diff options
| author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-03-25 03:53:42 -0300 |
|---|---|---|
| committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-03-25 03:53:42 -0300 |
| commit | 03dd4cb26d967f9588437b0fc9cc0e8353322bb7 (patch) | |
| tree | fa581f6dc1c0596391690d1f67eceef3af8246dc /arch/x86 | |
| parent | d4e493caf788ef44982e131ff9c786546904d934 (diff) | |
Linux-libre 4.5-gnu
Diffstat (limited to 'arch/x86')
210 files changed, 5770 insertions, 2078 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index db3622f22..c46662f64 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,12 +24,14 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_MMIO_FLUSH select ARCH_HAS_SG_CHAIN + select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT @@ -82,6 +84,8 @@ config X86 select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP select HAVE_ARCH_KGDB select HAVE_ARCH_KMEMCHECK + select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY if X86_64 select HAVE_ARCH_TRACEHOOK @@ -96,7 +100,6 @@ config X86 select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DMA_API_DEBUG - select HAVE_DMA_ATTRS select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS @@ -177,12 +180,23 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config HAVE_LATENCYTOP_SUPPORT - def_bool y - config MMU def_bool y +config ARCH_MMAP_RND_BITS_MIN + default 28 if 64BIT + default 8 + +config ARCH_MMAP_RND_BITS_MAX + default 32 if 64BIT + default 16 + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + default 8 + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + default 16 + config SBUS bool @@ -349,6 +363,17 @@ config X86_FEATURE_NAMES If in doubt, say Y. +config X86_FAST_FEATURE_TESTS + bool "Fast CPU feature tests" if EMBEDDED + default y + ---help--- + Some fast-paths in the kernel depend on the capabilities of the CPU. + Say Y here for the kernel to patch in the appropriate code at runtime + based on the capabilities of the CPU. The infrastructure for patching + code at runtime takes up some additional space; space-constrained + embedded systems may wish to say N here to produce smaller, slightly + slower code. + config X86_X2APIC bool "Support x2apic" depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) @@ -450,6 +475,7 @@ config X86_UV depends on X86_64 depends on X86_EXTENDED_PLATFORM depends on NUMA + depends on EFI depends on X86_X2APIC depends on PCI ---help--- @@ -484,11 +510,10 @@ config X86_INTEL_CE config X86_INTEL_MID bool "Intel MID platform support" - depends on X86_32 depends on X86_EXTENDED_PLATFORM depends on X86_PLATFORM_DEVICES depends on PCI - depends on PCI_GOANY + depends on X86_64 || (PCI_GOANY && X86_32) depends on X86_IO_APIC select SFI select I2C @@ -523,9 +548,10 @@ config X86_INTEL_QUARK config X86_INTEL_LPSS bool "Intel Low Power Subsystem Support" - depends on ACPI + depends on X86 && ACPI select COMMON_CLK select PINCTRL + select IOSF_MBI ---help--- Select to build support for Intel Low Power Subsystem such as found on Intel Lynxpoint PCH. Selecting this option enables @@ -687,6 +713,14 @@ 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 @@ -744,8 +778,8 @@ config HPET_TIMER HPET is the next generation timer replacing legacy 8254s. The HPET provides a stable time base on SMP systems, unlike the TSC, but it is more expensive to access, - as it is off-chip. You can find the HPET spec at - <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>. + as it is off-chip. The interface used is documented + in the HPET spec, revision 1. You can safely choose Y here. However, HPET will only be activated if the platform and the BIOS support this feature. @@ -2665,6 +2699,19 @@ config PMC_ATOM def_bool y depends on PCI +config VMD + depends on PCI_MSI + tristate "Volume Management Device Driver" + default N + ---help--- + Adds support for the Intel Volume Management Device (VMD). VMD is a + secondary PCI host bridge that allows PCI Express root ports, + and devices attached to them, to be removed from the default + PCI domain and placed within the VMD domain. This provides + more bus resources than are otherwise possible with a + single domain. If you know your system provides one of these and + has devices attached to it, say Y; if you are not sure, say N. + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 137dfa96a..9b18ed97a 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -5,23 +5,6 @@ config TRACE_IRQFLAGS_SUPPORT source "lib/Kconfig.debug" -config STRICT_DEVMEM - bool "Filter access to /dev/mem" - ---help--- - If this option is disabled, you allow userspace (root) access to all - of memory, including kernel and userspace memory. Accidental - access to this is obviously disastrous, but specific access can - be used by people debugging the kernel. Note that with PAT support - enabled, even in this case there are restrictions on /dev/mem - use due to the cache aliasing requirements. - - If this option is switched on, the /dev/mem file only allows - userspace access to PCI space and the BIOS code and data regions. - This is sufficient for dosemu and X and all common users of - /dev/mem. - - If in doubt, say Y. - config X86_VERBOSE_BOOTUP bool "Enable verbose x86 bootup info messages" default y @@ -69,7 +52,7 @@ config X86_PTDUMP_CORE def_bool n config X86_PTDUMP - bool "Export kernel pagetable layout to userspace via debugfs" + tristate "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL select DEBUG_FS select X86_PTDUMP_CORE diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 2ee62dba0..bbe1a62ef 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -60,6 +60,7 @@ clean-files += cpustr.h KBUILD_CFLAGS := $(USERINCLUDE) $(REALMODE_CFLAGS) -D_SETUP KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n +UBSAN_SANITIZE := n $(obj)/bzImage: asflags-y := $(SVGA_MODE) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0a291cdfa..f9ce75d80 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -33,6 +33,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n +UBSAN_SANITIZE :=n LDFLAGS := -m elf_$(UTS_MACHINE) LDFLAGS_vmlinux := -T diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 722bacea0..8baaff5af 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -125,7 +125,7 @@ static struct crypto_alg alg = { static int __init chacha20_simd_mod_init(void) { - if (!cpu_has_ssse3) + if (!boot_cpu_has(X86_FEATURE_SSSE3)) return -ENODEV; #ifdef CONFIG_AS_AVX2 diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 81a595d75..0e9871693 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -257,7 +257,7 @@ static int __init crc32c_intel_mod_init(void) if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; #ifdef CONFIG_X86_64 - if (cpu_has_pclmulqdq) { + if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { alg.update = crc32c_pcl_intel_update; alg.finup = crc32c_pcl_intel_finup; alg.digest = crc32c_pcl_intel_digest; diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 440df0c7a..a69321a77 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -219,6 +219,29 @@ static int ghash_async_final(struct ahash_request *req) } } +static int ghash_async_import(struct ahash_request *req, const void *in) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + ghash_async_init(req); + memcpy(dctx, in, sizeof(*dctx)); + return 0; + +} + +static int ghash_async_export(struct ahash_request *req, void *out) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + memcpy(out, dctx, sizeof(*dctx)); + return 0; + +} + static int ghash_async_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -288,8 +311,11 @@ static struct ahash_alg ghash_async_alg = { .final = ghash_async_final, .setkey = ghash_async_setkey, .digest = ghash_async_digest, + .export = ghash_async_export, + .import = ghash_async_import, .halg = { .digestsize = GHASH_DIGEST_SIZE, + .statesize = sizeof(struct ghash_desc_ctx), .base = { .cra_name = "ghash", .cra_driver_name = "ghash-clmulni", diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3c71dd947..e32206e09 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/entry_32.S b/arch/x86/entry/entry_32.S index f3b6d54e0..bb3e376d0 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -294,6 +294,7 @@ sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ + ASM_CLAC /* Clear AC after saving FLAGS */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ @@ -329,7 +330,8 @@ 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 $0, PT_FS(%esp) @@ -552,11 +554,6 @@ ENTRY(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) #endif ENTRY(overflow) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a55697d19..9d34d3cfc 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -520,9 +520,7 @@ END(irq_entries_start) */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode 1: /* @@ -1066,9 +1064,7 @@ ENTRY(error_entry) * (which can take locks). */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode ret .Lerror_entry_done: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 15cfebaa7..3c990eeee 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -18,13 +18,6 @@ .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) -#endif - /* * 32-bit SYSENTER instruction entry. * @@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat) * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * - * NB.: sysenter_fix_flags is a label with the code under it moved + * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ 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 @@ -126,10 +119,10 @@ sysenter_flags_fixed: "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) /* @@ -238,7 +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/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index f17705e13..cb713df81 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -383,3 +383,4 @@ 374 i386 userfaultfd sys_userfaultfd 375 i386 membarrier sys_membarrier 376 i386 mlock2 sys_mlock2 +377 i386 copy_file_range sys_copy_file_range diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 314a90bfc..dc1040a50 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -332,6 +332,7 @@ 323 common userfaultfd sys_userfaultfd 324 common membarrier sys_membarrier 325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 265c0ed68..c854541d9 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -4,6 +4,7 @@ KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n +UBSAN_SANITIZE := n VDSO64-$(CONFIG_X86_64) := y VDSOX32-$(CONFIG_X86_X32_ABI) := y diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index ca94fa649..1a50e09c9 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. + */ + + do { + version = pvti->version; + + smp_rmb(); + + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + + 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 de2c92102..4158acc17 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 785d9922b..491020b28 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/vma.c b/arch/x86/entry/vdso/vma.c index 64df47148..b8f69e264 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 a30316bf8..c80f6b6f3 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 ae5fb83e6..3e8674288 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 a11c30b77..a98411113 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/barrier.h b/arch/x86/include/asm/barrier.h index 0681d2532..a584e1c50 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -31,20 +31,10 @@ #endif #define dma_wmb() barrier() -#ifdef CONFIG_SMP -#define smp_mb() mb() -#define smp_rmb() dma_rmb() -#define smp_wmb() barrier() -#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) -#else /* !SMP */ -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) -#endif /* SMP */ - -#define read_barrier_depends() do { } while (0) -#define smp_read_barrier_depends() do { } while (0) +#define __smp_mb() mb() +#define __smp_rmb() dma_rmb() +#define __smp_wmb() barrier() +#define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) #if defined(CONFIG_X86_PPRO_FENCE) @@ -53,31 +43,31 @@ * model and we should fall back to full barriers. */ -#define smp_store_release(p, v) \ +#define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ - smp_mb(); \ + __smp_mb(); \ WRITE_ONCE(*p, v); \ } while (0) -#define smp_load_acquire(p) \ +#define __smp_load_acquire(p) \ ({ \ typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ - smp_mb(); \ + __smp_mb(); \ ___p1; \ }) #else /* regular x86 TSO memory ordering */ -#define smp_store_release(p, v) \ +#define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ barrier(); \ WRITE_ONCE(*p, v); \ } while (0) -#define smp_load_acquire(p) \ +#define __smp_load_acquire(p) \ ({ \ typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ @@ -88,7 +78,9 @@ do { \ #endif /* Atomic operations are already serializing on x86 */ -#define smp_mb__before_atomic() barrier() -#define smp_mb__after_atomic() barrier() +#define __smp_mb__before_atomic() barrier() +#define __smp_mb__after_atomic() barrier() + +#include <asm-generic/barrier.h> #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h index 0d467b338..a8303ebe0 100644 --- a/arch/x86/include/asm/calgary.h +++ b/arch/x86/include/asm/calgary.h @@ -31,7 +31,7 @@ #include <asm/types.h> struct iommu_table { - struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ + const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ unsigned long it_base; /* mapped address of tce table */ unsigned long it_hint; /* Hint for next alloc */ unsigned long *it_map; /* A simple allocation bitmap for now */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index f7e142926..e4959d023 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -109,6 +109,6 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) #endif -#define system_has_cmpxchg_double() cpu_has_cx8 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8) #endif /* _ASM_X86_CMPXCHG_32_H */ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 1af94697a..caa23a34c 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -18,6 +18,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) cmpxchg_local((ptr), (o), (n)); \ }) -#define system_has_cmpxchg_double() cpu_has_cx16 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) #endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index bf2caa1de..678637ad7 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -36,4 +36,7 @@ extern int _debug_hotplug_cpu(int cpu, int action); int mwait_usable(const struct cpuinfo_x86 *); +unsigned int x86_family(unsigned int sig); +unsigned int x86_model(unsigned int sig); +unsigned int x86_stepping(unsigned int sig); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index f7ba9fbf1..7ad8c9464 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include <asm/disabled-features.h> #endif -#define NCAPINTS 14 /* N 32-bit words worth of info */ +#define NCAPINTS 16 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -181,22 +181,17 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc, word 7 + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_IDA ( 7*32+ 0) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */ + #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_PLN ( 7*32+ 5) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */ + #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ -#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ -#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ -#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ + #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ /* Virtualization flags: Linux defined, word 8 */ @@ -205,16 +200,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT ( 8*32+ 5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV ( 8*32+ 6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML ( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS ( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ + #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -259,6 +245,30 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ + /* * BUG word(s) */ @@ -279,6 +289,26 @@ #include <asm/asm.h> #include <linux/bitops.h> +enum cpuid_leafs +{ + CPUID_1_EDX = 0, + CPUID_8000_0001_EDX, + CPUID_8086_0001_EDX, + CPUID_LNX_1, + CPUID_1_ECX, + CPUID_C000_0001_EDX, + CPUID_8000_0001_ECX, + CPUID_LNX_2, + CPUID_LNX_3, + CPUID_7_0_EBX, + CPUID_D_1_EAX, + CPUID_F_0_EDX, + CPUID_F_1_EDX, + CPUID_8000_0008_EBX, + CPUID_6_EAX, + CPUID_8000_000A_EDX, +}; + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; @@ -356,60 +386,31 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; } while (0) #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_de boot_cpu_has(X86_FEATURE_DE) #define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) #define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) #define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) #define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) -#define cpu_has_sep boot_cpu_has(X86_FEATURE_SEP) -#define cpu_has_mtrr boot_cpu_has(X86_FEATURE_MTRR) -#define cpu_has_mmx boot_cpu_has(X86_FEATURE_MMX) #define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR) #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) -#define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) -#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3) #define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) #define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) -#define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) -#define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) -#define cpu_has_xstore boot_cpu_has(X86_FEATURE_XSTORE) -#define cpu_has_xstore_enabled boot_cpu_has(X86_FEATURE_XSTORE_EN) -#define cpu_has_xcrypt boot_cpu_has(X86_FEATURE_XCRYPT) -#define cpu_has_xcrypt_enabled boot_cpu_has(X86_FEATURE_XCRYPT_EN) -#define cpu_has_ace2 boot_cpu_has(X86_FEATURE_ACE2) -#define cpu_has_ace2_enabled boot_cpu_has(X86_FEATURE_ACE2_EN) -#define cpu_has_phe boot_cpu_has(X86_FEATURE_PHE) -#define cpu_has_phe_enabled boot_cpu_has(X86_FEATURE_PHE_EN) -#define cpu_has_pmm boot_cpu_has(X86_FEATURE_PMM) -#define cpu_has_pmm_enabled boot_cpu_has(X86_FEATURE_PMM_EN) -#define cpu_has_ds boot_cpu_has(X86_FEATURE_DS) -#define cpu_has_pebs boot_cpu_has(X86_FEATURE_PEBS) #define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH) -#define cpu_has_bts boot_cpu_has(X86_FEATURE_BTS) #define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) #define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) #define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) -#define cpu_has_xmm4_1 boot_cpu_has(X86_FEATURE_XMM4_1) -#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) -#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) #define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) -#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) -#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) -#define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) -#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2) -#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) -#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) -#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) -#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) -#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT) - -#if __GNUC__ >= 4 +/* + * Do not add any more of those clumsy macros - use static_cpu_has_safe() for + * fast paths and boot_cpu_has() otherwise! + */ + +#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS) extern void warn_pre_alternatives(void); extern bool __static_cpu_has_safe(u16 bit); diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 03dd72957..684ed6c3a 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -10,6 +10,16 @@ struct dev_archdata { #endif }; +#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) +struct dma_domain { + struct list_head node; + struct dma_map_ops *dma_ops; + int domain_nr; +}; +void add_dma_domain(struct dma_domain *domain); +void del_dma_domain(struct dma_domain *domain); +#endif + struct pdev_archdata { }; diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 953b7263f..3a27b93e6 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -46,8 +46,6 @@ bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp); #define HAVE_ARCH_DMA_SUPPORTED 1 extern int dma_supported(struct device *hwdev, u64 mask); -#include <asm-generic/dma-mapping-common.h> - extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, struct dma_attrs *attrs); diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index f80d70009..6d7d0e52e 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/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 3c3550c3a..0fd440df6 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -42,6 +42,7 @@ extern void fpu__init_cpu_xstate(void); extern void fpu__init_system(struct cpuinfo_x86 *c); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); +extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: @@ -224,18 +225,67 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" -/* xstate instruction fault handler: */ -#define xstate_fault(__err) \ - \ - ".section .fixup,\"ax\"\n" \ - \ - "3: movl $-2,%[_err]\n" \ - " jmp 2b\n" \ - \ - ".previous\n" \ - \ - _ASM_EXTABLE(1b, 3b) \ - : [_err] "=r" (__err) +#define XSTATE_OP(op, st, lmask, hmask, err) \ + asm volatile("1:" op "\n\t" \ + "xor %[err], %[err]\n" \ + "2:\n\t" \ + ".pushsection .fixup,\"ax\"\n\t" \ + "3: movl $-2,%[err]\n\t" \ + "jmp 2b\n\t" \ + ".popsection\n\t" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact + * format and supervisor states in addition to modified optimization in + * XSAVEOPT. + * + * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT + * supports modified optimization which is not supported by XSAVE. + * + * We use XSAVE as a fallback. + * + * The 661 label is defined in the ALTERNATIVE* macros as the address of the + * original instruction which gets replaced. We need to use it here as the + * address of the instruction where we might get an exception at. + */ +#define XSTATE_XSAVE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE_2(XSAVE, \ + XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVES, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact + * XSAVE area format. + */ +#define XSTATE_XRESTORE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE(XRSTOR, \ + XRSTORS, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") /* * This function is called only during boot time when x86 caps are not set @@ -246,22 +296,14 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(system_state != SYSTEM_BOOTING); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XSAVES, xstate, lmask, hmask, err); else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XSAVE, xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -276,22 +318,14 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(system_state != SYSTEM_BOOTING); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -305,33 +339,11 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(!alternatives_patched); - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [xstate] "D" (xstate), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault(err) - : "0" (err) - : "memory"); + XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -344,23 +356,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault(err) - : "0" (err) - : "memory"); + XSTATE_XRESTORE(xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -388,12 +386,10 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf) if (unlikely(err)) return -EFAULT; - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault(err) - : "D" (buf), "a" (-1), "d" (-1), "0" (err) - : "memory"); + stac(); + XSTATE_OP(XSAVE, buf, -1, -1, err); + clac(); + return err; } @@ -405,14 +401,12 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault(err) - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); /* memory required? */ + int err; + + stac(); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + clac(); + return err; } diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index 3a6c89b70..f23cd8c80 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -22,7 +22,7 @@ #define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ - XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 1e3408e88..1815b7362 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -130,6 +130,11 @@ struct irq_alloc_info { char *uv_name; }; #endif +#if IS_ENABLED(CONFIG_VMD) + struct { + struct msi_desc *desc; + }; +#endif }; }; diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 000000000..e1a411786 --- /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/intel_punit_ipc.h b/arch/x86/include/asm/intel_punit_ipc.h new file mode 100644 index 000000000..201eb9dce --- /dev/null +++ b/arch/x86/include/asm/intel_punit_ipc.h @@ -0,0 +1,101 @@ +#ifndef _ASM_X86_INTEL_PUNIT_IPC_H_ +#define _ASM_X86_INTEL_PUNIT_IPC_H_ + +/* + * Three types of 8bit P-Unit IPC commands are supported, + * bit[7:6]: [00]: BIOS; [01]: GTD; [10]: ISPD. + */ +typedef enum { + BIOS_IPC = 0, + GTDRIVER_IPC, + ISPDRIVER_IPC, + RESERVED_IPC, +} IPC_TYPE; + +#define IPC_TYPE_OFFSET 6 +#define IPC_PUNIT_BIOS_CMD_BASE (BIOS_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_GTD_CMD_BASE (GTDDRIVER_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_ISPD_CMD_BASE (ISPDRIVER_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_CMD_TYPE_MASK (RESERVED_IPC << IPC_TYPE_OFFSET) + +/* BIOS => Pcode commands */ +#define IPC_PUNIT_BIOS_ZERO (IPC_PUNIT_BIOS_CMD_BASE | 0x00) +#define IPC_PUNIT_BIOS_VR_INTERFACE (IPC_PUNIT_BIOS_CMD_BASE | 0x01) +#define IPC_PUNIT_BIOS_READ_PCS (IPC_PUNIT_BIOS_CMD_BASE | 0x02) +#define IPC_PUNIT_BIOS_WRITE_PCS (IPC_PUNIT_BIOS_CMD_BASE | 0x03) +#define IPC_PUNIT_BIOS_READ_PCU_CONFIG (IPC_PUNIT_BIOS_CMD_BASE | 0x04) +#define IPC_PUNIT_BIOS_WRITE_PCU_CONFIG (IPC_PUNIT_BIOS_CMD_BASE | 0x05) +#define IPC_PUNIT_BIOS_READ_PL1_SETTING (IPC_PUNIT_BIOS_CMD_BASE | 0x06) +#define IPC_PUNIT_BIOS_WRITE_PL1_SETTING (IPC_PUNIT_BIOS_CMD_BASE | 0x07) +#define IPC_PUNIT_BIOS_TRIGGER_VDD_RAM (IPC_PUNIT_BIOS_CMD_BASE | 0x08) +#define IPC_PUNIT_BIOS_READ_TELE_INFO (IPC_PUNIT_BIOS_CMD_BASE | 0x09) +#define IPC_PUNIT_BIOS_READ_TELE_TRACE_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0a) +#define IPC_PUNIT_BIOS_WRITE_TELE_TRACE_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0b) +#define IPC_PUNIT_BIOS_READ_TELE_EVENT_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0c) +#define IPC_PUNIT_BIOS_WRITE_TELE_EVENT_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0d) +#define IPC_PUNIT_BIOS_READ_TELE_TRACE (IPC_PUNIT_BIOS_CMD_BASE | 0x0e) +#define IPC_PUNIT_BIOS_WRITE_TELE_TRACE (IPC_PUNIT_BIOS_CMD_BASE | 0x0f) +#define IPC_PUNIT_BIOS_READ_TELE_EVENT (IPC_PUNIT_BIOS_CMD_BASE | 0x10) +#define IPC_PUNIT_BIOS_WRITE_TELE_EVENT (IPC_PUNIT_BIOS_CMD_BASE | 0x11) +#define IPC_PUNIT_BIOS_READ_MODULE_TEMP (IPC_PUNIT_BIOS_CMD_BASE | 0x12) +#define IPC_PUNIT_BIOS_RESERVED (IPC_PUNIT_BIOS_CMD_BASE | 0x13) +#define IPC_PUNIT_BIOS_READ_VOLTAGE_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x14) +#define IPC_PUNIT_BIOS_WRITE_VOLTAGE_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x15) +#define IPC_PUNIT_BIOS_READ_RATIO_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x16) +#define IPC_PUNIT_BIOS_WRITE_RATIO_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x17) +#define IPC_PUNIT_BIOS_READ_VF_GL_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x18) +#define IPC_PUNIT_BIOS_WRITE_VF_GL_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x19) +#define IPC_PUNIT_BIOS_READ_FM_SOC_TEMP_THRESH (IPC_PUNIT_BIOS_CMD_BASE | 0x1a) +#define IPC_PUNIT_BIOS_WRITE_FM_SOC_TEMP_THRESH (IPC_PUNIT_BIOS_CMD_BASE | 0x1b) + +/* GT Driver => Pcode commands */ +#define IPC_PUNIT_GTD_ZERO (IPC_PUNIT_GTD_CMD_BASE | 0x00) +#define IPC_PUNIT_GTD_CONFIG (IPC_PUNIT_GTD_CMD_BASE | 0x01) +#define IPC_PUNIT_GTD_READ_ICCP_LIC_CDYN_SCAL (IPC_PUNIT_GTD_CMD_BASE | 0x02) +#define IPC_PUNIT_GTD_WRITE_ICCP_LIC_CDYN_SCAL (IPC_PUNIT_GTD_CMD_BASE | 0x03) +#define IPC_PUNIT_GTD_GET_WM_VAL (IPC_PUNIT_GTD_CMD_BASE | 0x06) +#define IPC_PUNIT_GTD_WRITE_CONFIG_WISHREQ (IPC_PUNIT_GTD_CMD_BASE | 0x07) +#define IPC_PUNIT_GTD_READ_REQ_DUTY_CYCLE (IPC_PUNIT_GTD_CMD_BASE | 0x16) +#define IPC_PUNIT_GTD_DIS_VOL_FREQ_CHG_REQUEST (IPC_PUNIT_GTD_CMD_BASE | 0x17) +#define IPC_PUNIT_GTD_DYNA_DUTY_CYCLE_CTRL (IPC_PUNIT_GTD_CMD_BASE | 0x1a) +#define IPC_PUNIT_GTD_DYNA_DUTY_CYCLE_TUNING (IPC_PUNIT_GTD_CMD_BASE | 0x1c) + +/* ISP Driver => Pcode commands */ +#define IPC_PUNIT_ISPD_ZERO (IPC_PUNIT_ISPD_CMD_BASE | 0x00) +#define IPC_PUNIT_ISPD_CONFIG (IPC_PUNIT_ISPD_CMD_BASE | 0x01) +#define IPC_PUNIT_ISPD_GET_ISP_LTR_VAL (IPC_PUNIT_ISPD_CMD_BASE | 0x02) +#define IPC_PUNIT_ISPD_ACCESS_IU_FREQ_BOUNDS (IPC_PUNIT_ISPD_CMD_BASE | 0x03) +#define IPC_PUNIT_ISPD_READ_CDYN_LEVEL (IPC_PUNIT_ISPD_CMD_BASE | 0x04) +#define IPC_PUNIT_ISPD_WRITE_CDYN_LEVEL (IPC_PUNIT_ISPD_CMD_BASE | 0x05) + +/* Error codes */ +#define IPC_PUNIT_ERR_SUCCESS 0 +#define IPC_PUNIT_ERR_INVALID_CMD 1 +#define IPC_PUNIT_ERR_INVALID_PARAMETER 2 +#define IPC_PUNIT_ERR_CMD_TIMEOUT 3 +#define IPC_PUNIT_ERR_CMD_LOCKED 4 +#define IPC_PUNIT_ERR_INVALID_VR_ID 5 +#define IPC_PUNIT_ERR_VR_ERR 6 + +#if IS_ENABLED(CONFIG_INTEL_PUNIT_IPC) + +int intel_punit_ipc_simple_command(int cmd, int para1, int para2); +int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out); + +#else + +static inline int intel_punit_ipc_simple_command(int cmd, + int para1, int para2) +{ + return -ENODEV; +} + +static inline int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, + u32 *in, u32 *out) +{ + return -ENODEV; +} + +#endif /* CONFIG_INTEL_PUNIT_IPC */ + +#endif diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h new file mode 100644 index 000000000..ed65fe701 --- /dev/null +++ b/arch/x86/include/asm/intel_telemetry.h @@ -0,0 +1,147 @@ +/* + * Intel SOC Telemetry Driver Header File + * Copyright (C) 2015, Intel Corporation. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ +#ifndef INTEL_TELEMETRY_H +#define INTEL_TELEMETRY_H + +#define TELEM_MAX_EVENTS_SRAM 28 +#define TELEM_MAX_OS_ALLOCATED_EVENTS 20 + +enum telemetry_unit { + TELEM_PSS = 0, + TELEM_IOSS, + TELEM_UNIT_NONE +}; + +struct telemetry_evtlog { + u32 telem_evtid; + u64 telem_evtlog; +}; + +struct telemetry_evtconfig { + /* Array of Event-IDs to Enable */ + u32 *evtmap; + + /* Number of Events (<29) in evtmap */ + u8 num_evts; + + /* Sampling period */ + u8 period; +}; + +struct telemetry_evtmap { + const char *name; + u32 evt_id; +}; + +struct telemetry_unit_config { + struct telemetry_evtmap *telem_evts; + void __iomem *regmap; + u32 ssram_base_addr; + u8 ssram_evts_used; + u8 curr_period; + u8 max_period; + u8 min_period; + u32 ssram_size; + +}; + +struct telemetry_plt_config { + struct telemetry_unit_config pss_config; + struct telemetry_unit_config ioss_config; + struct mutex telem_trace_lock; + struct mutex telem_lock; + bool telem_in_use; +}; + +struct telemetry_core_ops { + int (*get_sampling_period)(u8 *pss_min_period, u8 *pss_max_period, + u8 *ioss_min_period, u8 *ioss_max_period); + + int (*get_eventconfig)(struct telemetry_evtconfig *pss_evtconfig, + struct telemetry_evtconfig *ioss_evtconfig, + int pss_len, int ioss_len); + + int (*update_events)(struct telemetry_evtconfig pss_evtconfig, + struct telemetry_evtconfig ioss_evtconfig); + + int (*set_sampling_period)(u8 pss_period, u8 ioss_period); + + int (*get_trace_verbosity)(enum telemetry_unit telem_unit, + u32 *verbosity); + + int (*set_trace_verbosity)(enum telemetry_unit telem_unit, + u32 verbosity); + + int (*raw_read_eventlog)(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, + int len, int log_all_evts); + + int (*read_eventlog)(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, + int len, int log_all_evts); + + int (*add_events)(u8 num_pss_evts, u8 num_ioss_evts, + u32 *pss_evtmap, u32 *ioss_evtmap); + + int (*reset_events)(void); +}; + +int telemetry_set_pltdata(struct telemetry_core_ops *ops, + struct telemetry_plt_config *pltconfig); + +int telemetry_clear_pltdata(void); + +int telemetry_pltconfig_valid(void); + +int telemetry_get_evtname(enum telemetry_unit telem_unit, + const char **name, int len); + +int telemetry_update_events(struct telemetry_evtconfig pss_evtconfig, + struct telemetry_evtconfig ioss_evtconfig); + +int telemetry_add_events(u8 num_pss_evts, u8 num_ioss_evts, + u32 *pss_evtmap, u32 *ioss_evtmap); + +int telemetry_reset_events(void); + +int telemetry_get_eventconfig(struct telemetry_evtconfig *pss_config, + struct telemetry_evtconfig *ioss_config, + int pss_len, int ioss_len); + +int telemetry_read_events(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_raw_read_events(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_read_eventlog(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_raw_read_eventlog(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_get_sampling_period(u8 *pss_min_period, u8 *pss_max_period, + u8 *ioss_min_period, u8 *ioss_max_period); + +int telemetry_set_sampling_period(u8 pss_period, u8 ioss_period); + +int telemetry_set_trace_verbosity(enum telemetry_unit telem_unit, + u32 verbosity); + +int telemetry_get_trace_verbosity(enum telemetry_unit telem_unit, + u32 *verbosity); + +#endif /* INTEL_TELEMETRY_H */ diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index b72ad0faa..b41ee1649 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -1,5 +1,5 @@ /* - * iosf_mbi.h: Intel OnChip System Fabric MailBox access support + * Intel OnChip System Fabric MailBox access support */ #ifndef IOSF_MBI_SYMS_H @@ -16,6 +16,18 @@ #define MBI_MASK_LO 0x000000FF #define MBI_ENABLE 0xF0 +/* IOSF SB read/write opcodes */ +#define MBI_MMIO_READ 0x00 +#define MBI_MMIO_WRITE 0x01 +#define MBI_CFG_READ 0x04 +#define MBI_CFG_WRITE 0x05 +#define MBI_CR_READ 0x06 +#define MBI_CR_WRITE 0x07 +#define MBI_REG_READ 0x10 +#define MBI_REG_WRITE 0x11 +#define MBI_ESRAM_READ 0x12 +#define MBI_ESRAM_WRITE 0x13 + /* Baytrail available units */ #define BT_MBI_UNIT_AUNIT 0x00 #define BT_MBI_UNIT_SMC 0x01 @@ -28,50 +40,13 @@ #define BT_MBI_UNIT_SATA 0xA3 #define BT_MBI_UNIT_PCIE 0xA6 -/* Baytrail read/write opcodes */ -#define BT_MBI_AUNIT_READ 0x10 -#define BT_MBI_AUNIT_WRITE 0x11 -#define BT_MBI_SMC_READ 0x10 -#define BT_MBI_SMC_WRITE 0x11 -#define BT_MBI_CPU_READ 0x10 -#define BT_MBI_CPU_WRITE 0x11 -#define BT_MBI_BUNIT_READ 0x10 -#define BT_MBI_BUNIT_WRITE 0x11 -#define BT_MBI_PMC_READ 0x06 -#define BT_MBI_PMC_WRITE 0x07 -#define BT_MBI_GFX_READ 0x00 -#define BT_MBI_GFX_WRITE 0x01 -#define BT_MBI_SMIO_READ 0x06 -#define BT_MBI_SMIO_WRITE 0x07 -#define BT_MBI_USB_READ 0x06 -#define BT_MBI_USB_WRITE 0x07 -#define BT_MBI_SATA_READ 0x00 -#define BT_MBI_SATA_WRITE 0x01 -#define BT_MBI_PCIE_READ 0x00 -#define BT_MBI_PCIE_WRITE 0x01 - /* Quark available units */ #define QRK_MBI_UNIT_HBA 0x00 #define QRK_MBI_UNIT_HB 0x03 #define QRK_MBI_UNIT_RMU 0x04 #define QRK_MBI_UNIT_MM 0x05 -#define QRK_MBI_UNIT_MMESRAM 0x05 #define QRK_MBI_UNIT_SOC 0x31 -/* Quark read/write opcodes */ -#define QRK_MBI_HBA_READ 0x10 -#define QRK_MBI_HBA_WRITE 0x11 -#define QRK_MBI_HB_READ 0x10 -#define QRK_MBI_HB_WRITE 0x11 -#define QRK_MBI_RMU_READ 0x10 -#define QRK_MBI_RMU_WRITE 0x11 -#define QRK_MBI_MM_READ 0x10 -#define QRK_MBI_MM_WRITE 0x11 -#define QRK_MBI_MMESRAM_READ 0x12 -#define QRK_MBI_MMESRAM_WRITE 0x13 -#define QRK_MBI_SOC_READ 0x06 -#define QRK_MBI_SOC_WRITE 0x07 - #if IS_ENABLED(CONFIG_IOSF_MBI) bool iosf_mbi_available(void); diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 615fa9061..cfc9a0d2d 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 5daeca3d0..adc54c12c 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/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 30cfd6429..44adbb819 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -25,6 +25,7 @@ #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> #include <linux/irqbypass.h> +#include <linux/hyperv.