diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2013-11-14 17:38:05 -0800 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2013-11-14 17:38:05 -0800 |
| commit | 42249094f79422fbf5ed4b54eeb48ff096809b8f (patch) | |
| tree | 91e6850c8c7e8cc284cf8bb6363f8662f84011f4 /arch/x86/kernel | |
| parent | 936816161978ca716a56c5e553c68f25972b1e3a (diff) | |
| parent | 2c027b7c48a888ab173ba45babb4525e278375d9 (diff) | |
| download | op-kernel-dev-42249094f79422fbf5ed4b54eeb48ff096809b8f.zip op-kernel-dev-42249094f79422fbf5ed4b54eeb48ff096809b8f.tar.gz | |
Merge branch 'next' into for-linus
Merge first round of changes for 3.13 merge window.
Diffstat (limited to 'arch/x86/kernel')
118 files changed, 4356 insertions, 1501 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 7bd3bd3..a5408b9 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -16,6 +16,8 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg endif +CFLAGS_irq.o := -I$(src)/../include/asm/trace + obj-y := process_$(BITS).o signal.o entry_$(BITS).o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o @@ -67,7 +69,7 @@ obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o +obj-$(CONFIG_DOUBLEFAULT) += doublefault.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o @@ -93,6 +95,7 @@ obj-$(CONFIG_MICROCODE_INTEL_LIB) += microcode_intel_lib.o microcode-y := microcode_core.o microcode-$(CONFIG_MICROCODE_INTEL) += microcode_intel.o microcode-$(CONFIG_MICROCODE_AMD) += microcode_amd.o +obj-$(CONFIG_MICROCODE_AMD_EARLY) += microcode_amd_early.o obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o @@ -100,8 +103,12 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-y += sysfb.o +obj-$(CONFIG_X86_SYSFB) += sysfb_simplefb.o +obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o +obj-$(CONFIG_TRACING) += tracepoint.o ### # 64 bit specific files diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 230c8ea..40c7660 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -44,6 +44,7 @@ #include <asm/mpspec.h> #include <asm/smp.h> +#include "sleep.h" /* To include x86_acpi_suspend_lowlevel */ static int __initdata acpi_force = 0; u32 acpi_rsdt_forced; int acpi_disabled; @@ -66,6 +67,7 @@ EXPORT_SYMBOL(acpi_pci_disabled); int acpi_lapic; int acpi_ioapic; int acpi_strict; +int acpi_disable_cmcff; u8 acpi_sci_flags __initdata; int acpi_sci_override_gsi __initdata; @@ -140,16 +142,8 @@ static u32 irq_to_gsi(int irq) } /* - * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, - * to map the target physical address. The problem is that set_fixmap() - * provides a single page, and it is possible that the page is not - * sufficient. - * By using this area, we can map up to MAX_IO_APICS pages temporarily, - * i.e. until the next __va_range() call. - * - * Important Safety Note: The fixed I/O APIC page numbers are *subtracted* - * from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and - * count idx down while incrementing the phys address. + * This is just a simple wrapper around early_ioremap(), + * with sanity checks for phys == 0 and size == 0. */ char *__init __acpi_map_table(unsigned long phys, unsigned long size) { @@ -159,6 +153,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) return early_ioremap(phys, size); } + void __init __acpi_unmap_table(char *map, unsigned long size) { if (!map || !size) @@ -194,11 +189,11 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -static void __cpuinit acpi_register_lapic(int id, u8 enabled) +static void acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; - if (id >= (MAX_LOCAL_APIC-1)) { + if (id >= MAX_LOCAL_APIC) { printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); return; } @@ -559,6 +554,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity) = acpi_register_gsi_pic; +#ifdef CONFIG_ACPI_SLEEP +int (*acpi_suspend_lowlevel)(void) = x86_acpi_suspend_lowlevel; +#else +int (*acpi_suspend_lowlevel)(void); +#endif + /* * success: return IRQ number (>=0) * failure: return < 0 @@ -600,7 +601,7 @@ void __init acpi_set_irq_model_ioapic(void) #ifdef CONFIG_ACPI_HOTPLUG_CPU #include <acpi/processor.h> -static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) +static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) { #ifdef CONFIG_ACPI_NUMA int nid; @@ -613,7 +614,7 @@ static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu) +static int _acpi_map_lsapic(acpi_handle handle, int *pcpu) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; @@ -1113,6 +1114,7 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) int ioapic; int ioapic_pin; struct io_apic_irq_attr irq_attr; + int ret; if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) return gsi; @@ -1142,7 +1144,9 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin, trigger == ACPI_EDGE_SENSITIVE ? 0 : 1, polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr); + ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr); + if (ret < 0) + gsi = INT_MIN; return gsi; } @@ -1619,6 +1623,10 @@ static int __init parse_acpi(char *arg) /* "acpi=copy_dsdt" copys DSDT */ else if (strcmp(arg, "copy_dsdt") == 0) { acpi_gbl_copy_dsdt_locally = 1; + } + /* "acpi=nocmcff" disables FF mode for corrected errors */ + else if (strcmp(arg, "nocmcff") == 0) { + acpi_disable_cmcff = 1; } else { /* Core will printk when we return error. */ return -EINVAL; diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index b44577b..3312010 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -26,12 +26,12 @@ static char temp_stack[4096]; #endif /** - * acpi_suspend_lowlevel - save kernel state + * x86_acpi_suspend_lowlevel - save kernel state * * Create an identity mapped page table and copy the wakeup routine to * low memory. */ -int acpi_suspend_lowlevel(void) +int x86_acpi_suspend_lowlevel(void) { struct wakeup_header *header = (struct wakeup_header *) __va(real_mode_header->wakeup_header); @@ -48,9 +48,20 @@ int acpi_suspend_lowlevel(void) #ifndef CONFIG_64BIT native_store_gdt((struct desc_ptr *)&header->pmode_gdt); + /* + * We have to check that we can write back the value, and not + * just read it. At least on 90 nm Pentium M (Family 6, Model + * 13), reading an invalid MSR is not guaranteed to trap, see + * Erratum X4 in "Intel Pentium M Processor on 90 nm Process + * with 2-MB L2 Cache and Intel® Processor A100 and A110 on 90 + * nm process with 512-KB L2 Cache Specification Update". + */ if (!rdmsr_safe(MSR_EFER, &header->pmode_efer_low, - &header->pmode_efer_high)) + &header->pmode_efer_high) && + !wrmsr_safe(MSR_EFER, + header->pmode_efer_low, + header->pmode_efer_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER); #endif /* !CONFIG_64BIT */ @@ -61,7 +72,10 @@ int acpi_suspend_lowlevel(void) } if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, &header->pmode_misc_en_low, - &header->pmode_misc_en_high)) + &header->pmode_misc_en_high) && + !wrmsr_safe(MSR_IA32_MISC_ENABLE, + header->pmode_misc_en_low, + header->pmode_misc_en_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE); header->realmode_flags = acpi_realmode_flags; diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 67f59f8..c9c2c98 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -15,3 +15,5 @@ extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); extern void do_suspend_lowlevel(void); + +extern int x86_acpi_suspend_lowlevel(void); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c15cf9a..15e8563 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include <linux/memory.h> #include <linux/stop_machine.h> #include <linux/slab.h> +#include <linux/kdebug.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) return addr; } -/* - * Cross-modifying kernel text with stop_machine(). - * This code originally comes from immediate value. - */ -static atomic_t stop_machine_first; -static int wrote_text; +static void do_sync_core(void *info) +{ + sync_core(); +} -struct text_poke_params { - struct text_poke_param *params; - int nparams; -}; +static bool bp_patching_in_progress; +static void *bp_int3_handler, *bp_int3_addr; -static int __kprobes stop_machine_text_poke(void *data) +int poke_int3_handler(struct pt_regs *regs) { - struct text_poke_params *tpp = data; - struct text_poke_param *p; - int i; + /* bp_patching_in_progress */ + smp_rmb(); - if (atomic_xchg(&stop_machine_first, 0)) { - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - text_poke(p->addr, p->opcode, p->len); - } - smp_wmb(); /* Make sure other cpus see that this has run */ - wrote_text = 1; - } else { - while (!wrote_text) - cpu_relax(); - smp_mb(); /* Load wrote_text before following execution */ - } + if (likely(!bp_patching_in_progress)) + return 0; - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - flush_icache_range((unsigned long)p->addr, - (unsigned long)p->addr + p->len); - } - /* - * Intel Archiecture Software Developer's Manual section 7.1.3 specifies - * that a core serializing instruction such as "cpuid" should be - * executed on _each_ core before the new instruction is made visible. - */ - sync_core(); - return 0; -} + if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr) + return 0; + + /* set up the specified breakpoint handler */ + regs->ip = (unsigned long) bp_int3_handler; + + return 1; -/** - * text_poke_smp - Update instructions on a live kernel on SMP - * @addr: address to modify - * @opcode: source of the copy - * @len: length to copy - * - * Modify multi-byte instruction by using stop_machine() on SMP. This allows - * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying - * should be allowed, since stop_machine() does _not_ protect code against - * NMI and MCE. - * - * Note: Must be called under get_online_cpus() and text_mutex. - */ -void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) -{ - struct text_poke_params tpp; - struct text_poke_param p; - - p.addr = addr; - p.opcode = opcode; - p.len = len; - tpp.params = &p; - tpp.nparams = 1; - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - /* Use __stop_machine() because the caller already got online_cpus. */ - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); - return addr; } /** - * text_poke_smp_batch - Update instructions on a live kernel on SMP - * @params: an array of text_poke parameters - * @n: the number of elements in params. + * text_poke_bp() -- update instructions on live kernel on SMP + * @addr: address to patch + * @opcode: opcode of new instruction + * @len: length to copy + * @handler: address to jump to when the temporary breakpoint is hit * - * Modify multi-byte instruction by using stop_machine() on SMP. Since the - * stop_machine() is heavy task, it is better to aggregate text_poke requests - * and do it once if possible. + * Modify multi-byte instruction by using int3 breakpoint on SMP. + * We completely avoid stop_machine() here, and achieve the + * synchronization using int3 breakpoint. * - * Note: Must be called under get_online_cpus() and text_mutex. + * The way it is done: + * - add a int3 trap to the address that will be patched + * - sync cores + * - update all but the first byte of the patched range + * - sync cores + * - replace the first byte (int3) by the first byte of + * replacing opcode + * - sync cores + * + * Note: must be called under text_mutex. */ -void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) +void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) { - struct text_poke_params tpp = {.params = params, .nparams = n}; + unsigned char int3 = 0xcc; + + bp_int3_handler = handler; + bp_int3_addr = (u8 *)addr + sizeof(int3); + bp_patching_in_progress = true; + /* + * Corresponding read barrier in int3 notifier for + * making sure the in_progress flags is correctly ordered wrt. + * patching + */ + smp_wmb(); + + text_poke(addr, &int3, sizeof(int3)); - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); + on_each_cpu(do_sync_core, NULL, 1); + + if (len - sizeof(int3) > 0) { + /* patch all but the first byte */ + text_poke((char *)addr + sizeof(int3), + (const char *) opcode + sizeof(int3), + len - sizeof(int3)); + /* + * According to Intel, this core syncing is very likely + * not necessary and we'd be safe even without it. But + * better safe than sorry (plus there's not only Intel). + */ + on_each_cpu(do_sync_core, NULL, 1); + } + + /* patch the first byte */ + text_poke(addr, opcode, sizeof(int3)); + + on_each_cpu(do_sync_core, NULL, 1); + + bp_patching_in_progress = false; + smp_wmb(); + + return addr; } + diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3048ded..59554dc 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { 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_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, {} }; @@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} }; @@ -81,13 +83,20 @@ int amd_cache_northbridges(void) next_northbridge(misc, amd_nb_misc_ids); node_to_amd_nb(i)->link = link = next_northbridge(link, amd_nb_link_ids); - } + } + /* GART present only on Fam15h upto model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - boot_cpu_data.x86 == 0x15) + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) amd_northbridges.flags |= AMD_NB_GART; /* + * Check for L3 cache presence. + */ + if (!cpuid_edx(0x80000006)) + return 0; + + /* * Some CPU families support L3 Cache Index Disable. There are some * limitations because of E382 and E388 on family 0x10. */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 904611b..a7eb82d 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -35,6 +35,7 @@ #include <linux/smp.h> #include <linux/mm.h> +#include <asm/trace/irq_vectors.h> #include <asm/irq_remapping.h> #include <asm/perf_event.h> #include <asm/x86_init.h> @@ -57,7 +58,7 @@ unsigned int num_processors; -unsigned disabled_cpus __cpuinitdata; +unsigned disabled_cpus; /* Processor that is doing the boot up */ unsigned int boot_cpu_physical_apicid = -1U; @@ -543,7 +544,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); * Setup the local APIC timer for this CPU. Copy the initialized values * of the boot CPU and register the clock event in the framework. */ -static void __cpuinit setup_APIC_timer(void) +static void setup_APIC_timer(void) { struct clock_event_device *levt = &__get_cpu_var(lapic_events); @@ -865,7 +866,7 @@ void __init setup_boot_APIC_clock(void) setup_APIC_timer(); } -void __cpuinit setup_secondary_APIC_clock(void) +void setup_secondary_APIC_clock(void) { setup_APIC_timer(); } @@ -912,24 +913,42 @@ static void local_apic_timer_interrupt(void) * [ if a single-CPU system runs an SMP kernel then we call the local * interrupt as well. Thus we cannot inline the local irq ... ] */ -void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); /* * NOTE! We'd better ACK the irq immediately, * because timer handling can be slow. + * + * update_process_times() expects us to have done irq_enter(). + * Besides, if we don't timer interrupts ignore the global + * interrupt lock, which is the WrongThing (tm) to do. */ - ack_APIC_irq(); + entering_ack_irq(); + local_apic_timer_interrupt(); + exiting_irq(); + + set_irq_regs(old_regs); +} + +__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + /* + * NOTE! We'd better ACK the irq immediately, + * because timer handling can be slow. + * * update_process_times() expects us to have done irq_enter(). * Besides, if we don't timer interrupts ignore the global * interrupt lock, which is the WrongThing (tm) to do. */ - irq_enter(); - exit_idle(); + entering_ack_irq(); + trace_local_timer_entry(LOCAL_TIMER_VECTOR); local_apic_timer_interrupt(); - irq_exit(); + trace_local_timer_exit(LOCAL_TIMER_VECTOR); + exiting_irq(); set_irq_regs(old_regs); } @@ -1210,7 +1229,7 @@ void __init init_bsp_APIC(void) apic_write(APIC_LVT1, value); } -static void __cpuinit lapic_setup_esr(void) +static void lapic_setup_esr(void) { unsigned int oldvalue, value, maxlvt; @@ -1257,7 +1276,7 @@ static void __cpuinit lapic_setup_esr(void) * Used to setup local APIC while initializing BSP or bringin up APs. * Always called with preemption disabled. */ -void __cpuinit setup_local_APIC(void) +void setup_local_APIC(void) { int cpu = smp_processor_id(); unsigned int value, queued; @@ -1452,7 +1471,7 @@ void __cpuinit setup_local_APIC(void) #endif } -void __cpuinit end_local_APIC_setup(void) +void end_local_APIC_setup(void) { lapic_setup_esr(); @@ -1907,12 +1926,10 @@ int __init APIC_init_uniprocessor(void) /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -void smp_spurious_interrupt(struct pt_regs *regs) +static inline void __smp_spurious_interrupt(void) { u32 v; - irq_enter(); - exit_idle(); /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1927,13 +1944,28 @@ void smp_spurious_interrupt(struct pt_regs *regs) /* see sw-dev-man vol 3, chapter 7.4.13.5 */ pr_info("spurious APIC interrupt on CPU#%d, " "should never happen.\n", smp_processor_id()); - irq_exit(); +} + +__visible void smp_spurious_interrupt(struct pt_regs *regs) +{ + entering_irq(); + __smp_spurious_interrupt(); + exiting_irq(); +} + +__visible void smp_trace_spurious_interrupt(struct pt_regs *regs) +{ + entering_irq(); + trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR); + __smp_spurious_interrupt(); + trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR); + exiting_irq(); } /* * This interrupt should never happen with our APIC/SMP architecture */ -void smp_error_interrupt(struct pt_regs *regs) +static inline void __smp_error_interrupt(struct pt_regs *regs) { u32 v0, v1; u32 i = 0; @@ -1948,8 +1980,6 @@ void smp_error_interrupt(struct pt_regs *regs) "Illegal register address", /* APIC Error Bit 7 */ }; - irq_enter(); - exit_idle(); /* First tickle the hardware, only then report what went on. -- REW */ v0 = apic_read(APIC_ESR); apic_write(APIC_ESR, 0); @@ -1970,7 +2000,22 @@ void smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT "\n"); - irq_exit(); +} + +__visible void smp_error_interrupt(struct pt_regs *regs) +{ + entering_irq(); + __smp_error_interrupt(regs); + exiting_irq(); +} + +__visible void smp_trace_error_interrupt(struct pt_regs *regs) +{ + entering_irq(); + trace_error_apic_entry(ERROR_APIC_VECTOR); + __smp_error_interrupt(regs); + trace_error_apic_exit(ERROR_APIC_VECTOR); + exiting_irq(); } /** @@ -2062,7 +2107,7 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -void __cpuinit generic_processor_info(int apicid, int version) +void generic_processor_info(int apicid, int version) { int cpu, max = nr_cpu_ids; bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid, @@ -2302,7 +2347,7 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL) +#if defined(CONFIG_X86_MCE_INTEL) if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif @@ -2332,7 +2377,7 @@ static struct syscore_ops lapic_syscore_ops = { .suspend = lapic_suspend, }; -static void __cpuinit apic_pm_activate(void) +static void apic_pm_activate(void) { apic_pm_state.active = 1; } @@ -2357,7 +2402,7 @@ static void apic_pm_activate(void) { } #ifdef CONFIG_X86_64 -static int __cpuinit apic_cluster_num(void) +static int apic_cluster_num(void) { int i, clusters, zeros; unsigned id; @@ -2402,10 +2447,10 @@ static int __cpuinit apic_cluster_num(void) return clusters; } -static int __cpuinitdata multi_checked; -static int __cpuinitdata multi; +static int multi_checked; +static int multi; -static int __cpuinit set_multi(const struct dmi_system_id *d) +static int set_multi(const struct dmi_system_id *d) { if (multi) return 0; @@ -2414,7 +2459,7 @@ static int __cpuinit set_multi(const struct dmi_system_id *d) return 0; } -static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = { +static const struct dmi_system_id multi_dmi_table[] = { { .callback = set_multi, .ident = "IBM System Summit2", @@ -2426,7 +2471,7 @@ static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = { {} }; -static void __cpuinit dmi_check_multi(void) +static void dmi_check_multi(void) { if (multi_checked) return; @@ -2443,7 +2488,7 @@ static void __cpuinit dmi_check_multi(void) * multi-chassis. * Use DMI to check them */ -__cpuinit int apic_is_clustered_box(void) +int apic_is_clustered_box(void) { dmi_check_multi(); if (multi) diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 9a91109..3e67f9e 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -74,7 +74,7 @@ static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } -static int __cpuinit numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) { union numachip_csr_g3_ext_irq_gen int_gen; diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 0874799..c552247 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -130,7 +130,7 @@ int es7000_plat; */ -static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) +static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip) { unsigned long vect = 0, psaival = 0; diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 31cb9ae..a698d71 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -9,6 +9,7 @@ * */ #include <asm/apic.h> +#include <asm/nmi.h> #include <linux/cpumask.h> #include <linux/kdebug.h> diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 9ed796c..e63a5bd 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1534,6 +1534,11 @@ void intel_ir_io_apic_print_entries(unsigned int apic, } } +void ioapic_zap_locks(void) +{ + raw_spin_lock_init(&ioapic_lock); +} + __apicdebuginit(void) print_IO_APIC(int ioapic_idx) { union IO_APIC_reg_00 reg_00; @@ -3375,12 +3380,15 @@ int io_apic_setup_irq_pin_once(unsigned int irq, int node, { unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin; int ret; + struct IO_APIC_route_entry orig_entry; /* Avoid redundant programming */ if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) { - pr_debug("Pin %d-%d already programmed\n", - mpc_ioapic_id(ioapic_idx), pin); - return 0; + pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin); + orig_entry = ioapic_read_entry(attr->ioapic, pin); + if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity) + return 0; + return -EBUSY; } ret = io_apic_setup_irq_pin(irq, node, attr); if (!ret) diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index d661ee9..1e42e8f 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -105,7 +105,7 @@ static void __init smp_dump_qct(void) } } -void __cpuinit numaq_tsc_disable(void) +void numaq_tsc_disable(void) { if (!found_numaq) return; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index c88baa4..140e29d 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -148,7 +148,7 @@ static void init_x2apic_ldr(void) /* * At CPU state changes, update the x2apic cluster sibling info. */ -static int __cpuinit +static int update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int this_cpu = (unsigned long)hcpu; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 794f6eb..1191ac1 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -25,6 +25,7 @@ #include <linux/kdebug.h> #include <linux/delay.h> #include <linux/crash_dump.h> +#include <linux/reboot.h> #include <asm/uv/uv_mmrs.h> #include <asm/uv/uv_hub.h> @@ -36,7 +37,6 @@ #include <asm/ipi.h> #include <asm/smp.h> #include <asm/x86_init.h> -#include <asm/emergency-restart.h> #include <asm/nmi.h> /* BMC sets a bit this MMR non-zero before sending an NMI */ @@ -51,6 +51,8 @@ DEFINE_PER_CPU(int, x2apic_extra_bits); static enum uv_system_type uv_system_type; static u64 gru_start_paddr, gru_end_paddr; +static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr; +static u64 gru_dist_lmask, gru_dist_umask; static union uvh_apicid uvh_apicid; int uv_min_hub_revision_id; EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); @@ -72,7 +74,20 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr) static inline bool is_GRU_range(u64 start, u64 end) { - return start >= gru_start_paddr && end <= gru_end_paddr; + if (gru_dist_base) { + u64 su = start & gru_dist_umask; /* upper (incl pnode) bits */ + u64 sl = start & gru_dist_lmask; /* base offset bits */ + u64 eu = end & gru_dist_umask; + u64 el = end & gru_dist_lmask; + + /* Must reside completely within a single GRU range */ + return (sl == gru_dist_base && el == gru_dist_base && + su >= gru_first_node_paddr && + su <= gru_last_node_paddr && + eu == su); + } else { + return start >= gru_start_paddr && end <= gru_end_paddr; + } } static bool uv_is_untracked_pat_range(u64 start, u64 end) @@ -194,7 +209,7 @@ EXPORT_SYMBOL_GPL(uv_possible_blades); unsigned long sn_rtc_cycles_per_second; EXPORT_SYMBOL(sn_rtc_cycles_per_second); -static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) +static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { #ifdef CONFIG_SMP unsigned long val; @@ -401,7 +416,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .safe_wait_icr_idle = native_safe_x2apic_wait_icr_idle, }; -static __cpuinit void set_x2apic_extra_bits(int pnode) +static void set_x2apic_extra_bits(int pnode) { __this_cpu_write(x2apic_extra_bits, pnode << uvh_apicid.s.pnode_shift); } @@ -463,26 +478,63 @@ static __init void map_high(char *id, unsigned long base, int pshift, pr_info("UV: Map %s_HI base address NULL\n", id); return; } - pr_info("UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); + pr_debug("UV: Map %s_HI 0x%lx - 0x%lx\n", id, paddr, paddr + bytes); if (map_type == map_uc) init_extra_mapping_uc(paddr, bytes); else init_extra_mapping_wb(paddr, bytes); } +static __init void map_gru_distributed(unsigned long c) +{ + union uvh_rh_gam_gru_overlay_config_mmr_u gru; + u64 paddr; + unsigned long bytes; + int nid; + + gru.v = c; + /* only base bits 42:28 relevant in dist mode */ + gru_dist_base = gru.v & 0x000007fff0000000UL; + if (!gru_dist_base) { + pr_info("UV: Map GRU_DIST base address NULL\n"); + return; + } + bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; + gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1); + gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1); + gru_dist_base &= gru_dist_lmask; /* Clear bits above M */ + for_each_online_node(nid) { + paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) | + gru_dist_base; + init_extra_mapping_wb(paddr, bytes); + gru_first_node_paddr = min(paddr, gru_first_node_paddr); + gru_last_node_paddr = max(paddr, gru_last_node_paddr); + } + /* Save upper (63:M) bits of address only for is_GRU_range */ + gru_first_node_paddr &= gru_dist_umask; + gru_last_node_paddr &= gru_dist_umask; + pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", + gru_dist_base, gru_first_node_paddr, gru_last_node_paddr); +} + static __init void map_gru_high(int max_pnode) { union uvh_rh_gam_gru_overlay_config_mmr_u gru; int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR); - if (gru.s.enable) { - map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); - gru_start_paddr = ((u64)gru.s.base << shift); - gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); - } else { + if (!gru.s.enable) { pr_info("UV: GRU disabled\n"); + return; + } + + if (is_uv3_hub() && gru.s3.mode) { + map_gru_distributed(gru.v); + return; } + map_high("GRU", gru.s.base, shift, shift, max_pnode, map_wb); + gru_start_paddr = ((u64)gru.s.base << shift); + gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); } static __init void map_mmr_high(int max_pnode) @@ -683,7 +735,7 @@ static void uv_heartbeat(unsigned long ignored) mod_timer_pinned(timer, jiffies + SCIR_CPU_HB_INTERVAL); } -static void __cpuinit uv_heartbeat_enable(int cpu) +static void uv_heartbeat_enable(int cpu) { while (!uv_cpu_hub_info(cpu)->scir.enabled) { struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer; @@ -700,7 +752,7 @@ static void __cpuinit uv_heartbeat_enable(int cpu) } #ifdef CONFIG_HOTPLUG_CPU -static void __cpuinit uv_heartbeat_disable(int cpu) +static void uv_heartbeat_disable(int cpu) { if (uv_cpu_hub_info(cpu)->scir.enabled) { uv_cpu_hub_info(cpu)->scir.enabled = 0; @@ -712,8 +764,8 @@ static void __cpuinit uv_heartbeat_disable(int cpu) /* * cpu hotplug notifier */ -static __cpuinit int uv_scir_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int uv_scir_cpu_notify(struct notifier_block *self, unsigned long action, + void *hcpu) { long cpu = (long)hcpu; @@ -783,7 +835,7 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode, * Called on each cpu to initialize the per_cpu UV data area. * FIXME: hotplug not supported yet */ -void __cpuinit uv_cpu_init(void) +void uv_cpu_init(void) { /* CPU 0 initilization will be done via uv_system_init. */ if (!uv_blade_info) diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 53a4e27..3ab0343 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -392,7 +392,7 @@ static struct cpuidle_device apm_cpuidle_device; /* * Local variables */ -static struct { +__visible struct { unsigned long offset; unsigned short segment; } apm_bios_entry; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 0ef4bba..d67c4be 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -28,7 +28,6 @@ void foo(void) OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); OFFSET(CPUINFO_x86_mask, cpuinfo_x86, x86_mask); - OFFSET(CPUINFO_hard_math, cpuinfo_x86, hard_math); OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level); OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability); OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index b0684e4..47b56a7 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -31,11 +31,15 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_PERF_EVENTS obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o perf_event_amd_uncore.o +ifdef CONFIG_AMD_IOMMU +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o +endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o endif + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5013a48..903a264 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -66,10 +66,10 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) * performance at the same time.. */ -extern void vide(void); -__asm__(".align 4\nvide: ret"); +extern __visible void vide(void); +__asm__(".globl vide\n\t.align 4\nvide: ret"); -static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c) +static void init_amd_k5(struct cpuinfo_x86 *c) { /* * General Systems BIOSen alias the cpu frequency registers @@ -87,10 +87,10 @@ static void __cpuinit init_amd_k5(struct cpuinfo_x86 *c) } -static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) +static void init_amd_k6(struct cpuinfo_x86 *c) { u32 l, h; - int mbytes = num_physpages >> (20-PAGE_SHIFT); + int mbytes = get_num_physpages() >> (20-PAGE_SHIFT); if (c->x86_model < 6) { /* Based on AMD doc 20734R - June 2000 */ @@ -179,7 +179,7 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c) } } -static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) +static void amd_k7_smp_check(struct cpuinfo_x86 *c) { /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) @@ -222,7 +222,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE); } -static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) +static void init_amd_k7(struct cpuinfo_x86 *c) { u32 l, h; @@ -267,7 +267,7 @@ static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) * To workaround broken NUMA config. Read the comment in * srat_detect_node(). */ -static int __cpuinit nearby_node(int apicid) +static int nearby_node(int apicid) { int i, node; @@ -292,7 +292,7 @@ static int __cpuinit nearby_node(int apicid) * (2) AMD processors supporting compute units */ #ifdef CONFIG_X86_HT -static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) +static void amd_get_topology(struct cpuinfo_x86 *c) { u32 nodes, cores_per_cu = 1; u8 node_id; @@ -342,7 +342,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c) * On a AMD dual core setup the lower bits of the APIC id distingush the cores. * Assumes number of cores is a power of two. */ -static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) +static void amd_detect_cmp(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_HT unsigned bits; @@ -369,7 +369,7 @@ u16 amd_get_nb_id(int cpu) } EXPORT_SYMBOL_GPL(amd_get_nb_id); -static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) +static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA int cpu = smp_processor_id(); @@ -421,7 +421,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c) +static void early_init_amd_mc(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_HT unsigned bits, ecx; @@ -447,7 +447,7 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c) #endif } -static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c) +static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -475,7 +475,7 @@ static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c) } } -static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) +static void early_init_amd(struct cpuinfo_x86 *c) { early_init_amd_mc(c); @@ -512,9 +512,9 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) static const int amd_erratum_383[]; static const int amd_erratum_400[]; -static bool cpu_has_amd_erratum(const int *erratum); +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); -static void __cpuinit init_amd(struct cpuinfo_x86 *c) +static void init_amd(struct cpuinfo_x86 *c) { u32 dummy; unsigned long long value; @@ -729,19 +729,18 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) value &= ~(1ULL << 24); wrmsrl_safe(MSR_AMD64_BU_CFG2, value); - if (cpu_has_amd_erratum(amd_erratum_383)) + if (cpu_has_amd_erratum(c, amd_erratum_383)) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } - if (cpu_has_amd_erratum(amd_erratum_400)) + if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); } #ifdef CONFIG_X86_32 -static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, - unsigned int size) +static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ if ((c->x86 == 6)) { @@ -757,7 +756,7 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c, } #endif -static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) +static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) { tlb_flushall_shift = 5; @@ -765,7 +764,7 @@ static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) tlb_flushall_shift = 4; } -static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c) +static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) { u32 ebx, eax, ecx, edx; u16 mask = 0xfff; @@ -820,7 +819,7 @@ static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c) cpu_set_tlb_flushall_shift(c); } -static const struct cpu_dev __cpuinitconst amd_cpu_dev = { +static const struct cpu_dev amd_cpu_dev = { .c_vendor = "AMD", .c_ident = { "AuthenticAMD" }, #ifdef CONFIG_X86_32 @@ -879,23 +878,13 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); -static bool cpu_has_amd_erratum(const int *erratum) + +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { - struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info); int osvw_id = *erratum++; u32 range; u32 ms; - /* - * If called early enough that current_cpu_data hasn't been initialized - * yet, fall back to boot_cpu_data. - */ - if (cpu->x86 == 0) - cpu = &boot_cpu_data; - - if (cpu->x86_vendor != X86_VENDOR_AMD) - return false; - if (osvw_id >= 0 && osvw_id < 65536 && cpu_has(cpu, X86_FEATURE_OSVW)) { u64 osvw_len; diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4112be9..0344534 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -17,15 +17,6 @@ #include <asm/paravirt.h> #include <asm/alternative.h> -static int __init