diff options
Diffstat (limited to 'arch/x86')
128 files changed, 6071 insertions, 4947 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore index 7cab8c08e6d1..aff152c87cf4 100644 --- a/arch/x86/.gitignore +++ b/arch/x86/.gitignore @@ -1,4 +1,6 @@ boot/compressed/vmlinux tools/test_get_len tools/insn_sanity +purgatory/kexec-purgatory.c +purgatory/purgatory.ro diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e4b1f431c7ed..f2327e88e07c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -30,7 +30,6 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_INT128 if X86_64 - select ARCH_WANTS_PROT_NUMA_PROT_NONE select HAVE_IDE select HAVE_OPROFILE select HAVE_PCSPKR_PLATFORM @@ -492,6 +491,36 @@ config X86_INTEL_LPSS things like clock tree (common clock framework) and pincontrol which are needed by the LPSS peripheral drivers. +config IOSF_MBI + tristate "Intel SoC IOSF Sideband support for SoC platforms" + depends on PCI + ---help--- + This option enables sideband register access support for Intel SoC + platforms. On these platforms the IOSF sideband is used in lieu of + MSR's for some register accesses, mostly but not limited to thermal + and power. Drivers may query the availability of this device to + determine if they need the sideband in order to work on these + platforms. The sideband is available on the following SoC products. + This list is not meant to be exclusive. + - BayTrail + - Braswell + - Quark + + You should say Y if you are running a kernel on one of these SoC's. + +config IOSF_MBI_DEBUG + bool "Enable IOSF sideband access through debugfs" + depends on IOSF_MBI && DEBUG_FS + ---help--- + Select this option to expose the IOSF sideband access registers (MCR, + MDR, MCRX) through debugfs to write and read register information from + different units on the SoC. This is most useful for obtaining device + state information for debug and analysis. As this is a general access + mechanism, users of this option would have specific knowledge of the + device they want to access. + + If you don't require the option or are in doubt, say N. + config X86_RDC321X bool "RDC R-321x SoC" depends on X86_32 @@ -2455,11 +2484,6 @@ config X86_DMA_REMAP bool depends on STA2X11 -config IOSF_MBI - tristate - default m - depends on PCI - config PMC_ATOM def_bool y depends on PCI diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5692d6ac0f18..920e6160c535 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -50,9 +50,6 @@ ifeq ($(CONFIG_X86_32),y) KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return - # Don't autogenerate MMX or SSE instructions - KBUILD_CFLAGS += -mno-mmx -mno-sse - # Never want PIC in a 32-bit kernel, prevent breakage with GCC built # with nonstandard options KBUILD_CFLAGS += -fno-pic @@ -80,8 +77,7 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 - # Don't autogenerate traditional x87, MMX or SSE instructions - KBUILD_CFLAGS += -mno-mmx -mno-sse + # Don't autogenerate traditional x87 instructions KBUILD_CFLAGS += $(call cc-option,-mno-80387) KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) @@ -168,7 +164,7 @@ KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # prevent gcc from generating any FP code by mistake -KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 7c68808edeb7..bb1376381985 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -194,7 +194,7 @@ static bool mem_avoid_overlap(struct mem_vector *img) while (ptr) { struct mem_vector avoid; - avoid.start = (u64)ptr; + avoid.start = (unsigned long)ptr; avoid.size = sizeof(*ptr) + ptr->len; if (mem_overlaps(img, &avoid)) diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c index 4579eff0ef4d..637097e66a62 100644 --- a/arch/x86/boot/mkcpustr.c +++ b/arch/x86/boot/mkcpustr.c @@ -16,6 +16,7 @@ #include <stdio.h> #include "../include/asm/required-features.h" +#include "../include/asm/disabled-features.h" #include "../include/asm/cpufeature.h" #include "../kernel/cpu/capflags.c" diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index d21ff89207cd..df91466f973d 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -308,11 +308,8 @@ static int load_aout_binary(struct linux_binprm *bprm) (current->mm->start_brk = N_BSSADDR(ex)); retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); - if (retval < 0) { - /* Someone check-me: is this error path enough? */ - send_sig(SIGKILL, current, 0); + if (retval < 0) return retval; - } install_exec_creds(bprm); @@ -324,17 +321,13 @@ static int load_aout_binary(struct linux_binprm *bprm) error = vm_brk(text_addr & PAGE_MASK, map_size); - if (error != (text_addr & PAGE_MASK)) { - send_sig(SIGKILL, current, 0); + if (error != (text_addr & PAGE_MASK)) return error; - } error = read_code(bprm->file, text_addr, 32, ex.a_text + ex.a_data); - if ((signed long)error < 0) { - send_sig(SIGKILL, current, 0); + if ((signed long)error < 0) return error; - } } else { #ifdef WARN_OLD static unsigned long error_time, error_time2; @@ -368,20 +361,16 @@ static int load_aout_binary(struct linux_binprm *bprm) MAP_EXECUTABLE | MAP_32BIT, fd_offset); - if (error != N_TXTADDR(ex)) { - send_sig(SIGKILL, current, 0); + if (error != N_TXTADDR(ex)) return error; - } error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE | MAP_32BIT, fd_offset + ex.a_text); - if (error != N_DATADDR(ex)) { - send_sig(SIGKILL, current, 0); + if (error != N_DATADDR(ex)) return error; - } } beyond_if: set_binfmt(&aout_format); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4299eb05023c..711de084ab57 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target) 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) ASM_CLAC + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + */ + testl $X86_EFLAGS_NT,EFLAGS(%rsp) /* saved EFLAGS match cpu */ + jnz sysenter_fix_flags +sysenter_flags_fixed: + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -184,6 +194,8 @@ sysexit_from_sys_call: TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 + CFI_RESTORE_STATE + #ifdef CONFIG_AUDITSYSCALL .macro auditsys_entry_common movl %esi,%r9d /* 6th arg: 4th syscall arg */ @@ -226,7 +238,6 @@ sysexit_from_sys_call: .endm sysenter_auditsys: - CFI_RESTORE_STATE auditsys_entry_common movl %ebp,%r9d /* reload 6th syscall arg */ jmp sysenter_dispatch @@ -235,6 +246,11 @@ sysexit_audit: auditsys_exit sysexit_from_sys_call #endif +sysenter_fix_flags: + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) + popfq_cfi + jmp sysenter_flags_fixed + sysenter_tracesys: #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index 6dd1c7dd0473..5e5cd123fdfb 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -24,7 +24,7 @@ */ static inline int atomic_read(const atomic_t *v) { - return (*(volatile int *)&(v)->counter); + return ACCESS_ONCE((v)->counter); } /** @@ -219,21 +219,6 @@ static inline short int atomic_inc_short(short int *v) return *v; } -#ifdef CONFIG_X86_64 -/** - * atomic_or_long - OR of two long integers - * @v1: pointer to type unsigned long - * @v2: pointer to type unsigned long - * - * Atomically ORs @v1 and @v2 - * Returns the result of the OR - */ -static inline void atomic_or_long(unsigned long *v1, unsigned long v2) -{ - asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2)); -} -#endif - /* These are x86-specific, used by some header files */ #define atomic_clear_mask(mask, addr) \ asm volatile(LOCK_PREFIX "andl %0,%1" \ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 46e9052bbd28..f8d273e18516 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -18,7 +18,7 @@ */ static inline long atomic64_read(const atomic64_t *v) { - return (*(volatile long *)&(v)->counter); + return ACCESS_ONCE((v)->counter); } /** diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index cb4c73bfeb48..76659b67fd11 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -85,7 +85,7 @@ For 32-bit we have the following conventions - kernel is built with #define ARGOFFSET R11 #define SWFRAME ORIG_RAX - .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1 + .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0 subq $9*8+\addskip, %rsp CFI_ADJUST_CFA_OFFSET 9*8+\addskip movq_cfi rdi, 8*8 @@ -96,7 +96,11 @@ For 32-bit we have the following conventions - kernel is built with movq_cfi rcx, 5*8 .endif + .if \rax_enosys + movq $-ENOSYS, 4*8(%rsp) + .else movq_cfi rax, 4*8 + .endif .if \save_r891011 movq_cfi r8, 3*8 diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 094292a63e74..0bb1335313b2 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -8,6 +8,10 @@ #include <asm/required-features.h> #endif +#ifndef _ASM_X86_DISABLED_FEATURES_H +#include <asm/disabled-features.h> +#endif + #define NCAPINTS 11 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ @@ -282,6 +286,18 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \ (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) +#define DISABLED_MASK_BIT_SET(bit) \ + ( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0)) || \ + (((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1)) || \ + (((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2)) || \ + (((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3)) || \ + (((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4)) || \ + (((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5)) || \ + (((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6)) || \ + (((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7)) || \ + (((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8)) || \ + (((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9)) ) + #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) @@ -290,6 +306,18 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability)) +/* + * This macro is for detection of features which need kernel + * infrastructure to be used. It may *not* directly test the CPU + * itself. Use the cpu_has() family if you want true runtime + * testing of CPU features, like in hypervisor code where you are + * supporting a possible guest feature where host support for it + * is not relevant. + */ +#define cpu_feature_enabled(bit) \ + (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : \ + cpu_has(&boot_cpu_data, bit)) + #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) @@ -304,11 +332,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; } while (0) #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_vme boot_cpu_has(X86_FEATURE_VME) #define cpu_has_de boot_cpu_has(X86_FEATURE_DE) #define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) #define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) -#define cpu_has_pae boot_cpu_has(X86_FEATURE_PAE) #define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) #define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) #define cpu_has_sep boot_cpu_has(X86_FEATURE_SEP) @@ -324,9 +350,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) #define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) #define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) -#define cpu_has_k6_mtrr boot_cpu_has(X86_FEATURE_K6_MTRR) -#define cpu_has_cyrix_arr boot_cpu_has(X86_FEATURE_CYRIX_ARR) -#define cpu_has_centaur_mcr boot_cpu_has(X86_FEATURE_CENTAUR_MCR) #define cpu_has_xstore boot_cpu_has(X86_FEATURE_XSTORE) #define cpu_has_xstore_enabled boot_cpu_has(X86_FEATURE_XSTORE_EN) #define cpu_has_xcrypt boot_cpu_has(X86_FEATURE_XCRYPT) @@ -361,25 +384,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; #define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) #define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) -#ifdef CONFIG_X86_64 - -#undef cpu_has_vme -#define cpu_has_vme 0 - -#undef cpu_has_pae -#define cpu_has_pae ___BUG___ - -#undef cpu_has_k6_mtrr -#define cpu_has_k6_mtrr 0 - -#undef cpu_has_cyrix_arr -#define cpu_has_cyrix_arr 0 - -#undef cpu_has_centaur_mcr -#define cpu_has_centaur_mcr 0 - -#endif /* CONFIG_X86_64 */ - #if __GNUC__ >= 4 extern void warn_pre_alternatives(void); extern bool __static_cpu_has_safe(u16 bit); diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 4b528a970bd4..61fd18b83b6c 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -97,11 +97,11 @@ extern void hw_breakpoint_restore(void); DECLARE_PER_CPU(int, debug_stack_usage); static inline void debug_stack_usage_inc(void) { - __get_cpu_var(debug_stack_usage)++; + __this_cpu_inc(debug_stack_usage); } static inline void debug_stack_usage_dec(void) { - __get_cpu_var(debug_stack_usage)--; + __this_cpu_dec(debug_stack_usage); } int is_debug_stack(unsigned long addr); void debug_stack_set_zero(void); diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h new file mode 100644 index 000000000000..97534a7d38e3 --- /dev/null +++ b/arch/x86/include/asm/disabled-features.h @@ -0,0 +1,39 @@ +#ifndef _ASM_X86_DISABLED_FEATURES_H +#define _ASM_X86_DISABLED_FEATURES_H + +/* These features, although they might be available in a CPU + * will not be used because the compile options to support + * them are not present. + * + * This code allows them to be checked and disabled at + * compile time without an explicit #ifdef. Use + * cpu_feature_enabled(). + */ + +#ifdef CONFIG_X86_64 +# define DISABLE_VME (1<<(X86_FEATURE_VME & 31)) +# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) +# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) +# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +#else +# define DISABLE_VME 0 +# define DISABLE_K6_MTRR 0 +# define DISABLE_CYRIX_ARR 0 +# define DISABLE_CENTAUR_MCR 0 +#endif /* CONFIG_X86_64 */ + +/* + * Make sure to add features to the correct mask + */ +#define DISABLED_MASK0 (DISABLE_VME) +#define DISABLED_MASK1 0 +#define DISABLED_MASK2 0 +#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) +#define DISABLED_MASK4 0 +#define DISABLED_MASK5 0 +#define DISABLED_MASK6 0 +#define DISABLED_MASK7 0 +#define DISABLED_MASK8 0 +#define DISABLED_MASK9 0 + +#endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1a055c81d864..ca3347a9dab5 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -160,8 +160,9 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) \ - (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || \ + (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) #if __USER32_DS != __USER_DS # error "The following code assumes __USER32_DS == __USER_DS" diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 412ececa00b9..e97622f57722 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -344,7 +344,7 @@ static inline void __thread_fpu_end(struct task_struct *tsk) static inline void __thread_fpu_begin(struct task_struct *tsk) { - if (!static_cpu_has_safe(X86_FEATURE_EAGER_FPU)) + if (!use_eager_fpu()) clts(); __thread_set_has_fpu(tsk); } diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h new file mode 100644 index 000000000000..78162f8e248b --- /dev/null +++ b/arch/x86/include/asm/irq_work.h @@ -0,0 +1,11 @@ +#ifndef _ASM_IRQ_WORK_H +#define _ASM_IRQ_WORK_H + +#include <asm/processor.h> + +static inline bool arch_irq_work_has_interrupt(void) +{ + return cpu_has_apic; +} + +#endif /* _ASM_IRQ_WORK_H */ diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 9067166409bf..bbe296e0bce1 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -43,7 +43,7 @@ struct extended_sigtable { #define DWSIZE (sizeof(u32)) #define get_totalsize(mc) \ - (((struct microcode_intel *)mc)->hdr.totalsize ? \ + (((struct microcode_intel *)mc)->hdr.datasize ? \ ((struct microcode_intel *)mc)->hdr.totalsize : \ DEFAULT_UCODE_TOTALSIZE) diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index 4064acae625d..01b493e5a99b 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -9,7 +9,6 @@ #ifdef CONFIG_NUMA #define NR_NODE_MEMBLKS (MAX_NUMNODES*2) -#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT)) /* * Too small node sizes may confuse the VM badly. Usually they diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8249df45d2f2..8dfc9fd094a3 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -51,6 +51,14 @@ ARCH_PERFMON_EVENTSEL_EDGE | \ ARCH_PERFMON_EVENTSEL_INV | \ ARCH_PERFMON_EVENTSEL_CMASK) +#define X86_ALL_EVENT_FLAGS \ + (ARCH_PERFMON_EVENTSEL_EDGE | \ + ARCH_PERFMON_EVENTSEL_INV | \ + ARCH_PERFMON_EVENTSEL_CMASK | \ + ARCH_PERFMON_EVENTSEL_ANY | \ + ARCH_PERFMON_EVENTSEL_PIN_CONTROL | \ + HSW_IN_TX | \ + HSW_IN_TX_CHECKPOINTED) #define AMD64_RAW_EVENT_MASK \ (X86_RAW_EVENT_MASK | \ AMD64_EVENTSEL_EVENT) diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 85e13ccf15c4..d725382c2ae0 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu) { #ifdef CONFIG_SMP if (smp_num_siblings == 2) - return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); + return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map)); #endif return 0; } diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 9ee322103c6d..b6c0b404898a 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -32,9 +32,6 @@ static inline void pgtable_cache_init(void) { } static inline void check_pgt_cache(void) { } void paging_init(void); -extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t); - - /* * Define this if things work differently on an i386 and an i486: * it will (on an i486) warn about kernel memory accesses that are diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 3874693c0e53..4572b2f30237 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -116,7 +116,8 @@ static inline void native_pgd_clear(pgd_t *pgd) native_set_pgd(pgd, native_make_pgd(0)); } -extern void sync_global_pgds(unsigned long start, unsigned long end); +extern void sync_global_pgds(unsigned long start, unsigned long end, + int removed); /* * Conversion functions: convert a page and protection to a page entry, diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f216963760e5..07789647bf33 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -23,7 +23,6 @@ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 #define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ -#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */ #define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ @@ -52,7 +51,7 @@ #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) #define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) -#define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP) +#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) @@ -168,10 +167,10 @@ #define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE) #define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) -#define __PAGE_KERNEL_IO (__PAGE_KERNEL | _PAGE_IOMAP) -#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP) -#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP) -#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC | _PAGE_IOMAP) +#define __PAGE_KERNEL_IO (__PAGE_KERNEL) +#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) +#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS) +#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC) #define PAGE_KERNEL __pgprot(__PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) @@ -325,6 +324,20 @@ static inline pteval_t pte_flags(pte_t pte) return native_pte_val(pte) & PTE_FLAGS_MASK; } +#ifdef CONFIG_NUMA_BALANCING +/* Set of bits that distinguishes present, prot_none and numa ptes */ +#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT) +static inline pteval_t ptenuma_flags(pte_t pte) +{ + return pte_flags(pte) & _PAGE_NUMA_MASK; +} + +static inline pmdval_t pmdnuma_flags(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_NUMA_MASK; +} +#endif /* CONFIG_NUMA_BALANCING */ + #define pgprot_val(x) ((x).pgprot) #define __pgprot(x) ((pgprot_t) { (x) } ) diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 6205f0c434db..86fc2bb82287 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -75,6 +75,11 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code, int si_code); + +extern unsigned long syscall_trace_enter_phase1(struct pt_regs *, u32 arch); +extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch, + unsigned long phase1_result); + extern long syscall_trace_enter(struct pt_regs *); extern void syscall_trace_leave(struct pt_regs *); diff --git a/arch/x86/include/asm/rwlock.h b/arch/x86/include/asm/rwlock.h deleted file mode 100644 index a5370a03d90c..000000000000 --- a/arch/x86/include/asm/rwlock.h +++ /dev/null @@ -1,49 +0,0 @@ -#ifndef _ASM_X86_RWLOCK_H -#define _ASM_X86_RWLOCK_H - -#include <asm/asm.h> - -#if CONFIG_NR_CPUS <= 2048 - -#ifndef __ASSEMBLY__ -typedef union { - s32 lock; - s32 write; -} arch_rwlock_t; -#endif - -#define RW_LOCK_BIAS 0x00100000 -#define READ_LOCK_SIZE(insn) __ASM_FORM(insn##l) -#define READ_LOCK_ATOMIC(n) atomic_##n -#define WRITE_LOCK_ADD(n) __ASM_FORM_COMMA(addl n) -#define WRITE_LOCK_SUB(n) __ASM_FORM_COMMA(subl n) -#define WRITE_LOCK_CMP RW_LOCK_BIAS - -#else /* CONFIG_NR_CPUS > 2048 */ - -#include <linux/const.h> - -#ifndef __ASSEMBLY__ -typedef union { - s64 lock; - struct { - u32 read; - s32 write; - }; -} arch_rwlock_t; -#endif - -#define RW_LOCK_BIAS (_AC(1,L) << 32) -#define READ_LOCK_SIZE(insn) __ASM_FORM(insn##q) -#define READ_LOCK_ATOMIC(n) atomic64_##n -#define WRITE_LOCK_ADD(n) __ASM_FORM(incl) -#define WRITE_LOCK_SUB(n) __ASM_FORM(decl) -#define WRITE_LOCK_CMP 1 - -#endif /* CONFIG_NR_CPUS */ - -#define __ARCH_RW_LOCK_UNLOCKED { RW_LOCK_BIAS } - -/* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */ - -#endif /* _ASM_X86_RWLOCK_H */ diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h index 628c801535ea..460b84f64556 100644 --- a/arch/x86/include/asm/serial.h +++ b/arch/x86/include/asm/serial.h @@ -6,24 +6,24 @@ * * It'd be nice if someone built a serial card with a 24.576 MHz * clock, since the 16550A is capable of handling a top speed of 1.5 - * megabits/second; but this requires the faster clock. + * megabits/second; but this requires a faster clock. */ -#define BASE_BAUD ( 1843200 / 16 ) +#define BASE_BAUD (1843200/16) /* Standard COM flags (except for COM4, because of the 8514 problem) */ #ifdef CONFIG_SERIAL_DETECT_IRQ -#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ) -#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ) +# define STD_COMX_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ) +# define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | 0 | ASYNC_AUTO_IRQ) #else -#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST) -#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF +# define STD_COMX_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | 0 ) +# define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | 0 | 0 ) #endif -#define SERIAL_PORT_DFNS \ - /* UART CLK PORT IRQ FLAGS */ \ - { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS }, /* ttyS0 */ \ - { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS }, /* ttyS1 */ \ - { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS }, /* ttyS2 */ \ - { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */ +#define SERIAL_PORT_DFNS \ + /* UART CLK PORT IRQ FLAGS */ \ + { .uart = 0, BASE_BAUD, 0x3F8, 4, STD_COMX_FLAGS }, /* ttyS0 */ \ + { .uart = 0, BASE_BAUD, 0x2F8, 3, STD_COMX_FLAGS }, /* ttyS1 */ \ + { .uart = 0, BASE_BAUD, 0x3E8, 4, STD_COMX_FLAGS }, /* ttyS2 */ \ + { .uart = 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */ #endif /* _ASM_X86_SERIAL_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 54f1c8068c02..9295016485c9 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -187,7 +187,6 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) cpu_relax(); } -#ifndef CONFIG_QUEUE_RWLOCK /* * Read-write spinlocks, allowing multiple readers * but only one writer. @@ -198,91 +197,15 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) * irq-safe write-lock, but readers can get non-irqsafe * read-locks. * - * On x86, we implement read-write locks as a 32-bit counter - * with the high bit (sign) being the "contended" bit. + * On x86, we implement read-write locks using the generic qrwlock with + * x86 specific optimization. */ -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -static inline int arch_read_can_lock(arch_rwlock_t *lock) -{ - return lock->lock > 0; -} - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -static inline int arch_write_can_lock(arch_rwlock_t *lock) -{ - return lock->write == WRITE_LOCK_CMP; -} - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t" - "jns 1f\n" - "call __read_lock_failed\n\t" - "1:\n" - ::LOCK_PTR_REG (rw) : "memory"); -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t" - "jz 1f\n" - "call __write_lock_failed\n\t" - "1:\n" - ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS) - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *lock) -{ - READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock; - - if (READ_LOCK_ATOMIC(dec_return)(count) >= 0) - return 1; - READ_LOCK_ATOMIC(inc)(count); - return 0; -} - -static inline int arch_write_trylock(arch_rwlock_t *lock) -{ - atomic_t *count = (atomic_t *)&lock->write; - - if (atomic_sub_and_test(WRITE_LOCK_CMP, count)) - return 1; - atomic_add(WRITE_LOCK_CMP, count); - return 0; -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0" - :"+m" (rw->lock) : : "memory"); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0" - : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory"); -} -#else #include <asm/qrwlock.h> -#endif /* CONFIG_QUEUE_RWLOCK */ #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) -#undef READ_LOCK_SIZE -#undef READ_LOCK_ATOMIC -#undef WRITE_LOCK_ADD -#undef WRITE_LOCK_SUB -#undef WRITE_LOCK_CMP - #define arch_spin_relax(lock) cpu_relax() #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 73c4c007200f..5f9d7572d82b 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -34,10 +34,6 @@ typedef struct arch_spinlock { #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } -#ifdef CONFIG_QUEUE_RWLOCK #include <asm-generic/qrwlock_types.h> -#else -#include <asm/rwlock.h> -#endif #endif /* _ASM_X86_SPINLOCK_TYPES_H */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index c63e925fd6b7..a00ad8f2a657 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -164,7 +164,7 @@ struct uv_hub_info_s { }; DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); -#define uv_hub_info (&__get_cpu_var(__uv_hub_info)) +#define uv_hub_info this_cpu_ptr(&__uv_hub_info) #define uv_cpu_hub_info(cpu) (&per_cpu(__uv_hub_info, cpu)) /* @@ -601,16 +601,16 @@ struct uv_hub_nmi_s { struct uv_cpu_nmi_s { struct uv_hub_nmi_s *hub; - atomic_t state; - atomic_t pinging; + int state; + int pinging; int queries; int pings; }; -DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi); -#define uv_cpu_nmi (__get_cpu_var(__uv_cpu_nmi)) +DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi); + #define uv_hub_nmi (uv_cpu_nmi.hub) -#define uv_cpu_nmi_per(cpu) (per_cpu(__uv_cpu_nmi, cpu)) +#define uv_cpu_nmi_per(cpu) (per_cpu(uv_cpu_nmi, cpu)) #define uv_hub_nmi_per(cpu) (uv_cpu_nmi_per(cpu).hub) /* uv_cpu_nmi_states */ diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index bbae02470701..d993e33f5236 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -21,11 +21,6 @@ * this size. */ -/* - * Odd: 'make headers_check' complains about numa.h if I try - * to collapse the next two #ifdef lines to a single line: - * #if defined(__KERNEL__) && defined(CONFIG_EFI) - */ #ifndef __KERNEL__ #define E820_X_MAX E820MAX #endif diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index ada2e2d6be3e..8f1e77440b2b 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -39,8 +39,6 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o obj-y += pci-iommu_table.o obj-y += resource.o -obj-$(CONFIG_PREEMPT) += preempt.o - obj-y += process.o obj-y += i387.o xsave.o obj-y += ptrace.o diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index af5b08ab3b71..5972b108f15a 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -146,7 +146,7 @@ static inline int is_apbt_capable(void) static int __init apbt_clockevent_register(void) { struct sfi_timer_table_entry *mtmr; - struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev); + struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev); mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM); if (mtmr == NULL) { @@ -200,7 +200,7 @@ void apbt_setup_secondary_clock(void) if (!cpu) return; - adev = &__get_cpu_var(cpu_apbt_dev); + adev = this_cpu_ptr(&cpu_apbt_dev); if (!adev->timer) { adev->timer = dw_apb_clockevent_init(cpu, adev->name, APBT_CLOCKEVENT_RATING, adev_virt_addr(adev), diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 67760275544b..00853b254ab0 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -561,7 +561,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events); */ static void setup_APIC_timer(void) { - struct clock_event_device *levt = &__get_cpu_var(lapic_events); + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); if (this_cpu_has(X86_FEATURE_ARAT)) { lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP; @@ -696,7 +696,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc) static int __init calibrate_APIC_clock(void) { - struct clock_event_device *levt = &__get_cpu_var(lapic_events); + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); void (*real_handler)(struct clock_event_device *dev); unsigned long deltaj; long delta, deltatsc; diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index ae915391ebec..4128b5fcb559 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -32,7 +32,7 @@ static int numachip_system __read_mostly; -static const struct apic apic_numachip __read_mostly; +static const struct apic apic_numachip; static unsigned int get_apic_id(unsigned long x) { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 337ce5a9b15c..1183d545da1e 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2623,6 +2623,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_eoi = ack_apic_level, .irq_set_affinity = native_ioapic_set_affinity, .irq_retrigger = ioapic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, }; static inline void init_IO_APIC_traps(void) @@ -3173,6 +3174,7 @@ static struct irq_chip msi_chip = { .irq_ack = ack_apic_edge, .irq_set_affinity = msi_set_affinity, .irq_retrigger = ioapic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, }; int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, @@ -3271,6 +3273,7 @@ static struct irq_chip dmar_msi_type = { .irq_ack = ack_apic_edge, .irq_set_affinity = dmar_msi_set_affinity, .irq_retrigger = ioapic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, }; int arch_setup_dmar_msi(unsigned int irq) @@ -3321,6 +3324,7 @@ static struct irq_chip hpet_msi_type = { .irq_ack = ack_apic_edge, .irq_set_affinity = hpet_msi_set_affinity, .irq_retrigger = ioapic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, }; int default_setup_hpet_msi(unsigned int irq, unsigned int id) @@ -3384,6 +3388,7 @@ static struct irq_chip ht_irq_chip = { .irq_ack = ack_apic_edge, .irq_set_affinity = ht_set_affinity, .irq_retrigger = ioapic_retrigger_irq, + .flags = IRQCHIP_SKIP_SET_WAKE, }; int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 6ce600f9bc78..e658f21681c8 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -42,7 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) * We are to modify mask, so we need an own copy * and be sure it's manipulated with irq off. */ - ipi_mask_ptr = __raw_get_cpu_var(ipi_mask); + ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask); cpumask_copy(ipi_mask_ptr, mask); /* diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 004f017aa7b9..8e9dcfd630e4 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -204,7 +204,6 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second); static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) { -#ifdef CONFIG_SMP unsigned long val; int pnode; @@ -223,7 +222,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) uv_write_global_mmr64(pnode, UVH_IPI_INT, val); atomic_set(&init_deasserted, 1); -#endif return 0; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 77dcab277710..01d5453b5502 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,9 @@ 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 perf_event_intel_rapl.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_uncore_snb.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore_snbep.o perf_event_intel_uncore_nhmex.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c649f236e288..4b4f78c9ba19 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -964,6 +964,7 @@ static void vgetcpu_set_mode(void) vgetcpu_mode = VGETCPU_LSL; } +#ifdef CONFIG_IA32_EMULATION /* May not be __init: called during resume */ static void syscall32_cpu_init(void) { @@ -975,7 +976,8 @@ static void syscall32_cpu_init(void) wrmsrl(MSR_CSTAR, ia32_cstar_target); } -#endif +#endif /* CONFIG_IA32_EMULATION */ +#endif /* CONFIG_X86_64 */ #ifdef CONFIG_X86_32 void enable_sep_cpu(void) @@ -1184,7 +1186,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* @@ -1198,9 +1200,9 @@ DEFINE_PER_CPU(int, debug_stack_usage); int is_debug_stack(unsigned long addr) { - return __get_cpu_var(debug_stack_usage) || - (addr <= __get_cpu_var(debug_stack_addr) && - addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); + return __this_cpu_read(debug_stack_usage) || + (addr <= __this_cpu_read(debug_stack_addr) && + addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ)); } NOKPROBE_SYMBOL(is_debug_stack); @@ -1266,6 +1268,19 @@ static void dbg_restore_debug_regs(void) #define dbg_restore_debug_regs() #endif /* ! CONFIG_KGDB */ +static void wait_for_master_cpu(int cpu) +{ +#ifdef CONFIG_SMP + /* + * wait for ACK from master CPU before continuing + * with AP initialization + */ + WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)); + while (!cpumask_test_cpu(cpu, cpu_callout_mask)) + cpu_relax(); +#endif +} + /* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT @@ -1281,16 +1296,17 @@ void cpu_init(void) struct task_struct *me; struct tss_struct *t; unsigned long v; - int cpu; + int cpu = stack_smp_processor_id(); int i; + wait_for_master_cpu(cpu); + /* * Load microcode on this cpu if a valid microcode is available. * This is early microcode loading procedure. */ load_ucode_ap(); - cpu = stack_smp_processor_id(); t = &per_cpu(init_tss, cpu); oist = &per_cpu(orig_ist, cpu); @@ -1302,9 +1318,6 @@ void cpu_init(void) me = current; - if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) - panic("CPU#%d already initialized!\n", cpu); - pr_debug("Initializing CPU#%d\n", cpu); clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); @@ -1381,17 +1394,13 @@ void cpu_init(void) struct tss_struct *t = &per_cpu(init_tss, cpu); struct thread_struct *thread = &curr->thread; - show_ucode_info_early(); + wait_for_master_cpu(cpu); - if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) { - printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); - for (;;) - local_irq_enable(); - } + show_ucode_info_early(); printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_has_vme || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 74e804ddc5c7..1ef456273172 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -144,6 +144,21 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -382,6 +397,13 @@ static void init_intel(struct cpuinfo_x86 *c) } l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -485,6 +507,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -686,7 +715,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 5ac2d1fb28bc..4cfba4371a71 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -83,7 +83,7 @@ static DEFINE_MUTEX(mce_inject_mutex); static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) { int cpu = smp_processor_id(); - struct mce *m = &__get_cpu_var(injectm); + struct mce *m = this_cpu_ptr(&injectm); if (!cpumask_test_cpu(cpu, mce_inject_cpumask)) return NMI_DONE; cpumask_clear_cpu(cpu, mce_inject_cpumask); @@ -97,7 +97,7 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) static void mce_irq_ipi(void *info) { int cpu = smp_processor_id(); - struct mce *m = &__get_cpu_var(injectm); + struct mce *m = this_cpu_ptr(&injectm); if (cpumask_test_cpu(cpu, mce_inject_cpumask) && m->inject_flags & MCJ_EXCEPTION) { @@ -109,7 +109,7 @@ static void mce_irq_ipi(void *info) /* Inject mce on current CPU */ static int raise_local(void) { - struct mce *m = &__get_cpu_var(injectm); + struct mce *m = this_cpu_ptr(&injectm); int context = MCJ_CTX(m->inject_flags); int ret = 0; int cpu = m->extcpu; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index bd9ccda8087f..61a9668cebfd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -400,7 +400,7 @@ static u64 mce_rdmsrl(u32 msr) if (offset < 0) return 0; - return *(u64 *)((char *)&__get_cpu_var(injectm) + offset); + return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); } if (rdmsrl_safe(msr, &v)) { @@ -422,7 +422,7 @@ static void mce_wrmsrl(u32 msr, u64 v) int offset = msr_to_offset(msr); if (offset >= 0) - *(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v; + *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v; return; } wrmsrl(msr, v); @@ -478,7 +478,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring); /* Runs with CPU affinity in workqueue */ static int mce_ring_empty(void) { - struct mce_ring *r = &__get_cpu_var(mce_ring); + struct mce_ring *r = this_cpu_ptr(&mce_ring); return r->start == r->end; } @@ -490,7 +490,7 @@ static int mce_ring_get(unsigned long *pfn) *pfn = 0; get_cpu(); - r = &__get_cpu_var(mce_ring); + r = this_cpu_ptr(&mce_ring); if (r->start == r->end) goto out; *pfn = r->ring[r->start]; @@ -504,7 +504,7 @@ out: /* Always runs in MCE context with preempt off */ static int mce_ring_add(unsigned long pfn) { - struct mce_ring *r = &__get_cpu_var(mce_ring); + struct mce_ring *r = this_cpu_ptr(&mce_ring); unsigned next; next = (r->end + 1) % MCE_RING_SIZE; @@ -526,7 +526,7 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { if (!mce_ring_empty()) - schedule_work(&__get_cpu_var(mce_work)); + schedule_work(this_cpu_ptr(&mce_work)); } DEFINE_PER_CPU(struct irq_work, mce_irq_work); @@ -551,7 +551,7 @@ static void mce_report_event(struct pt_regs *regs) return; } - irq_work_queue(&__get_cpu_var(mce_irq_work)); + irq_work_queue(this_cpu_ptr(&mce_irq_work)); } /* @@ -1045,7 +1045,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_gather_info(&m, regs); - final = &__get_cpu_var(mces_seen); + final = this_cpu_ptr(&mces_seen); *final = m; memset(valid_banks, 0, sizeof(valid_banks)); @@ -1278,22 +1278,22 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) = static int cmc_error_seen(void) { - unsigned long *v = &__get_cpu_var(mce_polled_error); + unsigned long *v = this_cpu_ptr(&mce_polled_error); return test_and_clear_bit(0, v); } static void mce_timer_fn(unsigned long data) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv; int notify; WARN_ON(smp_processor_id() != data); - if (mce_available(__this_cpu_ptr(&cpu_info))) { + if (mce_available(this_cpu_ptr(&cpu_info))) { machine_check_poll(MCP_TIMESTAMP, - &__get_cpu_var(mce_poll_banks)); + this_cpu_ptr(&mce_poll_banks)); mce_intel_cmci_poll(); } @@ -1323,7 +1323,7 @@ static void mce_timer_fn(unsigned long data) */ void mce_timer_kick(unsigned long interval) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long when = jiffies + interval; unsigned long iv = __this_cpu_read(mce_next_interval); @@ -1659,7 +1659,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t) static void __mcheck_cpu_init_timer(void) { - struct timer_list *t = &__get_cpu_var(mce_timer); + struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned int cpu = smp_processor_id(); setup_timer(t, mce_timer_fn, cpu); @@ -1702,8 +1702,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_timer(); - INIT_WORK(&__get_cpu_var(mce_work), mce_process_work); - init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb); + INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work); + init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb); } /* @@ -1955,7 +1955,7 @@ static struct miscdevice mce_chrdev_device = { static void __mce_disable_bank(void *arg) { int bank = *((int *)arg); - __clear_bit(bank, __get_cpu_var(mce_poll_banks)); + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); cmci_disable_bank(bank); } @@ -2065,7 +2065,7 @@ static void mce_syscore_shutdown(void) static void mce_syscore_resume(void) { __mcheck_cpu_init_generic(); - __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info)); + __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info)); } static struct syscore_ops mce_syscore_ops = { @@ -2080,7 +2080,7 @@ static struct syscore_ops mce_syscore_ops = { static void mce_cpu_restart(void *data) { - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); __mcheck_cpu_init_timer(); @@ -2096,14 +2096,14 @@ static void mce_restart(void) /* Toggle features for corrected errors */ static void mce_disable_cmci(void *data) { - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; cmci_clear(); } static void mce_enable_ce(void *all) { - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; cmci_reenable(); cmci_recheck(); @@ -2336,7 +2336,7 @@ static void mce_disable_cpu(void *h) unsigned long action = *(unsigned long *)h; int i; - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; if (!(action & CPU_TASKS_FROZEN)) @@ -2354,7 +2354,7 @@ static void mce_reenable_cpu(void *h) unsigned long action = *(unsigned long *)h; int i; - if (!mce_available(__this_cpu_ptr(&cpu_info))) + if (!mce_available(raw_cpu_ptr(&cpu_info))) return; if (!(action & CPU_TASKS_FROZEN)) diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 1e49f8f41276..5d4999f95aec 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -310,7 +310,7 @@ static void amd_threshold_interrupt(void) * event. */ machine_check_poll(MCP_TIMESTAMP, - &__get_cpu_var(mce_poll_banks)); + this_cpu_ptr(&mce_poll_banks)); if (high & MASK_OVERFLOW_HI) { rdmsrl(address, m.misc); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 3bdb95ae8c43..b3c97bafc123 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -86,7 +86,7 @@ void mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) return; - machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); } void mce_intel_hcpu_update(unsigned long cpu) @@ -145,7 +145,7 @@ static void cmci_storm_disable_banks(void) u64 val; raw_spin_lock_irqsave(&cmci_discover_lock, flags); - owned = __get_cpu_var(mce_banks_owned); + owned = this_cpu_ptr(mce_banks_owned); for_each_set_bit(bank, owned, MAX_NR_BANKS) { rdmsrl(MSR_IA32_MCx_CTL2(bank), val); val &= ~MCI_CTL2_CMCI_EN; @@ -195,7 +195,7 @@ static void intel_threshold_interrupt(void) { if (cmci_storm_detect()) return; - machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); mce_notify_irq(); } @@ -206,7 +206,7 @@ static void intel_threshold_interrupt(void) */ static void cmci_discover(int banks) { - unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); unsigned long flags; int i; int bios_wrong_thresh = 0; @@ -228,7 +228,7 @@ static void cmci_discover(int banks) /* Already owned by someone else? */ if (val & MCI_CTL2_CMCI_EN) { clear_bit(i, owned); - __clear_bit(i, __get_cpu_var(mce_poll_banks)); + __clear_bit(i, this_cpu_ptr(mce_poll_banks)); continue; } @@ -252,7 +252,7 @@ static void cmci_discover(int banks) /* Did the enable bit stick? -- the bank supports CMCI */ if (val & MCI_CTL2_CMCI_EN) { set_bit(i, owned); - __clear_bit(i, __get_cpu_var(mce_poll_banks)); + __clear_bit(i, this_cpu_ptr(mce_poll_banks)); /* * We are able to set thresholds for some banks that * had a threshold of 0. This means the BIOS has not @@ -263,7 +263,7 @@ static void cmci_discover(int banks) (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) bios_wrong_thresh = 1; } else { - WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); + WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks))); } } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); @@ -284,10 +284,10 @@ void cmci_recheck(void) unsigned long flags; int banks; - if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) + if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) return; local_irq_save(flags); - machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned)); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); local_irq_restore(flags); } @@ -296,12 +296,12 @@ static void __cmci_disable_bank(int bank) { u64 val; - if (!test_bit(bank, __get_cpu_var(mce_banks_owned))) + if (!test_bit(bank, this_cpu_ptr(mce_banks_owned))) return; rdmsrl(MSR_IA32_MCx_CTL2(bank), val); val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(bank), val); - __clear_bit(bank, __get_cpu_var(mce_banks_owned)); + __clear_bit(bank, this_cpu_ptr(mce_banks_owned)); } /* diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 36a1bb6d1ee0..1af51b1586d7 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -498,8 +498,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { - printk(KERN_DEBUG - "CPU%d: Thermal monitoring handled by SMI\n", cpu); + if (system_state == SYSTEM_BOOTING) + printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); return; } diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e284245..7aa1acc79789 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -27,7 +27,7 @@ static u32 ucode_new_rev; u8 amd_ucode_patch[PATCH_MAX_SIZE]; static u16 this_equiv_id; -struct cpio_data ucode_cpio; +static struct cpio_data ucode_cpio; /* * Microcode patch container file is prepended to the initrd in cpio format. diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index a276fa75d9b5..c6826d1e8082 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -127,7 +127,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) return get_matching_microcode(csig, cpf, mc_intel, crev); } -int apply_microcode(int cpu) +static int apply_microcode_intel(int cpu) { struct microcode_intel *mc_intel; struct ucode_cpu_info *uci; @@ -314,7 +314,7 @@ static struct microcode_ops microcode_intel_ops = { .