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> @@ -45,6 +46,31 @@ #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS +/* x86-specific vcpu->requests bit members */ +#define KVM_REQ_MIGRATE_TIMER 8 +#define KVM_REQ_REPORT_TPR_ACCESS 9 +#define KVM_REQ_TRIPLE_FAULT 10 +#define KVM_REQ_MMU_SYNC 11 +#define KVM_REQ_CLOCK_UPDATE 12 +#define KVM_REQ_DEACTIVATE_FPU 13 +#define KVM_REQ_EVENT 14 +#define KVM_REQ_APF_HALT 15 +#define KVM_REQ_STEAL_UPDATE 16 +#define KVM_REQ_NMI 17 +#define KVM_REQ_PMU 18 +#define KVM_REQ_PMI 19 +#define KVM_REQ_SMI 20 +#define KVM_REQ_MASTERCLOCK_UPDATE 21 +#define KVM_REQ_MCLOCK_INPROGRESS 22 +#define KVM_REQ_SCAN_IOAPIC 23 +#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24 +#define KVM_REQ_APIC_PAGE_RELOAD 25 +#define KVM_REQ_HV_CRASH 26 +#define KVM_REQ_IOAPIC_EOI_EXIT 27 +#define KVM_REQ_HV_RESET 28 +#define KVM_REQ_HV_EXIT 29 +#define KVM_REQ_HV_STIMER 30 + #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ @@ -213,6 +239,10 @@ union kvm_mmu_page_role { }; }; +struct kvm_rmap_head { + unsigned long val; +}; + struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; @@ -230,7 +260,7 @@ struct kvm_mmu_page { bool unsync; int root_count; /* Currently serving as active root */ unsigned int unsync_children; - unsigned long parent_ptes; /* Reverse mapping for parent_pte */ + struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ unsigned long mmu_valid_gen; @@ -374,10 +404,38 @@ struct kvm_mtrr { struct list_head head; }; +/* Hyper-V SynIC timer */ +struct kvm_vcpu_hv_stimer { + struct hrtimer timer; + int index; + u64 config; + u64 count; + u64 exp_time; + struct hv_message msg; + bool msg_pending; +}; + +/* Hyper-V synthetic interrupt controller (SynIC)*/ +struct kvm_vcpu_hv_synic { + u64 version; + u64 control; + u64 msg_page; + u64 evt_page; + atomic64_t sint[HV_SYNIC_SINT_COUNT]; + atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT]; + DECLARE_BITMAP(auto_eoi_bitmap, 256); + DECLARE_BITMAP(vec_bitmap, 256); + bool active; +}; + /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { u64 hv_vapic; s64 runtime_offset; + struct kvm_vcpu_hv_synic synic; + struct kvm_hyperv_exit exit; + struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; + DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); }; struct kvm_vcpu_arch { @@ -400,7 +458,8 @@ struct kvm_vcpu_arch { u64 efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ - u64 eoi_exit_bitmap[4]; + bool apicv_active; + DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; int32_t apic_arb_prio; int mp_state; @@ -589,7 +648,7 @@ struct kvm_lpage_info { }; struct kvm_arch_memory_slot { - unsigned long *rmap[KVM_NR_PAGE_SIZES]; + struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; @@ -831,10 +890,11 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - int (*cpu_uses_apicv)(struct kvm_vcpu *vcpu); + bool (*get_enable_apicv)(void); + void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm *kvm, int isr); - void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu); + void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); @@ -1086,6 +1146,8 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); +void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, @@ -1231,6 +1293,9 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); +void kvm_make_mclock_inprogress_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request(struct kvm *kvm); + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h index 3bbc07a57..73d0c9b92 100644 --- a/arch/x86/include/asm/lguest.h +++ b/arch/x86/include/asm/lguest.h @@ -12,7 +12,9 @@ #define GUEST_PL 1 /* Page for Switcher text itself, then two pages per cpu */ -#define TOTAL_SWITCHER_PAGES (1 + 2 * nr_cpu_ids) +#define SWITCHER_TEXT_PAGES (1) +#define SWITCHER_STACK_PAGES (2 * nr_cpu_ids) +#define TOTAL_SWITCHER_PAGES (SWITCHER_TEXT_PAGES + SWITCHER_STACK_PAGES) /* Where we map the Switcher, in both Host and Guest. */ extern unsigned long switcher_addr; diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h index 19c099afa..e795f5274 100644 --- a/arch/x86/include/asm/livepatch.h +++ b/arch/x86/include/asm/livepatch.h @@ -41,7 +41,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } #else -#error Live patching support is disabled; check CONFIG_LIVEPATCH +#error Include linux/livepatch.h, not asm/livepatch.h #endif #endif /* _ASM_X86_LIVEPATCH_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 34e62b1dc..1e1b07a5a 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <asm/cpu.h> #include <linux/earlycpio.h> #define native_rdmsr(msr, val1, val2) \ @@ -95,14 +96,14 @@ static inline void __exit exit_amd_microcode(void) {} /* * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. - * x86_vendor() gets vendor id for BSP. + * x86_cpuid_vendor() gets vendor id for BSP. * * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify - * coding, we still use x86_vendor() to get vendor id for AP. + * coding, we still use x86_cpuid_vendor() to get vendor id for AP. * - * x86_vendor() gets vendor information directly from CPUID. + * x86_cpuid_vendor() gets vendor information directly from CPUID. */ -static inline int x86_vendor(void) +static inline int x86_cpuid_vendor(void) { u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; @@ -118,40 +119,14 @@ static inline int x86_vendor(void) return X86_VENDOR_UNKNOWN; } -static inline unsigned int __x86_family(unsigned int sig) -{ - unsigned int x86; - - x86 = (sig >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (sig >> 20) & 0xff; - - return x86; -} - -static inline unsigned int x86_family(void) +static inline unsigned int x86_cpuid_family(void) { u32 eax = 0x00000001; u32 ebx, ecx = 0, edx; native_cpuid(&eax, &ebx, &ecx, &edx); - return __x86_family(eax); -} - -static inline unsigned int x86_model(unsigned int sig) -{ - unsigned int x86, model; - - x86 = __x86_family(sig); - - model = (sig >> 4) & 0xf; - - if (x86 == 0x6 || x86 == 0xf) - model += ((sig >> 16) & 0xf) << 4; - - return model; + return x86_family(eax); } #ifdef CONFIG_MICROCODE diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 93724cc62..eb4b09b41 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-index.h b/arch/x86/include/asm/msr-index.h index 690b4027e..b05402ef3 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -321,6 +321,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 000000000..756722574 --- /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 77d8b284e..93fb7c1cf 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -32,6 +32,16 @@ struct msr_regs_info { int err; }; +struct saved_msr { + bool valid; + struct msr_info info; +}; + +struct saved_msrs { + unsigned int num; + struct saved_msr *array; +}; + static inline unsigned long long native_read_tscp(unsigned int *aux) { unsigned long low, high; @@ -57,11 +67,34 @@ 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 +111,8 @@ 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 +120,8 @@ 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 +139,8 @@ 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 +199,8 @@ 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); } @@ -190,7 +231,7 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high) static inline void wrmsrl(unsigned msr, u64 val) { - native_write_msr(msr, (u32)val, (u32)(val >> 32)); + native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); } /* wrmsr with exception handling */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index cc071c6f7..7bd009938 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -5,9 +5,9 @@ #include <linux/types.h> /* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_SHIFT 12 +#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) #define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c759b3cca..f61925021 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -291,15 +291,6 @@ static inline void slow_down_io(void) #endif } -#ifdef CONFIG_SMP -static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, - unsigned long start_esp) -{ - PVOP_VCALL3(pv_apic_ops.startup_ipi_hook, - phys_apicid, start_eip, start_esp); -} -#endif - static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { @@ -381,23 +372,6 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr, { PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep); } -static inline void pmd_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp); -} - -static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep); -} - -static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp); -} static inline pte_t __pte(pteval_t val) { @@ -928,23 +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 3d4419118..77db5616a 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -162,15 +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 @@ -179,14 +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); @@ -220,14 +203,6 @@ struct pv_irq_ops { #endif }; -struct pv_apic_ops { -#ifdef CONFIG_X86_LOCAL_APIC - void (*startup_ipi_hook)(int phys_apicid, - unsigned long start_eip, - unsigned long start_esp); -#endif -}; - struct pv_mmu_ops { unsigned long (*read_cr2)(void); void (*write_cr2)(unsigned long); @@ -279,12 +254,6 @@ struct pv_mmu_ops { pmd_t *pmdp, pmd_t pmdval); void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); - void (*pte_update_defer)(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); - void (*pmd_update)(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp); - void (*pmd_update_defer)(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp); pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); @@ -359,7 +328,6 @@ struct paravirt_patch_template { struct pv_time_ops pv_time_ops; struct pv_cpu_ops pv_cpu_ops; struct pv_irq_ops pv_irq_ops; - struct pv_apic_ops pv_apic_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; }; @@ -369,7 +337,6 @@ extern struct pv_init_ops pv_init_ops; extern struct pv_time_ops pv_time_ops; extern struct pv_cpu_ops pv_cpu_ops; extern struct pv_irq_ops pv_irq_ops; -extern struct pv_apic_ops pv_apic_ops; extern struct pv_mmu_ops pv_mmu_ops; extern struct pv_lock_ops pv_lock_ops; @@ -407,10 +374,8 @@ extern struct pv_lock_ops pv_lock_ops; __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) -unsigned paravirt_patch_nop(void); unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); -unsigned paravirt_patch_ignore(unsigned len); unsigned paravirt_patch_call(void *insnbuf, const void *target, u16 tgt_clobbers, unsigned long addr, u16 site_clobbers, diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index fa1195dae..d08eacd29 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); @@ -151,11 +153,11 @@ extern struct list_head pci_mmcfg_list; #define PCI_MMCFG_BUS_OFFSET(bus) ((bus) << 20) /* - * AMD Fam10h CPUs are buggy, and cannot access MMIO config space - * on their northbrige except through the * %eax register. As such, you MUST - * NOT use normal IOMEM accesses, you need to only use the magic mmio-config - * accessor functions. - * In fact just use pci_config_*, nothing else please. + * On AMD Fam10h CPUs, all PCI MMIO configuration space accesses must use + * %eax. No other source or target registers may be used. The following + * mmio_config_* accessors enforce this. See "BIOS and Kernel Developer's + * Guide (BKDG) For AMD Family 10h Processors", rev. 3.48, sec 2.11.1, + * "MMIO Configuration Coding Requirements". */ static inline unsigned char mmio_config_readb(void __iomem *pos) { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6ec0c8b2e..0687c4748 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -69,9 +69,6 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pmd_clear(pmd) native_pmd_clear(pmd) #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) -#define pmd_update(mm, addr, ptep) do { } while (0) -#define pmd_update_defer(mm, addr, ptep) do { } while (0) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) @@ -165,20 +162,22 @@ static inline int pmd_large(pmd_t pte) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int pmd_trans_splitting(pmd_t pmd) -{ - return pmd_val(pmd) & _PAGE_SPLITTING; -} - static inline int pmd_trans_huge(pmd_t pmd) { - return pmd_val(pmd) & _PAGE_PSE; + return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } static inline int has_transparent_hugepage(void) { return cpu_has_pse; } + +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pmd_devmap(pmd_t pmd) +{ + return !!(pmd_val(pmd) & _PAGE_DEVMAP); +} +#endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) @@ -255,6 +254,11 @@ static inline pte_t pte_mkspecial(pte_t pte) return pte_set_flags(pte, _PAGE_SPECIAL); } +static inline pte_t pte_mkdevmap(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); +} + static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); @@ -274,6 +278,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_ACCESSED); } +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_DIRTY); +} + static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); @@ -284,6 +293,11 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } +static inline pmd_t pmd_mkdevmap(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_DEVMAP); +} + static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); @@ -465,6 +479,13 @@ static inline int pte_present(pte_t a) return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } +#ifdef __HAVE_ARCH_PTE_DEVMAP +static inline int pte_devmap(pte_t a) +{ + return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; +} +#endif + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -731,14 +752,9 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr, * updates should either be sets, clears, or set_pte_atomic for P->P * transitions, which means this hook should only be called for user PTEs. * This hook implies a P->P protection or access change has taken place, which - * requires a subsequent TLB flush. The notification can optionally be delayed - * until the TLB flush event by using the pte_update_defer form of the - * interface, but care must be taken to assure that the flush happens while - * still holding the same page table lock so that the shadow and primary pages - * do not become out of sync on SMP. + * requires a subsequent TLB flush. */ #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) #endif /* @@ -816,10 +832,6 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); -#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH -extern void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmdp); - #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { @@ -830,9 +842,7 @@ static inline int pmd_write(pmd_t pmd) static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = native_pmdp_get_and_clear(pmdp); - pmd_update(mm, addr, pmdp); - return pmd; + return native_pmdp_get_and_clear(pmdp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -840,7 +850,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); - pmd_update(mm, addr, pmdp); } /* diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 79c91853e..4432ab7f4 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -22,10 +22,11 @@ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ -#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +#define _PAGE_BIT_SOFTW4 58 /* available for programmer */ +#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ @@ -46,7 +47,6 @@ #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) -#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) #define __HAVE_ARCH_PTE_SPECIAL #ifdef CONFIG_KMEMCHECK @@ -85,8 +85,11 @@ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) +#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) +#define __HAVE_ARCH_PTE_DEVMAP #else #define _PAGE_NX (_AT(pteval_t, 0)) +#define _PAGE_DEVMAP (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) diff --git a/arch/x86/include/asm/platform_sst_audio.h b/arch/x86/include/asm/platform_sst_audio.h index 7249e6d09..5973a2f3d 100644 --- a/arch/x86/include/asm/platform_sst_audio.h +++ b/arch/x86/include/asm/platform_sst_audio.h @@ -55,6 +55,7 @@ enum sst_audio_device_id_mrfld { PIPE_MEDIA0_IN = 0x8F, PIPE_MEDIA1_IN = 0x90, PIPE_MEDIA2_IN = 0x91, + PIPE_MEDIA3_IN = 0x9C, PIPE_RSVD = 0xFF, }; diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h index d8ce3ec81..c57fd1ea9 100644 --- a/arch/x86/include/asm/pmem.h +++ b/arch/x86/include/asm/pmem.h @@ -67,18 +67,19 @@ static inline void arch_wmb_pmem(void) } /** - * __arch_wb_cache_pmem - write back a cache range with CLWB + * arch_wb_cache_pmem - write back a cache range with CLWB * @vaddr: virtual start address * @size: number of bytes to write back * * Write back a cache range using the CLWB (cache line write back) * instruction. This function requires explicit ordering with an - * arch_wmb_pmem() call. This API is internal to the x86 PMEM implementation. + * arch_wmb_pmem() call. */ -static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) +static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size) { u16 x86_clflush_size = boot_cpu_data.x86_clflush_size; unsigned long clflush_mask = x86_clflush_size - 1; + void *vaddr = (void __force *)addr; void *vend = vaddr + size; void *p; @@ -115,7 +116,7 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, len = copy_from_iter_nocache(vaddr, bytes, i); if (__iter_needs_pmem_wb(i)) - __arch_wb_cache_pmem(vaddr, bytes); + arch_wb_cache_pmem(addr, bytes); return len; } @@ -132,13 +133,8 @@ static inline void arch_clear_pmem(void __pmem *addr, size_t size) { void *vaddr = (void __force *)addr; - /* TODO: implement the zeroing via non-temporal writes */ - if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) - clear_page(vaddr); - else - memset(vaddr, 0, size); - - __arch_wb_cache_pmem(vaddr, size); + memset(vaddr, 0, size); + arch_wb_cache_pmem(addr, size); } static inline bool __arch_has_wmb_pmem(void) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 2d5a50cb6..20c11d1aa 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -766,7 +766,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); * Return saved PC of a blocked thread. * What is this good for? it will be always the scheduler or ret_from_fork. */ -#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.sp - 8)) +#define thread_saved_pc(t) READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8)) #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5c0..fdcc04020 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 b002e711b..9f92c180e 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 a82c4f1b4..2cb1cc253 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/smp.h b/arch/x86/include/asm/smp.h index 222a6a3ca..dfcf07276 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,15 +21,6 @@ extern int smp_num_siblings; extern unsigned int num_processors; -static inline bool cpu_has_ht_siblings(void) -{ - bool has_siblings = false; -#ifdef CONFIG_SMP - has_siblings = cpu_has_ht && smp_num_siblings > 1; -#endif - return has_siblings; -} - DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); /* cpus sharing the last level cache: */ @@ -74,9 +65,6 @@ struct smp_ops { extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP -#ifndef CONFIG_PARAVIRT -#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0) -#endif extern struct smp_ops smp_ops; static inline void smp_send_stop(void) diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index d1793f068..8e9dbe7b7 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,6 +15,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; u16 ldt; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7ebf0ebe4..6136a1815 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -24,6 +24,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4, cr8; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 09b1b0ab9..a4a30e4b2 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -134,6 +134,9 @@ extern int __get_user_4(void); extern int __get_user_8(void); extern int __get_user_bad(void); +#define __uaccess_begin() stac() +#define __uaccess_end() clac() + /* * This is a type: either unsigned long, if the argument fits into * that type, or otherwise unsigned long long. @@ -193,10 +196,10 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) #ifdef CONFIG_X86_32 #define __put_user_asm_u64(x, addr, err, errret) \ - asm volatile(ASM_STAC "\n" \ + asm volatile("\n" \ "1: movl %%eax,0(%2)\n" \ "2: movl %%edx,4(%2)\n" \ - "3: " ASM_CLAC "\n" \ + "3:" \ ".section .fixup,\"ax\"\n" \ "4: movl %3,%0\n" \ " jmp 3b\n" \ @@ -207,10 +210,10 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) : "A" (x), "r" (addr), "i" (errret), "0" (err)) #define __put_user_asm_ex_u64(x, addr) \ - asm volatile(ASM_STAC "\n" \ + asm volatile("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ - "3: " ASM_CLAC "\n" \ + "3:" \ _ASM_EXTABLE_EX(1b, 2b) \ _ASM_EXTABLE_EX(2b, 3b) \ : : "A" (x), "r" (addr)) @@ -304,6 +307,10 @@ do { \ } \ } while (0) +/* + * This doesn't do __uaccess_begin/end - the exception handling + * around it must do that. + */ #define __put_user_size_ex(x, ptr, size) \ do { \ __chk_user_ptr(ptr); \ @@ -358,9 +365,9 @@ do { \ } while (0) #define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile(ASM_STAC "\n" \ + asm volatile("\n" \ "1: mov"itype" %2,%"rtype"1\n" \ - "2: " ASM_CLAC "\n" \ + "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %3,%0\n" \ " xor"itype" %"rtype"1,%"rtype"1\n" \ @@ -370,6 +377,10 @@ do { \ : "=r" (err), ltype(x) \ : "m" (__m(addr)), "i" (errret), "0" (err)) +/* + * This doesn't do __uaccess_begin/end - the exception handling + * around it must do that. + */ #define __get_user_size_ex(x, ptr, size) \ do { \ __chk_user_ptr(ptr); \ @@ -400,7 +411,9 @@ do { \ #define __put_user_nocheck(x, ptr, size) \ ({ \ int __pu_err; \ + __uaccess_begin(); \ __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ + __uaccess_end(); \ __builtin_expect(__pu_err, 0); \ }) @@ -408,7 +421,9 @@ do { \ ({ \ int __gu_err; \ unsigned long __gu_val; \ + __uaccess_begin(); \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ + __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __builtin_expect(__gu_err, 0); \ }) @@ -423,9 +438,9 @@ struct __large_struct { unsigned long buf[100]; }; * aliasing issues. */ #define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile(ASM_STAC "\n" \ + asm volatile("\n" \ "1: mov"itype" %"rtype"1,%2\n" \ - "2: " ASM_CLAC "\n" \ + "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %3,%0\n" \ " jmp 2b\n" \ @@ -445,11 +460,11 @@ struct __large_struct { unsigned long buf[100]; }; */ #define uaccess_try do { \ current_thread_info()->uaccess_err = 0; \ - stac(); \ + __uaccess_begin(); \ barrier(); #define uaccess_catch(err) \ - clac(); \ + __uaccess_end(); \ (err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0); \ } while (0) @@ -547,12 +562,13 @@ extern void __cmpxchg_wrong_size(void) __typeof__(ptr) __uval = (uval); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ + __uaccess_begin(); \ switch (size) { \ case 1: \ { \ - asm volatile("\t" ASM_STAC "\n" \ + asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n" \ - "2:\t" ASM_CLAC "\n" \ + "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ @@ -566,9 +582,9 @@ extern void __cmpxchg_wrong_size(void) } \ case 2: \ { \ - asm volatile("\t" ASM_STAC "\n" \ + asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n" \ - "2:\t" ASM_CLAC "\n" \ + "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ @@ -582,9 +598,9 @@ extern void __cmpxchg_wrong_size(void) } \ case 4: \ { \ - asm volatile("\t" ASM_STAC "\n" \ + asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" \ - "2:\t" ASM_CLAC "\n" \ + "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ @@ -601,9 +617,9 @@ extern void __cmpxchg_wrong_size(void) if (!IS_ENABLED(CONFIG_X86_64)) \ __cmpxchg_wrong_size(); \ \ - asm volatile("\t" ASM_STAC "\n" \ + asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" \ - "2:\t" ASM_CLAC "\n" \ + "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ @@ -618,6 +634,7 @@ extern void __cmpxchg_wrong_size(void) default: \ __cmpxchg_wrong_size(); \ } \ + __uaccess_end(); \ *__uval = __old; \ __ret; \ }) @@ -745,5 +762,39 @@ 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 + +/* + * The "unsafe" user accesses aren't really "unsafe", but the naming + * is a big fat warning: you have to not only do the access_ok() + * checking before using them, but you have to surround them with the + * user_access_begin/end() pair. + */ +#define user_access_begin() __uaccess_begin() +#define user_access_end() __uaccess_end() + +#define unsafe_put_user(x, ptr) \ +({ \ + int __pu_err; \ + __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ + __builtin_expect(__pu_err, 0); \ +}) + +#define unsafe_get_user(x, ptr) \ +({ \ + int __gu_err; \ + unsigned long __gu_val; \ + __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ + __builtin_expect(__gu_err, 0); \ +}) + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index f5dcb5204..3fe0eac59 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); + __uaccess_end(); return ret; case 8: + __uaccess_begin(); __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret, 8); + __uaccess_end(); return ret; } } @@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f2f9b39b2..b89c34c40 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -56,35 +56,49 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) if (!__builtin_constant_p(size)) return copy_user_generic(dst, (__force void *)src, size); switch (size) { - case 1:__get_user_asm(*(u8 *)dst, (u8 __user *)src, + case 1: + __uaccess_begin(); + __get_user_asm(*(u8 *)dst, (u8 __user *)src, ret, "b", "b", "=q", 1); + __uaccess_end(); return ret; - case 2:__get_user_asm(*(u16 *)dst, (u16 __user *)src, + case 2: + __uaccess_begin(); + __get_user_asm(*(u16 *)dst, (u16 __user *)src, ret, "w", "w", "=r", 2); + __uaccess_end(); return ret; - case 4:__get_user_asm(*(u32 *)dst, (u32 __user *)src, + case 4: + __uaccess_begin(); + __get_user_asm(*(u32 *)dst, (u32 __user *)src, ret, "l", "k", "=r", 4); + __uaccess_end(); return ret; - case 8:__get_user_asm(*(u64 *)dst, (u64 __user *)src, + case 8: + __uaccess_begin(); + __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 8); + __uaccess_end(); return ret; case 10: + __uaccess_begin(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 10); - if (unlikely(ret)) - return ret; - __get_user_asm(*(u16 *)(8 + (char *)dst), - (u16 __user *)(8 + (char __user *)src), - ret, "w", "w", "=r", 2); + if (likely(!ret)) + __get_user_asm(*(u16 *)(8 + (char *)dst), + (u16 __user *)(8 + (char __user *)src), + ret, "w", "w", "=r", 2); + __uaccess_end(); return ret; case 16: + __uaccess_begin(); __get_user_asm(*(u64 *)dst, (u64 __user *)src, ret, "q", "", "=r", 16); - if (unlikely(ret)) - return ret; - __get_user_asm(*(u64 *)(8 + (char *)dst), - (u64 __user *)(8 + (char __user *)src), - ret, "q", "", "=r", 8); + if (likely(!ret)) + __get_user_asm(*(u64 *)(8 + (char *)dst), + (u64 __user *)(8 + (char __user *)src), + ret, "q", "", "=r", 8); + __uaccess_end(); return ret; default: return copy_user_generic(dst, (__force void *)src, size); @@ -106,35 +120,51 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size) if (!