diff options
Diffstat (limited to 'arch/x86')
48 files changed, 1725 insertions, 1223 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2dc18605831f..a494fa34713a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -164,10 +164,6 @@ config INSTRUCTION_DECODER def_bool y depends on KPROBES || PERF_EVENTS || UPROBES -config PERF_EVENTS_INTEL_UNCORE - def_bool y - depends on PERF_EVENTS && CPU_SUP_INTEL && PCI - config OUTPUT_FORMAT string default "elf32-i386" if X86_32 @@ -1046,6 +1042,8 @@ config X86_THERMAL_VECTOR def_bool y depends on X86_MCE_INTEL +source "arch/x86/events/Kconfig" + config X86_LEGACY_VM86 bool "Legacy VM86 support" default n @@ -1210,15 +1208,6 @@ config MICROCODE_OLD_INTERFACE def_bool y depends on MICROCODE -config PERF_EVENTS_AMD_POWER - depends on PERF_EVENTS && CPU_SUP_AMD - tristate "AMD Processor Power Reporting Mechanism" - ---help--- - Provide power reporting mechanism support for AMD processors. - Currently, it leverages X86_FEATURE_ACC_POWER - (CPUID Fn8000_0007_EDX[12]) interface to calculate the - average power consumption on Family 15h processors. - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" ---help--- diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 583d539a4197..52fef606bc54 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -571,312 +571,6 @@ free_handle: efi_call_early(free_pool, pci_handle); } -static void -setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, - struct efi_pixel_bitmask pixel_info, int pixel_format) -{ - if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) { - si->lfb_depth = 32; - si->lfb_linelength = pixels_per_scan_line * 4; - si->red_size = 8; - si->red_pos = 0; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 16; - si->rsvd_size = 8; - si->rsvd_pos = 24; - } else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) { - si->lfb_depth = 32; - si->lfb_linelength = pixels_per_scan_line * 4; - si->red_size = 8; - si->red_pos = 16; - si->green_size = 8; - si->green_pos = 8; - si->blue_size = 8; - si->blue_pos = 0; - si->rsvd_size = 8; - si->rsvd_pos = 24; - } else if (pixel_format == PIXEL_BIT_MASK) { - find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size); - find_bits(pixel_info.green_mask, &si->green_pos, - &si->green_size); - find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size); - find_bits(pixel_info.reserved_mask, &si->rsvd_pos, - &si->rsvd_size); - si->lfb_depth = si->red_size + si->green_size + - si->blue_size + si->rsvd_size; - si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8; - } else { - si->lfb_depth = 4; - si->lfb_linelength = si->lfb_width / 2; - si->red_size = 0; - si->red_pos = 0; - si->green_size = 0; - si->green_pos = 0; - si->blue_size = 0; - si->blue_pos = 0; - si->rsvd_size = 0; - si->rsvd_pos = 0; - } -} - -static efi_status_t -__gop_query32(struct efi_graphics_output_protocol_32 *gop32, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_32 *mode; - efi_status_t status; - unsigned long m; - - m = gop32->mode; - mode = (struct efi_graphics_output_protocol_mode_32 *)m; - - status = efi_early->call(gop32->query_mode, gop32, - mode->mode, size, info); - if (status != EFI_SUCCESS) - return status; - - *fb_base = mode->frame_buffer_base; - return status; -} - -static efi_status_t -setup_gop32(struct screen_info *si, efi_guid_t *proto, - unsigned long size, void **gop_handle) -{ - struct efi_graphics_output_protocol_32 *gop32, *first_gop; - unsigned long nr_gops; - u16 width, height; - u32 pixels_per_scan_line; - u32 ext_lfb_base; - u64 fb_base; - struct efi_pixel_bitmask pixel_info; - int pixel_format; - efi_status_t status; - u32 *handles = (u32 *)(unsigned long)gop_handle; - int i; - - first_gop = NULL; - gop32 = NULL; - - nr_gops = size / sizeof(u32); - for (i = 0; i < nr_gops; i++) { - struct efi_graphics_output_mode_info *info = NULL; - efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; - bool conout_found = false; - void *dummy = NULL; - u32 h = handles[i]; - u64 current_fb_base; - - status = efi_call_early(handle_protocol, h, - proto, (void **)&gop32); - if (status != EFI_SUCCESS) - continue; - - status = efi_call_early(handle_protocol, h, - &conout_proto, &dummy); - if (status == EFI_SUCCESS) - conout_found = true; - - status = __gop_query32(gop32, &info, &size, ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { - /* - * Systems that use the UEFI Console Splitter may - * provide multiple GOP devices, not all of which are - * backed by real hardware. The workaround is to search - * for a GOP implementing the ConOut protocol, and if - * one isn't found, to just fall back to the first GOP. - */ - width = info->horizontal_resolution; - height = info->vertical_resolution; - pixel_format = info->pixel_format; - pixel_info = info->pixel_information; - pixels_per_scan_line = info->pixels_per_scan_line; - fb_base = current_fb_base; - - /* - * Once we've found a GOP supporting ConOut, - * don't bother looking any further. - */ - first_gop = gop32; - if (conout_found) - break; - } - } - - /* Did we find any GOPs? */ - if (!first_gop) - goto out; - - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; - - si->lfb_width = width; - si->lfb_height = height; - si->lfb_base = fb_base; - - ext_lfb_base = (u64)(unsigned long)fb_base >> 32; - if (ext_lfb_base) { - si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; - si->ext_lfb_base = ext_lfb_base; - } - - si->pages = 1; - - setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); - - si->lfb_size = si->lfb_linelength * si->lfb_height; - - si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; -} - -static efi_status_t -__gop_query64(struct efi_graphics_output_protocol_64 *gop64, - struct efi_graphics_output_mode_info **info, - unsigned long *size, u64 *fb_base) -{ - struct efi_graphics_output_protocol_mode_64 *mode; - efi_status_t status; - unsigned long m; - - m = gop64->mode; - mode = (struct efi_graphics_output_protocol_mode_64 *)m; - - status = efi_early->call(gop64->query_mode, gop64, - mode->mode, size, info); - if (status != EFI_SUCCESS) - return status; - - *fb_base = mode->frame_buffer_base; - return status; -} - -static efi_status_t -setup_gop64(struct screen_info *si, efi_guid_t *proto, - unsigned long size, void **gop_handle) -{ - struct efi_graphics_output_protocol_64 *gop64, *first_gop; - unsigned long nr_gops; - u16 width, height; - u32 pixels_per_scan_line; - u32 ext_lfb_base; - u64 fb_base; - struct efi_pixel_bitmask pixel_info; - int pixel_format; - efi_status_t status; - u64 *handles = (u64 *)(unsigned long)gop_handle; - int i; - - first_gop = NULL; - gop64 = NULL; - - nr_gops = size / sizeof(u64); - for (i = 0; i < nr_gops; i++) { - struct efi_graphics_output_mode_info *info = NULL; - efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID; - bool conout_found = false; - void *dummy = NULL; - u64 h = handles[i]; - u64 current_fb_base; - - status = efi_call_early(handle_protocol, h, - proto, (void **)&gop64); - if (status != EFI_SUCCESS) - continue; - - status = efi_call_early(handle_protocol, h, - &conout_proto, &dummy); - if (status == EFI_SUCCESS) - conout_found = true; - - status = __gop_query64(gop64, &info, &size, ¤t_fb_base); - if (status == EFI_SUCCESS && (!first_gop || conout_found)) { - /* - * Systems that use the UEFI Console Splitter may - * provide multiple GOP devices, not all of which are - * backed by real hardware. The workaround is to search - * for a GOP implementing the ConOut protocol, and if - * one isn't found, to just fall back to the first GOP. - */ - width = info->horizontal_resolution; - height = info->vertical_resolution; - pixel_format = info->pixel_format; - pixel_info = info->pixel_information; - pixels_per_scan_line = info->pixels_per_scan_line; - fb_base = current_fb_base; - - /* - * Once we've found a GOP supporting ConOut, - * don't bother looking any further. - */ - first_gop = gop64; - if (conout_found) - break; - } - } - - /* Did we find any GOPs? */ - if (!first_gop) - goto out; - - /* EFI framebuffer */ - si->orig_video_isVGA = VIDEO_TYPE_EFI; - - si->lfb_width = width; - si->lfb_height = height; - si->lfb_base = fb_base; - - ext_lfb_base = (u64)(unsigned long)fb_base >> 32; - if (ext_lfb_base) { - si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; - si->ext_lfb_base = ext_lfb_base; - } - - si->pages = 1; - - setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); - - si->lfb_size = si->lfb_linelength * si->lfb_height; - - si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS; -out: - return status; -} - -/* - * See if we have Graphics Output Protocol - */ -static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto, - unsigned long size) -{ - efi_status_t status; - void **gop_handle = NULL; - - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, - size, (void **)&gop_handle); - if (status != EFI_SUCCESS) - return status; - - status = efi_call_early(locate_handle, - EFI_LOCATE_BY_PROTOCOL, - proto, NULL, &size, gop_handle); - if (status != EFI_SUCCESS) - goto free_handle; - - if (efi_early->is64) - status = setup_gop64(si, proto, size, gop_handle); - else - status = setup_gop32(si, proto, size, gop_handle); - -free_handle: - efi_call_early(free_pool, gop_handle); - return status; -} - static efi_status_t setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height) { @@ -1038,7 +732,7 @@ void setup_graphics(struct boot_params *boot_params) EFI_LOCATE_BY_PROTOCOL, &graphics_proto, NULL, &size, gop_handle); if (status == EFI_BUFFER_TOO_SMALL) - status = setup_gop(si, &graphics_proto, size); + status = efi_setup_gop(NULL, si, &graphics_proto, size); if (status != EFI_SUCCESS) { size = 0; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index d487e727f1ec..c0223f1a89d7 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -11,80 +11,6 @@ #define DESC_TYPE_CODE_DATA (1 << 0) -#define EFI_CONSOLE_OUT_DEVICE_GUID \ - EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ - 0x3f, 0xc1, 0x4d) - -#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0 -#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1 -#define PIXEL_BIT_MASK 2 -#define PIXEL_BLT_ONLY 3 -#define PIXEL_FORMAT_MAX 4 - -struct efi_pixel_bitmask { - u32 red_mask; - u32 green_mask; - u32 blue_mask; - u32 reserved_mask; -}; - -struct efi_graphics_output_mode_info { - u32 version; - u32 horizontal_resolution; - u32 vertical_resolution; - int pixel_format; - struct efi_pixel_bitmask pixel_information; - u32 pixels_per_scan_line; -} __packed; - -struct efi_graphics_output_protocol_mode_32 { - u32 max_mode; - u32 mode; - u32 info; - u32 size_of_info; - u64 frame_buffer_base; - u32 frame_buffer_size; -} __packed; - -struct efi_graphics_output_protocol_mode_64 { - u32 max_mode; - u32 mode; - u64 info; - u64 size_of_info; - u64 frame_buffer_base; - u64 frame_buffer_size; -} __packed; - -struct efi_graphics_output_protocol_mode { - u32 max_mode; - u32 mode; - unsigned long info; - unsigned long size_of_info; - u64 frame_buffer_base; - unsigned long frame_buffer_size; -} __packed; - -struct efi_graphics_output_protocol_32 { - u32 query_mode; - u32 set_mode; - u32 blt; - u32 mode; -}; - -struct efi_graphics_output_protocol_64 { - u64 query_mode; - u64 set_mode; - u64 blt; - u64 mode; -}; - -struct efi_graphics_output_protocol { - void *query_mode; - unsigned long set_mode; - unsigned long blt; - struct efi_graphics_output_protocol_mode *mode; -}; - struct efi_uga_draw_protocol_32 { u32 get_mode; u32 set_mode; diff --git a/arch/x86/configs/kvm_guest.config b/arch/x86/configs/kvm_guest.config index f9affcc3b9f1..9906505c998a 100644 --- a/arch/x86/configs/kvm_guest.config +++ b/arch/x86/configs/kvm_guest.config @@ -26,3 +26,6 @@ CONFIG_VIRTIO_NET=y CONFIG_9P_FS=y CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y +CONFIG_SCSI_LOWLEVEL=y +CONFIG_SCSI_VIRTIO=y +CONFIG_VIRTIO_INPUT=y diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index b30dd8154cc2..4cddd17153fb 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -384,5 +384,5 @@ 375 i386 membarrier sys_membarrier 376 i386 mlock2 sys_mlock2 377 i386 copy_file_range sys_copy_file_range -378 i386 preadv2 sys_preadv2 -379 i386 pwritev2 sys_pwritev2 +378 i386 preadv2 sys_preadv2 compat_sys_preadv2 +379 i386 pwritev2 sys_pwritev2 compat_sys_pwritev2 diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig new file mode 100644 index 000000000000..98397db5ceae --- /dev/null +++ b/arch/x86/events/Kconfig @@ -0,0 +1,36 @@ +menu "Performance monitoring" + +config PERF_EVENTS_INTEL_UNCORE + tristate "Intel uncore performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel uncore performance events. These are + available on NehalemEX and more modern processors. + +config PERF_EVENTS_INTEL_RAPL + tristate "Intel rapl performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel rapl performance events for power + monitoring on modern processors. + +config PERF_EVENTS_INTEL_CSTATE + tristate "Intel cstate performance events" + depends on PERF_EVENTS && CPU_SUP_INTEL && PCI + default y + ---help--- + Include support for Intel cstate performance events for power + monitoring on modern processors. + +config PERF_EVENTS_AMD_POWER + depends on PERF_EVENTS && CPU_SUP_AMD + tristate "AMD Processor Power Reporting Mechanism" + ---help--- + Provide power reporting mechanism support for AMD processors. + Currently, it leverages X86_FEATURE_ACC_POWER + (CPUID Fn8000_0007_EDX[12]) interface to calculate the + average power consumption on Family 15h processors. + +endmenu diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index f59618a39990..1d392c39fe56 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -6,9 +6,6 @@ obj-$(CONFIG_X86_LOCAL_APIC) += amd/ibs.o msr.o ifdef CONFIG_AMD_IOMMU obj-$(CONFIG_CPU_SUP_AMD) += amd/iommu.o endif -obj-$(CONFIG_CPU_SUP_INTEL) += intel/core.o intel/bts.o intel/cqm.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/cstate.o intel/ds.o intel/knc.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/lbr.o intel/p4.o intel/p6.o intel/pt.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel/rapl.o msr.o -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore.o intel/uncore_nhmex.o -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel/uncore_snb.o intel/uncore_snbep.o + +obj-$(CONFIG_CPU_SUP_INTEL) += msr.