diff options
Diffstat (limited to 'arch/x86')
84 files changed, 1653 insertions, 429 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index a2abc2f..258965d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -698,6 +698,14 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. +config QUEUED_LOCK_STAT + bool "Paravirt queued spinlock statistics" + depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS + ---help--- + Enable the collection of statistical data on the slowpath + behavior of paravirtualized queued spinlocks and report + them on debugfs. + source "arch/x86/xen/Kconfig" config KVM_GUEST diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3c71dd9..e32206e 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,5 @@ +#include <linux/jump_label.h> + /* x86 function call convention, 64-bit: @@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with #endif /* CONFIG_X86_64 */ +/* + * This does 'call enter_from_user_mode' unless we can avoid it based on + * kernel config or using the static jump infrastructure. + */ +.macro CALL_enter_from_user_mode +#ifdef CONFIG_CONTEXT_TRACKING +#ifdef HAVE_JUMP_LABEL + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 +#endif + call enter_from_user_mode +.Lafter_call_\@: +#endif +.endm diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index a89fdbc..0366374 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -421,7 +421,7 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) regs->ip = landing_pad; /* - * Fetch ECX from where the vDSO stashed it. + * Fetch EBP from where the vDSO stashed it. * * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! */ @@ -432,10 +432,10 @@ __visible long do_fast_syscall_32(struct pt_regs *regs) * Micro-optimization: the pointer we're following is explicitly * 32 bits, so it can't be out of range. */ - __get_user(*(u32 *)®s->cx, + __get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #else - get_user(*(u32 *)®s->cx, + get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp) #endif ) { diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 3eb572e..77d8c51 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -292,7 +292,7 @@ ENTRY(entry_SYSENTER_32) movl TSS_sysenter_sp0(%esp), %esp sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ecx /* pt_regs->cx */ + pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ @@ -308,8 +308,9 @@ sysenter_past_esp: movl %esp, %eax call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ @@ -328,7 +329,8 @@ sysenter_past_esp: * Return back to the vDSO, which will pop ecx and edx. * Don't bother with DS and ES (they already contain __USER_DS). */ - ENABLE_INTERRUPTS_SYSEXIT + sti + sysexit .pushsection .fixup, "ax" 2: movl $0, PT_FS(%esp) @@ -551,11 +553,6 @@ ENTRY(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) #endif ENTRY(overflow) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a55697d..9d34d3c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -520,9 +520,7 @@ END(irq_entries_start) */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode 1: /* @@ -1066,9 +1064,7 @@ ENTRY(error_entry) * (which can take locks). */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode ret .Lerror_entry_done: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index c320183..ff1c6d6 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -18,13 +18,6 @@ .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) -#endif - /* * 32-bit SYSENTER instruction entry. * @@ -63,7 +56,7 @@ ENTRY(entry_SYSENTER_compat) /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rcx /* pt_regs->sp */ + pushq %rbp /* pt_regs->sp (stashed in bp) */ /* * Push flags. This is nasty. First, interrupts are currently @@ -82,14 +75,14 @@ ENTRY(entry_SYSENTER_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 = 0 */ pushq %r8 /* pt_regs->r9 = 0 */ pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat) * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * - * NB.: sysenter_fix_flags is a label with the code under it moved + * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ testl $X86_EFLAGS_NT, EFLAGS(%rsp) - jnz sysenter_fix_flags -sysenter_flags_fixed: + jnz .Lsysenter_fix_flags +.Lsysenter_flags_fixed: /* * User mode is traced as though IRQs are on, and SYSENTER @@ -121,14 +114,15 @@ sysenter_flags_fixed: movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV jmp sysret32_from_system_call -sysenter_fix_flags: +.Lsysenter_fix_flags: pushq $X86_EFLAGS_FIXED popfq - jmp sysenter_flags_fixed + jmp .Lsysenter_flags_fixed ENDPROC(entry_SYSENTER_compat) /* @@ -178,7 +172,7 @@ ENTRY(entry_SYSCALL_compat) pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ - pushq %rcx /* pt_regs->cx (will be overwritten) */ + pushq %rbp /* pt_regs->cx (stashed in bp) */ pushq $-ENOSYS /* pt_regs->ax */ xorq %r8,%r8 pushq %r8 /* pt_regs->r8 = 0 */ @@ -186,7 +180,7 @@ ENTRY(entry_SYSCALL_compat) pushq %r8 /* pt_regs->r10 = 0 */ pushq %r8 /* pt_regs->r11 = 0 */ pushq %rbx /* pt_regs->rbx */ - pushq %rbp /* pt_regs->rbp */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ pushq %r8 /* pt_regs->r12 = 0 */ pushq %r8 /* pt_regs->r13 = 0 */ pushq %r8 /* pt_regs->r14 = 0 */ @@ -200,8 +194,9 @@ ENTRY(entry_SYSCALL_compat) movq %rsp, %rdi call do_fast_syscall_32 - testl %eax, %eax - jz .Lsyscall_32_done + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV /* Opportunistic SYSRET */ sysret32_from_system_call: @@ -236,7 +231,8 @@ sysret32_from_system_call: xorq %r9, %r9 xorq %r10, %r10 movq RSP-ORIG_RAX(%rsp), %rsp - USERGS_SYSRET32 + swapgs + sysretl END(entry_SYSCALL_compat) /* diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index ca94fa6..8602f06 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -17,8 +17,10 @@ #include <asm/vvar.h> #include <asm/unistd.h> #include <asm/msr.h> +#include <asm/pvclock.h> #include <linux/math64.h> #include <linux/time.h> +#include <linux/kernel.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void) } #endif -#ifndef BUILD_VDSO32 +#ifdef CONFIG_PARAVIRT_CLOCK +extern u8 pvclock_page + __attribute__((visibility("hidden"))); +#endif -#include <linux/kernel.h> -#include <asm/vsyscall.h> -#include <asm/fixmap.h> -#include <asm/pvclock.h> +#ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { @@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } -#ifdef CONFIG_PARAVIRT_CLOCK - -static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) -{ - const struct pvclock_vsyscall_time_info *pvti_base; - int idx = cpu / (PAGE_SIZE/PVTI_SIZE); - int offset = cpu % (PAGE_SIZE/PVTI_SIZE); - - BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); - - pvti_base = (struct pvclock_vsyscall_time_info *) - __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); - - return &pvti_base[offset]; -} - -static notrace cycle_t vread_pvclock(int *mode) -{ - const struct pvclock_vsyscall_time_info *pvti; - cycle_t ret; - u64 last; - u32 version; - u8 flags; - unsigned cpu, cpu1; - - - /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * - */ - do { - cpu = __getcpu() & VGETCPU_CPU_MASK; - /* TODO: We can put vcpu id into higher bits of pvti.version. - * This will save a couple of cycles by getting rid of - * __getcpu() calls (Gleb). - */ - - pvti = get_pvti(cpu); - - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); - - /* - * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. - */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); - - if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) - *mode = VCLOCK_NONE; - - /* refer to tsc.c read_tsc() comment for rationale */ - last = gtod->cycle_last; - - if (likely(ret >= last)) - return ret; - - return last; -} -#endif #else @@ -162,15 +95,77 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } +#endif + #ifdef CONFIG_PARAVIRT_CLOCK +static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void) +{ + return (const struct pvclock_vsyscall_time_info *)&pvclock_page; +} static notrace cycle_t vread_pvclock(int *mode) { - *mode = VCLOCK_NONE; - return 0; -} -#endif + const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; + cycle_t ret; + u64 tsc, pvti_tsc; + u64 last, delta, pvti_system_time; + u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift; + + /* + * Note: The kernel and hypervisor must guarantee that cpu ID + * number maps 1:1 to per-CPU pvclock time info. + * + * Because the hypervisor is entirely unaware of guest userspace + * preemption, it cannot guarantee that per-CPU pvclock time + * info is updated if the underlying CPU changes or that that + * version is increased whenever underlying CPU changes. + * + * On KVM, we are guaranteed that pvti updates for any vCPU are + * atomic as seen by *all* vCPUs. This is an even stronger + * guarantee than we get with a normal seqlock. + * + * On Xen, we don't appear to have that guarantee, but Xen still + * supplies a valid seqlock using the version field. + + * We only do pvclock vdso timing at all if + * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to + * mean that all vCPUs have matching pvti and that the TSC is + * synced, so we can just look at vCPU 0's pvti. + */ + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + + do { + version = pvti->version; + + smp_rmb(); + + tsc = rdtsc_ordered(); + pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; + pvti_tsc_shift = pvti->tsc_shift; + pvti_system_time = pvti->system_time; + pvti_tsc = pvti->tsc_timestamp; + + /* Make sure that the version double-check is last. */ + smp_rmb(); + } while (unlikely((version & 1) || version != pvti->version)); + + delta = tsc - pvti_tsc; + ret = pvti_system_time + + pvclock_scale_delta(delta, pvti_tsc_to_system_mul, + pvti_tsc_shift); + + /* refer to vread_tsc() comment for rationale */ + last = gtod->cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} #endif notrace static cycle_t vread_tsc(void) diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index de2c921..4158acc 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 2 * PAGE_SIZE; + vvar_start = . - 3 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -36,6 +36,7 @@ SECTIONS #undef EMIT_VVAR hpet_page = vvar_start + PAGE_SIZE; + pvclock_page = vvar_start + 2 * PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 785d992..491020b 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -73,6 +73,7 @@ enum { sym_vvar_start, sym_vvar_page, sym_hpet_page, + sym_pvclock_page, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -80,6 +81,7 @@ enum { const int