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info, - .apply_microcode = apply_microcode, + .apply_microcode = apply_microcode_intel, .microcode_fini_cpu = microcode_fini_cpu, }; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 18f739129e72..b88343f7a3b3 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -28,8 +28,8 @@ #include <asm/tlbflush.h> #include <asm/setup.h> -unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; -struct mc_saved_data { +static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +static struct mc_saved_data { unsigned int mc_saved_count; struct microcode_intel **mc_saved; } mc_saved_data; @@ -415,7 +415,7 @@ static void __ref show_saved_mc(void) struct ucode_cpu_info uci; if (mc_saved_data.mc_saved_count == 0) { - pr_debug("no micorcode data saved.\n"); + pr_debug("no microcode data saved.\n"); return; } pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); @@ -506,7 +506,7 @@ int save_mc_for_early(u8 *mc) if (mc_saved && mc_saved_count) memcpy(mc_saved_tmp, mc_saved, - mc_saved_count * sizeof(struct mirocode_intel *)); + mc_saved_count * sizeof(struct microcode_intel *)); /* * Save the microcode patch mc in mc_save_tmp structure if it's a newer * version. @@ -526,7 +526,7 @@ int save_mc_for_early(u8 *mc) show_saved_mc(); /* - * Free old saved microcod data. + * Free old saved microcode data. */ if (mc_saved) { for (i = 0; i < mc_saved_count_init; i++) diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f961de9964c7..ea5f363a1948 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -707,7 +707,7 @@ void __init mtrr_bp_init(void) } else { switch (boot_cpu_data.x86_vendor) { case X86_VENDOR_AMD: - if (cpu_has_k6_mtrr) { + if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; size_or_mask = SIZE_OR_MASK_BITS(32); @@ -715,14 +715,14 @@ void __init mtrr_bp_init(void) } break; case X86_VENDOR_CENTAUR: - if (cpu_has_centaur_mcr) { + if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: - if (cpu_has_cyrix_arr) { + if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2879ecdaac43..1b8299dd3d91 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -243,7 +243,8 @@ static bool check_hw_exists(void) msr_fail: printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); - printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); + printk(boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR + "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new); return false; } @@ -387,7 +388,7 @@ int x86_pmu_hw_config(struct perf_event *event) precise++; /* Support for IP fixup */ - if (x86_pmu.lbr_nr) + if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; } @@ -443,6 +444,12 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + if (event->attr.sample_period && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, event->attr.sample_period) > + event->attr.sample_period) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -487,7 +494,7 @@ static int __x86_pmu_event_init(struct perf_event *event) void x86_pmu_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -505,7 +512,7 @@ void x86_pmu_disable_all(void) static void x86_pmu_disable(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu_initialized()) return; @@ -522,7 +529,7 @@ static void x86_pmu_disable(struct pmu *pmu) void x86_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -869,7 +876,7 @@ static void x86_pmu_start(struct perf_event *event, int flags); static void x86_pmu_enable(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; struct hw_perf_event *hwc; int i, added = cpuc->n_added; @@ -980,6 +987,9 @@ int x86_perf_event_set_period(struct perf_event *event) if (left > x86_pmu.max_period) left = x86_pmu.max_period; + if (x86_pmu.limit_period) + left = x86_pmu.limit_period(event, left); + per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; /* @@ -1020,7 +1030,7 @@ void x86_pmu_enable_event(struct perf_event *event) */ static int x86_pmu_add(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc; int assign[X86_PMC_IDX_MAX]; int n, n0, ret; @@ -1071,7 +1081,7 @@ out: static void x86_pmu_start(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx = event->hw.idx; if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) @@ -1150,7 +1160,7 @@ void perf_event_print_debug(void) void x86_pmu_stop(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) { @@ -1172,7 +1182,7 @@ void x86_pmu_stop(struct perf_event *event, int flags) static void x86_pmu_del(struct perf_event *event, int flags) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int i; /* @@ -1227,7 +1237,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); /* * Some chipsets need to unmask the LVTPC in a particular spot @@ -1636,7 +1646,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu) */ static int x86_pmu_commit_txn(struct pmu *pmu) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int assign[X86_PMC_IDX_MAX]; int n, ret; @@ -1995,7 +2005,7 @@ static unsigned long get_segment_base(unsigned int segment) if (idx > GDT_ENTRIES) return 0; - desc = __this_cpu_ptr(&gdt_page.gdt[0]); + desc = raw_cpu_ptr(gdt_page.gdt); } return get_desc_base(desc + idx); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 8ade93111e03..d98a34d435d7 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -67,8 +67,10 @@ struct event_constraint { */ #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_PEBS_ST_HSW 0x4 /* haswell style datala, store */ #define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -252,18 +254,52 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) #define INTEL_PLD_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) #define INTEL_PST_CONSTRAINT(c, n) \ - __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ 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, \ +/* Event constraint, but match on all event flags too. */ +#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + +/* Check only flags, but allow all event/umask */ +#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ + EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) + +/* Check flags and event code, and set the HSW store flag */ +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) + +/* Check flags and event code, and set the HSW load flag */ +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + +/* Check flags and event code/umask, and set the HSW store flag */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) +/* Check flags and event code/umask, and set the HSW load flag */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + +/* Check flags and event code/umask, and set the HSW N/A flag */ +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) + + /* * We define the end marker as having a weight of -1 * to enable blacklisting of events using a counter bitmask @@ -409,6 +445,7 @@ struct x86_pmu { struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; + unsigned (*limit_period)(struct perf_event *event, unsigned l); /* * sysfs attrs diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index beeb7cc07044..28926311aac1 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -699,7 +699,7 @@ __init int amd_pmu_init(void) void amd_pmu_enable_virt(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); cpuc->perf_ctr_virt_mask = 0; @@ -711,7 +711,7 @@ EXPORT_SYMBOL_GPL(amd_pmu_enable_virt); void amd_pmu_disable_virt(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); /* * We only mask out the Host-only bit so that host-only counting works diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 2502d0d9d246..a73947c53b65 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct event_constraint intel_bdw_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_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ + EVENT_CONSTRAINT_END +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -415,6 +424,126 @@ static __initconst const u64 snb_hw_cache_event_ids }; +static __initconst const u64 hsw_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x280, /* ICACHE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */ + [ C(RESULT_ACCESS) ] = 0x1b7, + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE| + L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x1b7, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE:ALL_RFO */ + /* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x1b7, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x108, /* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x6085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0x185, /* ITLB_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +static __initconst const u64 hsw_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD */ + [ C(RESULT_ACCESS) ] = 0x2d5, + /* OFFCORE_RESPONSE:ALL_DATA_RD|ALL_CODE_RD|SUPPLIER_NONE| + L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x3fbc0202d5ull, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x122, /* OFFCORE_RESPONSE:ALL_RFO */ + /* OFFCORE_RESPONSE:ALL_RFO|SUPPLIER_NONE|L3_MISS|ANY_SNOOP */ + [ C(RESULT_MISS) ] = 0x3fbc020122ull, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -1045,7 +1174,7 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) static void intel_pmu_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); @@ -1058,7 +1187,7 @@ static void intel_pmu_disable_all(void) static void intel_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); intel_pmu_pebs_enable_all(); intel_pmu_lbr_enable_all(); @@ -1092,7 +1221,7 @@ static void intel_pmu_enable_all(int added) */ static void intel_pmu_nhm_workaround(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); static const unsigned long nhm_magic[4] = { 0x4300B5, 0x4300D2, @@ -1191,7 +1320,7 @@ static inline bool event_is_checkpointed(struct perf_event *event) static void intel_pmu_disable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { intel_pmu_disable_bts(); @@ -1255,7 +1384,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc) static void intel_pmu_enable_event(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) { if (!__this_cpu_read(cpu_hw_events.enabled)) @@ -1349,7 +1478,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) u64 status; int handled; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); /* * No known reason to not always do late ACK, @@ -1781,7 +1910,7 @@ EXPORT_SYMBOL_GPL(perf_guest_get_msrs); static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs; arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL; @@ -1802,7 +1931,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr) static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs; int idx; @@ -1836,7 +1965,7 @@ static void core_pmu_enable_event(struct perf_event *event) static void core_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -1905,6 +2034,24 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) return c; } +/* + * Broadwell: + * The INST_RETIRED.ALL period always needs to have lowest + * 6bits cleared (BDM57). It shall not use a period smaller + * than 100 (BDM11). We combine the two to enforce + * a min-period of 128. + */ +static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +{ + if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (left < 128) + left = 128; + left &= ~0x3fu; + } + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -2367,15 +2514,15 @@ __init int intel_pmu_init(void) * Install the hw-cache-events table: */ switch (boot_cpu_data.x86_model) { - case 14: /* 65 nm core solo/duo, "Yonah" */ + case 14: /* 65nm Core "Yonah" */ pr_cont("Core events, "); break; - case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ + case 15: /* 65nm Core2 "Merom" */ x86_add_quirk(intel_clovertown_quirk); - case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 29: /* six-core 45 nm xeon "Dunnington" */ + case 22: /* 65nm Core2 "Merom-L" */ + case 23: /* 45nm Core2 "Penryn" */ + case 29: /* 45nm Core2 "Dunnington (MP) */ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2386,9 +2533,9 @@ __init int intel_pmu_init(void) pr_cont("Core2 events, "); break; - case 26: /* 45 nm nehalem, "Bloomfield" */ - case 30: /* 45 nm nehalem, "Lynnfield" */ - case 46: /* 45 nm nehalem-ex, "Beckton" */ + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -2415,11 +2562,11 @@ __init int intel_pmu_init(void) pr_cont("Nehalem events, "); break; - case 28: /* Atom */ - case 38: /* Lincroft */ - case 39: /* Penwell */ - case 53: /* Cloverview */ - case 54: /* Cedarview */ + case 28: /* 45nm Atom "Pineview" */ + case 38: /* 45nm Atom "Lincroft" */ + case 39: /* 32nm Atom "Penwell" */ + case 53: /* 32nm Atom "Cloverview" */ + case 54: /* 32nm Atom "Cedarview" */ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2430,8 +2577,8 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; - case 55: /* Atom 22nm "Silvermont" */ - case 77: /* Avoton "Silvermont" */ + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, @@ -2446,9 +2593,9 @@ __init int intel_pmu_init(void) pr_cont("Silvermont events, "); break; - case 37: /* 32 nm nehalem, "Clarkdale" */ - case 44: /* 32 nm nehalem, "Gulftown" */ - case 47: /* 32 nm Xeon E7 */ + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs, @@ -2474,8 +2621,8 @@ __init int intel_pmu_init(void) pr_cont("Westmere events, "); break; - case 42: /* SandyBridge */ - case 45: /* SandyBridge, "Romely-EP" */ + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ x86_add_quirk(intel_sandybridge_quirk); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -2506,8 +2653,9 @@ __init int intel_pmu_init(void) pr_cont("SandyBridge events, "); break; - case 58: /* IvyBridge */ - case 62: /* IvyBridge EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); /* dTLB-load-misses on IVB is different than SNB */ @@ -2539,20 +2687,19 @@ __init int intel_pmu_init(void) break; - case 60: /* Haswell Client */ - case 70: - case 71: - case 63: - case 69: + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ 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)); + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_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.extra_regs = intel_snbep_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; @@ -2565,6 +2712,28 @@ __init int intel_pmu_init(void) pr_cont("Haswell events, "); break; + case 61: /* 14nm Broadwell Core-M */ + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_snb(); + + x86_pmu.event_constraints = intel_bdw_event_constraints; + x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.extra_regs = intel_snbep_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* 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; + x86_pmu.limit_period = bdw_limit_period; + pr_cont("Broadwell events, "); + break; + default: switch (x86_pmu.version) { case 1: diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 696ade311ded..46211bcc813e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -108,14 +108,16 @@ static u64 precise_store_data(u64 status) return val; } -static u64 precise_store_data_hsw(struct perf_event *event, u64 status) +static u64 precise_datala_hsw(struct perf_event *event, u64 status) { union perf_mem_data_src dse; - u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK; - dse.val = 0; - dse.mem_op = PERF_MEM_OP_STORE; - dse.mem_lvl = PERF_MEM_LVL_NA; + dse.val = PERF_MEM_NA; + + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + dse.mem_op = PERF_MEM_OP_STORE; + else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW) + dse.mem_op = PERF_MEM_OP_LOAD; /* * L1 info only valid for following events: @@ -125,15 +127,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status) * MEM_UOPS_RETIRED.SPLIT_STORES * MEM_UOPS_RETIRED.ALL_STORES */ - if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0) - return dse.mem_lvl; - - if (status & 1) - dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; - else - dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; - - /* Nothing else supported. Sorry. */ + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) { + if (status & 1) + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + else + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; + } return dse.val; } @@ -475,7 +474,7 @@ void intel_pmu_enable_bts(u64 config) void intel_pmu_disable_bts(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned long debugctlmsr; if (!cpuc->ds) @@ -492,7 +491,7 @@ void intel_pmu_disable_bts(void) int intel_pmu_drain_bts_buffer(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; struct bts_record { u64 from; @@ -569,28 +568,10 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { }; struct event_constraint intel_slm_pebs_event_constraints[] = { - INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */ - INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */ - INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */ - INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */ - INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */ - INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */ - INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */ - INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */ - INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */ - INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */ - INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */ - INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -626,68 +607,44 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ - INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ - INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ - INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), 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 */ - + INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END }; @@ -712,7 +669,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) void intel_pmu_pebs_enable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; @@ -727,7 +684,7 @@ void intel_pmu_pebs_enable(struct perf_event *event) void intel_pmu_pebs_disable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -745,7 +702,7 @@ void intel_pmu_pebs_disable(struct perf_event *event) void intel_pmu_pebs_enable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -753,7 +710,7 @@ void intel_pmu_pebs_enable_all(void) void intel_pmu_pebs_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, 0); @@ -761,7 +718,7 @@ void intel_pmu_pebs_disable_all(void) static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); unsigned long from = cpuc->lbr_entries[0].from; unsigned long old_to, to = cpuc->lbr_entries[0].to; unsigned long ip = regs->ip; @@ -864,51 +821,53 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { +#define PERF_X86_EVENT_PEBS_HSW_PREC \ + (PERF_X86_EVENT_PEBS_ST_HSW | \ + PERF_X86_EVENT_PEBS_LD_HSW | \ + PERF_X86_EVENT_PEBS_NA_HSW) /* * We cast to the biggest pebs_record but are careful not to * unconditionally access the 'extra' entries. */ - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_record_hsw *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; u64 sample_type; - int fll, fst; + int fll, fst, dsrc; + int fl = event->hw.flags; if (!intel_pmu_save_and_restart(event)) return; - fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; - fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST | - PERF_X86_EVENT_PEBS_ST_HSW); + sample_type = event->attr.sample_type; + dsrc = sample_type & PERF_SAMPLE_DATA_SRC; + + fll = fl & PERF_X86_EVENT_PEBS_LDLAT; + fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); perf_sample_data_init(&data, 0, event->hw.last_period); data.period = event->hw.last_period; - sample_type = event->attr.sample_type; /* - * if PEBS-LL or PreciseStore + * Use latency for weight (only avail with PEBS-LL) */ - if (fll || fst) { - /* - * Use latency for weight (only avail with PEBS-LL) - */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; - - /* - * data.data_src encodes the data source - */ - 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(event, pebs->dse); - else - data.data_src.val = precise_store_data(pebs->dse); - } + if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) + data.weight = pebs->lat; + + /* + * data.data_src encodes the data source + */ + if (dsrc) { + u64 val = PERF_MEM_NA; + if (fll) + val = load_latency_data(pebs->dse); + else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) + val = precise_datala_hsw(event, pebs->dse); + else if (fst) + val = precise_store_data(pebs->dse); + data.data_src.val = val; } /* @@ -935,16 +894,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event, else regs.flags &= ~PERF_EFLAGS_EXACT; - if ((event->attr.sample_type & PERF_SAMPLE_ADDR) && + if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) data.addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll) + if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) data.weight = intel_hsw_weight(pebs); - if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION) + if (sample_type & PERF_SAMPLE_TRANSACTION) data.txn = intel_hsw_transaction(pebs); } @@ -957,7 +916,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; struct perf_event *event = cpuc->events[0]; /* PMC0 only */ struct pebs_record_core *at, *top; @@ -998,7 +957,7 @@ static void intel_pmu_drain_pebs_core(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 cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; struct perf_event *event = NULL; void *at, *top; @@ -1055,7 +1014,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) * BTS, PEBS probe and setup */ -void intel_ds_init(void) +void __init intel_ds_init(void) { /* * No support for 32bit formats diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 9dd2459a4c73..45fa730a5283 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -133,7 +133,7 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc); static void __intel_pmu_lbr_enable(void) { u64 debugctl; - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config); @@ -183,7 +183,7 @@ void intel_pmu_lbr_reset(void) void intel_pmu_lbr_enable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu.lbr_nr) return; @@ -203,7 +203,7 @@ void intel_pmu_lbr_enable(struct perf_event *event) void intel_pmu_lbr_disable(struct perf_event *event) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu.lbr_nr) return; @@ -220,7 +220,7 @@ void intel_pmu_lbr_disable(struct perf_event *event) void intel_pmu_lbr_enable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_users) __intel_pmu_lbr_enable(); @@ -228,7 +228,7 @@ void intel_pmu_lbr_enable_all(void) void intel_pmu_lbr_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_users) __intel_pmu_lbr_disable(); @@ -332,7 +332,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) void intel_pmu_lbr_read(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!cpuc->lbr_users) return; @@ -697,7 +697,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { }; /* core */ -void intel_pmu_lbr_init_core(void) +void __init intel_pmu_lbr_init_core(void) { x86_pmu.lbr_nr = 4; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -712,7 +712,7 @@ void intel_pmu_lbr_init_core(void) } /* nehalem/westmere */ -void intel_pmu_lbr_init_nhm(void) +void __init intel_pmu_lbr_init_nhm(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -733,7 +733,7 @@ void intel_pmu_lbr_init_nhm(void) } /* sandy bridge */ -void intel_pmu_lbr_init_snb(void) +void __init intel_pmu_lbr_init_snb(void) { x86_pmu.lbr_nr = 16; x86_pmu.lbr_tos = MSR_LBR_TOS; @@ -753,7 +753,7 @@ void intel_pmu_lbr_init_snb(void) } /* atom */ -void intel_pmu_lbr_init_atom(void) +void __init intel_pmu_lbr_init_atom(void) { /* * only models starting at stepping 10 seems diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 619f7699487a..d64f275fe274 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v) * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit); + return v << (32 - __this_cpu_read(rapl_pmu->hw_unit)); } static u64 rapl_event_update(struct perf_event *event) @@ -187,7 +187,7 @@ static void rapl_stop_hrtimer(struct rapl_pmu *pmu) static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); struct perf_event *event; unsigned long flags; @@ -234,7 +234,7 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu, static void rapl_pmu_event_start(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); unsigned long flags; spin_lock_irqsave(&pmu->lock, flags); @@ -244,7 +244,7 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode) static void rapl_pmu_event_stop(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); struct hw_perf_event *hwc = &event->hw; unsigned long flags; @@ -278,7 +278,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode) static int rapl_pmu_event_add(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu); + struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); struct hw_perf_event *hwc = &event->hw; unsigned long flags; @@ -696,7 +696,7 @@ static int __init rapl_pmu_init(void) return -1; } - pmu = __get_cpu_var(rapl_pmu); + pmu = __this_cpu_read(rapl_pmu); pr_info("RAPL PMU detected, hw unit 2^-%d Joules," " API unit is 2^-32 Joules," diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 0939f86f543d..9762dbd9f3f7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -1,83 +1,39 @@ #include "perf_event_intel_uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; -static struct intel_uncore_type **msr_uncores = empty_uncore; -static struct intel_uncore_type **pci_uncores = empty_uncore; -/* pci bus to socket mapping */ -static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; +struct intel_uncore_type **uncore_msr_uncores = empty_uncore; +struct intel_uncore_type **uncore_pci_uncores = empty_uncore; -static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +static bool pcidrv_registered; +struct pci_driver *uncore_pci_driver; +/* pci bus to socket mapping */ +int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, }; +struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; static DEFINE_RAW_SPINLOCK(uncore_box_lock); - /* mask of cpus that collect uncore events */ static cpumask_t uncore_cpu_mask; /* constraint for the fixed counter */ -static struct event_constraint constraint_fixed = +static struct event_constraint uncore_constraint_fixed = EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL); -static struct event_constraint constraint_empty = +struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); -#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ - ((1ULL << (n)) - 1))) - -DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); -DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); -DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); -DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); -DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); -DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); -DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); -DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); -DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); -DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); -DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); -DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); -DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); -DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); -DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); -DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); -DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); -DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); -DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); -DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); -DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); -DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); -DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); -DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); -DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); -DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); -DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); -DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); -DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); -DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); - -static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); -static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); -static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); -static void uncore_pmu_event_read(struct perf_event *event); - -static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct uncore_event_desc *event = + container_of(attr, struct uncore_event_desc, attr); + return sprintf(buf, "%s", event->config); +} + +struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct intel_uncore_pmu, pmu); } -static struct intel_uncore_box * -uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) +struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { struct intel_uncore_box *box; @@ -86,6 +42,9 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) return box; raw_spin_lock(&uncore_box_lock); + /* Recheck in lock to handle races. */ + if (*per_cpu_ptr(pmu->box, cpu)) + goto out; list_for_each_entry(box, &pmu->box_list, list) { if (box->phys_id == topology_physical_package_id(cpu)) { atomic_inc(&box->refcnt); @@ -93,12 +52,13 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) break; } } +out: raw_spin_unlock(&uncore_box_lock); return *per_cpu_ptr(pmu->box, cpu); } -static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) { /* * perf core schedules event on the basis of cpu, uncore events are @@ -107,7 +67,7 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } -static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) +u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { u64 count; @@ -119,7 +79,7 @@ static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_eve /* * generic get constraint function for shared match/mask registers. */ -static struct event_constraint * +struct event_constraint * uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_extra_reg *er; @@ -154,10 +114,10 @@ uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event) return NULL; } - return &constraint_empty; + return &uncore_constraint_empty; } -static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event) { struct intel_uncore_extra_reg *er; struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; @@ -178,7 +138,7 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even reg1->alloc = 0; } -static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) +u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) { struct intel_uncore_extra_reg *er; unsigned long flags; @@ -193,2936 +153,6 @@ static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) return config; } -/* Sandy Bridge-EP uncore support */ -static struct intel_uncore_type snbep_uncore_cbox; -static struct intel_uncore_type snbep_uncore_pcu; - -static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int box_ctl = uncore_pci_box_ctl(box); - u32 config = 0; - - if (!pci_read_config_dword(pdev, box_ctl, &config)) { - config |= SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); - } -} - -static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int box_ctl = uncore_pci_box_ctl(box); - u32 config = 0; - - if (!pci_read_config_dword(pdev, box_ctl, &config)) { - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - pci_write_config_dword(pdev, box_ctl, config); - } -} - -static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, hwc->config_base, hwc->config); -} - -static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - u64 count = 0; - - pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); - pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); - - return count; -} - -static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); -} - -static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - u64 config; - unsigned msr; - - msr = uncore_msr_box_ctl(box); - if (msr) { - rdmsrl(msr, config); - config |= SNBEP_PMON_BOX_CTL_FRZ; - wrmsrl(msr, config); - } -} - -static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - u64 config; - unsigned msr; - - msr = uncore_msr_box_ctl(box); - if (msr) { - rdmsrl(msr, config); - config &= ~SNBEP_PMON_BOX_CTL_FRZ; - wrmsrl(msr, config); - } -} - -static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (reg1->idx != EXTRA_REG_NONE) - wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); - - wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, - struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - wrmsrl(hwc->config_base, hwc->config); -} - -static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - - if (msr) - wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); -} - -static struct attribute *snbep_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute *snbep_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - NULL, -}; - -static struct attribute *snbep_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_tid_en.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_filter_tid.attr, - &format_attr_filter_nid.attr, - &format_attr_filter_state.attr, - &format_attr_filter_opc.attr, - NULL, -}; - -static struct attribute *snbep_uncore_pcu_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_occ_sel.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - &format_attr_occ_invert.attr, - &format_attr_occ_edge.attr, - &format_attr_filter_band0.attr, - &format_attr_filter_band1.attr, - &format_attr_filter_band2.attr, - &format_attr_filter_band3.attr, - NULL, -}; - -static struct attribute *snbep_uncore_qpi_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_match_rds.attr, - &format_attr_match_rnid30.attr, - &format_attr_match_rnid4.attr, - &format_attr_match_dnid.attr, - &format_attr_match_mc.attr, - &format_attr_match_opc.attr, - &format_attr_match_vnw.attr, - &format_attr_match0.attr, - &format_attr_match1.attr, - &format_attr_mask_rds.attr, - &format_attr_mask_rnid30.attr, - &format_attr_mask_rnid4.attr, - &format_attr_mask_dnid.attr, - &format_attr_mask_mc.attr, - &format_attr_mask_opc.attr, - &format_attr_mask_vnw.attr, - &format_attr_mask0.attr, - &format_attr_mask1.attr, - NULL, -}; - -static struct uncore_event_desc snbep_uncore_imc_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), - INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), - { /* end: all zeroes */ }, -}; - -static struct uncore_event_desc snbep_uncore_qpi_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), - INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), - { /* end: all zeroes */ }, -}; - -static struct attribute_group snbep_uncore_format_group = { - .name = "format", - .attrs = snbep_uncore_formats_attr, -}; - -static struct attribute_group snbep_uncore_ubox_format_group = { - .name = "format", - .attrs = snbep_uncore_ubox_formats_attr, -}; - -static struct attribute_group snbep_uncore_cbox_format_group = { - .name = "format", - .attrs = snbep_uncore_cbox_formats_attr, -}; - -static struct attribute_group snbep_uncore_pcu_format_group = { - .name = "format", - .attrs = snbep_uncore_pcu_formats_attr, -}; - -static struct attribute_group snbep_uncore_qpi_format_group = { - .name = "format", - .attrs = snbep_uncore_qpi_formats_attr, -}; - -#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ - .init_box = snbep_uncore_msr_init_box, \ - .disable_box = snbep_uncore_msr_disable_box, \ - .enable_box = snbep_uncore_msr_enable_box, \ - .disable_event = snbep_uncore_msr_disable_event, \ - .enable_event = snbep_uncore_msr_enable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops snbep_uncore_msr_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), -}; - -#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ - .init_box = snbep_uncore_pci_init_box, \ - .disable_box = snbep_uncore_pci_disable_box, \ - .enable_box = snbep_uncore_pci_enable_box, \ - .disable_event = snbep_uncore_pci_disable_event, \ - .read_counter = snbep_uncore_pci_read_counter - -static struct intel_uncore_ops snbep_uncore_pci_ops = { - SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), - .enable_event = snbep_uncore_pci_enable_event, \ -}; - -static struct event_constraint snbep_uncore_cbox_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x01, 0x1), - UNCORE_EVENT_CONSTRAINT(0x02, 0x3), - UNCORE_EVENT_CONSTRAINT(0x04, 0x3), - UNCORE_EVENT_CONSTRAINT(0x05, 0x3), - UNCORE_EVENT_CONSTRAINT(0x07, 0x3), - UNCORE_EVENT_CONSTRAINT(0x09, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x1), - UNCORE_EVENT_CONSTRAINT(0x12, 0x3), - UNCORE_EVENT_CONSTRAINT(0x13, 0x3), - UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), - UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), - EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), - UNCORE_EVENT_CONSTRAINT(0x21, 0x3), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x31, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - UNCORE_EVENT_CONSTRAINT(0x35, 0x3), - UNCORE_EVENT_CONSTRAINT(0x36, 0x1), - UNCORE_EVENT_CONSTRAINT(0x37, 0x3), - UNCORE_EVENT_CONSTRAINT(0x38, 0x3), - UNCORE_EVENT_CONSTRAINT(0x39, 0x3), - UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), - EVENT_CONSTRAINT_END -}; - -static struct event_constraint snbep_uncore_r2pcie_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x10, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x3), - UNCORE_EVENT_CONSTRAINT(0x12, 0x1), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x24, 0x3), - UNCORE_EVENT_CONSTRAINT(0x25, 0x3), - UNCORE_EVENT_CONSTRAINT(0x26, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - EVENT_CONSTRAINT_END -}; - -static struct event_constraint snbep_uncore_r3qpi_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x10, 0x3), - UNCORE_EVENT_CONSTRAINT(0x11, 0x3), - UNCORE_EVENT_CONSTRAINT(0x12, 0x3), - UNCORE_EVENT_CONSTRAINT(0x13, 0x1), - UNCORE_EVENT_CONSTRAINT(0x20, 0x3), - UNCORE_EVENT_CONSTRAINT(0x21, 0x3), - UNCORE_EVENT_CONSTRAINT(0x22, 0x3), - UNCORE_EVENT_CONSTRAINT(0x23, 0x3), - UNCORE_EVENT_CONSTRAINT(0x24, 0x3), - UNCORE_EVENT_CONSTRAINT(0x25, 0x3), - UNCORE_EVENT_CONSTRAINT(0x26, 0x3), - UNCORE_EVENT_CONSTRAINT(0x28, 0x3), - UNCORE_EVENT_CONSTRAINT(0x29, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), - UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), - UNCORE_EVENT_CONSTRAINT(0x30, 0x3), - UNCORE_EVENT_CONSTRAINT(0x31, 0x3), - UNCORE_EVENT_CONSTRAINT(0x32, 0x3), - UNCORE_EVENT_CONSTRAINT(0x33, 0x3), - UNCORE_EVENT_CONSTRAINT(0x34, 0x3), - UNCORE_EVENT_CONSTRAINT(0x36, 0x3), - UNCORE_EVENT_CONSTRAINT(0x37, 0x3), - UNCORE_EVENT_CONSTRAINT(0x38, 0x3), - UNCORE_EVENT_CONSTRAINT(0x39, 0x3), - EVENT_CONSTRAINT_END -}; - -static struct intel_uncore_type snbep_uncore_ubox = { - .name = "ubox", - .num_counters = 2, - .num_boxes = 1, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNBEP_U_MSR_PMON_CTR0, - .event_ctl = SNBEP_U_MSR_PMON_CTL0, - .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, - .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, - .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, - .ops = &snbep_uncore_msr_ops, - .format_group = &snbep_uncore_ubox_format_group, -}; - -static struct extra_reg snbep_uncore_cbox_extra_regs[] = { - SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, - SNBEP_CBO_PMON_CTL_TID_EN, 0x1), - SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), - SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), - SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), - SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), - EVENT_EXTRA_END -}; - -static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - int i; - - if (uncore_box_is_fake(box)) - return; - - for (i = 0; i < 5; i++) { - if (reg1->alloc & (0x1 << i)) - atomic_sub(1 << (i * 6), &er->ref); - } - reg1->alloc = 0; -} - -static struct event_constraint * -__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, - u64 (*cbox_filter_mask)(int fields)) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - int i, alloc = 0; - unsigned long flags; - u64 mask; - - if (reg1->idx == EXTRA_REG_NONE) - return NULL; - - raw_spin_lock_irqsave(&er->lock, flags); - for (i = 0; i < 5; i++) { - if (!(reg1->idx & (0x1 << i))) - continue; - if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) - continue; - - mask = cbox_filter_mask(0x1 << i); - if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || - !((reg1->config ^ er->config) & mask)) { - atomic_add(1 << (i * 6), &er->ref); - er->config &= ~mask; - er->config |= reg1->config & mask; - alloc |= (0x1 << i); - } else { - break; - } - } - raw_spin_unlock_irqrestore(&er->lock, flags); - if (i < 5) - goto fail; - - if (!uncore_box_is_fake(box)) - reg1->alloc |= alloc; - - return NULL; -fail: - for (; i >= 0; i--) { - if (alloc & (0x1 << i)) - atomic_sub(1 << (i * 6), &er->ref); - } - return &constraint_empty; -} - -static u64 snbep_cbox_filter_mask(int fields) -{ - u64 mask = 0; - - if (fields & 0x1) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; - if (fields & 0x2) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; - if (fields & 0x4) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; - if (fields & 0x8) - mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; - - return mask; -} - -static struct event_constraint * -snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); -} - -static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct extra_reg *er; - int idx = 0; - - for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - idx |= er->idx; - } - - if (idx) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); - reg1->idx = idx; - } - return 0; -} - -static struct intel_uncore_ops snbep_uncore_cbox_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_cbox_hw_config, - .get_constraint = snbep_cbox_get_constraint, - .put_constraint = snbep_cbox_put_constraint, -}; - -static struct intel_uncore_type snbep_uncore_cbox = { - .name = "cbox", - .num_counters = 4, - .num_boxes = 8, - .perf_ctr_bits = 44, - .event_ctl = SNBEP_C0_MSR_PMON_CTL0, - .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, - .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, - .msr_offset = SNBEP_CBO_MSR_OFFSET, - .num_shared_regs = 1, - .constraints = snbep_uncore_cbox_constraints, - .ops = &snbep_uncore_cbox_ops, - .format_group = &snbep_uncore_cbox_format_group, -}; - -static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - u64 config = reg1->config; - - if (new_idx > reg1->idx) - config <<= 8 * (new_idx - reg1->idx); - else - config >>= 8 * (reg1->idx - new_idx); - - if (modify) { - hwc->config += new_idx - reg1->idx; - reg1->config = config; - reg1->idx = new_idx; - } - return config; -} - -static struct event_constraint * -snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - unsigned long flags; - int idx = reg1->idx; - u64 mask, config1 = reg1->config; - bool ok = false; - - if (reg1->idx == EXTRA_REG_NONE || - (!uncore_box_is_fake(box) && reg1->alloc)) - return NULL; -again: - mask = 0xffULL << (idx * 8); - raw_spin_lock_irqsave(&er->lock, flags); - if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || - !((config1 ^ er->config) & mask)) { - atomic_add(1 << (idx * 8), &er->ref); - er->config &= ~mask; - er->config |= config1 & mask; - ok = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (!ok) { - idx = (idx + 1) % 4; - if (idx != reg1->idx) { - config1 = snbep_pcu_alter_er(event, idx, false); - goto again; - } - return &constraint_empty; - } - - if (!uncore_box_is_fake(box)) { - if (idx != reg1->idx) - snbep_pcu_alter_er(event, idx, true); - reg1->alloc = 1; - } - return NULL; -} - -static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct intel_uncore_extra_reg *er = &box->shared_regs[0]; - - if (uncore_box_is_fake(box) || !reg1->alloc) - return; - - atomic_sub(1 << (reg1->idx * 8), &er->ref); - reg1->alloc = 0; -} - -static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; - - if (ev_sel >= 0xb && ev_sel <= 0xe) { - reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; - reg1->idx = ev_sel - 0xb; - reg1->config = event->attr.config1 & (0xff << reg1->idx); - } - return 0; -} - -static struct intel_uncore_ops snbep_uncore_pcu_ops = { - SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_pcu_hw_config, - .get_constraint = snbep_pcu_get_constraint, - .put_constraint = snbep_pcu_put_constraint, -}; - -static struct intel_uncore_type snbep_uncore_pcu = { - .name = "pcu", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, - .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, - .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &snbep_uncore_pcu_ops, - .format_group = &snbep_uncore_pcu_format_group, -}; - -static struct intel_uncore_type *snbep_msr_uncores[] = { - &snbep_uncore_ubox, - &snbep_uncore_cbox, - &snbep_uncore_pcu, - NULL, -}; - -enum { - SNBEP_PCI_QPI_PORT0_FILTER, - SNBEP_PCI_QPI_PORT1_FILTER, -}; - -static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { - reg1->idx = 0; - reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; - reg1->config = event->attr.config1; - reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; - reg2->config = event->attr.config2; - } - return 0; -} - -static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; - struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx]; - WARN_ON_ONCE(!filter_pdev); - if (filter_pdev) { - pci_write_config_dword(filter_pdev, reg1->reg, - (u32)reg1->config); - pci_write_config_dword(filter_pdev, reg1->reg + 4, - (u32)(reg1->config >> 32)); - pci_write_config_dword(filter_pdev, reg2->reg, - (u32)reg2->config); - pci_write_config_dword(filter_pdev, reg2->reg + 4, - (u32)(reg2->config >> 32)); - } - } - - pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static struct intel_uncore_ops snbep_uncore_qpi_ops = { - SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), - .enable_event = snbep_qpi_enable_event, - .hw_config = snbep_qpi_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -#define SNBEP_UNCORE_PCI_COMMON_INIT() \ - .perf_ctr = SNBEP_PCI_PMON_CTR0, \ - .event_ctl = SNBEP_PCI_PMON_CTL0, \ - .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ - .ops = &snbep_uncore_pci_ops, \ - .format_group = &snbep_uncore_format_group - -static struct intel_uncore_type snbep_uncore_ha = { - .name = "ha", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_imc = { - .name = "imc", - .num_counters = 4, - .num_boxes = 4, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, - .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, - .event_descs = snbep_uncore_imc_events, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &snbep_uncore_qpi_ops, - .event_descs = snbep_uncore_qpi_events, - .format_group = &snbep_uncore_qpi_format_group, -}; - - -static struct intel_uncore_type snbep_uncore_r2pcie = { - .name = "r2pcie", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r2pcie_constraints, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type snbep_uncore_r3qpi = { - .name = "r3qpi", - .num_counters = 3, - .num_boxes = 2, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r3qpi_constraints, - SNBEP_UNCORE_PCI_COMMON_INIT(), -}; - -enum { - SNBEP_PCI_UNCORE_HA, - SNBEP_PCI_UNCORE_IMC, - SNBEP_PCI_UNCORE_QPI, - SNBEP_PCI_UNCORE_R2PCIE, - SNBEP_PCI_UNCORE_R3QPI, -}; - -static struct intel_uncore_type *snbep_pci_uncores[] = { - [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, - [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, - [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, - [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, - [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, - NULL, -}; - -static const struct pci_device_id snbep_uncore_pci_ids[] = { - { /* Home Agent */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), - }, - { /* MC Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), - }, - { /* MC Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), - }, - { /* MC Channel 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), - }, - { /* MC Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), - }, - { /* QPI Port 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), - }, - { /* QPI Port 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), - }, - { /* R2PCIe */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), - }, - { /* R3QPI Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), - }, - { /* R3QPI Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT0_FILTER), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT1_FILTER), - }, - { /* end: all zeroes */ } -}; - -static struct pci_driver snbep_uncore_pci_driver = { - .name = "snbep_uncore", - .id_table = snbep_uncore_pci_ids, -}; - -/* - * build pci bus to socket mapping - */ -static int snbep_pci2phy_map_init(int devid) -{ - struct pci_dev *ubox_dev = NULL; - int i, bus, nodeid; - int err = 0; - u32 config = 0; - - while (1) { - /* find the UBOX device */ - ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); - if (!ubox_dev) - break; - bus = ubox_dev->bus->number; - /* get the Node ID of the local register */ - err = pci_read_config_dword(ubox_dev, 0x40, &config); - if (err) - break; - nodeid = config; - /* get the Node ID mapping */ - err = pci_read_config_dword(ubox_dev, 0x54, &config); - if (err) - break; - /* - * every three bits in the Node ID mapping register maps - * to a particular node. - */ - for (i = 0; i < 8; i++) { - if (nodeid == ((config >> (3 * i)) & 0x7)) { - pcibus_to_physid[bus] = i; - break; - } - } - } - - if (!err) { - /* - * For PCI bus with no UBOX device, find the next bus - * that has UBOX device and use its mapping. - */ - i = -1; - for (bus = 255; bus >= 0; bus--) { - if (pcibus_to_physid[bus] >= 0) - i = pcibus_to_physid[bus]; - else - pcibus_to_physid[bus] = i; - } - } - - if (ubox_dev) - pci_dev_put(ubox_dev); - - return err ? pcibios_err_to_errno(err) : 0; -} -/* end of Sandy Bridge-EP uncore support */ - -/* IvyTown uncore support */ -static void ivt_uncore_msr_init_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - if (msr) - wrmsrl(msr, IVT_PMON_BOX_CTL_INT); -} - -static void ivt_uncore_pci_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT); -} - -#define IVT_UNCORE_MSR_OPS_COMMON_INIT() \ - .init_box = ivt_uncore_msr_init_box, \ - .disable_box = snbep_uncore_msr_disable_box, \ - .enable_box = snbep_uncore_msr_enable_box, \ - .disable_event = snbep_uncore_msr_disable_event, \ - .enable_event = snbep_uncore_msr_enable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops ivt_uncore_msr_ops = { - IVT_UNCORE_MSR_OPS_COMMON_INIT(), -}; - -static struct intel_uncore_ops ivt_uncore_pci_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_uncore_pci_enable_event, - .read_counter = snbep_uncore_pci_read_counter, -}; - -#define IVT_UNCORE_PCI_COMMON_INIT() \ - .perf_ctr = SNBEP_PCI_PMON_CTR0, \ - .event_ctl = SNBEP_PCI_PMON_CTL0, \ - .event_mask = IVT_PMON_RAW_EVENT_MASK, \ - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ - .ops = &ivt_uncore_pci_ops, \ - .format_group = &ivt_uncore_format_group - -static struct attribute *ivt_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute *ivt_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh5.attr, - NULL, -}; - -static struct attribute *ivt_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_tid_en.attr, - &format_attr_thresh8.attr, - &format_attr_filter_tid.attr, - &format_attr_filter_link.attr, - &format_attr_filter_state2.attr, - &format_attr_filter_nid2.attr, - &format_attr_filter_opc2.attr, - NULL, -}; - -static struct attribute *ivt_uncore_pcu_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_occ_sel.attr, - &format_attr_edge.attr, - &format_attr_thresh5.attr, - &format_attr_occ_invert.attr, - &format_attr_occ_edge.attr, - &format_attr_filter_band0.attr, - &format_attr_filter_band1.attr, - &format_attr_filter_band2.attr, - &format_attr_filter_band3.attr, - NULL, -}; - -static struct attribute *ivt_uncore_qpi_formats_attr[] = { - &format_attr_event_ext.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_thresh8.attr, - &format_attr_match_rds.attr, - &format_attr_match_rnid30.attr, - &format_attr_match_rnid4.attr, - &format_attr_match_dnid.attr, - &format_attr_match_mc.attr, - &format_attr_match_opc.attr, - &format_attr_match_vnw.attr, - &format_attr_match0.attr, - &format_attr_match1.attr, - &format_attr_mask_rds.attr, - &format_attr_mask_rnid30.attr, - &format_attr_mask_rnid4.attr, - &format_attr_mask_dnid.attr, - &format_attr_mask_mc.attr, - &format_attr_mask_opc.attr, - &format_attr_mask_vnw.attr, - &format_attr_mask0.attr, - &format_attr_mask1.attr, - NULL, -}; - -static struct attribute_group ivt_uncore_format_group = { - .name = "format", - .attrs = ivt_uncore_formats_attr, -}; - -static struct attribute_group ivt_uncore_ubox_format_group = { - .name = "format", - .attrs = ivt_uncore_ubox_formats_attr, -}; - -static struct attribute_group ivt_uncore_cbox_format_group = { - .name = "format", - .attrs = ivt_uncore_cbox_formats_attr, -}; - -static struct attribute_group ivt_uncore_pcu_format_group = { - .name = "format", - .attrs = ivt_uncore_pcu_formats_attr, -}; - -static struct attribute_group ivt_uncore_qpi_format_group = { - .name = "format", - .attrs = ivt_uncore_qpi_formats_attr, -}; - -static struct intel_uncore_type ivt_uncore_ubox = { - .name = "ubox", - .num_counters = 2, - .num_boxes = 1, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNBEP_U_MSR_PMON_CTR0, - .event_ctl = SNBEP_U_MSR_PMON_CTL0, - .event_mask = IVT_U_MSR_PMON_RAW_EVENT_MASK, - .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, - .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, - .ops = &ivt_uncore_msr_ops, - .format_group = &ivt_uncore_ubox_format_group, -}; - -static struct extra_reg ivt_uncore_cbox_extra_regs[] = { - SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, - SNBEP_CBO_PMON_CTL_TID_EN, 0x1), - SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), - - SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), - SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), - SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), - SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), - SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), - EVENT_EXTRA_END -}; - -static u64 ivt_cbox_filter_mask(int fields) -{ - u64 mask = 0; - - if (fields & 0x1) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID; - if (fields & 0x2) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK; - if (fields & 0x4) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE; - if (fields & 0x8) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID; - if (fields & 0x10) - mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC; - - return mask; -} - -static struct event_constraint * -ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask); -} - -static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct extra_reg *er; - int idx = 0; - - for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - idx |= er->idx; - } - - if (idx) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx); - reg1->idx = idx; - } - return 0; -} - -static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - u64 filter = uncore_shared_reg_config(box, 0); - wrmsrl(reg1->reg, filter & 0xffffffff); - wrmsrl(reg1->reg + 6, filter >> 32); - } - - wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); -} - -static struct intel_uncore_ops ivt_uncore_cbox_ops = { - .init_box = ivt_uncore_msr_init_box, - .disable_box = snbep_uncore_msr_disable_box, - .enable_box = snbep_uncore_msr_enable_box, - .disable_event = snbep_uncore_msr_disable_event, - .enable_event = ivt_cbox_enable_event, - .read_counter = uncore_msr_read_counter, - .hw_config = ivt_cbox_hw_config, - .get_constraint = ivt_cbox_get_constraint, - .put_constraint = snbep_cbox_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_cbox = { - .name = "cbox", - .num_counters = 4, - .num_boxes = 15, - .perf_ctr_bits = 44, - .event_ctl = SNBEP_C0_MSR_PMON_CTL0, - .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, - .event_mask = IVT_CBO_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, - .msr_offset = SNBEP_CBO_MSR_OFFSET, - .num_shared_regs = 1, - .constraints = snbep_uncore_cbox_constraints, - .ops = &ivt_uncore_cbox_ops, - .format_group = &ivt_uncore_cbox_format_group, -}; - -static struct intel_uncore_ops ivt_uncore_pcu_ops = { - IVT_UNCORE_MSR_OPS_COMMON_INIT(), - .hw_config = snbep_pcu_hw_config, - .get_constraint = snbep_pcu_get_constraint, - .put_constraint = snbep_pcu_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_pcu = { - .name = "pcu", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, - .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, - .event_mask = IVT_PCU_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &ivt_uncore_pcu_ops, - .format_group = &ivt_uncore_pcu_format_group, -}; - -static struct intel_uncore_type *ivt_msr_uncores[] = { - &ivt_uncore_ubox, - &ivt_uncore_cbox, - &ivt_uncore_pcu, - NULL, -}; - -static struct intel_uncore_type ivt_uncore_ha = { - .name = "ha", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type ivt_uncore_imc = { - .name = "imc", - .num_counters = 4, - .num_boxes = 8, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, - .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -/* registers in IRP boxes are not properly aligned */ -static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; -static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; - -static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], - hwc->config | SNBEP_PMON_CTL_EN); -} - -static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - - pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config); -} - -static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct pci_dev *pdev = box->pci_dev; - struct hw_perf_event *hwc = &event->hw; - u64 count = 0; - - pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count); - pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); - - return count; -} - -static struct intel_uncore_ops ivt_uncore_irp_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = ivt_uncore_irp_disable_event, - .enable_event = ivt_uncore_irp_enable_event, - .read_counter = ivt_uncore_irp_read_counter, -}; - -static struct intel_uncore_type ivt_uncore_irp = { - .name = "irp", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_mask = IVT_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &ivt_uncore_irp_ops, - .format_group = &ivt_uncore_format_group, -}; - -static struct intel_uncore_ops ivt_uncore_qpi_ops = { - .init_box = ivt_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_qpi_enable_event, - .read_counter = snbep_uncore_pci_read_counter, - .hw_config = snbep_qpi_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type ivt_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 3, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .num_shared_regs = 1, - .ops = &ivt_uncore_qpi_ops, - .format_group = &ivt_uncore_qpi_format_group, -}; - -static struct intel_uncore_type ivt_uncore_r2pcie = { - .name = "r2pcie", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r2pcie_constraints, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -static struct intel_uncore_type ivt_uncore_r3qpi = { - .name = "r3qpi", - .num_counters = 3, - .num_boxes = 2, - .perf_ctr_bits = 44, - .constraints = snbep_uncore_r3qpi_constraints, - IVT_UNCORE_PCI_COMMON_INIT(), -}; - -enum { - IVT_PCI_UNCORE_HA, - IVT_PCI_UNCORE_IMC, - IVT_PCI_UNCORE_IRP, - IVT_PCI_UNCORE_QPI, - IVT_PCI_UNCORE_R2PCIE, - IVT_PCI_UNCORE_R3QPI, -}; - -static struct intel_uncore_type *ivt_pci_uncores[] = { - [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, - [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, - [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp, - [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, - [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, - [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, - NULL, -}; - -static const struct pci_device_id ivt_uncore_pci_ids[] = { - { /* Home Agent 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0), - }, - { /* Home Agent 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1), - }, - { /* MC0 Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0), - }, - { /* MC0 Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1), - }, - { /* MC0 Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2), - }, - { /* MC0 Channel 4 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3), - }, - { /* MC1 Channel 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4), - }, - { /* MC1 Channel 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5), - }, - { /* MC1 Channel 3 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6), - }, - { /* MC1 Channel 4 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), - }, - { /* IRP */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0), - }, - { /* QPI0 Port 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), - }, - { /* QPI0 Port 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1), - }, - { /* QPI1 Port 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2), - }, - { /* R2PCIe */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0), - }, - { /* R3QPI0 Link 0 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0), - }, - { /* R3QPI0 Link 1 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1), - }, - { /* R3QPI1 Link 2 */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), - .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT0_FILTER), - }, - { /* QPI Port 0 filter */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - SNBEP_PCI_QPI_PORT1_FILTER), - }, - { /* end: all zeroes */ } -}; - -static struct pci_driver ivt_uncore_pci_driver = { - .name = "ivt_uncore", - .id_table = ivt_uncore_pci_ids, -}; -/* end of IvyTown uncore support */ - -/* Sandy Bridge uncore support */ -static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx < UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); - else - wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); -} - -static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - wrmsrl(event->hw.config_base, 0); -} - -static void snb_uncore_msr_init_box(struct intel_uncore_box *box) -{ - if (box->pmu->pmu_idx == 0) { - wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, - SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); - } -} - -static struct uncore_event_desc snb_uncore_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - { /* end: all zeroes */ }, -}; - -static struct attribute *snb_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_cmask5.attr, - NULL, -}; - -static struct attribute_group snb_uncore_format_group = { - .name = "format", - .attrs = snb_uncore_formats_attr, -}; - -static struct intel_uncore_ops snb_uncore_msr_ops = { - .init_box = snb_uncore_msr_init_box, - .disable_event = snb_uncore_msr_disable_event, - .enable_event = snb_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, -}; - -static struct event_constraint snb_uncore_cbox_constraints[] = { - UNCORE_EVENT_CONSTRAINT(0x80, 0x1), - UNCORE_EVENT_CONSTRAINT(0x83, 0x1), - EVENT_CONSTRAINT_END -}; - -static struct intel_uncore_type snb_uncore_cbox = { - .name = "cbox", - .num_counters = 2, - .num_boxes = 4, - .perf_ctr_bits = 44, - .fixed_ctr_bits = 48, - .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, - .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, - .fixed_ctr = SNB_UNC_FIXED_CTR, - .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, - .single_fixed = 1, - .event_mask = SNB_UNC_RAW_EVENT_MASK, - .msr_offset = SNB_UNC_CBO_MSR_OFFSET, - .constraints = snb_uncore_cbox_constraints, - .ops = &snb_uncore_msr_ops, - .format_group = &snb_uncore_format_group, - .event_descs = snb_uncore_events, -}; - -static struct intel_uncore_type *snb_msr_uncores[] = { - &snb_uncore_cbox, - NULL, -}; - -enum { - SNB_PCI_UNCORE_IMC, -}; - -static struct uncore_event_desc snb_uncore_imc_events[] = { - INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), - INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), - INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), - - INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), - INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), - INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), - - { /* end: all zeroes */ }, -}; - -#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff -#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 - -/* page size multiple covering all config regs */ -#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 - -#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 -#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 -#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 -#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 -#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE - -static struct attribute *snb_uncore_imc_formats_attr[] = { - &format_attr_event.attr, - NULL, -}; - -static struct attribute_group snb_uncore_imc_format_group = { - .name = "format", - .attrs = snb_uncore_imc_formats_attr, -}; - -static void snb_uncore_imc_init_box(struct intel_uncore_box *box) -{ - struct pci_dev *pdev = box->pci_dev; - int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; - resource_size_t addr; - u32 pci_dword; - - pci_read_config_dword(pdev, where, &pci_dword); - addr = pci_dword; - -#ifdef CONFIG_PHYS_ADDR_T_64BIT - pci_read_config_dword(pdev, where + 4, &pci_dword); - addr |= ((resource_size_t)pci_dword << 32); -#endif - - addr &= ~(PAGE_SIZE - 1); - - box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); - box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; -} - -static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) -{} - -static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) -{} - -static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{} - -static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{} - -static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); -} - -/* - * custom event_init() function because we define our own fixed, free - * running counters, so we do not want to conflict with generic uncore - * logic. Also simplifies processing - */ -static int snb_uncore_imc_event_init(struct perf_event *event) -{ - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - struct hw_perf_event *hwc = &event->hw; - u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; - int idx, base; - - if (event->attr.type != event->pmu->type) - return -ENOENT; - - pmu = uncore_event_to_pmu(event); - /* no device found for this pmu */ - if (pmu->func_id < 0) - return -ENOENT; - - /* Sampling not supported yet */ - if (hwc->sample_period) - return -EINVAL; - - /* unsupported modes and filters */ - if (event->attr.exclude_user || - event->attr.exclude_kernel || - event->attr.exclude_hv || - event->attr.exclude_idle || - event->attr.exclude_host || - event->attr.exclude_guest || - event->attr.sample_period) /* no sampling */ - return -EINVAL; - - /* - * Place all uncore events for a particular physical package - * onto a single cpu - */ - if (event->cpu < 0) - return -EINVAL; - - /* check only supported bits are set */ - if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) - return -EINVAL; - - box = uncore_pmu_to_box(pmu, event->cpu); - if (!box || box->cpu < 0) - return -EINVAL; - - event->cpu = box->cpu; - - event->hw.idx = -1; - event->hw.last_tag = ~0ULL; - event->hw.extra_reg.idx = EXTRA_REG_NONE; - event->hw.branch_reg.idx = EXTRA_REG_NONE; - /* - * check event is known (whitelist, determines counter) - */ - switch (cfg) { - case SNB_UNCORE_PCI_IMC_DATA_READS: - base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; - idx = UNCORE_PMC_IDX_FIXED; - break; - case SNB_UNCORE_PCI_IMC_DATA_WRITES: - base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; - idx = UNCORE_PMC_IDX_FIXED + 1; - break; - default: - return -EINVAL; - } - - /* must be done before validate_group */ - event->hw.event_base = base; - event->hw.config = cfg; - event->hw.idx = idx; - - /* no group validation needed, we have free running counters */ - - return 0; -} - -static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - return 0; -} - -static void snb_uncore_imc_event_start(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - u64 count; - - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) - return; - - event->hw.state = 0; - box->n_active++; - - list_add_tail(&event->active_entry, &box->active_list); - - count = snb_uncore_imc_read_counter(box, event); - local64_set(&event->hw.prev_count, count); - - if (box->n_active == 1) - uncore_pmu_start_hrtimer(box); -} - -static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - struct hw_perf_event *hwc = &event->hw; - - if (!(hwc->state & PERF_HES_STOPPED)) { - box->n_active--; - - WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); - hwc->state |= PERF_HES_STOPPED; - - list_del(&event->active_entry); - - if (box->n_active == 0) - uncore_pmu_cancel_hrtimer(box); - } - - if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { - /* - * Drain the remaining delta count out of a event - * that we are disabling: - */ - uncore_perf_event_update(box, event); - hwc->state |= PERF_HES_UPTODATE; - } -} - -static int snb_uncore_imc_event_add(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - struct hw_perf_event *hwc = &event->hw; - - if (!box) - return -ENODEV; - - hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; - if (!(flags & PERF_EF_START)) - hwc->state |= PERF_HES_ARCH; - - snb_uncore_imc_event_start(event, 0); - - box->n_events++; - - return 0; -} - -static void snb_uncore_imc_event_del(struct perf_event *event, int flags) -{ - struct intel_uncore_box *box = uncore_event_to_box(event); - int i; - - snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); - - for (i = 0; i < box->n_events; i++) { - if (event == box->event_list[i]) { - --box->n_events; - break; - } - } -} - -static int snb_pci2phy_map_init(int devid) -{ - struct pci_dev *dev = NULL; - int bus; - - dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); - if (!dev) - return -ENOTTY; - - bus = dev->bus->number; - - pcibus_to_physid[bus] = 0; - - pci_dev_put(dev); - - return 0; -} - -static struct pmu snb_uncore_imc_pmu = { - .task_ctx_nr = perf_invalid_context, - .event_init = snb_uncore_imc_event_init, - .add = snb_uncore_imc_event_add, - .del = snb_uncore_imc_event_del, - .start = snb_uncore_imc_event_start, - .stop = snb_uncore_imc_event_stop, - .read = uncore_pmu_event_read, -}; - -static struct intel_uncore_ops snb_uncore_imc_ops = { - .init_box = snb_uncore_imc_init_box, - .enable_box = snb_uncore_imc_enable_box, - .disable_box = snb_uncore_imc_disable_box, - .disable_event = snb_uncore_imc_disable_event, - .enable_event = snb_uncore_imc_enable_event, - .hw_config = snb_uncore_imc_hw_config, - .read_counter = snb_uncore_imc_read_counter, -}; - -static struct intel_uncore_type snb_uncore_imc = { - .name = "imc", - .num_counters = 2, - .num_boxes = 1, - .fixed_ctr_bits = 32, - .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, - .event_descs = snb_uncore_imc_events, - .format_group = &snb_uncore_imc_format_group, - .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, - .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, - .ops = &snb_uncore_imc_ops, - .pmu = &snb_uncore_imc_pmu, -}; - -static struct intel_uncore_type *snb_pci_uncores[] = { - [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, - NULL, -}; - -static const struct pci_device_id snb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static const struct pci_device_id ivb_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static const struct pci_device_id hsw_uncore_pci_ids[] = { - { /* IMC */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), - .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), - }, - { /* end: all zeroes */ }, -}; - -static struct pci_driver snb_uncore_pci_driver = { - .name = "snb_uncore", - .id_table = snb_uncore_pci_ids, -}; - -static struct pci_driver ivb_uncore_pci_driver = { - .name = "ivb_uncore", - .id_table = ivb_uncore_pci_ids, -}; - -static struct pci_driver hsw_uncore_pci_driver = { - .name = "hsw_uncore", - .id_table = hsw_uncore_pci_ids, -}; - -/* end of Sandy Bridge uncore support */ - -/* Nehalem uncore support */ -static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); -} - -static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); -} - -static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx < UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); - else - wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); -} - -static struct attribute *nhm_uncore_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_cmask8.attr, - NULL, -}; - -static struct attribute_group nhm_uncore_format_group = { - .name = "format", - .attrs = nhm_uncore_formats_attr, -}; - -static struct uncore_event_desc nhm_uncore_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), - INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), - INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), - INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), - INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), - INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), - INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), - INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhm_uncore_msr_ops = { - .disable_box = nhm_uncore_msr_disable_box, - .enable_box = nhm_uncore_msr_enable_box, - .disable_event = snb_uncore_msr_disable_event, - .enable_event = nhm_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, -}; - -static struct intel_uncore_type nhm_uncore = { - .name = "", - .num_counters = 8, - .num_boxes = 1, - .perf_ctr_bits = 48, - .fixed_ctr_bits = 48, - .event_ctl = NHM_UNC_PERFEVTSEL0, - .perf_ctr = NHM_UNC_UNCORE_PMC0, - .fixed_ctr = NHM_UNC_FIXED_CTR, - .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, - .event_mask = NHM_UNC_RAW_EVENT_MASK, - .event_descs = nhm_uncore_events, - .ops = &nhm_uncore_msr_ops, - .format_group = &nhm_uncore_format_group, -}; - -static struct intel_uncore_type *nhm_msr_uncores[] = { - &nhm_uncore, - NULL, -}; -/* end of Nehalem uncore support */ - -/* Nehalem-EX uncore support */ -DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); -DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); -DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); - -static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) -{ - wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); -} - -static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - u64 config; - - if (msr) { - rdmsrl(msr, config); - config &= ~((1ULL << uncore_num_counters(box)) - 1); - /* WBox has a fixed counter */ - if (uncore_msr_fixed_ctl(box)) - config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; - wrmsrl(msr, config); - } -} - -static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) -{ - unsigned msr = uncore_msr_box_ctl(box); - u64 config; - - if (msr) { - rdmsrl(msr, config); - config |= (1ULL << uncore_num_counters(box)) - 1; - /* WBox has a fixed counter */ - if (uncore_msr_fixed_ctl(box)) - config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; - wrmsrl(msr, config); - } -} - -static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - wrmsrl(event->hw.config_base, 0); -} - -static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - if (hwc->idx >= UNCORE_PMC_IDX_FIXED) - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); - else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); - else - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); -} - -#define NHMEX_UNCORE_OPS_COMMON_INIT() \ - .init_box = nhmex_uncore_msr_init_box, \ - .disable_box = nhmex_uncore_msr_disable_box, \ - .enable_box = nhmex_uncore_msr_enable_box, \ - .disable_event = nhmex_uncore_msr_disable_event, \ - .read_counter = uncore_msr_read_counter - -static struct intel_uncore_ops nhmex_uncore_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_uncore_msr_enable_event, -}; - -static struct attribute *nhmex_uncore_ubox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_edge.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_ubox_format_group = { - .name = "format", - .attrs = nhmex_uncore_ubox_formats_attr, -}; - -static struct intel_uncore_type nhmex_uncore_ubox = { - .name = "ubox", - .num_counters = 1, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, - .perf_ctr = NHMEX_U_MSR_PMON_CTR, - .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_ubox_format_group -}; - -static struct attribute *nhmex_uncore_cbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_cbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_cbox_formats_attr, -}; - -/* msr offset for each instance of cbox */ -static unsigned nhmex_cbox_msr_offsets[] = { - 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, -}; - -static struct intel_uncore_type nhmex_uncore_cbox = { - .name = "cbox", - .num_counters = 6, - .num_boxes = 10, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, - .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, - .msr_offsets = nhmex_cbox_msr_offsets, - .pair_ctr_ctl = 1, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_cbox_format_group -}; - -static struct uncore_event_desc nhmex_uncore_wbox_events[] = { - INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_type nhmex_uncore_wbox = { - .name = "wbox", - .num_counters = 4, - .num_boxes = 1, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_W_MSR_PMON_CNT0, - .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, - .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, - .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, - .pair_ctr_ctl = 1, - .event_descs = nhmex_uncore_wbox_events, - .ops = &nhmex_uncore_ops, - .format_group = &nhmex_uncore_cbox_format_group -}; - -static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int ctr, ev_sel; - - ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> - NHMEX_B_PMON_CTR_SHIFT; - ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> - NHMEX_B_PMON_CTL_EV_SEL_SHIFT; - - /* events that do not use the match/mask registers */ - if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || - (ctr == 2 && ev_sel != 0x4) || ctr == 3) - return 0; - - if (box->pmu->pmu_idx == 0) - reg1->reg = NHMEX_B0_MSR_MATCH; - else - reg1->reg = NHMEX_B1_MSR_MATCH; - reg1->idx = 0; - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - return 0; -} - -static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - wrmsrl(reg1->reg, reg1->config); - wrmsrl(reg1->reg + 1, reg2->config); - } - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | - (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); -} - -/* - * The Bbox has 4 counters, but each counter monitors different events. - * Use bits 6-7 in the event config to select counter. - */ -static struct event_constraint nhmex_uncore_bbox_constraints[] = { - EVENT_CONSTRAINT(0 , 1, 0xc0), - EVENT_CONSTRAINT(0x40, 2, 0xc0), - EVENT_CONSTRAINT(0x80, 4, 0xc0), - EVENT_CONSTRAINT(0xc0, 8, 0xc0), - EVENT_CONSTRAINT_END, -}; - -static struct attribute *nhmex_uncore_bbox_formats_attr[] = { - &format_attr_event5.attr, - &format_attr_counter.attr, - &format_attr_match.attr, - &format_attr_mask.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_bbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_bbox_formats_attr, -}; - -static struct intel_uncore_ops nhmex_uncore_bbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_bbox_msr_enable_event, - .hw_config = nhmex_bbox_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_bbox = { - .name = "bbox", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_B0_MSR_PMON_CTL0, - .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, - .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_B_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 1, - .constraints = nhmex_uncore_bbox_constraints, - .ops = &nhmex_uncore_bbox_ops, - .format_group = &nhmex_uncore_bbox_format_group -}; - -static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - /* only TO_R_PROG_EV event uses the match/mask register */ - if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != - NHMEX_S_EVENT_TO_R_PROG_EV) - return 0; - - if (box->pmu->pmu_idx == 0) - reg1->reg = NHMEX_S0_MSR_MM_CFG; - else - reg1->reg = NHMEX_S1_MSR_MM_CFG; - reg1->idx = 0; - reg1->config = event->attr.config1; - reg2->config = event->attr.config2; - return 0; -} - -static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - - if (reg1->idx != EXTRA_REG_NONE) { - wrmsrl(reg1->reg, 0); - wrmsrl(reg1->reg + 1, reg1->config); - wrmsrl(reg1->reg + 2, reg2->config); - wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); - } - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); -} - -static struct attribute *nhmex_uncore_sbox_formats_attr[] = { - &format_attr_event.attr, - &format_attr_umask.attr, - &format_attr_edge.attr, - &format_attr_inv.attr, - &format_attr_thresh8.attr, - &format_attr_match.attr, - &format_attr_mask.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_sbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_sbox_formats_attr, -}; - -static struct intel_uncore_ops nhmex_uncore_sbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_sbox_msr_enable_event, - .hw_config = nhmex_sbox_hw_config, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_sbox = { - .name = "sbox", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_S0_MSR_PMON_CTL0, - .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, - .event_mask = NHMEX_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, - .msr_offset = NHMEX_S_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 1, - .ops = &nhmex_uncore_sbox_ops, - .format_group = &nhmex_uncore_sbox_format_group -}; - -enum { - EXTRA_REG_NHMEX_M_FILTER, - EXTRA_REG_NHMEX_M_DSP, - EXTRA_REG_NHMEX_M_ISS, - EXTRA_REG_NHMEX_M_MAP, - EXTRA_REG_NHMEX_M_MSC_THR, - EXTRA_REG_NHMEX_M_PGT, - EXTRA_REG_NHMEX_M_PLD, - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, -}; - -static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { - MBOX_INC_SEL_EXTAR_REG(0x0, DSP), - MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), - MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), - MBOX_INC_SEL_EXTAR_REG(0x9, ISS), - /* event 0xa uses two extra registers */ - MBOX_INC_SEL_EXTAR_REG(0xa, ISS), - MBOX_INC_SEL_EXTAR_REG(0xa, PLD), - MBOX_INC_SEL_EXTAR_REG(0xb, PLD), - /* events 0xd ~ 0x10 use the same extra register */ - MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), - MBOX_INC_SEL_EXTAR_REG(0x16, PGT), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), - MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), - EVENT_EXTRA_END -}; - -/* Nehalem-EX or Westmere-EX ? */ -static bool uncore_nhmex; - -static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - bool ret = false; - u64 mask; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - er = &box->shared_regs[idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (!atomic_read(&er->ref) || er->config == config) { - atomic_inc(&er->ref); - er->config = config; - ret = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - return ret; - } - /* - * The ZDP_CTL_FVC MSR has 4 fields which are used to control - * events 0xd ~ 0x10. Besides these 4 fields, there are additional - * fields which are shared. - */ - idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (WARN_ON_ONCE(idx >= 4)) - return false; - - /* mask of the shared fields */ - if (uncore_nhmex) - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; - else - mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - - raw_spin_lock_irqsave(&er->lock, flags); - /* add mask of the non-shared field if it's in use */ - if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { - if (uncore_nhmex) - mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - } - - if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { - atomic_add(1 << (idx * 8), &er->ref); - if (uncore_nhmex) - mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | - NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | - WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - er->config &= ~mask; - er->config |= (config & mask); - ret = true; - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - return ret; -} - -static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - er = &box->shared_regs[idx]; - atomic_dec(&er->ref); - return; - } - - idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - atomic_sub(1 << (idx * 8), &er->ref); -} - -static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); - u64 config = reg1->config; - - /* get the non-shared control bits and shift them */ - idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (uncore_nhmex) - config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - else - config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); - if (new_idx > orig_idx) { - idx = new_idx - orig_idx; - config <<= 3 * idx; - } else { - idx = orig_idx - new_idx; - config >>= 3 * idx; - } - - /* add the shared control bits back */ - if (uncore_nhmex) - config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - else - config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; - if (modify) { - /* adjust the main event selector */ - if (new_idx > orig_idx) - hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; - else - hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; - reg1->config = config; - reg1->idx = ~0xff | new_idx; - } - return config; -} - -static struct event_constraint * -nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int i, idx[2], alloc = 0; - u64 config1 = reg1->config; - - idx[0] = __BITS_VALUE(reg1->idx, 0, 8); - idx[1] = __BITS_VALUE(reg1->idx, 1, 8); -again: - for (i = 0; i < 2; i++) { - if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) - idx[i] = 0xff; - - if (idx[i] == 0xff) - continue; - - if (!nhmex_mbox_get_shared_reg(box, idx[i], - __BITS_VALUE(config1, i, 32))) - goto fail; - alloc |= (0x1 << i); - } - - /* for the match/mask registers */ - if (reg2->idx != EXTRA_REG_NONE && - (uncore_box_is_fake(box) || !reg2->alloc) && - !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) - goto fail; - - /* - * If it's a fake box -- as per validate_{group,event}() we - * shouldn't touch event state and we can avoid doing so - * since both will only call get_event_constraints() once - * on each event, this avoids the need for reg->alloc. - */ - if (!uncore_box_is_fake(box)) { - if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) - nhmex_mbox_alter_er(event, idx[0], true); - reg1->alloc |= alloc; - if (reg2->idx != EXTRA_REG_NONE) - reg2->alloc = 1; - } - return NULL; -fail: - if (idx[0] != 0xff && !