diff options
Diffstat (limited to 'arch/x86')
35 files changed, 431 insertions, 202 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0a7b885964ba..d9a94da0c29f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2439,6 +2439,15 @@ config PCI_CNB20LE_QUIRK source "drivers/pci/Kconfig" +config ISA_BUS + bool "ISA-style bus support on modern systems" if EXPERT + select ISA_BUS_API + help + Enables ISA-style drivers on modern systems. This is necessary to + support PC/104 devices on X86_64 platforms. + + If unsure, say N. + # x86_64 have no ISA slots, but can have ISA-style DMA. config ISA_DMA_API bool "ISA-style DMA support" if (X86_64 && EXPERT) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee817f0..91eac39625be 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -263,7 +263,7 @@ static bool check_hw_exists(void) msr_fail: pr_cont("Broken PMU hardware detected, using software events only.\n"); - pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -2319,7 +2319,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const void __user *fp; + const unsigned long __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (void __user *)regs->bp; + fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; + frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 16)) + if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); + bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 3660b2cf245a..06c2baa51814 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o -obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o -intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o +intel-rapl-perf-objs := rapl.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7c666958a625..9b4f9d3ce465 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = { /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..c64b1e9c5d1a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,10 +301,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +308,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4421b5da409d..d1d1e5094c28 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -38,12 +38,11 @@ typedef u8 kprobe_opcode_t; #define RELATIVECALL_OPCODE 0xe8 #define RELATIVE_ADDR_SIZE 4 #define MAX_STACK_SIZE 64 -#define MIN_STACK_SIZE(ADDR) \ - (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \ - THREAD_SIZE - (unsigned long)(ADDR))) \ - ? (MAX_STACK_SIZE) \ - : (((unsigned long)current_thread_info()) + \ - THREAD_SIZE - (unsigned long)(ADDR))) +#define CUR_STACK_SIZE(ADDR) \ + (current_top_of_stack() - (unsigned long)(ADDR)) +#define MIN_STACK_SIZE(ADDR) \ + (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \ + MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR)) #define flush_insn_slot(p) do { } while (0) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e0fbe7e70dc1..69e62862b622 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -27,6 +27,7 @@ #include <linux/irqbypass.h> #include <linux/hyperv.h> +#include <asm/apic.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> #include <asm/mtrr.h> @@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} +static inline int kvm_cpu_get_apicid(int mps_cpu) +{ +#ifdef CONFIG_X86_LOCAL_APIC + return __default_cpu_present_to_apicid(mps_cpu); +#else + WARN_ON_ONCE(1); + return BAD_APICID; +#endif +} + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index bf7f8b55b0f9..574c23cf761a 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -81,7 +81,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; - page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -125,7 +125,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return (pud_t *)get_zeroed_page(GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index fdcc04020636..7c1c89598688 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -69,29 +69,22 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) } static __always_inline -u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) -{ - u64 delta = rdtsc_ordered() - src->tsc_timestamp; - return pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); -} - -static __always_inline unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, cycle_t *cycles, u8 *flags) { unsigned version; - cycle_t ret, offset; - u8 ret_flags; + cycle_t offset; + u64 delta; version = src->version; + /* Make the latest version visible */ + smp_rmb(); - offset = pvclock_get_nsec_offset(src); - ret = src->system_time + offset; - ret_flags = src->flags; - - *cycles = ret; - *flags = ret_flags; + delta = rdtsc_ordered() - src->tsc_timestamp; + offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + *cycles = src->system_time + offset; + *flags = src->flags; return version; } diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 66b057306f40..7427ca895a27 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -135,6 +135,7 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); +void hlt_play_dead(void); void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 7c247e7404be..0944218af9e2 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -14,7 +14,7 @@ extern int kstack_depth_to_print; struct thread_info; struct stacktrace_ops; -typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, +typedef unsigned long (*walk_stack_t)(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, @@ -23,13 +23,13 @@ typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, int *graph); extern unsigned long -print_context_stack(struct thread_info *tinfo, +print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph); extern unsigned long -print_context_stack_bp(struct thread_info *tinfo, +print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index a147e676fc7b..e991d5c8bb3a 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 2bb25c3fe2e8..ef8017ca5ba9 