diff options
Diffstat (limited to 'arch/x86')
76 files changed, 1588 insertions, 527 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a154a91c7e7..c49b4dc8ffe0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -108,7 +108,6 @@ config X86 select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) select GENERIC_TIME_VSYSCALL if X86_64 select KTIME_SCALAR if X86_32 - select ALWAYS_USE_PERSISTENT_CLOCK select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select HAVE_CONTEXT_TRACKING if X86_64 @@ -1726,7 +1725,7 @@ config PHYSICAL_ALIGN config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" - depends on SMP && HOTPLUG + depends on SMP ---help--- Say Y here to allow turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. @@ -2266,6 +2265,7 @@ source "fs/Kconfig.binfmt" config IA32_EMULATION bool "IA32 Emulation" depends on X86_64 + select BINFMT_ELF select COMPAT_BINFMT_ELF select HAVE_UID16 ---help--- diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c198b7e13e7b..b6a770132b67 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -122,7 +122,6 @@ config DEBUG_NX_TEST config DOUBLEFAULT default y bool "Enable doublefault exception handler" if EXPERT - depends on X86_32 ---help--- This option allows trapping of rare doublefault exceptions that would otherwise cause a system to silently reboot. Disabling this diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 7c6e5d957cc5..d606463aa6d6 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -251,51 +251,6 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size) *size = len; } -static efi_status_t setup_efi_vars(struct boot_params *params) -{ - struct setup_data *data; - struct efi_var_bootdata *efidata; - u64 store_size, remaining_size, var_size; - efi_status_t status; - - if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION) - return EFI_UNSUPPORTED; - - data = (struct setup_data *)(unsigned long)params->hdr.setup_data; - - while (data && data->next) - data = (struct setup_data *)(unsigned long)data->next; - - status = efi_call_phys4((void *)sys_table->runtime->query_variable_info, - EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS, &store_size, - &remaining_size, &var_size); - - if (status != EFI_SUCCESS) - return status; - - status = efi_call_phys3(sys_table->boottime->allocate_pool, - EFI_LOADER_DATA, sizeof(*efidata), &efidata); - - if (status != EFI_SUCCESS) - return status; - - efidata->data.type = SETUP_EFI_VARS; - efidata->data.len = sizeof(struct efi_var_bootdata) - - sizeof(struct setup_data); - efidata->data.next = 0; - efidata->store_size = store_size; - efidata->remaining_size = remaining_size; - efidata->max_var_size = var_size; - - if (data) - data->next = (unsigned long)efidata; - else - params->hdr.setup_data = (unsigned long)efidata; - -} - static efi_status_t setup_efi_pci(struct boot_params *params) { efi_pci_io_protocol *pci; @@ -1216,8 +1171,6 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, setup_graphics(boot_params); - setup_efi_vars(boot_params); - setup_efi_pci(boot_params); status = efi_call_phys3(sys_table->boottime->allocate_pool, diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 94c544650020..c941d6a8887f 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -243,6 +243,7 @@ static void parse_zoffset(char *fname) c = fread(buf, 1, sizeof(buf) - 1, file); if (ferror(file)) die("read-error on `zoffset.h'"); + fclose(file); buf[c] = 0; p = (char *)buf; diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 62fe22cd4cba..477e9d75149b 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -2681,56 +2681,68 @@ ENTRY(aesni_xts_crypt8) addq %rcx, KEYP movdqa IV, STATE1 - pxor 0x00(INP), STATE1 + movdqu 0x00(INP), INC + pxor INC, STATE1 movdqu IV, 0x00(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE2 - pxor 0x10(INP), STATE2 + movdqu 0x10(INP), INC + pxor INC, STATE2 movdqu IV, 0x10(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE3 - pxor 0x20(INP), STATE3 + movdqu 0x20(INP), INC + pxor INC, STATE3 movdqu IV, 0x20(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE4 - pxor 0x30(INP), STATE4 + movdqu 0x30(INP), INC + pxor INC, STATE4 movdqu IV, 0x30(OUTP) call *%r11 - pxor 0x00(OUTP), STATE1 + movdqu 0x00(OUTP), INC + pxor INC, STATE1 movdqu STATE1, 0x00(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE1 - pxor 0x40(INP), STATE1 + movdqu 0x40(INP), INC + pxor INC, STATE1 movdqu IV, 0x40(OUTP) - pxor 0x10(OUTP), STATE2 + movdqu 0x10(OUTP), INC + pxor INC, STATE2 movdqu STATE2, 0x10(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE2 - pxor 0x50(INP), STATE2 + movdqu 0x50(INP), INC + pxor INC, STATE2 movdqu IV, 0x50(OUTP) - pxor 0x20(OUTP), STATE3 + movdqu 0x20(OUTP), INC + pxor INC, STATE3 movdqu STATE3, 0x20(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE3 - pxor 0x60(INP), STATE3 + movdqu 0x60(INP), INC + pxor INC, STATE3 movdqu IV, 0x60(OUTP) - pxor 0x30(OUTP), STATE4 + movdqu 0x30(OUTP), INC + pxor INC, STATE4 movdqu STATE4, 0x30(OUTP) _aesni_gf128mul_x_ble() movdqa IV, STATE4 - pxor 0x70(INP), STATE4 + movdqu 0x70(INP), INC + pxor INC, STATE4 movdqu IV, 0x70(OUTP) _aesni_gf128mul_x_ble() @@ -2738,16 +2750,20 @@ ENTRY(aesni_xts_crypt8) call *%r11 - pxor 0x40(OUTP), STATE1 + movdqu 0x40(OUTP), INC + pxor INC, STATE1 movdqu STATE1, 0x40(OUTP) - pxor 0x50(OUTP), STATE2 + movdqu 0x50(OUTP), INC + pxor INC, STATE2 movdqu STATE2, 0x50(OUTP) - pxor 0x60(OUTP), STATE3 + movdqu 0x60(OUTP), INC + pxor INC, STATE3 movdqu STATE3, 0x60(OUTP) - pxor 0x70(OUTP), STATE4 + movdqu 0x70(OUTP), INC + pxor INC, STATE4 movdqu STATE4, 0x70(OUTP) ret diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S index 94c27df8a549..f247304299a2 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/crypto/crc32-pclmul_asm.S @@ -240,7 +240,7 @@ fold_64: pand %xmm3, %xmm1 PCLMULQDQ 0x00, CONSTANT, %xmm1 pxor %xmm2, %xmm1 - pextrd $0x01, %xmm1, %eax + PEXTRD 0x01, %xmm1, %eax ret ENDPROC(crc32_pclmul_le_16) diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 56610c4bf31b..642f15687a0a 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -118,7 +118,7 @@ y2 = %r15d _INP_END_SIZE = 8 _INP_SIZE = 8 -_XFER_SIZE = 8 +_XFER_SIZE = 16 _XMM_SAVE_SIZE = 0 _INP_END = 0 diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index 98d3c391da81..f833b74d902b 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -111,7 +111,7 @@ y2 = %r15d _INP_END_SIZE = 8 _INP_SIZE = 8 -_XFER_SIZE = 8 +_XFER_SIZE = 16 _XMM_SAVE_SIZE = 0 _INP_END = 0 diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 805078e08013..52ff81cce008 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -192,7 +192,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file, /* struct user */ DUMP_WRITE(&dump, sizeof(dump)); /* Now dump all of the user data. Include malloced stuff as well */ - DUMP_SEEK(PAGE_SIZE); + DUMP_SEEK(PAGE_SIZE - sizeof(dump)); /* now we start writing out the user space info */ set_fs(USER_DS); /* Dump the data area */ diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index cf1a471a18a2..bccfca68430e 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -34,8 +34,6 @@ #include <asm/sys_ia32.h> #include <asm/smap.h> -#define FIX_EFLAGS __FIX_EFLAGS - int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { int err = 0; diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 5b33686b6995..0062a0125041 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -102,13 +102,6 @@ extern void efi_call_phys_epilog(void); extern void efi_unmap_memmap(void); extern void efi_memory_uc(u64 addr, unsigned long size); -struct efi_var_bootdata { - struct setup_data data; - u64 store_size; - u64 remaining_size; - u64 max_var_size; -}; - #ifdef CONFIG_EFI static inline bool efi_is_native(void) diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h index 280bf7fb6aba..3e115273ed88 100644 --- a/arch/x86/include/asm/inst.h +++ b/arch/x86/include/asm/inst.h @@ -9,12 +9,68 @@ #define REG_NUM_INVALID 100 -#define REG_TYPE_R64 0 -#define REG_TYPE_XMM 1 +#define REG_TYPE_R32 0 +#define REG_TYPE_R64 1 +#define REG_TYPE_XMM 2 #define REG_TYPE_INVALID 100 + .macro R32_NUM opd r32 + \opd = REG_NUM_INVALID + .ifc \r32,%eax + \opd = 0 + .endif + .ifc \r32,%ecx + \opd = 1 + .endif + .ifc \r32,%edx + \opd = 2 + .endif + .ifc \r32,%ebx + \opd = 3 + .endif + .ifc \r32,%esp + \opd = 4 + .endif + .ifc \r32,%ebp + \opd = 5 + .endif + .ifc \r32,%esi + \opd = 6 + .endif + .ifc \r32,%edi + \opd = 7 + .endif +#ifdef CONFIG_X86_64 + .ifc \r32,%r8d + \opd = 8 + .endif + .ifc \r32,%r9d + \opd = 9 + .endif + .ifc \r32,%r10d + \opd = 10 + .endif + .ifc \r32,%r11d + \opd = 11 + .endif + .ifc \r32,%r12d + \opd = 12 + .endif + .ifc \r32,%r13d + \opd = 13 + .endif + .ifc \r32,%r14d + \opd = 14 + .endif + .ifc \r32,%r15d + \opd = 15 + .endif +#endif + .endm + .macro R64_NUM opd r64 \opd = REG_NUM_INVALID +#ifdef CONFIG_X86_64 .ifc \r64,%rax \opd = 0 .endif @@ -63,6 +119,7 @@ .ifc \r64,%r15 \opd = 15 .endif +#endif .endm .macro XMM_NUM opd xmm @@ -118,10 +175,13 @@ .endm .macro REG_TYPE type reg + R32_NUM reg_type_r32 \reg R64_NUM reg_type_r64 \reg XMM_NUM reg_type_xmm \reg .if reg_type_r64 <> REG_NUM_INVALID \type = REG_TYPE_R64 + .elseif reg_type_r32 <> REG_NUM_INVALID + \type = REG_TYPE_R32 .elseif reg_type_xmm <> REG_NUM_INVALID \type = REG_TYPE_XMM .else @@ -162,6 +222,16 @@ .byte \imm8 .endm + .macro PEXTRD imm8 xmm gpr + R32_NUM extrd_opd1 \gpr + XMM_NUM extrd_opd2 \xmm + PFX_OPD_SIZE + PFX_REX extrd_opd1 extrd_opd2 + .byte 0x0f, 0x3a, 0x16 + MODRM 0xc0 extrd_opd1 extrd_opd2 + .byte \imm8 + .endm + .macro AESKEYGENASSIST rcon xmm1 xmm2 XMM_NUM aeskeygen_opd1 \xmm1 XMM_NUM aeskeygen_opd2 \xmm2 diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index ba870bb6dd8e..57873beb3292 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -41,4 +41,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); +#ifdef CONFIG_X86_LOCAL_APIC +void arch_trigger_all_cpu_backtrace(void); +#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace +#endif + #endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3741c653767c..af9c5525434d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -59,7 +59,7 @@ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ - | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_RDWRGSFS \ + | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 6825e2efd1b4..6bc3985ee473 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -60,11 +60,11 @@ static inline void __exit exit_amd_microcode(void) {} #ifdef CONFIG_MICROCODE_EARLY #define MAX_UCODE_COUNT 128 extern void __init load_ucode_bsp(void); -extern __init void load_ucode_ap(void); +extern void __cpuinit load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); #else static inline void __init load_ucode_bsp(void) {} -static inline __init void load_ucode_ap(void) {} +static inline void __cpuinit load_ucode_ap(void) {} static inline int __init save_microcode_in_initrd(void) { return 0; diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h index 03f90c8a5a7c..0208c3c2cbc6 100644 --- a/arch/x86/include/asm/mutex_32.h +++ b/arch/x86/include/asm/mutex_32.h @@ -42,17 +42,14 @@ do { \ * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if it - * wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count, - int (*fail_fn)(atomic_t *)) +static inline int __mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(atomic_dec_return(count) < 0)) - return fail_fn(count); + return -1; else return 0; } diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h index 68a87b0f8e29..2c543fff241b 100644 --- a/arch/x86/include/asm/mutex_64.h +++ b/arch/x86/include/asm/mutex_64.h @@ -37,17 +37,14 @@ do { \ * __mutex_fastpath_lock_retval - try to take the lock by moving the count * from 1 to a 0 value * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 1 * - * Change the count from 1 to a value lower than 1, and call <fail_fn> if - * it wasn't 1 originally. This function returns 0 if the fastpath succeeds, - * or anything the slow path function returns + * Change the count from 1 to a value lower than 1. This function returns 0 + * if the fastpath succeeds, or -1 otherwise. */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count, - int (*fail_fn)(atomic_t *)) +static inline int __mutex_fastpath_lock_retval(atomic_t *count) { if (unlikely(atomic_dec_return(count) < 0)) - return fail_fn(count); + return -1; else return 0; } diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index c0fa356e90de..86f9301903c8 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -18,9 +18,7 @@ extern int proc_nmi_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; -void arch_trigger_all_cpu_backtrace(void); -#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace -#endif +#endif /* CONFIG_X86_LOCAL_APIC */ #define NMI_FLAG_FIRST 1 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 57cb63402213..8249df45d2f2 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -29,6 +29,9 @@ #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL +#define HSW_IN_TX (1ULL << 32) +#define HSW_IN_TX_CHECKPOINTED (1ULL << 33) + #define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36) #define AMD64_EVENTSEL_GUESTONLY (1ULL << 40) #define AMD64_EVENTSEL_HOSTONLY (1ULL << 41) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1e672234c4ff..5b0818bc8963 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -506,9 +506,6 @@ static inline unsigned long pages_to_mb(unsigned long npg) return npg >> (20 - PAGE_SHIFT); } -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - #if PAGETABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 22224b3b43bb..5b87d52eed0b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -981,5 +981,5 @@ bool xen_set_default_idle(void); #endif void stop_this_cpu(void *dummy); - +void df_debug(struct pt_regs *regs, long error_code); #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index beff97f7df37..7a958164088c 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -7,10 +7,10 @@ #include <asm/processor-flags.h> -#define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ +#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ - X86_EFLAGS_CF) + X86_EFLAGS_CF | X86_EFLAGS_RF) void signal_fault(struct pt_regs *regs, void __user *frame, char *where); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 41fc93a2e225..2f4d924fe6c9 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -16,7 +16,7 @@ static inline void native_clts(void) * all loads stores around it, which can hurt performance. Solution is to * use a variable and mimic reads and writes to it to enforce serialization */ -static unsigned long __force_order; +extern unsigned long __force_order; static inline unsigned long native_read_cr0(void) { diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 50a7fc0f824a..cf512003e663 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -62,7 +62,7 @@ static inline void __flush_tlb_all(void) static inline void __flush_tlb_one(unsigned long addr) { - __flush_tlb_single(addr); + __flush_tlb_single(addr); } #define TLB_FLUSH_ALL -1UL diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 142810c457dc..4f7923dd0007 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -235,7 +235,7 @@ extern long __copy_user_nocache(void *dst, const void __user *src, static inline int __copy_from_user_nocache(void *dst, const void __user *src, unsigned size) { - might_sleep(); + might_fault(); return __copy_user_nocache(dst, src, size, 1); } diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 08744242b8d2..c15ddaf90710 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -6,7 +6,6 @@ #define SETUP_E820_EXT 1 #define SETUP_DTB 2 #define SETUP_PCI 3 -#define SETUP_EFI_VARS 4 /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 2af848dfa754..bb0465090ae5 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -170,6 +170,9 @@ #define MSR_KNC_EVNTSEL0 0x00000028 #define MSR_KNC_EVNTSEL1 0x00000029 +/* Alternative perfctr range with full access. */ +#define MSR_IA32_PMC0 0x000004c1 + /* AMD64 MSRs. Not complete. See the architecture manual for a more complete list. */ diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 54991a746043..180a0c3c224d 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -2,75 +2,129 @@ #define _UAPI_ASM_X86_PROCESSOR_FLAGS_H /* Various flags defined: can be included from assembler. */ +#include <linux/const.h> + /* * EFLAGS bits */ -#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ -#define X86_EFLAGS_BIT1 0x00000002 /* Bit 1 - always on */ -#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ -#define X86_EFLAGS_AF 0x00000010 /* Auxiliary carry Flag */ -#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ -#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ -#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ -#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ -#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ -#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ -#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ -#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ -#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ -#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ -#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ -#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ -#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ -#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ +#define X86_EFLAGS_CF_BIT 0 /* Carry Flag */ +#define X86_EFLAGS_CF _BITUL(X86_EFLAGS_CF_BIT) +#define X86_EFLAGS_FIXED_BIT 1 /* Bit 1 - always on */ +#define X86_EFLAGS_FIXED _BITUL(X86_EFLAGS_FIXED_BIT) +#define X86_EFLAGS_PF_BIT 2 /* Parity Flag */ +#define X86_EFLAGS_PF _BITUL(X86_EFLAGS_PF_BIT) +#define X86_EFLAGS_AF_BIT 4 /* Auxiliary carry Flag */ +#define X86_EFLAGS_AF _BITUL(X86_EFLAGS_AF_BIT) +#define X86_EFLAGS_ZF_BIT 6 /* Zero Flag */ +#define X86_EFLAGS_ZF _BITUL(X86_EFLAGS_ZF_BIT) +#define X86_EFLAGS_SF_BIT 7 /* Sign Flag */ +#define X86_EFLAGS_SF _BITUL(X86_EFLAGS_SF_BIT) +#define X86_EFLAGS_TF_BIT 8 /* Trap Flag */ +#define X86_EFLAGS_TF _BITUL(X86_EFLAGS_TF_BIT) +#define X86_EFLAGS_IF_BIT 9 /* Interrupt Flag */ +#define X86_EFLAGS_IF _BITUL(X86_EFLAGS_IF_BIT) +#define X86_EFLAGS_DF_BIT 10 /* Direction Flag */ +#define X86_EFLAGS_DF _BITUL(X86_EFLAGS_DF_BIT) +#define X86_EFLAGS_OF_BIT 11 /* Overflow Flag */ +#define X86_EFLAGS_OF _BITUL(X86_EFLAGS_OF_BIT) +#define X86_EFLAGS_IOPL_BIT 12 /* I/O Privilege Level (2 bits) */ +#define X86_EFLAGS_IOPL (_AC(3,UL) << X86_EFLAGS_IOPL_BIT) +#define X86_EFLAGS_NT_BIT 14 /* Nested Task */ +#define X86_EFLAGS_NT _BITUL(X86_EFLAGS_NT_BIT) +#define X86_EFLAGS_RF_BIT 16 /* Resume Flag */ +#define X86_EFLAGS_RF _BITUL(X86_EFLAGS_RF_BIT) +#define X86_EFLAGS_VM_BIT 17 /* Virtual Mode */ +#define X86_EFLAGS_VM _BITUL(X86_EFLAGS_VM_BIT) +#define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */ +#define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT) +#define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */ +#define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT) +#define X86_EFLAGS_VIF_BIT 19 /* Virtual Interrupt Flag */ +#define X86_EFLAGS_VIF _BITUL(X86_EFLAGS_VIF_BIT) +#define X86_EFLAGS_VIP_BIT 20 /* Virtual Interrupt Pending */ +#define X86_EFLAGS_VIP _BITUL(X86_EFLAGS_VIP_BIT) +#define X86_EFLAGS_ID_BIT 21 /* CPUID detection */ +#define X86_EFLAGS_ID _BITUL(X86_EFLAGS_ID_BIT) /* * Basic CPU control in CR0 */ -#define X86_CR0_PE 0x00000001 /* Protection Enable */ -#define X86_CR0_MP 0x00000002 /* Monitor Coprocessor */ -#define X86_CR0_EM 0x00000004 /* Emulation */ -#define X86_CR0_TS 0x00000008 /* Task Switched */ -#define X86_CR0_ET 0x00000010 /* Extension Type */ -#define X86_CR0_NE 0x00000020 /* Numeric Error */ -#define X86_CR0_WP 0x00010000 /* Write Protect */ -#define X86_CR0_AM 0x00040000 /* Alignment Mask */ -#define X86_CR0_NW 0x20000000 /* Not Write-through */ -#define X86_CR0_CD 0x40000000 /* Cache Disable */ -#define X86_CR0_PG 0x80000000 /* Paging */ +#define X86_CR0_PE_BIT 0 /* Protection Enable */ +#define X86_CR0_PE _BITUL(X86_CR0_PE_BIT) +#define X86_CR0_MP_BIT 1 /* Monitor Coprocessor */ +#define X86_CR0_MP _BITUL(X86_CR0_MP_BIT) +#define X86_CR0_EM_BIT 2 /* Emulation */ +#define X86_CR0_EM _BITUL(X86_CR0_EM_BIT) +#define X86_CR0_TS_BIT 3 /* Task Switched */ +#define X86_CR0_TS _BITUL(X86_CR0_TS_BIT) +#define X86_CR0_ET_BIT 4 /* Extension Type */ +#define X86_CR0_ET _BITUL(X86_CR0_ET_BIT) +#define X86_CR0_NE_BIT 5 /* Numeric Error */ +#define X86_CR0_NE _BITUL(X86_CR0_NE_BIT) +#define X86_CR0_WP_BIT 16 /* Write Protect */ +#define X86_CR0_WP _BITUL(X86_CR0_WP_BIT) +#define X86_CR0_AM_BIT 18 /* Alignment Mask */ +#define X86_CR0_AM _BITUL(X86_CR0_AM_BIT) +#define X86_CR0_NW_BIT 29 /* Not Write-through */ +#define X86_CR0_NW _BITUL(X86_CR0_NW_BIT) +#define X86_CR0_CD_BIT 30 /* Cache Disable */ +#define X86_CR0_CD _BITUL(X86_CR0_CD_BIT) +#define X86_CR0_PG_BIT 31 /* Paging */ +#define X86_CR0_PG _BITUL(X86_CR0_PG_BIT) /* * Paging options in CR3 */ -#define X86_CR3_PWT 0x00000008 /* Page Write Through */ -#define X86_CR3_PCD 0x00000010 /* Page Cache Disable */ -#define X86_CR3_PCID_MASK 0x00000fff /* PCID Mask */ +#define X86_CR3_PWT_BIT 3 /* Page Write Through */ +#define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT) +#define X86_CR3_PCD_BIT 4 /* Page Cache Disable */ +#define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT) +#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */ /* * Intel CPU features in CR4 */ -#define X86_CR4_VME 0x00000001 /* enable vm86 extensions */ -#define X86_CR4_PVI 0x00000002 /* virtual interrupts flag enable */ -#define X86_CR4_TSD 0x00000004 /* disable time stamp at ipl 3 */ -#define X86_CR4_DE 0x00000008 /* enable debugging extensions */ -#define X86_CR4_PSE 0x00000010 /* enable page size extensions */ -#define X86_CR4_PAE 0x00000020 /* enable physical address extensions */ -#define X86_CR4_MCE 0x00000040 /* Machine check enable */ -#define X86_CR4_PGE 0x00000080 /* enable global pages */ -#define X86_CR4_PCE 0x00000100 /* enable performance counters at ipl 3 */ -#define X86_CR4_OSFXSR 0x00000200 /* enable fast FPU save and restore */ -#define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */ -#define X86_CR4_VMXE 0x00002000 /* enable VMX virtualization */ -#define X86_CR4_RDWRGSFS 0x00010000 /* enable RDWRGSFS support */ -#define X86_CR4_PCIDE 0x00020000 /* enable PCID support */ -#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */ -#define X86_CR4_SMEP 0x00100000 /* enable SMEP support */ -#define X86_CR4_SMAP 0x00200000 /* enable SMAP support */ +#define X86_CR4_VME_BIT 0 /* enable vm86 extensions */ +#define X86_CR4_VME _BITUL(X86_CR4_VME_BIT) +#define X86_CR4_PVI_BIT 1 /* virtual interrupts flag enable */ +#define X86_CR4_PVI _BITUL(X86_CR4_PVI_BIT) +#define X86_CR4_TSD_BIT 2 /* disable time stamp at ipl 3 */ +#define X86_CR4_TSD _BITUL(X86_CR4_TSD_BIT) +#define X86_CR4_DE_BIT 3 /* enable debugging extensions */ +#define X86_CR4_DE _BITUL(X86_CR4_DE_BIT) +#define X86_CR4_PSE_BIT 4 /* enable page size extensions */ +#define X86_CR4_PSE _BITUL(X86_CR4_PSE_BIT) +#define X86_CR4_PAE_BIT 5 /* enable physical address extensions */ +#define X86_CR4_PAE _BITUL(X86_CR4_PAE_BIT) +#define X86_CR4_MCE_BIT 6 /* Machine check enable */ +#define X86_CR4_MCE _BITUL(X86_CR4_MCE_BIT) +#define X86_CR4_PGE_BIT 7 /* enable global pages */ +#define X86_CR4_PGE _BITUL(X86_CR4_PGE_BIT) +#define X86_CR4_PCE_BIT 8 /* enable performance counters at ipl 3 */ +#define X86_CR4_PCE _BITUL(X86_CR4_PCE_BIT) +#define X86_CR4_OSFXSR_BIT 9 /* enable fast FPU save and restore */ +#define X86_CR4_OSFXSR _BITUL(X86_CR4_OSFXSR_BIT) +#define X86_CR4_OSXMMEXCPT_BIT 10 /* enable unmasked SSE exceptions */ +#define X86_CR4_OSXMMEXCPT _BITUL(X86_CR4_OSXMMEXCPT_BIT) +#define X86_CR4_VMXE_BIT 13 /* enable VMX virtualization */ +#define X86_CR4_VMXE _BITUL(X86_CR4_VMXE_BIT) +#define X86_CR4_SMXE_BIT 14 /* enable safer mode (TXT) */ +#define X86_CR4_SMXE _BITUL(X86_CR4_SMXE_BIT) +#define X86_CR4_FSGSBASE_BIT 16 /* enable RDWRFSGS support */ +#define X86_CR4_FSGSBASE _BITUL(X86_CR4_FSGSBASE_BIT) +#define X86_CR4_PCIDE_BIT 17 /* enable PCID support */ +#define X86_CR4_PCIDE _BITUL(X86_CR4_PCIDE_BIT) +#define X86_CR4_OSXSAVE_BIT 18 /* enable xsave and xrestore */ +#define X86_CR4_OSXSAVE _BITUL(X86_CR4_OSXSAVE_BIT) +#define X86_CR4_SMEP_BIT 20 /* enable SMEP support */ +#define X86_CR4_SMEP _BITUL(X86_CR4_SMEP_BIT) +#define X86_CR4_SMAP_BIT 21 /* enable SMAP support */ +#define X86_CR4_SMAP _BITUL(X86_CR4_SMAP_BIT) /* * x86-64 Task Priority Register, CR8 */ -#define X86_CR8_TPR 0x0000000F /* task priority register */ +#define X86_CR8_TPR _AC(0x0000000f,UL) /* task priority register */ /* * AMD and Transmeta use MSRs for configuration; see <asm/msr-index.h> diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 7bd3bd310106..4ce822ed58f5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -67,7 +67,7 @@ obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o +obj-$(CONFIG_DOUBLEFAULT) += doublefault.