__builtin_constant_p(size)) return copy_user_generic((__force void *)dst, src, size); switch (size) { - case 1:__put_user_asm(*(u8 *)src, (u8 __user *)dst, + case 1: + __uaccess_begin(); + __put_user_asm(*(u8 *)src, (u8 __user *)dst, ret, "b", "b", "iq", 1); + __uaccess_end(); return ret; - case 2:__put_user_asm(*(u16 *)src, (u16 __user *)dst, + case 2: + __uaccess_begin(); + __put_user_asm(*(u16 *)src, (u16 __user *)dst, ret, "w", "w", "ir", 2); + __uaccess_end(); return ret; - case 4:__put_user_asm(*(u32 *)src, (u32 __user *)dst, + case 4: + __uaccess_begin(); + __put_user_asm(*(u32 *)src, (u32 __user *)dst, ret, "l", "k", "ir", 4); + __uaccess_end(); return ret; - case 8:__put_user_asm(*(u64 *)src, (u64 __user *)dst, + case 8: + __uaccess_begin(); + __put_user_asm(*(u64 *)src, (u64 __user *)dst, ret, "q", "", "er", 8); + __uaccess_end(); return ret; case 10: + __uaccess_begin(); __put_user_asm(*(u64 *)src, (u64 __user *)dst, ret, "q", "", "er", 10); - if (unlikely(ret)) - return ret; - asm("":::"memory"); - __put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst, - ret, "w", "w", "ir", 2); + if (likely(!ret)) { + asm("":::"memory"); + __put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst, + ret, "w", "w", "ir", 2); + } + __uaccess_end(); return ret; case 16: + __uaccess_begin(); __put_user_asm(*(u64 *)src, (u64 __user *)dst, ret, "q", "", "er", 16); - if (unlikely(ret)) - return ret; - asm("":::"memory"); - __put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst, - ret, "q", "", "er", 8); + if (likely(!ret)) { + asm("":::"memory"); + __put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst, + ret, "q", "", "er", 8); + } + __uaccess_end(); return ret; default: return copy_user_generic((__force void *)dst, src, size); @@ -160,39 +190,47 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size) switch (size) { case 1: { u8 tmp; + __uaccess_begin(); __get_user_asm(tmp, (u8 __user *)src, ret, "b", "b", "=q", 1); if (likely(!ret)) __put_user_asm(tmp, (u8 __user *)dst, ret, "b", "b", "iq", 1); + __uaccess_end(); return ret; } case 2: { u16 tmp; + __uaccess_begin(); __get_user_asm(tmp, (u16 __user *)src, ret, "w", "w", "=r", 2); if (likely(!ret)) __put_user_asm(tmp, (u16 __user *)dst, ret, "w", "w", "ir", 2); + __uaccess_end(); return ret; } case 4: { u32 tmp; + __uaccess_begin(); __get_user_asm(tmp, (u32 __user *)src, ret, "l", "k", "=r", 4); if (likely(!ret)) __put_user_asm(tmp, (u32 __user *)dst, ret, "l", "k", "ir", 4); + __uaccess_end(); return ret; } case 8: { u64 tmp; + __uaccess_begin(); __get_user_asm(tmp, (u64 __user *)src, ret, "q", "", "=r", 8); if (likely(!ret)) __put_user_asm(tmp, (u64 __user *)dst, ret, "q", "", "er", 8); + __uaccess_end(); return ret; } default: diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 756de9190..deabaf975 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/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index cd0fc0cc7..1ae89a272 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -82,13 +82,11 @@ struct x86_init_paging { * struct x86_init_timers - platform specific timer setup * @setup_perpcu_clockev: set up the per cpu clock event device for the * boot cpu - * @tsc_pre_init: platform function called before TSC init * @timer_init: initialize the platform timer (default PIT/HPET) * @wallclock_init: init the wallclock device */ struct x86_init_timers { void (*setup_percpu_clockev)(void); - void (*tsc_pre_init)(void); void (*timer_init)(void); void (*wallclock_init)(void); }; diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 4c20dd333..3bcdcc842 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -310,10 +310,10 @@ HYPERVISOR_mca(struct xen_mc *mc_op) } static inline int -HYPERVISOR_dom0_op(struct xen_platform_op *platform_op) +HYPERVISOR_platform_op(struct xen_platform_op *op) { - platform_op->interface_version = XENPF_INTERFACE_VERSION; - return _hypercall1(int, dom0_op, platform_op); + op->interface_version = XENPF_INTERFACE_VERSION; + return _hypercall1(int, platform_op, op); } static inline int diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 968d57dd5..f320ee32d 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msi) return xen_pci_frontend->enable_msi(dev, vectors); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) { @@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msix) return xen_pci_frontend->enable_msix(dev, vectors, nvec); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev) { diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 5a08bc8bf..c54beb44c 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -553,7 +553,7 @@ do { \ if (cpu_has_xmm) { \ xor_speed(&xor_block_pIII_sse); \ xor_speed(&xor_block_sse_pf64); \ - } else if (cpu_has_mmx) { \ + } else if (boot_cpu_has(X86_FEATURE_MMX)) { \ xor_speed(&xor_block_pII_mmx); \ xor_speed(&xor_block_p5_mmx); \ } else { \ diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 040d4083c..7956412d0 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -269,4 +269,96 @@ typedef struct _HV_REFERENCE_TSC_PAGE { #define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17) #define HV_SYNIC_SINT_VECTOR_MASK (0xFF) +#define HV_SYNIC_STIMER_COUNT (4) + +/* Define synthetic interrupt controller message constants. */ +#define HV_MESSAGE_SIZE (256) +#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) +#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) + +/* Define hypervisor message types. */ +enum hv_message_type { + HVMSG_NONE = 0x00000000, + + /* Memory access messages. */ + HVMSG_UNMAPPED_GPA = 0x80000000, + HVMSG_GPA_INTERCEPT = 0x80000001, + + /* Timer notification messages. */ + HVMSG_TIMER_EXPIRED = 0x80000010, + + /* Error messages. */ + HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, + HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, + HVMSG_UNSUPPORTED_FEATURE = 0x80000022, + + /* Trace buffer complete messages. */ + HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, + + /* Platform-specific processor intercept messages. */ + HVMSG_X64_IOPORT_INTERCEPT = 0x80010000, + HVMSG_X64_MSR_INTERCEPT = 0x80010001, + HVMSG_X64_CPUID_INTERCEPT = 0x80010002, + HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, + HVMSG_X64_APIC_EOI = 0x80010004, + HVMSG_X64_LEGACY_FP_ERROR = 0x80010005 +}; + +/* Define synthetic interrupt controller message flags. */ +union hv_message_flags { + __u8 asu8; + struct { + __u8 msg_pending:1; + __u8 reserved:7; + }; +}; + +/* Define port identifier type. */ +union hv_port_id { + __u32 asu32; + struct { + __u32 id:24; + __u32 reserved:8; + } u; +}; + +/* Define synthetic interrupt controller message header. */ +struct hv_message_header { + __u32 message_type; + __u8 payload_size; + union hv_message_flags message_flags; + __u8 reserved[2]; + union { + __u64 sender; + union hv_port_id port; + }; +}; + +/* Define synthetic interrupt controller message format. */ +struct hv_message { + struct hv_message_header header; + union { + __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; + } u; +}; + +/* Define the synthetic interrupt message page layout. */ +struct hv_message_page { + struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; +}; + +/* Define timer message payload structure. */ +struct hv_timer_message_payload { + __u32 timer_index; + __u32 reserved; + __u64 expiration_time; /* When the timer expired */ + __u64 delivery_time; /* When the message was delivered */ +}; + +#define HV_STIMER_ENABLE (1ULL << 0) +#define HV_STIMER_PERIODIC (1ULL << 1) +#define HV_STIMER_LAZY (1ULL << 2) +#define HV_STIMER_AUTOENABLE (1ULL << 3) +#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) + #endif diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 03429da2f..218494334 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 2f69e3b18..8a5cddac7 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 f92ab3697..9968f30cc 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 0d96749cf..331a7a07c 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 2bd2292a3..c80c02c6e 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -273,6 +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, @@ -324,6 +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 971cf8875..cf9bd896c 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 62071569b..eb45fc9b6 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 5f1feb685..ade25320d 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 7694ae6c1..f316e34ab 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 a35f6b547..3b670df4b 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, vector_searchmask, searched_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 cc8311c4d..aca8b75c1 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 662e9150e..a1242e2c1 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 4a139465f..624db0058 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, @@ -888,7 +889,10 @@ void __init uv_system_init(void) return; } pr_info("UV: Found %s hub\n", hub); - map_low_mmrs(); + + /* We now only need to map the MMRs on UV1 */ + if (is_uv1_hub()) + map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 439df975b..84a7524b2 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 d8f42f902..f2edafb5f 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/amd.c b/arch/x86/kernel/cpu/amd.c index a8816b325..a07956a08 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -304,7 +304,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -434,8 +434,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) */ int ht_nodeid = c->initial_apicid; - if (ht_nodeid >= 0 && - __apicid_to_node[ht_nodeid] != NUMA_NO_NODE) + if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = __apicid_to_node[ht_nodeid]; /* Pick a nearby node */ if (!node_online(node)) @@ -678,9 +677,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) * Disable it on the affected CPUs. */ if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) { - if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { + if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) { value |= 0x1E; - wrmsrl_safe(0xc0011021, value); + wrmsrl_safe(MSR_F15H_IC_CFG, value); } } } @@ -922,7 +921,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) void set_dr_addr_mask(unsigned long mask, int dr) { - if (!cpu_has_bpext) + if (!boot_cpu_has(X86_FEATURE_BPEXT)) return; switch (dr) { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index d8fba5c15..ae20be6e4 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -43,7 +43,7 @@ static void init_c3(struct cpuinfo_x86 *c) /* store Centaur Extended Feature Flags as * word 5 of the CPU capability bit array */ - c->x86_capability[5] = cpuid_edx(0xC0000001); + c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001); } #ifdef CONFIG_X86_32 /* Cyrix III family needs CX8 & PGE explicitly enabled. */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c2b7522cb..37830de8f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -581,14 +581,9 @@ void cpu_detect(struct cpuinfo_x86 *c) u32 junk, tfms, cap0, misc; cpuid(0x00000001, &tfms, &misc, &junk, &cap0); - c->x86 = (tfms >> 8) & 0xf; - c->x86_model = (tfms >> 4) & 0xf; - c->x86_mask = tfms & 0xf; - - if (c->x86 == 0xf) - c->x86 += (tfms >> 20) & 0xff; - if (c->x86 >= 0x6) - c->x86_model += ((tfms >> 16) & 0xf) << 4; + c->x86 = x86_family(tfms); + c->x86_model = x86_model(tfms); + c->x86_mask = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -599,50 +594,47 @@ void cpu_detect(struct cpuinfo_x86 *c) void get_cpu_cap(struct cpuinfo_x86 *c) { - u32 tfms, xlvl; - u32 ebx; + u32 eax, ebx, ecx, edx; /* Intel-defined flags: level 0x00000001 */ if (c->cpuid_level >= 0x00000001) { - u32 capability, excap; + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); - cpuid(0x00000001, &tfms, &ebx, &excap, &capability); - c->x86_capability[0] = capability; - c->x86_capability[4] = excap; + c->x86_capability[CPUID_1_ECX] = ecx; + c->x86_capability[CPUID_1_EDX] = edx; } /* Additional Intel-defined flags: level 0x00000007 */ if (c->cpuid_level >= 0x00000007) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[9] = ebx; + c->x86_capability[CPUID_7_0_EBX] = ebx; + + c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); } /* Extended state features: level 0x0000000d */ if (c->cpuid_level >= 0x0000000d) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[10] = eax; + c->x86_capability[CPUID_D_1_EAX] = eax; } /* Additional Intel-defined flags: level 0x0000000F */ if (c->cpuid_level >= 0x0000000F) { - u32 eax, ebx, ecx, edx; /* QoS sub-leaf, EAX=0Fh, ECX=0 */ cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[11] = edx; + c->x86_capability[CPUID_F_0_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { /* will be overridden if occupancy monitoring exists */ c->x86_cache_max_rmid = ebx; /* QoS sub-leaf, EAX=0Fh, ECX=1 */ cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[12] = edx; + c->x86_capability[CPUID_F_1_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; @@ -654,22 +646,24 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - c->extended_cpuid_level = xlvl; + eax = cpuid_eax(0x80000000); + c->extended_cpuid_level = eax; - if ((xlvl & 0xffff0000) == 0x80000000) { - if (xlvl >= 0x80000001) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); + if ((eax & 0xffff0000) == 0x80000000) { + if (eax >= 0x80000001) { + cpuid(0x80000001, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0001_ECX] = ecx; + c->x86_capability[CPUID_8000_0001_EDX] = edx; } } if (c->extended_cpuid_level >= 0x80000008) { - u32 eax = cpuid_eax(0x80000008); + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; - c->x86_capability[13] = cpuid_ebx(0x80000008); + c->x86_capability[CPUID_8000_0008_EBX] = ebx; } #ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) @@ -679,6 +673,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + if (c->extended_cpuid_level >= 0x8000000a) + c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + init_scattered_cpuid_features(c); } @@ -1185,7 +1182,7 @@ void syscall_init(void) * They both write to the same internal register. STAR allows to * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ - wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION @@ -1443,7 +1440,9 @@ void cpu_init(void) printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || + cpu_has_tsc || + boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 209ac1e7d..565648bc1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -445,7 +445,8 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has_xmm2) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - if (cpu_has_ds) { + + if (boot_cpu_has(X86_FEATURE_DS)) { unsigned int l1; rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index e38d338a6..0b6c52388 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -591,7 +591,7 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (cpu_has_topoext) + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &edx); else @@ -637,7 +637,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { num_cache_leaves = find_num_cache_leaves(c); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) @@ -809,7 +809,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; this_leaf = this_cpu_ci->info_list + index; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 7e8a736d0..a006f4cd7 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; @@ -1100,7 +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/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3e94ef46..faec7120c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -129,8 +129,8 @@ void __init load_ucode_bsp(void) if (!have_cpuid_p()) return; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -165,8 +165,8 @@ void load_ucode_ap(void) if (!have_cpuid_p()) return; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -206,8 +206,8 @@ void reload_early_microcode(void) { int vendor, family; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ea6137081..de8a164a6 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -145,10 +145,10 @@ matching_model_microcode(struct microcode_header_intel *mc_header, int ext_sigcount, i; struct extended_signature *ext_sig; - fam = __x86_family(sig); + fam = x86_family(sig); model = x86_model(sig); - fam_ucode = __x86_family(mc_header->sig); + fam_ucode = x86_family(mc_header->sig); model_ucode = x86_model(mc_header->sig); if (fam == fam_ucode && model == model_ucode) @@ -163,7 +163,7 @@ matching_model_microcode(struct microcode_header_intel *mc_header, ext_sigcount = ext_header->count; for (i = 0; i < ext_sigcount; i++) { - fam_ucode = __x86_family(ext_sig->sig); + fam_ucode = x86_family(ext_sig->sig); model_ucode = x86_model(ext_sig->sig); if (fam == fam_ucode && model == model_ucode) @@ -365,7 +365,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_cpuid(&eax, &ebx, &ecx, &edx); csig.sig = eax; - family = __x86_family(csig.sig); + family = x86_family(csig.sig); model = x86_model(csig.sig); if ((model >= 5) || (family > 6)) { @@ -521,16 +521,12 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp) { #ifdef CONFIG_X86_64 unsigned int eax = 0x00000001, ebx, ecx = 0, edx; - unsigned int family, model, stepping; char name[30]; native_cpuid(&eax, &ebx, &ecx, &edx); - family = __x86_family(eax); - model = x86_model(eax); - stepping = eax & 0xf; - - sprintf(name, "/*(DEBLOBBED)*/", family, model, stepping); + sprintf(name, "/*(DEBLOBBED)*/", + x86_family(eax), x86_model(eax), x86_stepping(eax)); return get_builtin_firmware(cp, name); #else diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 70d7c93f4..0d98503c2 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -593,9 +593,16 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size, unsigned long x_remove_base, unsigned long x_remove_size, int i) { - static struct range range_new[RANGE_NUM]; + /* + * range_new should really be an automatic variable, but + * putting 4096 bytes on the stack is frowned upon, to put it + * mildly. It is safe to make it a static __initdata variable, + * since mtrr_calc_range_state is only called during init and + * there's no way it will call itself recursively. + */ + static struct range range_new[RANGE_NUM] __initdata; unsigned long range_sums_new; - static int nr_range_new; + int nr_range_new; int num_reg; /* Convert ranges to var ranges state: */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3b533cf37..c870af161 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -349,7 +349,7 @@ static void get_fixed_ranges(mtrr_type *frs) void mtrr_save_fixed_ranges(void *info) { - if (cpu_has_mtrr) + if (boot_cpu_has(X86_FEATURE_MTRR)) get_fixed_ranges(mtrr_state.fixed_ranges); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f891b4750..5c3d149ee 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -682,7 +682,7 @@ void __init mtrr_bp_init(void) phys_addr = 32; - if (cpu_has_mtrr) { + if (boot_cpu_has(X86_FEATURE_MTRR)) { mtrr_if = &generic_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7c9..1b443db2d 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 d0e35ebb2..7bb61e32f 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 1cee5d2d7..58610539b 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) ] = { @@ -160,7 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) offset = index; else offset = index << 1; @@ -652,7 +652,7 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; switch (boot_cpu_data.x86) { diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index cc6cedb8f..8836fc9fa 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -323,6 +323,8 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu) return 0; fail: + if (amd_uncore_nb) + *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; kfree(uncore_nb); return -ENOMEM; } @@ -523,10 +525,10 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; - if (!cpu_has_topoext) + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; - if (cpu_has_perfctr_nb) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); if (!amd_uncore_nb) { ret = -ENOMEM; @@ -540,7 +542,7 @@ static int __init amd_uncore_init(void) ret = 0; } - if (cpu_has_perfctr_l2) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { amd_uncore_l2 = alloc_percpu(struct amd_uncore *); if (!amd_uncore_l2) { ret = -ENOMEM; @@ -583,10 +585,11 @@ fail_online: /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */ amd_uncore_nb = amd_uncore_l2 = NULL; - if (cpu_has_perfctr_l2) + + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) perf_pmu_unregister(&amd_l2_pmu); fail_l2: - if (cpu_has_perfctr_nb) + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); if (amd_uncore_l2) free_percpu(amd_uncore_l2); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a430021..fed2ab1f1 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. */ @@ -1916,7 +1960,8 @@ intel_bts_constraints(struct perf_event *event) static int intel_alt_er(int idx, u64 config) { - int alt_idx; + int alt_idx = idx; + if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; @@ -2475,6 +2520,44 @@ 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; @@ -2815,14 +2898,12 @@ static void intel_pmu_cpu_starting(int cpu) return; if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { - void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - *onln = cpuc->shared_regs; + cpuc->kfree_on_online[0] = cpuc->shared_regs; cpuc->shared_regs = pc; break; } @@ -3332,6 +3413,7 @@ __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 +3513,8 @@ __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 +3547,8 @@ __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 +3583,8 @@ __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 +3596,24 @@ __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 +3624,8 @@ __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 5db1c7755..10602f0a4 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 659f01e16..653f88d25 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 868e11943..c0bbd1033 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 ed446bdcb..24a351ad6 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 61215a69b..3bf41d413 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 +992,12 @@ 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; + case 94: /* SkyLake */ + ret = skl_uncore_pci_init(); + break; default: return 0; } @@ -1287,9 +1303,13 @@ 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 2f0a4a98e..a7086b862 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -336,8 +336,10 @@ int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); +int skl_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 +350,8 @@ 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 845256158..2bd030ddd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -8,6 +8,7 @@ #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 #define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 +#define PCI_DEVICE_ID_INTEL_SKL_IMC 0x191f /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -417,7 +418,7 @@ 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; @@ -524,6 +525,14 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id skl_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -544,6 +553,11 @@ static struct pci_driver bdw_uncore_pci_driver = { .id_table = bdw_uncore_pci_ids, }; +static struct pci_driver skl_uncore_pci_driver = { + .name = "skl_uncore", + .id_table = skl_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -558,6 +572,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ + IMC_DEV(SKL_IMC, &skl_uncore_pci_driver), /* 6th Gen Core */ { /* end marker */ } }; @@ -610,6 +625,11 @@ int bdw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int skl_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ 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 f0f4fcba2..33acb884c 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/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 136ac74de..819d94982 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -33,28 +33,27 @@ static int __init x86_rdrand_setup(char *s) __setup("nordrand", x86_rdrand_setup); /* - * Force a reseed cycle; we are architecturally guaranteed a reseed - * after no more than 512 128-bit chunks of random data. This also - * acts as a test of the CPU capability. + * RDRAND has Built-In-Self-Test (BIST) that runs on every invocation. + * Run the instruction a few times as a sanity check. + * If it fails, it is simple to disable RDRAND here. */ -#define RESEED_LOOP ((512*128)/sizeof(unsigned long)) +#define SANITY_CHECK_LOOPS 8 void x86_init_rdrand(struct cpuinfo_x86 *c) { #ifdef CONFIG_ARCH_RANDOM unsigned long tmp; - int i, count, ok; + int i; if (!cpu_has(c, X86_FEATURE_RDRAND)) - return; /* Nothing to do */ + return; - for (count = i = 0; i < RESEED_LOOP; i++) { - ok = rdrand_long(&tmp); - if (ok) - count++; + for (i = 0; i < SANITY_CHECK_LOOPS; i++) { + if (!rdrand_long(&tmp)) { + clear_cpu_cap(c, X86_FEATURE_RDRAND); + printk_once(KERN_WARNING "rdrand: disabled\n"); + return; + } } - - if (count != RESEED_LOOP) - clear_cpu_cap(c, X86_FEATURE_RDRAND); #endif } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 608fb26c7..8cb57df93 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,32 +31,12 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, - { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, - { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, - { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 }, - { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, - { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, - { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, - { X86_FEATURE_TSCRATEMSR, CR_EDX, 4, 0x8000000a, 0 }, - { X86_FEATURE_VMCBCLEAN, CR_EDX, 5, 0x8000000a, 0 }, - { X86_FEATURE_FLUSHBYASID, CR_EDX, 6, 0x8000000a, 0 }, - { X86_FEATURE_DECODEASSISTS, CR_EDX, 7, 0x8000000a, 0 }, - { X86_FEATURE_PAUSEFILTER, CR_EDX,10, 0x8000000a, 0 }, - { X86_FEATURE_PFTHRESHOLD, CR_EDX,12, 0x8000000a, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 3fa0e5ad8..252da7ace 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -12,7 +12,7 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) xlvl = cpuid_eax(0x80860000); if ((xlvl & 0xffff0000) == 0x80860000) { if (xlvl >= 0x80860001) - c->x86_capability[2] = cpuid_edx(0x80860001); + c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } } @@ -82,7 +82,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) /* Unhide possibly hidden capability flags */ rdmsr(0x80860004, cap_mask, uk); wrmsr(0x80860004, ~0, uk); - c->x86_capability[0] = cpuid_edx(0x00000001); + c->x86_capability[CPUID_1_EDX] = cpuid_edx(0x00000001); wrmsr(0x80860004, cap_mask, uk); /* All Transmeta CPUs have a constant TSC */ diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index bd3507da3..2836de390 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -58,28 +58,6 @@ static void cpuid_smp_cpuid(void *cmd_block) &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx); } -static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file->f_mapping->host; - - mutex_lock(&inode->i_mutex); - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t cpuid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -132,7 +110,7 @@ static int cpuid_open(struct inode *inode, struct file *file) */ static const struct file_operations cpuid_fops = { .owner = THIS_MODULE, - .llseek = cpuid_seek, + .llseek = no_seek_end_llseek, .read = cpuid_read, .open = cpuid_open, }; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2c1910f67..58f34319b 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/early-quirks.c b/arch/x86/kernel/early-quirks.c index db9a675e7..bca14c899 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -547,6 +547,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_CHV_IDS(&chv_stolen_funcs), INTEL_SKL_IDS(&gen9_stolen_funcs), INTEL_BXT_IDS(&gen9_stolen_funcs), + INTEL_KBL_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index a457bce46..4d38416e2 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -173,7 +173,6 @@ void init_espfix_ap(int cpu) struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); pmd_p = (pmd_t *)page_address(page); - SetPageTOI_Untracked(virt_to_page(pmd_p)); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) @@ -186,7 +185,6 @@ void init_espfix_ap(int cpu) struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); pte_p = (pte_t *)page_address(page); - SetPageTOI_Untracked(virt_to_page(pte_p)); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) @@ -195,7 +193,6 @@ void init_espfix_ap(int cpu) pte_p = pte_offset_kernel(&pmd, addr); stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); - SetPageTOI_Untracked(virt_to_page(stack_page)); pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d25097c3f..d5804adfa 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -409,8 +409,10 @@ static inline void copy_init_fpstate_to_fpregs(void) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, -1); - else + else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); + else + copy_kernel_to_fregs(&init_fpstate.fsave); } /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index be39b5fde..bd08fb770 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -3,8 +3,11 @@ */ #include <asm/fpu/internal.h> #include <asm/tlbflush.h> +#include <asm/setup.h> +#include <asm/cmdline.h> #include <linux/sched.h> +#include <linux/init.h> /* * Initialize the TS bit in CR0 according to the style of context-switches @@ -12,7 +15,7 @@ */ static void fpu__init_cpu_ctx_switch(void) { - if (!cpu_has_eager_fpu) + if (!boot_cpu_has(X86_FEATURE_EAGER_FPU)) stts(); else clts(); @@ -75,13 +78,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + } #ifndef CONFIG_MATH_EMULATION if (!cpu_has_fpu) { @@ -129,7 +134,7 @@ static void __init fpu__init_system_generic(void) * Set up the legacy init FPU context. (xstate init might overwrite this * with a more modern format, if the CPU supports it.) */ - fpstate_init_fxstate(&init_fpstate.fxsave); + fpstate_init(&init_fpstate); fpu__init_system_mxcsr(); } @@ -143,9 +148,18 @@ 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: @@ -188,7 +202,7 @@ static void __init fpu__init_task_struct_size(void) */ static void __init fpu__init_system_xstate_size_legacy(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -261,24 +275,50 @@ static void __init fpu__init_system_xstate_size_legacy(void) */ static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) +/* + * Find supported xfeatures based on cpu features and command-line input. + * This must be called after fpu__init_parse_early_param() is called and + * xfeatures_mask is enumerated. + */ +u64 __init fpu__get_supported_xfeatures_mask(void) { - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; + /* Support all xfeatures known to us */ + if (eagerfpu != DISABLE) + return XCNTXT_MASK; + + /* Warning of xfeatures being disabled for no eagerfpu mode */ + if (xfeatures_mask & XFEATURE_MASK_EAGER) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XFEATURE_MASK_EAGER); + } + + /* Return a mask that masks out all features requiring eagerfpu mode */ + return ~XFEATURE_MASK_EAGER; +} + +/* + * Disable features dependent on eagerfpu. + */ +static void __init fpu__clear_eager_fpu_features(void) +{ + setup_clear_cpu_cap(X86_FEATURE_MPX); } -__setup("eagerfpu=", eager_fpu_setup); /* * Pick the FPU context switching strategy: + * + * When eagerfpu is AUTO or ENABLE, we ensure it is ENABLE if either of + * the following is true: + * + * (1) the cpu has xsaveopt, as it has the optimization and doing eager + * FPU switching has a relatively low cost compared to a plain xsave; + * (2) the cpu has xsave features (e.g. MPX) that depend on eager FPU + * switching. Should the kernel boot with noxsaveopt, we support MPX + * with eager FPU switching at a higher cost. */ static void __init fpu__init_system_ctx_switch(void) { - static bool on_boot_cpu = 1; + static bool on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -286,19 +326,11 @@ static void __init fpu__init_system_ctx_switch(void) WARN_ON_FPU(current->thread.fpu.fpstate_active); current_thread_info()->status = 0; - /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) + if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) eagerfpu = ENABLE; - if (xfeatures_mask & XFEATURE_MASK_EAGER) { - if (eagerfpu == DISABLE) { - pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", - xfeatures_mask & XFEATURE_MASK_EAGER); - xfeatures_mask &= ~XFEATURE_MASK_EAGER; - } else { - eagerfpu = ENABLE; - } - } + if (xfeatures_mask & XFEATURE_MASK_EAGER) + eagerfpu = ENABLE; if (eagerfpu == ENABLE) setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); @@ -307,11 +339,48 @@ static void __init fpu__init_system_ctx_switch(void) } /* + * We parse fpu parameters early because fpu__init_system() is executed + * before parse_early_param(). + */ +static void __init fpu__init_parse_early_param(void) +{ + /* + * No need to check "eagerfpu=auto" again, since it is the + * initial default. + */ + if (cmdline_find_option_bool(boot_command_line, "eagerfpu=off")) { + eagerfpu = DISABLE; + fpu__clear_eager_fpu_features(); + } else if (cmdline_find_option_bool(boot_command_line, "eagerfpu=on")) { + eagerfpu = ENABLE; + } + + if (cmdline_find_option_bool(boot_command_line, "no387")) + setup_clear_cpu_cap(X86_FEATURE_FPU); + + if (cmdline_find_option_bool(boot_command_line, "nofxsr")) { + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + } + + if (cmdline_find_option_bool(boot_command_line, "noxsave")) + fpu__xstate_clear_all_cpu_caps(); + + if (cmdline_find_option_bool(boot_command_line, "noxsaveopt")) + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + if (cmdline_find_option_bool(boot_command_line, "noxsaves")) + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* * Called on the boot CPU once per system bootup, to set up the initial * FPU state that is later cloned into all processes: */ void __init fpu__init_system(struct cpuinfo_x86 *c) { + fpu__init_parse_early_param(); fpu__init_system_early_generic(c); /* @@ -335,62 +404,3 @@ void __init fpu__init_system(struct cpuinfo_x86 *c) fpu__init_system_ctx_switch(); } - -/* - * Boot parameter to turn off FPU support and fall back to math-emu: - */ -static int __init no_387(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FPU); - return 1; -} -__setup("no387", no_387); - -/* - * Disable all xstate CPU features: - */ -static int __init x86_noxsave_setup(char *s) -{ - if (strlen(s)) - return 0; - - fpu__xstate_clear_all_cpu_caps(); - - return 1; -} -__setup("noxsave", x86_noxsave_setup); - -/* - * Disable the XSAVEOPT instruction specifically: - */ -static int __init x86_noxsaveopt_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - - return 1; -} -__setup("noxsaveopt", x86_noxsaveopt_setup); - -/* - * Disable the XSAVES instruction: - */ -static int __init x86_noxsaves_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - - return 1; -} -__setup("noxsaves", x86_noxsaves_setup); - -/* - * Disable FX save/restore and SSE support: - */ -static int __init x86_nofxsr_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FXSR); - setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); - setup_clear_cpu_cap(X86_FEATURE_XMM); - - return 1; -} -__setup("nofxsr", x86_nofxsr_setup); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 70fc31222..d425cda5a 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -52,6 +52,7 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_AVX512ER); setup_clear_cpu_cap(X86_FEATURE_AVX512CD); setup_clear_cpu_cap(X86_FEATURE_MPX); + setup_clear_cpu_cap(X86_FEATURE_XGETBV1); } /* @@ -297,7 +298,7 @@ static void __init setup_xstate_comp(void) */ static void __init setup_init_fpu_buf(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -608,7 +609,7 @@ static void fpu__init_disable_system_xstate(void) void __init fpu__init_system_xstate(void) { unsigned int eax, ebx, ecx, edx; - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; int err; WARN_ON_FPU(!on_boot_cpu); @@ -632,8 +633,7 @@ void __init fpu__init_system_xstate(void) BUG(); } - /* Support only the state known to the OS: */ - xfeatures_mask = xfeatures_mask & XCNTXT_MASK; + xfeatures_mask &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 311bcf338..29408d6d6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -105,14 +105,14 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, { unsigned char replaced[MCOUNT_INSN_SIZE]; + ftrace_expected = old_code; + /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ @@ -154,6 +154,8 @@ int ftrace_make_nop(struct module *mod, if (addr == MCOUNT_ADDR) return ftrace_modify_code_direct(rec->ip, old, new); + ftrace_expected = NULL; + /* Normal cases use add_brk_on_nop */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; @@ -220,6 +222,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); + ftrace_expected = NULL; return -EINVAL; } @@ -314,6 +317,8 @@ static int add_break(unsigned long ip, const char *old) if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; + ftrace_expected = old; + /* Make sure it is what we expect it to be */ if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) return -EINVAL; @@ -413,6 +418,8 @@ static int remove_breakpoint(struct dyn_ftrace *rec) ftrace_addr = ftrace_get_addr_curr(rec); nop = ftrace_call_replace(ip, ftrace_addr); + ftrace_expected = nop; + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index f129a9af6..2c0f3407b 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -192,5 +192,13 @@ void __init x86_64_start_reservations(char *real_mode_data) reserve_ebda_region(); + switch (boot_params.hdr.hardware_subarch) { + case X86_SUBARCH_INTEL_MID: + x86_intel_mid_early_setup(); + break; + default: + break; + } + start_kernel(); } diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 50a3fad5b..2bcfb5f2b 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -300,6 +300,10 @@ static int arch_build_bp_info(struct perf_event *bp) return -EINVAL; if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) return -EINVAL; + + if (!boot_cpu_has(X86_FEATURE_BPEXT)) + return -EOPNOTSUPP; + /* * It's impossible to use a range breakpoint to fake out * user vs kernel detection because bp_len - 1 can't @@ -307,8 +311,6 @@ static int arch_build_bp_info(struct perf_event *bp) * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ - if (!cpu_has_bpext) - return -EOPNOTSUPP; info->mask = bp->attr.bp_len - 1; info->len = X86_BREAKPOINT_LEN_1; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2bd81e302..72cef5869 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/livepatch.c b/arch/x86/kernel/livepatch.c index d1d35ccff..92fc1a51f 100644 --- a/arch/x86/kernel/livepatch.c +++ b/arch/x86/kernel/livepatch.c @@ -20,8 +20,6 @@ #include <linux/module.h> #include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/page_types.h> #include <asm/elf.h> #include <asm/livepatch.h> @@ -38,11 +36,10 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, unsigned long loc, unsigned long value) { - int ret, numpages, size = 4; - bool readonly; + size_t size = 4; unsigned long val; - unsigned long core = (unsigned long)mod->module_core; - unsigned long core_size = mod->core_size; + unsigned long core = (unsigned long)mod->core_layout.base; + unsigned long core_size = mod->core_layout.size; switch (type) { case R_X86_64_NONE: @@ -69,23 +66,5 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, /* loc does not point to any symbol inside the module */ return -EINVAL; - readonly = false; - -#ifdef CONFIG_DEBUG_SET_MODULE_RONX - if (loc < core + mod->core_ro_size) - readonly = true; -#endif - - /* determine if the relocation spans a page boundary */ - numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; - - if (readonly) - set_memory_rw(loc & PAGE_MASK, numpages); - - ret = probe_kernel_write((void *)loc, &val, size); - - if (readonly) - set_memory_ro(loc & PAGE_MASK, numpages); - - return ret; + return probe_kernel_write((void *)loc, &val, size); } diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 819ab3f9c..ba7fbba98 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -385,6 +385,7 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) return image->fops->cleanup(image->image_loader_data); } +#ifdef CONFIG_KEXEC_VERIFY_SIG int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, unsigned long kernel_len) { @@ -395,6 +396,7 @@ int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel, return image->fops->verify_sig(kernel, kernel_len); } +#endif /* * Apply purgatory relocations. diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 113e70784..64f9616f9 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -45,28 +45,6 @@ static struct class *msr_class; -static loff_t msr_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file_inode(file); - - mutex_lock(&inode->i_mutex); - switch (orig) { - case SEEK_SET: - file->f_pos = offset; - ret = file->f_pos; - break; - case SEEK_CUR: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t msr_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -194,7 +172,7 @@ static int msr_open(struct inode *inode, struct file *file) */ static const struct file_operations msr_fops = { .owner = THIS_MODULE, - .llseek = msr_seek, + .llseek = no_seek_end_llseek, .read = msr_read, .write = msr_write, .open = msr_open, diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 697f90db0..8a2cdd736 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 c2130aef3..f08ac28b8 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -74,16 +74,6 @@ void __init default_banner(void) /* Undefined instruction for dealing with missing ops pointers. */ static const unsigned char ud2a[] = { 0x0f, 0x0b }; -unsigned paravirt_patch_nop(void) -{ - return 0; -} - -unsigned paravirt_patch_ignore(unsigned len) -{ - return len; -} - struct branch { unsigned char opcode; u32 delta; @@ -133,7 +123,6 @@ static void *get_call_destination(u8 type) .pv_time_ops = pv_time_ops, .pv_cpu_ops = pv_cpu_ops, .pv_irq_ops = pv_irq_ops, - .