diff options
Diffstat (limited to 'arch/x86')
42 files changed, 639 insertions, 360 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba2657c49217..8ec3a1aa4abd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1527,7 +1527,7 @@ config SECCOMP If unsure, say Y. Only embedded should say N here. config CC_STACKPROTECTOR - bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)" + bool "Enable -fstack-protector buffer overflow detection" ---help--- This option turns on the -fstack-protector GCC feature. This feature puts, at the beginning of functions, a canary value on diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b0c5276861ec..682e9c210baa 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -27,6 +27,10 @@ ifeq ($(CONFIG_X86_32),y) KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return + # Never want PIC in a 32-bit kernel, prevent breakage with GCC built + # with nonstandard options + KBUILD_CFLAGS += -fno-pic + # prevent gcc from keeping the stack 16 byte aligned KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 5a747dd884db..f7535bedc33f 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -57,7 +57,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/code16gcc.h \ - -fno-strict-aliasing -fomit-frame-pointer \ + -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ $(call cc-option, -ffreestanding) \ $(call cc-option, -fno-toplevel-reorder,\ $(call cc-option, -fno-unit-at-a-time)) \ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 441520e4174f..a3ac52b29cbf 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -33,6 +33,14 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ +#define MCACOD 0xffff /* MCA Error Code */ + +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ /* MCi_MISC register defines */ #define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index dab39350e51e..cb4e43bce98a 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -196,11 +196,16 @@ static inline u32 get_ibs_caps(void) { return 0; } extern void perf_events_lapic_init(void); /* - * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups. - * This flag is otherwise unused and ABI specified to be 0, so nobody should - * care what we do with it. + * Abuse bits {3,5} of the cpu eflags register. These flags are otherwise + * unused and ABI specified to be 0, so nobody should care what we do with + * them. + * + * EXACT - the IP points to the exact instruction that triggered the + * event (HW bugs exempt). + * VM - original X86_VM_MASK; see set_linear_ip(). */ #define PERF_EFLAGS_EXACT (1UL << 3) +#define PERF_EFLAGS_VM (1UL << 5) struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index b315a33867f2..33692eaabab5 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -12,8 +12,7 @@ * Simple spin lock operations. There are two variants, one clears IRQ's * on the local processor, one does not. * - * These are fair FIFO ticket locks, which are currently limited to 256 - * CPUs. + * These are fair FIFO ticket locks, which support up to 2^16 CPUs. * * (the type definitions are in asm/spinlock_types.h) */ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 95bf99de9058..1b8e5a03d942 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -25,10 +25,6 @@ unsigned long acpi_realmode_flags; static char temp_stack[4096]; #endif -asmlinkage void acpi_enter_s3(void) -{ - acpi_enter_sleep_state(3, wake_sleep_flags); -} /** * acpi_suspend_lowlevel - save kernel state * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index 5653a5791ec9..67f59f8c6956 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -2,7 +2,6 @@ * Variables and functions used by the code in sleep.c */ -#include <linux/linkage.h> #include <asm/realmode.h> extern unsigned long saved_video_mode; @@ -11,7 +10,6 @@ extern long saved_magic; extern int wakeup_pmode_return; extern u8 wake_sleep_flags; -extern asmlinkage void acpi_enter_s3(void); extern unsigned long acpi_copy_wakeup_routine(unsigned long); extern void wakeup_long64(void); diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 72610839f03b..13ab720573e3 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -74,7 +74,9 @@ restore_registers: ENTRY(do_suspend_lowlevel) call save_processor_state call save_registers - call acpi_enter_s3 + pushl $3 + call acpi_enter_sleep_state + addl $4, %esp # In case of S3 failure, we'll emerge here. Jump # to ret_point to recover diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 014d1d28c397..8ea5164cbd04 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -71,7 +71,9 @@ ENTRY(do_suspend_lowlevel) movq %rsi, saved_rsi addq $8, %rsp - call acpi_enter_s3 + movl $3, %edi + xorl %eax, %eax + call acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ jmp resume_point diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 931280ff8299..ced4534baed5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -165,7 +165,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] = #endif #ifdef P6_NOP1 -static const unsigned char __initconst_or_module p6nops[] = +static const unsigned char p6nops[] = { P6_NOP1, P6_NOP2, @@ -224,7 +224,7 @@ void __init arch_init_ideal_nops(void) ideal_nops = intel_nops; #endif } - + break; default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 406eee784684..c265593ec2cd 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1204,7 +1204,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) BUG_ON(!cfg->vector); vector = cfg->vector; - for_each_cpu(cpu, cfg->domain) + for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) per_cpu(vector_irq, cpu)[vector] = -1; cfg->vector = 0; @@ -1212,7 +1212,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg) if (likely(!cfg->move_in_progress)) return; - for_each_cpu(cpu, cfg->old_domain) { + for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { if (per_cpu(vector_irq, cpu)[vector] != irq) @@ -1356,6 +1356,16 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, if (!IO_APIC_IRQ(irq)) return; + /* + * For legacy irqs, cfg->domain starts with cpu 0. Now that IO-APIC + * can handle this irq and the apic driver is finialized at this point, + * update the cfg->domain. + */ + if (irq < legacy_pic->nr_legacy_irqs && + cpumask_equal(cfg->domain, cpumask_of(0))) + apic->vector_allocation_domain(0, cfg->domain, + apic->target_cpus()); + if (assign_irq_vector(irq, cfg, apic->target_cpus())) return; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 46d8786d655e..a5fbc3c5fccc 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ static int __init x86_xsave_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); return 1; } __setup("noxsave", x86_xsave_setup); diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 413c2ced887c..13017626f9a8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -55,13 +55,6 @@ static struct severity { #define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) #define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) #define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) -#define MCACOD 0xffff -/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ -#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 -#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ -#define MCACOD_DATA 0x0134 /* Data Load */ -#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ MCESEV( NO, "Invalid", diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5e095f873e3e..292d0258311c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -103,6 +103,8 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { static DEFINE_PER_CPU(struct work_struct, mce_work); +static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); + /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. @@ -650,14 +652,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll); * Do a quick check if any of the events requires a panic. * This decides if we keep the events around or clear them. */ -static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp) +static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, + struct pt_regs *regs) { int i, ret = 0; for (i = 0; i < banks; i++) { m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); - if (m->status & MCI_STATUS_VAL) + if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); + if (quirk_no_way_out) + quirk_no_way_out(i, m, regs); + } if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY) ret = 1; } @@ -1040,7 +1046,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) *final = m; memset(valid_banks, 0, sizeof(valid_banks)); - no_way_out = mce_no_way_out(&m, &msg, valid_banks); + no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs); barrier(); @@ -1418,6 +1424,34 @@ static void __mcheck_cpu_init_generic(void) } } +/* + * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and + * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM + * Vol 3B Table 15-20). But this confuses both the code that determines + * whether the machine check occurred in kernel or user mode, and also + * the severity assessment code. Pretend that EIPV was set, and take the + * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. + */ +static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 0) + return; + if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0) + return; + if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC| + MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV| + MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR| + MCACOD)) != + (MCI_STATUS_UC|MCI_STATUS_EN| + MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S| + MCI_STATUS_AR|MCACOD_INSTR)) + return; + + m->mcgstatus |= MCG_STATUS_EIPV; + m->ip = regs->ip; + m->cs = regs->cs; +} + /* Add per CPU specific workarounds here */ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) { @@ -1515,6 +1549,9 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) mce_bootlog = 0; + + if (c->x86 == 6 && c->x86_model == 45) + quirk_no_way_out = quirk_sandybridge_ifu; } if (monarch_timeout < 0) monarch_timeout = 0; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 29557aa06dda..915b876edd1e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -32,6 +32,8 @@ #include <asm/smp.h> #include <asm/alternative.h> #include <asm/timer.h> +#include <asm/desc.h> +#include <asm/ldt.h> #include "perf_event.h" @@ -1738,6 +1740,29 @@ valid_user_frame(const void __user *fp, unsigned long size) return (__range_not_ok(fp, size, TASK_SIZE) == 0); } +static unsigned long get_segment_base(unsigned int segment) +{ + struct desc_struct *desc; + int idx = segment >> 3; + + if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { + if (idx > LDT_ENTRIES) + return 0; + + if (idx > current->active_mm->context.size) + return 0; + + desc = current->active_mm->context.ldt; + } else { + if (idx > GDT_ENTRIES) + return 0; + + desc = __this_cpu_ptr(&gdt_page.gdt[0]); + } + + return get_desc_base(desc + idx); +} + #ifdef CONFIG_COMPAT #include <asm/compat.h> @@ -1746,13 +1771,17 @@ static inline int perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) { /* 32-bit process in 64-bit kernel. */ + unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const void __user *fp; if (!test_thread_flag(TIF_IA32)) return 0; - fp = compat_ptr(regs->bp); + cs_base = get_segment_base(regs->cs); + ss_base = get_segment_base(regs->ss); + + fp = compat_ptr(ss_base + regs->bp); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; @@ -1765,8 +1794,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) if (!valid_user_frame(fp, sizeof(frame))) break; - perf_callchain_store(entry, frame.return_address); - fp = compat_ptr(frame.next_frame); + perf_callchain_store(entry, cs_base + frame.return_address); + fp = compat_ptr(ss_base + frame.next_frame); } return 1; } @@ -1789,6 +1818,12 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; } + /* + * We don't know what to do with VM86 stacks.. ignore them for now. + */ + if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) + return; + fp = (void __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -1816,16 +1851,50 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) } } -unsigned long perf_instruction_pointer(struct pt_regs *regs) +/* + * Deal with code segment offsets for the various execution modes: + * + * VM86 - the good olde 16 bit days, where the linear address is + * 20 bits and we use regs->ip + 0x10 * regs->cs. + * + * IA32 - Where we need to look at GDT/LDT segment descriptor tables + * to figure out what the 32bit base address is. + * + * X32 - has TIF_X32 set, but is running in x86_64 + * + * X86_64 - CS,DS,SS,ES are all zero based. + */ +static unsigned long code_segment_base(struct pt_regs *regs) { - unsigned long ip; + /* + * If we are in VM86 mode, add the segment offset to convert to a + * linear address. + */ + if (regs->flags & X86_VM_MASK) + return 0x10 * regs->cs; + + /* + * For IA32 we look at the GDT/LDT segment base to convert the + * effective IP to a linear address. + */ +#ifdef CONFIG_X86_32 + if (user_mode(regs) && regs->cs != __USER_CS) + return get_segment_base(regs->cs); +#else + if (test_thread_flag(TIF_IA32)) { + if (user_mode(regs) && regs->cs != __USER32_CS) + return get_segment_base(regs->cs); + } +#endif + return 0; +} +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - ip = perf_guest_cbs->get_guest_ip(); - else - ip = instruction_pointer(regs); + return perf_guest_cbs->get_guest_ip(); - return ip; + return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) @@ -1838,7 +1907,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs) else misc |= PERF_RECORD_MISC_GUEST_KERNEL; } else { - if (!kernel_ip(regs->ip)) + if (user_mode(regs)) misc |= PERF_RECORD_MISC_USER; else misc |= PERF_RECORD_MISC_KERNEL; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 821d53b696d1..6605a81ba339 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -516,6 +516,26 @@ static inline bool kernel_ip(unsigned long ip) #endif } +/* + * Not all PMUs provide the right context information to place the reported IP + * into full context. Specifically segment registers are typically not + * supplied. + * + * Assuming the address is a linear address (it is for IBS), we fake the CS and + * vm86 mode using the known zero-based code segment and 'fix up' the registers + * to reflect this. + * + * Intel PEBS/LBR appear to typically provide the effective address, nothing + * much we can do about that but pray and treat it like a linear address. + */ +static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) +{ + regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS; + if (regs->flags & X86_VM_MASK) + regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK); + regs->ip = ip; +} + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index da9bcdcd9856..7bfb5bec8630 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -13,6 +13,8 @@ #include <asm/apic.h> +#include "perf_event.h" + static u32 ibs_caps; #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) @@ -536,7 +538,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) { regs.flags &= ~PERF_EFLAGS_EXACT; } else { - instruction_pointer_set(®s, ibs_data.regs[1]); + set_linear_ip(®s, ibs_data.regs[1]); regs.flags |= PERF_EFLAGS_EXACT; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 382366977d4c..7f2739e03e79 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1522,8 +1522,16 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL; arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask; arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask; + /* + * If PMU counter has PEBS enabled it is not enough to disable counter + * on a guest entry since PEBS memory write can overshoot guest entry + * and corrupt guest memory. Disabling PEBS solves the problem. + */ + arr[1].msr = MSR_IA32_PEBS_ENABLE; + arr[1].host = cpuc->pebs_enabled; + arr[1].guest = 0; - *nr = 1; + *nr = 2; return arr; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 629ae0b7ad90..e38d97bf4259 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -499,7 +499,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) * We sampled a branch insn, rewind using the LBR stack */ if (ip == to) { - regs->ip = from; + set_linear_ip(regs, from); return 1; } @@ -529,7 +529,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) } while (to < ip); if (to == ip) { - regs->ip = old_to; + set_linear_ip(regs, old_to); return 1; } @@ -569,7 +569,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ regs = *iregs; - regs.ip = pebs->ip; + regs.flags = pebs->flags; + set_linear_ip(®s, pebs->ip); regs.bp = pebs->bp; regs.sp = pebs->sp; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 7563fda9f033..0a5571080e74 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -796,7 +796,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = { DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); -DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63"); DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); @@ -902,16 +901,21 @@ static struct attribute_group nhmex_uncore_cbox_format_group = { .attrs = nhmex_uncore_cbox_formats_attr, }; +/* msr offset for each instance of cbox */ +static unsigned nhmex_cbox_msr_offsets[] = { + 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, +}; + static struct intel_uncore_type nhmex_uncore_cbox = { .name = "cbox", .num_counters = 6, - .num_boxes = 8, + .num_boxes = 10, .perf_ctr_bits = 48, .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, .event_mask = NHMEX_PMON_RAW_EVENT_MASK, .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_C_MSR_OFFSET, + .msr_offsets = nhmex_cbox_msr_offsets, .pair_ctr_ctl = 1, .ops = &nhmex_uncore_ops, .format_group = &nhmex_uncore_cbox_format_group @@ -1032,24 +1036,22 @@ static struct intel_uncore_type nhmex_uncore_bbox = { static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) { - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) { - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - } else { - reg1->config = ~0ULL; - reg2->config = ~0ULL; - } + /* only TO_R_PROG_EV event uses the match/mask register */ + if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != + NHMEX_S_EVENT_TO_R_PROG_EV) + return 0; if (box->pmu->pmu_idx == 0) reg1->reg = NHMEX_S0_MSR_MM_CFG; else reg1->reg = NHMEX_S1_MSR_MM_CFG; - reg1->idx = 0; - + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; return 0; } @@ -1059,8 +1061,8 @@ static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct per struct hw_perf_event_extra *reg1 = &hwc->extra_reg; struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - wrmsrl(reg1->reg, 0); - if (reg1->config != ~0ULL || reg2->config != ~0ULL) { + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, 0); wrmsrl(reg1->reg + 1, reg1->config); wrmsrl(reg1->reg + 2, reg2->config); wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); @@ -1074,7 +1076,6 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = { &format_attr_edge.attr, &format_attr_inv.attr, &format_attr_thresh8.attr, - &format_attr_mm_cfg.attr, &format_attr_match.attr, &format_attr_mask.attr, NULL, @@ -1142,6 +1143,9 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { EVENT_EXTRA_END }; +/* Nehalem-EX or Westmere-EX ? */ +bool uncore_nhmex; + static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) { struct intel_uncore_extra_reg *er; @@ -1171,18 +1175,29 @@ static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 return false; /* mask of the shared fields */ - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; raw_spin_lock_irqsave(&er->lock, flags); /* add mask of the non-shared field if it's in use */ - if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) - mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { + if (uncore_nhmex) + mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + } if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { atomic_add(1 << (idx * 8), &er->ref); - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | - NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | + NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | + WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); er->config &= ~mask; er->config |= (config & mask); ret = true; @@ -1216,7 +1231,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) /* get the non-shared control bits and shift them */ idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (uncore_nhmex) + config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); if (new_idx > orig_idx) { idx = new_idx - orig_idx; config <<= 3 * idx; @@ -1226,6 +1244,10 @@ u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) } /* add the shared control bits back */ + if (uncore_nhmex) + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + else + config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; if (modify) { /* adjust the main event selector */ @@ -1264,7 +1286,8 @@ again: } /* for the match/mask registers */ - if ((uncore_box_is_fake(box) || !reg2->alloc) && + if (reg2->idx != EXTRA_REG_NONE && + (uncore_box_is_fake(box) || !reg2->alloc) && !