special_pages[] = { sym_vvar_page, sym_hpet_page, + sym_pvclock_page, }; struct vdso_sym { @@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_start] = {"vvar_start", true}, [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, + [sym_pvclock_page] = {"pvclock_page", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index 93bd845..3a1d929 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -1,5 +1,5 @@ /* - * Code for the vDSO. This version uses the old int $0x80 method. + * AT_SYSINFO entry point */ #include <asm/dwarf2.h> @@ -21,35 +21,67 @@ __kernel_vsyscall: /* * Reshuffle regs so that all of any of the entry instructions * will preserve enough state. + * + * A really nice entry sequence would be: + * pushl %edx + * pushl %ecx + * movl %esp, %ecx + * + * Unfortunately, naughty Android versions between July and December + * 2015 actually hardcode the traditional Linux SYSENTER entry + * sequence. That is severely broken for a number of reasons (ask + * anyone with an AMD CPU, for example). Nonetheless, we try to keep + * it working approximately as well as it ever worked. + * + * This link may eludicate some of the history: + * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 + * personally, I find it hard to understand what's going on there. + * + * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE. + * Execute an indirect call to the address in the AT_SYSINFO auxv + * entry. That is the ONLY correct way to make a fast 32-bit system + * call on Linux. (Open-coding int $0x80 is also fine, but it's + * slow.) */ + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 pushl %edx CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET edx, 0 - pushl %ecx + pushl %ebp CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET ecx, 0 - movl %esp, %ecx + CFI_REL_OFFSET ebp, 0 + + #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter" + #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall" #ifdef CONFIG_X86_64 /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */ - ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \ - "syscall", X86_FEATURE_SYSCALL32 + ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \ + SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32 #else - ALTERNATIVE "", "sysenter", X86_FEATURE_SEP + ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP #endif /* Enter using int $0x80 */ - movl (%esp), %ecx int $0x80 GLOBAL(int80_landing_pad) - /* Restore ECX and EDX in case they were clobbered. */ - popl %ecx - CFI_RESTORE ecx + /* + * Restore EDX and ECX in case they were clobbered. EBP is not + * clobbered (the kernel restores it), but it's cleaner and + * probably faster to pop it than to adjust ESP using addl. + */ + popl %ebp + CFI_RESTORE ebp CFI_ADJUST_CFA_OFFSET -4 popl %edx CFI_RESTORE edx CFI_ADJUST_CFA_OFFSET -4 + popl %ecx + CFI_RESTORE ecx + CFI_ADJUST_CFA_OFFSET -4 ret CFI_ENDPROC diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 64df471..b8f69e2 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -12,6 +12,7 @@ #include <linux/random.h> #include <linux/elf.h> #include <linux/cpu.h> +#include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> @@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) .name = "[vvar]", .pages = no_pages, }; + struct pvclock_vsyscall_time_info *pvti; if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, @@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) } #endif + pvti = pvclock_pvti_cpu0_va(); + if (pvti && image->sym_pvclock_page) { + ret = remap_pfn_range(vma, + text_start + image->sym_pvclock_page, + __pa(pvti) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + } + up_fail: if (ret) current->mm->context.vdso = NULL; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316b..c80f6b6 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -23,6 +23,11 @@ #define APIC_VERBOSE 1 #define APIC_DEBUG 2 +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + /* * Define the default level of output to be very little * This can be turned up by using apic=verbose for more @@ -303,6 +308,7 @@ struct apic { unsigned int *apicid); /* ipi */ + void (*send_IPI)(int cpu, int vector); void (*send_IPI_mask)(const struct cpumask *mask, int vector); void (*send_IPI_mask_allbutself)(const struct cpumask *mask, int vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index ae5fb83..3e86742 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index a11c30b..a984111 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> //#include <asm/cmpxchg.h> /* An 64bit atomic type */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 43e1444..7ad8c94 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -202,6 +202,7 @@ #define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index f80d700..6d7d0e5 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,7 +19,6 @@ #include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> -#include <asm/pvclock.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> @@ -72,10 +71,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #endif -#ifdef CONFIG_PARAVIRT_CLOCK - PVCLOCK_FIXMAP_BEGIN, - PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, -#endif #endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 0000000..e1a4117 --- /dev/null +++ b/arch/x86/include/asm/intel_pt.h @@ -0,0 +1,10 @@ +#ifndef _ASM_X86_INTEL_PT_H +#define _ASM_X86_INTEL_PT_H + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +void cpu_emergency_stop_pt(void); +#else +static inline void cpu_emergency_stop_pt(void) {} +#endif + +#endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 615fa90..cfc9a0d 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -119,6 +119,8 @@ static inline void native_apic_mem_write(APIC_ICR, cfg); } +extern void default_send_IPI_single(int cpu, int vector); +extern void default_send_IPI_single_phys(int cpu, int vector); extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 5daeca3..adc54c1 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,12 +1,18 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef __ASSEMBLY__ - -#include <linux/stringify.h> -#include <linux/types.h> -#include <asm/nops.h> -#include <asm/asm.h> +#ifndef HAVE_JUMP_LABEL +/* + * For better or for worse, if jump labels (the gcc extension) are missing, + * then the entire static branch patching infrastructure is compiled out. + * If that happens, the code in here will malfunction. Raise a compiler + * error instead. + * + * In theory, jump labels and the static branch patching infrastructure + * could be decoupled to fix this. + */ +#error asm/jump_label.h included on a non-jump-label kernel +#endif #define JUMP_LABEL_NOP_SIZE 5 @@ -16,6 +22,14 @@ # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif +#include <asm/asm.h> +#include <asm/nops.h> + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> +#include <linux/types.h> + static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" @@ -59,5 +73,40 @@ struct jump_entry { jump_label_t key; }; -#endif /* __ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +.macro STATIC_JUMP_IF_TRUE target, key, def +.Lstatic_jump_\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + .popsection +.endm + +.macro STATIC_JUMP_IF_FALSE target, key, def +.Lstatic_jump_\@: + .if \def + .byte STATIC_KEY_INIT_NOP + .else + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + 1 + .popsection +.endm + +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 93724cc..eb4b09b 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -1,7 +1,13 @@ #ifndef _ASM_X86_MSI_H #define _ASM_X86_MSI_H #include <asm/hw_irq.h> +#include <asm/irqdomain.h> typedef struct irq_alloc_info msi_alloc_info_t; +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg); + +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc); + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 0000000..7567225 --- /dev/null +++ b/arch/x86/include/asm/msr-trace.h @@ -0,0 +1,57 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM msr + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE msr-trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/ + +#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MSR_H + +#include <linux/tracepoint.h> + +/* + * Tracing for x86 model specific registers. Directly maps to the + * RDMSR/WRMSR instructions. + */ + +DECLARE_EVENT_CLASS(msr_trace_class, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed), + TP_STRUCT__entry( + __field( unsigned, msr ) + __field( u64, val ) + __field( int, failed ) + ), + TP_fast_assign( + __entry->msr = msr; + __entry->val = val; + __entry->failed = failed; + ), + TP_printk("%x, value %llx%s", + __entry->msr, + __entry->val, + __entry->failed ? " #GP" : "") +); + +DEFINE_EVENT(msr_trace_class, read_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, write_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, rdpmc, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +#endif /* _TRACE_MSR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 77d8b28..fedd6e6 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -57,11 +57,34 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif +#ifdef CONFIG_TRACEPOINTS +/* + * Be very careful with includes. This header is prone to include loops. + */ +#include <asm/atomic.h> +#include <linux/tracepoint-defs.h> + +extern struct tracepoint __tracepoint_read_msr; +extern struct tracepoint __tracepoint_write_msr; +extern struct tracepoint __tracepoint_rdpmc; +#define msr_tracepoint_active(t) static_key_false(&(t).key) +extern void do_trace_write_msr(unsigned msr, u64 val, int failed); +extern void do_trace_read_msr(unsigned msr, u64 val, int failed); +extern void do_trace_rdpmc(unsigned msr, u64 val, int failed); +#else +#define msr_tracepoint_active(t) false +static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {} +#endif + static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -78,6 +101,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) : "c" (msr), [fault] "i" (-EIO)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err); return EAX_EDX_VAL(val, low, high); } @@ -85,6 +110,8 @@ static inline void native_write_msr(unsigned int msr, unsigned low, unsigned high) { asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } /* Can be uninlined because referenced by paravirt */ @@ -102,6 +129,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr, : "c" (msr), "0" (low), "d" (high), [fault] "i" (-EIO) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } @@ -160,6 +189,8 @@ static inline unsigned long long native_read_pmc(int counter) DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); + if (msr_tracepoint_active(__tracepoint_rdpmc)) + do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cbbf41c..f619250 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -19,6 +19,12 @@ static inline int paravirt_enabled(void) return pv_info.paravirt_enabled; } +static inline int paravirt_has_feature(unsigned int feature) +{ + WARN_ON_ONCE(!pv_info.paravirt_enabled); + return (pv_info.features & feature); +} + static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -896,23 +902,11 @@ extern void default_banner(void); call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) -#define USERGS_SYSRET32 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32)) - #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx - -#define ENABLE_INTERRUPTS_SYSEXIT \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) - - #else /* !CONFIG_X86_32 */ /* diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 0451503..77db561 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -70,9 +70,14 @@ struct pv_info { #endif int paravirt_enabled; + unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; +#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) +/* Supported features */ +#define PV_SUPPORTED_RTC (1<<0) + struct pv_init_ops { /* * Patch may replace one of the defined code sequences with @@ -157,15 +162,6 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); -#ifdef CONFIG_X86_32 - /* - * Atomically enable interrupts and return to userspace. This - * is only used in 32-bit kernels. 64-bit kernels use - * usergs_sysret32 instead. - */ - void (*irq_enable_sysexit)(void); -#endif - /* * Switch to usermode gs and return to 64-bit usermode using * sysret. Only used in 64-bit kernels to return to 64-bit @@ -174,14 +170,6 @@ struct pv_cpu_ops { */ void (*usergs_sysret64)(void); - /* - * Switch to usermode gs and return to 32-bit usermode using - * sysret. Used to return to 32-on-64 compat processes. - * Other usermode register state, including %esp, must already - * be restored. - */ - void (*usergs_sysret32)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6752225..2d5a50c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -472,6 +472,7 @@ static inline unsigned long current_top_of_stack(void) #else #define __cpuid native_cpuid #define paravirt_enabled() 0 +#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5..fdcc040 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -4,6 +4,15 @@ #include <linux/clocksource.h> #include <asm/pvclock-abi.h> +#ifdef CONFIG_KVM_GUEST +extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); @@ -91,10 +100,5 @@ struct pvclock_vsyscall_time_info { } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) -#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size); -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index b002e71..9f92c18 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -1,6 +1,65 @@ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H +/* + * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit + * registers. For i386, however, only 1 32-bit register needs to be saved + * and restored. So an optimized version of __pv_queued_spin_unlock() is + * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit. + */ +#ifdef CONFIG_64BIT + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); +#define __pv_queued_spin_unlock __pv_queued_spin_unlock +#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" +#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" + +/* + * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock + * which combines the registers saving trunk and the body of the following + * C code: + * + * void __pv_queued_spin_unlock(struct qspinlock *lock) + * { + * struct __qspinlock *l = (void *)lock; + * u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + * + * if (likely(lockval == _Q_LOCKED_VAL)) + * return; + * pv_queued_spin_unlock_slowpath(lock, lockval); + * } + * + * For x86-64, + * rdi = lock (first argument) + * rsi = lockval (second argument) + * rdx = internal variable (set to 0) + */ +asm (".pushsection .text;" + ".globl " PV_UNLOCK ";" + ".align 4,0x90;" + PV_UNLOCK ": " + "push %rdx;" + "mov $0x1,%eax;" + "xor %edx,%edx;" + "lock cmpxchg %dl,(%rdi);" + "cmp $0x1,%al;" + "jne .slowpath;" + "pop %rdx;" + "ret;" + ".slowpath: " + "push %rsi;" + "movzbl %al,%esi;" + "call " PV_UNLOCK_SLOWPATH ";" + "pop %rsi;" + "pop %rdx;" + "ret;" + ".size " PV_UNLOCK ", .-" PV_UNLOCK ";" + ".popsection"); + +#else /* CONFIG_64BIT */ + +extern void __pv_queued_spin_unlock(struct qspinlock *lock); PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); +#endif /* CONFIG_64BIT */ #endif diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a82c4f1..2cb1cc2 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,5 +25,6 @@ void __noreturn machine_real_restart(unsigned int type); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); +void run_crash_ipi_callback(struct pt_regs *regs); #endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 09b1b0a..660458a 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -745,5 +745,14 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #undef __copy_from_user_overflow #undef __copy_to_user_overflow +/* + * We rely on the nested NMI work to allow atomic faults from the NMI path; the + * nested NMI paths are careful to preserve CR2. + * + * Caller must use pagefault_enable/disable, or run in interrupt context, + * and also do a uaccess_ok() check + */ +#define __copy_from_user_nmi __copy_from_user_inatomic + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 756de91..deabaf9 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -22,6 +22,7 @@ struct vdso_image { long sym_vvar_page; long sym_hpet_page; + long sym_pvclock_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 03429da..2184943 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -16,7 +16,7 @@ struct mce { __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ __u8 severity; - __u8 usable_addr; + __u8 pad; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2f69e3b..8a5cdda 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -82,6 +82,12 @@ physid_mask_t phys_cpu_present_map; static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; /* + * This variable controls which CPUs receive external NMIs. By default, + * external NMIs are delivered only to the BSP. + */ +static int apic_extnmi = APIC_EXTNMI_BSP; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -1161,6 +1167,8 @@ void __init init_bsp_APIC(void) value = APIC_DM_NMI; if (!lapic_is_integrated()) /* 82489DX */ value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; apic_write(APIC_LVT1, value); } @@ -1378,9 +1386,11 @@ void setup_local_APIC(void) apic_write(APIC_LVT0, value); /* - * only the BP should see the LINT1 NMI signal, obviously. + * Only the BSP sees the LINT1 NMI signal by default. This can be + * modified by apic_extnmi= boot option. */ - if (!cpu) + if ((!cpu && apic_extnmi != APIC_EXTNMI_NONE) || + apic_extnmi == APIC_EXTNMI_ALL) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; @@ -2270,6 +2280,7 @@ static struct { unsigned int apic_tmict; unsigned int apic_tdcr; unsigned int apic_thmr; + unsigned int apic_cmci; } apic_pm_state; static int lapic_suspend(void) @@ -2299,6 +2310,10 @@ static int lapic_suspend(void) if (maxlvt >= 5) apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_pm_state.apic_cmci = apic_read(APIC_LVTCMCI); +#endif local_irq_save(flags); disable_local_APIC(); @@ -2355,10 +2370,14 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_INTEL) +#ifdef CONFIG_X86_THERMAL_VECTOR if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_write(APIC_LVTCMCI, apic_pm_state.apic_cmci); +#endif if (maxlvt >= 4) apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc); apic_write(APIC_LVTT, apic_pm_state.apic_lvtt); @@ -2548,3 +2567,23 @@ static int __init apic_set_disabled_cpu_apicid(char *arg) return 0; } early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); + +static int __init apic_set_extnmi(char *arg) +{ + if (!arg) + return -EINVAL; + + if (!strncmp("all", arg, 3)) + apic_extnmi = APIC_EXTNMI_ALL; + else if (!strncmp("none", arg, 4)) + apic_extnmi = APIC_EXTNMI_NONE; + else if (!strncmp("bsp", arg, 3)) + apic_extnmi = APIC_EXTNMI_BSP; + else { + pr_warn("Unknown external NMI delivery mode `%s' ignored\n", arg); + return -EINVAL; + } + + return 0; +} +early_param("apic_extnmi", apic_set_extnmi); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f92ab36..9968f30 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -185,6 +185,7 @@ static struct apic apic_flat = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, .send_IPI_allbutself = flat_send_IPI_allbutself, @@ -230,17 +231,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) -{ - default_send_IPI_mask_sequence_phys(cpumask, vector); -} - -static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask, - int vector) -{ - default_send_IPI_mask_allbutself_phys(cpumask, vector); -} - static void physflat_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -248,7 +238,7 @@ static void physflat_send_IPI_allbutself(int vector) static void physflat_send_IPI_all(int vector) { - physflat_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int physflat_probe(void) @@ -292,8 +282,9 @@ static struct apic apic_physflat = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = physflat_send_IPI_mask, - .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, + .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys, .send_IPI_allbutself = physflat_send_IPI_allbutself, .