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, #ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, @@ -152,8 +141,7 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); else if (opfunc == _paravirt_nop) - /* If the operation is a nop, then nop the callsite */ - ret = paravirt_patch_nop(); + ret = 0; /* identity functions just return their single argument */ else if (opfunc == _paravirt_ident_32) @@ -162,10 +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); @@ -220,8 +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 = { @@ -379,13 +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, @@ -403,12 +379,6 @@ NOKPROBE_SYMBOL(native_get_debugreg); NOKPROBE_SYMBOL(native_set_debugreg); NOKPROBE_SYMBOL(native_load_idt); -struct pv_apic_ops pv_apic_ops = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) /* 32-bit pagetable entries */ #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) @@ -444,9 +414,6 @@ struct pv_mmu_ops pv_mmu_ops = { .set_pmd = native_set_pmd, .set_pmd_at = native_set_pmd_at, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, - .pmd_update = paravirt_nop, - .pmd_update_defer = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, @@ -492,6 +459,5 @@ struct pv_mmu_ops pv_mmu_ops = { EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); EXPORT_SYMBOL (pv_mmu_ops); -EXPORT_SYMBOL_GPL(pv_apic_ops); EXPORT_SYMBOL_GPL(pv_info); EXPORT_SYMBOL (pv_irq_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index c89f50a76..158dc0650 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 8aa05583b..e70087a04 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/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 0497f7199..833b1d329 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -180,13 +180,13 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl); static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); static void get_tce_space_from_tar(void); -static struct cal_chipset_ops calgary_chip_ops = { +static const struct cal_chipset_ops calgary_chip_ops = { .handle_quirks = calgary_handle_quirks, .tce_cache_blast = calgary_tce_cache_blast, .dump_error_regs = calgary_dump_error_regs }; -static struct cal_chipset_ops calioc2_chip_ops = { +static const struct cal_chipset_ops calioc2_chip_ops = { .handle_quirks = calioc2_handle_quirks, .tce_cache_blast = calioc2_tce_cache_blast, .dump_error_regs = calioc2_dump_error_regs diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index adf0392d5..7c577a178 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -88,7 +88,7 @@ int __init pci_swiotlb_detect_4gb(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ #ifdef CONFIG_X86_64 - if (!no_iommu && max_pfn > MAX_DMA32_PFN) + if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif return swiotlb; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e835d263a..b9d99e0f8 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -125,7 +125,7 @@ void release_thread(struct task_struct *dead_task) if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, - dead_task->mm->context.ldt, + dead_task->mm->context.ldt->entries, dead_task->mm->context.ldt->size); BUG(); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 558f50ede..32e9d9cbb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -124,21 +124,6 @@ const char *regs_query_register_name(unsigned int offset) return NULL; } -static const int arg_offs_table[] = { -#ifdef CONFIG_X86_32 - [0] = offsetof(struct pt_regs, ax), - [1] = offsetof(struct pt_regs, dx), - [2] = offsetof(struct pt_regs, cx) -#else /* CONFIG_X86_64 */ - [0] = offsetof(struct pt_regs, di), - [1] = offsetof(struct pt_regs, si), - [2] = offsetof(struct pt_regs, dx), - [3] = offsetof(struct pt_regs, cx), - [4] = offsetof(struct pt_regs, r8), - [5] = offsetof(struct pt_regs, r9) -#endif -}; - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229..99bfc0251 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 f660d63f4..ab0adc0fa 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -726,6 +726,7 @@ 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) { @@ -788,6 +789,9 @@ 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); @@ -796,9 +800,35 @@ 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/setup.c b/arch/x86/kernel/setup.c index d2bbe343f..d3d80e6d4 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1048,6 +1048,8 @@ void __init setup_arch(char **cmdline_p) if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820_end_of_ram_pfn(); + max_possible_pfn = max_pfn; + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 12c828620..658777cf3 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/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fbabe4fcc..24d57f77b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -304,7 +304,7 @@ do { \ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && @@ -630,13 +630,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) num_starts = 0; /* - * Paravirt / VMI wants a startup IPI hook here to set up the - * target processor state. - */ - startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - stack_start); - - /* * Run STARTUP IPI loop. */ pr_debug("#startup loops: %d\n", num_starts); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6ada9d131..3d743da82 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -12,7 +12,6 @@ #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> -#include <linux/mm.h> #include <asm/hpet.h> #include <asm/timer.h> @@ -196,10 +195,6 @@ static void cyc2ns_init(int cpu) c2n->head = c2n->data; c2n->tail = c2n->data; - - // Don't let TuxOnIce make data RO - a secondary CPU will cause a triple fault - // if it loads microcode, which then does a printk, which may end up invoking cycles_2_ns - SetPageTOI_Untracked(virt_to_page(c2n)); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) @@ -1190,8 +1185,6 @@ void __init tsc_init(void) u64 lpj; int cpu; - x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 4cf401f58..07efb35ee 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -48,31 +48,31 @@ verify_cpu: pushfl popl %eax cmpl %eax,%ebx - jz verify_cpu_no_longmode # cpu has no cpuid + jz .Lverify_cpu_no_longmode # cpu has no cpuid #endif movl $0x0,%eax # See if cpuid 1 is implemented cpuid cmpl $0x1,%eax - jb verify_cpu_no_longmode # no cpuid 1 + jb .Lverify_cpu_no_longmode # no cpuid 1 xor %di,%di cmpl $0x68747541,%ebx # AuthenticAMD - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd cmpl $0x69746e65,%edx - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd cmpl $0x444d4163,%ecx - jnz verify_cpu_noamd + jnz .Lverify_cpu_noamd mov $1,%di # cpu is from AMD - jmp verify_cpu_check + jmp .Lverify_cpu_check -verify_cpu_noamd: +.Lverify_cpu_noamd: cmpl $0x756e6547,%ebx # GenuineIntel? - jnz verify_cpu_check + jnz .Lverify_cpu_check cmpl $0x49656e69,%edx - jnz verify_cpu_check + jnz .Lverify_cpu_check cmpl $0x6c65746e,%ecx - jnz verify_cpu_check + jnz .Lverify_cpu_check # only call IA32_MISC_ENABLE when: # family > 6 || (family == 6 && model >= 0xd) @@ -83,59 +83,59 @@ verify_cpu_noamd: andl $0x0ff00f00, %eax # mask family and extended family shrl $8, %eax cmpl $6, %eax - ja verify_cpu_clear_xd # family > 6, ok - jb verify_cpu_check # family < 6, skip + ja .Lverify_cpu_clear_xd # family > 6, ok + jb .Lverify_cpu_check # family < 6, skip andl $0x000f00f0, %ecx # mask model and extended model shrl $4, %ecx cmpl $0xd, %ecx - jb verify_cpu_check # family == 6, model < 0xd, skip + jb .Lverify_cpu_check # family == 6, model < 0xd, skip -verify_cpu_clear_xd: +.Lverify_cpu_clear_xd: movl $MSR_IA32_MISC_ENABLE, %ecx rdmsr btrl $2, %edx # clear MSR_IA32_MISC_ENABLE_XD_DISABLE - jnc verify_cpu_check # only write MSR if bit was changed + jnc .Lverify_cpu_check # only write MSR if bit was changed wrmsr -verify_cpu_check: +.Lverify_cpu_check: movl $0x1,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK0,%edx xorl $REQUIRED_MASK0,%edx - jnz verify_cpu_no_longmode + jnz .Lverify_cpu_no_longmode movl $0x80000000,%eax # See if extended cpuid is implemented cpuid cmpl $0x80000001,%eax - jb verify_cpu_no_longmode # no extended cpuid + jb .Lverify_cpu_no_longmode # no extended cpuid movl $0x80000001,%eax # Does the cpu have what it takes cpuid andl $REQUIRED_MASK1,%edx xorl $REQUIRED_MASK1,%edx - jnz verify_cpu_no_longmode + jnz .Lverify_cpu_no_longmode -verify_cpu_sse_test: +.Lverify_cpu_sse_test: movl $1,%eax cpuid andl $SSE_MASK,%edx cmpl $SSE_MASK,%edx - je verify_cpu_sse_ok + je .Lverify_cpu_sse_ok test %di,%di - jz verify_cpu_no_longmode # only try to force SSE on AMD + jz .Lverify_cpu_no_longmode # only try to force SSE on AMD movl $MSR_K7_HWCR,%ecx rdmsr btr $15,%eax # enable SSE wrmsr xor %di,%di # don't loop - jmp verify_cpu_sse_test # try again + jmp .Lverify_cpu_sse_test # try again -verify_cpu_no_longmode: +.Lverify_cpu_no_longmode: popf # Restore caller passed flags movl $1,%eax ret -verify_cpu_sse_ok: +.Lverify_cpu_sse_ok: popf # Restore caller passed flags xorl %eax, %eax ret diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 524619351..e574b8546 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -175,7 +175,11 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd_mm(mm, 0xA0000, pmd); + + if (pmd_trans_huge(*pmd)) { + struct vm_area_struct *vma = find_vma(mm, 0xA0000); + split_huge_pmd(vma, pmd, 0xA0000); + } if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); @@ -357,8 +361,10 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) tss = &per_cpu(cpu_tss, get_cpu()); /* make room for real-mode segments */ tsk->thread.sp0 += 16; - if (cpu_has_sep) + + if (static_cpu_has_safe(X86_FEATURE_SEP)) tsk->thread.sysenter_cs = 0; + load_sp0(tss, &tsk->thread); put_cpu(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3839628d9..dad5fe963 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -68,7 +68,6 @@ struct x86_init_ops x86_init __initdata = { .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, - .tsc_pre_init = x86_init_noop, .timer_init = hpet_time_init, .wallclock_init = x86_init_noop, }, diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 3f5c48ddb..c8eda1498 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_CPUID_H #include "x86.h" +#include <asm/cpu.h> int kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, @@ -178,4 +179,37 @@ static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu) } #undef BIT_NRIPS +static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_family(best->eax); +} + +static inline int guest_cpuid_model(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_model(best->eax); +} + +static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_stepping(best->eax); +} + #endif diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 62cf8c915..c58ba6717 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,13 +23,665 @@ #include "x86.h" #include "lapic.h" +#include "ioapic.h" #include "hyperv.h" #include <linux/kvm_host.h> +#include <linux/highmem.h> +#include <asm/apicdef.h> #include <trace/events/kvm.h> #include "trace.h" +static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint) +{ + return atomic64_read(&synic->sint[sint]); +} + +static inline int synic_get_sint_vector(u64 sint_value) +{ + if (sint_value & HV_SYNIC_SINT_MASKED) + return -1; + return sint_value & HV_SYNIC_SINT_VECTOR_MASK; +} + +static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic, + int vector) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) + return true; + } + return false; +} + +static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic, + int vector) +{ + int i; + u64 sint_value; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + sint_value = synic_read_sint(synic, i); + if (synic_get_sint_vector(sint_value) == vector && + sint_value & HV_SYNIC_SINT_AUTO_EOI) + return true; + } + return false; +} + +static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, + u64 data, bool host) +{ + int vector; + + vector = data & HV_SYNIC_SINT_VECTOR_MASK; + if (vector < 16 && !host) + return 1; + /* + * Guest may configure multiple SINTs to use the same vector, so + * we maintain a bitmap of vectors handled by synic, and a + * bitmap of vectors with auto-eoi behavior. The bitmaps are + * updated here, and atomically queried on fast paths. + */ + + atomic64_set(&synic->sint[sint], data); + + if (synic_has_vector_connected(synic, vector)) + __set_bit(vector, synic->vec_bitmap); + else + __clear_bit(vector, synic->vec_bitmap); + + if (synic_has_vector_auto_eoi(synic, vector)) + __set_bit(vector, synic->auto_eoi_bitmap); + else + __clear_bit(vector, synic->auto_eoi_bitmap); + + /* Load SynIC vectors into EOI exit bitmap */ + kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic)); + return 0; +} + +static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id) +{ + struct kvm_vcpu *vcpu; + struct kvm_vcpu_hv_synic *synic; + + if (vcpu_id >= atomic_read(&kvm->online_vcpus)) + return NULL; + vcpu = kvm_get_vcpu(kvm, vcpu_id); + if (!vcpu) + return NULL; + synic = vcpu_to_synic(vcpu); + return (synic->active) ? synic : NULL; +} + +static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic, + u32 sint) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct page *page; + gpa_t gpa; + struct hv_message *msg; + struct hv_message_page *msg_page; + + gpa = synic->msg_page & PAGE_MASK; + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); + if (is_error_page(page)) { + vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n", + gpa); + return; + } + msg_page = kmap_atomic(page); + + msg = &msg_page->sint_message[sint]; + msg->header.message_flags.msg_pending = 0; + + kunmap_atomic(msg_page); + kvm_release_page_dirty(page); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); +} + +static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_stimer *stimer; + int gsi, idx, stimers_pending; + + trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint); + + if (synic->msg_page & HV_SYNIC_SIMP_ENABLE) + synic_clear_sint_msg_pending(synic, sint); + + /* Try to deliver pending Hyper-V SynIC timers messages */ + stimers_pending = 0; + for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) { + stimer = &hv_vcpu->stimer[idx]; + if (stimer->msg_pending && + (stimer->config & HV_STIMER_ENABLE) && + HV_STIMER_SINT(stimer->config) == sint) { + set_bit(stimer->index, + hv_vcpu->stimer_pending_bitmap); + stimers_pending++; + } + } + if (stimers_pending) + kvm_make_request(KVM_REQ_HV_STIMER, vcpu); + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = atomic_read(&synic->sint_to_gsi[sint]); + if (gsi != -1) + kvm_notify_acked_gsi(kvm, gsi); + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + + hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC; + hv_vcpu->exit.u.synic.msr = msr; + hv_vcpu->exit.u.synic.control = synic->control; + hv_vcpu->exit.u.synic.evt_page = synic->evt_page; + hv_vcpu->exit.u.synic.msg_page = synic->msg_page; + + kvm_make_request(KVM_REQ_HV_EXIT, vcpu); +} + +static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, + u32 msr, u64 data, bool host) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + int ret; + + if (!synic->active) + return 1; + + trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); + + ret = 0; + switch (msr) { + case HV_X64_MSR_SCONTROL: + synic->control = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_SVERSION: + if (!host) { + ret = 1; + break; + } + synic->version = data; + break; + case HV_X64_MSR_SIEFP: + if (data & HV_SYNIC_SIEFP_ENABLE) + if (kvm_clear_guest(vcpu->kvm, + data & PAGE_MASK, PAGE_SIZE)) { + ret = 1; + break; + } + synic->evt_page = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_SIMP: + if (data & HV_SYNIC_SIMP_ENABLE) + if (kvm_clear_guest(vcpu->kvm, + data & PAGE_MASK, PAGE_SIZE)) { + ret = 1; + break; + } + synic->msg_page = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_EOM: { + int i; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) + kvm_hv_notify_acked_sint(vcpu, i); + break; + } + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data, host); + break; + default: + ret = 1; + break; + } + return ret; +} + +static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata) +{ + int ret; + + if (!synic->active) + return 1; + + ret = 0; + switch (msr) { + case HV_X64_MSR_SCONTROL: + *pdata = synic->control; + break; + case HV_X64_MSR_SVERSION: + *pdata = synic->version; + break; + case HV_X64_MSR_SIEFP: + *pdata = synic->evt_page; + break; + case HV_X64_MSR_SIMP: + *pdata = synic->msg_page; + break; + case HV_X64_MSR_EOM: + *pdata = 0; + break; + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + *pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]); + break; + default: + ret = 1; + break; + } + return ret; +} + +int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_lapic_irq irq; + int ret, vector; + + if (sint >= ARRAY_SIZE(synic->sint)) + return -EINVAL; + + vector = synic_get_sint_vector(synic_read_sint(synic, sint)); + if (vector < 0) + return -ENOENT; + + memset(&irq, 0, sizeof(irq)); + irq.dest_id = kvm_apic_id(vcpu->arch.apic); + irq.dest_mode = APIC_DEST_PHYSICAL; + irq.delivery_mode = APIC_DM_FIXED; + irq.vector = vector; + irq.level = 1; + + ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL); + trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret); + return ret; +} + +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint) +{ + struct kvm_vcpu_hv_synic *synic; + + synic = synic_get(kvm, vcpu_id); + if (!synic) + return -EINVAL; + + return synic_set_irq(synic, sint); +} + +void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + int i; + + trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector); + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) + if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) + kvm_hv_notify_acked_sint(vcpu, i); +} + +static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi) +{ + struct kvm_vcpu_hv_synic *synic; + + synic = synic_get(kvm, vcpu_id); + if (!synic) + return -EINVAL; + + if (sint >= ARRAY_SIZE(synic->sint_to_gsi)) + return -EINVAL; + + atomic_set(&synic->sint_to_gsi[sint], gsi); + return 0; +} + +void kvm_hv_irq_routing_update(struct kvm *kvm) +{ + struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry *e; + u32 gsi; + + irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, + lockdep_is_held(&kvm->irq_lock)); + + for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) { + hlist_for_each_entry(e, &irq_rt->map[gsi], link) { + if (e->type == KVM_IRQ_ROUTING_HV_SINT) + kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu, + e->hv_sint.sint, gsi); + } + } +} + +static void synic_init(struct kvm_vcpu_hv_synic *synic) +{ + int i; + + memset(synic, 0, sizeof(*synic)); + synic->version = HV_SYNIC_VERSION_1; + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED); + atomic_set(&synic->sint_to_gsi[i], -1); + } +} + +static u64 get_time_ref_counter(struct kvm *kvm) +{ + return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); +} + +static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, + bool vcpu_kick) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + + set_bit(stimer->index, + vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + kvm_make_request(KVM_REQ_HV_STIMER, vcpu); + if (vcpu_kick) + kvm_vcpu_kick(vcpu); +} + +static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + + trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index); + + hrtimer_cancel(&stimer->timer); + clear_bit(stimer->index, + vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + stimer->msg_pending = false; + stimer->exp_time = 0; +} + +static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer) +{ + struct kvm_vcpu_hv_stimer *stimer; + + stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer); + trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index); + stimer_mark_pending(stimer, true); + + return HRTIMER_NORESTART; +} + +/* + * stimer_start() assumptions: + * a) stimer->count is not equal to 0 + * b) stimer->config has HV_STIMER_ENABLE flag + */ +static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) +{ + u64 time_now; + ktime_t ktime_now; + + time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm); + ktime_now = ktime_get(); + + if (stimer->config & HV_STIMER_PERIODIC) { + if (stimer->exp_time) { + if (time_now >= stimer->exp_time) { + u64 remainder; + + div64_u64_rem(time_now - stimer->exp_time, + stimer->count, &remainder); + stimer->exp_time = + time_now + (stimer->count - remainder); + } + } else + stimer->exp_time = time_now + stimer->count; + + trace_kvm_hv_stimer_start_periodic( + stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, + time_now, stimer->exp_time); + + hrtimer_start(&stimer->timer, + ktime_add_ns(ktime_now, + 100 * (stimer->exp_time - time_now)), + HRTIMER_MODE_ABS); + return 0; + } + stimer->exp_time = stimer->count; + if (time_now >= stimer->count) { + /* + * Expire timer according to Hypervisor Top-Level Functional + * specification v4(15.3.1): + * "If a one shot is enabled and the specified count is in + * the past, it will expire immediately." + */ + stimer_mark_pending(stimer, false); + return 0; + } + + trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, + time_now, stimer->count); + + hrtimer_start(&stimer->timer, + ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)), + HRTIMER_MODE_ABS); + return 0; +} + +static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, + bool host) +{ + trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, config, host); + + stimer_cleanup(stimer); + if ((stimer->config & HV_STIMER_ENABLE) && HV_STIMER_SINT(config) == 0) + config &= ~HV_STIMER_ENABLE; + stimer->config = config; + stimer_mark_pending(stimer, false); + return 0; +} + +static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, + bool host) +{ + trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, count, host); + + stimer_cleanup(stimer); + stimer->count = count; + if (stimer->count == 0) + stimer->config &= ~HV_STIMER_ENABLE; + else if (stimer->config & HV_STIMER_AUTOENABLE) + stimer->config |= HV_STIMER_ENABLE; + stimer_mark_pending(stimer, false); + return 0; +} + +static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig) +{ + *pconfig = stimer->config; + return 0; +} + +static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount) +{ + *pcount = stimer->count; + return 0; +} + +static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint, + struct hv_message *src_msg) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct page *page; + gpa_t gpa; + struct hv_message *dst_msg; + int r; + struct hv_message_page *msg_page; + + if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE)) + return -ENOENT; + + gpa = synic->msg_page & PAGE_MASK; + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); + if (is_error_page(page)) + return -EFAULT; + + msg_page = kmap_atomic(page); + dst_msg = &msg_page->sint_message[sint]; + if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE, + src_msg->header.message_type) != HVMSG_NONE) { + dst_msg->header.message_flags.msg_pending = 1; + r = -EAGAIN; + } else { + memcpy(&dst_msg->u.payload, &src_msg->u.payload, + src_msg->header.payload_size); + dst_msg->header.message_type = src_msg->header.message_type; + dst_msg->header.payload_size = src_msg->header.payload_size; + r = synic_set_irq(synic, sint); + if (r >= 1) + r = 0; + else if (r == 0) + r = -EFAULT; + } + kunmap_atomic(msg_page); + kvm_release_page_dirty(page); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); + return r; +} + +static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct hv_message *msg = &stimer->msg; + struct hv_timer_message_payload *payload = + (struct hv_timer_message_payload *)&msg->u.payload; + + payload->expiration_time = stimer->exp_time; + payload->delivery_time = get_time_ref_counter(vcpu->kvm); + return synic_deliver_msg(vcpu_to_synic(vcpu), + HV_STIMER_SINT(stimer->config), msg); +} + +static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) +{ + int r; + + stimer->msg_pending = true; + r = stimer_send_msg(stimer); + trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, r); + if (!r) { + stimer->msg_pending = false; + if (!(stimer->config & HV_STIMER_PERIODIC)) + stimer->config &= ~HV_STIMER_ENABLE; + } +} + +void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_stimer *stimer; + u64 time_now, exp_time; + int i; + + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) { + stimer = &hv_vcpu->stimer[i]; + if (stimer->config & HV_STIMER_ENABLE) { + exp_time = stimer->exp_time; + + if (exp_time) { + time_now = + get_time_ref_counter(vcpu->kvm); + if (time_now >= exp_time) + stimer_expiration(stimer); + } + + if ((stimer->config & HV_STIMER_ENABLE) && + stimer->count) + stimer_start(stimer); + else + stimer_cleanup(stimer); + } + } +} + +void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + int i; + + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + stimer_cleanup(&hv_vcpu->stimer[i]); +} + +static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer) +{ + struct hv_message *msg = &stimer->msg; + struct hv_timer_message_payload *payload = + (struct hv_timer_message_payload *)&msg->u.payload; + + memset(&msg->header, 0, sizeof(msg->header)); + msg->header.message_type = HVMSG_TIMER_EXPIRED; + msg->header.payload_size = sizeof(*payload); + + payload->timer_index = stimer->index; + payload->expiration_time = 0; + payload->delivery_time = 0; +} + +static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) +{ + memset(stimer, 0, sizeof(*stimer)); + stimer->index = timer_index; + hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + stimer->timer.function = stimer_timer_callback; + stimer_prepare_msg(stimer); +} + +void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + int i; + + synic_init(&hv_vcpu->synic); + + bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + stimer_init(&hv_vcpu->stimer[i], i); +} + +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu) +{ + /* + * Hyper-V SynIC auto EOI SINT's are + * not compatible with APICV, so deactivate APICV + */ + kvm_vcpu_deactivate_apicv(vcpu); + vcpu_to_synic(vcpu)->active = true; + return 0; +} + static bool kvm_hv_msr_partition_wide(u32 msr) { bool r = false; @@ -226,6 +878,31 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; hv->runtime_offset = data - current_task_runtime_100ns(); break; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host); + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: { + int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; + + return stimer_set_config(vcpu_to_stimer(vcpu, timer_index), + data, host); + } + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: { + int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; + + return stimer_set_count(vcpu_to_stimer(vcpu, timer_index), + data, host); + } default: vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", msr, data); @@ -248,11 +925,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_HYPERCALL: data = hv->hv_hypercall; break; - case HV_X64_MSR_TIME_REF_COUNT: { - data = - div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + case HV_X64_MSR_TIME_REF_COUNT: + data = get_time_ref_counter(kvm); break; - } case HV_X64_MSR_REFERENCE_TSC: data = hv->hv_tsc_page; break; @@ -304,6 +979,31 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_VP_RUNTIME: data = current_task_runtime_100ns() + hv->runtime_offset; break; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata); + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: { + int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; + + return stimer_get_config(vcpu_to_stimer(vcpu, timer_index), + pdata); + } + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: { + int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; + + return stimer_get_count(vcpu_to_stimer(vcpu, timer_index), + pdata); + } default: vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index c7bce559f..60eccd4bd 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -24,9 +24,64 @@ #ifndef __ARCH_X86_KVM_HYPERV_H__ #define __ARCH_X86_KVM_HYPERV_H__ +static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.hyperv; +} + +static inline struct kvm_vcpu *hv_vcpu_to_vcpu(struct kvm_vcpu_hv *hv_vcpu) +{ + struct kvm_vcpu_arch *arch; + + arch = container_of(hv_vcpu, struct kvm_vcpu_arch, hyperv); + return container_of(arch, struct kvm_vcpu, arch); +} + +static inline struct kvm_vcpu_hv_synic *vcpu_to_synic(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.hyperv.synic; +} + +static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) +{ + return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic)); +} + int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); + bool kvm_hv_hypercall_enabled(struct kvm *kvm); int kvm_hv_hypercall(struct kvm_vcpu *vcpu); +void kvm_hv_irq_routing_update(struct kvm *kvm); +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); +void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu); + +void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); + +static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu, + int timer_index) +{ + return &vcpu_to_hv_vcpu(vcpu)->stimer[timer_index]; +} + +static inline struct kvm_vcpu *stimer_to_vcpu(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu_hv *hv_vcpu; + + hv_vcpu = container_of(stimer - stimer->index, struct kvm_vcpu_hv, + stimer[0]); + return hv_vcpu_to_vcpu(hv_vcpu); +} + +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return !bitmap_empty(vcpu->arch.hyperv.stimer_pending_bitmap, + HV_SYNIC_STIMER_COUNT); +} + +void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 88d0a92d3..1facfd60b 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -233,7 +233,7 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr) } -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; union kvm_ioapic_redirect_entry *e; @@ -250,7 +250,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) (e->fields.trig_mode == IOAPIC_EDGE_TRIG && kvm_apic_pending_eoi(vcpu, e->fields.vector))) __set_bit(e->fields.vector, - (unsigned long *)eoi_exit_bitmap); + ioapic_handled_vectors); } } spin_unlock(&ioapic->lock); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 084617d37..2d16dc251 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -121,7 +121,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); -void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); - +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors); +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors); #endif diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c index 5c520ebf6..a22a488b4 100644 --- a/arch/x86/kvm/iommu.c +++ b/arch/x86/kvm/iommu.c @@ -43,11 +43,11 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm); static void kvm_iommu_put_pages(struct kvm *kvm, gfn_t base_gfn, unsigned long npages); -static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, +static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, unsigned long npages) { gfn_t end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; pfn = gfn_to_pfn_memslot(slot, gfn); end_gfn = gfn + npages; @@ -62,7 +62,8 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn, return pfn; } -static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn, + unsigned long npages) { unsigned long i; @@ -73,7 +74,7 @@ static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) { gfn_t gfn, end_gfn; - pfn_t pfn; + kvm_pfn_t pfn; int r = 0; struct iommu_domain *domain = kvm->arch.iommu_domain; int flags; @@ -275,7 +276,7 @@ static void kvm_iommu_put_pages(struct kvm *kvm, { struct iommu_domain *domain; gfn_t end_gfn, gfn; - pfn_t pfn; + kvm_pfn_t pfn; u64 phys; domain = kvm->arch.iommu_domain; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 097060e33..3982b479b 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -76,7 +76,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (kvm_cpu_has_extint(v)) return 1; - if (kvm_vcpu_apic_vid_enabled(v)) + if (kvm_vcpu_apicv_active(v)) return 0; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 84b96d319..8fc89efb5 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -33,6 +33,8 @@ #include "lapic.h" +#include "hyperv.h" + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -219,6 +221,16 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, srcu_read_unlock(&kvm->irq_srcu, idx); } +static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + if (!level) + return -1; + + return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); +} + int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { @@ -257,6 +269,11 @@ int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; break; + case KVM_IRQ_ROUTING_HV_SINT: + e->set = kvm_hv_set_sint; + e->hv_sint.vcpu = ue->u.hv_sint.vcpu; + e->hv_sint.sint = ue->u.hv_sint.sint; + break; default: goto out; } @@ -332,14 +349,15 @@ int kvm_setup_empty_irq_routing(struct kvm *kvm) return kvm_set_irq_routing(kvm, empty_routing, 0, 0); } -void kvm_arch_irq_routing_update(struct kvm *kvm) +void kvm_arch_post_irq_routing_update(struct kvm *kvm) { if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm)) return; kvm_make_scan_ioapic_request(kvm); } -void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors) { struct kvm *kvm = vcpu->kvm; struct kvm_kernel_irq_routing_entry *entry; @@ -369,9 +387,26 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) u32 vector = entry->msi.data & 0xff; __set_bit(vector, - (unsigned long *) eoi_exit_bitmap); + ioapic_handled_vectors); } } } srcu_read_unlock(&kvm->irq_srcu, idx); } + +int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + switch (irq->type) { + case KVM_IRQ_ROUTING_HV_SINT: + return kvm_hv_set_sint(irq, kvm, irq_source_id, level, + line_status); + default: + return -EWOULDBLOCK; + } +} + +void kvm_arch_irq_routing_update(struct kvm *kvm) +{ + kvm_hv_irq_routing_update(kvm); +} diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4d30b865b..3a045f39e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "trace.h" #include "x86.h" #include "cpuid.h" +#include "hyperv.