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 904611bf0e5a..1600b1ca4f04 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2302,7 +2302,7 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL) +#if defined(CONFIG_X86_MCE_INTEL) if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index 31cb9ae992b7..a698d7165c96 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -9,6 +9,7 @@ * */ #include <asm/apic.h> +#include <asm/nmi.h> #include <linux/cpumask.h> #include <linux/kdebug.h> diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index b0684e4a73aa..47b56a7e99cb 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -31,11 +31,15 @@ obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_PERF_EVENTS obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o perf_event_amd_uncore.o +ifdef CONFIG_AMD_IOMMU +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o +endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o endif + obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 7c6f7d548c0f..8dc72dda66fe 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -618,36 +618,34 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) * parameters cpuid leaf to find the cache details */ for (i = 0; i < num_cache_leaves; i++) { - struct _cpuid4_info_regs this_leaf; + struct _cpuid4_info_regs this_leaf = {}; int retval; retval = cpuid4_cache_lookup_regs(i, &this_leaf); - if (retval >= 0) { - switch (this_leaf.eax.split.level) { - case 1: - if (this_leaf.eax.split.type == - CACHE_TYPE_DATA) - new_l1d = this_leaf.size/1024; - else if (this_leaf.eax.split.type == - CACHE_TYPE_INST) - new_l1i = this_leaf.size/1024; - break; - case 2: - new_l2 = this_leaf.size/1024; - num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; - index_msb = get_count_order(num_threads_sharing); - l2_id = c->apicid & ~((1 << index_msb) - 1); - break; - case 3: - new_l3 = this_leaf.size/1024; - num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; - index_msb = get_count_order( - num_threads_sharing); - l3_id = c->apicid & ~((1 << index_msb) - 1); - break; - default: - break; - } + if (retval < 0) + continue; + + switch (this_leaf.eax.split.level) { + case 1: + if (this_leaf.eax.split.type == CACHE_TYPE_DATA) + new_l1d = this_leaf.size/1024; + else if (this_leaf.eax.split.type == CACHE_TYPE_INST) + new_l1i = this_leaf.size/1024; + break; + case 2: + new_l2 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l2_id = c->apicid & ~((1 << index_msb) - 1); + break; + case 3: + new_l3 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l3_id = c->apicid & ~((1 << index_msb) - 1); + break; + default: + break; } } } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 35ffda5d0727..5f90b85ff22e 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits) if (mtrr_tom2) x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base; - nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size); /* * [0, 1M) should always be covered by var mtrr with WB * and fixed mtrrs should take effect before var mtrr for it: */ - nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0, + nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0, 1ULL<<(20 - PAGE_SHIFT)); - /* Sort the ranges: */ - sort_range(range, nr_range); + /* add from var mtrr at last */ + nr_range = x86_get_mtrr_mem_range(range, nr_range, + x_remove_base, x_remove_size); range_sums = sum_ranges(range, nr_range); printk(KERN_INFO "total RAM covered: %ldM\n", diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 68a3343e5798..9e451b0876b5 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -167,7 +167,7 @@ static void post_set(void) setCx86(CX86_CCR3, ccr3); /* Enable caches */ - write_cr0(read_cr0() & 0xbfffffff); + write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ if (cpu_has_pge) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fa72a39e5d46..00f557b95b16 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -701,7 +701,7 @@ static void post_set(void) __releases(set_atomicity_lock) mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Enable caches */ - write_cr0(read_cr0() & 0xbfffffff); + write_cr0(read_cr0() & ~X86_CR0_CD); /* Restore value of CR4 */ if (cpu_has_pge) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1025f3c99d20..9e581c5cf6d0 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -403,7 +403,8 @@ int x86_pmu_hw_config(struct perf_event *event) * check that PEBS LBR correction does not conflict with * whatever the user is asking with attr->branch_sample_type */ - if (event->attr.precise_ip > 1) { + if (event->attr.precise_ip > 1 && + x86_pmu.intel_cap.pebs_format < 2) { u64 *br_type = &event->attr.branch_sample_type; if (has_branch_stack(event)) { @@ -568,7 +569,7 @@ struct sched_state { struct perf_sched { int max_weight; int max_events; - struct event_constraint **constraints; + struct perf_event **events; struct sched_state state; int saved_states; struct sched_state saved[SCHED_STATES_MAX]; @@ -577,7 +578,7 @@ struct perf_sched { /* * Initialize interator that runs through all events and counters. */ -static void perf_sched_init(struct perf_sched *sched, struct event_constraint **c, +static void perf_sched_init(struct perf_sched *sched, struct perf_event **events, int num, int wmin, int wmax) { int idx; @@ -585,10 +586,10 @@ static void perf_sched_init(struct perf_sched *sched, struct event_constraint ** memset(sched, 0, sizeof(*sched)); sched->max_events = num; sched->max_weight = wmax; - sched->constraints = c; + sched->events = events; for (idx = 0; idx < num; idx++) { - if (c[idx]->weight == wmin) + if (events[idx]->hw.constraint->weight == wmin) break; } @@ -635,8 +636,7 @@ static bool __perf_sched_find_counter(struct perf_sched *sched) if (sched->state.event >= sched->max_events) return false; - c = sched->constraints[sched->state.event]; - + c = sched->events[sched->state.event]->hw.constraint; /* Prefer fixed purpose counters */ if (c->idxmsk64 & (~0ULL << INTEL_PMC_IDX_FIXED)) { idx = INTEL_PMC_IDX_FIXED; @@ -694,7 +694,7 @@ static bool perf_sched_next_event(struct perf_sched *sched) if (sched->state.weight > sched->max_weight) return false; } - c = sched->constraints[sched->state.event]; + c = sched->events[sched->state.event]->hw.constraint; } while (c->weight != sched->state.weight); sched->state.counter = 0; /* start with first counter */ @@ -705,12 +705,12 @@ static bool perf_sched_next_event(struct perf_sched *sched) /* * Assign a counter for each event. */ -int perf_assign_events(struct event_constraint **constraints, int n, +int perf_assign_events(struct perf_event **events, int n, int wmin, int wmax, int *assign) { struct perf_sched sched; - perf_sched_init(&sched, constraints, n, wmin, wmax); + perf_sched_init(&sched, events, n, wmin, wmax); do { if (!perf_sched_find_counter(&sched)) @@ -724,16 +724,19 @@ int perf_assign_events(struct event_constraint **constraints, int n, int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { - struct event_constraint *c, *constraints[X86_PMC_IDX_MAX]; + struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; + struct perf_event *e; int i, wmin, wmax, num = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { + hwc = &cpuc->event_list[i]->hw; c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); - constraints[i] = c; + hwc->constraint = c; + wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } @@ -743,7 +746,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) */ for (i = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; - c = constraints[i]; + c = hwc->constraint; /* never assigned */ if (hwc->idx == -1) @@ -764,16 +767,35 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) /* slow path */ if (i != n) - num = perf_assign_events(constraints, n, wmin, wmax, assign); + num = perf_assign_events(cpuc->event_list, n, wmin, + wmax, assign); /* + * Mark the event as committed, so we do not put_constraint() + * in case new events are added and fail scheduling. + */ + if (!num && assign) { + for (i = 0; i < n; i++) { + e = cpuc->event_list[i]; + e->hw.flags |= PERF_X86_EVENT_COMMITTED; + } + } + /* * scheduling failed or is just a simulation, * free resources if necessary */ if (!assign || num) { for (i = 0; i < n; i++) { + e = cpuc->event_list[i]; + /* + * do not put_constraint() on comitted events, + * because they are good to go + */ + if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) + continue; + if (x86_pmu.put_event_constraints) - x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]); + x86_pmu.put_event_constraints(cpuc, e); } } return num ? -EINVAL : 0; @@ -1153,6 +1175,11 @@ static void x86_pmu_del(struct perf_event *event, int flags) int i; /* + * event is descheduled + */ + event->hw.flags &= ~PERF_X86_EVENT_COMMITTED; + + /* * If we're called during a txn, we don't need to do anything. * The events never got scheduled and ->cancel_txn will truncate * the event_list. @@ -1249,10 +1276,20 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + int ret; + u64 start_clock; + u64 finish_clock; + if (!atomic_read(&active_events)) return NMI_DONE; - return x86_pmu.handle_irq(regs); + start_clock = local_clock(); + ret = x86_pmu.handle_irq(regs); + finish_clock = local_clock(); + + perf_sample_event_took(finish_clock - start_clock); + + return ret; } struct event_constraint emptyconstraint; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index ba9aadfa683b..97e557bc4c91 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -63,10 +63,12 @@ struct event_constraint { int flags; }; /* - * struct event_constraint flags + * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style st data sampling */ +#define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -227,11 +229,14 @@ struct cpu_hw_events { * - inv * - edge * - cnt-mask + * - in_tx + * - in_tx_checkpointed * The other filters are supported by fixed counters. * The any-thread option is supported starting with v3. */ +#define FIXED_EVENT_FLAGS (X86_RAW_EVENT_MASK|HSW_IN_TX|HSW_IN_TX_CHECKPOINTED) #define FIXED_EVENT_CONSTRAINT(c, n) \ - EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK) + EVENT_CONSTRAINT(c, (1ULL << (32+n)), FIXED_EVENT_FLAGS) /* * Constraint on the Event code + UMask @@ -247,6 +252,11 @@ struct cpu_hw_events { __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) +/* DataLA version of store sampling without extra enable bit. */ +#define INTEL_PST_HSW_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) + #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -301,6 +311,11 @@ union perf_capabilities { u64 pebs_arch_reg:1; u64 pebs_format:4; u64 smm_freeze:1; + /* + * PMU supports separate counter range for writing + * values > 32bit. + */ + u64 full_width_write:1; }; u64 capabilities; }; @@ -375,6 +390,7 @@ struct x86_pmu { struct event_constraint *event_constraints; struct x86_pmu_quirk *quirks; int perfctr_second_write; + bool late_ack; /* * sysfs attrs @@ -528,7 +544,7 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc, void x86_pmu_enable_all(int added); -int perf_assign_events(struct event_constraint **constraints, int n, +int perf_assign_events(struct perf_event **events, int n, int wmin, int wmax, int *assign); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign); @@ -633,6 +649,8 @@ extern struct event_constraint intel_snb_pebs_event_constraints[]; extern struct event_constraint intel_ivb_pebs_event_constraints[]; +extern struct event_constraint intel_hsw_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 7e28d9467bb4..4cbe03287b08 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -648,48 +648,48 @@ static __initconst const struct x86_pmu amd_pmu = { .cpu_dead = amd_pmu_cpu_dead, }; -static int setup_event_constraints(void) +static int __init amd_core_pmu_init(void) { - if (boot_cpu_data.x86 == 0x15) + if (!cpu_has_perfctr_core) + return 0; + + switch (boot_cpu_data.x86) { + case 0x15: + pr_cont("Fam15h "); x86_pmu.get_event_constraints = amd_get_event_constraints_f15h; - return 0; -} + break; -static int setup_perfctr_core(void) -{ - if (!cpu_has_perfctr_core) { - WARN(x86_pmu.get_event_constraints == amd_get_event_constraints_f15h, - KERN_ERR "Odd, counter constraints enabled but no core perfctrs detected!"); + default: + pr_err("core perfctr but no constraints; unknown hardware!\n"); return -ENODEV; } - WARN(x86_pmu.get_event_constraints == amd_get_event_constraints, - KERN_ERR "hw perf events core counters need constraints handler!"); - /* * If core performance counter extensions exists, we must use * MSR_F15H_PERF_CTL/MSR_F15H_PERF_CTR msrs. See also - * x86_pmu_addr_offset(). + * amd_pmu_addr_offset(). */ x86_pmu.eventsel = MSR_F15H_PERF_CTL; x86_pmu.perfctr = MSR_F15H_PERF_CTR; x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE; - printk(KERN_INFO "perf: AMD core performance counters detected\n"); - + pr_cont("core perfctr, "); return 0; } __init int amd_pmu_init(void) { + int ret; + /* Performance-monitoring supported from K7 and later: */ if (boot_cpu_data.x86 < 6) return -ENODEV; x86_pmu = amd_pmu; - setup_event_constraints(); - setup_perfctr_core(); + ret = amd_core_pmu_init(); + if (ret) + return ret; /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c new file mode 100644 index 000000000000..0db655ef3918 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c @@ -0,0 +1,504 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Steven Kinney <Steven.Kinney@amd.com> + * Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com> + * + * Perf: amd_iommu - AMD IOMMU Performance Counter PMU implementation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/perf_event.