diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/memblock.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/mmzone_32.h | 11 | ||||
-rw-r--r-- | arch/x86/include/asm/mmzone_64.h | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/pvclock.h | 9 | ||||
-rw-r--r-- | arch/x86/kernel/apic/x2apic_uv_x.c | 8 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event.c | 150 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_amd.c | 14 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 385 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_ds.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_p4.c | 42 | ||||
-rw-r--r-- | arch/x86/kernel/kgdb.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/process.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/ptrace.c | 5 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 2 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 3 | ||||
-rw-r--r-- | arch/x86/mm/fault.c | 6 | ||||
-rw-r--r-- | arch/x86/mm/memblock.c | 4 | ||||
-rw-r--r-- | arch/x86/pci/acpi.c | 2 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi.c | 29 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 9 | ||||
-rw-r--r-- | arch/x86/xen/mmu.c | 12 | ||||
-rw-r--r-- | arch/x86/xen/setup.c | 10 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 7 |
24 files changed, 508 insertions, 219 deletions
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h index 19ae14ba6978..0cd3800f33b9 100644 --- a/arch/x86/include/asm/memblock.h +++ b/arch/x86/include/asm/memblock.h @@ -4,7 +4,6 @@ #define ARCH_DISCARD_MEMBLOCK u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); -void memblock_x86_to_bootmem(u64 start, u64 end); void memblock_x86_reserve_range(u64 start, u64 end, char *name); void memblock_x86_free_range(u64 start, u64 end); @@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end); u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); u64 memblock_x86_memory_in_range(u64 addr, u64 limit); +bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); #endif diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 5e83a416eca8..224e8c5eb307 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn) #endif } -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - static inline int pfn_valid(int pfn) { int nid = pfn_to_nid(pfn); diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index b3f88d7867c7..129d9aa3ceb3 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -13,8 +13,5 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ - NODE_DATA(nid)->node_spanned_pages) #endif #endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 31d84acc1512..a518c0a45044 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) u64 product; #ifdef __i386__ u32 tmp1, tmp2; +#else + ulong tmp; #endif if (shift < 0) @@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); #elif defined(__x86_64__) __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); + "mul %[mul_frac] ; shrd $32, %[hi], %[lo]" + : [lo]"=a"(product), + [hi]"=d"(tmp) + : "0"(delta), + [mul_frac]"rm"((u64)mul_frac)); #else #error implement me! #endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index b511a011b7d0..adc66c3a1fef 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -632,14 +632,14 @@ late_initcall(uv_init_heartbeat); /* Direct Legacy VGA I/O traffic to designated IOH */ int uv_set_vga_state(struct pci_dev *pdev, bool decode, - unsigned int command_bits, bool change_bridge) + unsigned int command_bits, u32 flags) { int domain, bus, rc; - PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n", - pdev->devfn, decode, command_bits, change_bridge); + PR_DEVEL("devfn %x decode %d cmd %x flags %d\n", + pdev->devfn, decode, command_bits, flags); - if (!change_bridge) + if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE)) return 0; if ((command_bits & PCI_COMMAND_IO) == 0) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 3a0338b4b179..c53d433c3dde 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -45,6 +45,29 @@ do { \ #endif /* + * | NHM/WSM | SNB | + * register ------------------------------- + * | HT | no HT | HT | no HT | + *----------------------------------------- + * offcore | core | core | cpu | core | + * lbr_sel | core | core | cpu | core | + * ld_lat | cpu | core | cpu | core | + *----------------------------------------- + * + * Given that there is a small number of shared regs, + * we can pre-allocate their slot in the per-cpu + * per-core reg tables. + */ +enum extra_reg_type { + EXTRA_REG_NONE = -1, /* not used */ + + EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ + EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ + + EXTRA_REG_MAX /* number of entries needed */ +}; + +/* * best effort, GUP based copy_from_user() that assumes IRQ or NMI context */ static unsigned long @@ -132,11 +155,10 @@ struct cpu_hw_events { struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; /* - * Intel percore register state. - * Coordinate shared resources between HT threads. + * manage shared (per-core, per-cpu) registers + * used on Intel NHM/WSM/SNB */ - int percore_used; /* Used by this CPU? */ - struct intel_percore *per_core; + struct intel_shared_regs *shared_regs; /* * AMD specific bits @@ -187,26 +209,45 @@ struct cpu_hw_events { for ((e) = (c); (e)->weight; (e)++) /* + * Per register state. + */ +struct er_account { + raw_spinlock_t lock; /* per-core: protect structure */ + u64 config; /* extra MSR config */ + u64 reg; /* extra MSR number */ + atomic_t ref; /* reference count */ +}; + +/* * Extra registers for specific events. + * * Some events need large masks and require external MSRs. - * Define a mapping to these extra registers. + * Those extra MSRs end up being shared for all events on + * a PMU and sometimes between PMU of sibling HT threads. + * In either case, the kernel needs to handle conflicting + * accesses to those extra, shared, regs. The data structure + * to manage those registers is stored in cpu_hw_event. */ struct extra_reg { unsigned int event; unsigned int msr; u64 config_mask; u64 valid_mask; + int idx; /* per_xxx->regs[] reg index */ }; -#define EVENT_EXTRA_REG(e, ms, m, vm) { \ +#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ .event = (e), \ .msr = (ms), \ .config_mask = (m), \ .valid_mask = (vm), \ + .idx = EXTRA_REG_##i \ } -#define INTEL_EVENT_EXTRA_REG(event, msr, vm) \ - EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm) -#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0) + +#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) + +#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) union perf_capabilities { struct { @@ -233,6 +274,7 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*hw_watchdog_set_attr)(struct perf_event_attr *attr); int (*hw_config)(struct perf_event *event); int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign); unsigned eventsel; @@ -252,7 +294,6 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); struct event_constraint *event_constraints; - struct event_constraint *percore_constraints; void (*quirks)(void); int perfctr_second_write; @@ -286,8 +327,12 @@ struct x86_pmu { * Extra registers for events */ struct extra_reg *extra_regs; + unsigned int er_flags; }; +#define ERF_NO_HT_SHARING 1 +#define ERF_HAS_RSP_1 2 + static struct x86_pmu x86_pmu __read_mostly; static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = { @@ -315,6 +360,12 @@ static u64 __read_mostly hw_cache_extra_regs [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; +void hw_nmi_watchdog_set_attr(struct perf_event_attr *wd_attr) +{ + if (x86_pmu.hw_watchdog_set_attr) + x86_pmu.hw_watchdog_set_attr(wd_attr); +} + /* * Propagate event elapsed time into the generic event. * Can only be executed on the CPU where the event is active. @@ -393,10 +444,10 @@ static inline unsigned int x86_pmu_event_addr(int index) */ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) { + struct hw_perf_event_extra *reg; struct extra_reg *er; - event->hw.extra_reg = 0; - event->hw.extra_config = 0; + reg = &event->hw.extra_reg; if (!x86_pmu.extra_regs) return 0; @@ -406,8 +457,10 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; - event->hw.extra_reg = er->msr; - event->hw.extra_config = event->attr.config1; + + reg->idx = er->idx; + reg->config = event->attr.config1; + reg->reg = er->msr; break; } return 0; @@ -706,6 +759,9 @@ static int __x86_pmu_event_init(struct perf_event *event) event->hw.last_cpu = -1; event->hw.last_tag = ~0ULL; + /* mark unused */ + event->hw.extra_reg.idx = EXTRA_REG_NONE; + return x86_pmu.hw_config(event); } @@ -747,8 +803,8 @@ static void x86_pmu_disable(struct pmu *pmu) static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, u64 enable_mask) { - if (hwc->extra_reg) - wrmsrl(hwc->extra_reg, hwc->extra_config); + if (hwc->extra_reg.reg) + wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config); wrmsrl(hwc->config_base, hwc->config | enable_mask); } @@ -1332,7 +1388,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1637,6 +1693,40 @@ static int x86_pmu_commit_txn(struct pmu *pmu) perf_pmu_enable(pmu); return 0; } +/* + * a fake_cpuc is used to validate event groups. Due to + * the extra reg logic, we need to also allocate a fake + * per_core and per_cpu structure. Otherwise, group events + * using extra reg may conflict without the kernel being + * able to catch this when the last event gets added to + * the group. + */ +static void free_fake_cpuc(struct cpu_hw_events *cpuc) +{ + kfree(cpuc->shared_regs); + kfree(cpuc); +} + +static struct cpu_hw_events *allocate_fake_cpuc(void) +{ + struct cpu_hw_events *cpuc; + int cpu = raw_smp_processor_id(); + + cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL); + if (!cpuc) + return ERR_PTR(-ENOMEM); + + /* only needed, if we have extra_regs */ + if (x86_pmu.extra_regs) { + cpuc->shared_regs = allocate_shared_regs(cpu); + if (!cpuc->shared_regs) + goto error; + } + return cpuc; +error: + free_fake_cpuc(cpuc); + return ERR_PTR(-ENOMEM); +} /* * validate that we can schedule this event @@ -1647,9 +1737,9 @@ static int validate_event(struct perf_event *event) struct event_constraint *c; int ret = 0; - fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); - if (!fake_cpuc) - return -ENOMEM; + fake_cpuc = allocate_fake_cpuc(); + if (IS_ERR(fake_cpuc)) + return PTR_ERR(fake_cpuc); c = x86_pmu.get_event_constraints(fake_cpuc, event); @@ -1659,7 +1749,7 @@ static int validate_event(struct perf_event *event) if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(fake_cpuc, event); - kfree(fake_cpuc); + free_fake_cpuc(fake_cpuc); return ret; } @@ -1679,36 +1769,32 @@ static int validate_group(struct perf_event *event) { struct perf_event *leader = event->group_leader; struct cpu_hw_events *fake_cpuc; - int ret, n; - - ret = -ENOMEM; - fake_cpuc = kmalloc(sizeof(*fake_cpuc), GFP_KERNEL | __GFP_ZERO); - if (!fake_cpuc) - goto out; + int ret = -ENOSPC, n; + fake_cpuc = allocate_fake_cpuc(); + if (IS_ERR(fake_cpuc)) + return PTR_ERR(fake_cpuc); /* * the event is not yet connected with its * siblings therefore we must first collect * existing siblings, then add the new event * before we can simulate the scheduling */ - ret = -ENOSPC; n = collect_events(fake_cpuc, leader, true); if (n < 0) - goto out_free; + goto out; fake_cpuc->n_events = n; n = collect_events(fake_cpuc, event, false); if (n < 0) - goto out_free; + goto out; fake_cpuc->n_events = n; ret = x86_pmu.schedule_events(fake_cpuc, n, NULL); -out_free: - kfree(fake_cpuc); out: + free_fake_cpuc(fake_cpuc); return ret; } diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index fe29c1d2219e..941caa2e449b 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -89,6 +89,20 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xb8e9, /* CPU Request to Memory, l+r */ + [ C(RESULT_MISS) ] = 0x98e9, /* CPU Request to Memory, r */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, }; /* diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 41178c826c48..45fbb8f7f549 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1,25 +1,15 @@ #ifdef CONFIG_CPU_SUP_INTEL -#define MAX_EXTRA_REGS 2 - -/* - * Per register state. - */ -struct er_account { - int ref; /* reference count */ - unsigned int extra_reg; /* extra MSR number */ - u64 extra_config; /* extra MSR config */ -}; - /* - * Per core state - * This used to coordinate shared registers for HT threads. + * Per core/cpu state + * + * Used to coordinate shared registers between HT threads or + * among events on a single PMU. */ -struct intel_percore { - raw_spinlock_t lock; /* protect structure */ - struct er_account regs[MAX_EXTRA_REGS]; - int refcnt; /* number of threads */ - unsigned core_id; +struct intel_shared_regs { + struct er_account regs[EXTRA_REG_MAX]; + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ }; /* @@ -88,16 +78,10 @@ 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), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), EVENT_EXTRA_END }; -static struct event_constraint intel_nehalem_percore_constraints[] __read_mostly = -{ - INTEL_EVENT_CONSTRAINT(0xb7, 0), - EVENT_CONSTRAINT_END -}; - static struct event_constraint intel_westmere_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ @@ -116,8 +100,6 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */ - INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ EVENT_CONSTRAINT_END @@ -125,15 +107,13 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), EVENT_EXTRA_END }; -static struct event_constraint