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 3db9569e658c..98ac57381bf9 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -263,6 +263,7 @@ static const struct attribute_group *amd_uncore_attr_groups[] = { }; static struct pmu amd_nb_pmu = { + .task_ctx_nr = perf_invalid_context, .attr_groups = amd_uncore_attr_groups, .name = "amd_nb", .event_init = amd_uncore_event_init, @@ -274,6 +275,7 @@ static struct pmu amd_nb_pmu = { }; static struct pmu amd_l2_pmu = { + .task_ctx_nr = perf_invalid_context, .attr_groups = amd_uncore_attr_groups, .name = "amd_l2", .event_init = amd_uncore_event_init, diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index dd39fde66b54..b7080bef9137 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -360,6 +360,9 @@ int x86_add_exclusive(unsigned int what) { int i; + if (x86_pmu.lbr_pt_coexist) + return 0; + if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { mutex_lock(&pmc_reserve_mutex); for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { @@ -380,6 +383,9 @@ fail_unlock: void x86_del_exclusive(unsigned int what) { + if (x86_pmu.lbr_pt_coexist) + return; + atomic_dec(&x86_pmu.lbr_exclusive[what]); atomic_dec(&active_events); } @@ -2277,7 +2283,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); - while (entry->nr < PERF_MAX_STACK_DEPTH) { + while (entry->nr < sysctl_perf_event_max_stack) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; @@ -2337,7 +2343,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) return; pagefault_disable(); - while (entry->nr < PERF_MAX_STACK_DEPTH) { + while (entry->nr < sysctl_perf_event_max_stack) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile new file mode 100644 index 000000000000..3660b2cf245a --- /dev/null +++ b/arch/x86/events/intel/Makefile @@ -0,0 +1,9 @@ +obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o +obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o +intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o +intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o +obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o +intel-cstate-objs := cstate.o diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index b99dc9258c0f..0a6e393a2e62 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -171,18 +171,6 @@ static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head) memset(page_address(phys->page) + index, 0, phys->size - index); } -static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts) -{ - if (buf->snapshot) - return false; - - if (local_read(&buf->data_size) >= bts->handle.size || - bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE) - return true; - - return false; -} - static void bts_update(struct bts_ctx *bts) { int cpu = raw_smp_processor_id(); @@ -213,18 +201,15 @@ static void bts_update(struct bts_ctx *bts) } } +static int +bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle); + static void __bts_event_start(struct perf_event *event) { struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct bts_buffer *buf = perf_get_aux(&bts->handle); u64 config = 0; - if (!buf || bts_buffer_is_full(buf, bts)) - return; - - event->hw.itrace_started = 1; - event->hw.state = 0; - if (!buf->snapshot) config |= ARCH_PERFMON_EVENTSEL_INT; if (!event->attr.exclude_kernel) @@ -241,16 +226,41 @@ static void __bts_event_start(struct perf_event *event) wmb(); intel_pmu_enable_bts(config); + } static void bts_event_start(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf; + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + goto fail_stop; + + if (bts_buffer_reset(buf, &bts->handle)) + goto fail_end_stop; + + bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; + bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; + bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; + + event->hw.itrace_started = 1; + event->hw.state = 0; __bts_event_start(event); /* PMI handler: this counter is running and likely generating PMIs */ ACCESS_ONCE(bts->started) = 1; + + return; + +fail_end_stop: + perf_aux_output_end(&bts->handle, 0, false); + +fail_stop: + event->hw.state = PERF_HES_STOPPED; } static void __bts_event_stop(struct perf_event *event) @@ -269,15 +279,32 @@ static void __bts_event_stop(struct perf_event *event) static void bts_event_stop(struct perf_event *event, int flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); /* PMI handler: don't restart this counter */ ACCESS_ONCE(bts->started) = 0; __bts_event_stop(event); - if (flags & PERF_EF_UPDATE) + if (flags & PERF_EF_UPDATE) { bts_update(bts); + + if (buf) { + if (buf->snapshot) + bts->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + } + + cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; + cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; + } } void intel_bts_enable_local(void) @@ -417,34 +444,14 @@ int intel_bts_interrupt(void) static void bts_event_del(struct perf_event *event, int mode) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); - struct bts_buffer *buf = perf_get_aux(&bts->handle); - bts_event_stop(event, PERF_EF_UPDATE); - - if (buf) { - if (buf->snapshot) - bts->handle.head = - local_xchg(&buf->data_size, - buf->nr_pages << PAGE_SHIFT); - perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), - !!local_xchg(&buf->lost, 0)); - } - - cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; - cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; - cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; - cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; } static int bts_event_add(struct perf_event *event, int mode) { - struct bts_buffer *buf; struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - int ret = -EBUSY; event->hw.state = PERF_HES_STOPPED; @@ -454,26 +461,10 @@ static int bts_event_add(struct perf_event *event, int mode) if (bts->handle.event) return -EBUSY; - buf = perf_aux_output_begin(&bts->handle, event); - if (!buf) - return -EINVAL; - - ret = bts_buffer_reset(buf, &bts->handle); - if (ret) { - perf_aux_output_end(&bts->handle, 0, false); - return ret; - } - - bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; - bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; - bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; - if (mode & PERF_EF_START) { bts_event_start(event, 0); - if (hwc->state & PERF_HES_STOPPED) { - bts_event_del(event, 0); - return -EBUSY; - } + if (hwc->state & PERF_HES_STOPPED) + return -EINVAL; } return 0; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a6fd4dbcf820..7c666958a625 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -1465,6 +1465,140 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +static struct extra_reg intel_glm_extra_regs[] __read_mostly = { + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x760005ffbfull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x360005ffbfull, RSP_1), + EVENT_EXTRA_END +}; + +#define GLM_DEMAND_DATA_RD BIT_ULL(0) +#define GLM_DEMAND_RFO BIT_ULL(1) +#define GLM_ANY_RESPONSE BIT_ULL(16) +#define GLM_SNP_NONE_OR_MISS BIT_ULL(33) +#define GLM_DEMAND_READ GLM_DEMAND_DATA_RD +#define GLM_DEMAND_WRITE GLM_DEMAND_RFO +#define GLM_DEMAND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO) +#define GLM_LLC_ACCESS GLM_ANY_RESPONSE +#define GLM_SNP_ANY (GLM_SNP_NONE_OR_MISS|SNB_NO_FWD|SNB_HITM) +#define GLM_LLC_MISS (GLM_SNP_ANY|SNB_NON_DRAM) + +static __initconst const u64 glm_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)] = 0x0, + }, + [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)] = 0x0380, /* ICACHE.ACCESSES */ + [C(RESULT_MISS)] = 0x0280, /* 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)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = 0x1b7, /* OFFCORE_RESPONSE */ + [C(RESULT_MISS)] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [C(RESULT_MISS)] = 0x0, + }, + [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(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0x00c0, /* INST_RETIRED.ANY_P */ + [C(RESULT_MISS)] = 0x0481, /* ITLB.MISS */ + }, + [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)] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [C(RESULT_MISS)] = 0x00c5, /* 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 glm_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_READ| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_READ| + GLM_LLC_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_WRITE| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_WRITE| + GLM_LLC_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = GLM_DEMAND_PREFETCH| + GLM_LLC_ACCESS, + [C(RESULT_MISS)] = GLM_DEMAND_PREFETCH| + GLM_LLC_MISS, + }, + }, +}; + #define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ #define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ #define KNL_MCDRAM_LOCAL BIT_ULL(21) @@ -3447,7 +3581,7 @@ __init int intel_pmu_init(void) memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); - intel_pmu_lbr_init_atom(); + intel_pmu_lbr_init_slm(); x86_pmu.event_constraints = intel_slm_event_constraints; x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; @@ -3456,6 +3590,30 @@ __init int intel_pmu_init(void) pr_cont("Silvermont events, "); break; + case 92: /* 14nm Atom "Goldmont" */ + case 95: /* 14nm Atom "Goldmont Denverton" */ + memcpy(hw_cache_event_ids, glm_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_glm_pebs_event_constraints; + x86_pmu.extra_regs = intel_glm_extra_regs; + /* + * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS + * for precise cycles. + * :pp is identical to :ppp + */ + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + pr_cont("Goldmont events, "); + break; + case 37: /* 32nm Westmere */ case 44: /* 32nm Westmere-EP */ case 47: /* 32nm Westmere-EX */ @@ -3708,7 +3866,7 @@ __init int intel_pmu_init(void) c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } c->idxmsk64 &= - ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); c->weight = hweight64(c->idxmsk64); } } diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 7946c4231169..9ba4e4136a15 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -91,6 +91,8 @@ #include <asm/cpu_device_id.h> #include "../perf_event.h" +MODULE_LICENSE("GPL"); + #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ struct kobj_attribute *attr, \ @@ -106,22 +108,27 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf); +/* Model -> events mapping */ +struct cstate_model { + unsigned long core_events; + unsigned long pkg_events; + unsigned long quirks; +}; + +/* Quirk flags */ +#define SLM_PKG_C6_USE_C7_MSR (1UL << 0) + struct perf_cstate_msr { u64 msr; struct perf_pmu_events_attr *attr; - bool (*test)(int idx); }; /* cstate_core PMU */ - static struct pmu cstate_core_pmu; static bool has_cstate_core; -enum perf_cstate_core_id { - /* - * cstate_core events - */ +enum perf_cstate_core_events { PERF_CSTATE_CORE_C1_RES = 0, PERF_CSTATE_CORE_C3_RES, PERF_CSTATE_CORE_C6_RES, @@ -130,69 +137,16 @@ enum perf_cstate_core_id { PERF_CSTATE_CORE_EVENT_MAX, }; -bool test_core(int idx) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || - boot_cpu_data.x86 != 6) - return false; - - switch (boot_cpu_data.x86_model) { - case 30: /* 45nm Nehalem */ - case 26: /* 45nm Nehalem-EP */ - case 46: /* 45nm Nehalem-EX */ - - case 37: /* 32nm Westmere */ - case 44: /* 32nm Westmere-EP */ - case 47: /* 32nm Westmere-EX */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - case 42: /* 32nm SandyBridge */ - case 45: /* 32nm SandyBridge-E/EN/EP */ - - case 58: /* 22nm IvyBridge */ - case 62: /* 22nm IvyBridge-EP/EX */ - - case 60: /* 22nm Haswell Core */ - case 63: /* 22nm Haswell Server */ - case 69: /* 22nm Haswell ULT */ - case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ - - case 61: /* 14nm Broadwell Core-M */ - case 86: /* 14nm Broadwell Xeon D */ - case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ - case 79: /* 14nm Broadwell Server */ - - case 78: /* 14nm Skylake Mobile */ - case 94: /* 14nm Skylake Desktop */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES || - idx == PERF_CSTATE_CORE_C7_RES) - return true; - break; - case 55: /* 22nm Atom "Silvermont" */ - case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ - case 76: /* 14nm Atom "Airmont" */ - if (idx == PERF_CSTATE_CORE_C1_RES || - idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - } - - return false; -} - PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00"); PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01"); PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02"); PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03"); static struct perf_cstate_msr core_msr[] = { - [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1, test_core, }, - [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3, test_core, }, - [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6, test_core, }, - [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7, test_core, }, + [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1 }, + [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3 }, + [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6 }, + [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7 }, }; static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = { @@ -234,18 +188,11 @@ static const struct attribute_group *core_attr_groups[] = { NULL, }; -/* cstate_core PMU end */ - - /* cstate_pkg PMU */ - static struct pmu cstate_pkg_pmu; static bool has_cstate_pkg; -enum perf_cstate_pkg_id { - /* - * cstate_pkg events - */ +enum perf_cstate_pkg_events { PERF_CSTATE_PKG_C2_RES = 0, PERF_CSTATE_PKG_C3_RES, PERF_CSTATE_PKG_C6_RES, @@ -257,69 +204,6 @@ enum perf_cstate_pkg_id { PERF_CSTATE_PKG_EVENT_MAX, }; -bool test_pkg(int idx) -{ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || - boot_cpu_data.x86 != 6) - return false; - - switch (boot_cpu_data.x86_model) { - case 30: /* 45nm Nehalem */ - case 26: /* 45nm Nehalem-EP */ - case 46: /* 45nm Nehalem-EX */ - - case 37: /* 32nm Westmere */ - case 44: /* 32nm Westmere-EP */ - case 47: /* 32nm Westmere-EX */ - if (idx == PERF_CSTATE_CORE_C3_RES || - idx == PERF_CSTATE_CORE_C6_RES || - idx == PERF_CSTATE_CORE_C7_RES) - return true; - break; - case 42: /* 32nm SandyBridge */ - case 45: /* 32nm SandyBridge-E/EN/EP */ - - case 58: /* 22nm IvyBridge */ - case 62: /* 22nm IvyBridge-EP/EX */ - - case 60: /* 22nm Haswell Core */ - case 63: /* 22nm Haswell Server */ - case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ - - case 61: /* 14nm Broadwell Core-M */ - case 86: /* 14nm Broadwell Xeon D */ - case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ - case 79: /* 14nm Broadwell Server */ - - case 78: /* 14nm Skylake Mobile */ - case 94: /* 14nm Skylake Desktop */ - if (idx == PERF_CSTATE_PKG_C2_RES || - idx == PERF_CSTATE_PKG_C3_RES || - idx == PERF_CSTATE_PKG_C6_RES || - idx == PERF_CSTATE_PKG_C7_RES) - return true; - break; - case 55: /* 22nm Atom "Silvermont" */ - case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ - case 76: /* 14nm Atom "Airmont" */ - if (idx == PERF_CSTATE_CORE_C6_RES) - return true; - break; - case 69: /* 22nm Haswell ULT */ - if (idx == PERF_CSTATE_PKG_C2_RES || - idx == PERF_CSTATE_PKG_C3_RES || - idx == PERF_CSTATE_PKG_C6_RES || - idx == PERF_CSTATE_PKG_C7_RES || - idx == PERF_CSTATE_PKG_C8_RES || - idx == PERF_CSTATE_PKG_C9_RES || - idx == PERF_CSTATE_PKG_C10_RES) - return true; - break; - } - - return false; -} - PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00"); PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01"); PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02"); @@ -329,13 +213,13 @@ PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05"); PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06"); static struct perf_cstate_msr pkg_msr[] = { - [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2, test_pkg, }, - [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3, test_pkg, }, - [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6, test_pkg, }, - [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7, test_pkg, }, - [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8, test_pkg, }, - [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9, test_pkg, }, - [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10, test_pkg, }, + [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2 }, + [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3 }, + [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6 }, + [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7 }, + [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8 }, + [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9 }, + [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10 }, }; static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = { @@ -366,8 +250,6 @@ static const struct attribute_group *pkg_attr_groups[] = { NULL, }; -/* cstate_pkg PMU end*/ - static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) @@ -385,7 +267,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, static int cstate_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config; - int ret = 0; + int cpu; if (event->attr.type != event->pmu->type) return -ENOENT; @@ -400,26 +282,36 @@ static int cstate_pmu_event_init(struct perf_event *event) event->attr.sample_period) /* no sampling */ return -EINVAL; + if (event->cpu < 0) + return -EINVAL; + if (event->pmu == &cstate_core_pmu) { if (cfg >= PERF_CSTATE_CORE_EVENT_MAX) return -EINVAL; if (!core_msr[cfg].attr) return -EINVAL; event->hw.event_base = core_msr[cfg].msr; + cpu = cpumask_any_and(&cstate_core_cpu_mask, + topology_sibling_cpumask(event->cpu)); } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; if (!pkg_msr[cfg].attr) return -EINVAL; event->hw.event_base = pkg_msr[cfg].msr; - } else + cpu = cpumask_any_and(&cstate_pkg_cpu_mask, + topology_core_cpumask(event->cpu)); + } else { return -ENOENT; + } + + if (cpu >= nr_cpu_ids) + return -ENODEV; - /* must be done before validate_group */ + event->cpu = cpu; event->hw.config = cfg; event->hw.idx = -1; - - return ret; + return 0; } static inline u64 cstate_pmu_read_counter(struct perf_event *event) @@ -469,172 +361,91 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode) return 0; } +/* + * Check if exiting cpu is the designated reader. If so migrate the + * events when there is a valid target available + */ static void cstate_cpu_exit(int cpu) { - int i, id, target; + unsigned int target; - /* cpu exit for cstate core */ - if (has_cstate_core) { - id = topology_core_id(cpu); - target = -1; - - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (id == topology_core_id(i)) { - target = i; - break; - } - } - if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0) + if (has_cstate_core && + cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) { + + target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &cstate_core_cpu_mask); - WARN_ON(cpumask_empty(&cstate_core_cpu_mask)); - if (target >= 0) perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); + } } - /* cpu exit for cstate pkg */ - if (has_cstate_pkg) { - id = topology_physical_package_id(cpu); - target = -1; - - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (id == topology_physical_package_id(i)) { - target = i; - break; - } - } - if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0) + if (has_cstate_pkg && + cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) { + + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { cpumask_set_cpu(target, &cstate_pkg_cpu_mask); - WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask)); - if (target >= 0) perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); + } } } static void cstate_cpu_init(int cpu) { - int i, id; + unsigned int target; - /* cpu init for cstate core */ - if (has_cstate_core) { - id = topology_core_id(cpu); - for_each_cpu(i, &cstate_core_cpu_mask) { - if (id == topology_core_id(i)) - break; - } - if (i >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_core_cpu_mask); - } + /* + * If this is the first online thread of that core, set it in + * the core cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_core_cpu_mask, + topology_sibling_cpumask(cpu)); - /* cpu init for cstate pkg */ - if (has_cstate_pkg) { - id = topology_physical_package_id(cpu); - for_each_cpu(i, &cstate_pkg_cpu_mask) { - if (id == topology_physical_package_id(i)) - break; - } - if (i >= nr_cpu_ids) - cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); - } + if (has_cstate_core && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_core_cpu_mask); + + /* + * If this is the first online thread of that package, set it + * in the package cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_pkg_cpu_mask, + topology_core_cpumask(cpu)); + if (has_cstate_pkg && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); } static int cstate_cpu_notifier(struct notifier_block *self, - unsigned long action, void *hcpu) + unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - break; case CPU_STARTING: cstate_cpu_init(cpu); break; - case CPU_UP_CANCELED: - case CPU_DYING: - break; - case CPU_ONLINE: - case CPU_DEAD: - break; case CPU_DOWN_PREPARE: cstate_cpu_exit(cpu); break; default: break; } - return NOTIFY_OK; } -/* - * Probe the cstate events and insert the available one into sysfs attrs - * Return false if there is no available events. - */ -static bool cstate_probe_msr(struct perf_cstate_msr *msr, - struct attribute **events_attrs, - int max_event_nr) -{ - int i, j = 0; - u64 val; - - /* Probe the cstate events. */ - for (i = 0; i < max_event_nr; i++) { - if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) - msr[i].attr = NULL; - } - - /* List remaining events in the sysfs attrs. */ - for (i = 0; i < max_event_nr; i++) { - if (msr[i].attr) - events_attrs[j++] = &msr[i].attr->attr.attr; - } - events_attrs[j] = NULL; - - return (j > 0) ? true : false; -} - -static int __init cstate_init(void) -{ - /* SLM has different MSR for PKG C6 */ - switch (boot_cpu_data.x86_model) { - case 55: - case 76: - case 77: - pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; - } - - if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX)) - has_cstate_core = true; - - if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX)) - has_cstate_pkg = true; - - return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; -} - -static void __init cstate_cpumask_init(void) -{ - int cpu; - - cpu_notifier_register_begin(); - - for_each_online_cpu(cpu) - cstate_cpu_init(cpu); - - __perf_cpu_notifier(cstate_cpu_notifier); - - cpu_notifier_register_done(); -} +static struct notifier_block cstate_cpu_nb = { + .notifier_call = cstate_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; static struct pmu cstate_core_pmu = { .attr_groups = core_attr_groups, .name = "cstate_core", .task_ctx_nr = perf_invalid_context, .event_init = cstate_pmu_event_init, - .add = cstate_pmu_event_add, /* must have */ - .del = cstate_pmu_event_del, /* must have */ + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, .start = cstate_pmu_event_start, .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, @@ -646,49 +457,203 @@ static struct pmu cstate_pkg_pmu = { .name = "cstate_pkg", .task_ctx_nr = perf_invalid_context, .event_init = cstate_pmu_event_init, - .add = cstate_pmu_event_add, /* must have */ - .del = cstate_pmu_event_del, /* must have */ + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, .start = cstate_pmu_event_start, .stop = cstate_pmu_event_stop, .read = cstate_pmu_event_update, .capabilities = PERF_PMU_CAP_NO_INTERRUPT, }; -static void __init cstate_pmus_register(void) +static const struct cstate_model nhm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES), +}; + +static const struct cstate_model snb_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES), +}; + +static const struct cstate_model hswult_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | + BIT(PERF_CSTATE_CORE_C6_RES) | + BIT(PERF_CSTATE_CORE_C7_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES) | + BIT(PERF_CSTATE_PKG_C7_RES) | + BIT(PERF_CSTATE_PKG_C8_RES) | + BIT(PERF_CSTATE_PKG_C9_RES) | + BIT(PERF_CSTATE_PKG_C10_RES), +}; + +static const struct cstate_model slm_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C6_RES), + .quirks = SLM_PKG_C6_USE_C7_MSR, +}; + +#define X86_CSTATES_MODEL(model, states) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } + +static const struct x86_cpu_id intel_cstates_match[] __initconst = { + X86_CSTATES_MODEL(30, nhm_cstates), /* 45nm Nehalem */ + X86_CSTATES_MODEL(26, nhm_cstates), /* 45nm Nehalem-EP */ + X86_CSTATES_MODEL(46, nhm_cstates), /* 45nm Nehalem-EX */ + + X86_CSTATES_MODEL(37, nhm_cstates), /* 32nm Westmere */ + X86_CSTATES_MODEL(44, nhm_cstates), /* 32nm Westmere-EP */ + X86_CSTATES_MODEL(47, nhm_cstates), /* 32nm Westmere-EX */ + + X86_CSTATES_MODEL(42, snb_cstates), /* 32nm SandyBridge */ + X86_CSTATES_MODEL(45, snb_cstates), /* 32nm SandyBridge-E/EN/EP */ + + X86_CSTATES_MODEL(58, snb_cstates), /* 22nm IvyBridge */ + X86_CSTATES_MODEL(62, snb_cstates), /* 22nm IvyBridge-EP/EX */ + + X86_CSTATES_MODEL(60, snb_cstates), /* 22nm Haswell Core */ + X86_CSTATES_MODEL(63, snb_cstates), /* 22nm Haswell Server */ + X86_CSTATES_MODEL(70, snb_cstates), /* 22nm Haswell + GT3e */ + + X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT */ + + X86_CSTATES_MODEL(55, slm_cstates), /* 22nm Atom Silvermont */ + X86_CSTATES_MODEL(77, slm_cstates), /* 22nm Atom Avoton/Rangely */ + X86_CSTATES_MODEL(76, slm_cstates), /* 22nm Atom Airmont */ + + X86_CSTATES_MODEL(61, snb_cstates), /* 14nm Broadwell Core-M */ + X86_CSTATES_MODEL(86, snb_cstates), /* 14nm Broadwell Xeon D */ + X86_CSTATES_MODEL(71, snb_cstates), /* 14nm Broadwell + GT3e */ + X86_CSTATES_MODEL(79, snb_cstates), /* 14nm Broadwell Server */ + + X86_CSTATES_MODEL(78, snb_cstates), /* 14nm Skylake Mobile */ + X86_CSTATES_MODEL(94, snb_cstates), /* 14nm Skylake Desktop */ + { }, +}; +MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); + +/* + * Probe the cstate events and insert the available one into sysfs attrs + * Return false if there are no available events. + */ +static bool __init cstate_probe_msr(const unsigned long evmsk, int max, + struct perf_cstate_msr *msr, + struct attribute **attrs) { - int err; + bool found = false; + unsigned int bit; + u64 val; + + for (bit = 0; bit < max; bit++) { + if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) { + *attrs++ = &msr[bit].attr->attr.attr; + found = true; + } else { + msr[bit].attr = NULL; + } + } + *attrs = NULL; + + return found; +} + +static int __init cstate_probe(const struct cstate_model *cm) +{ + /* SLM has different MSR for PKG C6 */ + if (cm->quirks & SLM_PKG_C6_USE_C7_MSR) + pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + + has_cstate_core = cstate_probe_msr(cm->core_events, + PERF_CSTATE_CORE_EVENT_MAX, + core_msr, core_events_attrs); + + has_cstate_pkg = cstate_probe_msr(cm->pkg_events, + PERF_CSTATE_PKG_EVENT_MAX, + pkg_msr, pkg_events_attrs); + + return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; +} + +static inline void cstate_cleanup(void) +{ + if (has_cstate_core) + perf_pmu_unregister(&cstate_core_pmu); + + if (has_cstate_pkg) + perf_pmu_unregister(&cstate_pkg_pmu); +} + +static int __init cstate_init(void) +{ + int cpu, err; + + cpu_notifier_register_begin(); + for_each_online_cpu(cpu) + cstate_cpu_init(cpu); if (has_cstate_core) { err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); - if (WARN_ON(err)) - pr_info("Failed to register PMU %s error %d\n", - cstate_core_pmu.name, err); + if (err) { + has_cstate_core = false; + pr_info("Failed to register cstate core pmu\n"); + goto out; + } } if (has_cstate_pkg) { err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1); - if (WARN_ON(err)) - pr_info("Failed to register PMU %s error %d\n", - cstate_pkg_pmu.name, err); + if (err) { + has_cstate_pkg = false; + pr_info("Failed to register cstate pkg pmu\n"); + cstate_cleanup(); + goto out; + } } + __register_cpu_notifier(&cstate_cpu_nb); +out: + cpu_notifier_register_done(); + return err; } static int __init cstate_pmu_init(void) { + const struct x86_cpu_id *id; int err; - if (cpu_has_hypervisor) + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + + id = x86_match_cpu(intel_cstates_match); + if (!id) return -ENODEV; - err = cstate_init(); + err = cstate_probe((const struct cstate_model *) id->driver_data); if (err) return err; - cstate_cpumask_init(); - - cstate_pmus_register(); - - return 0; + return cstate_init(); } +module_init(cstate_pmu_init); -device_initcall(cstate_pmu_init); +static void __exit cstate_pmu_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&cstate_cpu_nb); + cstate_cleanup(); + cpu_notifier_register_done(); +} +module_exit(cstate_pmu_exit); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8584b90d8e0b..7ce9f3f669e6 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -645,6 +645,12 @@ struct event_constraint intel_slm_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_glm_pebs_event_constraints[] = { + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 1ca5d1e7d4f2..9e2b40cdb05f 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -14,7 +14,8 @@ enum { LBR_FORMAT_EIP_FLAGS = 0x03, LBR_FORMAT_EIP_FLAGS2 = 0x04, LBR_FORMAT_INFO = 0x05, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO, + LBR_FORMAT_TIME = 0x06, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, }; static enum { @@ -464,6 +465,16 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) abort = !!(info & LBR_INFO_ABORT); cycles = (info & LBR_INFO_CYCLES); } + + if (lbr_format == LBR_FORMAT_TIME) { + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; + skip = 1; + cycles = ((to >> 48) & LBR_INFO_CYCLES); + + to = (u64)((((s64)to) << 16) >> 16); + } + if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; @@ -1049,6 +1060,24 @@ void __init intel_pmu_lbr_init_atom(void) pr_cont("8-deep LBR, "); } +/* slm */ +void __init intel_pmu_lbr_init_slm(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_CORE_FROM; + x86_pmu.lbr_to = MSR_LBR_CORE_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = nhm_lbr_sel_map; + + /* + * SW branch filter usage: + * - compensate for lack of HW filter + */ + pr_cont("8-deep LBR, "); +} + /* Knights Landing */ void intel_pmu_lbr_init_knl(void) { diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 09a77dbc73c9..04bb5fb5a8d7 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -67,11 +67,13 @@ static struct pt_cap_desc { PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)), + PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)), PT_CAP(mtc, 0, CR_EBX, BIT(3)), PT_CAP(topa_output, 0, CR_ECX, BIT(0)), PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), PT_CAP(single_range_output, 0, CR_ECX, BIT(2)), PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), + PT_CAP(num_address_ranges, 1, CR_EAX, 0x3), PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000), PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff), PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000), @@ -125,9 +127,46 @@ static struct attribute_group pt_format_group = { .attrs = pt_formats_attr, }; +static ssize_t +pt_timing_attr_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + switch (pmu_attr->id) { + case 0: + return sprintf(page, "%lu\n", pt_pmu.max_nonturbo_ratio); + case 1: + return sprintf(page, "%u:%u\n", + pt_pmu.tsc_art_num, + pt_pmu.tsc_art_den); + default: + break; + } + + return -EINVAL; +} + +PMU_EVENT_ATTR(max_nonturbo_ratio, timing_attr_max_nonturbo_ratio, 0, + pt_timing_attr_show); +PMU_EVENT_ATTR(tsc_art_ratio, timing_attr_tsc_art_ratio, 1, + pt_timing_attr_show); + +static struct attribute *pt_timing_attr[] = { + &timing_attr_max_nonturbo_ratio.attr.attr, + &timing_attr_tsc_art_ratio.attr.attr, + NULL, +}; + +static struct attribute_group pt_timing_group = { + .attrs = pt_timing_attr, +}; + static const struct attribute_group *pt_attr_groups[] = { &pt_cap_group, &pt_format_group, + &pt_timing_group, NULL, }; @@ -140,6 +179,23 @@ static int __init pt_pmu_hw_init(void) int ret; long i; + rdmsrl(MSR_PLATFORM_INFO, reg); + pt_pmu.max_nonturbo_ratio = (reg & 0xff00) >> 8; + + /* + * if available, read in TSC to core crystal clock ratio, + * otherwise, zero for numerator stands for "not enumerated" + * as per SDM + */ + if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) { + u32 eax, ebx, ecx, edx; + + cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx); + + pt_pmu.tsc_art_num = ebx; + pt_pmu.tsc_art_den = eax; + } + if (boot_cpu_has(X86_FEATURE_VMX)) { /* * Intel SDM, 36.5 "Tracing post-VMXON" says that @@ -263,6 +319,75 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ +/* Address ranges and their corresponding msr configuration registers */ +static const struct pt_address_range { + unsigned long msr_a; + unsigned long msr_b; + unsigned int reg_off; +} pt_address_ranges[] = { + { + .msr_a = MSR_IA32_RTIT_ADDR0_A, + .msr_b = MSR_IA32_RTIT_ADDR0_B, + .reg_off = RTIT_CTL_ADDR0_OFFSET, + }, + { + .msr_a = MSR_IA32_RTIT_ADDR1_A, + .msr_b = MSR_IA32_RTIT_ADDR1_B, + .reg_off = RTIT_CTL_ADDR1_OFFSET, + }, + { + .msr_a = MSR_IA32_RTIT_ADDR2_A, + .msr_b = MSR_IA32_RTIT_ADDR2_B, + .reg_off = RTIT_CTL_ADDR2_OFFSET, + }, + { + .msr_a = MSR_IA32_RTIT_ADDR3_A, + .msr_b = MSR_IA32_RTIT_ADDR3_B, + .reg_off = RTIT_CTL_ADDR3_OFFSET, + } +}; + +static u64 pt_config_filters(struct perf_event *event) +{ + struct pt_filters *filters = event->hw.addr_filters; + struct pt *pt = this_cpu_ptr(&pt_ctx); + unsigned int range = 0; + u64 rtit_ctl = 0; + + if (!filters) + return 0; + + perf_event_addr_filters_sync(event); + + for (range = 0; range < filters->nr_filters; range++) { + struct pt_filter *filter = &filters->filter[range]; + + /* + * Note, if the range has zero start/end addresses due + * to its dynamic object not being loaded yet, we just + * go ahead and program zeroed range, which will simply + * produce no data. Note^2: if executable code at 0x0 + * is a concern, we can set up an "invalid" configuration + * such as msr_b < msr_a. + */ + + /* avoid redundant msr writes */ + if (pt->filters.filter[range].msr_a != filter->msr_a) { + wrmsrl(pt_address_ranges[range].msr_a, filter->msr_a); + pt->filters.filter[range].msr_a = filter->msr_a; + } + + if (pt->filters.filter[range].msr_b != filter->msr_b) { + wrmsrl(pt_address_ranges[range].msr_b, filter->msr_b); + pt->filters.filter[range].msr_b = filter->msr_b; + } + + rtit_ctl |= filter->config << pt_address_ranges[range].reg_off; + } + + return rtit_ctl; +} + static void pt_config(struct perf_event *event) { u64 reg; @@ -272,7 +397,8 @@ static void pt_config(struct perf_event *event) wrmsrl(MSR_IA32_RTIT_STATUS, 0); } - reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; + reg = pt_config_filters(event); + reg |= RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; if (!event->attr.exclude_kernel) reg |= RTIT_CTL_OS; @@ -709,6 +835,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, /* clear STOP and INT from current entry */ buf->topa_index[buf->stop_pos]->stop = 0; + buf->topa_index[buf->stop_pos]->intr = 0; buf->topa_index[buf->intr_pos]->intr = 0; /* how many pages till the STOP marker */ @@ -733,6 +860,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, buf->intr_pos = idx; buf->topa_index[buf->stop_pos]->stop = 1; + buf->topa_index[buf->stop_pos]->intr = 1; buf->topa_index[buf->intr_pos]->intr = 1; return 0; @@ -919,24 +1047,80 @@ static void pt_buffer_free_aux(void *data) kfree(buf); } -/** - * pt_buffer_is_full() - check if the buffer is full - * @buf: PT buffer. - * @pt: Per-cpu pt handle. - * - * If the user hasn't read data from the output region that aux_head - * points to, the buffer is considered full: the user needs to read at - * least this region and update aux_tail to point past it. - */ -static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt) +static int pt_addr_filters_init(struct perf_event *event) { - if (buf->snapshot) - return false; + struct pt_filters *filters; + int node = event->cpu == -1 ? -1 : cpu_to_node(event->cpu); + + if (!pt_cap_get(PT_CAP_num_address_ranges)) + return 0; + + filters = kzalloc_node(sizeof(struct pt_filters), GFP_KERNEL, node); + if (!filters) + return -ENOMEM; + + if (event->parent) + memcpy(filters, event->parent->hw.addr_filters, + sizeof(*filters)); + + event->hw.addr_filters = filters; + + return 0; +} + +static void pt_addr_filters_fini(struct perf_event *event) +{ + kfree(event->hw.addr_filters); + event->hw.addr_filters = NULL; +} + +static int pt_event_addr_filters_validate(struct list_head *filters) +{ + struct perf_addr_filter *filter; + int range = 0; + + list_for_each_entry(filter, filters, entry) { + /* PT doesn't support single address triggers */ + if (!filter->range) + return -EOPNOTSUPP; + + if (!filter->inode && !kernel_ip(filter->offset)) + return -EINVAL; + + if (++range > pt_cap_get(PT_CAP_num_address_ranges)) + return -EOPNOTSUPP; + } + + return 0; +} + +static void pt_event_addr_filters_sync(struct perf_event *event) +{ + struct perf_addr_filters_head *head = perf_event_addr_filters(event); + unsigned long msr_a, msr_b, *offs = event->addr_filters_offs; + struct pt_filters *filters = event->hw.addr_filters; + struct perf_addr_filter *filter; + int range = 0; + + if (!filters) + return; - if (local_read(&buf->data_size) >= pt->handle.size) - return true; + list_for_each_entry(filter, &head->list, entry) { + if (filter->inode && !offs[range]) { + msr_a = msr_b = 0; + } else { + /* apply the offset */ + msr_a = filter->offset + offs[range]; + msr_b = filter->size + msr_a; + } + + filters->filter[range].msr_a = msr_a; + filters->filter[range].msr_b = msr_b; + filters->filter[range].config = filter->filter ? 1 : 2; + range++; + } - return false; + filters->nr_filters = range; } /** @@ -953,7 +1137,7 @@ void intel_pt_interrupt(void) * after PT has been disabled by pt_event_stop(). Make sure we don't * do anything (particularly, re-enable) for this event here. */ - if (!ACCESS_ONCE(pt->handle_nmi)) + if (!READ_ONCE(pt->handle_nmi)) return; /* @@ -1038,23 +1222,36 @@ EXPORT_SYMBOL_GPL(intel_pt_handle_vmx); static void pt_event_start(struct perf_event *event, int mode) { + struct hw_perf_event *hwc = &event->hw; struct pt *pt = this_cpu_ptr(&pt_ctx); - struct pt_buffer *buf = perf_get_aux(&pt->handle); + struct pt_buffer *buf; if (READ_ONCE(pt->vmx_on)) return; - if (!buf || pt_buffer_is_full(buf, pt)) { - event->hw.state = PERF_HES_STOPPED; - return; + buf = perf_aux_output_begin(&pt->handle, event); + if (!buf) + goto fail_stop; + + pt_buffer_reset_offsets(buf, pt->handle.head); + if (!buf->snapshot) { + if (pt_buffer_reset_markers(buf, &pt->handle)) + goto fail_end_stop; } - ACCESS_ONCE(pt->handle_nmi) = 1; - event->hw.state = 0; + WRITE_ONCE(pt->handle_nmi, 1); + hwc->state = 0; pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); pt_config(event); + + return; + +fail_end_stop: + perf_aux_output_end(&pt->handle, 0, true); +fail_stop: + hwc->state = PERF_HES_STOPPED; } static void pt_event_stop(struct perf_event *event, int mode) @@ -1065,7 +1262,7 @@ static void pt_event_stop(struct perf_event *event, int mode) * Protect against the PMI racing with disabling wrmsr, * see comment in intel_pt_interrupt(). */ - ACCESS_ONCE(pt->handle_nmi) = 0; + WRITE_ONCE(pt->handle_nmi, 0); pt_config_stop(event); @@ -1088,19 +1285,7 @@ static void pt_event_stop(struct perf_event *event, int mode) pt_handle_status(pt); pt_update_head(pt); - } -} - -static void pt_event_del(struct perf_event *event, int mode) -{ - struct pt *pt = this_cpu_ptr(&pt_ctx); - struct pt_buffer *buf; - pt_event_stop(event, PERF_EF_UPDATE); - - buf = perf_get_aux(&pt->handle); - - if (buf) { if (buf->snapshot) pt->handle.head = local_xchg(&buf->data_size, @@ -1110,9 +1295,13 @@ static void pt_event_del(struct perf_event *event, int mode) } } +static void pt_event_del(struct perf_event *event, int mode) +{ + pt_event_stop(event, PERF_EF_UPDATE); +} + static int pt_event_add(struct perf_event *event, int mode) { - struct pt_buffer *buf; struct pt *pt = this_cpu_ptr(&pt_ctx); struct hw_perf_event *hwc = &event->hw; int ret = -EBUSY; @@ -1120,34 +1309,18 @@ static int pt_event_add(struct perf_event *event, int mode) if (pt->handle.event) goto fail; - buf = perf_aux_output_begin(&pt->handle, event); - ret = -EINVAL; - if (!buf) - goto fail_stop; - - pt_buffer_reset_offsets(buf, pt->handle.head); - if (!buf->snapshot) { - ret = pt_buffer_reset_markers(buf, &pt->handle); - if (ret) - goto fail_end_stop; - } - if (mode & PERF_EF_START) { pt_event_start(event, 0); - ret = -EBUSY; + ret = -EINVAL; if (hwc->state == PERF_HES_STOPPED) - goto fail_end_stop; + goto fail; } else { hwc->state = PERF_HES_STOPPED; } - return 0; - -fail_end_stop: - perf_aux_output_end(&pt->handle, 0, true); -fail_stop: - hwc->state = PERF_HES_STOPPED; + ret = 0; fail: + return ret; } @@ -1157,6 +1330,7 @@ static void pt_event_read(struct perf_event *event) static void pt_event_destroy(struct perf_event *event) { + pt_addr_filters_fini(event); x86_del_exclusive(x86_lbr_exclusive_pt); } @@ -1171,6 +1345,11 @@ static int pt_event_init(struct perf_event *event) if (x86_add_exclusive(x86_lbr_exclusive_pt)) return -EBUSY; + if (pt_addr_filters_init(event)) { + x86_del_exclusive(x86_lbr_exclusive_pt); + return -ENOMEM; + } + event->destroy = pt_event_destroy; return 0; @@ -1190,7 +1369,7 @@ static __init int pt_init(void) BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); - if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + if (!boot_cpu_has(X86_FEATURE_INTEL_PT)) return -ENODEV; get_online_cpus(); @@ -1224,16 +1403,21 @@ static __init int pt_init(void) PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; - pt_pmu.pmu.attr_groups = pt_attr_groups; - pt_pmu.pmu.task_ctx_nr = perf_sw_context; - pt_pmu.pmu.event_init = pt_event_init; - pt_pmu.pmu.add = pt_event_add; - pt_pmu.pmu.del = pt_event_del; - pt_pmu.pmu.start = pt_event_start; - pt_pmu.pmu.stop = pt_event_stop; - pt_pmu.pmu.read = pt_event_read; - pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; - pt_pmu.pmu.free_aux = pt_buffer_free_aux; + pt_pmu.pmu.attr_groups = pt_attr_groups; + pt_pmu.pmu.task_ctx_nr = perf_sw_context; + pt_pmu.pmu.event_init = pt_event_init; + pt_pmu.pmu.add = pt_event_add; + pt_pmu.pmu.del = pt_event_del; + pt_pmu.pmu.start = pt_event_start; + pt_pmu.pmu.stop = pt_event_stop; + pt_pmu.pmu.read = pt_event_read; + pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; + pt_pmu.pmu.free_aux = pt_buffer_free_aux; + pt_pmu.pmu.addr_filters_sync = pt_event_addr_filters_sync; + pt_pmu.pmu.addr_filters_validate = pt_event_addr_filters_validate; + pt_pmu.pmu.nr_addr_filters = + pt_cap_get(PT_CAP_num_address_ranges); + ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1); return ret; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 3abb5f5cccc8..efffa4a09f68 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -20,6 +20,40 @@ #define __INTEL_PT_H__ /* + * PT MSR bit definitions + */ +#define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) +#define RTIT_CTL_OS BIT(2) +#define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_CR3EN BIT(7) +#define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) +#define RTIT_CTL_TSC_EN BIT(10) +#define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) +#define RTIT_CTL_ADDR0_OFFSET 32 +#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET) +#define RTIT_CTL_ADDR1_OFFSET 36 +#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET) +#define RTIT_CTL_ADDR2_OFFSET 40 +#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET) +#define RTIT_CTL_ADDR3_OFFSET 44 +#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET) +#define RTIT_STATUS_FILTEREN BIT(0) +#define RTIT_STATUS_CONTEXTEN BIT(1) +#define RTIT_STATUS_TRIGGEREN BIT(2) +#define RTIT_STATUS_BUFFOVF BIT(3) +#define RTIT_STATUS_ERROR BIT(4) +#define RTIT_STATUS_STOPPED BIT(5) + +/* * Single-entry ToPA: when this close to region boundary, switch * buffers to avoid losing data. */ @@ -48,15 +82,20 @@ struct topa_entry { #define PT_CPUID_LEAVES 2 #define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ +/* TSC to Core Crystal Clock Ratio */ +#define CPUID_TSC_LEAF 0x15 + enum pt_capabilities { PT_CAP_max_subleaf = 0, PT_CAP_cr3_filtering, PT_CAP_psb_cyc, + PT_CAP_ip_filtering, PT_CAP_mtc, PT_CAP_topa_output, PT_CAP_topa_multiple_entries, PT_CAP_single_range_output, PT_CAP_payloads_lip, + PT_CAP_num_address_ranges, PT_CAP_mtc_periods, PT_CAP_cycle_thresholds, PT_CAP_psb_periods, @@ -66,6 +105,9 @@ struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; bool vmx; + unsigned long max_nonturbo_ratio; + unsigned int tsc_art_num; + unsigned int tsc_art_den; }; /** @@ -104,14 +146,40 @@ struct pt_buffer { struct topa_entry *topa_index[0]; }; +#define PT_FILTERS_NUM 4 + +/** + * struct pt_filter - IP range filter configuration + * @msr_a: range start, goes to RTIT_ADDRn_A + * @msr_b: range end, goes to RTIT_ADDRn_B + * @config: 4-bit field in RTIT_CTL + */ +struct pt_filter { + unsigned long msr_a; + unsigned long msr_b; + unsigned long config; +}; + +/** + * struct pt_filters - IP range filtering context + * @filter: filters defined for this context + * @nr_filters: number of defined filters in the @filter array + */ +struct pt_filters { + struct pt_filter filter[PT_FILTERS_NUM]; + unsigned int nr_filters; +}; + /** * struct pt - per-cpu pt context * @handle: perf output handle + * @filters: last configured filters * @handle_nmi: do handle PT PMI on this cpu, there's an active event * @vmx_on: 1 if VMX is ON on this cpu */ struct pt { struct perf_output_handle handle; + struct pt_filters filters; int handle_nmi; int vmx_on; }; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 1705c9d75e44..99c4bab123cd 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -27,10 +27,14 @@ * event: rapl_energy_dram * perf code: 0x3 * - * dram counter: consumption of the builtin-gpu domain (client only) + * gpu counter: consumption of the builtin-gpu domain (client only) * event: rapl_energy_gpu * perf code: 0x4 * + * psys counter: consumption of the builtin-psys domain (client only) + * event: rapl_energy_psys + * perf code: 0x5 + * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * @@ -53,6 +57,8 @@ #include <asm/cpu_device_id.h> #include "../perf_event.h" +MODULE_LICENSE("GPL"); + /* * RAPL energy status counters */ @@ -64,13 +70,16 @@ #define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */ #define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ +#define RAPL_IDX_PSYS_NRG_STAT 4 /* psys */ +#define INTEL_RAPL_PSYS 0x5 /* pseudo-encoding */ -#define NR_RAPL_DOMAINS 0x4 +#define NR_RAPL_DOMAINS 0x5 static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", "pp1-gpu", + "psys", }; /* Clients have PP0, PKG */ @@ -89,6 +98,13 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { 1<<RAPL_IDX_RAM_NRG_STAT|\ 1<<RAPL_IDX_PP1_NRG_STAT) +/* SKL clients have PP0, PKG, RAM, PP1, PSYS */ +#define RAPL_IDX_SKL_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ + 1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_RAM_NRG_STAT|\ + 1<<RAPL_IDX_PP1_NRG_STAT|\ + 1<<RAPL_IDX_PSYS_NRG_STAT) + /* Knights Landing has PKG, RAM */ #define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\ 1<<RAPL_IDX_RAM_NRG_STAT) @@ -360,6 +376,10 @@ static int rapl_pmu_event_init(struct perf_event *event) bit = RAPL_IDX_PP1_NRG_STAT; msr = MSR_PP1_ENERGY_STATUS; break; + case INTEL_RAPL_PSYS: + bit = RAPL_IDX_PSYS_NRG_STAT; + msr = MSR_PLATFORM_ENERGY_STATUS; + break; default: return -EINVAL; } @@ -414,11 +434,13 @@ RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); +RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR @@ -427,6 +449,7 @@ RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890 RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); static struct attribute *rapl_events_srv_attr[] = { EVENT_PTR(rapl_cores), @@ -476,6 +499,27 @@ static struct attribute *rapl_events_hsw_attr[] = { NULL, }; +static struct attribute *rapl_events_skl_attr[] = { + EVENT_PTR(rapl_cores), + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_gpu), + EVENT_PTR(rapl_ram), + EVENT_PTR(rapl_psys), + + EVENT_PTR(rapl_cores_unit), + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_gpu_unit), + EVENT_PTR(rapl_ram_unit), + EVENT_PTR(rapl_psys_unit), + + EVENT_PTR(rapl_cores_scale), + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_gpu_scale), + EVENT_PTR(rapl_ram_scale), + EVENT_PTR(rapl_psys_scale), + NULL, +}; + static struct attribute *rapl_events_knl_attr[] = { EVENT_PTR(rapl_pkg), EVENT_PTR(rapl_ram), @@ -592,6 +636,11 @@ static int rapl_cpu_notifier(struct notifier_block *self, return NOTIFY_OK; } +static struct notifier_block rapl_cpu_nb = { + .notifier_call = rapl_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; + static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -660,7 +709,7 @@ static int __init rapl_prepare_cpus(void) return 0; } -static void __init cleanup_rapl_pmus(void) +static void cleanup_rapl_pmus(void) { int i; @@ -691,52 +740,92 @@ static int __init init_rapl_pmus(void) return 0; } +#define X86_RAPL_MODEL_MATCH(model, init) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } + +struct intel_rapl_init_fun { + bool apply_quirk; + int cntr_mask; + struct attribute **attrs; +}; + +static const struct intel_rapl_init_fun snb_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_CLN, + .attrs = rapl_events_cln_attr, +}; + +static const struct intel_rapl_init_fun hsx_rapl_init __initconst = { + .apply_quirk = true, + .cntr_mask = RAPL_IDX_SRV, + .attrs = rapl_events_srv_attr, +}; + +static const struct intel_rapl_init_fun hsw_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_HSW, + .attrs = rapl_events_hsw_attr, +}; + +static const struct intel_rapl_init_fun snbep_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_SRV, + .attrs = rapl_events_srv_attr, +}; + +static const struct intel_rapl_init_fun knl_rapl_init __initconst = { + .apply_quirk = true, + .cntr_mask = RAPL_IDX_KNL, + .attrs = rapl_events_knl_attr, +}; + +static const struct intel_rapl_init_fun skl_rapl_init __initconst = { + .apply_quirk = false, + .cntr_mask = RAPL_IDX_SKL_CLN, + .attrs = rapl_events_skl_attr, +}; + static const struct x86_cpu_id rapl_cpu_match[] __initconst = { - [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, - [1] = {}, + X86_RAPL_MODEL_MATCH(42, snb_rapl_init), /* Sandy Bridge */ + X86_RAPL_MODEL_MATCH(45, snbep_rapl_init), /* Sandy Bridge-EP */ + + X86_RAPL_MODEL_MATCH(58, snb_rapl_init), /* Ivy Bridge */ + X86_RAPL_MODEL_MATCH(62, snbep_rapl_init), /* IvyTown */ + + X86_RAPL_MODEL_MATCH(60, hsw_rapl_init), /* Haswell */ + X86_RAPL_MODEL_MATCH(63, hsx_rapl_init), /* Haswell-Server */ + X86_RAPL_MODEL_MATCH(69, hsw_rapl_init), /* Haswell-Celeron */ + X86_RAPL_MODEL_MATCH(70, hsw_rapl_init), /* Haswell GT3e */ + + X86_RAPL_MODEL_MATCH(61, hsw_rapl_init), /* Broadwell */ + X86_RAPL_MODEL_MATCH(71, hsw_rapl_init), /* Broadwell-H */ + X86_RAPL_MODEL_MATCH(79, hsx_rapl_init), /* Broadwell-Server */ + X86_RAPL_MODEL_MATCH(86, hsx_rapl_init), /* Broadwell Xeon D */ + + X86_RAPL_MODEL_MATCH(87, knl_rapl_init), /* Knights Landing */ + + X86_RAPL_MODEL_MATCH(78, skl_rapl_init), /* Skylake */ + X86_RAPL_MODEL_MATCH(94, skl_rapl_init), /* Skylake H/S */ + {}, }; +MODULE_DEVICE_TABLE(x86cpu, rapl_cpu_match); + static int __init rapl_pmu_init(void) { - bool apply_quirk = false; + const struct x86_cpu_id *id; + struct intel_rapl_init_fun *rapl_init; + bool apply_quirk; int ret; - if (!x86_match_cpu(rapl_cpu_match)) + id = x86_match_cpu(rapl_cpu_match); + if (!id) return -ENODEV; - switch (boot_cpu_data.x86_model) { - case 42: /* Sandy Bridge */ - case 58: /* Ivy Bridge */ - rapl_cntr_mask = RAPL_IDX_CLN; - rapl_pmu_events_group.attrs = rapl_events_cln_attr; - break; - case 63: /* Haswell-Server */ - case 79: /* Broadwell-Server */ - apply_quirk = true; - rapl_cntr_mask = RAPL_IDX_SRV; - rapl_pmu_events_group.attrs = rapl_events_srv_attr; - break; - case 60: /* Haswell */ - case 69: /* Haswell-Celeron */ - case 70: /* Haswell GT3e */ - case 61: /* Broadwell */ - case 71: /* Broadwell-H */ - rapl_cntr_mask = RAPL_IDX_HSW; - rapl_pmu_events_group.attrs = rapl_events_hsw_attr; - break; - case 45: /* Sandy Bridge-EP */ - case 62: /* IvyTown */ - rapl_cntr_mask = RAPL_IDX_SRV; - rapl_pmu_events_group.attrs = rapl_events_srv_attr; - break; - case 87: /* Knights Landing */ - apply_quirk = true; - rapl_cntr_mask = RAPL_IDX_KNL; - rapl_pmu_events_group.attrs = rapl_events_knl_attr; - break; - default: - return -ENODEV; - } + rapl_init = (struct intel_rapl_init_fun *)id->driver_data; + apply_quirk = rapl_init->apply_quirk; + rapl_cntr_mask = rapl_init->cntr_mask; + rapl_pmu_events_group.attrs = rapl_init->attrs; ret = rapl_check_hw_unit(apply_quirk); if (ret) @@ -756,7 +845,7 @@ static int __init rapl_pmu_init(void) if (ret) goto out; - __perf_cpu_notifier(rapl_cpu_notifier); + __register_cpu_notifier(&rapl_cpu_nb); cpu_notifier_register_done(); rapl_advertise(); return 0; @@ -767,4 +856,14 @@ out: cpu_notifier_register_done(); return ret; } -device_initcall(rapl_pmu_init); +module_init(rapl_pmu_init); + +static void __exit intel_rapl_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&rapl_cpu_nb); + perf_pmu_unregister(&rapl_pmus->pmu); + cleanup_rapl_pmus(); + cpu_notifier_register_done(); +} +module_exit(intel_rapl_exit); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7012d18bb293..17734a6ef474 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1,3 +1,4 @@ +#include <asm/cpu_device_id.h> #include "uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; @@ -21,6 +22,8 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +MODULE_LICENSE("GPL"); + static int uncore_pcibus_to_physid(struct pci_bus *bus) { struct pci2phy_map *map; @@ -754,7 +757,7 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) +static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) { struct intel_uncore_pmu *pmu = type->pmus; struct intel_uncore_box *box; @@ -770,7 +773,7 @@ static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) } } -static void __init uncore_exit_boxes(void *dummy) +static void uncore_exit_boxes(void *dummy) { struct intel_uncore_type **types; @@ -787,7 +790,7 @@ static void uncore_free_boxes(struct intel_uncore_pmu *pmu) kfree(pmu->boxes); } -static void __init uncore_type_exit(struct intel_uncore_type *type) +static void uncore_type_exit(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmu = type->pmus; int i; @@ -804,7 +807,7 @@ static void __init uncore_type_exit(struct intel_uncore_type *type) type->events_group = NULL; } -static void __init uncore_types_exit(struct intel_uncore_type **types) +static void uncore_types_exit(struct intel_uncore_type **types) { for (; *types; types++) uncore_type_exit(*types); @@ -989,46 +992,6 @@ static int __init uncore_pci_init(void) size_t size; int ret; - switch (boot_cpu_data.x86_model) { - case 45: /* Sandy Bridge-EP */ - ret = snbep_uncore_pci_init(); - break; - case 62: /* Ivy Bridge-EP */ - ret = ivbep_uncore_pci_init(); - break; - case 63: /* Haswell-EP */ - ret = hswep_uncore_pci_init(); - break; - case 79: /* BDX-EP */ - case 86: /* BDX-DE */ - ret = bdx_uncore_pci_init(); - break; - case 42: /* Sandy Bridge */ - ret = snb_uncore_pci_init(); - break; - case 58: /* Ivy Bridge */ - ret = ivb_uncore_pci_init(); - break; - case 60: /* Haswell */ - case 69: /* Haswell Celeron */ - ret = hsw_uncore_pci_init(); - break; - case 61: /* Broadwell */ - ret = bdw_uncore_pci_init(); - break; - case 87: /* Knights Landing */ - ret = knl_uncore_pci_init(); - break; - case 94: /* SkyLake */ - ret = skl_uncore_pci_init(); - break; - default: - return -ENODEV; - } - - if (ret) - return ret; - size = max_packages * sizeof(struct pci_extra_dev); uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL); if (!uncore_extra_pci_dev) { @@ -1060,7 +1023,7 @@ err: return ret; } -static void __init uncore_pci_exit(void) +static void uncore_pci_exit(void) { if (pcidrv_registered) { pcidrv_registered = false; @@ -1287,46 +1250,6 @@ static int __init uncore_cpu_init(void) { int ret; - switch (boot_cpu_data.x86_model) { - case 26: /* Nehalem */ - case 30: - case 37: /* Westmere */ - case 44: - nhm_uncore_cpu_init(); - break; - case 42: /* Sandy Bridge */ - case 58: /* Ivy Bridge */ - case 60: /* Haswell */ - case 69: /* Haswell */ - case 70: /* Haswell */ - case 61: /* Broadwell */ - case 71: /* Broadwell */ - snb_uncore_cpu_init(); - break; - case 45: /* Sandy Bridge-EP */ - snbep_uncore_cpu_init(); - break; - case 46: /* Nehalem-EX */ - case 47: /* Westmere-EX aka. Xeon E7 */ - nhmex_uncore_cpu_init(); - break; - case 62: /* Ivy Bridge-EP */ - ivbep_uncore_cpu_init(); - break; - case 63: /* Haswell-EP */ - hswep_uncore_cpu_init(); - break; - case 79: /* BDX-EP */ - case 86: /* BDX-DE */ - bdx_uncore_cpu_init(); - break; - case 87: /* Knights Landing */ - knl_uncore_cpu_init(); - break; - default: - return -ENODEV; - } - ret = uncore_types_init(uncore_msr_uncores, true); if (ret) goto err; @@ -1376,11 +1299,105 @@ static int __init uncore_cpumask_init(bool msr) return 0; } +#define X86_UNCORE_MODEL_MATCH(model, init) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init } + +struct intel_uncore_init_fun { + void (*cpu_init)(void); + int (*pci_init)(void); +}; + +static const struct intel_uncore_init_fun nhm_uncore_init __initconst = { + .cpu_init = nhm_uncore_cpu_init, +}; + +static const struct intel_uncore_init_fun snb_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = snb_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun ivb_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = ivb_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun hsw_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = hsw_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun bdw_uncore_init __initconst = { + .cpu_init = snb_uncore_cpu_init, + .pci_init = bdw_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun snbep_uncore_init __initconst = { + .cpu_init = snbep_uncore_cpu_init, + .pci_init = snbep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun nhmex_uncore_init __initconst = { + .cpu_init = nhmex_uncore_cpu_init, +}; + +static const struct intel_uncore_init_fun ivbep_uncore_init __initconst = { + .cpu_init = ivbep_uncore_cpu_init, + .pci_init = ivbep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun hswep_uncore_init __initconst = { + .cpu_init = hswep_uncore_cpu_init, + .pci_init = hswep_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun bdx_uncore_init __initconst = { + .cpu_init = bdx_uncore_cpu_init, + .pci_init = bdx_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun knl_uncore_init __initconst = { + .cpu_init = knl_uncore_cpu_init, + .pci_init = knl_uncore_pci_init, +}; + +static const struct intel_uncore_init_fun skl_uncore_init __initconst = { + .pci_init = skl_uncore_pci_init, +}; + +static const struct x86_cpu_id intel_uncore_match[] __initconst = { + X86_UNCORE_MODEL_MATCH(26, nhm_uncore_init), /* Nehalem */ + X86_UNCORE_MODEL_MATCH(30, nhm_uncore_init), + X86_UNCORE_MODEL_MATCH(37, nhm_uncore_init), /* Westmere */ + X86_UNCORE_MODEL_MATCH(44, nhm_uncore_init), + X86_UNCORE_MODEL_MATCH(42, snb_uncore_init), /* Sandy Bridge */ + X86_UNCORE_MODEL_MATCH(58, ivb_uncore_init), /* Ivy Bridge */ + X86_UNCORE_MODEL_MATCH(60, hsw_uncore_init), /* Haswell */ + X86_UNCORE_MODEL_MATCH(69, hsw_uncore_init), /* Haswell Celeron */ + X86_UNCORE_MODEL_MATCH(70, hsw_uncore_init), /* Haswell */ + X86_UNCORE_MODEL_MATCH(61, bdw_uncore_init), /* Broadwell */ + X86_UNCORE_MODEL_MATCH(71, bdw_uncore_init), /* Broadwell */ + X86_UNCORE_MODEL_MATCH(45, snbep_uncore_init), /* Sandy Bridge-EP */ + X86_UNCORE_MODEL_MATCH(46, nhmex_uncore_init), /* Nehalem-EX */ + X86_UNCORE_MODEL_MATCH(47, nhmex_uncore_init), /* Westmere-EX aka. Xeon E7 */ + X86_UNCORE_MODEL_MATCH(62, ivbep_uncore_init), /* Ivy Bridge-EP */ + X86_UNCORE_MODEL_MATCH(63, hswep_uncore_init), /* Haswell-EP */ + X86_UNCORE_MODEL_MATCH(79, bdx_uncore_init), /* BDX-EP */ + X86_UNCORE_MODEL_MATCH(86, bdx_uncore_init), /* BDX-DE */ + X86_UNCORE_MODEL_MATCH(87, knl_uncore_init), /* Knights Landing */ + X86_UNCORE_MODEL_MATCH(94, skl_uncore_init), /* SkyLake */ + {}, +}; + +MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); + static int __init intel_uncore_init(void) { - int pret, cret, ret; + const struct x86_cpu_id *id; + struct intel_uncore_init_fun *uncore_init; + int pret = 0, cret = 0, ret; - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + id = x86_match_cpu(intel_uncore_match); + if (!id) return -ENODEV; if (cpu_has_hypervisor) @@ -1388,8 +1405,17 @@ static int __init intel_uncore_init(void) max_packages = topology_max_packages(); - pret = uncore_pci_init(); - cret = uncore_cpu_init(); + uncore_init = (struct intel_uncore_init_fun *)id->driver_data; + if (uncore_init->pci_init) { + pret = uncore_init->pci_init(); + if (!pret) + pret = uncore_pci_init(); + } + + if (uncore_init->cpu_init) { + uncore_init->cpu_init(); + cret = uncore_cpu_init(); + } if (cret && pret) return -ENODEV; @@ -1409,4 +1435,14 @@ err: cpu_notifier_register_done(); return ret; } -device_initcall(intel_uncore_init); +module_init(intel_uncore_init); + +static void __exit intel_uncore_exit(void) +{ + cpu_notifier_register_begin(); + __unregister_cpu_notifier(&uncore_cpu_nb); + uncore_types_exit(uncore_msr_uncores); + uncore_pci_exit(); + cpu_notifier_register_done(); +} +module_exit(intel_uncore_exit); diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ab2bcaaebe38..b2625867ebd1 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -219,6 +219,9 @@ #define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff #define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) #define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) +#define KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE (0x1ULL << 32) +#define KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE (0x1ULL << 33) +#define KNL_CHA_MSR_PMON_BOX_FILTER_NNC (0x1ULL << 37) /* KNL EDC/MC UCLK */ #define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 @@ -1902,6 +1905,10 @@ static int knl_cha_hw_config(struct intel_uncore_box *box, reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + + reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_REMOTE_NODE; + reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_LOCAL_NODE; + reg1->config |= KNL_CHA_MSR_PMON_BOX_FILTER_NNC; reg1->idx = idx; } return 0; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ec863b9a9f78..85ef3c2e80e0 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -6,6 +6,8 @@ enum perf_msr_id { PERF_MSR_MPERF = 2, PERF_MSR_PPERF = 3, PERF_MSR_SMI = 4, + PERF_MSR_PTSC = 5, + PERF_MSR_IRPERF = 6, PERF_MSR_EVENT_MAX, }; @@ -15,6 +17,16 @@ static bool test_aperfmperf(int idx) return boot_cpu_has(X86_FEATURE_APERFMPERF); } +static bool test_ptsc(int idx) +{ + return boot_cpu_has(X86_FEATURE_PTSC); +} + +static bool test_irperf(int idx) +{ + return boot_cpu_has(X86_FEATURE_IRPERF); +} + static bool test_intel(int idx) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || @@ -69,18 +81,22 @@ struct perf_msr { bool (*test)(int idx); }; -PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); -PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); -PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); -PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); -PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); +PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); +PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); +PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); +PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); +PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); +PMU_EVENT_ATTR_STRING(ptsc, evattr_ptsc, "event=0x05"); +PMU_EVENT_ATTR_STRING(irperf, evattr_irperf, "event=0x06"); static