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/slab.h> + +#include "perf_event.h" +#include "perf_event_amd_iommu.h" + +#define COUNTER_SHIFT 16 + +#define _GET_BANK(ev) ((u8)(ev->hw.extra_reg.reg >> 8)) +#define _GET_CNTR(ev) ((u8)(ev->hw.extra_reg.reg)) + +/* iommu pmu config masks */ +#define _GET_CSOURCE(ev) ((ev->hw.config & 0xFFULL)) +#define _GET_DEVID(ev) ((ev->hw.config >> 8) & 0xFFFFULL) +#define _GET_PASID(ev) ((ev->hw.config >> 24) & 0xFFFFULL) +#define _GET_DOMID(ev) ((ev->hw.config >> 40) & 0xFFFFULL) +#define _GET_DEVID_MASK(ev) ((ev->hw.extra_reg.config) & 0xFFFFULL) +#define _GET_PASID_MASK(ev) ((ev->hw.extra_reg.config >> 16) & 0xFFFFULL) +#define _GET_DOMID_MASK(ev) ((ev->hw.extra_reg.config >> 32) & 0xFFFFULL) + +static struct perf_amd_iommu __perf_iommu; + +struct perf_amd_iommu { + struct pmu pmu; + u8 max_banks; + u8 max_counters; + u64 cntr_assign_mask; + raw_spinlock_t lock; + const struct attribute_group *attr_groups[4]; +}; + +#define format_group attr_groups[0] +#define cpumask_group attr_groups[1] +#define events_group attr_groups[2] +#define null_group attr_groups[3] + +/*--------------------------------------------- + * sysfs format attributes + *---------------------------------------------*/ +PMU_FORMAT_ATTR(csource, "config:0-7"); +PMU_FORMAT_ATTR(devid, "config:8-23"); +PMU_FORMAT_ATTR(pasid, "config:24-39"); +PMU_FORMAT_ATTR(domid, "config:40-55"); +PMU_FORMAT_ATTR(devid_mask, "config1:0-15"); +PMU_FORMAT_ATTR(pasid_mask, "config1:16-31"); +PMU_FORMAT_ATTR(domid_mask, "config1:32-47"); + +static struct attribute *iommu_format_attrs[] = { + &format_attr_csource.attr, + &format_attr_devid.attr, + &format_attr_pasid.attr, + &format_attr_domid.attr, + &format_attr_devid_mask.attr, + &format_attr_pasid_mask.attr, + &format_attr_domid_mask.attr, + NULL, +}; + +static struct attribute_group amd_iommu_format_group = { + .name = "format", + .attrs = iommu_format_attrs, +}; + +/*--------------------------------------------- + * sysfs events attributes + *---------------------------------------------*/ +struct amd_iommu_event_desc { + struct kobj_attribute attr; + const char *event; +}; + +static ssize_t _iommu_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct amd_iommu_event_desc *event = + container_of(attr, struct amd_iommu_event_desc, attr); + return sprintf(buf, "%s\n", event->event); +} + +#define AMD_IOMMU_EVENT_DESC(_name, _event) \ +{ \ + .attr = __ATTR(_name, 0444, _iommu_event_show, NULL), \ + .event = _event, \ +} + +static struct amd_iommu_event_desc amd_iommu_v2_event_descs[] = { + AMD_IOMMU_EVENT_DESC(mem_pass_untrans, "csource=0x01"), + AMD_IOMMU_EVENT_DESC(mem_pass_pretrans, "csource=0x02"), + AMD_IOMMU_EVENT_DESC(mem_pass_excl, "csource=0x03"), + AMD_IOMMU_EVENT_DESC(mem_target_abort, "csource=0x04"), + AMD_IOMMU_EVENT_DESC(mem_trans_total, "csource=0x05"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pte_hit, "csource=0x06"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pte_mis, "csource=0x07"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pde_hit, "csource=0x08"), + AMD_IOMMU_EVENT_DESC(mem_iommu_tlb_pde_mis, "csource=0x09"), + AMD_IOMMU_EVENT_DESC(mem_dte_hit, "csource=0x0a"), + AMD_IOMMU_EVENT_DESC(mem_dte_mis, "csource=0x0b"), + AMD_IOMMU_EVENT_DESC(page_tbl_read_tot, "csource=0x0c"), + AMD_IOMMU_EVENT_DESC(page_tbl_read_nst, "csource=0x0d"), + AMD_IOMMU_EVENT_DESC(page_tbl_read_gst, "csource=0x0e"), + AMD_IOMMU_EVENT_DESC(int_dte_hit, "csource=0x0f"), + AMD_IOMMU_EVENT_DESC(int_dte_mis, "csource=0x10"), + AMD_IOMMU_EVENT_DESC(cmd_processed, "csource=0x11"), + AMD_IOMMU_EVENT_DESC(cmd_processed_inv, "csource=0x12"), + AMD_IOMMU_EVENT_DESC(tlb_inv, "csource=0x13"), + { /* end: all zeroes */ }, +}; + +/*--------------------------------------------- + * sysfs cpumask attributes + *---------------------------------------------*/ +static cpumask_t iommu_cpumask; + +static ssize_t _iommu_cpumask_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &iommu_cpumask); + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} +static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL); + +static struct attribute *iommu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group amd_iommu_cpumask_group = { + .attrs = iommu_cpumask_attrs, +}; + +/*---------------------------------------------*/ + +static int get_next_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu) +{ + unsigned long flags; + int shift, bank, cntr, retval; + int max_banks = perf_iommu->max_banks; + int max_cntrs = perf_iommu->max_counters; + + raw_spin_lock_irqsave(&perf_iommu->lock, flags); + + for (bank = 0, shift = 0; bank < max_banks; bank++) { + for (cntr = 0; cntr < max_cntrs; cntr++) { + shift = bank + (bank*3) + cntr; + if (perf_iommu->cntr_assign_mask & (1ULL<<shift)) { + continue; + } else { + perf_iommu->cntr_assign_mask |= (1ULL<<shift); + retval = ((u16)((u16)bank<<8) | (u8)(cntr)); + goto out; + } + } + } + retval = -ENOSPC; +out: + raw_spin_unlock_irqrestore(&perf_iommu->lock, flags); + return retval; +} + +static int clear_avail_iommu_bnk_cntr(struct perf_amd_iommu *perf_iommu, + u8 bank, u8 cntr) +{ + unsigned long flags; + int max_banks, max_cntrs; + int shift = 0; + + max_banks = perf_iommu->max_banks; + max_cntrs = perf_iommu->max_counters; + + if ((bank > max_banks) || (cntr > max_cntrs)) + return -EINVAL; + + shift = bank + cntr + (bank*3); + + raw_spin_lock_irqsave(&perf_iommu->lock, flags); + perf_iommu->cntr_assign_mask &= ~(1ULL<<shift); + raw_spin_unlock_irqrestore(&perf_iommu->lock, flags); + + return 0; +} + +static int perf_iommu_event_init(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct perf_amd_iommu *perf_iommu; + u64 config, config1; + + /* test the event attr type check for PMU enumeration */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* + * IOMMU counters are shared across all cores. + * Therefore, it does not support per-process mode. + * Also, it does not support event sampling mode. + */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + /* IOMMU counters do not have usr/os/guest/host bits */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_host || event->attr.exclude_guest) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + perf_iommu = &__perf_iommu; + + if (event->pmu != &perf_iommu->pmu) + return -ENOENT; + + if (perf_iommu) { + config = event->attr.config; + config1 = event->attr.config1; + } else { + return -EINVAL; + } + + /* integrate with iommu base devid (0000), assume one iommu */ + perf_iommu->max_banks = + amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID); + perf_iommu->max_counters = + amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID); + if ((perf_iommu->max_banks == 0) || (perf_iommu->max_counters == 0)) + return -EINVAL; + + /* update the hw_perf_event struct with the iommu config data */ + hwc->config = config; + hwc->extra_reg.config = config1; + + return 0; +} + +static void perf_iommu_enable_event(struct perf_event *ev) +{ + u8 csource = _GET_CSOURCE(ev); + u16 devid = _GET_DEVID(ev); + u64 reg = 0ULL; + + reg = csource; + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_COUNTER_SRC_REG, ®, true); + + reg = 0ULL | devid | (_GET_DEVID_MASK(ev) << 32); + if (reg) + reg |= (1UL << 31); + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_DEVID_MATCH_REG, ®, true); + + reg = 0ULL | _GET_PASID(ev) | (_GET_PASID_MASK(ev) << 32); + if (reg) + reg |= (1UL << 31); + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_PASID_MATCH_REG, ®, true); + + reg = 0ULL | _GET_DOMID(ev) | (_GET_DOMID_MASK(ev) << 32); + if (reg) + reg |= (1UL << 31); + amd_iommu_pc_get_set_reg_val(devid, + _GET_BANK(ev), _GET_CNTR(ev) , + IOMMU_PC_DOMID_MATCH_REG, ®, true); +} + +static void perf_iommu_disable_event(struct perf_event *event) +{ + u64 reg = 0ULL; + + amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), + _GET_BANK(event), _GET_CNTR(event), + IOMMU_PC_COUNTER_SRC_REG, ®, true); +} + +static void perf_iommu_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + pr_debug("perf: amd_iommu:perf_iommu_start\n"); + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + hwc->state = 0; + + if (flags & PERF_EF_RELOAD) { + u64 prev_raw_count = local64_read(&hwc->prev_count); + amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), + _GET_BANK(event), _GET_CNTR(event), + IOMMU_PC_COUNTER_REG, &prev_raw_count, true); + } + + perf_iommu_enable_event(event); + perf_event_update_userpage(event); + +} + +static void perf_iommu_read(struct perf_event *event) +{ + u64 count = 0ULL; + u64 prev_raw_count = 0ULL; + u64 delta = 0ULL; + struct hw_perf_event *hwc = &event->hw; + pr_debug("perf: amd_iommu:perf_iommu_read\n"); + + amd_iommu_pc_get_set_reg_val(_GET_DEVID(event), + _GET_BANK(event), _GET_CNTR(event), + IOMMU_PC_COUNTER_REG, &count, false); + + /* IOMMU pc counter register is only 48 bits */ + count &= 0xFFFFFFFFFFFFULL; + + prev_raw_count = local64_read(&hwc->prev_count); + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + count) != prev_raw_count) + return; + + /* Handling 48-bit counter overflowing */ + delta = (count << COUNTER_SHIFT) - (prev_raw_count << COUNTER_SHIFT); + delta >>= COUNTER_SHIFT; + local64_add(delta, &event->count); + +} + +static void perf_iommu_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + u64 config; + + pr_debug("perf: amd_iommu:perf_iommu_stop\n"); + + if (hwc->state & PERF_HES_UPTODATE) + return; + + perf_iommu_disable_event(event); + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (hwc->state & PERF_HES_UPTODATE) + return; + + config = hwc->config; + perf_iommu_read(event); + hwc->state |= PERF_HES_UPTODATE; +} + +static int perf_iommu_add(struct perf_event *event, int flags) +{ + int retval; + struct perf_amd_iommu *perf_iommu = + container_of(event->pmu, struct perf_amd_iommu, pmu); + + pr_debug("perf: amd_iommu:perf_iommu_add\n"); + event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + /* request an iommu bank/counter */ + retval = get_next_avail_iommu_bnk_cntr(perf_iommu); + if (retval != -ENOSPC) + event->hw.extra_reg.reg = (u16)retval; + else + return retval; + + if (flags & PERF_EF_START) + perf_iommu_start(event, PERF_EF_RELOAD); + + return 0; +} + +static void perf_iommu_del(struct perf_event *event, int flags) +{ + struct perf_amd_iommu *perf_iommu = + container_of(event->pmu, struct perf_amd_iommu, pmu); + + pr_debug("perf: amd_iommu:perf_iommu_del\n"); + perf_iommu_stop(event, PERF_EF_UPDATE); + + /* clear the assigned iommu bank/counter */ + clear_avail_iommu_bnk_cntr(perf_iommu, + _GET_BANK(event), + _GET_CNTR(event)); + + perf_event_update_userpage(event); +} + +static __init int _init_events_attrs(struct perf_amd_iommu *perf_iommu) +{ + struct attribute **attrs; + struct attribute_group *attr_group; + int i = 0, j; + + while (amd_iommu_v2_event_descs[i].attr.attr.name) + i++; + + attr_group = kzalloc(sizeof(struct attribute *) + * (i + 1) + sizeof(*attr_group), GFP_KERNEL); + if (!attr_group) + return -ENOMEM; + + attrs = (struct attribute **)(attr_group + 1); + for (j = 0; j < i; j++) + attrs[j] = &amd_iommu_v2_event_descs[j].attr.attr; + + attr_group->name = "events"; + attr_group->attrs = attrs; + perf_iommu->events_group = attr_group; + + return 0; +} + +static __init void amd_iommu_pc_exit(void) +{ + if (__perf_iommu.events_group != NULL) { + kfree(__perf_iommu.events_group); + __perf_iommu.events_group = NULL; + } +} + +static __init int _init_perf_amd_iommu( + struct perf_amd_iommu *perf_iommu, char *name) +{ + int ret; + + raw_spin_lock_init(&perf_iommu->lock); + + /* Init format attributes */ + perf_iommu->format_group = &amd_iommu_format_group; + + /* Init cpumask attributes to only core 0 */ + cpumask_set_cpu(0, &iommu_cpumask); + perf_iommu->cpumask_group = &amd_iommu_cpumask_group; + + /* Init events attributes */ + if (_init_events_attrs(perf_iommu) != 0) + pr_err("perf: amd_iommu: Only support raw events.\n"); + + /* Init null attributes */ + perf_iommu->null_group = NULL; + perf_iommu->pmu.attr_groups = perf_iommu->attr_groups; + + ret = perf_pmu_register(&perf_iommu->pmu, name, -1); + if (ret) { + pr_err("perf: amd_iommu: Failed to initialized.\n"); + amd_iommu_pc_exit(); + } else { + pr_info("perf: amd_iommu: Detected. (%d banks, %d counters/bank)\n", + amd_iommu_pc_get_max_banks(IOMMU_BASE_DEVID), + amd_iommu_pc_get_max_counters(IOMMU_BASE_DEVID)); + } + + return ret; +} + +static struct perf_amd_iommu __perf_iommu = { + .pmu = { + .event_init = perf_iommu_event_init, + .add = perf_iommu_add, + .del = perf_iommu_del, + .start = perf_iommu_start, + .stop = perf_iommu_stop, + .read = perf_iommu_read, + }, + .max_banks = 0x00, + .max_counters = 0x00, + .cntr_assign_mask = 0ULL, + .format_group = NULL, + .cpumask_group = NULL, + .events_group = NULL, + .null_group = NULL, +}; + +static __init int amd_iommu_pc_init(void) +{ + /* Make sure the IOMMU PC resource is available */ + if (!amd_iommu_pc_supported()) { + pr_err("perf: amd_iommu PMU not installed. No support!