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -42,16 +42,14 @@ void printk_address(unsigned long address) static void print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, - struct thread_info *tinfo, int *graph) + struct task_struct *task, int *graph) { - struct task_struct *task; unsigned long ret_addr; int index; if (addr != (unsigned long)return_to_handler) return; - task = tinfo->task; index = task->curr_ret_stack; if (!task->ret_stack || index < *graph) @@ -68,7 +66,7 @@ print_ftrace_graph_addr(unsigned long addr, void *data, static inline void print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, - struct thread_info *tinfo, int *graph) + struct task_struct *task, int *graph) { } #endif @@ -79,10 +77,10 @@ print_ftrace_graph_addr(unsigned long addr, void *data, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -static inline int valid_stack_ptr(struct thread_info *tinfo, +static inline int valid_stack_ptr(struct task_struct *task, void *p, unsigned int size, void *end) { - void *t = tinfo; + void *t = task_stack_page(task); if (end) { if (p < end && p >= (end-THREAD_SIZE)) return 1; @@ -93,14 +91,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, } unsigned long -print_context_stack(struct thread_info *tinfo, +print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph) { struct stack_frame *frame = (struct stack_frame *)bp; - while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) { + while (valid_stack_ptr(task, stack, sizeof(*stack), end)) { unsigned long addr; addr = *stack; @@ -112,7 +110,7 @@ print_context_stack(struct thread_info *tinfo, } else { ops->address(data, addr, 0); } - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + print_ftrace_graph_addr(addr, data, ops, task, graph); } stack++; } @@ -121,7 +119,7 @@ print_context_stack(struct thread_info *tinfo, EXPORT_SYMBOL_GPL(print_context_stack); unsigned long -print_context_stack_bp(struct thread_info *tinfo, +print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph) @@ -129,7 +127,7 @@ print_context_stack_bp(struct thread_info *tinfo, struct stack_frame *frame = (struct stack_frame *)bp; unsigned long *ret_addr = &frame->return_address; - while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) { + while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) { unsigned long addr = *ret_addr; if (!__kernel_text_address(addr)) @@ -139,7 +137,7 @@ print_context_stack_bp(struct thread_info *tinfo, break; frame = frame->next_frame; ret_addr = &frame->return_address; - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + print_ftrace_graph_addr(addr, data, ops, task, graph); } return (unsigned long)frame; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 464ffd69b92e..fef917e79b9d 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -61,15 +61,13 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, bp = stack_frame(task, regs); for (;;) { - struct thread_info *context; void *end_stack; end_stack = is_hardirq_stack(stack, cpu); if (!end_stack) end_stack = is_softirq_stack(stack, cpu); - context = task_thread_info(task); - bp = ops->walk_stack(context, stack, bp, ops, data, + bp = ops->walk_stack(task, stack, bp, ops, data, end_stack, &graph); /* Stop if not on irq stack */ diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 5f1c6266eb30..d558a8a49016 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -153,7 +153,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); - struct thread_info *tinfo; unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); unsigned long dummy; unsigned used = 0; @@ -179,7 +178,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * current stack address. If the stacks consist of nested * exceptions */ - tinfo = task_thread_info(task); while (!done) { unsigned long *stack_end; enum stack_type stype; @@ -202,7 +200,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, id) < 0) break; - bp = ops->walk_stack(tinfo, stack, bp, ops, + bp = ops->walk_stack(task, stack, bp, ops, data, stack_end, &graph); ops->stack(data, "<EOE>"); /* @@ -218,7 +216,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, "IRQ") < 0) break; - bp = ops->walk_stack(tinfo, stack, bp, + bp = ops->walk_stack(task, stack, bp, ops, data, stack_end, &graph); /* * We link to the next stack (which would be @@ -240,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, /* * This handles the process stack: */ - bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph); put_cpu(); } EXPORT_SYMBOL(dump_trace); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index bca14c899137..57b71373bae3 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/dmi.h> #include <linux/pci_ids.h> +#include <linux/bcma/bcma.h> +#include <linux/bcma/bcma_regs.h> #include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> @@ -21,6 +25,9 @@ #include <asm/iommu.h> #include <asm/gart.h> #include <asm/irq_remapping.h> +#include <asm/early_ioremap.h> + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func) #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. * Unfortunately that's not true on many Asus boards. @@ -590,6 +604,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -603,12 +672,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -638,9 +701,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -649,7 +716,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -658,6 +725,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -685,25 +753,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 4d38416e2a7f..04f89caef9c4 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -57,7 +57,7 @@ # error "Need more than one PGD for the ESPFIX hack" #endif -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) /* This contains the *bottom* address of the espfix stack */ DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 