diff options
Diffstat (limited to 'arch')
164 files changed, 2002 insertions, 1322 deletions
diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts index 23fc670..5c21b23 100644 --- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts +++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f774101..ebe1d26 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -76,8 +76,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 4878d73..5730b87 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -95,8 +95,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x1000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index fb9e1bb..8af463f 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -65,8 +65,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 6e9820e..b89e6cf 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -70,8 +70,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 6ab3383..6522b04 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -68,8 +68,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; internal-regs { serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index 62175a8..d19f44c 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -64,8 +64,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index a5db177..853bd39 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -65,9 +65,9 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xd0000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x01, 0x2f) 0 0 0xf0000000 0x8000000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000 + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts index 2391b11..d17dab0 100644 --- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts +++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts @@ -78,8 +78,8 @@ soc { ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000 - MBUS_ID(0x09, 0x09) 0 0 0xf8100000 0x10000 - MBUS_ID(0x09, 0x05) 0 0 0xf8110000 0x10000>; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index c4d9175..f82aa44 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1500,6 +1500,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index d5525bf..9156fc3 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -491,7 +491,6 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif #ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); void set_kernel_text_rw(void); void set_kernel_text_ro(void); #else diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 7d0cba6f..139791e 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -176,13 +176,13 @@ static struct resource mem_res[] = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM }, { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM } }; @@ -851,7 +851,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) res->name = "System RAM"; res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index dda1959..08e49c4 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -506,18 +506,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm) struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); vcpu->arch.pause = false; - wake_up_interruptible(wq); + swake_up(wq); } } static void vcpu_sleep(struct kvm_vcpu *vcpu) { - wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); + struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); - wait_event_interruptible(*wq, ((!vcpu->arch.power_off) && + swait_event_interruptible(*wq, ((!vcpu->arch.power_off) && (!vcpu->arch.pause))); } diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index a9b3b90..c2b1315 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; - wait_queue_head_t *wq; + struct swait_queue_head *wq; unsigned long cpu_id; unsigned long context_id; phys_addr_t target_pc; @@ -119,7 +119,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) smp_mb(); /* Make sure the above is visible */ wq = kvm_arch_vcpu_wq(vcpu); - wake_up_interruptible(wq); + swake_up(wq); return PSCI_RET_SUCCESS; } diff --git a/arch/arm/mach-lpc32xx/phy3250.c b/arch/arm/mach-lpc32xx/phy3250.c index 77d6b1b..ee06fab 100644 --- a/arch/arm/mach-lpc32xx/phy3250.c +++ b/arch/arm/mach-lpc32xx/phy3250.c @@ -86,8 +86,8 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb) { dma_addr_t dma; - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, - PANEL_SIZE, &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, PANEL_SIZE, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { printk(KERN_ERR "CLCD: unable to map framebuffer\n"); return -ENOMEM; @@ -116,15 +116,14 @@ static int lpc32xx_clcd_setup(struct clcd_fb *fb) static int lpc32xx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } static void lpc32xx_clcd_remove(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } /* diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c index d122ee6..8814ee5 100644 --- a/arch/arm/mach-netx/fb.c +++ b/arch/arm/mach-netx/fb.c @@ -42,8 +42,8 @@ int netx_clcd_setup(struct clcd_fb *fb) fb->panel = netx_panel; - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, 1024*1024, - &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { printk(KERN_ERR "CLCD: unable to map framebuffer\n"); return -ENOMEM; @@ -57,16 +57,14 @@ int netx_clcd_setup(struct clcd_fb *fb) int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, - fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } void netx_clcd_remove(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL); diff --git a/arch/arm/mach-nspire/clcd.c b/arch/arm/mach-nspire/clcd.c index abea126..ea0e5b2 100644 --- a/arch/arm/mach-nspire/clcd.c +++ b/arch/arm/mach-nspire/clcd.c @@ -90,8 +90,8 @@ int nspire_clcd_setup(struct clcd_fb *fb) panel_size = ((panel->mode.xres * panel->mode.yres) * panel->bpp) / 8; panel_size = ALIGN(panel_size, PAGE_SIZE); - fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, - panel_size, &dma, GFP_KERNEL); + fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, panel_size, &dma, + GFP_KERNEL); if (!fb->fb.screen_base) { pr_err("CLCD: unable to map framebuffer\n"); @@ -107,13 +107,12 @@ int nspire_clcd_setup(struct clcd_fb *fb) int nspire_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) { - return dma_mmap_writecombine(&fb->dev->dev, vma, - fb->fb.screen_base, fb->fb.fix.smem_start, - fb->fb.fix.smem_len); + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); } void nspire_clcd_remove(struct clcd_fb *fb) { - dma_free_writecombine(&fb->dev->dev, fb->fb.fix.smem_len, - fb->fb.screen_base, fb->fb.fix.smem_start); + dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base, + fb->fb.fix.smem_start); } diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index e9f65fe..b6d62e4 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 76bce11..7c7a311 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm { * or idled. * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) #define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/plat-samsung/pm-check.c b/arch/arm/plat-samsung/pm-check.c index 04aff2c..70f2f69 100644 --- a/arch/arm/plat-samsung/pm-check.c +++ b/arch/arm/plat-samsung/pm-check.c @@ -53,8 +53,8 @@ static void s3c_pm_run_res(struct resource *ptr, run_fn_t fn, u32 *arg) if (ptr->child != NULL) s3c_pm_run_res(ptr->child, fn, arg); - if ((ptr->flags & IORESOURCE_MEM) && - strcmp(ptr->name, "System RAM") == 0) { + if ((ptr->flags & IORESOURCE_SYSTEM_RAM) + == IORESOURCE_SYSTEM_RAM) { S3C_PMDBG("Found system RAM at %08lx..%08lx\n", (unsigned long)ptr->start, (unsigned long)ptr->end); diff --git a/arch/arm/vdso/vdso.S b/arch/arm/vdso/vdso.S index b2b97e3..a62a7b6 100644 --- a/arch/arm/vdso/vdso.S +++ b/arch/arm/vdso/vdso.S @@ -23,9 +23,8 @@ #include <linux/const.h> #include <asm/page.h> - __PAGE_ALIGNED_DATA - .globl vdso_start, vdso_end + .section .data..ro_after_init .balign PAGE_SIZE vdso_start: .incbin "arch/arm/vdso/vdso.so" diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 7fc294c..22dda61 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -156,8 +156,4 @@ int set_memory_rw(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); -#endif - #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index f506086..819aff5 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -40,7 +40,7 @@ * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ -#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT - 1)) * sizeof(struct page), PUD_SIZE) +#define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) #ifndef CONFIG_KASAN #define VMALLOC_START (VA_START) @@ -52,7 +52,8 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) #define VMEMMAP_START (VMALLOC_END + SZ_64K) -#define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 8119479..450987d 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -73,13 +73,13 @@ static struct resource mem_res[] = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM }, { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM } }; @@ -210,7 +210,7 @@ static void __init request_standard_resources(void) res->name = "System RAM"; res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index e33fe33..fd10eb6 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -145,6 +145,10 @@ ENTRY(cpu_resume_mmu) ENDPROC(cpu_resume_mmu) .popsection cpu_resume_after_mmu: +#ifdef CONFIG_KASAN + mov x0, sp + bl kasan_unpoison_remaining_stack +#endif mov x0, #0 // return zero on success ldp x19, x20, [sp, #16] ldp x21, x22, [sp, #32] diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 82d607c..da30529 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -306,10 +306,6 @@ static __init int setup_hugepagesz(char *opt) hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); - } else if (ps == (PAGE_SIZE * CONT_PTES)) { - hugetlb_add_hstate(CONT_PTE_SHIFT); - } else if (ps == (PMD_SIZE * CONT_PMDS)) { - hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); return 0; @@ -317,13 +313,3 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); - -#ifdef CONFIG_ARM64_64K_PAGES -static __init int add_default_hugepagesz(void) -{ - if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) - hugetlb_add_hstate(CONT_PMD_SHIFT); - return 0; -} -arch_initcall(add_default_hugepagesz); -#endif diff --git a/arch/avr32/kernel/setup.c b/arch/avr32/kernel/setup.c index 209ae5a..e692889 100644 --- a/arch/avr32/kernel/setup.c +++ b/arch/avr32/kernel/setup.c @@ -49,13 +49,13 @@ static struct resource __initdata kernel_data = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM, + .flags = IORESOURCE_SYSTEM_RAM, }; static struct resource __initdata kernel_code = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM, + .flags = IORESOURCE_SYSTEM_RAM, .sibling = &kernel_data, }; @@ -134,7 +134,7 @@ add_physical_memory(resource_size_t start, resource_size_t end) new->start = start; new->end = end; new->name = "System RAM"; - new->flags = IORESOURCE_MEM; + new->flags = IORESOURCE_SYSTEM_RAM; *pprev = new; } diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index 72e17f7..786e36e 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -281,8 +281,6 @@ notrace void __init machine_init(unsigned long dt_ptr) */ set_ist(_vectors_start); - lockdep_init(); - /* * dtb is passed in from bootloader. * fdt is linked in blob. diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index caae3f4..300dac3 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -1178,7 +1178,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, efi_memory_desc_t *md; u64 efi_desc_size; char *name; - unsigned long flags; + unsigned long flags, desc; efi_map_start = __va(ia64_boot_param->efi_memmap); efi_map_end = efi_map_start + ia64_boot_param->efi_memmap_size; @@ -1193,6 +1193,8 @@ efi_initialize_iomem_resources(struct resource *code_resource, continue; flags = IORESOURCE_MEM | IORESOURCE_BUSY; + desc = IORES_DESC_NONE; + switch (md->type) { case EFI_MEMORY_MAPPED_IO: @@ -1207,14 +1209,17 @@ efi_initialize_iomem_resources(struct resource *code_resource, if (md->attribute & EFI_MEMORY_WP) { name = "System ROM"; flags |= IORESOURCE_READONLY; - } else if (md->attribute == EFI_MEMORY_UC) + } else if (md->attribute == EFI_MEMORY_UC) { name = "Uncached RAM"; - else + } else { name = "System RAM"; + flags |= IORESOURCE_SYSRAM; + } break; case EFI_ACPI_MEMORY_NVS: name = "ACPI Non-volatile Storage"; + desc = IORES_DESC_ACPI_NV_STORAGE; break; case EFI_UNUSABLE_MEMORY: @@ -1224,6 +1229,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, case EFI_PERSISTENT_MEMORY: name = "Persistent Memory"; + desc = IORES_DESC_PERSISTENT_MEMORY; break; case EFI_RESERVED_TYPE: @@ -1246,6 +1252,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, res->start = md->phys_addr; res->end = md->phys_addr + efi_md_size(md) - 1; res->flags = flags; + res->desc = desc; if (insert_resource(&iomem_resource, res) < 0) kfree(res); diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 4f118b0..2029a38 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -80,17 +80,17 @@ unsigned long vga_console_membase; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; unsigned long ia64_max_cacheline_size; diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index a5ecef7..136c69f 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -70,14 +70,14 @@ static struct resource data_resource = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; unsigned long memory_start; diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c index 89a2a93..f31ebb5 100644 --- a/arch/microblaze/kernel/setup.c +++ b/arch/microblaze/kernel/setup.c @@ -130,8 +130,6 @@ void __init machine_early_init(const char *cmdline, unsigned int ram, memset(__bss_start, 0, __bss_stop-__bss_start); memset(_ssbss, 0, _esbss-_ssbss); - lockdep_init(); - /* initialize device tree for usage in early_printk */ early_init_devtree(_fdt_start); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 74a3db9..d3da79d 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2169,7 +2169,7 @@ config MIPS_MT_SMP select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select MIPS_MT select SMP select SMP_UP @@ -2267,7 +2267,7 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2287,7 +2287,7 @@ config MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2306,6 +2306,7 @@ config MIPS_CPS_PM bool config MIPS_GIC_IPI + depends on MIPS_GIC bool config MIPS_CM diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c index 408799a..f752114 100644 --- a/arch/mips/boot/compressed/uart-16550.c +++ b/arch/mips/boot/compressed/uart-16550.c @@ -17,7 +17,7 @@ #define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset)) #endif -#ifdef CONFIG_MACH_JZ4740 +#if defined(CONFIG_MACH_JZ4740) || defined(CONFIG_MACH_JZ4780) #include <asm/mach-jz4740/base.h> #define PORT(offset) (CKSEG1ADDR(JZ4740_UART0_BASE_ADDR) + (4 * offset)) #endif diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 5fdaf8b..4f60734 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -732,21 +732,23 @@ static void __init resource_init(void) end = HIGHMEM_START - 1; res = alloc_bootmem(sizeof(struct resource)); + + res->start = start; + res->end = end; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + switch (boot_mem_map.map[i].type) { case BOOT_MEM_RAM: case BOOT_MEM_INIT_RAM: case BOOT_MEM_ROM_DATA: res->name = "System RAM"; + res->flags |= IORESOURCE_SYSRAM; break; case BOOT_MEM_RESERVED: default: res->name = "reserved"; } - res->start = start; - res->end = end; - - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); /* diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a..2b521e0 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -121,6 +121,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 3110447..70ef1a4 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -445,8 +445,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; - if (waitqueue_active(&dvcpu->wq)) - wake_up_interruptible(&dvcpu->wq); + if (swait_active(&dvcpu->wq)) + swake_up(&dvcpu->wq); return 0; } @@ -1174,8 +1174,8 @@ static void kvm_mips_comparecount_func(unsigned long data) kvm_mips_callbacks->queue_timer_int(vcpu); vcpu->arch.wait = 0; - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) + swake_up(&vcpu->wq); } /* low level hrtimer wake routine */ diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h index 3d0e17b..df0f52b 100644 --- a/arch/parisc/include/asm/cache.h +++ b/arch/parisc/include/asm/cache.h @@ -22,6 +22,9 @@ #define __read_mostly __attribute__((__section__(".data..read_mostly"))) +/* Read-only memory is marked before mark_rodata_ro() is called. */ +#define __ro_after_init __read_mostly + void parisc_cache_init(void); /* initializes cache-flushing */ void disable_sr_hashing_asm(int); /* low level support for above */ void disable_sr_hashing(void); /* turns off space register hashing */ diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index 845272c..7bd69bd 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -121,10 +121,6 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma } } -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); -#endif - #include <asm/kmap_types.h> #define ARCH_HAS_KMAP diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 1b366c4..3c07d6b 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -55,12 +55,12 @@ signed char pfnnid_map[PFNNID_MAP_MAX] __read_mostly; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource pdcdata_resource = { @@ -201,7 +201,7 @@ static void __init setup_bootmem(void) res->name = "System RAM"; res->start = pmem_ranges[i].start_pfn << PAGE_SHIFT; res->end = res->start + (pmem_ranges[i].pages << PAGE_SHIFT)-1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); } diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 9d08d8c..c98afa5 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -289,7 +289,7 @@ struct kvmppc_vcore { struct list_head runnable_threads; struct list_head preempt_list; spinlock_t lock; - wait_queue_head_t wq; + struct swait_queue_head wq; spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; @@ -629,7 +629,7 @@ struct kvm_vcpu_arch { u8 prodded; u32 last_inst; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; struct kvmppc_vcore *vcore; int ret; int trap; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index ad8c9db..d544fa3 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -114,8 +114,6 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { - lockdep_init(); - /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 5c03a6a..f98be83 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -255,9 +255,6 @@ void __init early_setup(unsigned long dt_ptr) setup_paca(&boot_paca); fixup_boot_paca(); - /* Initialize lockdep early or else spinlocks will blow */ - lockdep_init(); - /* -------- printk is now safe to use ------- */ /* Enable early debugging if any specified (see udbg.h) */ diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index baeddb0..f1187bb 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -114,11 +114,11 @@ static bool kvmppc_ipi_thread(int cpu) static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int cpu; - wait_queue_head_t *wqp; + struct swait_queue_head *wqp; wqp = kvm_arch_vcpu_wq(vcpu); - if (waitqueue_active(wqp)) { - wake_up_interruptible(wqp); + if (swait_active(wqp)) { + swake_up(wqp); ++vcpu->stat.halt_wakeup; } @@ -701,8 +701,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) tvcpu->arch.prodded = 1; smp_mb(); if (vcpu->arch.ceded) { - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); + if (swait_active(&vcpu->wq)) { + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } @@ -1459,7 +1459,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core) INIT_LIST_HEAD(&vcore->runnable_threads); spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_waitqueue_head(&vcore->wq); + init_swait_queue_head(&vcore->wq); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = core * threads_per_subcore; @@ -2531,10 +2531,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) { struct kvm_vcpu *vcpu; int do_sleep = 1; + DECLARE_SWAITQUEUE(wait); - DEFINE_WAIT(wait); - - prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE); /* * Check one last time for pending exceptions and ceded state after @@ -2548,7 +2547,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } if (!do_sleep) { - finish_wait(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); return; } @@ -2556,7 +2555,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); schedule(); - finish_wait(&vc->wq, &wait); + finish_swait(&vc->wq, &wait); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); @@ -2612,7 +2611,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - wake_up(&vc->wq); + swake_up(&vc->wq); } } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 6ee26de..25ae2c9 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index d0f0a51..f078a1f 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -541,7 +541,7 @@ static int __init add_system_ram_resources(void) res->name = "System RAM"; res->start = base; res->end = base + size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; WARN_ON(request_resource(&iomem_resource, res) < 0); } } diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 8959ebb..b0c8ad0 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -467,7 +467,7 @@ struct kvm_s390_irq_payload { struct kvm_s390_local_interrupt { spinlock_t lock; struct kvm_s390_float_interrupt *float_int; - wait_queue_head_t *wq; + struct swait_queue_head *wq; atomic_t *cpuflags; DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS); struct kvm_s390_irq_payload irq; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93e..e485817 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,25 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + if (mm->context.asce_limit == 0) { + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_bits = _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + mm->context.asce_limit = STACK_TOP_MAX; + } else if (mm->context.asce_limit == (1UL << 31)) { + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -111,8 +119,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f..d7cc79f 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index c55576b..a0684de 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -448,7 +448,6 @@ void __init startup_init(void) rescue_initrd(); clear_bss_section(); init_kernel_storage_key(); - lockdep_init(); lockdep_off(); setup_lowcore_early(); setup_facility_list(); diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index c5febe8..03c2b46 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ __HEAD ENTRY(startup_continue) - tm __LC_STFLE_FAC_LIST+6,0x80 # LPP available ? + tm __LC_STFLE_FAC_LIST+5,0x80 # LPP available ? jz 0f xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid mvi __LC_LPP,0x80 # and set LPP_MAGIC diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 9220db5..cedb019 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -374,17 +374,17 @@ static void __init setup_lowcore(void) static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource __initdata *standard_resources[] = { @@ -408,7 +408,7 @@ static void __init setup_resources(void) for_each_memblock(memory, reg) { res = alloc_bootmem_low(sizeof(*res)); - res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; res->name = "System RAM"; res->start = reg->base; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index f88ca72..9ffc732 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -966,13 +966,13 @@ no_timer: void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu) { - if (waitqueue_active(&vcpu->wq)) { + if (swait_active(&vcpu->wq)) { /* * The vcpu gave up the cpu voluntarily, mark it as a good * yield-candidate. */ vcpu->preempted = true; - wake_up_interruptible(&vcpu->wq); + swake_up(&vcpu->wq); vcpu->stat.halt_wakeup++; } } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 4af21c7..03dfe9c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2381,7 +2381,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) /* manually convert vector registers if necessary */ if (MACHINE_HAS_VX) { - convert_vx_to_fp(fprs, current->thread.fpu.vxrs); + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, fprs, 128); } else { diff --git a/arch/score/kernel/setup.c b/arch/score/kernel/setup.c index b48459a..f3a0649 100644 --- a/arch/score/kernel/setup.c +++ b/arch/score/kernel/setup.c @@ -101,7 +101,7 @@ static void __init resource_init(void) res->name = "System RAM"; res->start = MEMORY_START; res->end = MEMORY_START + MEMORY_SIZE - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); request_resource(res, &code_resource); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index de19cfa..3f1c18b 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -78,17 +78,17 @@ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0, }; static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, }; unsigned long memory_start; @@ -202,7 +202,7 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn, res->name = "System RAM"; res->start = start; res->end = end - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; if (request_resource(&iomem_resource, res)) { pr_err("unable to request memory_resource 0x%lx 0x%lx\n", diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index f2d30ca..cd1f592 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -696,14 +696,6 @@ tlb_fixup_done: call __bzero sub %o1, %o0, %o1 -#ifdef CONFIG_LOCKDEP - /* We have this call this super early, as even prom_init can grab - * spinlocks and thus call into the lockdep code. - */ - call lockdep_init - nop -#endif - call prom_init mov %l7, %o0 ! OpenPROM cif handler diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 6f21685..1cfe6aa 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2863,17 +2863,17 @@ void hugetlb_setup(struct pt_regs *regs) static struct resource code_resource = { .name = "Kernel code", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource data_resource = { .name = "Kernel data", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource bss_resource = { .name = "Kernel bss", - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static inline resource_size_t compute_kern_paddr(void *addr) @@ -2909,7 +2909,7 @@ static int __init report_memory(void) res->name = "System RAM"; res->start = pavail[i].phys_addr; res->end = pavail[i].phys_addr + pavail[i].reg_size - 1; - res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; if (insert_resource(&iomem_resource, res) < 0) { pr_warn("Resource insertion failed.\n"); diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index bbb855d..a992238 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -1632,14 +1632,14 @@ static struct resource data_resource = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; /* @@ -1673,10 +1673,15 @@ insert_ram_resource(u64 start_pfn, u64 end_pfn, bool reserved) kzalloc(sizeof(struct resource), GFP_ATOMIC); if (!res) return NULL; - res->name = reserved ? "Reserved" : "System RAM"; res->start = start_pfn << PAGE_SHIFT; res->end = (end_pfn << PAGE_SHIFT) - 1; res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + if (reserved) { + res->name = "Reserved"; + } else { + res->name = "System RAM"; + res->flags |= IORESOURCE_SYSRAM; + } if (insert_resource(&iomem_resource, res)) { kfree(res); return NULL; diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index 3fa317f..c2bffa5 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -72,13 +72,13 @@ static struct resource mem_res[] = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM }, { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_MEM + .flags = IORESOURCE_SYSTEM_RAM } }; @@ -211,7 +211,7 @@ request_standard_resources(struct meminfo *mi) res->name = "System RAM"; res->start = mi->bank[i].start; res->end = mi->bank[i].start + mi->bank[i].size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; request_resource(&iomem_resource, res); diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 1538562..eb3abf8 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -1,6 +1,7 @@ - obj-y += entry/ +obj-$(CONFIG_PERF_EVENTS) += events/ + obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c46662f..b105105 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -303,6 +303,9 @@ config ARCH_SUPPORTS_UPROBES config FIX_EARLYCON_MEM def_bool y +config DEBUG_RODATA + def_bool y + config PGTABLE_LEVELS int default 4 if X86_64 diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 68a2d1f..67eec55 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -74,28 +74,16 @@ config EFI_PGT_DUMP issues with the mapping of the EFI runtime regions into that table. -config DEBUG_RODATA - bool "Write protect kernel read-only data structures" - default y - depends on DEBUG_KERNEL - ---help--- - Mark the kernel read-only data as write-protected in the pagetables, - in order to catch accidental (and incorrect) writes to such const - data. This is recommended so that we can catch kernel bugs sooner. - If in doubt, say "Y". - config DEBUG_RODATA_TEST - bool "Testcase for the DEBUG_RODATA feature" - depends on DEBUG_RODATA + bool "Testcase for the marking rodata read-only" default y ---help--- - This option enables a testcase for the DEBUG_RODATA - feature as well as for the change_page_attr() infrastructure. + This option enables a testcase for the setting rodata read-only + as well as for the change_page_attr() infrastructure. If in doubt, say "N" config DEBUG_WX bool "Warn on W+X mappings at boot" - depends on DEBUG_RODATA select X86_PTDUMP_CORE ---help--- Generate a warning if any W+X mappings are found at boot. diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h index abe961c..63a03bb 100644 --- a/arch/x86/entry/vdso/vdso2c.h +++ b/arch/x86/entry/vdso/vdso2c.h @@ -140,7 +140,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len, fprintf(outfile, "#include <asm/vdso.h>\n"); fprintf(outfile, "\n"); fprintf(outfile, - "static unsigned char raw_data[%lu] __page_aligned_data = {", + "static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {", mapping_size); for (j = 0; j < stripped_len; j++) { if (j % 10 == 0) diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile new file mode 100644 index 0000000..fdfea15 --- /dev/null +++ b/arch/x86/events/Makefile @@ -0,0 +1,13 @@ +obj-y += core.o + +obj-$(CONFIG_CPU_SUP_AMD) += amd/core.o amd/uncore.o +obj-$(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 diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/events/amd/core.c index 5861053..049ada8d 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/events/amd/core.c @@ -5,7 +5,7 @@ #include <linux/slab.h> #include <asm/apicdef.h> -#include "perf_event.h" +#include "../perf_event.h" static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/events/amd/ibs.c index 989d3c2..51087c2 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -14,7 +14,7 @@ #include <asm/apic.h> -#include "perf_event.h" +#include "../perf_event.h" static u32 ibs_caps; @@ -670,7 +670,7 @@ static __init int perf_event_ibs_init(void) perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs"); - printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps); + pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps); return 0; } @@ -774,14 +774,14 @@ static int setup_ibs_ctl(int ibs_eilvt_off) pci_read_config_dword(cpu_cfg, IBSCTL, &value); if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) { pci_dev_put(cpu_cfg); - printk(KERN_DEBUG "Failed to setup IBS LVT offset, " - "IBSCTL = 0x%08x\n", value); + pr_debug("Failed to setup IBS LVT offset, IBSCTL = 0x%08x\n", + value); return -EINVAL; } } while (1); if (!nodes) { - printk(KERN_DEBUG "No CPU node configured for IBS\n"); + pr_debug("No CPU node configured for IBS\n"); return -ENODEV; } @@ -810,7 +810,7 @@ static void force_ibs_eilvt_setup(void) preempt_enable(); if (offset == APIC_EILVT_NR_MAX) { - printk(KERN_DEBUG "No EILVT entry available\n"); + pr_debug("No EILVT entry available\n"); return; } diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/events/amd/iommu.c index 97242a9..635e5eb 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -16,8 +16,8 @@ #include <linux/cpumask.h> #include <linux/slab.h> -#include "perf_event.h" -#include "perf_event_amd_iommu.h" +#include "../perf_event.h" +#include "iommu.h" #define COUNTER_SHIFT 16 diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.h b/arch/x86/events/amd/iommu.h index 845d173..845d173 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_iommu.h +++ b/arch/x86/events/amd/iommu.h diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/events/amd/uncore.c index 8836fc9..3db9569 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -538,7 +538,7 @@ static int __init amd_uncore_init(void) if (ret) goto fail_nb; - printk(KERN_INFO "perf: AMD NB counters detected\n"); + pr_info("perf: AMD NB counters detected\n"); ret = 0; } @@ -552,7 +552,7 @@ static int __init amd_uncore_init(void) if (ret) goto fail_l2; - printk(KERN_INFO "perf: AMD L2I counters detected\n"); + pr_info("perf: AMD L2I counters detected\n"); ret = 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/events/core.c index 1b443db..5e830d0 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/events/core.c @@ -254,15 +254,16 @@ static bool check_hw_exists(void) * We still allow the PMU driver to operate: */ if (bios_fail) { - printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); - printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); + pr_cont("Broken BIOS detected, complain to your hardware vendor.\n"); + pr_err(FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", + reg_fail, val_fail); } return true; msr_fail: - printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n"); - printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + pr_cont("Broken PMU hardware detected, using software events only.\n"); + pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -596,6 +597,19 @@ void x86_pmu_disable_all(void) } } +/* + * There may be PMI landing after enabled=0. The PMI hitting could be before or + * after disable_all. + * + * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. + * It will not be re-enabled in the NMI handler again, because enabled=0. After + * handling the NMI, disable_all will be called, which will not change the + * state either. If PMI hits after disable_all, the PMU is already disabled + * before entering NMI handler. The NMI handler will not change the state + * either. + * + * So either situation is harmless. + */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/events/intel/bts.c index 2cad71d..b99dc92 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/arch/x86/events/intel/bts.c @@ -26,7 +26,7 @@ #include <asm-generic/sizes.h> #include <asm/perf_event.h> -#include "perf_event.h" +#include "../perf_event.h" struct bts_ctx { struct perf_output_handle handle; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/events/intel/core.c index fed2ab1..68fa55b 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/events/intel/core.c @@ -18,7 +18,7 @@ #include <asm/hardirq.h> #include <asm/apic.h> -#include "perf_event.h" +#include "../perf_event.h" /* * Intel PerfMon, used on Core and later. @@ -1502,7 +1502,15 @@ static __initconst const u64 knl_hw_cache_extra_regs }; /* - * Use from PMIs where the LBRs are already disabled. + * Used from PMIs where the LBRs are already disabled. + * + * This function could be called consecutively. It is required to remain in + * disabled state if called consecutively. + * + * During consecutive calls, the same disable value will be written to related + * registers, so the PMU state remains unchanged. hw.state in + * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive + * calls. */ static void __intel_pmu_disable_all(void) { @@ -1884,6 +1892,16 @@ again: if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); + /* + * There are cases where, even though, the PEBS ovfl bit is set + * in GLOBAL_OVF_STATUS, the PEBS events may also have their + * overflow bits set for their counters. We must clear them + * here because they have been processed as exact samples in + * the drain_pebs() routine. They must not be processed again + * in the for_each_bit_set() loop for regular samples below. + */ + status &= ~cpuc->pebs_enabled; + status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } /* @@ -1929,7 +1947,10 @@ again: goto again; done: - __intel_pmu_enable_all(0, true); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + __intel_pmu_enable_all(0, true); + /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -3396,6 +3417,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); pr_cont("Nehalem events, "); @@ -3459,6 +3481,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); pr_cont("Westmere events, "); break; @@ -3581,7 +3604,7 @@ __init int intel_pmu_init(void) intel_pmu_lbr_init_hsw(); x86_pmu.event_constraints = intel_bdw_event_constraints; - x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.pebs_constraints = intel_bdw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; x86_pmu.pebs_prec_dist = true; diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/events/intel/cqm.c index a316ca9..93cb412 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -7,7 +7,7 @@ #include <linux/perf_event.h> #include <linux/slab.h> #include <asm/cpu_device_id.h> -#include "perf_event.h" +#include "../perf_event.h" #define MSR_IA32_PQR_ASSOC 0x0c8f #define MSR_IA32_QM_CTR 0x0c8e @@ -1244,15 +1244,12 @@ static struct pmu intel_cqm_pmu = { static inline void cqm_pick_event_reader(int cpu) { - int phys_id = topology_physical_package_id(cpu); - int i; + int reader; - for_each_cpu(i, &cqm_cpumask) { - if (phys_id == topology_physical_package_id(i)) - return; /* already got reader for this socket */ - } - - cpumask_set_cpu(cpu, &cqm_cpumask); + /* First online cpu in package becomes the reader */ + reader = cpumask_any_and(&cqm_cpumask, topology_core_cpumask(cpu)); + if (reader >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cqm_cpumask); } static