush-y := cache.o cache-mn10300.o +cacheflush-$(CONFIG_MN10300_CACHE_WBACK) += cache-flush-mn10300.o + +cacheflush-$(CONFIG_MN10300_CACHE_DISABLED) := cache-disabled.o + obj-y := \ init.o fault.o pgtable.o extable.o tlb-mn10300.o mmu-context.o \ - misalignment.o dma-alloc.o - -ifneq ($(CONFIG_MN10300_CACHE_DISABLED),y) -obj-y += cache.o cache-mn10300.o -ifeq ($(CONFIG_MN10300_CACHE_WBACK),y) -obj-y += cache-flush-mn10300.o -endif -endif + misalignment.o dma-alloc.o $(cacheflush-y) diff --git a/arch/frv/lib/perf_event.c b/arch/mn10300/mm/cache-disabled.c index 9ac5acfd2e91..f669ea42aba6 100644 --- a/arch/frv/lib/perf_event.c +++ b/arch/mn10300/mm/cache-disabled.c @@ -1,6 +1,6 @@ -/* Performance event handling +/* Handle the cache being disabled * - * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2010 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or @@ -8,12 +8,14 @@ * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. */ - -#include <linux/perf_event.h> +#include <linux/mm.h> /* - * mark the performance event as pending + * allow userspace to flush the instruction cache */ -void set_perf_event_pending(void) +asmlinkage long sys_cacheflush(unsigned long start, unsigned long end) { + if (end < start) + return -EINVAL; + return 0; } diff --git a/arch/mn10300/mm/cache.c b/arch/mn10300/mm/cache.c index 1b76719ec1c3..9261217e8d2c 100644 --- a/arch/mn10300/mm/cache.c +++ b/arch/mn10300/mm/cache.c @@ -54,13 +54,30 @@ EXPORT_SYMBOL(flush_icache_page); void flush_icache_range(unsigned long start, unsigned long end) { #ifdef CONFIG_MN10300_CACHE_WBACK - unsigned long addr, size, off; + unsigned long addr, size, base, off; struct page *page; pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *ppte, pte; + if (end > 0x80000000UL) { + /* addresses above 0xa0000000 do not go through the cache */ + if (end > 0xa0000000UL) { + end = 0xa0000000UL; + if (start >= end) + return; + } + + /* kernel addresses between 0x80000000 and 0x9fffffff do not + * require page tables, so we just map such addresses directly */ + base = (start >= 0x80000000UL) ? start : 0x80000000UL; + mn10300_dcache_flush_range(base, end); + if (base == start) + goto invalidate; + end = base; + } + for (; start < end; start += size) { /* work out how much of the page to flush */ off = start & (PAGE_SIZE - 1); @@ -104,6 +121,7 @@ void flush_icache_range(unsigned long start, unsigned long end) } #endif +invalidate: mn10300_icache_inv(); } EXPORT_SYMBOL(flush_icache_range); diff --git a/arch/mn10300/mm/dma-alloc.c b/arch/mn10300/mm/dma-alloc.c index 4e34880bea03..159acb02cfd4 100644 --- a/arch/mn10300/mm/dma-alloc.c +++ b/arch/mn10300/mm/dma-alloc.c @@ -25,7 +25,8 @@ void *dma_alloc_coherent(struct device *dev, size_t size, unsigned long addr; void *ret; - printk("dma_alloc_coherent(%s,%zu,,%x)\n", dev_name(dev), size, gfp); + pr_debug("dma_alloc_coherent(%s,%zu,%x)\n", + dev ? dev_name(dev) : "?", size, gfp); if (0xbe000000 - pci_sram_allocated >= size) { size = (size + 255) & ~255; diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 907417d187e1..79a04a9394d5 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -16,6 +16,7 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select BUG + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select GENERIC_ATOMIC64 if !64BIT help diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 02b77baa5da6..efa0b60c63fe 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -147,7 +147,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static __inline__ void __user *compat_alloc_user_space(long len) +static __inline__ void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = ¤t->thread.regs; return (void __user *)regs->gr[30]; diff --git a/arch/parisc/include/asm/perf_event.h b/arch/parisc/include/asm/perf_event.h index cc146427d8f9..1e0fd8ba6c03 100644 --- a/arch/parisc/include/asm/perf_event.h +++ b/arch/parisc/include/asm/perf_event.h @@ -1,7 +1,6 @@ #ifndef __ASM_PARISC_PERF_EVENT_H #define __ASM_PARISC_PERF_EVENT_H -/* parisc only supports software events through this interface. */ -static inline void set_perf_event_pending(void) { } +/* Empty, just to avoid compiling error */ #endif /* __ASM_PARISC_PERF_EVENT_H */ diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 159a2b81e90c..6e81bb596e5b 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -941,11 +941,10 @@ int module_finalize(const Elf_Ehdr *hdr, nsyms = newptr - (Elf_Sym *)symhdr->sh_addr; DEBUGP("NEW num_symtab %lu\n", nsyms); symhdr->sh_size = nsyms * sizeof(Elf_Sym); - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { deregister_unwind_table(mod); - module_bug_cleanup(mod); } diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 631e5a0fb6ab..4b1e521d966f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -138,6 +138,7 @@ config PPC select HAVE_OPROFILE select HAVE_SYSCALL_WRAPPERS if PPC64 select GENERIC_ATOMIC64 if PPC32 + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index e3ea151c9597..b7212b619c52 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -164,7 +164,7 @@ drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/ all: zImage # With make 3.82 we cannot mix normal and wildcard targets -BOOT_TARGETS1 := zImage zImage.initrd uImaged +BOOT_TARGETS1 := zImage zImage.initrd uImage BOOT_TARGETS2 := zImage% dtbImage% treeImage.% cuImage.% simpleImage.% PHONY += $(BOOT_TARGETS1) $(BOOT_TARGETS2) diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts index 5806ef0b860b..a30370396250 100644 --- a/arch/powerpc/boot/dts/canyonlands.dts +++ b/arch/powerpc/boot/dts/canyonlands.dts @@ -163,6 +163,14 @@ interrupts = <0x1e 4>; }; + SATA0: sata@bffd1000 { + compatible = "amcc,sata-460ex"; + reg = <4 0xbffd1000 0x800 4 0xbffd0800 0x400>; + interrupt-parent = <&UIC3>; + interrupts = <0x0 0x4 /* SATA */ + 0x5 0x4>; /* AHBDMA */ + }; + POB0: opb { compatible = "ibm,opb-460ex", "ibm,opb"; #address-cells = <1>; diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 396d21a80058..a11d4eac4f97 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -134,7 +134,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current->thread.regs; unsigned long usp = regs->gpr[1]; diff --git a/arch/powerpc/include/asm/fsldma.h b/arch/powerpc/include/asm/fsldma.h index a67aeed17d40..debc5ed96d6e 100644 --- a/arch/powerpc/include/asm/fsldma.h +++ b/arch/powerpc/include/asm/fsldma.h @@ -11,6 +11,7 @@ #ifndef __ARCH_POWERPC_ASM_FSLDMA_H__ #define __ARCH_POWERPC_ASM_FSLDMA_H__ +#include <linux/slab.h> #include <linux/dmaengine.h> /* diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 0e398cfee2c8..acac35d5b382 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -433,7 +433,7 @@ typedef struct { * with. However gcc is not clever enough to compute the * modulus (2^n-1) without a second multiply. */ -#define vsid_scrample(protovsid, size) \ +#define vsid_scramble(protovsid, size) \ ((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size)) #else /* 1 */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 1ff6662f7faf..9b287fdd8ea3 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -129,7 +129,7 @@ struct paca_struct { u8 soft_enabled; /* irq soft-enable flag */ u8 hard_enabled; /* set if irqs are enabled in MSR */ u8 io_sync; /* writel() needs spin_unlock sync */ - u8 perf_event_pending; /* PM interrupt while soft-disabled */ + u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ /* Stuff for accurate time accounting */ u64 user_time; /* accumulated usermode TB ticks */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index d8be016d2ede..ff0005eec7dd 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -951,7 +951,14 @@ #ifdef CONFIG_PPC64 extern void ppc64_runlatch_on(void); -extern void ppc64_runlatch_off(void); +extern void __ppc64_runlatch_off(void); + +#define ppc64_runlatch_off() \ + do { \ + if (cpu_has_feature(CPU_FTR_CTRL) && \ + test_thread_flag(TIF_RUNLATCH)) \ + __ppc64_runlatch_off(); \ + } while (0) extern unsigned long scom970_read(unsigned int address); extern void scom970_write(unsigned int address, unsigned long value); diff --git a/arch/powerpc/include/asm/rwsem.h b/arch/powerpc/include/asm/rwsem.h index 24cd9281ec37..8447d89fbe72 100644 --- a/arch/powerpc/include/asm/rwsem.h +++ b/arch/powerpc/include/asm/rwsem.h @@ -21,15 +21,20 @@ /* * the semaphore definition */ -struct rw_semaphore { - /* XXX this should be able to be an atomic_t -- paulus */ - signed int count; -#define RWSEM_UNLOCKED_VALUE 0x00000000 -#define RWSEM_ACTIVE_BIAS 0x00000001 -#define RWSEM_ACTIVE_MASK 0x0000ffff -#define RWSEM_WAITING_BIAS (-0x00010000) +#ifdef CONFIG_PPC64 +# define RWSEM_ACTIVE_MASK 0xffffffffL +#else +# define RWSEM_ACTIVE_MASK 0x0000ffffL +#endif + +#define RWSEM_UNLOCKED_VALUE 0x00000000L +#define RWSEM_ACTIVE_BIAS 0x00000001L +#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) #define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS #define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) + +struct rw_semaphore { + long count; spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -43,9 +48,13 @@ struct rw_semaphore { # define __RWSEM_DEP_MAP_INIT(lockname) #endif -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \ - LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) } +#define __RWSEM_INITIALIZER(name) \ +{ \ + RWSEM_UNLOCKED_VALUE, \ + __SPIN_LOCK_UNLOCKED((name).wait_lock), \ + LIST_HEAD_INIT((name).wait_list) \ + __RWSEM_DEP_MAP_INIT(name) \ +} #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) @@ -70,13 +79,13 @@ extern void __init_rwsem(struct rw_semaphore *sem, const char *name, */ static inline void __down_read(struct rw_semaphore *sem) { - if (unlikely(atomic_inc_return((atomic_t *)(&sem->count)) <= 0)) + if (unlikely(atomic_long_inc_return((atomic_long_t *)&sem->count) <= 0)) rwsem_down_read_failed(sem); } static inline int __down_read_trylock(struct rw_semaphore *sem) { - int tmp; + long tmp; while ((tmp = sem->count) >= 0) { if (tmp == cmpxchg(&sem->count, tmp, @@ -92,10 +101,10 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) */ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { - int tmp; + long tmp; - tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_t *)(&sem->count)); + tmp = atomic_long_add_return(RWSEM_ACTIVE_WRITE_BIAS, + (atomic_long_t *)&sem->count); if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) rwsem_down_write_failed(sem); } @@ -107,7 +116,7 @@ static inline void __down_write(struct rw_semaphore *sem) static inline int __down_write_trylock(struct rw_semaphore *sem) { - int tmp; + long tmp; tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); @@ -119,9 +128,9 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - int tmp; + long tmp; - tmp = atomic_dec_return((atomic_t *)(&sem->count)); + tmp = atomic_long_dec_return((atomic_long_t *)&sem->count); if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) rwsem_wake(sem); } @@ -131,17 +140,17 @@ static inline void __up_read(struct rw_semaphore *sem) */ static inline void __up_write(struct rw_semaphore *sem) { - if (unlikely(atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS, - (atomic_t *)(&sem->count)) < 0)) + if (unlikely(atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, + (atomic_long_t *)&sem->count) < 0)) rwsem_wake(sem); } /* * implement atomic add functionality */ -static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) +static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) { - atomic_add(delta, (atomic_t *)(&sem->count)); + atomic_long_add(delta, (atomic_long_t *)&sem->count); } /* @@ -149,9 +158,10 @@ static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) */ static inline void __downgrade_write(struct rw_semaphore *sem) { - int tmp; + long tmp; - tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count)); + tmp = atomic_long_add_return(-RWSEM_WAITING_BIAS, + (atomic_long_t *)&sem->count); if (tmp < 0) rwsem_downgrade_wake(sem); } @@ -159,14 +169,14 @@ static inline void __downgrade_write(struct rw_semaphore *sem) /* * implement exchange and add functionality */ -static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) +static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) { - return atomic_add_return(delta, (atomic_t *)(&sem->count)); + return atomic_long_add_return(delta, (atomic_long_t *)&sem->count); } static inline int rwsem_is_locked(struct rw_semaphore *sem) { - return (sem->count != 0); + return sem->count != 0; } #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index a5ee345b6a5c..3d212669a130 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -326,3 +326,6 @@ SYSCALL_SPU(perf_event_open) COMPAT_SYS_SPU(preadv) COMPAT_SYS_SPU(pwritev) COMPAT_SYS(rt_tgsigqueueinfo) +SYSCALL(fanotify_init) +COMPAT_SYS(fanotify_mark) +SYSCALL_SPU(prlimit64) diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h index 6c294acac848..9c3d160670b4 100644 --- a/arch/powerpc/include/asm/system.h +++ b/arch/powerpc/include/asm/system.h @@ -542,10 +542,6 @@ extern void reloc_got2(unsigned long); #define PTRRELOC(x) ((typeof(x)) add_reloc_offset((unsigned long)(x))) -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -extern void account_system_vtime(struct task_struct *); -#endif - extern struct dentry *powerpc_debugfs_root; #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index f0a10266e7f7..597e6f9d094a 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -345,10 +345,13 @@ #define __NR_preadv 320 #define __NR_pwritev 321 #define __NR_rt_tgsigqueueinfo 322 +#define __NR_fanotify_init 323 +#define __NR_fanotify_mark 324 +#define __NR_prlimit64 325 #ifdef __KERNEL__ -#define __NR_syscalls 323 +#define __NR_syscalls 326 #define __NR__exit __NR_exit #define NR_syscalls __NR_syscalls diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 65e2b4e10f97..1f9123f412ec 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1826,7 +1826,6 @@ static struct cpu_spec __initdata cpu_specs[] = { .cpu_features = CPU_FTRS_47X, .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, - .cpu_user_features = COMMON_USER_BOOKE, .mmu_features = MMU_FTR_TYPE_47x | MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL, .icache_bsize = 32, diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c index 417f7b05a9ce..4457382f8667 100644 --- a/arch/powerpc/kernel/crash.c +++ b/arch/powerpc/kernel/crash.c @@ -402,6 +402,18 @@ void default_machine_crash_shutdown(struct pt_regs *regs) */ hard_irq_disable(); + /* + * Make a note of crashing cpu. Will be used in machine_kexec + * such that another IPI will not be sent. + */ + crashing_cpu = smp_processor_id(); + crash_save_cpu(regs, crashing_cpu); + crash_kexec_prepare_cpus(crashing_cpu); + cpu_set(crashing_cpu, cpus_in_crash); +#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP) + crash_kexec_wait_realmode(crashing_cpu); +#endif + for_each_irq(i) { struct irq_desc *desc = irq_to_desc(i); @@ -438,18 +450,8 @@ void default_machine_crash_shutdown(struct pt_regs *regs) crash_shutdown_cpu = -1; __debugger_fault_handler = old_handler; - /* - * Make a note of crashing cpu. Will be used in machine_kexec - * such that another IPI will not be sent. - */ - crashing_cpu = smp_processor_id(); - crash_save_cpu(regs, crashing_cpu); - crash_kexec_prepare_cpus(crashing_cpu); - cpu_set(crashing_cpu, cpus_in_crash); crash_kexec_stop_spus(); -#if defined(CONFIG_PPC_STD_MMU_64) && defined(CONFIG_SMP) - crash_kexec_wait_realmode(crashing_cpu); -#endif + if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); } diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index 5ab484ef06a7..562305b40a8e 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -113,6 +113,10 @@ _ENTRY(_start); stw r5, 0(r4) /* Save abatron_pteptrs at a fixed location */ stw r6, 0(r5) + /* Clear the Machine Check Syndrome Register */ + li r0,0 + mtspr SPRN_MCSR,r0 + /* Let's move on */ lis r4,start_kernel@h ori r4,r4,start_kernel@l diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 844a44b64472..c571cd3c1453 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -572,15 +572,21 @@ __secondary_start: /* Set thread priority to MEDIUM */ HMT_MEDIUM - /* Do early setup for that CPU (stab, slb, hash table pointer) */ - bl .early_setup_secondary - /* Initialize the kernel stack. Just a repeat for iSeries. */ LOAD_REG_ADDR(r3, current_set) sldi r28,r24,3 /* get current_set[cpu#] */ - ldx r1,r3,r28 - addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD - std r1,PACAKSAVE(r13) + ldx r14,r3,r28 + addi r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD + std r14,PACAKSAVE(r13) + + /* Do early setup for that CPU (stab, slb, hash table pointer) */ + bl .early_setup_secondary + + /* + * setup the new stack pointer, but *don't* use this until + * translation is on. + */ + mr r1, r14 /* Clear backchain so we get nice backtraces */ li r7,0 diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 049dda60e475..39a2baa6ad58 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -94,9 +94,9 @@ void cpu_idle(void) HMT_medium(); ppc64_runlatch_on(); tick_nohz_restart_sched_tick(); + preempt_enable_no_resched(); if (cpu_should_die()) cpu_die(); - preempt_enable_no_resched(); schedule(); preempt_disable(); } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index d3ce67cf03be..4a65386995d7 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -67,6 +67,7 @@ #include <asm/machdep.h> #include <asm/udbg.h> #include <asm/dbell.h> +#include <asm/smp.h> #ifdef CONFIG_PPC64 #include <asm/paca.h> @@ -446,22 +447,23 @@ struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly; void exc_lvl_ctx_init(void) { struct thread_info *tp; - int i; + int i, hw_cpu; for_each_possible_cpu(i) { - memset((void *)critirq_ctx[i], 0, THREAD_SIZE); - tp = critirq_ctx[i]; + hw_cpu = get_hard_smp_processor_id(i); + memset((void *)critirq_ctx[hw_cpu], 0, THREAD_SIZE); + tp = critirq_ctx[hw_cpu]; tp->cpu = i; tp->preempt_count = 0; #ifdef CONFIG_BOOKE - memset((void *)dbgirq_ctx[i], 0, THREAD_SIZE); - tp = dbgirq_ctx[i]; + memset((void *)dbgirq_ctx[hw_cpu], 0, THREAD_SIZE); + tp = dbgirq_ctx[hw_cpu]; tp->cpu = i; tp->preempt_count = 0; - memset((void *)mcheckirq_ctx[i], 0, THREAD_SIZE); - tp = mcheckirq_ctx[i]; + memset((void *)mcheckirq_ctx[hw_cpu], 0, THREAD_SIZE); + tp = mcheckirq_ctx[hw_cpu]; tp->cpu = i; tp->preempt_count = HARDIRQ_OFFSET; #endif diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 6bbd7a604d24..a7a570dcdd57 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -810,6 +810,9 @@ relocate_new_kernel: isync sync + mfspr r3, SPRN_PIR /* current core we are running on */ + mr r4, r5 /* load physical address of chunk called */ + /* jump to the entry point, usually the setup routine */ mtlr r5 blrl diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 477c663e0140..49cee9df225b 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -63,11 +63,6 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { const Elf_Shdr *sect; - int err; - - err = module_bug_finalize(hdr, sechdrs, me); - if (err) - return err; /* Apply feature fixups */ sect = find_section(hdr, sechdrs, "__ftr_fixup"); @@ -101,5 +96,4 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 6ddb795f83e8..e751506323b4 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -336,7 +336,7 @@ static void __devinit __of_scan_bus(struct device_node *node, if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || dev->hdr_type == PCI_HEADER_TYPE_CARDBUS) { struct device_node *child = pci_device_to_OF_node(dev); - if (dev) + if (child) of_scan_pci_bridge(child, dev); } } diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c index 95ad9dad298e..d05ae4204bbf 100644 --- a/arch/powerpc/kernel/perf_callchain.c +++ b/arch/powerpc/kernel/perf_callchain.c @@ -23,18 +23,6 @@ #include "ppc32.h" #endif -/* - * Store another value in a callchain_entry. - */ -static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip) -{ - unsigned int nr = entry->nr; - - if (nr < PERF_MAX_STACK_DEPTH) { - entry->ip[nr] = ip; - entry->nr = nr + 1; - } -} /* * Is sp valid as the address of the next kernel stack frame after prev_sp? @@ -58,8 +46,8 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp) return 0; } -static void perf_callchain_kernel(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void +perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { unsigned long sp, next_sp; unsigned long next_ip; @@ -69,8 +57,7 @@ static void perf_callchain_kernel(struct pt_regs *regs, lr = regs->link; sp = regs->gpr[1]; - callchain_store(entry, PERF_CONTEXT_KERNEL); - callchain_store(entry, regs->nip); + perf_callchain_store(entry, regs->nip); if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD)) return; @@ -89,7 +76,7 @@ static void perf_callchain_kernel(struct pt_regs *regs, next_ip = regs->nip; lr = regs->link; level = 0; - callchain_store(entry, PERF_CONTEXT_KERNEL); + perf_callchain_store(entry, PERF_CONTEXT_KERNEL); } else { if (level == 0) @@ -111,7 +98,7 @@ static void perf_callchain_kernel(struct pt_regs *regs, ++level; } - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); if (!valid_next_sp(next_sp, sp)) return; sp = next_sp; @@ -233,8 +220,8 @@ static int sane_signal_64_frame(unsigned long sp) puc == (unsigned long) &sf->uc; } -static void perf_callchain_user_64(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static void perf_callchain_user_64(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned long sp, next_sp; unsigned long next_ip; @@ -246,8 +233,7 @@ static void perf_callchain_user_64(struct pt_regs *regs, next_ip = regs->nip; lr = regs->link; sp = regs->gpr[1]; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); for (;;) { fp = (unsigned long __user *) sp; @@ -276,14 +262,14 @@ static void perf_callchain_user_64(struct pt_regs *regs, read_user_stack_64(&uregs[PT_R1], &sp)) return; level = 0; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_store(entry, next_ip); continue; } if (level == 0) next_ip = lr; - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); ++level; sp = next_sp; } @@ -315,8 +301,8 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) return __get_user_inatomic(*ret, ptr); } -static inline void perf_callchain_user_64(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static inline void perf_callchain_user_64(struct perf_callchain_entry *entry, + struct pt_regs *regs) { } @@ -435,8 +421,8 @@ static unsigned int __user *signal_frame_32_regs(unsigned int sp, return mctx->mc_gregs; } -static void perf_callchain_user_32(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static void perf_callchain_user_32(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned int sp, next_sp; unsigned int next_ip; @@ -447,8 +433,7 @@ static void perf_callchain_user_32(struct pt_regs *regs, next_ip = regs->nip; lr = regs->link; sp = regs->gpr[1]; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); while (entry->nr < PERF_MAX_STACK_DEPTH) { fp = (unsigned int __user *) (unsigned long) sp; @@ -470,45 +455,24 @@ static void perf_callchain_user_32(struct pt_regs *regs, read_user_stack_32(&uregs[PT_R1], &sp)) return; level = 0; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, next_ip); + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_store(entry, next_ip); continue; } if (level == 0) next_ip = lr; - callchain_store(entry, next_ip); + perf_callchain_store(entry, next_ip); ++level; sp = next_sp; } } -/* - * Since we can't get PMU interrupts inside a PMU interrupt handler, - * we don't need separate irq and nmi entries here. - */ -static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain); - -struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) +void +perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { - struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain); - - entry->nr = 0; - - if (!user_mode(regs)) { - perf_callchain_kernel(regs, entry); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; - } - - if (regs) { - if (current_is_64bit()) - perf_callchain_user_64(regs, entry); - else - perf_callchain_user_32(regs, entry); - } - - return entry; + if (current_is_64bit()) + perf_callchain_user_64(entry, regs); + else + perf_callchain_user_32(entry, regs); } diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c index d301a30445e0..3129c855933c 100644 --- a/arch/powerpc/kernel/perf_event.c +++ b/arch/powerpc/kernel/perf_event.c @@ -402,6 +402,9 @@ static void power_pmu_read(struct perf_event *event) { s64 val, delta, prev; + if (event->hw.state & PERF_HES_STOPPED) + return; + if (!event->hw.idx) return; /* @@ -517,7 +520,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0) * Disable all events to prevent PMU interrupts and to allow * events to be added or removed. */ -void hw_perf_disable(void) +static void power_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -565,7 +568,7 @@ void hw_perf_disable(void) * If we were previously disabled and events were added, then * put the new config on the PMU. */ -void hw_perf_enable(void) +static void power_pmu_enable(struct pmu *pmu) { struct perf_event *event; struct cpu_hw_events *cpuhw; @@ -672,6 +675,8 @@ void hw_perf_enable(void) } local64_set(&event->hw.prev_count, val); event->hw.idx = idx; + if (event->hw.state & PERF_HES_STOPPED) + val = 0; write_pmc(idx, val); perf_event_update_userpage(event); } @@ -727,7 +732,7 @@ static int collect_events(struct perf_event *group, int max_count, * re-enable the PMU in order to get hw_perf_enable to do the * actual work of reconfiguring the PMU. */ -static int power_pmu_enable(struct perf_event *event) +static int power_pmu_add(struct perf_event *event, int ef_flags) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -735,7 +740,7 @@ static int power_pmu_enable(struct perf_event *event) int ret = -EAGAIN; local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); /* * Add the event to the list (if there is room) @@ -749,6 +754,9 @@ static int power_pmu_enable(struct perf_event *event) cpuhw->events[n0] = event->hw.config; cpuhw->flags[n0] = event->hw.event_base; + if (!(ef_flags & PERF_EF_START)) + event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be peformed @@ -769,7 +777,7 @@ nocheck: ret = 0; out: - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } @@ -777,14 +785,14 @@ nocheck: /* * Remove a event from the PMU. */ -static void power_pmu_disable(struct perf_event *event) +static void power_pmu_del(struct perf_event *event, int ef_flags) { struct cpu_hw_events *cpuhw; long i; unsigned long flags; local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); power_pmu_read(event); @@ -821,34 +829,60 @@ static void power_pmu_disable(struct perf_event *event) cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); } - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } /* - * Re-enable interrupts on a event after they were throttled - * because they were coming too fast. + * POWER-PMU does not support disabling individual counters, hence + * program their cycle counter to their max value and ignore the interrupts. */ -static void power_pmu_unthrottle(struct perf_event *event) + +static void power_pmu_start(struct perf_event *event, int ef_flags) +{ + unsigned long flags; + s64 left; + + if (!event->hw.idx || !event->hw.sample_period) + return; + + if (!(event->hw.state & PERF_HES_STOPPED)) + return; + + if (ef_flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + local_irq_save(flags); + perf_pmu_disable(event->pmu); + + event->hw.state = 0; + left = local64_read(&event->hw.period_left); + write_pmc(event->hw.idx, left); + + perf_event_update_userpage(event); + perf_pmu_enable(event->pmu); + local_irq_restore(flags); +} + +static void power_pmu_stop(struct perf_event *event, int ef_flags) { - s64 val, left; unsigned long flags; if (!event->hw.idx || !event->hw.sample_period) return; + + if (event->hw.state & PERF_HES_STOPPED) + return; + local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); + power_pmu_read(event); - left = event->hw.sample_period; - event->hw.last_period = left; - val = 0; - if (left < 0x80000000L) - val = 0x80000000L - left; - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); + event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + write_pmc(event->hw.idx, 0); + perf_event_update_userpage(event); - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } @@ -857,10 +891,11 @@ static void power_pmu_unthrottle(struct perf_event *event) * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time */ -void power_pmu_start_txn(const struct pmu *pmu) +void power_pmu_start_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + perf_pmu_disable(pmu); cpuhw->group_flag |= PERF_EVENT_TXN; cpuhw->n_txn_start = cpuhw->n_events; } @@ -870,11 +905,12 @@ void power_pmu_start_txn(const struct pmu *pmu) * Clear the flag and pmu::enable() will perform the * schedulability test. */ -void power_pmu_cancel_txn(const struct pmu *pmu) +void power_pmu_cancel_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); cpuhw->group_flag &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); } /* @@ -882,7 +918,7 @@ void power_pmu_cancel_txn(const struct pmu *pmu) * Perform the group schedulability test as a whole * Return 0 if success */ -int power_pmu_commit_txn(const struct pmu *pmu) +int power_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw; long i, n; @@ -901,19 +937,10 @@ int power_pmu_commit_txn(const struct pmu *pmu) cpuhw->event[i]->hw.config = cpuhw->events[i]; cpuhw->group_flag &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); return 0; } -struct pmu power_pmu = { - .enable = power_pmu_enable, - .disable = power_pmu_disable, - .read = power_pmu_read, - .unthrottle = power_pmu_unthrottle, - .start_txn = power_pmu_start_txn, - .cancel_txn = power_pmu_cancel_txn, - .commit_txn = power_pmu_commit_txn, -}; - /* * Return 1 if we might be able to put event on a limited PMC, * or 0 if not. @@ -1014,7 +1041,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp) return 0; } -const struct pmu *hw_perf_event_init(struct perf_event *event) +static int power_pmu_event_init(struct perf_event *event) { u64 ev; unsigned long flags; @@ -1026,25 +1053,27 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) struct cpu_hw_events *cpuhw; if (!ppmu) - return ERR_PTR(-ENXIO); + return -ENOENT; + switch (event->attr.type) { case PERF_TYPE_HARDWARE: ev = event->attr.config; if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; ev = ppmu->generic_events[ev]; break; case PERF_TYPE_HW_CACHE: err = hw_perf_cache_event(event->attr.config, &ev); if (err) - return ERR_PTR(err); + return err; break; case PERF_TYPE_RAW: ev = event->attr.config; break; default: - return ERR_PTR(-EINVAL); + return -ENOENT; } + event->hw.config_base = ev; event->hw.idx = 0; @@ -1063,7 +1092,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) * XXX we should check if the task is an idle task. */ flags = 0; - if (event->ctx->task) + if (event->attach_state & PERF_ATTACH_TASK) flags |= PPMU_ONLY_COUNT_RUN; /* @@ -1081,7 +1110,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) */ ev = normal_pmc_alternative(ev, flags); if (!ev) - return ERR_PTR(-EINVAL); + return -EINVAL; } } @@ -1095,19 +1124,19 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) n = collect_events(event->group_leader, ppmu->n_counter - 1, ctrs, events, cflags); if (n < 0) - return ERR_PTR(-EINVAL); + return -EINVAL; } events[n] = ev; ctrs[n] = event; cflags[n] = flags; if (check_excludes(ctrs, cflags, n, 1)) - return ERR_PTR(-EINVAL); + return -EINVAL; cpuhw = &get_cpu_var(cpu_hw_events); err = power_check_constraints(cpuhw, events, cflags, n + 1); put_cpu_var(cpu_hw_events); if (err) - return ERR_PTR(-EINVAL); + return -EINVAL; event->hw.config = events[n]; event->hw.event_base = cflags[n]; @@ -1132,11 +1161,23 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } event->destroy = hw_perf_event_destroy; - if (err) - return ERR_PTR(err); - return &power_pmu; + return err; } +struct pmu power_pmu = { + .pmu_enable = power_pmu_enable, + .pmu_disable = power_pmu_disable, + .event_init = power_pmu_event_init, + .add = power_pmu_add, + .del = power_pmu_del, + .start = power_pmu_start, + .stop = power_pmu_stop, + .read = power_pmu_read, + .start_txn = power_pmu_start_txn, + .cancel_txn = power_pmu_cancel_txn, + .commit_txn = power_pmu_commit_txn, +}; + /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -1149,6 +1190,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, s64 prev, delta, left; int record = 0; + if (event->hw.state & PERF_HES_STOPPED) { + write_pmc(event->hw.idx, 0); + return; + } + /* we don't have to worry about interrupts here */ prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; @@ -1171,6 +1217,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, val = 0x80000000LL - left; } + write_pmc(event->hw.idx, val); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); + /* * Finally record data if requested. */ @@ -1183,23 +1234,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_ADDR) perf_get_data_addr(regs, &data.addr); - if (perf_event_overflow(event, nmi, &data, regs)) { - /* - * Interrupts are coming too fast - throttle them - * by setting the event to 0, so it will be - * at least 2^30 cycles until the next interrupt - * (assuming each event counts at most 2 counts - * per cycle). - */ - val = 0; - left = ~0ULL >> 1; - } + if (perf_event_overflow(event, nmi, &data, regs)) + power_pmu_stop(event, 0); } - - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); - perf_event_update_userpage(event); } /* @@ -1342,6 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu) freeze_events_kernel = MMCR0_FCHV; #endif /* CONFIG_PPC64 */ + perf_pmu_register(&power_pmu); perf_cpu_notifier(power_pmu_notifier); return 0; diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/kernel/perf_event_fsl_emb.c index 1ba45471ae43..7ecca59ddf77 100644 --- a/arch/powerpc/kernel/perf_event_fsl_emb.c +++ b/arch/powerpc/kernel/perf_event_fsl_emb.c @@ -156,6 +156,9 @@ static void fsl_emb_pmu_read(struct perf_event *event) { s64 val, delta, prev; + if (event->hw.state & PERF_HES_STOPPED) + return; + /* * Performance monitor interrupts come even when interrupts * are soft-disabled, as long as interrupts are hard-enabled. @@ -177,7 +180,7 @@ static void fsl_emb_pmu_read(struct perf_event *event) * Disable all events to prevent PMU interrupts and to allow * events to be added or removed. */ -void hw_perf_disable(void) +static void fsl_emb_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -216,7 +219,7 @@ void hw_perf_disable(void) * If we were previously disabled and events were added, then * put the new config on the PMU. */ -void hw_perf_enable(void) +static void fsl_emb_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; unsigned long flags; @@ -262,8 +265,8 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -/* perf must be disabled, context locked on entry */ -static int fsl_emb_pmu_enable(struct perf_event *event) +/* context locked on entry */ +static int fsl_emb_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuhw; int ret = -EAGAIN; @@ -271,6 +274,7 @@ static int fsl_emb_pmu_enable(struct perf_event *event) u64 val; int i; + perf_pmu_disable(event->pmu); cpuhw = &get_cpu_var(cpu_hw_events); if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) @@ -301,6 +305,12 @@ static int fsl_emb_pmu_enable(struct perf_event *event) val = 0x80000000L - left; } local64_set(&event->hw.prev_count, val); + + if (!(flags & PERF_EF_START)) { + event->hw.state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + val = 0; + } + write_pmc(i, val); perf_event_update_userpage(event); @@ -310,15 +320,17 @@ static int fsl_emb_pmu_enable(struct perf_event *event) ret = 0; out: put_cpu_var(cpu_hw_events); + perf_pmu_enable(event->pmu); return ret; } -/* perf must be disabled, context locked on entry */ -static void fsl_emb_pmu_disable(struct perf_event *event) +/* context locked on entry */ +static void fsl_emb_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuhw; int i = event->hw.idx; + perf_pmu_disable(event->pmu); if (i < 0) goto out; @@ -346,44 +358,57 @@ static void fsl_emb_pmu_disable(struct perf_event *event) cpuhw->n_events--; out: + perf_pmu_enable(event->pmu); put_cpu_var(cpu_hw_events); } -/* - * Re-enable interrupts on a event after they were throttled - * because they were coming too fast. - * - * Context is locked on entry, but perf is not disabled. - */ -static void fsl_emb_pmu_unthrottle(struct perf_event *event) +static void fsl_emb_pmu_start(struct perf_event *event, int ef_flags) { - s64 val, left; unsigned long flags; + s64 left; if (event->hw.idx < 0 || !event->hw.sample_period) return; + + if (!(event->hw.state & PERF_HES_STOPPED)) + return; + + if (ef_flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + local_irq_save(flags); - perf_disable(); - fsl_emb_pmu_read(event); - left = event->hw.sample_period; - event->hw.last_period = left; - val = 0; - if (left < 0x80000000L) - val = 0x80000000L - left; - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); + perf_pmu_disable(event->pmu); + + event->hw.state = 0; + left = local64_read(&event->hw.period_left); + write_pmc(event->hw.idx, left); + perf_event_update_userpage(event); - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } -static struct pmu fsl_emb_pmu = { - .enable = fsl_emb_pmu_enable, - .disable = fsl_emb_pmu_disable, - .read = fsl_emb_pmu_read, - .unthrottle = fsl_emb_pmu_unthrottle, -}; +static void fsl_emb_pmu_stop(struct perf_event *event, int ef_flags) +{ + unsigned long flags; + + if (event->hw.idx < 0 || !event->hw.sample_period) + return; + + if (event->hw.state & PERF_HES_STOPPED) + return; + + local_irq_save(flags); + perf_pmu_disable(event->pmu); + + fsl_emb_pmu_read(event); + event->hw.state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; + write_pmc(event->hw.idx, 0); + + perf_event_update_userpage(event); + perf_pmu_enable(event->pmu); + local_irq_restore(flags); +} /* * Release the PMU if this is the last perf_event. @@ -428,7 +453,7 @@ static int hw_perf_cache_event(u64 config, u64 *eventp) return 0; } -const struct pmu *hw_perf_event_init(struct perf_event *event) +static int fsl_emb_pmu_event_init(struct perf_event *event) { u64 ev; struct perf_event *events[MAX_HWEVENTS]; @@ -441,14 +466,14 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) case PERF_TYPE_HARDWARE: ev = event->attr.config; if (ev >= ppmu->n_generic || ppmu->generic_events[ev] == 0) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP; ev = ppmu->generic_events[ev]; break; case PERF_TYPE_HW_CACHE: err = hw_perf_cache_event(event->attr.config, &ev); if (err) - return ERR_PTR(err); + return err; break; case PERF_TYPE_RAW: @@ -456,12 +481,12 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) break; default: - return ERR_PTR(-EINVAL); + return -ENOENT; } event->hw.config = ppmu->xlate_event(ev); if (!(event->hw.config & FSL_EMB_EVENT_VALID)) - return ERR_PTR(-EINVAL); + return -EINVAL; /* * If this is in a group, check if it can go on with all the @@ -473,7 +498,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) n = collect_events(event->group_leader, ppmu->n_counter - 1, events); if (n < 0) - return ERR_PTR(-EINVAL); + return -EINVAL; } if (event->hw.config & FSL_EMB_EVENT_RESTRICTED) { @@ -484,7 +509,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } if (num_restricted >= ppmu->n_restricted) - return ERR_PTR(-EINVAL); + return -EINVAL; } event->hw.idx = -1; @@ -497,7 +522,7 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) if (event->attr.exclude_kernel) event->hw.config_base |= PMLCA_FCS; if (event->attr.exclude_idle) - return ERR_PTR(-ENOTSUPP); + return -ENOTSUPP; event->hw.last_period = event->hw.sample_period; local64_set(&event->hw.period_left, event->hw.last_period); @@ -523,11 +548,20 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) } event->destroy = hw_perf_event_destroy; - if (err) - return ERR_PTR(err); - return &fsl_emb_pmu; + return err; } +static struct pmu fsl_emb_pmu = { + .pmu_enable = fsl_emb_pmu_enable, + .pmu_disable = fsl_emb_pmu_disable, + .event_init = fsl_emb_pmu_event_init, + .add = fsl_emb_pmu_add, + .del = fsl_emb_pmu_del, + .start = fsl_emb_pmu_start, + .stop = fsl_emb_pmu_stop, + .read = fsl_emb_pmu_read, +}; + /* * A counter has overflowed; update its count and record * things if requested. Note that interrupts are hard-disabled @@ -540,6 +574,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, s64 prev, delta, left; int record = 0; + if (event->hw.state & PERF_HES_STOPPED) { + write_pmc(event->hw.idx, 0); + return; + } + /* we don't have to worry about interrupts here */ prev = local64_read(&event->hw.prev_count); delta = (val - prev) & 0xfffffffful; @@ -562,6 +601,11 @@ static void record_and_restart(struct perf_event *event, unsigned long val, val = 0x80000000LL - left; } + write_pmc(event->hw.idx, val); + local64_set(&event->hw.prev_count, val); + local64_set(&event->hw.period_left, left); + perf_event_update_userpage(event); + /* * Finally record data if requested. */ @@ -571,23 +615,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, 0); data.period = event->hw.last_period; - if (perf_event_overflow(event, nmi, &data, regs)) { - /* - * Interrupts are coming too fast - throttle them - * by setting the event to 0, so it will be - * at least 2^30 cycles until the next interrupt - * (assuming each event counts at most 2 counts - * per cycle). - */ - val = 0; - left = ~0ULL >> 1; - } + if (perf_event_overflow(event, nmi, &data, regs)) + fsl_emb_pmu_stop(event, 0); } - - write_pmc(event->hw.idx, val); - local64_set(&event->hw.prev_count, val); - local64_set(&event->hw.period_left, left); - perf_event_update_userpage(event); } static void perf_event_interrupt(struct pt_regs *regs) @@ -651,5 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu) pr_info("%s performance monitor hardware support registered\n", pmu->name); + perf_pmu_register(&fsl_emb_pmu); + return 0; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 91356ffda2ca..b1c648a36b03 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -728,7 +728,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, p->thread.regs = childregs; if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_PPC64 - if (!test_thread_flag(TIF_32BIT)) + if (!is_32bit_task()) childregs->gpr[13] = childregs->gpr[6]; else #endif @@ -823,7 +823,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) regs->nip = start; regs->msr = MSR_USER; #else - if (!test_thread_flag(TIF_32BIT)) { + if (!is_32bit_task()) { unsigned long entry, toc; /* start is a relocated pointer to the function descriptor for @@ -995,7 +995,7 @@ int sys_clone(unsigned long clone_flags, unsigned long usp, if (usp == 0) usp = regs->gpr[1]; /* stack pointer for child */ #ifdef CONFIG_PPC64 - if (test_thread_flag(TIF_32BIT)) { + if (is_32bit_task()) { parent_tidp = TRUNC_PTR(parent_tidp); child_tidp = TRUNC_PTR(child_tidp); } @@ -1199,19 +1199,17 @@ void ppc64_runlatch_on(void) } } -void ppc64_runlatch_off(void) +void __ppc64_runlatch_off(void) { unsigned long ctrl; - if (cpu_has_feature(CPU_FTR_CTRL) && test_thread_flag(TIF_RUNLATCH)) { - HMT_medium(); + HMT_medium(); - clear_thread_flag(TIF_RUNLATCH); + clear_thread_flag(TIF_RUNLATCH); - ctrl = mfspr(SPRN_CTRLF); - ctrl &= ~CTRL_RUNLATCH; - mtspr(SPRN_CTRLT, ctrl); - } + ctrl = mfspr(SPRN_CTRLF); + ctrl &= ~CTRL_RUNLATCH; + mtspr(SPRN_CTRLT, ctrl); } #endif diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index a10ffc85ada7..93666f9cabf1 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -258,17 +258,18 @@ static void __init irqstack_early_init(void) #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) static void __init exc_lvl_early_init(void) { - unsigned int i; + unsigned int i, hw_cpu; /* interrupt stacks must be in lowmem, we get that for free on ppc32 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { - critirq_ctx[i] = (struct thread_info *) + hw_cpu = get_hard_smp_processor_id(i); + critirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE - dbgirq_ctx[i] = (struct thread_info *) + dbgirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); - mcheckirq_ctx[i] = (struct thread_info *) + mcheckirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #endif } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 1bee4b68fa45..e72690ec9b87 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -95,7 +95,7 @@ int ucache_bsize; #ifdef CONFIG_SMP -static int smt_enabled_cmdline; +static char *smt_enabled_cmdline; /* Look for ibm,smt-enabled OF option */ static void check_smt_enabled(void) @@ -103,37 +103,46 @@ static void check_smt_enabled(void) struct device_node *dn; const char *smt_option; - /* Allow the command line to overrule the OF option */ - if (smt_enabled_cmdline) - return; - - dn = of_find_node_by_path("/options"); - - if (dn) { - smt_option = of_get_property(dn, "ibm,smt-enabled", NULL); + /* Default to enabling all threads */ + smt_enabled_at_boot = threads_per_core; - if (smt_option) { - if (!strcmp(smt_option, "on")) - smt_enabled_at_boot = 1; - else if (!strcmp(smt_option, "off")) - smt_enabled_at_boot = 0; - } - } + /* Allow the command line to overrule the OF option */ + if (smt_enabled_cmdline) { + if (!strcmp(smt_enabled_cmdline, "on")) + smt_enabled_at_boot = threads_per_core; + else if (!strcmp(smt_enabled_cmdline, "off")) + smt_enabled_at_boot = 0; + else { + long smt; + int rc; + + rc = strict_strtol(smt_enabled_cmdline, 10, &smt); + if (!rc) + smt_enabled_at_boot = + min(threads_per_core, (int)smt); + } + } else { + dn = of_find_node_by_path("/options"); + if (dn) { + smt_option = of_get_property(dn, "ibm,smt-enabled", + NULL); + + if (smt_option) { + if (!strcmp(smt_option, "on")) + smt_enabled_at_boot = threads_per_core; + else if (!strcmp(smt_option, "off")) + smt_enabled_at_boot = 0; + } + + of_node_put(dn); + } + } } /* Look for smt-enabled= cmdline option */ static int __init early_smt_enabled(char *p) { - smt_enabled_cmdline = 1; - - if (!p) - return 0; - - if (!strcmp(p, "on") || !strcmp(p, "1")) - smt_enabled_at_boot = 1; - else if (!strcmp(p, "off") || !strcmp(p, "0")) - smt_enabled_at_boot = 0; - + smt_enabled_cmdline = p; return 0; } early_param("smt-enabled", early_smt_enabled); @@ -380,8 +389,8 @@ void __init setup_system(void) */ xmon_setup(); - check_smt_enabled(); smp_setup_cpu_maps(); + check_smt_enabled(); #ifdef CONFIG_SMP /* Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index 7109f5b1baa8..2300426e531a 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -138,6 +138,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs) ti->local_flags &= ~_TLF_RESTORE_SIGMASK; sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); } + regs->trap = 0; return 0; /* no signals delivered */ } @@ -164,6 +165,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs) ret = handle_rt_signal64(signr, &ka, &info, oldset, regs); } + regs->trap = 0; if (ret) { spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked, ¤t->blocked, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 266610119f66..b96a3a010c26 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -511,6 +511,7 @@ static long restore_user_regs(struct pt_regs *regs, if (!sig) save_r2 = (unsigned int)regs->gpr[2]; err = restore_general_regs(regs, sr); + regs->trap = 0; err |= __get_user(msr, &sr->mc_gregs[PT_MSR]); if (!sig) regs->gpr[2] = (unsigned long) save_r2; @@ -884,7 +885,6 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - regs->trap = 0; return 1; badframe: @@ -1228,7 +1228,6 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka, regs->nip = (unsigned long) ka->sa.sa_handler; /* enter the signal handler in big-endian mode */ regs->msr &= ~MSR_LE; - regs->trap = 0; return 1; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 2fe6fc64b614..27c4a4584f80 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -178,7 +178,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig, err |= __get_user(regs->xer, &sc->gp_regs[PT_XER]); err |= __get_user(regs->ccr, &sc->gp_regs[PT_CCR]); /* skip SOFTE */ - err |= __get_user(regs->trap, &sc->gp_regs[PT_TRAP]); + regs->trap = 0; err |= __get_user(regs->dar, &sc->gp_regs[PT_DAR]); err |= __get_user(regs->dsisr, &sc->gp_regs[PT_DSISR]); err |= __get_user(regs->result, &sc->gp_regs[PT_RESULT]); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index a61b3ddd7bb3..0008bc58e826 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -427,11 +427,11 @@ int __cpuinit __cpu_up(unsigned int cpu) #endif if (!cpu_callin_map[cpu]) { - printk("Processor %u is stuck.\n", cpu); + printk(KERN_ERR "Processor %u is stuck.\n", cpu); return -ENOENT; } - printk("Processor %u found.\n", cpu); + DBG("Processor %u found.\n", cpu); if (smp_ops->give_timebase) smp_ops->give_timebase(); diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 20fd701a686a..b1b6043a56c4 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -616,3 +616,11 @@ asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, return sys_sync_file_range(fd, offset, nbytes, flags); } + +asmlinkage long compat_sys_fanotify_mark(int fanotify_fd, unsigned int flags, + unsigned mask_hi, unsigned mask_lo, + int dfd, const char __user *pathname) +{ + u64 mask = ((u64)mask_hi << 32) | mask_lo; + return sys_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname); +} diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index ce53dfa7130d..54888eb10c3b 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -53,7 +53,7 @@ #include <linux/posix-timers.h> #include <linux/irq.h> #include <linux/delay.h> -#include <linux/perf_event.h> +#include <linux/irq_work.h> #include <asm/trace.h> #include <asm/io.h> @@ -493,60 +493,60 @@ void __init iSeries_time_init_early(void) } #endif /* CONFIG_PPC_ISERIES */ -#ifdef CONFIG_PERF_EVENTS +#ifdef CONFIG_IRQ_WORK /* * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */ #ifdef CONFIG_PPC64 -static inline unsigned long test_perf_event_pending(void) +static inline unsigned long test_irq_work_pending(void) { unsigned long x; asm volatile("lbz %0,%1(13)" : "=r" (x) - : "i" (offsetof(struct paca_struct, perf_event_pending))); + : "i" (offsetof(struct paca_struct, irq_work_pending))); return x; } -static inline void set_perf_event_pending_flag(void) +static inline void set_irq_work_pending_flag(void) { asm volatile("stb %0,%1(13)" : : "r" (1), - "i" (offsetof(struct paca_struct, perf_event_pending))); + "i" (offsetof(struct paca_struct, irq_work_pending))); } -static inline void clear_perf_event_pending(void) +static inline void clear_irq_work_pending(void) { asm volatile("stb %0,%1(13)" : : "r" (0), - "i" (offsetof(struct paca_struct, perf_event_pending))); + "i" (offsetof(struct paca_struct, irq_work_pending))); } #else /* 32-bit */ -DEFINE_PER_CPU(u8, perf_event_pending); +DEFINE_PER_CPU(u8, irq_work_pending); -#define set_perf_event_pending_flag() __get_cpu_var(perf_event_pending) = 1 -#define test_perf_event_pending() __get_cpu_var(perf_event_pending) -#define clear_perf_event_pending() __get_cpu_var(perf_event_pending) = 0 +#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 +#define test_irq_work_pending() __get_cpu_var(irq_work_pending) +#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 #endif /* 32 vs 64 bit */ -void set_perf_event_pending(void) +void set_irq_work_pending(void) { preempt_disable(); - set_perf_event_pending_flag(); + set_irq_work_pending_flag(); set_dec(1); preempt_enable(); } -#else /* CONFIG_PERF_EVENTS */ +#else /* CONFIG_IRQ_WORK */ -#define test_perf_event_pending() 0 -#define clear_perf_event_pending() +#define test_irq_work_pending() 0 +#define clear_irq_work_pending() -#endif /* CONFIG_PERF_EVENTS */ +#endif /* CONFIG_IRQ_WORK */ /* * For iSeries shared processors, we have to let the hypervisor @@ -577,28 +577,19 @@ void timer_interrupt(struct pt_regs * regs) * some CPUs will continuue to take decrementer exceptions */ set_dec(DECREMENTER_MAX); -#ifdef CONFIG_PPC32 +#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) do_IRQ(regs); #endif - now = get_tb_or_rtc(); - if (now < decrementer->next_tb) { - /* not time for this event yet */ - now = decrementer->next_tb - now; - if (now <= DECREMENTER_MAX) - set_dec((int)now); - trace_timer_interrupt_exit(regs); - return; - } old_regs = set_irq_regs(regs); irq_enter(); calculate_steal_time(); - if (test_perf_event_pending()) { - clear_perf_event_pending(); - perf_event_do_pending(); + if (test_irq_work_pending()) { + clear_irq_work_pending(); + irq_work_run(); } #ifdef CONFIG_PPC_ISERIES @@ -606,8 +597,16 @@ void timer_interrupt(struct pt_regs * regs) get_lppaca()->int_dword.fields.decr_int = 0; #endif - if (evt->event_handler) - evt->event_handler(evt); + now = get_tb_or_rtc(); + if (now >= decrementer->next_tb) { + decrementer->next_tb = ~(u64)0; + if (evt->event_handler) + evt->event_handler(evt); + } else { + now = decrementer->next_tb - now; + if (now <= DECREMENTER_MAX) + set_dec((int)now); + } #ifdef CONFIG_PPC_ISERIES if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending()) diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c index 00b9436f7652..fa3469ddaef8 100644 --- a/arch/powerpc/kernel/vio.c +++ b/arch/powerpc/kernel/vio.c @@ -1059,7 +1059,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) if (!dma_window) return NULL; - tbl = kmalloc(sizeof(*tbl), GFP_KERNEL); + tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); if (tbl == NULL) return NULL; @@ -1072,6 +1072,7 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev) tbl->it_offset = offset >> IOMMU_PAGE_SHIFT; tbl->it_busno = 0; tbl->it_type = TCE_VB; + tbl->it_blocksize = 16; return iommu_init_table(tbl, -1); } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 71f1415e2472..ace85fa74b29 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -79,7 +79,9 @@ #endif /* CONFIG_PPC_STD_MMU_64 */ phys_addr_t memstart_addr = ~0; +EXPORT_SYMBOL_GPL(memstart_addr); phys_addr_t kernstart_addr; +EXPORT_SYMBOL_GPL(kernstart_addr); void free_initmem(void) { diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index cfa768203d08..b9d9fed8f36e 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -200,6 +200,7 @@ _GLOBAL(_tlbivax_bcast) rlwimi r5,r4,0,16,31 wrteei 0 mtspr SPRN_MMUCR,r5 + isync /* tlbivax 0,r3 - use .long to avoid binutils deps */ .long 0x7c000624 | (r3 << 11) isync diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c index 5b243bd3eb3b..3dc2a8d262b8 100644 --- a/arch/powerpc/platforms/512x/clock.c +++ b/arch/powerpc/platforms/512x/clock.c @@ -57,7 +57,7 @@ static struct clk *mpc5121_clk_get(struct device *dev, const char *id) int id_match = 0; if (dev == NULL || id == NULL) - return NULL; + return clk; mutex_lock(&clocks_mutex); list_for_each_entry(p, &clocks, node) { diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c index 45c0cb9b67e6..18c104820198 100644 --- a/arch/powerpc/platforms/52xx/efika.c +++ b/arch/powerpc/platforms/52xx/efika.c @@ -99,7 +99,7 @@ static void __init efika_pcisetup(void) if (bus_range == NULL || len < 2 * sizeof(int)) { printk(KERN_WARNING EFIKA_PLATFORM_NAME ": Can't get bus-range for %s\n", pcictrl->full_name); - return; + goto out_put; } if (bus_range[1] == bus_range[0]) @@ -111,12 +111,12 @@ static void __init efika_pcisetup(void) printk(" controlled by %s\n", pcictrl->full_name); printk("\n"); - hose = pcibios_alloc_controller(of_node_get(pcictrl)); + hose = pcibios_alloc_controller(pcictrl); if (!hose) { printk(KERN_WARNING EFIKA_PLATFORM_NAME ": Can't allocate PCI controller structure for %s\n", pcictrl->full_name); - return; + goto out_put; } hose->first_busno = bus_range[0]; @@ -124,6 +124,9 @@ static void __init efika_pcisetup(void) hose->ops = &rtas_pci_ops; pci_process_bridge_OF_ranges(hose, pcictrl, 0); + return; +out_put: + of_node_put(pcictrl); } #else diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c index 6e905314ad5d..41f3a7eda1de 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_common.