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) goto fail; @@ -1278,7 +1301,8 @@ again: if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) nhmex_mbox_alter_er(event, idx[0], true); reg1->alloc |= alloc; - reg2->alloc = 1; + if (reg2->idx != EXTRA_REG_NONE) + reg2->alloc = 1; } return NULL; fail: @@ -1342,9 +1366,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event struct extra_reg *er; unsigned msr; int reg_idx = 0; - - if (WARN_ON_ONCE(reg1->idx != -1)) - return -EINVAL; /* * The mbox events may require 2 extra MSRs at the most. But only * the lower 32 bits in these MSRs are significant, so we can use @@ -1355,11 +1376,6 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; - if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) || - er->idx == __BITS_VALUE(reg1->idx, 1, 8)) - continue; - if (WARN_ON_ONCE(reg_idx >= 2)) - return -EINVAL; msr = er->msr + type->msr_offset * box->pmu->pmu_idx; if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) @@ -1368,6 +1384,8 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event /* always use the 32~63 bits to pass the PLD config */ if (er->idx == EXTRA_REG_NHMEX_M_PLD) reg_idx = 1; + else if (WARN_ON_ONCE(reg_idx > 0)) + return -EINVAL; reg1->idx &= ~(0xff << (reg_idx * 8)); reg1->reg &= ~(0xffff << (reg_idx * 16)); @@ -1376,17 +1394,21 @@ static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event reg1->config = event->attr.config1; reg_idx++; } - /* use config2 to pass the filter config */ - reg2->idx = EXTRA_REG_NHMEX_M_FILTER; - if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) - reg2->config = event->attr.config2; - else - reg2->config = ~0ULL; - if (box->pmu->pmu_idx == 0) - reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; - else - reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; - + /* + * The mbox only provides ability to perform address matching + * for the PLD events. + */ + if (reg_idx == 2) { + reg2->idx = EXTRA_REG_NHMEX_M_FILTER; + if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) + reg2->config = event->attr.config2; + else + reg2->config = ~0ULL; + if (box->pmu->pmu_idx == 0) + reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; + else + reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; + } return 0; } @@ -1422,34 +1444,36 @@ static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct per wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), nhmex_mbox_shared_reg_config(box, idx)); - wrmsrl(reg2->reg, 0); - if (reg2->config != ~0ULL) { - wrmsrl(reg2->reg + 1, - reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); - wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & - (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); - wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + if (reg2->idx != EXTRA_REG_NONE) { + wrmsrl(reg2->reg, 0); + if (reg2->config != ~0ULL) { + wrmsrl(reg2->reg + 1, + reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); + wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & + (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); + wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + } } wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); } -DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); -DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); -DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); -DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); -DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); -DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); -DEFINE_UNCORE_FORMAT_ATTR(filter_cfg, filter_cfg, "config2:63"); -DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); -DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); -DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); +DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); +DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); +DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); +DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); +DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); +DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); static struct attribute *nhmex_uncore_mbox_formats_attr[] = { &format_attr_count_mode.attr, @@ -1458,7 +1482,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = { &format_attr_flag_mode.attr, &format_attr_inc_sel.attr, &format_attr_set_flag_sel.attr, - &format_attr_filter_cfg.attr, + &format_attr_filter_cfg_en.attr, &format_attr_filter_match.attr, &format_attr_filter_mask.attr, &format_attr_dsp.attr, @@ -1482,6 +1506,12 @@ static struct uncore_event_desc nhmex_uncore_mbox_events[] = { { /* end: all zeroes */ }, }; +static struct uncore_event_desc wsmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), + { /* end: all zeroes */ }, +}; + static struct intel_uncore_ops nhmex_uncore_mbox_ops = { NHMEX_UNCORE_OPS_COMMON_INIT(), .enable_event = nhmex_mbox_msr_enable_event, @@ -1513,7 +1543,7 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) struct hw_perf_event_extra *reg1 = &hwc->extra_reg; int port; - /* adjust the main event selector */ + /* adjust the main event selector and extra register index */ if (reg1->idx % 2) { reg1->idx--; hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; @@ -1522,29 +1552,17 @@ void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; } - /* adjust address or config of extra register */ + /* adjust extra register config */ port = reg1->idx / 6 + box->pmu->pmu_idx * 4; switch (reg1->idx % 6) { - case 0: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port); - break; - case 1: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port); - break; case 2: - /* the 8~15 bits to the 0~7 bits */ + /* shift the 8~15 bits to the 0~7 bits */ reg1->config >>= 8; break; case 3: - /* the 0~7 bits to the 8~15 bits */ + /* shift the 0~7 bits to the 8~15 bits */ reg1->config <<= 8; break; - case 4: - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port); - break; - case 5: - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port); - break; }; } @@ -1671,7 +1689,7 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int port, idx; + int idx; idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> NHMEX_R_PMON_CTL_EV_SEL_SHIFT; @@ -1681,27 +1699,11 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event reg1->idx = idx; reg1->config = event->attr.config1; - port = idx / 6 + box->pmu->pmu_idx * 4; - idx %= 6; - switch (idx) { - case 0: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port); - break; - case 1: - reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port); - break; - case 2: - case 3: - reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port); - break; + switch (idx % 6) { case 4: case 5: - if (idx == 4) - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port); - else - reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port); - reg2->config = event->attr.config2; hwc->config |= event->attr.config & (~0ULL << 32); + reg2->config = event->attr.config2; break; }; return 0; @@ -1727,28 +1729,34 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx, er_idx; + int idx, port; - idx = reg1->idx % 6; - er_idx = idx; - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; + idx = reg1->idx; + port = idx / 6 + box->pmu->pmu_idx * 4; - switch (idx) { + switch (idx % 6) { case 0: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); + break; case 1: - wrmsrl(reg1->reg, reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); break; case 2: case 3: - wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx)); + wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), + nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5)); break; case 4: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); + break; case 5: - wrmsrl(reg1->reg, reg1->config); - wrmsrl(reg1->reg + 1, hwc->config >> 32); - wrmsrl(reg1->reg + 2, reg2->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); break; }; @@ -1756,8 +1764,8 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); } -DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); @@ -2303,6 +2311,7 @@ int uncore_pmu_event_init(struct perf_event *event) event->hw.idx = -1; event->hw.last_tag = ~0ULL; event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; if (event->attr.config == UNCORE_FIXED_EVENT) { /* no fixed