struct perf_msr msr[] = { - [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, - [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, - [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, - [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, - [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, + [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, + [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, + [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, + [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, + [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, + [PERF_MSR_PTSC] = { MSR_F15H_PTSC, &evattr_ptsc, test_ptsc, }, + [PERF_MSR_IRPERF] = { MSR_F17H_IRPERF, &evattr_irperf, test_irperf, }, }; static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = { @@ -166,7 +182,7 @@ again: if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) delta = sign_extend64(delta, 31); - local64_add(now - prev, &event->count); + local64_add(delta, &event->count); } static void msr_event_start(struct perf_event *event, int flags) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ad4dc7ffffb5..8bd764df815d 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -601,6 +601,7 @@ struct x86_pmu { u64 lbr_sel_mask; /* LBR_SELECT valid bits */ const int *lbr_sel_map; /* lbr_select mappings */ bool lbr_double_abort; /* duplicated lbr aborts */ + bool lbr_pt_coexist; /* LBR may coexist with PT */ /* * Intel PT/LBR/BTS are exclusive @@ -859,6 +860,8 @@ extern struct event_constraint intel_atom_pebs_event_constraints[]; extern struct event_constraint intel_slm_pebs_event_constraints[]; +extern struct event_constraint intel_glm_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; @@ -907,6 +910,8 @@ void intel_pmu_lbr_init_nhm(void); void intel_pmu_lbr_init_atom(void); +void intel_pmu_lbr_init_slm(void); + void intel_pmu_lbr_init_snb(void); void intel_pmu_lbr_init_hsw(void); diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 3636ec06c887..53ac9bbf2064 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -27,6 +27,7 @@ enum cpuid_leafs CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, + CPUID_8000_0007_EBX, }; #ifdef CONFIG_X86_FEATURE_NAMES diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8f9afefd2dc5..0aee9dd1976e 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -12,7 +12,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 17 /* N 32-bit words worth of info */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -177,6 +177,7 @@ #define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ #define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ @@ -250,6 +251,7 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -280,6 +282,11 @@ #define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ #define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ +/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 53748c45e488..78d1e7467eae 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -3,6 +3,7 @@ #include <asm/fpu/api.h> #include <asm/pgtable.h> +#include <asm/processor-flags.h> #include <asm/tlb.h> /* @@ -28,33 +29,22 @@ #define MAX_CMDLINE_ADDRESS UINT_MAX -#ifdef CONFIG_X86_32 +#define ARCH_EFI_IRQ_FLAGS_MASK X86_EFLAGS_IF +#ifdef CONFIG_X86_32 extern unsigned long asmlinkage efi_call_phys(void *, ...); +#define arch_efi_call_virt_setup() kernel_fpu_begin() +#define arch_efi_call_virt_teardown() kernel_fpu_end() + /* * Wrap all the virtual calls in a way that forces the parameters on the stack. */ - -/* Use this macro if your virtual returns a non-void value */ -#define efi_call_virt(f, args...) \ +#define arch_efi_call_virt(f, args...) \ ({ \ - efi_status_t __s; \ - kernel_fpu_begin(); \ - __s = ((efi_##f##_t __attribute__((regparm(0)))*) \ - efi.systab->runtime->f)(args); \ - kernel_fpu_end(); \ - __s; \ -}) - -/* Use this macro if your virtual call does not return any value */ -#define __efi_call_virt(f, args...) \ -({ \ - kernel_fpu_begin(); \ ((efi_##f##_t __attribute__((regparm(0)))*) \ efi.systab->runtime->f)(args); \ - kernel_fpu_end(); \ }) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) @@ -78,10 +68,8 @@ struct efi_scratch { u64 phys_stack; } __packed; -#define efi_call_virt(f, ...) \ +#define arch_efi_call_virt_setup() \ ({ \ - efi_status_t __s; \ - \ efi_sync_low_kernel_mappings(); \ preempt_disable(); \ __kernel_fpu_begin(); \ @@ -91,9 +79,13 @@ struct efi_scratch { write_cr3((unsigned long)efi_scratch.efi_pgt); \ __flush_tlb_all(); \ } \ - \ - __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \ - \ +}) + +#define arch_efi_call_virt(f, args...) \ + efi_call((void *)efi.systab->runtime->f, args) \ + +#define arch_efi_call_virt_teardown() \ +({ \ if (efi_scratch.use_pgd) { \ write_cr3(efi_scratch.prev_cr3); \ __flush_tlb_all(); \ @@ -101,15 +93,8 @@ struct efi_scratch { \ __kernel_fpu_end(); \ preempt_enable(); \ - __s; \ }) -/* - * All X86_64 virt calls return non-void values. Thus, use non-void call for - * virt calls that would be void on X86_32. - */ -#define __efi_call_virt(f, args...) efi_call_virt(f, args) - extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); @@ -180,6 +165,8 @@ static inline bool efi_runtime_supported(void) extern struct console early_efi_console; extern void parse_efi_setup(u64 phys_addr, u32 data_len); +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); + #ifdef CONFIG_EFI_MIXED extern void efi_thunk_runtime_setup(void); extern efi_status_t efi_thunk_set_virtual_address_map( @@ -225,6 +212,11 @@ __pure const struct efi_config *__efi_early(void); #define efi_call_early(f, ...) \ __efi_early()->call(__efi_early()->f, __VA_ARGS__); +#define __efi_call_early(f, ...) \ + __efi_early()->call((unsigned long)f, __VA_ARGS__); + +#define efi_is_64bit() __efi_early()->is64 + extern bool efi_reboot_required(void); #else diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 92b6f651fa4f..8bf766ef0e18 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -104,13 +104,23 @@ #define MCE_LOG_SIGNATURE "MACHINECHECK" /* AMD Scalable MCA */ +#define MSR_AMD64_SMCA_MC0_CTL 0xc0002000 +#define MSR_AMD64_SMCA_MC0_STATUS 0xc0002001 +#define MSR_AMD64_SMCA_MC0_ADDR 0xc0002002 #define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 #define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 #define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 +#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 #define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a +#define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_ADDR(x) (MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) #define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) /* @@ -168,9 +178,18 @@ struct mce_vendor_flags { __reserved_0 : 61; }; + +struct mca_msr_regs { + u32 (*ctl) (int bank); + u32 (*status) (int bank); + u32 (*addr) (int bank); + u32 (*misc) (int bank); +}; + extern struct mce_vendor_flags mce_flags; extern struct mca_config mca_cfg; +extern struct mca_msr_regs msr_ops; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 5b3c9a55f51c..5a73a9c62c39 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -89,27 +89,16 @@ #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 -#define RTIT_CTL_TRACEEN BIT(0) -#define RTIT_CTL_CYCLEACC BIT(1) -#define RTIT_CTL_OS BIT(2) -#define RTIT_CTL_USR BIT(3) -#define RTIT_CTL_CR3EN BIT(7) -#define RTIT_CTL_TOPA BIT(8) -#define RTIT_CTL_MTC_EN BIT(9) -#define RTIT_CTL_TSC_EN BIT(10) -#define RTIT_CTL_DISRETC BIT(11) -#define RTIT_CTL_BRANCH_EN BIT(13) -#define RTIT_CTL_MTC_RANGE_OFFSET 14 -#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) -#define RTIT_CTL_CYC_THRESH_OFFSET 19 -#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) -#define RTIT_CTL_PSB_FREQ_OFFSET 24 -#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) #define MSR_IA32_RTIT_STATUS 0x00000571 -#define RTIT_STATUS_CONTEXTEN BIT(1) -#define RTIT_STATUS_TRIGGEREN BIT(2) -#define RTIT_STATUS_ERROR BIT(4) -#define RTIT_STATUS_STOPPED BIT(5) +#define MSR_IA32_RTIT_STATUS 0x00000571 +#define MSR_IA32_RTIT_ADDR0_A 0x00000580 +#define MSR_IA32_RTIT_ADDR0_B 0x00000581 +#define MSR_IA32_RTIT_ADDR1_A 0x00000582 +#define MSR_IA32_RTIT_ADDR1_B 0x00000583 +#define MSR_IA32_RTIT_ADDR2_A 0x00000584 +#define MSR_IA32_RTIT_ADDR2_B 0x00000585 +#define MSR_IA32_RTIT_ADDR3_A 0x00000586 +#define MSR_IA32_RTIT_ADDR3_B 0x00000587 #define MSR_IA32_RTIT_CR3_MATCH 0x00000572 #define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560 #define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561 @@ -205,6 +194,8 @@ #define MSR_CONFIG_TDP_CONTROL 0x0000064B #define MSR_TURBO_ACTIVATION_RATIO 0x0000064C +#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D + #define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 #define MSR_PKG_ANY_CORE_C0_RES 0x00000659 #define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A @@ -315,6 +306,9 @@ #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +/* Fam 17h MSRs */ +#define MSR_F17H_IRPERF 0xc00000e9 + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 @@ -328,6 +322,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_PTSC 0xc0010280 #define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index ceec86eb68e9..453744c1d347 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -99,26 +99,36 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) /* * lock for writing */ -static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) +#define ____down_write(sem, slow_path) \ +({ \ + long tmp; \ + struct rw_semaphore* ret; \ + asm volatile("# beginning down_write\n\t" \ + LOCK_PREFIX " xadd %1,(%3)\n\t" \ + /* adds 0xffff0001, returns the old value */ \ + " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \ + /* was the active mask 0 before? */\ + " jz 1f\n" \ + " call " slow_path "\n" \ + "1:\n" \ + "# ending down_write" \ + : "+m" (sem->count), "=d" (tmp), "=a" (ret) \ + : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \ + : "memory", "cc"); \ + ret; \ +}) + +static inline void __down_write(struct rw_semaphore *sem) { - long tmp; - asm volatile("# beginning down_write\n\t" - LOCK_PREFIX " xadd %1,(%2)\n\t" - /* adds 0xffff0001, returns the old value */ - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" - /* was the active mask 0 before? */ - " jz 1f\n" - " call call_rwsem_down_write_failed\n" - "1:\n" - "# ending down_write" - : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) - : "memory", "cc"); + ____down_write(sem, "call_rwsem_down_write_failed"); } -static inline void __down_write(struct rw_semaphore *sem) +static inline int __down_write_killable(struct rw_semaphore *sem) { - __down_write_nested(sem, 0); + if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable"))) + return -EINTR; + + return 0; } /* diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a969ae607be8..2e7513d1f1f4 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -108,6 +108,14 @@ struct exception_table_entry { #define ARCH_HAS_RELATIVE_EXTABLE +#define swap_ex_entry_fixup(a, b, tmp, delta) \ + do { \ + (a)->fixup = (b)->fixup + (delta); \ + (b)->fixup = (tmp).fixup - (delta); \ + (a)->handler = (b)->handler + (delta); \ + (b)->handler = (tmp).handler - (delta); \ + } while (0) + extern int fixup_exception(struct pt_regs *regs, int trapnr); extern bool ex_has_fault_handler(unsigned long ip); extern int early_fixup_exception(unsigned long *ip); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8394b3d1f94f..dbc6f066e231 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -717,6 +717,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } } + if (c->extended_cpuid_level >= 0x80000007) { + cpuid(0x80000007, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0007_EBX] = ebx; + c->x86_power = edx; + } + if (c->extended_cpuid_level >= 0x80000008) { cpuid(0x80000008, &eax, &ebx, &ecx, &edx); @@ -729,9 +736,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_phys_bits = 36; #endif - if (c->extended_cpuid_level >= 0x80000007) - c->x86_power = cpuid_edx(0x80000007); - if (c->extended_cpuid_level >= 0x8000000a) c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 2658e2af74ec..93d824ec3120 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -26,6 +26,52 @@ static struct gen_pool *mce_evt_pool; static LLIST_HEAD(mce_event_llist); static char gen_pool_buf[MCE_POOLSZ]; +/* + * Compare the record "t" with each of the records on list "l" to see if + * an equivalent one is present in the list. + */ +static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l) +{ + struct mce_evt_llist *node; + struct mce *m1, *m2; + + m1 = &t->mce; + + llist_for_each_entry(node, &l->llnode, llnode) { + m2 = &node->mce; + + if (!mce_cmp(m1, m2)) + return true; + } + return false; +} + +/* + * The system has panicked - we'd like to peruse the list of MCE records + * that have been queued, but not seen by anyone yet. The list is in + * reverse time order, so we need to reverse it. While doing that we can + * also drop duplicate records (these were logged because some banks are + * shared between cores or by all threads on a socket). + */ +struct llist_node *mce_gen_pool_prepare_records(void) +{ + struct llist_node *head; + LLIST_HEAD(new_head); + struct mce_evt_llist *node, *t; + + head = llist_del_all(&mce_event_llist); + if (!head) + return NULL; + + /* squeeze out duplicates while reversing order */ + llist_for_each_entry_safe(node, t, head, llnode) { + if (!is_duplicate_mce_record(node, t)) + llist_add(&node->llnode, &new_head); + } + + return new_head.first; +} + void mce_gen_pool_process(void) { struct llist_node *head; diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 547720efd923..cd74a3f00aea 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -35,6 +35,7 @@ void mce_gen_pool_process(void); bool mce_gen_pool_empty(void); int mce_gen_pool_add(struct mce *mce); int mce_gen_pool_init(void); +struct llist_node *mce_gen_pool_prepare_records(void); extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); @@ -81,3 +82,17 @@ static inline int apei_clear_mce(u64 record_id) #endif void mce_inject_log(struct mce *m); + +/* + * We consider records to be equivalent if bank+status+addr+misc all match. + * This is only used when the system is going down because of a fatal error + * to avoid cluttering the console log with essentially repeated information. + * In normal processing all errors seen are logged. + */ +static inline bool mce_cmp(struct mce *m1, struct mce *m2) +{ + return m1->bank != m2->bank || + m1->status != m2->status || + m1->addr != m2->addr || + m1->misc != m2->misc; +} diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 5119766d9889..631356c8cca4 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -204,6 +204,33 @@ static int error_context(struct mce *m) return IN_KERNEL; } +static int mce_severity_amd_smca(struct mce *m, int err_ctx) +{ + u32 addr = MSR_AMD64_SMCA_MCx_CONFIG(m->bank); + u32 low, high; + + /* + * We need to look at the following bits: + * - "succor" bit (data poisoning support), and + * - TCC bit (Task Context Corrupt) + * in MCi_STATUS to determine error severity. + */ + if (!mce_flags.succor) + return MCE_PANIC_SEVERITY; + + if (rdmsr_safe(addr, &low, &high)) + return MCE_PANIC_SEVERITY; + + /* TCC (Task context corrupt). If set and if IN_KERNEL, panic. */ + if ((low & MCI_CONFIG_MCAX) && + (m->status & MCI_STATUS_TCC) && + (err_ctx == IN_KERNEL)) + return