(alloc & 0x1) && - idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { - /* - * events 0xd ~ 0x10 are functional identical, but are - * controlled by different fields in the ZDP_CTL_FVC - * register. If we failed to take one field, try the - * rest 3 choices. - */ - BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); - idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - idx[0] = (idx[0] + 1) % 4; - idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; - if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { - config1 = nhmex_mbox_alter_er(event, idx[0], false); - goto again; - } - } - - if (alloc & 0x1) - nhmex_mbox_put_shared_reg(box, idx[0]); - if (alloc & 0x2) - nhmex_mbox_put_shared_reg(box, idx[1]); - return &constraint_empty; -} - -static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - - if (uncore_box_is_fake(box)) - return; - - if (reg1->alloc & 0x1) - nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); - if (reg1->alloc & 0x2) - nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); - reg1->alloc = 0; - - if (reg2->alloc) { - nhmex_mbox_put_shared_reg(box, reg2->idx); - reg2->alloc = 0; - } -} - -static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) -{ - if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) - return er->idx; - return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; -} - -static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct intel_uncore_type *type = box->pmu->type; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - struct extra_reg *er; - unsigned msr; - int reg_idx = 0; - /* - * The mbox events may require 2 extra MSRs at the most. But only - * the lower 32 bits in these MSRs are significant, so we can use - * config1 to pass two MSRs' config. - */ - for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { - if (er->event != (event->hw.config & er->config_mask)) - continue; - if (event->attr.config1 & ~er->valid_mask) - return -EINVAL; - - msr = er->msr + type->msr_offset * box->pmu->pmu_idx; - if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) - return -EINVAL; - - /* always use the 32~63 bits to pass the PLD config */ - if (er->idx == EXTRA_REG_NHMEX_M_PLD) - reg_idx = 1; - else if (WARN_ON_ONCE(reg_idx > 0)) - return -EINVAL; - - reg1->idx &= ~(0xff << (reg_idx * 8)); - reg1->reg &= ~(0xffff << (reg_idx * 16)); - reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); - reg1->reg |= msr << (reg_idx * 16); - reg1->config = event->attr.config1; - reg_idx++; - } - /* - * The mbox only provides ability to perform address matching - * for the PLD events. - */ - if (reg_idx == 2) { - reg2->idx = EXTRA_REG_NHMEX_M_FILTER; - if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) - reg2->config = event->attr.config2; - else - reg2->config = ~0ULL; - if (box->pmu->pmu_idx == 0) - reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; - else - reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; - } - return 0; -} - -static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - u64 config; - - if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) - return box->shared_regs[idx].config; - - er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; - raw_spin_lock_irqsave(&er->lock, flags); - config = er->config; - raw_spin_unlock_irqrestore(&er->lock, flags); - return config; -} - -static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx; - - idx = __BITS_VALUE(reg1->idx, 0, 8); - if (idx != 0xff) - wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), - nhmex_mbox_shared_reg_config(box, idx)); - idx = __BITS_VALUE(reg1->idx, 1, 8); - if (idx != 0xff) - wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), - nhmex_mbox_shared_reg_config(box, idx)); - - if (reg2->idx != EXTRA_REG_NONE) { - wrmsrl(reg2->reg, 0); - if (reg2->config != ~0ULL) { - wrmsrl(reg2->reg + 1, - reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); - wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & - (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); - wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); - } - } - - wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); -} - -DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); -DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); -DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); -DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); -DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); -DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); -DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); -DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); -DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); -DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); -DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); - -static struct attribute *nhmex_uncore_mbox_formats_attr[] = { - &format_attr_count_mode.attr, - &format_attr_storage_mode.attr, - &format_attr_wrap_mode.attr, - &format_attr_flag_mode.attr, - &format_attr_inc_sel.attr, - &format_attr_set_flag_sel.attr, - &format_attr_filter_cfg_en.attr, - &format_attr_filter_match.attr, - &format_attr_filter_mask.attr, - &format_attr_dsp.attr, - &format_attr_thr.attr, - &format_attr_fvc.attr, - &format_attr_pgt.attr, - &format_attr_map.attr, - &format_attr_iss.attr, - &format_attr_pld.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_mbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_mbox_formats_attr, -}; - -static struct uncore_event_desc nhmex_uncore_mbox_events[] = { - INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), - INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), - { /* end: all zeroes */ }, -}; - -static struct uncore_event_desc wsmex_uncore_mbox_events[] = { - INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), - INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhmex_uncore_mbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_mbox_msr_enable_event, - .hw_config = nhmex_mbox_hw_config, - .get_constraint = nhmex_mbox_get_constraint, - .put_constraint = nhmex_mbox_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_mbox = { - .name = "mbox", - .num_counters = 6, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_M0_MSR_PMU_CTL0, - .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, - .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, - .msr_offset = NHMEX_M_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 8, - .event_descs = nhmex_uncore_mbox_events, - .ops = &nhmex_uncore_mbox_ops, - .format_group = &nhmex_uncore_mbox_format_group, -}; - -static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - /* adjust the main event selector and extra register index */ - if (reg1->idx % 2) { - reg1->idx--; - hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - } else { - reg1->idx++; - hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - } - - /* adjust extra register config */ - switch (reg1->idx % 6) { - case 2: - /* shift the 8~15 bits to the 0~7 bits */ - reg1->config >>= 8; - break; - case 3: - /* shift the 0~7 bits to the 8~15 bits */ - reg1->config <<= 8; - break; - }; -} - -/* - * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. - * An event set consists of 6 events, the 3rd and 4th events in - * an event set use the same extra register. So an event set uses - * 5 extra registers. - */ -static struct event_constraint * -nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - struct intel_uncore_extra_reg *er; - unsigned long flags; - int idx, er_idx; - u64 config1; - bool ok = false; - - if (!uncore_box_is_fake(box) && reg1->alloc) - return NULL; - - idx = reg1->idx % 6; - config1 = reg1->config; -again: - er_idx = idx; - /* the 3rd and 4th events use the same extra register */ - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; - - er = &box->shared_regs[er_idx]; - raw_spin_lock_irqsave(&er->lock, flags); - if (idx < 2) { - if (!atomic_read(&er->ref) || er->config == reg1->config) { - atomic_inc(&er->ref); - er->config = reg1->config; - ok = true; - } - } else if (idx == 2 || idx == 3) { - /* - * these two events use different fields in a extra register, - * the 0~7 bits and the 8~15 bits respectively. - */ - u64 mask = 0xff << ((idx - 2) * 8); - if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || - !((er->config ^ config1) & mask)) { - atomic_add(1 << ((idx - 2) * 8), &er->ref); - er->config &= ~mask; - er->config |= config1 & mask; - ok = true; - } - } else { - if (!atomic_read(&er->ref) || - (er->config == (hwc->config >> 32) && - er->config1 == reg1->config && - er->config2 == reg2->config)) { - atomic_inc(&er->ref); - er->config = (hwc->config >> 32); - er->config1 = reg1->config; - er->config2 = reg2->config; - ok = true; - } - } - raw_spin_unlock_irqrestore(&er->lock, flags); - - if (!ok) { - /* - * The Rbox events are always in pairs. The paired - * events are functional identical, but use different - * extra registers. If we failed to take an extra - * register, try the alternative. - */ - idx ^= 1; - if (idx != reg1->idx % 6) { - if (idx == 2) - config1 >>= 8; - else if (idx == 3) - config1 <<= 8; - goto again; - } - } else { - if (!uncore_box_is_fake(box)) { - if (idx != reg1->idx % 6) - nhmex_rbox_alter_er(box, event); - reg1->alloc = 1; - } - return NULL; - } - return &constraint_empty; -} - -static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) -{ - struct intel_uncore_extra_reg *er; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - int idx, er_idx; - - if (uncore_box_is_fake(box) || !reg1->alloc) - return; - - idx = reg1->idx % 6; - er_idx = idx; - if (er_idx > 2) - er_idx--; - er_idx += (reg1->idx / 6) * 5; - - er = &box->shared_regs[er_idx]; - if (idx == 2 || idx == 3) - atomic_sub(1 << ((idx - 2) * 8), &er->ref); - else - atomic_dec(&er->ref); - - reg1->alloc = 0; -} - -static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; - struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; - int idx; - - idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> - NHMEX_R_PMON_CTL_EV_SEL_SHIFT; - if (idx >= 0x18) - return -EINVAL; - - reg1->idx = idx; - reg1->config = event->attr.config1; - - switch (idx % 6) { - case 4: - case 5: - hwc->config |= event->attr.config & (~0ULL << 32); - reg2->config = event->attr.config2; - break; - }; - return 0; -} - -static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - struct hw_perf_event_extra *reg2 = &hwc->branch_reg; - int idx, port; - - idx = reg1->idx; - port = idx / 6 + box->pmu->pmu_idx * 4; - - switch (idx % 6) { - case 0: - wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); - break; - case 1: - wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); - break; - case 2: - case 3: - wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), - uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); - break; - case 4: - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), - hwc->config >> 32); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); - break; - case 5: - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), - hwc->config >> 32); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); - wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); - break; - }; - - wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | - (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); -} - -DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); -DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); -DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); - -static struct attribute *nhmex_uncore_rbox_formats_attr[] = { - &format_attr_event5.attr, - &format_attr_xbr_mm_cfg.attr, - &format_attr_xbr_match.attr, - &format_attr_xbr_mask.attr, - &format_attr_qlx_cfg.attr, - &format_attr_iperf_cfg.attr, - NULL, -}; - -static struct attribute_group nhmex_uncore_rbox_format_group = { - .name = "format", - .attrs = nhmex_uncore_rbox_formats_attr, -}; - -static struct uncore_event_desc nhmex_uncore_rbox_events[] = { - INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), - INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), - INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), - INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), - INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), - INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), - { /* end: all zeroes */ }, -}; - -static struct intel_uncore_ops nhmex_uncore_rbox_ops = { - NHMEX_UNCORE_OPS_COMMON_INIT(), - .enable_event = nhmex_rbox_msr_enable_event, - .hw_config = nhmex_rbox_hw_config, - .get_constraint = nhmex_rbox_get_constraint, - .put_constraint = nhmex_rbox_put_constraint, -}; - -static struct intel_uncore_type nhmex_uncore_rbox = { - .name = "rbox", - .num_counters = 8, - .num_boxes = 2, - .perf_ctr_bits = 48, - .event_ctl = NHMEX_R_MSR_PMON_CTL0, - .perf_ctr = NHMEX_R_MSR_PMON_CNT0, - .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, - .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, - .msr_offset = NHMEX_R_MSR_OFFSET, - .pair_ctr_ctl = 1, - .num_shared_regs = 20, - .event_descs = nhmex_uncore_rbox_events, - .ops = &nhmex_uncore_rbox_ops, - .format_group = &nhmex_uncore_rbox_format_group -}; - -static struct intel_uncore_type *nhmex_msr_uncores[] = { - &nhmex_uncore_ubox, - &nhmex_uncore_cbox, - &nhmex_uncore_bbox, - &nhmex_uncore_sbox, - &nhmex_uncore_mbox, - &nhmex_uncore_rbox, - &nhmex_uncore_wbox, - NULL, -}; -/* end of Nehalem-EX uncore support */ - static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx) { struct hw_perf_event *hwc = &event->hw; @@ -3140,7 +170,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_eve hwc->event_base = uncore_perf_ctr(box, hwc->idx); } -static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) +void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event) { u64 prev_count, new_count, delta; int shift; @@ -3201,14 +231,14 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) return HRTIMER_RESTART; } -static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) +void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { __hrtimer_start_range_ns(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), 0, HRTIMER_MODE_REL_PINNED, 0); } -static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) +void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) { hrtimer_cancel(&box->hrtimer); } @@ -3291,7 +321,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve } if (event->attr.config == UNCORE_FIXED_EVENT) - return &constraint_fixed; + return &uncore_constraint_fixed; if (type->constraints) { for_each_event_constraint(c, type->constraints) { @@ -3496,7 +526,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags) event->hw.last_tag = ~0ULL; } -static void uncore_pmu_event_read(struct perf_event *event) +void uncore_pmu_event_read(struct perf_event *event) { struct intel_uncore_box *box = uncore_event_to_box(event); uncore_perf_event_update(box, event); @@ -3635,7 +665,7 @@ static struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; -static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu) +static int uncore_pmu_register(struct intel_uncore_pmu *pmu) { int ret; @@ -3758,9 +788,6 @@ fail: return ret; } -static struct pci_driver *uncore_pci_driver; -static bool pcidrv_registered; - /* * add a pci uncore device */ @@ -3770,18 +797,20 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id struct intel_uncore_box *box; struct intel_uncore_type *type; int phys_id; + bool first_box = false; - phys_id = pcibus_to_physid[pdev->bus->number]; + phys_id = uncore_pcibus_to_physid[pdev->bus->number]; if (phys_id < 0) return -ENODEV; if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { - extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev; + int idx = UNCORE_PCI_DEV_IDX(id->driver_data); + uncore_extra_pci_dev[phys_id][idx] = pdev; pci_set_drvdata(pdev, NULL); return 0; } - type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; + type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; box = uncore_alloc_box(type, NUMA_NO_NODE); if (!box) return -ENOMEM; @@ -3803,9 +832,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id pci_set_drvdata(pdev, box); raw_spin_lock(&uncore_box_lock); + if (list_empty(&pmu->box_list)) + first_box = true; list_add_tail(&box->list, &pmu->box_list); raw_spin_unlock(&uncore_box_lock); + if (first_box) + uncore_pmu_register(pmu); return 0; } @@ -3813,13 +846,14 @@ static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + bool last_box = false; box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { - if (extra_pci_dev[phys_id][i] == pdev) { - extra_pci_dev[phys_id][i] = NULL; + if (uncore_extra_pci_dev[phys_id][i] == pdev) { + uncore_extra_pci_dev[phys_id][i] = NULL; break; } } @@ -3835,6 +869,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) raw_spin_lock(&uncore_box_lock); list_del(&box->list); + if (list_empty(&pmu->box_list)) + last_box = true; raw_spin_unlock(&uncore_box_lock); for_each_possible_cpu(cpu) { @@ -3846,6 +882,9 @@ static void uncore_pci_remove(struct pci_dev *pdev) WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); kfree(box); + + if (last_box) + perf_pmu_unregister(&pmu->pmu); } static int __init uncore_pci_init(void) @@ -3854,46 +893,32 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ - ret = snbep_pci2phy_map_init(0x3ce0); - if (ret) - return ret; - pci_uncores = snbep_pci_uncores; - uncore_pci_driver = &snbep_uncore_pci_driver; + ret = snbep_uncore_pci_init(); break; - case 62: /* IvyTown */ - ret = snbep_pci2phy_map_init(0x0e1e); - if (ret) - return ret; - pci_uncores = ivt_pci_uncores; - uncore_pci_driver = &ivt_uncore_pci_driver; + case 62: /* Ivy Bridge-EP */ + ret = ivbep_uncore_pci_init(); + break; + case 63: /* Haswell-EP */ + ret = hswep_uncore_pci_init(); break; case 42: /* Sandy Bridge */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &snb_uncore_pci_driver; + ret = snb_uncore_pci_init(); break; case 58: /* Ivy Bridge */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &ivb_uncore_pci_driver; + ret = ivb_uncore_pci_init(); break; case 60: /* Haswell */ case 69: /* Haswell Celeron */ - ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC); - if (ret) - return ret; - pci_uncores = snb_pci_uncores; - uncore_pci_driver = &hsw_uncore_pci_driver; + ret = hsw_uncore_pci_init(); break; default: return 0; } - ret = uncore_types_init(pci_uncores); + if (ret) + return ret; + + ret = uncore_types_init(uncore_pci_uncores); if (ret) return ret; @@ -3904,7 +929,7 @@ static int __init uncore_pci_init(void) if (ret == 0) pcidrv_registered = true; else - uncore_types_exit(pci_uncores); + uncore_types_exit(uncore_pci_uncores); return ret; } @@ -3914,7 +939,7 @@ static void __init uncore_pci_exit(void) if (pcidrv_registered) { pcidrv_registered = false; pci_unregister_driver(uncore_pci_driver); - uncore_types_exit(pci_uncores); + uncore_types_exit(uncore_pci_uncores); } } @@ -3940,8 +965,8 @@ static void uncore_cpu_dying(int cpu) struct intel_uncore_box *box; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); @@ -3961,8 +986,8 @@ static int uncore_cpu_starting(int cpu) phys_id = topology_physical_package_id(cpu); - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; box = *per_cpu_ptr(pmu->box, cpu); @@ -4002,8 +1027,8 @@ static int uncore_cpu_prepare(int cpu, int phys_id) struct intel_uncore_box *box; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; if (pmu->func_id < 0) @@ -4083,8 +1108,8 @@ static void uncore_event_exit_cpu(int cpu) if (target >= 0) cpumask_set_cpu(target, &uncore_cpu_mask); - uncore_change_context(msr_uncores, cpu, target); - uncore_change_context(pci_uncores, cpu, target); + uncore_change_context(uncore_msr_uncores, cpu, target); + uncore_change_context(uncore_pci_uncores, cpu, target); } static void uncore_event_init_cpu(int cpu) @@ -4099,8 +1124,8 @@ static void uncore_event_init_cpu(int cpu) cpumask_set_cpu(cpu, &uncore_cpu_mask); - uncore_change_context(msr_uncores, -1, cpu); - uncore_change_context(pci_uncores, -1, cpu); + uncore_change_context(uncore_msr_uncores, -1, cpu); + uncore_change_context(uncore_pci_uncores, -1, cpu); } static int uncore_cpu_notifier(struct notifier_block *self, @@ -4160,47 +1185,37 @@ static void __init uncore_cpu_setup(void *dummy) static int __init uncore_cpu_init(void) { - int ret, max_cores; + int ret; - max_cores = boot_cpu_data.x86_max_cores; switch (boot_cpu_data.x86_model) { case 26: /* Nehalem */ case 30: case 37: /* Westmere */ case 44: - msr_uncores = nhm_msr_uncores; + nhm_uncore_cpu_init(); break; case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ - if (snb_uncore_cbox.num_boxes > max_cores) - snb_uncore_cbox.num_boxes = max_cores; - msr_uncores = snb_msr_uncores; + snb_uncore_cpu_init(); break; case 45: /* Sandy Bridge-EP */ - if (snbep_uncore_cbox.num_boxes > max_cores) - snbep_uncore_cbox.num_boxes = max_cores; - msr_uncores = snbep_msr_uncores; + snbep_uncore_cpu_init(); break; case 46: /* Nehalem-EX */ - uncore_nhmex = true; case 47: /* Westmere-EX aka. Xeon E7 */ - if (!uncore_nhmex) - nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; - if (nhmex_uncore_cbox.num_boxes > max_cores) - nhmex_uncore_cbox.num_boxes = max_cores; - msr_uncores = nhmex_msr_uncores; + nhmex_uncore_cpu_init(); break; - case 62: /* IvyTown */ - if (ivt_uncore_cbox.num_boxes > max_cores) - ivt_uncore_cbox.num_boxes = max_cores; - msr_uncores = ivt_msr_uncores; + case 62: /* Ivy Bridge-EP */ + ivbep_uncore_cpu_init(); + break; + case 63: /* Haswell-EP */ + hswep_uncore_cpu_init(); break; - default: return 0; } - ret = uncore_types_init(msr_uncores); + ret = uncore_types_init(uncore_msr_uncores); if (ret) return ret; @@ -4213,16 +1228,8 @@ static int __init uncore_pmus_register(void) struct intel_uncore_type *type; int i, j; - for (i = 0; msr_uncores[i]; i++) { - type = msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - uncore_pmu_register(pmu); - } - } - - for (i = 0; pci_uncores[i]; i++) { - type = pci_uncores[i]; + for (i = 0; uncore_msr_uncores[i]; i++) { + type = uncore_msr_uncores[i]; for (j = 0; j < type->num_boxes; j++) { pmu = &type->pmus[j]; uncore_pmu_register(pmu); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 90236f0c94a9..18eb78bbdd10 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -24,395 +24,6 @@ #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) -/* SNB event control */ -#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff -#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 -#define SNB_UNC_CTL_EDGE_DET (1 << 18) -#define SNB_UNC_CTL_EN (1 << 22) -#define SNB_UNC_CTL_INVERT (1 << 23) -#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 -#define NHM_UNC_CTL_CMASK_MASK 0xff000000 -#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) - -#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ - SNB_UNC_CTL_UMASK_MASK | \ - SNB_UNC_CTL_EDGE_DET | \ - SNB_UNC_CTL_INVERT | \ - SNB_UNC_CTL_CMASK_MASK) - -#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ - SNB_UNC_CTL_UMASK_MASK | \ - SNB_UNC_CTL_EDGE_DET | \ - SNB_UNC_CTL_INVERT | \ - NHM_UNC_CTL_CMASK_MASK) - -/* SNB global control register */ -#define SNB_UNC_PERF_GLOBAL_CTL 0x391 -#define SNB_UNC_FIXED_CTR_CTRL 0x394 -#define SNB_UNC_FIXED_CTR 0x395 - -/* SNB uncore global control */ -#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) -#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) - -/* SNB Cbo register */ -#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 -#define SNB_UNC_CBO_0_PER_CTR0 0x706 -#define SNB_UNC_CBO_MSR_OFFSET 0x10 - -/* NHM global control register */ -#define NHM_UNC_PERF_GLOBAL_CTL 0x391 -#define NHM_UNC_FIXED_CTR 0x394 -#define NHM_UNC_FIXED_CTR_CTRL 0x395 - -/* NHM uncore global control */ -#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) -#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) - -/* NHM uncore register */ -#define NHM_UNC_PERFEVTSEL0 0x3c0 -#define NHM_UNC_UNCORE_PMC0 0x3b0 - -/* SNB-EP Box level control */ -#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) -#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) -#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) -#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) -#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ - SNBEP_PMON_BOX_CTL_RST_CTRS | \ - SNBEP_PMON_BOX_CTL_FRZ_EN) -/* SNB-EP event control */ -#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff -#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 -#define SNBEP_PMON_CTL_RST (1 << 17) -#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) -#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) -#define SNBEP_PMON_CTL_EN (1 << 22) -#define SNBEP_PMON_CTL_INVERT (1 << 23) -#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 -#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_PMON_CTL_TRESH_MASK) - -/* SNB-EP Ubox event control */ -#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 -#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_U_MSR_PMON_CTL_TRESH_MASK) - -#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) -#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ - SNBEP_CBO_PMON_CTL_TID_EN) - -/* SNB-EP PCU event control */ -#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 -#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 -#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) -#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) -#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_EV_SEL_EXT | \ - SNBEP_PMON_CTL_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) - -#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_RAW_EVENT_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT) - -/* SNB-EP pci control register */ -#define SNBEP_PCI_PMON_BOX_CTL 0xf4 -#define SNBEP_PCI_PMON_CTL0 0xd8 -/* SNB-EP pci counter register */ -#define SNBEP_PCI_PMON_CTR0 0xa0 - -/* SNB-EP home agent register */ -#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 -#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 -#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 -/* SNB-EP memory controller register */ -#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 -#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 -/* SNB-EP QPI register */ -#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 -#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c -#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 -#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c - -/* SNB-EP Ubox register */ -#define SNBEP_U_MSR_PMON_CTR0 0xc16 -#define SNBEP_U_MSR_PMON_CTL0 0xc10 - -#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 -#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 - -/* SNB-EP Cbo register */ -#define SNBEP_C0_MSR_PMON_CTR0 0xd16 -#define SNBEP_C0_MSR_PMON_CTL0 0xd10 -#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 -#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 -#define SNBEP_CBO_MSR_OFFSET 0x20 - -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 - -#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ - .event = (e), \ - .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ - .config_mask = (m), \ - .idx = (i) \ -} - -/* SNB-EP PCU register */ -#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 -#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 -#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 -#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 -#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff -#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc -#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd - -/* IVT event control */ -#define IVT_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ - SNBEP_PMON_BOX_CTL_RST_CTRS) -#define IVT_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PMON_CTL_TRESH_MASK) -/* IVT Ubox */ -#define IVT_U_MSR_PMON_GLOBAL_CTL 0xc00 -#define IVT_U_PMON_GLOBAL_FRZ_ALL (1 << 31) -#define IVT_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) - -#define IVT_U_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_UMASK_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_U_MSR_PMON_CTL_TRESH_MASK) -/* IVT Cbo */ -#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK (IVT_PMON_RAW_EVENT_MASK | \ - SNBEP_CBO_PMON_CTL_TID_EN) - -#define IVT_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) -#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) -#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) -#define IVT_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) -#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) -#define IVT_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) -#define IVT_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) -#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC (0x1ULL << 63) - -/* IVT home agent */ -#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) -#define IVT_HA_PCI_PMON_RAW_EVENT_MASK \ - (IVT_PMON_RAW_EVENT_MASK | \ - IVT_HA_PCI_PMON_CTL_Q_OCC_RST) -/* IVT PCU */ -#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \ - (SNBEP_PMON_CTL_EV_SEL_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ - SNBEP_PMON_CTL_EDGE_DET | \ - SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ - SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) -/* IVT QPI */ -#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \ - (IVT_PMON_RAW_EVENT_MASK | \ - SNBEP_PMON_CTL_EV_SEL_EXT) - -/* NHM-EX event control */ -#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff -#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 -#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) -#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) -#define NHMEX_PMON_CTL_PMI_EN (1 << 20) -#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) -#define NHMEX_PMON_CTL_INVERT (1 << 23) -#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 -#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ - NHMEX_PMON_CTL_UMASK_MASK | \ - NHMEX_PMON_CTL_EDGE_DET | \ - NHMEX_PMON_CTL_INVERT | \ - NHMEX_PMON_CTL_TRESH_MASK) - -/* NHM-EX Ubox */ -#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 -#define NHMEX_U_MSR_PMON_CTR 0xc11 -#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 - -#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) -#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e -#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) -#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) -#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) - -#define NHMEX_U_PMON_RAW_EVENT_MASK \ - (NHMEX_PMON_CTL_EV_SEL_MASK | \ - NHMEX_PMON_CTL_EDGE_DET) - -/* NHM-EX Cbox */ -#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 -#define NHMEX_C0_MSR_PMON_CTR0 0xd11 -#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 -#define NHMEX_C_MSR_OFFSET 0x20 - -/* NHM-EX Bbox */ -#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 -#define NHMEX_B0_MSR_PMON_CTR0 0xc31 -#define NHMEX_B0_MSR_PMON_CTL0 0xc30 -#define NHMEX_B_MSR_OFFSET 0x40 -#define NHMEX_B0_MSR_MATCH 0xe45 -#define NHMEX_B0_MSR_MASK 0xe46 -#define NHMEX_B1_MSR_MATCH 0xe4d -#define NHMEX_B1_MSR_MASK 0xe4e - -#define NHMEX_B_PMON_CTL_EN (1 << 0) -#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 -#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ - (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) -#define NHMEX_B_PMON_CTR_SHIFT 6 -#define NHMEX_B_PMON_CTR_MASK \ - (0x3 << NHMEX_B_PMON_CTR_SHIFT) -#define NHMEX_B_PMON_RAW_EVENT_MASK \ - (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ - NHMEX_B_PMON_CTR_MASK) - -/* NHM-EX Sbox */ -#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 -#define NHMEX_S0_MSR_PMON_CTR0 0xc51 -#define NHMEX_S0_MSR_PMON_CTL0 0xc50 -#define NHMEX_S_MSR_OFFSET 0x80 -#define NHMEX_S0_MSR_MM_CFG 0xe48 -#define NHMEX_S0_MSR_MATCH 0xe49 -#define NHMEX_S0_MSR_MASK 0xe4a -#define NHMEX_S1_MSR_MM_CFG 0xe58 -#define NHMEX_S1_MSR_MATCH 0xe59 -#define NHMEX_S1_MSR_MASK 0xe5a - -#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) -#define NHMEX_S_EVENT_TO_R_PROG_EV 0 - -/* NHM-EX Mbox */ -#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 -#define NHMEX_M0_MSR_PMU_DSP 0xca5 -#define NHMEX_M0_MSR_PMU_ISS 0xca6 -#define NHMEX_M0_MSR_PMU_MAP 0xca7 -#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 -#define NHMEX_M0_MSR_PMU_PGT 0xca9 -#define NHMEX_M0_MSR_PMU_PLD 0xcaa -#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab -#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 -#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 -#define NHMEX_M_MSR_OFFSET 0x40 -#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 -#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c - -#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) -#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL -#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL -#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 - -#define NHMEX_M_PMON_CTL_EN (1 << 0) -#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) -#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 -#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ - (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) -#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 -#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ - (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) -#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) -#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) -#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 -#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ - (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) -#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 -#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ - (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) -#define NHMEX_M_PMON_RAW_EVENT_MASK \ - (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ - NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ - NHMEX_M_PMON_CTL_WRAP_MODE | \ - NHMEX_M_PMON_CTL_FLAG_MODE | \ - NHMEX_M_PMON_CTL_INC_SEL_MASK | \ - 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) (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) (0x7ULL << (12 + 3 * (n))) - -/* - * use the 9~13 bits to select event If the 7th bit is not set, - * otherwise use the 19~21 bits to select event. - */ -#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) -#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ - NHMEX_M_PMON_CTL_FLAG_MODE) -#define MBOX_INC_SEL_EXTAR_REG(c, r) \ - EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ - MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) -#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ - EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ - MBOX_SET_FLAG_SEL_MASK, \ - (u64)-1, NHMEX_M_##r) - -/* NHM-EX Rbox */ -#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 -#define NHMEX_R_MSR_PMON_CTL0 0xe10 -#define NHMEX_R_MSR_PMON_CNT0 0xe11 -#define NHMEX_R_MSR_OFFSET 0x20 - -#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ - ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) -#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) -#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) -#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ - (((n) < 4 ? 0 : 0x10) + (n) * 4) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ - (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) -#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ - (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) -#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ - (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) - -#define NHMEX_R_PMON_CTL_EN (1 << 0) -#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 -#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ - (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) -#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) -#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK - -/* NHM-EX Wbox */ -#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 -#define NHMEX_W_MSR_PMON_CNT0 0xc90 -#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 -#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 -#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 - -#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) - struct intel_uncore_ops; struct intel_uncore_pmu; struct intel_uncore_box; @@ -505,6 +116,9 @@ struct uncore_event_desc { const char *config; }; +ssize_t uncore_event_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf); + #define INTEL_UNCORE_EVENT_DESC(_name, _config) \ { \ .attr = __ATTR(_name, 0444, uncore_event_show, NULL), \ @@ -522,15 +136,6 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __uncore_##_var##_show, NULL) - -static ssize_t uncore_event_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - struct uncore_event_desc *event = - container_of(attr, struct uncore_event_desc, attr); - return sprintf(buf, "%s", event->config); -} - static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box) { return box->pmu->type->box_ctl; @@ -694,3 +299,41 @@ static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { return (box->phys_id < 0); } + +struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event); +struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu); +struct intel_uncore_box *uncore_event_to_box(struct perf_event *event); +u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event); +void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); +void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); +void uncore_pmu_event_read(struct perf_event *event); +void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event); +struct event_constraint * +uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event); +void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event); +u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx); + +extern struct intel_uncore_type **uncore_msr_uncores; +extern struct intel_uncore_type **uncore_pci_uncores; +extern struct pci_driver *uncore_pci_driver; +extern int uncore_pcibus_to_physid[256]; +extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +extern struct event_constraint uncore_constraint_empty; + +/* perf_event_intel_uncore_snb.c */ +int snb_uncore_pci_init(void); +int ivb_uncore_pci_init(void); +int hsw_uncore_pci_init(void); +void snb_uncore_cpu_init(void); +void nhm_uncore_cpu_init(void); + +/* perf_event_intel_uncore_snbep.c */ +int snbep_uncore_pci_init(void); +void snbep_uncore_cpu_init(void); +int ivbep_uncore_pci_init(void); +void ivbep_uncore_cpu_init(void); +int hswep_uncore_pci_init(void); +void hswep_uncore_cpu_init(void); + +/* perf_event_intel_uncore_nhmex.c */ +void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c new file mode 100644 index 000000000000..2749965afed0 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c @@ -0,0 +1,1221 @@ +/* Nehalem-EX/Westmere-EX uncore support */ +#include "perf_event_intel_uncore.h" + +/* NHM-EX event control */ +#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff +#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 +#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0) +#define NHMEX_PMON_CTL_EDGE_DET (1 << 18) +#define NHMEX_PMON_CTL_PMI_EN (1 << 20) +#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22) +#define NHMEX_PMON_CTL_INVERT (1 << 23) +#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000 +#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_UMASK_MASK | \ + NHMEX_PMON_CTL_EDGE_DET | \ + NHMEX_PMON_CTL_INVERT | \ + NHMEX_PMON_CTL_TRESH_MASK) + +/* NHM-EX Ubox */ +#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define NHMEX_U_MSR_PMON_CTR 0xc11 +#define NHMEX_U_MSR_PMON_EV_SEL 0xc10 + +#define NHMEX_U_PMON_GLOBAL_EN (1 << 0) +#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e +#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28) +#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29) +#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31) + +#define NHMEX_U_PMON_RAW_EVENT_MASK \ + (NHMEX_PMON_CTL_EV_SEL_MASK | \ + NHMEX_PMON_CTL_EDGE_DET) + +/* NHM-EX Cbox */ +#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00 +#define NHMEX_C0_MSR_PMON_CTR0 0xd11 +#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10 +#define NHMEX_C_MSR_OFFSET 0x20 + +/* NHM-EX Bbox */ +#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20 +#define NHMEX_B0_MSR_PMON_CTR0 0xc31 +#define NHMEX_B0_MSR_PMON_CTL0 0xc30 +#define NHMEX_B_MSR_OFFSET 0x40 +#define NHMEX_B0_MSR_MATCH 0xe45 +#define NHMEX_B0_MSR_MASK 0xe46 +#define NHMEX_B1_MSR_MATCH 0xe4d +#define NHMEX_B1_MSR_MASK 0xe4e + +#define NHMEX_B_PMON_CTL_EN (1 << 0) +#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_B_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_B_PMON_CTR_SHIFT 6 +#define NHMEX_B_PMON_CTR_MASK \ + (0x3 << NHMEX_B_PMON_CTR_SHIFT) +#define NHMEX_B_PMON_RAW_EVENT_MASK \ + (NHMEX_B_PMON_CTL_EV_SEL_MASK | \ + NHMEX_B_PMON_CTR_MASK) + +/* NHM-EX Sbox */ +#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40 +#define NHMEX_S0_MSR_PMON_CTR0 0xc51 +#define NHMEX_S0_MSR_PMON_CTL0 0xc50 +#define NHMEX_S_MSR_OFFSET 0x80 +#define NHMEX_S0_MSR_MM_CFG 0xe48 +#define NHMEX_S0_MSR_MATCH 0xe49 +#define NHMEX_S0_MSR_MASK 0xe4a +#define NHMEX_S1_MSR_MM_CFG 0xe58 +#define NHMEX_S1_MSR_MATCH 0xe59 +#define NHMEX_S1_MSR_MASK 0xe5a + +#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63) +#define NHMEX_S_EVENT_TO_R_PROG_EV 0 + +/* NHM-EX Mbox */ +#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0 +#define NHMEX_M0_MSR_PMU_DSP 0xca5 +#define NHMEX_M0_MSR_PMU_ISS 0xca6 +#define NHMEX_M0_MSR_PMU_MAP 0xca7 +#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8 +#define NHMEX_M0_MSR_PMU_PGT 0xca9 +#define NHMEX_M0_MSR_PMU_PLD 0xcaa +#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab +#define NHMEX_M0_MSR_PMU_CTL0 0xcb0 +#define NHMEX_M0_MSR_PMU_CNT0 0xcb1 +#define NHMEX_M_MSR_OFFSET 0x40 +#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54 +#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c + +#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63) +#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL +#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL +#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34 + +#define NHMEX_M_PMON_CTL_EN (1 << 0) +#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1) +#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2 +#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4 +#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \ + (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT) +#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6) +#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7) +#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9 +#define NHMEX_M_PMON_CTL_INC_SEL_MASK \ + (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19 +#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \ + (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) +#define NHMEX_M_PMON_RAW_EVENT_MASK \ + (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \ + NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \ + NHMEX_M_PMON_CTL_WRAP_MODE | \ + NHMEX_M_PMON_CTL_FLAG_MODE | \ + NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + 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) (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) (0x7ULL << (12 + 3 * (n))) + +/* + * use the 9~13 bits to select event If the 7th bit is not set, + * otherwise use the 19~21 bits to select event. + */ +#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT) +#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \ + NHMEX_M_PMON_CTL_FLAG_MODE) +#define MBOX_INC_SEL_EXTAR_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r) +#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \ + EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \ + MBOX_SET_FLAG_SEL_MASK, \ + (u64)-1, NHMEX_M_##r) + +/* NHM-EX Rbox */ +#define NHMEX_R_MSR_GLOBAL_CTL 0xe00 +#define NHMEX_R_MSR_PMON_CTL0 0xe10 +#define NHMEX_R_MSR_PMON_CNT0 0xe11 +#define NHMEX_R_MSR_OFFSET 0x20 + +#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \ + ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n)) +#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n)) +#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \ + (((n) < 4 ? 