38da8f29a9c8..c627bf8d98ad 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -130,11 +130,9 @@ void irq_ctx_init(int cpu) void do_softirq_own_stack(void) { - struct thread_info *curstk; struct irq_stack *irqstk; u32 *isp, *prev_esp; - curstk = current_stack(); irqstk = __this_cpu_read(softirq_stack); /* build the stack frame on the softirq stack */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 38cf7a741250..7847e5c0e0b5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * normal page fault. */ regs->ip = (unsigned long)cur->addr; + /* + * Trap flag (TF) has been set here because this fault + * happened where the single stepping will be done. + * So clear it by resetting the current kprobe: + */ + regs->flags &= ~X86_EFLAGS_TF; + + /* + * If the TF flag was set before the kprobe hit, + * don't touch it: + */ regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 99bfc025111d..06c58ce46762 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -61,11 +61,16 @@ void pvclock_resume(void) u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret; u8 flags; do { - version = __pvclock_read_cycles(src, &ret, &flags); + version = src->version; + /* Make the latest version visible */ + smp_rmb(); + + flags = src->flags; + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fafe8b923cac..8264dfad9cf8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1622,7 +1622,7 @@ static inline void mwait_play_dead(void) } } -static inline void hlt_play_dead(void) +void hlt_play_dead(void) { if (__this_cpu_read(cpu_info.x86) >= 4) wbinvd(); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bbb5b283ff63..a397200281c1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(tsc_deadline - guest_tsc); + __delay(min(tsc_deadline - guest_tsc, + nsec_to_cycles(vcpu, lapic_timer_advance_ns))); } static void start_apic_timer(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1163e8173e5a..16ef31b87452 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO); /* enable / disable AVIC */ static int avic; +#ifdef CONFIG_X86_LOCAL_APIC module_param(avic, int, S_IRUGO); +#endif static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); @@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); - if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC))) - avic = false; - - if (avic) - pr_info("AVIC enabled\n"); + if (avic) { + if (!npt_enabled || + !boot_cpu_has(X86_FEATURE_AVIC) || + !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) + avic = false; + else + pr_info("AVIC enabled\n"); + } return 0; @@ -1324,7 +1329,7 @@ free_avic: static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { u64 entry; - int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu); + int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) @@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; /* ID = 0xff (broadcast), ID > 0xff (reserved) */ - int h_physical_id = __default_cpu_present_to_apicid(cpu); + int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) @@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) if (avic_vcpu_is_running(vcpu)) wrmsrl(SVM_AVIC_DOORBELL, - __default_cpu_present_to_apicid(vcpu->cpu)); + kvm_cpu_get_apicid(vcpu->cpu)); else kvm_vcpu_wake_up(vcpu); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index fb93010beaa4..64a79f271276 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; do { @@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; /* Set SN when the vCPU is preempted */ @@ -6669,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6686,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); @@ -10714,7 +10715,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return 0; vcpu->pre_pcpu = vcpu->cpu; @@ -10780,7 +10782,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu) unsigned long flags; if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; do { @@ -10833,7 +10836,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, int idx, ret = -EINVAL; if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(kvm->vcpus[0])) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 902d9da12392..7da5dd2057a9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) -{ - return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, - vcpu->arch.virtual_tsc_shift); -} - static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7ce3634ab5fe..a82ca466b62e 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_X86_H #include <linux/kvm_host.h> +#include <asm/pvclock.h> #include "kvm_cache_regs.h" #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL @@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns; extern struct static_key kvm_no_apic_vcpu; +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + /* Same "calling convention" as do_div: * - divide (n << 32) by base * - put result in n diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1b1110fa0057..0493c17b8a51 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -54,8 +54,8 @@ static int kasan_die_handler(struct notifier_block *self, void *data) { if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access"); + pr_emerg("CONFIG_KASAN_INLINE enabled\n"); + pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); } return NOTIFY_OK; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 4eb287e25043..aa0ff4b02a96 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include <asm/fixmap.h> #include <asm/mtrr.h> -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a61f6b..