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -128,11 +129,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline int kvm_apic_id(struct kvm_lapic *apic) -{ - return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; -} - /* The logical map is definitely wrong if we have multiple * modes at the same time. (Physical map is always right.) */ @@ -379,7 +375,8 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) if (!apic->irr_pending) return -1; - kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + if (apic->vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(apic->vcpu); result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); @@ -392,7 +389,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) vcpu = apic->vcpu; - if (unlikely(kvm_vcpu_apic_vid_enabled(vcpu))) { + if (unlikely(vcpu->arch.apicv_active)) { /* try to update RVI */ apic_clear_vector(vec, apic->regs + APIC_IRR); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -418,7 +415,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * because the processor can modify ISR under the hood. Instead * just set SVI. */ - if (unlikely(kvm_x86_ops->hwapic_isr_update)) + if (unlikely(vcpu->arch.apicv_active)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); else { ++apic->isr_count; @@ -466,7 +463,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * on the other hand isr_count and highest_isr_cache are unused * and must be left alone. */ - if (unlikely(kvm_x86_ops->hwapic_isr_update)) + if (unlikely(vcpu->arch.apicv_active)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); else { @@ -852,7 +849,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic_clear_vector(vector, apic->regs + APIC_TMR); } - if (kvm_x86_ops->deliver_posted_interrupt) + if (vcpu->arch.apicv_active) kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); else { apic_set_irr(vector, apic); @@ -932,7 +929,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) { - return test_bit(vector, (ulong *)apic->vcpu->arch.eoi_exit_bitmap); + return test_bit(vector, apic->vcpu->arch.ioapic_handled_vectors); } static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) @@ -974,6 +971,9 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); + if (test_bit(vector, vcpu_to_synic(apic->vcpu)->vec_bitmap)) + kvm_hv_synic_send_eoi(apic->vcpu, vector); + kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); return vector; @@ -1195,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; - wait_queue_head_t *q = &vcpu->wq; + struct swait_queue_head *q = &vcpu->wq; struct kvm_timer *ktimer = &apic->lapic_timer; if (atomic_read(&apic->lapic_timer.pending)) @@ -1204,8 +1204,8 @@ static void apic_timer_expired(struct kvm_lapic *apic) atomic_inc(&apic->lapic_timer.pending); kvm_set_pending_timer(vcpu); - if (waitqueue_active(q)) - wake_up_interruptible(q); + if (swait_active(q)) + swake_up(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; @@ -1225,7 +1225,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) int vec = reg & APIC_VECTOR_MASK; void *bitmap = apic->regs + APIC_ISR; - if (kvm_x86_ops->deliver_posted_interrupt) + if (vcpu->arch.apicv_active) bitmap = apic->regs + APIC_IRR; if (apic_test_vector(vec, bitmap)) @@ -1693,8 +1693,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = kvm_vcpu_apic_vid_enabled(vcpu); - apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0; + apic->irr_pending = vcpu->arch.apicv_active; + apic->isr_count = vcpu->arch.apicv_active ? 1 : 0; apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1883,6 +1883,12 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); + + if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { + apic_clear_isr(vector, apic); + apic_update_ppr(apic); + } + return vector; } @@ -1906,15 +1912,15 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = kvm_x86_ops->hwapic_isr_update ? + apic->isr_count = vcpu->arch.apicv_active ? 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; - if (kvm_x86_ops->hwapic_irr_update) + if (vcpu->arch.apicv_active) { kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); - if (unlikely(kvm_x86_ops->hwapic_isr_update)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); + } kvm_make_request(KVM_REQ_EVENT, vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_rtc_eoi_tracking_restore_one(vcpu); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index fde8e35d5..41bdb35b4 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -143,9 +143,9 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) return apic->vcpu->arch.apic_base & X2APIC_ENABLE; } -static inline bool kvm_vcpu_apic_vid_enabled(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->cpu_uses_apicv(vcpu); + return vcpu->arch.apic && vcpu->arch.apicv_active; } static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) @@ -164,6 +164,11 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } +static inline int kvm_apic_id(struct kvm_lapic *apic) +{ + return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e7c2c1428..1e7a49bfc 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -259,7 +259,7 @@ static unsigned get_mmio_spte_access(u64 spte) } static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, - pfn_t pfn, unsigned access) + kvm_pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { mark_mmio_spte(vcpu, sptep, gfn, access); @@ -311,11 +311,6 @@ static int is_large_pte(u64 pte) return pte & PT_PAGE_SIZE_MASK; } -static int is_rmap_spte(u64 pte) -{ - return is_shadow_present_pte(pte); -} - static int is_last_spte(u64 pte, int level) { if (level == PT_PAGE_TABLE_LEVEL) @@ -325,7 +320,7 @@ static int is_last_spte(u64 pte, int level) return 0; } -static pfn_t spte_to_pfn(u64 pte) +static kvm_pfn_t spte_to_pfn(u64 pte) { return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; } @@ -540,7 +535,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) u64 old_spte = *sptep; bool ret = false; - WARN_ON(!is_rmap_spte(new_spte)); + WARN_ON(!is_shadow_present_pte(new_spte)); if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); @@ -587,7 +582,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) */ static int mmu_spte_clear_track_bits(u64 *sptep) { - pfn_t pfn; + kvm_pfn_t pfn; u64 old_spte = *sptep; if (!spte_has_volatile_bits(old_spte)) @@ -595,7 +590,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep) else old_spte = __update_clear_spte_slow(sptep, 0ull); - if (!is_rmap_spte(old_spte)) + if (!is_shadow_present_pte(old_spte)) return 0; pfn = spte_to_pfn(old_spte); @@ -909,36 +904,35 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, } /* - * Pte mapping structures: + * About rmap_head encoding: * - * If pte_list bit zero is zero, then pte_list point to the spte. - * - * If pte_list bit zero is one, (then pte_list & ~1) points to a struct + * If the bit zero of rmap_head->val is clear, then it points to the only spte + * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct * pte_list_desc containing more mappings. - * - * Returns the number of pte entries before the spte was added or zero if - * the spte was not added. - * + */ + +/* + * Returns the number of pointers in the rmap chain, not counting the new one. */ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, - unsigned long *pte_list) + struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; int i, count = 0; - if (!*pte_list) { + if (!rmap_head->val) { rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte); - *pte_list = (unsigned long)spte; - } else if (!(*pte_list & 1)) { + rmap_head->val = (unsigned long)spte; + } else if (!(rmap_head->val & 1)) { rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte); desc = mmu_alloc_pte_list_desc(vcpu); - desc->sptes[0] = (u64 *)*pte_list; + desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; - *pte_list = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | 1; ++count; } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); - desc = (struct pte_list_desc *)(*pte_list & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { desc = desc->more; count += PTE_LIST_EXT; @@ -955,8 +949,9 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } static void -pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, - int i, struct pte_list_desc *prev_desc) +pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, + struct pte_list_desc *desc, int i, + struct pte_list_desc *prev_desc) { int j; @@ -967,43 +962,43 @@ pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, if (j != 0) return; if (!prev_desc && !desc->more) - *pte_list = (unsigned long)desc->sptes[0]; + rmap_head->val = (unsigned long)desc->sptes[0]; else if (prev_desc) prev_desc->more = desc->more; else - *pte_list = (unsigned long)desc->more | 1; + rmap_head->val = (unsigned long)desc->more | 1; mmu_free_pte_list_desc(desc); } -static void pte_list_remove(u64 *spte, unsigned long *pte_list) +static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; struct pte_list_desc *prev_desc; int i; - if (!*pte_list) { + if (!rmap_head->val) { printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte); BUG(); - } else if (!(*pte_list & 1)) { + } else if (!(rmap_head->val & 1)) { rmap_printk("pte_list_remove: %p 1->0\n", spte); - if ((u64 *)*pte_list != spte) { + if ((u64 *)rmap_head->val != spte) { printk(KERN_ERR "pte_list_remove: %p 1->BUG\n", spte); BUG(); } - *pte_list = 0; + rmap_head->val = 0; } else { rmap_printk("pte_list_remove: %p many->many\n", spte); - desc = (struct pte_list_desc *)(*pte_list & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); prev_desc = NULL; while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) + for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(pte_list, - desc, i, - prev_desc); + pte_list_desc_remove_entry(rmap_head, + desc, i, prev_desc); return; } + } prev_desc = desc; desc = desc->more; } @@ -1012,28 +1007,8 @@ static void pte_list_remove(u64 *spte, unsigned long *pte_list) } } -typedef void (*pte_list_walk_fn) (u64 *spte); -static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) -{ - struct pte_list_desc *desc; - int i; - - if (!*pte_list) - return; - - if (!(*pte_list & 1)) - return fn((u64 *)*pte_list); - - desc = (struct pte_list_desc *)(*pte_list & ~1ul); - while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) - fn(desc->sptes[i]); - desc = desc->more; - } -} - -static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { unsigned long idx; @@ -1041,10 +1016,8 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx]; } -/* - * Take gfn and return the reverse mapping to it. - */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) +static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, + struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; @@ -1065,24 +1038,24 @@ static bool rmap_can_add(struct kvm_vcpu *vcpu) static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { struct kvm_mmu_page *sp; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; sp = page_header(__pa(spte)); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); - return pte_list_add(vcpu, spte, rmapp); + rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); + return pte_list_add(vcpu, spte, rmap_head); } static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_mmu_page *sp; gfn_t gfn; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; sp = page_header(__pa(spte)); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmapp = gfn_to_rmap(kvm, gfn, sp); - pte_list_remove(spte, rmapp); + rmap_head = gfn_to_rmap(kvm, gfn, sp); + pte_list_remove(spte, rmap_head); } /* @@ -1102,19 +1075,26 @@ struct rmap_iterator { * * Returns sptep if found, NULL otherwise. */ -static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) +static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, + struct rmap_iterator *iter) { - if (!rmap) + u64 *sptep; + + if (!rmap_head->val) return NULL; - if (!(rmap & 1)) { + if (!(rmap_head->val & 1)) { iter->desc = NULL; - return (u64 *)rmap; + sptep = (u64 *)rmap_head->val; + goto out; } - iter->desc = (struct pte_list_desc *)(rmap & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); iter->pos = 0; - return iter->desc->sptes[iter->pos]; + sptep = iter->desc->sptes[iter->pos]; +out: + BUG_ON(!is_shadow_present_pte(*sptep)); + return sptep; } /* @@ -1124,14 +1104,14 @@ static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) */ static u64 *rmap_get_next(struct rmap_iterator *iter) { + u64 *sptep; + if (iter->desc) { if (iter->pos < PTE_LIST_EXT - 1) { - u64 *sptep; - ++iter->pos; sptep = iter->desc->sptes[iter->pos]; if (sptep) - return sptep; + goto out; } iter->desc = iter->desc->more; @@ -1139,17 +1119,20 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) if (iter->desc) { iter->pos = 0; /* desc->sptes[0] cannot be NULL */ - return iter->desc->sptes[iter->pos]; + sptep = iter->desc->sptes[iter->pos]; + goto out; } } return NULL; +out: + BUG_ON(!is_shadow_present_pte(*sptep)); + return sptep; } -#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \ - for (_spte_ = rmap_get_first(*_rmap_, _iter_); \ - _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \ - _spte_ = rmap_get_next(_iter_)) +#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_) \ + for (_spte_ = rmap_get_first(_rmap_head_, _iter_); \ + _spte_; _spte_ = rmap_get_next(_iter_)) static void drop_spte(struct kvm *kvm, u64 *sptep) { @@ -1207,14 +1190,15 @@ static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) return mmu_spte_update(sptep, spte); } -static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, +static bool __rmap_write_protect(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, bool pt_protect) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_write_protect(kvm, sptep, pt_protect); return flush; @@ -1231,13 +1215,13 @@ static bool spte_clear_dirty(struct kvm *kvm, u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp) +static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_clear_dirty(kvm, sptep); return flush; @@ -1254,13 +1238,13 @@ static bool spte_set_dirty(struct kvm *kvm, u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp) +static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_set_dirty(kvm, sptep); return flush; @@ -1280,12 +1264,12 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; while (mask) { - rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); - __rmap_write_protect(kvm, rmapp, false); + rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_write_protect(kvm, rmap_head, false); /* clear the first set bit */ mask &= mask - 1; @@ -1305,12 +1289,12 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; while (mask) { - rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); - __rmap_clear_dirty(kvm, rmapp); + rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_clear_dirty(kvm, rmap_head); /* clear the first set bit */ mask &= mask - 1; @@ -1342,28 +1326,27 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true); + rmap_head = __gfn_to_rmap(gfn, i, slot); + write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true); } return write_protected; } -static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) +static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - while ((sptep = rmap_get_first(*rmapp, &iter))) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + while ((sptep = rmap_get_first(rmap_head, &iter))) { rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); drop_spte(kvm, sptep); @@ -1373,14 +1356,14 @@ static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) return flush; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { - return kvm_zap_rmapp(kvm, rmapp); + return kvm_zap_rmapp(kvm, rmap_head); } -static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1389,13 +1372,13 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, int need_flush = 0; u64 new_spte; pte_t *ptep = (pte_t *)data; - pfn_t new_pfn; + kvm_pfn_t new_pfn; WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); restart: - for_each_rmap_spte(rmapp, &iter, sptep) { + for_each_rmap_spte(rmap_head, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); @@ -1433,11 +1416,11 @@ struct slot_rmap_walk_iterator { /* output fields. */ gfn_t gfn; - unsigned long *rmap; + struct kvm_rmap_head *rmap; int level; /* private field. */ - unsigned long *end_rmap; + struct kvm_rmap_head *end_rmap; }; static void @@ -1496,7 +1479,7 @@ static int kvm_handle_hva_range(struct kvm *kvm, unsigned long end, unsigned long data, int (*handler)(struct kvm *kvm, - unsigned long *rmapp, + struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, @@ -1540,7 +1523,8 @@ static int kvm_handle_hva_range(struct kvm *kvm, static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, unsigned long data, - int (*handler)(struct kvm *kvm, unsigned long *rmapp, + int (*handler)(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data)) @@ -1563,7 +1547,7 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); } -static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1573,18 +1557,19 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, BUG_ON(!shadow_accessed_mask); - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (*sptep & shadow_accessed_mask) { young = 1; clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } + } trace_kvm_age_page(gfn, level, slot, young); return young; } -static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1600,11 +1585,12 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (*sptep & shadow_accessed_mask) { young = 1; break; } + } out: return young; } @@ -1613,14 +1599,14 @@ out: static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *sp; sp = page_header(__pa(spte)); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); + rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); - kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0); + kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0); kvm_flush_remote_tlbs(vcpu->kvm); } @@ -1720,8 +1706,7 @@ static void drop_parent_pte(struct kvm_mmu_page *sp, mmu_spte_clear_no_track(parent_pte); } -static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte, int direct) +static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct) { struct kvm_mmu_page *sp; @@ -1737,8 +1722,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, * this feature. See the comments in kvm_zap_obsolete_pages(). */ list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - sp->parent_ptes = 0; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; } @@ -1746,7 +1729,12 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, static void mark_unsync(u64 *spte); static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { - pte_list_walk(&sp->parent_ptes, mark_unsync); + u64 *sptep; + struct rmap_iterator iter; + + for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) { + mark_unsync(sptep); + } } static void mark_unsync(u64 *spte) @@ -1806,6 +1794,13 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, return (pvec->nr == KVM_PAGE_ARRAY_NR); } +static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx) +{ + --sp->unsync_children; + WARN_ON((int)sp->unsync_children < 0); + __clear_bit(idx, sp->unsync_child_bitmap); +} + static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_pages *pvec) { @@ -1815,8 +1810,10 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_page *child; u64 ent = sp->spt[i]; - if (!is_shadow_present_pte(ent) || is_large_pte(ent)) - goto clear_child_bitmap; + if (!is_shadow_present_pte(ent) || is_large_pte(ent)) { + clear_unsync_child_bit(sp, i); + continue; + } child = page_header(ent & PT64_BASE_ADDR_MASK); @@ -1825,28 +1822,21 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, return -ENOSPC; ret = __mmu_unsync_walk(child, pvec); - if (!ret) - goto clear_child_bitmap; - else if (ret > 0) + if (!ret) { + clear_unsync_child_bit(sp, i); + continue; + } else if (ret > 0) { nr_unsync_leaf += ret; - else + } else return ret; } else if (child->unsync) { nr_unsync_leaf++; if (mmu_pages_add(pvec, child, i)) return -ENOSPC; } else - goto clear_child_bitmap; - - continue; - -clear_child_bitmap: - __clear_bit(i, sp->unsync_child_bitmap); - sp->unsync_children--; - WARN_ON((int)sp->unsync_children < 0); + clear_unsync_child_bit(sp, i); } - return nr_unsync_leaf; } @@ -2009,9 +1999,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) if (!sp) return; - --sp->unsync_children; - WARN_ON((int)sp->unsync_children < 0); - __clear_bit(idx, sp->unsync_child_bitmap); + clear_unsync_child_bit(sp, idx); level++; } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children); } @@ -2053,14 +2041,6 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } } -static void init_shadow_page_table(struct kvm_mmu_page *sp) -{ - int i; - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) - sp->spt[i] = 0ull; -} - static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) { sp->write_flooding_count = 0; @@ -2083,8 +2063,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int direct, - unsigned access, - u64 *parent_pte) + unsigned access) { union kvm_mmu_page_role role; unsigned quadrant; @@ -2116,21 +2095,18 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (sp->unsync && kvm_sync_page_transient(vcpu, sp)) break; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); - if (sp->unsync_children) { + if (sp->unsync_children) kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_mmu_mark_parents_unsync(sp); - } else if (sp->unsync) - kvm_mmu_mark_parents_unsync(sp); __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); return sp; } + ++vcpu->kvm->stat.mmu_cache_miss; - sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct); - if (!sp) - return sp; + + sp = kvm_mmu_alloc_page(vcpu, direct); + sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, @@ -2144,7 +2120,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; - init_shadow_page_table(sp); + clear_page(sp->spt); trace_kvm_mmu_get_page(sp, true); return sp; } @@ -2198,7 +2174,8 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) return __shadow_walk_next(iterator, *iterator->sptep); } -static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) +static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, + struct kvm_mmu_page *sp) { u64 spte; @@ -2206,12 +2183,14 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask; - - if (accessed) - spte |= shadow_accessed_mask; + shadow_user_mask | shadow_x_mask | shadow_accessed_mask; mmu_spte_set(sptep, spte); + + mmu_page_add_parent_pte(vcpu, sp, sptep); + + if (sp->unsync_children || sp->unsync) + mark_unsync(sptep); } static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, @@ -2270,17 +2249,12 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, mmu_page_zap_pte(kvm, sp, sp->spt + i); } -static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) -{ - mmu_page_remove_parent_pte(sp, parent_pte); -} - static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; - while ((sptep = rmap_get_first(sp->parent_ptes, &iter))) + while ((sptep = rmap_get_first(&sp->parent_ptes, &iter))) drop_parent_pte(sp, sptep); } @@ -2476,7 +2450,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } -static bool kvm_is_mmio_pfn(pfn_t pfn) +static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) { if (pfn_valid(pfn)) return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); @@ -2486,7 +2460,7 @@ static bool kvm_is_mmio_pfn(pfn_t pfn) static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, - gfn_t gfn, pfn_t pfn, bool speculative, + gfn_t gfn, kvm_pfn_t pfn, bool speculative, bool can_unsync, bool host_writable) { u64 spte; @@ -2564,18 +2538,18 @@ done: return ret; } -static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int write_fault, int *emulate, - int level, gfn_t gfn, pfn_t pfn, bool speculative, - bool host_writable) +static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, + int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn, + bool speculative, bool host_writable) { int was_rmapped = 0; int rmap_count; + bool emulate = false; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); - if (is_rmap_spte(*sptep)) { + if (is_shadow_present_pte(*sptep)) { /* * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. @@ -2600,12 +2574,12 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, true, host_writable)) { if (write_fault) - *emulate = 1; + emulate = true; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } - if (unlikely(is_mmio_spte(*sptep) && emulate)) - *emulate = 1; + if (unlikely(is_mmio_spte(*sptep))) + emulate = true; pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", @@ -2624,9 +2598,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } kvm_release_pfn_clean(pfn); + + return emulate; } -static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, +static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -2658,9 +2634,8 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, return -1; for (i = 0; i < ret; i++, gfn++, start++) - mmu_set_spte(vcpu, start, access, 0, NULL, - sp->role.level, gfn, page_to_pfn(pages[i]), - true, true); + mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, + page_to_pfn(pages[i]), true, true); return 0; } @@ -2708,9 +2683,8 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int map_writable, int level, gfn_t gfn, pfn_t pfn, - bool prefault) +static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, + int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -2722,9 +2696,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { if (iterator.level == level) { - mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, &emulate, level, gfn, pfn, - prefault, map_writable); + emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, + write, level, gfn, pfn, prefault, + map_writable); direct_pte_prefetch(vcpu, iterator.sptep); ++vcpu->stat.pf_fixed; break; @@ -2737,10 +2711,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, base_addr &= PT64_LVL_ADDR_MASK(iterator.level); pseudo_gfn = base_addr >> PAGE_SHIFT; sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, - 1, ACC_ALL, iterator.sptep); + iterator.level - 1, 1, ACC_ALL); - link_shadow_page(iterator.sptep, sp, true); + link_shadow_page(vcpu, iterator.sptep, sp); } } return emulate; @@ -2759,7 +2732,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_info(SIGBUS, &info, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) +static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { /* * Do not cache the mmio info caused by writing the readonly gfn @@ -2779,9 +2752,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) } static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, - gfn_t *gfnp, pfn_t *pfnp, int *levelp) + gfn_t *gfnp, kvm_pfn_t *pfnp, + int *levelp) { - pfn_t pfn = *pfnp; + kvm_pfn_t pfn = *pfnp; gfn_t gfn = *gfnp; int level = *levelp; @@ -2820,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, } static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn, - pfn_t pfn, unsigned access, int *ret_val) + kvm_pfn_t pfn, unsigned access, int *ret_val) { bool ret = true; @@ -2919,7 +2893,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, * If the mapping has been changed, let the vcpu fault on the * same address again. */ - if (!is_rmap_spte(spte)) { + if (!is_shadow_present_pte(spte)) { ret = true; goto exit; } @@ -2974,7 +2948,7 @@ exit: } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable); + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable); static void make_mmu_pages_available(struct kvm_vcpu *vcpu); static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, @@ -2983,7 +2957,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, int r; int level; bool force_pt_level = false; - pfn_t pfn; + kvm_pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; @@ -3018,11 +2992,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn, - prefault); + r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); - return r; out_unlock: @@ -3097,8 +3069,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); - sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, - 1, ACC_ALL, NULL); + sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = __pa(sp->spt); @@ -3110,9 +3081,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), - i << 30, - PT32_ROOT_LEVEL, 1, ACC_ALL, - NULL); + i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3149,7 +3118,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, - 0, ACC_ALL, NULL); + 0, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3182,9 +3151,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); - sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, 0, - ACC_ALL, NULL); + sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, + 0, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3443,7 +3411,7 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gva_t gva, pfn_t *pfn, bool write, bool *writable) + gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable) { struct kvm_memory_slot *slot; bool async; @@ -3481,7 +3449,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { - pfn_t pfn; + kvm_pfn_t pfn; int r; int level; bool force_pt_level; @@ -3531,8 +3499,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, - level, gfn, pfn, prefault); + r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); return r; @@ -3754,13 +3721,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } @@ -4058,10 +4027,12 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->inject_page_fault = kvm_inject_page_fault; /* - * Note that arch.mmu.gva_to_gpa translates l2_gva to l1_gpa. The - * translation of l2_gpa to l1_gpa addresses is done using the - * arch.nested_mmu.gva_to_gpa function. Basically the gva_to_gpa - * functions between mmu and nested_mmu are swapped. + * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using + * L1's nested page tables (e.g. EPT12). The nested translation + * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using + * L2's page tables as the first level of translation and L1's + * nested page tables as the second level of translation. Basically + * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) { g_context->nx = false; @@ -4495,7 +4466,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) } /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap); +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ static bool @@ -4589,9 +4560,10 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) spin_unlock(&kvm->mmu_lock); } -static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) +static bool slot_rmap_write_protect(struct kvm *kvm, + struct kvm_rmap_head *rmap_head) { - return __rmap_write_protect(kvm, rmapp, false); + return __rmap_write_protect(kvm, rmap_head, false); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -4627,16 +4599,16 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, - unsigned long *rmapp) + struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; int need_tlb_flush = 0; - pfn_t pfn; + kvm_pfn_t pfn; struct kvm_mmu_page *sp; restart: - for_each_rmap_spte(rmapp, &iter, sptep) { + for_each_rmap_spte(rmap_head, &iter, sptep) { sp = page_header(__pa(sptep)); pfn = spte_to_pfn(*sptep); diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 03d518e49..dcce533d4 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -97,7 +97,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) { struct kvm_mmu_page *sp; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; hpa_t hpa; sp = page_header(__pa(sptep)); @@ -129,7 +129,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *rev_sp; struct kvm_memslots *slots; struct kvm_memory_slot *slot; @@ -150,8 +150,8 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot); - if (!