0 : 0x10) + (n) * 4) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \ + (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \ + (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n)) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1) +#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \ + (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2) + +#define NHMEX_R_PMON_CTL_EN (1 << 0) +#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1 +#define NHMEX_R_PMON_CTL_EV_SEL_MASK \ + (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT) +#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6) +#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK + +/* NHM-EX Wbox */ +#define NHMEX_W_MSR_GLOBAL_CTL 0xc80 +#define NHMEX_W_MSR_PMON_CNT0 0xc90 +#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91 +#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394 +#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395 + +#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31) + +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); +DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63"); + +static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) +{ + wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); +} + +static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config &= ~((1ULL << uncore_num_counters(box)) - 1); + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + u64 config; + + if (msr) { + rdmsrl(msr, config); + config |= (1ULL << uncore_num_counters(box)) - 1; + /* WBox has a fixed counter */ + if (uncore_msr_fixed_ctl(box)) + config |= NHMEX_W_PMON_GLOBAL_FIXED_EN; + wrmsrl(msr, config); + } +} + +static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx >= UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0); + else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0) + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); + else + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +#define NHMEX_UNCORE_OPS_COMMON_INIT() \ + .init_box = nhmex_uncore_msr_init_box, \ + .disable_box = nhmex_uncore_msr_disable_box, \ + .enable_box = nhmex_uncore_msr_enable_box, \ + .disable_event = nhmex_uncore_msr_disable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops nhmex_uncore_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_uncore_msr_enable_event, +}; + +static struct attribute *nhmex_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_edge.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_ubox_format_group = { + .name = "format", + .attrs = nhmex_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type nhmex_uncore_ubox = { + .name = "ubox", + .num_counters = 1, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_U_MSR_PMON_EV_SEL, + .perf_ctr = NHMEX_U_MSR_PMON_CTR, + .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_ubox_format_group +}; + +static struct attribute *nhmex_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_cbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_cbox_formats_attr, +}; + +/* msr offset for each instance of cbox */ +static unsigned nhmex_cbox_msr_offsets[] = { + 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, +}; + +static struct intel_uncore_type nhmex_uncore_cbox = { + .name = "cbox", + .num_counters = 6, + .num_boxes = 10, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0, + .perf_ctr = NHMEX_C0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL, + .msr_offsets = nhmex_cbox_msr_offsets, + .pair_ctr_ctl = 1, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static struct uncore_event_desc nhmex_uncore_wbox_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type nhmex_uncore_wbox = { + .name = "wbox", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_W_MSR_PMON_CNT0, + .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0, + .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR, + .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_W_MSR_GLOBAL_CTL, + .pair_ctr_ctl = 1, + .event_descs = nhmex_uncore_wbox_events, + .ops = &nhmex_uncore_ops, + .format_group = &nhmex_uncore_cbox_format_group +}; + +static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int ctr, ev_sel; + + ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >> + NHMEX_B_PMON_CTR_SHIFT; + ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >> + NHMEX_B_PMON_CTL_EV_SEL_SHIFT; + + /* events that do not use the match/mask registers */ + if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) || + (ctr == 2 && ev_sel != 0x4) || ctr == 3) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_B0_MSR_MATCH; + else + reg1->reg = NHMEX_B1_MSR_MATCH; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg + 1, reg2->config); + } + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK)); +} + +/* + * The Bbox has 4 counters, but each counter monitors different events. + * Use bits 6-7 in the event config to select counter. + */ +static struct event_constraint nhmex_uncore_bbox_constraints[] = { + EVENT_CONSTRAINT(0 , 1, 0xc0), + EVENT_CONSTRAINT(0x40, 2, 0xc0), + EVENT_CONSTRAINT(0x80, 4, 0xc0), + EVENT_CONSTRAINT(0xc0, 8, 0xc0), + EVENT_CONSTRAINT_END, +}; + +static struct attribute *nhmex_uncore_bbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_counter.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_bbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_bbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_bbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_bbox_msr_enable_event, + .hw_config = nhmex_bbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_bbox = { + .name = "bbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_B0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_B0_MSR_PMON_CTR0, + .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_B_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .constraints = nhmex_uncore_bbox_constraints, + .ops = &nhmex_uncore_bbox_ops, + .format_group = &nhmex_uncore_bbox_format_group +}; + +static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + /* only TO_R_PROG_EV event uses the match/mask register */ + if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) != + NHMEX_S_EVENT_TO_R_PROG_EV) + return 0; + + if (box->pmu->pmu_idx == 0) + reg1->reg = NHMEX_S0_MSR_MM_CFG; + else + reg1->reg = NHMEX_S1_MSR_MM_CFG; + reg1->idx = 0; + reg1->config = event->attr.config1; + reg2->config = event->attr.config2; + return 0; +} + +static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + wrmsrl(reg1->reg, 0); + wrmsrl(reg1->reg + 1, reg1->config); + wrmsrl(reg1->reg + 2, reg2->config); + wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN); + } + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22); +} + +static struct attribute *nhmex_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_match.attr, + &format_attr_mask.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_sbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_ops nhmex_uncore_sbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_sbox_msr_enable_event, + .hw_config = nhmex_sbox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_S0_MSR_PMON_CTL0, + .perf_ctr = NHMEX_S0_MSR_PMON_CTR0, + .event_mask = NHMEX_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL, + .msr_offset = NHMEX_S_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 1, + .ops = &nhmex_uncore_sbox_ops, + .format_group = &nhmex_uncore_sbox_format_group +}; + +enum { + EXTRA_REG_NHMEX_M_FILTER, + EXTRA_REG_NHMEX_M_DSP, + EXTRA_REG_NHMEX_M_ISS, + EXTRA_REG_NHMEX_M_MAP, + EXTRA_REG_NHMEX_M_MSC_THR, + EXTRA_REG_NHMEX_M_PGT, + EXTRA_REG_NHMEX_M_PLD, + EXTRA_REG_NHMEX_M_ZDP_CTL_FVC, +}; + +static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { + MBOX_INC_SEL_EXTAR_REG(0x0, DSP), + MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR), + MBOX_INC_SEL_EXTAR_REG(0x9, ISS), + /* event 0xa uses two extra registers */ + MBOX_INC_SEL_EXTAR_REG(0xa, ISS), + MBOX_INC_SEL_EXTAR_REG(0xa, PLD), + MBOX_INC_SEL_EXTAR_REG(0xb, PLD), + /* events 0xd ~ 0x10 use the same extra register */ + MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC), + MBOX_INC_SEL_EXTAR_REG(0x16, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT), + MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP), + EVENT_EXTRA_END +}; + +/* Nehalem-EX or Westmere-EX ? */ +static bool uncore_nhmex; + +static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + bool ret = false; + u64 mask; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (!atomic_read(&er->ref) || er->config == config) { + atomic_inc(&er->ref); + er->config = config; + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; + } + /* + * The ZDP_CTL_FVC MSR has 4 fields which are used to control + * events 0xd ~ 0x10. Besides these 4 fields, there are additional + * fields which are shared. + */ + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (WARN_ON_ONCE(idx >= 4)) + return false; + + /* mask of the shared fields */ + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK; + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + + raw_spin_lock_irqsave(&er->lock, flags); + /* add mask of the non-shared field if it's in use */ + if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) { + if (uncore_nhmex) + mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + } + + if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + if (uncore_nhmex) + mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK | + NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK | + WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + er->config &= ~mask; + er->config |= (config & mask); + ret = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + return ret; +} + +static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + er = &box->shared_regs[idx]; + atomic_dec(&er->ref); + return; + } + + idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + atomic_sub(1 << (idx * 8), &er->ref); +} + +static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8); + u64 config = reg1->config; + + /* get the non-shared control bits and shift them */ + idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (uncore_nhmex) + config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + else + config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx); + if (new_idx > orig_idx) { + idx = new_idx - orig_idx; + config <<= 3 * idx; + } else { + idx = orig_idx - new_idx; + config >>= 3 * idx; + } + + /* add the shared control bits back */ + if (uncore_nhmex) + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + else + config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config; + if (modify) { + /* adjust the main event selector */ + if (new_idx > orig_idx) + hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + else + hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT; + reg1->config = config; + reg1->idx = ~0xff | new_idx; + } + return config; +} + +static struct event_constraint * +nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int i, idx[2], alloc = 0; + u64 config1 = reg1->config; + + idx[0] = __BITS_VALUE(reg1->idx, 0, 8); + idx[1] = __BITS_VALUE(reg1->idx, 1, 8); +again: + for (i = 0; i < 2; i++) { + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + idx[i] = 0xff; + + if (idx[i] == 0xff) + continue; + + if (!nhmex_mbox_get_shared_reg(box, idx[i], + __BITS_VALUE(config1, i, 32))) + goto fail; + alloc |= (0x1 << i); + } + + /* for the match/mask registers */ + if (reg2->idx != EXTRA_REG_NONE && + (uncore_box_is_fake(box) || !reg2->alloc) && + !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config)) + goto fail; + + /* + * If it's a fake box -- as per validate_{group,event}() we + * shouldn't touch event state and we can avoid doing so + * since both will only call get_event_constraints() once + * on each event, this avoids the need for reg->alloc. + */ + if (!uncore_box_is_fake(box)) { + if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) + nhmex_mbox_alter_er(event, idx[0], true); + reg1->alloc |= alloc; + if (reg2->idx != EXTRA_REG_NONE) + reg2->alloc = 1; + } + return NULL; +fail: + if (idx[0] != 0xff && !(alloc & 0x1) && + idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) { + /* + * events 0xd ~ 0x10 are functional identical, but are + * controlled by different fields in the ZDP_CTL_FVC + * register. If we failed to take one field, try the + * rest 3 choices. + */ + BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff); + idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + idx[0] = (idx[0] + 1) % 4; + idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC; + if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) { + config1 = nhmex_mbox_alter_er(event, idx[0], false); + goto again; + } + } + + if (alloc & 0x1) + nhmex_mbox_put_shared_reg(box, idx[0]); + if (alloc & 0x2) + nhmex_mbox_put_shared_reg(box, idx[1]); + return &uncore_constraint_empty; +} + +static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + + if (uncore_box_is_fake(box)) + return; + + if (reg1->alloc & 0x1) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8)); + if (reg1->alloc & 0x2) + nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8)); + reg1->alloc = 0; + + if (reg2->alloc) { + nhmex_mbox_put_shared_reg(box, reg2->idx); + reg2->alloc = 0; + } +} + +static int nhmex_mbox_extra_reg_idx(struct extra_reg *er) +{ + if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return er->idx; + return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd; +} + +static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_type *type = box->pmu->type; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + struct extra_reg *er; + unsigned msr; + int reg_idx = 0; + /* + * The mbox events may require 2 extra MSRs at the most. But only + * the lower 32 bits in these MSRs are significant, so we can use + * config1 to pass two MSRs' config. + */ + for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + if (event->attr.config1 & ~er->valid_mask) + return -EINVAL; + + msr = er->msr + type->msr_offset * box->pmu->pmu_idx; + if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff)) + return -EINVAL; + + /* always use the 32~63 bits to pass the PLD config */ + if (er->idx == EXTRA_REG_NHMEX_M_PLD) + reg_idx = 1; + else if (WARN_ON_ONCE(reg_idx > 0)) + return -EINVAL; + + reg1->idx &= ~(0xff << (reg_idx * 8)); + reg1->reg &= ~(0xffff << (reg_idx * 16)); + reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8); + reg1->reg |= msr << (reg_idx * 16); + reg1->config = event->attr.config1; + reg_idx++; + } + /* + * The mbox only provides ability to perform address matching + * for the PLD events. + */ + if (reg_idx == 2) { + reg2->idx = EXTRA_REG_NHMEX_M_FILTER; + if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN) + reg2->config = event->attr.config2; + else + reg2->config = ~0ULL; + if (box->pmu->pmu_idx == 0) + reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG; + else + reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG; + } + return 0; +} + +static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) + return box->shared_regs[idx].config; + + er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC]; + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + return config; +} + +static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx; + + idx = __BITS_VALUE(reg1->idx, 0, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 0, 16), + nhmex_mbox_shared_reg_config(box, idx)); + idx = __BITS_VALUE(reg1->idx, 1, 8); + if (idx != 0xff) + wrmsrl(__BITS_VALUE(reg1->reg, 1, 16), + nhmex_mbox_shared_reg_config(box, idx)); + + if (reg2->idx != EXTRA_REG_NONE) { + wrmsrl(reg2->reg, 0); + if (reg2->config != ~0ULL) { + wrmsrl(reg2->reg + 1, + reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK); + wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK & + (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT)); + wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN); + } + } + + wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0); +} + +DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3"); +DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5"); +DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6"); +DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7"); +DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13"); +DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61"); +DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63"); + +static struct attribute *nhmex_uncore_mbox_formats_attr[] = { + &format_attr_count_mode.attr, + &format_attr_storage_mode.attr, + &format_attr_wrap_mode.attr, + &format_attr_flag_mode.attr, + &format_attr_inc_sel.attr, + &format_attr_set_flag_sel.attr, + &format_attr_filter_cfg_en.attr, + &format_attr_filter_match.attr, + &format_attr_filter_mask.attr, + &format_attr_dsp.attr, + &format_attr_thr.attr, + &format_attr_fvc.attr, + &format_attr_pgt.attr, + &format_attr_map.attr, + &format_attr_iss.attr, + &format_attr_pld.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_mbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_mbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc wsmex_uncore_mbox_events[] = { + INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"), + INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_mbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_mbox_msr_enable_event, + .hw_config = nhmex_mbox_hw_config, + .get_constraint = nhmex_mbox_get_constraint, + .put_constraint = nhmex_mbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_mbox = { + .name = "mbox", + .num_counters = 6, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_M0_MSR_PMU_CTL0, + .perf_ctr = NHMEX_M0_MSR_PMU_CNT0, + .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_M_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 8, + .event_descs = nhmex_uncore_mbox_events, + .ops = &nhmex_uncore_mbox_ops, + .format_group = &nhmex_uncore_mbox_format_group, +}; + +static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + /* adjust the main event selector and extra register index */ + if (reg1->idx % 2) { + reg1->idx--; + hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } else { + reg1->idx++; + hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + } + + /* adjust extra register config */ + switch (reg1->idx % 6) { + case 2: + /* shift the 8~15 bits to the 0~7 bits */ + reg1->config >>= 8; + break; + case 3: + /* shift the 0~7 bits to the 8~15 bits */ + reg1->config <<= 8; + break; + } +} + +/* + * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7. + * An event set consists of 6 events, the 3rd and 4th events in + * an event set use the same extra register. So an event set uses + * 5 extra registers. + */ +static struct event_constraint * +nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + struct intel_uncore_extra_reg *er; + unsigned long flags; + int idx, er_idx; + u64 config1; + bool ok = false; + + if (!uncore_box_is_fake(box) && reg1->alloc) + return NULL; + + idx = reg1->idx % 6; + config1 = reg1->config; +again: + er_idx = idx; + /* the 3rd and 4th events use the same extra register */ + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + raw_spin_lock_irqsave(&er->lock, flags); + if (idx < 2) { + if (!atomic_read(&er->ref) || er->config == reg1->config) { + atomic_inc(&er->ref); + er->config = reg1->config; + ok = true; + } + } else if (idx == 2 || idx == 3) { + /* + * these two events use different fields in a extra register, + * the 0~7 bits and the 8~15 bits respectively. + */ + u64 mask = 0xff << ((idx - 2) * 8); + if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) || + !((er->config ^ config1) & mask)) { + atomic_add(1 << ((idx - 2) * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + } else { + if (!atomic_read(&er->ref) || + (er->config == (hwc->config >> 32) && + er->config1 == reg1->config && + er->config2 == reg2->config)) { + atomic_inc(&er->ref); + er->config = (hwc->config >> 32); + er->config1 = reg1->config; + er->config2 = reg2->config; + ok = true; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + /* + * The Rbox events are always in pairs. The paired + * events are functional identical, but use different + * extra registers. If we failed to take an extra + * register, try the alternative. + */ + idx ^= 1; + if (idx != reg1->idx % 6) { + if (idx == 2) + config1 >>= 8; + else if (idx == 3) + config1 <<= 8; + goto again; + } + } else { + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx % 6) + nhmex_rbox_alter_er(box, event); + reg1->alloc = 1; + } + return NULL; + } + return &uncore_constraint_empty; +} + +static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct intel_uncore_extra_reg *er; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + int idx, er_idx; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + idx = reg1->idx % 6; + er_idx = idx; + if (er_idx > 2) + er_idx--; + er_idx += (reg1->idx / 6) * 5; + + er = &box->shared_regs[er_idx]; + if (idx == 2 || idx == 3) + atomic_sub(1 << ((idx - 2) * 8), &er->ref); + else + atomic_dec(&er->ref); + + reg1->alloc = 0; +} + +static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct hw_perf_event_extra *reg2 = &event->hw.branch_reg; + int idx; + + idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >> + NHMEX_R_PMON_CTL_EV_SEL_SHIFT; + if (idx >= 0x18) + return -EINVAL; + + reg1->idx = idx; + reg1->config = event->attr.config1; + + switch (idx % 6) { + case 4: + case 5: + hwc->config |= event->attr.config & (~0ULL << 32); + reg2->config = event->attr.config2; + break; + } + return 0; +} + +static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + int idx, port; + + idx = reg1->idx; + port = idx / 6 + box->pmu->pmu_idx * 4; + + switch (idx % 6) { + case 0: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config); + break; + case 1: + wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config); + break; + case 2: + case 3: + wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), + uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); + break; + case 4: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config); + break; + case 5: + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port), + hwc->config >> 32); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config); + wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config); + break; + } + + wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 | + (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK)); +} + +DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63"); +DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15"); +DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31"); + +static struct attribute *nhmex_uncore_rbox_formats_attr[] = { + &format_attr_event5.attr, + &format_attr_xbr_mm_cfg.attr, + &format_attr_xbr_match.attr, + &format_attr_xbr_mask.attr, + &format_attr_qlx_cfg.attr, + &format_attr_iperf_cfg.attr, + NULL, +}; + +static struct attribute_group nhmex_uncore_rbox_format_group = { + .name = "format", + .attrs = nhmex_uncore_rbox_formats_attr, +}; + +static struct uncore_event_desc nhmex_uncore_rbox_events[] = { + INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"), + INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"), + INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhmex_uncore_rbox_ops = { + NHMEX_UNCORE_OPS_COMMON_INIT(), + .enable_event = nhmex_rbox_msr_enable_event, + .hw_config = nhmex_rbox_hw_config, + .get_constraint = nhmex_rbox_get_constraint, + .put_constraint = nhmex_rbox_put_constraint, +}; + +static struct intel_uncore_type nhmex_uncore_rbox = { + .name = "rbox", + .num_counters = 8, + .num_boxes = 2, + .perf_ctr_bits = 48, + .event_ctl = NHMEX_R_MSR_PMON_CTL0, + .perf_ctr = NHMEX_R_MSR_PMON_CNT0, + .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK, + .box_ctl = NHMEX_R_MSR_GLOBAL_CTL, + .msr_offset = NHMEX_R_MSR_OFFSET, + .pair_ctr_ctl = 1, + .num_shared_regs = 20, + .event_descs = nhmex_uncore_rbox_events, + .ops = &nhmex_uncore_rbox_ops, + .format_group = &nhmex_uncore_rbox_format_group +}; + +static struct intel_uncore_type *nhmex_msr_uncores[] = { + &nhmex_uncore_ubox, + &nhmex_uncore_cbox, + &nhmex_uncore_bbox, + &nhmex_uncore_sbox, + &nhmex_uncore_mbox, + &nhmex_uncore_rbox, + &nhmex_uncore_wbox, + NULL, +}; + +void nhmex_uncore_cpu_init(void) +{ + if (boot_cpu_data.x86_model == 46) + uncore_nhmex = true; + else + nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; + if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = nhmex_msr_uncores; +} +/* end of Nehalem-EX uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c new file mode 100644 index 000000000000..3001015b755c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -0,0 +1,636 @@ +/* Nehalem/SandBridge/Haswell uncore support */ +#include "perf_event_intel_uncore.h" + +/* SNB event control */ +#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff +#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 +#define SNB_UNC_CTL_EDGE_DET (1 << 18) +#define SNB_UNC_CTL_EN (1 << 22) +#define SNB_UNC_CTL_INVERT (1 << 23) +#define SNB_UNC_CTL_CMASK_MASK 0x1f000000 +#define NHM_UNC_CTL_CMASK_MASK 0xff000000 +#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0) + +#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + SNB_UNC_CTL_CMASK_MASK) + +#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + SNB_UNC_CTL_UMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET | \ + SNB_UNC_CTL_INVERT | \ + NHM_UNC_CTL_CMASK_MASK) + +/* SNB global control register */ +#define SNB_UNC_PERF_GLOBAL_CTL 0x391 +#define SNB_UNC_FIXED_CTR_CTRL 0x394 +#define SNB_UNC_FIXED_CTR 0x395 + +/* SNB uncore global control */ +#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1) +#define SNB_UNC_GLOBAL_CTL_EN (1 << 29) + +/* SNB Cbo register */ +#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700 +#define SNB_UNC_CBO_0_PER_CTR0 0x706 +#define SNB_UNC_CBO_MSR_OFFSET 0x10 + +/* NHM global control register */ +#define NHM_UNC_PERF_GLOBAL_CTL 0x391 +#define NHM_UNC_FIXED_CTR 0x394 +#define NHM_UNC_FIXED_CTR_CTRL 0x395 + +/* NHM uncore global control */ +#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1) +#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32) + +/* NHM uncore register */ +#define NHM_UNC_PERFEVTSEL0 0x3c0 +#define NHM_UNC_UNCORE_PMC0 0x3b0 + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31"); + +/* Sandy Bridge uncore support */ +static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, SNB_UNC_CTL_EN); +} + +static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + wrmsrl(event->hw.config_base, 0); +} + +static void snb_uncore_msr_init_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) { + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); + } +} + +static struct uncore_event_desc snb_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + { /* end: all zeroes */ }, +}; + +static struct attribute *snb_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask5.attr, + NULL, +}; + +static struct attribute_group snb_uncore_format_group = { + .name = "format", + .attrs = snb_uncore_formats_attr, +}; + +static struct intel_uncore_ops snb_uncore_msr_ops = { + .init_box = snb_uncore_msr_init_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = snb_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct event_constraint snb_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x80, 0x1), + UNCORE_EVENT_CONSTRAINT(0x83, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snb_uncore_cbox = { + .name = "cbox", + .num_counters = 2, + .num_boxes = 4, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNB_UNC_CBO_0_PER_CTR0, + .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0, + .fixed_ctr = SNB_UNC_FIXED_CTR, + .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL, + .single_fixed = 1, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_CBO_MSR_OFFSET, + .constraints = snb_uncore_cbox_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, + .event_descs = snb_uncore_events, +}; + +static struct intel_uncore_type *snb_msr_uncores[] = { + &snb_uncore_cbox, + NULL, +}; + +void snb_uncore_cpu_init(void) +{ + uncore_msr_uncores = snb_msr_uncores; + if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; +} + +enum { + SNB_PCI_UNCORE_IMC, +}; + +static struct uncore_event_desc snb_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"), + INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"), + INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + + { /* end: all zeroes */ }, +}; + +#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff +#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48 + +/* page size multiple covering all config regs */ +#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000 + +#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1 +#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2 +#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 +#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE + +static struct attribute *snb_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group snb_uncore_imc_format_group = { + .name = "format", + .attrs = snb_uncore_imc_formats_attr, +}; + +static void snb_uncore_imc_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET; + resource_size_t addr; + u32 pci_dword; + + pci_read_config_dword(pdev, where, &pci_dword); + addr = pci_dword; + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + pci_read_config_dword(pdev, where + 4, &pci_dword); + addr |= ((resource_size_t)pci_dword << 32); +#endif + + addr &= ~(PAGE_SIZE - 1); + + box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE); + box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; +} + +static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_disable_box(struct intel_uncore_box *box) +{} + +static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{} + +static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + return (u64)*(unsigned int *)(box->io_addr + hwc->event_base); +} + +/* + * custom event_init() function because we define our own fixed, free + * running counters, so we do not want to conflict with generic uncore + * logic. Also simplifies processing + */ +static int snb_uncore_imc_event_init(struct perf_event *event) +{ + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + struct hw_perf_event *hwc = &event->hw; + u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK; + int idx, base; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + pmu = uncore_event_to_pmu(event); + /* no device found for this pmu */ + if (pmu->func_id < 0) + return -ENOENT; + + /* Sampling not supported yet */ + if (hwc->sample_period) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + /* + * Place all uncore events for a particular physical package + * onto a single cpu + */ + if (event->cpu < 0) + return -EINVAL; + + /* check only supported bits are set */ + if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK) + return -EINVAL; + + box = uncore_pmu_to_box(pmu, event->cpu); + if (!box || box->cpu < 0) + return -EINVAL; + + event->cpu = box->cpu; + + event->hw.idx = -1; + event->hw.last_tag = ~0ULL; + event->hw.extra_reg.idx = EXTRA_REG_NONE; + event->hw.branch_reg.idx = EXTRA_REG_NONE; + /* + * check event is known (whitelist, determines counter) + */ + switch (cfg) { + case SNB_UNCORE_PCI_IMC_DATA_READS: + base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE; + idx = UNCORE_PMC_IDX_FIXED; + break; + case SNB_UNCORE_PCI_IMC_DATA_WRITES: + base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; + idx = UNCORE_PMC_IDX_FIXED + 1; + break; + default: + return -EINVAL; + } + + /* must be done before validate_group */ + event->hw.event_base = base; + event->hw.config = cfg; + event->hw.idx = idx; + + /* no group validation needed, we have free running counters */ + + return 0; +} + +static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + return 0; +} + +static void snb_uncore_imc_event_start(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + u64 count; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + event->hw.state = 0; + box->n_active++; + + list_add_tail(&event->active_entry, &box->active_list); + + count = snb_uncore_imc_read_counter(box, event); + local64_set(&event->hw.prev_count, count); + + if (box->n_active == 1) + uncore_pmu_start_hrtimer(box); +} + +static void snb_uncore_imc_event_stop(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!(hwc->state & PERF_HES_STOPPED)) { + box->n_active--; + + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + list_del(&event->active_entry); + + if (box->n_active == 0) + uncore_pmu_cancel_hrtimer(box); + } + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + /* + * Drain the remaining delta count out of a event + * that we are disabling: + */ + uncore_perf_event_update(box, event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int snb_uncore_imc_event_add(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + struct hw_perf_event *hwc = &event->hw; + + if (!box) + return -ENODEV; + + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + if (!(flags & PERF_EF_START)) + hwc->state |= PERF_HES_ARCH; + + snb_uncore_imc_event_start(event, 0); + + box->n_events++; + + return 0; +} + +static void snb_uncore_imc_event_del(struct perf_event *event, int flags) +{ + struct intel_uncore_box *box = uncore_event_to_box(event); + int i; + + snb_uncore_imc_event_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < box->n_events; i++) { + if (event == box->event_list[i]) { + --box->n_events; + break; + } + } +} + +static int snb_pci2phy_map_init(int devid) +{ + struct pci_dev *dev = NULL; + int bus; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); + if (!dev) + return -ENOTTY; + + bus = dev->bus->number; + + uncore_pcibus_to_physid[bus] = 0; + + pci_dev_put(dev); + + return 0; +} + +static struct pmu snb_uncore_imc_pmu = { + .task_ctx_nr = perf_invalid_context, + .event_init = snb_uncore_imc_event_init, + .add = snb_uncore_imc_event_add, + .del = snb_uncore_imc_event_del, + .start = snb_uncore_imc_event_start, + .stop = snb_uncore_imc_event_stop, + .read = uncore_pmu_event_read, +}; + +static struct intel_uncore_ops snb_uncore_imc_ops = { + .init_box = snb_uncore_imc_init_box, + .enable_box = snb_uncore_imc_enable_box, + .disable_box = snb_uncore_imc_disable_box, + .disable_event = snb_uncore_imc_disable_event, + .enable_event = snb_uncore_imc_enable_event, + .hw_config = snb_uncore_imc_hw_config, + .read_counter = snb_uncore_imc_read_counter, +}; + +static struct intel_uncore_type snb_uncore_imc = { + .name = "imc", + .num_counters = 2, + .num_boxes = 1, + .fixed_ctr_bits = 32, + .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE, + .event_descs = snb_uncore_imc_events, + .format_group = &snb_uncore_imc_format_group, + .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK, + .ops = &snb_uncore_imc_ops, + .pmu = &snb_uncore_imc_pmu, +}; + +static struct intel_uncore_type *snb_pci_uncores[] = { + [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc, + NULL, +}; + +static const struct pci_device_id snb_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static const struct pci_device_id ivb_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static const struct pci_device_id hsw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + +static struct pci_driver snb_uncore_pci_driver = { + .name = "snb_uncore", + .id_table = snb_uncore_pci_ids, +}; + +static struct pci_driver ivb_uncore_pci_driver = { + .name = "ivb_uncore", + .id_table = ivb_uncore_pci_ids, +}; + +static struct pci_driver hsw_uncore_pci_driver = { + .name = "hsw_uncore", + .id_table = hsw_uncore_pci_ids, +}; + +struct imc_uncore_pci_dev { + __u32 pci_id; + struct pci_driver *driver; +}; +#define IMC_DEV(a, d) \ + { .pci_id = PCI_DEVICE_ID_INTEL_##a, .driver = (d) } + +static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { + IMC_DEV(SNB_IMC, &snb_uncore_pci_driver), + IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver), /* 3rd Gen Core processor */ + IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ + IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ + { /* end marker */ } +}; + + +#define for_each_imc_pci_id(x, t) \ + for (x = (t); (x)->pci_id; x++) + +static struct pci_driver *imc_uncore_find_dev(void) +{ + const struct imc_uncore_pci_dev *p; + int ret; + + for_each_imc_pci_id(p, desktop_imc_pci_ids) { + ret = snb_pci2phy_map_init(p->pci_id); + if (ret == 0) + return p->driver; + } + return NULL; +} + +static int imc_uncore_pci_init(void) +{ + struct pci_driver *imc_drv = imc_uncore_find_dev(); + + if (!imc_drv) + return -ENODEV; + + uncore_pci_uncores = snb_pci_uncores; + uncore_pci_driver = imc_drv; + + return 0; +} + +int snb_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + +int ivb_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} +int hsw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + +/* end of Sandy Bridge uncore support */ + +/* Nehalem uncore support */ +static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0); +} + +static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC); +} + +static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < UNCORE_PMC_IDX_FIXED) + wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN); + else + wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN); +} + +static struct attribute *nhm_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_cmask8.attr, + NULL, +}; + +static struct attribute_group nhm_uncore_format_group = { + .name = "format", + .attrs = nhm_uncore_formats_attr, +}; + +static struct uncore_event_desc nhm_uncore_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"), + INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"), + INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_ops nhm_uncore_msr_ops = { + .disable_box = nhm_uncore_msr_disable_box, + .enable_box = nhm_uncore_msr_enable_box, + .disable_event = snb_uncore_msr_disable_event, + .enable_event = nhm_uncore_msr_enable_event, + .read_counter = uncore_msr_read_counter, +}; + +static struct intel_uncore_type nhm_uncore = { + .name = "", + .num_counters = 8, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .event_ctl = NHM_UNC_PERFEVTSEL0, + .perf_ctr = NHM_UNC_UNCORE_PMC0, + .fixed_ctr = NHM_UNC_FIXED_CTR, + .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL, + .event_mask = NHM_UNC_RAW_EVENT_MASK, + .event_descs = nhm_uncore_events, + .ops = &nhm_uncore_msr_ops, + .format_group = &nhm_uncore_format_group, +}; + +static struct intel_uncore_type *nhm_msr_uncores[] = { + &nhm_uncore, + NULL, +}; + +void nhm_uncore_cpu_init(void) +{ + uncore_msr_uncores = nhm_msr_uncores; +} + +/* end of Nehalem uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c new file mode 100644 index 000000000000..adf138eac85c --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -0,0 +1,2258 @@ +/* SandyBridge-EP/IvyTown uncore support */ +#include "perf_event_intel_uncore.h" + + +/* SNB-EP Box level control */ +#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) +#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1) +#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8) +#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16) +#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS | \ + SNBEP_PMON_BOX_CTL_FRZ_EN) +/* SNB-EP event control */ +#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff +#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 +#define SNBEP_PMON_CTL_RST (1 << 17) +#define SNBEP_PMON_CTL_EDGE_DET (1 << 18) +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) +#define SNBEP_PMON_CTL_EN (1 << 22) +#define SNBEP_PMON_CTL_INVERT (1 << 23) +#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 +#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PMON_CTL_TRESH_MASK) + +/* SNB-EP Ubox event control */ +#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) + +#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19) +#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* SNB-EP PCU event control */ +#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000 +#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000 +#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30) +#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31) +#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) + +#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + +/* SNB-EP pci control register */ +#define SNBEP_PCI_PMON_BOX_CTL 0xf4 +#define SNBEP_PCI_PMON_CTL0 0xd8 +/* SNB-EP pci counter register */ +#define SNBEP_PCI_PMON_CTR0 0xa0 + +/* SNB-EP home agent register */ +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40 +#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44 +#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48 +/* SNB-EP memory controller register */ +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0 +#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0 +/* SNB-EP QPI register */ +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228 +#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238 +#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c + +/* SNB-EP Ubox register */ +#define SNBEP_U_MSR_PMON_CTR0 0xc16 +#define SNBEP_U_MSR_PMON_CTL0 0xc10 + +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08 +#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09 + +/* SNB-EP Cbo register */ +#define SNBEP_C0_MSR_PMON_CTR0 0xd16 +#define SNBEP_C0_MSR_PMON_CTL0 0xd10 +#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 +#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 +#define SNBEP_CBO_MSR_OFFSET 0x20 + +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 + +#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ + .event = (e), \ + .