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6e7242be1c87..b226b3f497f1 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -139,7 +139,7 @@ int __init efi_alloc_page_tables(void) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO; + gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_page(gfp_mask); if (!efi_pgd) return -ENOMEM; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index d5f64996394a..b12c26e2e309 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -12,6 +12,7 @@ #include <linux/export.h> #include <linux/smp.h> #include <linux/perf_event.h> +#include <linux/tboot.h> #include <asm/pgtable.h> #include <asm/proto.h> @@ -266,6 +267,35 @@ void notrace restore_processor_state(void) EXPORT_SYMBOL(restore_processor_state); #endif +#if defined(CONFIG_HIBERNATION) && defined(CONFIG_HOTPLUG_CPU) +static void resume_play_dead(void) +{ + play_dead_common(); + tboot_shutdown(TB_SHUTDOWN_WFS); + hlt_play_dead(); +} + +int hibernate_resume_nonboot_cpu_disable(void) +{ + void (*play_dead)(void) = smp_ops.play_dead; + int ret; + + /* + * Ensure that MONITOR/MWAIT will not be used in the "play dead" loop + * during hibernate image restoration, because it is likely that the + * monitored address will be actually written to at that time and then + * the "dead" CPU will attempt to execute instructions again, but the + * address in its instruction pointer may not be possible to resolve + * any more at that point (the page tables used by it previously may + * have been overwritten by hibernate image data). + */ + smp_ops.play_dead = resume_play_dead; + ret = disable_nonboot_cpus(); + smp_ops.play_dead = play_dead; + return ret; +} +#endif + /* * When bsp_check() is called in hibernate and suspend, cpu hotplug * is disabled already. So it's unnessary to handle race condition between diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 009947d419a6..f2b5e6a5cf95 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -19,6 +19,7 @@ #include <asm/mtrr.h> #include <asm/sections.h> #include <asm/suspend.h> +#include <asm/tlbflush.h> /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); @@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void); * kernel's text (this value is passed in the image header). */ unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; /* * Value of the cr3 register from before the hibernation (this value is passed @@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible; pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code __visible; +unsigned long relocated_restore_code __visible; + +static int set_up_temporary_text_mapping(void) +{ + pmd_t *pmd; + pud_t *pud; + + /* + * The new mapping only has to cover the page containing the image + * kernel's entry point (jump_address_phys), because the switch over to + * it is carried out by relocated code running from a page allocated + * specifically for this purpose and covered by the identity mapping, so + * the temporary kernel text mapping is only needed for the final jump. + * Moreover, in that mapping the virtual address of the image kernel's + * entry point must be the same as its virtual address in the image + * kernel (restore_jump_address), so the image kernel's + * restore_registers() code doesn't find itself in a different area of + * the virtual address space after switching over to the original page + * tables used by the image kernel. + */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); + set_pud(pud + pud_index(restore_jump_address), + __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + __pgd(__pa(pud) | _KERNPG_TABLE)); + + return 0; +} static void *alloc_pgt_page(void *context) { @@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void) if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); + /* Prepare a temporary mapping for the kernel text */ + result = set_up_temporary_text_mapping(); + if (result) + return result; /* Set up the direct mapping from scratch */ for (i = 0; i < nr_pfn_mapped; i++) { @@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void) return 0; } +static int relocate_restore_code(void) +{ + pgd_t *pgd; + pud_t *pud; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pud = pud_offset(pgd, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + } else { + pmd_t *pmd = pmd_offset(pud, relocated_restore_code); + + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + } else { + pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); + + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); + } + } + __flush_tlb_all(); + + return 0; +} + int swsusp_arch_resume(void) { int error; /* We have got enough memory and from now on we cannot recover */ - if ((error = set_up_temporary_mappings())) + error = set_up_temporary_mappings(); + if (error) return error; - relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - memcpy(relocated_restore_code, &core_restore_code, - &restore_registers - &core_restore_code); + error = relocate_restore_code(); + if (error) + return error; restore_image(); return 0; @@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn) struct restore_data_record { unsigned long jump_address; + unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; }; -#define RESTORE_MAGIC 0x0123456789ABCDEFUL +#define RESTORE_MAGIC 0x123456789ABCDEF0UL /** * arch_hibernation_header_save - populate the architecture specific part @@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = restore_jump_address; + rdr->jump_address = (unsigned long)&restore_registers; + rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; return 0; @@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr) struct restore_data_record *rdr = addr; restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43b9e28..3177c2bc26f6 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend) pushfq popq pt_regs_flags(%rax) - /* save the address of restore_registers */ - movq $restore_registers, %rax - movq %rax, restore_jump_address(%rip) /* save cr3 */ movq %cr3, %rax movq %rax, restore_cr3(%rip) @@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend) ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) - /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rdx - movq temp_level4_pgt(%rip), %rax - subq %rdx, %rax - movq %rax, %cr3 - /* Flush TLB */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3; - movq %rax, %cr4; # turn PGE back on - /* prepare to jump to the image kernel */ - movq restore_jump_address(%rip), %rax - movq restore_cr3(%rip), %rbx + movq restore_jump_address(%rip), %r8 + movq restore_cr3(%rip), %r9 + + /* prepare to switch to temporary page tables */ + movq temp_level4_pgt(%rip), %rax + movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + + /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx /* code below has been relocated to a safe page */ ENTRY(core_restore_code) + /* switch to temporary page tables */ + movq $__PAGE_OFFSET, %rcx + subq %rcx, %rax + movq %rax, %cr3 + /* flush TLB */ + movq %rbx, %rcx + andq $~(X86_CR4_PGE), %rcx + movq %rcx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3; + movq %rbx, %cr4; # turn PGE back on .Lloop: testq %rdx, %rdx jz .Ldone @@ -96,24 +96,17 @@ ENTRY(core_restore_code) /* progress to the next pbe */ movq pbe_next(%rdx), %rdx jmp .Lloop + .Ldone: /* jump to the restore_registers address from the image header */ - jmpq *%rax - /* - * NOTE: This assumes that the boot kernel's text mapping covers the - * image kernel's page containing restore_registers and the address of - * this page is the same as in the image kernel's text mapping (it - * should always be true, because the text mapping is linear, starting - * from 0, and is supposed to cover the entire kernel text for every - * kernel). - * - * code below belongs to the image kernel - */ + jmpq *%r8 + /* code below belongs to the image kernel */ + .align PAGE_SIZE ENTRY(restore_registers) FRAME_BEGIN /* go back to the original page tables */ - movq %rbx, %cr3 + movq %r9, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 478a2de543a5..67433714b791 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr, /* NOTE: The loop is more greedy than the cleanup_highmap variant. * We include the PMD passed in on _both_ boundaries. */ - for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE)); + for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD)); pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; @@ -1551,41 +1551,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) #endif } -#ifdef CONFIG_X86_32 -static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) -{ - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); - - return pte; -} -#else /* CONFIG_X86_64 */ -static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) -{ - unsigned long pfn; - - if (xen_feature(XENFEAT_writable_page_tables) || - xen_feature(XENFEAT_auto_translated_physmap) || - xen_start_info->mfn_list >= __START_KERNEL_map) - return pte; - - /* - * Pages belonging to the initial p2m list mapped outside the default - * address range must be mapped read-only. This region contains the - * page tables for mapping the p2m list, too, and page tables MUST be - * mapped read-only. - */ - pfn = pte_pfn(pte); - if (pfn >= xen_start_info->first_p2m_pfn && - pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) - pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW); - - return pte; -} -#endif /* CONFIG_X86_64 */ - /* * Init-time set_pte while constructing initial pagetables, which * doesn't allow RO page table pages to be remapped RW. @@ -1600,13 +1565,37 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) * so always write the PTE directly and rely on Xen trapping and * emulating any updates as necessary. */ -static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +__visible pte_t xen_make_pte_init(pteval_t pte) { - if (pte_mfn(pte) != INVALID_P2M_ENTRY) - pte = mask_rw_pte(ptep, pte); - else - pte = __pte_ma(0); +#ifdef CONFIG_X86_64 + unsigned long pfn; + + /* + * Pages belonging to the initial p2m list mapped outside the default + * address range must be mapped read-only. This region contains the + * page tables for mapping the p2m list, too, and page tables MUST be + * mapped read-only. + */ + pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT; + if (xen_start_info->mfn_list < __START_KERNEL_map && + pfn >= xen_start_info->first_p2m_pfn && + pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) + pte &= ~_PAGE_RW; +#endif + pte = pte_pfn_to_mfn(pte); + return native_make_pte(pte); +} +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); +static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) +{ +#ifdef CONFIG_X86_32 + /* If there's an existing pte, then don't allow _PAGE_RW to be set */ + if (pte_mfn(pte) != INVALID_P2M_ENTRY + && pte_val_ma(*ptep) & _PAGE_PRESENT) + pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & + pte_val_ma(pte)); +#endif native_set_pte(ptep, pte); } @@ -2407,6 +2396,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif + pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte); #ifdef CONFIG_X86_64 pv_mmu_ops.write_cr3 = &xen_write_cr3; @@ -2455,7 +2445,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .pte_val = PV_CALLEE_SAVE(xen_pte_val), .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), - .make_pte = PV_CALLEE_SAVE(xen_make_pte), + .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), #ifdef CONFIG_X86_PAE diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index cab9f766bb06..dd2a49a8aacc 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -182,7 +182,7 @@ static void * __ref alloc_p2m_page(void) if (unlikely(!slab_is_available())) return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE); - return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); + return (void *)__get_free_page(GFP_KERNEL); } static void __ref free_p2m_page(void *p) |