no_387(char *s) -{ - boot_cpu_data.hard_math = 0; - write_cr0(X86_CR0_TS | X86_CR0_EM | X86_CR0_MP | read_cr0()); - return 1; -} - -__setup("no387", no_387); - static double __initdata x = 4195835.0; static double __initdata y = 3145727.0; @@ -44,15 +35,6 @@ static void __init check_fpu(void) { s32 fdiv_bug; - if (!boot_cpu_data.hard_math) { -#ifndef CONFIG_MATH_EMULATION - pr_emerg("No coprocessor found and no math emulation present\n"); - pr_emerg("Giving up\n"); - for (;;) ; -#endif - return; - } - kernel_fpu_begin(); /* @@ -107,5 +89,6 @@ void __init check_bugs(void) * kernel_fpu_begin/end() in check_fpu() relies on the patched * alternative instructions. */ - check_fpu(); + if (cpu_has_fpu) + check_fpu(); } diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 159103c..fbf6c3b 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -11,7 +11,7 @@ #ifdef CONFIG_X86_OOSTORE -static u32 __cpuinit power2(u32 x) +static u32 power2(u32 x) { u32 s = 1; @@ -25,7 +25,7 @@ static u32 __cpuinit power2(u32 x) /* * Set up an actual MCR */ -static void __cpuinit centaur_mcr_insert(int reg, u32 base, u32 size, int key) +static void centaur_mcr_insert(int reg, u32 base, u32 size, int key) { u32 lo, hi; @@ -42,7 +42,7 @@ static void __cpuinit centaur_mcr_insert(int reg, u32 base, u32 size, int key) * * Shortcut: We know you can't put 4Gig of RAM on a winchip */ -static u32 __cpuinit ramtop(void) +static u32 ramtop(void) { u32 clip = 0xFFFFFFFFUL; u32 top = 0; @@ -91,7 +91,7 @@ static u32 __cpuinit ramtop(void) /* * Compute a set of MCR's to give maximum coverage */ -static int __cpuinit centaur_mcr_compute(int nr, int key) +static int centaur_mcr_compute(int nr, int key) { u32 mem = ramtop(); u32 root = power2(mem); @@ -157,7 +157,7 @@ static int __cpuinit centaur_mcr_compute(int nr, int key) return ct; } -static void __cpuinit centaur_create_optimal_mcr(void) +static void centaur_create_optimal_mcr(void) { int used; int i; @@ -181,7 +181,7 @@ static void __cpuinit centaur_create_optimal_mcr(void) wrmsr(MSR_IDT_MCR0+i, 0, 0); } -static void __cpuinit winchip2_create_optimal_mcr(void) +static void winchip2_create_optimal_mcr(void) { u32 lo, hi; int used; @@ -217,7 +217,7 @@ static void __cpuinit winchip2_create_optimal_mcr(void) /* * Handle the MCR key on the Winchip 2. */ -static void __cpuinit winchip2_unprotect_mcr(void) +static void winchip2_unprotect_mcr(void) { u32 lo, hi; u32 key; @@ -229,7 +229,7 @@ static void __cpuinit winchip2_unprotect_mcr(void) wrmsr(MSR_IDT_MCR_CTRL, lo, hi); } -static void __cpuinit winchip2_protect_mcr(void) +static void winchip2_protect_mcr(void) { u32 lo, hi; @@ -247,7 +247,7 @@ static void __cpuinit winchip2_protect_mcr(void) #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */ -static void __cpuinit init_c3(struct cpuinfo_x86 *c) +static void init_c3(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -318,7 +318,7 @@ enum { EAMD3D = 1<<20, }; -static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) +static void early_init_centaur(struct cpuinfo_x86 *c) { switch (c->x86) { #ifdef CONFIG_X86_32 @@ -337,7 +337,7 @@ static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c) #endif } -static void __cpuinit init_centaur(struct cpuinfo_x86 *c) +static void init_centaur(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 char *name; @@ -468,7 +468,7 @@ static void __cpuinit init_centaur(struct cpuinfo_x86 *c) #endif } -static unsigned int __cpuinit +static unsigned int centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) { #ifdef CONFIG_X86_32 @@ -488,7 +488,7 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size) return size; } -static const struct cpu_dev __cpuinitconst centaur_cpu_dev = { +static const struct cpu_dev centaur_cpu_dev = { .c_vendor = "Centaur", .c_ident = { "CentaurHauls" }, .c_early_init = early_init_centaur, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 22018f7..2793d1f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -63,7 +63,7 @@ void __init setup_cpu_local_masks(void) alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); } -static void __cpuinit default_init(struct cpuinfo_x86 *c) +static void default_init(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 cpu_detect_cache_sizes(c); @@ -80,13 +80,13 @@ static void __cpuinit default_init(struct cpuinfo_x86 *c) #endif } -static const struct cpu_dev __cpuinitconst default_cpu = { +static const struct cpu_dev default_cpu = { .c_init = default_init, .c_vendor = "Unknown", .c_x86_vendor = X86_VENDOR_UNKNOWN, }; -static const struct cpu_dev *this_cpu __cpuinitdata = &default_cpu; +static const struct cpu_dev *this_cpu = &default_cpu; DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { #ifdef CONFIG_X86_64 @@ -160,8 +160,8 @@ static int __init x86_xsaveopt_setup(char *s) __setup("noxsaveopt", x86_xsaveopt_setup); #ifdef CONFIG_X86_32 -static int cachesize_override __cpuinitdata = -1; -static int disable_x86_serial_nr __cpuinitdata = 1; +static int cachesize_override = -1; +static int disable_x86_serial_nr = 1; static int __init cachesize_setup(char *str) { @@ -215,12 +215,12 @@ static inline int flag_is_changeable_p(u32 flag) } /* Probe for the CPUID instruction */ -int __cpuinit have_cpuid_p(void) +int have_cpuid_p(void) { return flag_is_changeable_p(X86_EFLAGS_ID); } -static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c) +static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) { unsigned long lo, hi; @@ -298,7 +298,7 @@ struct cpuid_dependent_feature { u32 level; }; -static const struct cpuid_dependent_feature __cpuinitconst +static const struct cpuid_dependent_feature cpuid_dependent_features[] = { { X86_FEATURE_MWAIT, 0x00000005 }, { X86_FEATURE_DCA, 0x00000009 }, @@ -306,7 +306,7 @@ cpuid_dependent_features[] = { { 0, 0 } }; -static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) +static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) { const struct cpuid_dependent_feature *df; @@ -344,7 +344,7 @@ static void __cpuinit filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) */ /* Look up CPU names by table lookup. */ -static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c) +static const char *table_lookup_model(struct cpuinfo_x86 *c) { const struct cpu_model_info *info; @@ -364,8 +364,8 @@ static const char *__cpuinit table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS] __cpuinitdata; -__u32 cpu_caps_set[NCAPINTS] __cpuinitdata; +__u32 cpu_caps_cleared[NCAPINTS]; +__u32 cpu_caps_set[NCAPINTS]; void load_percpu_segment(int cpu) { @@ -394,9 +394,9 @@ void switch_to_new_gdt(int cpu) load_percpu_segment(cpu); } -static const struct cpu_dev *__cpuinitdata cpu_devs[X86_VENDOR_NUM] = {}; +static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; -static void __cpuinit get_model_name(struct cpuinfo_x86 *c) +static void get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; char *p, *q; @@ -425,7 +425,7 @@ static void __cpuinit get_model_name(struct cpuinfo_x86 *c) } } -void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c) +void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) { unsigned int n, dummy, ebx, ecx, edx, l2size; @@ -479,7 +479,7 @@ u16 __read_mostly tlb_lld_4m[NR_INFO]; */ s8 __read_mostly tlb_flushall_shift = -1; -void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c) +void cpu_detect_tlb(struct cpuinfo_x86 *c) { if (this_cpu->c_detect_tlb) this_cpu->c_detect_tlb(c); @@ -493,7 +493,7 @@ void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_flushall_shift); } -void __cpuinit detect_ht(struct cpuinfo_x86 *c) +void detect_ht(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_HT u32 eax, ebx, ecx, edx; @@ -544,7 +544,7 @@ out: #endif } -static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) +static void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -571,7 +571,7 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c) this_cpu = &default_cpu; } -void __cpuinit cpu_detect(struct cpuinfo_x86 *c) +void cpu_detect(struct cpuinfo_x86 *c) { /* Get vendor name */ cpuid(0x00000000, (unsigned int *)&c->cpuid_level, @@ -601,7 +601,7 @@ void __cpuinit cpu_detect(struct cpuinfo_x86 *c) } } -void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) +void get_cpu_cap(struct cpuinfo_x86 *c) { u32 tfms, xlvl; u32 ebx; @@ -652,7 +652,7 @@ void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) init_scattered_cpuid_features(c); } -static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c) +static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 int i; @@ -711,10 +711,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) return; cpu_detect(c); - get_cpu_vendor(c); - get_cpu_cap(c); + fpu_detect(c); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -724,6 +723,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (this_cpu->c_bsp_init) this_cpu->c_bsp_init(c); + + setup_force_cpu_cap(X86_FEATURE_ALWAYS); } void __init early_cpu_init(void) @@ -768,7 +769,7 @@ void __init early_cpu_init(void) * 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) +static void detect_nopl(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 clear_cpu_cap(c, X86_FEATURE_NOPL); @@ -777,7 +778,7 @@ static void __cpuinit detect_nopl(struct cpuinfo_x86 *c) #endif } -static void __cpuinit generic_identify(struct cpuinfo_x86 *c) +static void generic_identify(struct cpuinfo_x86 *c) { c->extended_cpuid_level = 0; @@ -814,7 +815,7 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c) /* * This does the hard work of actually picking apart the CPU stuff... */ -static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) +static void identify_cpu(struct cpuinfo_x86 *c) { int i; @@ -959,7 +960,7 @@ void __init identify_boot_cpu(void) cpu_detect_tlb(&boot_cpu_data); } -void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c) +void identify_secondary_cpu(struct cpuinfo_x86 *c) { BUG_ON(c == &boot_cpu_data); identify_cpu(c); @@ -974,14 +975,14 @@ struct msr_range { unsigned max; }; -static const struct msr_range msr_range_array[] __cpuinitconst = { +static const struct msr_range msr_range_array[] = { { 0x00000000, 0x00000418}, { 0xc0000000, 0xc000040b}, { 0xc0010000, 0xc0010142}, { 0xc0011000, 0xc001103b}, }; -static void __cpuinit __print_cpu_msr(void) +static void __print_cpu_msr(void) { unsigned index_min, index_max; unsigned index; @@ -1000,7 +1001,7 @@ static void __cpuinit __print_cpu_msr(void) } } -static int show_msr __cpuinitdata; +static int show_msr; static __init int setup_show_msr(char *arg) { @@ -1021,7 +1022,7 @@ static __init int setup_noclflush(char *arg) } __setup("noclflush", setup_noclflush); -void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) +void print_cpu_info(struct cpuinfo_x86 *c) { const char *vendor = NULL; @@ -1050,7 +1051,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) print_cpu_msr(c); } -void __cpuinit print_cpu_msr(struct cpuinfo_x86 *c) +void print_cpu_msr(struct cpuinfo_x86 *c) { if (c->cpu_index < show_msr) __print_cpu_msr(); @@ -1071,11 +1072,11 @@ __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; -struct desc_ptr nmi_idt_descr = { NR_VECTORS * 16 - 1, - (unsigned long) nmi_idt_table }; +struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, + (unsigned long) debug_idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, - irq_stack_union) __aligned(PAGE_SIZE); + irq_stack_union) __aligned(PAGE_SIZE) __visible; /* * The following four percpu variables are hot. Align current_task to @@ -1092,7 +1093,7 @@ EXPORT_PER_CPU_SYMBOL(kernel_stack); DEFINE_PER_CPU(char *, irq_stack_ptr) = init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; -DEFINE_PER_CPU(unsigned int, irq_count) = -1; +DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); @@ -1148,20 +1149,20 @@ int is_debug_stack(unsigned long addr) addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); } -static DEFINE_PER_CPU(u32, debug_stack_use_ctr); +DEFINE_PER_CPU(u32, debug_idt_ctr); void debug_stack_set_zero(void) { - this_cpu_inc(debug_stack_use_ctr); - load_idt((const struct desc_ptr *)&nmi_idt_descr); + this_cpu_inc(debug_idt_ctr); + load_current_idt(); } void debug_stack_reset(void) { - if (WARN_ON(!this_cpu_read(debug_stack_use_ctr))) + if (WARN_ON(!this_cpu_read(debug_idt_ctr))) return; - if (this_cpu_dec_return(debug_stack_use_ctr) == 0) - load_idt((const struct desc_ptr *)&idt_descr); + if (this_cpu_dec_return(debug_idt_ctr) == 0) + load_current_idt(); } #else /* CONFIG_X86_64 */ @@ -1215,7 +1216,7 @@ static void dbg_restore_debug_regs(void) */ #ifdef CONFIG_X86_64 -void __cpuinit cpu_init(void) +void cpu_init(void) { struct orig_ist *oist; struct task_struct *me; @@ -1257,7 +1258,7 @@ void __cpuinit cpu_init(void) switch_to_new_gdt(cpu); loadsegment(fs, 0); - load_idt((const struct desc_ptr *)&idt_descr); + load_current_idt(); memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); syscall_init(); @@ -1314,7 +1315,7 @@ void __cpuinit cpu_init(void) #else -void __cpuinit cpu_init(void) +void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; @@ -1334,7 +1335,7 @@ void __cpuinit cpu_init(void) if (cpu_has_vme || cpu_has_tsc || cpu_has_de) clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - load_idt(&idt_descr); + load_current_idt(); switch_to_new_gdt(cpu); /* @@ -1363,3 +1364,17 @@ void __cpuinit cpu_init(void) fpu_init(); } #endif + +#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS +void warn_pre_alternatives(void) +{ + WARN(1, "You're using static_cpu_has before alternatives have run!\n"); +} +EXPORT_SYMBOL_GPL(warn_pre_alternatives); +#endif + +inline bool __static_cpu_has_safe(u16 bit) +{ + return boot_cpu_has(bit); +} +EXPORT_SYMBOL_GPL(__static_cpu_has_safe); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index d048d5c..d0969c7 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -15,7 +15,7 @@ /* * Read NSC/Cyrix DEVID registers (DIR) to get more detailed info. about the CPU */ -static void __cpuinit __do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) +static void __do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) { unsigned char ccr2, ccr3; @@ -44,7 +44,7 @@ static void __cpuinit __do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) } } -static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) +static void do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) { unsigned long flags; @@ -59,25 +59,25 @@ static void __cpuinit do_cyrix_devid(unsigned char *dir0, unsigned char *dir1) * Actually since bugs.h doesn't even reference this perhaps someone should * fix the documentation ??? */ -static unsigned char Cx86_dir0_msb __cpuinitdata = 0; +static unsigned char Cx86_dir0_msb = 0; -static const char __cpuinitconst Cx86_model[][9] = { +static const char Cx86_model[][9] = { "Cx486", "Cx486", "5x86 ", "6x86", "MediaGX ", "6x86MX ", "M II ", "Unknown" }; -static const char __cpuinitconst Cx486_name[][5] = { +static const char Cx486_name[][5] = { "SLC", "DLC", "SLC2", "DLC2", "SRx", "DRx", "SRx2", "DRx2" }; -static const char __cpuinitconst Cx486S_name[][4] = { +static const char Cx486S_name[][4] = { "S", "S2", "Se", "S2e" }; -static const char __cpuinitconst Cx486D_name[][4] = { +static const char Cx486D_name[][4] = { "DX", "DX2", "?", "?", "?", "DX4" }; -static char Cx86_cb[] __cpuinitdata = "?.5x Core/Bus Clock"; -static const char __cpuinitconst cyrix_model_mult1[] = "12??43"; -static const char __cpuinitconst cyrix_model_mult2[] = "12233445"; +static char Cx86_cb[] = "?.5x Core/Bus Clock"; +static const char cyrix_model_mult1[] = "12??43"; +static const char cyrix_model_mult2[] = "12233445"; /* * Reset the slow-loop (SLOP) bit on the 686(L) which is set by some old @@ -87,7 +87,7 @@ static const char __cpuinitconst cyrix_model_mult2[] = "12233445"; * FIXME: our newer udelay uses the tsc. We don't need to frob with SLOP */ -static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c) +static void check_cx686_slop(struct cpuinfo_x86 *c) { unsigned long flags; @@ -112,7 +112,7 @@ static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c) } -static void __cpuinit set_cx86_reorder(void) +static void set_cx86_reorder(void) { u8 ccr3; @@ -127,7 +127,7 @@ static void __cpuinit set_cx86_reorder(void) setCx86(CX86_CCR3, ccr3); } -static void __cpuinit set_cx86_memwb(void) +static void set_cx86_memwb(void) { printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); @@ -143,7 +143,7 @@ static void __cpuinit set_cx86_memwb(void) * Configure later MediaGX and/or Geode processor. */ -static void __cpuinit geode_configure(void) +static void geode_configure(void) { unsigned long flags; u8 ccr3; @@ -166,7 +166,7 @@ static void __cpuinit geode_configure(void) local_irq_restore(flags); } -static void __cpuinit early_init_cyrix(struct cpuinfo_x86 *c) +static void early_init_cyrix(struct cpuinfo_x86 *c) { unsigned char dir0, dir0_msn, dir1 = 0; @@ -185,7 +185,7 @@ static void __cpuinit early_init_cyrix(struct cpuinfo_x86 *c) } } -static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) +static void init_cyrix(struct cpuinfo_x86 *c) { unsigned char dir0, dir0_msn, dir0_lsn, dir1 = 0; char *buf = c->x86_model_id; @@ -333,7 +333,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) switch (dir0_lsn) { case 0xd: /* either a 486SLC or DLC w/o DEVID */ dir0_msn = 0; - p = Cx486_name[(c->hard_math) ? 1 : 0]; + p = Cx486_name[(cpu_has_fpu ? 1 : 0)]; break; case 0xe: /* a 486S A step */ @@ -356,7 +356,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) /* * Handle National Semiconductor branded processors */ -static void __cpuinit init_nsc(struct cpuinfo_x86 *c) +static void init_nsc(struct cpuinfo_x86 *c) { /* * There may be GX1 processors in the wild that are branded @@ -405,7 +405,7 @@ static inline int test_cyrix_52div(void) return (unsigned char) (test >> 8) == 0x02; } -static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c) +static void cyrix_identify(struct cpuinfo_x86 *c) { /* Detect Cyrix with disabled CPUID */ if (c->x86 == 4 && test_cyrix_52div()) { @@ -441,7 +441,7 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 *c) } } -static const struct cpu_dev __cpuinitconst cyrix_cpu_dev = { +static const struct cpu_dev cyrix_cpu_dev = { .c_vendor = "Cyrix", .c_ident = { "CyrixInstead" }, .c_early_init = early_init_cyrix, @@ -452,7 +452,7 @@ static const struct cpu_dev __cpuinitconst cyrix_cpu_dev = { cpu_dev_register(cyrix_cpu_dev); -static const struct cpu_dev __cpuinitconst nsc_cpu_dev = { +static const struct cpu_dev nsc_cpu_dev = { .c_vendor = "NSC", .c_ident = { "Geode by NSC" }, .c_init = init_nsc, diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 1e7e84a..36ce402 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -25,11 +25,6 @@ #include <asm/processor.h> #include <asm/hypervisor.h> -/* - * Hypervisor detect order. This is specified explicitly here because - * some hypervisors might implement compatibility modes for other - * hypervisors and therefore need to be detected in specific sequence. - */ static const __initconst struct hypervisor_x86 * const hypervisors[] = { #ifdef CONFIG_XEN_PVHVM @@ -49,18 +44,22 @@ static inline void __init detect_hypervisor_vendor(void) { const struct hypervisor_x86 *h, * const *p; + uint32_t pri, max_pri = 0; for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { h = *p; - if (h->detect()) { + pri = h->detect(); + if (pri != 0 && pri > max_pri) { + max_pri = pri; x86_hyper = h; - printk(KERN_INFO "Hypervisor detected: %s\n", h->name); - break; } } + + if (max_pri) + printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name); } -void __cpuinit init_hypervisor(struct cpuinfo_x86 *c) +void init_hypervisor(struct cpuinfo_x86 *c) { if (x86_hyper && x86_hyper->set_cpu_features) x86_hyper->set_cpu_features(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9b0c441..ec72995 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -26,7 +26,7 @@ #include <asm/apic.h> #endif -static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) +static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -163,7 +163,7 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) * This is called before we do cpu ident work */ -int __cpuinit ppro_with_ram_bug(void) +int ppro_with_ram_bug(void) { /* Uses data from early_cpu_detect now */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && @@ -176,7 +176,7 @@ int __cpuinit ppro_with_ram_bug(void) return 0; } -static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) +static void intel_smp_check(struct cpuinfo_x86 *c) { /* calling is from identify_secondary_cpu() ? */ if (!c->cpu_index) @@ -196,7 +196,7 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) } } -static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) +static void intel_workarounds(struct cpuinfo_x86 *c) { unsigned long lo, hi; @@ -275,12 +275,12 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) intel_smp_check(c); } #else -static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) +static void intel_workarounds(struct cpuinfo_x86 *c) { } #endif -static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) +static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA unsigned node; @@ -300,7 +300,7 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) /* * find out the number of processor cores on the die */ -static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c) +static int intel_num_cpu_cores(struct cpuinfo_x86 *c) { unsigned int eax, ebx, ecx, edx; @@ -315,7 +315,7 @@ static int __cpuinit intel_num_cpu_cores(struct cpuinfo_x86 *c) return 1; } -static void __cpuinit detect_vmx_virtcap(struct cpuinfo_x86 *c) +static void detect_vmx_virtcap(struct cpuinfo_x86 *c) { /* Intel VMX MSR indicated features */ #define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 @@ -353,7 +353,7 @@ static void __cpuinit detect_vmx_virtcap(struct cpuinfo_x86 *c) } } -static void __cpuinit init_intel(struct cpuinfo_x86 *c) +static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -472,7 +472,7 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) } #ifdef CONFIG_X86_32 -static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) +static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* * Intel PIII Tualatin. This comes in two flavours. @@ -506,7 +506,7 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i #define STLB_4K 0x41 -static const struct _tlb_table intel_tlb_table[] __cpuinitconst = { +static const struct _tlb_table intel_tlb_table[] = { { 0x01, TLB_INST_4K, 32, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0x02, TLB_INST_4M, 2, " TLB_INST 4 MByte pages, full associative" }, { 0x03, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way set associative" }, @@ -536,7 +536,7 @@ static const struct _tlb_table intel_tlb_table[] __cpuinitconst = { { 0x00, 0, 0 } }; -static void __cpuinit intel_tlb_lookup(const unsigned char desc) +static void intel_tlb_lookup(const unsigned char desc) { unsigned char k; if (desc == 0) @@ -605,7 +605,7 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc) } } -static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) +static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) { switch ((c->x86 << 8) + c->x86_model) { case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ @@ -634,7 +634,7 @@ static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) } } -static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c) +static void intel_detect_tlb(struct cpuinfo_x86 *c) { int i, j, n; unsigned int regs[4]; @@ -661,7 +661,7 @@ static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c) intel_tlb_flushall_shift_set(c); } -static const struct cpu_dev __cpuinitconst intel_cpu_dev = { +static const struct cpu_dev intel_cpu_dev = { .c_vendor = "Intel", .c_ident = { "GenuineIntel" }, #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 7c6f7d5..1414c90 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -37,7 +37,7 @@ struct _cache_table { /* All the cache descriptor types we care about (no TLB or trace cache entries) */ -static const struct _cache_table __cpuinitconst cache_table[] = +static const struct _cache_table cache_table[] = { { 0x06, LVL_1_INST, 8 }, /* 4-way set assoc, 32 byte line size */ { 0x08, LVL_1_INST, 16 }, /* 4-way set assoc, 32 byte line size */ @@ -203,7 +203,7 @@ union l3_cache { unsigned val; }; -static const unsigned short __cpuinitconst assocs[] = { +static const unsigned short assocs[] = { [1] = 1, [2] = 2, [4] = 4, @@ -217,10 +217,10 @@ static const unsigned short __cpuinitconst assocs[] = { [0xf] = 0xffff /* fully associative - no way to show this currently */ }; -static const unsigned char __cpuinitconst levels[] = { 1, 1, 2, 3 }; -static const unsigned char __cpuinitconst types[] = { 1, 2, 3, 3 }; +static const unsigned char levels[] = { 1, 1, 2, 3 }; +static const unsigned char types[] = { 1, 2, 3, 3 }; -static void __cpuinit +static void amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, union _cpuid4_leaf_ebx *ebx, union _cpuid4_leaf_ecx *ecx) @@ -302,7 +302,7 @@ struct _cache_attr { /* * L3 cache descriptors */ -static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb) +static void amd_calc_l3_indices(struct amd_northbridge *nb) { struct amd_l3_cache *l3 = &nb->l3_cache; unsigned int sc0, sc1, sc2, sc3; @@ -325,7 +325,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb) l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } -static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) +static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) { int node; @@ -528,8 +528,7 @@ static struct _cache_attr subcaches = #endif /* CONFIG_AMD_NB && CONFIG_SYSFS */ static int -__cpuinit cpuid4_cache_lookup_regs(int index, - struct _cpuid4_info_regs *this_leaf) +cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) { union _cpuid4_leaf_eax eax; union _cpuid4_leaf_ebx ebx; @@ -560,7 +559,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int __cpuinit find_num_cache_leaves(struct cpuinfo_x86 *c) +static int find_num_cache_leaves(struct cpuinfo_x86 *c) { unsigned int eax, ebx, ecx, edx, op; union _cpuid4_leaf_eax cache_eax; @@ -580,7 +579,7 @@ static int __cpuinit find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } -void __cpuinit init_amd_cacheinfo(struct cpuinfo_x86 *c) +void init_amd_cacheinfo(struct cpuinfo_x86 *c) { if (cpu_has_topoext) { @@ -593,7 +592,7 @@ void __cpuinit init_amd_cacheinfo(struct cpuinfo_x86 *c) } } -unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) +unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) { /* Cache sizes */ unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; @@ -618,36 +617,34 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) * parameters cpuid leaf to find the cache details */ for (i = 0; i < num_cache_leaves; i++) { - struct _cpuid4_info_regs this_leaf; + struct _cpuid4_info_regs this_leaf = {}; int retval; retval = cpuid4_cache_lookup_regs(i, &this_leaf); - if (retval >= 0) { - switch (this_leaf.eax.split.level) { - case 1: - if (this_leaf.eax.split.type == - CACHE_TYPE_DATA) - new_l1d = this_leaf.size/1024; - else if (this_leaf.eax.split.type == - CACHE_TYPE_INST) - new_l1i = this_leaf.size/1024; - break; - case 2: - new_l2 = this_leaf.size/1024; - num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; - index_msb = get_count_order(num_threads_sharing); - l2_id = c->apicid & ~((1 << index_msb) - 1); - break; - case 3: - new_l3 = this_leaf.size/1024; - num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; - index_msb = get_count_order( - num_threads_sharing); - l3_id = c->apicid & ~((1 << index_msb) - 1); - break; - default: - break; - } + if (retval < 0) + continue; + + switch (this_leaf.eax.split.level) { + case 1: + if (this_leaf.eax.split.type == CACHE_TYPE_DATA) + new_l1d = this_leaf.size/1024; + else if (this_leaf.eax.split.type == CACHE_TYPE_INST) + new_l1i = this_leaf.size/1024; + break; + case 2: + new_l2 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l2_id = c->apicid & ~((1 << index_msb) - 1); + break; + case 3: + new_l3 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l3_id = c->apicid & ~((1 << index_msb) - 1); + break; + default: + break; } } } @@ -746,7 +743,7 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); #ifdef CONFIG_SMP -static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) +static int cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf; int i, sibling; @@ -795,7 +792,7 @@ static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) return 1; } -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) +static void cache_shared_cpu_map_setup(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf, *sibling_leaf; unsigned long num_threads_sharing; @@ -830,7 +827,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) } } } -static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) +static void cache_remove_shared_cpu_map(unsigned int cpu, int index) { struct _cpuid4_info *this_leaf, *sibling_leaf; int sibling; @@ -843,16 +840,16 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) } } #else -static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) +static void cache_shared_cpu_map_setup(unsigned int cpu, int index) { } -static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) +static void cache_remove_shared_cpu_map(unsigned int cpu, int index) { } #endif -static void __cpuinit free_cache_attributes(unsigned int cpu) +static void free_cache_attributes(unsigned int cpu) { int i; @@ -863,7 +860,7 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) per_cpu(ici_cpuid4_info, cpu) = NULL; } -static void __cpuinit get_cpu_leaves(void *_retval) +static void get_cpu_leaves(void *_retval) { int j, *retval = _retval, cpu = smp_processor_id(); @@ -883,7 +880,7 @@ static void __cpuinit get_cpu_leaves(void *_retval) } } -static int __cpuinit detect_cache_attributes(unsigned int cpu) +static int detect_cache_attributes(unsigned int cpu) { int retval; @@ -1017,7 +1014,7 @@ static struct attribute *default_attrs[] = { }; #ifdef CONFIG_AMD_NB -static struct attribute ** __cpuinit amd_l3_attrs(void) +static struct attribute **amd_l3_attrs(void) { static struct attribute **attrs; int n; @@ -1093,7 +1090,7 @@ static struct kobj_type ktype_percpu_entry = { .sysfs_ops = &sysfs_ops, }; -static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu) +static void cpuid4_cache_sysfs_exit(unsigned int cpu) { kfree(per_cpu(ici_cache_kobject, cpu)); kfree(per_cpu(ici_index_kobject, cpu)); @@ -1102,7 +1099,7 @@ static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu) free_cache_attributes(cpu); } -static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu) +static int cpuid4_cache_sysfs_init(unsigned int cpu) { int err; @@ -1134,7 +1131,7 @@ err_out: static DECLARE_BITMAP(cache_dev_map, NR_CPUS); /* Add/Remove cache interface for CPU device */ -static int __cpuinit cache_add_dev(struct device *dev) +static int cache_add_dev(struct device *dev) { unsigned int cpu = dev->id; unsigned long i, j; @@ -1185,7 +1182,7 @@ static int __cpuinit cache_add_dev(struct device *dev) return 0; } -static void __cpuinit cache_remove_dev(struct device *dev) +static void cache_remove_dev(struct device *dev) { unsigned int cpu = dev->id; unsigned long i; @@ -1202,8 +1199,8 @@ static void __cpuinit cache_remove_dev(struct device *dev) cpuid4_cache_sysfs_exit(cpu); } -static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cacheinfo_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; struct device *dev; @@ -1222,7 +1219,7 @@ static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = { +static struct notifier_block cacheinfo_cpu_notifier = { .notifier_call = cacheinfo_cpu_callback, }; diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index ddc72f8..5ac2d1f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -153,7 +153,7 @@ static void raise_mce(struct mce *m) return; #ifdef CONFIG_X86_LOCAL_APIC - if (m->inject_flags & (MCJ_IRQ_BRAODCAST | MCJ_NMI_BROADCAST)) { + if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { unsigned long start; int cpu; @@ -167,7 +167,7 @@ static void raise_mce(struct mce *m) cpumask_clear_cpu(cpu, mce_inject_cpumask); } if (!cpumask_empty(mce_inject_cpumask)) { - if (m->inject_flags & MCJ_IRQ_BRAODCAST) { + if (m->inject_flags & MCJ_IRQ_BROADCAST) { /* * don't wait because mce_irq_ipi is necessary * to be sync with following raise_local diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 5b7d4fa..09edd0b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -25,15 +25,18 @@ int mce_severity(struct mce *a, int tolerant, char **msg); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; +extern mce_banks_t mce_banks_ce_disabled; #ifdef CONFIG_X86_MCE_INTEL unsigned long mce_intel_adjust_timer(unsigned long interval); void mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); +void cmci_disable_bank(int bank); #else # define mce_intel_adjust_timer mce_adjust_timer_default static inline void mce_intel_cmci_poll(void) { } static inline void mce_intel_hcpu_update(unsigned long cpu) { } +static inline void cmci_disable_bank(int bank) { } #endif void mce_timer_kick(unsigned long interval); diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index beb1f16..c370e1c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -110,22 +110,17 @@ static struct severity { /* known AR MCACODs: */ #ifdef CONFIG_MEMORY_FAILURE MCESEV( - KEEP, "HT thread notices Action required: data load error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), - MCGMASK(MCG_STATUS_EIPV, 0) + KEEP, "Action required but unaffected thread is continuable", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR, MCI_UC_SAR|MCI_ADDR), + MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV) ), MCESEV( - AR, "Action required: data load error", + AR, "Action required: data load error in a user process", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), USER ), MCESEV( - KEEP, "HT thread notices Action required: instruction fetch error", - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), - MCGMASK(MCG_STATUS_EIPV, 0) - ), - MCESEV( - AR, "Action required: instruction fetch error", + AR, "Action required: instruction fetch error in a user process", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), USER ), diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 9239504..b3218cd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -89,11 +89,23 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; -/* MCA banks polled by the period polling timer for corrected events */ +/* + * MCA banks polled by the period polling timer for corrected events. + * With Intel CMCI, this only has MCA banks which do not support CMCI (if any). + */ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { [0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL }; +/* + * MCA banks controlled through firmware first for corrected errors. + * This is a global list of banks for which we won't enable CMCI and we + * won't poll. Firmware controls these banks and is responsible for + * reporting corrected errors through GHES. Uncorrected/recoverable + * errors are still notified through a machine check. + */ +mce_banks_t mce_banks_ce_disabled; + static DEFINE_PER_CPU(struct work_struct, mce_work); static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); @@ -1360,7 +1372,7 @@ int mce_notify_irq(void) } EXPORT_SYMBOL_GPL(mce_notify_irq); -static int __cpuinit __mcheck_cpu_mce_banks_init(void) +static int __mcheck_cpu_mce_banks_init(void) { int i; u8 num_banks = mca_cfg.banks; @@ -1381,7 +1393,7 @@ static int __cpuinit __mcheck_cpu_mce_banks_init(void) /* * Initialize Machine Checks for a CPU. */ -static int __cpuinit __mcheck_cpu_cap_init(void) +static int __mcheck_cpu_cap_init(void) { unsigned b; u64 cap; @@ -1480,7 +1492,7 @@ static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) } /* Add per CPU specific workarounds here */ -static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { struct mca_config *cfg = &mca_cfg; @@ -1590,7 +1602,7 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) return 0; } -static int __cpuinit __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) +static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) { if (c->x86 != 5) return 0; @@ -1661,7 +1673,7 @@ void (*machine_check_vector)(struct pt_regs *, long error_code) = * Called for each booted CPU to set up machine checks. * Must be called with preempt off: */ -void __cpuinit mcheck_cpu_init(struct cpuinfo_x86 *c) +void mcheck_cpu_init(struct cpuinfo_x86 *c) { if (mca_cfg.disabled) return; @@ -1932,6 +1944,25 @@ static struct miscdevice mce_chrdev_device = { &mce_chrdev_ops, }; +static void __mce_disable_bank(void *arg) +{ + int bank = *((int *)arg); + __clear_bit(bank, __get_cpu_var(mce_poll_banks)); + cmci_disable_bank(bank); +} + +void mce_disable_bank(int bank) +{ + if (bank >= mca_cfg.banks) { + pr_warn(FW_BUG + "Ignoring request to disable invalid MCA bank %d.