\n"); + return -ENODEV; + } + + _init_perf_amd_iommu(&__perf_iommu, "amd_iommu"); + + return 0; +} + +device_initcall(amd_iommu_pc_init); diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.h b/arch/x86/kernel/cpu/perf_event_amd_iommu.h new file mode 100644 index 000000000000..845d173278e3 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.h @@ -0,0 +1,40 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Steven Kinney <Steven.Kinney@amd.com> + * Author: Suravee Suthikulpanit <Suraveee.Suthikulpanit@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _PERF_EVENT_AMD_IOMMU_H_ +#define _PERF_EVENT_AMD_IOMMU_H_ + +/* iommu pc mmio region register indexes */ +#define IOMMU_PC_COUNTER_REG 0x00 +#define IOMMU_PC_COUNTER_SRC_REG 0x08 +#define IOMMU_PC_PASID_MATCH_REG 0x10 +#define IOMMU_PC_DOMID_MATCH_REG 0x18 +#define IOMMU_PC_DEVID_MATCH_REG 0x20 +#define IOMMU_PC_COUNTER_REPORT_REG 0x28 + +/* maximun specified bank/counters */ +#define PC_MAX_SPEC_BNKS 64 +#define PC_MAX_SPEC_CNTRS 16 + +/* iommu pc reg masks*/ +#define IOMMU_BASE_DEVID 0x0000 + +/* amd_iommu_init.c external support functions */ +extern bool amd_iommu_pc_supported(void); + +extern u8 amd_iommu_pc_get_max_banks(u16 devid); + +extern u8 amd_iommu_pc_get_max_counters(u16 devid); + +extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, + u8 fxn, u64 *value, bool is_write); + +#endif /*_PERF_EVENT_AMD_IOMMU_H_*/ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index f60d41ff9a97..fbc9210b45bc 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/export.h> +#include <asm/cpufeature.h> #include <asm/hardirq.h> #include <asm/apic.h> @@ -165,13 +166,13 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; @@ -190,6 +191,22 @@ struct attribute *snb_events_attrs[] = { NULL, }; +static struct event_constraint intel_hsw_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + INTEL_EVENT_CONSTRAINT(0x08a3, 0x4), + /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ + INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4), + /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ + INTEL_EVENT_CONSTRAINT(0x04a3, 0xf), + EVENT_CONSTRAINT_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -872,7 +889,8 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) return true; /* implicit branch sampling to correct PEBS skid */ - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1) + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && + x86_pmu.intel_cap.pebs_format < 2) return true; return false; @@ -1167,15 +1185,11 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) cpuc = &__get_cpu_var(cpu_hw_events); /* - * Some chipsets need to unmask the LVTPC in a particular spot - * inside the nmi handler. As a result, the unmasking was pushed - * into all the nmi handlers. - * - * This handler doesn't seem to have any issues with the unmasking - * so it was left at the top. + * No known reason to not always do late ACK, + * but just in case do it opt-in. */ - apic_write(APIC_LVTPC, APIC_DM_NMI); - + if (!x86_pmu.late_ack) + apic_write(APIC_LVTPC, APIC_DM_NMI); intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); @@ -1188,8 +1202,12 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) again: intel_pmu_ack_status(status); if (++loops > 100) { - WARN_ONCE(1, "perfevents: irq loop stuck!\n"); - perf_event_print_debug(); + static bool warned = false; + if (!warned) { + WARN(1, "perfevents: irq loop stuck!\n"); + perf_event_print_debug(); + warned = true; + } intel_pmu_reset(); goto done; } @@ -1235,6 +1253,13 @@ again: done: intel_pmu_enable_all(0); + /* + * Only unmask the NMI after the overflow counters + * have been reset. This avoids spurious NMIs on + * Haswell CPUs. + */ + if (x86_pmu.late_ack) + apic_write(APIC_LVTPC, APIC_DM_NMI); return handled; } @@ -1425,7 +1450,6 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { if ((event->hw.config & c->cmask) == c->code) { - /* hw.flags zeroed at initialization */ event->hw.flags |= c->flags; return c; } @@ -1473,7 +1497,6 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { - event->hw.flags = 0; intel_put_shared_regs_event_constraints(cpuc, event); } @@ -1646,6 +1669,47 @@ static void core_pmu_enable_all(int added) } } +static int hsw_hw_config(struct perf_event *event) +{ + int ret = intel_pmu_hw_config(event); + + if (ret) + return ret; + if (!boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has(X86_FEATURE_HLE)) + return 0; + event->hw.config |= event->attr.config & (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED); + + /* + * IN_TX/IN_TX-CP filters are not supported by the Haswell PMU with + * PEBS or in ANY thread mode. Since the results are non-sensical forbid + * this combination. + */ + if ((event->hw.config & (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED)) && + ((event->hw.config & ARCH_PERFMON_EVENTSEL_ANY) || + event->attr.precise_ip > 0)) + return -EOPNOTSUPP; + + return 0; +} + +static struct event_constraint counter2_constraint = + EVENT_CONSTRAINT(0, 0x4, 0); + +static struct event_constraint * +hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +{ + struct event_constraint *c = intel_get_event_constraints(cpuc, event); + + /* Handle special quirk on in_tx_checkpointed only in counter 2 */ + if (event->hw.config & HSW_IN_TX_CHECKPOINTED) { + if (c->idxmsk64 & (1U << 2)) + return &counter2_constraint; + return &emptyconstraint; + } + + return c; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -1653,6 +1717,8 @@ PMU_FORMAT_ATTR(pc, "config:19" ); PMU_FORMAT_ATTR(any, "config:21" ); /* v3 + */ PMU_FORMAT_ATTR(inv, "config:23" ); PMU_FORMAT_ATTR(cmask, "config:24-31" ); +PMU_FORMAT_ATTR(in_tx, "config:32"); +PMU_FORMAT_ATTR(in_tx_cp, "config:33"); static struct attribute *intel_arch_formats_attr[] = { &format_attr_event.attr, @@ -1807,6 +1873,8 @@ static struct attribute *intel_arch3_formats_attr[] = { &format_attr_any.attr, &format_attr_inv.attr, &format_attr_cmask.attr, + &format_attr_in_tx.attr, + &format_attr_in_tx_cp.attr, &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ &format_attr_ldlat.attr, /* PEBS load latency */ @@ -1966,6 +2034,15 @@ static __init void intel_nehalem_quirk(void) } } +EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") + +static struct attribute *hsw_events_attrs[] = { + EVENT_PTR(mem_ld_hsw), + EVENT_PTR(mem_st_hsw), + NULL +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -2189,6 +2266,30 @@ __init int intel_pmu_init(void) break; + case 60: /* Haswell Client */ + case 70: + case 71: + case 63: + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_hsw_event_constraints; + x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.extra_regs = intel_snb_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.er_flags |= ERF_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.cpu_events = hsw_events_attrs; + pr_cont("Haswell events, "); + break; + default: switch (x86_pmu.version) { case 1: @@ -2227,7 +2328,7 @@ __init int intel_pmu_init(void) * counter, so do not extend mask to generic counters */ for_each_event_constraint(c, x86_pmu.event_constraints) { - if (c->cmask != X86_RAW_EVENT_MASK + if (c->cmask != FIXED_EVENT_FLAGS || c->idxmsk64 == INTEL_PMC_MSK_FIXED_REF_CYCLES) { continue; } @@ -2237,5 +2338,12 @@ __init int intel_pmu_init(void) } } + /* Support full width counters using alternative MSR range */ + if (x86_pmu.intel_cap.full_width_write) { + x86_pmu.max_period = x86_pmu.cntval_mask; + x86_pmu.perfctr = MSR_IA32_PMC0; + pr_cont("full-width counters, "); + } + return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 60250f687052..3065c57a63c1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -107,6 +107,19 @@ static u64 precise_store_data(u64 status) return val; } +static u64 precise_store_data_hsw(u64 status) +{ + union perf_mem_data_src dse; + + dse.val = 0; + dse.mem_op = PERF_MEM_OP_STORE; + dse.mem_lvl = PERF_MEM_LVL_NA; + if (status & 1) + dse.mem_lvl = PERF_MEM_LVL_L1; + /* Nothing else supported. Sorry. */ + return dse.val; +} + static u64 load_latency_data(u64 status) { union intel_x86_pebs_dse dse; @@ -165,6 +178,22 @@ struct pebs_record_nhm { u64 status, dla, dse, lat; }; +/* + * Same as pebs_record_nhm, with two additional fields. + */ +struct pebs_record_hsw { + struct pebs_record_nhm nhm; + /* + * Real IP of the event. In the Intel documentation this + * is called eventingrip. + */ + u64 real_ip; + /* + * TSX tuning information field: abort cycles and abort flags. + */ + u64 tsx_tuning; +}; + void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -548,6 +577,42 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_hsw_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ + INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ + INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */ + INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */ + INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */ + INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.* */ + /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), + /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), + INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), + INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */ + INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */ + INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */ + /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */ + INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf), + /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */ + INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf), + /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */ + INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf), + /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */ + INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf), + INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */ + INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */ + + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -588,6 +653,12 @@ void intel_pmu_pebs_disable(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); + + if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_LDLAT) + cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32)); + else if (event->hw.constraint->flags & PERF_X86_EVENT_PEBS_ST) + cpuc->pebs_enabled &= ~(1ULL << 63); + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -697,6 +768,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, */ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct pebs_record_nhm *pebs = __pebs; + struct pebs_record_hsw *pebs_hsw = __pebs; struct perf_sample_data data; struct pt_regs regs; u64 sample_type; @@ -706,7 +778,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event, return; fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; - fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST; + fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST | + PERF_X86_EVENT_PEBS_ST_HSW); perf_sample_data_init(&data, 0, event->hw.last_period); @@ -717,9 +790,6 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * if PEBS-LL or PreciseStore */ if (fll || fst) { - if (sample_type & PERF_SAMPLE_ADDR) - data.addr = pebs->dla; - /* * Use latency for weight (only avail with PEBS-LL) */ @@ -732,6 +802,9 @@ static void __intel_pmu_pebs_event(struct perf_event *event, if (sample_type & PERF_SAMPLE_DATA_SRC) { if (fll) data.data_src.val = load_latency_data(pebs->dse); + else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + data.data_src.val = + precise_store_data_hsw(pebs->dse); else data.data_src.val = precise_store_data(pebs->dse); } @@ -753,11 +826,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, regs.bp = pebs->bp; regs.sp = pebs->sp; - if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { + regs.ip = pebs_hsw->real_ip; + regs.flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) regs.flags |= PERF_EFLAGS_EXACT; else regs.flags &= ~PERF_EFLAGS_EXACT; + if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && + x86_pmu.intel_cap.pebs_format >= 1) + data.addr = pebs->dla; + if (has_branch_stack(event)) data.br_stack = &cpuc->lbr_stack; @@ -806,35 +886,22 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) __intel_pmu_pebs_event(event, iregs, at); } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at, + void *top) { struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct pebs_record_nhm *at, *top; struct perf_event *event = NULL; u64 status = 0; - int bit, n; - - if (!x86_pmu.pebs_active) - return; - - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; - top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + int bit; ds->pebs_index = ds->pebs_buffer_base; - n = top - at; - if (n <= 0) - return; - - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > x86_pmu.max_pebs_events, "Unexpected number of pebs records %d\n", n); + for (; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; - for ( ; at < top; at++) { - for_each_set_bit(bit, (unsigned long *)&at->status, x86_pmu.max_pebs_events) { + for_each_set_bit(bit, (unsigned long *)&p->status, + x86_pmu.max_pebs_events) { event = cpuc->events[bit]; if (!test_bit(bit, cpuc->active_mask)) continue; @@ -857,6 +924,61 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } } +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct pebs_record_nhm *at, *top; + int n; + + if (!x86_pmu.pebs_active) + return; + + at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; + + ds->pebs_index = ds->pebs_buffer_base; + + n = top - at; + if (n <= 0) + return; + + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ONCE(n > x86_pmu.max_pebs_events, + "Unexpected number of pebs records %d\n", n); + + return __intel_pmu_drain_pebs_nhm(iregs, at, top); +} + +static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs) +{ + struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct debug_store *ds = cpuc->ds; + struct pebs_record_hsw *at, *top; + int n; + + if (!x86_pmu.pebs_active) + return; + + at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base; + top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index; + + n = top - at; + if (n <= 0) + return; + /* + * Should not happen, we program the threshold at 1 and do not + * set a reset value. + */ + WARN_ONCE(n > x86_pmu.max_pebs_events, + "Unexpected number of pebs records %d\n", n); + + return __intel_pmu_drain_pebs_nhm(iregs, at, top); +} + /* * BTS, PEBS probe and setup */ @@ -888,6 +1010,12 @@ void intel_ds_init(void) x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; + case 2: + pr_cont("PEBS