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c @@ -325,12 +325,16 @@ int mpc5200_psc_ac97_gpio_reset(int psc_number) clrbits32(&simple_gpio->simple_dvo, sync | out); clrbits8(&wkup_gpio->wkup_dvo, reset); - /* wait at lease 1 us */ - udelay(2); + /* wait for 1 us */ + udelay(1); /* Deassert reset */ setbits8(&wkup_gpio->wkup_dvo, reset); + /* wait at least 200ns */ + /* 7 ~= (200ns * timebase) / ns2sec */ + __delay(7); + /* Restore pin-muxing */ out_be32(&simple_gpio->port_config, mux); diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c index f9751c8905be..83068322abd1 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c @@ -48,8 +48,10 @@ static int mpc837xmds_usb_cfg(void) return -1; np = of_find_node_by_name(NULL, "usb"); - if (!np) - return -ENODEV; + if (!np) { + ret = -ENODEV; + goto out; + } phy_type = of_get_property(np, "phy_type", NULL); if (phy_type && !strcmp(phy_type, "ulpi")) { clrbits8(bcsr_regs + 12, BCSR12_USB_SER_PIN); @@ -65,8 +67,9 @@ static int mpc837xmds_usb_cfg(void) } of_node_put(np); +out: iounmap(bcsr_regs); - return 0; + return ret; } /* ************************************************************************ diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c index da64be19d099..aa34cac4eb5c 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c @@ -357,6 +357,7 @@ static void __init mpc85xx_mds_setup_arch(void) { #ifdef CONFIG_PCI struct pci_controller *hose; + struct device_node *np; #endif dma_addr_t max = 0xffffffff; diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index e1467c937450..34e00902ce86 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -19,7 +19,7 @@ #include <linux/pci.h> #include <linux/of_platform.h> -#include <linux/lmb.h> +#include <linux/memblock.h> #include <asm/mpic.h> #include <asm/swiotlb.h> @@ -97,7 +97,7 @@ static void __init p1022_ds_setup_arch(void) #endif #ifdef CONFIG_SWIOTLB - if (lmb_end_of_DRAM() > max) { + if (memblock_end_of_DRAM() > max) { ppc_swiotlb_enable = 1; set_pci_dma_ops(&swiotlb_dma_ops); ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb; diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index d1663db7810f..81c9208025fa 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -106,8 +106,7 @@ config MMIO_NVRAM config MPIC_U3_HT_IRQS bool - depends on PPC_MAPLE - default y + default n config MPIC_BROKEN_REGREAD bool diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 58b13ce3847e..26a067122a54 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -477,7 +477,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np, ioid = cell_iommu_get_ioid(np); - window = kmalloc_node(sizeof(*window), GFP_KERNEL, iommu->nid); + window = kzalloc_node(sizeof(*window), GFP_KERNEL, iommu->nid); BUG_ON(window == NULL); window->offset = offset; diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c index ce61cea0afb5..d8b76335bd13 100644 --- a/arch/powerpc/platforms/iseries/iommu.c +++ b/arch/powerpc/platforms/iseries/iommu.c @@ -184,7 +184,7 @@ static void pci_dma_dev_setup_iseries(struct pci_dev *pdev) BUG_ON(lsn == NULL); - tbl = kmalloc(sizeof(struct iommu_table), GFP_KERNEL); + tbl = kzalloc(sizeof(struct iommu_table), GFP_KERNEL); iommu_table_getparms_iSeries(pdn->busno, *lsn, 0, tbl); diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 39df6ab1735a..df423993f175 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2873,12 +2873,11 @@ set_initial_features(void) /* Switch airport off */ for_each_node_by_name(np, "radio") { - if (np && np->parent == macio_chips[0].of_node) { + if (np->parent == macio_chips[0].of_node) { macio_chips[0].flags |= MACIO_FLAG_AIRPORT_ON; core99_airport_enable(np, 0, 0); } } - of_node_put(np); } /* On all machines that support sound PM, switch sound off */ diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index ab2027cdf893..3bc075c788ef 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -1155,13 +1155,11 @@ void __init pmac_pcibios_after_init(void) pmac_call_feature(PMAC_FTR_1394_CABLE_POWER, nd, 0, 0); } } - of_node_put(nd); for_each_node_by_name(nd, "ethernet") { if (nd->parent && of_device_is_compatible(nd, "gmac") && of_device_is_compatible(nd->parent, "uni-north")) pmac_call_feature(PMAC_FTR_GMAC_ENABLE, nd, 0, 0); } - of_node_put(nd); } void pmac_pci_fixup_cardbus(struct pci_dev* dev) diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 227c1c3d585e..72d8054fa739 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -129,20 +129,35 @@ struct device_node *dlpar_configure_connector(u32 drc_index) struct property *property; struct property *last_property = NULL; struct cc_workarea *ccwa; + char *data_buf; int cc_token; - int rc; + int rc = -1; cc_token = rtas_token("ibm,configure-connector"); if (cc_token == RTAS_UNKNOWN_SERVICE) return NULL; - spin_lock(&rtas_data_buf_lock); - ccwa = (struct cc_workarea *)&rtas_data_buf[0]; + data_buf = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); + if (!data_buf) + return NULL; + + ccwa = (struct cc_workarea *)&data_buf[0]; ccwa->drc_index = drc_index; ccwa->zero = 0; - rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL); - while (rc) { + do { + /* Since we release the rtas_data_buf lock between configure + * connector calls we want to re-populate the rtas_data_buffer + * with the contents of the previous call. + */ + spin_lock(&rtas_data_buf_lock); + + memcpy(rtas_data_buf, data_buf, RTAS_DATA_BUF_SIZE); + rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL); + memcpy(data_buf, rtas_data_buf, RTAS_DATA_BUF_SIZE); + + spin_unlock(&rtas_data_buf_lock); + switch (rc) { case NEXT_SIBLING: dn = dlpar_parse_cc_node(ccwa); @@ -197,18 +212,19 @@ struct device_node *dlpar_configure_connector(u32 drc_index) "returned from configure-connector\n", rc); goto cc_error; } + } while (rc); - rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL); +cc_error: + kfree(data_buf); + + if (rc) { + if (first_dn) + dlpar_free_cc_nodes(first_dn); + + return NULL; } - spin_unlock(&rtas_data_buf_lock); return first_dn; - -cc_error: - if (first_dn) - dlpar_free_cc_nodes(first_dn); - spin_unlock(&rtas_data_buf_lock); - return NULL; } static struct device_node *derive_parent(const char *path) diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 395848e30c52..a77bcaed80af 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -403,7 +403,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) pci->phb->dma_window_size = 0x8000000ul; pci->phb->dma_window_base_cur = 0x8000000ul; - tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL, + tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, pci->phb->node); iommu_table_setparms(pci->phb, dn, tbl); @@ -448,7 +448,7 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) pdn->full_name, ppci->iommu_table); if (!ppci->iommu_table) { - tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL, + tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, ppci->phb->node); iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window, bus->number); @@ -478,7 +478,7 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev) struct pci_controller *phb = PCI_DN(dn)->phb; pr_debug(" --> first child, no bridge. Allocating iommu table.\n"); - tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL, + tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, phb->node); iommu_table_setparms(phb, dn, tbl); PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node); @@ -544,7 +544,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) pci = PCI_DN(pdn); if (!pci->iommu_table) { - tbl = kmalloc_node(sizeof(struct iommu_table), GFP_KERNEL, + tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, pci->phb->node); iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window, pci->phb->bus->number); diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 3b1bf61c45be..0317cce877c6 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -182,10 +182,13 @@ static int smp_pSeries_cpu_bootable(unsigned int nr) /* Special case - we inhibit secondary thread startup * during boot if the user requests it. */ - if (system_state < SYSTEM_RUNNING && - cpu_has_feature(CPU_FTR_SMT) && - !smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) - return 0; + if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) { + if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0) + return 0; + if (smt_enabled_at_boot + && cpu_thread_in_core(nr) >= smt_enabled_at_boot) + return 0; + } return 1; } diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index 5b22b07c8f67..93834b0d8272 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -928,8 +928,10 @@ void xics_migrate_irqs_away(void) if (xics_status[0] != hw_cpu) goto unlock; - printk(KERN_WARNING "IRQ %u affinity broken off cpu %u\n", - virq, cpu); + /* This is expected during cpu offline. */ + if (cpu_online(cpu)) + printk(KERN_WARNING "IRQ %u affinity broken off cpu %u\n", + virq, cpu); /* Reset affinity to all cpus */ cpumask_setall(irq_to_desc(virq)->affinity); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 209384b6e039..4ae933225251 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -399,6 +399,8 @@ DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013E, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020E, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020, quirk_fsl_pcie_header); +DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1021E, quirk_fsl_pcie_header); +DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1021, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022E, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022, quirk_fsl_pcie_header); DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2010E, quirk_fsl_pcie_header); diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 6425abe5b7db..3017532319c8 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -240,12 +240,13 @@ struct rio_priv { static void __iomem *rio_regs_win; +#ifdef CONFIG_E500 static int (*saved_mcheck_exception)(struct pt_regs *regs); static int fsl_rio_mcheck_exception(struct pt_regs *regs) { const struct exception_table_entry *entry = NULL; - unsigned long reason = (mfspr(SPRN_MCSR) & MCSR_MASK); + unsigned long reason = mfspr(SPRN_MCSR); if (reason & MCSR_BUS_RBERR) { reason = in_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR)); @@ -269,6 +270,7 @@ static int fsl_rio_mcheck_exception(struct pt_regs *regs) else return cur_cpu_spec->machine_check(regs); } +#endif /** * fsl_rio_doorbell_send - Send a MPC85xx doorbell message @@ -1517,8 +1519,10 @@ int fsl_rio_setup(struct platform_device *dev) fsl_rio_doorbell_init(port); fsl_rio_port_write_init(port); +#ifdef CONFIG_E500 saved_mcheck_exception = ppc_md.machine_check_exception; ppc_md.machine_check_exception = fsl_rio_mcheck_exception; +#endif /* Ensure that RFXE is set */ mtspr(SPRN_HID1, (mfspr(SPRN_HID1) | 0x20000)); diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 3da8014931c9..90020de4dcf2 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -640,6 +640,7 @@ unsigned int qe_get_num_of_snums(void) if ((num_of_snums < 28) || (num_of_snums > QE_NUM_OF_SNUM)) { /* No QE ever has fewer than 28 SNUMs */ pr_err("QE: number of snum is invalid\n"); + of_node_put(qe); return -EINVAL; } } diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 0554445200bf..d17d04cfb2cd 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2880,15 +2880,14 @@ static void xmon_init(int enable) } #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_xmon(int key, struct tty_struct *tty) +static void sysrq_handle_xmon(int key) { /* ensure xmon is enabled */ xmon_init(1); debugger(get_irq_regs()); } -static struct sysrq_key_op sysrq_xmon_op = -{ +static struct sysrq_key_op sysrq_xmon_op = { .handler = sysrq_handle_xmon, .help_msg = "Xmon", .action_msg = "Entering xmon", diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index f0777a47e3a5..75976a141947 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -95,6 +95,7 @@ config S390 select HAVE_KVM if 64BIT select HAVE_ARCH_TRACEHOOK select INIT_ALL_POSSIBLE + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 @@ -198,6 +199,13 @@ config HOTPLUG_CPU can be controlled through /sys/devices/system/cpu/cpu#. Say N if you want to disable CPU hotplug. +config SCHED_BOOK + bool "Book scheduler support" + depends on SMP + help + Book scheduler support improves the CPU scheduler's decision making + when dealing with machines that have several books. + config MATHEMU bool "IEEE FPU emulation" depends on MARCH_G5 diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 104f2007f097..a875c2f542e1 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -181,7 +181,7 @@ static inline int is_compat_task(void) #endif -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index 498bc3892385..881d94590aeb 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -12,10 +12,6 @@ #ifndef __ASM_HARDIRQ_H #define __ASM_HARDIRQ_H -#include <linux/threads.h> -#include <linux/sched.h> -#include <linux/cache.h> -#include <linux/interrupt.h> #include <asm/lowcore.h> #define local_softirq_pending() (S390_lowcore.softirq_pending) diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index 670a1d1745d2..bb8343d157bc 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -97,6 +97,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, { pte_t pte = huge_ptep_get(ptep); + mm->context.flush_mm = 1; pmd_clear((pmd_t *) ptep); return pte; } @@ -167,7 +168,8 @@ static inline void huge_ptep_invalidate(struct mm_struct *mm, ({ \ pte_t __pte = huge_ptep_get(__ptep); \ if (pte_write(__pte)) { \ - if (atomic_read(&(__mm)->mm_users) > 1 || \ + (__mm)->context.flush_mm = 1; \ + if (atomic_read(&(__mm)->context.attach_count) > 1 || \ (__mm) != current->active_mm) \ huge_ptep_invalidate(__mm, __addr, __ptep); \ set_huge_pte_at(__mm, __addr, __ptep, \ diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 99e3409102b9..78522cdefdd4 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -2,6 +2,8 @@ #define __MMU_H typedef struct { + atomic_t attach_count; + unsigned int flush_mm; spinlock_t list_lock; struct list_head crst_list; struct list_head pgtable_list; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 976e273988c2..a6f0e7cc9cde 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -11,11 +11,14 @@ #include <asm/pgalloc.h> #include <asm/uaccess.h> +#include <asm/tlbflush.h> #include <asm-generic/mm_hooks.h> static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + atomic_set(&mm->context.attach_count, 0); + mm->context.flush_mm = 0; mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; #ifdef CONFIG_64BIT mm->context.asce_bits |= _ASCE_TYPE_REGION3; @@ -76,6 +79,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); update_mm(next, tsk); + atomic_dec(&prev->context.attach_count); + WARN_ON(atomic_read(&prev->context.attach_count) < 0); + atomic_inc(&next->context.attach_count); + /* Check for TLBs not flushed yet */ + if (next->context.flush_mm) + __tlb_flush_mm(next); } #define enter_lazy_tlb(mm,tsk) do { } while (0) diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index 3840cbe77637..a75f168d2718 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -4,7 +4,6 @@ * Copyright 2009 Martin Schwidefsky, IBM Corporation. */ -static inline void set_perf_event_pending(void) {} -static inline void clear_perf_event_pending(void) {} +/* Empty, just to avoid compiling error */ #define PERF_EVENT_INDEX_OFFSET 0 diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 89a504c3f12e..3157441ee1da 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -880,7 +880,8 @@ static inline void ptep_invalidate(struct mm_struct *mm, #define ptep_get_and_clear(__mm, __address, __ptep) \ ({ \ pte_t __pte = *(__ptep); \ - if (atomic_read(&(__mm)->mm_users) > 1 || \ + (__mm)->context.flush_mm = 1; \ + if (atomic_read(&(__mm)->context.attach_count) > 1 || \ (__mm) != current->active_mm) \ ptep_invalidate(__mm, __address, __ptep); \ else \ @@ -923,7 +924,8 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, ({ \ pte_t __pte = *(__ptep); \ if (pte_write(__pte)) { \ - if (atomic_read(&(__mm)->mm_users) > 1 || \ + (__mm)->context.flush_mm = 1; \ + if (atomic_read(&(__mm)->context.attach_count) > 1 || \ (__mm) != current->active_mm) \ ptep_invalidate(__mm, __addr, __ptep); \ set_pte_at(__mm, __addr, __ptep, pte_wrprotect(__pte)); \ diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h index cef66210c846..38ddd8a9a9e8 100644 --- a/arch/s390/include/asm/system.h +++ b/arch/s390/include/asm/system.h @@ -97,7 +97,6 @@ static inline void restore_access_regs(unsigned int *acrs) extern void account_vtime(struct task_struct *, struct task_struct *); extern void account_tick_vtime(struct task_struct *); -extern void account_system_vtime(struct task_struct *); #ifdef CONFIG_PFAULT extern void pfault_irq_init(void); diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 81150b053689..fd1c00d08bf5 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -50,8 +50,7 @@ static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm, struct mmu_gather *tlb = &get_cpu_var(mmu_gathers); tlb->mm = mm; - tlb->fullmm = full_mm_flush || (num_online_cpus() == 1) || - (atomic_read(&mm->mm_users) <= 1 && mm == current->active_mm); + tlb->fullmm = full_mm_flush; tlb->nr_ptes = 0; tlb->nr_pxds = TLB_NR_PTRS; if (tlb->fullmm) diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 304cffa623e1..29d5d6d4becc 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -94,8 +94,12 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) static inline void __tlb_flush_mm_cond(struct mm_struct * mm) { - if (atomic_read(&mm->mm_users) <= 1 && mm == current->active_mm) + spin_lock(&mm->page_table_lock); + if (mm->context.flush_mm) { __tlb_flush_mm(mm); + mm->context.flush_mm = 0; + } + spin_unlock(&mm->page_table_lock); } /* diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 831bd033ea77..051107a2c5e2 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -3,15 +3,32 @@ #include <linux/cpumask.h> -#define mc_capable() (1) - -const struct cpumask *cpu_coregroup_mask(unsigned int cpu); - extern unsigned char cpu_core_id[NR_CPUS]; extern cpumask_t cpu_core_map[NR_CPUS]; +static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu) +{ + return &cpu_core_map[cpu]; +} + #define topology_core_id(cpu) (cpu_core_id[cpu]) #define topology_core_cpumask(cpu) (&cpu_core_map[cpu]) +#define mc_capable() (1) + +#ifdef CONFIG_SCHED_BOOK + +extern unsigned char cpu_book_id[NR_CPUS]; +extern cpumask_t cpu_book_map[NR_CPUS]; + +static inline const struct cpumask *cpu_book_mask(unsigned int cpu) +{ + return &cpu_book_map[cpu]; +} + +#define topology_book_id(cpu) (cpu_book_id[cpu]) +#define topology_book_cpumask(cpu) (&cpu_book_map[cpu]) + +#endif /* CONFIG_SCHED_BOOK */ int topology_set_cpu_management(int fc); void topology_schedule_update(void); @@ -30,6 +47,8 @@ static inline void s390_init_cpu_topology(void) }; #endif +#define SD_BOOK_INIT SD_CPU_INIT + #include <asm-generic/topology.h> #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 403fb430a896..ff579b6bde06 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -42,8 +42,8 @@ long sys_clone(unsigned long newsp, unsigned long clone_flags, int __user *parent_tidptr, int __user *child_tidptr); long sys_vfork(void); void execve_tail(void); -long sys_execve(const char __user *name, char __user * __user *argv, - char __user * __user *envp); +long sys_execve(const char __user *name, const char __user *const __user *argv, + const char __user *const __user *envp); long sys_sigsuspend(int history0, int history1, old_sigset_t mask); long sys_sigaction(int sig, const struct old_sigaction __user *act, struct old_sigaction __user *oact); diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 22cfd634c355..f7167ee4604c 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -407,10 +407,9 @@ int module_finalize(const Elf_Ehdr *hdr, { vfree(me->arch.syminfo); me->arch.syminfo = NULL; - return module_bug_finalize(hdr, sechdrs, me); + return 0; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 541053ed234e..8127ebd59c4d 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -583,6 +583,7 @@ int __cpuinit __cpu_up(unsigned int cpu) sf->gprs[9] = (unsigned long) sf; cpu_lowcore->save_area[15] = (unsigned long) sf; __ctl_store(cpu_lowcore->cregs_save_area, 0, 15); + atomic_inc(&init_mm.context.attach_count); asm volatile( " stam 0,15,0(%0)" : : "a" (&cpu_lowcore->access_regs_save_area) : "memory"); @@ -659,6 +660,7 @@ void __cpu_die(unsigned int cpu) while (sigp_p(0, cpu, sigp_set_prefix) == sigp_busy) udelay(10); smp_free_lowcore(cpu); + atomic_dec(&init_mm.context.attach_count); pr_info("Processor %d stopped\n", cpu); } diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index bcef00766a64..13559c993847 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -57,8 +57,8 @@ struct tl_info { union tl_entry tle[0]; }; -struct core_info { - struct core_info *next; +struct mask_info { + struct mask_info *next; unsigned char id; cpumask_t mask; }; @@ -66,7 +66,6 @@ struct core_info { static int topology_enabled; static void topology_work_fn(struct work_struct *work); static struct tl_info *tl_info; -static struct core_info core_info; static int machine_has_topology; static struct timer_list topology_timer; static void set_topology_timer(void); @@ -74,38 +73,37 @@ static DECLARE_WORK(topology_work, topology_work_fn); /* topology_lock protects the core linked list */ static DEFINE_SPINLOCK(topology_lock); +static struct mask_info core_info; cpumask_t cpu_core_map[NR_CPUS]; unsigned char cpu_core_id[NR_CPUS]; -static cpumask_t cpu_coregroup_map(unsigned int cpu) +#ifdef CONFIG_SCHED_BOOK +static struct mask_info book_info; +cpumask_t cpu_book_map[NR_CPUS]; +unsigned char cpu_book_id[NR_CPUS]; +#endif + +static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) { - struct core_info *core = &core_info; - unsigned long flags; cpumask_t mask; cpus_clear(mask); if (!topology_enabled || !machine_has_topology) return cpu_possible_map; - spin_lock_irqsave(&topology_lock, flags); - while (core) { - if (cpu_isset(cpu, core->mask)) { - mask = core->mask; + while (info) { + if (cpu_isset(cpu, info->mask)) { + mask = info->mask; break; } - core = core->next; + info = info->next; } - spin_unlock_irqrestore(&topology_lock, flags); if (cpus_empty(mask)) mask = cpumask_of_cpu(cpu); return mask; } -const struct cpumask *cpu_coregroup_mask(unsigned int cpu) -{ - return &cpu_core_map[cpu]; -} - -static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core) +static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book, + struct mask_info *core) { unsigned int cpu; @@ -117,23 +115,35 @@ static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core) rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin; for_each_present_cpu(lcpu) { - if (cpu_logical_map(lcpu) == rcpu) { - cpu_set(lcpu, core->mask); - cpu_core_id[lcpu] = core->id; - smp_cpu_polarization[lcpu] = tl_cpu->pp; - } + if (cpu_logical_map(lcpu) != rcpu) + continue; +#ifdef CONFIG_SCHED_BOOK + cpu_set(lcpu, book->mask); + cpu_book_id[lcpu] = book->id; +#endif + cpu_set(lcpu, core->mask); + cpu_core_id[lcpu] = core->id; + smp_cpu_polarization[lcpu] = tl_cpu->pp; } } } -static void clear_cores(void) +static void clear_masks(void) { - struct core_info *core = &core_info; + struct mask_info *info; - while (core) { - cpus_clear(core->mask); - core = core->next; + info = &core_info; + while (info) { + cpus_clear(info->mask); + info = info->next; + } +#ifdef CONFIG_SCHED_BOOK + info = &book_info; + while (info) { + cpus_clear(info->mask); + info = info->next; } +#endif } static union tl_entry *next_tle(union tl_entry *tle) @@ -146,29 +156,36 @@ static union tl_entry *next_tle(union tl_entry *tle) static void tl_to_cores(struct tl_info *info) { +#ifdef CONFIG_SCHED_BOOK + struct mask_info *book = &book_info; +#else + struct mask_info *book = NULL; +#endif + struct mask_info *core = &core_info; union tl_entry *tle, *end; - struct core_info *core = &core_info; + spin_lock_irq(&topology_lock); - clear_cores(); + clear_masks(); tle = info->tle; end = (union tl_entry *)((unsigned long)info + info->length); while (tle < end) { switch (tle->nl) { - case 5: - case 4: - case 3: +#ifdef CONFIG_SCHED_BOOK case 2: + book = book->next; + book->id = tle->container.id; break; +#endif case 1: core = core->next; core->id = tle->container.id; break; case 0: - add_cpus_to_core(&tle->cpu, core); + add_cpus_to_mask(&tle->cpu, book, core); break; default: - clear_cores(); + clear_masks(); machine_has_topology = 0; goto out; } @@ -221,10 +238,29 @@ int topology_set_cpu_management(int fc) static void update_cpu_core_map(void) { + unsigned long flags; int cpu; - for_each_possible_cpu(cpu) - cpu_core_map[cpu] = cpu_coregroup_map(cpu); + spin_lock_irqsave(&topology_lock, flags); + for_each_possible_cpu(cpu) { + cpu_core_map[cpu] = cpu_group_map(&core_info, cpu); +#ifdef CONFIG_SCHED_BOOK + cpu_book_map[cpu] = cpu_group_map(&book_info, cpu); +#endif + } + spin_unlock_irqrestore(&topology_lock, flags); +} + +static void store_topology(struct tl_info *info) +{ +#ifdef CONFIG_SCHED_BOOK + int rc; + + rc = stsi(info, 15, 1, 3); + if (rc != -ENOSYS) + return; +#endif + stsi(info, 15, 1, 2); } int arch_update_cpu_topology(void) @@ -238,7 +274,7 @@ int arch_update_cpu_topology(void) topology_update_polarization_simple(); return 0; } - stsi(info, 15, 1, 2); + store_topology(info); tl_to_cores(info); update_cpu_core_map(); for_each_online_cpu(cpu) { @@ -299,12 +335,24 @@ out: } __initcall(init_topology_update); +static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset) +{ + int i, nr_masks; + + nr_masks = info->mag[NR_MAG - offset]; + for (i = 0; i < info->mnest - offset; i++) + nr_masks *= info->mag[NR_MAG - offset - 1 - i]; + nr_masks = max(nr_masks, 1); + for (i = 0; i < nr_masks; i++) { + mask->next = alloc_bootmem(sizeof(struct mask_info)); + mask = mask->next; + } +} + void __init s390_init_cpu_topology(void) { unsigned long long facility_bits; struct tl_info *info; - struct core_info *core; - int nr_cores; int i; if (stfle(&facility_bits, 1) <= 0) @@ -315,25 +363,13 @@ void __init s390_init_cpu_topology(void) tl_info = alloc_bootmem_pages(PAGE_SIZE); info = tl_info; - stsi(info, 15, 1, 2); - - nr_cores = info->mag[NR_MAG - 2]; - for (i = 0; i < info->mnest - 2; i++) - nr_cores *= info->mag[NR_MAG - 3 - i]; - + store_topology(info); pr_info("The CPU configuration topology of the machine is:"); for (i = 0; i < NR_MAG; i++) printk(" %d", info->mag[i]); printk(" / %d\n", info->mnest); - - core = &core_info; - for (i = 0; i < nr_cores; i++) { - core->next = alloc_bootmem(sizeof(struct core_info)); - core = core->next; - if (!core) - goto error; - } - return; -error: - machine_has_topology = 0; + alloc_masks(info, &core_info, 2); +#ifdef CONFIG_SCHED_BOOK + alloc_masks(info, &book_info, 3); +#endif } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index acc91c75bc94..30eb6d02ddb8 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -74,6 +74,8 @@ void __init paging_init(void) __ctl_load(S390_lowcore.kernel_asce, 13, 13); __raw_local_irq_ssm(ssm_mask); + atomic_set(&init_mm.context.attach_count, 1); + sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 33990fa95af0..35b6879628a0 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -16,6 +16,7 @@ config SUPERH select HAVE_ARCH_TRACEHOOK select HAVE_DMA_API_DEBUG select HAVE_DMA_ATTRS + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC select HAVE_KERNEL_GZIP @@ -249,6 +250,11 @@ config ARCH_SHMOBILE select PM select PM_RUNTIME +config CPU_HAS_PMU + depends on CPU_SH4 || CPU_SH4A + default y + bool + if SUPERH32 choice @@ -738,6 +744,14 @@ config GUSA_RB LLSC, this should be more efficient than the other alternative of disabling interrupts around the atomic sequence. +config HW_PERF_EVENTS + bool "Enable hardware performance counter support for perf events" + depends on PERF_EVENTS && CPU_HAS_PMU + default y + help + Enable hardware performance counter support for perf events. If + disabled, perf events will use software events only. + source "drivers/sh/Kconfig" endmenu diff --git a/arch/sh/include/asm/perf_event.h b/arch/sh/include/asm/perf_event.h index 3d0c9f36d150..14308bed7ea5 100644 --- a/arch/sh/include/asm/perf_event.h +++ b/arch/sh/include/asm/perf_event.h @@ -26,11 +26,4 @@ extern int register_sh_pmu(struct sh_pmu *); extern int reserve_pmc_hardware(void); extern void release_pmc_hardware(void); -static inline void set_perf_event_pending(void) -{ - /* Nothing to see here, move along. */ -} - -#define PERF_EVENT_INDEX_OFFSET 0 - #endif /* __ASM_SH_PERF_EVENT_H */ diff --git a/arch/sh/kernel/module.c b/arch/sh/kernel/module.c index 43adddfe4c04..ae0be697a89e 100644 --- a/arch/sh/kernel/module.c +++ b/arch/sh/kernel/module.c @@ -149,13 +149,11 @@ int module_finalize(const Elf_Ehdr *hdr, int ret = 0; ret |= module_dwarf_finalize(hdr, sechdrs, me); - ret |= module_bug_finalize(hdr, sechdrs, me); return ret; } void module_arch_cleanup(struct module *mod) { - module_bug_cleanup(mod); module_dwarf_cleanup(mod); } diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c index a9dd3abde28e..d5ca1ef50fa9 100644 --- a/arch/sh/kernel/perf_callchain.c +++ b/arch/sh/kernel/perf_callchain.c @@ -14,11 +14,6 @@ #include <asm/unwinder.h> #include <asm/ptrace.h> -static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip) -{ - if (entry->nr < PERF_MAX_STACK_DEPTH) - entry->ip[entry->nr++] = ip; -} static void callchain_warning(void *data, char *msg) { @@ -39,7 +34,7 @@ static void callchain_address(void *data, unsigned long addr, int reliable) struct perf_callchain_entry *entry = data; if (reliable) - callchain_store(entry, addr); + perf_callchain_store(entry, addr); } static const struct stacktrace_ops callchain_ops = { @@ -49,47 +44,10 @@ static const struct stacktrace_ops callchain_ops = { .address = callchain_address, }; -static void -perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) +void +perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { - callchain_store(entry, PERF_CONTEXT_KERNEL); - callchain_store(entry, regs->pc); + perf_callchain_store(entry, regs->pc); unwind_stack(NULL, regs, NULL, &callchain_ops, entry); } - -static void -perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry) -{ - int is_user; - - if (!regs) - return; - - is_user = user_mode(regs); - - if (is_user && current->state != TASK_RUNNING) - return; - - /* - * Only the kernel side is implemented for now. - */ - if (!is_user) - perf_callchain_kernel(regs, entry); -} - -/* - * No need for separate IRQ and NMI entries. - */ -static DEFINE_PER_CPU(struct perf_callchain_entry, callchain); - -struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) -{ - struct perf_callchain_entry *entry = &__get_cpu_var(callchain); - - entry->nr = 0; - - perf_do_callchain(regs, entry); - - return entry; -} diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7a3dc3567258..5a4b33435650 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -59,6 +59,24 @@ static inline int sh_pmu_initialized(void) return !!sh_pmu; } +const char *perf_pmu_name(void) +{ + if (!sh_pmu) + return NULL; + + return sh_pmu->name; +} +EXPORT_SYMBOL_GPL(perf_pmu_name); + +int perf_num_counters(void) +{ + if (!sh_pmu) + return 0; + + return sh_pmu->num_events; +} +EXPORT_SYMBOL_GPL(perf_num_counters); + /* * Release the PMU if this is the last perf_event. */ @@ -206,50 +224,80 @@ again: local64_add(delta, &event->count); } -static void sh_pmu_disable(struct perf_event *event) +static void sh_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; - clear_bit(idx, cpuc->active_mask); - sh_pmu->disable(hwc, idx); + if (!(event->hw.state & PERF_HES_STOPPED)) { + sh_pmu->disable(hwc, idx); + cpuc->events[idx] = NULL; + event->hw.state |= PERF_HES_STOPPED; + } + + if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) { + sh_perf_event_update(event, &event->hw, idx); + event->hw.state |= PERF_HES_UPTODATE; + } +} + +static void sh_pmu_start(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (WARN_ON_ONCE(idx == -1)) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); - barrier(); + cpuc->events[idx] = event; + event->hw.state = 0; + sh_pmu->enable(hwc, idx); +} - sh_perf_event_update(event, &event->hw, idx); +static void sh_pmu_del(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - cpuc->events[idx] = NULL; - clear_bit(idx, cpuc->used_mask); + sh_pmu_stop(event, PERF_EF_UPDATE); + __clear_bit(event->hw.idx, cpuc->used_mask); perf_event_update_userpage(event); } -static int sh_pmu_enable(struct perf_event *event) +static int sh_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; + int ret = -EAGAIN; + + perf_pmu_disable(event->pmu); - if (test_and_set_bit(idx, cpuc->used_mask)) { + if (__test_and_set_bit(idx, cpuc->used_mask)) { idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events); if (idx == sh_pmu->num_events) - return -EAGAIN; + goto out; - set_bit(idx, cpuc->used_mask); + __set_bit(idx, cpuc->used_mask); hwc->idx = idx; } sh_pmu->disable(hwc, idx); - cpuc->events[idx] = event; - set_bit(idx, cpuc->active_mask); - - sh_pmu->enable(hwc, idx); + event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (flags & PERF_EF_START) + sh_pmu_start(event, PERF_EF_RELOAD); perf_event_update_userpage(event); - - return 0; + ret = 0; +out: + perf_pmu_enable(event->pmu); + return ret; } static void sh_pmu_read(struct perf_event *event) @@ -257,24 +305,56 @@ static void sh_pmu_read(struct perf_event *event) sh_perf_event_update(event, &event->hw, event->hw.idx); } -static const struct pmu pmu = { - .enable = sh_pmu_enable, - .disable = sh_pmu_disable, - .read = sh_pmu_read, -}; - -const struct pmu *hw_perf_event_init(struct perf_event *event) +static int sh_pmu_event_init(struct perf_event *event) { - int err = __hw_perf_event_init(event); + int err; + + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HW_CACHE: + case PERF_TYPE_HARDWARE: + err = __hw_perf_event_init(event); + break; + + default: + return -ENOENT; + } + if (unlikely(err)) { if (event->destroy) event->destroy(event); - return ERR_PTR(err); } - return &pmu; + return err; +} + +static void sh_pmu_enable(struct pmu *pmu) +{ + if (!sh_pmu_initialized()) + return; + + sh_pmu->enable_all(); +} + +static void sh_pmu_disable(struct pmu *pmu) +{ + if (!sh_pmu_initialized()) + return; + + sh_pmu->disable_all(); } +static struct pmu pmu = { + .pmu_enable = sh_pmu_enable, + .pmu_disable = sh_pmu_disable, + .event_init = sh_pmu_event_init, + .add = sh_pmu_add, + .del = sh_pmu_del, + .start = sh_pmu_start, + .stop = sh_pmu_stop, + .read = sh_pmu_read, +}; + static void sh_pmu_setup(int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); @@ -299,32 +379,17 @@ sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) return NOTIFY_OK; } -void hw_perf_enable(void) -{ - if (!sh_pmu_initialized()) - return; - - sh_pmu->enable_all(); -} - -void hw_perf_disable(void) -{ - if (!sh_pmu_initialized()) - return; - - sh_pmu->disable_all(); -} - -int __cpuinit register_sh_pmu(struct sh_pmu *pmu) +int __cpuinit register_sh_pmu(struct sh_pmu *_pmu) { if (sh_pmu) return -EBUSY; - sh_pmu = pmu; + sh_pmu = _pmu; - pr_info("Performance Events: %s support registered\n", pmu->name); + pr_info("Performance Events: %s support registered\n", _pmu->name); - WARN_ON(pmu->num_events > MAX_HWEVENTS); + WARN_ON(_pmu->num_events > MAX_HWEVENTS); + perf_pmu_register(&pmu); perf_cpu_notifier(sh_pmu_notifier); return 0; } diff --git a/arch/sh/oprofile/Makefile b/arch/sh/oprofile/Makefile index 4886c5c1786c..e85aae73e3dc 100644 --- a/arch/sh/oprofile/Makefile +++ b/arch/sh/oprofile/Makefile @@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \ oprofilefs.o oprofile_stats.o \ timer_int.o ) +ifeq ($(CONFIG_HW_PERF_EVENTS),y) +DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o) +endif + oprofile-y := $(DRIVER_OBJS) common.o backtrace.o diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c index ac604937f3ee..e10d89376f9b 100644 --- a/arch/sh/oprofile/common.c +++ b/arch/sh/oprofile/common.c @@ -17,114 +17,45 @@ #include <linux/init.h> #include <linux/errno.h> #include <linux/smp.h> +#include <linux/perf_event.h> #include <asm/processor.h> -#include "op_impl.h" - -static struct op_sh_model *model; - -static struct op_counter_config ctr[20]; +#ifdef CONFIG_HW_PERF_EVENTS extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth); -static int op_sh_setup(void) -{ - /* Pre-compute the values to stuff in the hardware registers. */ - model->reg_setup(ctr); - - /* Configure the registers on all cpus. */ - on_each_cpu(model->cpu_setup, NULL, 1); - - return 0; -} - -static int op_sh_create_files(struct super_block *sb, struct dentry *root) +char *op_name_from_perf_id(void) { - int i, ret = 0; + const char *pmu; + char buf[20]; + int size; - for (i = 0; i < model->num_counters; i++) { - struct dentry *dir; - char buf[4]; + pmu = perf_pmu_name(); + if (!pmu) + return NULL; - snprintf(buf, sizeof(buf), "%d", i); - dir = oprofilefs_mkdir(sb, root, buf); + size = snprintf(buf, sizeof(buf), "sh/%s", pmu); + if (size > -1 && size < sizeof(buf)) + return buf; - ret |= oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled); - ret |= oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event); - ret |= oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel); - ret |= oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user); - - if (model->create_files) - ret |= model->create_files(sb, dir); - else - ret |= oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count); - - /* Dummy entries */ - ret |= oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask); - } - - return ret; + return NULL; } -static int op_sh_start(void) +int __init oprofile_arch_init(struct oprofile_operations *ops) { - /* Enable performance monitoring for all counters. */ - on_each_cpu(model->cpu_start, NULL, 1); + ops->backtrace = sh_backtrace; - return 0; + return oprofile_perf_init(ops); } -static void op_sh_stop(void) +void __exit oprofile_arch_exit(void) { - /* Disable performance monitoring for all counters. */ - on_each_cpu(model->cpu_stop, NULL, 1); + oprofile_perf_exit(); } - +#else int __init oprofile_arch_init(struct oprofile_operations *ops) { - struct op_sh_model *lmodel = NULL; - int ret; - - /* - * Always assign the backtrace op. If the counter initialization - * fails, we fall back to the timer which will still make use of - * this. - */ - ops->backtrace = sh_backtrace; - - /* - * XXX - * - * All of the SH7750/SH-4A counters have been converted to perf, - * this infrastructure hook is left for other users until they've - * had a chance to convert over, at which point all of this - * will be deleted. - */ - - if (!lmodel) - return -ENODEV; - if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER)) - return -ENODEV; - - ret = lmodel->init(); - if (unlikely(ret != 0)) - return ret; - - model = lmodel; - - ops->setup = op_sh_setup; - ops->create_files = op_sh_create_files; - ops->start = op_sh_start; - ops->stop = op_sh_stop; - ops->cpu_type = lmodel->cpu_type; - - printk(KERN_INFO "oprofile: using %s performance monitoring.\n", - lmodel->cpu_type); - - return 0; -} - -void oprofile_arch_exit(void) -{ - if (model && model->exit) - model->exit(); + pr_info("oprofile: hardware counters not available\n"); + return -ENODEV; } +void __exit oprofile_arch_exit(void) {} +#endif /* CONFIG_HW_PERF_EVENTS */ diff --git a/arch/sh/oprofile/op_impl.h b/arch/sh/oprofile/op_impl.h deleted file mode 100644 index 1244479ceb29..000000000000 --- a/arch/sh/oprofile/op_impl.h +++ /dev/null @@ -1,33 +0,0 @@ -#ifndef __OP_IMPL_H -#define __OP_IMPL_H - -/* Per-counter configuration as set via oprofilefs. */ -struct op_counter_config { - unsigned long enabled; - unsigned long event; - - unsigned long count; - - /* Dummy values for userspace tool compliance */ - unsigned long kernel; - unsigned long user; - unsigned long unit_mask; -}; - -/* Per-architecture configury and hooks. */ -struct op_sh_model { - void (*reg_setup)(struct op_counter_config *); - int (*create_files)(struct super_block *sb, struct dentry *dir); - void (*cpu_setup)(void *dummy); - int (*init)(void); - void (*exit)(void); - void (*cpu_start)(void *args); - void (*cpu_stop)(void *args); - char *cpu_type; - unsigned char num_counters; -}; - -/* arch/sh/oprofile/common.c */ -extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth); - -#endif /* __OP_IMPL_H */ diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 491e9d6de191..3e9d31401fb2 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -26,10 +26,12 @@ config SPARC select ARCH_WANT_OPTIONAL_GPIOLIB select RTC_CLASS select RTC_DRV_M48T59 + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG + select HAVE_ARCH_JUMP_LABEL config SPARC32 def_bool !64BIT @@ -53,6 +55,7 @@ config SPARC64 select RTC_DRV_BQ4802 select RTC_DRV_SUN4V select RTC_DRV_STARFIRE + select HAVE_IRQ_WORK select HAVE_PERF_EVENTS select PERF_USE_VMALLOC diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index f0c74227c737..bdb2ff880bdd 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -20,14 +20,14 @@ #define atomic64_set(v, i) (((v)->counter) = i) extern void atomic_add(int, atomic_t *); -extern void atomic64_add(int, atomic64_t *); +extern void atomic64_add(long, atomic64_t *); extern void atomic_sub(int, atomic_t *); -extern void atomic64_sub(int, atomic64_t *); +extern void atomic64_sub(long, atomic64_t *); extern int atomic_add_ret(int, atomic_t *); -extern long atomic64_add_ret(int, atomic64_t *); +extern long atomic64_add_ret(long, atomic64_t *); extern int atomic_sub_ret(int, atomic_t *); -extern long atomic64_sub_ret(int, atomic64_t *); +extern long atomic64_sub_ret(long, atomic64_t *); #define atomic_dec_return(v) atomic_sub_ret(1, v) #define atomic64_dec_return(v) atomic64_sub_ret(1, v) diff --git a/arch/sparc/include/asm/backoff.h b/arch/sparc/include/asm/backoff.h index fa1fdf67e350..db3af0d30fb1 100644 --- a/arch/sparc/include/asm/backoff.h +++ b/arch/sparc/include/asm/backoff.h @@ -8,6 +8,9 @@ #define BACKOFF_SETUP(reg) \ mov 1, reg +#define BACKOFF_LABEL(spin_label, continue_label) \ + spin_label + #define BACKOFF_SPIN(reg, tmp, label) \ mov reg, tmp; \ 88: brnz,pt tmp, 88b; \ @@ -22,9 +25,11 @@ #else #define BACKOFF_SETUP(reg) -#define BACKOFF_SPIN(reg, tmp, label) \ - ba,pt %xcc, label; \ - nop; + +#define BACKOFF_LABEL(spin_label, continue_label) \ + continue_label + +#define BACKOFF_SPIN(reg, tmp, label) #endif diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 5016f76ea98a..6f57325bb883 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -167,7 +167,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current_thread_info()->kregs; unsigned long usp = regs->u_regs[UREG_I6]; diff --git a/arch/sparc/include/asm/jump_label.h b/arch/sparc/include/asm/jump_label.h new file mode 100644 index 000000000000..62e66d7b2fb6 --- /dev/null +++ b/arch/sparc/include/asm/jump_label.h @@ -0,0 +1,32 @@ +#ifndef _ASM_SPARC_JUMP_LABEL_H +#define _ASM_SPARC_JUMP_LABEL_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <asm/system.h> + +#define JUMP_LABEL_NOP_SIZE 4 + +#define JUMP_LABEL(key, label) \ + do { \ + asm goto("1:\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".pushsection __jump_table, \"a\"\n\t"\ + ".word 1b, %l[" #label "], %c0\n\t" \ + ".popsection \n\t" \ + : : "i" (key) : : label);\ + } while (0) + +#endif /* __KERNEL__ */ + +typedef u32 jump_label_t; + +struct jump_entry { + jump_label_t code; + jump_label_t target; + jump_label_t key; +}; + +#endif diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a5db0317b5fb..3e0b2d62303d 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -185,9 +185,8 @@ extern int prom_getunumber(int syndrome_code, char *buf, int buflen); /* Retain physical memory to the caller across soft resets. */ -extern unsigned long prom_retain(const char *name, - unsigned long pa_low, unsigned long pa_high, - long size, long align); +extern int prom_retain(const char *name, unsigned long size, + unsigned long align, unsigned long *paddr); /* Load explicit I/D TLB entries into the calling processor. */ extern long prom_itlb_load(unsigned long index, @@ -287,26 +286,6 @@ extern void prom_sun4v_guest_soft_state(void); extern int prom_ihandle2path(int handle, char *buffer, int bufsize); /* Client interface level routines. */ -extern long p1275_cmd(const char *, long, ...); - -#if 0 -#define P1275_SIZE(x) ((((long)((x) / 32)) << 32) | (x)) -#else -#define P1275_SIZE(x) x -#endif - -/* We support at most 16 input and 1 output argument */ -#define P1275_ARG_NUMBER 0 -#define P1275_ARG_IN_STRING 1 -#define P1275_ARG_OUT_BUF 2 -#define P1275_ARG_OUT_32B 3 -#define P1275_ARG_IN_FUNCTION 4 -#define P1275_ARG_IN_BUF 5 -#define P1275_ARG_IN_64B 6 - -#define P1275_IN(x) ((x) & 0xf) -#define P1275_OUT(x) (((x) << 4) & 0xf0) -#define P1275_INOUT(i,o) (P1275_IN(i)|P1275_OUT(o)) -#define P1275_ARG(n,x) ((x) << ((n)*3 + 8)) +extern void p1275_cmd_direct(unsigned long *); #endif /* !