counter */ @@ -2373,7 +2382,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) type->attr_groups[1] = NULL; } -static void uncore_types_exit(struct intel_uncore_type **types) +static void __init uncore_types_exit(struct intel_uncore_type **types) { int i; for (i = 0; types[i]; i++) @@ -2814,7 +2823,13 @@ static int __init uncore_cpu_init(void) snbep_uncore_cbox.num_boxes = max_cores; msr_uncores = snbep_msr_uncores; break; - case 46: + case 46: /* Nehalem-EX */ + uncore_nhmex = true; + case 47: /* Westmere-EX aka. Xeon E7 */ + if (!uncore_nhmex) + nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; + if (nhmex_uncore_cbox.num_boxes > max_cores) + nhmex_uncore_cbox.num_boxes = max_cores; msr_uncores = nhmex_msr_uncores; break; default: diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index f3851892e077..5b81c1856aac 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -5,7 +5,7 @@ #include "perf_event.h" #define UNCORE_PMU_NAME_LEN 32 -#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC) +#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) #define UNCORE_FIXED_EVENT 0xff #define UNCORE_PMC_IDX_MAX_GENERIC 8 @@ -230,6 +230,7 @@ #define NHMEX_S1_MSR_MASK 0xe5a #define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) +#define NHMEX_S_EVENT_TO_R_PROG_EV 0 /* NHM-EX Mbox */ #define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 @@ -275,18 +276,12 @@ NHMEX_M_PMON_CTL_INC_SEL_MASK | \ NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) - -#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK 0x1f -#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK (0x7 << 5) -#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK (0x7 << 8) -#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR (1 << 23) -#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK \ - (NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK | \ - NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK | \ - NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK | \ - NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR) +#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) #define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (11 + 3 * (n))) +#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) +#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (12 + 3 * (n))) + /* * use the 9~13 bits to select event If the 7th bit is not set, * otherwise use the 19~21 bits to select event. @@ -368,6 +363,7 @@ struct intel_uncore_type { unsigned num_shared_regs:8; unsigned single_fixed:1; unsigned pair_ctr_ctl:1; + unsigned *msr_offsets; struct event_constraint unconstrainted; struct event_constraint *constraints; struct intel_uncore_pmu *pmus; @@ -485,29 +481,31 @@ unsigned uncore_pci_perf_ctr(struct intel_uncore_box *box, int idx) return idx * 8 + box->pmu->type->perf_ctr; } -static inline -unsigned uncore_msr_box_ctl(struct intel_uncore_box *box) +static inline unsigned uncore_msr_box_offset(struct intel_uncore_box *box) +{ + struct intel_uncore_pmu *pmu = box->pmu; + return pmu->type->msr_offsets ? + pmu->type->msr_offsets[pmu->pmu_idx] : + pmu->type->msr_offset * pmu->pmu_idx; +} + +static inline unsigned uncore_msr_box_ctl(struct intel_uncore_box *box) { if (!box->pmu->type->box_ctl) return 0; - return box->pmu->type->box_ctl + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + return box->pmu->type->box_ctl + uncore_msr_box_offset(box); } -static inline -unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box) +static inline unsigned uncore_msr_fixed_ctl(struct intel_uncore_box *box) { if (!box->pmu->type->fixed_ctl) return 0; - return box->pmu->type->fixed_ctl + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + return box->pmu->type->fixed_ctl + uncore_msr_box_offset(box); } -static inline -unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) +static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box) { - return box->pmu->type->fixed_ctr + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box); } static inline @@ -515,7 +513,7 @@ unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx) { return box->pmu->type->event_ctl + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + uncore_msr_box_offset(box); } static inline @@ -523,7 +521,7 @@ unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx) { return box->pmu->type->perf_ctr + (box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) + - box->pmu->type->msr_offset * box->pmu->pmu_idx; + uncore_msr_box_offset(box); } static inline diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 1f5f1d5d2a02..d44f7829968e 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -270,7 +270,7 @@ void fixup_irqs(void) if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; - affinity = cpu_all_mask; + affinity = cpu_online_mask; } chip = irq_data_get_irq_chip(data); @@ -328,6 +328,7 @@ void fixup_irqs(void) chip->irq_retrigger(data); raw_spin_unlock(&desc->lock); } + __this_cpu_write(vector_irq[vector], -1); } } #endif diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 1d5d31ea686b..dc1404bf8e4b 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -107,7 +107,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) { struct setup_data_node *node; struct setup_data *data; - int error = -ENOMEM; + int error; struct dentry *d; struct page *pg; u64 pa_data; @@ -121,8 +121,10 @@ static int __init create_setup_data_nodes(struct dentry *parent) while (pa_data) { node = kmalloc(sizeof(*node), GFP_KERNEL); - if (!node) + if (!node) { + error = -ENOMEM; goto err_dir; + } pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT); if (PageHighMem(pg)) { diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 8a2ce8fd41c0..82746f942cd8 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -143,11 +143,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr, unsigned int *current_size) { struct microcode_header_amd *mc_hdr; - unsigned int actual_size; + unsigned int actual_size, patch_size; u16 equiv_cpu_id; /* size of the current patch we're staring at */ - *current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE; + patch_size = *(u32 *)(ucode_ptr + 4); + *current_size = patch_size + SECTION_HDR_SIZE; equiv_cpu_id = find_equiv_id(); if (!equiv_cpu_id) @@ -174,7 +175,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr, /* * now that the header looks sane, verify its size */ - actual_size = verify_ucode_size(cpu, *current_size, leftover_size); + actual_size = verify_ucode_size(cpu, patch_size, leftover_size); if (!actual_size) return 0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 97d9a9914ba8..a3b57a27be88 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg) return address_mask(ctxt, reg); } +static void masked_increment(ulong *reg, ulong mask, int inc) +{ + assign_masked(reg, *reg + inc, mask); +} + static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc) { + ulong mask; + if (ctxt->ad_bytes == sizeof(unsigned long)) - *reg += inc; + mask = ~0UL; else - *reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt)); + mask = ad_mask(ctxt); + masked_increment(reg, mask, inc); +} + +static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) +{ + masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc); } static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes); - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + rsp_increment(ctxt, -bytes); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; return segmented_write(ctxt, addr, data, bytes); @@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, int rc; struct segmented_address addr; - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; rc = segmented_read(ctxt, addr, dest, len); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len); + rsp_increment(ctxt, len); return rc; } @@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], - ctxt->op_bytes); + rsp_increment(ctxt, ctxt->op_bytes); --reg; } @@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val); + rsp_increment(ctxt, ctxt->src.val); return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 1df8fb9e1d5d..9fc9aa7ac703 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -316,6 +316,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) addr &= 1; if (addr == 0) { if (val & 0x10) { + u8 edge_irr = s->irr & ~s->elcr; + int i; + bool found = false; + struct kvm_vcpu *vcpu; + s->init4 = val & 1; s->last_irr = 0; s->irr &= s->elcr; @@ -333,6 +338,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) if (val & 0x08) pr_pic_unimpl( "level sensitive irq not supported"); + + kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm) + if (kvm_apic_accept_pic_intr(vcpu)) { + found = true; + break; + } + + + if (found) + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (edge_irr & (1 << irq)) + pic_clear_isr(s, irq); } else if (val & 0x08) { if (val & 0x04) s->poll = 1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 01ca00423938..7fbd0d273ea8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4113,16 +4113,21 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) LIST_HEAD(invalid_list); /* + * Never scan more than sc->nr_to_scan VM instances. + * Will not hit this condition practically since we do not try + * to shrink more than one VM and it is very unlikely to see + * !n_used_mmu_pages so many times. + */ + if (!nr_to_scan--) + break; + /* * n_used_mmu_pages is accessed without holding kvm->mmu_lock * here. We may skip a VM instance errorneosly, but we do not * want to shrink a VM that only started to populate its MMU * anyway. */ - if (kvm->arch.n_used_mmu_pages > 0) { - if (!nr_to_scan--) - break; + if (!kvm->arch.n_used_mmu_pages) continue; - } idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c39b60707e02..b1eb202ee76a 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1488,13 +1488,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) loadsegment(ds, vmx->host_state.ds_sel); loadsegment(es, vmx->host_state.es_sel); } -#else - /* - * The sysexit path does not restore ds/es, so we must set them to - * a reasonable value ourselves. - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); #endif reload_tss(); #ifdef CONFIG_X86_64 @@ -3626,6 +3619,7 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { + struct page *page; struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; @@ -3640,7 +3634,13 @@ static int alloc_apic_access_page(struct kvm *kvm) if (r) goto out; - kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00); + page = gfn_to_page(kvm, 0xfee00); + if (is_error_page(page)) { + r = -EFAULT; + goto out; + } + + kvm->arch.apic_access_page = page; out: mutex_unlock(&kvm->slots_lock); return r; @@ -3648,6 +3648,7 @@ out: static int alloc_identity_pagetable(struct kvm *kvm) { + struct page *page; struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; @@ -3663,8 +3664,13 @@ static int alloc_identity_pagetable(struct kvm *kvm) if (r) goto out; - kvm->arch.ept_identity_pagetable = gfn_to_page(kvm, - kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); + page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT); + if (is_error_page(page)) { + r = -EFAULT; + goto out; + } + + kvm->arch.ept_identity_pagetable = page; out: mutex_unlock(&kvm->slots_lock); return r; @@ -6370,6 +6376,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); +#ifndef CONFIG_X86_64 + /* + * The sysexit path does not restore ds/es, so we must set them to + * a reasonable value ourselves. + * + * We can't defer this to vmx_load_host_state() since that function + * may be executed in interrupt context, which saves and restore segments + * around it, nullifying its effect. + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) | (1 << VCPU_EXREG_CPL) @@ -6569,7 +6588,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) /* Exposing INVPCID only when PCID is exposed */ best = kvm_find_cpuid_entry(vcpu, 0x7, 0); if (vmx_invpcid_supported() && - best && (best->ecx & bit(X86_FEATURE_INVPCID)) && + best && (best->ebx & bit(X86_FEATURE_INVPCID)) && guest_cpuid_has_pcid(vcpu)) { exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, @@ -6579,7 +6598,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); if (best) - best->ecx &= ~bit(X86_FEATURE_INVPCID); + best->ebx &= ~bit(X86_FEATURE_INVPCID); } } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 59b59508ff07..2966c847d489 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 9 +#define KVM_SAVE_MSRS_BEGIN 10 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, @@ -925,6 +925,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) */ getboottime(&boot); + if (kvm->arch.kvmclock_offset) { + struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset); + boot = timespec_sub(boot, ts); + } wc.sec = boot.tv_sec; wc.nsec = boot.tv_nsec; wc.version = version; @@ -1996,6 +2000,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_KVM_STEAL_TIME: data = vcpu->arch.st.msr_val; break; + case MSR_KVM_PV_EOI_EN: + data = vcpu->arch.pv_eoi.msr_val; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: @@ -5106,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) !kvm_event_needs_reinjection(vcpu); } -static void vapic_enter(struct kvm_vcpu *vcpu) +static int vapic_enter(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct page *page; if (!apic || !apic->vapic_addr) - return; + return 0; page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); + if (is_error_page(page)) + return -EFAULT; vcpu->arch.apic->vapic_page = page; + return 0; } static void vapic_exit(struct kvm_vcpu *vcpu) @@ -5423,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - vapic_enter(vcpu); + r = vapic_enter(vcpu); + if (r) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + return r; + } r = 1; while (r > 0) { diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index f6679a7fb8ca..b91e48512425 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) } /* - * search for a shareable pmd page for hugetlb. + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. */ -static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +static pte_t * +huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; @@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; + pte_t *pte; if (!vma_shareable(vma, addr)) - return; + return (pte_t *)pmd_alloc(mm, pud, addr); mutex_lock(&mapping->i_mmap_mutex); vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) { @@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) put_page(virt_to_page(spte)); spin_unlock(&mm->page_table_lock); out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); mutex_unlock(&mapping->i_mmap_mutex); + return pte; } /* @@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, } else { BUG_ON(sz != PMD_SIZE); if (pud_none(*pud)) - huge_pmd_share(mm, addr, pud); - pte = (pte_t *) pmd_alloc(mm, pud, addr); + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); } } BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 931930a96160..a718e0d23503 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, /* * On success we use clflush, when the CPU supports it to - * avoid the wbindv. If the CPU does not support it, in the - * error case, and during early boot (for EFI) we fall back - * to cpa_flush_all (which uses wbinvd): + * avoid the wbindv. If the CPU does not support it and in the + * error case we fall back to cpa_flush_all (which uses + * wbindv): */ - if (early_boot_irqs_disabled) - __cpa_flush_all((void *)(long)cache); - else if (!ret && cpu_has_clflush) { + if (!ret && cpu_has_clflush) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { cpa_flush_array(addr, numpages, cache, cpa.flags, pages); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 4599c3e8bcb6..4ddf497ca65b 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -142,23 +142,23 @@ static inline int save_add_info(void) {return 0;} #endif /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ -void __init +int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { u64 start, end; int node, pxm; if (srat_disabled()) - return; + return -1; if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) { bad_srat(); - return; + return -1; } if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) - return; + return -1; if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) - return; + return -1; start = ma->base_address; end = start + ma->length; pxm = ma->proximity_domain; @@ -168,12 +168,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) if (node < 0) { printk(KERN_ERR "SRAT: Too many proximity domains.\n"); bad_srat(); - return; + return -1; } if (numa_add_memblk(node, start, end) < 0) { bad_srat(); - return; + return -1; } node_set(node, numa_nodes_parsed); @@ -181,6 +181,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1); + return 0; } void __init acpi_numa_arch_fixup(void) {} diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 2dc29f51e75a..92660edaa1e7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -234,7 +234,22 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -static int efi_set_rtc_mmss(unsigned long nowtime) +static efi_status_t __init phys_efi_get_time(efi_time_t *tm, + efi_time_cap_t *tc) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + efi_call_phys_prelog(); + status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm), + virt_to_phys(tc)); + efi_call_phys_epilog(); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +int efi_set_rtc_mmss(unsigned long nowtime) { int real_seconds, real_minutes; efi_status_t status; @@ -263,7 +278,7 @@ static int efi_set_rtc_mmss(unsigned long nowtime) return 0; } -static unsigned long efi_get_time(void) +unsigned long efi_get_time(void) { efi_status_t status; efi_time_t eft; @@ -606,13 +621,18 @@ static int __init efi_runtime_init(void) } /* * We will only need *early* access to the following - * EFI runtime service before set_virtual_address_map + * two EFI runtime services before set_virtual_address_map * is invoked. */ + efi_phys.get_time = (efi_get_time_t *)runtime->get_time; efi_phys.set_virtual_address_map = (efi_set_virtual_address_map_t *) runtime->set_virtual_address_map; - + /* + * Make efi_get_time can be called before entering + * virtual mode. + */ + efi.get_time = phys_efi_get_time; early_iounmap(runtime, sizeof(efi_runtime_services_t)); return 0; @@ -700,10 +720,12 @@ void __init efi_init(void) efi_enabled = 0; return; } +#ifdef CONFIG_X86_32 if (efi_native) { x86_platform.get_wallclock = efi_get_time; x86_platform.set_wallclock = efi_set_rtc_mmss; } +#endif #if EFI_DEBUG print_efi_memmap(); diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index b2d534cab25f..88692871823f 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -72,7 +72,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/../../boot/code16gcc.h \ - -fno-strict-aliasing -fomit-frame-pointer \ + -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ $(call cc-option, -ffreestanding) \ $(call cc-option, -fno-toplevel-reorder,\ $(call cc-option, -fno-unit-at-a-time)) \ diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 51171aeff0dc..a582bfed95bb 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -60,8 +60,8 @@ 51 common getsockname sys_getsockname 52 common getpeername sys_getpeername 53 common socketpair sys_socketpair -54 common setsockopt sys_setsockopt -55 common getsockopt sys_getsockopt +54 64 setsockopt sys_setsockopt +55 64 getsockopt sys_getsockopt 56 common clone stub_clone 57 common fork stub_fork 58 common vfork stub_vfork @@ -318,7 +318,7 @@ 309 common getcpu sys_getcpu 310 64 process_vm_readv sys_process_vm_readv 311 64 process_vm_writev sys_process_vm_writev -312 64 kcmp sys_kcmp +312 common kcmp sys_kcmp # # x32-specific system call numbers start at 512 to avoid cache impact @@ -353,3 +353,5 @@ 538 x32 sendmmsg compat_sys_sendmmsg 539 x32 process_vm_readv compat_sys_process_vm_readv 540 x32 process_vm_writev compat_sys_process_vm_writev +541 x32 setsockopt compat_sys_setsockopt +542 x32 getsockopt compat_sys_getsockopt diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bf4bda6d3e9a..9642d4a38602 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,7 +31,6 @@ #include <linux/pci.h> #include <linux/gfp.h> #include <linux/memblock.h> -#include <linux/syscore_ops.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -1470,130 +1469,38 @@ asmlinkage void __init xen_start_kernel(void) #endif } -#ifdef CONFIG_XEN_PVHVM -/* - * The pfn containing the shared_info is located somewhere in RAM. This - * will cause trouble if the current kernel is doing a kexec boot into a - * new kernel. The new kernel (and its startup code) can not know where - * the pfn is, so it can not reserve the page. The hypervisor will - * continue to update the pfn, and as a result memory corruption occours - * in the new kernel. - * - * One way to work around this issue is to allocate a page in the - * xen-platform pci device's BAR memory range. But pci init is done very - * late and the shared_info page is already in use very early to read - * the pvclock. So moving the pfn from RAM to MMIO is racy because some - * code paths on other vcpus could access the pfn during the small - * window when the old pfn is moved to the new pfn. There is even a - * small window were the old pfn is not backed by a mfn, and during that - * time all reads return -1. - * - * Because it is not known upfront where the MMIO region is located it - * can not be used right from the start in xen_hvm_init_shared_info. - * - * To minimise trouble the move of the pfn is done shortly before kexec. - * This does not eliminate the race because all vcpus are still online - * when the syscore_ops will be called. But hopefully there is no work - * pending at this point in time. Also the syscore_op is run last which - * reduces the risk further. - */ - -static struct shared_info *xen_hvm_shared_info; - -static void xen_hvm_connect_shared_info(unsigned long pfn) +void __ref xen_hvm_init_shared_info(void) { + int