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 0d96749..331a7a0 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -30,6 +30,7 @@ #include <asm/e820.h> static void noop_init_apic_ldr(void) { } +static void noop_send_IPI(int cpu, int vector) { } static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_allbutself(int vector) { } @@ -144,6 +145,7 @@ struct apic apic_noop = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, .send_IPI_allbutself = noop_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 38dd5ef..c80c02c 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -193,20 +193,17 @@ static int __init numachip_system_init(void) case 1: init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); numachip_apic_icr_write = numachip1_apic_icr_write; - x86_init.pci.arch_init = pci_numachip_init; break; case 2: init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); numachip_apic_icr_write = numachip2_apic_icr_write; - - /* Use MCFG config cycles rather than locked CF8 cycles */ - raw_pci_ops = &pci_mmcfg; break; default: return 0; } x86_cpuinit.fixup_cpu_id = fixup_cpu_id; + x86_init.pci.arch_init = pci_numachip_init; return 0; } @@ -276,6 +273,7 @@ static const struct apic apic_numachip1 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, @@ -327,6 +325,7 @@ static const struct apic apic_numachip2 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 971cf88..cf9bd89 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -96,11 +96,6 @@ static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) -{ - default_send_IPI_mask_sequence_phys(mask, vector); -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -108,7 +103,7 @@ static void bigsmp_send_IPI_allbutself(int vector) static void bigsmp_send_IPI_all(int vector) { - bigsmp_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int dmi_bigsmp; /* can be set by dmi scanners */ @@ -180,7 +175,8 @@ static struct apic apic_bigsmp = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = bigsmp_send_IPI_mask, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, .send_IPI_mask_allbutself = NULL, .send_IPI_allbutself = bigsmp_send_IPI_allbutself, .send_IPI_all = bigsmp_send_IPI_all, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 6207156..eb45fc9 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -18,6 +18,16 @@ #include <asm/proto.h> #include <asm/ipi.h> +void default_send_IPI_single_phys(int cpu, int vector) +{ + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu), + vector, APIC_DEST_PHYSICAL); + local_irq_restore(flags); +} + void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector) { unsigned long query_cpu; @@ -55,6 +65,14 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, local_irq_restore(flags); } +/* + * Helper function for APICs which insist on cpumasks + */ +void default_send_IPI_single(int cpu, int vector) +{ + apic->send_IPI_mask(cpumask_of(cpu), vector); +} + #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 5f1feb6..ade2532 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -96,8 +96,8 @@ static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, return arg->msi_hwirq; } -static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { struct pci_dev *pdev = to_pci_dev(dev); struct msi_desc *desc = first_pci_msi_entry(pdev); @@ -113,11 +113,13 @@ static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, return 0; } +EXPORT_SYMBOL_GPL(pci_msi_prepare); -static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); } +EXPORT_SYMBOL_GPL(pci_msi_set_desc); static struct msi_domain_ops pci_msi_domain_ops = { .get_hwirq = pci_msi_get_hwirq, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7694ae6..f316e34 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,6 +105,7 @@ static struct apic apic_default = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, .send_IPI_allbutself = default_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59..908cb37 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -29,6 +29,7 @@ struct apic_chip_data { }; struct irq_domain *x86_vector_domain; +EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); static cpumask_var_t vector_cpumask; static struct irq_chip lapic_controller; @@ -66,6 +67,7 @@ struct irq_cfg *irqd_cfg(struct irq_data *irq_data) return data ? &data->cfg : NULL; } +EXPORT_SYMBOL_GPL(irqd_cfg); struct irq_cfg *irq_cfg(unsigned int irq) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cc8311c..aca8b75 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -23,6 +23,14 @@ static inline u32 x2apic_cluster(int cpu) return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -266,6 +274,7 @@ static struct apic apic_x2apic_cluster = { .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 662e915..a1242e2 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -36,6 +36,14 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -122,6 +130,7 @@ static struct apic apic_x2apic_phys = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 4a13946..d760c6b 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -406,6 +406,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, .send_IPI_allbutself = uv_send_IPI_allbutself, diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 439df97..84a7524 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -65,9 +65,6 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); -#ifdef CONFIG_X86_32 - OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); -#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d8f42f9..f2edafb 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,7 +23,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); - OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index c5b0d56..a006f4c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -114,7 +114,6 @@ static struct work_struct mce_work; static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); -static int mce_usable_address(struct mce *m); /* * CPU/chipset specific EDAC code can register a notifier call here to print @@ -475,6 +474,28 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&mce_irq_work); } +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granuality for now. + */ +static int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + return 1; +} + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -484,7 +505,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (!mce) return NOTIFY_DONE; - if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) { + if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; memory_failure(pfn, MCE_VECTOR, 0); } @@ -522,10 +543,10 @@ static bool memory_error(struct mce *m) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor == X86_VENDOR_AMD) { - /* - * coming soon - */ - return false; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); } else if (c->x86_vendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -567,7 +588,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); */ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { - bool error_logged = false; + bool error_seen = false; struct mce m; int severity; int i; @@ -601,6 +622,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; + error_seen = true; + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) @@ -608,27 +631,24 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* - * In the cases where we don't have a valid address after all, - * do not add it into the ring buffer. - */ - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { - if (m.status & MCI_STATUS_ADDRV) { + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) + if (m.status & MCI_STATUS_ADDRV) m.severity = severity; - m.usable_addr = mce_usable_address(&m); - - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } - } /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { - error_logged = true; + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); + else if (mce_usable_address(&m)) { + /* + * Although we skipped logging this, we still want + * to take action. Add to the pool so the registered + * notifiers will see it. + */ + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } /* @@ -644,7 +664,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) sync_core(); - return error_logged; + return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -931,23 +951,6 @@ reset: return ret; } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. - */ -static int mce_usable_address(struct mce *m) -{ - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) - return 0; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; - return 1; -} - static void mce_clear_state(unsigned long *toclear) { int i; @@ -999,6 +1002,17 @@ void do_machine_check(struct pt_regs *regs, long error_code) int flags = MF_ACTION_REQUIRED; int lmce = 0; + /* If this CPU is offline, just bail out. */ + if (cpu_is_offline(smp_processor_id())) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return; + } + } + ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1089,7 +1103,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* assuming valid severity level != 0 */ m.severity = severity; - m.usable_addr = mce_usable_address(&m); mce_log(&m); diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7..1b443db 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -482,6 +482,9 @@ int x86_pmu_hw_config(struct perf_event *event) /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; + + if (x86_pmu.pebs_prec_dist) + precise++; } if (event->attr.precise_ip > precise) @@ -1531,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs) { struct device_attribute *d; struct perf_pmu_events_attr *pmu_attr; + int offset = 0; int i, j; for (i = 0; attrs[i]; i++) { @@ -1539,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs) /* str trumps id */ if (pmu_attr->event_str) continue; - if (x86_pmu.event_map(i)) + if (x86_pmu.event_map(i + offset)) continue; for (j = i; attrs[j]; j++) @@ -1547,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs) /* Check the shifted attr. */ i--; + + /* + * event_map() is index based, the attrs array is organized + * by increasing event index. If we shift the events, then + * we need to compensate for the event_map(), otherwise + * we are looking up the wrong event in the map + */ + offset++; } } @@ -2250,12 +2262,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 8)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); if (bytes != 0) break; @@ -2265,6 +2284,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } + pagefault_enable(); return 1; } #else @@ -2302,12 +2322,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) if (perf_callchain_user32(regs, entry)) return; + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 16)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); if (bytes != 0) break; @@ -2315,8 +2342,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) break; perf_callchain_store(entry, frame.return_address); - fp = frame.next_frame; + fp = (void __user *)frame.next_frame; } + pagefault_enable(); } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index d0e35eb..7bb61e3 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -14,17 +14,7 @@ #include <linux/perf_event.h> -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - unsigned int _msr = (msr); \ - u64 _val = (val); \ - trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ - (unsigned long long)(_val)); \ - native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ -} while (0) -#endif +/* To enable MSR tracing please use the generic trace points. */ /* * | NHM/WSM | SNB | @@ -318,6 +308,10 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Constraint on specific umask bit only + event */ +#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c)) + /* Like UEVENT_CONSTRAINT, but match flags too */ #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) @@ -589,7 +583,8 @@ struct x86_pmu { bts_active :1, pebs :1, pebs_active :1, - pebs_broken :1; + pebs_broken :1, + pebs_prec_dist :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; @@ -907,6 +902,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_lbr_init_knl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 3ea177c..5861053 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -18,7 +18,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ + [ C(RESULT_ACCESS) ] = 0, [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a4300..a667078 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -185,6 +185,14 @@ struct event_constraint intel_skl_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_knl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, + MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, + MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1), + EVENT_EXTRA_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), @@ -255,7 +263,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -1457,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ +#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ +#define KNL_MCDRAM_LOCAL BIT_ULL(21) +#define KNL_MCDRAM_FAR BIT_ULL(22) +#define KNL_DDR_LOCAL BIT_ULL(23) +#define KNL_DDR_FAR BIT_ULL(24) +#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \ + KNL_DDR_LOCAL | KNL_DDR_FAR) +#define KNL_L2_READ SLM_DMND_READ +#define KNL_L2_WRITE SLM_DMND_WRITE +#define KNL_L2_PREFETCH SLM_DMND_PREFETCH +#define KNL_L2_ACCESS SLM_LLC_ACCESS +#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \ + KNL_DRAM_ANY | SNB_SNP_ANY | \ + SNB_NON_DRAM) + +static __initconst const u64 knl_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = KNL_L2_READ | KNL_L2_ACCESS, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS, + }, + }, +}; + /* * Use from PMIs where the LBRs are already disabled. */ @@ -2475,6 +2519,44 @@ static void intel_pebs_aliases_snb(struct perf_event *event) } } +static void intel_pebs_aliases_precdist(struct perf_event *event) +{ + if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.PREC_DIST + * (0x01c0), which is a PEBS capable event, to get the same + * count. + * + * The PREC_DIST event has special support to minimize sample + * shadowing effects. One drawback is that it can be + * only programmed on counter 1, but that seems like an + * acceptable trade off. + */ + u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16); + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } +} + +static void intel_pebs_aliases_ivb(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_snb(event); + return intel_pebs_aliases_precdist(event); +} + +static void intel_pebs_aliases_skl(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_core2(event); + return intel_pebs_aliases_precdist(event); +} + static unsigned long intel_pmu_free_running_flags(struct perf_event *event) { unsigned long flags = x86_pmu.free_running_flags; @@ -3332,6 +3414,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_gen_event_constraints; x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); break; @@ -3431,7 +3514,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; if (boot_cpu_data.x86_model == 62) x86_pmu.extra_regs = intel_snbep_extra_regs; else @@ -3464,7 +3548,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3499,7 +3584,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_bdw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3511,6 +3597,24 @@ __init int intel_pmu_init(void) pr_cont("Broadwell events, "); break; + case 87: /* Knights Landing Xeon Phi */ + memcpy(hw_cache_event_ids, + slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, + knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_knl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_knl_extra_regs; + + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + pr_cont("Knights Landing events, "); + break; + case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ x86_pmu.late_ack = true; @@ -3521,7 +3625,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_skl_event_constraints; x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints; x86_pmu.extra_regs = intel_skl_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_skl; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c77..10602f0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -620,6 +620,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -686,6 +688,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -700,6 +704,8 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -718,9 +724,10 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ @@ -1101,6 +1108,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1186,7 +1200,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; @@ -1230,12 +1244,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) pebs_status = p->status & cpuc->pebs_enabled; pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + /* + * On some CPUs the PEBS status can be zero when PEBS is + * racing with clearing of GLOBAL_STATUS. + * + * Normally we would drop that record, but in the + * case when there is only a single active PEBS event + * we can assume it's for that event. + */ + if (!pebs_status && cpuc->pebs_enabled && + !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) + pebs_status = cpuc->pebs_enabled; + bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); - if (WARN(bit >= x86_pmu.max_pebs_events, - "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx", - (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled, - *(unsigned long long *)cpuc->active_mask)) + if (bit >= x86_pmu.max_pebs_events) continue; /* diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 659f01e..653f88d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -42,6 +42,13 @@ static enum { #define LBR_FAR_BIT 8 /* do not capture far branches */ #define LBR_CALL_STACK_BIT 9 /* enable call stack */ +/* + * Following bit only exists in Linux; we mask it out before writing it to + * the actual MSR. But it helps the constraint perf code to understand + * that this is a separate configuration. + */ +#define LBR_NO_INFO_BIT 63 /* don't read LBR_INFO. */ + #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) #define LBR_JCC (1 << LBR_JCC_BIT) @@ -52,6 +59,7 @@ static enum { #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) #define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) +#define LBR_NO_INFO (1ULL << LBR_NO_INFO_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -152,8 +160,8 @@ static void __intel_pmu_lbr_enable(bool pmi) * did not change. */ if (cpuc->lbr_sel) - lbr_select = cpuc->lbr_sel->config; - if (!pmi) + lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask; + if (!pmi && cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, lbr_select); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); @@ -422,6 +430,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { + bool need_info = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -429,8 +438,11 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int out = 0; int num = x86_pmu.lbr_nr; - if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + if (cpuc->lbr_sel) { + need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + } for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; @@ -442,7 +454,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_INFO) { + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info); @@ -590,6 +602,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (v != LBR_IGN) mask |= v; } + reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; @@ -600,6 +613,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) */ reg->config = mask ^ x86_pmu.lbr_sel_mask; + if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && + (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && + (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + reg->config |= LBR_NO_INFO; + return 0; } @@ -1028,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void) */ pr_cont("8-deep LBR, "); } + +/* Knights Landing */ +void intel_pmu_lbr_init_knl(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + pr_cont("8-deep LBR, "); +} diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 868e119..c0bbd10 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -27,6 +27,7 @@ #include <asm/perf_event.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/intel_pt.h> #include "perf_event.h" #include "intel_pt.h" @@ -1122,6 +1123,14 @@ static int pt_event_init(struct perf_event *event) return 0; } +void cpu_emergency_stop_pt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + if (pt->handle.event) + pt_event_stop(pt->handle.event, PERF_EF_UPDATE); +} + static __init int pt_init(void) { int ret, cpu, prior_warn = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index ed446bd..24a351a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -63,7 +63,7 @@ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ #define NR_RAPL_DOMAINS 0x4 -static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -109,11 +109,11 @@ static struct kobj_attribute format_attr_##_var = \ #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ -#define RAPL_EVENT_ATTR_STR(_name, v, str) \ -static struct perf_pmu_events_attr event_attr_##v = { \ - .