(__SPARC64_OPLIB_H) */ diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h index 727af70646cb..6e8bfa1786da 100644 --- a/arch/sparc/include/asm/perf_event.h +++ b/arch/sparc/include/asm/perf_event.h @@ -1,10 +1,6 @@ #ifndef __ASM_SPARC_PERF_EVENT_H #define __ASM_SPARC_PERF_EVENT_H -extern void set_perf_event_pending(void); - -#define PERF_EVENT_INDEX_OFFSET 0 - #ifdef CONFIG_PERF_EVENTS #include <asm/ptrace.h> diff --git a/arch/sparc/include/asm/rwsem-const.h b/arch/sparc/include/asm/rwsem-const.h deleted file mode 100644 index e4c61a18bb28..000000000000 --- a/arch/sparc/include/asm/rwsem-const.h +++ /dev/null @@ -1,12 +0,0 @@ -/* rwsem-const.h: RW semaphore counter constants. */ -#ifndef _SPARC64_RWSEM_CONST_H -#define _SPARC64_RWSEM_CONST_H - -#define RWSEM_UNLOCKED_VALUE 0x00000000 -#define RWSEM_ACTIVE_BIAS 0x00000001 -#define RWSEM_ACTIVE_MASK 0x0000ffff -#define RWSEM_WAITING_BIAS (-0x00010000) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -#endif /* _SPARC64_RWSEM_CONST_H */ diff --git a/arch/sparc/include/asm/rwsem.h b/arch/sparc/include/asm/rwsem.h index 6e5621006f85..a2b4302869bc 100644 --- a/arch/sparc/include/asm/rwsem.h +++ b/arch/sparc/include/asm/rwsem.h @@ -15,16 +15,21 @@ #include <linux/list.h> #include <linux/spinlock.h> -#include <asm/rwsem-const.h> struct rwsem_waiter; struct rw_semaphore { - signed int count; - spinlock_t wait_lock; - struct list_head wait_list; + signed long count; +#define RWSEM_UNLOCKED_VALUE 0x00000000L +#define RWSEM_ACTIVE_BIAS 0x00000001L +#define RWSEM_ACTIVE_MASK 0xffffffffL +#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) +#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS +#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) + spinlock_t wait_lock; + struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; + struct lockdep_map dep_map; #endif }; @@ -41,6 +46,11 @@ struct rw_semaphore { #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) +extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); + extern void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key); @@ -51,27 +61,103 @@ do { \ __init_rwsem((sem), #sem, &__key); \ } while (0) -extern void __down_read(struct rw_semaphore *sem); -extern int __down_read_trylock(struct rw_semaphore *sem); -extern void __down_write(struct rw_semaphore *sem); -extern int __down_write_trylock(struct rw_semaphore *sem); -extern void __up_read(struct rw_semaphore *sem); -extern void __up_write(struct rw_semaphore *sem); -extern void __downgrade_write(struct rw_semaphore *sem); +/* + * lock for reading + */ +static inline void __down_read(struct rw_semaphore *sem) +{ + if (unlikely(atomic64_inc_return((atomic64_t *)(&sem->count)) <= 0L)) + rwsem_down_read_failed(sem); +} + +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + long tmp; + + while ((tmp = sem->count) >= 0L) { + if (tmp == cmpxchg(&sem->count, tmp, + tmp + RWSEM_ACTIVE_READ_BIAS)) { + return 1; + } + } + return 0; +} +/* + * lock for writing + */ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { - __down_write(sem); + long tmp; + + tmp = atomic64_add_return(RWSEM_ACTIVE_WRITE_BIAS, + (atomic64_t *)(&sem->count)); + if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) + rwsem_down_write_failed(sem); } -static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) +static inline void __down_write(struct rw_semaphore *sem) { - return atomic_add_return(delta, (atomic_t *)(&sem->count)); + __down_write_nested(sem, 0); +} + +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + long tmp; + + tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); + return tmp == RWSEM_UNLOCKED_VALUE; } -static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) +/* + * unlock after reading + */ +static inline void __up_read(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic64_dec_return((atomic64_t *)(&sem->count)); + if (unlikely(tmp < -1L && (tmp & RWSEM_ACTIVE_MASK) == 0L)) + rwsem_wake(sem); +} + +/* + * unlock after writing + */ +static inline void __up_write(struct rw_semaphore *sem) +{ + if (unlikely(atomic64_sub_return(RWSEM_ACTIVE_WRITE_BIAS, + (atomic64_t *)(&sem->count)) < 0L)) + rwsem_wake(sem); +} + +/* + * implement atomic add functionality + */ +static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem) +{ + atomic64_add(delta, (atomic64_t *)(&sem->count)); +} + +/* + * downgrade write lock to read lock + */ +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic64_add_return(-RWSEM_WAITING_BIAS, (atomic64_t *)(&sem->count)); + if (tmp < 0L) + rwsem_downgrade_wake(sem); +} + +/* + * implement exchange and add functionality + */ +static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem) { - atomic_add(delta, (atomic_t *)(&sem->count)); + return atomic64_add_return(delta, (atomic64_t *)(&sem->count)); } static inline int rwsem_is_locked(struct rw_semaphore *sem) diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h index d24cfe16afc1..e3b65d8cf41b 100644 --- a/arch/sparc/include/asm/system_64.h +++ b/arch/sparc/include/asm/system_64.h @@ -106,6 +106,7 @@ do { __asm__ __volatile__("ba,pt %%xcc, 1f\n\t" \ */ #define write_pic(__p) \ __asm__ __volatile__("ba,pt %%xcc, 99f\n\t" \ + " nop\n\t" \ ".align 64\n" \ "99:wr %0, 0x0, %%pic\n\t" \ "rd %%pic, %%g0" : : "r" (__p)) diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index 0c2dc1f24a9a..599398fbbc7c 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -119,3 +119,5 @@ obj-$(CONFIG_COMPAT) += $(audit--y) pc--$(CONFIG_PERF_EVENTS) := perf_event.o obj-$(CONFIG_SPARC64) += $(pc--y) + +obj-$(CONFIG_SPARC64) += jump_label.o diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c new file mode 100644 index 000000000000..ea2dafc93d78 --- /dev/null +++ b/arch/sparc/kernel/jump_label.c @@ -0,0 +1,47 @@ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/cpu.h> + +#include <linux/jump_label.h> +#include <linux/memory.h> + +#ifdef HAVE_JUMP_LABEL + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + u32 val; + u32 *insn = (u32 *) (unsigned long) entry->code; + + if (type == JUMP_LABEL_ENABLE) { + s32 off = (s32)entry->target - (s32)entry->code; + +#ifdef CONFIG_SPARC64 + /* ba,pt %xcc, . + (off << 2) */ + val = 0x10680000 | ((u32) off >> 2); +#else + /* ba . + (off << 2) */ + val = 0x10800000 | ((u32) off >> 2); +#endif + } else { + val = 0x01000000; + } + + get_online_cpus(); + mutex_lock(&text_mutex); + *insn = val; + flushi(insn); + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +void arch_jump_label_text_poke_early(jump_label_t addr) +{ + u32 *insn_p = (u32 *) (unsigned long) addr; + + *insn_p = 0x01000000; + flushi(insn_p); +} + +#endif diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index f848aadf54dc..ee3c7dde8d9f 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -18,6 +18,9 @@ #include <asm/spitfire.h> #ifdef CONFIG_SPARC64 + +#include <linux/jump_label.h> + static void *module_map(unsigned long size) { struct vm_struct *area; @@ -227,6 +230,9 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { + /* make jump label nops */ + jump_label_apply_nops(me); + /* Cheetah's I-cache is fully coherent. */ if (tlb_type == spitfire) { unsigned long va; diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index c4a6a50b4849..b87873c0e8ea 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -7,7 +7,7 @@ #include <linux/init.h> #include <linux/irq.h> -#include <linux/perf_event.h> +#include <linux/irq_work.h> #include <linux/ftrace.h> #include <asm/pil.h> @@ -43,14 +43,14 @@ void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs) old_regs = set_irq_regs(regs); irq_enter(); -#ifdef CONFIG_PERF_EVENTS - perf_event_do_pending(); +#ifdef CONFIG_IRQ_WORK + irq_work_run(); #endif irq_exit(); set_irq_regs(old_regs); } -void set_perf_event_pending(void) +void arch_irq_work_raise(void) { set_softint(1 << PIL_DEFERRED_PCR_WORK); } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 357ced3c33ff..0d6deb55a2ae 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -658,13 +658,16 @@ static u64 maybe_change_configuration(struct cpu_hw_events *cpuc, u64 pcr) enc = perf_event_get_enc(cpuc->events[i]); pcr &= ~mask_for_index(idx); - pcr |= event_encoding(enc, idx); + if (hwc->state & PERF_HES_STOPPED) + pcr |= nop_for_index(idx); + else + pcr |= event_encoding(enc, idx); } out: return pcr; } -void hw_perf_enable(void) +static void sparc_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); u64 pcr; @@ -691,7 +694,7 @@ void hw_perf_enable(void) pcr_ops->write(cpuc->pcr); } -void hw_perf_disable(void) +static void sparc_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); u64 val; @@ -710,19 +713,65 @@ void hw_perf_disable(void) pcr_ops->write(cpuc->pcr); } -static void sparc_pmu_disable(struct perf_event *event) +static int active_event_index(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + int i; + + for (i = 0; i < cpuc->n_events; i++) { + if (cpuc->event[i] == event) + break; + } + BUG_ON(i == cpuc->n_events); + return cpuc->current_idx[i]; +} + +static void sparc_pmu_start(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx = active_event_index(cpuc, event); + + if (flags & PERF_EF_RELOAD) { + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + sparc_perf_event_set_period(event, &event->hw, idx); + } + + event->hw.state = 0; + + sparc_pmu_enable_event(cpuc, &event->hw, idx); +} + +static void sparc_pmu_stop(struct perf_event *event, int flags) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + int idx = active_event_index(cpuc, event); + + if (!(event->hw.state & PERF_HES_STOPPED)) { + sparc_pmu_disable_event(cpuc, &event->hw, idx); + event->hw.state |= PERF_HES_STOPPED; + } + + if (!(event->hw.state & PERF_HES_UPTODATE) && (flags & PERF_EF_UPDATE)) { + sparc_perf_event_update(event, &event->hw, idx); + event->hw.state |= PERF_HES_UPTODATE; + } +} + +static void sparc_pmu_del(struct perf_event *event, int _flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; unsigned long flags; int i; local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event[i]) { - int idx = cpuc->current_idx[i]; + /* Absorb the final count and turn off the + * event. + */ + sparc_pmu_stop(event, PERF_EF_UPDATE); /* Shift remaining entries down into * the existing slot. @@ -734,13 +783,6 @@ static void sparc_pmu_disable(struct perf_event *event) cpuc->current_idx[i]; } - /* Absorb the final count and turn off the - * event. - */ - sparc_pmu_disable_event(cpuc, hwc, idx); - barrier(); - sparc_perf_event_update(event, hwc, idx); - perf_event_update_userpage(event); cpuc->n_events--; @@ -748,23 +790,10 @@ static void sparc_pmu_disable(struct perf_event *event) } } - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); } -static int active_event_index(struct cpu_hw_events *cpuc, - struct perf_event *event) -{ - int i; - - for (i = 0; i < cpuc->n_events; i++) { - if (cpuc->event[i] == event) - break; - } - BUG_ON(i == cpuc->n_events); - return cpuc->current_idx[i]; -} - static void sparc_pmu_read(struct perf_event *event) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -774,15 +803,6 @@ static void sparc_pmu_read(struct perf_event *event) sparc_perf_event_update(event, hwc, idx); } -static void sparc_pmu_unthrottle(struct perf_event *event) -{ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - int idx = active_event_index(cpuc, event); - struct hw_perf_event *hwc = &event->hw; - - sparc_pmu_enable_event(cpuc, hwc, idx); -} - static atomic_t active_events = ATOMIC_INIT(0); static DEFINE_MUTEX(pmc_grab_mutex); @@ -877,7 +897,7 @@ static int sparc_check_constraints(struct perf_event **evts, if (!n_ev) return 0; - if (n_ev > perf_max_events) + if (n_ev > MAX_HWEVENTS) return -1; msk0 = perf_event_get_msk(events[0]); @@ -984,23 +1004,27 @@ static int collect_events(struct perf_event *group, int max_count, return n; } -static int sparc_pmu_enable(struct perf_event *event) +static int sparc_pmu_add(struct perf_event *event, int ef_flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int n0, ret = -EAGAIN; unsigned long flags; local_irq_save(flags); - perf_disable(); + perf_pmu_disable(event->pmu); n0 = cpuc->n_events; - if (n0 >= perf_max_events) + if (n0 >= MAX_HWEVENTS) goto out; cpuc->event[n0] = event; cpuc->events[n0] = event->hw.event_base; cpuc->current_idx[n0] = PIC_NO_INDEX; + event->hw.state = PERF_HES_UPTODATE; + if (!(ef_flags & PERF_EF_START)) + event->hw.state |= PERF_HES_STOPPED; + /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be peformed @@ -1020,12 +1044,12 @@ nocheck: ret = 0; out: - perf_enable(); + perf_pmu_enable(event->pmu); local_irq_restore(flags); return ret; } -static int __hw_perf_event_init(struct perf_event *event) +static int sparc_pmu_event_init(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; struct perf_event *evts[MAX_HWEVENTS]; @@ -1038,16 +1062,37 @@ static int __hw_perf_event_init(struct perf_event *event) if (atomic_read(&nmi_active) < 0) return -ENODEV; - if (attr->type == PERF_TYPE_HARDWARE) { + switch (attr->type) { + case PERF_TYPE_HARDWARE: if (attr->config >= sparc_pmu->max_events) return -EINVAL; pmap = sparc_pmu->event_map(attr->config); - } else if (attr->type == PERF_TYPE_HW_CACHE) { + break; + + case PERF_TYPE_HW_CACHE: pmap = sparc_map_cache_event(attr->config); if (IS_ERR(pmap)) return PTR_ERR(pmap); - } else - return -EOPNOTSUPP; + break; + + case PERF_TYPE_RAW: + pmap = NULL; + break; + + default: + return -ENOENT; + + } + + if (pmap) { + hwc->event_base = perf_event_encode(pmap); + } else { + /* + * User gives us "(encoding << 16) | pic_mask" for + * PERF_TYPE_RAW events. + */ + hwc->event_base = attr->config; + } /* We save the enable bits in the config_base. */ hwc->config_base = sparc_pmu->irq_bit; @@ -1058,12 +1103,10 @@ static int __hw_perf_event_init(struct perf_event *event) if (!attr->exclude_hv) hwc->config_base |= sparc_pmu->hv_bit; - hwc->event_base = perf_event_encode(pmap); - n = 0; if (event->group_leader != event) { n = collect_events(event->group_leader, - perf_max_events - 1, + MAX_HWEVENTS - 1, evts, events, current_idx_dmy); if (n < 0) return -EINVAL; @@ -1099,10 +1142,11 @@ static int __hw_perf_event_init(struct perf_event *event) * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time */ -static void sparc_pmu_start_txn(const struct pmu *pmu) +static void sparc_pmu_start_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + perf_pmu_disable(pmu); cpuhw->group_flag |= PERF_EVENT_TXN; } @@ -1111,11 +1155,12 @@ static void sparc_pmu_start_txn(const struct pmu *pmu) * Clear the flag and pmu::enable() will perform the * schedulability test. */ -static void sparc_pmu_cancel_txn(const struct pmu *pmu) +static void sparc_pmu_cancel_txn(struct pmu *pmu) { struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); cpuhw->group_flag &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); } /* @@ -1123,7 +1168,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu) * Perform the group schedulability test as a whole * Return 0 if success */ -static int sparc_pmu_commit_txn(const struct pmu *pmu) +static int sparc_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int n; @@ -1139,28 +1184,24 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu) return -EAGAIN; cpuc->group_flag &= ~PERF_EVENT_TXN; + perf_pmu_enable(pmu); return 0; } -static const struct pmu pmu = { - .enable = sparc_pmu_enable, - .disable = sparc_pmu_disable, +static struct pmu pmu = { + .pmu_enable = sparc_pmu_enable, + .pmu_disable = sparc_pmu_disable, + .event_init = sparc_pmu_event_init, + .add = sparc_pmu_add, + .del = sparc_pmu_del, + .start = sparc_pmu_start, + .stop = sparc_pmu_stop, .read = sparc_pmu_read, - .unthrottle = sparc_pmu_unthrottle, .start_txn = sparc_pmu_start_txn, .cancel_txn = sparc_pmu_cancel_txn, .commit_txn = sparc_pmu_commit_txn, }; -const struct pmu *hw_perf_event_init(struct perf_event *event) -{ - int err = __hw_perf_event_init(event); - - if (err) - return ERR_PTR(err); - return &pmu; -} - void perf_event_print_debug(void) { unsigned long flags; @@ -1236,7 +1277,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, continue; if (perf_event_overflow(event, 1, &data, regs)) - sparc_pmu_disable_event(cpuc, hwc, idx); + sparc_pmu_stop(event, 0); } return NOTIFY_STOP; @@ -1277,28 +1318,21 @@ void __init init_hw_perf_events(void) pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type); - /* All sparc64 PMUs currently have 2 events. */ - perf_max_events = 2; - + perf_pmu_register(&pmu); register_die_notifier(&perf_event_nmi_notifier); } -static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip) -{ - if (entry->nr < PERF_MAX_STACK_DEPTH) - entry->ip[entry->nr++] = ip; -} - -static void perf_callchain_kernel(struct pt_regs *regs, - struct perf_callchain_entry *entry) +void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned long ksp, fp; #ifdef CONFIG_FUNCTION_GRAPH_TRACER int graph = 0; #endif - callchain_store(entry, PERF_CONTEXT_KERNEL); - callchain_store(entry, regs->tpc); + stack_trace_flush(); + + perf_callchain_store(entry, regs->tpc); ksp = regs->u_regs[UREG_I6]; fp = ksp + STACK_BIAS; @@ -1322,13 +1356,13 @@ static void perf_callchain_kernel(struct pt_regs *regs, pc = sf->callers_pc; fp = (unsigned long)sf->fp + STACK_BIAS; } - callchain_store(entry, pc); + perf_callchain_store(entry, pc); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if ((pc + 8UL) == (unsigned long) &return_to_handler) { int index = current->curr_ret_stack; if (current->ret_stack && index >= graph) { pc = current->ret_stack[index - graph].ret; - callchain_store(entry, pc); + perf_callchain_store(entry, pc); graph++; } } @@ -1336,13 +1370,12 @@ static void perf_callchain_kernel(struct pt_regs *regs, } while (entry->nr < PERF_MAX_STACK_DEPTH); } -static void perf_callchain_user_64(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static void perf_callchain_user_64(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned long ufp; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, regs->tpc); + perf_callchain_store(entry, regs->tpc); ufp = regs->u_regs[UREG_I6] + STACK_BIAS; do { @@ -1355,17 +1388,16 @@ static void perf_callchain_user_64(struct pt_regs *regs, pc = sf.callers_pc; ufp = (unsigned long)sf.fp + STACK_BIAS; - callchain_store(entry, pc); + perf_callchain_store(entry, pc); } while (entry->nr < PERF_MAX_STACK_DEPTH); } -static void perf_callchain_user_32(struct pt_regs *regs, - struct perf_callchain_entry *entry) +static void perf_callchain_user_32(struct perf_callchain_entry *entry, + struct pt_regs *regs) { unsigned long ufp; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, regs->tpc); + perf_callchain_store(entry, regs->tpc); ufp = regs->u_regs[UREG_I6] & 0xffffffffUL; do { @@ -1378,34 +1410,16 @@ static void perf_callchain_user_32(struct pt_regs *regs, pc = sf.callers_pc; ufp = (unsigned long)sf.fp; - callchain_store(entry, pc); + perf_callchain_store(entry, pc); } while (entry->nr < PERF_MAX_STACK_DEPTH); } -/* Like powerpc we can't get PMU interrupts within the PMU handler, - * so no need for separate NMI and IRQ chains as on x86. - */ -static DEFINE_PER_CPU(struct perf_callchain_entry, callchain); - -struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) +void +perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { - struct perf_callchain_entry *entry = &__get_cpu_var(callchain); - - entry->nr = 0; - if (!user_mode(regs)) { - stack_trace_flush(); - perf_callchain_kernel(regs, entry); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; - } - if (regs) { - flushw_user(); - if (test_thread_flag(TIF_32BIT)) - perf_callchain_user_32(regs, entry); - else - perf_callchain_user_64(regs, entry); - } - return entry; + flushw_user(); + if (test_thread_flag(TIF_32BIT)) + perf_callchain_user_32(entry, regs); + else + perf_callchain_user_64(entry, regs); } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 485f54748384..c158a95ec664 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -303,7 +303,7 @@ void arch_trigger_all_cpu_backtrace(void) #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_globreg(int key, struct tty_struct *tty) +static void sysrq_handle_globreg(int key) { arch_trigger_all_cpu_backtrace(); } diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index ea22cd373c64..75fad425e249 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -453,8 +453,66 @@ static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) return err; } -static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, - int signo, sigset_t *oldset) +/* The I-cache flush instruction only works in the primary ASI, which + * right now is the nucleus, aka. kernel space. + * + * Therefore we have to kick the instructions out using the kernel + * side linear mapping of the physical address backing the user + * instructions. + */ +static void flush_signal_insns(unsigned long address) +{ + unsigned long pstate, paddr; + pte_t *ptep, pte; + pgd_t *pgdp; + pud_t *pudp; + pmd_t *pmdp; + + /* Commit all stores of the instructions we are about to flush. */ + wmb(); + + /* Disable cross-call reception. In this way even a very wide + * munmap() on another cpu can't tear down the page table + * hierarchy from underneath us, since that can't complete + * until the IPI tlb flush returns. + */ + + __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate)); + __asm__ __volatile__("wrpr %0, %1, %%pstate" + : : "r" (pstate), "i" (PSTATE_IE)); + + pgdp = pgd_offset(current->mm, address); + if (pgd_none(*pgdp)) + goto out_irqs_on; + pudp = pud_offset(pgdp, address); + if (pud_none(*pudp)) + goto out_irqs_on; + pmdp = pmd_offset(pudp, address); + if (pmd_none(*pmdp)) + goto out_irqs_on; + + ptep = pte_offset_map(pmdp, address); + pte = *ptep; + if (!pte_present(pte)) + goto out_unmap; + + paddr = (unsigned long) page_address(pte_page(pte)); + + __asm__ __volatile__("flush %0 + %1" + : /* no outputs */ + : "r" (paddr), + "r" (address & (PAGE_SIZE - 1)) + : "memory"); + +out_unmap: + pte_unmap(ptep); +out_irqs_on: + __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate)); + +} + +static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, + int signo, sigset_t *oldset) { struct signal_frame32 __user *sf; int sigframe_size; @@ -547,13 +605,7 @@ static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (ka->ka_restorer) { regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer; } else { - /* Flush instruction space. */ unsigned long address = ((unsigned long)&(sf->insns[0])); - pgd_t *pgdp = pgd_offset(current->mm, address); - pud_t *pudp = pud_offset(pgdp, address); - pmd_t *pmdp = pmd_offset(pudp, address); - pte_t *ptep; - pte_t pte; regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2); @@ -562,34 +614,22 @@ static void setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (err) goto sigsegv; - preempt_disable(); - ptep = pte_offset_map(pmdp, address); - pte = *ptep; - if (pte_present(pte)) { - unsigned long page = (unsigned long) - page_address(pte_page(pte)); - - wmb(); - __asm__ __volatile__("flush %0 + %1" - : /* no outputs */ - : "r" (page), - "r" (address & (PAGE_SIZE - 1)) - : "memory"); - } - pte_unmap(ptep); - preempt_enable(); + flush_signal_insns(address); } - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, - unsigned long signr, sigset_t *oldset, - siginfo_t *info) +static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, + unsigned long signr, sigset_t *oldset, + siginfo_t *info) { struct rt_signal_frame32 __user *sf; int sigframe_size; @@ -687,12 +727,7 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (ka->ka_restorer) regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer; else { - /* Flush instruction space. */ unsigned long address = ((unsigned long)&(sf->insns[0])); - pgd_t *pgdp = pgd_offset(current->mm, address); - pud_t *pudp = pud_offset(pgdp, address); - pmd_t *pmdp = pmd_offset(pudp, address); - pte_t *ptep; regs->u_regs[UREG_I7] = (unsigned long) (&(sf->insns[0]) - 2); @@ -704,38 +739,32 @@ static void setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (err) goto sigsegv; - preempt_disable(); - ptep = pte_offset_map(pmdp, address); - if (pte_present(*ptep)) { - unsigned long page = (unsigned long) - page_address(pte_page(*ptep)); - - wmb(); - __asm__ __volatile__("flush %0 + %1" - : /* no outputs */ - : "r" (page), - "r" (address & (PAGE_SIZE - 1)) - : "memory"); - } - pte_unmap(ptep); - preempt_enable(); + flush_signal_insns(address); } - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signr, current); + return -EFAULT; } -static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka, - siginfo_t *info, - sigset_t *oldset, struct pt_regs *regs) +static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, + siginfo_t *info, + sigset_t *oldset, struct pt_regs *regs) { + int err; + if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame32(ka, regs, signr, oldset, info); + err = setup_rt_frame32(ka, regs, signr, oldset, info); else - setup_frame32(ka, regs, signr, oldset); + err = setup_frame32(ka, regs, signr, oldset); + + if (err) + return err; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); @@ -743,6 +772,10 @@ static inline void handle_signal32(unsigned long signr, struct k_sigaction *ka, sigaddset(¤t->blocked,signr); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + + tracehook_signal_handler(signr, info, ka, regs, 0); + + return 0; } static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs, @@ -789,16 +822,14 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, if (signr > 0) { if (restart_syscall) syscall_restart32(orig_i0, regs, &ka.sa); - handle_signal32(signr, &ka, &info, oldset, regs); - - /* A signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TS_RESTORE_SIGMASK flag. - */ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - - tracehook_signal_handler(signr, &info, &ka, regs, 0); + if (handle_signal32(signr, &ka, &info, oldset, regs) == 0) { + /* A signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; + } return; } if (restart_syscall && @@ -809,12 +840,14 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } if (restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } /* If there's no signal to deliver, we just put the saved sigmask diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 9882df92ba0a..5e5c5fd03783 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -315,8 +315,8 @@ save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) return err; } -static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs, - int signo, sigset_t *oldset) +static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, + int signo, sigset_t *oldset) { struct signal_frame __user *sf; int sigframe_size, err; @@ -384,16 +384,19 @@ static void setup_frame(struct k_sigaction *ka, struct pt_regs *regs, /* Flush instruction space. */ flush_sig_insns(current->mm, (unsigned long) &(sf->insns[0])); } - return; + return 0; sigill_and_return: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, - int signo, sigset_t *oldset, siginfo_t *info) +static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, + int signo, sigset_t *oldset, siginfo_t *info) { struct rt_signal_frame __user *sf; int sigframe_size; @@ -466,22 +469,30 @@ static void setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, /* Flush instruction space. */ flush_sig_insns(current->mm, (unsigned long) &(sf->insns[0])); } - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static inline void +static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + int err; + if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame(ka, regs, signr, oldset, info); + err = setup_rt_frame(ka, regs, signr, oldset, info); else - setup_frame(ka, regs, signr, oldset); + err = setup_frame(ka, regs, signr, oldset); + + if (err) + return err; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); @@ -489,6 +500,10 @@ handle_signal(unsigned long signr, struct k_sigaction *ka, sigaddset(¤t->blocked, signr); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + + tracehook_signal_handler(signr, info, ka, regs, 0); + + return 0; } static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, @@ -546,17 +561,15 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) if (signr > 0) { if (restart_syscall) syscall_restart(orig_i0, regs, &ka.sa); - handle_signal(signr, &ka, &info, oldset, regs); - - /* a signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TIF_RESTORE_SIGMASK flag. - */ - if (test_thread_flag(TIF_RESTORE_SIGMASK)) - clear_thread_flag(TIF_RESTORE_SIGMASK); - - tracehook_signal_handler(signr, &info, &ka, regs, 0); + if (handle_signal(signr, &ka, &info, oldset, regs) == 0) { + /* a signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TIF_RESTORE_SIGMASK flag. + */ + if (test_thread_flag(TIF_RESTORE_SIGMASK)) + clear_thread_flag(TIF_RESTORE_SIGMASK); + } return; } if (restart_syscall && @@ -567,12 +580,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->u_regs[UREG_I0] = orig_i0; regs->pc -= 4; regs->npc -= 4; + pt_regs_clear_syscall(regs); } if (restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->pc -= 4; regs->npc -= 4; + pt_regs_clear_syscall(regs); } /* if there's no signal to deliver, we just put the saved sigmask diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 9fa48c30037e..006fe4515886 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -409,7 +409,7 @@ static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs * return (void __user *) sp; } -static inline void +static inline int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset, siginfo_t *info) { @@ -483,26 +483,37 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, } /* 4. return to kernel instructions */ regs->u_regs[UREG_I7] = (unsigned long)ka->ka_restorer; - return; + return 0; sigill: do_exit(SIGILL); + return -EINVAL; + sigsegv: force_sigsegv(signo, current); + return -EFAULT; } -static inline void handle_signal(unsigned long signr, struct k_sigaction *ka, - siginfo_t *info, - sigset_t *oldset, struct pt_regs *regs) +static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, + siginfo_t *info, + sigset_t *oldset, struct pt_regs *regs) { - setup_rt_frame(ka, regs, signr, oldset, - (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); + int err; + + err = setup_rt_frame(ka, regs, signr, oldset, + (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); + if (err) + return err; spin_lock_irq(¤t->sighand->siglock); sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) sigaddset(¤t->blocked,signr); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); + + tracehook_signal_handler(signr, info, ka, regs, 0); + + return 0; } static inline void syscall_restart(unsigned long orig_i0, struct pt_regs *regs, @@ -571,16 +582,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) if (signr > 0) { if (restart_syscall) syscall_restart(orig_i0, regs, &ka.sa); - handle_signal(signr, &ka, &info, oldset, regs); - - /* A signal was successfully delivered; the saved - * sigmask will have been stored in the signal frame, - * and will be restored by sigreturn, so we can simply - * clear the TS_RESTORE_SIGMASK flag. - */ - current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - - tracehook_signal_handler(signr, &info, &ka, regs, 0); + if (handle_signal(signr, &ka, &info, oldset, regs) == 0) { + /* A signal was successfully delivered; the saved + * sigmask will have been stored in the signal frame, + * and will be restored by sigreturn, so we can simply + * clear the TS_RESTORE_SIGMASK flag. + */ + current_thread_info()->status &= ~TS_RESTORE_SIGMASK; + } return; } if (restart_syscall && @@ -591,12 +600,14 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) regs->u_regs[UREG_I0] = orig_i0; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } if (restart_syscall && regs->u_regs[UREG_I0] == ERESTART_RESTARTBLOCK) { regs->u_regs[UREG_G1] = __NR_restart_syscall; regs->tpc -= 4; regs->tnpc -= 4; + pt_regs_clear_syscall(regs); } /* If there's no signal to deliver, we just put the saved sigmask diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 50794137d710..675c9e11ada5 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -166,7 +166,6 @@ sparc_breakpoint (struct pt_regs *regs) { siginfo_t info; - lock_kernel(); #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Entering kernel PC=%x, nPC=%x\n", regs->pc, regs->npc); #endif @@ -180,7 +179,6 @@ sparc_breakpoint (struct pt_regs *regs) #ifdef DEBUG_SPARC_BREAKPOINT printk ("TRAP: Returning to space: PC=%x nPC=%x\n", regs->pc, regs->npc); #endif - unlock_kernel(); } asmlinkage int diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c index f8514e291e15..12b9f352595f 100644 --- a/arch/sparc/kernel/unaligned_32.c +++ b/arch/sparc/kernel/unaligned_32.c @@ -323,7 +323,6 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn) { enum direction dir; - lock_kernel(); if(!(current->thread.flags & SPARC_FLAG_UNALIGNED) || (((insn >> 30) & 3) != 3)) goto kill_user; @@ -377,5 +376,5 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn) kill_user: user_mna_trap_fault(regs, insn); out: - unlock_kernel(); + ; } diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c index f24d298bda29..b351770cbdd6 100644 --- a/arch/sparc/kernel/windows.c +++ b/arch/sparc/kernel/windows.c @@ -112,7 +112,6 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who) struct thread_info *tp = current_thread_info(); int window; - lock_kernel(); flush_user_windows(); for(window = 0; window < tp->w_saved; window++) { unsigned long sp = tp->rwbuf_stkptrs[window]; @@ -123,5 +122,4 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who) do_exit(SIGILL); } tp->w_saved = 0; - unlock_kernel(); } diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index c4b5e03af115..846d1c4374ea 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -15,7 +15,7 @@ lib-$(CONFIG_SPARC32) += divdi3.o udivdi3.o lib-$(CONFIG_SPARC32) += copy_user.o locks.o lib-y += atomic_$(BITS).o lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o -lib-y += rwsem_$(BITS).o +lib-$(CONFIG_SPARC32) += rwsem_32.o lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o diff --git a/arch/sparc/lib/atomic_64.S b/arch/sparc/lib/atomic_64.S index 0268210ca168..59186e0fcf39 100644 --- a/arch/sparc/lib/atomic_64.S +++ b/arch/sparc/lib/atomic_64.S @@ -21,7 +21,7 @@ atomic_add: /* %o0 = increment, %o1 = atomic_ptr */ add %g1, %o0, %g7 cas [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %icc, 2f + bne,pn %icc, BACKOFF_LABEL(2f, 1b) nop retl nop @@ -36,7 +36,7 @@ atomic_sub: /* %o0 = decrement, %o1 = atomic_ptr */ sub %g1, %o0, %g7 cas [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %icc, 2f + bne,pn %icc, BACKOFF_LABEL(2f, 1b) nop retl nop @@ -51,11 +51,10 @@ atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */ add %g1, %o0, %g7 cas [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %icc, 2f - add %g7, %o0, %g7 - sra %g7, 0, %o0 + bne,pn %icc, BACKOFF_LABEL(2f, 1b) + add %g1, %o0, %g1 retl - nop + sra %g1, 0, %o0 2: BACKOFF_SPIN(%o2, %o3, 1b) .size atomic_add_ret, .-atomic_add_ret @@ -67,11 +66,10 @@ atomic_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */ sub %g1, %o0, %g7 cas [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %icc, 2f - sub %g7, %o0, %g7 - sra %g7, 0, %o0 + bne,pn %icc, BACKOFF_LABEL(2f, 1b) + sub %g1, %o0, %g1 retl - nop + sra %g1, 0, %o0 2: BACKOFF_SPIN(%o2, %o3, 1b) .size atomic_sub_ret, .-atomic_sub_ret @@ -83,7 +81,7 @@ atomic64_add: /* %o0 = increment, %o1 = atomic_ptr */ add %g1, %o0, %g7 casx [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop retl nop @@ -98,7 +96,7 @@ atomic64_sub: /* %o0 = decrement, %o1 = atomic_ptr */ sub %g1, %o0, %g7 casx [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop retl nop @@ -113,11 +111,10 @@ atomic64_add_ret: /* %o0 = increment, %o1 = atomic_ptr */ add %g1, %o0, %g7 casx [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %xcc, 2f - add %g7, %o0, %g7 - mov %g7, %o0 - retl + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop + retl + add %g1, %o0, %o0 2: BACKOFF_SPIN(%o2, %o3, 1b) .size atomic64_add_ret, .-atomic64_add_ret @@ -129,10 +126,9 @@ atomic64_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */ sub %g1, %o0, %g7 casx [%o1], %g1, %g7 cmp %g1, %g7 - bne,pn %xcc, 2f - sub %g7, %o0, %g7 - mov %g7, %o0 - retl + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop + retl + sub %g1, %o0, %o0 2: BACKOFF_SPIN(%o2, %o3, 1b) .size atomic64_sub_ret, .-atomic64_sub_ret diff --git a/arch/sparc/lib/bitops.S b/arch/sparc/lib/bitops.S index 2b7228cb8c22..3dc61d5537c0 100644 --- a/arch/sparc/lib/bitops.S +++ b/arch/sparc/lib/bitops.S @@ -22,7 +22,7 @@ test_and_set_bit: /* %o0=nr, %o1=addr */ or %g7, %o2, %g1 casx [%o1], %g7, %g1 cmp %g7, %g1 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) and %g7, %o2, %g2 clr %o0 movrne %g2, 1, %o0 @@ -45,7 +45,7 @@ test_and_clear_bit: /* %o0=nr, %o1=addr */ andn %g7, %o2, %g1 casx [%o1], %g7, %g1 cmp %g7, %g1 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) and %g7, %o2, %g2 clr %o0 movrne %g2, 1, %o0 @@ -68,7 +68,7 @@ test_and_change_bit: /* %o0=nr, %o1=addr */ xor %g7, %o2, %g1 casx [%o1], %g7, %g1 cmp %g7, %g1 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) and %g7, %o2, %g2 clr %o0 movrne %g2, 1, %o0 @@ -91,7 +91,7 @@ set_bit: /* %o0=nr, %o1=addr */ or %g7, %o2, %g1 casx [%o1], %g7, %g1 cmp %g7, %g1 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop retl nop @@ -112,7 +112,7 @@ clear_bit: /* %o0=nr, %o1=addr */ andn %g7, %o2, %g1 casx [%o1], %g7, %g1 cmp %g7, %g1 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop retl nop @@ -133,7 +133,7 @@ change_bit: /* %o0=nr, %o1=addr */ xor %g7, %o2, %g1 casx [%o1], %g7, %g1 cmp %g7, %g1 - bne,pn %xcc, 2f + bne,pn %xcc, BACKOFF_LABEL(2f, 1b) nop retl nop diff --git a/arch/sparc/lib/rwsem_64.S b/arch/sparc/lib/rwsem_64.S deleted file mode 100644 index 91a7d29a79d5..000000000000 --- a/arch/sparc/lib/rwsem_64.S +++ /dev/null @@ -1,163 +0,0 @@ -/* rwsem.S: RW semaphore assembler. - * - * Written by David S. Miller (davem@redhat.com), 2001. - * Derived from asm-i386/rwsem.h - */ - -#include <asm/rwsem-const.h> - - .section .sched.text, "ax" - - .globl __down_read -__down_read: -1: lduw [%o0], %g1 - add %g1, 1, %g7 - cas [%o0], %g1, %g7 - cmp %g1, %g7 - bne,pn %icc, 1b - add %g7, 1, %g7 - cmp %g7, 0 - bl,pn %icc, 3f - nop -2: - retl - nop -3: - save %sp, -192, %sp - call rwsem_down_read_failed - mov %i0, %o0 - ret - restore - .size __down_read, .-__down_read - - .globl __down_read_trylock -__down_read_trylock: -1: lduw [%o0], %g1 - add %g1, 1, %g7 - cmp %g7, 0 - bl,pn %icc, 2f - mov 0, %o1 - cas [%o0], %g1, %g7 - cmp %g1, %g7 - bne,pn %icc, 1b - mov 1, %o1 -2: retl - mov %o1, %o0 - .size __down_read_trylock, .-__down_read_trylock - - .globl __down_write -__down_write: - sethi %hi(RWSEM_ACTIVE_WRITE_BIAS), %g1 - or %g1, %lo(RWSEM_ACTIVE_WRITE_BIAS), %g1 -1: - lduw [%o0], %g3 - add %g3, %g1, %g7 - cas [%o0], %g3, %g7 - cmp %g3, %g7 - bne,pn %icc, 1b - cmp %g7, 0 - bne,pn %icc, 3f - nop -2: retl - nop -3: - save %sp, -192, %sp - call rwsem_down_write_failed - mov %i0, %o0 - ret - restore - .size __down_write, .-__down_write - - .globl __down_write_trylock -__down_write_trylock: - sethi %hi(RWSEM_ACTIVE_WRITE_BIAS), %g1 - or %g1, %lo(RWSEM_ACTIVE_WRITE_BIAS), %g1 -1: - lduw [%o0], %g3 - cmp %g3, 0 - bne,pn %icc, 2f - mov 0, %o1 - add %g3, %g1, %g7 - cas [%o0], %g3, %g7 - cmp %g3, %g7 - bne,pn %icc, 1b - mov 1, %o1 -2: retl - mov %o1, %o0 - .size __down_write_trylock, .-__down_write_trylock - - .globl __up_read -__up_read: -1: - lduw [%o0], %g1 - sub %g1, 1, %g7 - cas [%o0], %g1, %g7 - cmp %g1, %g7 - bne,pn %icc, 1b - cmp %g7, 0 - bl,pn %icc, 3f - nop -2: retl - nop -3: sethi %hi(RWSEM_ACTIVE_MASK), %g1 - sub %g7, 1, %g7 - or %g1, %lo(RWSEM_ACTIVE_MASK), %g1 - andcc %g7, %g1, %g0 - bne,pn %icc, 2b - nop - save %sp, -192, %sp - call rwsem_wake - mov %i0, %o0 - ret - restore - .size __up_read, .-__up_read - - .globl __up_write -__up_write: - sethi %hi(RWSEM_ACTIVE_WRITE_BIAS), %g1 - or %g1, %lo(RWSEM_ACTIVE_WRITE_BIAS), %g1 -1: - lduw [%o0], %g3 - sub %g3, %g1, %g7 - cas [%o0], %g3, %g7 - cmp %g3, %g7 - bne,pn %icc, 1b - sub %g7, %g1, %g7 - cmp %g7, 0 - bl,pn %icc, 3f - nop -2: - retl - nop -3: - save %sp, -192, %sp - call rwsem_wake - mov %i0, %o0 - ret - restore - .size __up_write, .-__up_write - - .globl __downgrade_write -__downgrade_write: - sethi %hi(RWSEM_WAITING_BIAS), %g1 - or %g1, %lo(RWSEM_WAITING_BIAS), %g1 -1: - lduw [%o0], %g3 - sub %g3, %g1, %g7 - cas [%o0], %g3, %g7 - cmp %g3, %g7 - bne,pn %icc, 1b - sub %g7, %g1, %g7 - cmp %g7, 0 - bl,pn %icc, 3f - nop -2: - retl - nop -3: - save %sp, -192, %sp - call rwsem_downgrade_wake - mov %i0, %o0 - ret - restore - .size __downgrade_write, .-__downgrade_write diff --git a/arch/sparc/prom/cif.S b/arch/sparc/prom/cif.S index 5f27ad779c0c..9c86b4b7d429 100644 --- a/arch/sparc/prom/cif.S +++ b/arch/sparc/prom/cif.S @@ -9,18 +9,18 @@ #include <asm/thread_info.h> .text - .globl prom_cif_interface -prom_cif_interface: - sethi %hi(p1275buf), %o0 - or %o0, %lo(p1275buf), %o0 - ldx [%o0 + 0x010], %o1 ! prom_cif_stack - save %o1, -192, %sp - ldx [%i0 + 0x008], %l2 ! prom_cif_handler + .globl prom_cif_direct +prom_cif_direct: + sethi %hi(p1275buf), %o1 + or %o1, %lo(p1275buf), %o1 + ldx [%o1 + 0x0010], %o2 ! prom_cif_stack + save %o2, -192, %sp + ldx [%i1 + 0x0008], %l2 ! prom_cif_handler mov %g4, %l0 mov %g5, %l1 mov %g6, %l3 call %l2 - add %i0, 0x018, %o0 ! prom_args + mov %i0, %o0 ! prom_args mov %l0, %g4 mov %l1, %g5 mov %l3, %g6 diff --git a/arch/sparc/prom/console_64.c b/arch/sparc/prom/console_64.c index f55d58a8a156..10322dc2f557 100644 --- a/arch/sparc/prom/console_64.c +++ b/arch/sparc/prom/console_64.c @@ -21,14 +21,22 @@ extern int prom_stdin, prom_stdout; inline int prom_nbgetchar(void) { + unsigned long args[7]; char inc; - if (p1275_cmd("read", P1275_ARG(1,P1275_ARG_OUT_BUF)| - P1275_INOUT(3,1), - prom_stdin, &inc, P1275_SIZE(1)) == 1) + args[0] = (unsigned long) "read"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) prom_stdin; + args[4] = (unsigned long) &inc; + args[5] = 1; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[6] == 1) return inc; - else - return -1; + return -1; } /* Non blocking put character to console device, returns -1 if @@ -37,12 +45,22 @@ prom_nbgetchar(void) inline int prom_nbputchar(char c) { + unsigned long args[7]; char outc; outc = c; - if (p1275_cmd("write", P1275_ARG(1,P1275_ARG_IN_BUF)| - P1275_INOUT(3,1), - prom_stdout, &outc, P1275_SIZE(1)) == 1) + + args[0] = (unsigned long) "write"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) prom_stdout; + args[4] = (unsigned long) &outc; + args[5] = 1; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[6] == 1) return 0; else return -1; @@ -67,7 +85,15 @@ prom_putchar(char c) void prom_puts(const char *s, int len) { - p1275_cmd("write", P1275_ARG(1,P1275_ARG_IN_BUF)| - P1275_INOUT(3,1), - prom_stdout, s, P1275_SIZE(len)); + unsigned long args[7]; + + args[0] = (unsigned long) "write"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) prom_stdout; + args[4] = (unsigned long) s; + args[5] = len; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); } diff --git a/arch/sparc/prom/devops_64.c b/arch/sparc/prom/devops_64.c index 9dbd803e46e1..a017119e7ef1 100644 --- a/arch/sparc/prom/devops_64.c +++ b/arch/sparc/prom/devops_64.c @@ -18,16 +18,32 @@ int prom_devopen(const char *dstr) { - return p1275_cmd ("open", P1275_ARG(0,P1275_ARG_IN_STRING)| - P1275_INOUT(1,1), - dstr); + unsigned long args[5]; + + args[0] = (unsigned long) "open"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) dstr; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[4]; } /* Close the device described by device handle 'dhandle'. */ int prom_devclose(int dhandle) { - p1275_cmd ("close", P1275_INOUT(1,0), dhandle); + unsigned long args[4]; + + args[0] = (unsigned long) "close"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned int) dhandle; + + p1275_cmd_direct(args); + return 0; } @@ -37,5 +53,15 @@ prom_devclose(int dhandle) void prom_seek(int dhandle, unsigned int seekhi, unsigned int seeklo) { - p1275_cmd ("seek", P1275_INOUT(3,1), dhandle, seekhi, seeklo); + unsigned long args[7]; + + args[0] = (unsigned long) "seek"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) dhandle; + args[4] = seekhi; + args[5] = seeklo; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); } diff --git a/arch/sparc/prom/misc_64.c b/arch/sparc/prom/misc_64.c index 39fc6af21b7c..6cb1581d6aef 100644 --- a/arch/sparc/prom/misc_64.c +++ b/arch/sparc/prom/misc_64.c @@ -20,10 +20,17 @@ int prom_service_exists(const char *service_name) { - int err = p1275_cmd("test", P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_INOUT(1, 1), service_name); + unsigned long args[5]; - if (err) + args[0] = (unsigned long) "test"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) service_name; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[4]) return 0; return 1; } @@ -31,30 +38,47 @@ int prom_service_exists(const char *service_name) void prom_sun4v_guest_soft_state(void) { const char *svc = "SUNW,soft-state-supported"; + unsigned long args[3]; if (!prom_service_exists(svc)) return; - p1275_cmd(svc, P1275_INOUT(0, 0)); + args[0] = (unsigned long) svc; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } /* Reset and reboot the machine with the command 'bcommand'. */ void prom_reboot(const char *bcommand) { + unsigned long args[4]; + #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) ldom_reboot(bcommand); #endif - p1275_cmd("boot", P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_INOUT(1, 0), bcommand); + args[0] = (unsigned long) "boot"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned long) bcommand; + + p1275_cmd_direct(args); } /* Forth evaluate the expression contained in 'fstring'. */ void prom_feval(const char *fstring) { + unsigned long args[5]; + if (!fstring || fstring[0] == 0) return; - p1275_cmd("interpret", P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_INOUT(1, 1), fstring); + args[0] = (unsigned long) "interpret"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) fstring; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); } EXPORT_SYMBOL(prom_feval); @@ -68,6 +92,7 @@ extern void smp_release(void); */ void prom_cmdline(void) { + unsigned long args[3]; unsigned long flags; local_irq_save(flags); @@ -76,7 +101,11 @@ void prom_cmdline(void) smp_capture(); #endif - p1275_cmd("enter", P1275_INOUT(0, 0)); + args[0] = (unsigned long) "enter"; + args[1] = 0; + args[2] = 0; + + p1275_cmd_direct(args); #ifdef CONFIG_SMP smp_release(); @@ -90,22 +119,32 @@ void prom_cmdline(void) */ void notrace prom_halt(void) { + unsigned long args[3]; + #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) ldom_power_off(); #endif again: - p1275_cmd("exit", P1275_INOUT(0, 0)); + args[0] = (unsigned long) "exit"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); goto again; /* PROM is out to get me -DaveM */ } void prom_halt_power_off(void) { + unsigned long args[3]; + #ifdef CONFIG_SUN_LDOMS if (ldom_domaining_enabled) ldom_power_off(); #endif - p1275_cmd("SUNW,power-off", P1275_INOUT(0, 0)); + args[0] = (unsigned long) "SUNW,power-off"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); /* if nothing else helps, we just halt */ prom_halt(); @@ -114,10 +153,15 @@ void prom_halt_power_off(void) /* Set prom sync handler to call function 'funcp'. */ void prom_setcallback(callback_func_t funcp) { + unsigned long args[5]; if (!funcp) return; - p1275_cmd("set-callback", P1275_ARG(0, P1275_ARG_IN_FUNCTION) | - P1275_INOUT(1, 1), funcp); + args[0] = (unsigned long) "set-callback"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) funcp; + args[4] = (unsigned long) -1; + p1275_cmd_direct(args); } /* Get the idprom and stuff it into buffer 'idbuf'. Returns the @@ -173,57 +217,61 @@ static int prom_get_memory_ihandle(void) } /* Load explicit I/D TLB entries. */ +static long tlb_load(const char *type, unsigned long index, + unsigned long tte_data, unsigned long vaddr) +{ + unsigned long args[9]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 5; + args[2] = 1; + args[3] = (unsigned long) type; + args[4] = (unsigned int) prom_get_mmu_ihandle(); + args[5] = vaddr; + args[6] = tte_data; + args[7] = index; + args[8] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (long) args[8]; +} + long prom_itlb_load(unsigned long index, unsigned long tte_data, unsigned long vaddr) { - return p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(2, P1275_ARG_IN_64B) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_INOUT(5, 1)), - "SUNW,itlb-load", - prom_get_mmu_ihandle(), - /* And then our actual args are pushed backwards. */ - vaddr, - tte_data, - index); + return tlb_load("SUNW,itlb-load", index, tte_data, vaddr); } long prom_dtlb_load(unsigned long index, unsigned long tte_data, unsigned long vaddr) { - return p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(2, P1275_ARG_IN_64B) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_INOUT(5, 1)), - "SUNW,dtlb-load", - prom_get_mmu_ihandle(), - /* And then our actual args are pushed backwards. */ - vaddr, - tte_data, - index); + return tlb_load("SUNW,dtlb-load", index, tte_data, vaddr); } int prom_map(int mode, unsigned long size, unsigned long vaddr, unsigned long paddr) { - int ret = p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_ARG(4, P1275_ARG_IN_64B) | - P1275_ARG(6, P1275_ARG_IN_64B) | - P1275_INOUT(7, 1)), - prom_map_name, - prom_get_mmu_ihandle(), - mode, - size, - vaddr, - 0, - paddr); - + unsigned long args[11]; + int ret; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 7; + args[2] = 1; + args[3] = (unsigned long) prom_map_name; + args[4] = (unsigned int) prom_get_mmu_ihandle(); + args[5] = (unsigned int) mode; + args[6] = size; + args[7] = vaddr; + args[8] = 0; + args[9] = paddr; + args[10] = (unsigned long) -1; + + p1275_cmd_direct(args); + + ret = (int) args[10]; if (ret == 0) ret = -1; return ret; @@ -231,40 +279,51 @@ int prom_map(int mode, unsigned long size, void prom_unmap(unsigned long size, unsigned long vaddr) { - p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(2, P1275_ARG_IN_64B) | - P1275_ARG(3, P1275_ARG_IN_64B) | - P1275_INOUT(4, 0)), - prom_unmap_name, - prom_get_mmu_ihandle(), - size, - vaddr); + unsigned long args[7]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 4; + args[2] = 0; + args[3] = (unsigned long) prom_unmap_name; + args[4] = (unsigned int) prom_get_mmu_ihandle(); + args[5] = size; + args[6] = vaddr; + + p1275_cmd_direct(args); } /* Set aside physical memory which is not touched or modified * across soft resets. */ -unsigned long prom_retain(const char *name, - unsigned long pa_low, unsigned long pa_high, - long size, long align) +int prom_retain(const char *name, unsigned long size, + unsigned long align, unsigned long *paddr) { - /* XXX I don't think we return multiple values correctly. - * XXX OBP supposedly returns pa_low/pa_high here, how does - * XXX it work? + unsigned long args[11]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 5; + args[2] = 3; + args[3] = (unsigned long) "SUNW,retain"; + args[4] = (unsigned int) prom_get_memory_ihandle(); + args[5] = align; + args[6] = size; + args[7] = (unsigned long) name; + args[8] = (unsigned long) -1; + args[9] = (unsigned long) -1; + args[10] = (unsigned long) -1; + + p1275_cmd_direct(args); + + if (args[8]) + return (int) args[8]; + + /* Next we get "phys_high" then "phys_low". On 64-bit + * the phys_high cell is don't care since the phys_low + * cell has the full value. */ + *paddr = args[10]; - /* If align is zero, the pa_low/pa_high args are passed, - * else they are not. - */ - if (align == 0) - return p1275_cmd("SUNW,retain", - (P1275_ARG(0, P1275_ARG_IN_BUF) | P1275_INOUT(5, 2)), - name, pa_low, pa_high, size, align); - else - return p1275_cmd("SUNW,retain", - (P1275_ARG(0, P1275_ARG_IN_BUF) | P1275_INOUT(3, 2)), - name, size, align); + return 0; } /* Get "Unumber" string for the SIMM at the given @@ -277,62 +336,129 @@ int prom_getunumber(int syndrome_code, unsigned long phys_addr, char *buf, int buflen) { - return p1275_cmd(prom_callmethod_name, - (P1275_ARG(0, P1275_ARG_IN_STRING) | - P1275_ARG(3, P1275_ARG_OUT_BUF) | - P1275_ARG(6, P1275_ARG_IN_64B) | - P1275_INOUT(8, 2)), - "SUNW,get-unumber", prom_get_memory_ihandle(), - buflen, buf, P1275_SIZE(buflen), - 0, phys_addr, syndrome_code); + unsigned long args[12]; + + args[0] = (unsigned long) prom_callmethod_name; + args[1] = 7; + args[2] = 2; + args[3] = (unsigned long) "SUNW,get-unumber"; + args[4] = (unsigned int) prom_get_memory_ihandle(); + args[5] = buflen; + args[6] = (unsigned long) buf; + args[7] = 0; + args[8] = phys_addr; + args[9] = (unsigned int) syndrome_code; + args[10] = (unsigned long) -1; + args[11] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[10]; } /* Power management extensions. */ void prom_sleepself(void) { - p1275_cmd("SUNW,sleep-self", P1275_INOUT(0, 0)); + unsigned long args[3]; + + args[0] = (unsigned long) "SUNW,sleep-self"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } int prom_sleepsystem(void) { - return p1275_cmd("SUNW,sleep-system", P1275_INOUT(0, 1)); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,sleep-system"; + args[1] = 0; + args[2] = 1; + args[3] = (unsigned long) -1; + p1275_cmd_direct(args); + + return (int) args[3]; } int prom_wakeupsystem(void) { - return p1275_cmd("SUNW,wakeup-system", P1275_INOUT(0, 1)); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,wakeup-system"; + args[1] = 0; + args[2] = 1; + args[3] = (unsigned long) -1; + p1275_cmd_direct(args); + + return (int) args[3]; } #ifdef CONFIG_SMP void prom_startcpu(int cpunode, unsigned long pc, unsigned long arg) { - p1275_cmd("SUNW,start-cpu", P1275_INOUT(3, 0), cpunode, pc, arg); + unsigned long args[6]; + + args[0] = (unsigned long) "SUNW,start-cpu"; + args[1] = 3; + args[2] = 0; + args[3] = (unsigned int) cpunode; + args[4] = pc; + args[5] = arg; + p1275_cmd_direct(args); } void prom_startcpu_cpuid(int cpuid, unsigned long pc, unsigned long arg) { - p1275_cmd("SUNW,start-cpu-by-cpuid", P1275_INOUT(3, 0), - cpuid, pc, arg); + unsigned long args[6]; + + args[0] = (unsigned long) "SUNW,start-cpu-by-cpuid"; + args[1] = 3; + args[2] = 0; + args[3] = (unsigned int) cpuid; + args[4] = pc; + args[5] = arg; + p1275_cmd_direct(args); } void prom_stopcpu_cpuid(int cpuid) { - p1275_cmd("SUNW,stop-cpu-by-cpuid", P1275_INOUT(1, 0), - cpuid); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,stop-cpu-by-cpuid"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned int) cpuid; + p1275_cmd_direct(args); } void prom_stopself(void) { - p1275_cmd("SUNW,stop-self", P1275_INOUT(0, 0)); + unsigned long args[3]; + + args[0] = (unsigned long) "SUNW,stop-self"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } void prom_idleself(void) { - p1275_cmd("SUNW,idle-self", P1275_INOUT(0, 0)); + unsigned long args[3]; + + args[0] = (unsigned long) "SUNW,idle-self"; + args[1] = 0; + args[2] = 0; + p1275_cmd_direct(args); } void prom_resumecpu(int cpunode) { - p1275_cmd("SUNW,resume-cpu", P1275_INOUT(1, 0), cpunode); + unsigned long args[4]; + + args[0] = (unsigned long) "SUNW,resume-cpu"; + args[1] = 1; + args[2] = 0; + args[3] = (unsigned int) cpunode; + p1275_cmd_direct(args); } #endif diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index 2d8b70d397f1..fa6e4e219b9c 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -22,13 +22,11 @@ struct { long prom_callback; /* 0x00 */ void (*prom_cif_handler)(long *); /* 0x08 */ unsigned long prom_cif_stack; /* 0x10 */ - unsigned long prom_args [23]; /* 0x18 */ - char prom_buffer [3000]; } p1275buf; extern void prom_world(int); -extern void prom_cif_interface(void); +extern void prom_cif_direct(unsigned long *args); extern void prom_cif_callback(void); /* @@ -36,114 +34,20 @@ extern void prom_cif_callback(void); */ DEFINE_RAW_SPINLOCK(prom_entry_lock); -long p1275_cmd(const char *service, long fmt, ...) +void p1275_cmd_direct(unsigned long *args) { - char *p, *q; unsigned long flags; - int nargs, nrets, i; - va_list list; - long attrs, x; - - p = p1275buf.prom_buffer; raw_local_save_flags(flags); raw_local_irq_restore(PIL_NMI); raw_spin_lock(&prom_entry_lock); - p1275buf.prom_args[0] = (unsigned long)p; /* service */ - strcpy (p, service); - p = (char *)(((long)(strchr (p, 0) + 8)) & ~7); - p1275buf.prom_args[1] = nargs = (fmt & 0x0f); /* nargs */ - p1275buf.prom_args[2] = nrets = ((fmt & 0xf0) >> 4); /* nrets */ - attrs = fmt >> 8; - va_start(list, fmt); - for (i = 0; i < nargs; i++, attrs >>= 3) { - switch (attrs & 0x7) { - case P1275_ARG_NUMBER: - p1275buf.prom_args[i + 3] = - (unsigned)va_arg(list, long); - break; - case P1275_ARG_IN_64B: - p1275buf.prom_args[i + 3] = - va_arg(list, unsigned long); - break; - case P1275_ARG_IN_STRING: - strcpy (p, va_arg(list, char *)); - p1275buf.prom_args[i + 3] = (unsigned long)p; - p = (char *)(((long)(strchr (p, 0) + 8)) & ~7); - break; - case P1275_ARG_OUT_BUF: - (void) va_arg(list, char *); - p1275buf.prom_args[i + 3] = (unsigned long)p; - x = va_arg(list, long); - i++; attrs >>= 3; - p = (char *)(((long)(p + (int)x + 7)) & ~7); - p1275buf.prom_args[i + 3] = x; - break; - case P1275_ARG_IN_BUF: - q = va_arg(list, char *); - p1275buf.prom_args[i + 3] = (unsigned long)p; - x = va_arg(list, long); - i++; attrs >>= 3; - memcpy (p, q, (int)x); - p = (char *)(((long)(p + (int)x + 7)) & ~7); - p1275buf.prom_args[i + 3] = x; - break; - case P1275_ARG_OUT_32B: - (void) va_arg(list, char *); - p1275buf.prom_args[i + 3] = (unsigned long)p; - p += 32; - break; - case P1275_ARG_IN_FUNCTION: - p1275buf.prom_args[i + 3] = - (unsigned long)prom_cif_callback; - p1275buf.prom_callback = va_arg(list, long); - break; - } - } - va_end(list); - prom_world(1); - prom_cif_interface(); + prom_cif_direct(args); prom_world(0); - attrs = fmt >> 8; - va_start(list, fmt); - for (i = 0; i < nargs; i++, attrs >>= 3) { - switch (attrs & 0x7) { - case P1275_ARG_NUMBER: - (void) va_arg(list, long); - break; - case P1275_ARG_IN_STRING: - (void) va_arg(list, char *); - break; - case P1275_ARG_IN_FUNCTION: - (void) va_arg(list, long); - break; - case P1275_ARG_IN_BUF: - (void) va_arg(list, char *); - (void) va_arg(list, long); - i++; attrs >>= 3; - break; - case P1275_ARG_OUT_BUF: - p = va_arg(list, char *); - x = va_arg(list, long); - memcpy (p, (char *)(p1275buf.prom_args[i + 3]), (int)x); - i++; attrs >>= 3; - break; - case P1275_ARG_OUT_32B: - p = va_arg(list, char *); - memcpy (p, (char *)(p1275buf.prom_args[i + 3]), 32); - break; - } - } - va_end(list); - x = p1275buf.prom_args [nargs + 3]; - raw_spin_unlock(&prom_entry_lock); raw_local_irq_restore(flags); - - return x; } void prom_cif_init(void *cif_handler, void *cif_stack) diff --git a/arch/sparc/prom/tree_64.c b/arch/sparc/prom/tree_64.c index 3c0d2dd9f693..9d3f9137a43a 100644 --- a/arch/sparc/prom/tree_64.c +++ b/arch/sparc/prom/tree_64.c @@ -16,22 +16,39 @@ #include <asm/oplib.h> #include <asm/ldc.h> +static int prom_node_to_node(const char *type, int node) +{ + unsigned long args[5]; + + args[0] = (unsigned long) type; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[4]; +} + /* Return the child of node 'node' or zero if no this node has no * direct descendent. */ inline int __prom_getchild(int node) { - return p1275_cmd ("child", P1275_INOUT(1, 1), node); + return prom_node_to_node("child", node); } inline int prom_getchild(int node) { int cnode; - if(node == -1) return 0; + if (node == -1) + return 0; cnode = __prom_getchild(node); - if(cnode == -1) return 0; - return (int)cnode; + if (cnode == -1) + return 0; + return cnode; } EXPORT_SYMBOL(prom_getchild); @@ -39,10 +56,12 @@ inline int prom_getparent(int node) { int cnode; - if(node == -1) return 0; - cnode = p1275_cmd ("parent", P1275_INOUT(1, 1), node); - if(cnode == -1) return 0; - return (int)cnode; + if (node == -1) + return 0; + cnode = prom_node_to_node("parent", node); + if (cnode == -1) + return 0; + return cnode; } /* Return the next sibling of node 'node' or zero if no more siblings @@ -50,7 +69,7 @@ inline int prom_getparent(int node) */ inline int __prom_getsibling(int node) { - return p1275_cmd(prom_peer_name, P1275_INOUT(1, 1), node); + return prom_node_to_node(prom_peer_name, node); } inline int prom_getsibling(int node) @@ -72,11 +91,21 @@ EXPORT_SYMBOL(prom_getsibling); */ inline int prom_getproplen(int node, const char *prop) { - if((!node) || (!prop)) return -1; - return p1275_cmd ("getproplen", - P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_INOUT(2, 1), - node, prop); + unsigned long args[6]; + + if (!node || !prop) + return -1; + + args[0] = (unsigned long) "getproplen"; + args[1] = 2; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) prop; + args[5] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[5]; } EXPORT_SYMBOL(prom_getproplen); @@ -87,19 +116,25 @@ EXPORT_SYMBOL(prom_getproplen); inline int prom_getproperty(int node, const char *prop, char *buffer, int bufsize) { + unsigned long args[8]; int plen; plen = prom_getproplen(node, prop); - if ((plen > bufsize) || (plen == 0) || (plen == -1)) { + if ((plen > bufsize) || (plen == 0) || (plen == -1)) return -1; - } else { - /* Ok, things seem all right. */ - return p1275_cmd(prom_getprop_name, - P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_ARG(2,P1275_ARG_OUT_BUF)| - P1275_INOUT(4, 1), - node, prop, buffer, P1275_SIZE(plen)); - } + + args[0] = (unsigned long) prom_getprop_name; + args[1] = 4; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) prop; + args[5] = (unsigned long) buffer; + args[6] = bufsize; + args[7] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[7]; } EXPORT_SYMBOL(prom_getproperty); @@ -110,7 +145,7 @@ inline int prom_getint(int node, const char *prop) { int intprop; - if(prom_getproperty(node, prop, (char *) &intprop, sizeof(int)) != -1) + if (prom_getproperty(node, prop, (char *) &intprop, sizeof(int)) != -1) return intprop; return -1; @@ -126,7 +161,8 @@ int prom_getintdefault(int node, const char *property, int deflt) int retval; retval = prom_getint(node, property); - if(retval == -1) return deflt; + if (retval == -1) + return deflt; return retval; } @@ -138,7 +174,8 @@ int prom_getbool(int node, const char *prop) int retval; retval = prom_getproplen(node, prop); - if(retval == -1) return 0; + if (retval == -1) + return 0; return 1; } EXPORT_SYMBOL(prom_getbool); @@ -152,7 +189,8 @@ void prom_getstring(int node, const char *prop, char *user_buf, int ubuf_size) int len; len = prom_getproperty(node, prop, user_buf, ubuf_size); - if(len != -1) return; + if (len != -1) + return; user_buf[0] = 0; } EXPORT_SYMBOL(prom_getstring); @@ -164,7 +202,8 @@ int prom_nodematch(int node, const char *name) { char namebuf[128]; prom_getproperty(node, "name", namebuf, sizeof(namebuf)); - if(strcmp(namebuf, name) == 0) return 1; + if (strcmp(namebuf, name) == 0) + return 1; return 0; } @@ -190,16 +229,29 @@ int prom_searchsiblings(int node_start, const char *nodename) } EXPORT_SYMBOL(prom_searchsiblings); +static const char *prom_nextprop_name = "nextprop"; + /* Return the first property type for node 'node'. * buffer should be at least 32B in length */ inline char *prom_firstprop(int node, char *buffer) { + unsigned long args[7]; + *buffer = 0; - if(node == -1) return buffer; - p1275_cmd ("nextprop", P1275_ARG(2,P1275_ARG_OUT_32B)| - P1275_INOUT(3, 0), - node, (char *) 0x0, buffer); + if (node == -1) + return buffer; + + args[0] = (unsigned long) prom_nextprop_name; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = 0; + args[5] = (unsigned long) buffer; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + return buffer; } EXPORT_SYMBOL(prom_firstprop); @@ -210,9 +262,10 @@ EXPORT_SYMBOL(prom_firstprop); */ inline char *prom_nextprop(int node, const char *oprop, char *buffer) { + unsigned long args[7]; char buf[32]; - if(node == -1) { + if (node == -1) { *buffer = 0; return buffer; } @@ -220,10 +273,17 @@ inline char *prom_nextprop(int node, const char *oprop, char *buffer) strcpy (buf, oprop); oprop = buf; } - p1275_cmd ("nextprop", P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_ARG(2,P1275_ARG_OUT_32B)| - P1275_INOUT(3, 0), - node, oprop, buffer); + + args[0] = (unsigned long) prom_nextprop_name; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) oprop; + args[5] = (unsigned long) buffer; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + return buffer; } EXPORT_SYMBOL(prom_nextprop); @@ -231,12 +291,19 @@ EXPORT_SYMBOL(prom_nextprop); int prom_finddevice(const char *name) { + unsigned long args[5]; + if (!name) return 0; - return p1275_cmd(prom_finddev_name, - P1275_ARG(0,P1275_ARG_IN_STRING)| - P1275_INOUT(1, 1), - name); + args[0] = (unsigned long) "finddevice"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned long) name; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[4]; } EXPORT_SYMBOL(prom_finddevice); @@ -247,7 +314,7 @@ int prom_node_has_property(int node, const char *prop) *buf = 0; do { prom_nextprop(node, buf, buf); - if(!strcmp(buf, prop)) + if (!strcmp(buf, prop)) return 1; } while (*buf); return 0; @@ -260,6 +327,8 @@ EXPORT_SYMBOL(prom_node_has_property); int prom_setprop(int node, const char *pname, char *value, int size) { + unsigned long args[8]; + if (size == 0) return 0; if ((pname == 0) || (value == 0)) @@ -271,19 +340,37 @@ prom_setprop(int node, const char *pname, char *value, int size) return 0; } #endif - return p1275_cmd ("setprop", P1275_ARG(1,P1275_ARG_IN_STRING)| - P1275_ARG(2,P1275_ARG_IN_BUF)| - P1275_INOUT(4, 1), - node, pname, value, P1275_SIZE(size)); + args[0] = (unsigned long) "setprop"; + args[1] = 4; + args[2] = 1; + args[3] = (unsigned int) node; + args[4] = (unsigned long) pname; + args[5] = (unsigned long) value; + args[6] = size; + args[7] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[7]; } EXPORT_SYMBOL(prom_setprop); inline int prom_inst2pkg(int inst) { + unsigned long args[5]; int node; - node = p1275_cmd ("instance-to-package", P1275_INOUT(1, 1), inst); - if (node == -1) return 0; + args[0] = (unsigned long) "instance-to-package"; + args[1] = 1; + args[2] = 1; + args[3] = (unsigned int) inst; + args[4] = (unsigned long) -1; + + p1275_cmd_direct(args); + + node = (int) args[4]; + if (node == -1) + return 0; return node; } @@ -296,17 +383,28 @@ prom_pathtoinode(const char *path) int node, inst; inst = prom_devopen (path); - if (inst == 0) return 0; - node = prom_inst2pkg (inst); - prom_devclose (inst); - if (node == -1) return 0; + if (inst == 0) + return 0; + node = prom_inst2pkg(inst); + prom_devclose(inst); + if (node == -1) + return 0; return node; } int prom_ihandle2path(int handle, char *buffer, int bufsize) { - return p1275_cmd("instance-to-path", - P1275_ARG(1,P1275_ARG_OUT_BUF)| - P1275_INOUT(3, 1), - handle, buffer, P1275_SIZE(bufsize)); + unsigned long args[7]; + + args[0] = (unsigned long) "instance-to-path"; + args[1] = 3; + args[2] = 1; + args[3] = (unsigned int) handle; + args[4] = (unsigned long) buffer; + args[5] = bufsize; + args[6] = (unsigned long) -1; + + p1275_cmd_direct(args); + + return (int) args[6]; } diff --git a/arch/tile/include/arch/chip_tile64.h b/arch/tile/include/arch/chip_tile64.h index 1246573be59e..261aaba092d4 100644 --- a/arch/tile/include/arch/chip_tile64.h +++ b/arch/tile/include/arch/chip_tile64.h @@ -150,6 +150,9 @@ /** Is the PROC_STATUS SPR supported? */ #define CHIP_HAS_PROC_STATUS_SPR() 0 +/** Is the DSTREAM_PF SPR supported? */ +#define CHIP_HAS_DSTREAM_PF() 0 + /** Log of the number of mshims we have. */ #define CHIP_LOG_NUM_MSHIMS() 2 diff --git a/arch/tile/include/arch/chip_tilepro.h b/arch/tile/include/arch/chip_tilepro.h index e864c47fc89c..70017699a74c 100644 --- a/arch/tile/include/arch/chip_tilepro.h +++ b/arch/tile/include/arch/chip_tilepro.h @@ -150,6 +150,9 @@ /** Is the PROC_STATUS SPR supported? */ #define CHIP_HAS_PROC_STATUS_SPR() 1 +/** Is the DSTREAM_PF SPR supported? */ +#define CHIP_HAS_DSTREAM_PF() 0 + /** Log of the number of mshims we have. */ #define CHIP_LOG_NUM_MSHIMS() 2 diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h index 5a34da6cdd79..8b60ec8b2d19 100644 --- a/arch/tile/include/asm/compat.h +++ b/arch/tile/include/asm/compat.h @@ -195,7 +195,7 @@ static inline unsigned long ptr_to_compat_reg(void __user *uptr) return (long)(int)(long __force)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; @@ -214,8 +214,9 @@ extern int compat_setup_rt_frame(int sig, struct k_sigaction *ka, struct compat_sigaction; struct compat_siginfo; struct compat_sigaltstack; -long compat_sys_execve(char __user *path, compat_uptr_t __user *argv, - compat_uptr_t __user *envp); +long compat_sys_execve(const char __user *path, + const compat_uptr_t __user *argv, + const compat_uptr_t __user *envp); long compat_sys_rt_sigaction(int sig, struct compat_sigaction __user *act, struct compat_sigaction __user *oact, size_t sigsetsize); diff --git a/arch/tile/include/asm/io.h b/arch/tile/include/asm/io.h index 8c95bef3fa45..ee43328713ab 100644 --- a/arch/tile/include/asm/io.h +++ b/arch/tile/include/asm/io.h @@ -164,22 +164,22 @@ static inline void _tile_writeq(u64 val, unsigned long addr) #define iowrite32 writel #define iowrite64 writeq -static inline void *memcpy_fromio(void *dst, void *src, int len) +static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, + size_t len) { int x; BUG_ON((unsigned long)src & 0x3); for (x = 0; x < len; x += 4) *(u32 *)(dst + x) = readl(src + x); - return dst; } -static inline void *memcpy_toio(void *dst, void *src, int len) +static inline void memcpy_toio(volatile void __iomem *dst, const void *src, + size_t len) { int x; BUG_ON((unsigned long)dst & 0x3); for (x = 0; x < len; x += 4) writel(*(u32 *)(src + x), dst + x); - return dst; } /* diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h index d942d09b252e..ccd5f8425688 100644 --- a/arch/tile/include/asm/processor.h +++ b/arch/tile/include/asm/processor.h @@ -103,6 +103,18 @@ struct thread_struct { /* Any other miscellaneous processor state bits */ unsigned long proc_status; #endif +#if !CHIP_HAS_FIXED_INTVEC_BASE() + /* Interrupt base for PL0 interrupts */ + unsigned long interrupt_vector_base; +#endif +#if CHIP_HAS_TILE_RTF_HWM() + /* Tile cache retry fifo high-water mark */ + unsigned long tile_rtf_hwm; +#endif +#if CHIP_HAS_DSTREAM_PF() + /* Data stream prefetch control */ + unsigned long dstream_pf; +#endif #ifdef CONFIG_HARDWALL /* Is this task tied to an activated hardwall? */ struct hardwall_info *hardwall; diff --git a/arch/tile/include/asm/ptrace.h b/arch/tile/include/asm/ptrace.h index acdae814e016..4a02bb073979 100644 --- a/arch/tile/include/asm/ptrace.h +++ b/arch/tile/include/asm/ptrace.h @@ -51,10 +51,7 @@ typedef uint_reg_t pt_reg_t; /* * This struct defines the way the registers are stored on the stack during a - * system call/exception. It should be a multiple of 8 bytes to preserve - * normal stack alignment rules. - * - * Must track <sys/ucontext.h> and <sys/procfs.h> + * system call or exception. "struct sigcontext" has the same shape. */ struct pt_regs { /* Saved main processor registers; 56..63 are special. */ @@ -80,11 +77,6 @@ struct pt_regs { #endif /* __ASSEMBLY__ */ -/* Flag bits in pt_regs.flags */ -#define PT_FLAGS_DISABLE_IRQ 1 /* on return to kernel, disable irqs */ -#define PT_FLAGS_CALLER_SAVES 2 /* caller-save registers are valid */ -#define PT_FLAGS_RESTORE_REGS 4 /* restore callee-save regs on return */ - #define PTRACE_GETREGS 12 #define PTRACE_SETREGS 13 #define PTRACE_GETFPREGS 14 @@ -101,6 +93,11 @@ struct pt_regs { #ifdef __KERNEL__ +/* Flag bits in pt_regs.flags */ +#define PT_FLAGS_DISABLE_IRQ 1 /* on return to kernel, disable irqs */ +#define PT_FLAGS_CALLER_SAVES 2 /* caller-save registers are valid */ +#define PT_FLAGS_RESTORE_REGS 4 /* restore callee-save regs on return */ + #ifndef __ASSEMBLY__ #define instruction_pointer(regs) ((regs)->pc) diff --git a/arch/tile/include/asm/sigcontext.h b/arch/tile/include/asm/sigcontext.h index 7cd7672e3ad4..5e2d03336f53 100644 --- a/arch/tile/include/asm/sigcontext.h +++ b/arch/tile/include/asm/sigcontext.h @@ -15,13 +15,21 @@ #ifndef _ASM_TILE_SIGCONTEXT_H #define _ASM_TILE_SIGCONTEXT_H -/* NOTE: we can't include <linux/ptrace.h> due to #include dependencies. */ -#include <asm/ptrace.h> - -/* Must track <sys/ucontext.h> */ +#include <arch/abi.h> +/* + * struct sigcontext has the same shape as struct pt_regs, + * but is simplified since we know the fault is from userspace. + */ struct sigcontext { - struct pt_regs regs; + uint_reg_t gregs[53]; /* General-purpose registers. */ + uint_reg_t tp; /* Aliases gregs[TREG_TP]. */ + uint_reg_t sp; /* Aliases gregs[TREG_SP]. */ + uint_reg_t lr; /* Aliases gregs[TREG_LR]. */ + uint_reg_t pc; /* Program counter. */ + uint_reg_t ics; /* In Interrupt Critical Section? */ + uint_reg_t faultnum; /* Fault number. */ + uint_reg_t pad[5]; }; #endif /* _ASM_TILE_SIGCONTEXT_H */ diff --git a/arch/tile/include/asm/signal.h b/arch/tile/include/asm/signal.h index eb0253f32202..c1ee1d61d44c 100644 --- a/arch/tile/include/asm/signal.h +++ b/arch/tile/include/asm/signal.h @@ -24,6 +24,7 @@ #include <asm-generic/signal.h> #if defined(__KERNEL__) && !defined(__ASSEMBLY__) +struct pt_regs; int restore_sigcontext(struct pt_regs *, struct sigcontext __user *, long *); int setup_sigcontext(struct sigcontext __user *, struct pt_regs *); void do_signal(struct pt_regs *regs); diff --git a/arch/tile/include/asm/syscalls.h b/arch/tile/include/asm/syscalls.h index af165a74537f..ce99ffefeacf 100644 --- a/arch/tile/include/asm/syscalls.h +++ b/arch/tile/include/asm/syscalls.h @@ -62,10 +62,12 @@ long sys_fork(void); long _sys_fork(struct pt_regs *regs); long sys_vfork(void); long _sys_vfork(struct pt_regs *regs); -long sys_execve(char __user *filename, char __user * __user *argv, - char __user * __user *envp); -long _sys_execve(char __user *filename, char __user * __user *argv, - char __user * __user *envp, struct pt_regs *regs); +long sys_execve(const char __user *filename, + const char __user *const __user *argv, + const char __user *const __user *envp); +long _sys_execve(const char __user *filename, + const char __user *const __user *argv, + const char __user *const __user *envp, struct pt_regs *regs); /* kernel/signal.c */ long sys_sigaltstack(const stack_t __user *, stack_t __user *); @@ -86,10 +88,13 @@ int _sys_cmpxchg_badaddr(unsigned long address, struct pt_regs *); #endif #ifdef CONFIG_COMPAT -long compat_sys_execve(char __user *path, compat_uptr_t __user *argv, - compat_uptr_t __user *envp); -long _compat_sys_execve(char __user *path, compat_uptr_t __user *argv, - compat_uptr_t __user *envp, struct pt_regs *regs); +long compat_sys_execve(const char __user *path, + const compat_uptr_t __user *argv, + const compat_uptr_t __user *envp); +long _compat_sys_execve(const char __user *path, + const compat_uptr_t __user *argv, + const compat_uptr_t __user *envp, + struct pt_regs *regs); long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr, struct compat_sigaltstack __user *uoss_ptr); long _compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr, diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S index 84f296ca9e63..8f58bdff20d7 100644 --- a/arch/tile/kernel/intvec_32.S +++ b/arch/tile/kernel/intvec_32.S @@ -1506,13 +1506,6 @@ handle_ill: } STD_ENDPROC(handle_ill) - .pushsection .rodata, "a" - .align 8 -bpt_code: - bpt - ENDPROC(bpt_code) - .popsection - /* Various stub interrupt handlers and syscall handlers */ STD_ENTRY_LOCAL(_kernel_double_fault) diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 985cc28c74c5..84c29111756c 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -408,6 +408,15 @@ static void save_arch_state(struct thread_struct *t) #if CHIP_HAS_PROC_STATUS_SPR() t->proc_status = __insn_mfspr(SPR_PROC_STATUS); #endif +#if !CHIP_HAS_FIXED_INTVEC_BASE() + t->interrupt_vector_base = __insn_mfspr(SPR_INTERRUPT_VECTOR_BASE_0); +#endif +#if CHIP_HAS_TILE_RTF_HWM() + t->tile_rtf_hwm = __insn_mfspr(SPR_TILE_RTF_HWM); +#endif +#if CHIP_HAS_DSTREAM_PF() + t->dstream_pf = __insn_mfspr(SPR_DSTREAM_PF); +#endif } static void restore_arch_state(const struct thread_struct *t) @@ -428,14 +437,14 @@ static void restore_arch_state(const struct thread_struct *t) #if CHIP_HAS_PROC_STATUS_SPR() __insn_mtspr(SPR_PROC_STATUS, t->proc_status); #endif +#if !CHIP_HAS_FIXED_INTVEC_BASE() + __insn_mtspr(SPR_INTERRUPT_VECTOR_BASE_0, t->interrupt_vector_base); +#endif #if CHIP_HAS_TILE_RTF_HWM() - /* - * Clear this whenever we switch back to a process in case - * the previous process was monkeying with it. Even if enabled - * in CBOX_MSR1 via TILE_RTF_HWM_MIN, it's still just a - * performance hint, so isn't worth a full save/restore. - */ - __insn_mtspr(SPR_TILE_RTF_HWM, 0); + __insn_mtspr(SPR_TILE_RTF_HWM, t->tile_rtf_hwm); +#endif +#if CHIP_HAS_DSTREAM_PF() + __insn_mtspr(SPR_DSTREAM_PF, t->dstream_pf); #endif } @@ -561,8 +570,9 @@ out: } #ifdef CONFIG_COMPAT -long _compat_sys_execve(char __user *path, compat_uptr_t __user *argv, - compat_uptr_t __user *envp, struct pt_regs *regs) +long _compat_sys_execve(const char __user *path, + const compat_uptr_t __user *argv, + const compat_uptr_t __user *envp, struct pt_regs *regs) { long error; char *filename; @@ -657,7 +667,7 @@ void show_regs(struct pt_regs *regs) regs->regs[51], regs->regs[52], regs->tp); pr_err(" sp : "REGFMT" lr : "REGFMT"\n", regs->sp, regs->lr); #else - for (i = 0; i < 52; i += 3) + for (i = 0; i < 52; i += 4) pr_err(" r%-2d: "REGFMT" r%-2d: "REGFMT " r%-2d: "REGFMT" r%-2d: "REGFMT"\n", i, regs->regs[i], i+1, regs->regs[i+1], diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c index 45b66a3c991f..ce183aa1492c 100644 --- a/arch/tile/kernel/signal.c +++ b/arch/tile/kernel/signal.c @@ -61,13 +61,19 @@ int restore_sigcontext(struct pt_regs *regs, /* Always make any pending restarted system calls return -EINTR */ current_thread_info()->restart_block.fn = do_no_restart_syscall; + /* + * Enforce that sigcontext is like pt_regs, and doesn't mess + * up our stack alignment rules. + */ + BUILD_BUG_ON(sizeof(struct sigcontext) != sizeof(struct pt_regs)); + BUILD_BUG_ON(sizeof(struct sigcontext) % 8 != 0); + for (i = 0; i < sizeof(struct pt_regs)/sizeof(long); ++i) - err |= __get_user(((long *)regs)[i], - &((long __user *)(&sc->regs))[i]); + err |= __get_user(regs->regs[i], &sc->gregs[i]); regs->faultnum = INT_SWINT_1_SIGRETURN; - err |= __get_user(*pr0, &sc->regs.regs[0]); + err |= __get_user(*pr0, &sc->gregs[0]); return err; } @@ -112,8 +118,7 @@ int setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs) int i, err = 0; for (i = 0; i < sizeof(struct pt_regs)/sizeof(long); ++i) - err |= __put_user(((long *)regs)[i], - &((long __user *)(&sc->regs))[i]); + err |= __put_user(regs->regs[i], &sc->gregs[i]); return err; } @@ -203,19 +208,17 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, * Set up registers for signal handler. * Registers that we don't modify keep the value they had from * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). */ regs->pc = (unsigned long) ka->sa.sa_handler; regs->ex1 = PL_ICS_EX1(USER_PL, 1); /* set crit sec in handler */ regs->sp = (unsigned long) frame; regs->lr = restorer; regs->regs[0] = (unsigned long) usig; - - if (ka->sa.sa_flags & SA_SIGINFO) { - /* Need extra arguments, so mark to restore caller-saves. */ - regs->regs[1] = (unsigned long) &frame->info; - regs->regs[2] = (unsigned long) &frame->uc; - regs->flags |= PT_FLAGS_CALLER_SAVES; - } + regs->regs[1] = (unsigned long) &frame->info; + regs->regs[2] = (unsigned long) &frame->uc; + regs->flags |= PT_FLAGS_CALLER_SAVES; /* * Notify any tracer that was single-stepping it. diff --git a/arch/tile/kernel/stack.c b/arch/tile/kernel/stack.c index 38a68b0b4581..ea2e0ce28380 100644 --- a/arch/tile/kernel/stack.c +++ b/arch/tile/kernel/stack.c @@ -175,7 +175,7 @@ static struct pt_regs *valid_sigframe(struct KBacktraceIterator* kbt) pr_err(" <received signal %d>\n", frame->info.si_signo); } - return &frame->uc.uc_mcontext.regs; + return (struct pt_regs *)&frame->uc.uc_mcontext; } return NULL; } diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c index 0c46e398cd8f..63c740a85b4c 100644 --- a/arch/um/drivers/hostaudio_kern.c +++ b/arch/um/drivers/hostaudio_kern.c @@ -40,6 +40,11 @@ static char *mixer = HOSTAUDIO_DEV_MIXER; " This is used to specify the host mixer device to the hostaudio driver.\n"\ " The default is \"" HOSTAUDIO_DEV_MIXER "\".\n\n" +module_param(dsp, charp, 0644); +MODULE_PARM_DESC(dsp, DSP_HELP); +module_param(mixer, charp, 0644); +MODULE_PARM_DESC(mixer, MIXER_HELP); + #ifndef MODULE static int set_dsp(char *name, int *add) { @@ -56,15 +61,6 @@ static int set_mixer(char *name, int *add) } __uml_setup("mixer=", set_mixer, "mixer=<mixer device>\n" MIXER_HELP); - -#else /*MODULE*/ - -module_param(dsp, charp, 0644); -MODULE_PARM_DESC(dsp, DSP_HELP); - -module_param(mixer, charp, 0644); -MODULE_PARM_DESC(mixer, MIXER_HELP); - #endif /* /dev/dsp file operations */ diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index de317d0c3294..ebc680717e59 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -690,7 +690,7 @@ static void with_console(struct mc_request *req, void (*proc)(void *), static void sysrq_proc(void *arg) { char *op = arg; - handle_sysrq(*op, NULL); + handle_sysrq(*op); } void mconsole_sysrq(struct mc_request *req) diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 2ab233ba32c1..47d0c37897d5 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -255,18 +255,6 @@ static void uml_net_tx_timeout(struct net_device *dev) netif_wake_queue(dev); } -static int uml_net_set_mac(struct net_device *dev, void *addr) -{ - struct uml_net_private *lp = netdev_priv(dev); - struct sockaddr *hwaddr = addr; - - spin_lock_irq(&lp->lock); - eth_mac_addr(dev, hwaddr->sa_data); - spin_unlock_irq(&lp->lock); - - return 0; -} - static int uml_net_change_mtu(struct net_device *dev, int new_mtu) { dev->mtu = new_mtu; @@ -373,7 +361,7 @@ static const struct net_device_ops uml_netdev_ops = { .ndo_start_xmit = uml_net_start_xmit, .ndo_set_multicast_list = uml_net_set_multicast_list, .ndo_tx_timeout = uml_net_tx_timeout, - .ndo_set_mac_address = uml_net_set_mac, + .ndo_set_mac_address = eth_mac_addr, .ndo_change_mtu = uml_net_change_mtu, .ndo_validate_addr = eth_validate_addr, }; @@ -472,7 +460,8 @@ static void eth_configure(int n, void *init, char *mac, ((*transport->user->init)(&lp->user, dev) != 0)) goto out_unregister; - eth_mac_addr(dev, device->mac); + /* don't use eth_mac_addr, it will not work here */ + memcpy(dev->dev_addr, device->mac, ETH_ALEN); dev->mtu = transport->user->mtu; dev->netdev_ops = ¨_netdev_ops; dev->ethtool_ops = ¨_net_ethtool_ops; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 1bcd208c459f..9734994cba1e 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -163,6 +163,7 @@ struct ubd { struct scatterlist sg[MAX_SG]; struct request *request; int start_sg, end_sg; + sector_t rq_pos; }; #define DEFAULT_COW { \ @@ -187,6 +188,7 @@ struct ubd { .request = NULL, \ .start_sg = 0, \ .end_sg = 0, \ + .rq_pos = 0, \ } /* Protected by ubd_lock */ @@ -1228,7 +1230,6 @@ static void do_ubd_request(struct request_queue *q) { struct io_thread_req *io_req; struct request *req; - sector_t sector; int n; while(1){ @@ -1239,12 +1240,12 @@ static void do_ubd_request(struct request_queue *q) return; dev->request = req; + dev->rq_pos = blk_rq_pos(req); dev->start_sg = 0; dev->end_sg = blk_rq_map_sg(q, req, dev->sg); } req = dev->request; - sector = blk_rq_pos(req); while(dev->start_sg < dev->end_sg){ struct scatterlist *sg = &dev->sg[dev->start_sg]; @@ -1256,10 +1257,9 @@ static void do_ubd_request(struct request_queue *q) return; } prepare_request(req, io_req, - (unsigned long long)sector << 9, + (unsigned long long)dev->rq_pos << 9, sg->offset, sg->length, sg_page(sg)); - sector += sg->length >> 9; n = os_write_file(thread_fd, &io_req, sizeof(struct io_thread_req *)); if(n != sizeof(struct io_thread_req *)){ @@ -1272,6 +1272,7 @@ static void do_ubd_request(struct request_queue *q) return; } + dev->rq_pos += sg->length >> 9; dev->start_sg++; } dev->end_sg = 0; diff --git a/arch/um/kernel/exec.c b/arch/um/kernel/exec.c index cd145eda3579..49b5e1eb3262 100644 --- a/arch/um/kernel/exec.c +++ b/arch/um/kernel/exec.c @@ -62,7 +62,7 @@ static long execve1(const char *file, return error; } -long um_execve(const char *file, char __user *__user *argv, char __user *__user *env) +long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env) { long err; @@ -72,8 +72,8 @@ long um_execve(const char *file, char __user *__user *argv, char __user *__user return err; } -long sys_execve(const char __user *file, char __user *__user *argv, - char __user *__user *env) +long sys_execve(const char __user *file, const char __user *const __user *argv, + const char __user *const __user *env) { long error; char *filename; diff --git a/arch/um/kernel/internal.h b/arch/um/kernel/internal.h index 1303a105fe91..5bf97db24a04 100644 --- a/arch/um/kernel/internal.h +++ b/arch/um/kernel/internal.h @@ -1 +1 @@ -extern long um_execve(const char *file, char __user *__user *argv, char __user *__user *env); +extern long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env); diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 5ddb246626db..f958cb876ee3 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -60,8 +60,8 @@ int kernel_execve(const char *filename, fs = get_fs(); set_fs(KERNEL_DS); - ret = um_execve(filename, (char __user *__user *)argv, - (char __user *__user *) envp); + ret = um_execve(filename, (const char __user *const __user *)argv, + (const char __user *const __user *) envp); set_fs(fs); return ret; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f0ee331feeab..8c9e609a175b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -25,6 +25,7 @@ config X86 select HAVE_IDE select HAVE_OPROFILE select HAVE_PERF_EVENTS if (!M386 && !M486) + select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT select HAVE_KPROBES select ARCH_WANT_OPTIONAL_GPIOLIB @@ -33,6 +34,7 @@ config X86 select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_C_RECORDMCOUNT select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER @@ -59,6 +61,8 @@ config X86 select ANON_INODES select HAVE_ARCH_KMEMCHECK select HAVE_USER_RETURN_NOTIFIER + select HAVE_ARCH_JUMP_LABEL + select HAVE_TEXT_POKE_SMP config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) @@ -651,7 +655,7 @@ config GART_IOMMU bool "GART IOMMU support" if EMBEDDED default y select SWIOTLB - depends on X86_64 && PCI && K8_NB + depends on X86_64 && PCI && AMD_NB ---help--- Support for full DMA access of devices with 32bit memory access only on systems with more than 3GB. This is usually needed for USB, @@ -776,6 +780,17 @@ config SCHED_MC making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. +config IRQ_TIME_ACCOUNTING + bool "Fine granularity task level IRQ time accounting" + default n + ---help--- + Select this option to enable fine granularity task irq time + accounting. This is done by reading a timestamp on each + transitions between softirq and hardirq state, so there can be a + small performance impact. + + If in doubt, say N here. + source "kernel/Kconfig.preempt" config X86_UP_APIC @@ -1129,6 +1144,9 @@ config X86_PAE config ARCH_PHYS_ADDR_T_64BIT def_bool X86_64 || X86_PAE +config ARCH_DMA_ADDR_T_64BIT + def_bool X86_64 || HIGHMEM64G + config DIRECT_GBPAGES bool "Enable 1GB pages for kernel pagetables" if EMBEDDED default y @@ -1307,25 +1325,34 @@ config X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK Set whether the default state of memory_corruption_check is on or off. -config X86_RESERVE_LOW_64K - bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen" - default y +config X86_RESERVE_LOW + int "Amount of low memory, in kilobytes, to reserve for the BIOS" + default 64 + range 4 640 ---help--- - Reserve the first 64K of physical RAM on BIOSes that are known - to potentially corrupt that memory range. A numbers of BIOSes are - known to utilize this area during suspend/resume, so it must not - be used by the kernel. + Specify the amount of low memory to reserve for the BIOS. + + The first page contains BIOS data structures that the kernel + must not use, so that page must always be reserved. - Set this to N if you are absolutely sure that you trust the BIOS - to get all its memory reservations and usages right. + By default we reserve the first 64K of physical RAM, as a + number of BIOSes are known to corrupt that memory range + during events such as suspend/resume or monitor cable + insertion, so it must not be used by the kernel. - If you have doubts about the BIOS (e.g. suspend/resume does not - work or there's kernel crashes after certain hardware hotplug - events) and it's not AMI or Phoenix, then you might want to enable - X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical - corruption patterns. + You can set this to 4 if you are absolutely sure that you + trust the BIOS to get all its memory reservations and usages + right. If you know your BIOS have problems beyond the + default 64K area, you can set this to 640 to avoid using the + entire low memory range. - Say Y if unsure. + If you have doubts about the BIOS (e.g. suspend/resume does + not work or there's kernel crashes after certain hardware + hotplug events) then you might want to enable + X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check + typical corruption patterns. + + Leave this to the default value of 64 if you are unsure. config MATH_EMULATION bool @@ -1881,7 +1908,7 @@ config PCI_GODIRECT bool "Direct" config PCI_GOOLPC - bool "OLPC" + bool "OLPC XO-1" depends on OLPC config PCI_GOANY @@ -2042,14 +2069,21 @@ config SCx200HR_TIMER config OLPC bool "One Laptop Per Child support" select GPIOLIB + select OLPC_OPENFIRMWARE ---help--- Add support for detecting the unique features of the OLPC XO hardware. +config OLPC_XO1 + tristate "OLPC XO-1 support" + depends on OLPC && PCI + ---help--- + Add support for non-essential features of the OLPC XO-1 laptop. + config OLPC_OPENFIRMWARE bool "Support for OLPC's Open Firmware" depends on !X86_64 && !X86_PAE - default y if OLPC + default n help This option adds support for the implementation of Open Firmware that is used on the OLPC XO-1 Children's Machine. @@ -2057,7 +2091,7 @@ config OLPC_OPENFIRMWARE endif # X86_32 -config K8_NB +config AMD_NB def_bool y depends on CPU_SUP_AMD && PCI @@ -2106,6 +2140,10 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 +config HAVE_TEXT_POKE_SMP + bool + select STOP_MACHINE if SMP + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 75085080b63e..e5bb96b10f1a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -43,6 +43,10 @@ config EARLY_PRINTK with klogd/syslogd or the X server. You should normally N here, unless you want to debug such a crash. +config EARLY_PRINTK_MRST + bool "Early printk for MRST platform support" + depends on EARLY_PRINTK && X86_MRST + config EARLY_PRINTK_DBGP bool "Early printk via EHCI debug port" depends on EARLY_PRINTK && PCI diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 8aa1b59b9074..b02e509072a7 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -74,7 +74,7 @@ endif ifdef CONFIG_CC_STACKPROTECTOR cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh - ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(biarch)),y) + ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y) stackp-y := -fstack-protector KBUILD_CFLAGS += $(stackp-y) else @@ -96,8 +96,12 @@ cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_en # is .cfi_signal_frame supported too? cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1) cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) + +# does binutils support specific instructions? +asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1) + +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) LDFLAGS := -m elf_$(UTS_MACHINE) diff --git a/arch/x86/boot/early_serial_console.c b/arch/x86/boot/early_serial_console.c index 030f4b93e255..5df2869c874b 100644 --- a/arch/x86/boot/early_serial_console.c +++ b/arch/x86/boot/early_serial_console.c @@ -58,7 +58,19 @@ static void parse_earlyprintk(void) if (arg[pos] == ',') pos++; - if (!strncmp(arg, "ttyS", 4)) { + /* + * make sure we have + * "serial,0x3f8,115200" + * "serial,ttyS0,115200" + * "ttyS0,115200" + */ + if (pos == 7 && !strncmp(arg + pos, "0x", 2)) { + port = simple_strtoull(arg + pos, &e, 16); + if (port == 0 || arg + pos == e) + port = DEFAULT_SERIAL_PORT; + else + pos = e - arg; + } else if (!strncmp(arg + pos, "ttyS", 4)) { static const int bases[] = { 0x3f8, 0x2f8 }; int idx = 0; diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 0350311906ae..2d93bdbc9ac0 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -34,7 +34,7 @@ #include <asm/ia32.h> #undef WARN_OLD -#undef CORE_DUMP /* probably broken */ +#undef CORE_DUMP /* definitely broken */ static int load_aout_binary(struct linux_binprm *, struct pt_regs *regs); static int load_aout_library(struct file *); @@ -131,21 +131,15 @@ static void set_brk(unsigned long start, unsigned long end) * macros to write out all the necessary info. */ -static int dump_write(struct file *file, const void *addr, int nr) -{ - return file->f_op->write(file, addr, nr, &file->f_pos) == nr; -} +#include <linux/coredump.h> #define DUMP_WRITE(addr, nr) \ if (!dump_write(file, (void *)(addr), (nr))) \ goto end_coredump; -#define DUMP_SEEK(offset) \ - if (file->f_op->llseek) { \ - if (file->f_op->llseek(file, (offset), 0) != (offset)) \ - goto end_coredump; \ - } else \ - file->f_pos = (offset) +#define DUMP_SEEK(offset) \ + if (!dump_seek(file, offset)) \ + goto end_coredump; #define START_DATA() (u.u_tsize << PAGE_SHIFT) #define START_STACK(u) (u.start_stack) @@ -217,12 +211,6 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, dump_size = dump.u_ssize << PAGE_SHIFT; DUMP_WRITE(dump_start, dump_size); } - /* - * Finally dump the task struct. Not be used by gdb, but - * could be useful - */ - set_fs(KERNEL_DS); - DUMP_WRITE(current, sizeof(*current)); end_coredump: set_fs(fs); return has_dumped; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index b86feabed69b..518bb99c3394 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -50,7 +50,12 @@ /* * Reload arg registers from stack in case ptrace changed them. * We don't reload %eax because syscall_trace_enter() returned - * the value it wants us to use in the table lookup. + * the %rax value we should see. Instead, we just truncate that + * value to 32 bits again as we did on entry from user mode. + * If it's a new value set by user_regset during entry tracing, + * this matches the normal truncation of the user-mode value. + * If it's -1 to make us punt the syscall, then (u32)-1 is still + * an appropriately invalid value. */ .macro LOAD_ARGS32 offset, _r9=0 .if \_r9 @@ -60,6 +65,7 @@ movl \offset+48(%rsp),%edx movl \offset+56(%rsp),%esi movl \offset+64(%rsp),%edi + movl %eax,%eax /* zero extension */ .endm .macro CFI_STARTPROC32 simple @@ -153,7 +159,7 @@ ENTRY(ia32_sysenter_target) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10) CFI_REMEMBER_STATE jnz sysenter_tracesys - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys sysenter_do_call: IA32_ARG_FIXUP @@ -195,7 +201,7 @@ sysexit_from_sys_call: movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */ call audit_syscall_entry movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys movl %ebx,%edi /* reload 1st syscall arg */ movl RCX-ARGOFFSET(%rsp),%esi /* reload 2nd syscall arg */ @@ -248,7 +254,7 @@ sysenter_tracesys: call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ jmp sysenter_do_call CFI_ENDPROC @@ -314,7 +320,7 @@ ENTRY(ia32_cstar_target) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10) CFI_REMEMBER_STATE jnz cstar_tracesys - cmpl $IA32_NR_syscalls-1,%eax + cmpq $IA32_NR_syscalls-1,%rax ja ia32_badsys cstar_do_call: IA32_ARG_FIXUP 1 @@ -367,7 +373,7 @@ cstar_tracesys: LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */ RESTORE_REST xchgl %ebp,%r9d - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ jmp cstar_do_call END(ia32_cstar_target) @@ -425,7 +431,7 @@ ENTRY(ia32_syscall) orl $TS_COMPAT,TI_status(%r10) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10) jnz ia32_tracesys - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys ia32_do_call: IA32_ARG_FIXUP @@ -444,7 +450,7 @@ ia32_tracesys: call syscall_trace_enter LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ RESTORE_REST - cmpl $(IA32_NR_syscalls-1),%eax + cmpq $(IA32_NR_syscalls-1),%rax ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */ jmp ia32_do_call END(ia32_syscall) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index bc6abb7bc7ee..76561d20ea2f 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/stddef.h> #include <linux/stringify.h> +#include <linux/jump_label.h> #include <asm/asm.h> /* @@ -160,6 +161,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, #define __parainstructions_end NULL #endif +extern void *text_poke_early(void *addr, const void *opcode, size_t len); + /* * Clear and restore the kernel write-protection flag on the local CPU. * Allows the kernel to edit read-only pages. @@ -180,4 +183,12 @@ static inline void apply_paravirt(struct paravirt_patch_site *start, extern void *text_poke(void *addr, const void *opcode, size_t len); extern void *text_poke_smp(void *addr, const void *opcode, size_t len); +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) +#define IDEAL_NOP_SIZE_5 5 +extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; +extern void arch_init_ideal_nop5(void); +#else +static inline void arch_init_ideal_nop5(void) {} +#endif + #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h index 5af2982133b5..f16a2caca1e0 100644 --- a/arch/x86/include/asm/amd_iommu.h +++ b/arch/x86/include/asm/amd_iommu.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h index d2544f1d705d..916bc8111a01 100644 --- a/arch/x86/include/asm/amd_iommu_proto.h +++ b/arch/x86/include/asm/amd_iommu_proto.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009 Advanced Micro Devices, Inc. + * Copyright (C) 2009-2010 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * * This program is free software; you can redistribute it and/or modify it @@ -38,4 +38,10 @@ static inline void amd_iommu_stats_init(void) { } #endif /* !CONFIG_AMD_IOMMU_STATS */ +static inline bool is_rd890_iommu(struct pci_dev *pdev) +{ + return (pdev->vendor == PCI_VENDOR_ID_ATI) && + (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); +} + #endif /* _ASM_X86_AMD_IOMMU_PROTO_H */ diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index 7014e88bc779..e3509fc303bf 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -368,6 +368,9 @@ struct amd_iommu { /* capabilities of that IOMMU read from ACPI */ u32 cap; + /* flags read from acpi table */ + u8 acpi_flags; + /* * Capability pointer. There could be more than one IOMMU per PCI * device function if there are more than one AMD IOMMU capability @@ -411,6 +414,24 @@ struct amd_iommu { /* default dma_ops domain for that IOMMU */ struct dma_ops_domain *default_dom; + + /* + * We can't rely on the BIOS to restore all values on reinit, so we + * need to stash them + */ + + /* The iommu BAR */ + u32 stored_addr_lo; + u32 stored_addr_hi; + + /* + * Each iommu has 6 l1s, each of which is documented as having 0x12 + * registers + */ + u32 stored_l1[6][0x12]; + + /* The l2 indirect registers */ + u32 stored_l2[0x83]; }; /* diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/amd_nb.h index af00bd1d2089..c8517f81b21e 100644 --- a/arch/x86/include/asm/k8.h +++ b/arch/x86/include/asm/amd_nb.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_K8_H -#define _ASM_X86_K8_H +#ifndef _ASM_X86_AMD_NB_H +#define _ASM_X86_AMD_NB_H #include <linux/pci.h> @@ -7,24 +7,27 @@ extern struct pci_device_id k8_nb_ids[]; struct bootnode; extern int early_is_k8_nb(u32 value); -extern struct pci_dev **k8_northbridges; -extern int num_k8_northbridges; extern int cache_k8_northbridges(void); extern void k8_flush_garts(void); extern int k8_get_nodes(struct bootnode *nodes); extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn); extern int k8_scan_nodes(void); -#ifdef CONFIG_K8_NB -extern int num_k8_northbridges; +struct k8_northbridge_info { + u16 num; + u8 gart_supported; + struct pci_dev **nb_misc; +}; +extern struct k8_northbridge_info k8_northbridges; + +#ifdef CONFIG_AMD_NB static inline struct pci_dev *node_to_k8_nb_misc(int node) { - return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL; + return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL; } #else -#define num_k8_northbridges 0 static inline struct pci_dev *node_to_k8_nb_misc(int node) { @@ -33,4 +36,4 @@ static inline struct pci_dev *node_to_k8_nb_misc(int node) #endif -#endif /* _ASM_X86_K8_H */ +#endif /* _ASM_X86_AMD_NB_H */ diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index a69b1ac9eaf8..2fefa501d3ba 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -54,7 +54,6 @@ extern struct clock_event_device *global_clock_event; extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); -extern unsigned int boot_cpu_id; extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 545776efeb16..bafd80defa43 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -309,7 +309,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & - (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; + (addr[nr / BITS_PER_LONG])) != 0; } static inline int variable_test_bit(int nr, volatile const unsigned long *addr) diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 306160e58b48..1d9cd27c2920 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -205,7 +205,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index b185091bf19c..4fab24de26b1 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -32,6 +32,5 @@ extern void arch_unregister_cpu(int); DECLARE_PER_CPU(int, cpu_state); -extern unsigned int boot_cpu_id; #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 781a50b29a49..220e2ea08e80 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -152,10 +152,14 @@ #define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */ #define X86_FEATURE_OSVW (6*32+ 9) /* OS Visible Workaround */ #define X86_FEATURE_IBS (6*32+10) /* Instruction Based Sampling */ -#define X86_FEATURE_SSE5 (6*32+11) /* SSE-5 */ +#define X86_FEATURE_XOP (6*32+11) /* extended AVX instructions */ #define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */ #define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP (6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 (6*32+16) /* 4 operands MAC instructions */ #define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */ +#define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -168,6 +172,7 @@ #define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ #define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ #define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ @@ -179,6 +184,13 @@ #define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */ #define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ #define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */ + /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ #define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ @@ -296,6 +308,7 @@ extern const char * const x86_power_flags[32]; #endif /* CONFIG_X86_64 */ +#if __GNUC__ >= 4 /* * Static testing of CPU features. Used the same as boot_cpu_has(). * These are only valid after alternatives have run, but will statically @@ -304,7 +317,7 @@ extern const char * const x86_power_flags[32]; */ static __always_inline __pure bool __static_cpu_has(u16 bit) { -#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5) +#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5 asm goto("1: jmp %l[t_no]\n" "2:\n" ".section .altinstructions,\"a\"\n" @@ -345,7 +358,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) #endif } -#if __GNUC__ >= 4 #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index 733f7e91e7a9..326099199318 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -89,6 +89,16 @@ CFI_ADJUST_CFA_OFFSET -8 .endm + .macro pushfq_cfi + pushfq + CFI_ADJUST_CFA_OFFSET 8 + .endm + + .macro popfq_cfi + popfq + CFI_ADJUST_CFA_OFFSET -8 + .endm + .macro movq_cfi reg offset=0 movq %\reg, \offset(%rsp) CFI_REL_OFFSET \reg, \offset @@ -109,6 +119,16 @@ CFI_ADJUST_CFA_OFFSET -4 .endm + .macro pushfl_cfi + pushfl + CFI_ADJUST_CFA_OFFSET 4 + .endm + + .macro popfl_cfi + popfl + CFI_ADJUST_CFA_OFFSET -4 + .endm + .macro movl_cfi reg offset=0 movl %\reg, \offset(%esp) CFI_REL_OFFSET \reg, \offset diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index 8e8ec663a98f..b8e96a18676b 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -49,8 +49,8 @@ BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR) BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR) BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR) -#ifdef CONFIG_PERF_EVENTS -BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR) +#ifdef CONFIG_IRQ_WORK +BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR) #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index d07b44f7d1dc..4d293dced62f 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -214,5 +214,20 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr) BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); return __virt_to_fix(vaddr); } + +/* Return an pointer with offset calculated */ +static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags) +{ + __set_fixmap(idx, phys, flags); + return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1)); +} + +#define set_fixmap_offset(idx, phys) \ + __set_fixmap_offset(idx, phys, PAGE_KERNEL) + +#define set_fixmap_offset_nocache(idx, phys) \ + __set_fixmap_offset(idx, phys, PAGE_KERNEL_NOCACHE) + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h index 4ac5b0f33fc1..bf357f9b25f0 100644 --- a/arch/x86/include/asm/gart.h +++ b/arch/x86/include/asm/gart.h @@ -17,6 +17,7 @@ extern int fix_aperture; #define GARTEN (1<<0) #define DISGARTCPU (1<<4) #define DISGARTIO (1<<5) +#define DISTLBWALKPRB (1<<6) /* GART cache control register bits. */ #define INVGART (1<<0) @@ -27,7 +28,6 @@ extern int fix_aperture; #define AMD64_GARTAPERTUREBASE 0x94 #define AMD64_GARTTABLEBASE 0x98 #define AMD64_GARTCACHECTL 0x9c -#define AMD64_GARTEN (1<<0) #ifdef CONFIG_GART_IOMMU extern int gart_iommu_aperture; @@ -57,6 +57,19 @@ static inline void gart_iommu_hole_init(void) extern int agp_amd64_init(void); +static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order) +{ + u32 ctl; + + /* + * Don't enable translation but enable GART IO and CPU accesses. + * Also, set DISTLBWALKPRB since GART tables memory is UC. + */ + ctl = DISTLBWALKPRB | order << 1; + + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); +} + static inline void enable_gart_translation(struct pci_dev *dev, u64 addr) { u32 tmp, ctl; diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index aeab29aee617..55e4de613f0e 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -14,7 +14,7 @@ typedef struct { #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; - unsigned int apic_pending_irqs; + unsigned int apic_irq_work_irqs; #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 004e6e25e913..1d5c08a1bdfd 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -68,7 +68,6 @@ extern unsigned long force_hpet_address; extern u8 hpet_blockid; extern int hpet_force_user; extern u8 hpet_msi_disable; -extern u8 hpet_readback_cmp; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 528a11e8d3e3..824ca07860d0 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,7 +20,7 @@ struct arch_hw_breakpoint { #include <linux/list.h> /* Available HW breakpoint length encodings */ -#define X86_BREAKPOINT_LEN_X 0x00 +#define X86_BREAKPOINT_LEN_X 0x40 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 46c0fe05f230..3a54a1ca1a02 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -29,7 +29,7 @@ extern void apic_timer_interrupt(void); extern void x86_platform_ipi(void); extern void error_interrupt(void); -extern void perf_pending_interrupt(void); +extern void irq_work_interrupt(void); extern void spurious_interrupt(void); extern void thermal_interrupt(void); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index a73a8d5a5e69..4aa2bb3b242a 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -55,6 +55,12 @@ extern int save_i387_xstate_ia32(void __user *buf); extern int restore_i387_xstate_ia32(void __user *buf); #endif +#ifdef CONFIG_MATH_EMULATION +extern void finit_soft_fpu(struct i387_soft_struct *soft); +#else +static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} +#endif + #define X87_FSW_ES (1 << 7) /* Exception Summary */ static __always_inline __pure bool use_xsaveopt(void) @@ -67,6 +73,11 @@ static __always_inline __pure bool use_xsave(void) return static_cpu_has(X86_FEATURE_XSAVE); } +static __always_inline __pure bool use_fxsr(void) +{ + return static_cpu_has(X86_FEATURE_FXSR); +} + extern void __sanitize_i387_state(struct task_struct *); static inline void sanitize_i387_state(struct task_struct *tsk) @@ -77,19 +88,11 @@ static inline void sanitize_i387_state(struct task_struct *tsk) } #ifdef CONFIG_X86_64 - -/* Ignore delayed exceptions from user space */ -static inline void tolerant_fwait(void) -{ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); -} - static inline int fxrstor_checking(struct i387_fxsave_struct *fx) { int err; + /* See comment in fxsave() below. */ asm volatile("1: rex64/fxrstor (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -98,44 +101,10 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) ".previous\n" _ASM_EXTABLE(1b, 3b) : [err] "=r" (err) -#if 0 /* See comment in fxsave() below. */ - : [fx] "r" (fx), "m" (*fx), "0" (0)); -#else - : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0)); -#endif + : [fx] "R" (fx), "m" (*fx), "0" (0)); return err; } -/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception - is pending. Clear the x87 state here by setting it to fixed - values. The kernel data segment can be sometimes 0 and sometimes - new user value. Both should be ok. - Use the PDA as safe address because it should be already in L1. */ -static inline void fpu_clear(struct fpu *fpu) -{ - struct xsave_struct *xstate = &fpu->state->xsave; - struct i387_fxsave_struct *fx = &fpu->state->fxsave; - - /* - * xsave header may indicate the init state of the FP. - */ - if (use_xsave() && - !