cpu; struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = pfn; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); -} -static void xen_hvm_set_shared_info(struct shared_info *sip) -{ - int cpu; - - HYPERVISOR_shared_info = sip; + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info * page, we use it in the event channel upcall and in some pvclock * related functions. We don't need the vcpu_info placement * optimizations because we don't use any pv_mmu or pv_irq op on * HVM. - * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is - * online but xen_hvm_set_shared_info is run at resume time too and + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and * in that case multiple vcpus might be online. */ for_each_online_cpu(cpu) { per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; } } -/* Reconnect the shared_info pfn to a mfn */ -void xen_hvm_resume_shared_info(void) -{ - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); -} - -#ifdef CONFIG_KEXEC -static struct shared_info *xen_hvm_shared_info_kexec; -static unsigned long xen_hvm_shared_info_pfn_kexec; - -/* Remember a pfn in MMIO space for kexec reboot */ -void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn) -{ - xen_hvm_shared_info_kexec = sip; - xen_hvm_shared_info_pfn_kexec = pfn; -} - -static void xen_hvm_syscore_shutdown(void) -{ - struct xen_memory_reservation reservation = { - .domid = DOMID_SELF, - .nr_extents = 1, - }; - unsigned long prev_pfn; - int rc; - - if (!xen_hvm_shared_info_kexec) - return; - - prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT; - set_xen_guest_handle(reservation.extent_start, &prev_pfn); - - /* Move pfn to MMIO, disconnects previous pfn from mfn */ - xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec); - - /* Update pointers, following hypercall is also a memory barrier */ - xen_hvm_set_shared_info(xen_hvm_shared_info_kexec); - - /* Allocate new mfn for previous pfn */ - do { - rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); - if (rc == 0) - msleep(123); - } while (rc == 0); - - /* Make sure the previous pfn is really connected to a (new) mfn */ - BUG_ON(rc != 1); -} - -static struct syscore_ops xen_hvm_syscore_ops = { - .shutdown = xen_hvm_syscore_shutdown, -}; -#endif - -/* Use a pfn in RAM, may move to MMIO before kexec. */ -static void __init xen_hvm_init_shared_info(void) -{ - /* Remember pointer for resume */ - xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); - xen_hvm_set_shared_info(xen_hvm_shared_info); -} - +#ifdef CONFIG_XEN_PVHVM static void __init init_hvm_pv_info(void) { int major, minor; @@ -1644,9 +1551,6 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); xen_hvm_init_shared_info(); -#ifdef CONFIG_KEXEC - register_syscore_ops(&xen_hvm_syscore_ops); -#endif if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b65a76133f4f..5141d808e751 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1283,7 +1283,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { + if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { args->op.cmd = MMUEXT_INVLPG_MULTI; args->op.arg1.linear_addr = start; } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 64effdc6da94..76ba0e97e530 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -194,6 +194,13 @@ RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID * boundary violation will require three middle nodes. */ RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); +/* When we populate back during bootup, the amount of pages can vary. The + * max we have is seen is 395979, but that does not mean it can't be more. + * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle + * it can re-use Xen provided mfn_list array, so we only need to allocate at + * most three P2M top nodes. */ +RESERVE_BRK(p2m_populated, PAGE_SIZE * 3); + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -570,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn) } return true; } + +/* + * Skim over the P2M tree looking at pages that are either filled with + * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and + * replace the P2M leaf with a p2m_missing or p2m_identity. + * Stick the old page in the new P2M tree location. + */ +bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn) +{ + unsigned topidx; + unsigned mididx; + unsigned ident_pfns; + unsigned inv_pfns; + unsigned long *p2m; + unsigned long *mid_mfn_p; + unsigned idx; + unsigned long pfn; + + /* We only look when this entails a P2M middle layer */ + if (p2m_index(set_pfn)) + return false; + + for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { + topidx = p2m_top_index(pfn); + + if (!p2m_top[topidx]) + continue; + + if (p2m_top[topidx] == p2m_mid_missing) + continue; + + mididx = p2m_mid_index(pfn); + p2m = p2m_top[topidx][mididx]; + if (!p2m) + continue; + + if ((p2m == p2m_missing) || (p2m == p2m_identity)) + continue; + + if ((unsigned long)p2m == INVALID_P2M_ENTRY) + continue; + + ident_pfns = 0; + inv_pfns = 0; + for (idx = 0; idx < P2M_PER_PAGE; idx++) { + /* IDENTITY_PFNs are 1:1 */ + if (p2m[idx] == IDENTITY_FRAME(pfn + idx)) + ident_pfns++; + else if (p2m[idx] == INVALID_P2M_ENTRY) + inv_pfns++; + else + break; + } + if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE)) + goto found; + } + return false; +found: + /* Found one, replace old with p2m_identity or p2m_missing */ + p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing); + /* And the other for save/restore.. */ + mid_mfn_p = p2m_top_mfn_p[topidx]; + /* NOTE: Even if it is a p2m_identity it should still be point to + * a page filled with INVALID_P2M_ENTRY entries. */ + mid_mfn_p[mididx] = virt_to_mfn(p2m_missing); + + /* Reset where we want to stick the old page in. */ + topidx = p2m_top_index(set_pfn); + mididx = p2m_mid_index(set_pfn); + + /* This shouldn't happen */ + if (WARN_ON(p2m_top[topidx] == p2m_mid_missing)) + early_alloc_p2m(set_pfn); + + if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing)) + return false; + + p2m_init(p2m); + p2m_top[topidx][mididx] = p2m; + mid_mfn_p = p2m_top_mfn_p[topidx]; + mid_mfn_p[mididx] = virt_to_mfn(p2m); + + return true; +} bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!early_alloc_p2m(pfn)) return false; + if (early_can_reuse_p2m_middle(pfn, mfn)) + return __set_phys_to_machine(pfn, mfn); + if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/)) return false; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ead85576d54a..d11ca11d14fc 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -78,9 +78,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size) memblock_reserve(start, size); xen_max_p2m_pfn = PFN_DOWN(start + size); + for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) + continue; + WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", + pfn, mfn); - for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + } } static unsigned long __init xen_do_chunk(unsigned long start, diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index ae8a00c39de4..45329c8c226e 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_resume_shared_info(); + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1e4329e04e0f..202d4c150154 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -41,7 +41,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_resume_shared_info(void); +void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); |