\n", + bank); + return; + } + set_bit(bank, mce_banks_ce_disabled); + on_each_cpu(__mce_disable_bank, &bank, 1); +} + /* * mce=off Disables machine check * mce=no_cmci Disables CMCI @@ -2079,7 +2110,6 @@ static struct bus_type mce_subsys = { DEFINE_PER_CPU(struct device *, mce_device); -__cpuinitdata void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); static inline struct mce_bank *attr_to_bank(struct device_attribute *attr) @@ -2225,7 +2255,7 @@ static void mce_device_release(struct device *dev) } /* Per cpu device init. All of the cpus still share the same ctrl bank: */ -static __cpuinit int mce_device_create(unsigned int cpu) +static int mce_device_create(unsigned int cpu) { struct device *dev; int err; @@ -2271,7 +2301,7 @@ error: return err; } -static __cpuinit void mce_device_remove(unsigned int cpu) +static void mce_device_remove(unsigned int cpu) { struct device *dev = per_cpu(mce_device, cpu); int i; @@ -2291,7 +2321,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu) } /* Make sure there are no machine checks on offlined CPUs. */ -static void __cpuinit mce_disable_cpu(void *h) +static void mce_disable_cpu(void *h) { unsigned long action = *(unsigned long *)h; int i; @@ -2309,7 +2339,7 @@ static void __cpuinit mce_disable_cpu(void *h) } } -static void __cpuinit mce_reenable_cpu(void *h) +static void mce_reenable_cpu(void *h) { unsigned long action = *(unsigned long *)h; int i; @@ -2328,7 +2358,7 @@ static void __cpuinit mce_reenable_cpu(void *h) } /* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static int __cpuinit +static int mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; @@ -2364,7 +2394,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) return NOTIFY_OK; } -static struct notifier_block mce_cpu_notifier __cpuinitdata = { +static struct notifier_block mce_cpu_notifier = { .notifier_call = mce_cpu_callback, }; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9cb5276..603df4f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -458,10 +458,8 @@ static struct kobj_type threshold_ktype = { .default_attrs = default_attrs, }; -static __cpuinit int allocate_threshold_blocks(unsigned int cpu, - unsigned int bank, - unsigned int block, - u32 address) +static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, + unsigned int block, u32 address) { struct threshold_block *b = NULL; u32 low, high; @@ -543,7 +541,7 @@ out_free: return err; } -static __cpuinit int __threshold_add_blocks(struct threshold_bank *b) +static int __threshold_add_blocks(struct threshold_bank *b) { struct list_head *head = &b->blocks->miscj; struct threshold_block *pos = NULL; @@ -567,7 +565,7 @@ static __cpuinit int __threshold_add_blocks(struct threshold_bank *b) return err; } -static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) +static int threshold_create_bank(unsigned int cpu, unsigned int bank) { struct device *dev = per_cpu(mce_device, cpu); struct amd_northbridge *nb = NULL; @@ -632,7 +630,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) } /* create dir/files for all valid threshold banks */ -static __cpuinit int threshold_create_device(unsigned int cpu) +static int threshold_create_device(unsigned int cpu) { unsigned int bank; struct threshold_bank **bp; @@ -736,7 +734,7 @@ static void threshold_remove_device(unsigned int cpu) } /* get notified when a cpu comes on/off */ -static void __cpuinit +static void amd_64_threshold_cpu_callback(unsigned long action, unsigned int cpu) { switch (action) { diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index ae1697c..4cfe045 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -24,6 +24,18 @@ * Also supports reliable discovery of shared banks. */ +/* + * CMCI can be delivered to multiple cpus that share a machine check bank + * so we need to designate a single cpu to process errors logged in each bank + * in the interrupt handler (otherwise we would have many races and potential + * double reporting of the same error). + * Note that this can change when a cpu is offlined or brought online since + * some MCA banks are shared across cpus. When a cpu is offlined, cmci_clear() + * disables CMCI on all banks owned by the cpu and clears this bitfield. At + * this point, cmci_rediscover() kicks in and a different cpu may end up + * taking ownership of some of the shared MCA banks that were previously + * owned by the offlined cpu. + */ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); /* @@ -191,6 +203,10 @@ static void cmci_discover(int banks) if (test_bit(i, owned)) continue; + /* Skip banks in firmware first mode */ + if (test_bit(i, mce_banks_ce_disabled)) + continue; + rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Already owned by someone else? */ @@ -259,6 +275,19 @@ void cmci_recheck(void) local_irq_restore(flags); } +/* Caller must hold the lock on cmci_discover_lock */ +static void __cmci_disable_bank(int bank) +{ + u64 val; + + if (!test_bit(bank, __get_cpu_var(mce_banks_owned))) + return; + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + val &= ~MCI_CTL2_CMCI_EN; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + __clear_bit(bank, __get_cpu_var(mce_banks_owned)); +} + /* * Disable CMCI on this CPU for all banks it owns when it goes down. * This allows other CPUs to claim the banks on rediscovery. @@ -268,20 +297,12 @@ void cmci_clear(void) unsigned long flags; int i; int banks; - u64 val; if (!cmci_supported(&banks)) return; raw_spin_lock_irqsave(&cmci_discover_lock, flags); - for (i = 0; i < banks; i++) { - if (!test_bit(i, __get_cpu_var(mce_banks_owned))) - continue; - /* Disable CMCI */ - rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~MCI_CTL2_CMCI_EN; - wrmsrl(MSR_IA32_MCx_CTL2(i), val); - __clear_bit(i, __get_cpu_var(mce_banks_owned)); - } + for (i = 0; i < banks; i++) + __cmci_disable_bank(i); raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } @@ -315,6 +336,19 @@ void cmci_reenable(void) cmci_discover(banks); } +void cmci_disable_bank(int bank) +{ + int banks; + unsigned long flags; + + if (!cmci_supported(&banks)) + return; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + __cmci_disable_bank(bank); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + static void intel_init_cmci(void) { int banks; diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 47a1870..3eec7de 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -29,6 +29,7 @@ #include <asm/idle.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/trace/irq_vectors.h> /* How long to wait between reporting thermal events */ #define CHECK_INTERVAL (300 * HZ) @@ -54,12 +55,24 @@ struct thermal_state { struct _thermal_state package_power_limit; struct _thermal_state core_thresh0; struct _thermal_state core_thresh1; + struct _thermal_state pkg_thresh0; + struct _thermal_state pkg_thresh1; }; /* Callback to handle core threshold interrupts */ int (*platform_thermal_notify)(__u64 msr_val); EXPORT_SYMBOL(platform_thermal_notify); +/* Callback to handle core package threshold_interrupts */ +int (*platform_thermal_package_notify)(__u64 msr_val); +EXPORT_SYMBOL_GPL(platform_thermal_package_notify); + +/* Callback support of rate control, return true, if + * callback has rate control */ +bool (*platform_thermal_package_rate_control)(void); +EXPORT_SYMBOL_GPL(platform_thermal_package_rate_control); + + static DEFINE_PER_CPU(struct thermal_state, thermal_state); static atomic_t therm_throt_en = ATOMIC_INIT(0); @@ -181,11 +194,6 @@ static int therm_throt_process(bool new_event, int event, int level) this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); - else - printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n", - this_cpu, - level == CORE_LEVEL ? "Core" : "Package", - state->count); return 1; } if (old_event) { @@ -193,36 +201,46 @@ static int therm_throt_process(bool new_event, int event, int level) printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); - else - printk(KERN_INFO "CPU%d: %s power limit normal\n", - this_cpu, - level == CORE_LEVEL ? "Core" : "Package"); return 1; } return 0; } -static int thresh_event_valid(int event) +static int thresh_event_valid(int level, int event) { struct _thermal_state *state; unsigned int this_cpu = smp_processor_id(); struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu); u64 now = get_jiffies_64(); - state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1; + if (level == PACKAGE_LEVEL) + state = (event == 0) ? &pstate->pkg_thresh0 : + &pstate->pkg_thresh1; + else + state = (event == 0) ? &pstate->core_thresh0 : + &pstate->core_thresh1; if (time_before64(now, state->next_check)) return 0; state->next_check = now + CHECK_INTERVAL; + + return 1; +} + +static bool int_pln_enable; +static int __init int_pln_enable_setup(char *s) +{ + int_pln_enable = true; + return 1; } +__setup("int_pln_enable", int_pln_enable_setup); #ifdef CONFIG_SYSFS /* Add/Remove thermal_throttle interface for CPU device: */ -static __cpuinit int thermal_throttle_add_dev(struct device *dev, - unsigned int cpu) +static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu) { int err; struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -231,7 +249,7 @@ static __cpuinit int thermal_throttle_add_dev(struct device *dev, if (err) return err; - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_core_power_limit_count.attr, thermal_attr_group.name); @@ -239,7 +257,7 @@ static __cpuinit int thermal_throttle_add_dev(struct device *dev, err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_throttle_count.attr, thermal_attr_group.name); - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) err = sysfs_add_file_to_group(&dev->kobj, &dev_attr_package_power_limit_count.attr, thermal_attr_group.name); @@ -248,7 +266,7 @@ static __cpuinit int thermal_throttle_add_dev(struct device *dev, return err; } -static __cpuinit void thermal_throttle_remove_dev(struct device *dev) +static void thermal_throttle_remove_dev(struct device *dev) { sysfs_remove_group(&dev->kobj, &thermal_attr_group); } @@ -257,7 +275,7 @@ static __cpuinit void thermal_throttle_remove_dev(struct device *dev) static DEFINE_MUTEX(therm_cpu_lock); /* Get notified when a cpu comes on/off. Be hotplug friendly. */ -static __cpuinit int +static int thermal_throttle_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) @@ -288,7 +306,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb, return notifier_from_errno(err); } -static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata = +static struct notifier_block thermal_throttle_cpu_notifier = { .notifier_call = thermal_throttle_cpu_callback, }; @@ -321,6 +339,39 @@ device_initcall(thermal_throttle_init_device); #endif /* CONFIG_SYSFS */ +static void notify_package_thresholds(__u64 msr_val) +{ + bool notify_thres_0 = false; + bool notify_thres_1 = false; + + if (!platform_thermal_package_notify) + return; + + /* lower threshold check */ + if (msr_val & THERM_LOG_THRESHOLD0) + notify_thres_0 = true; + /* higher threshold check */ + if (msr_val & THERM_LOG_THRESHOLD1) + notify_thres_1 = true; + + if (!notify_thres_0 && !notify_thres_1) + return; + + if (platform_thermal_package_rate_control && + platform_thermal_package_rate_control()) { + /* Rate control is implemented in callback */ + platform_thermal_package_notify(msr_val); + return; + } + + /* lower threshold reached */ + if (notify_thres_0 && thresh_event_valid(PACKAGE_LEVEL, 0)) + platform_thermal_package_notify(msr_val); + /* higher threshold reached */ + if (notify_thres_1 && thresh_event_valid(PACKAGE_LEVEL, 1)) + platform_thermal_package_notify(msr_val); +} + static void notify_thresholds(__u64 msr_val) { /* check whether the interrupt handler is defined; @@ -330,10 +381,12 @@ static void notify_thresholds(__u64 msr_val) return; /* lower threshold reached */ - if ((msr_val & THERM_LOG_THRESHOLD0) && thresh_event_valid(0)) + if ((msr_val & THERM_LOG_THRESHOLD0) && + thresh_event_valid(CORE_LEVEL, 0)) platform_thermal_notify(msr_val); /* higher threshold reached */ - if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1)) + if ((msr_val & THERM_LOG_THRESHOLD1) && + thresh_event_valid(CORE_LEVEL, 1)) platform_thermal_notify(msr_val); } @@ -352,17 +405,19 @@ static void intel_thermal_interrupt(void) CORE_LEVEL) != 0) mce_log_therm_throt_event(msr_val); - if (this_cpu_has(X86_FEATURE_PLN)) + if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, CORE_LEVEL); if (this_cpu_has(X86_FEATURE_PTS)) { rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); + /* check violations of package thermal thresholds */ + notify_package_thresholds(msr_val); therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, PACKAGE_LEVEL); - if (this_cpu_has(X86_FEATURE_PLN)) + if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable) therm_throt_process(msr_val & PACKAGE_THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, @@ -378,15 +433,26 @@ static void unexpected_thermal_interrupt(void) static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; -asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) +static inline void __smp_thermal_interrupt(void) { - irq_enter(); - exit_idle(); inc_irq_stat(irq_thermal_count); smp_thermal_vector(); - irq_exit(); - /* Ack only at the end to avoid potential reentry */ - ack_APIC_irq(); +} + +asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) +{ + entering_irq(); + __smp_thermal_interrupt(); + exiting_ack_irq(); +} + +asmlinkage void smp_trace_thermal_interrupt(struct pt_regs *regs) +{ + entering_irq(); + trace_thermal_apic_entry(THERMAL_APIC_VECTOR); + __smp_thermal_interrupt(); + trace_thermal_apic_exit(THERMAL_APIC_VECTOR); + exiting_ack_irq(); } /* Thermal monitoring depends on APIC, ACPI and clock modulation */ @@ -470,9 +536,13 @@ void intel_init_thermal(struct cpuinfo_x86 *c) apic_write(APIC_LVTTHMR, h); rdmsr(MSR_IA32_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) + wrmsr(MSR_IA32_THERM_INTERRUPT, + (l | (THERM_INT_LOW_ENABLE + | THERM_INT_HIGH_ENABLE)) & ~THERM_INT_PLN_ENABLE, h); + else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) wrmsr(MSR_IA32_THERM_INTERRUPT, - l | (THERM_INT_LOW_ENABLE + l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h); else wrmsr(MSR_IA32_THERM_INTERRUPT, @@ -480,9 +550,14 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_PTS)) { rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h); - if (cpu_has(c, X86_FEATURE_PLN)) + if (cpu_has(c, X86_FEATURE_PLN) && !int_pln_enable) wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, - l | (PACKAGE_THERM_INT_LOW_ENABLE + (l | (PACKAGE_THERM_INT_LOW_ENABLE + | PACKAGE_THERM_INT_HIGH_ENABLE)) + & ~PACKAGE_THERM_INT_PLN_ENABLE, h); + else if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable) + wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, + l | (PACKAGE_THERM_INT_LOW_ENABLE | PACKAGE_THERM_INT_HIGH_ENABLE | PACKAGE_THERM_INT_PLN_ENABLE), h); else diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index aa578ca..fe6b1c8 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -8,6 +8,7 @@ #include <asm/apic.h> #include <asm/idle.h> #include <asm/mce.h> +#include <asm/trace/irq_vectors.h> static void default_threshold_interrupt(void) { @@ -17,13 +18,24 @@ static void default_threshold_interrupt(void) void (*mce_threshold_vector)(void) = default_threshold_interrupt; -asmlinkage void smp_threshold_interrupt(void) +static inline void __smp_threshold_interrupt(void) { - irq_enter(); - exit_idle(); inc_irq_stat(irq_threshold_count); mce_threshold_vector(); - irq_exit(); - /* Ack only at the end to avoid potential reentry */ - ack_APIC_irq(); +} + +asmlinkage void smp_threshold_interrupt(void) +{ + entering_irq(); + __smp_threshold_interrupt(); + exiting_ack_irq(); +} + +asmlinkage void smp_trace_threshold_interrupt(void) +{ + entering_irq(); + trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); + __smp_threshold_interrupt(); + trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); + exiting_ack_irq(); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 8f4be53..71a39f3 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -27,20 +27,23 @@ struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); -static bool __init ms_hyperv_platform(void) +static uint32_t __init ms_hyperv_platform(void) { u32 eax; u32 hyp_signature[3]; if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return false; + return 0; cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); - return eax >= HYPERV_CPUID_MIN && - eax <= HYPERV_CPUID_MAX && - !memcmp("Microsoft Hv", hyp_signature, 12); + if (eax >= HYPERV_CPUID_MIN && + eax <= HYPERV_CPUID_MAX && + !memcmp("Microsoft Hv", hyp_signature, 12)) + return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; + + return 0; } static cycle_t read_hv_clock(struct clocksource *arg) diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 35ffda5..5f90b85 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits) if (mtrr_tom2) x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base; - nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size); /* * [0, 1M) should always be covered by var mtrr with WB * and fixed mtrrs should take effect before var mtrr for it: */ - nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0, + nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0, 1ULL<<(20 - PAGE_SHIFT)); - /* Sort the ranges: */ - sort_range(range, nr_range); + /* add from var mtrr at last */ + nr_range = x86_get_mtrr_mem_range(range, nr_range, + x_remove_base, x_remove_size); range_sums = sum_ranges(range, nr_range); printk(KERN_INFO "total RAM covered: %ldM\n", diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 68a3343..9e451b0 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -167,7 +167,7 @@ static void post_set(void) setCx86(CX86_CCR3, ccr3); /* Enable caches */ - write_cr0(read_cr0() & 0xbfffffff); + write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ if (cpu_has_pge) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fa72a39..ce2d0a2 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -510,8 +510,9 @@ generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { - unsigned int mask_lo, mask_hi, base_lo, base_hi; - unsigned int tmp, hi; + u32 mask_lo, mask_hi, base_lo, base_hi; + unsigned int hi; + u64 tmp, mask; /* * get_mtrr doesn't need to update mtrr_state, also it could be called @@ -532,18 +533,18 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ - tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; - mask_lo = size_or_mask | tmp; + tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; + mask = size_or_mask | tmp; /* Expand tmp with high bits to all 1s: */ - hi = fls(tmp); + hi = fls64(tmp); if (hi > 0) { - tmp |= ~((1<<(hi - 1)) - 1); + tmp |= ~((1ULL<<(hi - 1)) - 1); - if (tmp != mask_lo) { + if (tmp != mask) { printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - mask_lo = tmp; + mask = tmp; } } @@ -551,8 +552,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, * This works correctly if size is a power of two, i.e. a * contiguous range: */ - *size = -mask_lo; - *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; + *size = -mask; + *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; out_put_cpu: @@ -682,6 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) } /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ + count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Save MTRR state */ @@ -695,13 +697,14 @@ static void prepare_set(void) __acquires(set_atomicity_lock) static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ + count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); __flush_tlb(); /* Intel (P6) standard MTRRs */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Enable caches */ - write_cr0(read_cr0() & 0xbfffffff); + write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ if (cpu_has_pge) diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 726bf96..f961de9 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -51,9 +51,13 @@ #include <asm/e820.h> #include <asm/mtrr.h> #include <asm/msr.h> +#include <asm/pat.h> #include "mtrr.h" +/* arch_phys_wc_add returns an MTRR register index plus this offset. */ +#define MTRR_TO_PHYS_WC_OFFSET 1000 + u32 num_var_ranges; unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; @@ -305,7 +309,8 @@ int mtrr_add_page(unsigned long base, unsigned long size, return -EINVAL; } - if (base & size_or_mask || size & size_or_mask) { + if ((base | (base + size - 1)) >> + (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { pr_warning("mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -524,6 +529,73 @@ int mtrr_del(int reg, unsigned long base, unsigned long size) } EXPORT_SYMBOL(mtrr_del); +/** + * arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable + * @base: Physical base address + * @size: Size of region + * + * If PAT is available, this does nothing. If PAT is unavailable, it + * attempts to add a WC MTRR covering size bytes starting at base and + * logs an error if this fails. + * + * Drivers must store the return value to pass to mtrr_del_wc_if_needed, + * but drivers should not try to interpret that return value. + */ +int arch_phys_wc_add(unsigned long base, unsigned long size) +{ + int ret; + + if (pat_enabled) + return 0; /* Success! (We don't need to do anything.) */ + + ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true); + if (ret < 0) { + pr_warn("Failed to add WC MTRR for [%p-%p]; performance may suffer.", + (void *)base, (void *)(base + size - 1)); + return ret; + } + return ret + MTRR_TO_PHYS_WC_OFFSET; +} +EXPORT_SYMBOL(arch_phys_wc_add); + +/* + * arch_phys_wc_del - undoes arch_phys_wc_add + * @handle: Return value from arch_phys_wc_add + * + * This cleans up after mtrr_add_wc_if_needed. + * + * The API guarantees that mtrr_del_wc_if_needed(error code) and + * mtrr_del_wc_if_needed(0) do nothing. + */ +void arch_phys_wc_del(int handle) +{ + if (handle >= 1) { + WARN_ON(handle < MTRR_TO_PHYS_WC_OFFSET); + mtrr_del(handle - MTRR_TO_PHYS_WC_OFFSET, 0, 0); + } +} +EXPORT_SYMBOL(arch_phys_wc_del); + +/* + * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value + * @handle: Return value from arch_phys_wc_add + * + * This will turn the return value from arch_phys_wc_add into an mtrr + * index suitable for debugging. + * + * Note: There is no legitimate use for this function, except possibly + * in printk line. Alas there is an illegitimate use in some ancient + * drm ioctls. + */ +int phys_wc_to_mtrr_index(int handle) +{ + if (handle < MTRR_TO_PHYS_WC_OFFSET) + return -1; + else + return handle - MTRR_TO_PHYS_WC_OFFSET; +} +EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index); + /* * HACK ALERT! * These should be called implicitly, but we can't yet until all the initcall @@ -583,6 +655,7 @@ static struct syscore_ops mtrr_syscore_ops = { int __initdata changed_by_mtrr_cleanup; +#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1)) /** * mtrr_bp_init - initialize mtrrs on the boot CPU * @@ -600,7 +673,7 @@ void __init mtrr_bp_init(void) if (cpu_has_mtrr) { mtrr_if = &generic_mtrr_ops; - size_or_mask = 0xff000000; /* 36 bits */ + size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; phys_addr = 36; @@ -619,7 +692,7 @@ void __init mtrr_bp_init(void) boot_cpu_data.x86_mask == 0x4)) phys_addr = 36; - size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1); + size_or_mask = SIZE_OR_MASK_BITS(phys_addr); size_and_mask = ~size_or_mask & 0xfffff00000ULL; } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && boot_cpu_data.x86 == 6) { @@ -627,7 +700,7 @@ void __init mtrr_bp_init(void) * VIA C* family have Intel style MTRRs, * but don't support PAE */ - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; phys_addr = 32; } @@ -637,21 +710,21 @@ void __init mtrr_bp_init(void) if (cpu_has_k6_mtrr) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CENTAUR: if (cpu_has_centaur_mcr) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: if (cpu_has_cyrix_arr) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1025f3c..897783b 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -403,7 +403,8 @@ int x86_pmu_hw_config(struct perf_event *event) * check that PEBS LBR correction does not conflict with * whatever the user is asking with attr->branch_sample_type */ - if (event->attr.precise_ip > 1) { + if (event->attr.precise_ip > 1 && + x86_pmu.intel_cap.pebs_format < 2) { u64 *br_type = &event->attr.branch_sample_type; if (has_branch_stack(event)) { @@ -568,7 +569,7 @@ struct sched_state { struct perf_sched { int max_weight; int max_events; - struct event_constraint **constraints; + struct perf_event **events; struct sched_state state; int saved_states; struct sched_state saved[SCHED_STATES_MAX]; @@ -577,7 +578,7 @@ struct perf_sched { /* * Initialize interator that runs through all events and counters. */ -static void perf_sched_init(struct perf_sched *sched, struct event_constraint **c, +static void perf_sched_init(struct perf_sched *sched, struct perf_event **events, int num, int wmin, int wmax) { int idx; @@ -585,10 +586,10 @@ static void perf_sched_init(struct perf_sched *sched, struct event_constraint ** memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; - sched->constraints = c; + sched->events = events; for (idx = 0; idx < num; idx++) { - if (c[idx]->weight == wmin) + if (events[idx]->hw.constraint->weight == wmin) break; } @@ -635,8 +636,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (sched->state.event >= sched->max_events) return false; - c = sched->constraints[sched->state.event]; - + c = sched->events[sched->state.event]->hw.constraint; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; @@ -694,7 +694,7 @@ static bool perf_sched_next_event(struct perf_sched *sched) if (sched->state.weight > sched->max_weight) return false; } - c = sched->constraints[sched->state.event]; + c = sched->events[sched->state.event]->hw.constraint; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ @@ -705,12 +705,12 @@ static bool perf_sched_next_event(struct perf_sched *sched) /* * Assign a counter for each event. */ -int perf_assign_events(struct event_constraint **constraints, int n, +int perf_assign_events(struct perf_event **events, int n, int wmin, int wmax, int *assign) { struct perf_sched sched; - perf_sched_init(&sched, constraints, n, wmin, wmax); + perf_sched_init(&sched, events, n, wmin, wmax); do { if (!perf_sched_find_counter(&sched)) @@ -724,16 +724,19 @@ int perf_assign_events(struct event_constraint **constraints, int n, int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { - struct event_constraint *c, *constraints[X86_PMC_IDX_MAX]; + struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + struct perf_event *e; int i, wmin, wmax, num = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { + hwc = &cpuc->event_list[i]->hw; c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); - constraints[i] = c; + hwc->constraint = c; + wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } @@ -743,7 +746,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) */ for (i = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; - c = constraints[i]; + c = hwc->constraint; /* never assigned */ if (hwc->idx == -1) @@ -764,16 +767,35 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) /* slow path */ if (i != n) - num = perf_assign_events(constraints, n, wmin, wmax, assign); + num = perf_assign_events(cpuc->event_list, n, wmin, + wmax, assign); /* + * Mark the event as committed, so we do not put_constraint() + * in case new events are added and fail scheduling. + */ + if (!num && assign) { + for (i = 0; i < n; i++) { + e = cpuc->event_list[i]; + e->hw.flags |= PERF_X86_EVENT_COMMITTED; + } + } + /* * scheduling failed or is just a simulation, * free resources if necessary */ if (!assign || num) { for (i = 0; i < n; i++) { + e = cpuc->event_list[i]; + /* + * do not put_constraint() on comitted events, + * because they are good to go + */ + if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) + continue; + if (x86_pmu.put_event_constraints) - x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]); + x86_pmu.put_event_constraints(cpuc, e); } } return num ? -EINVAL : 0; @@ -1153,6 +1175,11 @@ static void x86_pmu_del(struct perf_event *event, int flags) int i; /* + * event is descheduled + */ + event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; + + /* * If we're called during a txn, we don't need to do anything. * The events never got scheduled and ->cancel_txn will truncate * the event_list. @@ -1249,16 +1276,26 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + int ret; + u64 start_clock; + u64 finish_clock; + if (!atomic_read(&active_events)) return NMI_DONE; - return x86_pmu.handle_irq(regs); + start_clock = local_clock(); + ret = x86_pmu.handle_irq(regs); + finish_clock = local_clock(); + + perf_sample_event_took(finish_clock - start_clock); + + return ret; } struct event_constraint emptyconstraint; struct event_constraint unconstrained; -static int __cpuinit +static int x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; @@ -1469,7 +1506,7 @@ static int __init init_hw_perf_events(void) err = amd_pmu_init(); break; default: - return 0; + err = -ENOTSUPP; } if (err != 0) { pr_cont("no PMU driver, software events only.\n"); @@ -1846,8 +1883,9 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { - userpg->cap_usr_time = 0; - userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; + userpg->cap_user_time = 0; + userpg->cap_user_time_zero = 0; + userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -1856,10 +1894,15 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) return; - userpg->cap_usr_time = 1; + userpg->cap_user_time = 1; userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; + + if (sched_clock_stable && !check_tsc_disabled()) { + userpg->cap_user_time_zero = 1; + userpg->time_zero = this_cpu_read(cyc2ns_offset); + } } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index ba9aadf..cc16faa 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -63,10 +63,12 @@ struct event_constraint { int flags; }; /* - * struct event_constraint flags + * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style st data sampling */ +#define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -227,11 +229,14 @@ struct cpu_hw_events { * - inv * - edge * - cnt-mask + * - in_tx + * - in_tx_checkpointed * The other filters are supported by fixed counters. * The any-thread option is supported starting with v3. */ +#define FIXED_EVENT_FLAGS (X86_RAW_EVENT_MASK|HSW_IN_TX|HSW_IN_TX_CHECKPOINTED) #define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS) /* * Constraint on the Event code + UMask @@ -247,6 +252,11 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) +/* DataLA version of store sampling without extra enable bit. */ +#define INTEL_PST_HSW_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) + #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -301,6 +311,11 @@ union perf_capabilities { u64 pebs_arch_reg:1; u64 pebs_format:4; u64 smm_freeze:1; + /* + * PMU supports separate counter range for writing + * values > 32bit. + */ + u64 full_width_write:1; }; u64 capabilities; }; @@ -375,6 +390,7 @@ struct x86_pmu { struct event_constraint *event_constraints; struct x86_pmu_quirk *quirks; int perfctr_second_write; + bool late_ack; /* * sysfs attrs @@ -528,7 +544,7 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, void x86_pmu_enable_all(int added); -int perf_assign_events(struct event_constraint **constraints, int n, +int perf_assign_events(struct perf_event **events, int n, int wmin, int wmax, int *assign); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); @@ -625,6 +641,8 @@ extern struct event_constraint intel_core2_pebs_event_constraints[]; extern struct event_constraint intel_atom_pebs_event_constraints[]; +extern struct event_constraint intel_slm_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; @@ -633,6 +651,8 @@ extern struct event_constraint intel_snb_pebs_event_constraints[]; extern struct event_constraint intel_ivb_pebs_event_constraints[]; +extern struct event_constraint intel_hsw_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 7e28d94..beeb7cc 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -347,8 +347,7 @@ static struct amd_nb *amd_alloc_nb(int cpu) struct amd_nb *nb; int i; - nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO, - cpu_to_node(cpu)); + nb = kzalloc_node(sizeof(struct amd_nb), GFP_KERNEL, cpu_to_node(cpu)); if (!nb) return NULL; @@ -648,48 +647,48 @@ static __initconst const struct x86_pmu amd_pmu = { .cpu_dead = amd_pmu_cpu_dead, }; -static int setup_event_constraints(void) +static int __init amd_core_pmu_init(void) { - if (boot_cpu_data.x86 == 0x15) + if (!cpu_has_perfctr_core) + return 0; + + switch (boot_cpu_data.x86) { + case 0x15: + pr_cont("Fam15h "); x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; - return 0; -} + break; -static int setup_perfctr_core(void) -{ - if (!cpu_has_perfctr_core) { - WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h, - KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!"); + default: + pr_err("core perfctr but no constraints; unknown hardware!