(xstate->xsave_hdr.xstate_bv & XSTATE_FP)) - return; - - if (unlikely(fx->swd & X87_FSW_ES)) - asm volatile("fnclex"); - alternative_input(ASM_NOP8 ASM_NOP2, - " emms\n" /* clear stack tags */ - " fildl %%gs:0", /* load to clear state */ - X86_FEATURE_FXSAVE_LEAK); -} - -static inline void clear_fpu_state(struct task_struct *tsk) -{ - fpu_clear(&tsk->thread.fpu); -} - static inline int fxsave_user(struct i387_fxsave_struct __user *fx) { int err; @@ -149,6 +118,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) if (unlikely(err)) return -EFAULT; + /* See comment in fxsave() below. */ asm volatile("1: rex64/fxsave (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -157,11 +127,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx) ".previous\n" _ASM_EXTABLE(1b, 3b) : [err] "=r" (err), "=m" (*fx) -#if 0 /* See comment in fxsave() below. */ - : [fx] "r" (fx), "0" (0)); -#else - : [fx] "cdaSDb" (fx), "0" (0)); -#endif + : [fx] "R" (fx), "0" (0)); if (unlikely(err) && __clear_user(fx, sizeof(struct i387_fxsave_struct))) err = -EFAULT; @@ -175,56 +141,29 @@ static inline void fpu_fxsave(struct fpu *fpu) uses any extended registers for addressing, a second REX prefix will be generated (to the assembler, rex64 followed by semicolon is a separate instruction), and hence the 64-bitness is lost. */ -#if 0 + +#ifdef CONFIG_AS_FXSAVEQ /* Using "fxsaveq %0" would be the ideal choice, but is only supported starting with gas 2.16. */ __asm__ __volatile__("fxsaveq %0" : "=m" (fpu->state->fxsave)); -#elif 0 +#else /* Using, as a workaround, the properly prefixed form below isn't accepted by any binutils version so far released, complaining that the same type of prefix is used twice if an extended register is - needed for addressing (fix submitted to mainline 2005-11-21). */ - __asm__ __volatile__("rex64/fxsave %0" - : "=m" (fpu->state->fxsave)); -#else - /* This, however, we can work around by forcing the compiler to select + needed for addressing (fix submitted to mainline 2005-11-21). + asm volatile("rex64/fxsave %0" + : "=m" (fpu->state->fxsave)); + This, however, we can work around by forcing the compiler to select an addressing mode that doesn't require extended registers. */ - __asm__ __volatile__("rex64/fxsave (%1)" - : "=m" (fpu->state->fxsave) - : "cdaSDb" (&fpu->state->fxsave)); + asm volatile("rex64/fxsave (%[fx])" + : "=m" (fpu->state->fxsave) + : [fx] "R" (&fpu->state->fxsave)); #endif } -static inline void fpu_save_init(struct fpu *fpu) -{ - if (use_xsave()) - fpu_xsave(fpu); - else - fpu_fxsave(fpu); - - fpu_clear(fpu); -} - -static inline void __save_init_fpu(struct task_struct *tsk) -{ - fpu_save_init(&tsk->thread.fpu); - task_thread_info(tsk)->status &= ~TS_USEDFPU; -} - #else /* CONFIG_X86_32 */ -#ifdef CONFIG_MATH_EMULATION -extern void finit_soft_fpu(struct i387_soft_struct *soft); -#else -static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} -#endif - -static inline void tolerant_fwait(void) -{ - asm volatile("fnclex ; fwait"); -} - /* perform fxrstor iff the processor has extended states, otherwise frstor */ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) { @@ -241,6 +180,14 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) return 0; } +static inline void fpu_fxsave(struct fpu *fpu) +{ + asm volatile("fxsave %[fx]" + : [fx] "=m" (fpu->state->fxsave)); +} + +#endif /* CONFIG_X86_64 */ + /* We need a safe address that is cheap to find and that is already in L1 during context switch. The best choices are unfortunately different for UP and SMP */ @@ -256,47 +203,33 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx) static inline void fpu_save_init(struct fpu *fpu) { if (use_xsave()) { - struct xsave_struct *xstate = &fpu->state->xsave; - struct i387_fxsave_struct *fx = &fpu->state->fxsave; - fpu_xsave(fpu); /* * xsave header may indicate the init state of the FP. */ - if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP)) - goto end; - - if (unlikely(fx->swd & X87_FSW_ES)) - asm volatile("fnclex"); - - /* - * we can do a simple return here or be paranoid :) - */ - goto clear_state; + if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) + return; + } else if (use_fxsr()) { + fpu_fxsave(fpu); + } else { + asm volatile("fsave %[fx]; fwait" + : [fx] "=m" (fpu->state->fsave)); + return; } - /* Use more nops than strictly needed in case the compiler - varies code */ - alternative_input( - "fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4, - "fxsave %[fx]\n" - "bt $7,%[fsw] ; jnc 1f ; fnclex\n1:", - X86_FEATURE_FXSR, - [fx] "m" (fpu->state->fxsave), - [fsw] "m" (fpu->state->fxsave.swd) : "memory"); -clear_state: + if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) + asm volatile("fnclex"); + /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is pending. Clear the x87 state here by setting it to fixed values. safe_address is a random variable that should be in L1 */ alternative_input( - GENERIC_NOP8 GENERIC_NOP2, + ASM_NOP8 ASM_NOP2, "emms\n\t" /* clear stack tags */ - "fildl %[addr]", /* set F?P to defined value */ + "fildl %P[addr]", /* set F?P to defined value */ X86_FEATURE_FXSAVE_LEAK, [addr] "m" (safe_address)); -end: - ; } static inline void __save_init_fpu(struct task_struct *tsk) @@ -305,9 +238,6 @@ static inline void __save_init_fpu(struct task_struct *tsk) task_thread_info(tsk)->status &= ~TS_USEDFPU; } - -#endif /* CONFIG_X86_64 */ - static inline int fpu_fxrstor_checking(struct fpu *fpu) { return fxrstor_checking(&fpu->state->fxsave); @@ -344,7 +274,10 @@ static inline void __unlazy_fpu(struct task_struct *tsk) static inline void __clear_fpu(struct task_struct *tsk) { if (task_thread_info(tsk)->status & TS_USEDFPU) { - tolerant_fwait(); + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); task_thread_info(tsk)->status &= ~TS_USEDFPU; stts(); } @@ -405,19 +338,6 @@ static inline void irq_ts_restore(int TS_state) stts(); } -#ifdef CONFIG_X86_64 - -static inline void save_init_fpu(struct task_struct *tsk) -{ - __save_init_fpu(tsk); - stts(); -} - -#define unlazy_fpu __unlazy_fpu -#define clear_fpu __clear_fpu - -#else /* CONFIG_X86_32 */ - /* * These disable preemption on their own and are safe */ @@ -443,8 +363,6 @@ static inline void clear_fpu(struct task_struct *tsk) preempt_enable(); } -#endif /* CONFIG_X86_64 */ - /* * i387 state interaction */ @@ -508,7 +426,4 @@ extern void fpu_finit(struct fpu *fpu); #endif /* __ASSEMBLY__ */ -#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5 -#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5 - #endif /* _ASM_X86_I387_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 30a3e9776123..6a45ec41ec26 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -206,6 +206,7 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size) extern void iounmap(volatile void __iomem *addr); +extern void set_iounmap_nonlazy(void); #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h index f35eb45d6576..c4191b3b7056 100644 --- a/arch/x86/include/asm/iomap.h +++ b/arch/x86/include/asm/iomap.h @@ -26,11 +26,11 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> -void * +void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); void -iounmap_atomic(void *kvaddr, enum km_type type); +iounmap_atomic(void __iomem *kvaddr, enum km_type type); int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot); diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index e2ca30092557..6af0894dafb4 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -114,9 +114,9 @@ #define X86_PLATFORM_IPI_VECTOR 0xed /* - * Performance monitoring pending work vector: + * IRQ work vector: */ -#define LOCAL_PENDING_VECTOR 0xec +#define IRQ_WORK_VECTOR 0xec #define UV_BAU_MESSAGE 0xea diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h new file mode 100644 index 000000000000..f52d42e80585 --- /dev/null +++ b/arch/x86/include/asm/jump_label.h @@ -0,0 +1,37 @@ +#ifndef _ASM_X86_JUMP_LABEL_H +#define _ASM_X86_JUMP_LABEL_H + +#ifdef __KERNEL__ + +#include <linux/types.h> +#include <asm/nops.h> + +#define JUMP_LABEL_NOP_SIZE 5 + +# define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" + +# define JUMP_LABEL(key, label) \ + do { \ + asm goto("1:" \ + JUMP_LABEL_INITIAL_NOP \ + ".pushsection __jump_table, \"a\" \n\t"\ + _ASM_PTR "1b, %l[" #label "], %c0 \n\t" \ + ".popsection \n\t" \ + : : "i" (key) : : label); \ + } while (0) + +#endif /* __KERNEL__ */ + +#ifdef CONFIG_X86_64 +typedef u64 jump_label_t; +#else +typedef u32 jump_label_t; +#endif + +struct jump_entry { + jump_label_t code; + jump_label_t target; + jump_label_t key; +}; + +#endif diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 51cfd730ac5d..1f99ecfc48e1 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -152,9 +152,14 @@ struct x86_emulate_ops { struct operand { enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type; unsigned int bytes; - unsigned long orig_val, *ptr; + union { + unsigned long orig_val; + u64 orig_val64; + }; + unsigned long *ptr; union { unsigned long val; + u64 val64; char valptr[sizeof(unsigned long) + 2]; }; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 502e53f999cf..c52e2eb40a1e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -652,20 +652,6 @@ static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) return (struct kvm_mmu_page *)page_private(page); } -static inline u16 kvm_read_fs(void) -{ - u16 seg; - asm("mov %%fs, %0" : "=g"(seg)); - return seg; -} - -static inline u16 kvm_read_gs(void) -{ - u16 seg; - asm("mov %%gs, %0" : "=g"(seg)); - return seg; -} - static inline u16 kvm_read_ldt(void) { u16 ldt; @@ -673,16 +659,6 @@ static inline u16 kvm_read_ldt(void) return ldt; } -static inline void kvm_load_fs(u16 sel) -{ - asm("mov %0, %%fs" : : "rm"(sel)); -} - -static inline void kvm_load_gs(u16 sel) -{ - asm("mov %0, %%gs" : : "rm"(sel)); -} - static inline void kvm_load_ldt(u16 sel) { asm("lldt %0" : : "rm"(sel)); diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 16350740edf6..4a711a684b17 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -10,6 +10,9 @@ */ #ifndef _ASM_X86_MRST_H #define _ASM_X86_MRST_H + +#include <linux/sfi.h> + extern int pci_mrst_init(void); int __init sfi_parse_mrtc(struct sfi_table_header *table); @@ -26,7 +29,7 @@ enum mrst_cpu_type { }; extern enum mrst_cpu_type __mrst_cpu_chip; -static enum mrst_cpu_type mrst_identify_cpu(void) +static inline enum mrst_cpu_type mrst_identify_cpu(void) { return __mrst_cpu_chip; } @@ -42,4 +45,9 @@ extern enum mrst_timer_options mrst_timer_options; #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 +extern struct console early_mrst_console; +extern void mrst_early_console_init(void); + +extern struct console early_hsu_console; +extern void hsu_early_console_init(void); #endif /* _ASM_X86_MRST_H */ diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h new file mode 100644 index 000000000000..bcdff997668c --- /dev/null +++ b/arch/x86/include/asm/mwait.h @@ -0,0 +1,15 @@ +#ifndef _ASM_X86_MWAIT_H +#define _ASM_X86_MWAIT_H + +#define MWAIT_SUBSTATE_MASK 0xf +#define MWAIT_CSTATE_MASK 0xf +#define MWAIT_SUBSTATE_SIZE 4 +#define MWAIT_MAX_NUM_CSTATES 8 + +#define CPUID_MWAIT_LEAF 5 +#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1 +#define CPUID5_ECX_INTERRUPT_BREAK 0x2 + +#define MWAIT_ECX_INTERRUPT_BREAK 0x1 + +#endif /* _ASM_X86_MWAIT_H */ diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h index 08fde475cb3b..2a8478140bb3 100644 --- a/arch/x86/include/asm/olpc_ofw.h +++ b/arch/x86/include/asm/olpc_ofw.h @@ -21,10 +21,14 @@ extern void olpc_ofw_detect(void); /* install OFW's pde permanently into the kernel's pgtable */ extern void setup_olpc_ofw_pgd(void); +/* check if OFW was detected during boot */ +extern bool olpc_ofw_present(void); + #else /* !CONFIG_OLPC_OPENFIRMWARE */ static inline void olpc_ofw_detect(void) { } static inline void setup_olpc_ofw_pgd(void) { } +static inline bool olpc_ofw_present(void) { return false; } #endif /* !CONFIG_OLPC_OPENFIRMWARE */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index a667f24c7254..1df66211fd1b 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -8,7 +8,7 @@ #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) -#define __PHYSICAL_MASK ((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1) +#define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) /* Cast PAGE_MASK to a signed type so that it is sign-extended if diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 404a880ea325..d395540ff894 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -27,6 +27,9 @@ extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node); extern struct pci_bus *pci_scan_bus_with_sysdata(int busno); +#ifdef CONFIG_PCI + +#ifdef CONFIG_PCI_DOMAINS static inline int pci_domain_nr(struct pci_bus *bus) { struct pci_sysdata *sd = bus->sysdata; @@ -37,13 +40,12 @@ static inline int pci_proc_domain(struct pci_bus *bus) { return pci_domain_nr(bus); } - +#endif /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the loader */ -#ifdef CONFIG_PCI extern unsigned int pcibios_assign_all_busses(void); extern int pci_legacy_init(void); # ifdef CONFIG_ACPI diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index def500776b16..a70cd216be5d 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -36,19 +36,6 @@ #define P4_ESCR_EMASK(v) ((v) << P4_ESCR_EVENTMASK_SHIFT) #define P4_ESCR_TAG(v) ((v) << P4_ESCR_TAG_SHIFT) -/* Non HT mask */ -#define P4_ESCR_MASK \ - (P4_ESCR_EVENT_MASK | \ - P4_ESCR_EVENTMASK_MASK | \ - P4_ESCR_TAG_MASK | \ - P4_ESCR_TAG_ENABLE | \ - P4_ESCR_T0_OS | \ - P4_ESCR_T0_USR) - -/* HT mask */ -#define P4_ESCR_MASK_HT \ - (P4_ESCR_MASK | P4_ESCR_T1_OS | P4_ESCR_T1_USR) - #define P4_CCCR_OVF 0x80000000U #define P4_CCCR_CASCADE 0x40000000U #define P4_CCCR_OVF_PMI_T0 0x04000000U @@ -70,23 +57,6 @@ #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) -/* Non HT mask */ -#define P4_CCCR_MASK \ - (P4_CCCR_OVF | \ - P4_CCCR_CASCADE | \ - P4_CCCR_OVF_PMI_T0 | \ - P4_CCCR_FORCE_OVF | \ - P4_CCCR_EDGE | \ - P4_CCCR_THRESHOLD_MASK | \ - P4_CCCR_COMPLEMENT | \ - P4_CCCR_COMPARE | \ - P4_CCCR_ESCR_SELECT_MASK | \ - P4_CCCR_ENABLE) - -/* HT mask */ -#define P4_CCCR_MASK_HT \ - (P4_CCCR_MASK | P4_CCCR_OVF_PMI_T1 | P4_CCCR_THREAD_ANY) - #define P4_GEN_ESCR_EMASK(class, name, bit) \ class##__##name = ((1 << bit) << P4_ESCR_EVENTMASK_SHIFT) #define P4_ESCR_EMASK_BIT(class, name) class##__##name @@ -127,6 +97,28 @@ #define P4_CONFIG_HT_SHIFT 63 #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) +/* + * The bits we allow to pass for RAW events + */ +#define P4_CONFIG_MASK_ESCR \ + P4_ESCR_EVENT_MASK | \ + P4_ESCR_EVENTMASK_MASK | \ + P4_ESCR_TAG_MASK | \ + P4_ESCR_TAG_ENABLE + +#define P4_CONFIG_MASK_CCCR \ + P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE | \ + P4_CCCR_THREAD_ANY | \ + P4_CCCR_RESERVED + +/* some dangerous bits are reserved for kernel internals */ +#define P4_CONFIG_MASK \ + (p4_config_pack_escr(P4_CONFIG_MASK_ESCR)) | \ + (p4_config_pack_cccr(P4_CONFIG_MASK_CCCR)) + static inline bool p4_is_event_cascaded(u64 config) { u32 cccr = p4_config_unpack_cccr(config); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a34c785c5a63..ada823a13c7c 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -28,6 +28,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; extern spinlock_t pgd_lock; extern struct list_head pgd_list; +extern struct mm_struct *pgd_page_get_mm(struct page *page); + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT */ @@ -603,6 +605,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep); } +#define flush_tlb_fix_spurious_fault(vma, address) + /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 076052cd62be..f96ac9bedf75 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -102,6 +102,8 @@ static inline void native_pgd_clear(pgd_t *pgd) native_set_pgd(pgd, native_make_pgd(0)); } +extern void sync_global_pgds(unsigned long start, unsigned long end); + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 325b7bdbebaa..cae9c3cb95cf 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -110,6 +110,8 @@ struct cpuinfo_x86 { u16 phys_proc_id; /* Core id: */ u16 cpu_core_id; + /* Compute unit id */ + u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; #endif @@ -602,7 +604,7 @@ extern unsigned long mmu_cr4_features; static inline void set_in_cr4(unsigned long mask) { - unsigned cr4; + unsigned long cr4; mmu_cr4_features |= mask; cr4 = read_cr4(); @@ -612,7 +614,7 @@ static inline void set_in_cr4(unsigned long mask) static inline void clear_in_cr4(unsigned long mask) { - unsigned cr4; + unsigned long cr4; mmu_cr4_features &= ~mask; cr4 = read_cr4(); @@ -764,29 +766,6 @@ extern unsigned long idle_halt; extern unsigned long idle_nomwait; extern bool c1e_detected; -/* - * on systems with caches, caches must be flashed as the absolute - * last instruction before going into a suspended halt. Otherwise, - * dirty data can linger in the cache and become stale on resume, - * leading to strange errors. - * - * perform a variety of operations to guarantee that the compiler - * will not reorder instructions. wbinvd itself is serializing - * so the processor will not reorder. - * - * Systems without cache can just go into halt. - */ -static inline void wbinvd_halt(void) -{ - mb(); - /* check for clflush to determine if wbinvd is legal */ - if (cpu_has_clflush) - asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory"); - else - while (1) - halt(); -} - extern void enable_sep_cpu(void); extern int sysenter_setup(void); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ef292c792d74..d6763b139a84 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -93,6 +93,11 @@ void *extend_brk(size_t size, size_t align); : : "i" (sz)); \ } +/* Helper for reserving space for arrays of things */ +#define RESERVE_BRK_ARRAY(type, name, entries) \ + type *name; \ + RESERVE_BRK(name, sizeof(type) * entries) + #ifdef __i386__ void __init i386_start_kernel(void); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index c0427295e8f5..1ca132fc0d03 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -59,5 +59,7 @@ extern void check_tsc_sync_source(int cpu); extern void check_tsc_sync_target(void); extern int notsc_setup(char *); +extern void save_sched_clock_state(void); +extern void restore_sched_clock_state(void); #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 801127cd9754..80a93dc99076 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -11,6 +11,8 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_tsc.o = -pg CFLAGS_REMOVE_rtc.o = -pg CFLAGS_REMOVE_paravirt-spinlocks.o = -pg +CFLAGS_REMOVE_pvclock.o = -pg +CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif @@ -32,7 +34,8 @@ GCOV_PROFILE_paravirt.o := n obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o -obj-y += setup.o x86_init.o i8259.o irqinit.o +obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o +obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-$(CONFIG_X86_VISWS) += visws_quirks.o obj-$(CONFIG_X86_32) += probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o @@ -83,11 +86,12 @@ obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_EARLY_PRINTK_MRST) += early_printk_mrst.o obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_APB_TIMER) += apb_timer.o -obj-$(CONFIG_K8_NB) += k8.o +obj-$(CONFIG_AMD_NB) += amd_nb.o obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o @@ -103,6 +107,7 @@ obj-$(CONFIG_SCx200) += scx200.o scx200-y += scx200_32.o obj-$(CONFIG_OLPC) += olpc.o +obj-$(CONFIG_OLPC_XO1) += olpc-xo1.o obj-$(CONFIG_OLPC_OPENFIRMWARE) += olpc_ofw.o obj-$(CONFIG_X86_MRST) += mrst.o @@ -119,7 +124,6 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o # 64 bit specific files ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_X86_UV) += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o uv_time.o - obj-$(CONFIG_X86_PM_TIMER) += pmtimer_64.o obj-$(CONFIG_AUDIT) += audit_64.o obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index fb7a5f052e2b..5812404a0d4c 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -13,6 +13,7 @@ #include <acpi/processor.h> #include <asm/acpi.h> +#include <asm/mwait.h> /* * Initialize bm_flags based on the CPU cache properties @@ -61,20 +62,10 @@ struct cstate_entry { unsigned int ecx; } states[ACPI_PROCESSOR_MAX_POWER]; }; -static struct cstate_entry *cpu_cstate_entry; /* per CPU ptr */ +static struct cstate_entry __percpu *cpu_cstate_entry; /* per CPU ptr */ static short mwait_supported[ACPI_PROCESSOR_MAX_POWER]; -#define MWAIT_SUBSTATE_MASK (0xf) -#define MWAIT_CSTATE_MASK (0xf) -#define MWAIT_SUBSTATE_SIZE (4) - -#define CPUID_MWAIT_LEAF (5) -#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1) -#define CPUID5_ECX_INTERRUPT_BREAK (0x2) - -#define MWAIT_ECX_INTERRUPT_BREAK (0x1) - #define NATIVE_CSTATE_BEYOND_HALT (2) static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index f65ab8b014c4..a36bb90aef53 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -195,7 +195,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; -static void *text_poke_early(void *addr, const void *opcode, size_t len); +void *text_poke_early(void *addr, const void *opcode, size_t len); /* Replace instructions with better alternatives for this CPU type. This runs before SMP is initialized to avoid SMP problems with @@ -522,7 +522,7 @@ void __init alternative_instructions(void) * instructions. And on the local CPU you need to be protected again NMI or MCE * handlers seeing an inconsistent instruction while you patch. */ -static void *__init_or_module text_poke_early(void *addr, const void *opcode, +void *__init_or_module text_poke_early(void *addr, const void *opcode, size_t len) { unsigned long flags; @@ -637,7 +637,72 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) tpp.len = len; atomic_set(&stop_machine_first, 1); wrote_text = 0; - stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); + /* Use __stop_machine() because the caller already got online_cpus. */ + __stop_machine(stop_machine_text_poke, (void *)&tpp, NULL); return addr; } +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL) + +unsigned char ideal_nop5[IDEAL_NOP_SIZE_5]; + +void __init arch_init_ideal_nop5(void) +{ + extern const unsigned char ftrace_test_p6nop[]; + extern const unsigned char ftrace_test_nop5[]; + extern const unsigned char ftrace_test_jmp[]; + int faulted = 0; + + /* + * There is no good nop for all x86 archs. + * We will default to using the P6_NOP5, but first we + * will test to make sure that the nop will actually + * work on this CPU. If it faults, we will then + * go to a lesser efficient 5 byte nop. If that fails + * we then just use a jmp as our nop. This isn't the most + * efficient nop, but we can not use a multi part nop + * since we would then risk being preempted in the middle + * of that nop, and if we enabled tracing then, it might + * cause a system crash. + * + * TODO: check the cpuid to determine the best nop. + */ + asm volatile ( + "ftrace_test_jmp:" + "jmp ftrace_test_p6nop\n" + "nop\n" + "nop\n" + "nop\n" /* 2 byte jmp + 3 bytes */ + "ftrace_test_p6nop:" + P6_NOP5 + "jmp 1f\n" + "ftrace_test_nop5:" + ".byte 0x66,0x66,0x66,0x66,0x90\n" + "1:" + ".section .fixup, \"ax\"\n" + "2: movl $1, %0\n" + " jmp ftrace_test_nop5\n" + "3: movl $2, %0\n" + " jmp 1b\n" + ".previous\n" + _ASM_EXTABLE(ftrace_test_p6nop, 2b) + _ASM_EXTABLE(ftrace_test_nop5, 3b) + : "=r"(faulted) : "0" (faulted)); + + switch (faulted) { + case 0: + pr_info("converting mcount calls to 0f 1f 44 00 00\n"); + memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5); + break; + case 1: + pr_info("converting mcount calls to 66 66 66 66 90\n"); + memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5); + break; + case 2: + pr_info("converting mcount calls to jmp . + 5\n"); + memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5); + break; + } + +} +#endif diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index fa044e1e30a2..d2fdb0826df2 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -1953,6 +1953,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, size_t size, int dir) { + dma_addr_t flush_addr; dma_addr_t i, start; unsigned int pages; @@ -1960,6 +1961,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, (dma_addr + size > dma_dom->aperture_size)) return; + flush_addr = dma_addr; pages = iommu_num_pages(dma_addr, size, PAGE_SIZE); dma_addr &= PAGE_MASK; start = dma_addr; @@ -1974,7 +1976,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, dma_ops_free_addresses(dma_dom, dma_addr, pages); if (amd_iommu_unmap_flush || dma_dom->need_flush) { - iommu_flush_pages(&dma_dom->domain, dma_addr, size); + iommu_flush_pages(&dma_dom->domain, flush_addr, size); dma_dom->need_flush = false; } } diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 3cc63e2b8dd4..3cb482e123de 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2009 Advanced Micro Devices, Inc. + * Copyright (C) 2007-2010 Advanced Micro Devices, Inc. * Author: Joerg Roedel <joerg.roedel@amd.com> * Leo Duran <leo.duran@amd.com> * @@ -194,6 +194,39 @@ static inline unsigned long tbl_size(int entry_size) return 1UL << shift; } +/* Access to l1 and l2 indexed register spaces */ + +static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address) +{ + u32 val; + + pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16)); + pci_read_config_dword(iommu->dev, 0xfc, &val); + return val; +} + +static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val) +{ + pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31)); + pci_write_config_dword(iommu->dev, 0xfc, val); + pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16)); +} + +static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address) +{ + u32 val; + + pci_write_config_dword(iommu->dev, 0xf0, address); + pci_read_config_dword(iommu->dev, 0xf4, &val); + return val; +} + +static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val) +{ + pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8)); + pci_write_config_dword(iommu->dev, 0xf4, val); +} + /**************************************************************************** * * AMD IOMMU MMIO register space handling functions @@ -619,6 +652,7 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu) { int cap_ptr = iommu->cap_ptr; u32 range, misc; + int i, j; pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET, &iommu->cap); @@ -632,6 +666,30 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu) iommu->last_device = calc_devid(MMIO_GET_BUS(range), MMIO_GET_LD(range)); iommu->evt_msi_num = MMIO_MSI_NUM(misc); + + if (!is_rd890_iommu(iommu->dev)) + return; + + /* + * Some rd890 systems may not be fully reconfigured by the BIOS, so + * it's necessary for us to store this information so it can be + * reprogrammed on resume + */ + + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4, + &iommu->stored_addr_lo); + pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8, + &iommu->stored_addr_hi); + + /* Low bit locks writes to configuration space */ + iommu->stored_addr_lo &= ~1; + + for (i = 0; i < 6; i++) + for (j = 0; j < 0x12; j++) + iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j); + + for (i = 0; i < 0x83; i++) + iommu->stored_l2[i] = iommu_read_l2(iommu, i); } /* @@ -649,29 +707,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, struct ivhd_entry *e; /* - * First set the recommended feature enable bits from ACPI - * into the IOMMU control registers - */ - h->flags & IVHD_FLAG_HT_TUN_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : - iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - - h->flags & IVHD_FLAG_PASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - - h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - - h->flags & IVHD_FLAG_ISOC_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_ISOC_EN) : - iommu_feature_disable(iommu, CONTROL_ISOC_EN); - - /* - * make IOMMU memory accesses cache coherent + * First save the recommended feature enable bits from ACPI */ - iommu_feature_enable(iommu, CONTROL_COHERENT_EN); + iommu->acpi_flags = h->flags; /* * Done. Now parse the device entries @@ -1116,6 +1154,79 @@ static void init_device_table(void) } } +static void iommu_init_flags(struct amd_iommu *iommu) +{ + iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : + iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); + + iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_PASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_ISOC_EN) : + iommu_feature_disable(iommu, CONTROL_ISOC_EN); + + /* + * make IOMMU memory accesses cache coherent + */ + iommu_feature_enable(iommu, CONTROL_COHERENT_EN); +} + +static void iommu_apply_resume_quirks(struct amd_iommu *iommu) +{ + int i, j; + u32 ioc_feature_control; + struct pci_dev *pdev = NULL; + + /* RD890 BIOSes may not have completely reconfigured the iommu */ + if (!is_rd890_iommu(iommu->dev)) + return; + + /* + * First, we need to ensure that the iommu is enabled. This is + * controlled by a register in the northbridge + */ + pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0)); + + if (!pdev) + return; + + /* Select Northbridge indirect register 0x75 and enable writing */ + pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7)); + pci_read_config_dword(pdev, 0x64, &ioc_feature_control); + + /* Enable the iommu */ + if (!(ioc_feature_control & 0x1)) + pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1); + + pci_dev_put(pdev); + + /* Restore the iommu BAR */ + pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4, + iommu->stored_addr_lo); + pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8, + iommu->stored_addr_hi); + + /* Restore the l1 indirect regs for each of the 6 l1s */ + for (i = 0; i < 6; i++) + for (j = 0; j < 0x12; j++) + iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]); + + /* Restore the l2 indirect regs */ + for (i = 0; i < 0x83; i++) + iommu_write_l2(iommu, i, iommu->stored_l2[i]); + + /* Lock PCI setup registers */ + pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4, + iommu->stored_addr_lo | 1); +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1126,6 +1237,7 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); @@ -1150,6 +1262,11 @@ static void disable_iommus(void) static int amd_iommu_resume(struct sys_device *dev) { + struct amd_iommu *iommu; + + for_each_iommu(iommu) + iommu_apply_resume_quirks(iommu); + /* re-load the hardware */ enable_iommus(); diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/amd_nb.c index 0f7bc20cfcde..8f6463d8ed0d 100644 --- a/arch/x86/kernel/k8.c +++ b/arch/x86/kernel/amd_nb.c @@ -8,21 +8,19 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/spinlock.h> -#include <asm/k8.h> - -int num_k8_northbridges; -EXPORT_SYMBOL(num_k8_northbridges); +#include <asm/amd_nb.h> static u32 *flush_words; struct pci_device_id k8_nb_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) }, {} }; EXPORT_SYMBOL(k8_nb_ids); -struct pci_dev **k8_northbridges; +struct k8_northbridge_info k8_northbridges; EXPORT_SYMBOL(k8_northbridges); static struct pci_dev *next_k8_northbridge(struct pci_dev *dev) @@ -40,36 +38,45 @@ int cache_k8_northbridges(void) int i; struct pci_dev *dev; - if (num_k8_northbridges) + if (k8_northbridges.num) return 0; dev = NULL; while ((dev = next_k8_northbridge(dev)) != NULL) - num_k8_northbridges++; + k8_northbridges.num++; + + /* some CPU families (e.g. family 0x11) do not support GART */ + if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || + boot_cpu_data.x86 == 0x15) + k8_northbridges.gart_supported = 1; - k8_northbridges = kmalloc((num_k8_northbridges + 1) * sizeof(void *), - GFP_KERNEL); - if (!k8_northbridges) + k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) * + sizeof(void *), GFP_KERNEL); + if (!k8_northbridges.nb_misc) return -ENOMEM; - if (!num_k8_northbridges) { - k8_northbridges[0] = NULL; + if (!k8_northbridges.num) { + k8_northbridges.nb_misc[0] = NULL; return 0; } - flush_words = kmalloc(num_k8_northbridges * sizeof(u32), GFP_KERNEL); - if (!flush_words) { - kfree(k8_northbridges); - return -ENOMEM; + if (k8_northbridges.gart_supported) { + flush_words = kmalloc(k8_northbridges.num * sizeof(u32), + GFP_KERNEL); + if (!flush_words) { + kfree(k8_northbridges.nb_misc); + return -ENOMEM; + } } dev = NULL; i = 0; while ((dev = next_k8_northbridge(dev)) != NULL) { - k8_northbridges[i] = dev; - pci_read_config_dword(dev, 0x9c, &flush_words[i++]); + k8_northbridges.nb_misc[i] = dev; + if (k8_northbridges.gart_supported) + pci_read_config_dword(dev, 0x9c, &flush_words[i++]); } - k8_northbridges[i] = NULL; + k8_northbridges.nb_misc[i] = NULL; return 0; } EXPORT_SYMBOL_GPL(cache_k8_northbridges); @@ -93,22 +100,25 @@ void k8_flush_garts(void) unsigned long flags; static DEFINE_SPINLOCK(gart_lock); + if (!k8_northbridges.gart_supported) + return; + /* Avoid races between AGP and IOMMU. In theory it's not needed but I'm not sure if the hardware won't lose flush requests when another is pending. This whole thing is so expensive anyways that it doesn't matter to serialize more. -AK */ spin_lock_irqsave(&gart_lock, flags); flushed = 0; - for (i = 0; i < num_k8_northbridges; i++) { - pci_write_config_dword(k8_northbridges[i], 0x9c, + for (i = 0; i < k8_northbridges.num; i++) { + pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c, flush_words[i]|1); flushed++; } - for (i = 0; i < num_k8_northbridges; i++) { + for (i = 0; i < k8_northbridges.num; i++) { u32 w; /* Make sure the hardware actually executed the flush*/ for (;;) { - pci_read_config_dword(k8_northbridges[i], + pci_read_config_dword(k8_northbridges.nb_misc[i], 0x9c, &w); if (!(w & 1)) break; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 8dd77800ff5d..6fe2b5cb4f3c 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -343,7 +343,7 @@ void apbt_setup_secondary_clock(void) /* Don't register boot CPU clockevent */ cpu = smp_processor_id(); - if (cpu == boot_cpu_id) + if (!cpu) return; /* * We need to calculate the scaled math multiplication factor for @@ -398,7 +398,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n, } break; default: - pr_debug(KERN_INFO "APBT notified %lu, no action\n", action); + pr_debug("APBT notified %lu, no action\n", action); } return NOTIFY_OK; } @@ -552,7 +552,7 @@ bad_count: pr_debug("APB CS going back %lx:%lx:%lx ", t2, last_read, t2 - last_read); bad_count_x3: - pr_debug(KERN_INFO "tripple check enforced\n"); + pr_debug("triple check enforced\n"); t0 = apbt_readl(phy_cs_timer_id, APBTMR_N_CURRENT_VALUE); udelay(1); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index a2e0caf26e17..377f5db3b8b4 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -27,7 +27,7 @@ #include <asm/gart.h> #include <asm/pci-direct.h> #include <asm/dma.h> -#include <asm/k8.h> +#include <asm/amd_nb.h> #include <asm/x86_init.h> int gart_iommu_aperture; @@ -307,7 +307,7 @@ void __init early_gart_iommu_check(void) continue; ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); - aper_enabled = ctl & AMD64_GARTEN; + aper_enabled = ctl & GARTEN; aper_order = (ctl >> 1) & 7; aper_size = (32 * 1024 * 1024) << aper_order; aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; @@ -362,7 +362,7 @@ void __init early_gart_iommu_check(void) continue; ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL); - ctl &= ~AMD64_GARTEN; + ctl &= ~GARTEN; write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); } } @@ -505,8 +505,13 @@ out: /* Fix up the north bridges */ for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) { - int bus; - int dev_base, dev_limit; + int bus, dev_base, dev_limit; + + /* + * Don't enable translation yet but enable GART IO and CPU + * accesses and set DISTLBWALKPRB since GART table memory is UC. + */ + u32 ctl = DISTLBWALKPRB | aper_order << 1; bus = bus_dev_ranges[i].bus; dev_base = bus_dev_ranges[i].dev_base; @@ -515,10 +520,7 @@ out: if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00))) continue; - /* Don't enable translation yet. That is done later. - Assume this BIOS didn't initialise the GART so - just overwrite all previous bits */ - write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1); + write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl); write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25); } } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f1efebaf5510..f1e78940d908 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -162,7 +162,7 @@ int __init arch_early_irq_init(void) cfg = irq_cfgx; count = ARRAY_SIZE(irq_cfgx); - node= cpu_to_node(boot_cpu_id); + node = cpu_to_node(0); for (i = 0; i < count; i++) { desc = irq_to_desc(i); @@ -306,14 +306,19 @@ void arch_init_copy_chip_data(struct irq_desc *old_desc, old_cfg = old_desc->chip_data; - memcpy(cfg, old_cfg, sizeof(struct irq_cfg)); + cfg->vector = old_cfg->vector; + cfg->move_in_progress = old_cfg->move_in_progress; + cpumask_copy(cfg->domain, old_cfg->domain); + cpumask_copy(cfg->old_domain, old_cfg->old_domain); init_copy_irq_2_pin(old_cfg, cfg, node); } -static void free_irq_cfg(struct irq_cfg *old_cfg) +static void free_irq_cfg(struct irq_cfg *cfg) { - kfree(old_cfg); + free_cpumask_var(cfg->domain); + free_cpumask_var(cfg->old_domain); + kfree(cfg); } void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc) @@ -1483,7 +1488,7 @@ static void __init setup_IO_APIC_irqs(void) int notcon = 0; struct irq_desc *desc; struct irq_cfg *cfg; - int node = cpu_to_node(boot_cpu_id); + int node = cpu_to_node(0); apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); @@ -1548,7 +1553,7 @@ static void __init setup_IO_APIC_irqs(void) void setup_IO_APIC_irq_extra(u32 gsi) { int apic_id = 0, pin, idx, irq; - int node = cpu_to_node(boot_cpu_id); + int node = cpu_to_node(0); struct irq_desc *desc; struct irq_cfg *cfg; @@ -2927,7 +2932,7 @@ static inline void __init check_timer(void) { struct irq_desc *desc = irq_to_desc(0); struct irq_cfg *cfg = desc->chip_data; - int node = cpu_to_node(boot_cpu_id); + int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; unsigned long flags; int no_pin1 = 0; @@ -3281,7 +3286,7 @@ unsigned int create_irq_nr(unsigned int irq_want, int node) int create_irq(void) { - int node = cpu_to_node(boot_cpu_id); + int node = cpu_to_node(0); unsigned int irq_want; int irq; @@ -3903,7 +3908,7 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq, if (dev) node = dev_to_node(dev); else - node = cpu_to_node(boot_cpu_id); + node = cpu_to_node(0); desc = irq_to_desc_alloc_node(irq, node); if (!desc) { diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 7b598b84c902..f744f54cb248 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -698,9 +698,11 @@ void __init uv_system_init(void) for (j = 0; j < 64; j++) { if (!test_bit(j, &present)) continue; - uv_blade_info[blade].pnode = (i * 64 + j); + pnode = (i * 64 + j); + uv_blade_info[blade].pnode = pnode; uv_blade_info[blade].nr_possible_cpus = 0; uv_blade_info[blade].nr_online_cpus = 0; + max_pnode = max(pnode, max_pnode); blade++; } } @@ -738,7 +740,6 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->scir.offset = uv_scir_offset(apicid); uv_node_to_blade[nid] = blade; uv_cpu_to_blade[cpu] = blade; - max_pnode = max(pnode, max_pnode); } /* Add blade/pnode info for nodes without cpus */ @@ -750,7 +751,6 @@ void __init uv_system_init(void) pnode = (paddr >> m_val) & pnode_mask; blade = boot_pnode_to_blade(pnode); uv_node_to_blade[nid] = blade; - max_pnode = max(pnode, max_pnode); } map_gru_high(max_pnode); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ba5f62f45f01..9e093f8fe78c 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -148,7 +148,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ - if (c->cpu_index == boot_cpu_id) + if (!c->cpu_index) return; /* @@ -253,37 +253,51 @@ static int __cpuinit nearby_node(int apicid) #endif /* - * Fixup core topology information for AMD multi-node processors. - * Assumption: Number of cores in each internal node is the same. + * Fixup core topology information for + * (1) AMD multi-node processors + * Assumption: Number of cores in each internal node is the same. + * (2) AMD processors supporting compute units */ #ifdef CONFIG_X86_HT -static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c) +static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) { - unsigned long long value; - u32 nodes, cores_per_node; + u32 nodes; + u8 node_id; int cpu = smp_processor_id(); - if (!cpu_has(c, X86_FEATURE_NODEID_MSR)) - return; + /* get information required for multi-node processors */ + if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + u32 eax, ebx, ecx, edx; - /* fixup topology information only once for a core */ - if (cpu_has(c, X86_FEATURE_AMD_DCM)) - return; + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + nodes = ((ecx >> 8) & 7) + 1; + node_id = ecx & 7; - rdmsrl(MSR_FAM10H_NODE_ID, value); + /* get compute unit information */ + smp_num_siblings = ((ebx >> 8) & 3) + 1; + c->compute_unit_id = ebx & 0xff; + } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { + u64 value; - nodes = ((value >> 3) & 7) + 1; - if (nodes == 1) + rdmsrl(MSR_FAM10H_NODE_ID, value); + nodes = ((value >> 3) & 7) + 1; + node_id = value & 7; + } else return; - set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes; + /* fixup multi-node processor information */ + if (nodes > 1) { + u32 cores_per_node; + + set_cpu_cap(c, X86_FEATURE_AMD_DCM); + cores_per_node = c->x86_max_cores / nodes; - /* store NodeID, use llc_shared_map to store sibling info */ - per_cpu(cpu_llc_id, cpu) = value & 7; + /* store NodeID, use llc_shared_map to store sibling info */ + per_cpu(cpu_llc_id, cpu) = node_id; - /* fixup core id to be in range from 0 to (cores_per_node - 1) */ - c->cpu_core_id = c->cpu_core_id % cores_per_node; + /* core id to be in range from 0 to (cores_per_node - 1) */ + c->cpu_core_id = c->cpu_core_id % cores_per_node; + } } #endif @@ -304,9 +318,7 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; - /* fixup topology information on multi-node processors */ - if ((c->x86 == 0x10) && (c->x86_model == 9)) - amd_fixup_dcm(c); + amd_get_topology(c); #endif } @@ -412,6 +424,23 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); } #endif + + /* We need to do the following only once */ + if (c != &boot_cpu_data) + return; + + if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { + + if (c->x86 > 0x10 || + (c->x86 == 0x10 && c->x86_model >= 0x2)) { + u64 val; + + rdmsrl(MSR_K7_HWCR, val); + if (!(val & BIT(24))) + printk(KERN_WARNING FW_BUG "TSC doesn't count " + "with P0 frequency!\n"); + } + } } static void __cpuinit init_amd(struct cpuinfo_x86 *c) @@ -523,7 +552,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) #endif if (c->extended_cpuid_level >= 0x80000006) { - if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000)) + if (cpuid_edx(0x80000006) & 0xf000) num_cache_leaves = 4; else num_cache_leaves = 3; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 490dac63c2d2..4b68bda30938 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -545,7 +545,7 @@ void __cpuinit cpu_detect(struct cpuinfo_x86 *c) } } -static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) +void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) { u32 tfms, xlvl; u32 ebx; @@ -665,7 +665,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_early_init(c); #ifdef CONFIG_SMP - c->cpu_index = boot_cpu_id; + c->cpu_index = 0; #endif filter_cpuid_features(c, false); } @@ -704,16 +704,21 @@ void __init early_cpu_init(void) } /* - * The NOPL instruction is supposed to exist on all CPUs with - * family >= 6; unfortunately, that's not true in practice because - * of early VIA chips and (more importantly) broken virtualizers that - * are not easy to detect. In the latter case it doesn't even *fail* - * reliably, so probing for it doesn't even work. Disable it completely + * The NOPL instruction is supposed to exist on all CPUs of family >= 6; + * unfortunately, that's not true in practice because of early VIA + * chips and (more importantly) broken virtualizers that are not easy + * to detect. In the latter case it doesn't even *fail* reliably, so + * probing for it doesn't even work. Disable it completely on 32-bit * unless we can find a reliable way to detect all the broken cases. + * Enable it explicitly on 64-bit for non-constant inputs of cpu_has(). */ static void __cpuinit detect_nopl(struct cpuinfo_x86 *c) { +#ifdef CONFIG_X86_32 clear_cpu_cap(c, X86_FEATURE_NOPL); +#else + set_cpu_cap(c, X86_FEATURE_NOPL); +#endif } static void __cpuinit generic_identify(struct cpuinfo_x86 *c) @@ -1264,13 +1269,6 @@ void __cpuinit cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - /* - * Force FPU initialization: - */ - current_thread_info()->status = 0; - clear_used_math(); - mxcsr_feature_mask_init(); - fpu_init(); xsave_init(); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 3624e8a0f71b..e765633f210e 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -32,6 +32,8 @@ struct cpu_dev { extern const struct cpu_dev *const __x86_cpu_dev_start[], *const __x86_cpu_dev_end[]; +extern void get_cpu_cap(struct cpuinfo_x86 *c); extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c); +extern void get_cpu_cap(struct cpuinfo_x86 *c); #endif diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c index 994230d4dc4e..4f6f679f2799 100644 --- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c @@ -368,16 +368,22 @@ static int __init pcc_cpufreq_do_osc(acpi_handle *handle) return -ENODEV; out_obj = output.pointer; - if (out_obj->type != ACPI_TYPE_BUFFER) - return -ENODEV; + if (out_obj->type != ACPI_TYPE_BUFFER) { + ret = -ENODEV; + goto out_free; + } errors = *((u32 *)out_obj->buffer.pointer) & ~(1 << 0); - if (errors) - return -ENODEV; + if (errors) { + ret = -ENODEV; + goto out_free; + } supported = *((u32 *)(out_obj->buffer.pointer + 4)); - if (!(supported & 0x1)) - return -ENODEV; + if (!(supported & 0x1)) { + ret = -ENODEV; + goto out_free; + } out_free: kfree(output.pointer); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 85f69cdeae10..695f17731e23 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -39,6 +39,7 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID; wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); c->cpuid_level = cpuid_eax(0); + get_cpu_cap(c); } } @@ -169,7 +170,7 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP /* calling is from identify_secondary_cpu() ? */ - if (c->cpu_index == boot_cpu_id) + if (!c->cpu_index) return; /* diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 898c2f4eab88..12cd823c8d03 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -17,7 +17,7 @@ #include <asm/processor.h> #include <linux/smp.h> -#include <asm/k8.h> +#include <asm/amd_nb.h> #include <asm/smp.h> #define LVL_1_INST 1 @@ -306,7 +306,7 @@ struct _cache_attr { ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count); }; -#ifdef CONFIG_CPU_SUP_AMD +#ifdef CONFIG_AMD_NB /* * L3 cache descriptors @@ -369,7 +369,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, return; /* not in virtualized environments */ - if (num_k8_northbridges == 0) + if (k8_northbridges.num == 0) return; /* @@ -377,7 +377,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, * never freed but this is done only on shutdown so it doesn't matter. */ if (!l3_caches) { - int size = num_k8_northbridges * sizeof(struct amd_l3_cache *); + int size = k8_northbridges.num * sizeof(struct amd_l3_cache *); l3_caches = kzalloc(size, GFP_ATOMIC); if (!l3_caches) @@ -556,12 +556,12 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, show_cache_disable_1, store_cache_disable_1); -#else /* CONFIG_CPU_SUP_AMD */ +#else /* CONFIG_AMD_NB */ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index) { }; -#endif /* CONFIG_CPU_SUP_AMD */ +#endif /* CONFIG_AMD_NB */ static int __cpuinit cpuid4_cache_lookup_regs(int index, @@ -1000,7 +1000,7 @@ static struct attribute *default_attrs[] = { static struct attribute *default_l3_attrs[] = { DEFAULT_SYSFS_CACHE_ATTRS, -#ifdef CONFIG_CPU_SUP_AMD +#ifdef CONFIG_AMD_NB &cache_disable_0.attr, &cache_disable_1.attr, #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 224392d8fe8c..39aaee5c1ab2 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -141,6 +141,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) address = (low & MASK_BLKPTR_LO) >> 21; if (!address) break; + address += MCG_XBLK_ADDR; } else ++address; @@ -148,12 +149,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (rdmsr_safe(address, &low, &high)) break; - if (!(high & MASK_VALID_HI)) { - if (block) - continue; - else - break; - } + if (!(high & MASK_VALID_HI)) + continue; if (!