void intel_cqm_cpu_starting(unsigned int cpu) @@ -1270,24 +1267,17 @@ static void intel_cqm_cpu_starting(unsigned int cpu) static void intel_cqm_cpu_exit(unsigned int cpu) { - int phys_id = topology_physical_package_id(cpu); - int i; + int target; - /* - * Is @cpu a designated cqm reader? - */ + /* Is @cpu the current cqm reader for this package ? */ if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask)) return; - for_each_online_cpu(i) { - if (i == cpu) - continue; + /* Find another online reader in this package */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - if (phys_id == topology_physical_package_id(i)) { - cpumask_set_cpu(i, &cqm_cpumask); - break; - } - } + if (target < nr_cpu_ids) + cpumask_set_cpu(target, &cqm_cpumask); } static int intel_cqm_cpu_notifier(struct notifier_block *nb, diff --git a/arch/x86/kernel/cpu/perf_event_intel_cstate.c b/arch/x86/events/intel/cstate.c index 75a38b5..7946c42 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -89,7 +89,7 @@ #include <linux/slab.h> #include <linux/perf_event.h> #include <asm/cpu_device_id.h> -#include "perf_event.h" +#include "../perf_event.h" #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/events/intel/ds.c index 10602f0..ce7211a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/events/intel/ds.c @@ -5,7 +5,7 @@ #include <asm/perf_event.h> #include <asm/insn.h> -#include "perf_event.h" +#include "../perf_event.h" /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 @@ -51,7 +51,8 @@ union intel_x86_pebs_dse { #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) -static const u64 pebs_data_source[] = { +/* Version for Sandy Bridge and later */ +static u64 pebs_data_source[] = { P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = { OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ }; +/* Patch up minor differences in the bits */ +void __init intel_pmu_pebs_data_source_nhm(void) +{ + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); + buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu) per_cpu(insn_buffer, cpu) = ibuffer; } - max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; ds->pebs_index = ds->pebs_buffer_base; @@ -722,6 +731,30 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_bdw_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ + INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), + EVENT_CONSTRAINT_END +}; + + struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ @@ -1319,19 +1352,28 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; int format = x86_pmu.intel_cap.pebs_format; switch (format) { case 0: - printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); + pr_cont("PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + /* + * Using >PAGE_SIZE buffers makes the WRMSR to + * PERF_GLOBAL_CTRL in intel_pmu_enable_all() + * mysteriously hang on Core2. + * + * As a workaround, we don't do this. + */ + x86_pmu.pebs_buffer_size = PAGE_SIZE; x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; break; case 1: - printk(KERN_CONT "PEBS fmt1%c, ", pebs_type); + pr_cont("PEBS fmt1%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm); x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; @@ -1351,7 +1393,7 @@ void __init intel_ds_init(void) break; default: - printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); + pr_cont("no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; } } diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/events/intel/knc.c index 5b0c232..548d5f7 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/events/intel/knc.c @@ -5,7 +5,7 @@ #include <asm/hardirq.h> -#include "perf_event.h" +#include "../perf_event.h" static const u64 knc_perfmon_event_map[] = { @@ -263,7 +263,9 @@ again: goto again; done: - knc_pmu_enable_all(0); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + knc_pmu_enable_all(0); return handled; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/events/intel/lbr.c index 653f88d..69dd118 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -5,7 +5,7 @@ #include <asm/msr.h> #include <asm/insn.h> -#include "perf_event.h" +#include "../perf_event.h" enum { LBR_FORMAT_32 = 0x00, diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/events/intel/p4.c index f2e5678..0a5ede1 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/events/intel/p4.c @@ -13,7 +13,7 @@ #include <asm/hardirq.h> #include <asm/apic.h> -#include "perf_event.h" +#include "../perf_event.h" #define P4_CNTR_LIMIT 3 /* diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/events/intel/p6.c index 7c1a0c0..1f5c47a 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/events/intel/p6.c @@ -1,7 +1,7 @@ #include <linux/perf_event.h> #include <linux/types.h> -#include "perf_event.h" +#include "../perf_event.h" /* * Not sure about some of these diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/events/intel/pt.c index c0bbd10..6af7cf7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/events/intel/pt.c @@ -29,8 +29,8 @@ #include <asm/io.h> #include <asm/intel_pt.h> -#include "perf_event.h" -#include "intel_pt.h" +#include "../perf_event.h" +#include "pt.h" static DEFINE_PER_CPU(struct pt, pt_ctx); diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/events/intel/pt.h index 336878a..336878a 100644 --- a/arch/x86/kernel/cpu/intel_pt.h +++ b/arch/x86/events/intel/pt.h diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/events/intel/rapl.c index 24a351a..b834a3f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -44,11 +44,14 @@ * the duration of the measurement. Tools may use a function such as * ldexp(raw_count, -32); */ + +#define pr_fmt(fmt) "RAPL PMU: " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <asm/cpu_device_id.h> -#include "perf_event.h" +#include "../perf_event.h" /* * RAPL energy status counters @@ -107,7 +110,7 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __rapl_##_var##_show, NULL) -#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ +#define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ static struct perf_pmu_events_attr event_attr_##v = { \ @@ -117,23 +120,33 @@ static struct perf_pmu_events_attr event_attr_##v = { \ }; struct rapl_pmu { - spinlock_t lock; - int n_active; /* number of active events */ - struct list_head active_list; - struct pmu *pmu; /* pointer to rapl_pmu_class */ - ktime_t timer_interval; /* in ktime_t unit */ - struct hrtimer hrtimer; + raw_spinlock_t lock; + int n_active; + int cpu; + struct list_head active_list; + struct pmu *pmu; + ktime_t timer_interval; + struct hrtimer hrtimer; }; -static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; /* 1/2^hw_unit Joule */ -static struct pmu rapl_pmu_class; +struct rapl_pmus { + struct pmu pmu; + unsigned int maxpkg; + struct rapl_pmu *pmus[]; +}; + + /* 1/2^hw_unit Joule */ +static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; +static struct rapl_pmus *rapl_pmus; static cpumask_t rapl_cpu_mask; -static int rapl_cntr_mask; +static unsigned int rapl_cntr_mask; +static u64 rapl_timer_ms; -static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); -static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); +static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) +{ + return rapl_pmus->pmus[topology_logical_package_id(cpu)]; +} -static struct x86_pmu_quirk *rapl_quirks; static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; @@ -141,19 +154,10 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -#define rapl_add_quirk(func_) \ -do { \ - static struct x86_pmu_quirk __quirk __initdata = { \ - .func = func_, \ - }; \ - __quirk.next = rapl_quirks; \ - rapl_quirks = &__quirk; \ -} while (0) - static inline u64 rapl_scale(u64 v, int cfg) { if (cfg > NR_RAPL_DOMAINS) { - pr_warn("invalid domain %d, failed to scale data\n", cfg); + pr_warn("Invalid domain %d, failed to scale data\n", cfg); return v; } /* @@ -206,27 +210,21 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu) HRTIMER_MODE_REL_PINNED); } -static void rapl_stop_hrtimer(struct rapl_pmu *pmu) -{ - hrtimer_cancel(&pmu->hrtimer); -} - static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; if (!pmu->n_active) return HRTIMER_NORESTART; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); - list_for_each_entry(event, &pmu->active_list, active_entry) { + list_for_each_entry(event, &pmu->active_list, active_entry) rapl_event_update(event); - } - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); hrtimer_forward_now(hrtimer, pmu->timer_interval); @@ -260,28 +258,28 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu, static void rapl_pmu_event_start(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = event->pmu_private; unsigned long flags; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); __rapl_pmu_event_start(pmu, event); - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { WARN_ON_ONCE(pmu->n_active <= 0); pmu->n_active--; if (pmu->n_active == 0) - rapl_stop_hrtimer(pmu); + hrtimer_cancel(&pmu->hrtimer); list_del(&event->active_entry); @@ -299,23 +297,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode) hwc->state |= PERF_HES_UPTODATE; } - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu); + struct rapl_pmu *pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) __rapl_pmu_event_start(pmu, event); - spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&pmu->lock, flags); return 0; } @@ -329,15 +327,19 @@ static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; int bit, msr, ret = 0; + struct rapl_pmu *pmu; /* only look at RAPL events */ - if (event->attr.type != rapl_pmu_class.type) + if (event->attr.type != rapl_pmus->pmu.type) return -ENOENT; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) return -EINVAL; + if (event->cpu < 0) + return -EINVAL; + /* * check event is known (determines counter) */ @@ -376,6 +378,9 @@ static int rapl_pmu_event_init(struct perf_event *event) return -EINVAL; /* must be done before validate_group */ + pmu = cpu_to_rapl_pmu(event->cpu); + event->cpu = pmu->cpu; + event->pmu_private = pmu; event->hw.event_base = msr; event->hw.config = cfg; event->hw.idx = bit; @@ -506,139 +511,62 @@ const struct attribute_group *rapl_attr_groups[] = { NULL, }; -static struct pmu rapl_pmu_class = { - .attr_groups = rapl_attr_groups, - .task_ctx_nr = perf_invalid_context, /* system-wide only */ - .event_init = rapl_pmu_event_init, - .add = rapl_pmu_event_add, /* must have */ - .del = rapl_pmu_event_del, /* must have */ - .start = rapl_pmu_event_start, - .stop = rapl_pmu_event_stop, - .read = rapl_pmu_event_read, -}; - static void rapl_cpu_exit(int cpu) { - struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); - int i, phys_id = topology_physical_package_id(cpu); - int target = -1; + struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); + int target; - /* find a new cpu on same package */ - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (phys_id == topology_physical_package_id(i)) { - target = i; - break; - } - } - /* - * clear cpu from cpumask - * if was set in cpumask and still some cpu on package, - * then move to new cpu - */ - if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0) - cpumask_set_cpu(target, &rapl_cpu_mask); + /* Check if exiting cpu is used for collecting rapl events */ + if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask)) + return; - WARN_ON(cpumask_empty(&rapl_cpu_mask)); - /* - * migrate events and context to new cpu - */ - if (target >= 0) - perf_pmu_migrate_context(pmu->pmu, cpu, target); + pmu->cpu = -1; + /* Find a new cpu to collect rapl events */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - /* cancel overflow polling timer for CPU */ - rapl_stop_hrtimer(pmu); + /* Migrate rapl events to the new target */ + if (target < nr_cpu_ids) { + cpumask_set_cpu(target, &rapl_cpu_mask); + pmu->cpu = target; + perf_pmu_migrate_context(pmu->pmu, cpu, target); + } } static void rapl_cpu_init(int cpu) { - int i, phys_id = topology_physical_package_id(cpu); + struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); + int target; - /* check if phys_is is already covered */ - for_each_cpu(i, &rapl_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) - return; - } - /* was not found, so add it */ - cpumask_set_cpu(cpu, &rapl_cpu_mask); -} - -static __init void rapl_hsw_server_quirk(void) -{ /* - * DRAM domain on HSW server has fixed energy unit which can be - * different than the unit from power unit MSR. - * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 - * of 2. Datasheet, September 2014, Reference Number: 330784-001 " + * Check if there is an online cpu in the package which collects rapl + * events already. */ - rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; + target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu)); + if (target < nr_cpu_ids) + return; + + cpumask_set_cpu(cpu, &rapl_cpu_mask); + pmu->cpu = cpu; } static int rapl_cpu_prepare(int cpu) { - struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); - int phys_id = topology_physical_package_id(cpu); - u64 ms; + struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); if (pmu) return 0; - if (phys_id < 0) - return -1; - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) - return -1; - spin_lock_init(&pmu->lock); + return -ENOMEM; + raw_spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); - - pmu->pmu = &rapl_pmu_class; - - /* - * use reference of 200W for scaling the timeout - * to avoid missing counter overflows. - * 200W = 200 Joules/sec - * divide interval by 2 to avoid lockstep (2 * 100) - * if hw unit is 32, then we use 2 ms 1/200/2 - */ - if (rapl_hw_unit[0] < 32) - ms = (1000 / (2 * 100)) * (1ULL << (32 - rapl_hw_unit[0] - 1)); - else - ms = 2; - - pmu->timer_interval = ms_to_ktime(ms); - + pmu->pmu = &rapl_pmus->pmu; + pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + pmu->cpu = -1; rapl_hrtimer_init(pmu); - - /* set RAPL pmu for this cpu for now */ - per_cpu(rapl_pmu, cpu) = pmu; - per_cpu(rapl_pmu_to_free, cpu) = NULL; - - return 0; -} - -static void rapl_cpu_kfree(int cpu) -{ - struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu); - - kfree(pmu); - - per_cpu(rapl_pmu_to_free, cpu) = NULL; -} - -static int rapl_cpu_dying(int cpu) -{ - struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); - - if (!pmu) - return 0; - - per_cpu(rapl_pmu, cpu) = NULL; - - per_cpu(rapl_pmu_to_free, cpu) = pmu; - + rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; return 0; } @@ -651,28 +579,20 @@ static int rapl_cpu_notifier(struct notifier_block *self, case CPU_UP_PREPARE: rapl_cpu_prepare(cpu); break; - case CPU_STARTING: - rapl_cpu_init(cpu); - break; - case CPU_UP_CANCELED: - case CPU_DYING: - rapl_cpu_dying(cpu); - break; + + case CPU_DOWN_FAILED: case CPU_ONLINE: - case CPU_DEAD: - rapl_cpu_kfree(cpu); + rapl_cpu_init(cpu); break; + case CPU_DOWN_PREPARE: rapl_cpu_exit(cpu); break; - default: - break; } - return NOTIFY_OK; } -static int rapl_check_hw_unit(void) +static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; int i; @@ -683,28 +603,107 @@ static int rapl_check_hw_unit(void) for (i = 0; i < NR_RAPL_DOMAINS; i++) rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + /* + * DRAM domain on HSW server and KNL has fixed energy unit which can be + * different than the unit from power unit MSR. See + * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 + * of 2. Datasheet, September 2014, Reference Number: 330784-001 " + */ + if (apply_quirk) + rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; + + /* + * Calculate the timer rate: + * Use reference of 200W for scaling the timeout to avoid counter + * overflows. 200W = 200 Joules/sec + * Divide interval by 2 to avoid lockstep (2 * 100) + * if hw unit is 32, then we use 2 ms 1/200/2 + */ + rapl_timer_ms = 2; + if (rapl_hw_unit[0] < 32) { + rapl_timer_ms = (1000 / (2 * 100)); + rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1)); + } + return 0; +} + +static void __init rapl_advertise(void) +{ + int i; + + pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", + hweight32(rapl_cntr_mask), rapl_timer_ms); + + for (i = 0; i < NR_RAPL_DOMAINS; i++) { + if (rapl_cntr_mask & (1 << i)) { + pr_info("hw unit of domain %s 2^-%d Joules\n", + rapl_domain_names[i], rapl_hw_unit[i]); + } + } +} + +static int __init rapl_prepare_cpus(void) +{ + unsigned int cpu, pkg; + int ret; + + for_each_online_cpu(cpu) { + pkg = topology_logical_package_id(cpu); + if (rapl_pmus->pmus[pkg]) + continue; + + ret = rapl_cpu_prepare(cpu); + if (ret) + return ret; + rapl_cpu_init(cpu); + } + return 0; +} + +static void __init cleanup_rapl_pmus(void) +{ + int i; + + for (i = 0; i < rapl_pmus->maxpkg; i++) + kfree(rapl_pmus->pmus + i); + kfree(rapl_pmus); +} + +static int __init init_rapl_pmus(void) +{ + int maxpkg = topology_max_packages(); + size_t size; + + size = sizeof(*rapl_pmus) + maxpkg * sizeof(struct rapl_pmu *); + rapl_pmus = kzalloc(size, GFP_KERNEL); + if (!rapl_pmus) + return -ENOMEM; + + rapl_pmus->maxpkg = maxpkg; + rapl_pmus->pmu.attr_groups = rapl_attr_groups; + rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; + rapl_pmus->pmu.event_init = rapl_pmu_event_init; + rapl_pmus->pmu.add = rapl_pmu_event_add; + rapl_pmus->pmu.del = rapl_pmu_event_del; + rapl_pmus->pmu.start = rapl_pmu_event_start; + rapl_pmus->pmu.stop = rapl_pmu_event_stop; + rapl_pmus->pmu.read = rapl_pmu_event_read; return 0; } -static const struct x86_cpu_id rapl_cpu_match[] = { +static const struct x86_cpu_id rapl_cpu_match[] __initconst = { [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, [1] = {}, }; static int __init rapl_pmu_init(void) { - struct rapl_pmu *pmu; - int cpu, ret; - struct x86_pmu_quirk *quirk; - int i; + bool apply_quirk = false; + int ret; - /* - * check for Intel processor family 6 - */ if (!x86_match_cpu(rapl_cpu_match)) - return 0; + return -ENODEV; - /* check supported CPU */ switch (boot_cpu_data.x86_model) { case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ @@ -712,7 +711,7 @@ static int __init rapl_pmu_init(void) rapl_pmu_events_group.attrs = rapl_events_cln_attr; break; case 63: /* Haswell-Server */ - rapl_add_quirk(rapl_hsw_server_quirk); + apply_quirk = true; rapl_cntr_mask = RAPL_IDX_SRV; rapl_pmu_events_group.attrs = rapl_events_srv_attr; break; @@ -728,56 +727,41 @@ static int __init rapl_pmu_init(void) rapl_pmu_events_group.attrs = rapl_events_srv_attr; break; case 87: /* Knights Landing */ - rapl_add_quirk(rapl_hsw_server_quirk); + apply_quirk = true; rapl_cntr_mask = RAPL_IDX_KNL; rapl_pmu_events_group.attrs = rapl_events_knl_attr; - + break; default: - /* unsupported */ - return 0; + return -ENODEV; } - ret = rapl_check_hw_unit(); + + ret = rapl_check_hw_unit(apply_quirk); if (ret) return ret; - /* run cpu model quirks */ - for (quirk = rapl_quirks; quirk; quirk = quirk->next) - quirk->func(); - cpu_notifier_register_begin(); + ret = init_rapl_pmus(); + if (ret) + return ret; - for_each_online_cpu(cpu) { - ret = rapl_cpu_prepare(cpu); - if (ret) - goto out; - rapl_cpu_init(cpu); - } + cpu_notifier_register_begin(); - __perf_cpu_notifier(rapl_cpu_notifier); + ret = rapl_prepare_cpus(); + if (ret) + goto out; - ret = perf_pmu_register(&rapl_pmu_class, "power", -1); - if (WARN_ON(ret)) { - pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret); - cpu_notifier_register_done(); - return -1; - } + ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); + if (ret) + goto out; - pmu = __this_cpu_read(rapl_pmu); + __perf_cpu_notifier(rapl_cpu_notifier); + cpu_notifier_register_done(); + rapl_advertise(); + return 0; - pr_info("RAPL PMU detected," - " API unit is 2^-32 Joules," - " %d fixed counters" - " %llu ms ovfl timer\n", - hweight32(rapl_cntr_mask), - ktime_to_ms(pmu->timer_interval)); - for (i = 0; i < NR_RAPL_DOMAINS; i++) { - if (rapl_cntr_mask & (1 << i)) { - pr_info("hw unit of domain %s 2^-%d Joules\n", - rapl_domain_names[i], rapl_hw_unit[i]); - } - } out: + pr_warn("Initialization failed (%d), disabled\n", ret); + cleanup_rapl_pmus(); cpu_notifier_register_done(); - - return 0; + return ret; } device_initcall(rapl_pmu_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/events/intel/uncore.c index 3bf41d4..7012d18 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1,4 +1,4 @@ -#include "perf_event_intel_uncore.h" +#include "uncore.h" static struct intel_uncore_type *empty_uncore[] = { NULL, }; struct intel_uncore_type **uncore_msr_uncores = empty_uncore; @@ -9,9 +9,9 @@ struct pci_driver *uncore_pci_driver; /* pci bus to socket mapping */ DEFINE_RAW_SPINLOCK(pci2phy_map_lock); struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head); -struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +struct pci_extra_dev *uncore_extra_pci_dev; +static int max_packages; -static DEFINE_RAW_SPINLOCK(uncore_box_lock); /* mask of cpus that collect uncore events */ static cpumask_t uncore_cpu_mask; @@ -21,7 +21,7 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); -int uncore_pcibus_to_physid(struct pci_bus *bus) +static int uncore_pcibus_to_physid(struct pci_bus *bus) { struct pci2phy_map *map; int phys_id = -1; @@ -38,6 +38,16 @@ int uncore_pcibus_to_physid(struct pci_bus *bus) return phys_id; } +static void uncore_free_pcibus_map(void) +{ + struct pci2phy_map *map, *tmp; + + list_for_each_entry_safe(map, tmp, &pci2phy_map_head, list) { + list_del(&map->list); + kfree(map); + } +} + struct pci2phy_map *__find_pci2phy_map(int segment) { struct pci2phy_map *map, *alloc = NULL; @@ -82,43 +92,9 @@ ssize_t uncore_event_show(struct kobject *kobj, return sprintf(buf, "%s", event->config); } -struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) -{ - return container_of(event->pmu, struct intel_uncore_pmu, pmu); -} - struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - struct intel_uncore_box *box; - - box = *per_cpu_ptr(pmu->box, cpu); - if (box) - return box; - - raw_spin_lock(&uncore_box_lock); - /* Recheck in lock to handle races. */ - if (*per_cpu_ptr(pmu->box, cpu)) - goto out; - list_for_each_entry(box, &pmu->box_list, list) { - if (box->phys_id == topology_physical_package_id(cpu)) { - atomic_inc(&box->refcnt); - *per_cpu_ptr(pmu->box, cpu) = box; - break; - } - } -out: - raw_spin_unlock(&uncore_box_lock); - - return *per_cpu_ptr(pmu->box, cpu); -} - -struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) -{ - /* - * perf core schedules event on the basis of cpu, uncore events are - * collected by one of the cpus inside a physical package. - */ - return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); + return pmu->boxes[topology_logical_package_id(cpu)]; } u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) @@ -207,7 +183,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) return config; } -static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx) +static void uncore_assign_hw_event(struct intel_uncore_box *box, + struct perf_event *event, int idx) { struct hw_perf_event *hwc = &event->hw; @@ -302,24 +279,25 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box) box->hrtimer.function = uncore_pmu_hrtimer; } -static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node) +static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, + int node) { + int i, size, numshared = type->num_shared_regs ; struct intel_uncore_box *box; - int i, size; - size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); + size = sizeof(*box) + numshared * sizeof(struct intel_uncore_extra_reg); box = kzalloc_node(size, GFP_KERNEL, node); if (!box) return NULL; - for (i = 0; i < type->num_shared_regs; i++) + for (i = 0; i < numshared; i++) raw_spin_lock_init(&box->shared_regs[i].lock); uncore_pmu_init_hrtimer(box); - atomic_set(&box->refcnt, 1); box->cpu = -1; - box->phys_id = -1; + box->pci_phys_id = -1; + box->pkgid = -1; /* set default hrtimer timeout */ box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL; @@ -341,7 +319,8 @@ static bool is_uncore_event(struct perf_event *event) } static int -uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) +uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, + bool dogrp) { struct perf_event *event; int n, max_count; @@ -402,7 +381,8 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve return &type->unconstrainted; } -static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event) +static void uncore_put_event_constraint(struct intel_uncore_box *box, + struct perf_event *event) { if (box->pmu->type->ops->put_constraint) box->pmu->type->ops->put_constraint(box, event); @@ -582,7 +562,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags) if (event == box->event_list[i]) { uncore_put_event_constraint(box, event); - while (++i < box->n_events) + for (++i; i < box->n_events; i++) box->event_list[i - 1] = box->event_list[i]; --box->n_events; @@ -676,6 +656,7 @@ static int uncore_pmu_event_init(struct perf_event *event) if (!box || box->cpu < 0) return -EINVAL; event->cpu = box->cpu; + event->pmu_private = box; event->hw.idx = -1; event->hw.last_tag = ~0ULL; @@ -760,64 +741,110 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu) } ret = perf_pmu_register(&pmu->pmu, pmu->name, -1); + if (!ret) + pmu->registered = true; return ret; } +static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) +{ + if (!pmu->registered) + return; + perf_pmu_unregister(&pmu->pmu); + pmu->registered = false; +} + +static void __init __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) +{ + struct intel_uncore_pmu *pmu = type->pmus; + struct intel_uncore_box *box; + int i, pkg; + + if (pmu) { + pkg = topology_physical_package_id(cpu); + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box) + uncore_box_exit(box); + } + } +} + +static void __init uncore_exit_boxes(void *dummy) +{ + struct intel_uncore_type **types; + + for (types = uncore_msr_uncores; *types; types++) + __uncore_exit_boxes(*types++, smp_processor_id()); +} + +static void uncore_free_boxes(struct intel_uncore_pmu *pmu) +{ + int pkg; + + for (pkg = 0; pkg < max_packages; pkg++) + kfree(pmu->boxes[pkg]); + kfree(pmu->boxes); +} + static void __init uncore_type_exit(struct intel_uncore_type *type) { + struct intel_uncore_pmu *pmu = type->pmus; int i; - for (i = 0; i < type->num_boxes; i++) - free_percpu(type->pmus[i].box); - kfree(type->pmus); - type->pmus = NULL; + if (pmu) { + for (i = 0; i < type->num_boxes; i++, pmu++) { + uncore_pmu_unregister(pmu); + uncore_free_boxes(pmu); + } + kfree(type->pmus); + type->pmus = NULL; + } kfree(type->events_group); type->events_group = NULL; } static void __init uncore_types_exit(struct intel_uncore_type **types) { - int i; - for (i = 0; types[i]; i++) - uncore_type_exit(types[i]); + for (; *types; types++) + uncore_type_exit(*types); } -static int __init uncore_type_init(struct intel_uncore_type *type) +static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) { struct intel_uncore_pmu *pmus; struct attribute_group *attr_group; struct attribute **attrs; + size_t size; int i, j; pmus = kzalloc(sizeof(*pmus) * type->num_boxes, GFP_KERNEL); if (!pmus) return -ENOMEM; - type->pmus = pmus; + size = max_packages * sizeof(struct intel_uncore_box *); + for (i = 0; i < type->num_boxes; i++) { + pmus[i].func_id = setid ? i : -1; + pmus[i].pmu_idx = i; + pmus[i].type = type; + pmus[i].boxes = kzalloc(size, GFP_KERNEL); + if (!pmus[i].boxes) + return -ENOMEM; + } + + type->pmus = pmus; type->unconstrainted = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, 0, type->num_counters, 0, 0); - for (i = 0; i < type->num_boxes; i++) { - pmus[i].func_id = -1; - pmus[i].pmu_idx = i; - pmus[i].type = type; - INIT_LIST_HEAD(&pmus[i].box_list); - pmus[i].box = alloc_percpu(struct intel_uncore_box *); - if (!pmus[i].box) - goto fail; - } - if (type->event_descs) { - i = 0; - while (type->event_descs[i].attr.attr.name) - i++; + for (i = 0; type->event_descs[i].attr.attr.name; i++); attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + sizeof(*attr_group), GFP_KERNEL); if (!attr_group) - goto fail; + return -ENOMEM; attrs = (struct attribute **)(attr_group + 1); attr_group->name = "events"; @@ -831,25 +858,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type) type->pmu_group = &uncore_pmu_attr_group; return 0; -fail: - uncore_type_exit(type); - return -ENOMEM; } -static int __init uncore_types_init(struct intel_uncore_type **types) +static int __init +uncore_types_init(struct intel_uncore_type **types, bool setid) { - int i, ret; + int ret; - for (i = 0; types[i]; i++) { - ret = uncore_type_init(types[i]); + for (; *types; types++) { + ret = uncore_type_init(*types, setid); if (ret) - goto fail; + return ret; } return 0; -fail: - while (--i >= 0) - uncore_type_exit(types[i]); - return ret; } /* @@ -857,28 +878,28 @@ fail: */ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { + struct intel_uncore_type *type; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - struct intel_uncore_type *type; - int phys_id; - bool first_box = false; + int phys_id, pkg, ret; phys_id = uncore_pcibus_to_physid(pdev->bus); if (phys_id < 0) return -ENODEV; + pkg = topology_phys_to_logical_pkg(phys_id); + if (WARN_ON_ONCE(pkg < 0)) + return -EINVAL; + if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { int idx = UNCORE_PCI_DEV_IDX(id->driver_data); - uncore_extra_pci_dev[phys_id][idx] = pdev; + + uncore_extra_pci_dev[pkg].dev[idx] = pdev; pci_set_drvdata(pdev, NULL); return 0; } type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; - box = uncore_alloc_box(type, NUMA_NO_NODE); - if (!box) - return -ENOMEM; - /* * for performance monitoring unit with multiple boxes, * each box has a different function id. @@ -890,44 +911,60 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * some device types. Hence PCI device idx would be 0 for all devices. * So increment pmu pointer to point to an unused array element. */ - if (boot_cpu_data.x86_model == 87) + if (boot_cpu_data.x86_model == 87) { while (pmu->func_id >= 0) pmu++; + } + + if (WARN_ON_ONCE(pmu->boxes[pkg] != NULL)) + return -EINVAL; + + box = uncore_alloc_box(type, NUMA_NO_NODE); + if (!box) + return -ENOMEM; + if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else WARN_ON_ONCE(pmu->func_id != pdev->devfn); - box->phys_id = phys_id; + atomic_inc(&box->refcnt); + box->pci_phys_id = phys_id; + box->pkgid = pkg; box->pci_dev = pdev; box->pmu = pmu; uncore_box_init(box); pci_set_drvdata(pdev, box); - raw_spin_lock(&uncore_box_lock); - if (list_empty(&pmu->box_list)) - first_box = true; - list_add_tail(&box->list, &pmu->box_list); - raw_spin_unlock(&uncore_box_lock); + pmu->boxes[pkg] = box; + if (atomic_inc_return(&pmu->activeboxes) > 1) + return 0; - if (first_box) - uncore_pmu_register(pmu); - return 0; + /* First active box registers the pmu */ + ret = uncore_pmu_register(pmu); + if (ret) { + pci_set_drvdata(pdev, NULL); + pmu->boxes[pkg] = NULL; + uncore_box_exit(box); + kfree(box); + } + return ret; } static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id; - bool last_box = false; + int i, phys_id, pkg; phys_id = uncore_pcibus_to_physid(pdev->bus); + pkg = topology_phys_to_logical_pkg(phys_id); + box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { - if (uncore_extra_pci_dev[phys_id][i] == pdev) { - uncore_extra_pci_dev[phys_id][i] = NULL; + if (uncore_extra_pci_dev[pkg].dev[i] == pdev) { + uncore_extra_pci_dev[pkg].dev[i] = NULL; break; } } @@ -936,33 +973,20 @@ static void uncore_pci_remove(struct pci_dev *pdev) } pmu = box->pmu; - if (WARN_ON_ONCE(phys_id != box->phys_id)) + if (WARN_ON_ONCE(phys_id != box->pci_phys_id)) return; pci_set_drvdata(pdev, NULL); - - raw_spin_lock(&uncore_box_lock); - list_del(&box->list); - if (list_empty(&pmu->box_list)) - last_box = true; - raw_spin_unlock(&uncore_box_lock); - - for_each_possible_cpu(cpu) { - if (*per_cpu_ptr(pmu->box, cpu) == box) { - *per_cpu_ptr(pmu->box, cpu) = NULL; - atomic_dec(&box->refcnt); - } - } - - WARN_ON_ONCE(atomic_read(&box->refcnt) != 1); + pmu->boxes[pkg] = NULL; + if (atomic_dec_return(&pmu->activeboxes) == 0) + uncore_pmu_unregister(pmu); + uncore_box_exit(box); kfree(box); - - if (last_box) - perf_pmu_unregister(&pmu->pmu); } static int __init uncore_pci_init(void) { + size_t size; int ret; switch (boot_cpu_data.x86_model) { @@ -999,25 +1023,40 @@ static int __init uncore_pci_init(void) ret = skl_uncore_pci_init(); break; default: - return 0; + return -ENODEV; } if (ret) return ret; - ret = uncore_types_init(uncore_pci_uncores); + size = max_packages * sizeof(struct pci_extra_dev); + uncore_extra_pci_dev = kzalloc(size, GFP_KERNEL); + if (!uncore_extra_pci_dev) { + ret = -ENOMEM; + goto err; + } + + ret = uncore_types_init(uncore_pci_uncores, false); if (ret) - return ret; + goto errtype; uncore_pci_driver->probe = uncore_pci_probe; uncore_pci_driver->remove = uncore_pci_remove; ret = pci_register_driver(uncore_pci_driver); - if (ret == 0) - pcidrv_registered = true; - else - uncore_types_exit(uncore_pci_uncores); + if (ret) + goto errtype; + + pcidrv_registered = true; + return 0; +errtype: + uncore_types_exit(uncore_pci_uncores); + kfree(uncore_extra_pci_dev); + uncore_extra_pci_dev = NULL; + uncore_free_pcibus_map(); +err: + uncore_pci_uncores = empty_uncore; return ret; } @@ -1027,173 +1066,139 @@ static void __init uncore_pci_exit(void) pcidrv_registered = false; pci_unregister_driver(uncore_pci_driver); uncore_types_exit(uncore_pci_uncores); - } -} - -/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */ -static LIST_HEAD(boxes_to_free); - -static void uncore_kfree_boxes(void) -{ - struct intel_uncore_box *box; - - while (!list_empty(&boxes_to_free)) { - box = list_entry(boxes_to_free.next, - struct intel_uncore_box, list); - list_del(&box->list); - kfree(box); + kfree(uncore_extra_pci_dev); + uncore_free_pcibus_map(); } } static void uncore_cpu_dying(int cpu) { - struct intel_uncore_type *type; + struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, j; - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - box = *per_cpu_ptr(pmu->box, cpu); - *per_cpu_ptr(pmu->box, cpu) = NULL; - if (box && atomic_dec_and_test(&box->refcnt)) - list_add(&box->list, &boxes_to_free); + int i, pkg; + + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); } } } -static int uncore_cpu_starting(int cpu) +static void uncore_cpu_starting(int cpu, bool init) { - struct intel_uncore_type *type; + struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box, *exist; - int i, j, k, phys_id; - - phys_id = topology_physical_package_id(cpu); - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - box = *per_cpu_ptr(pmu->box, cpu); - /* called by uncore_cpu_init? */ - if (box && box->phys_id >= 0) { - uncore_box_init(box); - continue; - } + struct intel_uncore_box *box; + int i, pkg, ncpus = 1; - for_each_online_cpu(k) { - exist = *per_cpu_ptr(pmu->box, k); - if (exist && exist->phys_id == phys_id) { - atomic_inc(&exist->refcnt); - *per_cpu_ptr(pmu->box, cpu) = exist; - if (box) { - list_add(&box->list, - &boxes_to_free); - box = NULL; - } - break; - } - } + if (init) { + /* + * On init we get the number of online cpus in the package + * and set refcount for all of them. + */ + ncpus = cpumask_weight(topology_core_cpumask(cpu)); + } - if (box) { - box->phys_id = phys_id; + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box) + continue; + /* The first cpu on a package activates the box */ + if (atomic_add_return(ncpus, &box->refcnt) == ncpus) uncore_box_init(box); - } } } - return 0; } -static int uncore_cpu_prepare(int cpu, int phys_id) +static int uncore_cpu_prepare(int cpu) { - struct intel_uncore_type *type; + struct intel_uncore_type *type, **types = uncore_msr_uncores; struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, j; - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - if (pmu->func_id < 0) - pmu->func_id = j; - + int i, pkg; + + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[pkg]) + continue; + /* First cpu of a package allocates the box */ box = uncore_alloc_box(type, cpu_to_node(cpu)); if (!box) return -ENOMEM; - box->pmu = pmu; - box->phys_id = phys_id; - *per_cpu_ptr(pmu->box, cpu) = box; + box->pkgid = pkg; + pmu->boxes[pkg] = box; } } return 0; } -static void -uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu) +static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu, + int new_cpu) { - struct intel_uncore_type *type; - struct intel_uncore_pmu *pmu; + struct intel_uncore_pmu *pmu = type->pmus; struct intel_uncore_box *box; - int i, j; + int i, pkg; - for (i = 0; uncores[i]; i++) { - type = uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - if (old_cpu < 0) - box = uncore_pmu_to_box(pmu, new_cpu); - else - box = uncore_pmu_to_box(pmu, old_cpu); - if (!box) - continue; - - if (old_cpu < 0) { - WARN_ON_ONCE(box->cpu != -1); - box->cpu = new_cpu; - continue; - } + pkg = topology_logical_package_id(old_cpu < 0 ? new_cpu : old_cpu); + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box) + continue; - WARN_ON_ONCE(box->cpu != old_cpu); - if (new_cpu >= 0) { - uncore_pmu_cancel_hrtimer(box); - perf_pmu_migrate_context(&pmu->pmu, - old_cpu, new_cpu); - box->cpu = new_cpu; - } else { - box->cpu = -1; - } + if (old_cpu < 0) { + WARN_ON_ONCE(box->cpu != -1); + box->cpu = new_cpu; + continue; } + + WARN_ON_ONCE(box->cpu != old_cpu); + box->cpu = -1; + if (new_cpu < 0) + continue; + + uncore_pmu_cancel_hrtimer(box); + perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu); + box->cpu = new_cpu; } } +static void uncore_change_context(struct intel_uncore_type **uncores, + int old_cpu, int new_cpu) +{ + for (; *uncores; uncores++) + uncore_change_type_ctx(*uncores, old_cpu, new_cpu); +} + static void uncore_event_exit_cpu(int cpu) { - int i, phys_id, target; + int target; - /* if exiting cpu is used for collecting uncore events */ + /* Check if exiting cpu is used for collecting uncore events */ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) return; - /* find