intel_westmere_percore_constraints[] __read_mostly = +static struct event_constraint intel_v1_event_constraints[] __read_mostly = { - INTEL_EVENT_CONSTRAINT(0xb7, 0), - INTEL_EVENT_CONSTRAINT(0xbb, 0), EVENT_CONSTRAINT_END }; @@ -145,6 +125,12 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct extra_reg intel_snb_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + EVENT_EXTRA_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -245,6 +231,21 @@ static __initconst const u64 snb_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + }; static __initconst const u64 westmere_hw_cache_event_ids @@ -346,6 +347,20 @@ static __initconst const u64 westmere_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, }; /* @@ -398,7 +413,21 @@ static __initconst const u64 nehalem_hw_cache_extra_regs [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS, [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS, }, - } + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM, + [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE_DRAM, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM, + [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM, + [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM, + }, + }, }; static __initconst const u64 nehalem_hw_cache_event_ids @@ -500,6 +529,20 @@ static __initconst const u64 nehalem_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, }; static __initconst const u64 core2_hw_cache_event_ids @@ -1003,7 +1046,7 @@ again: data.period = event->hw.last_period; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1037,65 +1080,121 @@ intel_bts_constraints(struct perf_event *event) return NULL; } +static bool intel_try_alt_er(struct perf_event *event, int orig_idx) +{ + if (!(x86_pmu.er_flags & ERF_HAS_RSP_1)) + return false; + + if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) { + event->hw.config &= ~INTEL_ARCH_EVENT_MASK; + event->hw.config |= 0x01bb; + event->hw.extra_reg.idx = EXTRA_REG_RSP_1; + event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1; + } else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) { + event->hw.config &= ~INTEL_ARCH_EVENT_MASK; + event->hw.config |= 0x01b7; + event->hw.extra_reg.idx = EXTRA_REG_RSP_0; + event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0; + } + + if (event->hw.extra_reg.idx == orig_idx) + return false; + + return true; +} + +/* + * manage allocation of shared extra msr for certain events + * + * sharing can be: + * per-cpu: to be shared between the various events on a single PMU + * per-core: per-cpu + shared by HT threads + */ static struct event_constraint * -intel_percore_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +__intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; - unsigned int e = hwc->config & ARCH_PERFMON_EVENTSEL_EVENT; - struct event_constraint *c; - struct intel_percore *pc; + struct event_constraint *c = &emptyconstraint; + struct hw_perf_event_extra *reg = &event->hw.extra_reg; struct er_account *era; - int i; - int free_slot; - int found; + unsigned long flags; + int orig_idx = reg->idx; - if (!x86_pmu.percore_constraints || hwc->extra_alloc) - return NULL; + /* already allocated shared msr */ + if (reg->alloc) + return &unconstrained; - for (c = x86_pmu.percore_constraints; c->cmask; c++) { - if (e != c->code) - continue; +again: + era = &cpuc->shared_regs->regs[reg->idx]; + /* + * we use spin_lock_irqsave() to avoid lockdep issues when + * passing a fake cpuc + */ + raw_spin_lock_irqsave(&era->lock, flags); + + if (!atomic_read(&era->ref) || era->config == reg->config) { + + /* lock in msr value */ + era->config = reg->config; + era->reg = reg->reg; + + /* one more user */ + atomic_inc(&era->ref); + + /* no need to reallocate during incremental event scheduling */ + reg->alloc = 1; /* - * Allocate resource per core. + * All events using extra_reg are unconstrained. + * Avoids calling x86_get_event_constraints() + * + * Must revisit if extra_reg controlling events + * ever have constraints. Worst case we go through + * the regular event constraint table. */ - pc = cpuc->per_core; - if (!pc) - break; - c = &emptyconstraint; - raw_spin_lock(&pc->lock); - free_slot = -1; - found = 0; - for (i = 0; i < MAX_EXTRA_REGS; i++) { - era = &pc->regs[i]; - if (era->ref > 0 && hwc->extra_reg == era->extra_reg) { - /* Allow sharing same config */ - if (hwc->extra_config == era->extra_config) { - era->ref++; - cpuc->percore_used = 1; - hwc->extra_alloc = 1; - c = NULL; - } - /* else