(high & MASK_CNTP_HI) || (high & MASK_LOCKED_HI)) @@ -530,7 +527,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) err = -ENOMEM; goto out; } - if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) { + if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) { kfree(b); err = -ENOMEM; goto out; @@ -543,7 +540,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifndef CONFIG_SMP cpumask_setall(b->cpus); #else - cpumask_copy(b->cpus, c->llc_shared_map); + cpumask_set_cpu(cpu, b->cpus); #endif per_cpu(threshold_banks, cpu)[bank] = b; diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index c2a8b26d4fea..4b683267eca5 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -202,10 +202,11 @@ static int therm_throt_process(bool new_event, int event, int level) #ifdef CONFIG_SYSFS /* Add/Remove thermal_throttle interface for CPU device: */ -static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) +static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev, + unsigned int cpu) { int err; - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); + struct cpuinfo_x86 *c = &cpu_data(cpu); err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group); if (err) @@ -215,7 +216,7 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) err = sysfs_add_file_to_group(&sys_dev->kobj, &attr_core_power_limit_count.attr, thermal_attr_group.name); - if (cpu_has(c, X86_FEATURE_PTS)) + if (cpu_has(c, X86_FEATURE_PTS)) { err = sysfs_add_file_to_group(&sys_dev->kobj, &attr_package_throttle_count.attr, thermal_attr_group.name); @@ -223,6 +224,7 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev) err = sysfs_add_file_to_group(&sys_dev->kobj, &attr_package_power_limit_count.attr, thermal_attr_group.name); + } return err; } @@ -251,7 +253,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb, case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: mutex_lock(&therm_cpu_lock); - err = thermal_throttle_add_dev(sys_dev); + err = thermal_throttle_add_dev(sys_dev, cpu); mutex_unlock(&therm_cpu_lock); WARN_ON(err); break; @@ -287,7 +289,7 @@ static __init int thermal_throttle_init_device(void) #endif /* connect live CPUs to sysfs */ for_each_online_cpu(cpu) { - err = thermal_throttle_add_dev(get_cpu_sysdev(cpu)); + err = thermal_throttle_add_dev(get_cpu_sysdev(cpu), cpu); WARN_ON(err); } #ifdef CONFIG_HOTPLUG_CPU @@ -348,7 +350,7 @@ static void intel_thermal_interrupt(void) static void unexpected_thermal_interrupt(void) { - printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n", + printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n", smp_processor_id()); add_taint(TAINT_MACHINE_CHECK); } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index c5f59d071425..ac140c7be396 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -827,7 +827,7 @@ int __init amd_special_default_mtrr(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return 0; - if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11) + if (boot_cpu_data.x86 < 0xf) return 0; /* In case some hypervisor doesn't pass SYSCFG through: */ if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 7d28d7d03885..9f27228ceffd 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -64,18 +64,59 @@ static inline void k8_check_syscfg_dram_mod_en(void) } } +/* Get the size of contiguous MTRR range */ +static u64 get_mtrr_size(u64 mask) +{ + u64 size; + + mask >>= PAGE_SHIFT; + mask |= size_or_mask; + size = -mask; + size <<= PAGE_SHIFT; + return size; +} + /* - * Returns the effective MTRR type for the region - * Error returns: - * - 0xFE - when the range is "not entirely covered" by _any_ var range MTRR - * - 0xFF - when MTRR is not enabled + * Check and return the effective type for MTRR-MTRR type overlap. + * Returns 1 if the effective type is UNCACHEABLE, else returns 0 */ -u8 mtrr_type_lookup(u64 start, u64 end) +static int check_type_overlap(u8 *prev, u8 *curr) +{ + if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) { + *prev = MTRR_TYPE_UNCACHABLE; + *curr = MTRR_TYPE_UNCACHABLE; + return 1; + } + + if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) || + (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) { + *prev = MTRR_TYPE_WRTHROUGH; + *curr = MTRR_TYPE_WRTHROUGH; + } + + if (*prev != *curr) { + *prev = MTRR_TYPE_UNCACHABLE; + *curr = MTRR_TYPE_UNCACHABLE; + return 1; + } + + return 0; +} + +/* + * Error/Semi-error returns: + * 0xFF - when MTRR is not enabled + * *repeat == 1 implies [start:end] spanned across MTRR range and type returned + * corresponds only to [start:*partial_end]. + * Caller has to lookup again for [*partial_end:end]. + */ +static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) { int i; u64 base, mask; u8 prev_match, curr_match; + *repeat = 0; if (!mtrr_state_set) return 0xFF; @@ -126,8 +167,34 @@ u8 mtrr_type_lookup(u64 start, u64 end) start_state = ((start & mask) == (base & mask)); end_state = ((end & mask) == (base & mask)); - if (start_state != end_state) - return 0xFE; + + if (start_state != end_state) { + /* + * We have start:end spanning across an MTRR. + * We split the region into + * either + * (start:mtrr_end) (mtrr_end:end) + * or + * (start:mtrr_start) (mtrr_start:end) + * depending on kind of overlap. + * Return the type for first region and a pointer to + * the start of second region so that caller will + * lookup again on the second region. + * Note: This way we handle multiple overlaps as well. + */ + if (start_state) + *partial_end = base + get_mtrr_size(mask); + else + *partial_end = base; + + if (unlikely(*partial_end <= start)) { + WARN_ON(1); + *partial_end = start + PAGE_SIZE; + } + + end = *partial_end - 1; /* end is inclusive */ + *repeat = 1; + } if ((start & mask) != (base & mask)) continue; @@ -138,21 +205,8 @@ u8 mtrr_type_lookup(u64 start, u64 end) continue; } - if (prev_match == MTRR_TYPE_UNCACHABLE || - curr_match == MTRR_TYPE_UNCACHABLE) { - return MTRR_TYPE_UNCACHABLE; - } - - if ((prev_match == MTRR_TYPE_WRBACK && - curr_match == MTRR_TYPE_WRTHROUGH) || - (prev_match == MTRR_TYPE_WRTHROUGH && - curr_match == MTRR_TYPE_WRBACK)) { - prev_match = MTRR_TYPE_WRTHROUGH; - curr_match = MTRR_TYPE_WRTHROUGH; - } - - if (prev_match != curr_match) - return MTRR_TYPE_UNCACHABLE; + if (check_type_overlap(&prev_match, &curr_match)) + return curr_match; } if (mtrr_tom2) { @@ -166,6 +220,36 @@ u8 mtrr_type_lookup(u64 start, u64 end) return mtrr_state.def_type; } +/* + * Returns the effective MTRR type for the region + * Error return: + * 0xFF - when MTRR is not enabled + */ +u8 mtrr_type_lookup(u64 start, u64 end) +{ + u8 type, prev_type; + int repeat; + u64 partial_end; + + type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + + /* + * Common path is with repeat = 0. + * However, we can have cases where [start:end] spans across some + * MTRR range. Do repeated lookups for that case here. + */ + while (repeat) { + prev_type = type; + start = partial_end; + type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + + if (check_type_overlap(&prev_type, &type)) + return type; + } + + return type; +} + /* Get the MSR pair relating to a var range */ static void get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index f2da20fda02d..fe73c1844a9a 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -102,6 +102,7 @@ struct cpu_hw_events { */ struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */ unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; int enabled; int n_events; @@ -530,7 +531,7 @@ static int x86_pmu_hw_config(struct perf_event *event) /* * Setup the hardware configuration for a given attr_type */ -static int __hw_perf_event_init(struct perf_event *event) +static int __x86_pmu_event_init(struct perf_event *event) { int err; @@ -583,7 +584,7 @@ static void x86_pmu_disable_all(void) } } -void hw_perf_disable(void) +static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -618,7 +619,7 @@ static void x86_pmu_enable_all(int added) } } -static const struct pmu pmu; +static struct pmu pmu; static inline int is_x86_event(struct perf_event *event) { @@ -800,10 +801,10 @@ static inline int match_prev_assignment(struct hw_perf_event *hwc, hwc->last_tag == cpuc->tags[i]; } -static int x86_pmu_start(struct perf_event *event); -static void x86_pmu_stop(struct perf_event *event); +static void x86_pmu_start(struct perf_event *event, int flags); +static void x86_pmu_stop(struct perf_event *event, int flags); -void hw_perf_enable(void) +static void x86_pmu_enable(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct perf_event *event; @@ -839,7 +840,14 @@ void hw_perf_enable(void) match_prev_assignment(hwc, cpuc, i)) continue; - x86_pmu_stop(event); + /* + * Ensure we don't accidentally enable a stopped + * counter simply because we rescheduled. + */ + if (hwc->state & PERF_HES_STOPPED) + hwc->state |= PERF_HES_ARCH; + + x86_pmu_stop(event, PERF_EF_UPDATE); } for (i = 0; i < cpuc->n_events; i++) { @@ -851,7 +859,10 @@ void hw_perf_enable(void) else if (i < n_running) continue; - x86_pmu_start(event); + if (hwc->state & PERF_HES_ARCH) + continue; + + x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; perf_events_lapic_init(); @@ -952,15 +963,12 @@ static void x86_pmu_enable_event(struct perf_event *event) } /* - * activate a single event + * Add a single event to the PMU. * * The event is added to the group of enabled events * but only if it can be scehduled with existing events. - * - * Called with PMU disabled. If successful and return value 1, - * then guaranteed to call perf_enable() and hw_perf_enable() */ -static int x86_pmu_enable(struct perf_event *event) +static int x86_pmu_add(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc; @@ -969,57 +977,67 @@ static int x86_pmu_enable(struct perf_event *event) hwc = &event->hw; + perf_pmu_disable(event->pmu); n0 = cpuc->n_events; - n = collect_events(cpuc, event, false); - if (n < 0) - return n; + ret = n = collect_events(cpuc, event, false); + if (ret < 0) + goto out; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; /* * If group events scheduling transaction was started, * skip the schedulability test here, it will be peformed - * at commit time(->commit_txn) as a whole + * at commit time (->commit_txn) as a whole */ if (cpuc->group_flag & PERF_EVENT_TXN) - goto out; + goto done_collect; ret = x86_pmu.schedule_events(cpuc, n, assign); if (ret) - return ret; + goto out; /* * copy new assignment, now we know it is possible * will be used by hw_perf_enable() */ memcpy(cpuc->assign, assign, n*sizeof(int)); -out: +done_collect: cpuc->n_events = n; cpuc->n_added += n - n0; cpuc->n_txn += n - n0; - return 0; + ret = 0; +out: + perf_pmu_enable(event->pmu); + return ret; } -static int x86_pmu_start(struct perf_event *event) +static void x86_pmu_start(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int idx = event->hw.idx; - if (idx == -1) - return -EAGAIN; + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + if (WARN_ON_ONCE(idx == -1)) + return; + + if (flags & PERF_EF_RELOAD) { + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + x86_perf_event_set_period(event); + } + + event->hw.state = 0; - x86_perf_event_set_period(event); cpuc->events[idx] = event; __set_bit(idx, cpuc->active_mask); + __set_bit(idx, cpuc->running); x86_pmu.enable(event); perf_event_update_userpage(event); - - return 0; -} - -static void x86_pmu_unthrottle(struct perf_event *event) -{ - int ret = x86_pmu_start(event); - WARN_ON_ONCE(ret); } void perf_event_print_debug(void) @@ -1076,27 +1094,29 @@ void perf_event_print_debug(void) local_irq_restore(flags); } -static void x86_pmu_stop(struct perf_event *event) +static void x86_pmu_stop(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - - if (!__test_and_clear_bit(idx, cpuc->active_mask)) - return; - - x86_pmu.disable(event); - /* - * Drain the remaining delta count out of a event - * that we are disabling: - */ - x86_perf_event_update(event); + if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { + x86_pmu.disable(event); + cpuc->events[hwc->idx] = NULL; + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + } - cpuc->events[idx] = NULL; + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + x86_perf_event_update(event); + hwc->state |= PERF_HES_UPTODATE; + } } -static void x86_pmu_disable(struct perf_event *event) +static void x86_pmu_del(struct perf_event *event, int flags) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int i; @@ -1109,7 +1129,7 @@ static void x86_pmu_disable(struct perf_event *event) if (cpuc->group_flag & PERF_EVENT_TXN) return; - x86_pmu_stop(event); + x86_pmu_stop(event, PERF_EF_UPDATE); for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) { @@ -1132,7 +1152,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) struct perf_sample_data data; struct cpu_hw_events *cpuc; struct perf_event *event; - struct hw_perf_event *hwc; int idx, handled = 0; u64 val; @@ -1141,11 +1160,18 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { - if (!test_bit(idx, cpuc->active_mask)) + if (!test_bit(idx, cpuc->active_mask)) { + /* + * Though we deactivated the counter some cpus + * might still deliver spurious interrupts still + * in flight. Catch them: + */ + if (__test_and_clear_bit(idx, cpuc->running)) + handled++; continue; + } event = cpuc->events[idx]; - hwc = &event->hw; val = x86_perf_event_update(event); if (val & (1ULL << (x86_pmu.cntval_bits - 1))) @@ -1154,14 +1180,14 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) /* * event overflow */ - handled = 1; + handled++; data.period = event->hw.last_period; if (!x86_perf_event_set_period(event)) continue; if (perf_event_overflow(event, 1, &data, regs)) - x86_pmu_stop(event); + x86_pmu_stop(event, 0); } if (handled) @@ -1170,25 +1196,6 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) return handled; } -void smp_perf_pending_interrupt(struct pt_regs *regs) -{ - irq_enter(); - ack_APIC_irq(); - inc_irq_stat(apic_pending_irqs); - perf_event_do_pending(); - irq_exit(); -} - -void set_perf_event_pending(void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - if (!x86_pmu.apic || !x86_pmu_initialized()) - return; - - apic->send_IPI_self(LOCAL_PENDING_VECTOR); -#endif -} - void perf_events_lapic_init(void) { if (!x86_pmu.apic || !x86_pmu_initialized()) @@ -1200,12 +1207,20 @@ void perf_events_lapic_init(void) apic_write(APIC_LVTPC, APIC_DM_NMI); } +struct pmu_nmi_state { + unsigned int marked; + int handled; +}; + +static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi); + static int __kprobes perf_event_nmi_handler(struct notifier_block *self, unsigned long cmd, void *__args) { struct die_args *args = __args; - struct pt_regs *regs; + unsigned int this_nmi; + int handled; if (!atomic_read(&active_events)) return NOTIFY_DONE; @@ -1214,22 +1229,47 @@ perf_event_nmi_handler(struct notifier_block *self, case DIE_NMI: case DIE_NMI_IPI: break; - + case DIE_NMIUNKNOWN: + this_nmi = percpu_read(irq_stat.__nmi_count); + if (this_nmi != __get_cpu_var(pmu_nmi).marked) + /* let the kernel handle the unknown nmi */ + return NOTIFY_DONE; + /* + * This one is a PMU back-to-back nmi. Two events + * trigger 'simultaneously' raising two back-to-back + * NMIs. If the first NMI handles both, the latter + * will be empty and daze the CPU. So, we drop it to + * avoid false-positive 'unknown nmi' messages. + */ + return NOTIFY_STOP; default: return NOTIFY_DONE; } - regs = args->regs; - apic_write(APIC_LVTPC, APIC_DM_NMI); - /* - * Can't rely on the handled return value to say it was our NMI, two - * events could trigger 'simultaneously' raising two back-to-back NMIs. - * - * If the first NMI handles both, the latter will be empty and daze - * the CPU. - */ - x86_pmu.handle_irq(regs); + + handled = x86_pmu.handle_irq(args->regs); + if (!handled) + return NOTIFY_DONE; + + this_nmi = percpu_read(irq_stat.__nmi_count); + if ((handled > 1) || + /* the next nmi could be a back-to-back nmi */ + ((__get_cpu_var(pmu_nmi).marked == this_nmi) && + (__get_cpu_var(pmu_nmi).handled > 1))) { + /* + * We could have two subsequent back-to-back nmis: The + * first handles more than one counter, the 2nd + * handles only one counter and the 3rd handles no + * counter. + * + * This is the 2nd nmi because the previous was + * handling more than one counter. We will mark the + * next (3rd) and then drop it if unhandled. + */ + __get_cpu_var(pmu_nmi).marked = this_nmi + 1; + __get_cpu_var(pmu_nmi).handled = handled; + } return NOTIFY_STOP; } @@ -1345,7 +1385,6 @@ void __init init_hw_perf_events(void) x86_pmu.num_counters = X86_PMC_MAX_GENERIC; } x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1; - perf_max_events = x86_pmu.num_counters; if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) { WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!", @@ -1381,6 +1420,7 @@ void __init init_hw_perf_events(void) pr_info("... fixed-purpose events: %d\n", x86_pmu.num_counters_fixed); pr_info("... event mask: %016Lx\n", x86_pmu.intel_ctrl); + perf_pmu_register(&pmu); perf_cpu_notifier(x86_pmu_notifier); } @@ -1394,10 +1434,11 @@ static inline void x86_pmu_read(struct perf_event *event) * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time */ -static void x86_pmu_start_txn(const struct pmu *pmu) +static void x86_pmu_start_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + perf_pmu_disable(pmu); cpuc->group_flag |= PERF_EVENT_TXN; cpuc->n_txn = 0; } @@ -1407,7 +1448,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu) * Clear the flag and pmu::enable() will perform the * schedulability test. */ -static void x86_pmu_cancel_txn(const struct pmu *pmu) +static void x86_pmu_cancel_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); @@ -1417,6 +1458,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu) */ cpuc->n_added -= cpuc->n_txn; cpuc->n_events -= cpuc->n_txn; + perf_pmu_enable(pmu); } /* @@ -1424,7 +1466,7 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu) * Perform the group schedulability test as a whole * Return 0 if success */ -static int x86_pmu_commit_txn(const struct pmu *pmu) +static int x86_pmu_commit_txn(struct pmu *pmu) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int assign[X86_PMC_IDX_MAX]; @@ -1446,22 +1488,10 @@ static int x86_pmu_commit_txn(const struct pmu *pmu) memcpy(cpuc->assign, assign, n*sizeof(int)); cpuc->group_flag &= ~PERF_EVENT_TXN; - + perf_pmu_enable(pmu); return 0; } -static const struct pmu pmu = { - .enable = x86_pmu_enable, - .disable = x86_pmu_disable, - .start = x86_pmu_start, - .stop = x86_pmu_stop, - .read = x86_pmu_read, - .unthrottle = x86_pmu_unthrottle, - .start_txn = x86_pmu_start_txn, - .cancel_txn = x86_pmu_cancel_txn, - .commit_txn = x86_pmu_commit_txn, -}; - /* * validate that we can schedule this event */ @@ -1536,12 +1566,22 @@ out: return ret; } -const struct pmu *hw_perf_event_init(struct perf_event *event) +int x86_pmu_event_init(struct perf_event *event) { - const struct pmu *tmp; + struct pmu *tmp; int err; - err = __hw_perf_event_init(event); + switch (event->attr.type) { + case PERF_TYPE_RAW: + case PERF_TYPE_HARDWARE: + case PERF_TYPE_HW_CACHE: + break; + + default: + return -ENOENT; + } + + err = __x86_pmu_event_init(event); if (!err) { /* * we temporarily connect event to its pmu @@ -1561,26 +1601,31 @@ const struct pmu *hw_perf_event_init(struct perf_event *event) if (err) { if (event->destroy) event->destroy(event); - return ERR_PTR(err); } - return &pmu; + return err; } -/* - * callchain support - */ +static struct pmu pmu = { + .pmu_enable = x86_pmu_enable, + .pmu_disable = x86_pmu_disable, -static inline -void callchain_store(struct perf_callchain_entry *entry, u64 ip) -{ - if (entry->nr < PERF_MAX_STACK_DEPTH) - entry->ip[entry->nr++] = ip; -} + .event_init = x86_pmu_event_init, -static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); -static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry); + .add = x86_pmu_add, + .del = x86_pmu_del, + .start = x86_pmu_start, + .stop = x86_pmu_stop, + .read = x86_pmu_read, + .start_txn = x86_pmu_start_txn, + .cancel_txn = x86_pmu_cancel_txn, + .commit_txn = x86_pmu_commit_txn, +}; + +/* + * callchain support + */ static void backtrace_warning_symbol(void *data, char *msg, unsigned long symbol) @@ -1602,7 +1647,7 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry *entry = data; - callchain_store(entry, addr); + perf_callchain_store(entry, addr); } static const struct stacktrace_ops backtrace_ops = { @@ -1613,11 +1658,15 @@ static const struct stacktrace_ops backtrace_ops = { .walk_stack = print_context_stack_bp, }; -static void -perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry) +void +perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { - callchain_store(entry, PERF_CONTEXT_KERNEL); - callchain_store(entry, regs->ip); + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* TODO: We don't support guest os callchain now */ + return; + } + + perf_callchain_store(entry, regs->ip); dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry); } @@ -1646,7 +1695,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) if (fp < compat_ptr(regs->sp)) break; - callchain_store(entry, frame.return_address); + perf_callchain_store(entry, frame.return_address); fp = compat_ptr(frame.next_frame); } return 1; @@ -1659,19 +1708,20 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) } #endif -static void -perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry) +void +perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) { struct stack_frame frame; const void __user *fp; - if (!user_mode(regs)) - regs = task_pt_regs(current); + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* TODO: We don't support guest os callchain now */ + return; + } fp = (void __user *)regs->bp; - callchain_store(entry, PERF_CONTEXT_USER); - callchain_store(entry, regs->ip); + perf_callchain_store(entry, regs->ip); if (perf_callchain_user32(regs, entry)) return; @@ -1688,52 +1738,11 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry) if ((unsigned long)fp < regs->sp) break; - callchain_store(entry, frame.return_address); + perf_callchain_store(entry, frame.return_address); fp = frame.next_frame; } } -static void -perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry) -{ - int is_user; - - if (!regs) - return; - - is_user = user_mode(regs); - - if (is_user && current->state != TASK_RUNNING) - return; - - if (!is_user) - perf_callchain_kernel(regs, entry); - - if (current->mm) - perf_callchain_user(regs, entry); -} - -struct perf_callchain_entry *perf_callchain(struct pt_regs *regs) -{ - struct perf_callchain_entry *entry; - - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - /* TODO: We don't support guest os callchain now */ - return NULL; - } - - if (in_nmi()) - entry = &__get_cpu_var(pmc_nmi_entry); - else - entry = &__get_cpu_var(pmc_irq_entry); - - entry->nr = 0; - - perf_do_callchain(regs, entry); - - return entry; -} - unsigned long perf_instruction_pointer(struct pt_regs *regs) { unsigned long ip; diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index c2897b7b4a3b..46d58448c3af 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -52,7 +52,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(DTLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses */ - [ C(RESULT_MISS) ] = 0x0046, /* L1 DTLB and L2 DLTB Miss */ + [ C(RESULT_MISS) ] = 0x0746, /* L1_DTLB_AND_L2_DLTB_MISS.ALL */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = 0, @@ -66,7 +66,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(ITLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes */ - [ C(RESULT_MISS) ] = 0x0085, /* Instr. fetch ITLB misses */ + [ C(RESULT_MISS) ] = 0x0385, /* L1_ITLB_AND_L2_ITLB_MISS.ALL */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = -1, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index d8d86d014008..c8f5c088cad1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -712,22 +712,24 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) struct perf_sample_data data; struct cpu_hw_events *cpuc; int bit, loops; - u64 ack, status; + u64 status; + int handled; perf_sample_data_init(&data, 0); cpuc = &__get_cpu_var(cpu_hw_events); intel_pmu_disable_all(); - intel_pmu_drain_bts_buffer(); + handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); if (!status) { intel_pmu_enable_all(0); - return 0; + return handled; } loops = 0; again: + intel_pmu_ack_status(status); if (++loops > 100) { WARN_ONCE(1, "perfevents: irq loop stuck!\n"); perf_event_print_debug(); @@ -736,19 +738,22 @@ again: } inc_irq_stat(apic_perf_irqs); - ack = status; intel_pmu_lbr_read(); /* * PEBS overflow sets bit 62 in the global status register */ - if (__test_and_clear_bit(62, (unsigned long *)&status)) + if (__test_and_clear_bit(62, (unsigned long *)&status)) { + handled++; x86_pmu.drain_pebs(regs); + } for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; + handled++; + if (!test_bit(bit, cpuc->active_mask)) continue; @@ -758,11 +763,9 @@ again: data.period = event->hw.last_period; if (perf_event_overflow(event, 1, &data, regs)) - x86_pmu_stop(event); + x86_pmu_stop(event, 0); } - intel_pmu_ack_status(ack); - /* * Repeat if there is more work to be done: */ @@ -772,7 +775,7 @@ again: done: intel_pmu_enable_all(0); - return 1; + return handled; } static struct event_constraint * diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 18018d1311cd..4977f9c400e5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -214,7 +214,7 @@ static void intel_pmu_disable_bts(void) update_debugctlmsr(debugctlmsr); } -static void intel_pmu_drain_bts_buffer(void) +static int intel_pmu_drain_bts_buffer(void) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -231,16 +231,16 @@ static void intel_pmu_drain_bts_buffer(void) struct pt_regs regs; if (!event) - return; + return 0; if (!ds) - return; + return 0; at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; top = (struct bts_record *)(unsigned long)ds->bts_index; if (top <= at) - return; + return 0; ds->bts_index = ds->bts_buffer_base; @@ -256,7 +256,7 @@ static void intel_pmu_drain_bts_buffer(void) perf_prepare_sample(&header, &data, event, ®s); if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1)) - return; + return 1; for (; at < top; at++) { data.ip = at->from; @@ -270,6 +270,7 @@ static void intel_pmu_drain_bts_buffer(void) /* There's new data available. */ event->hw.interrupts++; event->pending_kill = POLL_IN; + return 1; } /* @@ -491,7 +492,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.flags &= ~PERF_EFLAGS_EXACT; if (perf_event_overflow(event, 1, &data, ®s)) - x86_pmu_stop(event); + x86_pmu_stop(event, 0); } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index febb12cea795..81400b93e694 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -18,6 +18,8 @@ struct p4_event_bind { unsigned int opcode; /* Event code and ESCR selector */ unsigned int escr_msr[2]; /* ESCR MSR for this event */ + unsigned int escr_emask; /* valid ESCR EventMask bits */ + unsigned int shared; /* event is shared across threads */ char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ }; @@ -66,231 +68,435 @@ static struct p4_event_bind p4_event_bind_map[] = { [P4_EVENT_TC_DELIVER_MODE] = { .opcode = P4_OPCODE(P4_EVENT_TC_DELIVER_MODE), .escr_msr = { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD) | + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DB) | + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DI) | + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BD) | + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BB) | + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, BI) | + P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, ID), + .shared = 1, .cntr = { {4, 5, -1}, {6, 7, -1} }, }, [P4_EVENT_BPU_FETCH_REQUEST] = { .opcode = P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST), .escr_msr = { MSR_P4_BPU_ESCR0, MSR_P4_BPU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_BPU_FETCH_REQUEST, TCMISS), .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_ITLB_REFERENCE] = { .opcode = P4_OPCODE(P4_EVENT_ITLB_REFERENCE), .escr_msr = { MSR_P4_ITLB_ESCR0, MSR_P4_ITLB_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT) | + P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_ITLB_REFERENCE, HIT_UK), .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_MEMORY_CANCEL] = { .opcode = P4_OPCODE(P4_EVENT_MEMORY_CANCEL), .escr_msr = { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL) | + P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_CANCEL, 64K_CONF), .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_MEMORY_COMPLETE] = { .opcode = P4_OPCODE(P4_EVENT_MEMORY_COMPLETE), .escr_msr = { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, LSC) | + P4_ESCR_EMASK_BIT(P4_EVENT_MEMORY_COMPLETE, SSC), .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_LOAD_PORT_REPLAY] = { .opcode = P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY), .escr_msr = { MSR_P4_SAAT_ESCR0, MSR_P4_SAAT_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD), .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_STORE_PORT_REPLAY] = { .opcode = P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY), .escr_msr = { MSR_P4_SAAT_ESCR0 , MSR_P4_SAAT_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST), .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_MOB_LOAD_REPLAY] = { .opcode = P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY), .escr_msr = { MSR_P4_MOB_ESCR0, MSR_P4_MOB_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STA) | + P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, NO_STD) | + P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA) | + P4_ESCR_EMASK_BIT(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR), .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_PAGE_WALK_TYPE] = { .opcode = P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE), .escr_msr = { MSR_P4_PMH_ESCR0, MSR_P4_PMH_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, DTMISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_PAGE_WALK_TYPE, ITMISS), + .shared = 1, .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_BSQ_CACHE_REFERENCE] = { .opcode = P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE), .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS), .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_IOQ_ALLOCATION] = { .opcode = P4_OPCODE(P4_EVENT_IOQ_ALLOCATION), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, DEFAULT) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_READ) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_UC) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WC) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WT) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WP) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, MEM_WB) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OWN) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, OTHER) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ALLOCATION, PREFETCH), .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_IOQ_ACTIVE_ENTRIES] = { /* shared ESCR */ .opcode = P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES), .escr_msr = { MSR_P4_FSB_ESCR1, MSR_P4_FSB_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER) | + P4_ESCR_EMASK_BIT(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH), .cntr = { {2, -1, -1}, {3, -1, -1} }, }, [P4_EVENT_FSB_DATA_ACTIVITY] = { .opcode = P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN) | + P4_ESCR_EMASK_BIT(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER), + .shared = 1, .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_BSQ_ALLOCATION] = { /* shared ESCR, broken CCCR1 */ .opcode = P4_OPCODE(P4_EVENT_BSQ_ALLOCATION), .escr_msr = { MSR_P4_BSU_ESCR0, MSR_P4_BSU_ESCR0 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2), .cntr = { {0, -1, -1}, {1, -1, -1} }, }, [P4_EVENT_BSQ_ACTIVE_ENTRIES] = { /* shared ESCR */ .opcode = P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES), .escr_msr = { MSR_P4_BSU_ESCR1 , MSR_P4_BSU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1) | + P4_ESCR_EMASK_BIT(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2), .cntr = { {2, -1, -1}, {3, -1, -1} }, }, [P4_EVENT_SSE_INPUT_ASSIST] = { .opcode = P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_SSE_INPUT_ASSIST, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_PACKED_SP_UOP] = { .opcode = P4_OPCODE(P4_EVENT_PACKED_SP_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_SP_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_PACKED_DP_UOP] = { .opcode = P4_OPCODE(P4_EVENT_PACKED_DP_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_PACKED_DP_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_SCALAR_SP_UOP] = { .opcode = P4_OPCODE(P4_EVENT_SCALAR_SP_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_SP_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_SCALAR_DP_UOP] = { .opcode = P4_OPCODE(P4_EVENT_SCALAR_DP_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_SCALAR_DP_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_64BIT_MMX_UOP] = { .opcode = P4_OPCODE(P4_EVENT_64BIT_MMX_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_64BIT_MMX_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_128BIT_MMX_UOP] = { .opcode = P4_OPCODE(P4_EVENT_128BIT_MMX_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_128BIT_MMX_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_X87_FP_UOP] = { .opcode = P4_OPCODE(P4_EVENT_X87_FP_UOP), .escr_msr = { MSR_P4_FIRM_ESCR0, MSR_P4_FIRM_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_X87_FP_UOP, ALL), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_TC_MISC] = { .opcode = P4_OPCODE(P4_EVENT_TC_MISC), .escr_msr = { MSR_P4_TC_ESCR0, MSR_P4_TC_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_TC_MISC, FLUSH), .cntr = { {4, 5, -1}, {6, 7, -1} }, }, [P4_EVENT_GLOBAL_POWER_EVENTS] = { .opcode = P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING), .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_TC_MS_XFER] = { .opcode = P4_OPCODE(P4_EVENT_TC_MS_XFER), .escr_msr = { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_TC_MS_XFER, CISC), .cntr = { {4, 5, -1}, {6, 7, -1} }, }, [P4_EVENT_UOP_QUEUE_WRITES] = { .opcode = P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES), .escr_msr = { MSR_P4_MS_ESCR0, MSR_P4_MS_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD) | + P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER) | + P4_ESCR_EMASK_BIT(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM), .cntr = { {4, 5, -1}, {6, 7, -1} }, }, [P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE] = { .opcode = P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE), .escr_msr = { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR0 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT), .cntr = { {4, 5, -1}, {6, 7, -1} }, }, [P4_EVENT_RETIRED_BRANCH_TYPE] = { .opcode = P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE), .escr_msr = { MSR_P4_TBPU_ESCR0 , MSR_P4_TBPU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, CALL) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN) | + P4_ESCR_EMASK_BIT(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT), .cntr = { {4, 5, -1}, {6, 7, -1} }, }, [P4_EVENT_RESOURCE_STALL] = { .opcode = P4_OPCODE(P4_EVENT_RESOURCE_STALL), .escr_msr = { MSR_P4_ALF_ESCR0, MSR_P4_ALF_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_RESOURCE_STALL, SBFULL), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_WC_BUFFER] = { .opcode = P4_OPCODE(P4_EVENT_WC_BUFFER), .escr_msr = { MSR_P4_DAC_ESCR0, MSR_P4_DAC_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_EVICTS) | + P4_ESCR_EMASK_BIT(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS), + .shared = 1, .cntr = { {8, 9, -1}, {10, 11, -1} }, }, [P4_EVENT_B2B_CYCLES] = { .opcode = P4_OPCODE(P4_EVENT_B2B_CYCLES), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = 0, .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_BNR] = { .opcode = P4_OPCODE(P4_EVENT_BNR), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = 0, .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_SNOOP] = { .opcode = P4_OPCODE(P4_EVENT_SNOOP), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = 0, .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_RESPONSE] = { .opcode = P4_OPCODE(P4_EVENT_RESPONSE), .escr_msr = { MSR_P4_FSB_ESCR0, MSR_P4_FSB_ESCR1 }, + .escr_emask = 0, .cntr = { {0, -1, -1}, {2, -1, -1} }, }, [P4_EVENT_FRONT_END_EVENT] = { .opcode = P4_OPCODE(P4_EVENT_FRONT_END_EVENT), .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, NBOGUS) | + P4_ESCR_EMASK_BIT(P4_EVENT_FRONT_END_EVENT, BOGUS), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_EXECUTION_EVENT] = { .opcode = P4_OPCODE(P4_EVENT_EXECUTION_EVENT), .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_REPLAY_EVENT] = { .opcode = P4_OPCODE(P4_EVENT_REPLAY_EVENT), .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, NBOGUS) | + P4_ESCR_EMASK_BIT(P4_EVENT_REPLAY_EVENT, BOGUS), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_INSTR_RETIRED] = { .opcode = P4_OPCODE(P4_EVENT_INSTR_RETIRED), .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, NBOGUSTAG) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSNTAG) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_RETIRED, BOGUSTAG), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_UOPS_RETIRED] = { .opcode = P4_OPCODE(P4_EVENT_UOPS_RETIRED), .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, NBOGUS) | + P4_ESCR_EMASK_BIT(P4_EVENT_UOPS_RETIRED, BOGUS), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_UOP_TYPE] = { .opcode = P4_OPCODE(P4_EVENT_UOP_TYPE), .escr_msr = { MSR_P4_RAT_ESCR0, MSR_P4_RAT_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGLOADS) | + P4_ESCR_EMASK_BIT(P4_EVENT_UOP_TYPE, TAGSTORES), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_BRANCH_RETIRED] = { .opcode = P4_OPCODE(P4_EVENT_BRANCH_RETIRED), .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNP) | + P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMNM) | + P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTP) | + P4_ESCR_EMASK_BIT(P4_EVENT_BRANCH_RETIRED, MMTM), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_MISPRED_BRANCH_RETIRED] = { .opcode = P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED), .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_X87_ASSIST] = { .opcode = P4_OPCODE(P4_EVENT_X87_ASSIST), .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSU) | + P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, FPSO) | + P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAO) | + P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, POAU) | + P4_ESCR_EMASK_BIT(P4_EVENT_X87_ASSIST, PREA), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_MACHINE_CLEAR] = { .opcode = P4_OPCODE(P4_EVENT_MACHINE_CLEAR), .escr_msr = { MSR_P4_CRU_ESCR2, MSR_P4_CRU_ESCR3 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, CLEAR) | + P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, MOCLEAR) | + P4_ESCR_EMASK_BIT(P4_EVENT_MACHINE_CLEAR, SMCLEAR), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, [P4_EVENT_INSTR_COMPLETED] = { .opcode = P4_OPCODE(P4_EVENT_INSTR_COMPLETED), .escr_msr = { MSR_P4_CRU_ESCR0, MSR_P4_CRU_ESCR1 }, + .escr_emask = + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, NBOGUS) | + P4_ESCR_EMASK_BIT(P4_EVENT_INSTR_COMPLETED, BOGUS), .cntr = { {12, 13, 16}, {14, 15, 17} }, }, }; @@ -428,29 +634,73 @@ static u64 p4_pmu_event_map(int hw_event) return config; } +/* check cpu model specifics */ +static bool p4_event_match_cpu_model(unsigned int event_idx) +{ + /* INSTR_COMPLETED event only exist for model 3, 4, 6 (Prescott) */ + if (event_idx == P4_EVENT_INSTR_COMPLETED) { + if (boot_cpu_data.x86_model != 3 && + boot_cpu_data.x86_model != 4 && + boot_cpu_data.x86_model != 6) + return false; + } + + /* + * For info + * - IQ_ESCR0, IQ_ESCR1 only for models 1 and 2 + */ + + return true; +} + static int p4_validate_raw_event(struct perf_event *event) { - unsigned int v; + unsigned int v, emask; - /* user data may have out-of-bound event index */ + /* User data may have out-of-bound event index */ v = p4_config_unpack_event(event->attr.config); - if (v >= ARRAY_SIZE(p4_event_bind_map)) { - pr_warning("P4 PMU: Unknown event code: %d\n", v); + if (v >= ARRAY_SIZE(p4_event_bind_map)) + return -EINVAL; + + /* It may be unsupported: */ + if (!p4_event_match_cpu_model(v)) return -EINVAL; + + /* + * NOTE: P4_CCCR_THREAD_ANY has not the same meaning as + * in Architectural Performance Monitoring, it means not + * on _which_ logical cpu to count but rather _when_, ie it + * depends on logical cpu state -- count event if one cpu active, + * none, both or any, so we just allow user to pass any value + * desired. + * + * In turn we always set Tx_OS/Tx_USR bits bound to logical + * cpu without their propagation to another cpu + */ + + /* + * if an event is shared accross the logical threads + * the user needs special permissions to be able to use it + */ + if (p4_event_bind_map[v].shared) { + if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN)) + return -EACCES; } + /* ESCR EventMask bits may be invalid */ + emask = p4_config_unpack_escr(event->attr.config) & P4_ESCR_EVENTMASK_MASK; + if (emask & ~p4_event_bind_map[v].escr_emask) + return -EINVAL; + /* - * it may have some screwed PEBS bits + * it may have some invalid PEBS bits */ - if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) { - pr_warning("P4 PMU: PEBS are not supported yet\n"); + if (p4_config_pebs_has(event->attr.config, P4_PEBS_CONFIG_ENABLE)) return -EINVAL; - } + v = p4_config_unpack_metric(event->attr.config); - if (v >= ARRAY_SIZE(p4_pebs_bind_map)) { - pr_warning("P4 PMU: Unknown metric code: %d\n", v); + if (v >= ARRAY_SIZE(p4_pebs_bind_map)) return -EINVAL; - } return 0; } @@ -478,25 +728,21 @@ static int p4_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) { + /* + * Clear bits we reserve to be managed by kernel itself + * and never allowed from a user space + */ + event->attr.config &= P4_CONFIG_MASK; + rc = p4_validate_raw_event(event); if (rc) goto out; /* - * We don't control raw events so it's up to the caller - * to pass sane values (and we don't count the thread number - * on HT machine but allow HT-compatible specifics to be - * passed on) - * * Note that for RAW events we allow user to use P4_CCCR_RESERVED * bits since we keep additional info here (for cache events and etc) - * - * XXX: HT wide things should check perf_paranoid_cpu() && - * CAP_SYS_ADMIN */ - event->hw.config |= event->attr.config & - (p4_config_pack_escr(P4_ESCR_MASK_HT) | - p4_config_pack_cccr(P4_CCCR_MASK_HT | P4_CCCR_RESERVED)); + event->hw.config |= event->attr.config; } rc = x86_setup_perfctr(event); @@ -658,8 +904,12 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) for (idx = 0; idx < x86_pmu.num_counters; idx++) { int overflow; - if (!test_bit(idx, cpuc->active_mask)) + if (!test_bit(idx, cpuc->active_mask)) { + /* catch in-flight IRQs */ + if (__test_and_clear_bit(idx, cpuc->running)) + handled++; continue; + } event = cpuc->events[idx]; hwc = &event->hw; @@ -690,7 +940,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) inc_irq_stat(apic_perf_irqs); } - return handled > 0; + return handled; } /* diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index fb329e9f8494..d9f4ff8fcd69 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -700,11 +700,10 @@ static void probe_nmi_watchdog(void) { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: - if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 && - boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17) - return; - wd_ops = &k7_wd_ops; - break; + if (boot_cpu_data.x86 == 6 || + (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15)) + wd_ops = &k7_wd_ops; + return; case X86_VENDOR_INTEL: /* Work around where perfctr1 doesn't have a working enable * bit as described in the following errata: diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 34b4dad6f0b8..c7f64e6f537a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { + { X86_FEATURE_DTS, CR_EAX, 0, 0x00000006, 0 }, { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, @@ -43,6 +44,12 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, + { X86_FEATURE_TSCRATEMSR, CR_EDX, 4, 0x8000000a, 0 }, + { X86_FEATURE_VMCBCLEAN, CR_EDX, 5, 0x8000000a, 0 }, + { X86_FEATURE_FLUSHBYASID, CR_EDX, 6, 0x8000000a, 0 }, + { X86_FEATURE_DECODEASSISTS, CR_EDX, 7, 0x8000000a, 0 }, + { X86_FEATURE_PAUSEFILTER, CR_EDX,10, 0x8000000a, 0 }, + { X86_FEATURE_PFTHRESHOLD, CR_EDX,12, 0x8000000a, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index 045b36cada65..994828899e09 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -34,7 +34,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!csize) return 0; - vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE); + vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE); if (!vaddr) return -ENOMEM; @@ -46,6 +46,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, } else memcpy(buf, vaddr + offset, csize); + set_iounmap_nonlazy(); iounmap(vaddr); return csize; } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index e5cc7e82e60d..76b8cd953dee 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -18,7 +18,6 @@ #include <asm/apic.h> #include <asm/iommu.h> #include <asm/gart.h> -#include <asm/hpet.h> static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -98,7 +97,6 @@ static void __init nvidia_bugs(int num, int slot, int func) } #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC) -#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC) static u32 __init ati_ixp4x0_rev(int num, int slot, int func) { u32 d; @@ -116,7 +114,6 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func) d &= 0xff; return d; } -#endif static void __init ati_bugs(int num, int slot, int func) { @@ -192,21 +189,6 @@ static void __init ati_bugs_contd(int num, int slot, int func) } #endif -/* - * Force the read back of the CMP register in hpet_next_event() - * to work around the problem that the CMP register write seems to be - * delayed. See hpet_next_event() for details. - * - * We do this on all SMBUS incarnations for now until we have more - * information about the affected chipsets. - */ -static void __init ati_hpet_bugs(int num, int slot, int func) -{ -#ifdef CONFIG_HPET_TIMER - hpet_readback_cmp = 1; -#endif -} - #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -236,8 +218,6 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs }, { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, - { PCI_VENDOR_ID_ATI, PCI_ANY_ID, - PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs }, {} }; diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index fa99bae75ace..4572f25f9325 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -14,6 +14,7 @@ #include <xen/hvc-console.h> #include <asm/pci-direct.h> #include <asm/fixmap.h> +#include <asm/mrst.h> #include <asm/pgtable.h> #include <linux/usb/ehci_def.h> @@ -239,6 +240,18 @@ static int __init setup_early_printk(char *buf) if (!strncmp(buf, "xen", 3)) early_console_register(&xenboot_console, keep); #endif +#ifdef CONFIG_X86_MRST_EARLY_PRINTK + if (!strncmp(buf, "mrst", 4)) { + mrst_early_console_init(); + early_console_register(&early_mrst_console, keep); + } + + if (!strncmp(buf, "hsu", 3)) { + hsu_early_console_init(); + early_console_register(&early_hsu_console, keep); + } + +#endif buf++; } return 0; diff --git a/arch/x86/kernel/early_printk_mrst.c b/arch/x86/kernel/early_printk_mrst.c new file mode 100644 index 000000000000..65df603622b2 --- /dev/null +++ b/arch/x86/kernel/early_printk_mrst.c @@ -0,0 +1,319 @@ +/* + * early_printk_mrst.c - early consoles for Intel MID platforms + * + * Copyright (c) 2008-2010, Intel 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. + */ + +/* + * This file implements two early consoles named mrst and hsu. + * mrst is based on Maxim3110 spi-uart device, it exists in both + * Moorestown and Medfield platforms, while hsu is based on a High + * Speed UART device which only exists in the Medfield platform + */ + +#include <linux/serial_reg.h> +#include <linux/serial_mfd.h> +#include <linux/kmsg_dump.h> +#include <linux/console.h> +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/io.h> + +#include <asm/fixmap.h> +#include <asm/pgtable.h> +#include <asm/mrst.h> + +#define MRST_SPI_TIMEOUT 0x200000 +#define MRST_REGBASE_SPI0 0xff128000 +#define MRST_REGBASE_SPI1 0xff128400 +#define MRST_CLK_SPI0_REG 0xff11d86c + +/* Bit fields in CTRLR0 */ +#define SPI_DFS_OFFSET 0 + +#define SPI_FRF_OFFSET 4 +#define SPI_FRF_SPI 0x0 +#define SPI_FRF_SSP 0x1 +#define SPI_FRF_MICROWIRE 0x2 +#define SPI_FRF_RESV 0x3 + +#define SPI_MODE_OFFSET 6 +#define SPI_SCPH_OFFSET 6 +#define SPI_SCOL_OFFSET 7 +#define SPI_TMOD_OFFSET 8 +#define SPI_TMOD_TR 0x0 /* xmit & recv */ +#define SPI_TMOD_TO 0x1 /* xmit only */ +#define SPI_TMOD_RO 0x2 /* recv only */ +#define SPI_TMOD_EPROMREAD 0x3 /* eeprom read mode */ + +#define SPI_SLVOE_OFFSET 10 +#define SPI_SRL_OFFSET 11 +#define SPI_CFS_OFFSET 12 + +/* Bit fields in SR, 7 bits */ +#define SR_MASK 0x7f /* cover 7 bits */ +#define SR_BUSY (1 << 0) +#define SR_TF_NOT_FULL (1 << 1) +#define SR_TF_EMPT (1 << 2) +#define SR_RF_NOT_EMPT (1 << 3) +#define SR_RF_FULL (1 << 4) +#define SR_TX_ERR (1 << 5) +#define SR_DCOL (1 << 6) + +struct dw_spi_reg { + u32 ctrl0; + u32 ctrl1; + u32 ssienr; + u32 mwcr; + u32 ser; + u32 baudr; + u32 txfltr; + u32 rxfltr; + u32 txflr; + u32 rxflr; + u32 sr; + u32 imr; + u32 isr; + u32 risr; + u32 txoicr; + u32 rxoicr; + u32 rxuicr; + u32 msticr; + u32 icr; + u32 dmacr; + u32 dmatdlr; + u32 dmardlr; + u32 idr; + u32 version; + + /* Currently operates as 32 bits, though only the low 16 bits matter */ + u32 dr; +} __packed; + +#define dw_readl(dw, name) __raw_readl(&(dw)->name) +#define dw_writel(dw, name, val) __raw_writel((val), &(dw)->name) + +/* Default use SPI0 register for mrst, we will detect Penwell and use SPI1 */ +static unsigned long mrst_spi_paddr = MRST_REGBASE_SPI0; + +static u32 *pclk_spi0; +/* Always contains an accessable address, start with 0 */ +static struct dw_spi_reg *pspi; + +static struct kmsg_dumper dw_dumper; +static int dumper_registered; + +static void dw_kmsg_dump(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason, + const char *s1, unsigned long l1, + const char *s2, unsigned long l2) +{ + int i; + + /* When run to this, we'd better re-init the HW */ + mrst_early_console_init(); + + for (i = 0; i < l1; i++) + early_mrst_console.write(&early_mrst_console, s1 + i, 1); + for (i = 0; i < l2; i++) + early_mrst_console.write(&early_mrst_console, s2 + i, 1); +} + +/* Set the ratio rate to 115200, 8n1, IRQ disabled */ +static void max3110_write_config(void) +{ + u16 config; + + config = 0xc001; + dw_writel(pspi, dr, config); +} + +/* Translate char to a eligible word and send to max3110 */ +static void max3110_write_data(char c) +{ + u16 data; + + data = 0x8000 | c; + dw_writel(pspi, dr, data); +} + +void mrst_early_console_init(void) +{ + u32 ctrlr0 = 0; + u32 spi0_cdiv; + u32 freq; /* Freqency info only need be searched once */ + + /* Base clk is 100 MHz, the actual clk = 100M / (clk_divider + 1) */ + pclk_spi0 = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE, + MRST_CLK_SPI0_REG); + spi0_cdiv = ((*pclk_spi0) & 0xe00) >> 9; + freq = 100000000 / (spi0_cdiv + 1); + + if (mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL) + mrst_spi_paddr = MRST_REGBASE_SPI1; + + pspi = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE, + mrst_spi_paddr); + + /* Disable SPI controller */ + dw_writel(pspi, ssienr, 0); + + /* Set control param, 8 bits, transmit only mode */ + ctrlr0 = dw_readl(pspi, ctrl0); + + ctrlr0 &= 0xfcc0; + ctrlr0 |= 0xf | (SPI_FRF_SPI << SPI_FRF_OFFSET) + | (SPI_TMOD_TO << SPI_TMOD_OFFSET); + dw_writel(pspi, ctrl0, ctrlr0); + + /* + * Change the spi0 clk to comply with 115200 bps, use 100000 to + * calculate the clk dividor to make the clock a little slower + * than real baud rate. + */ + dw_writel(pspi, baudr, freq/100000); + + /* Disable all INT for early phase */ + dw_writel(pspi, imr, 0x0); + + /* Set the cs to spi-uart */ + dw_writel(pspi, ser, 0x2); + + /* Enable the HW, the last step for HW init */ + dw_writel(pspi, ssienr, 0x1); + + /* Set the default configuration */ + max3110_write_config(); + + /* Register the kmsg dumper */ + if (!dumper_registered) { + dw_dumper.dump = dw_kmsg_dump; + kmsg_dump_register(&dw_dumper); + dumper_registered = 1; + } +} + +/* Slave select should be called in the read/write function */ +static void early_mrst_spi_putc(char c) +{ + unsigned int timeout; + u32 sr; + + timeout = MRST_SPI_TIMEOUT; + /* Early putc needs to make sure the TX FIFO is not full */ + while (--timeout) { + sr = dw_readl(pspi, sr); + if (!