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ + .config_mask = (m), \ + .idx = (i) \ +} + +/* SNB-EP PCU register */ +#define SNBEP_PCU_MSR_PMON_CTR0 0xc36 +#define SNBEP_PCU_MSR_PMON_CTL0 0xc30 +#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34 +#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff +#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc +#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd + +/* IVBEP event control */ +#define IVBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS) +#define IVBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_TRESH_MASK) +/* IVBEP Ubox */ +#define IVBEP_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define IVBEP_U_PMON_GLOBAL_FRZ_ALL (1 << 31) +#define IVBEP_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) + +#define IVBEP_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) +/* IVBEP Cbo */ +#define IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK (IVBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + +/* IVBEP home agent */ +#define IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) +#define IVBEP_HA_PCI_PMON_RAW_EVENT_MASK \ + (IVBEP_PMON_RAW_EVENT_MASK | \ + IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST) +/* IVBEP PCU */ +#define IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +/* IVBEP QPI */ +#define IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK \ + (IVBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + +/* Haswell-EP Ubox */ +#define HSWEP_U_MSR_PMON_CTR0 0x705 +#define HSWEP_U_MSR_PMON_CTL0 0x709 +#define HSWEP_U_MSR_PMON_FILTER 0x707 + +#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703 +#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTR 0x704 + +#define HSWEP_U_MSR_PMON_BOX_FILTER_TID (0x1 << 0) +#define HSWEP_U_MSR_PMON_BOX_FILTER_CID (0x1fULL << 1) +#define HSWEP_U_MSR_PMON_BOX_FILTER_MASK \ + (HSWEP_U_MSR_PMON_BOX_FILTER_TID | \ + HSWEP_U_MSR_PMON_BOX_FILTER_CID) + +/* Haswell-EP CBo */ +#define HSWEP_C0_MSR_PMON_CTR0 0xe08 +#define HSWEP_C0_MSR_PMON_CTL0 0xe01 +#define HSWEP_C0_MSR_PMON_BOX_CTL 0xe00 +#define HSWEP_C0_MSR_PMON_BOX_FILTER0 0xe05 +#define HSWEP_CBO_MSR_OFFSET 0x10 + + +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_TID (0x3fULL << 0) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 6) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x7fULL << 17) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63) + + +/* Haswell-EP Sbox */ +#define HSWEP_S0_MSR_PMON_CTR0 0x726 +#define HSWEP_S0_MSR_PMON_CTL0 0x721 +#define HSWEP_S0_MSR_PMON_BOX_CTL 0x720 +#define HSWEP_SBOX_MSR_OFFSET 0xa +#define HSWEP_S_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +/* Haswell-EP PCU */ +#define HSWEP_PCU_MSR_PMON_CTR0 0x717 +#define HSWEP_PCU_MSR_PMON_CTL0 0x711 +#define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 +#define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 + + +DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); +DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); +DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); +DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); +DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); +DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); +DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); +DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); +DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); +DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); + +static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config = 0; + + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config |= SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } +} + +static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + u32 config = 0; + + if (!pci_read_config_dword(pdev, box_ctl, &config)) { + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + pci_write_config_dword(pdev, box_ctl, config); + } +} + +static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, hwc->config_base, hwc->config); +} + +static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count); + pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1); + + return count; +} + +static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); +} + +static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config |= SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + } +} + +static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + u64 config; + unsigned msr; + + msr = uncore_msr_box_ctl(box); + if (msr) { + rdmsrl(msr, config); + config &= ~SNBEP_PMON_BOX_CTL_FRZ; + wrmsrl(msr, config); + } +} + +static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) + wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); +} + +static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + + if (msr) + wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); +} + +static struct attribute *snbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *snbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *snbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_nid.attr, + &format_attr_filter_state.attr, + &format_attr_filter_opc.attr, + NULL, +}; + +static struct attribute *snbep_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *snbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, + NULL, +}; + +static struct uncore_event_desc snbep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + { /* end: all zeroes */ }, +}; + +static struct uncore_event_desc snbep_uncore_qpi_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), + INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), + { /* end: all zeroes */ }, +}; + +static struct attribute_group snbep_uncore_format_group = { + .name = "format", + .attrs = snbep_uncore_formats_attr, +}; + +static struct attribute_group snbep_uncore_ubox_format_group = { + .name = "format", + .attrs = snbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group snbep_uncore_cbox_format_group = { + .name = "format", + .attrs = snbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group snbep_uncore_pcu_format_group = { + .name = "format", + .attrs = snbep_uncore_pcu_formats_attr, +}; + +static struct attribute_group snbep_uncore_qpi_format_group = { + .name = "format", + .attrs = snbep_uncore_qpi_formats_attr, +}; + +#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops snbep_uncore_msr_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_pci_init_box, \ + .disable_box = snbep_uncore_pci_disable_box, \ + .enable_box = snbep_uncore_pci_enable_box, \ + .disable_event = snbep_uncore_pci_disable_event, \ + .read_counter = snbep_uncore_pci_read_counter + +static struct intel_uncore_ops snbep_uncore_pci_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_uncore_pci_enable_event, \ +}; + +static struct event_constraint snbep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x02, 0x3), + UNCORE_EVENT_CONSTRAINT(0x04, 0x3), + UNCORE_EVENT_CONSTRAINT(0x05, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1b, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1c, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1d, 0xc), + UNCORE_EVENT_CONSTRAINT(0x1e, 0xc), + EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct event_constraint snbep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x24, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x30, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type snbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &snbep_uncore_ubox_format_group, +}; + +static struct extra_reg snbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), + EVENT_EXTRA_END +}; + +static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i; + + if (uncore_box_is_fake(box)) + return; + + for (i = 0; i < 5; i++) { + if (reg1->alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + reg1->alloc = 0; +} + +static struct event_constraint * +__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, + u64 (*cbox_filter_mask)(int fields)) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i, alloc = 0; + unsigned long flags; + u64 mask; + + if (reg1->idx == EXTRA_REG_NONE) + return NULL; + + raw_spin_lock_irqsave(&er->lock, flags); + for (i = 0; i < 5; i++) { + if (!(reg1->idx & (0x1 << i))) + continue; + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + continue; + + mask = cbox_filter_mask(0x1 << i); + if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || + !((reg1->config ^ er->config) & mask)) { + atomic_add(1 << (i * 6), &er->ref); + er->config &= ~mask; + er->config |= reg1->config & mask; + alloc |= (0x1 << i); + } else { + break; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + if (i < 5) + goto fail; + + if (!uncore_box_is_fake(box)) + reg1->alloc |= alloc; + + return NULL; +fail: + for (; i >= 0; i--) { + if (alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + return &uncore_constraint_empty; +} + +static u64 snbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x4) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); +} + +static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_cbox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_cbox_hw_config, + .get_constraint = snbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type snbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &snbep_uncore_cbox_ops, + .format_group = &snbep_uncore_cbox_format_group, +}; + +static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 config = reg1->config; + + if (new_idx > reg1->idx) + config <<= 8 * (new_idx - reg1->idx); + else + config >>= 8 * (reg1->idx - new_idx); + + if (modify) { + hwc->config += new_idx - reg1->idx; + reg1->config = config; + reg1->idx = new_idx; + } + return config; +} + +static struct event_constraint * +snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + unsigned long flags; + int idx = reg1->idx; + u64 mask, config1 = reg1->config; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || + (!uncore_box_is_fake(box) && reg1->alloc)) + return NULL; +again: + mask = 0xffULL << (idx * 8); + raw_spin_lock_irqsave(&er->lock, flags); + if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || + !((config1 ^ er->config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + idx = (idx + 1) % 4; + if (idx != reg1->idx) { + config1 = snbep_pcu_alter_er(event, idx, false); + goto again; + } + return &uncore_constraint_empty; + } + + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx) + snbep_pcu_alter_er(event, idx, true); + reg1->alloc = 1; + } + return NULL; +} + +static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + atomic_sub(1 << (reg1->idx * 8), &er->ref); + reg1->alloc = 0; +} + +static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << (reg1->idx * 8)); + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type snbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *snbep_msr_uncores[] = { + &snbep_uncore_ubox, + &snbep_uncore_cbox, + &snbep_uncore_pcu, + NULL, +}; + +void snbep_uncore_cpu_init(void) +{ + if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = snbep_msr_uncores; +} + +enum { + SNBEP_PCI_QPI_PORT0_FILTER, + SNBEP_PCI_QPI_PORT1_FILTER, +}; + +static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { + reg1->idx = 0; + reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; + reg1->config = event->attr.config1; + reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; + reg2->config = event->attr.config2; + } + return 0; +} + +static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; + struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx]; + if (filter_pdev) { + pci_write_config_dword(filter_pdev, reg1->reg, + (u32)reg1->config); + pci_write_config_dword(filter_pdev, reg1->reg + 4, + (u32)(reg1->config >> 32)); + pci_write_config_dword(filter_pdev, reg2->reg, + (u32)reg2->config); + pci_write_config_dword(filter_pdev, reg2->reg + 4, + (u32)(reg2->config >> 32)); + } + } + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops snbep_uncore_qpi_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_qpi_enable_event, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +#define SNBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &snbep_uncore_pci_ops, \ + .format_group = &snbep_uncore_format_group + +static struct intel_uncore_type snbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .event_descs = snbep_uncore_qpi_events, + .format_group = &snbep_uncore_qpi_format_group, +}; + + +static struct intel_uncore_type snbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type snbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + SNBEP_PCI_UNCORE_HA, + SNBEP_PCI_UNCORE_IMC, + SNBEP_PCI_UNCORE_QPI, + SNBEP_PCI_UNCORE_R2PCIE, + SNBEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *snbep_pci_uncores[] = { + [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, + [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, + [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, + [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, + [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id snbep_uncore_pci_ids[] = { + { /* Home Agent */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), + }, + { /* MC Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), + }, + { /* MC Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), + }, + { /* MC Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), + }, + { /* MC Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), + }, + { /* QPI Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver snbep_uncore_pci_driver = { + .name = "snbep_uncore", + .id_table = snbep_uncore_pci_ids, +}; + +/* + * build pci bus to socket mapping + */ +static int snbep_pci2phy_map_init(int devid) +{ + struct pci_dev *ubox_dev = NULL; + int i, bus, nodeid; + int err = 0; + u32 config = 0; + + while (1) { + /* find the UBOX device */ + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); + if (!ubox_dev) + break; + bus = ubox_dev->bus->number; + /* get the Node ID of the local register */ + err = pci_read_config_dword(ubox_dev, 0x40, &config); + if (err) + break; + nodeid = config; + /* get the Node ID mapping */ + err = pci_read_config_dword(ubox_dev, 0x54, &config); + if (err) + break; + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == ((config >> (3 * i)) & 0x7)) { + uncore_pcibus_to_physid[bus] = i; + break; + } + } + } + + if (!err) { + /* + * For PCI bus with no UBOX device, find the next bus + * that has UBOX device and use its mapping. + */ + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (uncore_pcibus_to_physid[bus] >= 0) + i = uncore_pcibus_to_physid[bus]; + else + uncore_pcibus_to_physid[bus] = i; + } + } + + if (ubox_dev) + pci_dev_put(ubox_dev); + + return err ? pcibios_err_to_errno(err) : 0; +} + +int snbep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x3ce0); + if (ret) + return ret; + uncore_pci_uncores = snbep_pci_uncores; + uncore_pci_driver = &snbep_uncore_pci_driver; + return 0; +} +/* end of Sandy Bridge-EP uncore support */ + +/* IvyTown uncore support */ +static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT); +} + +static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT); +} + +#define IVBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = ivbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops ivbep_uncore_msr_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +static struct intel_uncore_ops ivbep_uncore_pci_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +#define IVBEP_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = IVBEP_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &ivbep_uncore_pci_ops, \ + .format_group = &ivbep_uncore_format_group + +static struct attribute *ivbep_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_link.attr, + &format_attr_filter_state2.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *ivbep_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, + NULL, +}; + +static struct attribute_group ivbep_uncore_format_group = { + .name = "format", + .attrs = ivbep_uncore_formats_attr, +}; + +static struct attribute_group ivbep_uncore_ubox_format_group = { + .name = "format", + .attrs = ivbep_uncore_ubox_formats_attr, +}; + +static struct attribute_group ivbep_uncore_cbox_format_group = { + .name = "format", + .attrs = ivbep_uncore_cbox_formats_attr, +}; + +static struct attribute_group ivbep_uncore_pcu_format_group = { + .name = "format", + .attrs = ivbep_uncore_pcu_formats_attr, +}; + +static struct attribute_group ivbep_uncore_qpi_format_group = { + .name = "format", + .attrs = ivbep_uncore_qpi_formats_attr, +}; + +static struct intel_uncore_type ivbep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = IVBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_ubox_format_group, +}; + +static struct extra_reg ivbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + EVENT_EXTRA_END +}; + +static u64 ivbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) { + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NC; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_C6; + mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC; + } + + return mask; +} + +static struct event_constraint * +ivbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, ivbep_cbox_filter_mask); +} + +static int ivbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = ivbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & ivbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 6, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops ivbep_uncore_cbox_ops = { + .init_box = ivbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = ivbep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = ivbep_cbox_hw_config, + .get_constraint = ivbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 15, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &ivbep_uncore_cbox_ops, + .format_group = &ivbep_uncore_cbox_format_group, +}; + +static struct intel_uncore_ops ivbep_uncore_pcu_ops = { + IVBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_pcu_ops, + .format_group = &ivbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *ivbep_msr_uncores[] = { + &ivbep_uncore_ubox, + &ivbep_uncore_cbox, + &ivbep_uncore_pcu, + NULL, +}; + +void ivbep_uncore_cpu_init(void) +{ + if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = ivbep_msr_uncores; +} + +static struct intel_uncore_type ivbep_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivbep_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = snbep_uncore_imc_events, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +/* registers in IRP boxes are not properly aligned */ +static unsigned ivbep_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4}; +static unsigned ivbep_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0}; + +static void ivbep_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], + hwc->config | SNBEP_PMON_CTL_EN); +} + +static void ivbep_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + + pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], hwc->config); +} + +static u64 ivbep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + u64 count = 0; + + pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx], (u32 *)&count); + pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1); + + return count; +} + +static struct intel_uncore_ops ivbep_uncore_irp_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivbep_uncore_irp_disable_event, + .enable_event = ivbep_uncore_irp_enable_event, + .read_counter = ivbep_uncore_irp_read_counter, +}; + +static struct intel_uncore_type ivbep_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = IVBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivbep_uncore_irp_ops, + .format_group = &ivbep_uncore_format_group, +}; + +static struct intel_uncore_ops ivbep_uncore_qpi_ops = { + .init_box = ivbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_qpi_enable_event, + .read_counter = snbep_uncore_pci_read_counter, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type ivbep_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_qpi_ops, + .format_group = &ivbep_uncore_qpi_format_group, +}; + +static struct intel_uncore_type ivbep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivbep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + IVBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + IVBEP_PCI_UNCORE_HA, + IVBEP_PCI_UNCORE_IMC, + IVBEP_PCI_UNCORE_IRP, + IVBEP_PCI_UNCORE_QPI, + IVBEP_PCI_UNCORE_R2PCIE, + IVBEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *ivbep_pci_uncores[] = { + [IVBEP_PCI_UNCORE_HA] = &ivbep_uncore_ha, + [IVBEP_PCI_UNCORE_IMC] = &ivbep_uncore_imc, + [IVBEP_PCI_UNCORE_IRP] = &ivbep_uncore_irp, + [IVBEP_PCI_UNCORE_QPI] = &ivbep_uncore_qpi, + [IVBEP_PCI_UNCORE_R2PCIE] = &ivbep_uncore_r2pcie, + [IVBEP_PCI_UNCORE_R3QPI] = &ivbep_uncore_r3qpi, + NULL, +}; + +static const struct pci_device_id ivbep_uncore_pci_ids[] = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), + .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver ivbep_uncore_pci_driver = { + .name = "ivbep_uncore", + .id_table = ivbep_uncore_pci_ids, +}; + +int ivbep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x0e1e); + if (ret) + return ret; + uncore_pci_uncores = ivbep_pci_uncores; + uncore_pci_driver = &ivbep_uncore_pci_driver; + return 0; +} +/* end of IvyTown uncore support */ + +/* Haswell-EP uncore support */ +static struct attribute *hswep_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + &format_attr_filter_tid2.attr, + &format_attr_filter_cid.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_ubox_format_group = { + .name = "format", + .attrs = hswep_uncore_ubox_formats_attr, +}; + +static int hswep_ubox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + reg1->reg = HSWEP_U_MSR_PMON_FILTER; + reg1->config = event->attr.config1 & HSWEP_U_MSR_PMON_BOX_FILTER_MASK; + reg1->idx = 0; + return 0; +} + +static struct intel_uncore_ops hswep_uncore_ubox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_ubox_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .num_shared_regs = 1, + .ops = &hswep_uncore_ubox_ops, + .format_group = &hswep_uncore_ubox_format_group, +}; + +static struct attribute *hswep_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid3.attr, + &format_attr_filter_link2.attr, + &format_attr_filter_state3.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_c6.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_cbox_format_group = { + .name = "format", + .attrs = hswep_uncore_cbox_formats_attr, +}; + +static struct event_constraint hswep_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x1), + UNCORE_EVENT_CONSTRAINT(0x09, 0x1), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x3b, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg hswep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4028, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4032, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4029, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4033, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x402A, 0x40ff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x12), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + EVENT_EXTRA_END +}; + +static u64 hswep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + if (fields & 0x1) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) { + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NC; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_C6; + mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC; + } + return mask; +} + +static struct event_constraint * +hswep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, hswep_cbox_filter_mask); +} + +static int hswep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = hswep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & hswep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 1, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops hswep_uncore_cbox_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = hswep_cbox_hw_config, + .get_constraint = hswep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 18, + .perf_ctr_bits = 44, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = hswep_uncore_cbox_constraints, + .ops = &hswep_uncore_cbox_ops, + .format_group = &hswep_uncore_cbox_format_group, +}; + +static struct attribute *hswep_uncore_sbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group hswep_uncore_sbox_format_group = { + .name = "format", + .attrs = hswep_uncore_sbox_formats_attr, +}; + +static struct intel_uncore_type hswep_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 44, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &snbep_uncore_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + +static int hswep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = HSWEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << reg1->idx); + } + return 0; +} + +static struct intel_uncore_ops hswep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = hswep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type hswep_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &hswep_uncore_pcu_ops, + .format_group = &snbep_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *hswep_msr_uncores[] = { + &hswep_uncore_ubox, + &hswep_uncore_cbox, + &hswep_uncore_sbox, + &hswep_uncore_pcu, + NULL, +}; + +void hswep_uncore_cpu_init(void) +{ + if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = hswep_msr_uncores; +} + +static struct intel_uncore_type hswep_uncore_ha = { + .name = "ha", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct uncore_event_desc hswep_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"), + INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type hswep_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_ops hswep_uncore_irp_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = ivbep_uncore_irp_disable_event, + .enable_event = ivbep_uncore_irp_enable_event, + .read_counter = ivbep_uncore_irp_read_counter, +}; + +static struct intel_uncore_type hswep_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &hswep_uncore_irp_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type hswep_uncore_qpi = { + .name = "qpi", + .num_counters = 5, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; + +static struct event_constraint hswep_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x1), + UNCORE_EVENT_CONSTRAINT(0x24, 0x1), + UNCORE_EVENT_CONSTRAINT(0x25, 0x1), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x27, 0x1), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x1), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x35, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type hswep_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = hswep_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct event_constraint hswep_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x3), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x12, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x31, 0x3), + UNCORE_EVENT_CONSTRAINT(0x32, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type hswep_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 44, + .constraints = hswep_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + HSWEP_PCI_UNCORE_HA, + HSWEP_PCI_UNCORE_IMC, + HSWEP_PCI_UNCORE_IRP, + HSWEP_PCI_UNCORE_QPI, + HSWEP_PCI_UNCORE_R2PCIE, + HSWEP_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *hswep_pci_uncores[] = { + [HSWEP_PCI_UNCORE_HA] = &hswep_uncore_ha, + [HSWEP_PCI_UNCORE_IMC] = &hswep_uncore_imc, + [HSWEP_PCI_UNCORE_IRP] = &hswep_uncore_irp, + [HSWEP_PCI_UNCORE_QPI] = &hswep_uncore_qpi, + [HSWEP_PCI_UNCORE_R2PCIE] = &hswep_uncore_r2pcie, + [HSWEP_PCI_UNCORE_R3QPI] = &hswep_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0), + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f38), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 1), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb0), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb1), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 1), + }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb4), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb5), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd0), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd1), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd4), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd5), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 7), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f39), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IRP, 0), + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f32), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f33), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3a), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 2), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f34), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R2PCIE, 0), + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f36), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f37), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3e), + .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver hswep_uncore_pci_driver = { + .name = "hswep_uncore", + .id_table = hswep_uncore_pci_ids, +}; + +int hswep_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x2f1e); + if (ret) + return ret; + uncore_pci_uncores = hswep_pci_uncores; + uncore_pci_driver = &hswep_uncore_pci_driver; + return 0; +} +/* end of Haswell-EP uncore support */ diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 838fa8772c62..5b0c232d1ee6 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -217,7 +217,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs) int bit, loops; u64 status; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); knc_pmu_disable_all(); diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 5d466b7d8609..f2e56783af3d 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -915,7 +915,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) static void p4_pmu_disable_all(void) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -984,7 +984,7 @@ static void p4_pmu_enable_event(struct perf_event *event) static void p4_pmu_enable_all(int added) { - struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int idx; for (idx = 0; idx < x86_pmu.num_counters; idx++) { @@ -1004,7 +1004,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) int idx, handled = 0; u64 val; - cpuc = &__get_cpu_var(cpu_hw_events); + cpuc = this_cpu_ptr(&cpu_hw_events); for (idx = 0; idx < x86_pmu.num_counters; idx++) { int overflow; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a618fcd2c07d..f5ab56d14287 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -237,7 +237,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->max_nr_ranges++; /* If crashk_low_res is not 0, another range split possible */ - if (crashk_low_res.end != 0) + if (crashk_low_res.end) ced->max_nr_ranges++; } @@ -335,9 +335,11 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, if (ret) return ret; - ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); - if (ret) - return ret; + if (crashk_low_res.end) { + ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); + if (ret) + return ret; + } /* Exclude GART region */ if (ced->gart_end) { diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 988c00a1f60d..49f886481615 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -682,15 +682,14 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). * * This function requires the e820 map to be sorted and without any - * overlapping entries and assumes the first e820 area to be RAM. + * overlapping entries. */ void __init e820_mark_nosave_regions(unsigned long limit_pfn) { int i; - unsigned long pfn; + unsigned long pfn = 0; - pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size); - for (i = 1; i < e820.nr_map; i++) { + for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; if (pfn < PFN_UP(ei->addr)) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 2fac1343a90b..df088bb03fb3 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -404,8 +404,8 @@ GLOBAL(system_call_after_swapgs) * and short: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,0 - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) + SAVE_ARGS 8, 0, rax_enosys=1 + movq_cfi rax,(ORIG_RAX-ARGOFFSET) movq %rcx,RIP-ARGOFFSET(%rsp) CFI_REL_OFFSET rip,RIP-ARGOFFSET testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) @@ -417,7 +417,7 @@ system_call_fastpath: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja badsys + ja ret_from_sys_call /* and return regs->ax */ movq %r10,%rcx call *sys_call_table(,%rax,8) # XXX: rip relative movq %rax,RAX-ARGOFFSET(%rsp) @@ -476,28 +476,8 @@ sysret_signal: FIXUP_TOP_OF_STACK %r11, -ARGOFFSET jmp int_check_syscall_exit_work -badsys: - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp ret_from_sys_call - #ifdef CONFIG_AUDITSYSCALL /* - * Fast path for syscall audit without full syscall trace. - * We just call __audit_syscall_entry() directly, and then - * jump back to the normal fast path. - */ -auditsys: - movq %r10,%r9 /* 6th arg: 4th syscall arg */ - movq %rdx,%r8 /* 5th arg: 3rd syscall arg */ - movq %rsi,%rcx /* 4th arg: 2nd syscall arg */ - movq %rdi,%rdx /* 3rd arg: 1st syscall arg */ - movq %rax,%rsi /* 2nd arg: syscall number */ - movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */ - call __audit_syscall_entry - LOAD_ARGS 0 /* reload call-clobbered registers */ - jmp system_call_fastpath - - /* * Return fast path for syscall audit. Call __audit_syscall_exit() * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT * masked off. @@ -514,18 +494,25 @@ sysret_audit: /* Do syscall tracing */ tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) - jz auditsys -#endif + leaq -REST_SKIP(%rsp), %rdi + movq $AUDIT_ARCH_X86_64, %rsi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + LOAD_ARGS 0 /* else restore clobbered regs */ + jmp system_call_fastpath /* and return to the fast path */ + +tracesys_phase2: SAVE_REST - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ FIXUP_TOP_OF_STACK %rdi - movq %rsp,%rdi - call syscall_trace_enter + movq %rsp, %rdi + movq $AUDIT_ARCH_X86_64, %rsi + movq %rax,%rdx + call syscall_trace_enter_phase2 + /* * Reload arg registers from stack in case ptrace changed them. - * We don't reload %rax because syscall_trace_enter() returned + * We don't reload %rax because syscall_trace_entry_phase2() returned * the value it wants us to use in the table lookup. */ LOAD_ARGS ARGOFFSET, 1 @@ -536,7 +523,7 @@ tracesys: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */ + ja int_ret_from_sys_call /* RAX(%rsp) is already set */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 5f9cf20cdb68..3d5fb509bdeb 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -108,7 +108,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) int i; for (i = 0; i < HBP_NUM; i++) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (!*slot) { *slot = bp; @@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) set_debugreg(info->address, i); __this_cpu_write(cpu_debugreg[i], info->address); - dr7 = &__get_cpu_var(cpu_dr7); + dr7 = this_cpu_ptr(&cpu_dr7); *dr7 |= encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); @@ -146,7 +146,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) int i; for (i = 0; i < HBP_NUM; i++) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); if (*slot == bp) { *slot = NULL; @@ -157,7 +157,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) return; - dr7 = &__get_cpu_var(cpu_dr7); + dr7 = this_cpu_ptr(&cpu_dr7); *dr7 &= ~__encode_dr7(i, info->len, info->type); set_debugreg(*dr7, 7); diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index 9030e83db6ee..82f8d02f0df2 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -22,10 +22,13 @@ #include <linux/init.h> #include <linux/spinlock.h> #include <linux/pci.h> +#include <linux/debugfs.h> +#include <linux/capability.h> #include <asm/iosf_mbi.h> #define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 #define PCI_DEVICE_ID_QUARK_X1000 0x0958 static DEFINE_SPINLOCK(iosf_mbi_lock); @@ -187,6 +190,89 @@ bool iosf_mbi_available(void) } EXPORT_SYMBOL(iosf_mbi_available); +#ifdef CONFIG_IOSF_MBI_DEBUG +static u32 dbg_mdr; +static u32 dbg_mcr; +static u32 dbg_mcrx; + +static int mcr_get(void *data, u64 *val) +{ + *val = *(u32 *)data; + return 0; +} + +static int mcr_set(void *data, u64 val) +{ + u8 command = ((u32)val & 0xFF000000) >> 24, + port = ((u32)val & 0x00FF0000) >> 16, + offset = ((u32)val & 0x0000FF00) >> 8; + int err; + + *(u32 *)data = val; + + if (!capable(CAP_SYS_RAWIO)) + return -EACCES; + + if (command & 1u) + err = iosf_mbi_write(port, + command, + dbg_mcrx | offset, + dbg_mdr); + else + err = iosf_mbi_read(port, + command, + dbg_mcrx | offset, + &dbg_mdr); + + return err; +} +DEFINE_SIMPLE_ATTRIBUTE(iosf_mcr_fops, mcr_get, mcr_set , "%llx\n"); + +static struct dentry *iosf_dbg; + +static void iosf_sideband_debug_init(void) +{ + struct dentry *d; + + iosf_dbg = debugfs_create_dir("iosf_sb", NULL); + if (IS_ERR_OR_NULL(iosf_dbg)) + return; + + /* mdr */ + d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + /* mcrx */ + debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + /* mcr - initiates mailbox tranaction */ + debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); + if (IS_ERR_OR_NULL(d)) + goto cleanup; + + return; + +cleanup: + debugfs_remove_recursive(d); +} + +static void iosf_debugfs_init(void) +{ + iosf_sideband_debug_init(); +} + +static void iosf_debugfs_remove(void) +{ + debugfs_remove_recursive(iosf_dbg); +} +#else +static inline void iosf_debugfs_init(void) { } +static inline void iosf_debugfs_remove(void) { } +#endif /* CONFIG_IOSF_MBI_DEBUG */ + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -204,6 +290,7 @@ static int iosf_mbi_probe(struct pci_dev *pdev, static const struct pci_device_id iosf_mbi_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; @@ -217,11 +304,15 @@ static struct pci_driver iosf_mbi_pci_driver = { static int __init iosf_mbi_init(void) { + iosf_debugfs_init(); + return pci_register_driver(&iosf_mbi_pci_driver); } static void __exit iosf_mbi_exit(void) { + iosf_debugfs_remove(); + pci_unregister_driver(&iosf_mbi_pci_driver); if (mbi_pdev) { pci_dev_put(mbi_pdev); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 4d1c746892eb..e4b503d5558c 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -52,13 +52,13 @@ static inline void stack_overflow_check(struct pt_regs *regs) regs->sp <= curbase + THREAD_SIZE) return; - irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) + + irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) + STACK_TOP_MARGIN; - irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr); + irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr); if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom) return; - oist = &__get_cpu_var(orig_ist); + oist = this_cpu_ptr(&orig_ist); estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN; estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1]; if (regs->sp >= estack_top && regs->sp <= estack_bottom) diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 1de84e3ab4e0..15d741ddfeeb 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -41,7 +41,7 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) void arch_irq_work_raise(void) { #ifdef CONFIG_X86_LOCAL_APIC - if (!cpu_has_apic) + if (!arch_irq_work_has_interrupt()) return; apic->send_IPI_self(IRQ_WORK_VECTOR); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 9642b9b33655..ca05f86481aa 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -26,6 +26,7 @@ #include <asm/setup.h> #include <asm/crash.h> #include <asm/efi.h> +#include <asm/kexec-bzimage64.h> #define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */ @@ -267,7 +268,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, return ret; } -int bzImage64_probe(const char *buf, unsigned long len) +static int bzImage64_probe(const char *buf, unsigned long len) { int ret = -ENOEXEC; struct setup_header *header; @@ -325,10 +326,10 @@ int bzImage64_probe(const char *buf, unsigned long len) return ret; } -void *bzImage64_load(struct kimage *image, char *kernel, - unsigned long kernel_len, char *initrd, - unsigned long initrd_len, char *cmdline, - unsigned long cmdline_len) +static void *bzImage64_load(struct kimage *image, char *kernel, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) { struct setup_header *header; @@ -514,7 +515,7 @@ out_free_params: } /* This cleanup function is called after various segments have been loaded */ -int bzImage64_cleanup(void *loader_data) +static int bzImage64_cleanup(void *loader_data) { struct bzimage64_data *ldata = loader_data; @@ -528,7 +529,7 @@ int bzImage64_cleanup(void *loader_data) } #ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG -int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) +static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) { bool trusted; int ret; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 3dd8e2c4d74a..f6945bef2cd1 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/kprobes.h> #include <linux/debugfs.h> +#include <linux/nmi.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -243,9 +244,9 @@ u32 kvm_read_and_reset_pf_reason(void) { u32 reason = 0; - if (__get_cpu_var(apf_reason).enabled) { - reason = __get_cpu_var(apf_reason).reason; - __get_cpu_var(apf_reason).reason = 0; + if (__this_cpu_read(apf_reason.enabled)) { + reason = __this_cpu_read(apf_reason.reason); + __this_cpu_write(apf_reason.reason, 0); } return reason; @@ -318,7 +319,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) * there's no need for lock or memory barriers. * An optimization barrier is implied in apic write. */ - if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi))) + if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi))) return; apic_write(APIC_EOI, APIC_EOI_ACK); } @@ -329,13 +330,13 @@ void kvm_guest_cpu_init(void) return; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { - u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason)); + u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); #ifdef CONFIG_PREEMPT pa |= KVM_ASYNC_PF_SEND_ALWAYS; #endif wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED); - __get_cpu_var(apf_reason).enabled = 1; + __this_cpu_write(apf_reason.enabled, 1); printk(KERN_INFO"KVM setup async PF for cpu %d\n", smp_processor_id()); } @@ -344,8 +345,8 @@ void kvm_guest_cpu_init(void) unsigned long pa; /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); - __get_cpu_var(kvm_apic_eoi) = 0; - pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi)) + __this_cpu_write(kvm_apic_eoi, 0); + pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi)) | KVM_MSR_ENABLED; wrmsrl(MSR_KVM_PV_EOI_EN, pa); } @@ -356,11 +357,11 @@ void kvm_guest_cpu_init(void) static void kvm_pv_disable_apf(void) { - if (!__get_cpu_var(apf_reason).enabled) + if (!__this_cpu_read(apf_reason.enabled)) return; wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); - __get_cpu_var(apf_reason).enabled = 0; + __this_cpu_write(apf_reason.enabled, 0); printk(KERN_INFO"Unregister pv shared memory for cpu %d\n", smp_processor_id()); @@ -499,6 +500,13 @@ void __init kvm_guest_init(void) #else kvm_guest_cpu_init(); #endif + + /* + * Hard lockup detection is enabled by default. Disable it, as guests + * can get false positives too easily, for example if the host is + * overcommitted. + */ + watchdog_enable_hardlockup_detector(false); } static noinline uint32_t __kvm_cpuid_base(void) @@ -716,7 +724,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) if (in_nmi()) return; - w = &__get_cpu_var(klock_waiting); + w = this_cpu_ptr(&klock_waiting); cpu = smp_processor_id(); start = spin_time_start(); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 1667b1de8d5d..72e8e310258d 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -247,7 +247,8 @@ void machine_kexec(struct kimage *image) /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, (unsigned long)page_list, - image->start, cpu_has_pae, + image->start, + boot_cpu_has(X86_FEATURE_PAE), image->preserve_context); #ifdef CONFIG_KEXEC_JUMP diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c index 0c424a67985d..0ee5025e0fa4 100644 --- a/arch/x86/kernel/pmc_atom.c +++ b/arch/x86/kernel/pmc_atom.c @@ -235,6 +235,11 @@ err: pmc_dbgfs_unregister(pmc); return -ENODEV; } +#else +static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +{ + return 0; +} #endif /* CONFIG_DEBUG_FS */ static int pmc_setup_dev(struct pci_dev *pdev) @@ -262,14 +267,12 @@ static int pmc_setup_dev(struct pci_dev *pdev) /* PMC hardware registers setup */ pmc_hw_reg_setup(pmc); -#ifdef CONFIG_DEBUG_FS ret = pmc_dbgfs_register(pmc, pdev); if (ret) { iounmap(pmc->regmap); - return ret; } -#endif /* CONFIG_DEBUG_FS */ - return 0; + + return ret; } /* diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S deleted file mode 100644 index ca7f0d58a87d..000000000000 --- a/arch/x86/kernel/preempt.S +++ /dev/null @@ -1,25 +0,0 @@ - -#include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/asm.h> -#include <asm/calling.h> - -ENTRY(___preempt_schedule) - CFI_STARTPROC - SAVE_ALL - call preempt_schedule - RESTORE_ALL - ret - CFI_ENDPROC - -#ifdef CONFIG_CONTEXT_TRACKING - -ENTRY(___preempt_schedule_context) - CFI_STARTPROC - SAVE_ALL - call preempt_schedule_context - RESTORE_ALL - ret - CFI_ENDPROC - -#endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f804dc935d2a..e127ddaa2d5a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -64,14 +64,16 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep); */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - int ret; - *dst = *src; - if (fpu_allocated(&src->thread.fpu)) { - memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu)); - ret = fpu_alloc(&dst->thread.fpu); - if (ret) - return ret; + + dst->thread.fpu_counter = 0; + dst->thread.fpu.has_fpu = 0; + dst->thread.fpu.last_cpu = ~0; + dst->thread.fpu.state = NULL; + if (tsk_used_math(src)) { + int err = fpu_alloc(&dst->thread.fpu); + if (err) + return err; fpu_copy(dst, src); } return 0; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 7bc86bbe7485..8f3ebfe710d0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -138,6 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.sp0 = (unsigned long) (childregs+1); + memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ @@ -152,9 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); return 0; } *childregs = *current_pt_regs(); @@ -165,13 +164,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; tsk = current; err = -ENOMEM; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ca5b02d405c3..3ed4a68d4013 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -163,7 +163,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp = (unsigned long) childregs; p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); - p->thread.fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -193,8 +192,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->sp = sp; err = -ENOMEM; - memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); - if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr, IO_BITMAP_BYTES, GFP_KERNEL); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 678c0ada3b3c..29576c244699 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,24 +1441,126 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + audit_syscall_entry(arch, regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else #endif + { + audit_syscall_entry(arch, regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} /* - * We must return the syscall number to actually look up in the table. - * This can be -1L to skip running any syscall at all. + * We can return 0 to resume the syscall or anything else to go to phase + * 2. If we resume the syscall, we need to put something appropriate in + * regs->orig_ax. + * + * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax + * are fully functional. + * + * For phase 2's benefit, our return value is: + * 0: resume the syscall + * 1: go to phase 2; no seccomp phase 2 needed + * anything else: go to phase 2; pass return value to seccomp */ -long syscall_trace_enter(struct pt_regs *regs) +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + unsigned long ret = 0; + u32 work; + + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; + + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + user_exit(); + work &= ~TIF_NOHZ; + } + +#ifdef CONFIG_SECCOMP + /* + * Do seccomp first -- it should minimize exposure of other + * code, and keeping seccomp fast is probably more valuable + * than the rest of this. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + sd.args[5] = regs->bp; + } + + BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); + BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); + + ret = seccomp_phase1(&sd); + if (ret == SECCOMP_PHASE1_SKIP) { + regs->orig_ax = -1; + ret = 0; + } else if (ret != SECCOMP_PHASE1_OK) { + return ret; /* Go directly to phase 2 */ + } + + work &= ~_TIF_SECCOMP; + } +#endif + + /* Do our best to finish without phase 2. */ + if (work == 0) + return ret; /* seccomp and/or nohz only (ret == 0 here) */ + +#ifdef CONFIG_AUDITSYSCALL + if (work == _TIF_SYSCALL_AUDIT) { + /* + * If there is no more work to be done except auditing, + * then audit in phase 1. Phase 2 always audits, so, if + * we audit here, then we can't go on to phase 2. + */ + do_audit_syscall_entry(regs, arch); + return 0; + } +#endif + + return 1; /* Something is enabled that we can't handle in phase 1 */ +} + +/* Returns the syscall nr to run (which should match regs->orig_ax). */ +long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, + unsigned long phase1_result) { long ret = 0; + u32 work = ACCESS_ONCE(current_thread_info()->flags) & + _TIF_WORK_SYSCALL_ENTRY; - user_exit(); + BUG_ON(regs != task_pt_regs(current)); /* * If we stepped into a sysenter/syscall insn, it trapped in @@ -1467,17 +1569,21 @@ long syscall_trace_enter(struct pt_regs *regs) * do_debug() and we need to set it again to restore the user * state. If we entered on the slow path, TF was already set. */ - if (test_thread_flag(TIF_SINGLESTEP)) + if (work & _TIF_SINGLESTEP) regs->flags |= X86_EFLAGS_TF; - /* do the secure computing check first */ - if (secure_computing(regs->orig_ax)) { +#ifdef CONFIG_SECCOMP + /* + * Call seccomp_phase2 before running the other hooks so that + * they can see any changes made by a seccomp tracer. + */ + if (phase1_result > 1 && seccomp_phase2(phase1_result)) { /* seccomp failures shouldn't expose any additional code. */ - ret = -1L; - goto out; + return -1; } +#endif - if (unlikely(test_thread_flag(TIF_SYSCALL_EMU))) + if (unlikely(work & _TIF_SYSCALL_EMU)) ret = -1L; if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && @@ -1487,23 +1593,22 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) - audit_syscall_entry(AUDIT_ARCH_I386, - regs->orig_ax, - regs->bx, regs->cx, - regs->dx, regs->si); -#ifdef CONFIG_X86_64 - else - audit_syscall_entry(AUDIT_ARCH_X86_64, - regs->orig_ax, - regs->di, regs->si, - regs->dx, regs->r10); -#endif + do_audit_syscall_entry(regs, arch); -out: return ret ?: regs->orig_ax; } +long syscall_trace_enter(struct pt_regs *regs) +{ + u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); + + if (phase1_result == 0) + return regs->orig_ax; + else + return syscall_trace_enter_phase2(regs, arch, phase1_result); +} + void syscall_trace_leave(struct pt_regs *regs) { bool step; diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index ff898bbf579d..176a0f99d4da 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -498,6 +498,24 @@ void force_hpet_resume(void) } /* + * According to the datasheet e6xx systems have the HPET hardwired to + * 0xfed00000 + */ +static void e6xx_force_enable_hpet(struct pci_dev *dev) +{ + if (hpet_address || force_hpet_address) + return; + + force_hpet_address = 0xFED00000; + force_hpet_resume_type = NONE_FORCE_HPET_RESUME; + dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at " + "0x%lx\n", force_hpet_address); + return; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU, + e6xx_force_enable_hpet); + +/* * HPET MSI on some boards (ATI SB700/SB800) has side effect on * floppy DMA. Disable HPET MSI on such platforms. * See erratum #27 (Misinterpreted MSI Requests May Result in diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 41ead8d3bc0b..235cfd39e0d7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -879,6 +879,15 @@ void __init setup_arch(char **cmdline_p) KERNEL_PGD_PTRS); load_cr3(swapper_pg_dir); + /* + * Note: Quark X1000 CPUs advertise PGE incorrectly and require + * a cr3 based tlb flush, so the following __flush_tlb_all() + * will not flush anything because the cpu quirk which clears + * X86_FEATURE_PGE has not been invoked yet. Though due to the + * load_cr3() above the TLB has been flushed already. The + * quirk is invoked before subsequent calls to __flush_tlb_all() + * so proper operation is guaranteed. + */ __flush_tlb_all(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 2851d63c1202..ed37a768d0fc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -675,6 +675,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } 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 42a2dca984b3..2d5200e56357 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -102,6 +102,8 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +static DEFINE_PER_CPU(struct completion, die_complete); + atomic_t init_deasserted; /* @@ -111,7 +113,6 @@ atomic_t init_deasserted; static void smp_callin(void) { int cpuid, phys_id; - unsigned long timeout; /* * If waken up by an INIT in an 82489DX configuration @@ -130,37 +131,6 @@ static void smp_callin(void) * (This works even if the APIC is not enabled.) */ phys_id = read_apic_id(); - if (cpumask_test_cpu(cpuid, cpu_callin_mask)) { - panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__, - phys_id, cpuid); - } - pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id); - - /* - * STARTUP IPIs are fragile beasts as they might sometimes - * trigger some glue motherboard logic. Complete APIC bus - * silence for 1 second, this overestimates the time the - * boot CPU is spending to send the up to 2 STARTUP IPIs - * by a factor of two. This should be enough. - */ - - /* - * Waiting 2s total for startup (udelay is not yet working) - */ - timeout = jiffies + 2*HZ; - while (time_before(jiffies, timeout)) { - /* - * Has the boot CPU finished it's STARTUP sequence? - */ - if (cpumask_test_cpu(cpuid, cpu_callout_mask)) - break; - cpu_relax(); - } - - if (!time_before(jiffies, timeout)) { - panic("%s: CPU%d started up but did not get a callout!\n", - __func__, cpuid); - } /* * the boot CPU has finished the init stage and is spinning @@ -296,11 +266,19 @@ void smp_store_cpu_info(int id) } static bool +topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +{ + int cpu1 = c->cpu_index, cpu2 = o->cpu_index; + + return (cpu_to_node(cpu1) == cpu_to_node(cpu2)); +} + +static bool topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2), + return !WARN_ONCE(!topology_same_node(c, o), "sched: CPU #%d's %s-sibling CPU #%d is not on the same node! " "[node: %d != %d]. Ignoring dependency.\n", cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); @@ -341,17 +319,44 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) return false; } -static bool match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) +/* + * Unlike the other levels, we do not enforce keeping a + * multicore group inside a NUMA node. If this happens, we will + * discard the MC level of the topology later. + */ +static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->phys_proc_id == o->phys_proc_id) { - if (cpu_has(c, X86_FEATURE_AMD_DCM)) - return true; - - return topology_sane(c, o, "mc"); - } + if (c->phys_proc_id == o->phys_proc_id) + return true; return false; } +static struct sched_domain_topology_level numa_inside_package_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { NULL, }, +}; +/* + * set_sched_topology() sets the topology internal to a CPU. The + * NUMA topologies are layered on top of it to build the full + * system topology. + * + * If NUMA nodes are observed to occur within a CPU package, this + * function should be called. It forces the sched domain code to + * only use the SMT level for the CPU portion of the topology. + * This essentially falls back to relying on NUMA information + * from the SRAT table to describe the entire system topology + * (except for hyperthreads). + */ +static void primarily_use_numa_for_topology(void) +{ + set_sched_topology(numa_inside_package_topology); +} + void set_cpu_sibling_map(int cpu) { bool has_smt = smp_num_siblings > 1; @@ -388,7 +393,7 @@ void set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); - if ((i == cpu) || (has_mp && match_mc(c, o))) { + if ((i == cpu) || (has_mp && match_die(c, o))) { link_mask(core, cpu, i); /* @@ -410,6 +415,8 @@ void set_cpu_sibling_map(int cpu) } else if (i != cpu && !c->booted_cores) c->booted_cores = cpu_data(i).booted_cores; } + if (match_die(c, o) && !topology_same_node(c, o)) + primarily_use_numa_for_topology(); } } @@ -753,8 +760,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - int timeout; int cpu0_nmi_registered = 0; + unsigned long timeout; /* Just in case we booted with a single CPU. */ alternatives_enable_smp(); @@ -802,6 +809,15 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) } /* + * AP might wait on cpu_callout_mask in cpu_init() with + * cpu_initialized_mask set if previous attempt to online + * it timed-out. Clear cpu_initialized_mask so that after + * INIT/SIPI it could start with a clean state. + */ + cpumask_clear_cpu(cpu, cpu_initialized_mask); + smp_mb(); + + /* * Wake up a CPU in difference cases: * - Use the method in the APIC driver if it's defined * Otherwise, @@ -815,53 +831,38 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) if (!boot_error) { /* - * allow APs to start initializing. + * Wait 10s total for a response from AP */ - pr_debug("Before Callout %d\n", cpu); - cpumask_set_cpu(cpu, cpu_callout_mask); - pr_debug("After Callout %d\n", cpu); + boot_error = -1; + timeout = jiffies + 10*HZ; + while (time_before(jiffies, timeout)) { + if (cpumask_test_cpu(cpu, cpu_initialized_mask)) { + /* + * Tell AP to proceed with initialization + */ + cpumask_set_cpu(cpu, cpu_callout_mask); + boot_error = 0; + break; + } + udelay(100); + schedule(); + } + } + if (!boot_error) { /* - * Wait 5s total for a response + * Wait till AP completes initial initialization */ - for (timeout = 0; timeout < 50000; timeout++) { - if (cpumask_test_cpu(cpu, cpu_callin_mask)) - break; /* It has booted */ - udelay(100); + while (!cpumask_test_cpu(cpu, cpu_callin_mask)) { /* * Allow other tasks to run while we wait for the * AP to come online. This also gives a chance * for the MTRR work(triggered by the AP coming online) * to be completed in the stop machine context. */ + udelay(100); schedule(); } - - if (cpumask_test_cpu(cpu, cpu_callin_mask)) { - print_cpu_msr(&cpu_data(cpu)); - pr_debug("CPU%d: has booted.\n", cpu); - } else { - boot_error = 1; - if (*trampoline_status == 0xA5A5A5A5) - /* trampoline started but...? */ - pr_err("CPU%d: Stuck ??\n", cpu); - else - /* trampoline code not run */ - pr_err("CPU%d: Not responding\n", cpu); - if (apic->inquire_remote_apic) - apic->inquire_remote_apic(apicid); - } - } - - if (boot_error) { - /* Try to put things back the way they were before ... */ - numa_remove_cpu(cpu); /* was set by numa_add_cpu */ - - /* was set by do_boot_cpu() */ - cpumask_clear_cpu(cpu, cpu_callout_mask); - - /* was set by cpu_init() */ - cpumask_clear_cpu(cpu, cpu_initialized_mask); } /* mark "stuck" area as not stuck */ @@ -1326,26 +1327,24 @@ int native_cpu_disable(void) return ret; clear_local_APIC(); - + init_completion(&per_cpu(die_complete, smp_processor_id())); cpu_disable_common(); + return 0; } void native_cpu_die(unsigned int cpu) { /* We don't do anything here: idle task is faking death itself. */ - unsigned int i; + wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ); - for (i = 0; i < 10; i++) { - /* They ack this in play_dead by setting CPU_DEAD */ - if (per_cpu(cpu_state, cpu) == CPU_DEAD) { - if (system_state == SYSTEM_RUNNING) - pr_info("CPU %u is now offline\n", cpu); - return; - } - msleep(100); + /* They ack this in play_dead() by setting CPU_DEAD */ + if (per_cpu(cpu_state, cpu) == CPU_DEAD) { + if (system_state == SYSTEM_RUNNING) + pr_info("CPU %u is now offline\n", cpu); + } else { + pr_err("CPU %u didn't die...\n", cpu); } - pr_err("CPU %u didn't die...\n", cpu); } void play_dead_common(void) @@ -1357,6 +1356,7 @@ void play_dead_common(void) mb(); /* Ack it */ __this_cpu_write(cpu_state, CPU_DEAD); + complete(&per_cpu(die_complete, smp_processor_id())); /* * With physical CPU hotplug, we should halt the cpu diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index e1e1e80fc6a6..957779f4eb40 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -216,7 +216,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) */ regs->orig_ax = syscall_nr; regs->ax = -ENOSYS; - tmp = secure_computing(syscall_nr); + tmp = secure_computing(); if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 940b142cc11f..4c540c4719d8 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -271,8 +271,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -402,8 +400,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) set_used_math(); } - if (use_eager_fpu()) + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 3201e93ebd07..ac1c4de3a484 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4549,7 +4549,7 @@ int kvm_mmu_module_init(void) if (!mmu_page_header_cache) goto nomem; - if (percpu_counter_init(&kvm_total_used_mmu_pages, 0)) + if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto nomem; register_shrinker(&mmu_shrinker); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f7f6a4a157a6..65510f624dfe 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -670,7 +670,7 @@ static int svm_hardware_enable(void) if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); - __get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT; + __this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT); } @@ -1313,8 +1313,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); if (static_cpu_has(X86_FEATURE_TSCRATEMSR) && - svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) { - __get_cpu_var(current_tsc_ratio) = svm->tsc_ratio; + svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) { + __this_cpu_write(current_tsc_ratio, svm->tsc_ratio); wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio); } } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 04fa1b8298c8..d9dcfa27aa84 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1626,7 +1626,7 @@ static void reload_tss(void) /* * VT restores TR but not its size. Useless. */ - struct desc_ptr *gdt = &__get_cpu_var(host_gdt); + struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *descs; descs = (void *)gdt->address; @@ -1672,7 +1672,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) static unsigned long segment_base(u16 selector) { - struct desc_ptr *gdt = &__get_cpu_var(host_gdt); + struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); struct desc_struct *d; unsigned long table_base; unsigned long v; @@ -1802,7 +1802,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) */ if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) stts(); - load_gdt(&__get_cpu_var(host_gdt)); + load_gdt(this_cpu_ptr(&host_gdt)); } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -1832,7 +1832,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } if (vmx->loaded_vmcs->cpu != cpu) { - struct desc_ptr *gdt = &__get_cpu_var(host_gdt); + struct desc_ptr *gdt = this_cpu_ptr(&host_gdt); unsigned long sysenter_esp; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); @@ -2771,7 +2771,7 @@ static int hardware_enable(void) ept_sync_global(); } - native_store_gdt(&__get_cpu_var(host_gdt)); + native_store_gdt(this_cpu_ptr(&host_gdt)); return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5430e4b0af29..34c8f94331f8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1559,7 +1559,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - this_tsc_khz = __get_cpu_var(cpu_tsc_khz); + this_tsc_khz = __this_cpu_read(cpu_tsc_khz); if (unlikely(this_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 4d4f96a27638..db92793b7e23 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -20,7 +20,6 @@ lib-y := delay.o misc.o cmdline.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o -lib-$(CONFIG_SMP) += rwlock.o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o @@ -39,7 +38,7 @@ endif else obj-y += iomap_copy_64.o lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o - lib-y += thunk_64.o clear_page_64.o copy_page_64.o + lib-y += clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o lib-y += copy_user_64.o copy_user_nocache_64.o lib-y += cmpxchg16b_emu.o diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index 1e572c507d06..40a172541ee2 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -6,15 +6,8 @@ * */ #include <linux/linkage.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> #include <asm/dwarf2.h> - -#ifdef CONFIG_SMP -#define SEG_PREFIX %gs: -#else -#define SEG_PREFIX -#endif +#include <asm/percpu.h> .text @@ -39,24 +32,25 @@ CFI_STARTPROC # *atomic* on a single cpu (as provided by the this_cpu_xx class of # macros). # -this_cpu_cmpxchg16b_emu: - pushf + pushfq_cfi cli - cmpq SEG_PREFIX(%rsi), %rax - jne not_same - cmpq SEG_PREFIX 8(%rsi), %rdx - jne not_same + cmpq PER_CPU_VAR((%rsi)), %rax + jne .Lnot_same + cmpq PER_CPU_VAR(8(%rsi)), %rdx + jne .Lnot_same - movq %rbx, SEG_PREFIX(%rsi) - movq %rcx, SEG_PREFIX 8(%rsi) + movq %rbx, PER_CPU_VAR((%rsi)) + movq %rcx, PER_CPU_VAR(8(%rsi)) - popf + CFI_REMEMBER_STATE + popfq_cfi mov $1, %al ret - not_same: - popf + CFI_RESTORE_STATE +.Lnot_same: + popfq_cfi xor %al,%al ret diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 828cb710dec2..b4807fce5177 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -7,11 +7,8 @@ */ #include <linux/linkage.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> #include <asm/dwarf2.h> - .text /* @@ -30,27 +27,28 @@ CFI_STARTPROC # set the whole ZF thing (caller will just compare # eax:edx with the expected value) # -cmpxchg8b_emu: - pushfl + pushfl_cfi cli cmpl (%esi), %eax - jne not_same + jne .Lnot_same cmpl 4(%esi), %edx - jne half_same + jne .Lhalf_same movl %ebx, (%esi) movl %ecx, 4(%esi) - popfl + CFI_REMEMBER_STATE + popfl_cfi ret - not_same: + CFI_RESTORE_STATE +.Lnot_same: movl (%esi), %eax - half_same: +.Lhalf_same: movl 4(%esi), %edx - popfl + popfl_cfi ret CFI_ENDPROC diff --git a/arch/x86/lib/rwlock.S b/arch/x86/lib/rwlock.S deleted file mode 100644 index 1cad22139c88..000000000000 --- a/arch/x86/lib/rwlock.S +++ /dev/null @@ -1,44 +0,0 @@ -/* Slow paths of read/write spinlocks. */ - -#include <linux/linkage.h> -#include <asm/alternative-asm.h> -#include <asm/frame.h> -#include <asm/rwlock.h> - -#ifdef CONFIG_X86_32 -# define __lock_ptr eax -#else -# define __lock_ptr rdi -#endif - -ENTRY(__write_lock_failed) - CFI_STARTPROC - FRAME -0: LOCK_PREFIX - WRITE_LOCK_ADD($RW_LOCK_BIAS) (%__lock_ptr) -1: rep; nop - cmpl $WRITE_LOCK_CMP, (%__lock_ptr) - jne 1b - LOCK_PREFIX - WRITE_LOCK_SUB($RW_LOCK_BIAS) (%__lock_ptr) - jnz 0b - ENDFRAME - ret - CFI_ENDPROC -END(__write_lock_failed) - -ENTRY(__read_lock_failed) - CFI_STARTPROC - FRAME -0: LOCK_PREFIX - READ_LOCK_SIZE(inc) (%__lock_ptr) -1: rep; nop - READ_LOCK_SIZE(cmp) $1, (%__lock_ptr) - js 1b - LOCK_PREFIX - READ_LOCK_SIZE(dec) (%__lock_ptr) - js 0b - ENDFRAME - ret - CFI_ENDPROC -END(__read_lock_failed) diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S index 28f85c916712..e28cdaf5ac2c 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/lib/thunk_32.S @@ -6,25 +6,46 @@ */ #include <linux/linkage.h> #include <asm/asm.h> + #include <asm/dwarf2.h> -#ifdef CONFIG_TRACE_IRQFLAGS /* put return address in eax (arg1) */ - .macro thunk_ra name,func + .macro THUNK name, func, put_ret_addr_in_eax=0 .globl \name \name: - pushl %eax - pushl %ecx - pushl %edx + CFI_STARTPROC + pushl_cfi %eax + CFI_REL_OFFSET eax, 0 + pushl_cfi %ecx + CFI_REL_OFFSET ecx, 0 + pushl_cfi %edx + CFI_REL_OFFSET edx, 0 + + .if \put_ret_addr_in_eax /* Place EIP in the arg1 */ movl 3*4(%esp), %eax + .endif + call \func - popl %edx - popl %ecx - popl %eax + popl_cfi %edx + CFI_RESTORE edx + popl_cfi %ecx + CFI_RESTORE ecx + popl_cfi %eax + CFI_RESTORE eax ret + CFI_ENDPROC _ASM_NOKPROBE(\name) .endm - thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller - thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller +#ifdef CONFIG_TRACE_IRQFLAGS + THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1 + THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 +#endif + +#ifdef CONFIG_PREEMPT + THUNK ___preempt_schedule, preempt_schedule +#ifdef CONFIG_CONTEXT_TRACKING + THUNK ___preempt_schedule_context, preempt_schedule_context #endif +#endif + diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index 92d9feaff42b..b30b5ebd614a 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -38,6 +38,13 @@ THUNK lockdep_sys_exit_thunk,lockdep_sys_exit #endif +#ifdef CONFIG_PREEMPT + THUNK ___preempt_schedule, preempt_schedule +#ifdef CONFIG_CONTEXT_TRACKING + THUNK ___preempt_schedule_context, preempt_schedule_context +#endif +#endif + /* SAVE_ARGS below is used only for the .cfi directives it contains. */ CFI_STARTPROC SAVE_ARGS diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a24194681513..d973e61e450d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -3,7 +3,6 @@ * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ -#include <linux/magic.h> /* STACK_END_MAGIC */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/module.h> /* search_exception_table */ @@ -350,7 +349,7 @@ out: void vmalloc_sync_all(void) { - sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); + sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0); } /* @@ -649,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; - unsigned long *stackend; unsigned long flags; int sig; @@ -709,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, show_fault_oops(regs, error_code, address); - stackend = end_of_stack(tsk); - if (tsk != &init_task && *stackend != STACK_END_MAGIC) + if (task_stack_end_corrupted(tsk)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); tsk->thread.cr2 = address; @@ -933,8 +930,17 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * + * Spurious faults may only occur if the TLB contains an entry with + * fewer permission than the page table entry. Non-present (P = 0) + * and reserved bit (R = 1) faults are never spurious. + * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. + * + * Returns non-zero if a spurious fault was handled, zero otherwise. + * + * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 + * (Optional Invalidation). */ static noinline int spurious_fault(unsigned long error_code, unsigned long address) @@ -945,8 +951,17 @@ spurious_fault(unsigned long error_code, unsigned long address) pte_t *pte; int ret; - /* Reserved-bit violation or user access to kernel space? */ - if (error_code & (PF_USER | PF_RSVD)) + /* + * Only writes to RO or instruction fetches from NX may cause + * spurious faults. + * + * These could be from user or supervisor accesses but the TLB + * is only lazily flushed after a kernel mapping protection + * change, so user accesses are not expected to cause spurious + * faults. + */ + if (error_code != (PF_WRITE | PF_PROT) + && error_code != (PF_INSTR | PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 7d05565ba781..c8140e12816a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -537,7 +537,7 @@ static void __init pagetable_init(void) permanent_kmaps_init(pgd_base); } -pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP); +pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL); EXPORT_SYMBOL_GPL(__supported_pte_mask); /* user-defined highmem size */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 5621c47d7a1a..4cb8763868fc 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -151,7 +151,7 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP; +pteval_t __supported_pte_mask __read_mostly = ~0; EXPORT_SYMBOL_GPL(__supported_pte_mask); int force_personality32; @@ -178,7 +178,7 @@ __setup("noexec32=", nonx32_setup); * When memory was added/removed make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ -void sync_global_pgds(unsigned long start, unsigned long end) +void sync_global_pgds(unsigned long start, unsigned long end, int removed) { unsigned long address; @@ -186,7 +186,12 @@ void sync_global_pgds(unsigned long start, unsigned long end) const pgd_t *pgd_ref = pgd_offset_k(address); struct page *page; - if (pgd_none(*pgd_ref)) + /* + * When it is called after memory hot remove, pgd_none() + * returns true. In this case (removed == 1), we must clear + * the PGD entries in the local PGD level page. + */ + if (pgd_none(*pgd_ref) && !removed) continue; spin_lock(&pgd_lock); @@ -199,12 +204,18 @@ void sync_global_pgds(unsigned long start, unsigned long end) pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); - else + if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + if (removed) { + if (pgd_none(*pgd_ref) && !pgd_none(*pgd)) + pgd_clear(pgd); + } else { + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + } + spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); @@ -633,7 +644,7 @@ kernel_physical_mapping_init(unsigned long start, } if (pgd_changed) - sync_global_pgds(addr, end - 1); + sync_global_pgds(addr, end - 1, 0); __flush_tlb_all(); @@ -976,25 +987,26 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end, bool direct) { unsigned long next; + unsigned long addr; pgd_t *pgd; pud_t *pud; bool pgd_changed = false; - for (; start < end; start = next) { - next = pgd_addr_end(start, end); + for (addr = start; addr < end; addr = next) { + next = pgd_addr_end(addr, end); - pgd = pgd_offset_k(start); + pgd = pgd_offset_k(addr); if (!pgd_present(*pgd)) continue; pud = (pud_t *)pgd_page_vaddr(*pgd); - remove_pud_table(pud, start, next, direct); + remove_pud_table(pud, addr, next, direct); if (free_pud_table(pud, pgd)) pgd_changed = true; } if (pgd_changed) - sync_global_pgds(start, end - 1); + sync_global_pgds(start, end - 1, 1); flush_tlb_all(); } @@ -1341,7 +1353,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) else err = vmemmap_populate_basepages(start, end, node); if (!err) - sync_global_pgds(start, end - 1); + sync_global_pgds(start, end - 1, 0); return err; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index baff1da354e0..af78e50ca6ce 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -86,6 +86,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pgprot_t prot; int retval; void __iomem *ret_addr; + int ram_region; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -108,12 +109,23 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) + /* First check if whole region can be identified as RAM or not */ + ram_region = region_is_ram(phys_addr, size); + if (ram_region > 0) { + WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n", + (unsigned long int)phys_addr, + (unsigned long int)last_addr); return NULL; + } + /* If could not be identified(-1), check page by page */ + if (ram_region < 0) { + pfn = phys_addr >> PAGE_SHIFT; + last_pfn = last_addr >> PAGE_SHIFT; + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) + return NULL; + } /* * Mappings have to be page-aligned */ diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c index dd89a13f1051..b4f2e7e9e907 100644 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ b/arch/x86/mm/kmemcheck/kmemcheck.c @@ -140,7 +140,7 @@ static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context); bool kmemcheck_active(struct pt_regs *regs) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); return data->balance > 0; } @@ -148,7 +148,7 @@ bool kmemcheck_active(struct pt_regs *regs) /* Save an address that needs to be shown/hidden */ static void kmemcheck_save_addr(unsigned long addr) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr)); data->addr[data->n_addrs++] = addr; @@ -156,7 +156,7 @@ static void kmemcheck_save_addr(unsigned long addr) static unsigned int kmemcheck_show_all(void) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); unsigned int i; unsigned int n; @@ -169,7 +169,7 @@ static unsigned int kmemcheck_show_all(void) static unsigned int kmemcheck_hide_all(void) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); unsigned int i; unsigned int n; @@ -185,7 +185,7 @@ static unsigned int kmemcheck_hide_all(void) */ void kmemcheck_show(struct pt_regs *regs) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); BUG_ON(!irqs_disabled()); @@ -226,7 +226,7 @@ void kmemcheck_show(struct pt_regs *regs) */ void kmemcheck_hide(struct pt_regs *regs) { - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); int n; BUG_ON(!irqs_disabled()); @@ -528,7 +528,7 @@ static void kmemcheck_access(struct pt_regs *regs, const uint8_t *insn_primary; unsigned int size; - struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context); + struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); /* Recursive fault -- ouch. */ if (data->busy) { diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a32b706c401a..1a883705a12a 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -185,8 +185,8 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) return numa_add_memblk_to(nid, start, end, &numa_meminfo); } -/* Initialize NODE_DATA for a node on the local memory */ -static void __init setup_node_data(int nid, u64 start, u64 end) +/* Allocate NODE_DATA for a node on the local memory */ +static void __init alloc_node_data(int nid) { const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); u64 nd_pa; @@ -194,18 +194,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end) int tnid; /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: - */ - if (end && (end - start) < NODE_MIN_SIZE) - return; - - start = roundup(start, ZONE_ALIGN); - - printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", - nid, start, end - 1); - - /* * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ @@ -222,7 +210,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end) nd = __va(nd_pa); /* report and initialize */ - printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]\n", + printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid, nd_pa, nd_pa + nd_size - 1); tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); if (tnid != nid) @@ -230,9 +218,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end) node_data[nid] = nd; memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); - NODE_DATA(nid)->node_id = nid; - NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT; - NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT; node_set_online(nid); } @@ -478,6 +463,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) return true; } +static void __init numa_clear_kernel_node_hotplug(void) +{ + int i, nid; + nodemask_t numa_kernel_nodes = NODE_MASK_NONE; + unsigned long start, end; + struct memblock_region *r; + + /* + * At this time, all memory regions reserved by memblock are + * used by the kernel. Set the nid in memblock.reserved will + * mark out all the nodes the kernel resides in. + */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + struct numa_memblk *mb = &numa_meminfo.blk[i]; + + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.reserved, mb->nid); + } + + /* Mark all kernel nodes. */ + for_each_memblock(reserved, r) + node_set(r->nid, numa_kernel_nodes); + + /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + nid = numa_meminfo.blk[i].nid; + if (!node_isset(nid, numa_kernel_nodes)) + continue; + + start = numa_meminfo.blk[i].start; + end = numa_meminfo.blk[i].end; + + memblock_clear_hotplug(start, end - start); + } +} + static int __init numa_register_memblks(struct numa_meminfo *mi) { unsigned long uninitialized_var(pfn_align); @@ -496,6 +517,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) } /* + * At very early time, the kernel have to use some memory such as + * loading the kernel image. We cannot prevent this anyway. So any + * node the kernel resides in should be un-hotpluggable. + * + * And when we come here, alloc node data won't fail. + */ + numa_clear_kernel_node_hotplug(); + + /* * If sections array is gonna be used for pfn -> nid mapping, check * whether its granularity is fine enough. */ @@ -523,8 +553,17 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) end = max(mi->blk[i].end, end); } - if (start < end) - setup_node_data(nid, start, end); + if (start >= end) + continue; + + /* + * Don't confuse VM with a node that doesn't have the + * minimum amount of memory: + */ + if (end && (end - start) < NODE_MIN_SIZE) + continue; + + alloc_node_data(nid); } /* Dump memblock with node info and return. */ @@ -554,41 +593,6 @@ static void __init numa_init_array(void) } } -static void __init numa_clear_kernel_node_hotplug(void) -{ - int i, nid; - nodemask_t numa_kernel_nodes = NODE_MASK_NONE; - unsigned long start, end; - struct memblock_region *r; - - /* - * At this time, all memory regions reserved by memblock are - * used by the kernel. Set the nid in memblock.reserved will - * mark out all the nodes the kernel resides in. - */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - struct numa_memblk *mb = &numa_meminfo.blk[i]; - memblock_set_node(mb->start, mb->end - mb->start, - &memblock.reserved, mb->nid); - } - - /* Mark all kernel nodes. */ - for_each_memblock(reserved, r) - node_set(r->nid, numa_kernel_nodes); - - /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ - for (i = 0; i < numa_meminfo.nr_blks; i++) { - nid = numa_meminfo.blk[i].nid; - if (!node_isset(nid, numa_kernel_nodes)) - continue; - - start = numa_meminfo.blk[i].start; - end = numa_meminfo.blk[i].end; - - memblock_clear_hotplug(start, end - start); - } -} - static int __init numa_init(int (*init_func)(void)) { int i; @@ -643,15 +647,6 @@ static int __init numa_init(int (*init_func)(void)) } numa_init_array(); - /* - * At very early time, the kernel have to use some memory such as - * loading the kernel image. We cannot prevent this anyway. So any - * node the kernel resides in should be un-hotpluggable. - * - * And when we come here, numa_init() won't fail. - */ - numa_clear_kernel_node_hotplug(); - return 0; } diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 4dd8cf652579..75cc0978d45d 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -59,41 +59,6 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval) __flush_tlb_one(vaddr); } -/* - * Associate a large virtual page frame with a given physical page frame - * and protection flags for that frame. pfn is for the base of the page, - * vaddr is what the page gets mapped to - both must be properly aligned. - * The pmd must already be instantiated. Assumes PAE mode. - */ -void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - - if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */ - printk(KERN_WARNING "set_pmd_pfn: vaddr misaligned\n"); - return; /* BUG(); */ - } - if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */ - printk(KERN_WARNING "set_pmd_pfn: pfn misaligned\n"); - return; /* BUG(); */ - } - pgd = swapper_pg_dir + pgd_index(vaddr); - if (pgd_none(*pgd)) { - printk(KERN_WARNING "set_pmd_pfn: pgd_none\n"); - return; /* BUG(); */ - } - pud = pud_offset(pgd, vaddr); - pmd = pmd_offset(pud, vaddr); - set_pmd(pmd, pfn_pmd(pfn, flags)); - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - unsigned long __FIXADDR_TOP = 0xfffff000; EXPORT_SYMBOL(__FIXADDR_TOP); diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 379e8bd0deea..1d2e6392f5fa 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -64,11 +64,11 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model, static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs) { if (ctr_running) - model->check_ctrs(regs, &__get_cpu_var(cpu_msrs)); + model->check_ctrs(regs, this_cpu_ptr(&cpu_msrs)); else if (!nmi_enabled) return NMI_DONE; else - model->stop(&__get_cpu_var(cpu_msrs)); + model->stop(this_cpu_ptr(&cpu_msrs)); return NMI_HANDLED; } @@ -91,7 +91,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs) static void nmi_cpu_start(void *dummy) { - struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs); + struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs); if (!msrs->controls) WARN_ON_ONCE(1); else @@ -111,7 +111,7 @@ static int nmi_start(void) static void nmi_cpu_stop(void *dummy) { - struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs); + struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs); if (!msrs->controls) WARN_ON_ONCE(1); else diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 98ab13058f89..ad1d91f475ab 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -372,7 +372,7 @@ static unsigned int get_stagger(void) { #ifdef CONFIG_SMP int cpu = smp_processor_id(); - return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); + return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map)); #endif return 0; } diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 059a76c29739..7b20bccf3648 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -81,14 +81,14 @@ struct pci_ops pci_root_ops = { */ DEFINE_RAW_SPINLOCK(pci_config_lock); -static int can_skip_ioresource_align(const struct dmi_system_id *d) +static int __init can_skip_ioresource_align(const struct dmi_system_id *d) { pci_probe |= PCI_CAN_SKIP_ISA_ALIGN; printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident); return 0; } -static const struct dmi_system_id can_skip_pciprobe_dmi_table[] = { +static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __initconst = { /* * Systems where PCI IO resource ISA alignment can be skipped * when the ISA enable bit in the bridge control is not set @@ -186,7 +186,7 @@ void pcibios_remove_bus(struct pci_bus *bus) * on the kernel command line (which was parsed earlier). */ -static int set_bf_sort(const struct dmi_system_id *d) +static int __init set_bf_sort(const struct dmi_system_id *d) { if (pci_bf_sort == pci_bf_sort_default) { pci_bf_sort = pci_dmi_bf; @@ -195,8 +195,8 @@ static int set_bf_sort(const struct dmi_system_id *d) return 0; } -static void read_dmi_type_b1(const struct dmi_header *dm, - void *private_data) +static void __init read_dmi_type_b1(const struct dmi_header *dm, + void *private_data) { u8 *d = (u8 *)dm + 4; @@ -217,7 +217,7 @@ static void read_dmi_type_b1(const struct dmi_header *dm, } } -static int find_sort_method(const struct dmi_system_id *d) +static int __init find_sort_method(const struct dmi_system_id *d) { dmi_walk(read_dmi_type_b1, NULL); @@ -232,7 +232,7 @@ static int find_sort_method(const struct dmi_system_id *d) * Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus) */ #ifdef __i386__ -static int assign_all_busses(const struct dmi_system_id *d) +static int __init assign_all_busses(const struct dmi_system_id *d) { pci_probe |= PCI_ASSIGN_ALL_BUSSES; printk(KERN_INFO "%s detected: enabling PCI bus# renumbering" @@ -241,7 +241,7 @@ static int assign_all_busses(const struct dmi_system_id *d) } #endif -static int set_scan_all(const struct dmi_system_id *d) +static int __init set_scan_all(const struct dmi_system_id *d) { printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n", d->ident); @@ -249,7 +249,7 @@ static int set_scan_all(const struct dmi_system_id *d) return 0; } -static const struct dmi_system_id pciprobe_dmi_table[] = { +static const struct dmi_system_id pciprobe_dmi_table[] __initconst = { #ifdef __i386__ /* * Laptops which need pci=assign-busses to see Cardbus cards @@ -512,7 +512,7 @@ int __init pcibios_init(void) return 0; } -char * __init pcibios_setup(char *str) +char *__init pcibios_setup(char *str) { if (!strcmp(str, "off")) { pci_probe = 0; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 2ae525e0d8ba..37c1435889ce 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -442,8 +442,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, */ prot |= _PAGE_CACHE_UC_MINUS; - prot |= _PAGE_IOMAP; /* creating a mapping for IO */ - vma->vm_page_prot = __pgprot(prot); if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 248642f4bab7..326198a4434e 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -31,7 +31,7 @@ static DEFINE_MUTEX(pci_mmcfg_lock); LIST_HEAD(pci_mmcfg_list); -static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg) +static void __init pci_mmconfig_remove(struct pci_mmcfg_region *cfg) { if (cfg->res.parent) release_resource(&cfg->res); @@ -39,7 +39,7 @@ static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg) kfree(cfg); } -static __init void free_all_mmcfg(void) +static void __init free_all_mmcfg(void) { struct pci_mmcfg_region *cfg, *tmp; @@ -93,7 +93,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start, return new; } -static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start, +static struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, int end, u64 addr) { struct pci_mmcfg_region *new; @@ -125,7 +125,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus) return NULL; } -static const char __init *pci_mmcfg_e7520(void) +static const char *__init pci_mmcfg_e7520(void) { u32 win; raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win); @@ -140,7 +140,7 @@ static const char __init *pci_mmcfg_e7520(void) return "Intel Corporation E7520 Memory Controller Hub"; } -static const char __init *pci_mmcfg_intel_945(void) +static const char *__init pci_mmcfg_intel_945(void) { u32 pciexbar, mask = 0, len = 0; @@ -184,7 +184,7 @@ static const char __init *pci_mmcfg_intel_945(void) return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub"; } -static const char __init *pci_mmcfg_amd_fam10h(void) +static const char *__init pci_mmcfg_amd_fam10h(void) { u32 low, high, address; u64 base, msr; @@ -235,21 +235,25 @@ static const char __init *pci_mmcfg_amd_fam10h(void) } static bool __initdata mcp55_checked; -static const char __init *pci_mmcfg_nvidia_mcp55(void) +static const char *__init pci_mmcfg_nvidia_mcp55(void) { int bus; int mcp55_mmconf_found = 0; - static const u32 extcfg_regnum = 0x90; - static const u32 extcfg_regsize = 4; - static const u32 extcfg_enable_mask = 1<<31; - static const u32 extcfg_start_mask = 0xff<<16; - static const int extcfg_start_shift = 16; - static const u32 extcfg_size_mask = 0x3<<28; - static const int extcfg_size_shift = 28; - static const int extcfg_sizebus[] = {0x100, 0x80, 0x40, 0x20}; - static const u32 extcfg_base_mask[] = {0x7ff8, 0x7ffc, 0x7ffe, 0x7fff}; - static const int extcfg_base_lshift = 25; + static const u32 extcfg_regnum __initconst = 0x90; + static const u32 extcfg_regsize __initconst = 4; + static const u32 extcfg_enable_mask __initconst = 1 << 31; + static const u32 extcfg_start_mask __initconst = 0xff << 16; + static const int extcfg_start_shift __initconst = 16; + static const u32 extcfg_size_mask __initconst = 0x3 << 28; + static const int extcfg_size_shift __initconst = 28; + static const int extcfg_sizebus[] __initconst = { + 0x100, 0x80, 0x40, 0x20 + }; + static const u32 extcfg_base_mask[] __initconst = { + 0x7ff8, 0x7ffc, 0x7ffe, 0x7fff + }; + static const int extcfg_base_lshift __initconst = 25; /* * do check if amd fam10h already took over @@ -302,7 +306,7 @@ struct pci_mmcfg_hostbridge_probe { const char *(*probe)(void); }; -static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = { +static const struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initconst = { { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, pci_mmcfg_e7520 }, { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL, diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index c77b24a8b2da..9b83b9051ae7 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -79,13 +79,13 @@ union bios32 { static struct { unsigned long address; unsigned short segment; -} bios32_indirect = { 0, __KERNEL_CS }; +} bios32_indirect __initdata = { 0, __KERNEL_CS }; /* * Returns the entry point for the given service, NULL on error */ -static unsigned long bios32_service(unsigned long service) +static unsigned long __init bios32_service(unsigned long service) { unsigned char return_code; /* %al */ unsigned long address; /* %ebx */ @@ -124,7 +124,7 @@ static struct { static int pci_bios_present; -static int check_pcibios(void) +static int __init check_pcibios(void) { u32 signature, eax, ebx, ecx; u8 status, major_ver, minor_ver, hw_mech; @@ -312,7 +312,7 @@ static const struct pci_raw_ops pci_bios_access = { * Try to find PCI BIOS. */ -static const struct pci_raw_ops *pci_find_bios(void) +static const struct pci_raw_ops *__init pci_find_bios(void) { union bios32 *check; unsigned char sum; diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index c89c93320c12..c6b146e67116 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -63,8 +63,8 @@ static struct uv_hub_nmi_s **uv_hub_nmi_list; -DEFINE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi); -EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_nmi); +DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi); +EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi); static unsigned long nmi_mmr; static unsigned long nmi_mmr_clear; @@ -215,7 +215,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi) int nmi = 0; local64_inc(&uv_nmi_count); - uv_cpu_nmi.queries++; + this_cpu_inc(uv_cpu_nmi.queries); do { nmi = atomic_read(&hub_nmi->in_nmi); @@ -293,7 +293,7 @@ static void uv_nmi_nr_cpus_ping(void) int cpu; for_each_cpu(cpu, uv_nmi_cpu_mask) - atomic_set(&uv_cpu_nmi_per(cpu).pinging, 1); + uv_cpu_nmi_per(cpu).pinging = 1; apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI); } @@ -304,8 +304,8 @@ static void uv_nmi_cleanup_mask(void) int cpu; for_each_cpu(cpu, uv_nmi_cpu_mask) { - atomic_set(&uv_cpu_nmi_per(cpu).pinging, 0); - atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_OUT); + uv_cpu_nmi_per(cpu).pinging = 0; + uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_OUT; cpumask_clear_cpu(cpu, uv_nmi_cpu_mask); } } @@ -328,7 +328,7 @@ static int uv_nmi_wait_cpus(int first) int loop_delay = uv_nmi_loop_delay; for_each_cpu(j, uv_nmi_cpu_mask) { - if (atomic_read(&uv_cpu_nmi_per(j).state)) { + if (uv_cpu_nmi_per(j).state) { cpumask_clear_cpu(j, uv_nmi_cpu_mask); if (++k >= n) break; @@ -359,7 +359,7 @@ static int uv_nmi_wait_cpus(int first) static void uv_nmi_wait(int master) { /* indicate this cpu is in */ - atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_IN); + this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN); /* if not the first cpu in (the master), then we are a slave cpu */ if (!master) @@ -419,7 +419,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs) "UV:%sNMI process trace for CPU %d\n", dots, cpu); show_regs(regs); } - atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE); + this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE); } /* Trigger a slave cpu to dump it's state */ @@ -427,20 +427,20 @@ static void uv_nmi_trigger_dump(int cpu) { int retry = uv_nmi_trigger_delay; - if (atomic_read(&uv_cpu_nmi_per(cpu).state) != UV_NMI_STATE_IN) + if (uv_cpu_nmi_per(cpu).state != UV_NMI_STATE_IN) return; - atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP); + uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP; do { cpu_relax(); udelay(10); - if (atomic_read(&uv_cpu_nmi_per(cpu).state) + if (uv_cpu_nmi_per(cpu).state != UV_NMI_STATE_DUMP) return; } while (--retry > 0); pr_crit("UV: CPU %d stuck in process dump function\n", cpu); - atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP_DONE); + uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE; } /* Wait until all cpus ready to exit */ @@ -488,7 +488,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master) } else { while (!atomic_read(&uv_nmi_slave_continue)) cpu_relax(); - while (atomic_read(&uv_cpu_nmi.state) != UV_NMI_STATE_DUMP) + while (this_cpu_read(uv_cpu_nmi.state) != UV_NMI_STATE_DUMP) cpu_relax(); uv_nmi_dump_state_cpu(cpu, regs); } @@ -615,7 +615,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) local_irq_save(flags); /* If not a UV System NMI, ignore */ - if (!atomic_read(&uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) { + if (!this_cpu_read(uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) { local_irq_restore(flags); return NMI_DONE; } @@ -639,7 +639,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) uv_call_kgdb_kdb(cpu, regs, master); /* Clear per_cpu "in nmi" flag */ - atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_OUT); + this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT); /* Clear MMR NMI flag on each hub */ uv_clear_nmi(cpu); @@ -666,16 +666,16 @@ static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs) { int ret; - uv_cpu_nmi.queries++; - if (!atomic_read(&uv_cpu_nmi.pinging)) { + this_cpu_inc(uv_cpu_nmi.queries); + if (!this_cpu_read(uv_cpu_nmi.pinging)) { local64_inc(&uv_nmi_ping_misses); return NMI_DONE; } - uv_cpu_nmi.pings++; + this_cpu_inc(uv_cpu_nmi.pings); local64_inc(&uv_nmi_ping_count); ret = uv_handle_nmi(reason, regs); - atomic_set(&uv_cpu_nmi.pinging, 0); + this_cpu_write(uv_cpu_nmi.pinging, 0); return ret; } diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 5c86786bbfd2..a244237f3cfa 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -365,7 +365,7 @@ __setup("uvrtcevt", uv_enable_evt_rtc); static __init void uv_rtc_register_clockevents(struct work_struct *dummy) { - struct clock_event_device *ced = &__get_cpu_var(cpu_ced); + struct clock_event_device *ced = this_cpu_ptr(&cpu_ced); *ced = clock_event_device_uv; ced->cpumask = cpumask_of(smp_processor_id()); diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 7d28c885d238..291226b952a9 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -13,13 +13,11 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mmzone.h> +#include <asm/sections.h> /* Defined in hibernate_asm_32.S */ extern int restore_image(void); -/* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; - /* Pointer to the temporary resume page tables */ pgd_t *resume_pg_dir; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 35e2bb6c0f37..009947d419a6 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -17,11 +17,9 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mtrr.h> +#include <asm/sections.h> #include <asm/suspend.h> -/* References to section boundaries */ -extern __visible const void __nosave_begin, __nosave_end; - /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 899dd2454256..f52e033557c9 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -18,8 +18,9 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE targets += kexec-purgatory.c +CMD_BIN2C = $(objtree)/scripts/basic/bin2c quiet_cmd_bin2c = BIN2C $@ - cmd_bin2c = cat $(obj)/purgatory.ro | $(objtree)/scripts/basic/bin2c kexec_purgatory > $(obj)/kexec-purgatory.c + cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@ $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE $(call if_changed,bin2c) diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index bbb1d2259ecf..a5efb21d5228 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -695,7 +695,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel, * */ static int per_cpu_shndx = -1; -Elf_Addr per_cpu_load_addr; +static Elf_Addr per_cpu_load_addr; static void percpu_init(void) { diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S index 8d0c420465cc..fa4b8b9841ff 100644 --- a/arch/x86/um/checksum_32.S +++ b/arch/x86/um/checksum_32.S @@ -214,242 +214,3 @@ csum_partial: ret #endif - -/* -unsigned int csum_partial_copy_generic (const char *src, char *dst, - int len, int sum, int *src_err_ptr, int *dst_err_ptr) - */ - -/* - * Copy from ds while checksumming, otherwise like csum_partial - * - * The macros SRC and DST specify the type of access for the instruction. - * thus we can call a custom exception handler for all access types. - * - * FIXME: could someone double-check whether I haven't mixed up some SRC and - * DST definitions? It's damn hard to trigger all cases. I hope I got - * them all but there's no guarantee. - */ - -#define SRC(y...) \ - 9999: y; \ - _ASM_EXTABLE(9999b, 6001f) - -#define DST(y...) \ - 9999: y; \ - _ASM_EXTABLE(9999b, 6002f) - -.align 4 - -#ifndef CONFIG_X86_USE_PPRO_CHECKSUM - -#define ARGBASE 16 -#define FP 12 - -csum_partial_copy_generic_i386: - subl $4,%esp - pushl %edi - pushl %esi - pushl %ebx - movl ARGBASE+16(%esp),%eax # sum - movl ARGBASE+12(%esp),%ecx # len - movl ARGBASE+4(%esp),%esi # src - movl ARGBASE+8(%esp),%edi # dst - - testl $2, %edi # Check alignment. - jz 2f # Jump if alignment is ok. - subl $2, %ecx # Alignment uses up two bytes. - jae 1f # Jump if we had at least two bytes. - addl $2, %ecx # ecx was < 2. Deal with it. - jmp 4f -SRC(1: movw (%esi), %bx ) - addl $2, %esi -DST( movw %bx, (%edi) ) - addl $2, %edi - addw %bx, %ax - adcl $0, %eax -2: - movl %ecx, FP(%esp) - shrl $5, %ecx - jz 2f - testl %esi, %esi -SRC(1: movl (%esi), %ebx ) -SRC( movl 4(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, (%edi) ) - adcl %edx, %eax -DST( movl %edx, 4(%edi) ) - -SRC( movl 8(%esi), %ebx ) -SRC( movl 12(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, 8(%edi) ) - adcl %edx, %eax -DST( movl %edx, 12(%edi) ) - -SRC( movl 16(%esi), %ebx ) -SRC( movl 20(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, 16(%edi) ) - adcl %edx, %eax -DST( movl %edx, 20(%edi) ) - -SRC( movl 24(%esi), %ebx ) -SRC( movl 28(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, 24(%edi) ) - adcl %edx, %eax -DST( movl %edx, 28(%edi) ) - - lea 32(%esi), %esi - lea 32(%edi), %edi - dec %ecx - jne 1b - adcl $0, %eax -2: movl FP(%esp), %edx - movl %edx, %ecx - andl $0x1c, %edx - je 4f - shrl $2, %edx # This clears CF -SRC(3: movl (%esi), %ebx ) - adcl %ebx, %eax -DST( movl %ebx, (%edi) ) - lea 4(%esi), %esi - lea 4(%edi), %edi - dec %edx - jne 3b - adcl $0, %eax -4: andl $3, %ecx - jz 7f - cmpl $2, %ecx - jb 5f -SRC( movw (%esi), %cx ) - leal 2(%esi), %esi -DST( movw %cx, (%edi) ) - leal 2(%edi), %edi - je 6f - shll $16,%ecx -SRC(5: movb (%esi), %cl ) -DST( movb %cl, (%edi) ) -6: addl %ecx, %eax - adcl $0, %eax -7: -5000: - -# Exception handler: -.section .fixup, "ax" - -6001: - movl ARGBASE+20(%esp), %ebx # src_err_ptr - movl $-EFAULT, (%ebx) - - # zero the complete destination - computing the rest - # is too much work - movl ARGBASE+8(%esp), %edi # dst - movl ARGBASE+12(%esp), %ecx # len - xorl %eax,%eax - rep ; stosb - - jmp 5000b - -6002: - movl ARGBASE+24(%esp), %ebx # dst_err_ptr - movl $-EFAULT,(%ebx) - jmp 5000b - -.previous - - popl %ebx - popl %esi - popl %edi - popl %ecx # equivalent to addl $4,%esp - ret - -#else - -/* Version for PentiumII/PPro */ - -#define ROUND1(x) \ - SRC(movl x(%esi), %ebx ) ; \ - addl %ebx, %eax ; \ - DST(movl %ebx, x(%edi) ) ; - -#define ROUND(x) \ - SRC(movl x(%esi), %ebx ) ; \ - adcl %ebx, %eax ; \ - DST(movl %ebx, x(%edi) ) ; - -#define ARGBASE 12 - -csum_partial_copy_generic_i386: - pushl %ebx - pushl %edi - pushl %esi - movl ARGBASE+4(%esp),%esi #src - movl ARGBASE+8(%esp),%edi #dst - movl ARGBASE+12(%esp),%ecx #len - movl ARGBASE+16(%esp),%eax #sum -# movl %ecx, %edx - movl %ecx, %ebx - movl %esi, %edx - shrl $6, %ecx - andl $0x3c, %ebx - negl %ebx - subl %ebx, %esi - subl %ebx, %edi - lea -1(%esi),%edx - andl $-32,%edx - lea 3f(%ebx,%ebx), %ebx - testl %esi, %esi - jmp *%ebx -1: addl $64,%esi - addl $64,%edi - SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) - ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52) - ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36) - ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20) - ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4) -3: adcl $0,%eax - addl $64, %edx - dec %ecx - jge 1b -4: movl ARGBASE+12(%esp),%edx #len - andl $3, %edx - jz 7f - cmpl $2, %edx - jb 5f -SRC( movw (%esi), %dx ) - leal 2(%esi), %esi -DST( movw %dx, (%edi) ) - leal 2(%edi), %edi - je 6f - shll $16,%edx -5: -SRC( movb (%esi), %dl ) -DST( movb %dl, (%edi) ) -6: addl %edx, %eax - adcl $0, %eax -7: -.section .fixup, "ax" -6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr - movl $-EFAULT, (%ebx) - # zero the complete destination (computing the rest is too much work) - movl ARGBASE+8(%esp),%edi # dst - movl ARGBASE+12(%esp),%ecx # len - xorl %eax,%eax - rep; stosb - jmp 7b -6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr - movl $-EFAULT, (%ebx) - jmp 7b -.previous - - popl %esi - popl %edi - popl %ebx - ret - -#undef ROUND -#undef ROUND1 - -#endif diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h index fd57829b30d8..0224987556ce 100644 --- a/arch/x86/vdso/vdso2c.h +++ b/arch/x86/vdso/vdso2c.h @@ -109,16 +109,18 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, /* Validate mapping addresses. */ for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) { - if (!syms[i]) + INT_BITS symval = syms[special_pages[i]]; + + if (!symval) continue; /* The mapping isn't used; ignore it. */ - if (syms[i] % 4096) + if (symval % 4096) fail("%s must be a multiple of 4096\n", required_syms[i].name); - if (syms[sym_vvar_start] > syms[i] + 4096) - fail("%s underruns begin_vvar\n", + if (symval + 4096 < syms[sym_vvar_start]) + fail("%s underruns vvar_start\n", required_syms[i].name); - if (syms[i] + 4096 > 0) + if (symval + 4096 > 0) fail("%s is on the wrong side of the vdso text\n", required_syms[i].name); } diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index a02e09e18f57..be14cc3e48d5 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -15,12 +15,14 @@ * with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/bitops.h> #include <linux/efi.h> #include <linux/init.h> #include <linux/string.h> #include <xen/xen-ops.h> +#include <asm/page.h> #include <asm/setup.h> void __init xen_efi_init(void) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c0cb11fb5008..1a3f0445432a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -821,7 +821,7 @@ static void xen_convert_trap_info(const struct desc_ptr *desc, void xen_copy_trap_info(struct trap_info *traps) { - const struct desc_ptr *desc = &__get_cpu_var(idt_desc); + const struct desc_ptr *desc = this_cpu_ptr(&idt_desc); xen_convert_trap_info(desc, traps); } @@ -838,7 +838,7 @@ static void xen_load_idt(const struct desc_ptr *desc) spin_lock(&lock); - __get_cpu_var(idt_desc) = *desc; + memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc)); xen_convert_trap_info(desc, traps); @@ -1463,6 +1463,7 @@ static void __ref xen_setup_gdt(int cpu) pv_cpu_ops.load_gdt = xen_load_gdt; } +#ifdef CONFIG_XEN_PVH /* * A PV guest starts with default flags that are not set for PVH, set them * here asap. @@ -1508,17 +1509,21 @@ static void __init xen_pvh_early_guest_init(void) return; xen_have_vector_callback = 1; + + xen_pvh_early_cpu_init(0, false); xen_pvh_set_cr_flags(0); #ifdef CONFIG_X86_32 BUG(); /* PVH: Implement proper support. */ #endif } +#endif /* CONFIG_XEN_PVH */ /* First C function to be called on Xen boot */ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; + unsigned long initrd_start = 0; int rc; if (!xen_start_info) @@ -1527,7 +1532,9 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_domain_type = XEN_PV_DOMAIN; xen_setup_features(); +#ifdef CONFIG_XEN_PVH xen_pvh_early_guest_init(); +#endif xen_setup_machphys_mapping(); /* Install Xen paravirt ops */ @@ -1559,8 +1566,6 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); - __supported_pte_mask |= _PAGE_IOMAP; - /* * Prevent page tables from being allocated in highmem, even * if CONFIG_HIGHPTE is enabled. @@ -1667,10 +1672,16 @@ asmlinkage __visible void __init xen_start_kernel(void) new_cpu_data.x86_capability[0] = cpuid_edx(1); #endif + if (xen_start_info->mod_start) { + if (xen_start_info->flags & SIF_MOD_START_PFN) + initrd_start = PFN_PHYS(xen_start_info->mod_start); + else + initrd_start = __pa(xen_start_info->mod_start); + } + /* Poke various useful things into boot_params */ boot_params.hdr.type_of_loader = (9 << 4) | 0; - boot_params.hdr.ramdisk_image = xen_start_info->mod_start - ? __pa(xen_start_info->mod_start) : 0; + boot_params.hdr.ramdisk_image = initrd_start; boot_params.hdr.ramdisk_size = xen_start_info->mod_len; boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 16fb0099b7f2..f62af7647ec9 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -399,38 +399,14 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) if (unlikely(mfn == INVALID_P2M_ENTRY)) { mfn = 0; flags = 0; - } else { - /* - * Paramount to do this test _after_ the - * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY & - * IDENTITY_FRAME_BIT resolves to true. - */ - mfn &= ~FOREIGN_FRAME_BIT; - if (mfn & IDENTITY_FRAME_BIT) { - mfn &= ~IDENTITY_FRAME_BIT; - flags |= _PAGE_IOMAP; - } - } + } else + mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT); val = ((pteval_t)mfn << PAGE_SHIFT) | flags; } return val; } -static pteval_t iomap_pte(pteval_t val) -{ - if (val & _PAGE_PRESENT) { - unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; - pteval_t flags = val & PTE_FLAGS_MASK; - - /* We assume the pte frame number is a MFN, so - just use it as-is. */ - val = ((pteval_t)pfn << PAGE_SHIFT) | flags; - } - - return val; -} - __visible pteval_t xen_pte_val(pte_t pte) { pteval_t pteval = pte.pte; @@ -441,9 +417,6 @@ __visible pteval_t xen_pte_val(pte_t pte) pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT; } #endif - if (xen_initial_domain() && (pteval & _PAGE_IOMAP)) - return pteval; - return pte_mfn_to_pfn(pteval); } PV_CALLEE_SAVE_REGS_THUNK(xen_pte_val); @@ -481,7 +454,6 @@ void xen_set_pat(u64 pat) __visible pte_t xen_make_pte(pteval_t pte) { - phys_addr_t addr = (pte & PTE_PFN_MASK); #if 0 /* If Linux is trying to set a WC pte, then map to the Xen WC. * If _PAGE_PAT is set, then it probably means it is really @@ -496,19 +468,7 @@ __visible pte_t xen_make_pte(pteval_t pte) pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT; } #endif - /* - * Unprivileged domains are allowed to do IOMAPpings for - * PCI passthrough, but not map ISA space. The ISA - * mappings are just dummy local mappings to keep other - * parts of the kernel happy. - */ - if (unlikely(pte & _PAGE_IOMAP) && - (xen_initial_domain() || addr >= ISA_END_ADDRESS)) { - pte = iomap_pte(pte); - } else { - pte &= ~_PAGE_IOMAP; - pte = pte_pfn_to_mfn(pte); - } + pte = pte_pfn_to_mfn(pte); return native_make_pte(pte); } @@ -2091,7 +2051,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) default: /* By default, set_fixmap is used for hardware mappings */ - pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP)); + pte = mfn_pte(phys, prot); break; } diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 0d82003e76ad..ea54a08d8301 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -54,7 +54,7 @@ DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags); void xen_mc_flush(void) { - struct mc_buffer *b = &__get_cpu_var(mc_buffer); + struct mc_buffer *b = this_cpu_ptr(&mc_buffer); struct multicall_entry *mc; int ret = 0; unsigned long flags; @@ -131,7 +131,7 @@ void xen_mc_flush(void) struct multicall_space __xen_mc_entry(size_t args) { - struct mc_buffer *b = &__get_cpu_var(mc_buffer); + struct mc_buffer *b = this_cpu_ptr(&mc_buffer); struct multicall_space ret; unsigned argidx = roundup(b->argidx, sizeof(u64)); @@ -162,7 +162,7 @@ struct multicall_space __xen_mc_entry(size_t args) struct multicall_space xen_mc_extend_args(unsigned long op, size_t size) { - struct mc_buffer *b = &__get_cpu_var(mc_buffer); + struct mc_buffer *b = this_cpu_ptr(&mc_buffer); struct multicall_space ret = { NULL, NULL }; BUG_ON(preemptible()); @@ -192,7 +192,7 @@ out: void xen_mc_callback(void (*fn)(void *), void *data) { - struct mc_buffer *b = &__get_cpu_var(mc_buffer); + struct mc_buffer *b = this_cpu_ptr(&mc_buffer); struct callback *cb; if (b->cbidx == MC_BATCH) { diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 3172692381ae..9f5983b01ed9 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -173,6 +173,7 @@ #include <xen/balloon.h> #include <xen/grant_table.h> +#include "p2m.h" #include "multicalls.h" #include "xen-ops.h" @@ -180,12 +181,6 @@ static void __init m2p_override_init(void); unsigned long xen_max_p2m_pfn __read_mostly; -#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) -#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) -#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) - -#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) - /* Placeholders for holes in the address space */ static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE); @@ -202,16 +197,12 @@ static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE); RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); -/* We might hit two boundary violations at the start and end, at max each - * boundary violation will require three middle nodes. */ -RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3); - -/* When we populate back during bootup, the amount of pages can vary. The - * max we have is seen is 395979, but that does not mean it can't be more. - * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle - * it can re-use Xen provided mfn_list array, so we only need to allocate at - * most three P2M top nodes. */ -RESERVE_BRK(p2m_populated, PAGE_SIZE * 3); +/* For each I/O range remapped we may lose up to two leaf pages for the boundary + * violations and three mid pages to cover up to 3GB. With + * early_can_reuse_p2m_middle() most of the leaf pages will be reused by the + * remapped region. + */ +RESERVE_BRK(p2m_identity_remap, PAGE_SIZE * 2 * 3 * MAX_REMAP_RANGES); static inline unsigned p2m_top_index(unsigned long pfn) { diff --git a/arch/x86/xen/p2m.h b/arch/x86/xen/p2m.h new file mode 100644 index 000000000000..ad8aee24ab72 --- /dev/null +++ b/arch/x86/xen/p2m.h @@ -0,0 +1,15 @@ +#ifndef _XEN_P2M_H +#define _XEN_P2M_H + +#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) +#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) +#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) + +#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) + +#define MAX_REMAP_RANGES 10 + +extern unsigned long __init set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e); + +#endif /* _XEN_P2M_H */ diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 2e555163c2fe..af7216128d93 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -29,6 +29,7 @@ #include <xen/features.h> #include "xen-ops.h" #include "vdso.h" +#include "p2m.h" /* These are code, but not functions. Defined in entry.S */ extern const char xen_hypervisor_callback[]; @@ -46,6 +47,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; +/* Buffer used to remap identity mapped pages */ +unsigned long xen_remap_buf[P2M_PER_PAGE] __initdata; + /* * The maximum amount of extra memory compared to the base size. The * main scaling factor is the size of struct page. At extreme ratios @@ -151,107 +155,325 @@ static unsigned long __init xen_do_chunk(unsigned long start, return len; } -static unsigned long __init xen_release_chunk(unsigned long start, - unsigned long end) -{ - return xen_do_chunk(start, end, true); -} - -static unsigned long __init xen_populate_chunk( +/* + * Finds the next RAM pfn available in the E820 map after min_pfn. + * This function updates min_pfn with the pfn found and returns + * the size of that range or zero if not found. + */ +static unsigned long __init xen_find_pfn_range( const struct e820entry *list, size_t map_size, - unsigned long max_pfn, unsigned long *last_pfn, - unsigned long credits_left) + unsigned long *min_pfn) { const struct e820entry *entry; unsigned int i; unsigned long done = 0; - unsigned long dest_pfn; for (i = 0, entry = list; i < map_size; i++, entry++) { unsigned long s_pfn; unsigned long e_pfn; - unsigned long pfns; - long capacity; - - if (credits_left <= 0) - break; if (entry->type != E820_RAM) continue; e_pfn = PFN_DOWN(entry->addr + entry->size); - /* We only care about E820 after the xen_start_info->nr_pages */ - if (e_pfn <= max_pfn) + /* We only care about E820 after this */ + if (e_pfn < *min_pfn) continue; s_pfn = PFN_UP(entry->addr); - /* If the E820 falls within the nr_pages, we want to start - * at the nr_pages PFN. - * If that would mean going past the E820 entry, skip it + + /* If min_pfn falls within the E820 entry, we want to start + * at the min_pfn PFN. */ - if (s_pfn <= max_pfn) { - capacity = e_pfn - max_pfn; - dest_pfn = max_pfn; + if (s_pfn <= *min_pfn) { + done = e_pfn - *min_pfn; } else { - capacity = e_pfn - s_pfn; - dest_pfn = s_pfn; + done = e_pfn - s_pfn; + *min_pfn = s_pfn; } + break; + } - if (credits_left < capacity) - capacity = credits_left; + return done; +} - pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false); - done += pfns; - *last_pfn = (dest_pfn + pfns); - if (pfns < capacity) - break; - credits_left -= pfns; +/* + * This releases a chunk of memory and then does the identity map. It's used as + * as a fallback if the remapping fails. + */ +static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, + unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity, + unsigned long *released) +{ + WARN_ON(start_pfn > end_pfn); + + /* Need to release pages first */ + *released += xen_do_chunk(start_pfn, min(end_pfn, nr_pages), true); + *identity += set_phys_range_identity(start_pfn, end_pfn); +} + +/* + * Helper function to update both the p2m and m2p tables. + */ +static unsigned long __init xen_update_mem_tables(unsigned long pfn, + unsigned long mfn) +{ + struct mmu_update update = { + .ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE, + .val = pfn + }; + + /* Update p2m */ + if (!early_set_phys_to_machine(pfn, mfn)) { + WARN(1, "Failed to set p2m mapping for pfn=%ld mfn=%ld\n", + pfn, mfn); + return false; } - return done; + + /* Update m2p */ + if (HYPERVISOR_mmu_update(&update, 1, NULL, DOMID_SELF) < 0) { + WARN(1, "Failed to set m2p mapping for mfn=%ld pfn=%ld\n", + mfn, pfn); + return false; + } + + return true; } -static void __init xen_set_identity_and_release_chunk( - unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, - unsigned long *released, unsigned long *identity) +/* + * This function updates the p2m and m2p tables with an identity map from + * start_pfn to start_pfn+size and remaps the underlying RAM of the original + * allocation at remap_pfn. It must do so carefully in P2M_PER_PAGE sized blocks + * to not exhaust the reserved brk space. Doing it in properly aligned blocks + * ensures we only allocate the minimum required leaf pages in the p2m table. It + * copies the existing mfns from the p2m table under the 1:1 map, overwrites + * them with the identity map and then updates the p2m and m2p tables with the + * remapped memory. + */ +static unsigned long __init xen_do_set_identity_and_remap_chunk( + unsigned long start_pfn, unsigned long size, unsigned long remap_pfn) { - unsigned long pfn; + unsigned long ident_pfn_iter, remap_pfn_iter; + unsigned long ident_start_pfn_align, remap_start_pfn_align; + unsigned long ident_end_pfn_align, remap_end_pfn_align; + unsigned long ident_boundary_pfn, remap_boundary_pfn; + unsigned long ident_cnt = 0; + unsigned long remap_cnt = 0; + unsigned long left = size; + unsigned long mod; + int i; + + WARN_ON(size == 0); + + BUG_ON(xen_feature(XENFEAT_auto_translated_physmap)); /* - * If the PFNs are currently mapped, clear the mappings - * (except for the ISA region which must be 1:1 mapped) to - * release the refcounts (in Xen) on the original frames. + * Determine the proper alignment to remap memory in P2M_PER_PAGE sized + * blocks. We need to keep track of both the existing pfn mapping and + * the new pfn remapping. */ - for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) { - pte_t pte = __pte_ma(0); + mod = start_pfn % P2M_PER_PAGE; + ident_start_pfn_align = + mod ? (start_pfn - mod + P2M_PER_PAGE) : start_pfn; + mod = remap_pfn % P2M_PER_PAGE; + remap_start_pfn_align = + mod ? (remap_pfn - mod + P2M_PER_PAGE) : remap_pfn; + mod = (start_pfn + size) % P2M_PER_PAGE; + ident_end_pfn_align = start_pfn + size - mod; + mod = (remap_pfn + size) % P2M_PER_PAGE; + remap_end_pfn_align = remap_pfn + size - mod; + + /* Iterate over each p2m leaf node in each range */ + for (ident_pfn_iter = ident_start_pfn_align, remap_pfn_iter = remap_start_pfn_align; + ident_pfn_iter < ident_end_pfn_align && remap_pfn_iter < remap_end_pfn_align; + ident_pfn_iter += P2M_PER_PAGE, remap_pfn_iter += P2M_PER_PAGE) { + /* Check we aren't past the end */ + BUG_ON(ident_pfn_iter + P2M_PER_PAGE > start_pfn + size); + BUG_ON(remap_pfn_iter + P2M_PER_PAGE > remap_pfn + size); + + /* Save p2m mappings */ + for (i = 0; i < P2M_PER_PAGE; i++) + xen_remap_buf[i] = pfn_to_mfn(ident_pfn_iter + i); + + /* Set identity map which will free a p2m leaf */ + ident_cnt += set_phys_range_identity(ident_pfn_iter, + ident_pfn_iter + P2M_PER_PAGE); + +#ifdef DEBUG + /* Helps verify a p2m leaf has been freed */ + for (i = 0; i < P2M_PER_PAGE; i++) { + unsigned int pfn = ident_pfn_iter + i; + BUG_ON(pfn_to_mfn(pfn) != pfn); + } +#endif + /* Now remap memory */ + for (i = 0; i < P2M_PER_PAGE; i++) { + unsigned long mfn = xen_remap_buf[i]; + + /* This will use the p2m leaf freed above */ + if (!xen_update_mem_tables(remap_pfn_iter + i, mfn)) { + WARN(1, "Failed to update mem mapping for pfn=%ld mfn=%ld\n", + remap_pfn_iter + i, mfn); + return 0; + } + + remap_cnt++; + } - if (pfn < PFN_UP(ISA_END_ADDRESS)) - pte = mfn_pte(pfn, PAGE_KERNEL_IO); + left -= P2M_PER_PAGE; + } - (void)HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), pte, 0); + /* Max boundary space possible */ + BUG_ON(left > (P2M_PER_PAGE - 1) * 2); + + /* Now handle the boundary conditions */ + ident_boundary_pfn = start_pfn; + remap_boundary_pfn = remap_pfn; + for (i = 0; i < left; i++) { + unsigned long mfn; + + /* These two checks move from the start to end boundaries */ + if (ident_boundary_pfn == ident_start_pfn_align) + ident_boundary_pfn = ident_pfn_iter; + if (remap_boundary_pfn == remap_start_pfn_align) + remap_boundary_pfn = remap_pfn_iter; + + /* Check we aren't past the end */ + BUG_ON(ident_boundary_pfn >= start_pfn + size); + BUG_ON(remap_boundary_pfn >= remap_pfn + size); + + mfn = pfn_to_mfn(ident_boundary_pfn); + + if (!xen_update_mem_tables(remap_boundary_pfn, mfn)) { + WARN(1, "Failed to update mem mapping for pfn=%ld mfn=%ld\n", + remap_pfn_iter + i, mfn); + return 0; + } + remap_cnt++; + + ident_boundary_pfn++; + remap_boundary_pfn++; } - if (start_pfn < nr_pages) - *released += xen_release_chunk( - start_pfn, min(end_pfn, nr_pages)); + /* Finish up the identity map */ + if (ident_start_pfn_align >= ident_end_pfn_align) { + /* + * In this case we have an identity range which does not span an + * aligned block so everything needs to be identity mapped here. + * If we didn't check this we might remap too many pages since + * the align boundaries are not meaningful in this case. + */ + ident_cnt += set_phys_range_identity(start_pfn, + start_pfn + size); + } else { + /* Remapped above so check each end of the chunk */ + if (start_pfn < ident_start_pfn_align) + ident_cnt += set_phys_range_identity(start_pfn, + ident_start_pfn_align); + if (start_pfn + size > ident_pfn_iter) + ident_cnt += set_phys_range_identity(ident_pfn_iter, + start_pfn + size); + } - *identity += set_phys_range_identity(start_pfn, end_pfn); + BUG_ON(ident_cnt != size); + BUG_ON(remap_cnt != size); + + return size; } -static unsigned long __init xen_set_identity_and_release( - const struct e820entry *list, size_t map_size, unsigned long nr_pages) +/* + * This function takes a contiguous pfn range that needs to be identity mapped + * and: + * + * 1) Finds a new range of pfns to use to remap based on E820 and remap_pfn. + * 2) Calls the do_ function to actually do the mapping/remapping work. + * + * The goal is to not allocate additional memory but to remap the existing + * pages. In the case of an error the underlying memory is simply released back + * to Xen and not remapped. + */ +static unsigned long __init xen_set_identity_and_remap_chunk( + const struct e820entry *list, size_t map_size, unsigned long start_pfn, + unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn, + unsigned long *identity, unsigned long *remapped, + unsigned long *released) +{ + unsigned long pfn; + unsigned long i = 0; + unsigned long n = end_pfn - start_pfn; + + while (i < n) { + unsigned long cur_pfn = start_pfn + i; + unsigned long left = n - i; + unsigned long size = left; + unsigned long remap_range_size; + + /* Do not remap pages beyond the current allocation */ + if (cur_pfn >= nr_pages) { + /* Identity map remaining pages */ + *identity += set_phys_range_identity(cur_pfn, + cur_pfn + size); + break; + } + if (cur_pfn + size > nr_pages) + size = nr_pages - cur_pfn; + + remap_range_size = xen_find_pfn_range(list, map_size, + &remap_pfn); + if (!remap_range_size) { + pr_warning("Unable to find available pfn range, not remapping identity pages\n"); + xen_set_identity_and_release_chunk(cur_pfn, + cur_pfn + left, nr_pages, identity, released); + break; + } + /* Adjust size to fit in current e820 RAM region */ + if (size > remap_range_size) + size = remap_range_size; + + if (!xen_do_set_identity_and_remap_chunk(cur_pfn, size, remap_pfn)) { + WARN(1, "Failed to remap 1:1 memory cur_pfn=%ld size=%ld remap_pfn=%ld\n", + cur_pfn, size, remap_pfn); + xen_set_identity_and_release_chunk(cur_pfn, + cur_pfn + left, nr_pages, identity, released); + break; + } + + /* Update variables to reflect new mappings. */ + i += size; + remap_pfn += size; + *identity += size; + *remapped += size; + } + + /* + * If the PFNs are currently mapped, the VA mapping also needs + * to be updated to be 1:1. + */ + for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) + (void)HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + mfn_pte(pfn, PAGE_KERNEL_IO), 0); + + return remap_pfn; +} + +static unsigned long __init xen_set_identity_and_remap( + const struct e820entry *list, size_t map_size, unsigned long nr_pages, + unsigned long *released) { phys_addr_t start = 0; - unsigned long released = 0; unsigned long identity = 0; + unsigned long remapped = 0; + unsigned long last_pfn = nr_pages; const struct e820entry *entry; + unsigned long num_released = 0; int i; /* * Combine non-RAM regions and gaps until a RAM region (or the * end of the map) is reached, then set the 1:1 map and - * release the pages (if available) in those non-RAM regions. + * remap the memory in those non-RAM regions. * * The combined non-RAM regions are rounded to a whole number * of pages so any partial pages are accessible via the 1:1 @@ -269,22 +491,24 @@ static unsigned long __init xen_set_identity_and_release( end_pfn = PFN_UP(entry->addr); if (start_pfn < end_pfn) - xen_set_identity_and_release_chunk( - start_pfn, end_pfn, nr_pages, - &released, &identity); - + last_pfn = xen_set_identity_and_remap_chunk( + list, map_size, start_pfn, + end_pfn, nr_pages, last_pfn, + &identity, &remapped, + &num_released); start = end; } } - if (released) - printk(KERN_INFO "Released %lu pages of unused memory\n", released); - if (identity) - printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity); + *released = num_released; - return released; -} + pr_info("Set %ld page(s) to 1-1 mapping\n", identity); + pr_info("Remapped %ld page(s), last_pfn=%ld\n", remapped, + last_pfn); + pr_info("Released %ld page(s)\n", num_released); + return last_pfn; +} static unsigned long __init xen_get_max_pages(void) { unsigned long max_pages = MAX_DOMAIN_PAGES; @@ -347,7 +571,6 @@ char * __init xen_memory_setup(void) unsigned long max_pages; unsigned long last_pfn = 0; unsigned long extra_pages = 0; - unsigned long populated; int i; int op; @@ -392,20 +615,11 @@ char * __init xen_memory_setup(void) extra_pages += max_pages - max_pfn; /* - * Set P2M for all non-RAM pages and E820 gaps to be identity - * type PFNs. Any RAM pages that would be made inaccesible by - * this are first released. + * Set identity map on non-RAM pages and remap the underlying RAM. */ - xen_released_pages = xen_set_identity_and_release( - map, memmap.nr_entries, max_pfn); - - /* - * Populate back the non-RAM pages and E820 gaps that had been - * released. */ - populated = xen_populate_chunk(map, memmap.nr_entries, - max_pfn, &last_pfn, xen_released_pages); + last_pfn = xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn, + &xen_released_pages); - xen_released_pages -= populated; extra_pages += xen_released_pages; if (last_pfn > max_pfn) { diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 7005974c3ff3..8650cdb53209 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -37,6 +37,7 @@ #include <xen/hvc-console.h> #include "xen-ops.h" #include "mmu.h" +#include "smp.h" cpumask_var_t xen_cpu_initialized_map; @@ -99,10 +100,14 @@ static void cpu_bringup(void) wmb(); /* make sure everything is out */ } -/* Note: cpu parameter is only relevant for PVH */ -static void cpu_bringup_and_idle(int cpu) +/* + * Note: cpu parameter is only relevant for PVH. The reason for passing it + * is we can't do smp_processor_id until the percpu segments are loaded, for + * which we need the cpu number! So we pass it in rdi as first parameter. + */ +asmlinkage __visible void cpu_bringup_and_idle(int cpu) { -#ifdef CONFIG_X86_64 +#ifdef CONFIG_XEN_PVH if (xen_feature(XENFEAT_auto_translated_physmap) && xen_feature(XENFEAT_supervisor_mode_kernel)) xen_pvh_secondary_vcpu_init(cpu); @@ -360,6 +365,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) struct desc_struct *gdt; unsigned long gdt_mfn; + /* used to tell cpu_init() that it can proceed with initialization */ + cpumask_set_cpu(cpu, cpu_callout_mask); if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map)) return 0; @@ -374,11 +381,10 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->user_regs.fs = __KERNEL_PERCPU; ctxt->user_regs.gs = __KERNEL_STACK_CANARY; #endif - ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; - memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); if (!xen_feature(XENFEAT_auto_translated_physmap)) { + ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle; ctxt->flags = VGCF_IN_KERNEL; ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */ ctxt->user_regs.ds = __USER_DS; @@ -413,15 +419,18 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) (unsigned long)xen_failsafe_callback; ctxt->user_regs.cs = __KERNEL_CS; per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir); -#ifdef CONFIG_X86_32 } -#else - } else - /* N.B. The user_regs.eip (cpu_bringup_and_idle) is called with - * %rdi having the cpu number - which means are passing in - * as the first parameter the cpu. Subtle! +#ifdef CONFIG_XEN_PVH + else { + /* + * The vcpu comes on kernel page tables which have the NX pte + * bit set. This means before DS/SS is touched, NX in + * EFER must be set. Hence the following assembly glue code. */ + ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init; ctxt->user_regs.rdi = cpu; + ctxt->user_regs.rsi = true; /* entry == true */ + } #endif ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs); ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir)); diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index c7c2d89efd76..963d62a35c82 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -8,4 +8,12 @@ extern void xen_send_IPI_allbutself(int vector); extern void xen_send_IPI_all(int vector); extern void xen_send_IPI_self(int vector); +#ifdef CONFIG_XEN_PVH +extern void xen_pvh_early_cpu_init(int cpu, bool entry); +#else +static inline void xen_pvh_early_cpu_init(int cpu, bool entry) +{ +} +#endif + #endif diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 0ba5f3b967f0..23b45eb9a89c 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -109,7 +109,7 @@ static bool xen_pvspin = true; __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { int irq = __this_cpu_read(lock_kicker_irq); - struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting); + struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting); int cpu = smp_processor_id(); u64 start; unsigned long flags; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 5718b0b58b60..a1d430b112b3 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -80,7 +80,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res) BUG_ON(preemptible()); - state = &__get_cpu_var(xen_runstate); + state = this_cpu_ptr(&xen_runstate); /* * The runstate info is always updated by the hypervisor on @@ -123,7 +123,7 @@ static void do_stolen_accounting(void) WARN_ON(state.state != RUNSTATE_running); - snap = &__get_cpu_var(xen_runstate_snapshot); + snap = this_cpu_ptr(&xen_runstate_snapshot); /* work out how much time the VCPU has not been runn*ing* */ runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; @@ -158,7 +158,7 @@ cycle_t xen_clocksource_read(void) cycle_t ret; preempt_disable_notrace(); - src = &__get_cpu_var(xen_vcpu)->time; + src = this_cpu_ptr(&xen_vcpu->time); ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -397,7 +397,7 @@ static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt. static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) { - struct clock_event_device *evt = &__get_cpu_var(xen_clock_events).evt; + struct clock_event_device *evt = this_cpu_ptr(&xen_clock_events.evt); irqreturn_t ret; ret = IRQ_NONE; @@ -460,7 +460,7 @@ void xen_setup_cpu_clockevents(void) { BUG_ON(preemptible()); - clockevents_register_device(&__get_cpu_var(xen_clock_events).evt); + clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt)); } void xen_timer_resume(void) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 485b69585540..674b222544b7 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -47,6 +47,41 @@ ENTRY(startup_xen) __FINIT +#ifdef CONFIG_XEN_PVH +/* + * xen_pvh_early_cpu_init() - early PVH VCPU initialization + * @cpu: this cpu number (%rdi) + * @entry: true if this is a secondary vcpu coming up on this entry + * point, false if this is the boot CPU being initialized for + * the first time (%rsi) + * + * Note: This is called as a function on the boot CPU, and is the entry point + * on the secondary CPU. + */ +ENTRY(xen_pvh_early_cpu_init) + mov %rsi, %r11 + + /* Gather features to see if NX implemented. */ + mov $0x80000001, %eax + cpuid + mov %edx, %esi + + mov $MSR_EFER, %ecx + rdmsr + bts $_EFER_SCE, %eax + + bt $20, %esi + jnc 1f /* No NX, skip setting it */ + bts $_EFER_NX, %eax +1: wrmsr +#ifdef CONFIG_SMP + cmp $0, %r11b + jne cpu_bringup_and_idle +#endif + ret + +#endif /* CONFIG_XEN_PVH */ + .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) @@ -124,6 +159,7 @@ NEXT_HYPERCALL(arch_6) ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID, .quad _PAGE_PRESENT; .quad _PAGE_PRESENT) ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1) + ELFNOTE(Xen, XEN_ELFNOTE_MOD_START_PFN, .long 1) ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW, _ASM_PTR __HYPERVISOR_VIRT_START) ELFNOTE(Xen, XEN_ELFNOTE_PADDR_OFFSET, _ASM_PTR 0) |