\n"); return -ENODEV; } - WARN(x86_pmu.get_event_constraints == amd_get_event_constraints, - KERN_ERR "hw perf events core counters need constraints handler!"); - /* * If core performance counter extensions exists, we must use * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also - * x86_pmu_addr_offset(). + * amd_pmu_addr_offset(). */ x86_pmu.eventsel = MSR_F15H_PERF_CTL; x86_pmu.perfctr = MSR_F15H_PERF_CTR; x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE; - printk(KERN_INFO "perf: AMD core performance counters detected\n"); - + pr_cont("core perfctr, "); return 0; } __init int amd_pmu_init(void) { + int ret; + /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) return -ENODEV; x86_pmu = amd_pmu; - setup_event_constraints(); - setup_perfctr_core(); + ret = amd_core_pmu_init(); + if (ret) + return ret; /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 5f0581e..e09f0bf 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -851,7 +851,7 @@ static void clear_APIC_ibs(void *dummy) setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); } -static int __cpuinit +static int perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c new file mode 100644 index 0000000..639d128 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c @@ -0,0 +1,502 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Steven Kinney <Steven.Kinney@amd.com> + * Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com> + * + * Perf: amd_iommu - AMD IOMMU Performance Counter PMU implementation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/perf_event.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/slab.h> + +#include "perf_event.h" +#include "perf_event_amd_iommu.h" + +#define COUNTER_SHIFT 16 + +#define _GET_BANK(ev) ((u8)(ev->hw.extra_reg.reg >> 8)) +#define _GET_CNTR(ev) ((u8)(ev->hw.extra_reg.reg)) + +/* iommu pmu config masks */ +#define _GET_CSOURCE(ev) ((ev->hw.config & 0xFFULL)) +#define _GET_DEVID(ev) ((ev->hw.config >> 8) & 0xFFFFULL) +#define _GET_PASID(ev) ((ev->hw.config >> 24) & 0xFFFFULL) +#define _GET_DOMID(ev) ((ev->hw.config >> 40) & 0xFFFFULL) +#define _GET_DEVID_MASK(ev) ((ev->hw.extra_reg.config) & 0xFFFFULL) +#define _GET_PASID_MASK(ev) ((ev->hw.extra_reg.config >> 16) & 0xFFFFULL) +#define _GET_DOMID_MASK(ev) ((ev->hw.extra_reg.config >> 32) & 0xFFFFULL) + +static struct perf_amd_iommu __perf_iommu; + +struct perf_amd_iommu { + struct pmu pmu; + u8 max_banks; + u8 max_counters; + u64 cntr_assign_mask; + raw_spinlock_t lock; + const struct attribute_group *attr_groups[4]; +}; + +#define format_group attr_groups[0] +#define cpumask_group attr_groups[1] +#define events_group attr_groups[2] +#define null_group attr_groups[3] + +/*--------------------------------------------- + * sysfs format attributes + *---------------------------------------------*/ +PMU_FORMAT_ATTR(csource, "config:0-7"); +PMU_FORMAT_ATTR(devid, "config:8-23"); +PMU_FORMAT_ATTR(pasid, "config:24-39"); +PMU_FORMAT_ATTR(domid, "config:40-55"); +PMU_FORMAT_ATTR(devid_mask, "config1:0-15"); +PMU_FORMAT_ATTR(pasid_mask, "config1:16-31"); +PMU_FORMAT_ATTR(domid_mask, "config1:32-47"); + +static struct attribute *iommu_format_attrs[] = { + &format_attr_csource.attr, + &format_attr_devid.attr, + &format_attr_pasid.attr, + &format_attr_domid.attr, + &format_attr_devid_mask.attr, + &format_attr_pasid_mask.attr, + &format_attr_domid_mask.attr, + NULL, +}; + +static struct attribute_group amd_iommu_format_group = { + .name = "format", + .attrs = iommu_format_attrs, +}; + +/*--------------------------------------------- + * sysfs events attributes + *---------------------------------------------*/ +struct amd_iommu_event_desc { + struct kobj_attribute attr; + const char *event; +}; + +static ssize_t _iommu_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct amd_iommu_event_desc *event = + container_of(attr, struct amd_iommu_event_desc, attr); + return sprintf(buf, "%s\n", event->event); +} + +#define AMD_IOMMU_EVENT_DESC(_name, _event) \ +{ \ + .attr = __ATTR(_name, 0444, _iommu_event_show, NULL), \ + .event = _event, \ +} + +static struct amd_iommu_event_desc amd_iommu_v2_event_descs[] = { + AMD_IOMMU_EVENT_DESC(mem_pass_untrans, "csource=0x01"), + AMD_IOMMU_EVENT_DESC(mem_pass_pretrans, "csource=0x02"), + AMD_IOMMU_EVENT_DESC(mem_pass_excl, "csource=0x03"), + AMD_IOMMU_EVENT_DESC(mem_target_abort, "csource=0x04"), + AMD_IOMMU_EVENT_DESC(mem_trans_total, "csource=0x05"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pte_hit, "csource=0x06"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pte_mis, "csource=0x07"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pde_hit, "csource=0x08"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pde_mis, "csource=0x09"), + AMD_IOMMU_EVENT_DESC(mem_dte_hit, "csource=0x0a"), + AMD_IOMMU_EVENT_DESC(mem_dte_mis, "csource=0x0b"), + AMD_IOMMU_EVENT_DESC(page_tbl_read_tot, "csource=0x0c"), + AMD_IOMMU_EVENT_DESC(page_tbl_read_nst, "csource=0x0d"), + AMD_IOMMU_EVENT_DESC(page_tbl_read_gst, "csource=0x0e"), + AMD_IOMMU_EVENT_DESC(int_dte_hit, "csource=0x0f"), + AMD_IOMMU_EVENT_DESC(int_dte_mis, "csource=0x10"), + AMD_IOMMU_EVENT_DESC(cmd_processed, "csource=0x11"), + AMD_IOMMU_EVENT_DESC(cmd_processed_inv, "csource=0x12"), + AMD_IOMMU_EVENT_DESC(tlb_inv, "csource=0x13"), + { /* end: all zeroes */ }, +}; + +/*--------------------------------------------- + * sysfs cpumask attributes + *---------------------------------------------*/ +static cpumask_t iommu_cpumask; + +static ssize_t _iommu_cpumask_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &iommu_cpumask); + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} +static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL); + +static struct attribute *iommu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group amd_iommu_cpumask_group = { + .attrs = iommu_cpumask_attrs, +}; + +/*---------------------------------------------*/ + +static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu) +{ + unsigned long flags; + int shift, bank, cntr, retval; + int max_banks = perf_iommu->max_banks; + int max_cntrs = perf_iommu->max_counters; + + raw_spin_lock_irqsave(&perf_iommu->lock, flags); + + for (bank = 0, shift = 0; bank < max_banks; bank++) { + for (cntr = 0; cntr < max_cntrs; cntr++) { + shift = bank + (bank*3) + cntr; + if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) { + continue; + } else { + perf_iommu->cntr_assign_mask |= (1ULL<<shift); + retval = ((u16)((u16)bank<<8) | (u8)(cntr)); + goto out; + } + } + } + retval = -ENOSPC; +out: + raw_spin_unlock_irqrestore(&perf_iommu->lock, flags); + return retval; +} + +static int clear_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu, + u8 bank, u8 cntr) +{ + unsigned long flags; + int max_banks, max_cntrs; + int shift = 0; + + max_banks = perf_iommu->max_banks; + max_cntrs = perf_iommu->max_counters; + + if ((bank > max_banks) || (cntr > max_cntrs)) + return -EINVAL; + + shift = bank + cntr + (bank*3); + + raw_spin_lock_irqsave(&perf_iommu->lock, flags); + perf_iommu->cntr_assign_mask &= ~(1ULL<<shift); + raw_spin_unlock_irqrestore(&perf_iommu->lock, flags); + + return 0; +} + +static int perf_iommu_event_init(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct perf_amd_iommu *perf_iommu; + u64 config, config1; + + /* test the event attr type check for PMU enumeration */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* + * IOMMU counters are shared across all cores. + * Therefore, it does not support per-process mode. + * Also, it does not support event sampling mode. + */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + /* IOMMU counters do not have usr/os/guest/host bits */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_host || event->attr.exclude_guest) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + perf_iommu = &__perf_iommu; + + if (event->pmu != &perf_iommu->pmu) + return -ENOENT; + + if (perf_iommu) { + config = event->attr.config; + config1 = event->attr.config1; + } else { + return -EINVAL; + } + + /* integrate with iommu base devid (0000), assume one iommu */ + perf_iommu->max_banks = + amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID); + perf_iommu->max_counters = + amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID); + if ((perf_iommu->max_banks == 0) || (perf_iommu->max_counters == 0)) + return -EINVAL; + + /* update the hw_perf_event struct with the iommu config data */ + hwc->config = config; + hwc->extra_reg.config = config1; + + return 0; +} + +static void perf_iommu_enable_event(struct perf_event *ev) +{ + u8 csource = _GET_CSOURCE(ev); + u16 devid = _GET_DEVID(ev); + u64 reg = 0ULL; + + reg = csource; + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_COUNTER_SRC_REG, ®, true); + + reg = 0ULL | devid | (_GET_DEVID_MASK(ev) << 32); + if (reg) + reg |= (1UL << 31); + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_DEVID_MATCH_REG, ®, true); + + reg = 0ULL | _GET_PASID(ev) | (_GET_PASID_MASK(ev) << 32); + if (reg) + reg |= (1UL << 31); + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_PASID_MATCH_REG, ®, true); + + reg = 0ULL | _GET_DOMID(ev) | (_GET_DOMID_MASK(ev) << 32); + if (reg) + reg |= (1UL << 31); + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_DOMID_MATCH_REG, ®, true); +} + +static void perf_iommu_disable_event(struct perf_event *event) +{ + u64 reg = 0ULL; + + amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), + _GET_BANK(event), _GET_CNTR(event), + IOMMU_PC_COUNTER_SRC_REG, ®, true); +} + +static void perf_iommu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + pr_debug("perf: amd_iommu:perf_iommu_start\n"); + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + hwc->state = 0; + + if (flags & PERF_EF_RELOAD) { + u64 prev_raw_count = local64_read(&hwc->prev_count); + amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), + _GET_BANK(event), _GET_CNTR(event), + IOMMU_PC_COUNTER_REG, &prev_raw_count, true); + } + + perf_iommu_enable_event(event); + perf_event_update_userpage(event); + +} + +static void perf_iommu_read(struct perf_event *event) +{ + u64 count = 0ULL; + u64 prev_raw_count = 0ULL; + u64 delta = 0ULL; + struct hw_perf_event *hwc = &event->hw; + pr_debug("perf: amd_iommu:perf_iommu_read\n"); + + amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), + _GET_BANK(event), _GET_CNTR(event), + IOMMU_PC_COUNTER_REG, &count, false); + + /* IOMMU pc counter register is only 48 bits */ + count &= 0xFFFFFFFFFFFFULL; + + prev_raw_count = local64_read(&hwc->prev_count); + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + count) != prev_raw_count) + return; + + /* Handling 48-bit counter overflowing */ + delta = (count << COUNTER_SHIFT) - (prev_raw_count << COUNTER_SHIFT); + delta >>= COUNTER_SHIFT; + local64_add(delta, &event->count); + +} + +static void perf_iommu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + u64 config; + + pr_debug("perf: amd_iommu:perf_iommu_stop\n"); + + if (hwc->state & PERF_HES_UPTODATE) + return; + + perf_iommu_disable_event(event); + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (hwc->state & PERF_HES_UPTODATE) + return; + + config = hwc->config; + perf_iommu_read(event); + hwc->state |= PERF_HES_UPTODATE; +} + +static int perf_iommu_add(struct perf_event *event, int flags) +{ + int retval; + struct perf_amd_iommu *perf_iommu = + container_of(event->pmu, struct perf_amd_iommu, pmu); + + pr_debug("perf: amd_iommu:perf_iommu_add\n"); + event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + /* request an iommu bank/counter */ + retval = get_next_avail_iommu_bnk_cntr(perf_iommu); + if (retval != -ENOSPC) + event->hw.extra_reg.reg = (u16)retval; + else + return retval; + + if (flags & PERF_EF_START) + perf_iommu_start(event, PERF_EF_RELOAD); + + return 0; +} + +static void perf_iommu_del(struct perf_event *event, int flags) +{ + struct perf_amd_iommu *perf_iommu = + container_of(event->pmu, struct perf_amd_iommu, pmu); + + pr_debug("perf: amd_iommu:perf_iommu_del\n"); + perf_iommu_stop(event, PERF_EF_UPDATE); + + /* clear the assigned iommu bank/counter */ + clear_avail_iommu_bnk_cntr(perf_iommu, + _GET_BANK(event), + _GET_CNTR(event)); + + perf_event_update_userpage(event); +} + +static __init int _init_events_attrs(struct perf_amd_iommu *perf_iommu) +{ + struct attribute **attrs; + struct attribute_group *attr_group; + int i = 0, j; + + while (amd_iommu_v2_event_descs[i].attr.attr.name) + i++; + + attr_group = kzalloc(sizeof(struct attribute *) + * (i + 1) + sizeof(*attr_group), GFP_KERNEL); + if (!attr_group) + return -ENOMEM; + + attrs = (struct attribute **)(attr_group + 1); + for (j = 0; j < i; j++) + attrs[j] = &amd_iommu_v2_event_descs[j].attr.attr; + + attr_group->name = "events"; + attr_group->attrs = attrs; + perf_iommu->events_group = attr_group; + + return 0; +} + +static __init void amd_iommu_pc_exit(void) +{ + if (__perf_iommu.events_group != NULL) { + kfree(__perf_iommu.events_group); + __perf_iommu.events_group = NULL; + } +} + +static __init int _init_perf_amd_iommu( + struct perf_amd_iommu *perf_iommu, char *name) +{ + int ret; + + raw_spin_lock_init(&perf_iommu->lock); + + /* Init format attributes */ + perf_iommu->format_group = &amd_iommu_format_group; + + /* Init cpumask attributes to only core 0 */ + cpumask_set_cpu(0, &iommu_cpumask); + perf_iommu->cpumask_group = &amd_iommu_cpumask_group; + + /* Init events attributes */ + if (_init_events_attrs(perf_iommu) != 0) + pr_err("perf: amd_iommu: Only support raw events.\n"); + + /* Init null attributes */ + perf_iommu->null_group = NULL; + perf_iommu->pmu.attr_groups = perf_iommu->attr_groups; + + ret = perf_pmu_register(&perf_iommu->pmu, name, -1); + if (ret) { + pr_err("perf: amd_iommu: Failed to initialized.\n"); + amd_iommu_pc_exit(); + } else { + pr_info("perf: amd_iommu: Detected. (%d banks, %d counters/bank)\n", + amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID), + amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID)); + } + + return ret; +} + +static struct perf_amd_iommu __perf_iommu = { + .pmu = { + .event_init = perf_iommu_event_init, + .add = perf_iommu_add, + .del = perf_iommu_del, + .start = perf_iommu_start, + .stop = perf_iommu_stop, + .read = perf_iommu_read, + }, + .max_banks = 0x00, + .max_counters = 0x00, + .cntr_assign_mask = 0ULL, + .format_group = NULL, + .cpumask_group = NULL, + .events_group = NULL, + .null_group = NULL, +}; + +static __init int amd_iommu_pc_init(void) +{ + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_supported()) + return -ENODEV; + + _init_perf_amd_iommu(&__perf_iommu, "amd_iommu"); + + return 0; +} + +device_initcall(amd_iommu_pc_init); diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.h b/arch/x86/kernel/cpu/perf_event_amd_iommu.h new file mode 100644 index 0000000..845d173 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Steven Kinney <Steven.Kinney@amd.com> + * Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _PERF_EVENT_AMD_IOMMU_H_ +#define _PERF_EVENT_AMD_IOMMU_H_ + +/* iommu pc mmio region register indexes */ +#define IOMMU_PC_COUNTER_REG 0x00 +#define IOMMU_PC_COUNTER_SRC_REG 0x08 +#define IOMMU_PC_PASID_MATCH_REG 0x10 +#define IOMMU_PC_DOMID_MATCH_REG 0x18 +#define IOMMU_PC_DEVID_MATCH_REG 0x20 +#define IOMMU_PC_COUNTER_REPORT_REG 0x28 + +/* maximun specified bank/counters */ +#define PC_MAX_SPEC_BNKS 64 +#define PC_MAX_SPEC_CNTRS 16 + +/* iommu pc reg masks*/ +#define IOMMU_BASE_DEVID 0x0000 + +/* amd_iommu_init.c external support functions */ +extern bool amd_iommu_pc_supported(void); + +extern u8 amd_iommu_pc_get_max_banks(u16 devid); + +extern u8 amd_iommu_pc_get_max_counters(u16 devid); + +extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, + u8 fxn, u64 *value, bool is_write); + +#endif /*_PERF_EVENT_AMD_IOMMU_H_*/ diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index c0c661a..754291a 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -288,13 +288,13 @@ static struct pmu amd_l2_pmu = { .read = amd_uncore_read, }; -static struct amd_uncore * __cpuinit amd_uncore_alloc(unsigned int cpu) +static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) { return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL, cpu_to_node(cpu)); } -static void __cpuinit amd_uncore_cpu_up_prepare(unsigned int cpu) +static void amd_uncore_cpu_up_prepare(unsigned int cpu) { struct amd_uncore *uncore; @@ -322,8 +322,8 @@ static void __cpuinit amd_uncore_cpu_up_prepare(unsigned int cpu) } static struct amd_uncore * -__cpuinit amd_uncore_find_online_sibling(struct amd_uncore *this, - struct amd_uncore * __percpu *uncores) +amd_uncore_find_online_sibling(struct amd_uncore *this, + struct amd_uncore * __percpu *uncores) { unsigned int cpu; struct amd_uncore *that; @@ -348,7 +348,7 @@ __cpuinit amd_uncore_find_online_sibling(struct amd_uncore *this, return this; } -static void __cpuinit amd_uncore_cpu_starting(unsigned int cpu) +static void amd_uncore_cpu_starting(unsigned int cpu) { unsigned int eax, ebx, ecx, edx; struct amd_uncore *uncore; @@ -376,8 +376,8 @@ static void __cpuinit amd_uncore_cpu_starting(unsigned int cpu) } } -static void __cpuinit uncore_online(unsigned int cpu, - struct amd_uncore * __percpu *uncores) +static void uncore_online(unsigned int cpu, + struct amd_uncore * __percpu *uncores) { struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); @@ -388,7 +388,7 @@ static void __cpuinit uncore_online(unsigned int cpu, cpumask_set_cpu(cpu, uncore->active_mask); } -static void __cpuinit amd_uncore_cpu_online(unsigned int cpu) +static void amd_uncore_cpu_online(unsigned int cpu) { if (amd_uncore_nb) uncore_online(cpu, amd_uncore_nb); @@ -397,8 +397,8 @@ static void __cpuinit amd_uncore_cpu_online(unsigned int cpu) uncore_online(cpu, amd_uncore_l2); } -static void __cpuinit uncore_down_prepare(unsigned int cpu, - struct amd_uncore * __percpu *uncores) +static void uncore_down_prepare(unsigned int cpu, + struct amd_uncore * __percpu *uncores) { unsigned int i; struct amd_uncore *this = *per_cpu_ptr(uncores, cpu); @@ -423,7 +423,7 @@ static void __cpuinit uncore_down_prepare(unsigned int cpu, } } -static void __cpuinit amd_uncore_cpu_down_prepare(unsigned int cpu) +static void amd_uncore_cpu_down_prepare(unsigned int cpu) { if (amd_uncore_nb) uncore_down_prepare(cpu, amd_uncore_nb); @@ -432,8 +432,7 @@ static void __cpuinit amd_uncore_cpu_down_prepare(unsigned int cpu) uncore_down_prepare(cpu, amd_uncore_l2); } -static void __cpuinit uncore_dead(unsigned int cpu, - struct amd_uncore * __percpu *uncores) +static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores) { struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); @@ -445,7 +444,7 @@ static void __cpuinit uncore_dead(unsigned int cpu, *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; } -static void __cpuinit amd_uncore_cpu_dead(unsigned int cpu) +static void amd_uncore_cpu_dead(unsigned int cpu) { if (amd_uncore_nb) uncore_dead(cpu, amd_uncore_nb); @@ -454,7 +453,7 @@ static void __cpuinit amd_uncore_cpu_dead(unsigned int cpu) uncore_dead(cpu, amd_uncore_l2); } -static int __cpuinit +static int amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -489,7 +488,7 @@ amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action, return NOTIFY_OK; } -static struct notifier_block amd_uncore_cpu_notifier_block __cpuinitdata = { +static struct notifier_block amd_uncore_cpu_notifier_block = { .notifier_call = amd_uncore_cpu_notifier, .priority = CPU_PRI_PERF + 1, }; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f60d41f..f31a165 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/export.h> +#include <asm/cpufeature.h> #include <asm/hardirq.h> #include <asm/apic.h> @@ -80,7 +81,8 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = static struct extra_reg intel_nehalem_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -122,6 +124,7 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */ INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */ + INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */ INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */ @@ -142,8 +145,9 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -161,17 +165,28 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_slm_event_constraints[] __read_mostly = +{ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */ + EVENT_CONSTRAINT_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), - INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; @@ -190,6 +205,22 @@ struct attribute *snb_events_attrs[] = { NULL, }; +static struct event_constraint intel_hsw_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + INTEL_EVENT_CONSTRAINT(0x08a3, 0x4), + /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ + INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4), + /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ + INTEL_EVENT_CONSTRAINT(0x04a3, 0xf), + EVENT_CONSTRAINT_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -865,6 +896,140 @@ static __initconst const u64 atom_hw_cache_event_ids }, }; +static struct extra_reg intel_slm_extra_regs[] __read_mostly = +{ + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1), + EVENT_EXTRA_END +}; + +#define SLM_DMND_READ SNB_DMND_DATA_RD +#define SLM_DMND_WRITE SNB_DMND_RFO +#define SLM_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO) + +#define SLM_SNP_ANY (SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM) +#define SLM_LLC_ACCESS SNB_RESP_ANY +#define SLM_LLC_MISS (SLM_SNP_ANY|SNB_NON_DRAM) + +static __initconst const u64 slm_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_WRITE|SLM_LLC_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_PREFETCH|SLM_LLC_MISS, + }, + }, +}; + +static __initconst const u64 slm_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0104, /* LD_DCU_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */ + [ C(RESULT_MISS) ] = 0x0280, /* ICACGE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0804, /* LD_DTLB_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ + [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) { /* user explicitly requested branch sampling */ @@ -872,7 +1037,8 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) return true; /* implicit branch sampling to correct PEBS skid */ - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && + x86_pmu.intel_cap.pebs_format < 2) return true; return false; @@ -1167,15 +1333,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); /* - * Some chipsets need to unmask the LVTPC in a particular spot - * inside the nmi handler. As a result, the unmasking was pushed - * into all the nmi handlers. - * - * This handler doesn't seem to have any issues with the unmasking - * so it was left at the top. + * No known reason to not always do late ACK, + * but just in case do it opt-in. */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - + if (!x86_pmu.late_ack) + apic_write(APIC_LVTPC, APIC_DM_NMI); intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); @@ -1188,8 +1350,12 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) again: intel_pmu_ack_status(status); if (++loops > 100) { - WARN_ONCE(1, "perfevents: irq loop stuck!\n"); - perf_event_print_debug(); + static bool warned = false; + if (!warned) { + WARN(1, "perfevents: irq loop stuck!\n"); + perf_event_print_debug(); + warned = true; + } intel_pmu_reset(); goto done; } @@ -1235,6 +1401,13 @@ again: done: intel_pmu_enable_all(0); + /* + * Only unmask the NMI after the overflow counters + * have been reset. This avoids spurious NMIs on + * Haswell CPUs. + */ + if (x86_pmu.late_ack) + apic_write(APIC_LVTPC, APIC_DM_NMI); return handled; } @@ -1276,11 +1449,11 @@ static void intel_fixup_er(struct perf_event *event, int idx) if (idx == EXTRA_REG_RSP_0) { event->hw.config &= ~INTEL_ARCH_EVENT_MASK; - event->hw.config |= 0x01b7; + event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event; event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0; } else if (idx == EXTRA_REG_RSP_1) { event->hw.config &= ~INTEL_ARCH_EVENT_MASK; - event->hw.config |= 0x01bb; + event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event; event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1; } } @@ -1425,7 +1598,6 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { if ((event->hw.config & c->cmask) == c->code) { - /* hw.flags zeroed at initialization */ event->hw.flags |= c->flags; return c; } @@ -1473,7 +1645,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - event->hw.flags = 0; intel_put_shared_regs_event_constraints(cpuc, event); } @@ -1646,6 +1817,47 @@ static void core_pmu_enable_all(int added) } } +static int hsw_hw_config(struct perf_event *event) +{ + int ret = intel_pmu_hw_config(event); + + if (ret) + return ret; + if (!boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has(X86_FEATURE_HLE)) + return 0; + event->hw.config |= event->attr.config & (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED); + + /* + * IN_TX/IN_TX-CP filters are not supported by the Haswell PMU with + * PEBS or in ANY thread mode. Since the results are non-sensical forbid + * this combination. + */ + if ((event->hw.config & (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)) && + ((event->hw.config & ARCH_PERFMON_EVENTSEL_ANY) || + event->attr.precise_ip > 0)) + return -EOPNOTSUPP; + + return 0; +} + +static struct event_constraint counter2_constraint = + EVENT_CONSTRAINT(0, 0x4, 0); + +static struct event_constraint * +hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c = intel_get_event_constraints(cpuc, event); + + /* Handle special quirk on in_tx_checkpointed only in counter 2 */ + if (event->hw.config & HSW_IN_TX_CHECKPOINTED) { + if (c->idxmsk64 & (1U << 2)) + return &counter2_constraint; + return &emptyconstraint; + } + + return c; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -1653,6 +1865,8 @@ PMU_FORMAT_ATTR(pc, "config:19" ); PMU_FORMAT_ATTR(any, "config:21" ); /* v3 + */ PMU_FORMAT_ATTR(inv, "config:23" ); PMU_FORMAT_ATTR(cmask, "config:24-31" ); +PMU_FORMAT_ATTR(in_tx, "config:32"); +PMU_FORMAT_ATTR(in_tx_cp, "config:33"); static struct attribute *intel_arch_formats_attr[] = { &format_attr_event.attr, @@ -1807,6 +2021,8 @@ static struct attribute *intel_arch3_formats_attr[] = { &format_attr_any.attr, &format_attr_inv.attr, &format_attr_cmask.attr, + &format_attr_in_tx.attr, + &format_attr_in_tx_cp.attr, &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ &format_attr_ldlat.attr, /* PEBS load latency */ @@ -1966,6 +2182,15 @@ static __init void intel_nehalem_quirk(void) } } +EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") + +static struct attribute *hsw_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + NULL +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -2099,6 +2324,22 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; + case 55: /* Atom 22nm "Silvermont" */ + case 77: /* Avoton "Silvermont" */ + memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_atom(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_slm_extra_regs; + x86_pmu.er_flags |= ERF_HAS_RSP_1; + pr_cont("Silvermont events, "); + break; + case 37: /* 32 nm nehalem, "Clarkdale" */ case 44: /* 32 nm nehalem, "Gulftown" */ case 47: /* 32 nm Xeon E7 */ @@ -2189,6 +2430,31 @@ __init int intel_pmu_init(void) break; + case 60: /* Haswell Client */ + case 70: + case 71: + case 63: + case 69: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_hsw_event_constraints; + x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.extra_regs = intel_snb_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.cpu_events = hsw_events_attrs; + pr_cont("Haswell events, "); + break; + default: switch (x86_pmu.version) { case 1: @@ -2227,7 +2493,7 @@ __init int intel_pmu_init(void) * counter, so do not extend mask to generic counters */ for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != X86_RAW_EVENT_MASK + if (c->cmask != FIXED_EVENT_FLAGS || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { continue; } @@ -2237,5 +2503,12 @@ __init int intel_pmu_init(void) } } + /* Support full width counters using alternative MSR range */ + if (x86_pmu.intel_cap.full_width_write) { + x86_pmu.max_period = x86_pmu.cntval_mask; + x86_pmu.perfctr = MSR_IA32_PMC0; + pr_cont("full-width counters, "); + } + return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 60250f6..ab3ba1c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -107,6 +107,19 @@ static u64 precise_store_data(u64 status) return val; } +static u64 precise_store_data_hsw(u64 status) +{ + union perf_mem_data_src dse; + + dse.val = 0; + dse.mem_op = PERF_MEM_OP_STORE; + dse.mem_lvl = PERF_MEM_LVL_NA; + if (status & 1) + dse.mem_lvl = PERF_MEM_LVL_L1; + /* Nothing else supported. Sorry. */ + return dse.val; +} + static u64 load_latency_data(u64 status) { union intel_x86_pebs_dse dse; @@ -165,6 +178,22 @@ struct pebs_record_nhm { u64 status, dla, dse, lat; }; +/* + * Same as pebs_record_nhm, with two additional fields. + */ +struct pebs_record_hsw { + struct pebs_record_nhm nhm; + /* + * Real IP of the event. In the Intel documentation this + * is called eventingrip. + */ + u64 real_ip; + /* + * TSX tuning information field: abort cycles and abort flags. + */ + u64 tsx_tuning; +}; + void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -195,7 +224,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node); + buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -233,7 +262,7 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node); + buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -266,7 +295,7 @@ static int alloc_ds_buffer(int cpu) int node = cpu_to_node(cpu); struct debug_store *ds; - ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node); + ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); if (unlikely(!ds)) return -ENOMEM; @@ -488,6 +517,32 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_slm_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */ + INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */ + INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */ + INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */ + INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */ + INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */ + INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */ + INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */ + INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */ + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ @@ -529,6 +584,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ EVENT_CONSTRAINT_END }; @@ -548,6 +604,42 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_hsw_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */ + INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */ + INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */ + INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.* */ + /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), + /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), + INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), + INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */ + INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */ + INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */ + /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */ + INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf), + /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */ + INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf), + /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */ + INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf), + /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */ + INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */ + INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -588,6 +680,12 @@ void intel_pmu_pebs_disable(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); + + if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT) + cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); + else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST) + cpuc->pebs_enabled &= ~(1ULL << 63); + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -697,6 +795,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, */ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct pebs_record_nhm *pebs = __pebs; + struct pebs_record_hsw *pebs_hsw = __pebs; struct perf_sample_data data; struct pt_regs regs; u64 sample_type; @@ -706,7 +805,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event, return; fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; - fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST; + fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST | + PERF_X86_EVENT_PEBS_ST_HSW); perf_sample_data_init(&data, 0, event->hw.last_period); @@ -717,9 +817,6 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * if PEBS-LL or PreciseStore */ if (fll || fst) { - if (sample_type & PERF_SAMPLE_ADDR) - data.addr = pebs->dla; - /* * Use latency for weight (only avail with PEBS-LL) */ @@ -732,6 +829,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) { if (fll) data.data_src.val = load_latency_data(pebs->dse); + else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + data.data_src.val = + precise_store_data_hsw(pebs->dse); else data.data_src.val = precise_store_data(pebs->dse); } @@ -753,11 +853,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.bp = pebs->bp; regs.sp = pebs->sp; - if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { + regs.ip = pebs_hsw->real_ip; + regs.flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) regs.flags |= PERF_EFLAGS_EXACT; else regs.flags &= ~PERF_EFLAGS_EXACT; + if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && + x86_pmu.intel_cap.pebs_format >= 1) + data.addr = pebs->dla; + if (has_branch_stack(event)) data.br_stack = &cpuc->lbr_stack; @@ -806,35 +913,22 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) __intel_pmu_pebs_event(event, iregs, at); } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at, + void *top) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct pebs_record_nhm *at, *top; struct perf_event *event = NULL; u64 status = 0; - int bit, n; - - if (!x86_pmu.pebs_active) - return; - - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; - top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + int bit; ds->pebs_index = ds->pebs_buffer_base; - n = top - at; - if (n <= 0) - return; + for (; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n); - - for ( ; at < top; at++) { - for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) { + for_each_set_bit(bit, (unsigned long *)&p->status, + x86_pmu.max_pebs_events) { event = cpuc->events[bit]; if (!test_bit(bit, cpuc->active_mask)) continue; @@ -857,6 +951,61 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } } +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct pebs_record_nhm *at, *top; + int n; + + if (!x86_pmu.pebs_active) + return; + + at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + n = top - at; + if (n <= 0) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ONCE(n > x86_pmu.max_pebs_events, + "Unexpected number of pebs records %d\n", n); + + return __intel_pmu_drain_pebs_nhm(iregs, at, top); +} + +static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct pebs_record_hsw *at, *top; + int n; + + if (!x86_pmu.pebs_active) + return; + + at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index; + + n = top - at; + if (n <= 0) + return; + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ONCE(n > x86_pmu.max_pebs_events, + "Unexpected number of pebs records %d\n", n); + + return __intel_pmu_drain_pebs_nhm(iregs, at, top); +} + /* * BTS, PEBS probe and setup */ @@ -888,6 +1037,12 @@ void intel_ds_init(void) x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; + case 2: + pr_cont("PEBS fmt2%c, ", pebs_type); + x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw; + break; + default: printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d978353..d5be06a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -12,6 +12,16 @@ enum { LBR_FORMAT_LIP = 0x01, LBR_FORMAT_EIP = 0x02, LBR_FORMAT_EIP_FLAGS = 0x03, + LBR_FORMAT_EIP_FLAGS2 = 0x04, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_EIP_FLAGS2, +}; + +static enum { + LBR_EIP_FLAGS = 1, + LBR_TSX = 2, +} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { + [LBR_FORMAT_EIP_FLAGS] = LBR_EIP_FLAGS, + [LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX, }; /* @@ -56,6 +66,8 @@ enum { LBR_FAR) #define LBR_FROM_FLAG_MISPRED (1ULL << 63) +#define LBR_FROM_FLAG_IN_TX (1ULL << 62) +#define LBR_FROM_FLAG_ABORT (1ULL << 61) #define for_each_branch_sample_type(x) \ for ((x) = PERF_SAMPLE_BRANCH_USER; \ @@ -81,9 +93,13 @@ enum { X86_BR_JMP = 1 << 9, /* jump */ X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ X86_BR_IND_CALL = 1 << 11,/* indirect calls */ + X86_BR_ABORT = 1 << 12,/* transaction abort */ + X86_BR_IN_TX = 1 << 13,/* in transaction */ + X86_BR_NO_TX = 1 << 14,/* not in transaction */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) +#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX) #define X86_BR_ANY \ (X86_BR_CALL |\ @@ -95,6 +111,7 @@ enum { X86_BR_JCC |\ X86_BR_JMP |\ X86_BR_IRQ |\ + X86_BR_ABORT |\ X86_BR_IND_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -270,21 +287,31 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; - u64 from, to, mis = 0, pred = 0; + u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; + int skip = 0; + int lbr_flags = lbr_desc[lbr_format]; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_EIP_FLAGS) { + if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; - from = (u64)((((s64)from) << 1) >> 1); + skip = 1; + } + if (lbr_flags & LBR_TSX) { + in_tx = !!