(sr & SR_TF_NOT_FULL)) + cpu_relax(); + else + break; + } + + if (!timeout) + pr_warning("MRST earlycon: timed out\n"); + else + max3110_write_data(c); +} + +/* Early SPI only uses polling mode */ +static void early_mrst_spi_write(struct console *con, const char *str, unsigned n) +{ + int i; + + for (i = 0; i < n && *str; i++) { + if (*str == '\n') + early_mrst_spi_putc('\r'); + early_mrst_spi_putc(*str); + str++; + } +} + +struct console early_mrst_console = { + .name = "earlymrst", + .write = early_mrst_spi_write, + .flags = CON_PRINTBUFFER, + .index = -1, +}; + +/* + * Following is the early console based on Medfield HSU (High + * Speed UART) device. + */ +#define HSU_PORT2_PADDR 0xffa28180 + +static void __iomem *phsu; + +void hsu_early_console_init(void) +{ + u8 lcr; + + phsu = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE, + HSU_PORT2_PADDR); + + /* Disable FIFO */ + writeb(0x0, phsu + UART_FCR); + + /* Set to default 115200 bps, 8n1 */ + lcr = readb(phsu + UART_LCR); + writeb((0x80 | lcr), phsu + UART_LCR); + writeb(0x18, phsu + UART_DLL); + writeb(lcr, phsu + UART_LCR); + writel(0x3600, phsu + UART_MUL*4); + + writeb(0x8, phsu + UART_MCR); + writeb(0x7, phsu + UART_FCR); + writeb(0x3, phsu + UART_LCR); + + /* Clear IRQ status */ + readb(phsu + UART_LSR); + readb(phsu + UART_RX); + readb(phsu + UART_IIR); + readb(phsu + UART_MSR); + + /* Enable FIFO */ + writeb(0x7, phsu + UART_FCR); +} + +#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) + +static void early_hsu_putc(char ch) +{ + unsigned int timeout = 10000; /* 10ms */ + u8 status; + + while (--timeout) { + status = readb(phsu + UART_LSR); + if (status & BOTH_EMPTY) + break; + udelay(1); + } + + /* Only write the char when there was no timeout */ + if (timeout) + writeb(ch, phsu + UART_TX); +} + +static void early_hsu_write(struct console *con, const char *str, unsigned n) +{ + int i; + + for (i = 0; i < n && *str; i++) { + if (*str == '\n') + early_hsu_putc('\r'); + early_hsu_putc(*str); + str++; + } +} + +struct console early_hsu_console = { + .name = "earlyhsu", + .write = early_hsu_write, + .flags = CON_PRINTBUFFER, + .index = -1, +}; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 227d00920d2f..9fb188d7bc76 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -115,8 +115,7 @@ /* unfortunately push/pop can't be no-op */ .macro PUSH_GS - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 .endm .macro POP_GS pop=0 addl $(4 + \pop), %esp @@ -140,14 +139,12 @@ #else /* CONFIG_X86_32_LAZY_GS */ .macro PUSH_GS - pushl %gs - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %gs /*CFI_REL_OFFSET gs, 0*/ .endm .macro POP_GS pop=0 -98: popl %gs - CFI_ADJUST_CFA_OFFSET -4 +98: popl_cfi %gs /*CFI_RESTORE gs*/ .if \pop <> 0 add $\pop, %esp @@ -195,35 +192,25 @@ .macro SAVE_ALL cld PUSH_GS - pushl %fs - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %fs /*CFI_REL_OFFSET fs, 0;*/ - pushl %es - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %es /*CFI_REL_OFFSET es, 0;*/ - pushl %ds - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ds /*CFI_REL_OFFSET ds, 0;*/ - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax CFI_REL_OFFSET eax, 0 - pushl %ebp - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebp CFI_REL_OFFSET ebp, 0 - pushl %edi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edi CFI_REL_OFFSET edi, 0 - pushl %esi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %esi CFI_REL_OFFSET esi, 0 - pushl %edx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edx CFI_REL_OFFSET edx, 0 - pushl %ecx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx CFI_REL_OFFSET ecx, 0 - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx CFI_REL_OFFSET ebx, 0 movl $(__USER_DS), %edx movl %edx, %ds @@ -234,39 +221,29 @@ .endm .macro RESTORE_INT_REGS - popl %ebx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebx CFI_RESTORE ebx - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ecx CFI_RESTORE ecx - popl %edx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %edx CFI_RESTORE edx - popl %esi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %esi CFI_RESTORE esi - popl %edi - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %edi CFI_RESTORE edi - popl %ebp - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ebp CFI_RESTORE ebp - popl %eax - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %eax CFI_RESTORE eax .endm .macro RESTORE_REGS pop=0 RESTORE_INT_REGS -1: popl %ds - CFI_ADJUST_CFA_OFFSET -4 +1: popl_cfi %ds /*CFI_RESTORE ds;*/ -2: popl %es - CFI_ADJUST_CFA_OFFSET -4 +2: popl_cfi %es /*CFI_RESTORE es;*/ -3: popl %fs - CFI_ADJUST_CFA_OFFSET -4 +3: popl_cfi %fs /*CFI_RESTORE fs;*/ POP_GS \pop .pushsection .fixup, "ax" @@ -320,16 +297,12 @@ ENTRY(ret_from_fork) CFI_STARTPROC - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax call schedule_tail GET_THREAD_INFO(%ebp) - popl %eax - CFI_ADJUST_CFA_OFFSET -4 - pushl $0x0202 # Reset kernel eflags - CFI_ADJUST_CFA_OFFSET 4 - popfl - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %eax + pushl_cfi $0x0202 # Reset kernel eflags + popfl_cfi jmp syscall_exit CFI_ENDPROC END(ret_from_fork) @@ -409,29 +382,23 @@ sysenter_past_esp: * enough kernel state to call TRACE_IRQS_OFF can be called - but * we immediately enable interrupts at that point anyway. */ - pushl $(__USER_DS) - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $(__USER_DS) /*CFI_REL_OFFSET ss, 0*/ - pushl %ebp - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebp CFI_REL_OFFSET esp, 0 - pushfl + pushfl_cfi orl $X86_EFLAGS_IF, (%esp) - CFI_ADJUST_CFA_OFFSET 4 - pushl $(__USER_CS) - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $(__USER_CS) /*CFI_REL_OFFSET cs, 0*/ /* * Push current_thread_info()->sysenter_return to the stack. * A tiny bit of offset fixup is necessary - 4*4 means the 4 words * pushed above; +8 corresponds to copy_thread's esp0 setting. */ - pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp) - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp) CFI_REL_OFFSET eip, 0 - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax SAVE_ALL ENABLE_INTERRUPTS(CLBR_NONE) @@ -486,8 +453,7 @@ sysenter_audit: movl %eax,%edx /* 2nd arg: syscall number */ movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */ call audit_syscall_entry - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx movl PT_EAX(%esp),%eax /* reload syscall number */ jmp sysenter_do_call @@ -529,8 +495,7 @@ ENDPROC(ia32_sysenter_target) # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway - pushl %eax # save orig_eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax # save orig_eax SAVE_ALL GET_THREAD_INFO(%ebp) # system call tracing in operation / emulation @@ -566,7 +531,6 @@ restore_all_notrace: je ldt_ss # returning to user-space with LDT SS restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code - CFI_ADJUST_CFA_OFFSET -4 irq_return: INTERRUPT_RETURN .section .fixup,"ax" @@ -619,10 +583,8 @@ ldt_ss: shr $16, %edx mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ - pushl $__ESPFIX_SS - CFI_ADJUST_CFA_OFFSET 4 - push %eax /* new kernel esp */ - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $__ESPFIX_SS + pushl_cfi %eax /* new kernel esp */ /* Disable interrupts, but do not irqtrace this section: we * will soon execute iret and the tracer was already set to * the irqstate after the iret */ @@ -666,11 +628,9 @@ work_notifysig: # deal with pending signals and ALIGN work_notifysig_v86: - pushl %ecx # save ti_flags for do_notify_resume - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx # save ti_flags for do_notify_resume call save_v86_state # %eax contains pt_regs pointer - popl %ecx - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %ecx movl %eax, %esp #else movl %esp, %eax @@ -750,14 +710,18 @@ ptregs_##name: \ #define PTREGSCALL3(name) \ ALIGN; \ ptregs_##name: \ + CFI_STARTPROC; \ leal 4(%esp),%eax; \ - pushl %eax; \ + pushl_cfi %eax; \ movl PT_EDX(%eax),%ecx; \ movl PT_ECX(%eax),%edx; \ movl PT_EBX(%eax),%eax; \ call sys_##name; \ addl $4,%esp; \ - ret + CFI_ADJUST_CFA_OFFSET -4; \ + ret; \ + CFI_ENDPROC; \ +ENDPROC(ptregs_##name) PTREGSCALL1(iopl) PTREGSCALL0(fork) @@ -772,15 +736,19 @@ PTREGSCALL1(vm86old) /* Clone is an oddball. The 4th arg is in %edi */ ALIGN; ptregs_clone: + CFI_STARTPROC leal 4(%esp),%eax - pushl %eax - pushl PT_EDI(%eax) + pushl_cfi %eax + pushl_cfi PT_EDI(%eax) movl PT_EDX(%eax),%ecx movl PT_ECX(%eax),%edx movl PT_EBX(%eax),%eax call sys_clone addl $8,%esp + CFI_ADJUST_CFA_OFFSET -8 ret + CFI_ENDPROC +ENDPROC(ptregs_clone) .macro FIXUP_ESPFIX_STACK /* @@ -795,10 +763,8 @@ ptregs_clone: mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ shl $16, %eax addl %esp, %eax /* the adjusted stack pointer */ - pushl $__KERNEL_DS - CFI_ADJUST_CFA_OFFSET 4 - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $__KERNEL_DS + pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 .endm @@ -835,8 +801,7 @@ vector=FIRST_EXTERNAL_VECTOR .if vector <> FIRST_EXTERNAL_VECTOR CFI_ADJUST_CFA_OFFSET -4 .endif -1: pushl $(~vector+0x80) /* Note: always in signed byte range */ - CFI_ADJUST_CFA_OFFSET 4 +1: pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 jmp 2f .endif @@ -876,8 +841,7 @@ ENDPROC(common_interrupt) #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ - pushl $~(nr); \ - CFI_ADJUST_CFA_OFFSET 4; \ + pushl_cfi $~(nr); \ SAVE_ALL; \ TRACE_IRQS_OFF \ movl %esp,%eax; \ @@ -893,21 +857,18 @@ ENDPROC(name) ENTRY(coprocessor_error) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_coprocessor_error - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi $do_coprocessor_error jmp error_code CFI_ENDPROC END(coprocessor_error) ENTRY(simd_coprocessor_error) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ -661: pushl $do_general_protection +661: pushl_cfi $do_general_protection 662: .section .altinstructions,"a" .balign 4 @@ -922,19 +883,16 @@ ENTRY(simd_coprocessor_error) 664: .previous #else - pushl $do_simd_coprocessor_error + pushl_cfi $do_simd_coprocessor_error #endif - CFI_ADJUST_CFA_OFFSET 4 jmp error_code CFI_ENDPROC END(simd_coprocessor_error) ENTRY(device_not_available) RING0_INT_FRAME - pushl $-1 # mark this as an int - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_device_not_available - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $-1 # mark this as an int + pushl_cfi $do_device_not_available jmp error_code CFI_ENDPROC END(device_not_available) @@ -956,82 +914,68 @@ END(native_irq_enable_sysexit) ENTRY(overflow) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_overflow - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi $do_overflow jmp error_code CFI_ENDPROC END(overflow) ENTRY(bounds) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_bounds - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi $do_bounds jmp error_code CFI_ENDPROC END(bounds) ENTRY(invalid_op) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_invalid_op - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi $do_invalid_op jmp error_code CFI_ENDPROC END(invalid_op) ENTRY(coprocessor_segment_overrun) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_coprocessor_segment_overrun - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi $do_coprocessor_segment_overrun jmp error_code CFI_ENDPROC END(coprocessor_segment_overrun) ENTRY(invalid_TSS) RING0_EC_FRAME - pushl $do_invalid_TSS - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_invalid_TSS jmp error_code CFI_ENDPROC END(invalid_TSS) ENTRY(segment_not_present) RING0_EC_FRAME - pushl $do_segment_not_present - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_segment_not_present jmp error_code CFI_ENDPROC END(segment_not_present) ENTRY(stack_segment) RING0_EC_FRAME - pushl $do_stack_segment - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_stack_segment jmp error_code CFI_ENDPROC END(stack_segment) ENTRY(alignment_check) RING0_EC_FRAME - pushl $do_alignment_check - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_alignment_check jmp error_code CFI_ENDPROC END(alignment_check) ENTRY(divide_error) RING0_INT_FRAME - pushl $0 # no error code - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_divide_error - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 # no error code + pushl_cfi $do_divide_error jmp error_code CFI_ENDPROC END(divide_error) @@ -1039,10 +983,8 @@ END(divide_error) #ifdef CONFIG_X86_MCE ENTRY(machine_check) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl machine_check_vector - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi machine_check_vector jmp error_code CFI_ENDPROC END(machine_check) @@ -1050,10 +992,8 @@ END(machine_check) ENTRY(spurious_interrupt_bug) RING0_INT_FRAME - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 - pushl $do_spurious_interrupt_bug - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 + pushl_cfi $do_spurious_interrupt_bug jmp error_code CFI_ENDPROC END(spurious_interrupt_bug) @@ -1084,8 +1024,7 @@ ENTRY(xen_sysenter_target) ENTRY(xen_hypervisor_callback) CFI_STARTPROC - pushl $0 - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $0 SAVE_ALL TRACE_IRQS_OFF @@ -1121,23 +1060,20 @@ ENDPROC(xen_hypervisor_callback) # We distinguish between categories by maintaining a status value in EAX. ENTRY(xen_failsafe_callback) CFI_STARTPROC - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax movl $1,%eax 1: mov 4(%esp),%ds 2: mov 8(%esp),%es 3: mov 12(%esp),%fs 4: mov 16(%esp),%gs testl %eax,%eax - popl %eax - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %eax lea 16(%esp),%esp CFI_ADJUST_CFA_OFFSET -16 jz 5f addl $16,%esp jmp iret_exc # EAX != 0 => Category 2 (Bad IRET) -5: pushl $0 # EAX == 0 => Category 1 (Bad segment) - CFI_ADJUST_CFA_OFFSET 4 +5: pushl_cfi $0 # EAX == 0 => Category 1 (Bad segment) SAVE_ALL jmp ret_from_exception CFI_ENDPROC @@ -1287,40 +1223,29 @@ syscall_table_size=(.-sys_call_table) ENTRY(page_fault) RING0_EC_FRAME - pushl $do_page_fault - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_page_fault ALIGN error_code: /* the function address is in %gs's slot on the stack */ - pushl %fs - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %fs /*CFI_REL_OFFSET fs, 0*/ - pushl %es - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %es /*CFI_REL_OFFSET es, 0*/ - pushl %ds - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ds /*CFI_REL_OFFSET ds, 0*/ - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax CFI_REL_OFFSET eax, 0 - pushl %ebp - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebp CFI_REL_OFFSET ebp, 0 - pushl %edi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edi CFI_REL_OFFSET edi, 0 - pushl %esi - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %esi CFI_REL_OFFSET esi, 0 - pushl %edx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %edx CFI_REL_OFFSET edx, 0 - pushl %ecx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ecx CFI_REL_OFFSET ecx, 0 - pushl %ebx - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ebx CFI_REL_OFFSET ebx, 0 cld movl $(__KERNEL_PERCPU), %ecx @@ -1362,12 +1287,9 @@ END(page_fault) movl TSS_sysenter_sp0 + \offset(%esp), %esp CFI_DEF_CFA esp, 0 CFI_UNDEFINED eip - pushfl - CFI_ADJUST_CFA_OFFSET 4 - pushl $__KERNEL_CS - CFI_ADJUST_CFA_OFFSET 4 - pushl $sysenter_past_esp - CFI_ADJUST_CFA_OFFSET 4 + pushfl_cfi + pushl_cfi $__KERNEL_CS + pushl_cfi $sysenter_past_esp CFI_REL_OFFSET eip, 0 .endm @@ -1377,8 +1299,7 @@ ENTRY(debug) jne debug_stack_correct FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn debug_stack_correct: - pushl $-1 # mark this as an int - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $-1 # mark this as an int SAVE_ALL TRACE_IRQS_OFF xorl %edx,%edx # error code 0 @@ -1398,32 +1319,27 @@ END(debug) */ ENTRY(nmi) RING0_INT_FRAME - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax - popl %eax - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %eax je nmi_espfix_stack cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax movl %esp,%eax /* Do not access memory above the end of our stack page, * it might not exist. */ andl $(THREAD_SIZE-1),%eax cmpl $(THREAD_SIZE-20),%eax - popl %eax - CFI_ADJUST_CFA_OFFSET -4 + popl_cfi %eax jae nmi_stack_correct cmpl $ia32_sysenter_target,12(%esp) je nmi_debug_stack_check nmi_stack_correct: /* We have a RING0_INT_FRAME here */ - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax SAVE_ALL xorl %edx,%edx # zero error code movl %esp,%eax # pt_regs pointer @@ -1452,18 +1368,14 @@ nmi_espfix_stack: * * create the pointer to lss back */ - pushl %ss - CFI_ADJUST_CFA_OFFSET 4 - pushl %esp - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %ss + pushl_cfi %esp addl $4, (%esp) /* copy the iret frame of 12 bytes */ .rept 3 - pushl 16(%esp) - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi 16(%esp) .endr - pushl %eax - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi %eax SAVE_ALL FIXUP_ESPFIX_STACK # %eax == %esp xorl %edx,%edx # zero error code @@ -1477,8 +1389,7 @@ END(nmi) ENTRY(int3) RING0_INT_FRAME - pushl $-1 # mark this as an int - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $-1 # mark this as an int SAVE_ALL TRACE_IRQS_OFF xorl %edx,%edx # zero error code @@ -1490,8 +1401,7 @@ END(int3) ENTRY(general_protection) RING0_EC_FRAME - pushl $do_general_protection - CFI_ADJUST_CFA_OFFSET 4 + pushl_cfi $do_general_protection jmp error_code CFI_ENDPROC END(general_protection) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 17be5ec7cbba..a7ae7fd1010f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -213,23 +213,17 @@ ENDPROC(native_usergs_sysret64) .macro FAKE_STACK_FRAME child_rip /* push in order ss, rsp, eflags, cs, rip */ xorl %eax, %eax - pushq $__KERNEL_DS /* ss */ - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $__KERNEL_DS /* ss */ /*CFI_REL_OFFSET ss,0*/ - pushq %rax /* rsp */ - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rax /* rsp */ CFI_REL_OFFSET rsp,0 - pushq $X86_EFLAGS_IF /* eflags - interrupts on */ - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $X86_EFLAGS_IF /* eflags - interrupts on */ /*CFI_REL_OFFSET rflags,0*/ - pushq $__KERNEL_CS /* cs */ - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $__KERNEL_CS /* cs */ /*CFI_REL_OFFSET cs,0*/ - pushq \child_rip /* rip */ - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi \child_rip /* rip */ CFI_REL_OFFSET rip,0 - pushq %rax /* orig rax */ - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rax /* orig rax */ .endm .macro UNFAKE_STACK_FRAME @@ -398,10 +392,8 @@ ENTRY(ret_from_fork) LOCK ; btr $TIF_FORK,TI_flags(%r8) - push kernel_eflags(%rip) - CFI_ADJUST_CFA_OFFSET 8 - popf # reset kernel eflags - CFI_ADJUST_CFA_OFFSET -8 + pushq_cfi kernel_eflags(%rip) + popfq_cfi # reset kernel eflags call schedule_tail # rdi: 'prev' task parameter @@ -521,11 +513,9 @@ sysret_careful: jnc sysret_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rdi call schedule - popq %rdi - CFI_ADJUST_CFA_OFFSET -8 + popq_cfi %rdi jmp sysret_check /* Handle a signal */ @@ -634,11 +624,9 @@ int_careful: jnc int_very_careful TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rdi call schedule - popq %rdi - CFI_ADJUST_CFA_OFFSET -8 + popq_cfi %rdi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF jmp int_with_check @@ -652,12 +640,10 @@ int_check_syscall_exit_work: /* Check for syscall exit trace */ testl $_TIF_WORK_SYSCALL_EXIT,%edx jz int_signal - pushq %rdi - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rdi leaq 8(%rsp),%rdi # &ptregs -> arg1 call syscall_trace_leave - popq %rdi - CFI_ADJUST_CFA_OFFSET -8 + popq_cfi %rdi andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi jmp int_restore_rest @@ -714,9 +700,8 @@ END(ptregscall_common) ENTRY(stub_execve) CFI_STARTPROC - popq %r11 - CFI_ADJUST_CFA_OFFSET -8 - CFI_REGISTER rip, r11 + addq $8, %rsp + PARTIAL_FRAME 0 SAVE_REST FIXUP_TOP_OF_STACK %r11 movq %rsp, %rcx @@ -735,7 +720,7 @@ END(stub_execve) ENTRY(stub_rt_sigreturn) CFI_STARTPROC addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 + PARTIAL_FRAME 0 SAVE_REST movq %rsp,%rdi FIXUP_TOP_OF_STACK %r11 @@ -766,8 +751,7 @@ vector=FIRST_EXTERNAL_VECTOR .if vector <> FIRST_EXTERNAL_VECTOR CFI_ADJUST_CFA_OFFSET -8 .endif -1: pushq $(~vector+0x80) /* Note: always in signed byte range */ - CFI_ADJUST_CFA_OFFSET 8 +1: pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */ .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 jmp 2f .endif @@ -796,8 +780,8 @@ END(interrupt) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func - subq $10*8, %rsp - CFI_ADJUST_CFA_OFFSET 10*8 + subq $ORIG_RAX-ARGOFFSET+8, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8 call save_args PARTIAL_FRAME 0 call \func @@ -822,6 +806,7 @@ ret_from_intr: TRACE_IRQS_OFF decl PER_CPU_VAR(irq_count) leaveq + CFI_RESTORE rbp CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET -8 exit_intr: @@ -903,11 +888,9 @@ retint_careful: jnc retint_signal TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - pushq %rdi - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rdi call schedule - popq %rdi - CFI_ADJUST_CFA_OFFSET -8 + popq_cfi %rdi GET_THREAD_INFO(%rcx) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -956,8 +939,7 @@ END(common_interrupt) .macro apicinterrupt num sym do_sym ENTRY(\sym) INTR_FRAME - pushq $~(\num) - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi $~(\num) interrupt \do_sym jmp ret_from_intr CFI_ENDPROC @@ -1023,9 +1005,9 @@ apicinterrupt ERROR_APIC_VECTOR \ apicinterrupt SPURIOUS_APIC_VECTOR \ spurious_interrupt smp_spurious_interrupt -#ifdef CONFIG_PERF_EVENTS -apicinterrupt LOCAL_PENDING_VECTOR \ - perf_pending_interrupt smp_perf_pending_interrupt +#ifdef CONFIG_IRQ_WORK +apicinterrupt IRQ_WORK_VECTOR \ + irq_work_interrupt smp_irq_work_interrupt #endif /* @@ -1036,8 +1018,8 @@ ENTRY(\sym) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $15*8,%rsp - CFI_ADJUST_CFA_OFFSET 15*8 + subq $ORIG_RAX-R15, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 call error_entry DEFAULT_FRAME 0 movq %rsp,%rdi /* pt_regs pointer */ @@ -1052,9 +1034,9 @@ END(\sym) ENTRY(\sym) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $-1 /* ORIG_RAX: no syscall to restart */ - CFI_ADJUST_CFA_OFFSET 8 - subq $15*8, %rsp + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + subq $ORIG_RAX-R15, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 call save_paranoid TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ @@ -1070,9 +1052,9 @@ END(\sym) ENTRY(\sym) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq $-1 /* ORIG_RAX: no syscall to restart */ - CFI_ADJUST_CFA_OFFSET 8 - subq $15*8, %rsp + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + subq $ORIG_RAX-R15, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 call save_paranoid TRACE_IRQS_OFF movq %rsp,%rdi /* pt_regs pointer */ @@ -1089,8 +1071,8 @@ END(\sym) ENTRY(\sym) XCPT_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - subq $15*8,%rsp - CFI_ADJUST_CFA_OFFSET 15*8 + subq $ORIG_RAX-R15, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 call error_entry DEFAULT_FRAME 0 movq %rsp,%rdi /* pt_regs pointer */ @@ -1107,8 +1089,8 @@ END(\sym) ENTRY(\sym) XCPT_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME - subq $15*8,%rsp - CFI_ADJUST_CFA_OFFSET 15*8 + subq $ORIG_RAX-R15, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 call save_paranoid DEFAULT_FRAME 0 TRACE_IRQS_OFF @@ -1139,16 +1121,14 @@ zeroentry simd_coprocessor_error do_simd_coprocessor_error /* edi: new selector */ ENTRY(native_load_gs_index) CFI_STARTPROC - pushf - CFI_ADJUST_CFA_OFFSET 8 + pushfq_cfi DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS gs_change: movl %edi,%gs 2: mfence /* workaround */ SWAPGS - popf - CFI_ADJUST_CFA_OFFSET -8 + popfq_cfi ret CFI_ENDPROC END(native_load_gs_index) @@ -1215,8 +1195,7 @@ END(kernel_execve) /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(call_softirq) CFI_STARTPROC - push %rbp - CFI_ADJUST_CFA_OFFSET 8 + pushq_cfi %rbp CFI_REL_OFFSET rbp,0 mov %rsp,%rbp CFI_DEF_CFA_REGISTER rbp @@ -1225,6 +1204,7 @@ ENTRY(call_softirq) push %rbp # backlink for old unwinder call __do_softirq leaveq + CFI_RESTORE rbp CFI_DEF_CFA_REGISTER rsp CFI_ADJUST_CFA_OFFSET -8 decl PER_CPU_VAR(irq_count) @@ -1368,7 +1348,7 @@ paranoidzeroentry machine_check *machine_check_vector(%rip) /* ebx: no swapgs flag */ ENTRY(paranoid_exit) - INTR_FRAME + DEFAULT_FRAME DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF testl %ebx,%ebx /* swapgs needed? */ @@ -1445,7 +1425,6 @@ error_swapgs: error_sti: TRACE_IRQS_OFF ret - CFI_ENDPROC /* * There are two places in the kernel that can potentially fault with @@ -1470,6 +1449,7 @@ bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) jmp error_swapgs + CFI_ENDPROC END(error_entry) @@ -1498,8 +1478,8 @@ ENTRY(nmi) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME pushq_cfi $-1 - subq $15*8, %rsp - CFI_ADJUST_CFA_OFFSET 15*8 + subq $ORIG_RAX-R15, %rsp + CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 call save_paranoid DEFAULT_FRAME 0 /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cd37469b54ee..3afb33f14d2d 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) return mod_code_status; } - - - -static unsigned char ftrace_nop[MCOUNT_INSN_SIZE]; - static unsigned char *ftrace_nop_replace(void) { - return ftrace_nop; + return ideal_nop5; } static int @@ -338,62 +333,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func) int __init ftrace_dyn_arch_init(void *data) { - extern const unsigned char ftrace_test_p6nop[]; - extern const unsigned char ftrace_test_nop5[]; - extern const unsigned char ftrace_test_jmp[]; - int faulted = 0; - - /* - * There is no good nop for all x86 archs. - * We will default to using the P6_NOP5, but first we - * will test to make sure that the nop will actually - * work on this CPU. If it faults, we will then - * go to a lesser efficient 5 byte nop. If that fails - * we then just use a jmp as our nop. This isn't the most - * efficient nop, but we can not use a multi part nop - * since we would then risk being preempted in the middle - * of that nop, and if we enabled tracing then, it might - * cause a system crash. - * - * TODO: check the cpuid to determine the best nop. - */ - asm volatile ( - "ftrace_test_jmp:" - "jmp ftrace_test_p6nop\n" - "nop\n" - "nop\n" - "nop\n" /* 2 byte jmp + 3 bytes */ - "ftrace_test_p6nop:" - P6_NOP5 - "jmp 1f\n" - "ftrace_test_nop5:" - ".byte 0x66,0x66,0x66,0x66,0x90\n" - "1:" - ".section .fixup, \"ax\"\n" - "2: movl $1, %0\n" - " jmp ftrace_test_nop5\n" - "3: movl $2, %0\n" - " jmp 1b\n" - ".previous\n" - _ASM_EXTABLE(ftrace_test_p6nop, 2b) - _ASM_EXTABLE(ftrace_test_nop5, 3b) - : "=r"(faulted) : "0" (faulted)); - - switch (faulted) { - case 0: - pr_info("converting mcount calls to 0f 1f 44 00 00\n"); - memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE); - break; - case 1: - pr_info("converting mcount calls to 66 66 66 66 90\n"); - memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE); - break; - case 2: - pr_info("converting mcount calls to jmp . + 5\n"); - memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE); - break; - } - /* The return code is retured via data */ *(unsigned long *)data = 0; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 351f9c0fea1f..7494999141b3 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -35,7 +35,6 @@ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ u8 hpet_msi_disable; -u8 hpet_readback_cmp; #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; @@ -395,23 +394,27 @@ static int hpet_next_event(unsigned long delta, * at that point and we would wait for the next hpet interrupt * forever. We found out that reading the CMP register back * forces the transfer so we can rely on the comparison with - * the counter register below. + * the counter register below. If the read back from the + * compare register does not match the value we programmed + * then we might have a real hardware problem. We can not do + * much about it here, but at least alert the user/admin with + * a prominent warning. * - * That works fine on those ATI chipsets, but on newer Intel - * chipsets (ICH9...) this triggers due to an erratum: Reading - * the comparator immediately following a write is returning - * the old value. + * An erratum on some chipsets (ICH9,..), results in + * comparator read immediately following a write returning old + * value. Workaround for this is to read this value second + * time, when first read returns old value. * - * We restrict the read back to the affected ATI chipsets (set - * by quirks) and also run it with hpet=verbose for debugging - * purposes. + * In fact the write to the comparator register is delayed up + * to two HPET cycles so the workaround we tried to restrict + * the readback to those known to be borked ATI chipsets + * failed miserably. So we give up on optimizations forever + * and penalize all HPET incarnations unconditionally. */ - if (hpet_readback_cmp || hpet_verbose) { - u32 cmp = hpet_readl(HPET_Tn_CMP(timer)); - - if (cmp != cnt) + if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) { + if (hpet_readl(HPET_Tn_CMP(timer)) != cnt) printk_once(KERN_WARNING - "hpet: compare register read back failed.\n"); + "hpet: compare register read back failed.\n"); } return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; @@ -503,7 +506,7 @@ static int hpet_assign_irq(struct hpet_dev *dev) { unsigned int irq; - irq = create_irq(); + irq = create_irq_nr(0, -1); if (!irq) return -EINVAL; diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a474ec37c32f..ff15c9dcc25d 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -206,11 +206,27 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { - /* Len */ - switch (x86_len) { - case X86_BREAKPOINT_LEN_X: + /* Type */ + switch (x86_type) { + case X86_BREAKPOINT_EXECUTE: + if (x86_len != X86_BREAKPOINT_LEN_X) + return -EINVAL; + + *gen_type = HW_BREAKPOINT_X; *gen_len = sizeof(long); + return 0; + case X86_BREAKPOINT_WRITE: + *gen_type = HW_BREAKPOINT_W; break; + case X86_BREAKPOINT_RW: + *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (x86_len) { case X86_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; @@ -229,21 +245,6 @@ int arch_bp_generic_fields(int x86_len, int x86_type, return -EINVAL; } - /* Type */ - switch (x86_type) { - case X86_BREAKPOINT_EXECUTE: - *gen_type = HW_BREAKPOINT_X; - break; - case X86_BREAKPOINT_WRITE: - *gen_type = HW_BREAKPOINT_W; - break; - case X86_BREAKPOINT_RW: - *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; - break; - default: - return -EINVAL; - } - return 0; } @@ -316,9 +317,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) ret = -EINVAL; switch (info->len) { - case X86_BREAKPOINT_LEN_X: - align = sizeof(long) -1; - break; case X86_BREAKPOINT_LEN_1: align = 0; break; diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index a46cb3522c0c..58bb239a2fd7 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -68,19 +68,22 @@ static void __cpuinit init_thread_xstate(void) */ if (!HAVE_HWFP) { + /* + * Disable xsave as we do not support it if i387 + * emulation is enabled. + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); xstate_size = sizeof(struct i387_soft_struct); return; } if (cpu_has_fxsr) xstate_size = sizeof(struct i387_fxsave_struct); -#ifdef CONFIG_X86_32 else xstate_size = sizeof(struct i387_fsave_struct); -#endif } -#ifdef CONFIG_X86_64 /* * Called at bootup to set up the initial FPU state that is later cloned * into all processes. @@ -88,12 +91,21 @@ static void __cpuinit init_thread_xstate(void) void __cpuinit fpu_init(void) { - unsigned long oldcr0 = read_cr0(); - - set_in_cr4(X86_CR4_OSFXSR); - set_in_cr4(X86_CR4_OSXMMEXCPT); + unsigned long cr0; + unsigned long cr4_mask = 0; - write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */ + if (cpu_has_fxsr) + cr4_mask |= X86_CR4_OSFXSR; + if (cpu_has_xmm) + cr4_mask |= X86_CR4_OSXMMEXCPT; + if (cr4_mask) + set_in_cr4(cr4_mask); + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ + if (!HAVE_HWFP) + cr0 |= X86_CR0_EM; + write_cr0(cr0); if (!smp_processor_id()) init_thread_xstate(); @@ -104,24 +116,12 @@ void __cpuinit fpu_init(void) clear_used_math(); } -#else /* CONFIG_X86_64 */ - -void __cpuinit fpu_init(void) -{ - if (!smp_processor_id()) - init_thread_xstate(); -} - -#endif /* CONFIG_X86_32 */ - void fpu_finit(struct fpu *fpu) { -#ifdef CONFIG_X86_32 if (!HAVE_HWFP) { finit_soft_fpu(&fpu->state->soft); return; } -#endif if (cpu_has_fxsr) { struct i387_fxsave_struct *fx = &fpu->state->fxsave; @@ -386,19 +386,17 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) #ifdef CONFIG_X86_64 env->fip = fxsave->rip; env->foo = fxsave->rdp; + /* + * should be actually ds/cs at fpu exception time, but + * that information is not available in 64bit mode. + */ + env->fcs = task_pt_regs(tsk)->cs; if (tsk == current) { - /* - * should be actually ds/cs at fpu exception time, but - * that information is not available in 64bit mode. - */ - asm("mov %%ds, %[fos]" : [fos] "=r" (env->fos)); - asm("mov %%cs, %[fcs]" : [fcs] "=r" (env->fcs)); + savesegment(ds, env->fos); } else { - struct pt_regs *regs = task_pt_regs(tsk); - - env->fos = 0xffff0000 | tsk->thread.ds; - env->fcs = regs->cs; + env->fos = tsk->thread.ds; } + env->fos |= 0xffff0000; #else env->fip = fxsave->fip; env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 91fd0c70a18a..44edb03fc9ec 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -67,10 +67,10 @@ static int show_other_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs); seq_printf(p, " Performance monitoring interrupts\n"); - seq_printf(p, "%*s: ", prec, "PND"); + seq_printf(p, "%*s: ", prec, "IWI"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs); - seq_printf(p, " Performance pending work\n"); + seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs); + seq_printf(p, " IRQ work interrupts\n"); #endif if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); @@ -185,7 +185,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_timer_irqs; sum += irq_stats(cpu)->irq_spurious_count; sum += irq_stats(cpu)->apic_perf_irqs; - sum += irq_stats(cpu)->apic_pending_irqs; + sum += irq_stats(cpu)->apic_irq_work_irqs; #endif if (x86_platform_ipi_callback) sum += irq_stats(cpu)->x86_platform_ipis; diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c new file mode 100644 index 000000000000..ca8f703a1e70 --- /dev/null +++ b/arch/x86/kernel/irq_work.c @@ -0,0 +1,30 @@ +/* + * x86 specific code for irq_work + * + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + */ + +#include <linux/kernel.h> +#include <linux/irq_work.h> +#include <linux/hardirq.h> +#include <asm/apic.h> + +void smp_irq_work_interrupt(struct pt_regs *regs) +{ + irq_enter(); + ack_APIC_irq(); + inc_irq_stat(apic_irq_work_irqs); + irq_work_run(); + irq_exit(); +} + +void arch_irq_work_raise(void) +{ +#ifdef CONFIG_X86_LOCAL_APIC + if (!cpu_has_apic) + return; + + apic->send_IPI_self(IRQ_WORK_VECTOR); + apic_wait_icr_idle(); +#endif +} diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 990ae7cfc578..713969b9266b 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -224,9 +224,9 @@ static void __init apic_intr_init(void) alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt); - /* Performance monitoring interrupts: */ -# ifdef CONFIG_PERF_EVENTS - alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt); + /* IRQ work interrupts: */ +# ifdef CONFIG_IRQ_WORK + alloc_intr_gate(IRQ_WORK_VECTOR, irq_work_interrupt); # endif #endif diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c new file mode 100644 index 000000000000..961b6b30ba90 --- /dev/null +++ b/arch/x86/kernel/jump_label.c @@ -0,0 +1,50 @@ +/* + * jump label x86 support + * + * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> + * + */ +#include <linux/jump_label.h> +#include <linux/memory.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/list.h> +#include <linux/jhash.h> +#include <linux/cpu.h> +#include <asm/kprobes.h> +#include <asm/alternative.h> + +#ifdef HAVE_JUMP_LABEL + +union jump_code_union { + char code[JUMP_LABEL_NOP_SIZE]; + struct { + char jump; + int offset; + } __attribute__((packed)); +}; + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + union jump_code_union code; + + if (type == JUMP_LABEL_ENABLE) { + code.jump = 0xe9; + code.offset = entry->target - + (entry->code + JUMP_LABEL_NOP_SIZE); + } else + memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE); + get_online_cpus(); + mutex_lock(&text_mutex); + text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + mutex_unlock(&text_mutex); + put_online_cpus(); +} + +void arch_jump_label_text_poke_early(jump_label_t addr) +{ + text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE); +} + +#endif diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 770ebfb349e9..1cbd54c0df99 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -230,9 +230,6 @@ static int recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) return 0; } -/* Dummy buffers for kallsyms_lookup */ -static char __dummy_buf[KSYM_NAME_LEN]; - /* Check if paddr is at an instruction boundary */ static int __kprobes can_probe(unsigned long paddr) { @@ -241,7 +238,7 @@ static int __kprobes can_probe(unsigned long paddr) struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; - if (!kallsyms_lookup(paddr, NULL, &offset, NULL, __dummy_buf)) + if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) return 0; /* Decode instructions */ @@ -1129,7 +1126,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, *(unsigned long *)addr = val; } -void __kprobes kprobes_optinsn_template_holder(void) +static void __used __kprobes kprobes_optinsn_template_holder(void) { asm volatile ( ".global optprobe_template_entry\n" @@ -1221,7 +1218,8 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether the address range is reserved */ if (ftrace_text_reserved(src, src + len - 1) || - alternatives_text_reserved(src, src + len - 1)) + alternatives_text_reserved(src, src + len - 1) || + jump_label_text_reserved(src, src + len - 1)) return -EBUSY; return len; @@ -1269,11 +1267,9 @@ static int __kprobes can_optimize(unsigned long paddr) unsigned long addr, size = 0, offset = 0; struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; - /* Dummy buffers for lookup_symbol_attrs */ - static char __dummy_buf[KSYM_NAME_LEN]; /* Lookup symbol including addr */ - if (!kallsyms_lookup(paddr, &size, &offset, NULL, __dummy_buf)) + if (!kallsyms_lookup_size_offset(paddr, &size, &offset)) return 0; /* Check there is enough space for a relative jump. */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 035c8c529181..b3ea9db39db6 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -36,7 +36,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd, if (!page) goto out; pud = (pud_t *)page_address(page); - memset(pud, 0, PAGE_SIZE); + clear_page(pud); set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); } pud = pud_offset(pgd, addr); @@ -45,7 +45,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd, if (!page) goto out; pmd = (pmd_t *)page_address(page); - memset(pmd, 0, PAGE_SIZE); + clear_page(pmd); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); } pmd = pmd_offset(pud, addr); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index e0bc186d7501..8f2956091735 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -239,11 +239,13 @@ int module_finalize(const Elf_Ehdr *hdr, apply_paravirt(pseg, pseg + para->sh_size); } - return module_bug_finalize(hdr, sechdrs, me); + /* make jump label nops */ + jump_label_apply_nops(me); + + return 0; } void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); - module_bug_cleanup(mod); } diff --git a/arch/x86/kernel/olpc-xo1.c b/arch/x86/kernel/olpc-xo1.c new file mode 100644 index 000000000000..f5442c03abc3 --- /dev/null +++ b/arch/x86/kernel/olpc-xo1.c @@ -0,0 +1,140 @@ +/* + * Support for features of the OLPC XO-1 laptop + * + * Copyright (C) 2010 One Laptop per Child + * Copyright (C) 2006 Red Hat, Inc. + * Copyright (C) 2006 Advanced Micro Devices, Inc. + * + * 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; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/platform_device.h> +#include <linux/pm.h> + +#include <asm/io.h> +#include <asm/olpc.h> + +#define DRV_NAME "olpc-xo1" + +#define PMS_BAR 4 +#define ACPI_BAR 5 + +/* PMC registers (PMS block) */ +#define PM_SCLK 0x10 +#define PM_IN_SLPCTL 0x20 +#define PM_WKXD 0x34 +#define PM_WKD 0x30 +#define PM_SSC 0x54 + +/* PM registers (ACPI block) */ +#define PM1_CNT 0x08 +#define PM_GPE0_STS 0x18 + +static unsigned long acpi_base; +static unsigned long pms_base; + +static void xo1_power_off(void) +{ + printk(KERN_INFO "OLPC XO-1 power off sequence...\n"); + + /* Enable all of these controls with 0 delay */ + outl(0x40000000, pms_base + PM_SCLK); + outl(0x40000000, pms_base + PM_IN_SLPCTL); + outl(0x40000000, pms_base + PM_WKXD); + outl(0x40000000, pms_base + PM_WKD); + + /* Clear status bits (possibly unnecessary) */ + outl(0x0002ffff, pms_base + PM_SSC); + outl(0xffffffff, acpi_base + PM_GPE0_STS); + + /* Write SLP_EN bit to start the machinery */ + outl(0x00002000, acpi_base + PM1_CNT); +} + +/* Read the base addresses from the PCI BAR info */ +static int __devinit setup_bases(struct pci_dev *pdev) +{ + int r; + + r = pci_enable_device_io(pdev); + if (r) { + dev_err(&pdev->dev, "can't enable device IO\n"); + return r; + } + + r = pci_request_region(pdev, ACPI_BAR, DRV_NAME); + if (r) { + dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", ACPI_BAR); + return r; + } + + r = pci_request_region(pdev, PMS_BAR, DRV_NAME); + if (r) { + dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", PMS_BAR); + pci_release_region(pdev, ACPI_BAR); + return r; + } + + acpi_base = pci_resource_start(pdev, ACPI_BAR); + pms_base = pci_resource_start(pdev, PMS_BAR); + + return 0; +} + +static int __devinit olpc_xo1_probe(struct platform_device *pdev) +{ + struct pci_dev *pcidev; + int r; + + pcidev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, + NULL); + if (!pdev) + return -ENODEV; + + r = setup_bases(pcidev); + if (r) + return r; + + pm_power_off = xo1_power_off; + + printk(KERN_INFO "OLPC XO-1 support registered\n"); + return 0; +} + +static int __devexit olpc_xo1_remove(struct platform_device *pdev) +{ + pm_power_off = NULL; + return 0; +} + +static struct platform_driver olpc_xo1_driver = { + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, + }, + .probe = olpc_xo1_probe, + .remove = __devexit_p(olpc_xo1_remove), +}; + +static int __init olpc_xo1_init(void) +{ + return platform_driver_register(&olpc_xo1_driver); +} + +static void __exit olpc_xo1_exit(void) +{ + platform_driver_unregister(&olpc_xo1_driver); +} + +MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:olpc-xo1"); + +module_init(olpc_xo1_init); +module_exit(olpc_xo1_exit); diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c index 0e0cdde519be..edaf3fe8dc5e 100644 --- a/arch/x86/kernel/olpc.c +++ b/arch/x86/kernel/olpc.c @@ -17,6 +17,7 @@ #include <linux/spinlock.h> #include <linux/io.h> #include <linux/string.h> +#include <linux/platform_device.h> #include <asm/geode.h> #include <asm/setup.h> @@ -114,6 +115,7 @@ int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen, unsigned long flags; int ret = -EIO; int i; + int restarts = 0; spin_lock_irqsave(&ec_lock, flags); @@ -169,7 +171,9 @@ restart: if (wait_on_obf(0x6c, 1)) { printk(KERN_ERR "olpc-ec: timeout waiting for" " EC to provide data!\n"); - goto restart; + if (restarts++ < 10) + goto restart; + goto err; } outbuf[i] = inb(0x68); pr_devel("olpc-ec: received 0x%x\n", outbuf[i]); @@ -183,8 +187,21 @@ err: } EXPORT_SYMBOL_GPL(olpc_ec_cmd); -#ifdef CONFIG_OLPC_OPENFIRMWARE -static void __init platform_detect(void) +static bool __init check_ofw_architecture(void) +{ + size_t propsize; + char olpc_arch[5]; + const void *args[] = { NULL, "architecture", olpc_arch, (void *)5 }; + void *res[] = { &propsize }; + + if (olpc_ofw("getprop", args, res)) { + printk(KERN_ERR "ofw: getprop call failed!\n"); + return false; + } + return propsize == 5 && strncmp("OLPC", olpc_arch, 5) == 0; +} + +static u32 __init get_board_revision(void) { size_t propsize; __be32 rev; @@ -193,45 +210,43 @@ static void __init platform_detect(void) if (olpc_ofw("getprop", args, res) || propsize != 4) { printk(KERN_ERR "ofw: getprop call failed!\n"); - rev = cpu_to_be32(0); + return cpu_to_be32(0); } - olpc_platform_info.boardrev = be32_to_cpu(rev); + return be32_to_cpu(rev); } -#else -static void __init platform_detect(void) + +static bool __init platform_detect(void) { - /* stopgap until OFW support is added to the kernel */ - olpc_platform_info.boardrev = olpc_board(0xc2); + if (!check_ofw_architecture()) + return false; + olpc_platform_info.flags |= OLPC_F_PRESENT; + olpc_platform_info.boardrev = get_board_revision(); + return true; } -#endif -static int __init olpc_init(void) +static int __init add_xo1_platform_devices(void) { - unsigned char *romsig; + struct platform_device *pdev; - /* The ioremap check is dangerous; limit what we run it on */ - if (!is_geode() || cs5535_has_vsa2()) - return 0; + pdev = platform_device_register_simple("xo1-rfkill", -1, NULL, 0); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); - spin_lock_init(&ec_lock); + pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0); + if (IS_ERR(pdev)) + return PTR_ERR(pdev); - romsig = ioremap(0xffffffc0, 16); - if (!romsig) - return 0; + return 0; +} - if (strncmp(romsig, "CL1 Q", 7)) - goto unmap; - if (strncmp(romsig+6, romsig+13, 3)) { - printk(KERN_INFO "OLPC BIOS signature looks invalid. " - "Assuming not OLPC\n"); - goto unmap; - } +static int __init olpc_init(void) +{ + int r = 0; - printk(KERN_INFO "OLPC board with OpenFirmware %.16s\n", romsig); - olpc_platform_info.flags |= OLPC_F_PRESENT; + if (!olpc_ofw_present() || !platform_detect()) + return 0; - /* get the platform revision */ - platform_detect(); + spin_lock_init(&ec_lock); /* assume B1 and above models always have a DCON */ if (olpc_board_at_least(olpc_board(0xb1))) @@ -242,8 +257,10 @@ static int __init olpc_init(void) (unsigned char *) &olpc_platform_info.ecver, 1); #ifdef CONFIG_PCI_OLPC - /* If the VSA exists let it emulate PCI, if not emulate in kernel */ - if (!cs5535_has_vsa2()) + /* If the VSA exists let it emulate PCI, if not emulate in kernel. + * XO-1 only. */ + if (olpc_platform_info.boardrev < olpc_board_pre(0xd0) && + !cs5535_has_vsa2()) x86_init.pci.arch_init = pci_olpc_init; #endif @@ -252,8 +269,12 @@ static int __init olpc_init(void) olpc_platform_info.boardrev >> 4, olpc_platform_info.ecver); -unmap: - iounmap(romsig); + if (olpc_platform_info.boardrev < olpc_board_pre(0xd0)) { /* XO-1 */ + r = add_xo1_platform_devices(); + if (r) + return r; + } + return 0; } diff --git a/arch/x86/kernel/olpc_ofw.c b/arch/x86/kernel/olpc_ofw.c index 3218aa71ab5e..787320464379 100644 --- a/arch/x86/kernel/olpc_ofw.c +++ b/arch/x86/kernel/olpc_ofw.c @@ -74,6 +74,12 @@ int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res, } EXPORT_SYMBOL_GPL(__olpc_ofw); +bool olpc_ofw_present(void) +{ + return olpc_ofw_cif != NULL; +} +EXPORT_SYMBOL_GPL(olpc_ofw_present); + /* OFW cif _should_ be above this address */ #define OFW_MIN 0xff000000 diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 0f7f130caa67..c562207b1b3d 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -39,7 +39,7 @@ #include <asm/cacheflush.h> #include <asm/swiotlb.h> #include <asm/dma.h> -#include <asm/k8.h> +#include <asm/amd_nb.h> #include <asm/x86_init.h> static unsigned long iommu_bus_base; /* GART remapping area (physical) */ @@ -560,8 +560,11 @@ static void enable_gart_translations(void) { int i; - for (i = 0; i < num_k8_northbridges; i++) { - struct pci_dev *dev = k8_northbridges[i]; + if (!k8_northbridges.gart_supported) + return; + + for (i = 0; i < k8_northbridges.num; i++) { + struct pci_dev *dev = k8_northbridges.nb_misc[i]; enable_gart_translation(dev, __pa(agp_gatt_table)); } @@ -592,16 +595,19 @@ static void gart_fixup_northbridges(struct sys_device *dev) if (!fix_up_north_bridges) return; + if (!k8_northbridges.gart_supported) + return; + pr_info("PCI-DMA: Restoring GART aperture settings\n"); - for (i = 0; i < num_k8_northbridges; i++) { - struct pci_dev *dev = k8_northbridges[i]; + for (i = 0; i < k8_northbridges.num; i++) { + struct pci_dev *dev = k8_northbridges.nb_misc[i]; /* * Don't enable translations just yet. That is the next * step. Restore the pre-suspend aperture settings. */ - pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, aperture_order << 1); + gart_set_size_and_enable(dev, aperture_order); pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, aperture_alloc >> 25); } } @@ -649,8 +655,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info) aper_size = aper_base = info->aper_size = 0; dev = NULL; - for (i = 0; i < num_k8_northbridges; i++) { - dev = k8_northbridges[i]; + for (i = 0; i < k8_northbridges.num; i++) { + dev = k8_northbridges.nb_misc[i]; new_aper_base = read_aperture(dev, &new_aper_size); if (!new_aper_base) goto nommu; @@ -718,10 +724,13 @@ static void gart_iommu_shutdown(void) if (!no_agp) return; - for (i = 0; i < num_k8_northbridges; i++) { + if (!k8_northbridges.gart_supported) + return; + + for (i = 0; i < k8_northbridges.num; i++) { u32 ctl; - dev = k8_northbridges[i]; + dev = k8_northbridges.nb_misc[i]; pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); ctl &= ~GARTEN; @@ -739,7 +748,7 @@ int __init gart_iommu_init(void) unsigned long scratch; long i; - if (num_k8_northbridges == 0) + if (!k8_northbridges.gart_supported) return 0; #ifndef CONFIG_AGP_AMD64 diff --git a/arch/x86/kernel/pmtimer_64.c b/arch/x86/kernel/pmtimer_64.c deleted file mode 100644 index b112406f1996..000000000000 --- a/arch/x86/kernel/pmtimer_64.c +++ /dev/null @@ -1,69 +0,0 @@ -/* Ported over from i386 by AK, original copyright was: - * - * (C) Dominik Brodowski <linux@brodo.de> 2003 - * - * Driver to use the Power Management Timer (PMTMR) available in some - * southbridges as primary timing source for the Linux kernel. - * - * Based on parts of linux/drivers/acpi/hardware/hwtimer.c, timer_pit.c, - * timer_hpet.c, and on Arjan van de Ven's implementation for 2.4. - * - * This file is licensed under the GPL v2. - * - * Dropped all the hardware bug workarounds for now. Hopefully they - * are not needed on 64bit chipsets. - */ - -#include <linux/jiffies.h> -#include <linux/kernel.h> -#include <linux/time.h> -#include <linux/init.h> -#include <linux/cpumask.h> -#include <linux/acpi_pmtmr.h> - -#include <asm/io.h> -#include <asm/proto.h> -#include <asm/msr.h> -#include <asm/vsyscall.h> - -static inline u32 cyc2us(u32 cycles) -{ - /* The Power Management Timer ticks at 3.579545 ticks per microsecond. - * 1 / PM_TIMER_FREQUENCY == 0.27936511 =~ 286/1024 [error: 0.024%] - * - * Even with HZ = 100, delta is at maximum 35796 ticks, so it can - * easily be multiplied with 286 (=0x11E) without having to fear - * u32 overflows. - */ - cycles *= 286; - return (cycles >> 10); -} - -static unsigned pmtimer_wait_tick(void) -{ - u32 a, b; - for (a = b = inl(pmtmr_ioport) & ACPI_PM_MASK; - a == b; - b = inl(pmtmr_ioport) & ACPI_PM_MASK) - cpu_relax(); - return b; -} - -/* note: wait time is rounded up to one tick */ -void pmtimer_wait(unsigned us) -{ - u32 a, b; - a = pmtimer_wait_tick(); - do { - b = inl(pmtmr_ioport); - cpu_relax(); - } while (cyc2us(b - a) < us); -} - -static int __init nopmtimer_setup(char *s) -{ - pmtmr_ioport = 0; - return 1; -} - -__setup("nopmtimer", nopmtimer_setup); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3d9ea531ddd1..b3d7a3a04f38 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -424,7 +424,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) load_TLS(next, cpu); /* Must be after DS reload */ - unlazy_fpu(prev_p); + __unlazy_fpu(prev_p); /* Make sure cpu is ready for new context */ if (preload_fpu) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index e3af342fe83a..7a4cf14223ba 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -84,7 +84,7 @@ static int __init reboot_setup(char *str) } /* we will leave sorting out the final value when we are ready to reboot, since we might not - have set up boot_cpu_id or smp_num_cpu */ + have detected BSP APIC ID or smp_num_cpu */ break; #endif /* CONFIG_SMP */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index feb4c21e499a..a59f6a6df5e2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -106,11 +106,12 @@ #include <asm/percpu.h> #include <asm/topology.h> #include <asm/apicdef.h> -#include <asm/k8.h> +#include <asm/amd_nb.h> #ifdef CONFIG_X86_64 #include <asm/numa_64.h> #endif #include <asm/mce.h> +#include <asm/alternative.h> /* * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries. @@ -124,7 +125,6 @@ unsigned long max_pfn_mapped; RESERVE_BRK(dmi_alloc, 65536); #endif -unsigned int boot_cpu_id __read_mostly; static __initdata unsigned long _brk_start = (unsigned long)__brk_base; unsigned long _brk_end = (unsigned long)__brk_base; @@ -617,79 +617,7 @@ static __init void reserve_ibft_region(void) reserve_early_overlap_ok(addr, addr + size, "ibft"); } -#ifdef CONFIG_X86_RESERVE_LOW_64K -static int __init dmi_low_memory_corruption(const struct dmi_system_id *d) -{ - printk(KERN_NOTICE - "%s detected: BIOS may corrupt low RAM, working around it.\n", - d->ident); - - e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED); - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - - return 0; -} -#endif - -/* List of systems that have known low memory corruption BIOS problems */ -static struct dmi_system_id __initdata bad_bios_dmi_table[] = { -#ifdef CONFIG_X86_RESERVE_LOW_64K - { - .callback = dmi_low_memory_corruption, - .ident = "AMI BIOS", - .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), - }, - }, - { - .callback = dmi_low_memory_corruption, - .ident = "Phoenix BIOS", - .