conflict */ - found = 1; - break; - } else if (era->ref == 0 && free_slot == -1) - free_slot = i; - } - if (!found && free_slot != -1) { - era = &pc->regs[free_slot]; - era->ref = 1; - era->extra_reg = hwc->extra_reg; - era->extra_config = hwc->extra_config; - cpuc->percore_used = 1; - hwc->extra_alloc = 1; - c = NULL; - } - raw_spin_unlock(&pc->lock); - return c; + c = &unconstrained; + } else if (intel_try_alt_er(event, orig_idx)) { + raw_spin_unlock(&era->lock); + goto again; } + raw_spin_unlock_irqrestore(&era->lock, flags); - return NULL; + return c; +} + +static void +__intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc, + struct hw_perf_event_extra *reg) +{ + struct er_account *era; + + /* + * only put constraint if extra reg was actually + * allocated. Also takes care of event which do + * not use an extra shared reg + */ + if (!reg->alloc) + return; + + era = &cpuc->shared_regs->regs[reg->idx]; + + /* one fewer user */ + atomic_dec(&era->ref); + + /* allocate again next time */ + reg->alloc = 0; +} + +static struct event_constraint * +intel_shared_regs_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct event_constraint *c = NULL; + + if (event->hw.extra_reg.idx != EXTRA_REG_NONE) + c = __intel_shared_reg_get_constraints(cpuc, event); + + return c; } static struct event_constraint * @@ -1111,49 +1210,28 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event if (c) return c; - c = intel_percore_constraints(cpuc, event); + c = intel_shared_regs_constraints(cpuc, event); if (c) return c; return x86_get_event_constraints(cpuc, event); } -static void intel_put_event_constraints(struct cpu_hw_events *cpuc, +static void +intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - struct extra_reg *er; - struct intel_percore *pc; - struct er_account *era; - struct hw_perf_event *hwc = &event->hw; - int i, allref; + struct hw_perf_event_extra *reg; - if (!cpuc->percore_used) - return; - - for (er = x86_pmu.extra_regs; er->msr; er++) { - if (er->event != (hwc->config & er->config_mask)) - continue; + reg = &event->hw.extra_reg; + if (reg->idx != EXTRA_REG_NONE) + __intel_shared_reg_put_constraints(cpuc, reg); +} - pc = cpuc->per_core; - raw_spin_lock(&pc->lock); - for (i = 0; i < MAX_EXTRA_REGS; i++) { - era = &pc->regs[i]; - if (era->ref > 0 && - era->extra_config == hwc->extra_config && - era->extra_reg == er->msr) { - era->ref--; - hwc->extra_alloc = 0; - break; - } - } - allref = 0; - for (i = 0; i < MAX_EXTRA_REGS; i++) - allref += pc->regs[i].ref; - if (allref == 0) - cpuc->percore_used = 0; - raw_spin_unlock(&pc->lock); - break; - } +static void intel_put_event_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + intel_put_shared_regs_event_constraints(cpuc, event); } static int intel_pmu_hw_config(struct perf_event *event) @@ -1231,20 +1309,36 @@ static __initconst const struct x86_pmu core_pmu = { .event_constraints = intel_core_event_constraints, }; +static struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + struct intel_shared_regs *regs; + int i; + + regs = kzalloc_node(sizeof(struct intel_shared_regs), + GFP_KERNEL, cpu_to_node(cpu)); + if (regs) { + /* + * initialize the locks to keep lockdep happy + */ + for (i = 0; i < EXTRA_REG_MAX; i++) + raw_spin_lock_init(®s->regs[i].lock); + + regs->core_id = -1; + } + return regs; +} + static int intel_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - if (!cpu_has_ht_siblings()) + if (!x86_pmu.extra_regs) return NOTIFY_OK; - cpuc->per_core = kzalloc_node(sizeof(struct intel_percore), - GFP_KERNEL, cpu_to_node(cpu)); - if (!cpuc->per_core) + cpuc->shared_regs = allocate_shared_regs(cpu); + if (!cpuc->shared_regs) return NOTIFY_BAD; - raw_spin_lock_init(&cpuc->per_core->lock); - cpuc->per_core->core_id = -1; return NOTIFY_OK; } @@ -1260,32 +1354,34 @@ static void intel_pmu_cpu_starting(int cpu) */ intel_pmu_lbr_reset(); - if (!cpu_has_ht_siblings()) + if (!cpuc->shared_regs || (x86_pmu.er_flags & ERF_NO_HT_SHARING)) return; for_each_cpu(i, topology_thread_cpumask(cpu)) { - struct intel_percore *pc = per_cpu(cpu_hw_events, i).per_core; + struct intel_shared_regs *pc; + pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - kfree(cpuc->per_core); - cpuc->per_core = pc; + kfree(cpuc->shared_regs); + cpuc->shared_regs = pc; break; } } - cpuc->per_core->core_id = core_id; - cpuc->per_core->refcnt++; + cpuc->shared_regs->core_id = core_id; + cpuc->shared_regs->refcnt++; } static void intel_pmu_cpu_dying(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - struct