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \ - .id = 0, \ - .event_str = str, \ +#define RAPL_EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ }; struct rapl_pmu { @@ -405,19 +405,6 @@ static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; -static ssize_t rapl_sysfs_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct perf_pmu_events_attr *pmu_attr = \ - container_of(attr, struct perf_pmu_events_attr, attr); - - if (pmu_attr->event_str) - return sprintf(page, "%s", pmu_attr->event_str); - - return 0; -} - RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 61215a6..f97f807 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -884,6 +884,15 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * each box has a different function id. */ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + /* Knights Landing uses a common PCI device ID for multiple instances of + * an uncore PMU device type. There is only one entry per device type in + * the knl_uncore_pci_ids table inspite of multiple devices present for + * some device types. Hence PCI device idx would be 0 for all devices. + * So increment pmu pointer to point to an unused array element. + */ + if (boot_cpu_data.x86_model == 87) + while (pmu->func_id >= 0) + pmu++; if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else @@ -966,6 +975,7 @@ static int __init uncore_pci_init(void) case 63: /* Haswell-EP */ ret = hswep_uncore_pci_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ ret = bdx_uncore_pci_init(); break; @@ -982,6 +992,9 @@ static int __init uncore_pci_init(void) case 61: /* Broadwell */ ret = bdw_uncore_pci_init(); break; + case 87: /* Knights Landing */ + ret = knl_uncore_pci_init(); + break; default: return 0; } @@ -1287,9 +1300,13 @@ static int __init uncore_cpu_init(void) case 63: /* Haswell-EP */ hswep_uncore_cpu_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ bdx_uncore_cpu_init(); break; + case 87: /* Knights Landing */ + knl_uncore_cpu_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 2f0a4a9..07aa2d6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -338,6 +338,7 @@ int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); +int snb_pci2phy_map_init(int devid); /* perf_event_intel_uncore_snbep.c */ int snbep_uncore_pci_init(void); @@ -348,6 +349,8 @@ int hswep_uncore_pci_init(void); void hswep_uncore_cpu_init(void); int bdx_uncore_pci_init(void); void bdx_uncore_cpu_init(void); +int knl_uncore_pci_init(void); +void knl_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 8452561..0b93482 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -417,7 +417,7 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags) } } -static int snb_pci2phy_map_init(int devid) +int snb_pci2phy_map_init(int devid) { struct pci_dev *dev = NULL; struct pci2phy_map *map; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index f0f4fcb..33acb88 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -209,31 +209,98 @@ #define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 #define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 +/* KNL Ubox */ +#define KNL_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) +/* KNL CHA */ +#define KNL_CHA_MSR_OFFSET 0xc +#define KNL_CHA_MSR_PMON_CTL_QOR (1 << 16) +#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +#define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff +#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) +#define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) + +/* KNL EDC/MC UCLK */ +#define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 +#define KNL_UCLK_MSR_PMON_CTL0 0x420 +#define KNL_UCLK_MSR_PMON_BOX_CTL 0x430 +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW 0x44c +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL 0x454 +#define KNL_PMON_FIXED_CTL_EN 0x1 + +/* KNL EDC */ +#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW 0xa00 +#define KNL_EDC0_ECLK_MSR_PMON_CTL0 0xa20 +#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL 0xa30 +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW 0xa3c +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL 0xa44 + +/* KNL MC */ +#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW 0xb00 +#define KNL_MC0_CH0_MSR_PMON_CTL0 0xb20 +#define KNL_MC0_CH0_MSR_PMON_BOX_CTL 0xb30 +#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW 0xb3c +#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL 0xb44 + +/* KNL IRP */ +#define KNL_IRP_PCI_PMON_BOX_CTL 0xf0 +#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +/* KNL PCU */ +#define KNL_PCU_PMON_CTL_EV_SEL_MASK 0x0000007f +#define KNL_PCU_PMON_CTL_USE_OCC_CTR (1 << 7) +#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK 0x3f000000 +#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK \ + (KNL_PCU_PMON_CTL_EV_SEL_MASK | \ + KNL_PCU_PMON_CTL_USE_OCC_CTR | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_CBO_PMON_CTL_TID_EN | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29"); DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20"); +DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); @@ -315,8 +382,9 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); + pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT); } static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) @@ -1728,6 +1796,419 @@ int ivbep_uncore_pci_init(void) } /* end of IvyTown uncore support */ +/* KNL uncore support */ +static struct attribute *knl_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute_group knl_uncore_ubox_format_group = { + .name = "format", + .attrs = knl_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = KNL_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_ubox_format_group, +}; + +static struct attribute *knl_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid4.attr, + &format_attr_filter_link3.attr, + &format_attr_filter_state4.attr, + &format_attr_filter_local.attr, + &format_attr_filter_all_op.attr, + &format_attr_filter_nnm.attr, + &format_attr_filter_opc3.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group knl_uncore_cha_format_group = { + .name = "format", + .attrs = knl_uncore_cha_formats_attr, +}; + +static struct event_constraint knl_uncore_cha_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg knl_uncore_cha_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4), + EVENT_EXTRA_END +}; + +static u64 knl_cha_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x4) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP; + return mask; +} + +static struct event_constraint * +knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask); +} + +static int knl_cha_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = knl_uncore_cha_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event); + +static struct intel_uncore_ops knl_uncore_cha_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = knl_cha_hw_config, + .get_constraint = knl_cha_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type knl_uncore_cha = { + .name = "cha", + .num_counters = 4, + .num_boxes = 38, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = KNL_CHA_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = KNL_CHA_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = knl_uncore_cha_constraints, + .ops = &knl_uncore_cha_ops, + .format_group = &knl_uncore_cha_format_group, +}; + +static struct attribute *knl_uncore_pcu_formats_attr[] = { + &format_attr_event2.attr, + &format_attr_use_occ_ctr.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh6.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + NULL, +}; + +static struct attribute_group knl_uncore_pcu_format_group = { + .name = "format", + .attrs = knl_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = KNL_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *knl_msr_uncores[] = { + &knl_uncore_ubox, + &knl_uncore_cha, + &knl_uncore_pcu, + NULL, +}; + +void knl_uncore_cpu_init(void) +{ + uncore_msr_uncores = knl_msr_uncores; +} + +static void knl_uncore_imc_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + + pci_write_config_dword(pdev, box_ctl, 0); +} + +static void knl_uncore_imc_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK) + == UNCORE_FIXED_EVENT) + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | KNL_PMON_FIXED_CTL_EN); + else + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops knl_uncore_imc_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = knl_uncore_imc_enable_box, + .read_counter = snbep_uncore_pci_read_counter, + .enable_event = knl_uncore_imc_enable_event, + .disable_event = snbep_uncore_pci_disable_event, +}; + +static struct intel_uncore_type knl_uncore_imc_uclk = { + .name = "imc_uclk", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_imc_dclk = { + .name = "imc", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_MC0_CH0_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_MC0_CH0_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_MC0_CH0_MSR_PMON_FIXED_LOW, + .fixed_ctl = KNL_MC0_CH0_MSR_PMON_FIXED_CTL, + .box_ctl = KNL_MC0_CH0_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_uclk = { + .name = "edc_uclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_eclk = { + .name = "edc_eclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_EDC0_ECLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW, + .fixed_ctl = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL, + .box_ctl = KNL_EDC0_ECLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct event_constraint knl_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type knl_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = knl_uncore_m2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct attribute *knl_uncore_irp_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group knl_uncore_irp_format_group = { + .name = "format", + .attrs = knl_uncore_irp_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = KNL_IRP_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = KNL_IRP_PCI_PMON_BOX_CTL, + .ops = &snbep_uncore_pci_ops, + .format_group = &knl_uncore_irp_format_group, +}; + +enum { + KNL_PCI_UNCORE_MC_UCLK, + KNL_PCI_UNCORE_MC_DCLK, + KNL_PCI_UNCORE_EDC_UCLK, + KNL_PCI_UNCORE_EDC_ECLK, + KNL_PCI_UNCORE_M2PCIE, + KNL_PCI_UNCORE_IRP, +}; + +static struct intel_uncore_type *knl_pci_uncores[] = { + [KNL_PCI_UNCORE_MC_UCLK] = &knl_uncore_imc_uclk, + [KNL_PCI_UNCORE_MC_DCLK] = &knl_uncore_imc_dclk, + [KNL_PCI_UNCORE_EDC_UCLK] = &knl_uncore_edc_uclk, + [KNL_PCI_UNCORE_EDC_ECLK] = &knl_uncore_edc_eclk, + [KNL_PCI_UNCORE_M2PCIE] = &knl_uncore_m2pcie, + [KNL_PCI_UNCORE_IRP] = &knl_uncore_irp, + NULL, +}; + +/* + * KNL uses a common PCI device ID for multiple instances of an Uncore PMU + * device type. prior to KNL, each instance of a PMU device type had a unique + * device ID. + * + * PCI Device ID Uncore PMU Devices + * ---------------------------------- + * 0x7841 MC0 UClk, MC1 UClk + * 0x7843 MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2, + * MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2 + * 0x7833 EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk, + * EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk + * 0x7835 EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk, + * EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk + * 0x7817 M2PCIe + * 0x7814 IRP +*/ + +static const struct pci_device_id knl_uncore_pci_ids[] = { + { /* MC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0), + }, + { /* MC DClk Channel */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0), + }, + { /* EDC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0), + }, + { /* EDC EClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0), + }, + { /* M2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver knl_uncore_pci_driver = { + .name = "knl_uncore", + .id_table = knl_uncore_pci_ids, +}; + +int knl_uncore_pci_init(void) +{ + int ret; + + /* All KNL PCI based PMON units are on the same PCI bus except IRP */ + ret = snb_pci2phy_map_init(0x7814); /* IRP */ + if (ret) + return ret; + ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */ + if (ret) + return ret; + uncore_pci_uncores = knl_pci_uncores; + uncore_pci_driver = &knl_uncore_pci_driver; + return 0; +} + +/* end of KNL uncore support */ + /* Haswell-EP uncore support */ static struct attribute *hswep_uncore_ubox_formats_attr[] = { &format_attr_event.attr, @@ -2338,7 +2819,7 @@ int hswep_uncore_pci_init(void) } /* end of Haswell-EP uncore support */ -/* BDX-DE uncore support */ +/* BDX uncore support */ static struct intel_uncore_type bdx_uncore_ubox = { .name = "ubox", @@ -2360,13 +2841,14 @@ static struct event_constraint bdx_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x09, 0x3), UNCORE_EVENT_CONSTRAINT(0x11, 0x1), UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), EVENT_CONSTRAINT_END }; static struct intel_uncore_type bdx_uncore_cbox = { .name = "cbox", .num_counters = 4, - .num_boxes = 8, + .num_boxes = 24, .perf_ctr_bits = 48, .event_ctl = HSWEP_C0_MSR_PMON_CTL0, .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, @@ -2379,9 +2861,24 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, + &bdx_uncore_sbox, &hswep_uncore_pcu, NULL, }; @@ -2396,7 +2893,7 @@ void bdx_uncore_cpu_init(void) static struct intel_uncore_type bdx_uncore_ha = { .name = "ha", .num_counters = 4, - .num_boxes = 1, + .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), }; @@ -2404,7 +2901,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", .num_counters = 5, - .num_boxes = 2, + .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, @@ -2424,6 +2921,19 @@ static struct intel_uncore_type bdx_uncore_irp = { .format_group = &snbep_uncore_format_group, }; +static struct intel_uncore_type bdx_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x10, 0x3), @@ -2432,6 +2942,8 @@ static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x23, 0x1), UNCORE_EVENT_CONSTRAINT(0x25, 0x1), UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), EVENT_CONSTRAINT_END }; @@ -2445,18 +2957,65 @@ static struct intel_uncore_type bdx_uncore_r2pcie = { SNBEP_UNCORE_PCI_COMMON_INIT(), }; +static struct event_constraint bdx_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x7), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 3, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + enum { BDX_PCI_UNCORE_HA, BDX_PCI_UNCORE_IMC, BDX_PCI_UNCORE_IRP, + BDX_PCI_UNCORE_QPI, BDX_PCI_UNCORE_R2PCIE, + BDX_PCI_UNCORE_R3QPI, }; static struct intel_uncore_type *bdx_pci_uncores[] = { [BDX_PCI_UNCORE_HA] = &bdx_uncore_ha, [BDX_PCI_UNCORE_IMC] = &bdx_uncore_imc, [BDX_PCI_UNCORE_IRP] = &bdx_uncore_irp, + [BDX_PCI_UNCORE_QPI] = &bdx_uncore_qpi, [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie, + [BDX_PCI_UNCORE_R3QPI] = &bdx_uncore_r3qpi, NULL, }; @@ -2465,6 +3024,10 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0), }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1), + }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0), @@ -2473,14 +3036,74 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1), }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7), + }, { /* IRP */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0), }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2), + }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0), }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + }, + { /* QPI Port 2 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + }, { /* end: all zeroes */ } }; @@ -2500,4 +3123,4 @@ int bdx_uncore_pci_init(void) return 0; } -/* end of BDX-DE uncore support */ +/* end of BDX uncore support */ diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2c1910f..58f3431 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -35,6 +35,7 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> +#include <asm/intel_pt.h> /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -125,6 +126,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + disable_local_APIC(); } @@ -169,6 +175,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 22abea0..0d4e092 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -143,9 +143,18 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +/* Get alignment of the TYPE. */ +#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) + +/* + * Enforce that 'MEMBER' is the last field of 'TYPE'. + * + * Align the computed size with alignment of the TYPE, + * because that's how C aligns structs. + */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ + TYPE_ALIGN(TYPE))) /* * We append the 'struct fpu' to the task_struct: diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2bd81e3..72cef58 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock); static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; +struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return hv_clock; +} + /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -305,7 +310,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 int cpu; - int ret; u8 flags; struct pvclock_vcpu_time_info *vcpu_time; unsigned int size; @@ -325,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } - if ((ret = pvclock_init_vsyscall(hv_clock, size))) { - put_cpu(); - return ret; - } - put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 697f90d..8a2cdd7 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -29,6 +29,7 @@ #include <asm/mach_traps.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/reboot.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -231,7 +232,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) #endif if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); @@ -255,8 +256,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); show_regs(regs); - if (panic_on_io_nmi) - panic("NMI IOCK error: Not continuing"); + if (panic_on_io_nmi) { + nmi_panic(regs, "NMI IOCK error: Not continuing"); + + /* + * If we end up here, it means we have received an NMI while + * processing panic(). Simply return without delaying and + * re-enabling NMIs. + */ + return; + } /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; @@ -297,7 +306,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Do you have a strange power saving mode enabled?\n"); if (unknown_nmi_panic || panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); } @@ -348,8 +357,19 @@ static void default_do_nmi(struct pt_regs *regs) return; } - /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ - raw_spin_lock(&nmi_reason_lock); + /* + * Non-CPU-specific NMI: NMI sources can be processed on any CPU. + * + * Another CPU may be processing panic routines while holding + * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping, + * and if so, call its callback directly. If there is no CPU preparing + * crash dump, we simply loop here. + */ + while (!raw_spin_trylock(&nmi_reason_lock)) { + run_crash_ipi_callback(regs); + cpu_relax(); + } + reason = x86_platform.get_nmi_reason(); if (reason & NMI_REASON_MASK) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 3265ea0..f08ac28 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -150,10 +150,6 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || -#ifdef CONFIG_X86_32 - type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || -#endif - type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); @@ -208,8 +204,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_irq_enable_sysexit(void); -extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { @@ -367,13 +361,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) - .irq_enable_sysexit = native_irq_enable_sysexit, -#endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_IA32_EMULATION - .usergs_sysret32 = native_usergs_sysret32, -#endif .usergs_sysret64 = native_usergs_sysret64, #endif .iret = native_iret, diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index c89f50a..158dc06 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -5,7 +5,6 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); @@ -46,7 +45,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, restore_fl); PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa0558..e70087a 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); -DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); @@ -55,7 +53,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); PATCH_SITE(pv_mmu_ops, read_cr2); diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d2..99bfc02 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } - -#ifdef CONFIG_X86_64 -/* - * Initialize the generic pvclock vsyscall state. This will allocate - * a/some page(s) for the per-vcpu pvclock information, set up a - * fixmap mapping for the page(s) - */ - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size) -{ - int idx; - - WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { - __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, - __pa(i) + (idx*PAGE_SIZE), - PAGE_KERNEL_VVAR); - } - - return 0; -} -#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd..d64889a 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -718,6 +718,7 @@ static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; +static int crash_ipi_issued; static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) { @@ -780,6 +781,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) smp_send_nmi_allbutself(); + /* Kick CPUs looping in NMI context. */ + WRITE_ONCE(crash_ipi_issued, 1); + msecs = 1000; /* Wait at most a second for the other cpus to stop */ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { mdelay(1); @@ -788,9 +792,35 