(from & LBR_FROM_FLAG_IN_TX); + abort = !!(from & LBR_FROM_FLAG_ABORT); + skip = 3; } + from = (u64)((((s64)from) << skip) >> skip); cpuc->lbr_entries[i].from = from; cpuc->lbr_entries[i].to = to; cpuc->lbr_entries[i].mispred = mis; cpuc->lbr_entries[i].predicted = pred; + cpuc->lbr_entries[i].in_tx = in_tx; + cpuc->lbr_entries[i].abort = abort; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; @@ -310,7 +337,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -318,11 +345,8 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_USER) mask |= X86_BR_USER; - if (br_type & PERF_SAMPLE_BRANCH_KERNEL) { - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) mask |= X86_BR_KERNEL; - } /* we ignore BRANCH_HV here */ @@ -337,13 +361,21 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) mask |= X86_BR_IND_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX) + mask |= X86_BR_ABORT; + + if (br_type & PERF_SAMPLE_BRANCH_IN_TX) + mask |= X86_BR_IN_TX; + + if (br_type & PERF_SAMPLE_BRANCH_NO_TX) + mask |= X86_BR_NO_TX; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; - - return 0; } /* @@ -391,9 +423,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - ret = intel_pmu_setup_sw_lbr_filter(event); - if (ret) - return ret; + intel_pmu_setup_sw_lbr_filter(event); /* * setup HW LBR filter, if any @@ -415,7 +445,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) * decoded (e.g., text page not present), then X86_BR_NONE is * returned. */ -static int branch_type(unsigned long from, unsigned long to) +static int branch_type(unsigned long from, unsigned long to, int abort) { struct insn insn; void *addr; @@ -435,6 +465,9 @@ static int branch_type(unsigned long from, unsigned long to) if (from == 0 || to == 0) return X86_BR_NONE; + if (abort) + return X86_BR_ABORT | to_plm; + if (from_plm == X86_BR_USER) { /* * can happen if measuring at the user level only @@ -581,7 +614,13 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) from = cpuc->lbr_entries[i].from; to = cpuc->lbr_entries[i].to; - type = branch_type(from, to); + type = branch_type(from, to, cpuc->lbr_entries[i].abort); + if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) { + if (cpuc->lbr_entries[i].in_tx) + type |= X86_BR_IN_TX; + else + type |= X86_BR_NO_TX; + } /* if type does not correspond, then discard */ if (type == X86_BR_NONE || (br_sel & type) != type) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 52441a2..4118f9f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -6,6 +6,8 @@ static struct intel_uncore_type **pci_uncores = empty_uncore; /* pci bus to socket mapping */ static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; +static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; + static DEFINE_RAW_SPINLOCK(uncore_box_lock); /* mask of cpus that collect uncore events */ @@ -45,6 +47,24 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); +DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); +DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { @@ -281,7 +301,7 @@ static struct attribute *snbep_uncore_cbox_formats_attr[] = { }; static struct attribute *snbep_uncore_pcu_formats_attr[] = { - &format_attr_event.attr, + &format_attr_event_ext.attr, &format_attr_occ_sel.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -301,6 +321,24 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = { &format_attr_edge.attr, &format_attr_inv.attr, &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, NULL, }; @@ -314,8 +352,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = { static struct uncore_event_desc snbep_uncore_qpi_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), { /* end: all zeroes */ }, }; @@ -356,13 +394,16 @@ static struct intel_uncore_ops snbep_uncore_msr_ops = { SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), }; +#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_pci_init_box, \ + .disable_box = snbep_uncore_pci_disable_box, \ + .enable_box = snbep_uncore_pci_enable_box, \ + .disable_event = snbep_uncore_pci_disable_event, \ + .read_counter = snbep_uncore_pci_read_counter + static struct intel_uncore_ops snbep_uncore_pci_ops = { - .init_box = snbep_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_uncore_pci_enable_event, - .read_counter = snbep_uncore_pci_read_counter, + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_uncore_pci_enable_event, \ }; static struct event_constraint snbep_uncore_cbox_constraints[] = { @@ -536,7 +577,7 @@ __snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *eve if (!uncore_box_is_fake(box)) reg1->alloc |= alloc; - return 0; + return NULL; fail: for (; i >= 0; i--) { if (alloc & (0x1 << i)) @@ -644,7 +685,7 @@ snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) (!uncore_box_is_fake(box) && reg1->alloc)) return NULL; again: - mask = 0xff << (idx * 8); + mask = 0xffULL << (idx * 8); raw_spin_lock_irqsave(&er->lock, flags); if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || !((config1 ^ er->config) & mask)) { @@ -726,6 +767,61 @@ static struct intel_uncore_type *snbep_msr_uncores[] = { NULL, }; +enum { + SNBEP_PCI_QPI_PORT0_FILTER, + SNBEP_PCI_QPI_PORT1_FILTER, +}; + +static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { + reg1->idx = 0; + reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; + reg1->config = event->attr.config1; + reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; + reg2->config = event->attr.config2; + } + return 0; +} + +static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; + struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx]; + WARN_ON_ONCE(!filter_pdev); + if (filter_pdev) { + pci_write_config_dword(filter_pdev, reg1->reg, + (u32)reg1->config); + pci_write_config_dword(filter_pdev, reg1->reg + 4, + (u32)(reg1->config >> 32)); + pci_write_config_dword(filter_pdev, reg2->reg, + (u32)reg2->config); + pci_write_config_dword(filter_pdev, reg2->reg + 4, + (u32)(reg2->config >> 32)); + } + } + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops snbep_uncore_qpi_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_qpi_enable_event, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + #define SNBEP_UNCORE_PCI_COMMON_INIT() \ .perf_ctr = SNBEP_PCI_PMON_CTR0, \ .event_ctl = SNBEP_PCI_PMON_CTL0, \ @@ -755,17 +851,18 @@ static struct intel_uncore_type snbep_uncore_imc = { }; static struct intel_uncore_type snbep_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &snbep_uncore_pci_ops, - .event_descs = snbep_uncore_qpi_events, - .format_group = &snbep_uncore_qpi_format_group, + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .event_descs = snbep_uncore_qpi_events, + .format_group = &snbep_uncore_qpi_format_group, }; @@ -807,43 +904,53 @@ static struct intel_uncore_type *snbep_pci_uncores[] = { static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { { /* Home Agent */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = SNBEP_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), }, { /* MC Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), }, { /* MC Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), }, { /* MC Channel 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), }, { /* MC Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), }, { /* QPI Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = SNBEP_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), }, { /* QPI Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = SNBEP_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = SNBEP_PCI_UNCORE_R2PCIE, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), }, { /* R3QPI Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = SNBEP_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), }, { /* R3QPI Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = SNBEP_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* end: all zeroes */ } }; @@ -1256,71 +1363,71 @@ static struct intel_uncore_type *ivt_pci_uncores[] = { static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { { /* Home Agent 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), - .driver_data = IVT_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0), }, { /* Home Agent 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), - .driver_data = IVT_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1), }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0), }, { /* MC0 Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1), }, { /* MC0 Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2), }, { /* MC0 Channel 4 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3), }, { /* MC1 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4), }, { /* MC1 Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5), }, { /* MC1 Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6), }, { /* MC1 Channel 4 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), }, { /* QPI0 Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), }, { /* QPI0 Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1), }, { /* QPI1 Port 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2), }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), - .driver_data = IVT_PCI_UNCORE_R2PCIE, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0), }, { /* R3QPI0 Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0), }, { /* R3QPI0 Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1), }, { /* R3QPI1 Link 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), }, { /* end: all zeroes */ } }; @@ -1923,7 +2030,7 @@ static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modif { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); + u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); u64 config = reg1->config; /* get the non-shared control bits and shift them */ @@ -2599,14 +2706,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) { struct intel_uncore_box *box; int i, size; size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; @@ -2701,7 +2808,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve return c; } - if (event->hw.config == ~0ULL) + if (event->attr.config == UNCORE_FIXED_EVENT) return &constraint_fixed; if (type->constraints) { @@ -2723,15 +2830,16 @@ static void uncore_put_event_constraint(struct intel_uncore_box *box, struct per static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n) { unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; - struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX]; + struct event_constraint *c; int i, wmin, wmax, ret = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { + hwc = &box->event_list[i]->hw; c = uncore_get_event_constraint(box, box->event_list[i]); - constraints[i] = c; + hwc->constraint = c; wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } @@ -2739,7 +2847,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int /* fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { hwc = &box->event_list[i]->hw; - c = constraints[i]; + c = hwc->constraint; /* never assigned */ if (hwc->idx == -1) @@ -2759,7 +2867,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int } /* slow path */ if (i != n) - ret = perf_assign_events(constraints, n, wmin, wmax, assign); + ret = perf_assign_events(box->event_list, n, + wmin, wmax, assign); if (!assign || ret) { for (i = 0; i < n; i++) @@ -2922,7 +3031,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu, struct intel_uncore_box *fake_box; int ret = -EINVAL, n; - fake_box = uncore_alloc_box(pmu->type, smp_processor_id()); + fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE); if (!fake_box) return -ENOMEM; @@ -3003,7 +3112,9 @@ static int uncore_pmu_event_init(struct perf_event *event) */ if (pmu->type->single_fixed && pmu->pmu_idx > 0) return -EINVAL; - hwc->config = ~0ULL; + + /* fixed counters have event field hardcoded to zero */ + hwc->config = 0ULL; } else { hwc->config = event->attr.config & pmu->type->event_mask; if (pmu->type->ops->hw_config) { @@ -3165,17 +3276,25 @@ static bool pcidrv_registered; /* * add a pci uncore device */ -static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) +static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, phys_id; + struct intel_uncore_type *type; + int phys_id; phys_id = pcibus_to_physid[pdev->bus->number]; if (phys_id < 0) return -ENODEV; - box = uncore_alloc_box(type, 0); + if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { + extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev; + pci_set_drvdata(pdev, NULL); + return 0; + } + + type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; + box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3183,21 +3302,11 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) * for performance monitoring unit with multiple boxes, * each box has a different function id. */ - for (i = 0; i < type->num_boxes; i++) { - pmu = &type->pmus[i]; - if (pmu->func_id == pdev->devfn) - break; - if (pmu->func_id < 0) { - pmu->func_id = pdev->devfn; - break; - } - pmu = NULL; - } - - if (!pmu) { - kfree(box); - return -EINVAL; - } + pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + if (pmu->func_id < 0) + pmu->func_id = pdev->devfn; + else + WARN_ON_ONCE(pmu->func_id != pdev->devfn); box->phys_id = phys_id; box->pci_dev = pdev; @@ -3215,9 +3324,22 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); - struct intel_uncore_pmu *pmu = box->pmu; - int cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + struct intel_uncore_pmu *pmu; + int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + box = pci_get_drvdata(pdev); + if (!box) { + for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { + if (extra_pci_dev[phys_id][i] == pdev) { + extra_pci_dev[phys_id][i] = NULL; + break; + } + } + WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX); + return; + } + + pmu = box->pmu; if (WARN_ON_ONCE(phys_id != box->phys_id)) return; @@ -3238,12 +3360,6 @@ static void uncore_pci_remove(struct pci_dev *pdev) kfree(box); } -static int uncore_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) -{ - return uncore_pci_add(pci_uncores[id->driver_data], pdev); -} - static int __init uncore_pci_init(void) { int ret; @@ -3295,7 +3411,7 @@ static void __init uncore_pci_exit(void) /* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */ static LIST_HEAD(boxes_to_free); -static void __cpuinit uncore_kfree_boxes(void) +static void uncore_kfree_boxes(void) { struct intel_uncore_box *box; @@ -3307,7 +3423,7 @@ static void __cpuinit uncore_kfree_boxes(void) } } -static void __cpuinit uncore_cpu_dying(int cpu) +static void uncore_cpu_dying(int cpu) { struct intel_uncore_type *type; struct intel_uncore_pmu *pmu; @@ -3326,7 +3442,7 @@ static void __cpuinit uncore_cpu_dying(int cpu) } } -static int __cpuinit uncore_cpu_starting(int cpu) +static int uncore_cpu_starting(int cpu) { struct intel_uncore_type *type; struct intel_uncore_pmu *pmu; @@ -3369,7 +3485,7 @@ static int __cpuinit uncore_cpu_starting(int cpu) return 0; } -static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id) +static int uncore_cpu_prepare(int cpu, int phys_id) { struct intel_uncore_type *type; struct intel_uncore_pmu *pmu; @@ -3383,7 +3499,7 @@ static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id) if (pmu->func_id < 0) pmu->func_id = j; - box = uncore_alloc_box(type, cpu); + box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; @@ -3395,7 +3511,7 @@ static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id) return 0; } -static void __cpuinit +static void uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu) { struct intel_uncore_type *type; @@ -3433,7 +3549,7 @@ uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_c } } -static void __cpuinit uncore_event_exit_cpu(int cpu) +static void uncore_event_exit_cpu(int cpu) { int i, phys_id, target; @@ -3461,7 +3577,7 @@ static void __cpuinit uncore_event_exit_cpu(int cpu) uncore_change_context(pci_uncores, cpu, target); } -static void __cpuinit uncore_event_init_cpu(int cpu) +static void uncore_event_init_cpu(int cpu) { int i, phys_id; @@ -3477,8 +3593,8 @@ static void __cpuinit uncore_event_init_cpu(int cpu) uncore_change_context(pci_uncores, -1, cpu); } -static int - __cpuinit uncore_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) +static int uncore_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; @@ -3518,7 +3634,7 @@ static int return NOTIFY_OK; } -static struct notifier_block uncore_cpu_nb __cpuinitdata = { +static struct notifier_block uncore_cpu_nb = { .notifier_call = uncore_cpu_notifier, /* * to migrate uncore events, our notifier should be executed diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index f952891..a80ab71 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -12,6 +12,15 @@ #define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC #define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) +#define UNCORE_PCI_DEV_DATA(type, idx) ((type << 8) | idx) +#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) +#define UNCORE_PCI_DEV_IDX(data) (data & 0xff) +#define UNCORE_EXTRA_PCI_DEV 0xff +#define UNCORE_EXTRA_PCI_DEV_MAX 2 + +/* support up to 8 sockets */ +#define UNCORE_SOCKET_MAX 8 + #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) /* SNB event control */ @@ -108,6 +117,7 @@ (SNBEP_PMON_CTL_EV_SEL_MASK | \ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ SNBEP_PMON_CTL_INVERT | \ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ @@ -337,10 +347,10 @@ NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) #define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) -#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (11 + 3 * (n))) +#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n))) #define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) -#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (12 + 3 * (n))) +#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n))) /* * use the 9~13 bits to select event If the 7th bit is not set, diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c index 7b3fe56..31f0f33 100644 --- a/arch/x86/kernel/cpu/powerflags.c +++ b/arch/x86/kernel/cpu/powerflags.c @@ -11,10 +11,10 @@ const char *const x86_power_flags[32] = { "fid", /* frequency id control */ "vid", /* voltage id control */ "ttp", /* thermal trip */ - "tm", - "stc", - "100mhzsteps", - "hwpstate", + "tm", /* hardware thermal control */ + "stc", /* software thermal control */ + "100mhzsteps", /* 100 MHz multiplier control */ + "hwpstate", /* hardware P-state control */ "", /* tsc invariant mapped to constant_tsc */ "cpb", /* core performance boost */ "eff_freq_ro", /* Readonly aperf/mperf */ diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 37a198b..aee6317 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -37,8 +37,8 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no", static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no", static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no", - c->hard_math ? "yes" : "no", - c->hard_math ? "yes" : "no", + static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no", + static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no", c->cpuid_level, c->wp_works_ok ? "yes" : "no"); } diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index feca286..88db010 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -52,7 +52,7 @@ static inline int rdrand_long(unsigned long *v) */ #define RESEED_LOOP ((512*128)/sizeof(unsigned long)) -void __cpuinit x86_init_rdrand(struct cpuinfo_x86 *c) +void x86_init_rdrand(struct cpuinfo_x86 *c) { #ifdef CONFIG_ARCH_RANDOM unsigned long tmp; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index d92b5da..f2cc63e 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -24,13 +24,13 @@ enum cpuid_regs { CR_EBX }; -void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) +void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { u32 max_level; u32 regs[4]; const struct cpuid_bit *cb; - static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { + static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 4397e98..4c60eaf 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -26,7 +26,7 @@ * exists, use it for populating initial_apicid and cpu topology * detection. */ -void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c) +void detect_extended_topology(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP unsigned int eax, ebx, ecx, edx, sub_index; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 2800074..aa0430d 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -5,7 +5,7 @@ #include <asm/msr.h> #include "cpu.h" -static void __cpuinit early_init_transmeta(struct cpuinfo_x86 *c) +static void early_init_transmeta(struct cpuinfo_x86 *c) { u32 xlvl; @@ -17,7 +17,7 @@ static void __cpuinit early_init_transmeta(struct cpuinfo_x86 *c) } } -static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) +static void init_transmeta(struct cpuinfo_x86 *c) { unsigned int cap_mask, uk, max, dummy; unsigned int cms_rev1, cms_rev2; @@ -98,7 +98,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c) #endif } -static const struct cpu_dev __cpuinitconst transmeta_cpu_dev = { +static const struct cpu_dev transmeta_cpu_dev = { .c_vendor = "Transmeta", .c_ident = { "GenuineTMx86", "TransmetaCPU" }, .c_early_init = early_init_transmeta, diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c index fd2c37b..202759a 100644 --- a/arch/x86/kernel/cpu/umc.c +++ b/arch/x86/kernel/cpu/umc.c @@ -8,7 +8,7 @@ * so no special init takes place. */ -static const struct cpu_dev __cpuinitconst umc_cpu_dev = { +static const struct cpu_dev umc_cpu_dev = { .c_vendor = "UMC", .c_ident = { "UMC UMC UMC" }, .c_models = { diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 03a3632..628a059 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -93,7 +93,7 @@ static void __init vmware_platform_setup(void) * serial key should be enough, as this will always have a VMware * specific string when running under VMware hypervisor. */ -static bool __init vmware_platform(void) +static uint32_t __init vmware_platform(void) { if (cpu_has_hypervisor) { unsigned int eax; @@ -102,12 +102,12 @@ static bool __init vmware_platform(void) cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0], &hyper_vendor_id[1], &hyper_vendor_id[2]); if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) - return true; + return CPUID_VMWARE_INFO_LEAF; } else if (dmi_available && dmi_name_in_serial("VMware") && __vmware_platform()) - return true; + return 1; - return false; + return 0; } /* @@ -122,7 +122,7 @@ static bool __init vmware_platform(void) * so that the kernel could just trust the hypervisor with providing a * reliable virtual TSC that is suitable for timekeeping. */ -static void __cpuinit vmware_set_cpu_features(struct cpuinfo_x86 *c) +static void vmware_set_cpu_features(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 1e4dbcf..7d9481c 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -137,7 +137,7 @@ static const struct file_operations cpuid_fops = { .open = cpuid_open, }; -static __cpuinit int cpuid_device_create(int cpu) +static int cpuid_device_create(int cpu) { struct device *dev; @@ -151,9 +151,8 @@ static void cpuid_device_destroy(int cpu) device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu)); } -static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) +static int cpuid_class_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; int err = 0; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 74467fe..e0e0841 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -128,7 +128,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_svm_disable(); lapic_shutdown(); -#if defined(CONFIG_X86_IO_APIC) +#ifdef CONFIG_X86_IO_APIC + /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ + ioapic_zap_locks(); disable_IO_APIC(); #endif #ifdef CONFIG_HPET_TIMER diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index b158152..376dc78 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) } #ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end) +void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) { initrd_start = (unsigned long)__va(start); initrd_end = (unsigned long)__va(end); @@ -133,7 +132,7 @@ static void x86_of_pci_irq_disable(struct pci_dev *dev) { } -void __cpuinit x86_of_pci_init(void) +void x86_of_pci_init(void) { pcibios_enable_irq = x86_of_pci_irq_enable; pcibios_disable_irq = x86_of_pci_irq_disable; @@ -364,9 +363,7 @@ static void dt_add_ioapic_domain(unsigned int ioapic_num, * and assigned so we can keep the 1:1 mapping which the ioapic * is having. */ - ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY); - if (ret) - pr_err("Error mapping legacy IRQs: %d\n", ret); + irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY); if (num > NR_IRQS_LEGACY) { ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY, diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault.c index 155a13f..5d3fe8d 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault.c @@ -9,6 +9,8 @@ #include <asm/processor.h> #include <asm/desc.h> +#ifdef CONFIG_X86_32 + #define DOUBLEFAULT_STACKSIZE (1024) static unsigned long doublefault_stack[DOUBLEFAULT_STACKSIZE]; #define STACK_START (unsigned long)(doublefault_stack+DOUBLEFAULT_STACKSIZE) @@ -67,3 +69,16 @@ struct tss_struct doublefault_tss __cacheline_aligned = { .__cr3 = __pa_nodebug(swapper_pg_dir), } }; + +/* dummy for do_double_fault() call */ +void df_debug(struct pt_regs *regs, long error_code) {} + +#else /* !CONFIG_X86_32 */ + +void df_debug(struct pt_regs *regs, long error_code) +{ + pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); + show_regs(regs); + panic("Machine halted."); +} +#endif diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abea..174da5f 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -658,15 +658,18 @@ __init void e820_setup_gap(void) * boot_params.e820_map, others are passed via SETUP_E820_EXT node of * linked list of struct setup_data, which is parsed here. */ -void __init parse_e820_ext(struct setup_data *sdata) +void __init parse_e820_ext(u64 phys_addr, u32 data_len) { int entries; struct e820entry *extmap; + struct setup_data *sdata; + sdata = early_memremap(phys_addr, data_len); entries = sdata->len / sizeof(struct e820entry); extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + early_iounmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 94ab6b9..b3cd3eb 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <linux/acpi.h> #include <linux/pci_ids.h> +#include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> #include <asm/io_apic.h> @@ -196,16 +197,175 @@ static void __init ati_bugs_contd(int num, int slot, int func) static void __init intel_remapping_check(int num, int slot, int func) { u8 revision; + u16 device; + device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID); /* - * Revision 0x13 of this chipset supports irq remapping - * but has an erratum that breaks its behavior, flag it as such + * Revision 13 of all triggering devices id in this quirk have + * a problem draining interrupts when irq remapping is enabled, + * and should be flagged as broken. Additionally revisions 0x12 + * and 0x22 of device id 0x3405 has this problem. */ if (revision == 0x13) set_irq_remapping_broken(); + else if ((device == 0x3405) && + ((revision == 0x12) || + (revision == 0x22))) + set_irq_remapping_broken(); + +} + +/* + * Systems with Intel graphics controllers set aside memory exclusively + * for gfx driver use. This memory is not marked in the E820 as reserved + * or as RAM, and so is subject to overlap from E820 manipulation later + * in the boot process. On some systems, MMIO space is allocated on top, + * despite the efforts of the "RAM buffer" approach, which simply rounds + * memory boundaries up to 64M to try to catch space that may decode + * as RAM and so is not suitable for MMIO. + * + * And yes, so far on current devices the base addr is always under 4G. + */ +static u32 __init intel_stolen_base(int num, int slot, int func) +{ + u32 base; + + /* + * For the PCI IDs in this quirk, the stolen base is always + * in 0x5c, aka the BDSM register (yes that's really what + * it's called). + */ + base = read_pci_config(num, slot, func, 0x5c); + base &= ~((1<<20) - 1); + + return base; +} + +#define KB(x) ((x) * 1024) +#define MB(x) (KB (KB (x))) +#define GB(x) (MB (KB (x))) + +static size_t __init gen3_stolen_size(int num, int slot, int func) +{ + size_t stolen_size; + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL); + + switch (gmch_ctrl & I855_GMCH_GMS_MASK) { + case I855_GMCH_GMS_STOLEN_1M: + stolen_size = MB(1); + break; + case I855_GMCH_GMS_STOLEN_4M: + stolen_size = MB(4); + break; + case I855_GMCH_GMS_STOLEN_8M: + stolen_size = MB(8); + break; + case I855_GMCH_GMS_STOLEN_16M: + stolen_size = MB(16); + break; + case I855_GMCH_GMS_STOLEN_32M: + stolen_size = MB(32); + break; + case I915_GMCH_GMS_STOLEN_48M: + stolen_size = MB(48); + break; + case I915_GMCH_GMS_STOLEN_64M: + stolen_size = MB(64); + break; + case G33_GMCH_GMS_STOLEN_128M: + stolen_size = MB(128); + break; + case G33_GMCH_GMS_STOLEN_256M: + stolen_size = MB(256); + break; + case INTEL_GMCH_GMS_STOLEN_96M: + stolen_size = MB(96); + break; + case INTEL_GMCH_GMS_STOLEN_160M: + stolen_size = MB(160); + break; + case INTEL_GMCH_GMS_STOLEN_224M: + stolen_size = MB(224); + break; + case INTEL_GMCH_GMS_STOLEN_352M: + stolen_size = MB(352); + break; + default: + stolen_size = 0; + break; + } + + return stolen_size; +} + +static size_t __init gen6_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + return gmch_ctrl << 25; /* 32 MB units */ +} + +typedef size_t (*stolen_size_fn)(int num, int slot, int func); + +static struct pci_device_id intel_stolen_ids[] __initdata = { + INTEL_I915G_IDS(gen3_stolen_size), + INTEL_I915GM_IDS(gen3_stolen_size), + INTEL_I945G_IDS(gen3_stolen_size), + INTEL_I945GM_IDS(gen3_stolen_size), + INTEL_VLV_M_IDS(gen3_stolen_size), + INTEL_VLV_D_IDS(gen3_stolen_size), + INTEL_PINEVIEW_IDS(gen3_stolen_size), + INTEL_I965G_IDS(gen3_stolen_size), + INTEL_G33_IDS(gen3_stolen_size), + INTEL_I965GM_IDS(gen3_stolen_size), + INTEL_GM45_IDS(gen3_stolen_size), + INTEL_G45_IDS(gen3_stolen_size), + INTEL_IRONLAKE_D_IDS(gen3_stolen_size), + INTEL_IRONLAKE_M_IDS(gen3_stolen_size), + INTEL_SNB_D_IDS(gen6_stolen_size), + INTEL_SNB_M_IDS(gen6_stolen_size), + INTEL_IVB_M_IDS(gen6_stolen_size), + INTEL_IVB_D_IDS(gen6_stolen_size), + INTEL_HSW_D_IDS(gen6_stolen_size), + INTEL_HSW_M_IDS(gen6_stolen_size), +}; +static void __init intel_graphics_stolen(int num, int slot, int func) +{ + size_t size; + int i; + u32 start; + u16 device, subvendor, subdevice; + + device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); + subvendor = read_pci_config_16(num, slot, func, + PCI_SUBSYSTEM_VENDOR_ID); + subdevice = read_pci_config_16(num, slot, func, PCI_SUBSYSTEM_ID); + + for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) { + if (intel_stolen_ids[i].device == device) { + stolen_size_fn stolen_size = + (stolen_size_fn)intel_stolen_ids[i].driver_data; + size = stolen_size(num, slot, func); + start = intel_stolen_base(num, slot, func); + if (size && start) { + /* Mark this space as reserved */ + e820_add_region(start, size, E820_RESERVED); + sanitize_e820_map(e820.map, + ARRAY_SIZE(e820.map), + &e820.nr_map); + } + return; + } + } } #define QFLAG_APPLY_ONCE 0x1 @@ -239,8 +399,12 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, { PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, + { PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST, + PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, + { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID, + QFLAG_APPLY_ONCE, intel_graphics_stolen }, {} }; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 8f3e2de..f0dcb0c 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -801,7 +801,17 @@ ENTRY(name) \ CFI_ENDPROC; \ ENDPROC(name) -#define BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(name, nr, smp_##name) + +#ifdef CONFIG_TRACING +#define TRACE_BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) +#else +#define TRACE_BUILD_INTERRUPT(name, nr) +#endif + +#define BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(name, nr, smp_##name); \ + TRACE_BUILD_INTERRUPT(name, nr) /* The include is where all of the SMP etc. interrupts come from */ #include <asm/entry_arch.h> @@ -1166,6 +1176,9 @@ ftrace_restore_flags: #else /* ! CONFIG_DYNAMIC_FTRACE */ ENTRY(mcount) + cmpl $__PAGE_OFFSET, %esp + jb ftrace_stub /* Paging not enabled yet? */ + cmpl $0, function_trace_stop jne ftrace_stub diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 7272089..b077f4c 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -365,7 +365,7 @@ ENDPROC(native_usergs_sysret64) /*CFI_REL_OFFSET ss,0*/ pushq_cfi %rax /* rsp */ CFI_REL_OFFSET rsp,0 - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */ + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */ /*CFI_REL_OFFSET rflags,0*/ pushq_cfi $__KERNEL_CS /* cs */ /*CFI_REL_OFFSET cs,0*/ @@ -487,21 +487,6 @@ ENDPROC(native_usergs_sysret64) TRACE_IRQS_OFF .endm -ENTRY(save_rest) - PARTIAL_FRAME 1 (REST_SKIP+8) - movq 5*8+16(%rsp), %r11 /* save return address */ - movq_cfi rbx, RBX+16 - movq_cfi rbp, RBP+16 - movq_cfi r12, R12+16 - movq_cfi r13, R13+16 - movq_cfi r14, R14+16 - movq_cfi r15, R15+16 - movq %r11, 8(%rsp) /* return address */ - FIXUP_TOP_OF_STACK %r11, 16 - ret - CFI_ENDPROC -END(save_rest) - /* save complete stack frame */ .pushsection .kprobes.text, "ax" ENTRY(save_paranoid) @@ -1138,7 +1123,7 @@ END(common_interrupt) /* * APIC interrupts. */ -.macro apicinterrupt num sym do_sym +.macro apicinterrupt3 num sym do_sym ENTRY(\sym) INTR_FRAME ASM_CLAC @@ -1150,15 +1135,32 @@ ENTRY(\sym) END(\sym) .endm +#ifdef CONFIG_TRACING +#define trace(sym) trace_##sym +#define smp_trace(sym) smp_trace_##sym + +.macro trace_apicinterrupt num sym +apicinterrupt3 \num trace(\sym) smp_trace(\sym) +.endm +#else +.macro trace_apicinterrupt num sym do_sym +.endm +#endif + +.macro apicinterrupt num sym do_sym +apicinterrupt3 \num \sym \do_sym +trace_apicinterrupt \num \sym +.endm + #ifdef CONFIG_SMP -apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \ +apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \ irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt -apicinterrupt REBOOT_VECTOR \ +apicinterrupt3 REBOOT_VECTOR \ reboot_interrupt smp_reboot_interrupt #endif #ifdef CONFIG_X86_UV -apicinterrupt UV_BAU_MESSAGE \ +apicinterrupt3 UV_BAU_MESSAGE \ uv_bau_message_intr1 uv_bau_message_interrupt #endif apicinterrupt LOCAL_TIMER_VECTOR \ @@ -1167,14 +1169,19 @@ apicinterrupt X86_PLATFORM_IPI_VECTOR \ x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_HAVE_KVM -apicinterrupt POSTED_INTR_VECTOR \ +apicinterrupt3 POSTED_INTR_VECTOR \ kvm_posted_intr_ipi smp_kvm_posted_intr_ipi #endif +#ifdef CONFIG_X86_MCE_THRESHOLD apicinterrupt THRESHOLD_APIC_VECTOR \ threshold_interrupt smp_threshold_interrupt +#endif + +#ifdef CONFIG_X86_THERMAL_VECTOR apicinterrupt THERMAL_APIC_VECTOR \ thermal_interrupt smp_thermal_interrupt +#endif #ifdef CONFIG_SMP apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ @@ -1451,13 +1458,13 @@ ENTRY(xen_failsafe_callback) CFI_ENDPROC END(xen_failsafe_callback) -apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ +apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ xen_hvm_callback_vector xen_evtchn_do_upcall #endif /* CONFIG_XEN */ #if IS_ENABLED(CONFIG_HYPERV) -apicinterrupt HYPERVISOR_CALLBACK_VECTOR \ +apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 138463a..06f87be 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void) reserve_ebda_region(); } -void __init i386_start_kernel(void) +asmlinkage void __init i386_start_kernel(void) { sanitize_boot_params(&boot_params); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 55b6761..1be8e43 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data) } } -void __init x86_64_start_kernel(char * real_mode_data) +asmlinkage void __init x86_64_start_kernel(char * real_mode_data) { int i; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 73afd11..81ba276 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -292,7 +292,6 @@ ENDPROC(start_cpu0) * If cpu hotplug is not supported then this code can go in init section * which will be freed later */ -__CPUINIT ENTRY(startup_32_smp) cld movl $(__BOOT_DS),%eax @@ -410,6 +409,7 @@ enable_paging: /* * Check if it is 486 */ + movb $4,X86 # at least 486 cmpl $-1,X86_CPUID je is486 @@ -437,14 +437,12 @@ enable_paging: movl %edx,X86_CAPABILITY is486: - movb $4,X86 movl $0x50022,%ecx # set AM, WP, NE and MP movl %cr0,%eax andl $0x80000011,%eax # Save PG,PE,ET orl %ecx,%eax movl %eax,%cr0 - call check_x87 lgdt early_gdt_descr lidt idt_descr ljmp $(__KERNEL_CS),$1f @@ -467,26 +465,6 @@ is486: pushl $0 # fake return address for unwinder jmp *(initial_code) -/* - * We depend on ET to be correct. This checks for 287/387. - */ -check_x87: - movb $0,X86_HARD_MATH - clts - fninit - fstsw %ax - cmpb $0,%al - je 1f - movl %cr0,%eax /* no coprocessor: have to set bits */ - xorl $4,%eax /* set EM */ - movl %eax,%cr0 - ret - ALIGN -1: movb $1,X86_HARD_MATH - .byte 0xDB,0xE4 /* fsetpm for 287, ignored by 387 */ - ret - - #include "verify_cpu.S" /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 321d65e..e1aabdb 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -512,15 +512,6 @@ ENTRY(phys_base) #include "../../x86/xen/xen-head.S" - .section .bss, "aw", @nobits - .align L1_CACHE_BYTES -ENTRY(idt_table) - .skip IDT_ENTRIES * 16 - - .align L1_CACHE_BYTES -ENTRY(nmi_idt_table) - .skip IDT_ENTRIES * 16 - __PAGE_ALIGNED_BSS NEXT_PAGE(empty_zero_page) .skip PAGE_SIZE diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 02f0763..f66ff16 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -393,6 +393,9 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) unregister_hw_breakpoint(t->ptrace_bps[i]); t->ptrace_bps[i] = NULL; } + + t->debugreg6 = 0; + t->ptrace_dr7 = 0; } void hw_breakpoint_restore(void) diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index cb33909..5d576ab 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -108,15 +108,15 @@ EXPORT_SYMBOL(unlazy_fpu); unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -static struct i387_fxsave_struct fx_scratch __cpuinitdata; +static struct i387_fxsave_struct fx_scratch; -static void __cpuinit mxcsr_feature_mask_init(void) +static void mxcsr_feature_mask_init(void) { unsigned long mask = 0; if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : : "m" (fx_scratch)); + asm volatile("fxsave %0" : "+m" (fx_scratch)); mask = fx_scratch.mxcsr_mask; if (mask == 0) mask = 0x0000ffbf; @@ -124,14 +124,14 @@ static void __cpuinit mxcsr_feature_mask_init(void) mxcsr_feature_mask &= mask; } -static void __cpuinit init_thread_xstate(void) +static void init_thread_xstate(void) { /* * Note that xstate_size might be overwriten later during * xsave_init(). */ - if (!HAVE_HWFP) { + if (!cpu_has_fpu) { /* * Disable xsave as we do not support it if i387 * emulation is enabled. @@ -153,11 +153,19 @@ static void __cpuinit init_thread_xstate(void) * into all processes. */ -void __cpuinit fpu_init(void) +void fpu_init(void) { unsigned long cr0; unsigned long cr4_mask = 0; +#ifndef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) { + pr_emerg("No FPU found and no math emulation present\n"); + pr_emerg("Giving up\n"); + for (;;) + asm volatile("hlt"); + } +#endif if (cpu_has_fxsr) cr4_mask |= X86_CR4_OSFXSR; if (cpu_has_xmm) @@ -167,7 +175,7 @@ void __cpuinit fpu_init(void) cr0 = read_cr0(); cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!HAVE_HWFP) + if (!cpu_has_fpu) cr0 |= X86_CR0_EM; write_cr0(cr0); @@ -185,7 +193,7 @@ void __cpuinit fpu_init(void) void fpu_finit(struct fpu *fpu) { - if (!HAVE_HWFP) { + if (!cpu_has_fpu) { finit_soft_fpu(&fpu->state->soft); return; } @@ -214,7 +222,7 @@ int init_fpu(struct task_struct *tsk) int ret; if (tsk_used_math(tsk)) { - if (HAVE_HWFP && tsk == current) + if (cpu_has_fpu && tsk == current) unlazy_fpu(tsk); tsk->thread.fpu.last_cpu = ~0; return 0; @@ -511,14 +519,13 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - if (!HAVE_HWFP) + if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) { + if (!cpu_has_fxsr) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fpu.state->fsave, 0, -1); - } sanitize_i387_state(target); @@ -545,13 +552,13 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, sanitize_i387_state(target); - if (!HAVE_HWFP) + if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - if (!cpu_has_fxsr) { + if (!cpu_has_fxsr) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, -1); - } + &target->thread.fpu.state->fsave, 0, + -1); if (pos > 0 || count < sizeof(env)) convert_from_fxsr(&env, target); @@ -592,3 +599,33 @@ int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu) EXPORT_SYMBOL(dump_fpu); #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ + +static int __init no_387(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FPU); + return 1; +} + +__setup("no387", no_387); + +void fpu_detect(struct cpuinfo_x86 *c) +{ + unsigned long cr0; + u16 fsw, fcw; + + fsw = fcw = 0xffff; + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS | X86_CR0_EM); + write_cr0(cr0); + + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); + + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + + /* The final cr0 value is set in fpu_init() */ +} diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index ac0631d..22d0687 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -18,6 +18,9 @@ #include <asm/mce.h> #include <asm/hw_irq.h> +#define CREATE_TRACE_POINTS +#include <asm/trace/irq_vectors.h> + atomic_t irq_err_count; /* Function pointer for generic interrupt vector handling */ @@ -174,7 +177,7 @@ u64 arch_irq_stat(void) * SMP cross-CPU interrupts have their own specific * handlers). */ -unsigned int __irq_entry do_IRQ(struct pt_regs *regs) +__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -204,23 +207,21 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) /* * Handler for X86_PLATFORM_IPI_VECTOR. */ -void smp_x86_platform_ipi(struct pt_regs *regs) +void __smp_x86_platform_ipi(void) { - struct pt_regs *old_regs = set_irq_regs(regs); - - ack_APIC_irq(); - - irq_enter(); - - exit_idle(); - inc_irq_stat(x86_platform_ipis); if (x86_platform_ipi_callback) x86_platform_ipi_callback(); +} - irq_exit(); +__visible void smp_x86_platform_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + entering_ack_irq(); + __smp_x86_platform_ipi(); + exiting_irq(); set_irq_regs(old_regs); } @@ -228,7 +229,7 @@ void smp_x86_platform_ipi(struct pt_regs *regs) /* * Handler for POSTED_INTERRUPT_VECTOR. */ -void smp_kvm_posted_intr_ipi(struct pt_regs *regs) +__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -246,6 +247,18 @@ void smp_kvm_posted_intr_ipi(struct pt_regs *regs) } #endif +__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + entering_ack_irq(); + trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); + __smp_x86_platform_ipi(); + trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); + exiting_irq(); + set_irq_regs(old_regs); +} + EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq); #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 344faf8..4186755 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -119,7 +119,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) /* * allocate per-cpu stacks for hardirq and for softirq processing */ -void __cpuinit irq_ctx_init(int cpu) +void irq_ctx_init(int cpu) { union irq_ctx *irqctx; diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index ca8f703..1de84e3a 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -8,14 +8,34 @@ #include <linux/irq_work.h> #include <linux/hardirq.h> #include <asm/apic.h> +#include <asm/trace/irq_vectors.h> -void smp_irq_work_interrupt(struct pt_regs *regs) +static inline void irq_work_entering_irq(void) { irq_enter(); ack_APIC_irq(); +} + +static inline void __smp_irq_work_interrupt(void) +{ inc_irq_stat(apic_irq_work_irqs); irq_work_run(); - irq_exit(); +} + +__visible void smp_irq_work_interrupt(struct pt_regs *regs) +{ + irq_work_entering_irq(); + __smp_irq_work_interrupt(); + exiting_irq(); +} + +__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) +{ + irq_work_entering_irq(); + trace_irq_work_entry(IRQ_WORK_VECTOR); + __smp_irq_work_interrupt(); + trace_irq_work_exit(IRQ_WORK_VECTOR); + exiting_irq(); } void arch_irq_work_raise(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 2889b3d..ee11b7d 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -24,20 +24,71 @@ union jump_code_union { } __attribute__((packed)); }; +static void bug_at(unsigned char *ip, int line) +{ + /* + * The location is not an op that we were expecting. + * Something went wrong. Crash the box, as something could be + * corrupting the kernel. + */ + pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n", + ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line); + BUG(); +} + static void __jump_label_transform(struct jump_entry *entry, enum jump_label_type type, - void *(*poker)(void *, const void *, size_t)) + void *(*poker)(void *, const void *, size_t), + int init) { union jump_code_union code; + const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; if (type == JUMP_LABEL_ENABLE) { + /* + * We are enabling this jump label. If it is not a nop + * then something must have gone wrong. + */ + if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) != 0)) + bug_at((void *)entry->code, __LINE__); + code.jump = 0xe9; code.offset = entry->target - (entry->code + JUMP_LABEL_NOP_SIZE); - } else + } else { + /* + * We are disabling this jump label. If it is not what + * we think it is, then something must have gone wrong. + * If this is the first initialization call, then we + * are converting the default nop to the ideal nop. + */ + if (init) { + const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; + if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0)) + bug_at((void *)entry->code, __LINE__); + } else { + code.jump = 0xe9; + code.offset = entry->target - + (entry->code + JUMP_LABEL_NOP_SIZE); + if (unlikely(memcmp((void *)entry->code, &code, 5) != 0)) + bug_at((void *)entry->code, __LINE__); + } memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); + } - (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + /* + * Make text_poke_bp() a default fallback poker. + * + * At the time the change is being done, just ignore whether we + * are doing nop -> jump or jump -> nop transition, and assume + * always nop being the 'currently valid' instruction + * + */ + if (poker) + (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + else + text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE, + (void *)entry->code + JUMP_LABEL_NOP_SIZE); } void arch_jump_label_transform(struct jump_entry *entry, @@ -45,15 +96,38 @@ void arch_jump_label_transform(struct jump_entry *entry, { get_online_cpus(); mutex_lock(&text_mutex); - __jump_label_transform(entry, type, text_poke_smp); + __jump_label_transform(entry, type, NULL, 0); mutex_unlock(&text_mutex); put_online_cpus(); } +static enum { + JL_STATE_START, + JL_STATE_NO_UPDATE, + JL_STATE_UPDATE, +} jlstate __initdata_or_module = JL_STATE_START; + __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { - __jump_label_transform(entry, type, text_poke_early); + /* + * This function is called at boot up and when modules are + * first loaded. Check if the default nop, the one that is + * inserted at compile time, is the ideal nop. If it is, then + * we do not need to update the nop, and we can leave it as is. + * If it is not, then we need to update the nop to the ideal nop. + */ + if (jlstate == JL_STATE_START) { + const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; + const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; + + if (memcmp(ideal_nop, default_nop, 5) != 0) + jlstate = JL_STATE_UPDATE; + else + jlstate = JL_STATE_NO_UPDATE; + } + if (jlstate == JL_STATE_UPDATE) + __jump_label_transform(entry, type, text_poke_early, 1); } #endif diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index 2e9d4b5..c6ee63f 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to); extern void synthesize_relcall(void *from, void *to); #ifdef CONFIG_OPTPROBES -extern int arch_init_optprobes(void); extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); #else /* !CONFIG_OPTPROBES */ -static inline int arch_init_optprobes(void) -{ - return 0; -} static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) { return 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 9895a9a..79a3f96 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -365,10 +365,14 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) return insn.length; } -static void __kprobes arch_copy_kprobe(struct kprobe *p) +static int __kprobes arch_copy_kprobe(struct kprobe *p) { + int ret; + /* Copy an instruction with recovering if other optprobe modifies it.*/ - __copy_instruction(p->ainsn.insn, p->addr); + ret = __copy_instruction(p->ainsn.insn, p->addr); + if (!ret) + return -EINVAL; /* * __copy_instruction can modify the displacement of the instruction, @@ -384,6 +388,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) /* Also, displacement change doesn't affect the first byte */ p->opcode = p->ainsn.insn[0]; + + return 0; } int __kprobes arch_prepare_kprobe(struct kprobe *p) @@ -397,8 +403,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) p->ainsn.insn = get_insn_slot(); if (!p->ainsn.insn) return -ENOMEM; - arch_copy_kprobe(p); - return 0; + + return arch_copy_kprobe(p); } void __kprobes arch_arm_kprobe(struct kprobe *p) @@ -655,7 +661,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void) /* * Called from kretprobe_trampoline */ -static __used __kprobes void *trampoline_handler(struct pt_regs *regs) +__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; @@ -1062,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) int __init arch_init_kprobes(void) { - return arch_init_optprobes(); + return 0; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 76dc6f0..898160b 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -88,9 +88,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long v *(unsigned long *)addr = val; } -static void __used __kprobes kprobes_optinsn_template_holder(void) -{ - asm volatile ( +asm ( ".global optprobe_template_entry\n" "optprobe_template_entry:\n" #ifdef CONFIG_X86_64 @@ -129,7 +127,6 @@ static void __used __kprobes kprobes_optinsn_template_holder(void) #endif ".global optprobe_template_end\n" "optprobe_template_end:\n"); -} #define TMPL_MOVE_IDX \ ((long)&optprobe_template_val - (long)&optprobe_template_entry) @@ -371,31 +368,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - /* * Replace breakpoints (int3) with relative jumps. * Caller must call with locking kprobe_mutex and text_mutex. @@ -403,37 +375,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, void __kprobes arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - int c = 0; + u8 insn_buf[RELATIVEJUMP_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); + list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); } -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) { + u8 insn_buf[RELATIVEJUMP_SIZE]; + /* Set int3 to first byte for kprobes */ insn_buf[0] = BREAKPOINT_INSTRUCTION; memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); } /* @@ -444,34 +417,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list) { struct optimized_kprobe *op, *tmp; - int c = 0; list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + arch_unoptimize_kprobe(op); list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); } int __kprobes @@ -491,22 +441,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) } return 0; } - -int __kprobes arch_init_optprobes(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index cd6d9a5..697b93a 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -34,6 +34,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/kprobes.h> +#include <linux/debugfs.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -320,7 +321,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) apic_write(APIC_EOI, APIC_EOI_ACK); } -void __cpuinit kvm_guest_cpu_init(void) +void kvm_guest_cpu_init(void) { if (!kvm_para_available()) return; @@ -419,9 +420,10 @@ static void __init kvm_smp_prepare_boot_cpu(void) WARN_ON(kvm_register_clock("primary cpu clock")); kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); + kvm_spinlock_init(); } -static void __cpuinit kvm_guest_cpu_online(void *dummy) +static void kvm_guest_cpu_online(void *dummy) { kvm_guest_cpu_init(); } @@ -435,8 +437,8 @@ static void kvm_guest_cpu_offline(void *dummy) apf_task_wake_all(); } -static int __cpuinit kvm_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) +static int kvm_cpu_notify(struct notifier_block *self, unsigned long action, + void *hcpu) { int cpu = (unsigned long)hcpu; switch (action) { @@ -455,7 +457,7 @@ static int __cpuinit kvm_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata kvm_cpu_notifier = { +static struct notifier_block kvm_cpu_notifier = { .notifier_call = kvm_cpu_notify, }; #endif @@ -498,11 +500,9 @@ void __init kvm_guest_init(void) #endif } -static bool __init kvm_detect(void) +static uint32_t __init kvm_detect(void) { - if (!kvm_para_available()) - return false; - return true; + return kvm_cpuid_base(); } const struct hypervisor_x86 x86_hyper_kvm __refconst = { @@ -523,3 +523,263 @@ static __init int activate_jump_labels(void) return 0; } arch_initcall(activate_jump_labels); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +/* Kick a cpu by its apicid. Used to wake up a halted vcpu */ +static void kvm_kick_cpu(int cpu) +{ + int apicid; + unsigned long flags = 0; + + apicid = per_cpu(x86_cpu_to_apicid, cpu); + kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); +} + +enum kvm_contention_stat { + TAKEN_SLOW, + TAKEN_SLOW_PICKUP, + RELEASED_SLOW, + RELEASED_SLOW_KICKED, + NR_CONTENTION_STATS +}; + +#ifdef CONFIG_KVM_DEBUG_FS +#define HISTO_BUCKETS 30 + +static struct kvm_spinlock_stats +{ + u32 contention_stats[NR_CONTENTION_STATS]; + u32 histo_spin_blocked[HISTO_BUCKETS+1]; + u64 time_blocked; +} spinlock_stats; + +static u8 zero_stats; + +static inline void check_zero(void) +{ + u8 ret; + u8 old; + + old = ACCESS_ONCE(zero_stats); + if (unlikely(old)) { + ret = cmpxchg(&zero_stats, old, 0); + /* This ensures only one fellow resets the stat */ + if (ret == old) + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); + } +} + +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ + check_zero(); + spinlock_stats.contention_stats[var] += val; +} + + +static inline u64 spin_time_start(void) +{ + return sched_clock(); +} + +static void __spin_time_accum(u64 delta, u32 *array) +{ + unsigned index; + + index = ilog2(delta); + check_zero(); + + if (index < HISTO_BUCKETS) + array[index]++; + else + array[HISTO_BUCKETS]++; +} + +static inline void spin_time_accum_blocked(u64 start) +{ + u32 delta; + + delta = sched_clock() - start; + __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); + spinlock_stats.time_blocked += delta; +} + +static struct dentry *d_spin_debug; +static struct dentry *d_kvm_debug; + +struct dentry *kvm_init_debugfs(void) +{ + d_kvm_debug = debugfs_create_dir("kvm", NULL); + if (!d_kvm_debug) + printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); + + return d_kvm_debug; +} + +static int __init kvm_spinlock_debugfs(void) +{ + struct dentry *d_kvm; + + d_kvm = kvm_init_debugfs(); + if (d_kvm == NULL) + return -ENOMEM; + + d_spin_debug = debugfs_create_dir("spinlocks", d_kvm); + + debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); + + debugfs_create_u32("taken_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW]); + debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); + + debugfs_create_u32("released_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW]); + debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); + + debugfs_create_u64("time_blocked", 0444, d_spin_debug, + &spinlock_stats.time_blocked); + + debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, + spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); + + return 0; +} +fs_initcall(kvm_spinlock_debugfs); +#else /* !CONFIG_KVM_DEBUG_FS */ +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ +} + +static inline u64 spin_time_start(void) +{ + return 0; +} + +static inline void spin_time_accum_blocked(u64 start) +{ +} +#endif /* CONFIG_KVM_DEBUG_FS */ + +struct kvm_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; +}; + +/* cpus 'waiting' on a spinlock to become available */ +static cpumask_t waiting_cpus; + +/* Track spinlock on which a cpu is waiting */ +static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting); + +static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) +{ + struct kvm_lock_waiting *w; + int cpu; + u64 start; + unsigned long flags; + + if (in_nmi()) + return; + + w = &__get_cpu_var(klock_waiting); + cpu = smp_processor_id(); + start = spin_time_start(); + + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); + + /* + * The ordering protocol on this is that the "lock" pointer + * may only be set non-NULL if the "want" ticket is correct. + * If we're updating "want", we must first clear "lock". + */ + w->lock = NULL; + smp_wmb(); + w->want = want; + smp_wmb(); + w->lock = lock; + + add_stats(TAKEN_SLOW, 1); + + /* + * This uses set_bit, which is atomic but we should not rely on its + * reordering gurantees. So barrier is needed after this call. + */ + cpumask_set_cpu(cpu, &waiting_cpus); + + barrier(); + + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ + __ticket_enter_slowpath(lock); + + /* + * check again make sure it didn't become free while + * we weren't looking. + */ + if (ACCESS_ONCE(lock->tickets.head) == want) { + add_stats(TAKEN_SLOW_PICKUP, 1); + goto out; + } + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; + local_irq_restore(flags); + spin_time_accum_blocked(start); +} +PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning); + +/* Kick vcpu waiting on @lock->head to reach value @ticket */ +static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) +{ + int cpu; + + add_stats(RELEASED_SLOW, 1); + for_each_cpu(cpu, &waiting_cpus) { + const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu); + if (ACCESS_ONCE(w->lock) == lock && + ACCESS_ONCE(w->want) == ticket) { + add_stats(RELEASED_SLOW_KICKED, 1); + kvm_kick_cpu(cpu); + break; + } + } +} + +/* + * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. + */ +void __init kvm_spinlock_init(void) +{ + if (!kvm_para_available()) + return; + /* Does host kernel support KVM_FEATURE_PV_UNHALT? */ + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return; + + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + + static_key_slow_inc(¶virt_ticketlocks_enabled); + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d2c3812..1570e07 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -48,10 +48,9 @@ static struct pvclock_wall_clock wall_clock; * have elapsed since the hypervisor wrote the data. So we try to account for * that with system time */ -static unsigned long kvm_get_wallclock(void) +static void kvm_get_wallclock(struct timespec *now) { struct pvclock_vcpu_time_info *vcpu_time; - struct timespec ts; int low, high; int cpu; @@ -64,14 +63,12 @@ static unsigned long kvm_get_wallclock(void) cpu = smp_processor_id(); vcpu_time = &hv_clock[cpu].pvti; - pvclock_read_wallclock(&wall_clock, vcpu_time, &ts); + pvclock_read_wallclock(&wall_clock, vcpu_time, now); preempt_enable(); - - return ts.tv_sec; } -static int kvm_set_wallclock(unsigned long now) +static int kvm_set_wallclock(const struct timespec *now) { return -1; } @@ -185,7 +182,7 @@ static void kvm_restore_sched_clock_state(void) } #ifdef CONFIG_X86_LOCAL_APIC -static void __cpuinit kvm_setup_secondary_clock(void) +static void kvm_setup_secondary_clock(void) { /* * Now that the first cpu already had this clocksource initialized, @@ -242,6 +239,7 @@ void __init kvmclock_init(void) if (!mem) return; hv_clock = __va(mem); + memset(hv_clock, 0, size); if (kvm_register_clock("boot clock")) { hv_clock = NULL; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index efdec7c..af99f71 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -31,48 +31,12 @@ #include <asm/microcode.h> #include <asm/processor.h> #include <asm/msr.h> +#include <asm/microcode_amd.h> MODULE_DESCRIPTION("AMD Microcode Update Driver"); MODULE_AUTHOR("Peter Oruba"); MODULE_LICENSE("GPL v2"); -#define UCODE_MAGIC 0x00414d44 -#define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 -#define UCODE_UCODE_TYPE 0x00000001 - -struct equiv_cpu_entry { - u32 installed_cpu; - u32 fixed_errata_mask; - u32 fixed_errata_compare; - u16 equiv_cpu; - u16 res; -} __attribute__((packed)); - -struct microcode_header_amd { - u32 data_code; - u32 patch_id; - u16 mc_patch_data_id; - u8 mc_patch_data_len; - u8 init_flag; - u32 mc_patch_data_checksum; - u32 nb_dev_id; - u32 sb_dev_id; - u16 processor_rev_id; - u8 nb_rev_id; - u8 sb_rev_id; - u8 bios_api_rev; - u8 reserved1[3]; - u32 match_reg[8]; -} __attribute__((packed)); - -struct microcode_amd { - struct microcode_header_amd hdr; - unsigned int mpb[0]; -}; - -#define SECTION_HDR_SIZE 8 -#define CONTAINER_HDR_SZ 12 - static struct equiv_cpu_entry *equiv_cpu_table; struct ucode_patch { @@ -84,21 +48,10 @@ struct ucode_patch { static LIST_HEAD(pcache); -static u16 find_equiv_id(unsigned int cpu) +static u16 __find_equiv_id(unsigned int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - int i = 0; - - if (!equiv_cpu_table) - return 0; - - while (equiv_cpu_table[i].installed_cpu != 0) { - if (uci->cpu_sig.sig == equiv_cpu_table[i].installed_cpu) - return equiv_cpu_table[i].equiv_cpu; - - i++; - } - return 0; + return find_equiv_id(equiv_cpu_table, uci->cpu_sig.sig); } static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu) @@ -163,7 +116,7 @@ static struct ucode_patch *find_patch(unsigned int cpu) { u16 equiv_id; - equiv_id = find_equiv_id(cpu); + equiv_id = __find_equiv_id(cpu); if (!equiv_id) return NULL; @@ -173,18 +126,28 @@ static struct ucode_patch *find_patch(unsigned int cpu) static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { struct cpuinfo_x86 *c = &cpu_data(cpu); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct ucode_patch *p; csig->sig = cpuid_eax(0x00000001); csig->rev = c->microcode; + + /* + * a patch could have been loaded early, set uci->mc so that + * mc_bp_resume() can call apply_microcode() + */ + p = find_patch(cpu); + if (p && (p->patch_id == csig->rev)) + uci->mc = p->data; + pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev); return 0; } -static unsigned int verify_patch_size(int cpu, u32 patch_size, +static unsigned int verify_patch_size(u8 family, u32 patch_size, unsigned int size) { - struct cpuinfo_x86 *c = &cpu_data(cpu); u32 max_size; #define F1XH_MPB_MAX_SIZE 2048 @@ -192,7 +155,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, #define F15H_MPB_MAX_SIZE 4096 #define F16H_MPB_MAX_SIZE 3458 - switch (c->x86) { + switch (family) { case 0x14: max_size = F14H_MPB_MAX_SIZE; break; @@ -215,7 +178,21 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, return patch_size; } -static int apply_microcode_amd(int cpu) +int __apply_microcode_amd(struct microcode_amd *mc_amd) +{ + u32 rev, dummy; + + wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); + + /* verify patch application was successful */ + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (rev != mc_amd->hdr.patch_id) + return -1; + + return 0; +} + +int apply_microcode_amd(int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_amd *mc_amd; @@ -239,22 +216,20 @@ static int apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { c->microcode = rev; + uci->cpu_sig.rev = rev; return 0; } - wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code); - - /* verify patch application was successful */ - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); - if (rev != mc_amd->hdr.patch_id) { + if (__apply_microcode_amd(mc_amd)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", - cpu, mc_amd->hdr.patch_id); + cpu, mc_amd->hdr.patch_id); return -1; } + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, + mc_amd->hdr.patch_id); - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - uci->cpu_sig.rev = rev; - c->microcode = rev; + uci->cpu_sig.rev = mc_amd->hdr.patch_id; + c->microcode = mc_amd->hdr.patch_id; return 0; } @@ -302,9 +277,8 @@ static void cleanup(void) * driver cannot continue functioning normally. In such cases, we tear * down everything we've used up so far and exit. */ -static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) +static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover) { - struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_header_amd *mc_hdr; struct ucode_patch *patch; unsigned int patch_size, crnt_size, ret; @@ -324,7 +298,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) /* check if patch is for the current family */ proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff); - if (proc_fam != c->x86) + if (proc_fam != family) return crnt_size; if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { @@ -333,7 +307,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) return crnt_size; } - ret = verify_patch_size(cpu, patch_size, leftover); + ret = verify_patch_size(family, patch_size, leftover); if (!ret) { pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id); return crnt_size; @@ -364,7 +338,8 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) return crnt_size; } -static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) +static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, + size_t size) { enum ucode_state ret = UCODE_ERROR; unsigned int leftover; @@ -387,7 +362,7 @@ static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) } while (leftover) { - crnt_size = verify_and_add_patch(cpu, fw, leftover); + crnt_size = verify_and_add_patch(family, fw, leftover); if (crnt_size < 0) return ret; @@ -398,6 +373,32 @@ static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) return UCODE_OK; } +enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) +{ + enum ucode_state ret; + + /* free old equiv table */ + free_equiv_cpu_table(); + + ret = __load_microcode_amd(family, data, size); + + if (ret != UCODE_OK) + cleanup(); + +#if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) + /* save BSP's matching patch for early load */ + if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) { + struct ucode_patch *p = find_patch(smp_processor_id()); + if (p) { + memset(amd_bsp_mpb, 0, MPB_MAX_SIZE); + memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data), + MPB_MAX_SIZE)); + } + } +#endif + return ret; +} + /* * AMD microcode firmware naming convention, up to family 15h they are in * the legacy file: @@ -440,12 +441,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - /* free old equiv table */ - free_equiv_cpu_table(); - - ret = load_microcode_amd(cpu, fw->data, fw->size); - if (ret != UCODE_OK) - cleanup(); + ret = load_microcode_amd(c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c new file mode 100644 index 0000000..6073104 --- /dev/null +++ b/arch/x86/kernel/microcode_amd_early.c @@ -0,0 +1,301 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Jacob Shin <jacob.shin@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/earlycpio.h> +#include <linux/initrd.h> + +#include <asm/cpu.h> +#include <asm/setup.h> +#include <asm/microcode_amd.h> + +static bool ucode_loaded; +static u32 ucode_new_rev; +static unsigned long ucode_offset; +static size_t ucode_size; + +/* + * Microcode patch container file is prepended to the initrd in cpio format. + * See Documentation/x86/early-microcode.txt + */ +static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; + +static struct cpio_data __init find_ucode_in_initrd(void) +{ + long offset = 0; + char *path; + void *start; + size_t size; + unsigned long *uoffset; + size_t *usize; + struct cpio_data cd; + +#ifdef CONFIG_X86_32 + struct boot_params *p; + + /* + * On 32-bit, early load occurs before paging is turned on so we need + * to use physical addresses. + */ + p = (struct boot_params *)__pa_nodebug(&boot_params); + path = (char *)__pa_nodebug(ucode_path); + start = (void *)p->hdr.ramdisk_image; + size = p->hdr.ramdisk_size; + uoffset = (unsigned long *)__pa_nodebug(&ucode_offset); + usize = (size_t *)__pa_nodebug(&ucode_size); +#else + path = ucode_path; + start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); + size = boot_params.hdr.ramdisk_size; + uoffset = &ucode_offset; + usize = &ucode_size; +#endif + + cd = find_cpio_data(path, start, size, &offset); + if (!cd.data) + return cd; + + if (*(u32 *)cd.data != UCODE_MAGIC) { + cd.data = NULL; + cd.size = 0; + return cd; + } + + *uoffset = (u8 *)cd.data - (u8 *)start; + *usize = cd.size; + + return cd; +} + +/* + * Early load occurs before we can vmalloc(). So we look for the microcode + * patch container file in initrd, traverse equivalent cpu table, look for a + * matching microcode patch, and update, all in initrd memory in place. + * When vmalloc() is available for use later -- on 64-bit during first AP load, + * and on 32-bit during save_microcode_in_initrd_amd() -- we can call + * load_microcode_amd() to save equivalent cpu table and microcode patches in + * kernel heap memory. + */ +static void apply_ucode_in_initrd(void *ucode, size_t size) +{ + struct equiv_cpu_entry *eq; + u32 *header; + u8 *data; + u16 eq_id = 0; + int offset, left; + u32 rev, eax; + u32 *new_rev; + unsigned long *uoffset; + size_t *usize; + +#ifdef CONFIG_X86_32 + new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); + uoffset = (unsigned long *)__pa_nodebug(&ucode_offset); + usize = (size_t *)__pa_nodebug(&ucode_size); +#else + new_rev = &ucode_new_rev; + uoffset = &ucode_offset; + usize = &ucode_size; +#endif + + data = ucode; + left = size; + header = (u32 *)data; + + /* find equiv cpu table */ + + if (header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + header[2] == 0) /* size */ + return; + + eax = cpuid_eax(0x00000001); + + while (left > 0) { + eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + + offset = header[2] + CONTAINER_HDR_SZ; + data += offset; + left -= offset; + + eq_id = find_equiv_id(eq, eax); + if (eq_id) + break; + + /* + * support multiple container files appended together. if this + * one does not have a matching equivalent cpu entry, we fast + * forward to the next container file. + */ + while (left > 0) { + header = (u32 *)data; + if (header[0] == UCODE_MAGIC && + header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) + break; + + offset = header[1] + SECTION_HDR_SIZE; + data += offset; + left -= offset; + } + + /* mark where the next microcode container file starts */ + offset = data - (u8 *)ucode; + *uoffset += offset; + *usize -= offset; + ucode = data; + } + + if (!eq_id) { + *usize = 0; + return; + } + + /* find ucode and update if needed */ + + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); + + while (left > 0) { + struct microcode_amd *mc; + + header = (u32 *)data; + if (header[0] != UCODE_UCODE_TYPE || /* type */ + header[1] == 0) /* size */ + break; + + mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); + if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) + if (__apply_microcode_amd(mc) == 0) { + rev = mc->hdr.patch_id; + *new_rev = rev; + } + + offset = header[1] + SECTION_HDR_SIZE; + data += offset; + left -= offset; + } + + /* mark where this microcode container file ends */ + offset = *usize - (data - (u8 *)ucode); + *usize -= offset; + + if (!