intel_percore *pc = cpuc->per_core; + struct intel_shared_regs *pc; + pc = cpuc->shared_regs; if (pc) { if (pc->core_id == -1 || --pc->refcnt == 0) kfree(pc); - cpuc->per_core = NULL; + cpuc->shared_regs = NULL; } fini_debug_store_on_cpu(cpu); @@ -1436,7 +1532,6 @@ static __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_nehalem_event_constraints; x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints; - x86_pmu.percore_constraints = intel_nehalem_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; @@ -1481,10 +1576,10 @@ static __init int intel_pmu_init(void) intel_pmu_lbr_init_nhm(); x86_pmu.event_constraints = intel_westmere_event_constraints; - x86_pmu.percore_constraints = intel_westmere_percore_constraints; x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints; x86_pmu.extra_regs = intel_westmere_extra_regs; + x86_pmu.er_flags |= ERF_HAS_RSP_1; /* UOPS_ISSUED.STALLED_CYCLES */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; @@ -1502,6 +1597,10 @@ static __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_events; + x86_pmu.extra_regs = intel_snb_extra_regs; + /* 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; /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e; @@ -1512,11 +1611,19 @@ static __init int intel_pmu_init(void) break; default: - /* - * default constraints for v2 and up - */ - x86_pmu.event_constraints = intel_gen_event_constraints; - pr_cont("generic architected perfmon, "); + switch (x86_pmu.version) { + case 1: + x86_pmu.event_constraints = intel_v1_event_constraints; + pr_cont("generic architected perfmon v1, "); + break; + default: + /* + * default constraints for v2 and up + */ + x86_pmu.event_constraints = intel_gen_event_constraints; + pr_cont("generic architected perfmon, "); + break; + } } return 0; } @@ -1528,4 +1635,8 @@ static int intel_pmu_init(void) return 0; } +static struct intel_shared_regs *allocate_shared_regs(int cpu) +{ + return NULL; +} #endif /* CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index bab491b8ee25..1b1ef3addcfd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -340,7 +340,7 @@ static int intel_pmu_drain_bts_buffer(void) */ perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1)) + if (perf_output_begin(&handle, event, header.size * (top - at))) return 1; for (; at < top; at++) { @@ -616,7 +616,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; - if (perf_event_overflow(event, 1, &data, ®s)) + if (perf_event_overflow(event, &data, ®s)) x86_pmu_stop(event, 0); } diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index ead584fb6a7d..fb901c5080f7 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -554,6 +554,20 @@ static __initconst const u64 p4_hw_cache_event_ids [ C(RESULT_MISS) ] = -1, }, }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, }; static u64 p4_general_events[PERF_COUNT_HW_MAX] = { @@ -705,6 +719,31 @@ static int p4_validate_raw_event(struct perf_event *event) return 0; } +static void p4_hw_watchdog_set_attr(struct perf_event_attr *wd_attr) +{ + /* + * Watchdog ticks are special on Netburst, we use + * that named "non-sleeping" ticks as recommended + * by Intel SDM Vol3b. + */ + WARN_ON_ONCE(wd_attr->type != PERF_TYPE_HARDWARE || + wd_attr->config != PERF_COUNT_HW_CPU_CYCLES); + + wd_attr->type = PERF_TYPE_RAW; + wd_attr->config = + p4_config_pack_escr(P4_ESCR_EVENT(P4_EVENT_EXECUTION_EVENT) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS0) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS1) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS2) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, NBOGUS3) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS0) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS1) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS2) | + P4_ESCR_EMASK_BIT(P4_EVENT_EXECUTION_EVENT, BOGUS3)) | + p4_config_pack_cccr(P4_CCCR_THRESHOLD(15) | P4_CCCR_COMPLEMENT | + P4_CCCR_COMPARE); +} + static int p4_hw_config(struct perf_event *event) { int cpu = get_cpu(); @@ -945,7 +984,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); } @@ -1179,6 +1218,7 @@ static __initconst const struct x86_pmu p4_pmu = { .cntval_bits = ARCH_P4_CNTRVAL_BITS, .cntval_mask = ARCH_P4_CNTRVAL_MASK, .max_period = (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1, + .hw_watchdog_set_attr = p4_hw_watchdog_set_attr, .hw_config = p4_hw_config, .schedule_events = p4_pmu_schedule_events, /* diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 