fmt2%c, ", pebs_type); + x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw; + break; + default: printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d978353c939b..d5be06a5005e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -12,6 +12,16 @@ enum { LBR_FORMAT_LIP = 0x01, LBR_FORMAT_EIP = 0x02, LBR_FORMAT_EIP_FLAGS = 0x03, + LBR_FORMAT_EIP_FLAGS2 = 0x04, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_EIP_FLAGS2, +}; + +static enum { + LBR_EIP_FLAGS = 1, + LBR_TSX = 2, +} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { + [LBR_FORMAT_EIP_FLAGS] = LBR_EIP_FLAGS, + [LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX, }; /* @@ -56,6 +66,8 @@ enum { LBR_FAR) #define LBR_FROM_FLAG_MISPRED (1ULL << 63) +#define LBR_FROM_FLAG_IN_TX (1ULL << 62) +#define LBR_FROM_FLAG_ABORT (1ULL << 61) #define for_each_branch_sample_type(x) \ for ((x) = PERF_SAMPLE_BRANCH_USER; \ @@ -81,9 +93,13 @@ enum { X86_BR_JMP = 1 << 9, /* jump */ X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ X86_BR_IND_CALL = 1 << 11,/* indirect calls */ + X86_BR_ABORT = 1 << 12,/* transaction abort */ + X86_BR_IN_TX = 1 << 13,/* in transaction */ + X86_BR_NO_TX = 1 << 14,/* not in transaction */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) +#define X86_BR_ANYTX (X86_BR_NO_TX | X86_BR_IN_TX) #define X86_BR_ANY \ (X86_BR_CALL |\ @@ -95,6 +111,7 @@ enum { X86_BR_JCC |\ X86_BR_JMP |\ X86_BR_IRQ |\ + X86_BR_ABORT |\ X86_BR_IND_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -270,21 +287,31 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < x86_pmu.lbr_nr; i++) { unsigned long lbr_idx = (tos - i) & mask; - u64 from, to, mis = 0, pred = 0; + u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; + int skip = 0; + int lbr_flags = lbr_desc[lbr_format]; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_EIP_FLAGS) { + if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; - from = (u64)((((s64)from) << 1) >> 1); + skip = 1; + } + if (lbr_flags & LBR_TSX) { + in_tx = !!(from & LBR_FROM_FLAG_IN_TX); + abort = !!(from & LBR_FROM_FLAG_ABORT); + skip = 3; } + from = (u64)((((s64)from) << skip) >> skip); cpuc->lbr_entries[i].from = from; cpuc->lbr_entries[i].to = to; cpuc->lbr_entries[i].mispred = mis; cpuc->lbr_entries[i].predicted = pred; + cpuc->lbr_entries[i].in_tx = in_tx; + cpuc->lbr_entries[i].abort = abort; cpuc->lbr_entries[i].reserved = 0; } cpuc->lbr_stack.nr = i; @@ -310,7 +337,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -318,11 +345,8 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_USER) mask |= X86_BR_USER; - if (br_type & PERF_SAMPLE_BRANCH_KERNEL) { - if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) - return -EACCES; + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) mask |= X86_BR_KERNEL; - } /* we ignore BRANCH_HV here */ @@ -337,13 +361,21 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_IND_CALL) mask |= X86_BR_IND_CALL; + + if (br_type & PERF_SAMPLE_BRANCH_ABORT_TX) + mask |= X86_BR_ABORT; + + if (br_type & PERF_SAMPLE_BRANCH_IN_TX) + mask |= X86_BR_IN_TX; + + if (br_type & PERF_SAMPLE_BRANCH_NO_TX) + mask |= X86_BR_NO_TX; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; - - return 0; } /* @@ -391,9 +423,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - ret = intel_pmu_setup_sw_lbr_filter(event); - if (ret) - return ret; + intel_pmu_setup_sw_lbr_filter(event); /* * setup HW LBR filter, if any @@ -415,7 +445,7 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) * decoded (e.g., text page not present), then X86_BR_NONE is * returned. */ -static int branch_type(unsigned long from, unsigned long to) +static int branch_type(unsigned long from, unsigned long to, int abort) { struct insn insn; void *addr; @@ -435,6 +465,9 @@ static int branch_type(unsigned long from, unsigned long to) if (from == 0 || to == 0) return X86_BR_NONE; + if (abort) + return X86_BR_ABORT | to_plm; + if (from_plm == X86_BR_USER) { /* * can happen if measuring at the user level only @@ -581,7 +614,13 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) from = cpuc->lbr_entries[i].from; to = cpuc->lbr_entries[i].to; - type = branch_type(from, to); + type = branch_type(from, to, cpuc->lbr_entries[i].abort); + if (type != X86_BR_NONE && (br_sel & X86_BR_ANYTX)) { + if (cpuc->lbr_entries[i].in_tx) + type |= X86_BR_IN_TX; + else + type |= X86_BR_NO_TX; + } /* if type does not correspond, then discard */ if (type == X86_BR_NONE || (br_sel & type) != type) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 52441a2af538..9dd99751ccf9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -536,7 +536,7 @@ __snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *eve if (!uncore_box_is_fake(box)) reg1->alloc |= alloc; - return 0; + return NULL; fail: for (; i >= 0; i--) { if (alloc & (0x1 << i)) @@ -644,7 +644,7 @@ snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) (!uncore_box_is_fake(box) && reg1->alloc)) return NULL; again: - mask = 0xff << (idx * 8); + mask = 0xffULL << (idx * 8); raw_spin_lock_irqsave(&er->lock, flags); if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || !((config1 ^ er->config) & mask)) { @@ -1923,7 +1923,7 @@ static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modif { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); + u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); u64 config = reg1->config; /* get the non-shared control bits and shift them */ @@ -2723,15 +2723,16 @@ static void uncore_put_event_constraint(struct intel_uncore_box *box, struct per static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n) { unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)]; - struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX]; + struct event_constraint *c; int i, wmin, wmax, ret = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, UNCORE_PMC_IDX_MAX); for (i = 0, wmin = UNCORE_PMC_IDX_MAX, wmax = 0; i < n; i++) { + hwc = &box->event_list[i]->hw; c = uncore_get_event_constraint(box, box->event_list[i]); - constraints[i] = c; + hwc->constraint = c; wmin = min(wmin, c->weight); wmax = max(wmax, c->weight); } @@ -2739,7 +2740,7 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int /* fastpath, try to reuse previous register */ for (i = 0; i < n; i++) { hwc = &box->event_list[i]->hw; - c = constraints[i]; + c = hwc->constraint; /* never assigned */ if (hwc->idx == -1) @@ -2759,7 +2760,8 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int } /* slow path */ if (i != n) - ret = perf_assign_events(constraints, n, wmin, wmax, assign); + ret = perf_assign_events(box->event_list, n, + wmin, wmax, assign); if (!assign || ret) { for (i = 0; i < n; i++) diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index f9528917f6e8..47b3d00c9d89 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -337,10 +337,10 @@ NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK) #define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23)) -#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (11 + 3 * (n))) +#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n))) #define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24)) -#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7 << (12 + 3 * (n))) +#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n))) /* * use the 9~13 bits to select event If the 7th bit is not set, diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault.c index 155a13f33ed8..5d3fe8d36e4a 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault.c @@ -9,6 +9,8 @@ #include <asm/processor.h> #include <asm/desc.h> +#ifdef CONFIG_X86_32 + #define DOUBLEFAULT_STACKSIZE (1024) static unsigned long doublefault_stack[DOUBLEFAULT_STACKSIZE]; #define STACK_START (unsigned long)(doublefault_stack+DOUBLEFAULT_STACKSIZE) @@ -67,3 +69,16 @@ struct tss_struct doublefault_tss __cacheline_aligned = { .__cr3 = __pa_nodebug(swapper_pg_dir), } }; + +/* dummy for do_double_fault() call */ +void df_debug(struct pt_regs *regs, long error_code) {} + +#else /* !CONFIG_X86_32 */ + +void df_debug(struct pt_regs *regs, long error_code) +{ + pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); + show_regs(regs); + panic("Machine halted."); +} +#endif diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 727208941030..5fe1fb2d1490 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -365,7 +365,7 @@ ENDPROC(native_usergs_sysret64) /*CFI_REL_OFFSET ss,0*/ pushq_cfi %rax /* rsp */ CFI_REL_OFFSET rsp,0 - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */ + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */ /*CFI_REL_OFFSET rflags,0*/ pushq_cfi $__KERNEL_CS /* cs */ /*CFI_REL_OFFSET cs,0*/ diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index dab95a85f7f8..55b67614ed94 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -34,7 +34,7 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt = 2; -pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 08f7e8039099..321d65ebaffe 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -115,8 +115,10 @@ startup_64: movq %rdi, %rax shrq $PUD_SHIFT, %rax andl $(PTRS_PER_PUD-1), %eax - movq %rdx, (4096+0)(%rbx,%rax,8) - movq %rdx, (4096+8)(%rbx,%rax,8) + movq %rdx, 4096(%rbx,%rax,8) + incl %eax + andl $(PTRS_PER_PUD-1), %eax + movq %rdx, 4096(%rbx,%rax,8) addq $8192, %rbx movq %rdi, %rax diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 245a71db401a..cb339097b9ea 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -22,23 +22,19 @@ /* * Were we in an interrupt that interrupted kernel mode? * - * For now, with eagerfpu we will return interrupted kernel FPU - * state as not-idle. TBD: Ideally we can change the return value - * to something like __thread_has_fpu(current). But we need to - * be careful of doing __thread_clear_has_fpu() before saving - * the FPU etc for supporting nested uses etc. For now, take - * the simple route! - * * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that * pair does nothing at all: the thread must not have fpu (so * that we don't try to save the FPU state), and TS must * be set (so that the clts/stts pair does nothing that is * visible in the interrupted kernel thread). + * + * Except for the eagerfpu case when we return 1 unless we've already + * been eager and saved the state in kernel_fpu_begin(). */ static inline bool interrupted_kernel_fpu_idle(void) { if (use_eager_fpu()) - return 0; + return __thread_has_fpu(current); return !__thread_has_fpu(current) && (read_cr0() & X86_CR0_TS); @@ -78,8 +74,8 @@ void __kernel_fpu_begin(void) struct task_struct *me = current; if (__thread_has_fpu(me)) { - __save_init_fpu(me); __thread_clear_has_fpu(me); + __save_init_fpu(me); /* We do 'stts()' in __kernel_fpu_end() */ } else if (!use_eager_fpu()) { this_cpu_write(fpu_owner_task, NULL); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 9895a9a41380..211bce445522 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -365,10 +365,14 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) return insn.length; } -static void __kprobes arch_copy_kprobe(struct kprobe *p) +static int __kprobes arch_copy_kprobe(struct kprobe *p) { + int ret; + /* Copy an instruction with recovering if other optprobe modifies it.*/ - __copy_instruction(p->ainsn.insn, p->addr); + ret = __copy_instruction(p->ainsn.insn, p->addr); + if (!ret) + return -EINVAL; /* * __copy_instruction can modify the displacement of the instruction, @@ -384,6 +388,8 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) /* Also, displacement change doesn't affect the first byte */ p->opcode = p->ainsn.insn[0]; + + return 0; } int __kprobes arch_prepare_kprobe(struct kprobe *p) @@ -397,8 +403,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) p->ainsn.insn = get_insn_slot(); if (!p->ainsn.insn) return -ENOMEM; - arch_copy_kprobe(p); - return 0; + + return arch_copy_kprobe(p); } void __kprobes arch_arm_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d2c381280e3c..3dd37ebd591b 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -242,6 +242,7 @@ void __init kvmclock_init(void) if (!mem) return; hv_clock = __va(mem); + memset(hv_clock, 0, size); if (kvm_register_clock("boot clock")) { hv_clock = NULL; diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index d893e8ed8ac9..2e9e12871c2b 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -487,6 +487,7 @@ static inline void show_saved_mc(void) #endif #if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +static DEFINE_MUTEX(x86_cpu_microcode_mutex); /* * Save this mc into mc_saved_data. So it will be loaded early when a CPU is * hot added or resumes. @@ -507,7 +508,7 @@ int save_mc_for_early(u8 *mc) * Hold hotplug lock so mc_saved_data is not accessed by a CPU in * hotplug. */ - cpu_hotplug_driver_lock(); + mutex_lock(&x86_cpu_microcode_mutex); mc_saved_count_init = mc_saved_data.mc_saved_count; mc_saved_count = mc_saved_data.mc_saved_count; @@ -544,7 +545,7 @@ int save_mc_for_early(u8 *mc) } out: - cpu_hotplug_driver_unlock(); + mutex_unlock(&x86_cpu_microcode_mutex); return ret; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 60308053fdb2..0920212e6159 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -14,6 +14,7 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> #include <linux/nmi.