(*new_rev)) + *usize = 0; +} + +void __init load_ucode_amd_bsp(void) +{ + struct cpio_data cd = find_ucode_in_initrd(); + if (!cd.data) + return; + + apply_ucode_in_initrd(cd.data, cd.size); +} + +#ifdef CONFIG_X86_32 +u8 amd_bsp_mpb[MPB_MAX_SIZE]; + +/* + * On 32-bit, since AP's early load occurs before paging is turned on, we + * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during + * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During + * save_microcode_in_initrd_amd() BSP's patch is copied to amd_bsp_mpb, which + * is used upon resume from suspend. + */ +void load_ucode_amd_ap(void) +{ + struct microcode_amd *mc; + unsigned long *initrd; + unsigned long *uoffset; + size_t *usize; + void *ucode; + + mc = (struct microcode_amd *)__pa(amd_bsp_mpb); + if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { + __apply_microcode_amd(mc); + return; + } + + initrd = (unsigned long *)__pa(&initrd_start); + uoffset = (unsigned long *)__pa(&ucode_offset); + usize = (size_t *)__pa(&ucode_size); + + if (!*usize || !*initrd) + return; + + ucode = (void *)((unsigned long)__pa(*initrd) + *uoffset); + apply_ucode_in_initrd(ucode, *usize); +} + +static void __init collect_cpu_sig_on_bsp(void *arg) +{ + unsigned int cpu = smp_processor_id(); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + uci->cpu_sig.sig = cpuid_eax(0x00000001); +} +#else +void load_ucode_amd_ap(void) +{ + unsigned int cpu = smp_processor_id(); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + u32 rev, eax; + + rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); + eax = cpuid_eax(0x00000001); + + uci->cpu_sig.rev = rev; + uci->cpu_sig.sig = eax; + + if (cpu && !ucode_loaded) { + void *ucode; + + if (!ucode_size || !initrd_start) + return; + + ucode = (void *)(initrd_start + ucode_offset); + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK) + return; + + ucode_loaded = true; + } + + apply_microcode_amd(cpu); +} +#endif + +int __init save_microcode_in_initrd_amd(void) +{ + enum ucode_state ret; + void *ucode; + u32 eax; + +#ifdef CONFIG_X86_32 + unsigned int bsp = boot_cpu_data.cpu_index; + struct ucode_cpu_info *uci = ucode_cpu_info + bsp; + + if (!uci->cpu_sig.sig) + smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); +#endif + if (ucode_new_rev) + pr_info("microcode: updated early to new patch_level=0x%08x\n", + ucode_new_rev); + + if (ucode_loaded || !ucode_size || !initrd_start) + return 0; + + ucode = (void *)(initrd_start + ucode_offset); + eax = cpuid_eax(0x00000001); + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + + ret = load_microcode_amd(eax, ucode, ucode_size); + if (ret != UCODE_OK) + return -EINVAL; + + ucode_loaded = true; + return 0; +} diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 22db92b..15c9876 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -468,7 +468,7 @@ static struct syscore_ops mc_syscore_ops = { .resume = mc_bp_resume, }; -static __cpuinit int +static int mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 833d51d..be7f851 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -18,6 +18,7 @@ */ #include <linux/module.h> #include <asm/microcode_intel.h> +#include <asm/microcode_amd.h> #include <asm/processor.h> #define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) @@ -40,7 +41,7 @@ * * x86_vendor() gets vendor information directly through cpuid. */ -static int __cpuinit x86_vendor(void) +static int x86_vendor(void) { u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; @@ -56,7 +57,7 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } -static int __cpuinit x86_family(void) +static int x86_family(void) { u32 eax = 0x00000001; u32 ebx, ecx = 0, edx; @@ -81,11 +82,21 @@ void __init load_ucode_bsp(void) vendor = x86_vendor(); x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL && x86 >= 6) - load_ucode_intel_bsp(); + switch (vendor) { + case X86_VENDOR_INTEL: + if (x86 >= 6) + load_ucode_intel_bsp(); + break; + case X86_VENDOR_AMD: + if (x86 >= 0x10) + load_ucode_amd_bsp(); + break; + default: + break; + } } -void __cpuinit load_ucode_ap(void) +void load_ucode_ap(void) { int vendor, x86; @@ -95,6 +106,36 @@ void __cpuinit load_ucode_ap(void) vendor = x86_vendor(); x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL && x86 >= 6) - load_ucode_intel_ap(); + switch (vendor) { + case X86_VENDOR_INTEL: + if (x86 >= 6) + load_ucode_intel_ap(); + break; + case X86_VENDOR_AMD: + if (x86 >= 0x10) + load_ucode_amd_ap(); + break; + default: + break; + } +} + +int __init save_microcode_in_initrd(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + if (c->x86 >= 6) + save_microcode_in_initrd_intel(); + break; + case X86_VENDOR_AMD: + if (c->x86 >= 0x10) + save_microcode_in_initrd_amd(); + break; + default: + break; + } + + return 0; } diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index 2e9e128..1575deb 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -34,7 +34,7 @@ struct mc_saved_data { struct microcode_intel **mc_saved; } mc_saved_data; -static enum ucode_state __cpuinit +static enum ucode_state generic_load_microcode_early(struct microcode_intel **mc_saved_p, unsigned int mc_saved_count, struct ucode_cpu_info *uci) @@ -69,7 +69,7 @@ out: return state; } -static void __cpuinit +static void microcode_pointer(struct microcode_intel **mc_saved, unsigned long *mc_saved_in_initrd, unsigned long initrd_start, int mc_saved_count) @@ -82,7 +82,7 @@ microcode_pointer(struct microcode_intel **mc_saved, } #ifdef CONFIG_X86_32 -static void __cpuinit +static void microcode_phys(struct microcode_intel **mc_saved_tmp, struct mc_saved_data *mc_saved_data) { @@ -101,7 +101,7 @@ microcode_phys(struct microcode_intel **mc_saved_tmp, } #endif -static enum ucode_state __cpuinit +static enum ucode_state load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *mc_saved_in_initrd, unsigned long initrd_start, @@ -375,7 +375,7 @@ do { \ #define native_wrmsr(msr, low, high) \ native_write_msr(msr, low, high); -static int __cpuinit collect_cpu_info_early(struct ucode_cpu_info *uci) +static int collect_cpu_info_early(struct ucode_cpu_info *uci) { unsigned int val[2]; u8 x86, x86_model; @@ -529,7 +529,7 @@ int save_mc_for_early(u8 *mc) */ ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); if (ret) { - pr_err("Can not save microcode patch.\n"); + pr_err("Cannot save microcode patch.\n"); goto out; } @@ -584,7 +584,7 @@ scan_microcode(unsigned long start, unsigned long end, /* * Print ucode update info. */ -static void __cpuinit +static void print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) { int cpu = smp_processor_id(); @@ -605,7 +605,7 @@ static int current_mc_date; /* * Print early updated ucode info after printk works. This is delayed info dump. */ -void __cpuinit show_ucode_info_early(void) +void show_ucode_info_early(void) { struct ucode_cpu_info uci; @@ -621,7 +621,7 @@ void __cpuinit show_ucode_info_early(void) * mc_saved_data.mc_saved and delay printing microcode info in * show_ucode_info_early() until printk() works. */ -static void __cpuinit print_ucode(struct ucode_cpu_info *uci) +static void print_ucode(struct ucode_cpu_info *uci) { struct microcode_intel *mc_intel; int *delay_ucode_info_p; @@ -643,12 +643,12 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci) * Flush global tlb. We only do this in x86_64 where paging has been enabled * already and PGE should be enabled as well. */ -static inline void __cpuinit flush_tlb_early(void) +static inline void flush_tlb_early(void) { __native_flush_tlb_global_irq_disabled(); } -static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci) +static inline void print_ucode(struct ucode_cpu_info *uci) { struct microcode_intel *mc_intel; @@ -660,8 +660,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci) } #endif -static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data, - struct ucode_cpu_info *uci) +static int apply_microcode_early(struct mc_saved_data *mc_saved_data, + struct ucode_cpu_info *uci) { struct microcode_intel *mc_intel; unsigned int val[2]; @@ -699,7 +699,7 @@ static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data, * This function converts microcode patch offsets previously stored in * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. */ -int __init save_microcode_in_initrd(void) +int __init save_microcode_in_initrd_intel(void) { unsigned int count = mc_saved_data.mc_saved_count; struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; @@ -711,7 +711,7 @@ int __init save_microcode_in_initrd(void) microcode_pointer(mc_saved, mc_saved_in_initrd, initrd_start, count); ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) - pr_err("Can not save microcod patches from initrd"); + pr_err("Cannot save microcode patches from initrd.\n"); show_saved_mc(); @@ -763,7 +763,7 @@ load_ucode_intel_bsp(void) #endif } -void __cpuinit load_ucode_intel_ap(void) +void load_ucode_intel_ap(void) { struct mc_saved_data *mc_saved_data_p; struct ucode_cpu_info uci; diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index ac861b8..f4c886d 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -24,14 +24,14 @@ struct pci_hostbridge_probe { u32 device; }; -static u64 __cpuinitdata fam10h_pci_mmconf_base; +static u64 fam10h_pci_mmconf_base; -static struct pci_hostbridge_probe pci_probes[] __cpuinitdata = { +static struct pci_hostbridge_probe pci_probes[] = { { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, }; -static int __cpuinit cmp_range(const void *x1, const void *x2) +static int cmp_range(const void *x1, const void *x2) { const struct range *r1 = x1; const struct range *r2 = x2; @@ -49,7 +49,7 @@ static int __cpuinit cmp_range(const void *x1, const void *x2) /* need to avoid (0xfd<<32), (0xfe<<32), and (0xff<<32), ht used space */ #define FAM10H_PCI_MMCONF_BASE (0xfcULL<<32) #define BASE_VALID(b) ((b) + MMCONF_SIZE <= (0xfdULL<<32) || (b) >= (1ULL<<40)) -static void __cpuinit get_fam10h_pci_mmconf_base(void) +static void get_fam10h_pci_mmconf_base(void) { int i; unsigned bus; @@ -166,7 +166,7 @@ out: fam10h_pci_mmconf_base = base; } -void __cpuinit fam10h_check_enable_mmcfg(void) +void fam10h_check_enable_mmcfg(void) { u64 val; u32 address; @@ -230,7 +230,7 @@ static const struct dmi_system_id __initconst mmconf_dmi_table[] = { {} }; -/* Called from a __cpuinit function, but only on the BSP. */ +/* Called from a non __init function, but only on the BSP. */ void __ref check_enable_amd_mmconf_dmi(void) { dmi_check_system(mmconf_dmi_table); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index ce13049..88458fa 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -200,7 +200,7 @@ static const struct file_operations msr_fops = { .compat_ioctl = msr_ioctl, }; -static int __cpuinit msr_device_create(int cpu) +static int msr_device_create(int cpu) { struct device *dev; @@ -214,8 +214,8 @@ static void msr_device_destroy(int cpu) device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu)); } -static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int msr_class_cpu_callback(struct notifier_block *nfb, + unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; int err = 0; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 6030805..ba77ebc 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -14,6 +14,7 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/nmi.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/hardirq.h> #include <linux/slab.h> @@ -29,6 +30,9 @@ #include <asm/nmi.h> #include <asm/x86_init.h> +#define CREATE_TRACE_POINTS +#include <trace/events/nmi.h> + struct nmi_desc { spinlock_t lock; struct list_head head; @@ -82,6 +86,15 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) +static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; +static int __init nmi_warning_debugfs(void) +{ + debugfs_create_u64("nmi_longest_ns", 0644, + arch_debugfs_dir, &nmi_longest_ns); + return 0; +} +fs_initcall(nmi_warning_debugfs); + static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); @@ -96,8 +109,28 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 * can be latched at any given time. Walk the whole list * to handle those situations. */ - list_for_each_entry_rcu(a, &desc->head, list) - handled += a->handler(type, regs); + list_for_each_entry_rcu(a, &desc->head, list) { + u64 before, delta, whole_msecs; + int remainder_ns, decimal_msecs, thishandled; + + before = local_clock(); + thishandled = a->handler(type, regs); + handled += thishandled; + delta = local_clock() - before; + trace_nmi_handler(a->handler, (int)delta, thishandled); + + if (delta < nmi_longest_ns) + continue; + + nmi_longest_ns = delta; + whole_msecs = delta; + remainder_ns = do_div(whole_msecs, (1000 * 1000)); + decimal_msecs = remainder_ns / 1000; + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: " + "%lld.%03d msecs\n", a->handler, whole_msecs, + decimal_msecs); + } rcu_read_unlock(); diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 676b8c7..bbb6c73 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -4,25 +4,17 @@ */ #include <linux/spinlock.h> #include <linux/module.h> +#include <linux/jump_label.h> #include <asm/paravirt.h> -static inline void -default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - arch_spin_lock(lock); -} - struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP - .spin_is_locked = __ticket_spin_is_locked, - .spin_is_contended = __ticket_spin_is_contended, - - .spin_lock = __ticket_spin_lock, - .spin_lock_flags = default_spin_lock_flags, - .spin_trylock = __ticket_spin_trylock, - .spin_unlock = __ticket_spin_unlock, + .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), + .unlock_kick = paravirt_nop, #endif }; EXPORT_SYMBOL(pv_lock_ops); +struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index cd6de64..1b10af8 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -62,11 +62,6 @@ void __init default_banner(void) pv_info.name); } -/* Simple instruction patching code. */ -#define DEF_NATIVE(ops, name, code) \ - extern const char start_##ops##_##name[], end_##ops##_##name[]; \ - asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") - /* Undefined instruction for dealing with missing ops pointers. */ static const unsigned char ud2a[] = { 0x0f, 0x0b }; @@ -324,7 +319,7 @@ struct pv_time_ops pv_time_ops = { .steal_clock = native_steal_clock, }; -struct pv_irq_ops pv_irq_ops = { +__visible struct pv_irq_ops pv_irq_ops = { .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), @@ -336,7 +331,7 @@ struct pv_irq_ops pv_irq_ops = { #endif }; -struct pv_cpu_ops pv_cpu_ops = { +__visible struct pv_cpu_ops pv_cpu_ops = { .cpuid = native_cpuid, .get_debugreg = native_get_debugreg, .set_debugreg = native_set_debugreg, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 4e7a37f..c83516b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -36,7 +36,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; #ifdef CONFIG_X86_64 static DEFINE_PER_CPU(unsigned char, is_idle); @@ -277,18 +277,6 @@ void exit_idle(void) } #endif -void arch_cpu_idle_prepare(void) -{ - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); -} - void arch_cpu_idle_enter(void) { local_touch_nmi(); @@ -410,7 +398,7 @@ static void amd_e400_idle(void) default_idle(); } -void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) +void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7305f7d..884f98f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -110,11 +110,16 @@ void __show_regs(struct pt_regs *regs, int all) get_debugreg(d1, 1); get_debugreg(d2, 2); get_debugreg(d3, 3); - printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", - d0, d1, d2, d3); - get_debugreg(d6, 6); get_debugreg(d7, 7); + + /* Only print out debug registers if they are in their non-default state. */ + if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && + (d6 == DR6_RESERVED) && (d7 == 0x400)) + return; + + printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", + d0, d1, d2, d3); printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n", d6, d7); } @@ -147,7 +152,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -242,7 +247,7 @@ EXPORT_SYMBOL_GPL(start_thread); * the task-switch, and shows up in ret_from_fork in entry.S, * for example. */ -__notrace_funcgraph struct task_struct * +__visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 355ae06..bb1dc51 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ asmlinkage extern void ret_from_fork(void); -DEFINE_PER_CPU(unsigned long, old_rsp); +asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp); /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) @@ -105,11 +105,18 @@ void __show_regs(struct pt_regs *regs, int all) get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); - printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); get_debugreg(d3, 3); get_debugreg(d6, 6); get_debugreg(d7, 7); + + /* Only print out debug registers if they are in their non-default state. */ + if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && + (d6 == DR6_RESERVED) && (d7 == 0x400)) + return; + + printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + } void release_thread(struct task_struct *dead_task) @@ -176,7 +183,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; return 0; } *childregs = *current_pt_regs(); @@ -267,7 +274,7 @@ void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) * Kprobes not supported here. Set the probe on schedule instead. * Function graph tracer not supported too. */ -__notrace_funcgraph struct task_struct * +__visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 29a8120..7461f50 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -601,30 +601,48 @@ static unsigned long ptrace_get_dr7(struct perf_event *bp[]) return dr7; } -static int -ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, - struct task_struct *tsk, int disabled) +static int ptrace_fill_bp_fields(struct perf_event_attr *attr, + int len, int type, bool disabled) +{ + int err, bp_len, bp_type; + + err = arch_bp_generic_fields(len, type, &bp_len, &bp_type); + if (!err) { + attr->bp_len = bp_len; + attr->bp_type = bp_type; + attr->disabled = disabled; + } + + return err; +} + +static struct perf_event * +ptrace_register_breakpoint(struct task_struct *tsk, int len, int type, + unsigned long addr, bool disabled) { - int err; - int gen_len, gen_type; struct perf_event_attr attr; + int err; - /* - * We should have at least an inactive breakpoint at this - * slot. It means the user is writing dr7 without having - * written the address register first - */ - if (!bp) - return -EINVAL; + ptrace_breakpoint_init(&attr); + attr.bp_addr = addr; - err = arch_bp_generic_fields(len, type, &gen_len, &gen_type); + err = ptrace_fill_bp_fields(&attr, len, type, disabled); if (err) - return err; + return ERR_PTR(err); + + return register_user_hw_breakpoint(&attr, ptrace_triggered, + NULL, tsk); +} - attr = bp->attr; - attr.bp_len = gen_len; - attr.bp_type = gen_type; - attr.disabled = disabled; +static int ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, + int disabled) +{ + struct perf_event_attr attr = bp->attr; + int err; + + err = ptrace_fill_bp_fields(&attr, len, type, disabled); + if (err) + return err; return modify_user_hw_breakpoint(bp, &attr); } @@ -634,67 +652,50 @@ ptrace_modify_breakpoint(struct perf_event *bp, int len, int type, */ static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data) { - struct thread_struct *thread = &(tsk->thread); + struct thread_struct *thread = &tsk->thread; unsigned long old_dr7; - int i, orig_ret = 0, rc = 0; - int enabled, second_pass = 0; - unsigned len, type; - struct perf_event *bp; - - if (ptrace_get_breakpoints(tsk) < 0) - return -ESRCH; + bool second_pass = false; + int i, rc, ret = 0; data &= ~DR_CONTROL_RESERVED; old_dr7 = ptrace_get_dr7(thread->ptrace_bps); + restore: - /* - * Loop through all the hardware breakpoints, making the - * appropriate changes to each. - */ + rc = 0; for (i = 0; i < HBP_NUM; i++) { - enabled = decode_dr7(data, i, &len, &type); - bp = thread->ptrace_bps[i]; - - if (!enabled) { - if (bp) { - /* - * Don't unregister the breakpoints right-away, - * unless all register_user_hw_breakpoint() - * requests have succeeded. This prevents - * any window of opportunity for debug - * register grabbing by other users. - */ - if (!second_pass) - continue; - - rc = ptrace_modify_breakpoint(bp, len, type, - tsk, 1); - if (rc) - break; + unsigned len, type; + bool disabled = !decode_dr7(data, i, &len, &type); + struct perf_event *bp = thread->ptrace_bps[i]; + + if (!bp) { + if (disabled) + continue; + + bp = ptrace_register_breakpoint(tsk, + len, type, 0, disabled); + if (IS_ERR(bp)) { + rc = PTR_ERR(bp); + break; } + + thread->ptrace_bps[i] = bp; continue; } - rc = ptrace_modify_breakpoint(bp, len, type, tsk, 0); + rc = ptrace_modify_breakpoint(bp, len, type, disabled); if (rc) break; } - /* - * Make a second pass to free the remaining unused breakpoints - * or to restore the original breakpoints if an error occurred. - */ - if (!second_pass) { - second_pass = 1; - if (rc < 0) { - orig_ret = rc; - data = old_dr7; - } + + /* Restore if the first pass failed, second_pass shouldn't fail. */ + if (rc && !WARN_ON(second_pass)) { + ret = rc; + data = old_dr7; + second_pass = true; goto restore; } - ptrace_put_breakpoints(tsk); - - return ((orig_ret < 0) ? orig_ret : rc); + return ret; } /* @@ -702,25 +703,17 @@ restore: */ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) { - struct thread_struct *thread = &(tsk->thread); + struct thread_struct *thread = &tsk->thread; unsigned long val = 0; if (n < HBP_NUM) { - struct perf_event *bp; + struct perf_event *bp = thread->ptrace_bps[n]; - if (ptrace_get_breakpoints(tsk) < 0) - return -ESRCH; - - bp = thread->ptrace_bps[n]; - if (!bp) - val = 0; - else + if (bp) val = bp->hw.info.address; - - ptrace_put_breakpoints(tsk); } else if (n == 6) { val = thread->debugreg6; - } else if (n == 7) { + } else if (n == 7) { val = thread->ptrace_dr7; } return val; @@ -729,29 +722,14 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, unsigned long addr) { - struct perf_event *bp; struct thread_struct *t = &tsk->thread; - struct perf_event_attr attr; + struct perf_event *bp = t->ptrace_bps[nr]; int err = 0; - if (ptrace_get_breakpoints(tsk) < 0) - return -ESRCH; - - if (!t->ptrace_bps[nr]) { - ptrace_breakpoint_init(&attr); - /* - * Put stub len and type to register (reserve) an inactive but - * correct bp - */ - attr.bp_addr = addr; - attr.bp_len = HW_BREAKPOINT_LEN_1; - attr.bp_type = HW_BREAKPOINT_W; - attr.disabled = 1; - - bp = register_user_hw_breakpoint(&attr, ptrace_triggered, - NULL, tsk); - + if (!bp) { /* + * Put stub len and type to create an inactive but correct bp. + * * CHECKME: the previous code returned -EIO if the addr wasn't * a valid task virtual addr. The new one will return -EINVAL in * this case. @@ -760,22 +738,20 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, * writing for the user. And anyway this is the previous * behaviour. */ - if (IS_ERR(bp)) { + bp = ptrace_register_breakpoint(tsk, + X86_BREAKPOINT_LEN_1, X86_BREAKPOINT_WRITE, + addr, true); + if (IS_ERR(bp)) err = PTR_ERR(bp); - goto put; - } - - t->ptrace_bps[nr] = bp; + else + t->ptrace_bps[nr] = bp; } else { - bp = t->ptrace_bps[nr]; + struct perf_event_attr attr = bp->attr; - attr = bp->attr; attr.bp_addr = addr; err = modify_user_hw_breakpoint(bp, &attr); } -put: - ptrace_put_breakpoints(tsk); return err; } @@ -785,30 +761,20 @@ put: static int ptrace_set_debugreg(struct task_struct *tsk, int n, unsigned long val) { - struct thread_struct *thread = &(tsk->thread); - int rc = 0; - + struct thread_struct *thread = &tsk->thread; /* There are no DR4 or DR5 registers */ - if (n == 4 || n == 5) - return -EIO; + int rc = -EIO; - if (n == 6) { - thread->debugreg6 = val; - goto ret_path; - } if (n < HBP_NUM) { rc = ptrace_set_breakpoint_addr(tsk, n, val); - if (rc) - return rc; - } - /* All that's left is DR7 */ - if (n == 7) { + } else if (n == 6) { + thread->debugreg6 = val; + rc = 0; + } else if (n == 7) { rc = ptrace_write_dr7(tsk, val); if (!rc) thread->ptrace_dr7 = val; } - -ret_path: return rc; } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2cb9470..a16bae3 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -128,46 +128,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -181,17 +142,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 76fa1e9..e643e74 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -36,22 +36,6 @@ void (*pm_power_off)(void); EXPORT_SYMBOL(pm_power_off); static const struct desc_ptr no_idt = {}; -static int reboot_mode; -enum reboot_type reboot_type = BOOT_ACPI; -int reboot_force; - -/* - * This variable is used privately to keep track of whether or not - * reboot_type is still set to its default value (i.e., reboot= hasn't - * been set on the command line). This is needed so that we can - * suppress DMI scanning for reboot quirks. Without it, it's - * impossible to override a faulty reboot quirk without recompiling. - */ -static int reboot_default = 1; - -#ifdef CONFIG_SMP -static int reboot_cpu = -1; -#endif /* * This is set if we need to go through the 'emergency' path. @@ -64,79 +48,6 @@ static int reboot_emergency; bool port_cf9_safe = false; /* - * reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci] - * warm Don't set the cold reboot flag - * cold Set the cold reboot flag - * bios Reboot by jumping through the BIOS - * smp Reboot by executing reset on BSP or other CPU - * triple Force a triple fault (init) - * kbd Use the keyboard controller. cold reset (default) - * acpi Use the RESET_REG in the FADT - * efi Use efi reset_system runtime service - * pci Use the so-called "PCI reset register", CF9 - * force Avoid anything that could hang. - */ -static int __init reboot_setup(char *str) -{ - for (;;) { - /* - * Having anything passed on the command line via - * reboot= will cause us to disable DMI checking - * below. - */ - reboot_default = 0; - - switch (*str) { - case 'w': - reboot_mode = 0x1234; - break; - - case 'c': - reboot_mode = 0; - break; - -#ifdef CONFIG_SMP - case 's': - if (isdigit(*(str+1))) { - reboot_cpu = (int) (*(str+1) - '0'); - if (isdigit(*(str+2))) - reboot_cpu = reboot_cpu*10 + (int)(*(str+2) - '0'); - } - /* - * We will leave sorting out the final value - * when we are ready to reboot, since we might not - * have detected BSP APIC ID or smp_num_cpu - */ - break; -#endif /* CONFIG_SMP */ - - case 'b': - case 'a': - case 'k': - case 't': - case 'e': - case 'p': - reboot_type = *str; - break; - - case 'f': - reboot_force = 1; - break; - } - - str = strchr(str, ','); - if (str) - str++; - else - break; - } - return 1; -} - -__setup("reboot=", reboot_setup); - - -/* * Reboot options and system auto-detection code provided by * Dell Inc. so their systems "just work". :-) */ @@ -441,12 +352,28 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, { /* Handle problems with rebooting on the Precision M6600. */ .callback = set_pci_reboot, - .ident = "Dell OptiPlex 990", + .ident = "Dell Precision M6600", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), }, }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Some C6100 machines were shipped with vendor being 'Dell'. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, { } }; @@ -536,6 +463,7 @@ static void native_machine_emergency_restart(void) int i; int attempt = 0; int orig_reboot_type = reboot_type; + unsigned short mode; if (reboot_emergency) emergency_vmx_disable_all(); @@ -543,7 +471,8 @@ static void native_machine_emergency_restart(void) tboot_shutdown(TB_SHUTDOWN_REBOOT); /* Tell the BIOS if we want cold or warm reboot */ - *((unsigned short *)__va(0x472)) = reboot_mode; + mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0; + *((unsigned short *)__va(0x472)) = mode; for (;;) { /* Could also try the reset bit in the Hammer NB */ @@ -585,7 +514,7 @@ static void native_machine_emergency_restart(void) case BOOT_EFI: if (efi_enabled(EFI_RUNTIME_SERVICES)) - efi.reset_system(reboot_mode ? + efi.reset_system(reboot_mode == REBOOT_WARM ? EFI_RESET_WARM : EFI_RESET_COLD, EFI_SUCCESS, 0, NULL); @@ -614,26 +543,10 @@ void native_machine_shutdown(void) { /* Stop the cpus and apics */ #ifdef CONFIG_SMP - - /* The boot cpu is always logical cpu 0 */ - int reboot_cpu_id = 0; - - /* See if there has been given a command line override */ - if ((reboot_cpu != -1) && (reboot_cpu < nr_cpu_ids) && - cpu_online(reboot_cpu)) - reboot_cpu_id = reboot_cpu; - - /* Make certain the cpu I'm about to reboot on is online */ - if (!cpu_online(reboot_cpu_id)) - reboot_cpu_id = smp_processor_id(); - - /* Make certain I only run on the appropriate processor */ - set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id)); - /* - * O.K Now that I'm on the appropriate processor, stop all of the - * others. Also disable the local irq to not receive the per-cpu - * timer interrupt which may trigger scheduler's load balance. + * Stop all of the others. Also disable the local irq to + * not receive the per-cpu timer interrupt which may trigger + * scheduler's load balance. */ local_irq_disable(); stop_other_cpus(); diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 36818f8..e13f8e7 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -186,7 +186,7 @@ identity_mapped: movl CP_PA_PGD(%ebx), %eax movl %eax, %cr3 movl %cr0, %eax - orl $(1<<31), %eax + orl $X86_CR0_PG, %eax movl %eax, %cr0 lea PAGE_SIZE(%edi), %esp movl %edi, %eax diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 7a6f3b3..3fd2c69 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -151,21 +151,21 @@ identity_mapped: testq %r11, %r11 jnz 1f - xorq %rax, %rax - xorq %rbx, %rbx - xorq %rcx, %rcx - xorq %rdx, %rdx - xorq %rsi, %rsi - xorq %rdi, %rdi - xorq %rbp, %rbp - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r9 - xorq %r11, %r11 - xorq %r12, %r12 - xorq %r13, %r13 - xorq %r14, %r14 - xorq %r15, %r15 + xorl %eax, %eax + xorl %ebx, %ebx + xorl %ecx, %ecx + xorl %edx, %edx + xorl %esi, %esi + xorl %edi, %edi + xorl %ebp, %ebp + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d + xorl %r11d, %r11d + xorl %r12d, %r12d + xorl %r13d, %r13d + xorl %r14d, %r14d + xorl %r15d, %r15d ret @@ -212,8 +212,8 @@ virtual_mapped: /* Do the copies */ swap_pages: movq %rdi, %rcx /* Put the page_list in %rcx */ - xorq %rdi, %rdi - xorq %rsi, %rsi + xorl %edi, %edi + xorl %esi, %esi jmp 1f 0: /* top, read another word for the indirection page */ diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 198eb20..0aa2939 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -38,8 +38,9 @@ EXPORT_SYMBOL(rtc_lock); * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. */ -int mach_set_rtc_mmss(unsigned long nowtime) +int mach_set_rtc_mmss(const struct timespec *now) { + unsigned long nowtime = now->tv_sec; struct rtc_time tm; int retval = 0; @@ -58,7 +59,7 @@ int mach_set_rtc_mmss(unsigned long nowtime) return retval; } -unsigned long mach_get_cmos_time(void) +void mach_get_cmos_time(struct timespec *now) { unsigned int status, year, mon, day, hour, min, sec, century = 0; unsigned long flags; @@ -107,7 +108,8 @@ unsigned long mach_get_cmos_time(void) } else year += CMOS_YEARS_OFFS; - return mktime(year, mon, day, hour, min, sec); + now->tv_sec = mktime(year, mon, day, hour, min, sec); + now->tv_nsec = 0; } /* Routines for accessing the CMOS RAM/RTC. */ @@ -135,18 +137,13 @@ EXPORT_SYMBOL(rtc_cmos_write); int update_persistent_clock(struct timespec now) { - return x86_platform.set_wallclock(now.tv_sec); + return x86_platform.set_wallclock(&now); } /* not static: needed by APM */ void read_persistent_clock(struct timespec *ts) { - unsigned long retval; - - retval = x86_platform.get_wallclock(); - - ts->tv_sec = retval; - ts->tv_nsec = 0; + x86_platform.get_wallclock(ts); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 56f7fcf..f0de629 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -170,7 +170,7 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 /* cpu data as detected by the assembly code in head.S */ -struct cpuinfo_x86 new_cpu_data __cpuinitdata = { +struct cpuinfo_x86 new_cpu_data = { .wp_works_ok = -1, }; /* common cpu data for all cpus */ @@ -206,9 +206,9 @@ EXPORT_SYMBOL(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) -unsigned long mmu_cr4_features; +__visible unsigned long mmu_cr4_features; #else -unsigned long mmu_cr4_features = X86_CR4_PAE; +__visible unsigned long mmu_cr4_features = X86_CR4_PAE; #endif /* Boot loader ID and version as integers, for the benefit of proc_dointvec */ @@ -426,25 +426,23 @@ static void __init reserve_initrd(void) static void __init parse_setup_data(void) { struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; pa_data = boot_params.hdr.setup_data; while (pa_data) { - u32 data_len, map_len; + u32 data_len, map_len, data_type; map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), (u64)sizeof(struct setup_data)); data = early_memremap(pa_data, map_len); data_len = data->len + sizeof(struct setup_data); - if (data_len > map_len) { - early_iounmap(data, map_len); - data = early_memremap(pa_data, data_len); - map_len = data_len; - } + data_type = data->type; + pa_next = data->next; + early_iounmap(data, map_len); - switch (data->type) { + switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(data); + parse_e820_ext(pa_data, data_len); break; case SETUP_DTB: add_dtb(pa_data); @@ -452,8 +450,7 @@ static void __init parse_setup_data(void) default: break; } - pa_data = data->next; - early_iounmap(data, map_len); + pa_data = pa_next; } } @@ -1040,8 +1037,6 @@ void __init setup_arch(char **cmdline_p) /* max_low_pfn get updated here */ find_low_pfn_range(); #else - num_physpages = max_pfn; - check_x2apic(); /* How many end-of-memory variables you have, grandma! */ @@ -1072,7 +1067,7 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); - memblock.current_limit = ISA_END_ADDRESS; + memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); /* @@ -1105,7 +1100,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); - memblock.current_limit = get_max_mapped(); + memblock_set_current_limit(get_max_mapped()); dma_contiguous_reserve(0); /* diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 6956299..9e5de68 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -43,12 +43,6 @@ #include <asm/sigframe.h> -#ifdef CONFIG_X86_32 -# define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) -#else -# define FIX_EFLAGS __FIX_EFLAGS -#endif - #define COPY(x) do { \ get_user_ex(regs->x, &sc->x); \ } while (0) @@ -364,7 +358,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -429,7 +423,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -496,7 +490,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ksig->ka.sa.sa_flags & SA_RESTORER) { @@ -539,7 +533,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, * Do a signal return; undo the signal stack. */ #ifdef CONFIG_X86_32 -unsigned long sys_sigreturn(void) +asmlinkage unsigned long sys_sigreturn(void) { struct pt_regs *regs = current_pt_regs(); struct sigframe __user *frame; @@ -568,7 +562,7 @@ badframe: } #endif /* CONFIG_X86_32 */ -long sys_rt_sigreturn(void) +asmlinkage long sys_rt_sigreturn(void) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; @@ -668,15 +662,17 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) if (!failed) { /* * Clear the direction flag as per the ABI for function entry. - */ - regs->flags &= ~X86_EFLAGS_DF; - /* + * + * Clear RF when entering the signal handler, because + * it might disable possible debug exception from the + * signal handler. + * * Clear TF when entering the signal handler, but * notify any tracer that was single-stepping it. * The tracer may want to single-step inside the * handler too. */ - regs->flags &= ~X86_EFLAGS_TF; + regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } @@ -732,7 +728,7 @@ static void do_signal(struct pt_regs *regs) * notification of userspace execution resumption * - triggered by the TIF_WORK_MASK flags */ -void +__visible void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { user_exit(); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 48d2b7d..7c3a5a6 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -30,6 +30,7 @@ #include <asm/proto.h> #include <asm/apic.h> #include <asm/nmi.h> +#include <asm/trace/irq_vectors.h> /* * Some notes on x86 processor bugs affecting SMP operation: * @@ -249,32 +250,87 @@ finish: /* * Reschedule call back. */ -void smp_reschedule_interrupt(struct pt_regs *regs) +static inline void __smp_reschedule_interrupt(void) { - ack_APIC_irq(); inc_irq_stat(irq_resched_count); scheduler_ipi(); +} + +__visible void smp_reschedule_interrupt(struct pt_regs *regs) +{ + ack_APIC_irq(); + __smp_reschedule_interrupt(); /* * KVM uses this interrupt to force a cpu out of guest mode */ } -void smp_call_function_interrupt(struct pt_regs *regs) +static inline void smp_entering_irq(void) { ack_APIC_irq(); irq_enter(); +} + +__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) +{ + /* + * Need to call irq_enter() before calling the trace point. + * __smp_reschedule_interrupt() calls irq_enter/exit() too (in + * scheduler_ipi(). This is OK, since those functions are allowed + * to nest. + */ + smp_entering_irq(); + trace_reschedule_entry(RESCHEDULE_VECTOR); + __smp_reschedule_interrupt(); + trace_reschedule_exit(RESCHEDULE_VECTOR); + exiting_irq(); + /* + * KVM uses this interrupt to force a cpu out of guest mode + */ +} + +static inline void __smp_call_function_interrupt(void) +{ generic_smp_call_function_interrupt(); inc_irq_stat(irq_call_count); - irq_exit(); } -void smp_call_function_single_interrupt(struct pt_regs *regs) +__visible void smp_call_function_interrupt(struct pt_regs *regs) +{ + smp_entering_irq(); + __smp_call_function_interrupt(); + exiting_irq(); +} + +__visible void smp_trace_call_function_interrupt(struct pt_regs *regs) +{ + smp_entering_irq(); + trace_call_function_entry(CALL_FUNCTION_VECTOR); + __smp_call_function_interrupt(); + trace_call_function_exit(CALL_FUNCTION_VECTOR); + exiting_irq(); +} + +static inline void __smp_call_function_single_interrupt(void) { - ack_APIC_irq(); - irq_enter(); generic_smp_call_function_single_interrupt(); inc_irq_stat(irq_call_count); - irq_exit(); +} + +__visible void smp_call_function_single_interrupt(struct pt_regs *regs) +{ + smp_entering_irq(); + __smp_call_function_single_interrupt(); + exiting_irq(); +} + +__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs) +{ + smp_entering_irq(); + trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); + __smp_call_function_single_interrupt(); + trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); + exiting_irq(); } static int __init nonmi_ipi_setup(char *str) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9c73b51..6cacab6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -130,7 +130,7 @@ atomic_t init_deasserted; * Report back to the Boot Processor during boot time or to the caller processor * during CPU online. */ -static void __cpuinit smp_callin(void) +static void smp_callin(void) { int cpuid, phys_id; unsigned long timeout; @@ -237,7 +237,7 @@ static int enable_start_cpu0; /* * Activate a secondary processor. */ -notrace static void __cpuinit start_secondary(void *unused) +static void notrace start_secondary(void *unused) { /* * Don't put *anything* before cpu_init(), SMP booting is too @@ -300,7 +300,7 @@ void __init smp_store_boot_cpu_info(void) * The bootstrap kernel entry code has set these up. Save them for * a given CPU */ -void __cpuinit smp_store_cpu_info(int id) +void smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); @@ -313,7 +313,7 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } -static bool __cpuinit +static bool topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; @@ -330,7 +330,7 @@ do { \ cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ } while (0) -static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { if (cpu_has_topoext) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; @@ -348,7 +348,7 @@ static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } -static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; @@ -359,7 +359,7 @@ static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } -static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +static bool match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { if (c->phys_proc_id == o->phys_proc_id) { if (cpu_has(c, X86_FEATURE_AMD_DCM)) @@ -370,17 +370,17 @@ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } -void __cpuinit set_cpu_sibling_map(int cpu) +void set_cpu_sibling_map(int cpu) { - bool has_mc = boot_cpu_data.x86_max_cores > 1; bool has_smt = smp_num_siblings > 1; + bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i; cpumask_set_cpu(cpu, cpu_sibling_setup_mask); - if (!has_smt && !has_mc) { + if (!has_mp) { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(cpu)); @@ -394,7 +394,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) if ((i == cpu) || (has_smt && match_smt(c, o))) link_mask(sibling, cpu, i); - if ((i == cpu) || (has_mc && match_llc(c, o))) + if ((i == cpu) || (has_mp && match_llc(c, o))) link_mask(llc_shared, cpu, i); } @@ -406,7 +406,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); - if ((i == cpu) || (has_mc && match_mc(c, o))) { + if ((i == cpu) || (has_mp && match_mc(c, o))) { link_mask(core, cpu, i); /* @@ -499,7 +499,7 @@ void __inquire_remote_apic(int apicid) * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this * won't ... remember to clear down the APIC, etc later. */ -int __cpuinit +int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; @@ -533,7 +533,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) return (send_status | accept_status); } -static int __cpuinit +static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) { unsigned long send_status, accept_status = 0; @@ -649,10 +649,11 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) } /* reduce the number of lines printed when booting a large cpu count system */ -static void __cpuinit announce_cpu(int cpu, int apicid) +static void announce_cpu(int cpu, int apicid) { static int current_node = -1; int node = early_cpu_to_node(cpu); + int max_cpu_present = find_last_bit(cpumask_bits(cpu_present_mask), NR_CPUS); if (system_state == SYSTEM_BOOTING) { if (node != current_node) { @@ -661,7 +662,7 @@ static void __cpuinit announce_cpu(int cpu, int apicid) current_node = node; pr_info("Booting Node %3d, Processors ", node); } - pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : ""); + pr_cont(" #%4d%s", cpu, cpu == max_cpu_present ? " OK\n" : ""); return; } else pr_info("Booting Node %d Processor %d APIC 0x%x\n", @@ -691,7 +692,7 @@ static int wakeup_cpu0_nmi(unsigned int cmd, struct pt_regs *regs) * We'll change this code in the future to wake up hard offlined CPU0 if * real platform and request are available. */ -static int __cpuinit +static int wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, int *cpu0_nmi_registered) { @@ -731,7 +732,7 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid, * Returns zero if CPU booted OK, else error code from * ->wakeup_secondary_cpu. */ -static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) { volatile u32 *trampoline_status = (volatile u32 *) __va(real_mode_header->trampoline_status); @@ -872,7 +873,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle) return boot_error; } -int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) +int native_cpu_up(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); unsigned long flags; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index dbded5a..30277e2 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = TASK_UNMAPPED_BASE; + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c index 147fcd4..e9bcd57 100644 --- a/arch/x86/kernel/syscall_32.c +++ b/arch/x86/kernel/syscall_32.c @@ -15,7 +15,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { +__visible const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index 5c7f8c2..4ac730b 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -4,6 +4,7 @@ #include <linux/sys.h> #include <linux/cache.h> #include <asm/asm-offsets.h> +#include <asm/syscall.h> #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) @@ -19,11 +20,9 @@ #define __SYSCALL_64(nr, sym, compat) [nr] = sym, -typedef void (*sys_call_ptr_t)(void); - extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { +asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c new file mode 100644 index 0000000..193ec2c --- /dev/null +++ b/arch/x86/kernel/sysfb.c @@ -0,0 +1,74 @@ +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +/* + * Simple-Framebuffer support for x86 systems + * Create a platform-device for any available boot framebuffer. The + * simple-framebuffer platform device is already available on DT systems, so + * this module parses the global "screen_info" object and creates a suitable + * platform device compatible with the "simple-framebuffer" DT object. If + * the framebuffer is incompatible, we instead create a legacy + * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and + * pass the screen_info as platform_data. This allows legacy drivers + * to pick these devices up without messing with simple-framebuffer drivers. + * The global "screen_info" is still valid at all times. + * + * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer" + * platform devices, but only use legacy framebuffer devices for + * backwards compatibility. + * + * TODO: We set the dev_id field of all platform-devices to 0. This allows + * other x86 OF/DT parsers to create such devices, too. However, they must + * start at offset 1 for this to work. + */ + +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/platform_data/simplefb.h> +#include <linux/platform_device.h> +#include <linux/screen_info.h> +#include <asm/sysfb.h> + +static __init int sysfb_init(void) +{ + struct screen_info *si = &screen_info; + struct simplefb_platform_data mode; + struct platform_device *pd; + const char *name; + bool compatible; + int ret; + + sysfb_apply_efi_quirks(); + + /* try to create a simple-framebuffer device */ + compatible = parse_mode(si, &mode); + if (compatible) { + ret = create_simplefb(si, &mode); + if (!ret) + return 0; + } + + /* if the FB is incompatible, create a legacy framebuffer device */ + if (si->orig_video_isVGA == VIDEO_TYPE_EFI) + name = "efi-framebuffer"; + else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) + name = "vesa-framebuffer"; + else + name = "platform-framebuffer"; + + pd = platform_device_register_resndata(NULL, name, 0, + NULL, 0, si, sizeof(*si)); + return IS_ERR(pd) ? PTR_ERR(pd) : 0; +} + +/* must execute after PCI subsystem for EFI quirks */ +device_initcall(sysfb_init); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c new file mode 100644 index 0000000..b285d4e --- /dev/null +++ b/arch/x86/kernel/sysfb_efi.c @@ -0,0 +1,214 @@ +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> + * + * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +/* + * EFI Quirks + * Several EFI systems do not correctly advertise their boot framebuffers. + * Hence, we use this static table of known broken machines and fix up the + * information so framebuffer drivers can load corectly. + */ + +#include <linux/dmi.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/pci.h> +#include <linux/screen_info.h> +#include <video/vga.h> +#include <asm/sysfb.h> + +enum { + OVERRIDE_NONE = 0x0, + OVERRIDE_BASE = 0x1, + OVERRIDE_STRIDE = 0x2, + OVERRIDE_HEIGHT = 0x4, + OVERRIDE_WIDTH = 0x8, +}; + +struct efifb_dmi_info efifb_dmi_list[] = { + [M_I17] = { "i17", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, /* guess */ + [M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, + [M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, /* guess */ + [M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080, OVERRIDE_NONE }, + [M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440, OVERRIDE_NONE }, + [M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768, OVERRIDE_NONE }, + [M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768, OVERRIDE_NONE }, + [M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + /* 11" Macbook Air 3,1 passes the wrong stride */ + [M_MBA_3] = { "mba3", 0, 2048 * 4, 0, 0, OVERRIDE_STRIDE }, + [M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_2] = { "mbp2", 0, 0, 0, 0, OVERRIDE_NONE }, /* placeholder */ + [M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050, OVERRIDE_NONE }, + [M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MBP_8_2] = { "mbp82", 0x90010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE } +}; + +#define choose_value(dmivalue, fwvalue, field, flags) ({ \ + typeof(fwvalue) _ret_ = fwvalue; \ + if ((flags) & (field)) \ + _ret_ = dmivalue; \ + else if ((fwvalue) == 0) \ + _ret_ = dmivalue; \ + _ret_; \ + }) + +static int __init efifb_set_system(const struct dmi_system_id *id) +{ + struct efifb_dmi_info *info = id->driver_data; + + if (info->base == 0 && info->height == 0 && info->width == 0 && + info->stride == 0) + return 0; + + /* Trust the bootloader over the DMI tables */ + if (screen_info.lfb_base == 0) { +#if defined(CONFIG_PCI) + struct pci_dev *dev = NULL; + int found_bar = 0; +#endif + if (info->base) { + screen_info.lfb_base = choose_value(info->base, + screen_info.lfb_base, OVERRIDE_BASE, + info->flags); + +#if defined(CONFIG_PCI) + /* make sure that the address in the table is actually + * on a VGA device's PCI BAR */ + + for_each_pci_dev(dev) { + int i; + if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) + continue; + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + resource_size_t start, end; + + start = pci_resource_start(dev, i); + if (start == 0) + break; + end = pci_resource_end(dev, i); + if (screen_info.lfb_base >= start && + screen_info.lfb_base < end) { + found_bar = 1; + } + } + } + if (!found_bar) + screen_info.lfb_base = 0; +#endif + } + } + if (screen_info.lfb_base) { + screen_info.lfb_linelength = choose_value(info->stride, + screen_info.lfb_linelength, OVERRIDE_STRIDE, + info->flags); + screen_info.lfb_width = choose_value(info->width, + screen_info.lfb_width, OVERRIDE_WIDTH, + info->flags); + screen_info.lfb_height = choose_value(info->height, + screen_info.lfb_height, OVERRIDE_HEIGHT, + info->flags); + if (screen_info.orig_video_isVGA == 0) + screen_info.orig_video_isVGA = VIDEO_TYPE_EFI; + } else { + screen_info.lfb_linelength = 0; + screen_info.lfb_width = 0; + screen_info.lfb_height = 0; + screen_info.orig_video_isVGA = 0; + return 0; + } + + printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x " + "(%dx%d, stride %d)\n", id->ident, + screen_info.lfb_base, screen_info.lfb_width, + screen_info.lfb_height, screen_info.lfb_linelength); + + return 1; +} + +#define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid) \ + { \ + efifb_set_system, \ + name, \ + { \ + DMI_MATCH(DMI_BIOS_VENDOR, vendor), \ + DMI_MATCH(DMI_PRODUCT_NAME, name) \ + }, \ + &efifb_dmi_list[enumid] \ + } + +static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac4,1", M_I17), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac5,1", M_I20), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac5,1", M_I20), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook2,1", M_MB), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir3,1", M_MBA_3), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro8,2", M_MBP_8_2), + {}, +}; + +__init void sysfb_apply_efi_quirks(void) +{ + if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || + !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) + dmi_check_system(efifb_dmi_system_table); +} diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c new file mode 100644 index 0000000..86179d4 --- /dev/null +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -0,0 +1,95 @@ +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +/* + * simple-framebuffer probing + * Try to convert "screen_info" into a "simple-framebuffer" compatible mode. + * If the mode is incompatible, we return "false" and let the caller create + * legacy nodes instead. + */ + +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/platform_data/simplefb.h> +#include <linux/platform_device.h> +#include <linux/screen_info.h> +#include <asm/sysfb.h> + +static const char simplefb_resname[] = "BOOTFB"; +static const struct simplefb_format formats[] = SIMPLEFB_FORMATS; + +/* try parsing x86 screen_info into a simple-framebuffer mode struct */ +__init bool parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode) +{ + const struct simplefb_format *f; + __u8 type; + unsigned int i; + + type = si->orig_video_isVGA; + if (type != VIDEO_TYPE_VLFB && type != VIDEO_TYPE_EFI) + return false; + + for (i = 0; i < ARRAY_SIZE(formats); ++i) { + f = &formats[i]; + if (si->lfb_depth == f->bits_per_pixel && + si->red_size == f->red.length && + si->red_pos == f->red.offset && + si->green_size == f->green.length && + si->green_pos == f->green.offset && + si->blue_size == f->blue.length && + si->blue_pos == f->blue.offset && + si->rsvd_size == f->transp.length && + si->rsvd_pos == f->transp.offset) { + mode->format = f->name; + mode->width = si->lfb_width; + mode->height = si->lfb_height; + mode->stride = si->lfb_linelength; + return true; + } + } + + return false; +} + +__init int create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) +{ + struct platform_device *pd; + struct resource res; + unsigned long len; + + /* don't use lfb_size as it may contain the whole VMEM instead of only + * the part that is occupied by the framebuffer */ + len = mode->height * mode->stride; + len = PAGE_ALIGN(len); + if (len > (u64)si->lfb_size << 16) { + printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); + return -EINVAL; + } + + /* setup IORESOURCE_MEM as framebuffer memory */ + memset(&res, 0, sizeof(res)); + res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.name = simplefb_resname; + res.start = si->lfb_base; + res.end = si->lfb_base + len - 1; + if (res.end <= res.start) + return -EINVAL; + + pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0, + &res, 1, mode, sizeof(*mode)); + if (IS_ERR(pd)) + return PTR_ERR(pd); + + return 0; +} diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index f84fe00..91a4496 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -31,6 +31,7 @@ #include <linux/pfn.h> #include <linux/mm.h> #include <linux/tboot.h> +#include <linux/debugfs.h> #include <asm/realmode.h> #include <asm/processor.h> @@ -300,6 +301,15 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) return 0; } +static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b) +{ + if (!tboot_enabled()) + return 0; + + pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)"); + return -ENODEV; +} + static atomic_t ap_wfs_count; static int tboot_wait_for_aps(int num_aps) @@ -319,8 +329,8 @@ static int tboot_wait_for_aps(int num_aps) return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps); } -static int __cpuinit tboot_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int tboot_cpu_callback(struct notifier_block *nfb, unsigned long action, + void *hcpu) { switch (action) { case CPU_DYING: @@ -333,11 +343,78 @@ static int __cpuinit tboot_cpu_callback(struct notifier_block *nfb, return NOTIFY_OK; } -static struct notifier_block tboot_cpu_notifier __cpuinitdata = +static struct notifier_block tboot_cpu_notifier = { .notifier_call = tboot_cpu_callback, }; +#ifdef CONFIG_DEBUG_FS + +#define TBOOT_LOG_UUID { 0x26, 0x25, 0x19, 0xc0, 0x30, 0x6b, 0xb4, 0x4d, \ + 0x4c, 0x84, 0xa3, 0xe9, 0x53, 0xb8, 0x81, 0x74 } + +#define TBOOT_SERIAL_LOG_ADDR 0x60000 +#define TBOOT_SERIAL_LOG_SIZE 0x08000 +#define LOG_MAX_SIZE_OFF 16 +#define LOG_BUF_OFF 24 + +static uint8_t tboot_log_uuid[16] = TBOOT_LOG_UUID; + +static ssize_t tboot_log_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) +{ + void __iomem *log_base; + u8 log_uuid[16]; + u32 max_size; + void *kbuf; + int ret = -EFAULT; + + log_base = ioremap_nocache(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); + if (!log_base) + return ret; + + memcpy_fromio(log_uuid, log_base, sizeof(log_uuid)); + if (memcmp(&tboot_log_uuid, log_uuid, sizeof(log_uuid))) + goto err_iounmap; + + max_size = readl(log_base + LOG_MAX_SIZE_OFF); + if (*ppos >= max_size) { + ret = 0; + goto err_iounmap; + } + + if (*ppos + count > max_size) + count = max_size - *ppos; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + goto err_iounmap; + } + + memcpy_fromio(kbuf, log_base + LOG_BUF_OFF + *ppos, count); + if (copy_to_user(user_buf, kbuf, count)) + goto err_kfree; + + *ppos += count; + + ret = count; + +err_kfree: + kfree(kbuf); + +err_iounmap: + iounmap(log_base); + + return ret; +} + +static const struct file_operations tboot_log_fops = { + .read = tboot_log_read, + .llseek = default_llseek, +}; + +#endif /* CONFIG_DEBUG_FS */ + static __init int tboot_late_init(void) { if (!tboot_enabled()) @@ -348,7 +425,13 @@ static __init int tboot_late_init(void) atomic_set(&ap_wfs_count, 0); register_hotcpu_notifier(&tboot_cpu_notifier); +#ifdef CONFIG_DEBUG_FS + debugfs_create_file("tboot_log", S_IRUSR, + arch_debugfs_dir, NULL, &tboot_log_fops); +#endif + acpi_os_set_prepare_sleep(&tboot_sleep); + acpi_os_set_prepare_extended_sleep(&tboot_extended_sleep); return 0; } diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c new file mode 100644 index 0000000..1c113db --- /dev/null +++ b/arch/x86/kernel/tracepoint.c @@ -0,0 +1,59 @@ +/* + * Code for supporting irq vector tracepoints. + * + * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com> + * + */ +#include <asm/hw_irq.h> +#include <asm/desc.h> +#include <linux/atomic.h> + +atomic_t trace_idt_ctr = ATOMIC_INIT(0); +struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1, + (unsigned long) trace_idt_table }; + +/* No need to be aligned, but done to keep all IDTs defined the same way. */ +gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss; + +static int trace_irq_vector_refcount; +static DEFINE_MUTEX(irq_vector_mutex); + +static void set_trace_idt_ctr(int val) +{ + atomic_set(&trace_idt_ctr, val); + /* Ensure the trace_idt_ctr is set before sending IPI */ + wmb(); +} + +static void switch_idt(void *arg) +{ + unsigned long flags; + + local_irq_save(flags); + load_current_idt(); + local_irq_restore(flags); +} + +void trace_irq_vector_regfunc(void) +{ + mutex_lock(&irq_vector_mutex); + if (!trace_irq_vector_refcount) { + set_trace_idt_ctr(1); + smp_call_function(switch_idt, NULL, 0); + switch_idt(NULL); + } + trace_irq_vector_refcount++; + mutex_unlock(&irq_vector_mutex); +} + +void trace_irq_vector_unregfunc(void) +{ + mutex_lock(&irq_vector_mutex); + trace_irq_vector_refcount--; + if (!trace_irq_vector_refcount) { + set_trace_idt_ctr(0); + smp_call_function(switch_idt, NULL, 0); + switch_idt(NULL); + } + mutex_unlock(&irq_vector_mutex); +} diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 772e2a8..8c8093b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -58,24 +58,25 @@ #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> +#include <asm/alternative.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> #include <asm/pgalloc.h> #include <asm/proto.h> + +/* No need to be aligned, but done to keep all IDTs defined the same way. */ +gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> asmlinkage int system_call(void); - -/* - * The IDT has to be page-aligned to simplify the Pentium - * F0 0F bug workaround. - */ -gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, }; #endif +/* Must be page-aligned because the real IDT is used in a fixmap. */ +gate_desc idt_table[NR_VECTORS] __page_aligned_bss; + DECLARE_BITMAP(used_vectors, NR_VECTORS); EXPORT_SYMBOL_GPL(used_vectors); @@ -254,6 +255,9 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_DF; +#ifdef CONFIG_DOUBLEFAULT + df_debug(regs, error_code); +#endif /* * This is always a kernel trap and never fixable (and thus must * never return). @@ -324,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + if (poke_int3_handler(regs)) + return; + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, @@ -437,7 +444,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; - if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, + if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, SIGTRAP) == NOTIFY_STOP) goto exit; @@ -785,7 +792,7 @@ void __init trap_init(void) x86_init.irqs.trap_init(); #ifdef CONFIG_X86_64 - memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16); + memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); set_nmi_gate(X86_TRAP_DB, &debug); set_nmi_gate(X86_TRAP_BP, &int3); #endif diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 098b3cf..930e5d4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -89,6 +89,12 @@ int check_tsc_unstable(void) } EXPORT_SYMBOL_GPL(check_tsc_unstable); +int check_tsc_disabled(void) +{ + return tsc_disabled; +} +EXPORT_SYMBOL_GPL(check_tsc_disabled); + #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { @@ -824,7 +830,7 @@ static void __init check_system_tsc_reliable(void) * Make an educated guess if the TSC is trustworthy and synchronized * over all CPUs. */ -__cpuinit int unsynchronized_tsc(void) +int unsynchronized_tsc(void) { if (!cpu_has_tsc || tsc_unstable) return 1; @@ -1020,7 +1026,7 @@ void __init tsc_init(void) * been calibrated. This assumes that CONSTANT_TSC applies to all * cpus in the socket - this should be a safe assumption. */ -unsigned long __cpuinit calibrate_delay_is_known(void) +unsigned long calibrate_delay_is_known(void) { int i, cpu = smp_processor_id(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index fc25e60..adfdf56 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -25,24 +25,24 @@ * Entry/exit counters that make sure that both CPUs * run the measurement code at once: */ -static __cpuinitdata atomic_t start_count; -static __cpuinitdata atomic_t stop_count; +static atomic_t start_count; +static atomic_t stop_count; /* * We use a raw spinlock in this exceptional case, because * we want to have the fastest, inlined, non-debug version * of a critical section, to be able to prove TSC time-warps: */ -static __cpuinitdata arch_spinlock_t sync_lock = __ARCH_SPIN_LOCK_UNLOCKED; +static arch_spinlock_t sync_lock = __ARCH_SPIN_LOCK_UNLOCKED; -static __cpuinitdata cycles_t last_tsc; -static __cpuinitdata cycles_t max_warp; -static __cpuinitdata int nr_warps; +static cycles_t last_tsc; +static cycles_t max_warp; +static int nr_warps; /* * TSC-warp measurement loop running on both CPUs: */ -static __cpuinit void check_tsc_warp(unsigned int timeout) +static void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; @@ -121,7 +121,7 @@ static inline unsigned int loop_timeout(int cpu) * Source CPU calls into this - it waits for the freshly booted * target CPU to arrive and then starts the measurement: */ -void __cpuinit check_tsc_sync_source(int cpu) +void check_tsc_sync_source(int cpu) { int cpus = 2; @@ -187,7 +187,7 @@ void __cpuinit check_tsc_sync_source(int cpu) /* * Freshly booted CPUs call into this: */ -void __cpuinit check_tsc_sync_target(void) +void check_tsc_sync_target(void) { int cpus = 2; diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 9a907a6..1f96f93 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -331,7 +331,7 @@ sigsegv: * Assume __initcall executes before all user space. Hopefully kmod * doesn't violate that. We'll find out if it does. */ -static void __cpuinit vsyscall_set_cpu(int cpu) +static void vsyscall_set_cpu(int cpu) { unsigned long d; unsigned long node = 0; @@ -353,13 +353,13 @@ static void __cpuinit vsyscall_set_cpu(int cpu) write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S); } -static void __cpuinit cpu_vsyscall_init(void *arg) +static void cpu_vsyscall_init(void *arg) { /* preemption should be already off */ vsyscall_set_cpu(raw_smp_processor_id()); } -static int __cpuinit +static int cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg) { long cpu = (long)arg; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 45a14db..8ce0072 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -25,7 +25,7 @@ #include <asm/iommu.h> #include <asm/mach_traps.h> -void __cpuinit x86_init_noop(void) { } +void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } int __init iommu_init_noop(void) { return 0; } void iommu_shutdown_noop(void) { } @@ -85,7 +85,7 @@ struct x86_init_ops x86_init __initdata = { }, }; -struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = { +struct x86_cpuinit_ops x86_cpuinit = { .early_percpu_clock_init = x86_init_noop, .setup_percpu_clockev = setup_secondary_APIC_clock, }; @@ -107,6 +107,8 @@ struct x86_platform_ops x86_platform = { }; EXPORT_SYMBOL_GPL(x86_platform); + +#if defined(CONFIG_PCI_MSI) struct x86_msi_ops x86_msi = { .setup_msi_irqs = native_setup_msi_irqs, .compose_msi_msg = native_compose_msi_msg, @@ -116,6 +118,28 @@ struct x86_msi_ops x86_msi = { .setup_hpet_msi = default_setup_hpet_msi, }; +/* MSI arch specific hooks */ +int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + return x86_msi.setup_msi_irqs(dev, nvec, type); +} + +void arch_teardown_msi_irqs(struct pci_dev *dev) +{ + x86_msi.teardown_msi_irqs(dev); +} + +void arch_teardown_msi_irq(unsigned int irq) +{ + x86_msi.teardown_msi_irq(irq); +} + +void arch_restore_msi_irqs(struct pci_dev *dev, int irq) +{ + x86_msi.restore_msi_irqs(dev, irq); +} +#endif + struct x86_io_apic_ops x86_io_apic_ops = { .init = native_io_apic_init_mappings, .read = native_io_apic_read, diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index ada87a3..422fd82 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -243,7 +243,7 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (!access_ok(VERIFY_WRITE, buf, size)) return -EACCES; - if (!HAVE_HWFP) + if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_get(current, NULL, 0, sizeof(struct user_i387_ia32_struct), NULL, (struct _fpstate_ia32 __user *) buf) ? -1 : 1; @@ -350,11 +350,10 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (!used_math() && init_fpu(tsk)) return -1; - if (!HAVE_HWFP) { + if (!static_cpu_has(X86_FEATURE_FPU)) return fpregs_soft_set(current, NULL, 0, sizeof(struct user_i387_ia32_struct), NULL, buf) != 0; - } if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user; @@ -574,7 +573,7 @@ static void __init xstate_enable_boot_cpu(void) * This is somewhat obfuscated due to the lack of powerful enough * overrides for the section checks. */ -void __cpuinit xsave_init(void) +void xsave_init(void) { static __refdata void (*next_func)(void) = xstate_enable_boot_cpu; void (*this_func)(void); @@ -595,7 +594,7 @@ static inline void __init eager_fpu_init_bp(void) setup_init_fpu_buf(); } -void __cpuinit eager_fpu_init(void) +void eager_fpu_init(void) { static __refdata void (*boot_func)(void) = eager_fpu_init_bp; |