*rmapp) { + rmap_head = __gfn_to_rmap(gfn, rev_sp->role.level, slot); + if (!rmap_head->val) { if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no rmap for writable spte %llx\n", @@ -183,7 +183,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) return; for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (!is_rmap_spte(sp->spt[i])) + if (!is_shadow_present_pte(sp->spt[i])) continue; inspect_spte_has_rmap(kvm, sp->spt + i); @@ -192,7 +192,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; u64 *sptep; struct rmap_iterator iter; struct kvm_memslots *slots; @@ -203,13 +203,14 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, sp->gfn); - rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); + rmap_head = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (is_writable_pte(*sptep)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); + } } static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 7be8a2513..2ce4f05e8 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -456,7 +456,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, { unsigned pte_access; gfn_t gfn; - pfn_t pfn; + kvm_pfn_t pfn; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; @@ -475,8 +475,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * we call mmu_set_spte() with host_writable = true because * pte_prefetch_gfn_to_pfn always gets a writable pfn. */ - mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL, - gfn, pfn, true, true); + mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, + true, true); return true; } @@ -551,12 +551,12 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct guest_walker *gw, int write_fault, int hlevel, - pfn_t pfn, bool map_writable, bool prefault) + kvm_pfn_t pfn, bool map_writable, bool prefault) { struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, emulate = 0; + int top_level, emulate; direct_access = gw->pte_access; @@ -587,7 +587,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access, it.sptep); + false, access); } /* @@ -598,7 +598,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, goto out_gpte_changed; if (sp) - link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); + link_shadow_page(vcpu, it.sptep, sp); } for (; @@ -617,20 +617,18 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access, it.sptep); - link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); + true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); } clear_sp_write_flooding_count(it.sptep); - mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate, - it.level, gw->gfn, pfn, prefault, map_writable); + emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, + it.level, gw->gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); return emulate; out_gpte_changed: - if (sp) - kvm_mmu_put_page(sp, it.sptep); kvm_release_pfn_clean(pfn); return 0; } @@ -696,7 +694,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int user_fault = error_code & PFERR_USER_MASK; struct guest_walker walker; int r; - pfn_t pfn; + kvm_pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; bool force_pt_level = false; unsigned long mmu_seq; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 899c40f82..c13a64b7d 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -86,6 +86,7 @@ static const u32 host_save_user_msrs[] = { MSR_FS_BASE, #endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_TSC_AUX, }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) @@ -135,6 +136,7 @@ struct vcpu_svm { uint64_t asid_generation; uint64_t sysenter_esp; uint64_t sysenter_eip; + uint64_t tsc_aux; u64 next_rip; @@ -1238,6 +1240,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); } } + /* This assumes that the kernel never uses MSR_TSC_AUX */ + if (static_cpu_has(X86_FEATURE_RDTSCP)) + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) @@ -3024,6 +3029,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_SYSENTER_ESP: msr_info->data = svm->sysenter_esp; break; + case MSR_TSC_AUX: + if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + return 1; + msr_info->data = svm->tsc_aux; + break; /* * Nobody will change the following 5 values in the VMCB so we can * safely return them on rdmsr. They will always be 0 until LBRV is @@ -3053,6 +3063,23 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; + case MSR_F15H_IC_CFG: { + + int family, model; + + family = guest_cpuid_family(vcpu); + model = guest_cpuid_model(vcpu); + + if (family < 0 || model < 0) + return kvm_get_msr_common(vcpu, msr_info); + + msr_info->data = 0; + + if (family == 0x15 && + (model >= 0x2 && model < 0x20)) + msr_info->data = 0x1E; + } + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -3145,6 +3172,18 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp = data; svm->vmcb->save.sysenter_esp = data; break; + case MSR_TSC_AUX: + if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + return 1; + + /* + * This is rare, so we update the MSR here instead of using + * direct_access_msrs. Doing that would require a rdmsr in + * svm_vcpu_put. + */ + svm->tsc_aux = data; + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + break; case MSR_IA32_DEBUGCTLMSR: if (!boot_cpu_has(X86_FEATURE_LBRV)) { vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", @@ -3561,12 +3600,16 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } -static int svm_cpu_uses_apicv(struct kvm_vcpu *vcpu) +static bool svm_get_enable_apicv(void) { - return 0; + return false; } -static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu) +static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ +} + +static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { return; } @@ -4037,7 +4080,7 @@ static int svm_get_lpage_level(void) static bool svm_rdtscp_supported(void) { - return false; + return boot_cpu_has(X86_FEATURE_RDTSCP); } static bool svm_invpcid_supported(void) @@ -4328,7 +4371,8 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, - .cpu_uses_apicv = svm_cpu_uses_apicv, + .get_enable_apicv = svm_get_enable_apicv, + .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, .sync_pir_to_irr = svm_sync_pir_to_irr, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index ab9ae67a8..ad9f6a23f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1025,6 +1025,269 @@ TRACE_EVENT(kvm_pi_irte_update, __entry->pi_desc_addr) ); +/* + * Tracepoint for kvm_hv_notify_acked_sint. + */ +TRACE_EVENT(kvm_hv_notify_acked_sint, + TP_PROTO(int vcpu_id, u32 sint), + TP_ARGS(vcpu_id, sint), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sint = sint; + ), + + TP_printk("vcpu_id %d sint %u", __entry->vcpu_id, __entry->sint) +); + +/* + * Tracepoint for synic_set_irq. + */ +TRACE_EVENT(kvm_hv_synic_set_irq, + TP_PROTO(int vcpu_id, u32 sint, int vector, int ret), + TP_ARGS(vcpu_id, sint, vector, ret), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + __field(int, vector) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sint = sint; + __entry->vector = vector; + __entry->ret = ret; + ), + + TP_printk("vcpu_id %d sint %u vector %d ret %d", + __entry->vcpu_id, __entry->sint, __entry->vector, + __entry->ret) +); + +/* + * Tracepoint for kvm_hv_synic_send_eoi. + */ +TRACE_EVENT(kvm_hv_synic_send_eoi, + TP_PROTO(int vcpu_id, int vector), + TP_ARGS(vcpu_id, vector), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + __field(int, vector) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vector = vector; + ), + + TP_printk("vcpu_id %d vector %d", __entry->vcpu_id, __entry->vector) +); + +/* + * Tracepoint for synic_set_msr. + */ +TRACE_EVENT(kvm_hv_synic_set_msr, + TP_PROTO(int vcpu_id, u32 msr, u64 data, bool host), + TP_ARGS(vcpu_id, msr, data, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, msr) + __field(u64, data) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->msr = msr; + __entry->data = data; + __entry->host = host + ), + + TP_printk("vcpu_id %d msr 0x%x data 0x%llx host %d", + __entry->vcpu_id, __entry->msr, __entry->data, __entry->host) +); + +/* + * Tracepoint for stimer_set_config. + */ +TRACE_EVENT(kvm_hv_stimer_set_config, + TP_PROTO(int vcpu_id, int timer_index, u64 config, bool host), + TP_ARGS(vcpu_id, timer_index, config, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, config) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->config = config; + __entry->host = host; + ), + + TP_printk("vcpu_id %d timer %d config 0x%llx host %d", + __entry->vcpu_id, __entry->timer_index, __entry->config, + __entry->host) +); + +/* + * Tracepoint for stimer_set_count. + */ +TRACE_EVENT(kvm_hv_stimer_set_count, + TP_PROTO(int vcpu_id, int timer_index, u64 count, bool host), + TP_ARGS(vcpu_id, timer_index, count, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, count) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->count = count; + __entry->host = host; + ), + + TP_printk("vcpu_id %d timer %d count %llu host %d", + __entry->vcpu_id, __entry->timer_index, __entry->count, + __entry->host) +); + +/* + * Tracepoint for stimer_start(periodic timer case). + */ +TRACE_EVENT(kvm_hv_stimer_start_periodic, + TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 exp_time), + TP_ARGS(vcpu_id, timer_index, time_now, exp_time), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, time_now) + __field(u64, exp_time) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->time_now = time_now; + __entry->exp_time = exp_time; + ), + + TP_printk("vcpu_id %d timer %d time_now %llu exp_time %llu", + __entry->vcpu_id, __entry->timer_index, __entry->time_now, + __entry->exp_time) +); + +/* + * Tracepoint for stimer_start(one-shot timer case). + */ +TRACE_EVENT(kvm_hv_stimer_start_one_shot, + TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 count), + TP_ARGS(vcpu_id, timer_index, time_now, count), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, time_now) + __field(u64, count) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->time_now = time_now; + __entry->count = count; + ), + + TP_printk("vcpu_id %d timer %d time_now %llu count %llu", + __entry->vcpu_id, __entry->timer_index, __entry->time_now, + __entry->count) +); + +/* + * Tracepoint for stimer_timer_callback. + */ +TRACE_EVENT(kvm_hv_stimer_callback, + TP_PROTO(int vcpu_id, int timer_index), + TP_ARGS(vcpu_id, timer_index), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + ), + + TP_printk("vcpu_id %d timer %d", + __entry->vcpu_id, __entry->timer_index) +); + +/* + * Tracepoint for stimer_expiration. + */ +TRACE_EVENT(kvm_hv_stimer_expiration, + TP_PROTO(int vcpu_id, int timer_index, int msg_send_result), + TP_ARGS(vcpu_id, timer_index, msg_send_result), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(int, msg_send_result) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->msg_send_result = msg_send_result; + ), + + TP_printk("vcpu_id %d timer %d msg send result %d", + __entry->vcpu_id, __entry->timer_index, + __entry->msg_send_result) +); + +/* + * Tracepoint for stimer_cleanup. + */ +TRACE_EVENT(kvm_hv_stimer_cleanup, + TP_PROTO(int vcpu_id, int timer_index), + TP_ARGS(vcpu_id, timer_index), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + ), + + TP_printk("vcpu_id %d timer %d", + __entry->vcpu_id, __entry->timer_index) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5fd846cd6..9bd8f44ba 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -19,6 +19,7 @@ #include "irq.h" #include "mmu.h" #include "cpuid.h" +#include "lapic.h" #include <linux/kvm_host.h> #include <linux/module.h> @@ -864,7 +865,6 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static bool vmx_mpx_supported(void); static bool vmx_xsaves_supported(void); -static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -872,7 +872,6 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static bool guest_state_valid(struct kvm_vcpu *vcpu); static u32 vmx_segment_access_rights(struct kvm_segment *var); -static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); @@ -1450,7 +1449,51 @@ static inline void ept_sync_context(u64 eptp) } } -static __always_inline unsigned long vmcs_readl(unsigned long field) +static __always_inline void vmcs_check16(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, + "16-bit accessor invalid for 64-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "16-bit accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "16-bit accessor invalid for 32-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "16-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_check32(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "32-bit accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "32-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_check64(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "64-bit accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "64-bit accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "64-bit accessor invalid for 32-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "64-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_checkl(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "Natural width accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, + "Natural width accessor invalid for 64-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "Natural width accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "Natural width accessor invalid for 32-bit field"); +} + +static __always_inline unsigned long __vmcs_readl(unsigned long field) { unsigned long value; @@ -1461,23 +1504,32 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) static __always_inline u16 vmcs_read16(unsigned long field) { - return vmcs_readl(field); + vmcs_check16(field); + return __vmcs_readl(field); } static __always_inline u32 vmcs_read32(unsigned long field) { - return vmcs_readl(field); + vmcs_check32(field); + return __vmcs_readl(field); } static __always_inline u64 vmcs_read64(unsigned long field) { + vmcs_check64(field); #ifdef CONFIG_X86_64 - return vmcs_readl(field); + return __vmcs_readl(field); #else - return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32); + return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32); #endif } +static __always_inline unsigned long vmcs_readl(unsigned long field) +{ + vmcs_checkl(field); + return __vmcs_readl(field); +} + static noinline void vmwrite_error(unsigned long field, unsigned long value) { printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", @@ -1485,7 +1537,7 @@ static noinline void vmwrite_error(unsigned long field, unsigned long value) dump_stack(); } -static void vmcs_writel(unsigned long field, unsigned long value) +static __always_inline void __vmcs_writel(unsigned long field, unsigned long value) { u8 error; @@ -1495,33 +1547,46 @@ static void vmcs_writel(unsigned long field, unsigned long value) vmwrite_error(field, value); } -static void vmcs_write16(unsigned long field, u16 value) +static __always_inline void vmcs_write16(unsigned long field, u16 value) { - vmcs_writel(field, value); + vmcs_check16(field); + __vmcs_writel(field, value); } -static void vmcs_write32(unsigned long field, u32 value) +static __always_inline void vmcs_write32(unsigned long field, u32 value) { - vmcs_writel(field, value); + vmcs_check32(field); + __vmcs_writel(field, value); } -static void vmcs_write64(unsigned long field, u64 value) +static __always_inline void vmcs_write64(unsigned long field, u64 value) { - vmcs_writel(field, value); + vmcs_check64(field); + __vmcs_writel(field, value); #ifndef CONFIG_X86_64 asm volatile (""); - vmcs_writel(field+1, value >> 32); + __vmcs_writel(field+1, value >> 32); #endif } -static void vmcs_clear_bits(unsigned long field, u32 mask) +static __always_inline void vmcs_writel(unsigned long field, unsigned long value) { - vmcs_writel(field, vmcs_readl(field) & ~mask); + vmcs_checkl(field); + __vmcs_writel(field, value); } -static void vmcs_set_bits(unsigned long field, u32 mask) +static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask) { - vmcs_writel(field, vmcs_readl(field) | mask); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, + "vmcs_clear_bits does not support 64-bit fields"); + __vmcs_writel(field, __vmcs_readl(field) & ~mask); +} + +static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, + "vmcs_set_bits does not support 64-bit fields"); + __vmcs_writel(field, __vmcs_readl(field) | mask); } static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val) @@ -1748,6 +1813,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1785,26 +1857,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1815,16 +1892,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -2502,7 +2584,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - if (vmx_cpu_uses_apicv(&vmx->vcpu)) + if (kvm_vcpu_apicv_active(&vmx->vcpu)) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_POSTED_INTR; @@ -4190,7 +4272,7 @@ out: static int init_rmode_identity_map(struct kvm *kvm) { int i, idx, r = 0; - pfn_t identity_map_pfn; + kvm_pfn_t identity_map_pfn; u32 tmp; if (!enable_ept) @@ -4466,9 +4548,9 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } -static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu) +static bool vmx_get_enable_apicv(void) { - return enable_apicv && lapic_in_kernel(vcpu); + return enable_apicv; } static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4590,11 +4672,6 @@ static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); } -static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu) -{ - return; -} - /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. @@ -4664,11 +4741,18 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - if (!vmx_cpu_uses_apicv(&vmx->vcpu)) + if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; return pin_based_exec_ctrl; } +static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); +} + static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; @@ -4707,7 +4791,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!vmx_cpu_uses_apicv(&vmx->vcpu)) + if (!kvm_vcpu_apicv_active(&vmx->vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; @@ -4771,7 +4855,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, vmx_secondary_exec_control(vmx)); - if (vmx_cpu_uses_apicv(&vmx->vcpu)) { + if (kvm_vcpu_apicv_active(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); @@ -4779,7 +4863,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(GUEST_INTR_STATUS, 0); - vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); } @@ -4871,7 +4955,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_write32(GUEST_CS_BASE, 0xffff0000); + vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); @@ -4907,7 +4991,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); - vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); setup_msrs(vmx); @@ -4923,7 +5007,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx_cpu_uses_apicv(vcpu)) + if (kvm_vcpu_apicv_active(vcpu)) memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); if (vmx->vpid != 0) @@ -6207,15 +6291,6 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - if (enable_apicv) - kvm_x86_ops->update_cr8_intercept = NULL; - else { - kvm_x86_ops->hwapic_irr_update = NULL; - kvm_x86_ops->hwapic_isr_update = NULL; - kvm_x86_ops->deliver_posted_interrupt = NULL; - kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy; - } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); vmx_disable_intercept_for_msr(MSR_GS_BASE, false); vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); @@ -7905,7 +7980,7 @@ static void dump_vmcs(void) u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); u32 secondary_exec_control = 0; unsigned long cr4 = vmcs_readl(GUEST_CR4); - u64 efer = vmcs_readl(GUEST_IA32_EFER); + u64 efer = vmcs_read64(GUEST_IA32_EFER); int i, n; if (cpu_has_secondary_exec_ctrls()) @@ -7921,10 +7996,10 @@ static void dump_vmcs(void) if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) { - pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n", - vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1)); - pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n", - vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3)); + pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", + vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", + vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); } pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); @@ -7945,16 +8020,16 @@ static void dump_vmcs(void) vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) - pr_err("EFER = 0x%016llx PAT = 0x%016lx\n", - efer, vmcs_readl(GUEST_IA32_PAT)); - pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n", - vmcs_readl(GUEST_IA32_DEBUGCTL), + pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", + efer, vmcs_read64(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", + vmcs_read64(GUEST_IA32_DEBUGCTL), vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016lx\n", - vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL)); + pr_err("PerfGlobCtl = 0x%016llx\n", + vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) - pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); pr_err("Interruptibility = %08x ActivityState = %08x\n", vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), vmcs_read32(GUEST_ACTIVITY_STATE)); @@ -7983,11 +8058,12 @@ static void dump_vmcs(void) vmcs_read32(HOST_IA32_SYSENTER_CS), vmcs_readl(HOST_IA32_SYSENTER_EIP)); if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) - pr_err("EFER = 0x%016lx PAT = 0x%016lx\n", - vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT)); + pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", + vmcs_read64(HOST_IA32_EFER), + vmcs_read64(HOST_IA32_PAT)); if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016lx\n", - vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL)); + pr_err("PerfGlobCtl = 0x%016llx\n", + vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); pr_err("*** Control State ***\n"); pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", @@ -8010,16 +8086,16 @@ static void dump_vmcs(void) pr_err("IDTVectoring: info=%08x errcode=%08x\n", vmcs_read32(IDT_VECTORING_INFO_FIELD), vmcs_read32(IDT_VECTORING_ERROR_CODE)); - pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) - pr_err("TSC Multiplier = 0x%016lx\n", - vmcs_readl(TSC_MULTIPLIER)); + pr_err("TSC Multiplier = 0x%016llx\n", + vmcs_read64(TSC_MULTIPLIER)); if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) - pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER)); + pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); n = vmcs_read32(CR3_TARGET_COUNT); for (i = 0; i + 1 < n; i += 4) pr_err("CR3 target%u=%016lx target%u=%016lx\n", @@ -8158,7 +8234,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) * apicv */ if (!cpu_has_vmx_virtualize_x2apic_mode() || - !vmx_cpu_uses_apicv(vcpu)) + !kvm_vcpu_apicv_active(vcpu)) return; if (!cpu_need_tpr_shadow(vcpu)) @@ -8263,10 +8339,9 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu) +static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { - u64 *eoi_exit_bitmap = vcpu->arch.eoi_exit_bitmap; - if (!vmx_cpu_uses_apicv(vcpu)) + if (!kvm_vcpu_apicv_active(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); @@ -9513,7 +9588,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) */ vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, page_to_phys(vmx->nested.pi_desc_page) + (unsigned long)(vmcs12->posted_intr_desc_addr & @@ -10174,7 +10249,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Additionally, restore L2's PDPTR to vmcs12. */ if (enable_ept) { - vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3); + vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3); vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); @@ -10810,7 +10885,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .cpu_uses_apicv = vmx_cpu_uses_apicv, + .get_enable_apicv = vmx_get_enable_apicv, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d2945024e..eaf6ee8c2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -966,6 +966,8 @@ static u32 emulated_msrs[] = { HV_X64_MSR_RESET, HV_X64_MSR_VP_INDEX, HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, @@ -1167,7 +1169,8 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) ++version; - kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); + if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) + return; /* * The guest calculates current wall clock time by adding @@ -1683,6 +1686,11 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #endif } +void kvm_make_mclock_inprogress_request(struct kvm *kvm) +{ + kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); +} + static void kvm_gen_update_masterclock(struct kvm *kvm) { #ifdef CONFIG_X86_64 @@ -2198,6 +2206,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: @@ -2402,6 +2411,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data); break; @@ -2541,6 +2551,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -2693,6 +2704,11 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) return kvm_arch_has_noncoherent_dma(vcpu->kvm); } +static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu) +{ + set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests); +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ @@ -2748,7 +2764,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - kvm_x86_ops->sync_pir_to_irr(vcpu); + if (vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); return 0; @@ -3191,6 +3209,20 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_HYPERV_SYNIC: + return kvm_hv_activate_synic(vcpu); + default: + return -EINVAL; + } +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3455,6 +3487,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_set_guest_paused(vcpu); goto out; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -EINVAL; } @@ -5107,7 +5148,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, int emulation_type) { gpa_t gpa = cr2; - pfn_t pfn; + kvm_pfn_t pfn; if (emulation_type & EMULTYPE_NO_REEXECUTE) return false; @@ -5873,6 +5914,12 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } +void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) +{ + vcpu->arch.apicv_active = false; + kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -5966,6 +6013,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!vcpu->arch.apic) return; + if (vcpu->arch.apicv_active) + return; + if (!vcpu->arch.apic->vapic_addr) max_irr = kvm_lapic_find_highest_irr(vcpu); else @@ -6302,20 +6352,30 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); } +void kvm_make_scan_ioapic_request(struct kvm *kvm) +{ + kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); +} + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { + u64 eoi_exit_bitmap[4]; + if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8); + bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); if (irqchip_split(vcpu->kvm)) - kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap); + kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - kvm_x86_ops->sync_pir_to_irr(vcpu); - kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap); + if (vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } - kvm_x86_ops->load_eoi_exitmap(vcpu); + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, + vcpu_to_synic(vcpu)->vec_bitmap, 256); + kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) @@ -6423,7 +6483,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, - (void *) vcpu->arch.eoi_exit_bitmap)) { + vcpu->arch.ioapic_handled_vectors)) { vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; vcpu->run->eoi.vector = vcpu->arch.pending_ioapic_eoi; @@ -6447,6 +6507,20 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } + if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv = vcpu->arch.hyperv.exit; + r = 0; + goto out; + } + + /* + * KVM_REQ_HV_STIMER has to be processed after + * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers + * depend on the guest clock being up-to-date + */ + if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) + kvm_hv_process_stimers(vcpu); } /* @@ -6458,7 +6532,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * Update architecture specific hints for APIC * virtual interrupt delivery. */ - if (kvm_x86_ops->hwapic_irr_update) + if (vcpu->arch.apicv_active) kvm_x86_ops->hwapic_irr_update(vcpu, kvm_lapic_find_highest_irr(vcpu)); } @@ -7529,6 +7603,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) BUG_ON(vcpu->kvm == NULL); kvm = vcpu->kvm; + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(); vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) @@ -7586,6 +7661,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; + kvm_hv_vcpu_init(vcpu); + return 0; fail_free_mce_banks: @@ -7604,6 +7681,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { int idx; + kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); @@ -7998,6 +8076,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) kvm_cpu_has_interrupt(vcpu)) return true; + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + return false; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a43b2eafc..4ba229ac3 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1473,7 +1473,6 @@ __init void lguest_init(void) pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; - pv_mmu_ops.pte_update_defer = lguest_pte_update; #ifdef CONFIG_X86_LOCAL_APIC /* APIC read/write intercepts */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f2587888d..a501fa25d 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -16,7 +16,7 @@ clean-files := inat-tables.c obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o -lib-y := delay.o misc.o cmdline.o +lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c new file mode 100644 index 000000000..aa417a975 --- /dev/null +++ b/arch/x86/lib/cpu.c @@ -0,0 +1,35 @@ +#include <linux/module.h> + +unsigned int x86_family(unsigned int sig) +{ + unsigned int x86; + + x86 = (sig >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (sig >> 20) & 0xff; + + return x86; +} +EXPORT_SYMBOL_GPL(x86_family); + +unsigned int x86_model(unsigned int sig) +{ + unsigned int fam, model; + + fam = x86_family(sig); + + model = (sig >> 4) & 0xf; + + if (fam >= 0x6) + model += ((sig >> 16) & 0xf) << 4; + + return model; +} +EXPORT_SYMBOL_GPL(x86_model); + +unsigned int x86_stepping(unsigned int sig) +{ + return sig & 0xf; +} +EXPORT_SYMBOL_GPL(x86_stepping); diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index e912b2f6d..2f07c291d 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -102,7 +102,7 @@ static void delay_mwaitx(unsigned long __loops) * Use cpu_tss