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/hardirq.h> #include <linux/slab.h> @@ -29,6 +30,9 @@ #include <asm/nmi.h> #include <asm/x86_init.h> +#define CREATE_TRACE_POINTS +#include <trace/events/nmi.h> + struct nmi_desc { spinlock_t lock; struct list_head head; @@ -82,6 +86,15 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic); #define nmi_to_desc(type) (&nmi_desc[type]) +static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC; +static int __init nmi_warning_debugfs(void) +{ + debugfs_create_u64("nmi_longest_ns", 0644, + arch_debugfs_dir, &nmi_longest_ns); + return 0; +} +fs_initcall(nmi_warning_debugfs); + static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); @@ -96,8 +109,27 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 * can be latched at any given time. Walk the whole list * to handle those situations. */ - list_for_each_entry_rcu(a, &desc->head, list) - handled += a->handler(type, regs); + list_for_each_entry_rcu(a, &desc->head, list) { + u64 before, delta, whole_msecs; + int decimal_msecs, thishandled; + + before = local_clock(); + thishandled = a->handler(type, regs); + handled += thishandled; + delta = local_clock() - before; + trace_nmi_handler(a->handler, (int)delta, thishandled); + + if (delta < nmi_longest_ns) + continue; + + nmi_longest_ns = delta; + whole_msecs = do_div(delta, (1000 * 1000)); + decimal_msecs = do_div(delta, 1000) % 1000; + printk_ratelimited(KERN_INFO + "INFO: NMI handler (%ps) took too long to run: " + "%lld.%03d msecs\n", a->handler, whole_msecs, + decimal_msecs); + } rcu_read_unlock(); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 607af0d4d5ef..81a5f5e8f142 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -277,18 +277,6 @@ void exit_idle(void) } #endif -void arch_cpu_idle_prepare(void) -{ - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. CPU0 already has it initialized but no harm in - * doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); -} - void arch_cpu_idle_enter(void) { local_touch_nmi(); @@ -312,6 +300,8 @@ void arch_cpu_idle(void) { if (cpuidle_idle_call()) x86_idle(); + else + local_irq_enable(); } /* @@ -368,9 +358,6 @@ void amd_e400_remove_cpu(int cpu) */ static void amd_e400_idle(void) { - if (need_resched()) - return; - if (!amd_e400_c1e_detected) { u32 lo, hi; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7305f7dfc7ab..f8adefca71dc 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -110,11 +110,16 @@ void __show_regs(struct pt_regs *regs, int all) get_debugreg(d1, 1); get_debugreg(d2, 2); get_debugreg(d3, 3); - printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", - d0, d1, d2, d3); - get_debugreg(d6, 6); get_debugreg(d7, 7); + + /* Only print out debug registers if they are in their non-default state. */ + if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && + (d6 == DR6_RESERVED) && (d7 == 0x400)) + return; + + printk(KERN_DEFAULT "DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", + d0, d1, d2, d3); printk(KERN_DEFAULT "DR6: %08lx DR7: %08lx\n", d6, d7); } @@ -147,7 +152,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 355ae06dbf94..05646bab4ca6 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -105,11 +105,18 @@ void __show_regs(struct pt_regs *regs, int all) get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); - printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); get_debugreg(d3, 3); get_debugreg(d6, 6); get_debugreg(d7, 7); + + /* Only print out debug registers if they are in their non-default state. */ + if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && + (d6 == DR6_RESERVED) && (d7 == 0x400)) + return; + + printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + } void release_thread(struct task_struct *dead_task) @@ -176,7 +183,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; return 0; } *childregs = *current_pt_regs(); diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 36818f8ec2be..e13f8e7c22a6 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -186,7 +186,7 @@ identity_mapped: movl CP_PA_PGD(%ebx), %eax movl %eax, %cr3 movl %cr0, %eax - orl $(1<<31), %eax + orl $X86_CR0_PG, %eax movl %eax, %cr0 lea PAGE_SIZE(%edi), %esp movl %edi, %eax diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 7a6f3b3be3cf..3fd2c693e475 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -151,21 +151,21 @@ identity_mapped: testq %r11, %r11 jnz 1f - xorq %rax, %rax - xorq %rbx, %rbx - xorq %rcx, %rcx - xorq %rdx, %rdx - xorq %rsi, %rsi - xorq %rdi, %rdi - xorq %rbp, %rbp - xorq %r8, %r8 - xorq %r9, %r9 - xorq %r10, %r9 - xorq %r11, %r11 - xorq %r12, %r12 - xorq %r13, %r13 - xorq %r14, %r14 - xorq %r15, %r15 + xorl %eax, %eax + xorl %ebx, %ebx + xorl %ecx, %ecx + xorl %edx, %edx + xorl %esi, %esi + xorl %edi, %edi + xorl %ebp, %ebp + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d + xorl %r11d, %r11d + xorl %r12d, %r12d + xorl %r13d, %r13d + xorl %r14d, %r14d + xorl %r15d, %r15d ret @@ -212,8 +212,8 @@ virtual_mapped: /* Do the copies */ swap_pages: movq %rdi, %rcx /* Put the page_list in %rcx */ - xorq %rdi, %rdi - xorq %rsi, %rsi + xorl %edi, %edi + xorl %esi, %esi jmp 1f 0: /* top, read another word for the indirection page */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 69562992e457..cf913587d4dd 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -43,12 +43,6 @@ #include <asm/sigframe.h> -#ifdef CONFIG_X86_32 -# define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF) -#else -# define FIX_EFLAGS __FIX_EFLAGS -#endif - #define COPY(x) do { \ get_user_ex(regs->x, &sc->x); \ } while (0) @@ -668,15 +662,17 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) if (!failed) { /* * Clear the direction flag as per the ABI for function entry. - */ - regs->flags &= ~X86_EFLAGS_DF; - /* + * + * Clear RF when entering the signal handler, because + * it might disable possible debug exception from the + * signal handler. + * * Clear TF when entering the signal handler, but * notify any tracer that was single-stepping it. * The tracer may want to single-step inside the * handler too. */ - regs->flags &= ~X86_EFLAGS_TF; + regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9c73b51817e4..bfd348e99369 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -372,15 +372,15 @@ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) void __cpuinit set_cpu_sibling_map(int cpu) { - bool has_mc = boot_cpu_data.x86_max_cores > 1; bool has_smt = smp_num_siblings > 1; + bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i; cpumask_set_cpu(cpu, cpu_sibling_setup_mask); - if (!has_smt && !has_mc) { + if (!has_mp) { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(cpu)); @@ -394,7 +394,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) if ((i == cpu) || (has_smt && match_smt(c, o))) link_mask(sibling, cpu, i); - if ((i == cpu) || (has_mc && match_llc(c, o))) + if ((i == cpu) || (has_mp && match_llc(c, o))) link_mask(llc_shared, cpu, i); } @@ -406,7 +406,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); - if ((i == cpu) || (has_mc && match_mc(c, o))) { + if ((i == cpu) || (has_mp && match_mc(c, o))) { link_mask(core, cpu, i); /* diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index f84fe00fad48..3ff42d2f046d 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -31,6 +31,7 @@ #include <linux/pfn.h> #include <linux/mm.h> #include <linux/tboot.h> +#include <linux/debugfs.h> #include <asm/realmode.h> #include <asm/processor.h> @@ -338,6 +339,73 @@ static struct notifier_block tboot_cpu_notifier __cpuinitdata = .notifier_call = tboot_cpu_callback, }; +#ifdef CONFIG_DEBUG_FS + +#define TBOOT_LOG_UUID { 0x26, 0x25, 0x19, 0xc0, 0x30, 0x6b, 0xb4, 0x4d, \ + 0x4c, 0x84, 0xa3, 0xe9, 0x53, 0xb8, 0x81, 0x74 } + +#define TBOOT_SERIAL_LOG_ADDR 0x60000 +#define TBOOT_SERIAL_LOG_SIZE 0x08000 +#define LOG_MAX_SIZE_OFF 16 +#define LOG_BUF_OFF 24 + +static uint8_t tboot_log_uuid[16] = TBOOT_LOG_UUID; + +static ssize_t tboot_log_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) +{ + void __iomem *log_base; + u8 log_uuid[16]; + u32 max_size; + void *kbuf; + int ret = -EFAULT; + + log_base = ioremap_nocache(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); + if (!log_base) + return ret; + + memcpy_fromio(log_uuid, log_base, sizeof(log_uuid)); + if (memcmp(&tboot_log_uuid, log_uuid, sizeof(log_uuid))) + goto err_iounmap; + + max_size = readl(log_base + LOG_MAX_SIZE_OFF); + if (*ppos >= max_size) { + ret = 0; + goto err_iounmap; + } + + if (*ppos + count > max_size) + count = max_size - *ppos; + + kbuf = kmalloc(count, GFP_KERNEL); + if (!kbuf) { + ret = -ENOMEM; + goto err_iounmap; + } + + memcpy_fromio(kbuf, log_base + LOG_BUF_OFF + *ppos, count); + if (copy_to_user(user_buf, kbuf, count)) + goto err_kfree; + + *ppos += count; + + ret = count; + +err_kfree: + kfree(kbuf); + +err_iounmap: + iounmap(log_base); + + return ret; +} + +static const struct file_operations tboot_log_fops = { + .read = tboot_log_read, + .llseek = default_llseek, +}; + +#endif /* CONFIG_DEBUG_FS */ + static __init int tboot_late_init(void) { if (!tboot_enabled()) @@ -348,6 +416,11 @@ static __init int tboot_late_init(void) atomic_set(&ap_wfs_count, 0); register_hotcpu_notifier(&tboot_cpu_notifier); +#ifdef CONFIG_DEBUG_FS + debugfs_create_file("tboot_log", S_IRUSR, + arch_debugfs_dir, NULL, &tboot_log_fops); +#endif + acpi_os_set_prepare_sleep(&tboot_sleep); return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 772e2a846dec..ee3d8e510504 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -254,6 +254,9 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_DF; +#ifdef CONFIG_DOUBLEFAULT + df_debug(regs, error_code); +#endif /* * This is always a kernel trap and never fixable (and thus must * never return). @@ -437,7 +440,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; - if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code, + if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, SIGTRAP) == NOTIFY_STOP) goto exit; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 8db0010ed150..5953dcea752d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1240,9 +1240,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_seg = VCPU_SREG_DS; if (ctxt->modrm_mod == 3) { + int highbyte_regs = ctxt->rex_prefix == 0; + op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; - op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp); + op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, + highbyte_regs && (ctxt->d & ByteOp)); if (ctxt->d & Sse) { op->type = OP_XMM; op->bytes = 16; @@ -3997,7 +4000,8 @@ static const struct opcode twobyte_table[256] = { DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM), N, N, /* 0x10 - 0x1F */ - N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N, + N, N, N, N, N, N, N, N, + D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM), /* 0x20 - 0x2F */ DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), @@ -4836,6 +4840,7 @@ twobyte_insn: case 0x08: /* invd */ case 0x0d: /* GrpP (prefetch) */ case 0x18: /* Grp16 (prefetch/nop) */ + case 0x1f: /* nop */ break; case 0x20: /* mov cr, reg */ ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e1adbb4aca75..0eee2c8b64d1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1861,11 +1861,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; unsigned int sipi_vector; + unsigned long pe; - if (!kvm_vcpu_has_lapic(vcpu)) + if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) return; - if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) { + pe = xchg(&apic->pending_events, 0); + + if (test_bit(KVM_APIC_INIT, &pe)) { kvm_lapic_reset(vcpu); kvm_vcpu_reset(vcpu); if (kvm_vcpu_is_bsp(apic->vcpu)) @@ -1873,7 +1876,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) else vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED; } - if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) && + if (test_bit(KVM_APIC_SIPI, &pe) && vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { /* evaluate pending_events before reading the vector */ smp_rmb(); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 260a91939555..b30f5a54a2ab 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7942,7 +7942,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip); - vmx_set_rflags(vcpu, X86_EFLAGS_BIT1); + vmx_set_rflags(vcpu, X86_EFLAGS_FIXED); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't * actually changed, because it depends on the current state of diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 094b5d96ab14..292e6ca89f42 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -582,8 +582,6 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if (index != XCR_XFEATURE_ENABLED_MASK) return 1; xcr0 = xcr; - if (kvm_x86_ops->get_cpl(vcpu) != 0) - return 1; if (!