a new cpu to collect uncore events */ - phys_id = topology_physical_package_id(cpu); - target = -1; - for_each_online_cpu(i) { - if (i == cpu) - continue; - if (phys_id == topology_physical_package_id(i)) { - target = i; - break; - } - } + /* Find a new cpu to collect uncore events */ + target = cpumask_any_but(topology_core_cpumask(cpu), cpu); - /* migrate uncore events to the new cpu */ - if (target >= 0) + /* Migrate uncore events to the new target */ + if (target < nr_cpu_ids) cpumask_set_cpu(target, &uncore_cpu_mask); + else + target = -1; uncore_change_context(uncore_msr_uncores, cpu, target); uncore_change_context(uncore_pci_uncores, cpu, target); @@ -1201,13 +1206,15 @@ static void uncore_event_exit_cpu(int cpu) static void uncore_event_init_cpu(int cpu) { - int i, phys_id; + int target; - phys_id = topology_physical_package_id(cpu); - for_each_cpu(i, &uncore_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) - return; - } + /* + * Check if there is an online cpu in the package + * which collects uncore events already. + */ + target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu)); + if (target < nr_cpu_ids) + return; cpumask_set_cpu(cpu, &uncore_cpu_mask); @@ -1220,39 +1227,25 @@ static int uncore_cpu_notifier(struct notifier_block *self, { unsigned int cpu = (long)hcpu; - /* allocate/free data structure for uncore box */ switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - uncore_cpu_prepare(cpu, -1); - break; + return notifier_from_errno(uncore_cpu_prepare(cpu)); + case CPU_STARTING: - uncore_cpu_starting(cpu); + uncore_cpu_starting(cpu, false); + case CPU_DOWN_FAILED: + uncore_event_init_cpu(cpu); break; + case CPU_UP_CANCELED: case CPU_DYING: uncore_cpu_dying(cpu); break; - case CPU_ONLINE: - case CPU_DEAD: - uncore_kfree_boxes(); - break; - default: - break; - } - /* select the cpu that collects uncore events */ - switch (action & ~CPU_TASKS_FROZEN) { - case CPU_DOWN_FAILED: - case CPU_STARTING: - uncore_event_init_cpu(cpu); - break; case CPU_DOWN_PREPARE: uncore_event_exit_cpu(cpu); break; - default: - break; } - return NOTIFY_OK; } @@ -1265,9 +1258,29 @@ static struct notifier_block uncore_cpu_nb = { .priority = CPU_PRI_PERF + 1, }; -static void __init uncore_cpu_setup(void *dummy) +static int __init type_pmu_register(struct intel_uncore_type *type) { - uncore_cpu_starting(smp_processor_id()); + int i, ret; + + for (i = 0; i < type->num_boxes; i++) { + ret = uncore_pmu_register(&type->pmus[i]); + if (ret) + return ret; + } + return 0; +} + +static int __init uncore_msr_pmus_register(void) +{ + struct intel_uncore_type **types = uncore_msr_uncores; + int ret; + + for (; *types; types++) { + ret = type_pmu_register(*types); + if (ret) + return ret; + } + return 0; } static int __init uncore_cpu_init(void) @@ -1311,71 +1324,61 @@ static int __init uncore_cpu_init(void) knl_uncore_cpu_init(); break; default: - return 0; + return -ENODEV; } - ret = uncore_types_init(uncore_msr_uncores); + ret = uncore_types_init(uncore_msr_uncores, true); if (ret) - return ret; + goto err; + ret = uncore_msr_pmus_register(); + if (ret) + goto err; return 0; +err: + uncore_types_exit(uncore_msr_uncores); + uncore_msr_uncores = empty_uncore; + return ret; } -static int __init uncore_pmus_register(void) +static void __init uncore_cpu_setup(void *dummy) { - struct intel_uncore_pmu *pmu; - struct intel_uncore_type *type; - int i, j; - - for (i = 0; uncore_msr_uncores[i]; i++) { - type = uncore_msr_uncores[i]; - for (j = 0; j < type->num_boxes; j++) { - pmu = &type->pmus[j]; - uncore_pmu_register(pmu); - } - } - - return 0; + uncore_cpu_starting(smp_processor_id(), true); } -static void __init uncore_cpumask_init(void) -{ - int cpu; - - /* - * ony invoke once from msr or pci init code - */ - if (!cpumask_empty(&uncore_cpu_mask)) - return; +/* Lazy to avoid allocation of a few bytes for the normal case */ +static __initdata DECLARE_BITMAP(packages, MAX_LOCAL_APIC); - cpu_notifier_register_begin(); +static int __init uncore_cpumask_init(bool msr) +{ + unsigned int cpu; for_each_online_cpu(cpu) { - int i, phys_id = topology_physical_package_id(cpu); + unsigned int pkg = topology_logical_package_id(cpu); + int ret; - for_each_cpu(i, &uncore_cpu_mask) { - if (phys_id == topology_physical_package_id(i)) { - phys_id = -1; - break; - } - } - if (phys_id < 0) + if (test_and_set_bit(pkg, packages)) continue; - - uncore_cpu_prepare(cpu, phys_id); + /* + * The first online cpu of each package allocates and takes + * the refcounts for all other online cpus in that package. + * If msrs are not enabled no allocation is required. + */ + if (msr) { + ret = uncore_cpu_prepare(cpu); + if (ret) + return ret; + } uncore_event_init_cpu(cpu); + smp_call_function_single(cpu, uncore_cpu_setup, NULL, 1); } - on_each_cpu(uncore_cpu_setup, NULL, 1); - __register_cpu_notifier(&uncore_cpu_nb); - - cpu_notifier_register_done(); + return 0; } - static int __init intel_uncore_init(void) { - int ret; + int pret, cret, ret; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return -ENODEV; @@ -1383,19 +1386,27 @@ static int __init intel_uncore_init(void) if (cpu_has_hypervisor) return -ENODEV; - ret = uncore_pci_init(); - if (ret) - goto fail; - ret = uncore_cpu_init(); - if (ret) { - uncore_pci_exit(); - goto fail; - } - uncore_cpumask_init(); + max_packages = topology_max_packages(); + + pret = uncore_pci_init(); + cret = uncore_cpu_init(); - uncore_pmus_register(); + if (cret && pret) + return -ENODEV; + + cpu_notifier_register_begin(); + ret = uncore_cpumask_init(!cret); + if (ret) + goto err; + cpu_notifier_register_done(); return 0; -fail: + +err: + /* Undo box->init_box() */ + on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1); + uncore_types_exit(uncore_msr_uncores); + uncore_pci_exit(); + cpu_notifier_register_done(); return ret; } device_initcall(intel_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/events/intel/uncore.h index a7086b8..79766b9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -1,8 +1,10 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/pci.h> +#include <asm/apicdef.h> + #include <linux/perf_event.h> -#include "perf_event.h" +#include "../perf_event.h" #define UNCORE_PMU_NAME_LEN 32 #define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC) @@ -19,11 +21,12 @@ #define UNCORE_EXTRA_PCI_DEV 0xff #define UNCORE_EXTRA_PCI_DEV_MAX 3 -/* support up to 8 sockets */ -#define UNCORE_SOCKET_MAX 8 - #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) +struct pci_extra_dev { + struct pci_dev *dev[UNCORE_EXTRA_PCI_DEV_MAX]; +}; + struct intel_uncore_ops; struct intel_uncore_pmu; struct intel_uncore_box; @@ -61,6 +64,7 @@ struct intel_uncore_type { struct intel_uncore_ops { void (*init_box)(struct intel_uncore_box *); + void (*exit_box)(struct intel_uncore_box *); void (*disable_box)(struct intel_uncore_box *); void (*enable_box)(struct intel_uncore_box *); void (*disable_event)(struct intel_uncore_box *, struct perf_event *); @@ -73,13 +77,14 @@ struct intel_uncore_ops { }; struct intel_uncore_pmu { - struct pmu pmu; - char name[UNCORE_PMU_NAME_LEN]; - int pmu_idx; - int func_id; - struct intel_uncore_type *type; - struct intel_uncore_box ** __percpu box; - struct list_head box_list; + struct pmu pmu; + char name[UNCORE_PMU_NAME_LEN]; + int pmu_idx; + int func_id; + bool registered; + atomic_t activeboxes; + struct intel_uncore_type *type; + struct intel_uncore_box **boxes; }; struct intel_uncore_extra_reg { @@ -89,7 +94,8 @@ struct intel_uncore_extra_reg { }; struct intel_uncore_box { - int phys_id; + int pci_phys_id; + int pkgid; int n_active; /* number of active events */ int n_events; int cpu; /* cpu to collect events */ @@ -123,7 +129,6 @@ struct pci2phy_map { int pbus_to_physid[256]; }; -int uncore_pcibus_to_physid(struct pci_bus *bus); struct pci2phy_map *__find_pci2phy_map(int segment); ssize_t uncore_event_show(struct kobject *kobj, @@ -305,14 +310,30 @@ static inline void uncore_box_init(struct intel_uncore_box *box) } } +static inline void uncore_box_exit(struct intel_uncore_box *box) +{ + if (test_and_clear_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) { + if (box->pmu->type->ops->exit_box) + box->pmu->type->ops->exit_box(box); + } +} + static inline bool uncore_box_is_fake(struct intel_uncore_box *box) { - return (box->phys_id < 0); + return (box->pkgid < 0); +} + +static inline struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct intel_uncore_pmu, pmu); +} + +static inline struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) +{ + return event->pmu_private; } -struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event); struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu); -struct intel_uncore_box *uncore_event_to_box(struct perf_event *event); u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event); void uncore_pmu_start_hrtimer(struct intel_uncore_box *box); void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box); @@ -328,7 +349,7 @@ extern struct intel_uncore_type **uncore_pci_uncores; extern struct pci_driver *uncore_pci_driver; extern raw_spinlock_t pci2phy_map_lock; extern struct list_head pci2phy_map_head; -extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; +extern struct pci_extra_dev *uncore_extra_pci_dev; extern struct event_constraint uncore_constraint_empty; /* perf_event_intel_uncore_snb.c */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index 2749965..cda5693 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -1,5 +1,5 @@ /* Nehalem-EX/Westmere-EX uncore support */ -#include "perf_event_intel_uncore.h" +#include "uncore.h" /* NHM-EX event control */ #define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff @@ -201,6 +201,11 @@ static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box) wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL); } +static void nhmex_uncore_msr_exit_box(struct intel_uncore_box *box) +{ + wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0); +} + static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box) { unsigned msr = uncore_msr_box_ctl(box); @@ -250,6 +255,7 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p #define NHMEX_UNCORE_OPS_COMMON_INIT() \ .init_box = nhmex_uncore_msr_init_box, \ + .exit_box = nhmex_uncore_msr_exit_box, \ .disable_box = nhmex_uncore_msr_disable_box, \ .enable_box = nhmex_uncore_msr_enable_box, \ .disable_event = nhmex_uncore_msr_disable_event, \ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 2bd030d..96531d2 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1,5 +1,5 @@ /* Nehalem/SandBridge/Haswell uncore support */ -#include "perf_event_intel_uncore.h" +#include "uncore.h" /* Uncore IMC PCI IDs */ #define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 @@ -95,6 +95,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void snb_uncore_msr_exit_box(struct intel_uncore_box *box) +{ + if (box->pmu->pmu_idx == 0) + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, 0); +} + static struct uncore_event_desc snb_uncore_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"), { /* end: all zeroes */ }, @@ -116,6 +122,7 @@ static struct attribute_group snb_uncore_format_group = { static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, + .exit_box = snb_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, .read_counter = uncore_msr_read_counter, @@ -231,6 +238,11 @@ static void snb_uncore_imc_init_box(struct intel_uncore_box *box) box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL; } +static void snb_uncore_imc_exit_box(struct intel_uncore_box *box) +{ + iounmap(box->io_addr); +} + static void snb_uncore_imc_enable_box(struct intel_uncore_box *box) {} @@ -301,6 +313,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event) return -EINVAL; event->cpu = box->cpu; + event->pmu_private = box; event->hw.idx = -1; event->hw.last_tag = ~0ULL; @@ -458,6 +471,7 @@ static struct pmu snb_uncore_imc_pmu = { static struct intel_uncore_ops snb_uncore_imc_ops = { .init_box = snb_uncore_imc_init_box, + .exit_box = snb_uncore_imc_exit_box, .enable_box = snb_uncore_imc_enable_box, .disable_box = snb_uncore_imc_disable_box, .disable_event = snb_uncore_imc_disable_event, diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 33acb88..93f6bd9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1,6 +1,5 @@ /* SandyBridge-EP/IvyTown uncore support */ -#include "perf_event_intel_uncore.h" - +#include "uncore.h" /* SNB-EP Box level control */ #define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0) @@ -987,7 +986,9 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve if (reg1->idx != EXTRA_REG_NONE) { int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; - struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx]; + int pkg = topology_phys_to_logical_pkg(box->pci_phys_id); + struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx]; + if (filter_pdev) { pci_write_config_dword(filter_pdev, reg1->reg, (u32)reg1->config); @@ -2521,14 +2522,16 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { void hswep_uncore_cpu_init(void) { + int pkg = topology_phys_to_logical_pkg(0); + if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; /* Detect 6-8 core systems with only two SBOXes */ - if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) { + if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { u32 capid4; - pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3], + pci_read_config_dword(uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3], 0x94, &capid4); if (((capid4 >> 6) & 0x3) == 0) hswep_uncore_sbox.num_boxes = 2; @@ -2875,11 +2878,13 @@ static struct intel_uncore_type bdx_uncore_sbox = { .format_group = &hswep_uncore_sbox_format_group, }; +#define BDX_MSR_UNCORE_SBOX 3 + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, - &bdx_uncore_sbox, &hswep_uncore_pcu, + &bdx_uncore_sbox, NULL, }; @@ -2888,6 +2893,10 @@ void bdx_uncore_cpu_init(void) if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; + + /* BDX-DE doesn't have SBOX */ + if (boot_cpu_data.x86_model == 86) + uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; } static struct intel_uncore_type bdx_uncore_ha = { diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/events/msr.c index ec863b9..ec863b9 100644 --- a/arch/x86/kernel/cpu/perf_event_msr.c +++ b/arch/x86/events/msr.c diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/events/perf_event.h index 7bb61e3..68155ca 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -586,6 +586,7 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1; int pebs_record_size; + int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); @@ -860,6 +861,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[]; extern struct event_constraint intel_hsw_pebs_event_constraints[]; +extern struct event_constraint intel_bdw_pebs_event_constraints[]; + extern struct event_constraint intel_skl_pebs_event_constraints[]; struct event_constraint *intel_pebs_constraints(struct perf_event *event); @@ -904,6 +907,8 @@ void intel_pmu_lbr_init_skl(void); void intel_pmu_lbr_init_knl(void); +void intel_pmu_pebs_data_source_nhm(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 3c56ef1..5e828da 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -27,15 +27,23 @@ struct amd_l3_cache { }; struct threshold_block { - unsigned int block; - unsigned int bank; - unsigned int cpu; - u32 address; - u16 interrupt_enable; - bool interrupt_capable; - u16 threshold_limit; - struct kobject kobj; - struct list_head miscj; + unsigned int block; /* Number within bank */ + unsigned int bank; /* MCA bank the block belongs to */ + unsigned int cpu; /* CPU which controls MCA bank */ + u32 address; /* MSR address for the block */ + u16 interrupt_enable; /* Enable/Disable APIC interrupt */ + bool interrupt_capable; /* Bank can generate an interrupt. */ + + u16 threshold_limit; /* + * Value upon which threshold + * interrupt is generated. + */ + + struct kobject kobj; /* sysfs object */ + struct list_head miscj; /* + * List of threshold blocks + * within a bank. + */ }; struct threshold_bank { diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 189679a..f5063b6 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -44,19 +44,22 @@ /* Exception table entry */ #ifdef __ASSEMBLY__ -# define _ASM_EXTABLE(from,to) \ +# define _ASM_EXTABLE_HANDLE(from, to, handler) \ .pushsection "__ex_table","a" ; \ - .balign 8 ; \ + .balign 4 ; \ .long (from) - . ; \ .long (to) - . ; \ + .long (handler) - . ; \ .popsection -# define _ASM_EXTABLE_EX(from,to) \ - .pushsection "__ex_table","a" ; \ - .balign 8 ; \ - .long (from) - . ; \ - .long (to) - . + 0x7ffffff0 ; \ - .popsection +# define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) + +# define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) + +# define _ASM_EXTABLE_EX(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) # define _ASM_NOKPROBE(entry) \ .pushsection "_kprobe_blacklist","aw" ; \ @@ -89,19 +92,24 @@ .endm #else -# define _ASM_EXTABLE(from,to) \ +# define _EXPAND_EXTABLE_HANDLE(x) #x +# define _ASM_EXTABLE_HANDLE(from, to, handler) \ " .pushsection \"__ex_table\",\"a\"\n" \ - " .balign 8\n" \ + " .balign 4\n" \ " .long (" #from ") - .\n" \ " .long (" #to ") - .\n" \ + " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \ " .popsection\n" -# define _ASM_EXTABLE_EX(from,to) \ - " .pushsection \"__ex_table\",\"a\"\n" \ - " .balign 8\n" \ - " .long (" #from ") - .