MCE_PANIC_SEVERITY; + + /* ...otherwise invoke hwpoison handler. */ + return MCE_AR_SEVERITY; +} + /* * See AMD Error Scope Hierarchy table in a newer BKDG. For example * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" @@ -225,6 +252,9 @@ static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_exc * to at least kill process to prolong system operation. */ if (mce_flags.overflow_recov) { + if (mce_flags.smca) + return mce_severity_amd_smca(m, ctx); + /* software can try to contain */ if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) return MCE_PANIC_SEVERITY; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index f0c921b03e42..92e5e37d97bf 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -161,7 +161,6 @@ void mce_log(struct mce *mce) if (!mce_gen_pool_add(mce)) irq_work_queue(&mce_irq_work); - mce->finished = 0; wmb(); for (;;) { entry = mce_log_get_idx_check(mcelog.next); @@ -194,7 +193,6 @@ void mce_log(struct mce *mce) mcelog.entry[entry].finished = 1; wmb(); - mce->finished = 1; set_bit(0, &mce_need_notify); } @@ -224,6 +222,53 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); +static inline u32 ctl_reg(int bank) +{ + return MSR_IA32_MCx_CTL(bank); +} + +static inline u32 status_reg(int bank) +{ + return MSR_IA32_MCx_STATUS(bank); +} + +static inline u32 addr_reg(int bank) +{ + return MSR_IA32_MCx_ADDR(bank); +} + +static inline u32 misc_reg(int bank) +{ + return MSR_IA32_MCx_MISC(bank); +} + +static inline u32 smca_ctl_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_CTL(bank); +} + +static inline u32 smca_status_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_STATUS(bank); +} + +static inline u32 smca_addr_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_ADDR(bank); +} + +static inline u32 smca_misc_reg(int bank) +{ + return MSR_AMD64_SMCA_MCx_MISC(bank); +} + +struct mca_msr_regs msr_ops = { + .ctl = ctl_reg, + .status = status_reg, + .addr = addr_reg, + .misc = misc_reg +}; + static void print_mce(struct mce *m) { int ret = 0; @@ -290,7 +335,9 @@ static void wait_for_panic(void) static void mce_panic(const char *msg, struct mce *final, char *exp) { - int i, apei_err = 0; + int apei_err = 0; + struct llist_node *pending; + struct mce_evt_llist *l; if (!fake_panic) { /* @@ -307,11 +354,10 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) if (atomic_inc_return(&mce_fake_panicked) > 1) return; } + pending = mce_gen_pool_prepare_records(); /* First print corrected ones that are still unlogged */ - for (i = 0; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - if (!(m->status & MCI_STATUS_VAL)) - continue; + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; if (!(m->status & MCI_STATUS_UC)) { print_mce(m); if (!apei_err) @@ -319,13 +365,11 @@ static void mce_panic(const char *msg, struct mce *final, char *exp) } } /* Now print uncorrected but with the final one last */ - for (i = 0; i < MCE_LOG_LEN; i++) { - struct mce *m = &mcelog.entry[i]; - if (!(m->status & MCI_STATUS_VAL)) - continue; + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; if (!(m->status & MCI_STATUS_UC)) continue; - if (!final || memcmp(m, final, sizeof(struct mce))) { + if (!final || mce_cmp(m, final)) { print_mce(m); if (!apei_err) apei_err = apei_write_mce(m); @@ -356,11 +400,11 @@ static int msr_to_offset(u32 msr) if (msr == mca_cfg.rip_msr) return offsetof(struct mce, ip); - if (msr == MSR_IA32_MCx_STATUS(bank)) + if (msr == msr_ops.status(bank)) return offsetof(struct mce, status); - if (msr == MSR_IA32_MCx_ADDR(bank)) + if (msr == msr_ops.addr(bank)) return offsetof(struct mce, addr); - if (msr == MSR_IA32_MCx_MISC(bank)) + if (msr == msr_ops.misc(bank)) return offsetof(struct mce, misc); if (msr == MSR_IA32_MCG_STATUS) return offsetof(struct mce, mcgstatus); @@ -523,9 +567,9 @@ static struct notifier_block mce_srao_nb = { static void mce_read_aux(struct mce *m, int i) { if (m->status & MCI_STATUS_MISCV) - m->misc = mce_rdmsrl(MSR_IA32_MCx_MISC(i)); + m->misc = mce_rdmsrl(msr_ops.misc(i)); if (m->status & MCI_STATUS_ADDRV) { - m->addr = mce_rdmsrl(MSR_IA32_MCx_ADDR(i)); + m->addr = mce_rdmsrl(msr_ops.addr(i)); /* * Mask the reported address by the reported granularity. @@ -607,7 +651,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) m.tsc = 0; barrier(); - m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m.status = mce_rdmsrl(msr_ops.status(i)); if (!(m.status & MCI_STATUS_VAL)) continue; @@ -654,7 +698,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) /* * Clear state for this bank. */ - mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + mce_wrmsrl(msr_ops.status(i), 0); } /* @@ -679,7 +723,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, char *tmp; for (i = 0; i < mca_cfg.banks; i++) { - m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m->status = mce_rdmsrl(msr_ops.status(i)); if (m->status & MCI_STATUS_VAL) { __set_bit(i, validp); if (quirk_no_way_out) @@ -830,9 +874,9 @@ static int mce_start(int *no_way_out) atomic_add(*no_way_out, &global_nwo); /* - * global_nwo should be updated before mce_callin + * Rely on the implied barrier below, such that global_nwo + * is updated before mce_callin. */ - smp_wmb(); order = atomic_inc_return(&mce_callin); /* @@ -957,7 +1001,7 @@ static void mce_clear_state(unsigned long *toclear) for (i = 0; i < mca_cfg.banks; i++) { if (test_bit(i, toclear)) - mce_wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + mce_wrmsrl(msr_ops.status(i), 0); } } @@ -994,11 +1038,12 @@ void do_machine_check(struct pt_regs *regs, long error_code) int i; int worst = 0; int severity; + /* * Establish sequential order between the CPUs entering the machine * check handler. */ - int order; + int order = -1; /* * If no_way_out gets set, there is no safe way to recover from this * MCE. If mca_cfg.tolerant is cranked up, we'll try anyway. @@ -1012,7 +1057,12 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - int lmce = 0; + + /* + * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES + * on Intel. + */ + int lmce = 1; /* If this CPU is offline, just bail out. */ if (cpu_is_offline(smp_processor_id())) { @@ -1051,19 +1101,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) kill_it = 1; /* - * Check if this MCE is signaled to only this logical processor + * Check if this MCE is signaled to only this logical processor, + * on Intel only. */ - if (m.mcgstatus & MCG_STATUS_LMCES) - lmce = 1; - else { - /* - * Go through all the banks in exclusion of the other CPUs. - * This way we don't report duplicated events on shared banks - * because the first one to see it will clear it. - * If this is a Local MCE, then no need to perform rendezvous. - */ + if (m.cpuvendor == X86_VENDOR_INTEL) + lmce = m.mcgstatus & MCG_STATUS_LMCES; + + /* + * Go through all banks in exclusion of the other CPUs. This way we + * don't report duplicated events on shared banks because the first one + * to see it will clear it. If this is a Local MCE, then no need to + * perform rendezvous. + */ + if (!lmce) order = mce_start(&no_way_out); - } for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); @@ -1076,7 +1127,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) m.addr = 0; m.bank = i; - m.status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i)); + m.status = mce_rdmsrl(msr_ops.status(i)); if ((m.status & MCI_STATUS_VAL) == 0) continue; @@ -1420,7 +1471,6 @@ static void __mcheck_cpu_init_generic(void) enum mcp_flags m_fl = 0; mce_banks_t all_banks; u64 cap; - int i; if (!mca_cfg.bootlog) m_fl = MCP_DONTLOG; @@ -1436,14 +1486,19 @@ static void __mcheck_cpu_init_generic(void) rdmsrl(MSR_IA32_MCG_CAP, cap); if (cap & MCG_CTL_P) wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); +} + +static void __mcheck_cpu_init_clear_banks(void) +{ + int i; for (i = 0; i < mca_cfg.banks; i++) { struct mce_bank *b = &mce_banks[i]; if (!b->init) continue; - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); - wrmsrl(MSR_IA32_MCx_STATUS(i), 0); + wrmsrl(msr_ops.ctl(i), b->ctl); + wrmsrl(msr_ops.status(i), 0); } } @@ -1495,7 +1550,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 <= 17 && cfg->bootlog < 0) { + if (c->x86 < 17 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: @@ -1628,11 +1683,19 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) break; case X86_VENDOR_AMD: { - u32 ebx = cpuid_ebx(0x80000007); + mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); + mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); + mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); - mce_flags.overflow_recov = !!(ebx & BIT(0)); - mce_flags.succor = !!(ebx & BIT(1)); - mce_flags.smca = !!(ebx & BIT(3)); + /* + * Install proper ops for Scalable MCA enabled processors + */ + if (mce_flags.smca) { + msr_ops.ctl = smca_ctl_reg; + msr_ops.status = smca_status_reg; + msr_ops.addr = smca_addr_reg; + msr_ops.misc = smca_misc_reg; + } mce_amd_feature_init(c); break; @@ -1717,6 +1780,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); + __mcheck_cpu_init_clear_banks(); __mcheck_cpu_init_timer(); } @@ -2082,7 +2146,7 @@ static void mce_disable_error_reporting(void) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), 0); + wrmsrl(msr_ops.ctl(i), 0); } return; } @@ -2121,6 +2185,7 @@ static void mce_syscore_resume(void) { __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info)); + __mcheck_cpu_init_clear_banks(); } static struct syscore_ops mce_syscore_ops = { @@ -2138,6 +2203,7 @@ static void mce_cpu_restart(void *data) if (!mce_available(raw_cpu_ptr(&cpu_info))) return; __mcheck_cpu_init_generic(); + __mcheck_cpu_init_clear_banks(); __mcheck_cpu_init_timer(); } @@ -2413,7 +2479,7 @@ static void mce_reenable_cpu(void *h) struct mce_bank *b = &mce_banks[i]; if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl); + wrmsrl(msr_ops.ctl(i), b->ctl); } } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 9d656fd436ef..10b0661651e0 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -54,14 +54,6 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 -/* - * OS is required to set the MCAX bit to acknowledge that it is now using the - * new MSR ranges and new registers under each bank. It also means that the OS - * will configure deferred errors in the new MCx_CONFIG register. If the bit is - * not set, uncorrectable errors will cause a system panic. - */ -#define SMCA_MCAX_EN_OFF 0x1 - static const char * const th_names[] = { "load_store", "insn_fetch", @@ -333,7 +325,7 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high, /* Fall back to method we used for older processors: */ switch (block) { case 0: - addr = MSR_IA32_MCx_MISC(bank); + addr = msr_ops.misc(bank); break; case 1: offset = ((low & MASK_BLKPTR_LO) >> 21); @@ -351,6 +343,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); + u32 smca_low, smca_high, smca_addr; struct threshold_block b; int new; @@ -369,24 +362,49 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, b.interrupt_enable = 1; - if (mce_flags.smca) { - u32 smca_low, smca_high; - u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); + if (!mce_flags.smca) { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + goto set_offset; + } - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - smca_high |= SMCA_MCAX_EN_OFF; - wrmsr(smca_addr, smca_low, smca_high); - } + smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - /* Gather LVT offset for thresholding: */ - if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) - goto out; + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + smca_high |= BIT(0); - new = (smca_low & SMCA_THR_LVT_OFF) >> 12; - } else { - new = (misc_high & MASK_LVTOFF_HI) >> 20; + /* + * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} + * registers with the option of additionally logging to + * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. + * + * This bit is usually set by BIOS to retain the old behavior + * for OSes that don't use the new registers. Linux supports the + * new registers so let's disable that additional logging here. + * + * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high + * portion of the MSR). + */ + smca_high &= ~BIT(2); + + wrmsr(smca_addr, smca_low, smca_high); } + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + +set_offset: offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) @@ -430,12 +448,23 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +static void +__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) { + u32 msr_status = msr_ops.status(bank); + u32 msr_addr = msr_ops.addr(bank); struct mce m; u64 status; - rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + WARN_ON_ONCE(deferred_err && threshold_err); + + if (deferred_err && mce_flags.smca) { + msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); + msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); + } + + rdmsrl(msr_status, status); + if (!(status & MCI_STATUS_VAL)) return; @@ -448,10 +477,11 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc) m.misc = misc; if (m.status & MCI_STATUS_ADDRV) - rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr); + rdmsrl(msr_addr, m.addr); mce_log(&m); - wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); + + wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -479,17 +509,21 @@ asmlinkage __visible void smp_trace_deferred_error_interrupt(void) /* APIC interrupt handler for deferred errors */ static void amd_deferred_error_interrupt(void) { - u64 status; unsigned int bank; + u32 msr_status; + u64 status; for (bank = 0; bank < mca_cfg.banks; ++bank) { - rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) + : msr_ops.status(bank); + + rdmsrl(msr_status, status); if (!(status & MCI_STATUS_VAL) || !(status & MCI_STATUS_DEFERRED)) continue; - __log_error(bank, false, 0); + __log_error(bank, true, false, 0); break; } } @@ -544,7 +578,7 @@ static void amd_threshold_interrupt(void) return; log: - __log_error(bank, true, ((u64)high << 32) | low); + __log_error(bank, false, true, ((u64)high << 32) | low); } /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index ab0adc0fa5db..a9b31eb815f2 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -535,6 +535,15 @@ static void native_machine_emergency_restart(void) mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0; *((unsigned short *)__va(0x472)) = mode; + /* + * If an EFI capsule has been registered with the firmware then + * override the reboot= parameter. + */ + if (efi_capsule_pending(NULL)) { + pr_info("EFI capsule is pending, forcing EFI reboot.