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* Leave the nmi callback set */ } + +/* + * Check if the crash dumping IPI got issued and if so, call its callback + * directly. This function is used when we have already been in NMI handler. + * It doesn't return. + */ +void run_crash_ipi_callback(struct pt_regs *regs) +{ + if (crash_ipi_issued) + crash_nmi_callback(0, regs); +} + +/* Override the weak function in kernel/panic.c */ +void nmi_panic_self_stop(struct pt_regs *regs) +{ + while (1) { + /* If no CPU is preparing crash dump, we simply loop here. */ + run_crash_ipi_callback(regs); + cpu_relax(); + } +} + #else /* !CONFIG_SMP */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { /* No other CPUs to shoot down */ } + +void run_crash_ipi_callback(struct pt_regs *regs) +{ +} #endif diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index cd96852..4af8d06 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -200,6 +200,9 @@ static __init int add_rtc_cmos(void) } #endif + if (paravirt_enabled() && !paravirt_has(RTC)) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 12c8286..658777c 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -125,12 +125,12 @@ static void native_smp_send_reschedule(int cpu) WARN_ON(1); return; } - apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); + apic->send_IPI(cpu, RESCHEDULE_VECTOR); } void native_send_call_func_single_ipi(int cpu) { - apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); + apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); } void native_send_call_func_ipi(const struct cpumask *mask) diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 06332cb..3f5c48d 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -38,6 +38,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->edx & bit(X86_FEATURE_MTRR)); +} + static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 08116ff..b0ea42b 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -420,6 +420,7 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_s u8 saved_mode; if (hpet_legacy_start) { /* save existing mode for later reenablement */ + WARN_ON(channel != 0); saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ pit_load_count(kvm, channel, val); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 9e8bf13..3f8c732 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -120,14 +120,22 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; } -static u8 mtrr_disabled_type(void) +static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) { /* * Intel SDM 11.11.2.2: all MTRRs are disabled when * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC * memory type is applied to all of physical memory. + * + * However, virtual machines can be run with CPUID such that + * there are no MTRRs. In that case, the firmware will never + * enable MTRRs and it is obviously undesirable to run the + * guest entirely with UC memory and we use WB. */ - return MTRR_TYPE_UNCACHABLE; + if (guest_cpuid_has_mtrr(vcpu)) + return MTRR_TYPE_UNCACHABLE; + else + return MTRR_TYPE_WRBACK; } /* @@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr) for (seg = 0; seg < seg_num; seg++) { mtrr_seg = &fixed_seg_table[seg]; - if (mtrr_seg->start >= addr && addr < mtrr_seg->end) + if (mtrr_seg->start <= addr && addr < mtrr_seg->end) return seg; } @@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) *start = range->base & PAGE_MASK; mask = range->mask & PAGE_MASK; - mask |= ~0ULL << boot_cpu_data.x86_phys_bits; /* This cannot overflow because writing to the reserved bits of * variable MTRRs causes a #GP. @@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (var_mtrr_range_is_valid(cur)) list_del(&mtrr_state->var_ranges[index].node); + /* Extend the mask with all 1 bits to the left, since those + * bits must implicitly be 0. The bits are then cleared + * when reading them. + */ if (!is_mtrr_mask) cur->base = data; else - cur->mask = data; + cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); /* add it to the list if it's enabled. */ if (var_mtrr_range_is_valid(cur)) { @@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; else *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + + *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; } return 0; @@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) } if (iter.mtrr_disabled) - return mtrr_disabled_type(); + return mtrr_disabled_type(vcpu); /* not contained in any MTRRs. */ if (type == -1) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 83a1c64..899c40f 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3422,6 +3422,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; + trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3892,8 +3894,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); - if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index af823a3..44976a5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2803,7 +2803,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: @@ -2909,7 +2909,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!guest_cpuid_has_rdtscp(vcpu)) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -8042,6 +8042,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -8668,7 +8670,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index eed3228..97592e1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3572,9 +3572,11 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -3593,6 +3595,7 @@ static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { int start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3602,7 +3605,9 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + start && i == 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); return 0; } @@ -6515,6 +6520,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); + trace_kvm_entry(vcpu->vcpu_id); + wait_lapic_expire(vcpu); __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -6527,8 +6534,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); kvm_x86_ops->run(vcpu); /* diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a1900d4..4ba229a 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1414,6 +1414,7 @@ __init void lguest_init(void) pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; + pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 4362373..004c861 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,6 +1,8 @@ #include <linux/module.h> #include <linux/preempt.h> #include <asm/msr.h> +#define CREATE_TRACE_POINTS +#include <asm/msr-trace.h> struct msr *msrs_alloc(void) { @@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, false); } + +#ifdef CONFIG_TRACEPOINTS +void do_trace_write_msr(unsigned msr, u64 val, int failed) +{ + trace_write_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_write_msr); +EXPORT_TRACEPOINT_SYMBOL(write_msr); + +void do_trace_read_msr(unsigned msr, u64 val, int failed) +{ + trace_read_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_read_msr); +EXPORT_TRACEPOINT_SYMBOL(read_msr); + +void do_trace_rdpmc(unsigned counter, u64 val, int failed) +{ + trace_rdpmc(counter, val, failed); +} +EXPORT_SYMBOL(do_trace_rdpmc); +EXPORT_TRACEPOINT_SYMBOL(rdpmc); + +#endif diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 327f21c..8dd8005 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -28,6 +28,7 @@ #include <linux/nmi.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/clocksource.h> #include <asm/apic.h> #include <asm/current.h> diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index e5f854c..14fcd01 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -470,7 +470,7 @@ long sys_sigreturn(void) struct sigcontext __user *sc = &frame->sc; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], (void *)sc->oldmask, sizeof(set.sig[0])) || + if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) || copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 4334e511..2306392 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1192,7 +1192,7 @@ static const struct pv_info xen_info __initconst = { #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - + .features = 0, .name = "Xen", }; @@ -1229,10 +1229,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .iret = xen_iret, #ifdef CONFIG_X86_64 - .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, -#else - .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1529,6 +1526,8 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; + if (xen_initial_domain()) + pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1879,8 +1878,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) + if (xen_pv_domain()) { clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + set_cpu_cap(c, X86_FEATURE_XENPV); + } } const struct hypervisor_x86 x86_hyper_xen = { diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 3705eab..df0c405 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include <linux/tick.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index fd92a64..feb6d40 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -35,20 +35,6 @@ check_events: ret /* - * We can't use sysexit directly, because we're not running in ring0. - * But we can easily fake it up using iret. Assuming xen_sysexit is - * jumped to with a standard stack frame, we can just strip it back to - * a standard iret frame and use iret. - */ -ENTRY(xen_sysexit) - movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ - orl $X86_EFLAGS_IF, PT_EFLAGS(%esp) - lea PT_EIP(%esp), %esp - - jmp xen_iret -ENDPROC(xen_sysexit) - -/* * This is run where a normal iret would be run, with the same stack setup: * 8: eflags * 4: cs diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index f22667a..cc8acc4 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -68,25 +68,6 @@ ENTRY(xen_sysret64) ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) -ENTRY(xen_sysret32) - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back - */ - movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER32_DS - pushq PER_CPU_VAR(rsp_scratch) - pushq %r11 - pushq $__USER32_CS - pushq %rcx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysret32) -RELOC(xen_sysret32, 1b+1) - /* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1399423..4140b07 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -139,9 +139,6 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); -#ifdef CONFIG_X86_32 -__visible void xen_sysexit(void); -#endif __visible void xen_sysret32(void); __visible void xen_sysret64(void); __visible void xen_adjust_exception_frame(void); |