5f9ecff328b5..00354d4919a9 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -608,7 +608,7 @@ int kgdb_arch_init(void) return register_die_notifier(&kgdb_notifier); } -static void kgdb_hw_overflow_handler(struct perf_event *event, int nmi, +static void kgdb_hw_overflow_handler(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { struct task_struct *tsk = current; @@ -638,7 +638,7 @@ void kgdb_arch_late(void) for (i = 0; i < HBP_NUM; i++) { if (breakinfo[i].pev) continue; - breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL); + breakinfo[i].pev = register_wide_hw_breakpoint(&attr, NULL, NULL); if (IS_ERR((void * __force)breakinfo[i].pev)) { printk(KERN_ERR "kgdb: Could not allocate hw" "breakpoints\nDisabling the kernel debugger\n"); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 2e4928d45a2d..e1ba8cb24e4e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -337,7 +337,7 @@ EXPORT_SYMBOL(boot_option_idle_override); * Powermanagement idle function, if any.. */ void (*pm_idle)(void); -#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE) +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(pm_idle); #endif @@ -399,7 +399,7 @@ void default_idle(void) cpu_relax(); } } -#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE) +#ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(default_idle); #endif diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 807c2a2b80f1..82528799c5de 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -528,7 +528,7 @@ static int genregs_set(struct task_struct *target, return ret; } -static void ptrace_triggered(struct perf_event *bp, int nmi, +static void ptrace_triggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { @@ -715,7 +715,8 @@ static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr, attr.bp_type = HW_BREAKPOINT_W; attr.disabled = 1; - bp = register_user_hw_breakpoint(&attr, ptrace_triggered, tsk); + bp = register_user_hw_breakpoint(&attr, ptrace_triggered, + NULL, tsk); /* * CHECKME: the previous code returned -EIO if the addr wasn't diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index bd14bb4c8594..aee38623b768 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -565,7 +565,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) { - return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); + return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); } static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c4dc010c4cb..9d03ad4dd5ec 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, gva_t addr, u32 access) { pt_element_t pte; - pt_element_t __user *ptep_user; + pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; unsigned index, pt_access, uninitialized_var(pte_access); gpa_t pte_gpa; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4c3fa0f67469..d48ec60ea421 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0, unsigned long cr0, struct kvm_vcpu *vcpu) { - vmx_decache_cr3(vcpu); + if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail)) + vmx_decache_cr3(vcpu); if (!(cr0 & X86_CR0_PG)) { /* From paging/starting to nonpaging */ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2dbf6bf4c7e5..4d09df054e39 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1059,7 +1059,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* * If we're in an interrupt, have no user context or are running @@ -1161,11 +1161,11 @@ good_area: if (flags & FAULT_FLAG_ALLOW_RETRY) { if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); } else { tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } if (fault & VM_FAULT_RETRY) { diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c index aa1169392b83..992da5ec5a64 100644 --- a/arch/x86/mm/memblock.c +++ b/arch/x86/mm/memblock.c @@ -8,7 +8,7 @@ #include <linux/range.h> /* Check for already reserved areas */ -static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align) +bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align) { struct memblock_region *r; u64 addr = *addrp, last; @@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align) if (addr >= ei_last) continue; *sizep = ei_last - addr; - while (check_with_memblock_reserved_size(&addr, sizep, align)) + while (memblock_x86_check_reserved_size(&addr, sizep, align)) ; if (*sizep) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0972315c3860..68c3c1395202 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point) return false; } -static void coalesce_windows(struct pci_root_info *info, int type) +static void