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"), - }, - }, - { - .callback = dmi_low_memory_corruption, - .ident = "Phoenix/MSC BIOS", - .matches = { - DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"), - }, - }, - /* - * AMI BIOS with low memory corruption was found on Intel DG45ID and - * DG45FC boards. - * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will - * match only DMI_BOARD_NAME and see if there is more bad products - * with this vendor. - */ - { - .callback = dmi_low_memory_corruption, - .ident = "AMI BIOS", - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "DG45ID"), - }, - }, - { - .callback = dmi_low_memory_corruption, - .ident = "AMI BIOS", - .matches = { - DMI_MATCH(DMI_BOARD_NAME, "DG45FC"), - }, - }, - /* - * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so - * match on the product name. - */ - { - .callback = dmi_low_memory_corruption, - .ident = "Phoenix BIOS", - .matches = { - DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"), - }, - }, -#endif - {} -}; +static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; static void __init trim_bios_range(void) { @@ -697,8 +625,14 @@ static void __init trim_bios_range(void) * A special case is the first 4Kb of memory; * This is a BIOS owned area, not kernel ram, but generally * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. */ - e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED); + e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE), + E820_RAM, E820_RESERVED); + /* * special case: Some BIOSen report the PC BIOS * area (640->1Mb) as ram even though it is not. @@ -708,6 +642,28 @@ static void __init trim_bios_range(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } +static int __init parse_reservelow(char *p) +{ + unsigned long long size; + + if (!p) + return -EINVAL; + + size = memparse(p, &p); + + if (size < 4096) + size = 4096; + + if (size > 640*1024) + size = 640*1024; + + reserve_low = size; + + return 0; +} + +early_param("reservelow", parse_reservelow); + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -725,6 +681,7 @@ void __init setup_arch(char **cmdline_p) { int acpi = 0; int k8 = 0; + unsigned long flags; #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); @@ -859,8 +816,6 @@ void __init setup_arch(char **cmdline_p) dmi_scan_machine(); - dmi_check_system(bad_bios_dmi_table); - /* * VMware detection requires dmi to be available, so this * needs to be done after dmi_scan_machine, for the BP. @@ -1067,6 +1022,10 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.banner(); mcheck_init(); + + local_irq_save(flags); + arch_init_ideal_nop5(); + local_irq_restore(flags); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index a60df9ae6454..2335c15c93a4 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -253,7 +253,7 @@ void __init setup_per_cpu_areas(void) * Up to this point, the boot CPU has been using .init.data * area. Reload any changed state for the boot CPU. */ - if (cpu == boot_cpu_id) + if (!cpu) switch_to_new_gdt(cpu); } diff --git a/arch/x86/kernel/sfi.c b/arch/x86/kernel/sfi.c index cb22acf3ed09..dd4c281ffe57 100644 --- a/arch/x86/kernel/sfi.c +++ b/arch/x86/kernel/sfi.c @@ -34,7 +34,7 @@ #ifdef CONFIG_X86_LOCAL_APIC static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; -void __init mp_sfi_register_lapic_address(unsigned long address) +static void __init mp_sfi_register_lapic_address(unsigned long address) { mp_lapic_addr = address; @@ -46,7 +46,7 @@ void __init mp_sfi_register_lapic_address(unsigned long address) } /* All CPUs enumerated by SFI must be present and enabled */ -void __cpuinit mp_sfi_register_lapic(u8 id) +static void __cpuinit mp_sfi_register_lapic(u8 id) { if (MAX_APICS - id <= 0) { pr_warning("Processor #%d invalid (max %d)\n", diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 63a1a5596ac0..a3df9f830037 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -62,6 +62,7 @@ #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> +#include <asm/mwait.h> #include <asm/apic.h> #include <asm/setup.h> #include <asm/uv/uv.h> @@ -395,6 +396,19 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } +static void __cpuinit link_thread_siblings(int cpu1, int cpu2) +{ + struct cpuinfo_x86 *c1 = &cpu_data(cpu1); + struct cpuinfo_x86 *c2 = &cpu_data(cpu2); + + cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); + cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1)); + cpumask_set_cpu(cpu1, cpu_core_mask(cpu2)); + cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); + cpumask_set_cpu(cpu1, c2->llc_shared_map); + cpumask_set_cpu(cpu2, c1->llc_shared_map); +} + void __cpuinit set_cpu_sibling_map(int cpu) { @@ -407,14 +421,13 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { struct cpuinfo_x86 *o = &cpu_data(i); - if (c->phys_proc_id == o->phys_proc_id && - c->cpu_core_id == o->cpu_core_id) { - cpumask_set_cpu(i, cpu_sibling_mask(cpu)); - cpumask_set_cpu(cpu, cpu_sibling_mask(i)); - cpumask_set_cpu(i, cpu_core_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(i)); - cpumask_set_cpu(i, c->llc_shared_map); - cpumask_set_cpu(cpu, o->llc_shared_map); + if (cpu_has(c, X86_FEATURE_TOPOEXT)) { + if (c->phys_proc_id == o->phys_proc_id && + c->compute_unit_id == o->compute_unit_id) + link_thread_siblings(cpu, i); + } else if (c->phys_proc_id == o->phys_proc_id && + c->cpu_core_id == o->cpu_core_id) { + link_thread_siblings(cpu, i); } } } else { @@ -1381,11 +1394,88 @@ void play_dead_common(void) local_irq_disable(); } +/* + * We need to flush the caches before going to sleep, lest we have + * dirty data in our caches when we come back up. + */ +static inline void mwait_play_dead(void) +{ + unsigned int eax, ebx, ecx, edx; + unsigned int highest_cstate = 0; + unsigned int highest_subcstate = 0; + int i; + void *mwait_ptr; + + if (!cpu_has(¤t_cpu_data, X86_FEATURE_MWAIT)) + return; + if (!cpu_has(¤t_cpu_data, X86_FEATURE_CLFLSH)) + return; + if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) + return; + + eax = CPUID_MWAIT_LEAF; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + + /* + * eax will be 0 if EDX enumeration is not valid. + * Initialized below to cstate, sub_cstate value when EDX is valid. + */ + if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) { + eax = 0; + } else { + edx >>= MWAIT_SUBSTATE_SIZE; + for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) { + if (edx & MWAIT_SUBSTATE_MASK) { + highest_cstate = i; + highest_subcstate = edx & MWAIT_SUBSTATE_MASK; + } + } + eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) | + (highest_subcstate - 1); + } + + /* + * This should be a memory location in a cache line which is + * unlikely to be touched by other processors. The actual + * content is immaterial as it is not actually modified in any way. + */ + mwait_ptr = ¤t_thread_info()->flags; + + wbinvd(); + + while (1) { + /* + * The CLFLUSH is a workaround for erratum AAI65 for + * the Xeon 7400 series. It's not clear it is actually + * needed, but it should be harmless in either case. + * The WBINVD is insufficient due to the spurious-wakeup + * case where we return around the loop. + */ + clflush(mwait_ptr); + __monitor(mwait_ptr, 0, 0); + mb(); + __mwait(eax, 0); + } +} + +static inline void hlt_play_dead(void) +{ + if (current_cpu_data.x86 >= 4) + wbinvd(); + + while (1) { + native_halt(); + } +} + void native_play_dead(void) { play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); - wbinvd_halt(); + + mwait_play_dead(); /* Only returns on failure */ + hlt_play_dead(); } #else /* ... !CONFIG_HOTPLUG_CPU */ diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index d5e06624e34a..0b0cb5fede19 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -33,8 +33,8 @@ int kernel_execve(const char *filename, const char *const envp[]) { long __res; - asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx" + asm volatile ("int $0x80" : "=a" (__res) - : "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory"); + : "0" (__NR_execve), "b" (filename), "c" (argv), "d" (envp) : "memory"); return __res; } diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index a874495b3673..e2a595257390 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -45,8 +45,7 @@ void __init setup_trampoline_page_table(void) /* Copy kernel address range */ clone_pgd_range(trampoline_pg_dir + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, - min_t(unsigned long, KERNEL_PGD_PTRS, - KERNEL_PGD_BOUNDARY)); + KERNEL_PGD_PTRS); /* Initialize low mappings */ clone_pgd_range(trampoline_pg_dir, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 60788dee0f8a..d43968503dd2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -776,21 +776,10 @@ asmlinkage void math_state_restore(void) } EXPORT_SYMBOL_GPL(math_state_restore); -#ifndef CONFIG_MATH_EMULATION -void math_emulate(struct math_emu_info *info) -{ - printk(KERN_EMERG - "math-emulation not enabled and no coprocessor found.\n"); - printk(KERN_EMERG "killing %s.\n", current->comm); - force_sig(SIGFPE, current); - schedule(); -} -#endif /* CONFIG_MATH_EMULATION */ - dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_X86_32 +#ifdef CONFIG_MATH_EMULATION if (read_cr0() & X86_CR0_EM) { struct math_emu_info info = { }; @@ -798,12 +787,12 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - } else { - math_state_restore(); /* interrupts still off */ - conditional_sti(regs); + return; } -#else - math_state_restore(); +#endif + math_state_restore(); /* interrupts still off */ +#ifdef CONFIG_X86_32 + conditional_sti(regs); #endif } @@ -881,18 +870,6 @@ void __init trap_init(void) #endif #ifdef CONFIG_X86_32 - if (cpu_has_fxsr) { - printk(KERN_INFO "Enabling fast FPU save and restore... "); - set_in_cr4(X86_CR4_OSFXSR); - printk("done.\n"); - } - if (cpu_has_xmm) { - printk(KERN_INFO - "Enabling unmasked SIMD FPU exception support... "); - set_in_cr4(X86_CR4_OSXMMEXCPT); - printk("done.\n"); - } - set_system_trap_gate(SYSCALL_VECTOR, &system_call); set_bit(SYSCALL_VECTOR, used_vectors); #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ce8e50239332..0c40d8b72416 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -104,10 +104,14 @@ int __init notsc_setup(char *str) __setup("notsc", notsc_setup); +static int no_sched_irq_time; + static int __init tsc_setup(char *str) { if (!strcmp(str, "reliable")) tsc_clocksource_reliable = 1; + if (!strncmp(str, "noirqtime", 9)) + no_sched_irq_time = 1; return 1; } @@ -626,6 +630,44 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) local_irq_restore(flags); } +static unsigned long long cyc2ns_suspend; + +void save_sched_clock_state(void) +{ + if (!sched_clock_stable) + return; + + cyc2ns_suspend = sched_clock(); +} + +/* + * Even on processors with invariant TSC, TSC gets reset in some the + * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to + * arbitrary value (still sync'd across cpu's) during resume from such sleep + * states. To cope up with this, recompute the cyc2ns_offset for each cpu so + * that sched_clock() continues from the point where it was left off during + * suspend. + */ +void restore_sched_clock_state(void) +{ + unsigned long long offset; + unsigned long flags; + int cpu; + + if (!sched_clock_stable) + return; + + local_irq_save(flags); + + __get_cpu_var(cyc2ns_offset) = 0; + offset = cyc2ns_suspend - sched_clock(); + + for_each_possible_cpu(cpu) + per_cpu(cyc2ns_offset, cpu) = offset; + + local_irq_restore(flags); +} + #ifdef CONFIG_CPU_FREQ /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency @@ -763,6 +805,7 @@ void mark_tsc_unstable(char *reason) if (!tsc_unstable) { tsc_unstable = 1; sched_clock_stable = 0; + disable_sched_clock_irqtime(); printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) @@ -854,60 +897,6 @@ static void __init init_tsc_clocksource(void) clocksource_register_khz(&clocksource_tsc, tsc_khz); } -#ifdef CONFIG_X86_64 -/* - * calibrate_cpu is used on systems with fixed rate TSCs to determine - * processor frequency - */ -#define TICK_COUNT 100000000 -static unsigned long __init calibrate_cpu(void) -{ - int tsc_start, tsc_now; - int i, no_ctr_free; - unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0; - unsigned long flags; - - for (i = 0; i < 4; i++) - if (avail_to_resrv_perfctr_nmi_bit(i)) - break; - no_ctr_free = (i == 4); - if (no_ctr_free) { - WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... " - "cpu_khz value may be incorrect.\n"); - i = 3; - rdmsrl(MSR_K7_EVNTSEL3, evntsel3); - wrmsrl(MSR_K7_EVNTSEL3, 0); - rdmsrl(MSR_K7_PERFCTR3, pmc3); - } else { - reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i); - reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } - local_irq_save(flags); - /* start measuring cycles, incrementing from 0 */ - wrmsrl(MSR_K7_PERFCTR0 + i, 0); - wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76); - rdtscl(tsc_start); - do { - rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now); - tsc_now = get_cycles(); - } while ((tsc_now - tsc_start) < TICK_COUNT); - - local_irq_restore(flags); - if (no_ctr_free) { - wrmsrl(MSR_K7_EVNTSEL3, 0); - wrmsrl(MSR_K7_PERFCTR3, pmc3); - wrmsrl(MSR_K7_EVNTSEL3, evntsel3); - } else { - release_perfctr_nmi(MSR_K7_PERFCTR0 + i); - release_evntsel_nmi(MSR_K7_EVNTSEL0 + i); - } - - return pmc_now * tsc_khz / (tsc_now - tsc_start); -} -#else -static inline unsigned long calibrate_cpu(void) { return cpu_khz; } -#endif - void __init tsc_init(void) { u64 lpj; @@ -926,10 +915,6 @@ void __init tsc_init(void) return; } - if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) && - (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)) - cpu_khz = calibrate_cpu(); - printk("Detected %lu.%03lu MHz processor.\n", (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); @@ -949,6 +934,9 @@ void __init tsc_init(void) /* now allow native_sched_clock() to use rdtsc */ tsc_disabled = 0; + if (!no_sched_irq_time) + enable_sched_clock_irqtime(); + lpj = ((u64)tsc_khz * 1000); do_div(lpj, HZ); lpj_fine = lpj; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b38bd8b92aa6..66ca98aafdd6 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1870,17 +1870,16 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - u64 old = c->dst.orig_val; + u64 old = c->dst.orig_val64; if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) || ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) { - c->regs[VCPU_REGS_RAX] = (u32) (old >> 0); c->regs[VCPU_REGS_RDX] = (u32) (old >> 32); ctxt->eflags &= ~EFLG_ZF; } else { - c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) | - (u32) c->regs[VCPU_REGS_RBX]; + c->dst.val64 = ((u64)c->regs[VCPU_REGS_RCX] << 32) | + (u32) c->regs[VCPU_REGS_RBX]; ctxt->eflags |= EFLG_ZF; } @@ -2616,7 +2615,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) c->src.valptr, c->src.bytes); if (rc != X86EMUL_CONTINUE) goto done; - c->src.orig_val = c->src.val; + c->src.orig_val64 = c->src.val64; } if (c->src2.type == OP_MEM) { diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 8d10c063d7f2..4b7b73ce2098 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -64,6 +64,9 @@ static void pic_unlock(struct kvm_pic *s) if (!found) found = s->kvm->bsp_vcpu; + if (!found) + return; + kvm_vcpu_kick(found); } } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index ffed06871c5c..63c314502993 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -43,7 +43,6 @@ struct kvm_kpic_state { u8 irr; /* interrupt request register */ u8 imr; /* interrupt mask register */ u8 isr; /* interrupt service register */ - u8 isr_ack; /* interrupt ack detection */ u8 priority_add; /* highest irq priority */ u8 irq_base; u8 read_reg_select; @@ -56,6 +55,7 @@ struct kvm_kpic_state { u8 init4; /* true if 4 byte init */ u8 elcr; /* PIIX edge/trigger selection */ u8 elcr_mask; + u8 isr_ack; /* interrupt ack detection */ struct kvm_pic *pics_state; }; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 77d8c0f4817d..22b06f7660f4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1056,14 +1056,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) vcpu->arch.apic = apic; - apic->regs_page = alloc_page(GFP_KERNEL); + apic->regs_page = alloc_page(GFP_KERNEL|__GFP_ZERO); if (apic->regs_page == NULL) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); goto nomem_free_apic; } apic->regs = page_address(apic->regs_page); - memset(apic->regs, 0, PAGE_SIZE); apic->vcpu = vcpu; hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index bc5b9b8d4a33..8a3f9f64f86f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -766,7 +766,6 @@ static void init_vmcb(struct vcpu_svm *svm) control->iopm_base_pa = iopm_base; control->msrpm_base_pa = __pa(svm->msrpm); - control->tsc_offset = 0; control->int_ctl = V_INTR_MASKING_MASK; init_seg(&save->es); @@ -902,6 +901,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; init_vmcb(svm); + svm->vmcb->control.tsc_offset = 0-native_read_tsc(); err = fx_init(&svm->vcpu); if (err) @@ -3163,8 +3163,8 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) sync_lapic_to_cr8(vcpu); save_host_msrs(vcpu); - fs_selector = kvm_read_fs(); - gs_selector = kvm_read_gs(); + savesegment(fs, fs_selector); + savesegment(gs, gs_selector); ldt_selector = kvm_read_ldt(); svm->vmcb->save.cr2 = vcpu->arch.cr2; /* required for live migration with NPT */ @@ -3251,10 +3251,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - kvm_load_fs(fs_selector); - kvm_load_gs(gs_selector); - kvm_load_ldt(ldt_selector); load_host_msrs(vcpu); + loadsegment(fs, fs_selector); +#ifdef CONFIG_X86_64 + load_gs_index(gs_selector); + wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); +#else + loadsegment(gs, gs_selector); +#endif + kvm_load_ldt(ldt_selector); reload_tss(vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 49b25eee25ac..7bddfab12013 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -803,7 +803,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) */ vmx->host_state.ldt_sel = kvm_read_ldt(); vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; - vmx->host_state.fs_sel = kvm_read_fs(); + savesegment(fs, vmx->host_state.fs_sel); if (!(vmx->host_state.fs_sel & 7)) { vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); vmx->host_state.fs_reload_needed = 0; @@ -811,7 +811,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) vmcs_write16(HOST_FS_SELECTOR, 0); vmx->host_state.fs_reload_needed = 1; } - vmx->host_state.gs_sel = kvm_read_gs(); + savesegment(gs, vmx->host_state.gs_sel); if (!(vmx->host_state.gs_sel & 7)) vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel); else { @@ -841,27 +841,21 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) static void __vmx_load_host_state(struct vcpu_vmx *vmx) { - unsigned long flags; - if (!vmx->host_state.loaded) return; ++vmx->vcpu.stat.host_state_reload; vmx->host_state.loaded = 0; if (vmx->host_state.fs_reload_needed) - kvm_load_fs(vmx->host_state.fs_sel); + loadsegment(fs, vmx->host_state.fs_sel); if (vmx->host_state.gs_ldt_reload_needed) { kvm_load_ldt(vmx->host_state.ldt_sel); - /* - * If we have to reload gs, we must take care to - * preserve our gs base. - */ - local_irq_save(flags); - kvm_load_gs(vmx->host_state.gs_sel); #ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE)); + load_gs_index(vmx->host_state.gs_sel); + wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); +#else + loadsegment(gs, vmx->host_state.gs_sel); #endif - local_irq_restore(flags); } reload_tss(); #ifdef CONFIG_X86_64 @@ -2589,8 +2583,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_FS_SELECTOR, kvm_read_fs()); /* 22.2.4 */ - vmcs_write16(HOST_GS_SELECTOR, kvm_read_gs()); /* 22.2.4 */ + vmcs_write16(HOST_FS_SELECTOR, 0); /* 22.2.4 */ + vmcs_write16(HOST_GS_SELECTOR, 0); /* 22.2.4 */ vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ #ifdef CONFIG_X86_64 rdmsrl(MSR_FS_BASE, a); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3a09c625d526..6c2ecf0a806d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1991,13 +1991,14 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | 0 /* Reserved, DCA */ | F(XMM4_1) | F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX); + 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | + F(F16C); /* cpuid 0x80000001.ecx */ const u32 kvm_supported_word6_x86_features = F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ | F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) | - 0 /* SKINIT */ | 0 /* WDT */; + F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 9257510b4836..9d5f55848455 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -324,9 +324,8 @@ static void lguest_load_gdt(const struct desc_ptr *desc) } /* - * For a single GDT entry which changes, we do the lazy thing: alter our GDT, - * then tell the Host to reload the entire thing. This operation is so rare - * that this naive implementation is reasonable. + * For a single GDT entry which changes, we simply change our copy and + * then tell the host about it. */ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) @@ -338,9 +337,13 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, } /* - * OK, I lied. There are three "thread local storage" GDT entries which change + * There are three "thread local storage" GDT entries which change * on every context switch (these three entries are how glibc implements - * __thread variables). So we have a hypercall specifically for this case. + * __thread variables). As an optimization, we have a hypercall + * specifically for this case. + * + * Wouldn't it be nicer to have a general LOAD_GDT_ENTRIES hypercall + * which took a range of entries? */ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) { diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index 5415a9d06f53..b908a59eccf5 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -22,22 +22,187 @@ EXPORT_SYMBOL(memset); void *memmove(void *dest, const void *src, size_t n) { - int d0, d1, d2; - - if (dest < src) { - memcpy(dest, src, n); - } else { - __asm__ __volatile__( - "std\n\t" - "rep\n\t" - "movsb\n\t" - "cld" - : "=&c" (d0), "=&S" (d1), "=&D" (d2) - :"0" (n), - "1" (n-1+src), - "2" (n-1+dest) - :"memory"); - } - return dest; + int d0,d1,d2,d3,d4,d5; + char *ret = dest; + + __asm__ __volatile__( + /* Handle more 16bytes in loop */ + "cmp $0x10, %0\n\t" + "jb 1f\n\t" + + /* Decide forward/backward copy mode */ + "cmp %2, %1\n\t" + "jb 2f\n\t" + + /* + * movs instruction have many startup latency + * so we handle small size by general register. + */ + "cmp $680, %0\n\t" + "jb 3f\n\t" + /* + * movs instruction is only good for aligned case. + */ + "mov %1, %3\n\t" + "xor %2, %3\n\t" + "and $0xff, %3\n\t" + "jz 4f\n\t" + "3:\n\t" + "sub $0x10, %0\n\t" + + /* + * We gobble 16byts forward in each loop. + */ + "3:\n\t" + "sub $0x10, %0\n\t" + "mov 0*4(%1), %3\n\t" + "mov 1*4(%1), %4\n\t" + "mov %3, 0*4(%2)\n\t" + "mov %4, 1*4(%2)\n\t" + "mov 2*4(%1), %3\n\t" + "mov 3*4(%1), %4\n\t" + "mov %3, 2*4(%2)\n\t" + "mov %4, 3*4(%2)\n\t" + "lea 0x10(%1), %1\n\t" + "lea 0x10(%2), %2\n\t" + "jae 3b\n\t" + "add $0x10, %0\n\t" + "jmp 1f\n\t" + + /* + * Handle data forward by movs. + */ + ".p2align 4\n\t" + "4:\n\t" + "mov -4(%1, %0), %3\n\t" + "lea -4(%2, %0), %4\n\t" + "shr $2, %0\n\t" + "rep movsl\n\t" + "mov %3, (%4)\n\t" + "jmp 11f\n\t" + /* + * Handle data backward by movs. + */ + ".p2align 4\n\t" + "6:\n\t" + "mov (%1), %3\n\t" + "mov %2, %4\n\t" + "lea -4(%1, %0), %1\n\t" + "lea -4(%2, %0), %2\n\t" + "shr $2, %0\n\t" + "std\n\t" + "rep movsl\n\t" + "mov %3,(%4)\n\t" + "cld\n\t" + "jmp 11f\n\t" + + /* + * Start to prepare for backward copy. + */ + ".p2align 4\n\t" + "2:\n\t" + "cmp $680, %0\n\t" + "jb 5f\n\t" + "mov %1, %3\n\t" + "xor %2, %3\n\t" + "and $0xff, %3\n\t" + "jz 6b\n\t" + + /* + * Calculate copy position to tail. + */ + "5:\n\t" + "add %0, %1\n\t" + "add %0, %2\n\t" + "sub $0x10, %0\n\t" + + /* + * We gobble 16byts backward in each loop. + */ + "7:\n\t" + "sub $0x10, %0\n\t" + + "mov -1*4(%1), %3\n\t" + "mov -2*4(%1), %4\n\t" + "mov %3, -1*4(%2)\n\t" + "mov %4, -2*4(%2)\n\t" + "mov -3*4(%1), %3\n\t" + "mov -4*4(%1), %4\n\t" + "mov %3, -3*4(%2)\n\t" + "mov %4, -4*4(%2)\n\t" + "lea -0x10(%1), %1\n\t" + "lea -0x10(%2), %2\n\t" + "jae 7b\n\t" + /* + * Calculate copy position to head. + */ + "add $0x10, %0\n\t" + "sub %0, %1\n\t" + "sub %0, %2\n\t" + + /* + * Move data from 8 bytes to 15 bytes. + */ + ".p2align 4\n\t" + "1:\n\t" + "cmp $8, %0\n\t" + "jb 8f\n\t" + "mov 0*4(%1), %3\n\t" + "mov 1*4(%1), %4\n\t" + "mov -2*4(%1, %0), %5\n\t" + "mov -1*4(%1, %0), %1\n\t" + + "mov %3, 0*4(%2)\n\t" + "mov %4, 1*4(%2)\n\t" + "mov %5, -2*4(%2, %0)\n\t" + "mov %1, -1*4(%2, %0)\n\t" + "jmp 11f\n\t" + + /* + * Move data from 4 bytes to 7 bytes. + */ + ".p2align 4\n\t" + "8:\n\t" + "cmp $4, %0\n\t" + "jb 9f\n\t" + "mov 0*4(%1), %3\n\t" + "mov -1*4(%1, %0), %4\n\t" + "mov %3, 0*4(%2)\n\t" + "mov %4, -1*4(%2, %0)\n\t" + "jmp 11f\n\t" + + /* + * Move data from 2 bytes to 3 bytes. + */ + ".p2align 4\n\t" + "9:\n\t" + "cmp $2, %0\n\t" + "jb 10f\n\t" + "movw 0*2(%1), %%dx\n\t" + "movw -1*2(%1, %0), %%bx\n\t" + "movw %%dx, 0*2(%2)\n\t" + "movw %%bx, -1*2(%2, %0)\n\t" + "jmp 11f\n\t" + + /* + * Move data for 1 byte. + */ + ".p2align 4\n\t" + "10:\n\t" + "cmp $1, %0\n\t" + "jb 11f\n\t" + "movb (%1), %%cl\n\t" + "movb %%cl, (%2)\n\t" + ".p2align 4\n\t" + "11:" + : "=&c" (d0), "=&S" (d1), "=&D" (d2), + "=r" (d3),"=r" (d4), "=r"(d5) + :"0" (n), + "1" (src), + "2" (dest) + :"memory"); + + return ret; + } EXPORT_SYMBOL(memmove); diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index bcbcd1e0f7d5..75ef61e35e38 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -40,84 +40,132 @@ ENTRY(__memcpy) ENTRY(memcpy) CFI_STARTPROC + movq %rdi, %rax /* - * Put the number of full 64-byte blocks into %ecx. - * Tail portion is handled at the end: + * Use 32bit CMP here to avoid long NOP padding. */ - movq %rdi, %rax - movl %edx, %ecx - shrl $6, %ecx - jz .Lhandle_tail + cmp $0x20, %edx + jb .Lhandle_tail - .p2align 4 -.Lloop_64: /* - * We decrement the loop index here - and the zero-flag is - * checked at the end of the loop (instructions inbetween do - * not change the zero flag): + * We check whether memory false dependece could occur, + * then jump to corresponding copy mode. */ - decl %ecx + cmp %dil, %sil + jl .Lcopy_backward + subl $0x20, %edx +.Lcopy_forward_loop: + subq $0x20, %rdx /* - * Move in blocks of 4x16 bytes: + * Move in blocks of 4x8 bytes: */ - movq 0*8(%rsi), %r11 - movq 1*8(%rsi), %r8 - movq %r11, 0*8(%rdi) - movq %r8, 1*8(%rdi) - - movq 2*8(%rsi), %r9 - movq 3*8(%rsi), %r10 - movq %r9, 2*8(%rdi) - movq %r10, 3*8(%rdi) - - movq 4*8(%rsi), %r11 - movq 5*8(%rsi), %r8 - movq %r11, 4*8(%rdi) - movq %r8, 5*8(%rdi) - - movq 6*8(%rsi), %r9 - movq 7*8(%rsi), %r10 - movq %r9, 6*8(%rdi) - movq %r10, 7*8(%rdi) - - leaq 64(%rsi), %rsi - leaq 64(%rdi), %rdi - - jnz .Lloop_64 + movq 0*8(%rsi), %r8 + movq 1*8(%rsi), %r9 + movq 2*8(%rsi), %r10 + movq 3*8(%rsi), %r11 + leaq 4*8(%rsi), %rsi + + movq %r8, 0*8(%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) + leaq 4*8(%rdi), %rdi + jae .Lcopy_forward_loop + addq $0x20, %rdx + jmp .Lhandle_tail + +.Lcopy_backward: + /* + * Calculate copy position to tail. + */ + addq %rdx, %rsi + addq %rdx, %rdi + subq $0x20, %rdx + /* + * At most 3 ALU operations in one cycle, + * so append NOPS in the same 16bytes trunk. + */ + .p2align 4 +.Lcopy_backward_loop: + subq $0x20, %rdx + movq -1*8(%rsi), %r8 + movq -2*8(%rsi), %r9 + movq -3*8(%rsi), %r10 + movq -4*8(%rsi), %r11 + leaq -4*8(%rsi), %rsi + movq %r8, -1*8(%rdi) + movq %r9, -2*8(%rdi) + movq %r10, -3*8(%rdi) + movq %r11, -4*8(%rdi) + leaq -4*8(%rdi), %rdi + jae .Lcopy_backward_loop + /* + * Calculate copy position to head. + */ + addq $0x20, %rdx + subq %rdx, %rsi + subq %rdx, %rdi .Lhandle_tail: - movl %edx, %ecx - andl $63, %ecx - shrl $3, %ecx - jz .Lhandle_7 + cmpq $16, %rdx + jb .Lless_16bytes + /* + * Move data from 16 bytes to 31 bytes. + */ + movq 0*8(%rsi), %r8 + movq 1*8(%rsi), %r9 + movq -2*8(%rsi, %rdx), %r10 + movq -1*8(%rsi, %rdx), %r11 + movq %r8, 0*8(%rdi) + movq %r9, 1*8(%rdi) + movq %r10, -2*8(%rdi, %rdx) + movq %r11, -1*8(%rdi, %rdx) + retq .p2align 4 -.Lloop_8: - decl %ecx - movq (%rsi), %r8 - movq %r8, (%rdi) - leaq 8(%rdi), %rdi - leaq 8(%rsi), %rsi - jnz .Lloop_8 - -.Lhandle_7: - movl %edx, %ecx - andl $7, %ecx - jz .Lend +.Lless_16bytes: + cmpq $8, %rdx + jb .Lless_8bytes + /* + * Move data from 8 bytes to 15 bytes. + */ + movq 0*8(%rsi), %r8 + movq -1*8(%rsi, %rdx), %r9 + movq %r8, 0*8(%rdi) + movq %r9, -1*8(%rdi, %rdx) + retq + .p2align 4 +.Lless_8bytes: + cmpq $4, %rdx + jb .Lless_3bytes + /* + * Move data from 4 bytes to 7 bytes. + */ + movl (%rsi), %ecx + movl -4(%rsi, %rdx), %r8d + movl %ecx, (%rdi) + movl %r8d, -4(%rdi, %rdx) + retq .p2align 4 +.Lless_3bytes: + cmpl $0, %edx + je .Lend + /* + * Move data from 1 bytes to 3 bytes. + */ .Lloop_1: movb (%rsi), %r8b movb %r8b, (%rdi) incq %rdi incq %rsi - decl %ecx + decl %edx jnz .Lloop_1 .Lend: - ret + retq CFI_ENDPROC ENDPROC(memcpy) ENDPROC(__memcpy) diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c index 0a33909bf122..6d0f0ec41b34 100644 --- a/arch/x86/lib/memmove_64.c +++ b/arch/x86/lib/memmove_64.c @@ -8,14 +8,185 @@ #undef memmove void *memmove(void *dest, const void *src, size_t count) { - if (dest < src) { - return memcpy(dest, src, count); - } else { - char *p = dest + count; - const char *s = src + count; - while (count--) - *--p = *--s; - } - return dest; + unsigned long d0,d1,d2,d3,d4,d5,d6,d7; + char *ret; + + __asm__ __volatile__( + /* Handle more 32bytes in loop */ + "mov %2, %3\n\t" + "cmp $0x20, %0\n\t" + "jb 1f\n\t" + + /* Decide forward/backward copy mode */ + "cmp %2, %1\n\t" + "jb 2f\n\t" + + /* + * movsq instruction have many startup latency + * so we handle small size by general register. + */ + "cmp $680, %0\n\t" + "jb 3f\n\t" + /* + * movsq instruction is only good for aligned case. + */ + "cmpb %%dil, %%sil\n\t" + "je 4f\n\t" + "3:\n\t" + "sub $0x20, %0\n\t" + /* + * We gobble 32byts forward in each loop. + */ + "5:\n\t" + "sub $0x20, %0\n\t" + "movq 0*8(%1), %4\n\t" + "movq 1*8(%1), %5\n\t" + "movq 2*8(%1), %6\n\t" + "movq 3*8(%1), %7\n\t" + "leaq 4*8(%1), %1\n\t" + + "movq %4, 0*8(%2)\n\t" + "movq %5, 1*8(%2)\n\t" + "movq %6, 2*8(%2)\n\t" + "movq %7, 3*8(%2)\n\t" + "leaq 4*8(%2), %2\n\t" + "jae 5b\n\t" + "addq $0x20, %0\n\t" + "jmp 1f\n\t" + /* + * Handle data forward by movsq. + */ + ".p2align 4\n\t" + "4:\n\t" + "movq %0, %8\n\t" + "movq -8(%1, %0), %4\n\t" + "lea -8(%2, %0), %5\n\t" + "shrq $3, %8\n\t" + "rep movsq\n\t" + "movq %4, (%5)\n\t" + "jmp 13f\n\t" + /* + * Handle data backward by movsq. + */ + ".p2align 4\n\t" + "7:\n\t" + "movq %0, %8\n\t" + "movq (%1), %4\n\t" + "movq %2, %5\n\t" + "leaq -8(%1, %0), %1\n\t" + "leaq -8(%2, %0), %2\n\t" + "shrq $3, %8\n\t" + "std\n\t" + "rep movsq\n\t" + "cld\n\t" + "movq %4, (%5)\n\t" + "jmp 13f\n\t" + + /* + * Start to prepare for backward copy. + */ + ".p2align 4\n\t" + "2:\n\t" + "cmp $680, %0\n\t" + "jb 6f \n\t" + "cmp %%dil, %%sil\n\t" + "je 7b \n\t" + "6:\n\t" + /* + * Calculate copy position to tail. + */ + "addq %0, %1\n\t" + "addq %0, %2\n\t" + "subq $0x20, %0\n\t" + /* + * We gobble 32byts backward in each loop. + */ + "8:\n\t" + "subq $0x20, %0\n\t" + "movq -1*8(%1), %4\n\t" + "movq -2*8(%1), %5\n\t" + "movq -3*8(%1), %6\n\t" + "movq -4*8(%1), %7\n\t" + "leaq -4*8(%1), %1\n\t" + + "movq %4, -1*8(%2)\n\t" + "movq %5, -2*8(%2)\n\t" + "movq %6, -3*8(%2)\n\t" + "movq %7, -4*8(%2)\n\t" + "leaq -4*8(%2), %2\n\t" + "jae 8b\n\t" + /* + * Calculate copy position to head. + */ + "addq $0x20, %0\n\t" + "subq %0, %1\n\t" + "subq %0, %2\n\t" + "1:\n\t" + "cmpq $16, %0\n\t" + "jb 9f\n\t" + /* + * Move data from 16 bytes to 31 bytes. + */ + "movq 0*8(%1), %4\n\t" + "movq 1*8(%1), %5\n\t" + "movq -2*8(%1, %0), %6\n\t" + "movq -1*8(%1, %0), %7\n\t" + "movq %4, 0*8(%2)\n\t" + "movq %5, 1*8(%2)\n\t" + "movq %6, -2*8(%2, %0)\n\t" + "movq %7, -1*8(%2, %0)\n\t" + "jmp 13f\n\t" + ".p2align 4\n\t" + "9:\n\t" + "cmpq $8, %0\n\t" + "jb 10f\n\t" + /* + * Move data from 8 bytes to 15 bytes. + */ + "movq 0*8(%1), %4\n\t" + "movq -1*8(%1, %0), %5\n\t" + "movq %4, 0*8(%2)\n\t" + "movq %5, -1*8(%2, %0)\n\t" + "jmp 13f\n\t" + "10:\n\t" + "cmpq $4, %0\n\t" + "jb 11f\n\t" + /* + * Move data from 4 bytes to 7 bytes. + */ + "movl (%1), %4d\n\t" + "movl -4(%1, %0), %5d\n\t" + "movl %4d, (%2)\n\t" + "movl %5d, -4(%2, %0)\n\t" + "jmp 13f\n\t" + "11:\n\t" + "cmp $2, %0\n\t" + "jb 12f\n\t" + /* + * Move data from 2 bytes to 3 bytes. + */ + "movw (%1), %4w\n\t" + "movw -2(%1, %0), %5w\n\t" + "movw %4w, (%2)\n\t" + "movw %5w, -2(%2, %0)\n\t" + "jmp 13f\n\t" + "12:\n\t" + "cmp $1, %0\n\t" + "jb 13f\n\t" + /* + * Move data for 1 byte. + */ + "movb (%1), %4b\n\t" + "movb %4b, (%2)\n\t" + "13:\n\t" + : "=&d" (d0), "=&S" (d1), "=&D" (d2), "=&a" (ret) , + "=r"(d3), "=r"(d4), "=r"(d5), "=r"(d6), "=&c" (d7) + :"0" (count), + "1" (src), + "2" (dest) + :"memory"); + + return ret; + } EXPORT_SYMBOL(memmove); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 4c4508e8a204..79b0b372d2d0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -229,7 +229,16 @@ void vmalloc_sync_all(void) spin_lock_irqsave(&pgd_lock, flags); list_for_each_entry(page, &pgd_list, lru) { - if (!vmalloc_sync_one(page_address(page), address)) + spinlock_t *pgt_lock; + pmd_t *ret; + + pgt_lock = &pgd_page_get_mm(page)->page_table_lock; + + spin_lock(pgt_lock); + ret = vmalloc_sync_one(page_address(page), address); + spin_unlock(pgt_lock); + + if (!ret) break; } spin_unlock_irqrestore(&pgd_lock, flags); @@ -251,6 +260,8 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; + WARN_ON_ONCE(in_nmi()); + /* * Synchronize this task's top level page-table * with the 'reference' page table. @@ -326,29 +337,7 @@ out: void vmalloc_sync_all(void) { - unsigned long address; - - for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END; - address += PGDIR_SIZE) { - - const pgd_t *pgd_ref = pgd_offset_k(address); - unsigned long flags; - struct page *page; - - if (pgd_none(*pgd_ref)) - continue; - - spin_lock_irqsave(&pgd_lock, flags); - list_for_each_entry(page, &pgd_list, lru) { - pgd_t *pgd; - pgd = (pgd_t *)page_address(page) + pgd_index(address); - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); - else - BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); - } - spin_unlock_irqrestore(&pgd_lock, flags); - } + sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); } /* @@ -369,6 +358,8 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; + WARN_ON_ONCE(in_nmi()); + /* * Copy kernel mappings over when needed. This can also * happen within a race in page table update. In the later @@ -894,8 +885,14 @@ spurious_fault(unsigned long error_code, unsigned long address) if (pmd_large(*pmd)) return spurious_fault_check(error_code, (pte_t *) pmd); + /* + * Note: don't use pte_present() here, since it returns true + * if the _PAGE_PROTNONE bit is set. However, this aliases the + * _PAGE_GLOBAL bit, which for kernel pages give false positives + * when CONFIG_DEBUG_PAGEALLOC is used. + */ pte = pte_offset_kernel(pmd, address); - if (!pte_present(*pte)) + if (!(pte_flags(*pte) & _PAGE_PRESENT)) return 0; ret = spurious_fault_check(error_code, pte); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bca79091b9d6..558f2d332076 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -67,7 +67,7 @@ static __init void *alloc_low_page(void) panic("alloc_low_page: ran out of memory"); adr = __va(pfn * PAGE_SIZE); - memset(adr, 0, PAGE_SIZE); + clear_page(adr); return adr; } @@ -558,7 +558,7 @@ char swsusp_pg_dir[PAGE_SIZE] static inline void save_pg_dir(void) { - memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE); + copy_page(swsusp_pg_dir, swapper_pg_dir); } #else /* !CONFIG_ACPI_SLEEP */ static inline void save_pg_dir(void) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 9a6674689a20..c55f900fbf89 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -98,6 +98,43 @@ static int __init nonx32_setup(char *str) __setup("noexec32=", nonx32_setup); /* + * When memory was added/removed make sure all the processes MM have + * suitable PGD entries in the local PGD level page. + */ +void sync_global_pgds(unsigned long start, unsigned long end) +{ + unsigned long address; + + for (address = start; address <= end; address += PGDIR_SIZE) { + const pgd_t *pgd_ref = pgd_offset_k(address); + unsigned long flags; + struct page *page; + + if (pgd_none(*pgd_ref)) + continue; + + spin_lock_irqsave(&pgd_lock, flags); + list_for_each_entry(page, &pgd_list, lru) { + pgd_t *pgd; + spinlock_t *pgt_lock; + + pgd = (pgd_t *)page_address(page) + pgd_index(address); + pgt_lock = &pgd_page_get_mm(page)->page_table_lock; + spin_lock(pgt_lock); + + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + else + BUG_ON(pgd_page_vaddr(*pgd) + != pgd_page_vaddr(*pgd_ref)); + + spin_unlock(pgt_lock); + } + spin_unlock_irqrestore(&pgd_lock, flags); + } +} + +/* * NOTE: This function is marked __ref because it calls __init function * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. */ @@ -293,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys) panic("alloc_low_page: ran out of memory"); adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE); - memset(adr, 0, PAGE_SIZE); + clear_page(adr); *phys = pfn * PAGE_SIZE; return adr; } @@ -534,11 +571,13 @@ kernel_physical_mapping_init(unsigned long start, unsigned long end, unsigned long page_size_mask) { - + bool pgd_changed = false; unsigned long next, last_map_addr = end; + unsigned long addr; start = (unsigned long)__va(start); end = (unsigned long)__va(end); + addr = start; for (; start < end; start = next) { pgd_t *pgd = pgd_offset_k(start); @@ -563,7 +602,12 @@ kernel_physical_mapping_init(unsigned long start, spin_lock(&init_mm.page_table_lock); pgd_populate(&init_mm, pgd, __va(pud_phys)); spin_unlock(&init_mm.page_table_lock); + pgd_changed = true; } + + if (pgd_changed) + sync_global_pgds(addr, end); + __flush_tlb_all(); return last_map_addr; @@ -1003,6 +1047,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) } } + sync_global_pgds((unsigned long)start_page, end); return 0; } diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 84e236ce76ba..72fc70cf6184 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -74,7 +74,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) /* * Map 'pfn' using fixed map 'type' and protections 'prot' */ -void * +void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) { /* @@ -86,12 +86,12 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC)) prot = PAGE_KERNEL_UC_MINUS; - return kmap_atomic_prot_pfn(pfn, type, prot); + return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, type, prot); } EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn); void -iounmap_atomic(void *kvaddr, enum km_type type) +iounmap_atomic(void __iomem *kvaddr, enum km_type type) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c index 970ed579d4e4..52d54bfc1ebb 100644 --- a/arch/x86/mm/k8topology_64.c +++ b/arch/x86/mm/k8topology_64.c @@ -22,7 +22,7 @@ #include <asm/numa.h> #include <asm/mpspec.h> #include <asm/apic.h> -#include <asm/k8.h> +#include <asm/amd_nb.h> static struct bootnode __initdata nodes[8]; static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE; @@ -54,8 +54,8 @@ static __init int find_northbridge(void) static __init void early_get_boot_cpu_id(void) { /* - * need to get boot_cpu_id so can use that to create apicid_to_node - * in k8_scan_nodes() + * need to get the APIC ID of the BSP so can use that to + * create apicid_to_node in k8_scan_nodes() */ #ifdef CONFIG_X86_MPPARSE /* @@ -212,7 +212,7 @@ int __init k8_scan_nodes(void) bits = boot_cpu_data.x86_coreid_bits; cores = (1<<bits); apicid_base = 0; - /* need to get boot_cpu_id early for system with apicid lifting */ + /* get the APIC ID of the BSP early for systems with apicid lifting */ early_get_boot_cpu_id(); if (boot_cpu_physical_apicid > 0) { pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid); diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c index b3b531a4f8e5..d87dd6d042d6 100644 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ b/arch/x86/mm/kmemcheck/kmemcheck.c @@ -631,6 +631,8 @@ bool kmemcheck_fault(struct pt_regs *regs, unsigned long address, if (!pte) return false; + WARN_ON_ONCE(in_nmi()); + if (error_code & 2) kmemcheck_access(regs, address, KMEMCHECK_WRITE); else diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c index 63c19e27aa6f..324aa3f07237 100644 --- a/arch/x86/mm/kmemcheck/opcode.c +++ b/arch/x86/mm/kmemcheck/opcode.c @@ -9,7 +9,7 @@ static bool opcode_is_prefix(uint8_t b) b == 0xf0 || b == 0xf2 || b == 0xf3 /* Group 2 */ || b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26 - || b == 0x64 || b == 0x65 || b == 0x2e || b == 0x3e + || b == 0x64 || b == 0x65 /* Group 3 */ || b == 0x66 /* Group 4 */ diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index a7bcc23ef96c..4962f1aeda6f 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -18,7 +18,7 @@ #include <asm/dma.h> #include <asm/numa.h> #include <asm/acpi.h> -#include <asm/k8.h> +#include <asm/amd_nb.h> struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index a96023e872ae..8be8c7d7bc89 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -87,7 +87,19 @@ static inline void pgd_list_del(pgd_t *pgd) #define UNSHARED_PTRS_PER_PGD \ (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD) -static void pgd_ctor(pgd_t *pgd) + +static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm) +{ + BUILD_BUG_ON(sizeof(virt_to_page(pgd)->index) < sizeof(mm)); + virt_to_page(pgd)->index = (pgoff_t)mm; +} + +struct mm_struct *pgd_page_get_mm(struct page *page) +{ + return (struct mm_struct *)page->index; +} + +static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) { /* If the pgd points to a shared pagetable level (either the ptes in non-PAE, or shared PMD in PAE), then just copy the @@ -101,8 +113,10 @@ static void pgd_ctor(pgd_t *pgd) } /* list required to sync kernel mapping updates */ - if (!SHARED_KERNEL_PMD) + if (!SHARED_KERNEL_PMD) { + pgd_set_mm(pgd, mm); pgd_list_add(pgd); + } } static void pgd_dtor(pgd_t *pgd) @@ -268,7 +282,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) */ spin_lock_irqsave(&pgd_lock, flags); - pgd_ctor(pgd); + pgd_ctor(mm, pgd); pgd_prepopulate_pmd(mm, pgd, pmds); spin_unlock_irqrestore(&pgd_lock, flags); diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index f9897f7a9ef1..9c0d0d399c30 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -420,9 +420,11 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) return -1; } - for_each_node_mask(i, nodes_parsed) - e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, - nodes[i].end >> PAGE_SHIFT); + for (i = 0; i < num_node_memblks; i++) + e820_register_active_regions(memblk_nodeid[i], + node_memblk_range[i].start >> PAGE_SHIFT, + node_memblk_range[i].end >> PAGE_SHIFT); + /* for out of order entries in SRAT */ sort_node_map(); if (!nodes_cover_memory(nodes)) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index c03f14ab6667..49358481c733 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -5,6 +5,7 @@ #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/cpu.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -52,6 +53,8 @@ union smp_flush_state { want false sharing in the per cpu data segment. */ static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS]; +static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset); + /* * We cannot call mmdrop() because we are in interrupt context, * instead update mm->cpu_vm_mask. @@ -173,7 +176,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, union smp_flush_state *f; /* Caller has disabled preemption */ - sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS; + sender = this_cpu_read(tlb_vector_offset); f = &flush_state[sender]; /* @@ -218,6 +221,47 @@ void native_flush_tlb_others(const struct cpumask *cpumask, flush_tlb_others_ipi(cpumask, mm, va); } +static void __cpuinit calculate_tlb_offset(void) +{ + int cpu, node, nr_node_vecs; + /* + * we are changing tlb_vector_offset for each CPU in runtime, but this + * will not cause inconsistency, as the write is atomic under X86. we + * might see more lock contentions in a short time, but after all CPU's + * tlb_vector_offset are changed, everything should go normal + * + * Note: if NUM_INVALIDATE_TLB_VECTORS % nr_online_nodes !=0, we might + * waste some vectors. + **/ + if (nr_online_nodes > NUM_INVALIDATE_TLB_VECTORS) + nr_node_vecs = 1; + else + nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes; + + for_each_online_node(node) { + int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) * + nr_node_vecs; + int cpu_offset = 0; + for_each_cpu(cpu, cpumask_of_node(node)) { + per_cpu(tlb_vector_offset, cpu) = node_offset + + cpu_offset; + cpu_offset++; + cpu_offset = cpu_offset % nr_node_vecs; + } + } +} + +static int tlb_cpuhp_notify(struct notifier_block *n, + unsigned long action, void *hcpu) +{ + switch (action & 0xf) { + case CPU_ONLINE: + case CPU_DEAD: + calculate_tlb_offset(); + } + return NOTIFY_OK; +} + static int __cpuinit init_smp_flush(void) { int i; @@ -225,6 +269,8 @@ static int __cpuinit init_smp_flush(void) for (i = 0; i < ARRAY_SIZE(flush_state); i++) raw_spin_lock_init(&flush_state[i].tlbstate_lock); + calculate_tlb_offset(); + hotcpu_notifier(tlb_cpuhp_notify, 0); return 0; } core_initcall(init_smp_flush); diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 3855096c59b8..2d49d4e19a36 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -14,6 +14,7 @@ #include <asm/ptrace.h> #include <asm/uaccess.h> #include <asm/stacktrace.h> +#include <linux/compat.h> static void backtrace_warning_symbol(void *data, char *msg, unsigned long symbol) @@ -48,14 +49,12 @@ static struct stacktrace_ops backtrace_ops = { .walk_stack = print_context_stack, }; -struct frame_head { - struct frame_head *bp; - unsigned long ret; -} __attribute__((packed)); - -static struct frame_head *dump_user_backtrace(struct frame_head *head) +#ifdef CONFIG_COMPAT +static struct stack_frame_ia32 * +dump_user_backtrace_32(struct stack_frame_ia32 *head) { - struct frame_head bufhead[2]; + struct stack_frame_ia32 bufhead[2]; + struct stack_frame_ia32 *fp; /* Also check accessibility of one struct frame_head beyond */ if (!access_ok(VERIFY_READ, head, sizeof(bufhead))) @@ -63,20 +62,66 @@ static struct frame_head *dump_user_backtrace(struct frame_head *head) if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead))) return NULL; - oprofile_add_trace(bufhead[0].ret); + fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame); + + oprofile_add_trace(bufhead[0].return_address); + + /* frame pointers should strictly progress back up the stack + * (towards higher addresses) */ + if (head >= fp) + return NULL; + + return fp; +} + +static inline int +x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) +{ + struct stack_frame_ia32 *head; + + /* User process is 32-bit */ + if (!current || !test_thread_flag(TIF_IA32)) + return 0; + + head = (struct stack_frame_ia32 *) regs->bp; + while (depth-- && head) + head = dump_user_backtrace_32(head); + + return 1; +} + +#else +static inline int +x86_backtrace_32(struct pt_regs * const regs, unsigned int depth) +{ + return 0; +} +#endif /* CONFIG_COMPAT */ + +static struct stack_frame *dump_user_backtrace(struct stack_frame *head) +{ + struct stack_frame bufhead[2]; + + /* Also check accessibility of one struct stack_frame beyond */ + if (!access_ok(VERIFY_READ, head, sizeof(bufhead))) + return NULL; + if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead))) + return NULL; + + oprofile_add_trace(bufhead[0].return_address); /* frame pointers should strictly progress back up the stack * (towards higher addresses) */ - if (head >= bufhead[0].bp) + if (head >= bufhead[0].next_frame) return NULL; - return bufhead[0].bp; + return bufhead[0].next_frame; } void x86_backtrace(struct pt_regs * const regs, unsigned int depth) { - struct frame_head *head = (struct frame_head *)frame_pointer(regs); + struct stack_frame *head = (struct stack_frame *)frame_pointer(regs); if (!user_mode_vm(regs)) { unsigned long stack = kernel_stack_pointer(regs); @@ -86,6 +131,9 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) return; } + if (x86_backtrace_32(regs, depth)) + return; + while (depth-- && head) head = dump_user_backtrace(head); } diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index f6b48f6c5951..bd1489c3ce09 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -568,8 +568,13 @@ static int __init init_sysfs(void) int error; error = sysdev_class_register(&oprofile_sysclass); - if (!error) - error = sysdev_register(&device_oprofile); + if (error) + return error; + + error = sysdev_register(&device_oprofile); + if (error) + sysdev_class_unregister(&oprofile_sysclass); + return error; } @@ -580,8 +585,10 @@ static void exit_sysfs(void) } #else -#define init_sysfs() do { } while (0) -#define exit_sysfs() do { } while (0) + +static inline int init_sysfs(void) { return 0; } +static inline void exit_sysfs(void) { } + #endif /* CONFIG_PM */ static int __init p4_init(char **cpu_type) @@ -664,7 +671,10 @@ static int __init ppro_init(char **cpu_type) case 14: *cpu_type = "i386/core"; break; - case 15: case 23: + case 0x0f: + case 0x16: + case 0x17: + case 0x1d: *cpu_type = "i386/core_2"; break; case 0x1a: @@ -685,9 +695,6 @@ static int __init ppro_init(char **cpu_type) return 1; } -/* in order to get sysfs right */ -static int using_nmi; - int __init op_nmi_init(struct oprofile_operations *ops) { __u8 vendor = boot_cpu_data.x86_vendor; @@ -774,14 +781,15 @@ int __init op_nmi_init(struct oprofile_operations *ops) mux_init(ops); - init_sysfs(); - using_nmi = 1; + ret = init_sysfs(); + if (ret) + return ret; + printk(KERN_INFO "oprofile: using NMI interrupt.\n"); return 0; } void op_nmi_exit(void) { - if (using_nmi) - exit_sysfs(); + exit_sysfs(); } diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c index b34815408f58..13700ec8e2e4 100644 --- a/arch/x86/pci/olpc.c +++ b/arch/x86/pci/olpc.c @@ -304,7 +304,7 @@ static struct pci_raw_ops pci_olpc_conf = { int __init pci_olpc_init(void) { - printk(KERN_INFO "PCI: Using configuration type OLPC\n"); + printk(KERN_INFO "PCI: Using configuration type OLPC XO-1\n"); raw_pci_ops = &pci_olpc_conf; is_lx = is_geode_lx(); return 0; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index e7e8c5f54956..87bb35e34ef1 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -113,6 +113,7 @@ static void __save_processor_state(struct saved_context *ctxt) void save_processor_state(void) { __save_processor_state(&saved_context); + save_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(save_processor_state); @@ -229,6 +230,7 @@ static void __restore_processor_state(struct saved_context *ctxt) void restore_processor_state(void) { __restore_processor_state(&saved_context); + restore_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(restore_processor_state); diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 554c002a1e1a..0f456386cce5 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -72,13 +72,17 @@ void __init xen_unplug_emulated_devices(void) { int r; + /* user explicitly requested no unplug */ + if (xen_emul_unplug & XEN_UNPLUG_NEVER) + return; /* check the version of the xen platform PCI device */ r = check_platform_magic(); /* If the version matches enable the Xen platform PCI driver. - * Also enable the Xen platform PCI driver if the version is really old - * and the user told us to ignore it. */ + * Also enable the Xen platform PCI driver if the host does + * not support the unplug protocol (XEN_PLATFORM_ERR_MAGIC) + * but the user told us that unplugging is unnecessary. */ if (r && !(r == XEN_PLATFORM_ERR_MAGIC && - (xen_emul_unplug & XEN_UNPLUG_IGNORE))) + (xen_emul_unplug & XEN_UNPLUG_UNNECESSARY))) return; /* Set the default value of xen_emul_unplug depending on whether or * not the Xen PV frontends and the Xen platform PCI driver have @@ -99,7 +103,7 @@ void __init xen_unplug_emulated_devices(void) } } /* Now unplug the emulated devices */ - if (!(xen_emul_unplug & XEN_UNPLUG_IGNORE)) + if (!(xen_emul_unplug & XEN_UNPLUG_UNNECESSARY)) outw(xen_emul_unplug, XEN_IOPORT_UNPLUG); xen_platform_pci_unplug = xen_emul_unplug; } @@ -125,8 +129,10 @@ static int __init parse_xen_emul_unplug(char *arg) xen_emul_unplug |= XEN_UNPLUG_AUX_IDE_DISKS; else if (!strncmp(p, "nics", l)) xen_emul_unplug |= XEN_UNPLUG_ALL_NICS; - else if (!strncmp(p, "ignore", l)) - xen_emul_unplug |= XEN_UNPLUG_IGNORE; + else if (!strncmp(p, "unnecessary", l)) + xen_emul_unplug |= XEN_UNPLUG_UNNECESSARY; + else if (!strncmp(p, "never", l)) + xen_emul_unplug |= XEN_UNPLUG_NEVER; else printk(KERN_WARNING "unrecognised option '%s' " "in parameter 'xen_emul_unplug'\n", p); diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 1a5353a753fc..b2bb5aa3b054 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -489,8 +489,9 @@ static void xen_hvm_setup_cpu_clockevents(void) __init void xen_hvm_init_time_ops(void) { /* vector callback is needed otherwise we cannot receive interrupts - * on cpu > 0 */ - if (!xen_have_vector_callback && num_present_cpus() > 1) + * on cpu > 0 and at this point we don't know how many cpus are + * available */ + if (!xen_have_vector_callback) return; if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { printk(KERN_INFO "Xen doesn't support pvclock on HVM," |