(xcr0 & XSTATE_FP)) return 1; if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) @@ -597,7 +595,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (__kvm_set_xcr(vcpu, index, xcr)) { + if (kvm_x86_ops->get_cpl(vcpu) != 0 || + __kvm_set_xcr(vcpu, index, xcr)) { kvm_inject_gp(vcpu, 0); return 1; } @@ -619,7 +618,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP)) return 1; - if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_RDWRGSFS)) + if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE)) return 1; if (is_long_mode(vcpu)) { diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fdc5dca14fb3..1f34e9219775 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -277,6 +277,9 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, end_pfn = limit_pfn; nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0); + if (!after_bootmem) + adjust_range_page_size_mask(mr, nr_range); + /* try to merge same page size and continuous */ for (i = 0; nr_range > 1 && i < nr_range - 1; i++) { unsigned long old_start; @@ -291,9 +294,6 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, nr_range--; } - if (!after_bootmem) - adjust_range_page_size_mask(mr, nr_range); - for (i = 0; i < nr_range; i++) printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, @@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, } /* - * would have hole in the middle or ends, and only ram parts will be mapped. + * We need to iterate through the E820 memory map and create direct mappings + * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply + * create direct mappings for all pfns from [0 to max_low_pfn) and + * [4GB to max_pfn) because of possible memory holes in high addresses + * that cannot be marked as UC by fixed/variable range MTRRs. + * Depending on the alignment of E820 ranges, this may possibly result + * in using smaller size (i.e. 4K instead of 2M or 1G) page tables. + * + * init_mem_mapping() calls init_range_memory_mapping() with big range. + * That range would have hole in the middle or ends, and only ram parts + * will be mapped in init_range_memory_mapping(). */ static unsigned long __init init_range_memory_mapping( unsigned long r_start, @@ -419,6 +429,13 @@ void __init init_mem_mapping(void) max_pfn_mapped = 0; /* will get exact value next */ min_pfn_mapped = real_end >> PAGE_SHIFT; last_start = start = real_end; + + /* + * We start from the top (end of memory) and go to the bottom. + * The memblock_find_in_range() gets us a block of RAM from the + * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages + * for page table. + */ while (last_start > ISA_END_ADDRESS) { if (last_start > step_size) { start = round_down(last_start - 1, step_size); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 305c68b8d538..981c2dbd72cc 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -628,7 +628,9 @@ int pcibios_add_device(struct pci_dev *dev) pa_data = boot_params.hdr.setup_data; while (pa_data) { - data = phys_to_virt(pa_data); + data = ioremap(pa_data, sizeof(*rom)); + if (!data) + return -ENOMEM; if (data->type == SETUP_PCI) { rom = (struct pci_setup_rom *)data; @@ -645,6 +647,7 @@ int pcibios_add_device(struct pci_dev *dev) } } pa_data = data->next; + iounmap(data); } return 0; } diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 0e0fabf17342..6eb18c42a28a 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -141,11 +141,6 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn, */ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) { - if (bus == 0 && (devfn == PCI_DEVFN(2, 0) - || devfn == PCI_DEVFN(0, 0) - || devfn == PCI_DEVFN(3, 0))) - return 1; - /* This is a workaround for A0 LNC bug where PCI status register does * not have new CAP bit set. can not be written by SW either. * @@ -155,7 +150,10 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) */ if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE) return 0; - + if (bus == 0 && (devfn == PCI_DEVFN(2, 0) + || devfn == PCI_DEVFN(0, 0) + || devfn == PCI_DEVFN(3, 0))) + return 1; return 0; /* langwell on others */ } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 339e11f9b3a9..b410b71bdcf7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -42,7 +42,6 @@ #include <linux/io.h> #include <linux/reboot.h> #include <linux/bcd.h> -#include <linux/ucs2_string.h> #include <asm/setup.h> #include <asm/efi.h> @@ -54,12 +53,12 @@ #define EFI_DEBUG 1 -/* - * There's some additional metadata associated with each - * variable. Intel's reference implementation is 60 bytes - bump that - * to account for potential alignment constraints - */ -#define VAR_METADATA_SIZE 64 +#define EFI_MIN_RESERVE 5120 + +#define EFI_DUMMY_GUID \ + EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9) + +static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; struct efi __read_mostly efi = { .mps = EFI_INVALID_TABLE_ADDR, @@ -79,13 +78,6 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; -static u64 efi_var_store_size; -static u64 efi_var_remaining_size; -static u64 efi_var_max_var_size; -static u64 boot_used_size; -static u64 boot_var_size; -static u64 active_size; - unsigned long x86_efi_facility; /* @@ -188,53 +180,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - efi_status_t status; - static bool finished = false; - static u64 var_size; - - status = efi_call_virt3(get_next_variable, - name_size, name, vendor); - - if (status == EFI_NOT_FOUND) { - finished = true; - if (var_size < boot_used_size) { - boot_var_size = boot_used_size - var_size; - active_size += boot_var_size; - } else { - printk(KERN_WARNING FW_BUG "efi: Inconsistent initial sizes\n"); - } - } - - if (boot_used_size && !finished) { - unsigned long size; - u32 attr; - efi_status_t s; - void *tmp; - - s = virt_efi_get_variable(name, vendor, &attr, &size, NULL); - - if (s != EFI_BUFFER_TOO_SMALL || !size) - return status; - - tmp = kmalloc(size, GFP_ATOMIC); - - if (!tmp) - return status; - - s = virt_efi_get_variable(name, vendor, &attr, &size, tmp); - - if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) { - var_size += size; - var_size += ucs2_strsize(name, 1024); - active_size += size; - active_size += VAR_METADATA_SIZE; - active_size += ucs2_strsize(name, 1024); - } - - kfree(tmp); - } - - return status; + return efi_call_virt3(get_next_variable, + name_size, name, vendor); } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -243,34 +190,9 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - efi_status_t status; - u32 orig_attr = 0; - unsigned long orig_size = 0; - - status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size, - NULL); - - if (status != EFI_BUFFER_TOO_SMALL) - orig_size = 0; - - status = efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); - - if (status == EFI_SUCCESS) { - if (orig_size) { - active_size -= orig_size; - active_size -= ucs2_strsize(name, 1024); - active_size -= VAR_METADATA_SIZE; - } - if (data_size) { - active_size += data_size; - active_size += ucs2_strsize(name, 1024); - active_size += VAR_METADATA_SIZE; - } - } - - return status; + return efi_call_virt5(set_variable, + name, vendor, attr, + data_size, data); } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -786,9 +708,6 @@ void __init efi_init(void) char vendor[100] = "unknown"; int i = 0; void *tmp; - struct setup_data *data; - struct efi_var_bootdata *efi_var_data; - u64 pa_data; #ifdef CONFIG_X86_32 if (boot_params.efi_info.efi_systab_hi || @@ -806,22 +725,6 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - pa_data = boot_params.hdr.setup_data; - while (pa_data) { - data = early_ioremap(pa_data, sizeof(*efi_var_data)); - if (data->type == SETUP_EFI_VARS) { - efi_var_data = (struct efi_var_bootdata *)data; - - efi_var_store_size = efi_var_data->store_size; - efi_var_remaining_size = efi_var_data->remaining_size; - efi_var_max_var_size = efi_var_data->max_var_size; - } - pa_data = data->next; - early_iounmap(data, sizeof(*efi_var_data)); - } - - boot_used_size = efi_var_store_size - efi_var_remaining_size; - set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); /* @@ -1092,6 +995,13 @@ void __init efi_enter_virtual_mode(void) runtime_code_page_mkexec(); kfree(new_memmap); + + /* clean DUMMY object */ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, NULL); } /* @@ -1143,33 +1053,70 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) efi_status_t status; u64 storage_size, remaining_size, max_size; + if (!(attributes & EFI_VARIABLE_NON_VOLATILE)) + return 0; + status = efi.query_variable_info(attributes, &storage_size, &remaining_size, &max_size); if (status != EFI_SUCCESS) return status; - if (!max_size && remaining_size > size) - printk_once(KERN_ERR FW_BUG "Broken EFI implementation" - " is returning MaxVariableSize=0\n"); /* * Some firmware implementations refuse to boot if there's insufficient * space in the variable store. We account for that by refusing the * write if permitting it would reduce the available space to under - * 50%. However, some firmware won't reclaim variable space until - * after the used (not merely the actively used) space drops below - * a threshold. We can approximate that case with the value calculated - * above. If both the firmware and our calculations indicate that the - * available space would drop below 50%, refuse the write. + * 5KB. This figure was provided by Samsung, so should be safe. */ + if ((remaining_size - size < EFI_MIN_RESERVE) && + !efi_no_storage_paranoia) { + + /* + * Triggering garbage collection may require that the firmware + * generate a real EFI_OUT_OF_RESOURCES error. We can force + * that by attempting to use more space than is available. + */ + unsigned long dummy_size = remaining_size + 1024; + void *dummy = kzalloc(dummy_size, GFP_ATOMIC); + + if (!dummy) + return EFI_OUT_OF_RESOURCES; + + status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + dummy_size, dummy); + + if (status == EFI_SUCCESS) { + /* + * This should have failed, so if it didn't make sure + * that we delete it... + */ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, dummy); + } + + kfree(dummy); - if (!storage_size || size > remaining_size || - (max_size && size > max_size)) - return EFI_OUT_OF_RESOURCES; + /* + * The runtime code may now have triggered a garbage collection + * run, so check the variable info again + */ + status = efi.query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); - if (!efi_no_storage_paranoia && - ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) && - (remaining_size - size < storage_size / 2))) - return EFI_OUT_OF_RESOURCES; + if (status != EFI_SUCCESS) + return status; + + /* + * There still isn't enough room, so return an error + */ + if (remaining_size - size < EFI_MIN_RESERVE) + return EFI_OUT_OF_RESOURCES; + } return EFI_SUCCESS; } diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index 590be1090892..f7bab68a4b83 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -42,9 +42,6 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "^(xen_irq_disable_direct_reloc$|" "xen_save_fl_direct_reloc$|" "VDSO|" -#if ELF_BITS == 64 - "__vvar_page|" -#endif "__crc_)", /* @@ -72,6 +69,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { "__per_cpu_load|" "init_per_cpu__.*|" "__end_rodata_hpage_align|" + "__vvar_page|" #endif "_end)$" }; diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 0faad646f5fd..d6bfb876cfb0 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -372,7 +372,7 @@ subsys_initcall(sysenter_setup); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> -static ctl_table abi_table2[] = { +static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &sysctl_vsyscall32, @@ -383,7 +383,7 @@ static ctl_table abi_table2[] = { {} }; -static ctl_table abi_root_table2[] = { +static struct ctl_table abi_root_table2[] = { { .procname = "abi", .mode = 0555, diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 8ff37995d54e..d99cae8147d1 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/smp.h> #include <linux/irq_work.h> +#include <linux/tick.h> #include <asm/paravirt.h> #include <asm/desc.h> @@ -447,6 +448,13 @@ static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */ play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL); cpu_bringup(); + /* + * commit 4b0c0f294 (tick: Cleanup NOHZ per cpu data on cpu down) + * clears certain data that the cpu_idle loop (which called us + * and that we return from) expects. The only way to get that + * data back is to call: + */ + tick_nohz_idle_enter(); } #else /* !CONFIG_HOTPLUG_CPU */ @@ -576,24 +584,22 @@ void xen_send_IPI_mask_allbutself(const struct cpumask *mask, { unsigned cpu; unsigned int this_cpu = smp_processor_id(); + int xen_vector = xen_map_vector(vector); - if (!(num_online_cpus() > 1)) + if (!(num_online_cpus() > 1) || (xen_vector < 0)) return; for_each_cpu_and(cpu, mask, cpu_online_mask) { if (this_cpu == cpu) continue; - xen_smp_send_call_function_single_ipi(cpu); + xen_send_IPI_one(cpu, xen_vector); } } void xen_send_IPI_allbutself(int vector) { - int xen_vector = xen_map_vector(vector); - - if (xen_vector >= 0) - xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector); + xen_send_IPI_mask_allbutself(cpu_online_mask, vector); } static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id) diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index 8981a76d081a..c7c2d89efd76 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -5,7 +5,6 @@ extern void xen_send_IPI_mask(const struct cpumask *mask, extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask, int vector); extern void xen_send_IPI_allbutself(int vector); -extern void physflat_send_IPI_allbutself(int vector); extern void xen_send_IPI_all(int vector); extern void xen_send_IPI_self(int vector); |