\n" \ - " .long (" #to ") - . + 0x7ffffff0\n" \ - " .popsection\n" +# define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) + +# define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) + +# define _ASM_EXTABLE_EX(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext) + /* For C file, we already have NOKPROBE_SYMBOL macro */ #endif diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index a584e1c..bfb28ca 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -6,18 +6,17 @@ /* * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking + * And yes, this might be required on UP too when we're talking * to devices. */ #ifdef CONFIG_X86_32 -/* - * Some non-Intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") +#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") +#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") #else #define mb() asm volatile("mfence":::"memory") #define rmb() asm volatile("lfence":::"memory") diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index e63aa38..61518cf 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size); #define mmio_flush_range(addr, size) clflush_cache_range(addr, size) -#ifdef CONFIG_DEBUG_RODATA -void mark_rodata_ro(void); extern const int rodata_test_data; extern int kernel_set_to_readonly; void set_kernel_text_rw(void); void set_kernel_text_ro(void); -#else -static inline void set_kernel_text_rw(void) { } -static inline void set_kernel_text_ro(void) { } -#endif #ifdef CONFIG_DEBUG_RODATA_TEST int rodata_test(void); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1514753..15340e3 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -256,7 +256,7 @@ extern int force_personality32; instruction set this CPU supports. This could be done in user space, but it's not easy, and we've already done it here. */ -#define ELF_HWCAP (boot_cpu_data.x86_capability[0]) +#define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index af30fde..f23cd8c 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -20,16 +20,15 @@ /* Supported features which support lazy state saving */ #define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ - XFEATURE_MASK_SSE) - -/* Supported features which require eager state saving */ -#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | \ - XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_SSE | \ XFEATURE_MASK_YMM | \ XFEATURE_MASK_OPMASK | \ XFEATURE_MASK_ZMM_Hi256 | \ XFEATURE_MASK_Hi16_ZMM) +/* Supported features which require eager state saving */ +#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR) + /* All currently supported features */ #define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c1adf33..bc62e7c 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void) } #endif /* CONFIG_KVM_GUEST */ -#ifdef CONFIG_DEBUG_RODATA #define KVM_HYPERCALL \ ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL) -#else -/* On AMD processors, vmcall will generate a trap that we will - * then rewrite to the appropriate instruction. - */ -#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" -#endif /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall * instruction. The hypervisor may replace it with something else but only the diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 18d2ba9..92b6f65 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -40,8 +40,20 @@ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ /* AMD-specific bits */ -#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */ +#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ +#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */ + +/* + * McaX field if set indicates a given bank supports MCA extensions: + * - Deferred error interrupt type is specifiable by bank. + * - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers, + * But should not be used to determine MSR numbers. + * - TCC bit is present in MCx_STATUS. + */ +#define MCI_CONFIG_MCAX 0x1 +#define MCI_IPID_MCATYPE 0xFFFF0000 +#define MCI_IPID_HWID 0xFFF /* * Note that the full MCACOD field of IA32_MCi_STATUS MSR is @@ -91,6 +103,16 @@ #define MCE_LOG_LEN 32 #define MCE_LOG_SIGNATURE "MACHINECHECK" +/* AMD Scalable MCA */ +#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_MISC1 0xc000200a +#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_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) + /* * This structure contains all data related to the MCE log. Also * carries a signature to make it easier to find from external @@ -288,4 +310,49 @@ struct cper_sec_mem_err; extern void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err); +/* + * Enumerate new IP types and HWID values in AMD processors which support + * Scalable MCA. + */ +#ifdef CONFIG_X86_MCE_AMD +enum amd_ip_types { + SMCA_F17H_CORE = 0, /* Core errors */ + SMCA_DF, /* Data Fabric */ + SMCA_UMC, /* Unified Memory Controller */ + SMCA_PB, /* Parameter Block */ + SMCA_PSP, /* Platform Security Processor */ + SMCA_SMU, /* System Management Unit */ + N_AMD_IP_TYPES +}; + +struct amd_hwid { + const char *name; + unsigned int hwid; +}; + +extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES]; + +enum amd_core_mca_blocks { + SMCA_LS = 0, /* Load Store */ + SMCA_IF, /* Instruction Fetch */ + SMCA_L2_CACHE, /* L2 cache */ + SMCA_DE, /* Decoder unit */ + RES, /* Reserved */ + SMCA_EX, /* Execution unit */ + SMCA_FP, /* Floating Point */ + SMCA_L3_CACHE, /* L3 cache */ + N_CORE_MCA_BLOCKS +}; + +extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS]; + +enum amd_df_mca_blocks { + SMCA_CS = 0, /* Coherent Slave */ + SMCA_PIE, /* Power management, Interrupts, etc */ + N_DF_BLOCKS +}; + +extern const char * const amd_df_mcablock_names[N_DF_BLOCKS]; +#endif + #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7bcb861..5a2ed3e 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -165,6 +165,7 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_ASIF BIT_ULL(60) #define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) #define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* * IBS cpuid feature detection diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 50a6dc8..983738a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -128,6 +128,8 @@ struct cpuinfo_x86 { u16 booted_cores; /* Physical processor id: */ u16 phys_proc_id; + /* Logical processor id: */ + u16 logical_proc_id; /* Core id: */ u16 cpu_core_id; /* Compute unit id */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 0a52424..13b6cdd 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -7,7 +7,7 @@ extern char __brk_base[], __brk_limit[]; extern struct exception_table_entry __stop___ex_table[]; -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; #endif diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index ff8b9a1..ca6ba36 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -78,6 +78,19 @@ int strcmp(const char *cs, const char *ct); #define memset(s, c, n) __memset(s, c, n) #endif +/** + * memcpy_mcsafe - copy memory with indication if a machine check happened + * + * @dst: destination address + * @src: source address + * @cnt: number of bytes to copy + * + * Low level memory copy function that catches machine checks + * + * Return true for success, false for fail + */ +bool memcpy_mcsafe(void *dst, const void *src, size_t cnt); + #endif /* __KERNEL__ */ #endif /* _ASM_X86_STRING_64_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 0fb4648..7f991bd5 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -119,12 +119,23 @@ static inline void setup_node_to_cpumask_map(void) { } extern const struct cpumask *cpu_coregroup_mask(int cpu); +#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id) #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) #ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) + +extern unsigned int __max_logical_packages; +#define topology_max_packages() (__max_logical_packages) +int topology_update_package_map(unsigned int apicid, unsigned int cpu); +extern int topology_phys_to_logical_pkg(unsigned int pkg); +#else +#define topology_max_packages() (1) +static inline int +topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } +static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a4a30e4..c0f27d7 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -90,12 +90,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un likely(!__range_not_ok(addr, size, user_addr_max())) /* - * The exception table consists of pairs of addresses relative to the - * exception table enty itself: the first is the address of an - * instruction that is allowed to fault, and the second is the address - * at which the program should continue. No registers are modified, - * so it is entirely up to the continuation code to figure out what to - * do. + * The exception table consists of triples of addresses relative to the + * exception table entry itself. The first address is of an instruction + * that is allowed to fault, the second is the target at which the program + * should continue. The third is a handler function to deal with the fault + * caused by the instruction in the first field. * * All the routines below use bits of fixup code that are out of line * with the main instruction path. This means when everything is well, @@ -104,13 +103,14 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un */ struct exception_table_entry { - int insn, fixup; + int insn, fixup, handler; }; /* This is not the generic standard exception_table_entry format */ #define ARCH_HAS_SORT_EXTABLE #define ARCH_HAS_SEARCH_EXTABLE -extern int fixup_exception(struct pt_regs *regs); +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/apic/apic.c b/arch/x86/kernel/apic/apic.c index 8a5cdda..531b961 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2078,6 +2078,20 @@ int generic_processor_info(int apicid, int version) cpu = cpumask_next_zero(-1, cpu_present_mask); /* + * This can happen on physical hotplug. The sanity check at boot time + * is done from native_smp_prepare_cpus() after num_possible_cpus() is + * established. + */ + if (topology_update_package_map(apicid, cpu) < 0) { + int thiscpu = max + disabled_cpus; + + pr_warning("ACPI: Package limit reached. Processor %d/0x%x ignored.\n", + thiscpu, apicid); + disabled_cpus++; + return -ENOSPC; + } + + /* * Validate version */ if (version == 0x0) { diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index faa7b52..0d373d7 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -30,33 +30,11 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o - -ifdef CONFIG_PERF_EVENTS -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o perf_event_amd_uncore.o -ifdef CONFIG_AMD_IOMMU -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o -endif -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_cstate.o - -obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ - perf_event_intel_uncore_snb.o \ - perf_event_intel_uncore_snbep.o \ - perf_event_intel_uncore_nhmex.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_msr.o -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_msr.o -endif - - obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o +obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a07956a..97c59fd 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -117,7 +117,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) void (*f_vide)(void); u64 d, d2; - printk(KERN_INFO "AMD K6 stepping B detected - "); + pr_info("AMD K6 stepping B detected - "); /* * It looks like AMD fixed the 2.6.2 bug and improved indirect @@ -133,10 +133,9 @@ static void init_amd_k6(struct cpuinfo_x86 *c) d = d2-d; if (d > 20*K6_BUG_LOOP) - printk(KERN_CONT - "system stability may be impaired when more than 32 MB are used.\n"); + pr_cont("system stability may be impaired when more than 32 MB are used.\n"); else - printk(KERN_CONT "probably OK (after B9730xxxx).\n"); + pr_cont("probably OK (after B9730xxxx).\n"); } /* K6 with old style WHCR */ @@ -154,7 +153,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) wbinvd(); wrmsr(MSR_K6_WHCR, l, h); local_irq_restore(flags); - printk(KERN_INFO "Enabling old style K6 write allocation for %d Mb\n", + pr_info("Enabling old style K6 write allocation for %d Mb\n", mbytes); } return; @@ -175,7 +174,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) wbinvd(); wrmsr(MSR_K6_WHCR, l, h); local_irq_restore(flags); - printk(KERN_INFO "Enabling new style K6 write allocation for %d Mb\n", + pr_info("Enabling new style K6 write allocation for %d Mb\n", mbytes); } @@ -202,7 +201,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c) */ if (c->x86_model >= 6 && c->x86_model <= 10) { if (!cpu_has(c, X86_FEATURE_XMM)) { - printk(KERN_INFO "Enabling disabled K7/SSE Support.\n"); + pr_info("Enabling disabled K7/SSE Support.\n"); msr_clear_bit(MSR_K7_HWCR, 15); set_cpu_cap(c, X86_FEATURE_XMM); } @@ -216,9 +215,8 @@ static void init_amd_k7(struct cpuinfo_x86 *c) if ((c->x86_model == 8 && c->x86_mask >= 1) || (c->x86_model > 8)) { rdmsr(MSR_K7_CLK_CTL, l, h); if ((l & 0xfff00000) != 0x20000000) { - printk(KERN_INFO - "CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", - l, ((l & 0x000fffff)|0x20000000)); + pr_info("CPU: CLK_CTL MSR was %x. Reprogramming to %x\n", + l, ((l & 0x000fffff)|0x20000000)); wrmsr(MSR_K7_CLK_CTL, (l & 0x000fffff)|0x20000000, h); } } @@ -485,7 +483,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) { unsigned long pfn = tseg >> PAGE_SHIFT; - printk(KERN_DEBUG "tseg: %010llx\n", tseg); + pr_debug("tseg: %010llx\n", tseg); if (pfn_range_is_mapped(pfn, pfn + 1)) set_memory_4k((unsigned long)__va(tseg), 1); } @@ -500,8 +498,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) rdmsrl(MSR_K7_HWCR, val); if (!(val & BIT(24))) - printk(KERN_WARNING FW_BUG "TSC doesn't count " - "with P0 frequency!\n"); + pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n"); } } diff --git a/arch/x86/kernel/cpu/bugs_64.c b/arch/x86/kernel/cpu/bugs_64.c index 04f0fe5..a972ac4 100644 --- a/arch/x86/kernel/cpu/bugs_64.c +++ b/arch/x86/kernel/cpu/bugs_64.c @@ -15,7 +15,7 @@ void __init check_bugs(void) { identify_boot_cpu(); #if !defined(CONFIG_SMP) - printk(KERN_INFO "CPU: "); + pr_info("CPU: "); print_cpu_info(&boot_cpu_data); #endif alternative_instructions(); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 6608c03..1661d8e 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -29,7 +29,7 @@ static void init_c3(struct cpuinfo_x86 *c) rdmsr(MSR_VIA_FCR, lo, hi); lo |= ACE_FCR; /* enable ACE unit */ wrmsr(MSR_VIA_FCR, lo, hi); - printk(KERN_INFO "CPU: Enabled ACE h/w crypto\n"); + pr_info("CPU: Enabled ACE h/w crypto\n"); } /* enable RNG unit, if present and disabled */ @@ -37,7 +37,7 @@ static void init_c3(struct cpuinfo_x86 *c) rdmsr(MSR_VIA_RNG, lo, hi); lo |= RNG_ENABLE; /* enable RNG unit */ wrmsr(MSR_VIA_RNG, lo, hi); - printk(KERN_INFO "CPU: Enabled h/w RNG\n"); + pr_info("CPU: Enabled h/w RNG\n"); } /* store Centaur Extended Feature Flags as @@ -130,7 +130,7 @@ static void init_centaur(struct cpuinfo_x86 *c) name = "C6"; fcr_set = ECX8|DSMC|EDCTLB|EMMX|ERETSTK; fcr_clr = DPDC; - printk(KERN_NOTICE "Disabling bugged TSC.\n"); + pr_notice("Disabling bugged TSC.\n"); clear_cpu_cap(c, X86_FEATURE_TSC); break; case 8: @@ -163,11 +163,11 @@ static void init_centaur(struct cpuinfo_x86 *c) newlo = (lo|fcr_set) & (~fcr_clr); if (newlo != lo) { - printk(KERN_INFO "Centaur FCR was 0x%X now 0x%X\n", + pr_info("Centaur FCR was 0x%X now 0x%X\n", lo, newlo); wrmsr(MSR_IDT_FCR1, newlo, hi); } else { - printk(KERN_INFO "Centaur FCR is 0x%X\n", lo); + pr_info("Centaur FCR is 0x%X\n", lo); } /* Emulate MTRRs using Centaur's MCR. */ set_cpu_cap(c, X86_FEATURE_CENTAUR_MCR); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d8337f3..4e8d25d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -228,7 +228,7 @@ static void squash_the_stupid_serial_number(struct cpuinfo_x86 *c) lo |= 0x200000; wrmsr(MSR_IA32_BBL_CR_CTL, lo, hi); - printk(KERN_NOTICE "CPU serial number disabled.\n"); + pr_notice("CPU serial number disabled.\n"); clear_cpu_cap(c, X86_FEATURE_PN); /* Disabling the serial number may affect the cpuid level */ @@ -329,9 +329,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn) if (!warn) continue; - printk(KERN_WARNING - "CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n", - x86_cap_flag(df->feature), df->level); + pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n", + x86_cap_flag(df->feature), df->level); } } @@ -510,7 +509,7 @@ void detect_ht(struct cpuinfo_x86 *c) smp_num_siblings = (ebx & 0xff0000) >> 16; if (smp_num_siblings == 1) { - printk_once(KERN_INFO "CPU0: Hyper-Threading is disabled\n"); + pr_info_once("CPU0: Hyper-Threading is disabled\n"); goto out; } @@ -531,10 +530,10 @@ void detect_ht(struct cpuinfo_x86 *c) out: if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) { - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - c->phys_proc_id); - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - c->cpu_core_id); + pr_info("CPU: Physical Processor ID: %d\n", + c->phys_proc_id); + pr_info("CPU: Processor Core ID: %d\n", + c->cpu_core_id); printed = 1; } #endif @@ -559,9 +558,8 @@ static void get_cpu_vendor(struct cpuinfo_x86 *c) } } - printk_once(KERN_ERR - "CPU: vendor_id '%s' unknown, using generic init.\n" \ - "CPU: Your system may be unstable.\n", v); + pr_err_once("CPU: vendor_id '%s' unknown, using generic init.\n" \ + "CPU: Your system may be unstable.\n", v); c->x86_vendor = X86_VENDOR_UNKNOWN; this_cpu = &default_cpu; @@ -760,7 +758,7 @@ void __init early_cpu_init(void) int count = 0; #ifdef CONFIG_PROCESSOR_SELECT - printk(KERN_INFO "KERNEL supported cpus:\n"); + pr_info("KERNEL supported cpus:\n"); #endif for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { @@ -778,7 +776,7 @@ void __init early_cpu_init(void) for (j = 0; j < 2; j++) { if (!cpudev->c_ident[j]) continue; - printk(KERN_INFO " %s %s\n", cpudev->c_vendor, + pr_info(" %s %s\n", cpudev->c_vendor, cpudev->c_ident[j]); } } @@ -1002,6 +1000,8 @@ static void identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif + /* The boot/hotplug time assigment got cleared, restore it */ + c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id); } /* @@ -1086,7 +1086,7 @@ static void __print_cpu_msr(void) for (index = index_min; index < index_max; index++) { if (rdmsrl_safe(index, &val)) continue; - printk(KERN_INFO " MSR%08x: %016llx\n", index, val); + pr_info(" MSR%08x: %016llx\n", index, val); } } } @@ -1125,19 +1125,19 @@ void print_cpu_info(struct cpuinfo_x86 *c) } if (vendor && !strstr(c->x86_model_id, vendor)) - printk(KERN_CONT "%s ", vendor); + pr_cont("%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", c->x86_model_id); + pr_cont("%s", c->x86_model_id); else - printk(KERN_CONT "%d86", c->x86); + pr_cont("%d86", c->x86); - printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model); + pr_cont(" (family: 0x%x, model: 0x%x", c->x86, c->x86_model); if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask); + pr_cont(", stepping: 0x%x)\n", c->x86_mask); else - printk(KERN_CONT ")\n"); + pr_cont(")\n"); print_cpu_msr(c); } @@ -1463,7 +1463,7 @@ void cpu_init(void) show_ucode_info_early(); - printk(KERN_INFO "Initializing CPU#%d\n", cpu); + pr_info("Initializing CPU#%d\n", cpu); if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 15e47c1..6adef9c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -104,7 +104,7 @@ static void check_cx686_slop(struct cpuinfo_x86 *c) local_irq_restore(flags); if (ccr5 & 2) { /* possible wrong calibration done */ - printk(KERN_INFO "Recalibrating delay loop with SLOP bit reset\n"); + pr_info("Recalibrating delay loop with SLOP bit reset\n"); calibrate_delay(); c->loops_per_jiffy = loops_per_jiffy; } @@ -116,7 +116,7 @@ static void set_cx86_reorder(void) { u8 ccr3; - printk(KERN_INFO "Enable Memory access reorder on Cyrix/NSC processor.\n"); + pr_info("Enable Memory access reorder on Cyrix/NSC processor.\n"); ccr3 = getCx86(CX86_CCR3); setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ @@ -129,7 +129,7 @@ static void set_cx86_reorder(void) static void set_cx86_memwb(void) { - printk(KERN_INFO "Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); + pr_info("Enable Memory-Write-back mode on Cyrix/NSC processor.\n"); /* CCR2 bit 2: unlock NW bit */ setCx86_old(CX86_CCR2, getCx86_old(CX86_CCR2) & ~0x04); @@ -269,7 +269,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) * VSA1 we work around however. */ - printk(KERN_INFO "Working around Cyrix MediaGX virtual DMA bugs.