\n"); + reboot_type = BOOT_EFI; + } + for (;;) { /* Could also try the reset bit in the Hammer NB */ switch (reboot_type) { diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 548ddf7d6fd2..3e84ef16f657 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -248,18 +248,17 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (config_enabled(CONFIG_X86_64)) sp -= 128; - if (!onsigstack) { - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (current->sas_ss_size) - sp = current->sas_ss_sp + current->sas_ss_size; - } else if (config_enabled(CONFIG_X86_32) && - (regs->ss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) { - /* This is the legacy signal stack switching. */ - sp = (unsigned long) ka->sa.sa_restorer; - } + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (sas_ss_flags(sp) == 0) + sp = current->sas_ss_sp + current->sas_ss_size; + } else if (config_enabled(CONFIG_X86_32) && + !onsigstack && + (regs->ss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + /* This is the legacy signal stack switching. */ + sp = (unsigned long) ka->sa.sa_restorer; } if (fpu->fpstate_active) { diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 5da924bbf0a0..623965e86b65 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -68,6 +68,21 @@ struct efifb_dmi_info efifb_dmi_list[] = { [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE } }; +void efifb_setup_from_dmi(struct screen_info *si, const char *opt) +{ + int i; + + for (i = 0; i < M_UNKNOWN; i++) { + if (efifb_dmi_list[i].base != 0 && + !strcmp(opt, efifb_dmi_list[i].optname)) { + si->lfb_base = efifb_dmi_list[i].base; + si->lfb_linelength = efifb_dmi_list[i].stride; + si->lfb_width = efifb_dmi_list[i].width; + si->lfb_height = efifb_dmi_list[i].height; + } + } +} + #define choose_value(dmivalue, fwvalue, field, flags) ({ \ typeof(fwvalue) _ret_ = fwvalue; \ if ((flags) & (field)) \ diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index bf4db6eaec8f..bd074151bfd6 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -578,7 +578,7 @@ static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs) riprel_post_xol(auprobe, regs); } -static struct uprobe_xol_ops default_xol_ops = { +static const struct uprobe_xol_ops default_xol_ops = { .pre_xol = default_pre_xol_op, .post_xol = default_post_xol_op, .abort = default_abort_op, @@ -695,7 +695,7 @@ static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn) 0, insn->immediate.nbytes); } -static struct uprobe_xol_ops branch_xol_ops = { +static const struct uprobe_xol_ops branch_xol_ops = { .emulate = branch_emulate_op, .post_xol = branch_post_xol_op, }; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0f6294376fbd..a2f24af3c999 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5110,13 +5110,17 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { + register void *__sp asm(_ASM_SP); ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; + if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; + asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), - [fastop]"+S"(fop) + [fastop]"+S"(fop), "+r"(__sp) : "c"(ctxt->src2.val)); + ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); if (!fop) /* exception is returned in fop variable */ return emulate_de(ctxt); diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S index be110efa0096..bf2c6074efd2 100644 --- a/arch/x86/lib/rwsem.S +++ b/arch/x86/lib/rwsem.S @@ -29,8 +29,10 @@ * there is contention on the semaphore. * * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax whish is either a return - * value or just clobbered.. + * registers (%eax, %edx and %ecx) except %eax which is either a return + * value or just gets clobbered. Same is true for %edx so make sure GCC + * reloads it after the slow path, by making it hold a temporary, for + * example see ____down_write(). */ #define save_common_regs \ @@ -106,6 +108,16 @@ ENTRY(call_rwsem_down_write_failed) ret ENDPROC(call_rwsem_down_write_failed) +ENTRY(call_rwsem_down_write_failed_killable) + FRAME_BEGIN + save_common_regs + movq %rax,%rdi + call rwsem_down_write_failed_killable + restore_common_regs + FRAME_END + ret +ENDPROC(call_rwsem_down_write_failed_killable) + ENTRY(call_rwsem_wake) FRAME_BEGIN /* do nothing if still outstanding active readers */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 01be9ec3bf79..a1f0e1d0ddc2 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1125,8 +1125,14 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr) static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, int primary) { - if (cpa->pgd) + if (cpa->pgd) { + /* + * Right now, we only execute this code path when mapping + * the EFI virtual memory map regions, no other users + * provide a ->pgd value. This may change in the future. + */ return populate_pgd(cpa, vaddr); + } /* * Ignore all non primary paths. diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 994a7df84a7b..f93545e7dc54 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -54,10 +54,6 @@ #include <asm/rtc.h> #include <asm/uv/uv.h> -#define EFI_DEBUG - -struct efi_memory_map memmap; - static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; @@ -119,11 +115,10 @@ void efi_get_time(struct timespec *now) void __init efi_find_mirror(void) { - void *p; + efi_memory_desc_t *md; u64 mirror_size = 0, total_size = 0; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; @@ -146,10 +141,9 @@ void __init efi_find_mirror(void) static void __init do_add_efi_memmap(void) { - void *p; + efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; int e820_type; @@ -209,47 +203,47 @@ int __init efi_memblock_x86_reserve_range(void) #else pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); #endif - memmap.phys_map = pmap; - memmap.nr_map = e->efi_memmap_size / + efi.memmap.phys_map = pmap; + efi.memmap.nr_map = e->efi_memmap_size / e->efi_memdesc_size; - memmap.desc_size = e->efi_memdesc_size; - memmap.desc_version = e->efi_memdesc_version; + efi.memmap.desc_size = e->efi_memdesc_size; + efi.memmap.desc_version = e->efi_memdesc_version; - memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); + WARN(efi.memmap.desc_version != 1, + "Unexpected EFI_MEMORY_DESCRIPTOR version %ld", + efi.memmap.desc_version); - efi.memmap = &memmap; + memblock_reserve(pmap, efi.memmap.nr_map * efi.memmap.desc_size); return 0; } void __init efi_print_memmap(void) { -#ifdef EFI_DEBUG efi_memory_desc_t *md; - void *p; - int i; + int i = 0; - for (p = memmap.map, i = 0; - p < memmap.map_end; - p += memmap.desc_size, i++) { + for_each_efi_memory_desc(md) { char buf[64]; - md = p; pr_info("mem%02u: %s range=[0x%016llx-0x%016llx] (%lluMB)\n", - i, efi_md_typeattr_format(buf, sizeof(buf), md), + i++, efi_md_typeattr_format(buf, sizeof(buf), md), md->phys_addr, md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1, (md->num_pages >> (20 - EFI_PAGE_SHIFT))); } -#endif /* EFI_DEBUG */ } void __init efi_unmap_memmap(void) { + unsigned long size; + clear_bit(EFI_MEMMAP, &efi.flags); - if (memmap.map) { - early_memunmap(memmap.map, memmap.nr_map * memmap.desc_size); - memmap.map = NULL; + + size = efi.memmap.nr_map * efi.memmap.desc_size; + if (efi.memmap.map) { + early_memunmap(efi.memmap.map, size); + efi.memmap.map = NULL; } } @@ -352,8 +346,6 @@ static int __init efi_systab_init(void *phys) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); - set_bit(EFI_SYSTEM_TABLES, &efi.flags); - return 0; } @@ -440,17 +432,22 @@ static int __init efi_runtime_init(void) static int __init efi_memmap_init(void) { + unsigned long addr, size; + if (efi_enabled(EFI_PARAVIRT)) return 0; /* Map the EFI memory map */ - memmap.map = early_memremap((unsigned long)memmap.phys_map, - memmap.nr_map * memmap.desc_size); - if (memmap.map == NULL) { + size = efi.memmap.nr_map * efi.memmap.desc_size; + addr = (unsigned long)efi.memmap.phys_map; + + efi.memmap.map = early_memremap(addr, size); + if (efi.memmap.map == NULL) { pr_err("Could not map the memory map!\n"); return -ENOMEM; } - memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size); + + efi.memmap.map_end = efi.memmap.map + size; if (add_efi_memmap) do_add_efi_memmap(); @@ -552,12 +549,9 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable) void __init runtime_code_page_mkexec(void) { efi_memory_desc_t *md; - void *p; /* Make EFI runtime service code area executable */ - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; - + for_each_efi_memory_desc(md) { if (md->type != EFI_RUNTIME_SERVICES_CODE) continue; @@ -604,12 +598,10 @@ void __init old_map_region(efi_memory_desc_t *md) /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { - void *p; efi_memory_desc_t *md, *prev_md = NULL; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + for_each_efi_memory_desc(md) { u64 prev_size; - md = p; if (!prev_md) { prev_md = md; @@ -651,30 +643,31 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) static void __init save_runtime_map(void) { #ifdef CONFIG_KEXEC_CORE + unsigned long desc_size; efi_memory_desc_t *md; - void *tmp, *p, *q = NULL; + void *tmp, *q = NULL; int count = 0; if (efi_enabled(EFI_OLD_MEMMAP)) return; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + desc_size = efi.memmap.desc_size; + for_each_efi_memory_desc(md) { if (!(md->attribute & EFI_MEMORY_RUNTIME) || (md->type == EFI_BOOT_SERVICES_CODE) || (md->type == EFI_BOOT_SERVICES_DATA)) continue; - tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL); + tmp = krealloc(q, (count + 1) * desc_size, GFP_KERNEL); if (!tmp) goto out; q = tmp; - memcpy(q + count * memmap.desc_size, md, memmap.desc_size); + memcpy(q + count * desc_size, md, desc_size); count++; } - efi_runtime_map_setup(q, count, memmap.desc_size); + efi_runtime_map_setup(q, count, desc_size); return; out: @@ -714,10 +707,10 @@ static inline void *efi_map_next_entry_reverse(void *entry) { /* Initial call */ if (!entry) - return memmap.map_end - memmap.desc_size; + return efi.memmap.map_end - efi.memmap.desc_size; - entry -= memmap.desc_size; - if (entry < memmap.map) + entry -= efi.memmap.desc_size; + if (entry < efi.memmap.map) return NULL; return entry; @@ -759,10 +752,10 @@ static void *efi_map_next_entry(void *entry) /* Initial call */ if (!entry) - return memmap.map; + return efi.memmap.map; - entry += memmap.desc_size; - if (entry >= memmap.map_end) + entry += efi.memmap.desc_size; + if (entry >= efi.memmap.map_end) return NULL; return entry; @@ -776,8 +769,11 @@ static void * __init efi_map_regions(int *count, int *pg_shift) { void *p, *new_memmap = NULL; unsigned long left = 0; + unsigned long desc_size; efi_memory_desc_t *md; + desc_size = efi.memmap.desc_size; + p = NULL; while ((p = efi_map_next_entry(p))) { md = p; @@ -792,7 +788,7 @@ static void * __init efi_map_regions(int *count, int *pg_shift) efi_map_region(md); get_systab_virt_addr(md); - if (left < memmap.desc_size) { + if (left < desc_size) { new_memmap = realloc_pages(new_memmap, *pg_shift); if (!new_memmap) return NULL; @@ -801,10 +797,9 @@ static void * __init efi_map_regions(int *count, int *pg_shift) (*pg_shift)++; } - memcpy(new_memmap + (*count * memmap.desc_size), md, - memmap.desc_size); + memcpy(new_memmap + (*count * desc_size), md, desc_size); - left -= memmap.desc_size; + left -= desc_size; (*count)++; } @@ -816,7 +811,6 @@ static void __init kexec_enter_virtual_mode(void) #ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; unsigned int num_pages; - void *p; efi.systab = NULL; @@ -840,8 +834,7 @@ static void __init kexec_enter_virtual_mode(void) * Map efi regions which were passed via setup_data. The virt_addr is a * fixed addr which was used in first kernel of a kexec boot. */ - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + for_each_efi_memory_desc(md) { efi_map_region_fixed(md); /* FIXME: add error handling */ get_systab_virt_addr(md); } @@ -850,10 +843,10 @@ static void __init kexec_enter_virtual_mode(void) BUG_ON(!efi.systab); - num_pages = ALIGN(memmap.nr_map * memmap.desc_size, PAGE_SIZE); + num_pages = ALIGN(efi.memmap.nr_map * efi.memmap.desc_size, PAGE_SIZE); num_pages >>= PAGE_SHIFT; - if (efi_setup_page_tables(memmap.phys_map, num_pages)) { + if (efi_setup_page_tables(efi.memmap.phys_map, num_pages)) { clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; } @@ -937,16 +930,16 @@ static void __init __efi_enter_virtual_mode(void) if (efi_is_native()) { status = phys_efi_set_virtual_address_map( - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, + efi.memmap.desc_size * count, + efi.memmap.desc_size, + efi.memmap.desc_version, (efi_memory_desc_t *)__pa(new_memmap)); } else { status = efi_thunk_set_virtual_address_map( efi_phys.set_virtual_address_map, - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, + efi.memmap.desc_size * count, + efi.memmap.desc_size, + efi.memmap.desc_version, (efi_memory_desc_t *)__pa(new_memmap)); } @@ -1011,13 +1004,11 @@ void __init efi_enter_virtual_mode(void) u32 efi_mem_type(unsigned long phys_addr) { efi_memory_desc_t *md; - void *p; if (!efi_enabled(EFI_MEMMAP)) return 0; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + for_each_efi_memory_desc(md) { if ((md->phys_addr <= phys_addr) && (phys_addr < (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT)))) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 49e4dd4a1f58..6e7242be1c87 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -55,14 +55,12 @@ struct efi_scratch efi_scratch; static void __init early_code_mapping_set_exec(int executable) { efi_memory_desc_t *md; - void *p; if (!(__supported_pte_mask & _PAGE_NX)) return; /* Make EFI service code area executable */ - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; + for_each_efi_memory_desc(md) { if (md->type == EFI_RUNTIME_SERVICES_CODE || md->type == EFI_BOOT_SERVICES_CODE) efi_set_executable(md, executable); @@ -253,7 +251,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) * Map all of RAM so that we can access arguments in the 1:1 * mapping when making EFI runtime calls. */ - for_each_efi_memory_desc(&memmap, md) { + for_each_efi_memory_desc(md) { if (md->type != EFI_CONVENTIONAL_MEMORY && md->type != EFI_LOADER_DATA && md->type != EFI_LOADER_CODE) @@ -398,7 +396,6 @@ void __init efi_runtime_update_mappings(void) unsigned long pfn; pgd_t *pgd = efi_pgd; efi_memory_desc_t *md; - void *p; if (efi_enabled(EFI_OLD_MEMMAP)) { if (__supported_pte_mask & _PAGE_NX) @@ -409,9 +406,8 @@ void __init efi_runtime_update_mappings(void) if (!efi_enabled(EFI_NX_PE_DATA)) return; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + for_each_efi_memory_desc(md) { unsigned long pf = 0; - md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) continue; diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index ab50ada1d56e..097cb09d917b 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -195,10 +195,9 @@ static bool can_free_region(u64 start, u64 size) */ void __init efi_reserve_boot_services(void) { - void *p; + efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; bool already_reserved; @@ -250,10 +249,9 @@ void __init efi_reserve_boot_services(void) void __init efi_free_boot_services(void) { - void *p; + efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; + for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index df280da34825..d957d5f21a86 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,4 +1,4 @@ -config AMD_MCE_INJ +config MCE_AMD_INJ tristate "Simple MCE injection interface for AMD processors" depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB default n diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile index dd2c98b84037..5f94546db280 100644 --- a/arch/x86/ras/Makefile +++ b/arch/x86/ras/Makefile @@ -1,2 +1,2 @@ -obj-$(CONFIG_AMD_MCE_INJ) += mce_amd_inj.o +obj-$(CONFIG_MCE_AMD_INJ) += mce_amd_inj.o diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c index 9e02dcaef683..e69f4701a076 100644 --- a/arch/x86/ras/mce_amd_inj.c +++ b/arch/x86/ras/mce_amd_inj.c @@ -290,14 +290,33 @@ static void do_inject(void) wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, (u32)mcg_status, (u32)(mcg_status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), - (u32)i_mce.status, (u32)(i_mce.status >> 32)); + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (inj_type == DFR_INT_INJ) { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DESTAT(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_DEADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + } + + wrmsr_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } else { + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), - (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); - wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), - (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + } toggle_hw_mce_inject(cpu, false); |