as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(this_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 43623739c..004c861b1 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/mm/Makefile b/arch/x86/mm/Makefile index 65c47fda2..f9d38a48e 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c new file mode 100644 index 000000000..bfcffdf6c --- /dev/null +++ b/arch/x86/mm/debug_pagetables.c @@ -0,0 +1,46 @@ +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <asm/pgtable.h> + +static int ptdump_show(struct seq_file *m, void *v) +{ + ptdump_walk_pgd_level(m, NULL); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .owner = THIS_MODULE, + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *pe; + +static int __init pt_dump_debug_init(void) +{ + pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL, + &ptdump_fops); + if (!pe) + return -ENOMEM; + + return 0; +} + +static void __exit pt_dump_debug_exit(void) +{ + debugfs_remove_recursive(pe); +} + +module_init(pt_dump_debug_init); +module_exit(pt_dump_debug_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); +MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0f1c6fc3d..4a6f1d9b5 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -426,38 +426,15 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { ptdump_walk_pgd_level_core(m, pgd, false); } +EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level); void ptdump_walk_pgd_level_checkwx(void) { ptdump_walk_pgd_level_core(NULL, NULL, true); } -#ifdef CONFIG_X86_PTDUMP -static int ptdump_show(struct seq_file *m, void *v) +static int __init pt_dump_init(void) { - ptdump_walk_pgd_level(m, NULL); - return 0; -} - -static int ptdump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, ptdump_show, NULL); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif - -static int pt_dump_init(void) -{ -#ifdef CONFIG_X86_PTDUMP - struct dentry *pe; -#endif - #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; @@ -468,13 +445,6 @@ static int pt_dump_init(void) address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif -#ifdef CONFIG_X86_PTDUMP - pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, - &ptdump_fops); - if (!pe) - return -ENOMEM; -#endif - return 0; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8d2472be4..e830c71a1 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -13,7 +13,6 @@ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ -#include <linux/tuxonice.h> /* incremental image support */ #include <linux/uaccess.h> /* faulthandler_disabled() */ #include <asm/traps.h> /* dotraplinkage, ... */ @@ -663,10 +662,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, unsigned long flags; int sig; - if (toi_make_writable(init_mm.pgd, address)) { - return; - } - /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs)) { /* @@ -921,101 +916,10 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, } } -#ifdef CONFIG_TOI_INCREMENTAL -/** - * _toi_do_cbw - Do a copy-before-write before letting the faulting process continue - */ -static void toi_do_cbw(struct page *page) -{ - struct toi_cbw_state *state = this_cpu_ptr(&toi_cbw_states); - - state->active = 1; - wmb(); - - if (state->enabled && state->next && PageTOI_CBW(page)) { - struct toi_cbw *this = state->next; - memcpy(this->virt, page_address(page), PAGE_SIZE); - this->pfn = page_to_pfn(page); - state->next = this->next; - } - - state->active = 0; -} - -/** - * _toi_make_writable - Defuse TOI's write protection - */ -int _toi_make_writable(pte_t *pte) -{ - struct page *page = pte_page(*pte); - if (PageTOI_RO(page)) { - pgd_t *pgd = __va(read_cr3()); - /* - * If this is a TuxOnIce caused fault, we may not have permission to - * write to a page needed to reset the permissions of the original - * page. Use swapper_pg_dir to get around this. - */ - load_cr3(swapper_pg_dir); - - set_pte_atomic(pte, pte_mkwrite(*pte)); - SetPageTOI_Dirty(page); - ClearPageTOI_RO(page); - - toi_do_cbw(page); - - load_cr3(pgd); - return 1; - } - return 0; -} - -/** - * toi_make_writable - Handle a (potential) fault caused by TOI's write protection - * - * Make a page writable that was protected. Might be because of a fault, or - * because we're allocating it and want it to be untracked. - * - * Note that in the fault handling case, we don't care about the error code. If - * called from the double fault handler, we won't have one. We just check to - * see if the page was made RO by TOI, and mark it dirty/release the protection - * if it was. - */ -int toi_make_writable(pgd_t *pgd, unsigned long address) -{ - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pgd = pgd + pgd_index(address); - if (!pgd_present(*pgd)) - return 0; - - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) - return 0; - - if (pud_large(*pud)) - return _toi_make_writable((pte_t *) pud); - - pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) - return 0; - - if (pmd_large(*pmd)) - return _toi_make_writable((pte_t *) pmd); - - pte = pte_offset_kernel(pmd, address); - if (!pte_present(*pte)) - return 0; - - return _toi_make_writable(pte); -} -#endif - static int spurious_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & PF_WRITE) && !pte_write(*pte)) - return 0; + return 0; if ((error_code & PF_INSTR) && !pte_exec(*pte)) return 0; @@ -1178,15 +1082,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, kmemcheck_hide(regs); prefetchw(&mm->mmap_sem); - /* - * Detect and handle page faults due to TuxOnIce making pages read-only - * so that it can create incremental images. - * - * Do it early to avoid double faults. - */ - if (unlikely(toi_make_writable(init_mm.pgd, address))) - return; - if (unlikely(kmmio_fault(regs, address))) return; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index ae9a37bf1..d8a798d8b 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -9,6 +9,7 @@ #include <linux/vmstat.h> #include <linux/highmem.h> #include <linux/swap.h> +#include <linux/memremap.h> #include <asm/pgtable.h> @@ -63,6 +64,16 @@ retry: #endif } +static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) +{ + while ((*nr) - nr_start) { + struct page *page = pages[--(*nr)]; + + ClearPageReferenced(page); + put_page(page); + } +} + /* * The performance critical leaf functions are made noinline otherwise gcc * inlines everything into a single function which results in too much @@ -71,7 +82,9 @@ retry: static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { + struct dev_pagemap *pgmap = NULL; unsigned long mask; + int nr_start = *nr; pte_t *ptep; mask = _PAGE_PRESENT|_PAGE_USER; @@ -89,13 +102,21 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } - if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { + if (pte_devmap(pte)) { + pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + pte_unmap(ptep); + return 0; + } + } else if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) { pte_unmap(ptep); return 0; } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); get_page(page); + put_dev_pagemap(pgmap); SetPageReferenced(page); pages[*nr] = page; (*nr)++; @@ -114,6 +135,32 @@ static inline void get_head_page_multiple(struct page *page, int nr) SetPageReferenced(page); } +static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, struct page **pages, int *nr) +{ + int nr_start = *nr; + unsigned long pfn = pmd_pfn(pmd); + struct dev_pagemap *pgmap = NULL; + + pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; + do { + struct page *page = pfn_to_page(pfn); + + pgmap = get_dev_pagemap(pfn, pgmap); + if (unlikely(!pgmap)) { + undo_dev_pagemap(nr, nr_start, pages); + return 0; + } + SetPageReferenced(page); + pages[*nr] = page; + get_page(page); + put_dev_pagemap(pgmap); + (*nr)++; + pfn++; + } while (addr += PAGE_SIZE, addr != end); + return 1; +} + static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -126,9 +173,13 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, mask |= _PAGE_RW; if ((pmd_flags(pmd) & mask) != mask) return 0; + + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); + if (pmd_devmap(pmd)) + return __gup_device_huge_pmd(pmd, addr, end, pages, nr); + /* hugepages are never "special" */ VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); refs = 0; head = pmd_page(pmd); @@ -136,8 +187,6 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; @@ -158,18 +207,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmd_t pmd = *pmdp; next = pmd_addr_end(addr, end); - /* - * The pmd_trans_splitting() check below explains why - * pmdp_splitting_flush has to flush the tlb, to stop - * this gup-fast code from running while we set the - * splitting bit in the pmd. Returning zero will take - * the slow path that will call wait_split_huge_page() - * if the pmd is still in splitting state. gup-fast - * can't because it has irq disabled and - * wait_split_huge_page() would never return as the - * tlb flush IPI wouldn't run. - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) + if (pmd_none(pmd)) return 0; if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* @@ -212,8 +250,6 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, do { VM_BUG_ON_PAGE(compound_head(page) != head, page); pages[*nr] = page; - if (PageTail(page)) - get_huge_page_tail(page); (*nr)++; page++; refs++; diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 42982b26e..740d7ac03 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -173,10 +173,10 @@ static __init int setup_hugepagesz(char *opt) } __setup("hugepagesz=", setup_hugepagesz); -#ifdef CONFIG_CMA +#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) static __init int gigantic_pages_init(void) { - /* With CMA we can allocate gigantic pages at runtime */ + /* With compaction or CMA we can allocate gigantic pages at runtime */ if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT)) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); return 0; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 695ac7d37..493f54172 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -150,10 +150,9 @@ static int page_size_mask; static void __init probe_page_size_mask(void) { -#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK) && !defined(CONFIG_TOI_INCREMENTAL) +#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK) /* - * For CONFIG_DEBUG_PAGEALLOC or TuxOnIce's incremental image support, - * identity mapping will use small pages. + * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec081fe0c..5488d2112 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> +#include <linux/memremap.h> #include <linux/nmi.h> #include <linux/gfp.h> #include <linux/kcore.h> @@ -714,6 +715,12 @@ static void __meminit free_pagetable(struct page *page, int order) { unsigned long magic; unsigned int nr_pages = 1 << order; + struct vmem_altmap *altmap = to_vmem_altmap((unsigned long) page); + + if (altmap) { + vmem_altmap_free(altmap, nr_pages); + return; + } /* bootmem page has reserved flag */ if (PageReserved(page)) { @@ -814,8 +821,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, if (phys_addr < (phys_addr_t)0x40000000) return; - if (IS_ALIGNED(addr, PAGE_SIZE) && - IS_ALIGNED(next, PAGE_SIZE)) { + if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { /* * Do not free direct mapping pages since they were * freed when offlining, or simplely not in use. @@ -1018,13 +1024,19 @@ int __ref arch_remove_memory(u64 start, u64 size) { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; + struct page *page = pfn_to_page(start_pfn); + struct vmem_altmap *altmap; struct zone *zone; int ret; - zone = page_zone(pfn_to_page(start_pfn)); - kernel_physical_mapping_remove(start, start + size); + /* With altmap the first mapped page is offset from @start */ + altmap = to_vmem_altmap((unsigned long) page); + if (altmap) + page += vmem_altmap_offset(altmap); + zone = page_zone(page); ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + kernel_physical_mapping_remove(start, start + size); return ret; } @@ -1236,7 +1248,7 @@ static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node) + unsigned long end, int node, struct vmem_altmap *altmap) { unsigned long addr; unsigned long next; @@ -1259,7 +1271,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = __vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; @@ -1280,7 +1292,8 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, addr_end = addr + PMD_SIZE; p_end = p + PMD_SIZE; continue; - } + } else if (altmap) + return -ENOMEM; /* no fallback */ } else if (pmd_large(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); continue; @@ -1294,11 +1307,16 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { + struct vmem_altmap *altmap = to_vmem_altmap(start); int err; if (cpu_has_pse) - err = vmemmap_populate_hugepages(start, end, node); - else + err = vmemmap_populate_hugepages(start, end, node, altmap); + else if (altmap) { + pr_err_once("%s: no cpu support for altmap allocations\n", + __func__); + err = -ENOMEM; + } else err = vmemmap_populate_basepages(start, end, node); if (!err) sync_global_pgds(start, end - 1, 0); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b9c78f3bc..0d8d53d1f 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -194,8 +194,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Check if the request spans more than any BAR in the iomem resource * tree. */ - WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size), - KERN_INFO "Info: mapping multiple BARs. Your kernel is fine."); + if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size)) + pr_warn("caller %pS mapping multiple BARs\n", caller); return ret_addr; err_free_area: diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 844b06d67..72bb52f93 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -69,14 +69,14 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - /* - * 8 bits of randomness in 32bit mmaps, 20 address space bits - * 28 bits of randomness in 64bit mmaps, 40 address space bits - */ if (mmap_is_ia32()) - rnd = (unsigned long)get_random_int() % (1<<8); +#ifdef CONFIG_COMPAT + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); +#else + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); +#endif else - rnd = (unsigned long)get_random_int() % (1<<28); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index c3b3f653e..d04f8094b 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -469,7 +469,7 @@ static void __init numa_clear_kernel_node_hotplug(void) { int i, nid; nodemask_t numa_kernel_nodes = NODE_MASK_NONE; - unsigned long start, end; + phys_addr_t start, end; struct memblock_region *r; /* diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index db20ee9a4..9cf96d821 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -66,6 +66,9 @@ void update_page_count(int level, unsigned long pages) static void split_page_count(int level) { + if (direct_pages_count[level] == 0) + return; + direct_pages_count[level]--; direct_pages_count[level - 1] += PTRS_PER_PTE; } @@ -129,14 +132,16 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + const unsigned long clflush_size = boot_cpu_data.x86_clflush_size; + void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1)); void *vend = vaddr + size; - void *p; + + if (p >= vend) + return; mb(); - for (p = (void *)((unsigned long)vaddr & ~clflush_mask); - p < vend; p += boot_cpu_data.x86_clflush_size) + for (; p < vend; p += clflush_size) clflushopt(p); mb(); @@ -414,24 +419,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 188e3e07e..f4ae536b0 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -12,6 +12,7 @@ #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/pfn_t.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/fs.h> @@ -586,7 +587,7 @@ int free_memtype(u64 start, u64 end) entry = rbt_memtype_erase(start, end); spin_unlock(&memtype_lock); - if (!entry) { + if (IS_ERR(entry)) { pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, start, end - 1); return -EINVAL; @@ -949,7 +950,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, } int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, - unsigned long pfn) + pfn_t pfn) { enum page_cache_mode pcm; @@ -957,7 +958,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, return 0; /* Set prot based on lookup */ - pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT); + pcm = lookup_memtype(pfn_t_to_phys(pfn)); *prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) | cachemode2protval(pcm)); @@ -992,6 +993,16 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, vma->vm_flags &= ~VM_PAT; } +/* + * untrack_pfn_moved is called, while mremapping a pfnmap for a new region, + * with the old vma after its pfnmap page table has been removed. The new + * vma has a new pfnmap to the same pfn & cache type with VM_PAT set. + */ +void untrack_pfn_moved(struct vm_area_struct *vma) +{ + vma->vm_flags &= ~VM_PAT; +} + pgprot_t pgprot_writecombine(pgprot_t prot) { return __pgprot(pgprot_val(prot) | diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 639310803..2f7702253 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -98,8 +98,13 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root, return last_lower; /* Returns NULL if there is no overlap */ } -static struct memtype *memtype_rb_exact_match(struct rb_root *root, - u64 start, u64 end) +enum { + MEMTYPE_EXACT_MATCH = 0, + MEMTYPE_END_MATCH = 1 +}; + +static struct memtype *memtype_rb_match(struct rb_root *root, + u64 start, u64 end, int match_type) { struct memtype *match; @@ -107,7 +112,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, while (match != NULL && match->start < end) { struct rb_node *node; - if (match->start == start && match->end == end) + if ((match_type == MEMTYPE_EXACT_MATCH) && + (match->start == start) && (match->end == end)) + return match; + + if ((match_type == MEMTYPE_END_MATCH) && + (match->start < start) && (match->end == end)) return match; node = rb_next(&match->rb); @@ -117,7 +127,7 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, match = NULL; } - return NULL; /* Returns NULL if there is no exact match */ + return NULL; /* Returns NULL if there is no match */ } static int memtype_rb_check_conflict(struct rb_root *root, @@ -210,12 +220,36 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end) { struct memtype *data; - data = memtype_rb_exact_match(&memtype_rbroot, start, end); - if (!data) - goto out; + /* + * Since the memtype_rbroot tree allows overlapping ranges, + * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free + * a whole node for the munmap case. If no such entry is found, + * it then checks with END_MATCH, i.e. shrink the size of a node + * from the end for the mremap case. + */ + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_EXACT_MATCH); + if (!data) { + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_END_MATCH); + if (!data) + return ERR_PTR(-EINVAL); + } + + if (data->start == start) { + /* munmap: erase this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + } else { + /* mremap: update the end value of this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + data->end = start; + data->subtree_max_end = data->end; + memtype_rb_insert(&memtype_rbroot, data); + return NULL; + } - rb_erase_augmented(&data->rb, &memtype_rbroot, &memtype_rb_augment_cb); -out: return data; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index fb0a9dd1d..4eb287e25 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -414,7 +414,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *ptep = entry; - pte_update_defer(vma->vm_mm, address, ptep); + pte_update(vma->vm_mm, address, ptep); } return changed; @@ -431,7 +431,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *pmdp = entry; - pmd_update_defer(vma->vm_mm, address, pmdp); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -469,9 +468,6 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); - if (ret) - pmd_update(vma->vm_mm, addr, pmdp); - return ret; } #endif @@ -509,20 +505,6 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, return young; } - -void pmdp_splitting_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - int set; - VM_BUG_ON(address & ~HPAGE_PMD_MASK); - set = !test_and_set_bit(_PAGE_BIT_SPLITTING, - (unsigned long *)pmdp); - if (set) { - pmd_update(vma->vm_mm, address, pmdp); - /* need tlb flush only to serialize against gup-fast */ - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); - } -} #endif /** diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 90555bf60..92e2eacb3 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -31,7 +31,7 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - if (cpu_has_nx && !disable_nx) + if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) __supported_pte_mask |= _PAGE_NX; else __supported_pte_mask &= ~_PAGE_NX; @@ -39,7 +39,7 @@ void x86_configure_nx(void) void __init x86_report_nx(void) { - if (!cpu_has_nx) { + if (!boot_cpu_has(X86_FEATURE_NX)) { printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " "missing in CPU!\n"); } else { diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index c2aea63be..b5f821881 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -203,6 +203,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", (unsigned long long)start, (unsigned long long)end - 1); + max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); + return 0; out_err_bad_srat: bad_srat(); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 75991979f..4286f3618 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -193,7 +193,7 @@ struct jit_context { 32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 51 +#define PROLOGUE_SIZE 48 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program @@ -229,11 +229,15 @@ static void emit_prologue(u8 **pprog) /* mov qword ptr [rbp-X],r15 */ EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); - /* clear A and X registers */ - EMIT2(0x31, 0xc0); /* xor eax, eax */ - EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */ + /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls + * we need to reset the counter to 0. It's done in two instructions, + * resetting rax register to 0 (xor on eax gets 0 extended), and + * moving it to the counter location. + */ - /* clear tail_cnt: mov qword ptr [rbp-X], rax */ + /* xor eax, eax */ + EMIT2(0x31, 0xc0); + /* mov qword ptr [rbp-X], rax */ EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); @@ -455,6 +459,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } case BPF_ALU | BPF_MOV | BPF_K: + /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + break; + } + /* mov %eax, imm32 */ if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); @@ -469,6 +485,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, return -EINVAL; } + /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' + * to save 7 bytes. + */ + if (insn[0].imm == 0 && insn[1].imm == 0) { + b1 = add_2mod(0x48, dst_reg, dst_reg); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); + + insn++; + i++; + break; + } + /* movabsq %rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(insn[0].imm, 4); diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile index 5c6fc3577..97062a635 100644 --- a/arch/x86/pci/Makefile +++ b/arch/x86/pci/Makefile @@ -23,6 +23,8 @@ obj-y += bus_numa.o obj-$(CONFIG_AMD_NB) += amd_bus.o obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o +obj-$(CONFIG_VMD) += vmd.o + ifeq ($(CONFIG_PCI_DEBUG),y) EXTRA_CFLAGS += -DDEBUG endif diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index eccd4d99e..d34b5118b 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -641,6 +641,43 @@ unsigned int pcibios_assign_all_busses(void) return (pci_probe & PCI_ASSIGN_ALL_BUSSES) ? 1 : 0; } +#if defined(CONFIG_X86_DEV_DMA_OPS) && defined(CONFIG_PCI_DOMAINS) +static LIST_HEAD(dma_domain_list); +static DEFINE_SPINLOCK(dma_domain_list_lock); + +void add_dma_domain(struct dma_domain *domain) +{ + spin_lock(&dma_domain_list_lock); + list_add(&domain->node, &dma_domain_list); + spin_unlock(&dma_domain_list_lock); +} +EXPORT_SYMBOL_GPL(add_dma_domain); + +void del_dma_domain(struct dma_domain *domain) +{ + spin_lock(&dma_domain_list_lock); + list_del(&domain->node); + spin_unlock(&dma_domain_list_lock); +} +EXPORT_SYMBOL_GPL(del_dma_domain); + +static void set_dma_domain_ops(struct pci_dev *pdev) +{ + struct dma_domain *domain; + + spin_lock(&dma_domain_list_lock); + list_for_each_entry(domain, &dma_domain_list, node) { + if (pci_domain_nr(pdev->bus) == domain->domain_nr) { + pdev->dev.archdata.dma_ops = domain->dma_ops; + break; + } + } + spin_unlock(&dma_domain_list_lock); +} +#else +static void set_dma_domain_ops(struct pci_dev *pdev) {} +#endif + int pcibios_add_device(struct pci_dev *dev) { struct setup_data *data; @@ -670,31 +707,26 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = data->next; iounmap(data); } + set_dma_domain_ops(dev); return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) +int pcibios_enable_device(struct pci_dev *dev, int mask) { - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; + int err; - return pcibios_enable_irq(dev); -} + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +void pcibios_disable_device (struct pci_dev *dev) { - return pci_enable_resources(dev, mask); + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10..8b93e634a 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e..9bd115484 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9b83b9051..9770e55e7 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -180,6 +180,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, unsigned long result = 0; unsigned long flags; unsigned long bx = (bus << 8) | devfn; + u16 number = 0, mask = 0; WARN_ON(seg); if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) @@ -189,53 +190,35 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, switch (len) { case 1: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_BYTE), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); - /* - * Zero-extend the result beyond 8 bits, do not trust the - * BIOS having done it: - */ - *value &= 0xff; + number = PCIBIOS_READ_CONFIG_BYTE; + mask = 0xff; break; case 2: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_WORD), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); - /* - * Zero-extend the result beyond 16 bits, do not trust the - * BIOS having done it: - */ - *value &= 0xffff; + number = PCIBIOS_READ_CONFIG_WORD; + mask = 0xffff; break; case 4: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=c" (*value), - "=a" (result) - : "1" (PCIBIOS_READ_CONFIG_DWORD), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_READ_CONFIG_DWORD; break; } + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=c" (*value), + "=a" (result) + : "1" (number), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + /* + * Zero-extend the result beyond 8 or 16 bits, do not trust the + * BIOS having done it: + */ + if (mask) + *value &= mask; + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); @@ -247,6 +230,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, unsigned long result = 0; unsigned long flags; unsigned long bx = (bus << 8) | devfn; + u16 number = 0; WARN_ON(seg); if ((bus > 255) || (devfn > 255) || (reg > 255)) @@ -256,43 +240,27 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, switch (len) { case 1: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_BYTE), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_BYTE; break; case 2: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_WORD), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_WORD; break; case 4: - __asm__("lcall *(%%esi); cld\n\t" - "jc 1f\n\t" - "xor %%ah, %%ah\n" - "1:" - : "=a" (result) - : "0" (PCIBIOS_WRITE_CONFIG_DWORD), - "c" (value), - "b" (bx), - "D" ((long)reg), - "S" (&pci_indirect)); + number = PCIBIOS_WRITE_CONFIG_DWORD; break; } + __asm__("lcall *(%%esi); cld\n\t" + "jc 1f\n\t" + "xor %%ah, %%ah\n" + "1:" + : "=a" (result) + : "0" (number), + "c" (value), + "b" (bx), + "D" ((long)reg), + "S" (&pci_indirect)); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); return (int)((result & 0xff00) >> 8); diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c new file mode 100644 index 000000000..d57e48016 --- /dev/null +++ b/arch/x86/pci/vmd.c @@ -0,0 +1,723 @@ +/* + * Volume Management Device driver + * Copyright (c) 2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/device.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/pci.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> + +#include <asm/irqdomain.h> +#include <asm/device.h> +#include <asm/msi.h> +#include <asm/msidef.h> + +#define VMD_CFGBAR 0 +#define VMD_MEMBAR1 2 +#define VMD_MEMBAR2 4 + +/* + * Lock for manipulating VMD IRQ lists. + */ +static DEFINE_RAW_SPINLOCK(list_lock); + +/** + * struct vmd_irq - private data to map driver IRQ to the VMD shared vector + * @node: list item for parent traversal. + * @rcu: RCU callback item for freeing. + * @irq: back pointer to parent. + * @virq: the virtual IRQ value provided to the requesting driver. + * + * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to + * a VMD IRQ using this structure. + */ +struct vmd_irq { + struct list_head node; + struct rcu_head rcu; + struct vmd_irq_list *irq; + unsigned int virq; +}; + +/** + * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector + * @irq_list: the list of irq's the VMD one demuxes to. + * @vmd_vector: the h/w IRQ assigned to the VMD. + * @index: index into the VMD MSI-X table; used for message routing. + * @count: number of child IRQs assigned to this vector; used to track + * sharing. + */ +struct vmd_irq_list { + struct list_head irq_list; + struct vmd_dev *vmd; + unsigned int vmd_vector; + unsigned int index; + unsigned int count; +}; + +struct vmd_dev { + struct pci_dev *dev; + + spinlock_t cfg_lock; + char __iomem *cfgbar; + + int msix_count; + struct msix_entry *msix_entries; + struct vmd_irq_list *irqs; + + struct pci_sysdata sysdata; + struct resource resources[3]; + struct irq_domain *irq_domain; + struct pci_bus *bus; + +#ifdef CONFIG_X86_DEV_DMA_OPS + struct dma_map_ops dma_ops; + struct dma_domain dma_domain; +#endif +}; + +static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) +{ + return container_of(bus->sysdata, struct vmd_dev, sysdata); +} + +/* + * Drivers managing a device in a VMD domain allocate their own IRQs as before, + * but the MSI entry for the hardware it's driving will be programmed with a + * destination ID for the VMD MSI-X table. The VMD muxes interrupts in its + * domain into one of its own, and the VMD driver de-muxes these for the + * handlers sharing that VMD IRQ. The vmd irq_domain provides the operations + * and irq_chip to set this up. + */ +static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct vmd_irq *vmdirq = data->chip_data; + struct vmd_irq_list *irq = vmdirq->irq; + + msg->address_hi = MSI_ADDR_BASE_HI; + msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(irq->index); + msg->data = 0; +} + +/* + * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops. + */ +static void vmd_irq_enable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + + raw_spin_lock(&list_lock); + list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + raw_spin_unlock(&list_lock); + + data->chip->irq_unmask(data); +} + +static void vmd_irq_disable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + + data->chip->irq_mask(data); + + raw_spin_lock(&list_lock); + list_del_rcu(&vmdirq->node); + raw_spin_unlock(&list_lock); +} + +/* + * XXX: Stubbed until we develop acceptable way to not create conflicts with + * other devices sharing the same vector. + */ +static int vmd_irq_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + return -EINVAL; +} + +static struct irq_chip vmd_msi_controller = { + .name = "VMD-MSI", + .irq_enable = vmd_irq_enable, + .irq_disable = vmd_irq_disable, + .irq_compose_msi_msg = vmd_compose_msi_msg, + .irq_set_affinity = vmd_irq_set_affinity, +}; + +static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return 0; +} + +/* + * XXX: We can be even smarter selecting the best IRQ once we solve the + * affinity problem. + */ +static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd) +{ + int i, best = 0; + + raw_spin_lock(&list_lock); + for (i = 1; i < vmd->msix_count; i++) + if (vmd->irqs[i].count < vmd->irqs[best].count) + best = i; + vmd->irqs[best].count++; + raw_spin_unlock(&list_lock); + + return &vmd->irqs[best]; +} + +static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, + unsigned int virq, irq_hw_number_t hwirq, + msi_alloc_info_t *arg) +{ + struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(arg->desc)->bus); + struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); + + if (!vmdirq) + return -ENOMEM; + + INIT_LIST_HEAD(&vmdirq->node); + vmdirq->irq = vmd_next_irq(vmd); + vmdirq->virq = virq; + + irq_domain_set_info(domain, virq, vmdirq->irq->vmd_vector, info->chip, + vmdirq, handle_simple_irq, vmd, NULL); + return 0; +} + +static void vmd_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + struct vmd_irq *vmdirq = irq_get_chip_data(virq); + + /* XXX: Potential optimization to rebalance */ + raw_spin_lock(&list_lock); + vmdirq->irq->count--; + raw_spin_unlock(&list_lock); + + kfree_rcu(vmdirq, rcu); +} + +static int vmd_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 vmd_dev *vmd = vmd_from_bus(pdev->bus); + + if (nvec > vmd->msix_count) + return vmd->msix_count; + + memset(arg, 0, sizeof(*arg)); + return 0; +} + +static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; +} + +static struct msi_domain_ops vmd_msi_domain_ops = { + .get_hwirq = vmd_get_hwirq, + .msi_init = vmd_msi_init, + .msi_free = vmd_msi_free, + .msi_prepare = vmd_msi_prepare, + .set_desc = vmd_set_desc, +}; + +static struct msi_domain_info vmd_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &vmd_msi_domain_ops, + .chip = &vmd_msi_controller, +}; + +#ifdef CONFIG_X86_DEV_DMA_OPS +/* + * VMD replaces the requester ID with its own. DMA mappings for devices in a + * VMD domain need to be mapped for the VMD, not the device requiring + * the mapping. + */ +static struct device *to_vmd_dev(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = vmd_from_bus(pdev->bus); + + return &vmd->dev->dev; +} + +static struct dma_map_ops *vmd_dma_ops(struct device *dev) +{ + return to_vmd_dev(dev)->archdata.dma_ops; +} + +static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, + gfp_t flag, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag, + attrs); +} + +static void vmd_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t addr, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr, + attrs); +} + +static int vmd_mmap(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t addr, size_t size, + struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr, + size, attrs); +} + +static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t addr, size_t size, + struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr, + addr, size, attrs); +} + +static dma_addr_t vmd_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size, + dir, attrs); +} + +static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs); +} + +static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs); +} + +static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) +{ + vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs); +} + +static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir); +} + +static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size, + dir); +} + +static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir); +} + +static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir) +{ + vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir); +} + +static int vmd_mapping_error(struct device *dev, dma_addr_t addr) +{ + return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr); +} + +static int vmd_dma_supported(struct device *dev, u64 mask) +{ + return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask); +} + +#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK +static u64 vmd_get_required_mask(struct device *dev) +{ + return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev)); +} +#endif + +static void vmd_teardown_dma_ops(struct vmd_dev *vmd) +{ + struct dma_domain *domain = &vmd->dma_domain; + + if (vmd->dev->dev.archdata.dma_ops) + del_dma_domain(domain); +} + +#define ASSIGN_VMD_DMA_OPS(source, dest, fn) \ + do { \ + if (source->fn) \ + dest->fn = vmd_##fn; \ + } while (0) + +static void vmd_setup_dma_ops(struct vmd_dev *vmd) +{ + const struct dma_map_ops *source = vmd->dev->dev.archdata.dma_ops; + struct dma_map_ops *dest = &vmd->dma_ops; + struct dma_domain *domain = &vmd->dma_domain; + + domain->domain_nr = vmd->sysdata.domain; + domain->dma_ops = dest; + + if (!source) + return; + ASSIGN_VMD_DMA_OPS(source, dest, alloc); + ASSIGN_VMD_DMA_OPS(source, dest, free); + ASSIGN_VMD_DMA_OPS(source, dest, mmap); + ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable); + ASSIGN_VMD_DMA_OPS(source, dest, map_page); + ASSIGN_VMD_DMA_OPS(source, dest, unmap_page); + ASSIGN_VMD_DMA_OPS(source, dest, map_sg); + ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg); + ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu); + ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device); + ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu); + ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device); + ASSIGN_VMD_DMA_OPS(source, dest, mapping_error); + ASSIGN_VMD_DMA_OPS(source, dest, dma_supported); +#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK + ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask); +#endif + add_dma_domain(domain); +} +#undef ASSIGN_VMD_DMA_OPS +#else +static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {} +static void vmd_setup_dma_ops(struct vmd_dev *vmd) {} +#endif + +static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, + unsigned int devfn, int reg, int len) +{ + char __iomem *addr = vmd->cfgbar + + (bus->number << 20) + (devfn << 12) + reg; + + if ((addr - vmd->cfgbar) + len >= + resource_size(&vmd->dev->resource[VMD_CFGBAR])) + return NULL; + + return addr; +} + +/* + * CPU may deadlock if config space is not serialized on some versions of this + * hardware, so all config space access is done under a spinlock. + */ +static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, + int len, u32 *value) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + *value = readb(addr); + break; + case 2: + *value = readw(addr); + break; + case 4: + *value = readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +/* + * VMD h/w converts non-posted config writes to posted memory writes. The + * read-back in this function forces the completion so it returns only after + * the config space was written, as expected. + */ +static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, + int len, u32 value) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + writeb(value, addr); + readb(addr); + break; + case 2: + writew(value, addr); + readw(addr); + break; + case 4: + writel(value, addr); + readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +static struct pci_ops vmd_ops = { + .read = vmd_pci_read, + .write = vmd_pci_write, +}; + +/* + * VMD domains start at 0x1000 to not clash with ACPI _SEG domains. + */ +static int vmd_find_free_domain(void) +{ + int domain = 0xffff; + struct pci_bus *bus = NULL; + + while ((bus = pci_find_next_bus(bus)) != NULL) + domain = max_t(int, domain, pci_domain_nr(bus)); + return domain + 1; +} + +static int vmd_enable_domain(struct vmd_dev *vmd) +{ + struct pci_sysdata *sd = &vmd->sysdata; + struct resource *res; + u32 upper_bits; + unsigned long flags; + LIST_HEAD(resources); + + res = &vmd->dev->resource[VMD_CFGBAR]; + vmd->resources[0] = (struct resource) { + .name = "VMD CFGBAR", + .start = res->start, + .end = (resource_size(res) >> 20) - 1, + .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, + }; + + res = &vmd->dev->resource[VMD_MEMBAR1]; + upper_bits = upper_32_bits(res->end); + flags = res->flags & ~IORESOURCE_SIZEALIGN; + if (!upper_bits) + flags &= ~IORESOURCE_MEM_64; + vmd->resources[1] = (struct resource) { + .name = "VMD MEMBAR1", + .start = res->start, + .end = res->end, + .flags = flags, + }; + + res = &vmd->dev->resource[VMD_MEMBAR2]; + upper_bits = upper_32_bits(res->end); + flags = res->flags & ~IORESOURCE_SIZEALIGN; + if (!upper_bits) + flags &= ~IORESOURCE_MEM_64; + vmd->resources[2] = (struct resource) { + .name = "VMD MEMBAR2", + .start = res->start + 0x2000, + .end = res->end, + .flags = flags, + }; + + sd->domain = vmd_find_free_domain(); + if (sd->domain < 0) + return sd->domain; + + sd->node = pcibus_to_node(vmd->dev->bus); + + vmd->irq_domain = pci_msi_create_irq_domain(NULL, &vmd_msi_domain_info, + NULL); + if (!vmd->irq_domain) + return -ENODEV; + + pci_add_resource(&resources, &vmd->resources[0]); + pci_add_resource(&resources, &vmd->resources[1]); + pci_add_resource(&resources, &vmd->resources[2]); + vmd->bus = pci_create_root_bus(&vmd->dev->dev, 0, &vmd_ops, sd, + &resources); + if (!vmd->bus) { + pci_free_resource_list(&resources); + irq_domain_remove(vmd->irq_domain); + return -ENODEV; + } + + vmd_setup_dma_ops(vmd); + dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); + pci_rescan_bus(vmd->bus); + + WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, + "domain"), "Can't create symlink to domain\n"); + return 0; +} + +static irqreturn_t vmd_irq(int irq, void *data) +{ + struct vmd_irq_list *irqs = data; + struct vmd_irq *vmdirq; + + rcu_read_lock(); + list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) + generic_handle_irq(vmdirq->virq); + rcu_read_unlock(); + + return IRQ_HANDLED; +} + +static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) +{ + struct vmd_dev *vmd; + int i, err; + + if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) + return -ENOMEM; + + vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL); + if (!vmd) + return -ENOMEM; + + vmd->dev = dev; + err = pcim_enable_device(dev); + if (err < 0) + return err; + + vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); + if (!vmd->cfgbar) + return -ENOMEM; + + pci_set_master(dev); + if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && + dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) + return -ENODEV; + + vmd->msix_count = pci_msix_vec_count(dev); + if (vmd->msix_count < 0) + return -ENODEV; + + vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), + GFP_KERNEL); + if (!vmd->irqs) + return -ENOMEM; + + vmd->msix_entries = devm_kcalloc(&dev->dev, vmd->msix_count, + sizeof(*vmd->msix_entries), + GFP_KERNEL); + if (!vmd->msix_entries) + return -ENOMEM; + for (i = 0; i < vmd->msix_count; i++) + vmd->msix_entries[i].entry = i; + + vmd->msix_count = pci_enable_msix_range(vmd->dev, vmd->msix_entries, 1, + vmd->msix_count); + if (vmd->msix_count < 0) + return vmd->msix_count; + + for (i = 0; i < vmd->msix_count; i++) { + INIT_LIST_HEAD(&vmd->irqs[i].irq_list); + vmd->irqs[i].vmd_vector = vmd->msix_entries[i].vector; + vmd->irqs[i].index = i; + + err = devm_request_irq(&dev->dev, vmd->irqs[i].vmd_vector, + vmd_irq, 0, "vmd", &vmd->irqs[i]); + if (err) + return err; + } + + spin_lock_init(&vmd->cfg_lock); + pci_set_drvdata(dev, vmd); + err = vmd_enable_domain(vmd); + if (err) + return err; + + dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", + vmd->sysdata.domain); + return 0; +} + +static void vmd_remove(struct pci_dev *dev) +{ + struct vmd_dev *vmd = pci_get_drvdata(dev); + + pci_set_drvdata(dev, NULL); + sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); + pci_stop_root_bus(vmd->bus); + pci_remove_root_bus(vmd->bus); + vmd_teardown_dma_ops(vmd); + irq_domain_remove(vmd->irq_domain); +} + +#ifdef CONFIG_PM +static int vmd_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + pci_save_state(pdev); + return 0; +} + +static int vmd_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + pci_restore_state(pdev); + return 0; +} +#endif +static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); + +static const struct pci_device_id vmd_ids[] = { + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x201d),}, + {0,} +}; +MODULE_DEVICE_TABLE(pci, vmd_ids); + +static struct pci_driver vmd_drv = { + .name = "vmd", + .id_table = vmd_ids, + .probe = vmd_probe, + .remove = vmd_remove, + .driver = { + .pm = &vmd_dev_pm_ops, + }, +}; +module_pci_driver(vmd_drv); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION("0.6"); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464..beac4dfda 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + if (ret == -ENOSYS) + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + else if (ret) + dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret); free: kfree(v); return ret; diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index 5ca8ead91..81c769e80 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -25,8 +25,6 @@ #include <asm/cpu_device_id.h> #include <asm/iosf_mbi.h> -/* Side band Interface port */ -#define PUNIT_PORT 0x04 /* Power gate status reg */ #define PWRGT_STATUS 0x61 /* Subsystem config/status Video processor */ @@ -85,9 +83,8 @@ static int punit_dev_state_show(struct seq_file *seq_file, void *unused) seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n"); while (punit_devp->name) { - status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ, - punit_devp->reg, - &punit_pwr_status); + status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ, + punit_devp->reg, &punit_pwr_status); if (status) { seq_printf(seq_file, "%9s : Read Failed\n", punit_devp->name); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 1c7380da6..ed30e7934 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -8,6 +8,7 @@ #include <linux/memblock.h> #include <linux/bootmem.h> #include <linux/acpi.h> +#include <linux/dmi.h> #include <asm/efi.h> #include <asm/uv/uv.h> @@ -130,6 +131,27 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) EXPORT_SYMBOL_GPL(efi_query_variable_store); /* + * Helper function for efi_reserve_boot_services() to figure out if we + * can free regions in efi_free_boot_services(). + * + * Use this function to ensure we do not free regions owned by somebody + * else. We must only reserve (and then free) regions: + * + * - Not within any part of the kernel + * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc) + */ +static bool can_free_region(u64 start, u64 size) +{ + if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) + return false; + + if (!e820_all_mapped(start, start+size, E820_RAM)) + return false; + + return true; +} + +/* * The UEFI specification makes it clear that the operating system is free to do * whatever it wants with boot services code after ExitBootServices() has been * called. Ignoring this recommendation a significant bunch of EFI implementations @@ -146,26 +168,50 @@ void __init efi_reserve_boot_services(void) efi_memory_desc_t *md = p; u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; + bool already_reserved; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Only reserve where possible: - * - Not within any already allocated areas - * - Not over any memory area (really needed, if above?) - * - Not within any part of the kernel - * - Not the bios reserved area - */ - if ((start + size > __pa_symbol(_text) - && start <= __pa_symbol(_end)) || - !e820_all_mapped(start, start+size, E820_RAM) || - memblock_is_region_reserved(start, size)) { - /* Could not reserve, skip it */ - md->num_pages = 0; - memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", - start, start+size-1); - } else + + already_reserved = memblock_is_region_reserved(start, size); + + /* + * Because the following memblock_reserve() is paired + * with free_bootmem_late() for this region in + * efi_free_boot_services(), we must be extremely + * careful not to reserve, and subsequently free, + * critical regions of memory (like the kernel image) or + * those regions that somebody else has already + * reserved. + * + * A good example of a critical region that must not be + * freed is page zero (first 4Kb of memory), which may + * contain boot services code/data but is marked + * E820_RESERVED by trim_bios_range(). + */ + if (!already_reserved) { memblock_reserve(start, size); + + /* + * If we are the first to reserve the region, no + * one else cares about it. We own it and can + * free it later. + */ + if (can_free_region(start, size)) + continue; + } + + /* + * We don't own the region. We must not free it. + * + * Setting this bit for a boot services region really + * doesn't make sense as far as the firmware is + * concerned, but it does provide us with a way to tag + * those regions that must not be paired with + * free_bootmem_late(). + */ + md->attribute |= EFI_MEMORY_RUNTIME; } } @@ -182,8 +228,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Could not reserve boot area */ - if (!size) + /* Do not free, someone else owns it: */ + if (md->attribute & EFI_MEMORY_RUNTIME) continue; free_bootmem_late(start, size); @@ -248,6 +294,16 @@ out: return ret; } +static const struct dmi_system_id sgi_uv1_dmi[] = { + { NULL, "SGI UV1", + { DMI_MATCH(DMI_PRODUCT_NAME, "Stoutland Platform"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), + DMI_MATCH(DMI_BIOS_VENDOR, "SGI.COM"), + } + }, + { } /* NULL entry stops DMI scanning */ +}; + void __init efi_apply_memmap_quirks(void) { /* @@ -260,10 +316,8 @@ void __init efi_apply_memmap_quirks(void) efi_unmap_memmap(); } - /* - * UV doesn't support the new EFI pagetable mapping yet. - */ - if (is_uv_system()) + /* UV2+ BIOS has a fix for this issue. UV1 still needs the quirk. */ + if (dmi_check_system(sgi_uv1_dmi)) set_bit(EFI_OLD_MEMMAP, &efi.flags); } diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 1bbc21e2e..90bb997ed 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -138,7 +138,7 @@ static void intel_mid_arch_setup(void) intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip](); else { intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL](); - pr_info("ARCH: Unknown SoC, assuming PENWELL!\n"); + pr_info("ARCH: Unknown SoC, assuming Penwell!\n"); } out: @@ -214,12 +214,10 @@ static inline int __init setup_x86_intel_mid_timer(char *arg) else if (strcmp("lapic_and_apbt", arg) == 0) intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT; else { - pr_warn("X86 INTEL_MID timer option %s not recognised" - " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", - arg); + pr_warn("X86 INTEL_MID timer option %s not recognised use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n", + arg); return -EINVAL; } return 0; } __setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer); - diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index 0ee619f9f..bfadcd0f4 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -111,23 +111,19 @@ static int imr_read(struct imr_device *idev, u32 imr_id, struct imr_regs *imr) u32 reg = imr_id * IMR_NUM_REGS + idev->reg_base; int ret; - ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->addr_lo); + ret = iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->addr_lo); if (ret) return ret; - ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->addr_hi); + ret = iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->addr_hi); if (ret) return ret; - ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->rmask); + ret = iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->rmask); if (ret) return ret; - return iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ, - reg++, &imr->wmask); + return iosf_mbi_read(QRK_MBI_UNIT_MM, MBI_REG_READ, reg++, &imr->wmask); } /** @@ -151,31 +147,27 @@ static int imr_write(struct imr_device *idev, u32 imr_id, local_irq_save(flags); - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, reg++, - imr->addr_lo); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->addr_lo); if (ret) goto failed; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg++, imr->addr_hi); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->addr_hi); if (ret) goto failed; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg++, imr->rmask); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->rmask); if (ret) goto failed; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg++, imr->wmask); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, reg++, imr->wmask); if (ret) goto failed; /* Lock bit must be set separately to addr_lo address bits. */ if (lock) { imr->addr_lo |= IMR_LOCK; - ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, - reg - IMR_NUM_REGS, imr->addr_lo); + ret = iosf_mbi_write(QRK_MBI_UNIT_MM, MBI_REG_WRITE, + reg - IMR_NUM_REGS, imr->addr_lo); if (ret) goto failed; } @@ -228,11 +220,12 @@ static int imr_dbgfs_state_show(struct seq_file *s, void *unused) if (imr_is_enabled(&imr)) { base = imr_to_phys(imr.addr_lo); end = imr_to_phys(imr.addr_hi) + IMR_MASK; + size = end - base + 1; } else { base = 0; end = 0; + size = 0; } - size = end - base; seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx " "rmask=0x%08x, wmask=0x%08x, %s, %s\n", i, &base, &end, size, imr.rmask, imr.wmask, @@ -587,6 +580,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) { phys_addr_t base = virt_to_phys(&_text); size_t size = virt_to_phys(&__end_rodata) - base; + unsigned long start, end; int i; int ret; @@ -594,18 +588,24 @@ static void __init imr_fixup_memmap(struct imr_device *idev) for (i = 0; i < idev->max_imr; i++) imr_clear(i); + start = (unsigned long)_text; + end = (unsigned long)__end_rodata - 1; + /* - * Setup a locked IMR around the physical extent of the kernel + * Setup an unlocked IMR around the physical extent of the kernel * from the beginning of the .text secton to the end of the * .rodata section as one physically contiguous block. + * + * We don't round up @size since it is already PAGE_SIZE aligned. + * See vmlinux.lds.S for details. */ - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); if (ret < 0) { - pr_err("unable to setup IMR for kernel: (%p - %p)\n", - &_text, &__end_rodata); + pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", + size / 1024, start, end); } else { - pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n", - size / 1024, &_text, &__end_rodata); + pr_info("protecting kernel .text - .rodata: %zu KiB (%lx - %lx)\n", + size / 1024, start, end); } } diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 327f21c3b..8dd80050d 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/power/cpu.c b/arch/x86/power/cpu.c index 9ab52791f..d5f649963 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -23,6 +23,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> +#include <linux/dmi.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -32,6 +33,29 @@ __visible unsigned long saved_context_eflags; #endif struct saved_context saved_context; +static void msr_save_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + msr++; + } +} + +static void msr_restore_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + if (msr->valid) + wrmsrl(msr->info.msr_no, msr->info.reg.q); + msr++; + } +} + /** * __save_processor_state - save CPU registers before creating a * hibernation image and before restoring the memory state from it @@ -111,6 +135,7 @@ static void __save_processor_state(struct saved_context *ctxt) #endif ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, &ctxt->misc_enable); + msr_save_context(ctxt); } /* Needed by apm.c */ @@ -229,6 +254,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -320,3 +346,69 @@ static int __init bsp_pm_check_init(void) } core_initcall(bsp_pm_check_init); + +static int msr_init_context(const u32 *msr_id, const int total_num) +{ + int i = 0; + struct saved_msr *msr_array; + + if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { + pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); + return -EINVAL; + } + + msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); + if (!msr_array) { + pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n"); + return -ENOMEM; + } + + for (i = 0; i < total_num; i++) { + msr_array[i].info.msr_no = msr_id[i]; + msr_array[i].valid = false; + msr_array[i].info.reg.q = 0; + } + saved_context.saved_msrs.num = total_num; + saved_context.saved_msrs.array = msr_array; + + return 0; +} + +/* + * The following section is a quirk framework for problematic BIOSen: + * Sometimes MSRs are modified by the BIOSen after suspended to + * RAM, this might cause unexpected behavior after wakeup. + * Thus we save/restore these specified MSRs across suspend/resume + * in order to work around it. + * + * For any further problematic BIOSen/platforms, + * please add your own function similar to msr_initialize_bdw. + */ +static int msr_initialize_bdw(const struct dmi_system_id *d) +{ + /* Add any extra MSR ids into this array. */ + u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; + + pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); + return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); +} + +static struct dmi_system_id msr_save_dmi_table[] = { + { + .callback = msr_initialize_bdw, + .ident = "BROADWELL BDX_EP", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"), + DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"), + }, + }, + {} +}; + +static int pm_check_save_msr(void) +{ + dmi_check_system(msr_save_dmi_table); + return 0; +} + +device_initcall(pm_check_save_msr); diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 2730d775e..3e75fcf6b 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -70,3 +70,4 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) $(REALMODE_CFLAGS) -D_SETUP -D_WAKEUP \ -I$(srctree)/arch/x86/boot KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n +UBSAN_SANITIZE := n diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index a8fecc226..3ee2bb6b4 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -17,7 +17,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \ ifeq ($(CONFIG_X86_32),y) obj-y += checksum_32.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 755481f14..174781a40 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -36,13 +36,6 @@ #endif /* CONFIG_X86_PPRO_FENCE */ #define dma_wmb() barrier() -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() - -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) - -#define read_barrier_depends() do { } while (0) -#define smp_read_barrier_depends() do { } while (0) +#include <asm-generic/barrier.h> #endif diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h index 81d6562ce..11ab90dc5 100644 --- a/arch/x86/um/asm/syscall.h +++ b/arch/x86/um/asm/syscall.h @@ -1,6 +1,7 @@ #ifndef __UM_ASM_SYSCALL_H #define __UM_ASM_SYSCALL_H +#include <asm/syscall-generic.h> #include <uapi/linux/audit.h> typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, diff --git a/arch/x86/um/os-Linux/task_size.c b/arch/x86/um/os-Linux/task_size.c index 8502ad30e..5adb6a2fd 100644 --- a/arch/x86/um/os-Linux/task_size.c +++ b/arch/x86/um/os-Linux/task_size.c @@ -109,7 +109,7 @@ unsigned long os_get_top_address(void) exit(1); } - printf("0x%x\n", bottom << UM_KERN_PAGE_SHIFT); + printf("0x%lx\n", bottom << UM_KERN_PAGE_SHIFT); printf("Locating the top of the address space ... "); fflush(stdout); @@ -134,7 +134,7 @@ out: exit(1); } top <<= UM_KERN_PAGE_SHIFT; - printf("0x%x\n", top); + printf("0x%lx\n", top); return top; } diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index a29756f2d..47c78d5e5 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -68,6 +68,7 @@ static const int reg_offsets[] = { [EFL] = HOST_EFLAGS, [UESP] = HOST_SP, [SS] = HOST_SS, + [ORIG_EAX] = HOST_ORIG_AX, }; int putreg(struct task_struct *child, int regno, unsigned long value) @@ -83,6 +84,7 @@ int putreg(struct task_struct *child, int regno, unsigned long value) case EAX: case EIP: case UESP: + case ORIG_EAX: break; case FS: if (value && (value & 3) != 3) @@ -108,9 +110,6 @@ int putreg(struct task_struct *child, int regno, unsigned long value) value &= FLAG_MASK; child->thread.regs.regs.gp[HOST_EFLAGS] |= value; return 0; - case ORIG_EAX: - child->thread.regs.regs.syscall = value; - return 0; default : panic("Bad register in putreg() : %d\n", regno); } @@ -143,8 +142,6 @@ unsigned long getreg(struct task_struct *child, int regno) regno >>= 2; switch (regno) { - case ORIG_EAX: - return child->thread.regs.regs.syscall; case FS: case GS: case DS: @@ -163,6 +160,7 @@ unsigned long getreg(struct task_struct *child, int regno) case EDI: case EBP: case EFL: + case ORIG_EAX: break; default: panic("Bad register in getreg() : %d\n", regno); diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index acda713ab..abf4901c9 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -64,7 +64,7 @@ static u32 xen_apic_read(u32 reg) if (reg != APIC_ID) return 0; - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) return 0; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b7de78bdc..d09e4c9d7 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -415,7 +415,7 @@ static bool __init xen_check_mwait(void) set_xen_guest_handle(op.u.set_pminfo.pdc, buf); - if ((HYPERVISOR_dom0_op(&op) == 0) && + if ((HYPERVISOR_platform_op(&op) == 0) && (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) { cpuid_leaf5_ecx_val = cx; cpuid_leaf5_edx_val = dx; @@ -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, @@ -1265,12 +1262,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .end_context_switch = xen_end_context_switch, }; -static const struct pv_apic_ops xen_apic_ops __initconst = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; @@ -1374,7 +1365,7 @@ static void __init xen_boot_params_init_edd(void) info->params.length = sizeof(info->params); set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, &info->params); - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) break; @@ -1392,7 +1383,7 @@ static void __init xen_boot_params_init_edd(void) op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { op.u.firmware_info.index = nr; - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) break; mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; @@ -1538,7 +1529,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (xen_initial_domain()) pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; - pv_apic_ops = xen_apic_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1700,7 +1690,7 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; - if (HYPERVISOR_dom0_op(&op) == 0) + if (HYPERVISOR_platform_op(&op) == 0) boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; /* Make sure ACS will be enabled */ diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index cb5e266a8..c913ca4f6 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2436,7 +2436,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_others = xen_flush_tlb_others, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, .pgd_alloc = xen_pgd_alloc, .pgd_free = xen_pgd_free, diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index f1ba6a092..a0a4e554c 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -16,6 +16,7 @@ #include <linux/gfp.h> #include <linux/slab.h> #include <linux/pvclock_gtod.h> +#include <linux/timekeeper_internal.h> #include <asm/pvclock.h> #include <asm/xen/hypervisor.h> @@ -32,86 +33,12 @@ #define TIMER_SLOP 100000 #define NS_PER_TICK (1000000000LL / HZ) -/* runstate info updated by Xen */ -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); - /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); /* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -/* return an consistent snapshot of 64-bit time/counter value */ -static u64 get64(const u64 *p) -{ - u64 ret; - - if (BITS_PER_LONG < 64) { - u32 *p32 = (u32 *)p; - u32 h, l; - - /* - * Read high then low, and then make sure high is - * still the same; this will only loop if low wraps - * and carries into high. - * XXX some clean way to make this endian-proof? - */ - do { - h = p32[1]; - barrier(); - l = p32[0]; - barrier(); - } while (p32[1] != h); - - ret = (((u64)h) << 32) | l; - } else - ret = *p; - - return ret; -} - -/* - * Runstate accounting - */ -static void get_runstate_snapshot(struct vcpu_runstate_info *res) -{ - u64 state_time; - struct vcpu_runstate_info *state; - - BUG_ON(preemptible()); - - state = this_cpu_ptr(&xen_runstate); - - /* - * The runstate info is always updated by the hypervisor on - * the current CPU, so there's no need to use anything - * stronger than a compiler barrier when fetching it. - */ - do { - state_time = get64(&state->state_entry_time); - barrier(); - *res = *state; - barrier(); - } while (get64(&state->state_entry_time) != state_time); -} - -/* return true when a vcpu could run but has no real cpu to run on */ -bool xen_vcpu_stolen(int vcpu) -{ - return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; -} - -void xen_setup_runstate_info(int cpu) -{ - struct vcpu_register_runstate_memory_area area; - - area.addr.v = &per_cpu(xen_runstate, cpu); - - if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area, - cpu, &area)) - BUG(); -} - static void do_stolen_accounting(void) { struct vcpu_runstate_info state; @@ -119,7 +46,7 @@ static void do_stolen_accounting(void) s64 runnable, offline, stolen; cputime_t ticks; - get_runstate_snapshot(&state); + xen_get_runstate_snapshot(&state); WARN_ON(state.state != RUNSTATE_running); @@ -194,26 +121,46 @@ static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set, void *priv) { /* Protected by the calling core code serialization */ - static struct timespec next_sync; + static struct timespec64 next_sync; struct xen_platform_op op; - struct timespec now; + struct timespec64 now; + struct timekeeper *tk = priv; + static bool settime64_supported = true; + int ret; - now = __current_kernel_time(); + now.tv_sec = tk->xtime_sec; + now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); /* * We only take the expensive HV call when the clock was set * or when the 11 minutes RTC synchronization time elapsed. */ - if (!was_set && timespec_compare(&now, &next_sync) < 0) + if (!was_set && timespec64_compare(&now, &next_sync) < 0) return NOTIFY_OK; - op.cmd = XENPF_settime; - op.u.settime.secs = now.tv_sec; - op.u.settime.nsecs = now.tv_nsec; - op.u.settime.system_time = xen_clocksource_read(); +again: + if (settime64_supported) { + op.cmd = XENPF_settime64; + op.u.settime64.mbz = 0; + op.u.settime64.secs = now.tv_sec; + op.u.settime64.nsecs = now.tv_nsec; + op.u.settime64.system_time = xen_clocksource_read(); + } else { + op.cmd = XENPF_settime32; + op.u.settime32.secs = now.tv_sec; + op.u.settime32.nsecs = now.tv_nsec; + op.u.settime32.system_time = xen_clocksource_read(); + } + + ret = HYPERVISOR_platform_op(&op); - (void)HYPERVISOR_dom0_op(&op); + if (ret == -ENOSYS && settime64_supported) { + settime64_supported = false; + goto again; + } + if (ret < 0) + return NOTIFY_BAD; /* * Move the next drift compensation time 11 minutes diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index fd92a64d7..feb6d40a0 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 f22667abf..cc8acc410 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 1399423f3..4140b070f 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); |