\n"); + pr_info("Working around Cyrix MediaGX virtual DMA bugs.\n"); isa_dma_bridge_buggy = 2; /* We do this before the PCI layer is running. However we @@ -427,7 +427,7 @@ static void cyrix_identify(struct cpuinfo_x86 *c) if (dir0 == 5 || dir0 == 3) { unsigned char ccr3; unsigned long flags; - printk(KERN_INFO "Enabling CPUID on Cyrix processor.\n"); + pr_info("Enabling CPUID on Cyrix processor.\n"); local_irq_save(flags); ccr3 = getCx86(CX86_CCR3); /* enable MAPEN */ diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index d820d8e..73d391a 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -56,7 +56,7 @@ detect_hypervisor_vendor(void) } if (max_pri) - printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name); + pr_info("Hypervisor detected: %s\n", x86_hyper->name); } void init_hypervisor(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9299e3b..1f7fdb9 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -61,7 +61,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2 && c->microcode < 0x20e) { - printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n"); + pr_warn("Atom PSE erratum detected, BIOS microcode update recommended\n"); clear_cpu_cap(c, X86_FEATURE_PSE); } @@ -140,7 +140,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable); if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) { - printk(KERN_INFO "Disabled fast string operations\n"); + pr_info("Disabled fast string operations\n"); setup_clear_cpu_cap(X86_FEATURE_REP_GOOD); setup_clear_cpu_cap(X86_FEATURE_ERMS); } @@ -160,6 +160,19 @@ static void early_init_intel(struct cpuinfo_x86 *c) pr_info("Disabling PGE capability bit\n"); setup_clear_cpu_cap(X86_FEATURE_PGE); } + + if (c->cpuid_level >= 0x00000001) { + u32 eax, ebx, ecx, edx; + + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); + /* + * If HTT (EDX[28]) is set EBX[16:23] contain the number of + * apicids which are reserved per package. Store the resulting + * shift value for the package management code. + */ + if (edx & (1U << 28)) + c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); + } } #ifdef CONFIG_X86_32 @@ -176,7 +189,7 @@ int ppro_with_ram_bug(void) boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_mask < 8) { - printk(KERN_INFO "Pentium Pro with Errata#50 detected. Taking evasive action.\n"); + pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n"); return 1; } return 0; @@ -225,7 +238,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_F00F); if (!f00f_workaround_enabled) { - printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n"); + pr_notice("Intel Pentium with F0 0F bug - workaround enabled.\n"); f00f_workaround_enabled = 1; } } @@ -244,7 +257,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c) * Forcefully enable PAE if kernel parameter "forcepae" is present. */ if (forcepae) { - printk(KERN_WARNING "PAE forced!\n"); + pr_warn("PAE forced!\n"); set_cpu_cap(c, X86_FEATURE_PAE); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE); } diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 341449c..de6626c 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -444,7 +444,7 @@ static ssize_t store_cache_disable(struct cacheinfo *this_leaf, err = amd_set_l3_disable_slot(nb, cpu, slot, val); if (err) { if (err == -EEXIST) - pr_warning("L3 slot %d in use/index already disabled!\n", + pr_warn("L3 slot %d in use/index already disabled!\n", slot); return err; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 4cfba43..517619e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -115,7 +115,7 @@ static int raise_local(void) int cpu = m->extcpu; if (m->inject_flags & MCJ_EXCEPTION) { - printk(KERN_INFO "Triggering MCE exception on CPU %d\n", cpu); + pr_info("Triggering MCE exception on CPU %d\n", cpu); switch (context) { case MCJ_CTX_IRQ: /* @@ -128,15 +128,15 @@ static int raise_local(void) raise_exception(m, NULL); break; default: - printk(KERN_INFO "Invalid MCE context\n"); + pr_info("Invalid MCE context\n"); ret = -EINVAL; } - printk(KERN_INFO "MCE exception done on CPU %d\n", cpu); + pr_info("MCE exception done on CPU %d\n", cpu); } else if (m->status) { - printk(KERN_INFO "Starting machine check poll CPU %d\n", cpu); + pr_info("Starting machine check poll CPU %d\n", cpu); raise_poll(m); mce_notify_irq(); - printk(KERN_INFO "Machine check poll done on CPU %d\n", cpu); + pr_info("Machine check poll done on CPU %d\n", cpu); } else m->finished = 0; @@ -183,8 +183,7 @@ static void raise_mce(struct mce *m) start = jiffies; while (!cpumask_empty(mce_inject_cpumask)) { if (!time_before(jiffies, start + 2*HZ)) { - printk(KERN_ERR - "Timeout waiting for mce inject %lx\n", + pr_err("Timeout waiting for mce inject %lx\n", *cpumask_bits(mce_inject_cpumask)); break; } @@ -241,7 +240,7 @@ static int inject_init(void) { if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) return -ENOMEM; - printk(KERN_INFO "Machine check injector initialized\n"); + pr_info("Machine check injector initialized\n"); register_mce_write_callback(mce_write); register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify"); diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 9c682c2..5119766 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/debugfs.h> #include <asm/mce.h> +#include <asm/uaccess.h> #include "mce-internal.h" @@ -29,7 +30,7 @@ * panic situations) */ -enum context { IN_KERNEL = 1, IN_USER = 2 }; +enum context { IN_KERNEL = 1, IN_USER = 2, IN_KERNEL_RECOV = 3 }; enum ser { SER_REQUIRED = 1, NO_SER = 2 }; enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 }; @@ -48,6 +49,7 @@ static struct severity { #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c } #define KERNEL .context = IN_KERNEL #define USER .context = IN_USER +#define KERNEL_RECOV .context = IN_KERNEL_RECOV #define SER .ser = SER_REQUIRED #define NOSER .ser = NO_SER #define EXCP .excp = EXCP_CONTEXT @@ -87,6 +89,10 @@ static struct severity { EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) ), MCESEV( + PANIC, "In kernel and no restart IP", + EXCP, KERNEL_RECOV, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( DEFERRED, "Deferred error", NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED) ), @@ -123,6 +129,11 @@ static struct severity { MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV) ), MCESEV( + AR, "Action required: data load in error recoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL_RECOV + ), + MCESEV( AR, "Action required: data load error in a user process", SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), USER @@ -170,6 +181,9 @@ static struct severity { ) /* always matches. keep at end */ }; +#define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \ + (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) + /* * If mcgstatus indicated that ip/cs on the stack were * no good, then "m->cs" will be zero and we will have @@ -183,7 +197,11 @@ static struct severity { */ static int error_context(struct mce *m) { - return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; + if ((m->cs & 3) == 3) + return IN_USER; + if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) + return IN_KERNEL_RECOV; + return IN_KERNEL; } /* diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index b5b187c..f0c921b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -961,6 +961,20 @@ static void mce_clear_state(unsigned long *toclear) } } +static int do_memory_failure(struct mce *m) +{ + int flags = MF_ACTION_REQUIRED; + int ret; + + pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr); + if (!(m->mcgstatus & MCG_STATUS_RIPV)) + flags |= MF_MUST_KILL; + ret = memory_failure(m->addr >> PAGE_SHIFT, MCE_VECTOR, flags); + if (ret) + pr_err("Memory error not recovered"); + return ret; +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -998,8 +1012,6 @@ 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"; - u64 recover_paddr = ~0ull; - int flags = MF_ACTION_REQUIRED; int lmce = 0; /* If this CPU is offline, just bail out. */ @@ -1136,22 +1148,13 @@ void do_machine_check(struct pt_regs *regs, long error_code) } /* - * At insane "tolerant" levels we take no action. Otherwise - * we only die if we have no other choice. For less serious - * issues we try to recover, or limit damage to the current - * process. + * If tolerant is at an insane level we drop requests to kill + * processes and continue even when there is no way out. */ - if (cfg->tolerant < 3) { - if (no_way_out) - mce_panic("Fatal machine check on current CPU", &m, msg); - if (worst == MCE_AR_SEVERITY) { - recover_paddr = m.addr; - if (!(m.mcgstatus & MCG_STATUS_RIPV)) - flags |= MF_MUST_KILL; - } else if (kill_it) { - force_sig(SIGBUS, current); - } - } + if (cfg->tolerant == 3) + kill_it = 0; + else if (no_way_out) + mce_panic("Fatal machine check on current CPU", &m, msg); if (worst > 0) mce_report_event(regs); @@ -1159,25 +1162,24 @@ void do_machine_check(struct pt_regs *regs, long error_code) out: sync_core(); - if (recover_paddr == ~0ull) - goto done; + if (worst != MCE_AR_SEVERITY && !kill_it) + goto out_ist; - pr_err("Uncorrected hardware memory error in user-access at %llx", - recover_paddr); - /* - * We must call memory_failure() here even if the current process is - * doomed. We still need to mark the page as poisoned and alert any - * other users of the page. - */ - ist_begin_non_atomic(regs); - local_irq_enable(); - if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) { - pr_err("Memory error not recovered"); - force_sig(SIGBUS, current); + /* Fault was in user mode and we need to take some action */ + if ((m.cs & 3) == 3) { + ist_begin_non_atomic(regs); + local_irq_enable(); + + if (kill_it || do_memory_failure(&m)) + force_sig(SIGBUS, current); + local_irq_disable(); + ist_end_non_atomic(); + } else { + if (!fixup_exception(regs, X86_TRAP_MC)) + mce_panic("Failed kernel mode recovery", &m, NULL); } - local_irq_disable(); - ist_end_non_atomic(); -done: + +out_ist: ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1628,10 +1630,10 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) case X86_VENDOR_AMD: { u32 ebx = cpuid_ebx(0x80000007); - mce_amd_feature_init(c); mce_flags.overflow_recov = !!(ebx & BIT(0)); mce_flags.succor = !!(ebx & BIT(1)); mce_flags.smca = !!(ebx & BIT(3)); + mce_amd_feature_init(c); break; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index e99b150..9d656fd 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1,5 +1,5 @@ /* - * (c) 2005-2015 Advanced Micro Devices, Inc. + * (c) 2005-2016 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html @@ -28,7 +28,7 @@ #include <asm/msr.h> #include <asm/trace/irq_vectors.h> -#define NR_BLOCKS 9 +#define NR_BLOCKS 5 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 #define MASK_VALID_HI 0x80000000 @@ -49,6 +49,19 @@ #define DEF_LVT_OFF 0x2 #define DEF_INT_TYPE_APIC 0x2 +/* Scalable MCA: */ + +/* 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", @@ -58,6 +71,35 @@ static const char * const th_names[] = { "execution_unit", }; +/* Define HWID to IP type mappings for Scalable MCA */ +struct amd_hwid amd_hwids[] = { + [SMCA_F17H_CORE] = { "f17h_core", 0xB0 }, + [SMCA_DF] = { "data_fabric", 0x2E }, + [SMCA_UMC] = { "umc", 0x96 }, + [SMCA_PB] = { "param_block", 0x5 }, + [SMCA_PSP] = { "psp", 0xFF }, + [SMCA_SMU] = { "smu", 0x1 }, +}; +EXPORT_SYMBOL_GPL(amd_hwids); + +const char * const amd_core_mcablock_names[] = { + [SMCA_LS] = "load_store", + [SMCA_IF] = "insn_fetch", + [SMCA_L2_CACHE] = "l2_cache", + [SMCA_DE] = "decode_unit", + [RES] = "", + [SMCA_EX] = "execution_unit", + [SMCA_FP] = "floating_point", + [SMCA_L3_CACHE] = "l3_cache", +}; +EXPORT_SYMBOL_GPL(amd_core_mcablock_names); + +const char * const amd_df_mcablock_names[] = { + [SMCA_CS] = "coherent_slave", + [SMCA_PIE] = "pie", +}; +EXPORT_SYMBOL_GPL(amd_df_mcablock_names); + static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ @@ -84,6 +126,13 @@ struct thresh_restart { static inline bool is_shared_bank(int bank) { + /* + * Scalable MCA provides for only one core to have access to the MSRs of + * a shared bank. + */ + if (mce_flags.smca) + return false; + /* Bank 4 is for northbridge reporting and is thus shared */ return (bank == 4); } @@ -135,6 +184,14 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) } if (apic != msr) { + /* + * On SMCA CPUs, LVT offset is programmed at a different MSR, and + * the BIOS provides the value. The original field where LVT offset + * was set is reserved. Return early here: + */ + if (mce_flags.smca) + return 0; + pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, apic, b->bank, b->block, b->address, hi, lo); @@ -144,10 +201,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) return 1; }; -/* - * Called via smp_call_function_single(), must be called with correct - * cpu affinity. - */ +/* Reprogram MCx_MISC MSR behind this threshold bank. */ static void threshold_restart_bank(void *_tr) { struct thresh_restart *tr = _tr; @@ -247,27 +301,116 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) wrmsr(MSR_CU_DEF_ERR, low, high); } +static u32 get_block_address(u32 current_addr, u32 low, u32 high, + unsigned int bank, unsigned int block) +{ + u32 addr = 0, offset = 0; + + if (mce_flags.smca) { + if (!block) { + addr = MSR_AMD64_SMCA_MCx_MISC(bank); + } else { + /* + * For SMCA enabled processors, BLKPTR field of the + * first MISC register (MCx_MISC0) indicates presence of + * additional MISC register set (MISC1-4). + */ + u32 low, high; + + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + return addr; + + if (!(low & MCI_CONFIG_MCAX)) + return addr; + + if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) && + (low & MASK_BLKPTR_LO)) + addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); + } + return addr; + } + + /* Fall back to method we used for older processors: */ + switch (block) { + case 0: + addr = MSR_IA32_MCx_MISC(bank); + break; + case 1: + offset = ((low & MASK_BLKPTR_LO) >> 21); + if (offset) + addr = MCG_XBLK_ADDR + offset; + break; + default: + addr = ++current_addr; + } + return addr; +} + +static int +prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, + int offset, u32 misc_high) +{ + unsigned int cpu = smp_processor_id(); + struct threshold_block b; + int new; + + if (!block) + per_cpu(bank_map, cpu) |= (1 << bank); + + memset(&b, 0, sizeof(b)); + b.cpu = cpu; + b.bank = bank; + b.block = block; + b.address = addr; + b.interrupt_capable = lvt_interrupt_supported(bank, misc_high); + + if (!b.interrupt_capable) + goto done; + + b.interrupt_enable = 1; + + if (mce_flags.smca) { + u32 smca_low, smca_high; + u32 smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); + + if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { + smca_high |= SMCA_MCAX_EN_OFF; + 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; + } else { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + } + + offset = setup_APIC_mce_threshold(offset, new); + + if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) + mce_threshold_vector = amd_threshold_interrupt; + +done: + mce_threshold_block_init(&b, offset); + +out: + return offset; +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { - struct threshold_block b; - unsigned int cpu = smp_processor_id(); u32 low = 0, high = 0, address = 0; unsigned int bank, block; - int offset = -1, new; + int offset = -1; for (bank = 0; bank < mca_cfg.banks; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { - if (block == 0) - address = MSR_IA32_MCx_MISC(bank); - else if (block == 1) { - address = (low & MASK_BLKPTR_LO) >> 21; - if (!address) - break; - - address += MCG_XBLK_ADDR; - } else - ++address; + address = get_block_address(address, low, high, bank, block); + if (!address) + break; if (rdmsr_safe(address, &low, &high)) break; @@ -279,29 +422,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) (high & MASK_LOCKED_HI)) continue; - if (!block) - per_cpu(bank_map, cpu) |= (1 << bank); - - memset(&b, 0, sizeof(b)); - b.cpu = cpu; - b.bank = bank; - b.block = block; - b.address = address; - b.interrupt_capable = lvt_interrupt_supported(bank, high); - - if (!b.interrupt_capable) - goto init; - - b.interrupt_enable = 1; - new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce_threshold(offset, new); - - if ((offset == new) && - (mce_threshold_vector != amd_threshold_interrupt)) - mce_threshold_vector = amd_threshold_interrupt; - -init: - mce_threshold_block_init(&b, offset); + offset = prepare_threshold_block(bank, block, address, offset, high); } } @@ -394,16 +515,9 @@ static void amd_threshold_interrupt(void) if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; for (block = 0; block < NR_BLOCKS; ++block) { - if (block == 0) { - address = MSR_IA32_MCx_MISC(bank); - } else if (block == 1) { - address = (low & MASK_BLKPTR_LO) >> 21; - if (!address) - break; - address += MCG_XBLK_ADDR; - } else { - ++address; - } + address = get_block_address(address, low, high, bank, block); + if (!address) + break; if (rdmsr_safe(address, &low, &high)) break; @@ -623,16 +737,11 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, if (err) goto out_free; recurse: - if (!block) { - address = (low & MASK_BLKPTR_LO) >> 21; - if (!address) - return 0; - address += MCG_XBLK_ADDR; - } else { - ++address; - } + address = get_block_address(address, low, high, bank, ++block); + if (!address) + return 0; - err = allocate_threshold_blocks(cpu, bank, ++block, address); + err = allocate_threshold_blocks(cpu, bank, block, address); if (err) goto out_free; diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c index 12402e1..2a0717b 100644 --- a/arch/x86/kernel/cpu/mcheck/p5.c +++ b/arch/x86/kernel/cpu/mcheck/p5.c @@ -26,14 +26,12 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); - printk(KERN_EMERG - "CPU#%d: Machine Check Exception: 0x%8X (type 0x%8X).\n", - smp_processor_id(), loaddr, lotype); + pr_emerg("CPU#%d: Machine Check Exception: 0x%8X (type 0x%8X).\n", + smp_processor_id(), loaddr, lotype); if (lotype & (1<<5)) { - printk(KERN_EMERG - "CPU#%d: Possible thermal failure (CPU on fire ?).\n", - smp_processor_id()); + pr_emerg("CPU#%d: Possible thermal failure (CPU on fire ?).\n", + smp_processor_id()); } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); @@ -61,12 +59,10 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c) /* Read registers before enabling: */ rdmsr(MSR_IA32_P5_MC_ADDR, l, h); rdmsr(MSR_IA32_P5_MC_TYPE, l, h); - printk(KERN_INFO - "Intel old style machine check architecture supported.\n"); + pr_info("Intel old style machine check architecture supported.\n"); /* Enable MCE: */ cr4_set_bits(X86_CR4_MCE); - printk(KERN_INFO - "Intel old style machine check reporting enabled on CPU#%d.\n", - smp_processor_id()); + pr_info("Intel old style machine check reporting enabled on CPU#%d.