coalesce_windows(struct pci_root_info *info, unsigned long type) { int i, j; struct resource *res1, *res2; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 0d3a4fa34560..474356b98ede 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -310,14 +310,31 @@ void __init efi_reserve_boot_services(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; - unsigned long long start = md->phys_addr; - unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + u64 start = md->phys_addr; + u64 size = md->num_pages << EFI_PAGE_SHIFT; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - - memblock_x86_reserve_range(start, start + size, "EFI Boot"); + /* Only reserve where possible: + * - Not within any already allocated areas + * - Not over any memory area (really needed, if above?) + * - Not within any part of the kernel + * - Not the bios reserved area + */ + if ((start+size >= virt_to_phys(_text) + && start <= virt_to_phys(_end)) || + !e820_all_mapped(start, start+size, E820_RAM) || + memblock_x86_check_reserved_size(&start, &size, + 1<<EFI_PAGE_SHIFT)) { + /* Could not reserve, skip it */ + md->num_pages = 0; + memblock_dbg(PFX "Could not reserve boot range " + "[0x%010llx-0x%010llx]\n", + start, start+size-1); + } else + memblock_x86_reserve_range(start, start+size, + "EFI Boot"); } } @@ -334,6 +351,10 @@ static void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; + /* Could not reserve boot area */ + if (!size) + continue; + free_bootmem_late(start, size); } } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index dd7b88f2ec7a..5525163a0398 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1033,6 +1033,13 @@ static void xen_machine_halt(void) xen_reboot(SHUTDOWN_poweroff); } +static void xen_machine_power_off(void) +{ + if (pm_power_off) + pm_power_off(); + xen_reboot(SHUTDOWN_poweroff); +} + static void xen_crash_shutdown(struct pt_regs *regs) { xen_reboot(SHUTDOWN_crash); @@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void) static const struct machine_ops xen_machine_ops __initconst = { .restart = xen_restart, .halt = xen_machine_halt, - .power_off = xen_machine_halt, + .power_off = xen_machine_power_off, .shutdown = xen_machine_halt, .crash_shutdown = xen_crash_shutdown, .emergency_restart = xen_emergency_restart, diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index dc708dcc62f1..673e968df3cf 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -59,6 +59,7 @@ #include <asm/page.h> #include <asm/init.h> #include <asm/pat.h> +#include <asm/smp.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -1231,7 +1232,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; - DECLARE_BITMAP(mask, NR_CPUS); + DECLARE_BITMAP(mask, num_processors); } *args; struct multicall_space mcs; @@ -1599,6 +1600,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { pte_t pte; +#ifdef CONFIG_X86_32 + if (pfn > max_pfn_mapped) + max_pfn_mapped = pfn; +#endif + if (!pte_none(pte_page[pteidx])) continue; @@ -1766,7 +1772,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + + xen_start_info->nr_pt_frames * PAGE_SIZE + + 512*1024); kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index be1a464f6d66..60aeeb56948f 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -227,11 +227,7 @@ char * __init xen_memory_setup(void) memcpy(map_raw, map, sizeof(map)); e820.nr_map = 0; -#ifdef CONFIG_X86_32 xen_extra_mem_start = mem_end; -#else - xen_extra_mem_start = max((1ULL << 32), mem_end); -#endif for (i = 0; i < memmap.nr_entries; i++) { unsigned long long end; @@ -266,6 +262,12 @@ char * __init xen_memory_setup(void) if (map[i].size > 0) e820_add_region(map[i].addr, map[i].size, map[i].type); } + /* Align the balloon area so that max_low_pfn does not get set + * to be at the _end_ of the PCI gap at the far end (fee01000). + * Note that xen_extra_mem_start gets set in the loop above to be + * past the last E820 region. */ + if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32))) + xen_extra_mem_start = (1ULL<<32); /* * In domU, the ISA region is normal, usable memory, but we diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 41038c01de40..b4533a86d7e4 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void) static void __init xen_smp_prepare_cpus(unsigned int max_cpus) { unsigned cpu; + unsigned int i; xen_init_lock_cpu(0); smp_store_cpu_info(0); cpu_data(0).x86_max_cores = 1; + + for_each_possible_cpu(i) { + zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL); + } set_cpu_sibling_map(0); if (xen_smp_intr_init(0)) |