diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/include/asm/jump_label.h | 9 | ||||
-rw-r--r-- | arch/x86/include/asm/pgtable.h | 34 | ||||
-rw-r--r-- | arch/x86/include/asm/pgtable_types.h | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/tlbflush.h | 37 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/mtrr/generic.c | 2 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel.c | 1 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/perf_event_intel_uncore.c | 6 | ||||
-rw-r--r-- | arch/x86/kernel/devicetree.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/early-quirks.c | 154 | ||||
-rw-r--r-- | arch/x86/kernel/jump_label.c | 70 | ||||
-rw-r--r-- | arch/x86/mm/hugetlbpage.c | 8 | ||||
-rw-r--r-- | arch/x86/mm/tlb.c | 14 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 1 | ||||
-rw-r--r-- | arch/x86/xen/p2m.c | 10 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 28 | ||||
-rw-r--r-- | arch/x86/xen/spinlock.c | 45 |
16 files changed, 344 insertions, 81 deletions
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 3a16c14..64507f3 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -3,18 +3,23 @@ #ifdef __KERNEL__ +#include <linux/stringify.h> #include <linux/types.h> #include <asm/nops.h> #include <asm/asm.h> #define JUMP_LABEL_NOP_SIZE 5 -#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t" +#ifdef CONFIG_X86_64 +# define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC +#else +# define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC +#endif static __always_inline bool arch_static_branch(struct static_key *key) { asm goto("1:" - STATIC_KEY_INITIAL_NOP + ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" _ASM_PTR "1b, %l[l_yes], %c0 \n\t" diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 8d16bef..3d19994 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -315,21 +315,6 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } -static inline pte_t pte_swp_mksoft_dirty(pte_t pte) -{ - return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); -} - -static inline int pte_swp_soft_dirty(pte_t pte) -{ - return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; -} - -static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) -{ - return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); -} - static inline pte_t pte_file_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); @@ -446,6 +431,7 @@ pte_t *populate_extra_pte(unsigned long vaddr); #ifndef __ASSEMBLY__ #include <linux/mm_types.h> +#include <linux/mmdebug.h> #include <linux/log2.h> static inline int pte_none(pte_t pte) @@ -864,6 +850,24 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, { } +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + VM_BUG_ON(pte_present(pte)); + return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + VM_BUG_ON(pte_present(pte)); + return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + VM_BUG_ON(pte_present(pte)); + return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f4843e0..0ecac25 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -75,6 +75,9 @@ * with swap entry format. On x86 bits 6 and 7 are *not* involved * into swap entry computation, but bit 6 is used for nonlinear * file mapping, so we borrow bit 7 for soft dirty tracking. + * + * Please note that this bit must be treated as swap dirty page + * mark if and only if the PTE has present bit clear! */ #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index cf51200..e6d90ba 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,6 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { + count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); } @@ -84,14 +85,38 @@ static inline void __flush_tlb_one(unsigned long addr) #ifndef CONFIG_SMP -#define flush_tlb() __flush_tlb() -#define flush_tlb_all() __flush_tlb_all() -#define local_flush_tlb() __flush_tlb() +/* "_up" is for UniProcessor. + * + * This is a helper for other header functions. *Not* intended to be called + * directly. All global TLB flushes need to either call this, or to bump the + * vm statistics themselves. + */ +static inline void __flush_tlb_up(void) +{ + count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + __flush_tlb(); +} + +static inline void flush_tlb_all(void) +{ + count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); + __flush_tlb_all(); +} + +static inline void flush_tlb(void) +{ + __flush_tlb_up(); +} + +static inline void local_flush_tlb(void) +{ + __flush_tlb_up(); +} static inline void flush_tlb_mm(struct mm_struct *mm) { if (mm == current->active_mm) - __flush_tlb(); + __flush_tlb_up(); } static inline void flush_tlb_page(struct vm_area_struct *vma, @@ -105,14 +130,14 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_mm == current->active_mm) - __flush_tlb(); + __flush_tlb_up(); } static inline void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { if (mm == current->active_mm) - __flush_tlb(); + __flush_tlb_up(); } static inline void native_flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index d4cdfa6..ce2d0a2 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -683,6 +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 */ @@ -696,6 +697,7 @@ 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 */ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 0abf674..c62d883 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -124,6 +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 */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index fd8011e..8ed4458 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2808,7 +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) { @@ -3112,7 +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) { diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 69eb2fa..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); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 63bdb29..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> @@ -216,6 +217,157 @@ static void __init intel_remapping_check(int num, int slot, int func) } +/* + * 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 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -251,6 +403,8 @@ static struct chipset early_qrk[] __initdata = { 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/jump_label.c b/arch/x86/kernel/jump_label.c index 460f5d9..ee11b7d 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -24,18 +24,57 @@ 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); + } /* * Make text_poke_bp() a default fallback poker. @@ -57,15 +96,38 @@ void arch_jump_label_transform(struct jump_entry *entry, { get_online_cpus(); mutex_lock(&text_mutex); - __jump_label_transform(entry, type, NULL); + __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/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 7e73e8c..9d980d8 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -59,6 +59,10 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, return NULL; } +int pmd_huge_support(void) +{ + return 0; +} #else struct page * @@ -77,6 +81,10 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_PSE); } +int pmd_huge_support(void) +{ + return 1; +} #endif /* x86_64 also uses this file */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 282375f..ae699b3 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -103,6 +103,7 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; + count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { if (f->flush_end == TLB_FLUSH_ALL) local_flush_tlb(); @@ -130,6 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_start = start; info.flush_end = end; + count_vm_event(NR_TLB_REMOTE_FLUSH); if (is_uv_system()) { unsigned int cpu; @@ -149,6 +151,7 @@ void flush_tlb_current_task(void) preempt_disable(); + count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -211,16 +214,19 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm; /* tlb_flushall_shift is on balance point, details in commit log */ - if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) + if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) { + count_vm_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); - else { + } else { if (has_large_page(mm, start, end)) { local_flush_tlb(); goto flush_all; } /* flush range by one by one 'invlpg' */ - for (addr = start; addr < end; addr += PAGE_SIZE) + for (addr = start; addr < end; addr += PAGE_SIZE) { + count_vm_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); + } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) @@ -256,6 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) static void do_flush_tlb_all(void *info) { + count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED); __flush_tlb_all(); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY) leave_mm(smp_processor_id()); @@ -263,6 +270,7 @@ static void do_flush_tlb_all(void *info) void flush_tlb_all(void) { + count_vm_event(NR_TLB_REMOTE_FLUSH); on_each_cpu(do_flush_tlb_all, NULL, 1); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 2fc216d..fa6ade7 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1692,7 +1692,6 @@ static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action, case CPU_UP_PREPARE: xen_vcpu_setup(cpu); if (xen_have_vector_callback) { - xen_init_lock_cpu(cpu); if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 0d4ec35..8b901e8 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -990,10 +990,13 @@ int m2p_remove_override(struct page *page, printk(KERN_WARNING "m2p_remove_override: " "pfn %lx mfn %lx, failed to modify kernel mappings", pfn, mfn); + put_balloon_scratch_page(); return -1; } - mcs = xen_mc_entry( + xen_mc_batch(); + + mcs = __xen_mc_entry( sizeof(struct gnttab_unmap_and_replace)); unmap_op = mcs.args; unmap_op->host_addr = kmap_op->host_addr; @@ -1003,12 +1006,11 @@ int m2p_remove_override(struct page *page, MULTI_grant_table_op(mcs.mc, GNTTABOP_unmap_and_replace, unmap_op, 1); - xen_mc_issue(PARAVIRT_LAZY_MMU); - mcs = __xen_mc_entry(0); MULTI_update_va_mapping(mcs.mc, scratch_page_address, - pfn_pte(page_to_pfn(get_balloon_scratch_page()), + pfn_pte(page_to_pfn(scratch_page), PAGE_KERNEL_RO), 0); + xen_mc_issue(PARAVIRT_LAZY_MMU); kmap_op->host_addr = 0; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 9235842..d1e4777 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -273,12 +273,20 @@ static void __init xen_smp_prepare_boot_cpu(void) BUG_ON(smp_processor_id() != 0); native_smp_prepare_boot_cpu(); - /* We've switched to the "real" per-cpu gdt, so make sure the - old memory can be recycled */ - make_lowmem_page_readwrite(xen_initial_gdt); + if (xen_pv_domain()) { + /* We've switched to the "real" per-cpu gdt, so make sure the + old memory can be recycled */ + make_lowmem_page_readwrite(xen_initial_gdt); - xen_filter_cpu_maps(); - xen_setup_vcpu_info_placement(); + xen_filter_cpu_maps(); + xen_setup_vcpu_info_placement(); + } + /* + * The alternative logic (which patches the unlock/lock) runs before + * the smp bootup up code is activated. Hence we need to set this up + * the core kernel is being patched. Otherwise we will have only + * modules patched but not core code. + */ xen_init_spinlocks(); } @@ -709,6 +717,15 @@ static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) WARN_ON(rc); if (!rc) rc = native_cpu_up(cpu, tidle); + + /* + * We must initialize the slowpath CPU kicker _after_ the native + * path has executed. If we initialized it before none of the + * unlocker IPI kicks would reach the booting CPU as the booting + * CPU had not set itself 'online' in cpu_online_mask. That mask + * is checked when IPIs are sent (on HVM at least). + */ + xen_init_lock_cpu(cpu); return rc; } @@ -728,4 +745,5 @@ void __init xen_hvm_smp_init(void) smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; + smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu; } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 0438b93..253f63f 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -81,7 +81,6 @@ static inline void spin_time_accum_blocked(u64 start) spinlock_stats.time_blocked += delta; } #else /* !CONFIG_XEN_DEBUG_FS */ -#define TIMEOUT (1 << 10) static inline void add_stats(enum xen_contention_stat var, u32 val) { } @@ -96,23 +95,6 @@ static inline void spin_time_accum_blocked(u64 start) } #endif /* CONFIG_XEN_DEBUG_FS */ -/* - * Size struct xen_spinlock so it's the same as arch_spinlock_t. - */ -#if NR_CPUS < 256 -typedef u8 xen_spinners_t; -# define inc_spinners(xl) \ - asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory"); -# define dec_spinners(xl) \ - asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory"); -#else -typedef u16 xen_spinners_t; -# define inc_spinners(xl) \ - asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory"); -# define dec_spinners(xl) \ - asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory"); -#endif - struct xen_lock_waiting { struct arch_spinlock *lock; __ticket_t want; @@ -123,6 +105,7 @@ static DEFINE_PER_CPU(char *, irq_name); static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); static cpumask_t waiting_cpus; +static bool xen_pvspin = true; static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { int irq = __this_cpu_read(lock_kicker_irq); @@ -241,16 +224,12 @@ void xen_init_lock_cpu(int cpu) int irq; char *name; + if (!xen_pvspin) + return; + WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n", cpu, per_cpu(lock_kicker_irq, cpu)); - /* - * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 - * (xen: disable PV spinlocks on HVM) - */ - if (xen_hvm_domain()) - return; - name = kasprintf(GFP_KERNEL, "spinlock%d", cpu); irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, @@ -270,11 +249,7 @@ void xen_init_lock_cpu(int cpu) void xen_uninit_lock_cpu(int cpu) { - /* - * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 - * (xen: disable PV spinlocks on HVM) - */ - if (xen_hvm_domain()) + if (!xen_pvspin) return; unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); @@ -283,16 +258,9 @@ void xen_uninit_lock_cpu(int cpu) per_cpu(irq_name, cpu) = NULL; } -static bool xen_pvspin __initdata = true; void __init xen_init_spinlocks(void) { - /* - * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23 - * (xen: disable PV spinlocks on HVM) - */ - if (xen_hvm_domain()) - return; if (!xen_pvspin) { printk(KERN_DEBUG "xen: PV spinlocks disabled\n"); @@ -323,6 +291,9 @@ static int __init xen_spinlock_debugfs(void) if (d_xen == NULL) return -ENOMEM; + if (!xen_pvspin) + return 0; + d_spin_debug = debugfs_create_dir("spinlocks", d_xen); debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); |