\n", + smp_processor_id()); } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2c5aaf8..0b445c2 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -190,7 +190,7 @@ static int therm_throt_process(bool new_event, int event, int level) /* if we just entered the thermal event */ if (new_event) { if (event == THERMAL_THROTTLING_EVENT) - printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", + pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package", state->count); @@ -198,8 +198,7 @@ static int therm_throt_process(bool new_event, int event, int level) } if (old_event) { if (event == THERMAL_THROTTLING_EVENT) - printk(KERN_INFO "CPU%d: %s temperature/speed normal\n", - this_cpu, + pr_info("CPU%d: %s temperature/speed normal\n", this_cpu, level == CORE_LEVEL ? "Core" : "Package"); return 1; } @@ -417,8 +416,8 @@ static void intel_thermal_interrupt(void) static void unexpected_thermal_interrupt(void) { - printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n", - smp_processor_id()); + pr_err("CPU%d: Unexpected LVT thermal interrupt!\n", + smp_processor_id()); } static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; @@ -499,7 +498,7 @@ void intel_init_thermal(struct cpuinfo_x86 *c) if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) { if (system_state == SYSTEM_BOOTING) - printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu); + pr_debug("CPU%d: Thermal monitoring handled by SMI\n", cpu); return; } @@ -557,8 +556,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c) l = apic_read(APIC_LVTTHMR); apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - printk_once(KERN_INFO "CPU0: Thermal monitoring enabled (%s)\n", - tm2 ? "TM2" : "TM1"); + pr_info_once("CPU0: Thermal monitoring enabled (%s)\n", + tm2 ? "TM2" : "TM1"); /* enable thermal throttle processing */ atomic_set(&therm_throt_en, 1); diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index 7245980..fcf9ae9 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -12,8 +12,8 @@ static void default_threshold_interrupt(void) { - printk(KERN_ERR "Unexpected threshold interrupt at vector %x\n", - THRESHOLD_APIC_VECTOR); + pr_err("Unexpected threshold interrupt at vector %x\n", + THRESHOLD_APIC_VECTOR); } void (*mce_threshold_vector)(void) = default_threshold_interrupt; diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c index 01dd870..c6a722e 100644 --- a/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/arch/x86/kernel/cpu/mcheck/winchip.c @@ -17,7 +17,7 @@ static void winchip_machine_check(struct pt_regs *regs, long error_code) { ist_enter(regs); - printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); + pr_emerg("CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); ist_exit(regs); @@ -39,6 +39,5 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c) cr4_set_bits(X86_CR4_MCE); - printk(KERN_INFO - "Winchip machine check reporting enabled on CPU#0.\n"); + pr_info("Winchip machine check reporting enabled on CPU#0.\n"); } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 2233f8a..75d3aab 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -953,7 +953,7 @@ struct microcode_ops * __init init_amd_microcode(void) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { - pr_warning("AMD CPU family 0x%x not supported\n", c->x86); + pr_warn("AMD CPU family 0x%x not supported\n", c->x86); return NULL; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 20e242e..4e7c693 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -161,8 +161,8 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); - printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", - ms_hyperv.features, ms_hyperv.hints); + pr_info("HyperV: features 0x%x, hints 0x%x\n", + ms_hyperv.features, ms_hyperv.hints); #ifdef CONFIG_X86_LOCAL_APIC if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { @@ -174,8 +174,8 @@ static void __init ms_hyperv_init_platform(void) rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency); hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ); lapic_timer_frequency = hv_lapic_frequency; - printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n", - lapic_timer_frequency); + pr_info("HyperV: LAPIC Timer Frequency: %#x\n", + lapic_timer_frequency); } #endif diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index 316fe3e..3d68993 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -103,7 +103,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t */ if (type != MTRR_TYPE_WRCOMB && (centaur_mcr_type == 0 || type != MTRR_TYPE_UNCACHABLE)) { - pr_warning("mtrr: only write-combining%s supported\n", + pr_warn("mtrr: only write-combining%s supported\n", centaur_mcr_type ? " and uncacheable are" : " is"); return -EINVAL; } diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 0d98503..31e951c 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -57,9 +57,9 @@ static int __initdata nr_range; static struct var_mtrr_range_state __initdata range_state[RANGE_NUM]; static int __initdata debug_print; -#define Dprintk(x...) do { if (debug_print) printk(KERN_DEBUG x); } while (0) +#define Dprintk(x...) do { if (debug_print) pr_debug(x); } while (0) -#define BIOS_BUG_MSG KERN_WARNING \ +#define BIOS_BUG_MSG \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" static int __init @@ -81,9 +81,9 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, base, base + size); } if (debug_print) { - printk(KERN_DEBUG "After WB checking\n"); + pr_debug("After WB checking\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + pr_debug("MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end); } @@ -101,7 +101,7 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { /* Var MTRR contains UC entry below 1M? Skip it: */ - printk(BIOS_BUG_MSG, i); + pr_warn(BIOS_BUG_MSG, i); if (base + size <= (1<<(20-PAGE_SHIFT))) continue; size -= (1<<(20-PAGE_SHIFT)) - base; @@ -114,11 +114,11 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, extra_remove_base + extra_remove_size); if (debug_print) { - printk(KERN_DEBUG "After UC checking\n"); + pr_debug("After UC checking\n"); for (i = 0; i < RANGE_NUM; i++) { if (!range[i].end) continue; - printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + pr_debug("MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end); } } @@ -126,9 +126,9 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, /* sort the ranges */ nr_range = clean_sort_range(range, RANGE_NUM); if (debug_print) { - printk(KERN_DEBUG "After sorting\n"); + pr_debug("After sorting\n"); for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG "MTRR MAP PFN: %016llx - %016llx\n", + pr_debug("MTRR MAP PFN: %016llx - %016llx\n", range[i].start, range[i].end); } @@ -544,7 +544,7 @@ static void __init print_out_mtrr_range_state(void) start_base = to_size_factor(start_base, &start_factor), type = range_state[i].type; - printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n", + pr_debug("reg %d, base: %ld%cB, range: %ld%cB, type %s\n", i, start_base, start_factor, size_base, size_factor, (type == MTRR_TYPE_UNCACHABLE) ? "UC" : @@ -713,7 +713,7 @@ int __init mtrr_cleanup(unsigned address_bits) return 0; /* Print original var MTRRs at first, for debugging: */ - printk(KERN_DEBUG "original variable MTRRs\n"); + pr_debug("original variable MTRRs\n"); print_out_mtrr_range_state(); memset(range, 0, sizeof(range)); @@ -733,7 +733,7 @@ int __init mtrr_cleanup(unsigned address_bits) x_remove_base, x_remove_size); range_sums = sum_ranges(range, nr_range); - printk(KERN_INFO "total RAM covered: %ldM\n", + pr_info("total RAM covered: %ldM\n", range_sums >> (20 - PAGE_SHIFT)); if (mtrr_chunk_size && mtrr_gran_size) { @@ -745,12 +745,11 @@ int __init mtrr_cleanup(unsigned address_bits) if (!result[i].bad) { set_var_mtrr_all(address_bits); - printk(KERN_DEBUG "New variable MTRRs\n"); + pr_debug("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } - printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, " - "will find optimal one\n"); + pr_info("invalid mtrr_gran_size or mtrr_chunk_size, will find optimal one\n"); } i = 0; @@ -768,7 +767,7 @@ int __init mtrr_cleanup(unsigned address_bits) x_remove_base, x_remove_size, i); if (debug_print) { mtrr_print_out_one_result(i); - printk(KERN_INFO "\n"); + pr_info("\n"); } i++; @@ -779,7 +778,7 @@ int __init mtrr_cleanup(unsigned address_bits) index_good = mtrr_search_optimal_index(); if (index_good != -1) { - printk(KERN_INFO "Found optimal setting for mtrr clean up\n"); + pr_info("Found optimal setting for mtrr clean up\n"); i = index_good; mtrr_print_out_one_result(i); @@ -790,7 +789,7 @@ int __init mtrr_cleanup(unsigned address_bits) gran_size <<= 10; x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size); set_var_mtrr_all(address_bits); - printk(KERN_DEBUG "New variable MTRRs\n"); + pr_debug("New variable MTRRs\n"); print_out_mtrr_range_state(); return 1; } else { @@ -799,8 +798,8 @@ int __init mtrr_cleanup(unsigned address_bits) mtrr_print_out_one_result(i); } - printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n"); - printk(KERN_INFO "please specify mtrr_gran_size/mtrr_chunk_size\n"); + pr_info("mtrr_cleanup: can not find optimal value\n"); + pr_info("please specify mtrr_gran_size/mtrr_chunk_size\n"); return 0; } @@ -918,7 +917,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all: */ if (!highest_pfn) { - printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n"); + pr_info("CPU MTRRs all blank - virtualized system.\n"); return 0; } @@ -973,7 +972,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) end_pfn); if (total_trim_size) { - pr_warning("WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing %lluMB of RAM.\n", total_trim_size >> 20); + pr_warn("WARNING: BIOS bug: CPU MTRRs don't cover all of memory, losing %lluMB of RAM.\n", + total_trim_size >> 20); if (!changed_by_mtrr_cleanup) WARN_ON(1); diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index c870af1..fcbcb2f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -55,7 +55,7 @@ static inline void k8_check_syscfg_dram_mod_en(void) rdmsr(MSR_K8_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { - printk(KERN_ERR FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" + pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" " not cleared by BIOS, clearing this bit\n", smp_processor_id()); lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; @@ -501,14 +501,14 @@ void __init mtrr_state_warn(void) if (!mask) return; if (mask & MTRR_CHANGE_MASK_FIXED) - pr_warning("mtrr: your CPUs had inconsistent fixed MTRR settings\n"); + pr_warn("mtrr: your CPUs had inconsistent fixed MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_VARIABLE) - pr_warning("mtrr: your CPUs had inconsistent variable MTRR settings\n"); + pr_warn("mtrr: your CPUs had inconsistent variable MTRR settings\n"); if (mask & MTRR_CHANGE_MASK_DEFTYPE) - pr_warning("mtrr: your CPUs had inconsistent MTRRdefType settings\n"); + pr_warn("mtrr: your CPUs had inconsistent MTRRdefType settings\n"); - printk(KERN_INFO "mtrr: probably your BIOS does not setup all CPUs.\n"); - printk(KERN_INFO "mtrr: corrected configuration.\n"); + pr_info("mtrr: probably your BIOS does not setup all CPUs.\n"); + pr_info("mtrr: corrected configuration.\n"); } /* @@ -519,8 +519,7 @@ void __init mtrr_state_warn(void) void mtrr_wrmsr(unsigned msr, unsigned a, unsigned b) { if (wrmsr_safe(msr, a, b) < 0) { - printk(KERN_ERR - "MTRR: CPU %u: Writing MSR %x to %x:%x failed\n", + pr_err("MTRR: CPU %u: Writing MSR %x to %x:%x failed\n", smp_processor_id(), msr, a, b); } } @@ -607,7 +606,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, tmp |= ~((1ULL<<(hi - 1)) - 1); if (tmp != mask) { - printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); + pr_warn("mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); mask = tmp; } @@ -858,13 +857,13 @@ int generic_validate_add_page(unsigned long base, unsigned long size, boot_cpu_data.x86_model == 1 && boot_cpu_data.x86_mask <= 7) { if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) { - pr_warning("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); + pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base); return -EINVAL; } if (!(base + size < 0x70000 || base > 0x7003F) && (type == MTRR_TYPE_WRCOMB || type == MTRR_TYPE_WRBACK)) { - pr_warning("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); + pr_warn("mtrr: writable mtrr between 0x70000000 and 0x7003FFFF may hang the CPU.\n"); return -EINVAL; } } @@ -878,7 +877,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size, lbase = lbase >> 1, last = last >> 1) ; if (lbase != last) { - pr_warning("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size); + pr_warn("mtrr: base(0x%lx000) is not aligned on a size(0x%lx000) boundary\n", base, size); return -EINVAL; } return 0; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 74f1d90..10f8d47 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -300,24 +300,24 @@ int mtrr_add_page(unsigned long base, unsigned long size, return error; if (type >= MTRR_NUM_TYPES) { - pr_warning("mtrr: type: %u invalid\n", type); + pr_warn("mtrr: type: %u invalid\n", type); return -EINVAL; } /* If the type is WC, check that this processor supports it */ if ((type == MTRR_TYPE_WRCOMB) && !have_wrcomb()) { - pr_warning("mtrr: your processor doesn't support write-combining\n"); + pr_warn("mtrr: your processor doesn't support write-combining\n"); return -ENOSYS; } if (!size) { - pr_warning("mtrr: zero sized request\n"); + pr_warn("mtrr: zero sized request\n"); return -EINVAL; } if ((base | (base + size - 1)) >> (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { - pr_warning("mtrr: base or size exceeds the MTRR width\n"); + pr_warn("mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -348,7 +348,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, } else if (types_compatible(type, ltype)) continue; } - pr_warning("mtrr: 0x%lx000,0x%lx000 overlaps existing" + pr_warn("mtrr: 0x%lx000,0x%lx000 overlaps existing" " 0x%lx000,0x%lx000\n", base, size, lbase, lsize); goto out; @@ -357,7 +357,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (ltype != type) { if (types_compatible(type, ltype)) continue; - pr_warning("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", + pr_warn("mtrr: type mismatch for %lx000,%lx000 old: %s new: %s\n", base, size, mtrr_attrib_to_str(ltype), mtrr_attrib_to_str(type)); goto out; @@ -395,7 +395,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, static int mtrr_check(unsigned long base, unsigned long size) { if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { - pr_warning("mtrr: size and base must be multiples of 4 kiB\n"); + pr_warn("mtrr: size and base must be multiples of 4 kiB\n"); pr_debug("mtrr: size: 0x%lx base: 0x%lx\n", size, base); dump_stack(); return -1; @@ -493,16 +493,16 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) } } if (reg >= max) { - pr_warning("mtrr: register: %d too big\n", reg); + pr_warn("mtrr: register: %d too big\n", reg); goto out; } mtrr_if->get(reg, &lbase, &lsize, <ype); if (lsize < 1) { - pr_warning("mtrr: MTRR %d not used\n", reg); + pr_warn("mtrr: MTRR %d not used\n", reg); goto out; } if (mtrr_usage_table[reg] < 1) { - pr_warning("mtrr: reg: %d has count=0\n", reg); + pr_warn("mtrr: reg: %d has count=0\n", reg); goto out; } if (--mtrr_usage_table[reg] < 1) diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 819d949..f6f50c4 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -51,7 +51,7 @@ void x86_init_rdrand(struct cpuinfo_x86 *c) for (i = 0; i < SANITY_CHECK_LOOPS; i++) { if (!rdrand_long(&tmp)) { clear_cpu_cap(c, X86_FEATURE_RDRAND); - printk_once(KERN_WARNING "rdrand: disabled\n"); + pr_warn_once("rdrand: disabled\n"); return; } } diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 4c60eaf..cd53135 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -87,10 +87,10 @@ void detect_extended_topology(struct cpuinfo_x86 *c) c->x86_max_cores = (core_level_siblings / smp_num_siblings); if (!printed) { - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + pr_info("CPU: Physical Processor ID: %d\n", c->phys_proc_id); if (c->x86_max_cores > 1) - printk(KERN_INFO "CPU: Processor Core ID: %d\n", + pr_info("CPU: Processor Core ID: %d\n", c->cpu_core_id); printed = 1; } diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index a19a663..3417856 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -33,7 +33,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) if (max >= 0x80860001) { cpuid(0x80860001, &dummy, &cpu_rev, &cpu_freq, &cpu_flags); if (cpu_rev != 0x02000000) { - printk(KERN_INFO "CPU: Processor revision %u.%u.%u.%u, %u MHz\n", + pr_info("CPU: Processor revision %u.%u.%u.%u, %u MHz\n", (cpu_rev >> 24) & 0xff, (cpu_rev >> 16) & 0xff, (cpu_rev >> 8) & 0xff, @@ -44,10 +44,10 @@ static void init_transmeta(struct cpuinfo_x86 *c) if (max >= 0x80860002) { cpuid(0x80860002, &new_cpu_rev, &cms_rev1, &cms_rev2, &dummy); if (cpu_rev == 0x02000000) { - printk(KERN_INFO "CPU: Processor revision %08X, %u MHz\n", + pr_info("CPU: Processor revision %08X, %u MHz\n", new_cpu_rev, cpu_freq); } - printk(KERN_INFO "CPU: Code Morphing Software revision %u.%u.%u-%u-%u\n", + pr_info("CPU: Code Morphing Software revision %u.%u.%u-%u-%u\n", (cms_rev1 >> 24) & 0xff, (cms_rev1 >> 16) & 0xff, (cms_rev1 >> 8) & 0xff, @@ -76,7 +76,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) (void *)&cpu_info[56], (void *)&cpu_info[60]); cpu_info[64] = '\0'; - printk(KERN_INFO "CPU: %s\n", cpu_info); + pr_info("CPU: %s\n", cpu_info); } /* Unhide possibly hidden capability flags */ diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 628a059..364e583 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -62,7 +62,7 @@ static unsigned long vmware_get_tsc_khz(void) tsc_hz = eax | (((uint64_t)ebx) << 32); do_div(tsc_hz, 1000); BUG_ON(tsc_hz >> 32); - printk(KERN_INFO "TSC freq read from hypervisor : %lu.%03lu MHz\n", + pr_info("TSC freq read from hypervisor : %lu.%03lu MHz\n", (unsigned long) tsc_hz / 1000, (unsigned long) tsc_hz % 1000); @@ -84,8 +84,7 @@ static void __init vmware_platform_setup(void) if (ebx != UINT_MAX) x86_platform.calibrate_tsc = vmware_get_tsc_khz; else - printk(KERN_WARNING - "Failed to get TSC freq from the hypervisor\n"); + pr_warn("Failed to get TSC freq from the hypervisor\n"); } /* diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 58f3431..9ef978d 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -57,10 +57,9 @@ struct crash_elf_data { struct kimage *image; /* * Total number of ram ranges we have after various adjustments for - * GART, crash reserved region etc. + * crash reserved region, etc. */ unsigned int max_nr_ranges; - unsigned long gart_start, gart_end; /* Pointer to elf header */ void *ehdr; @@ -201,17 +200,6 @@ static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) return 0; } -static int get_gart_ranges_callback(u64 start, u64 end, void *arg) -{ - struct crash_elf_data *ced = arg; - - ced->gart_start = start; - ced->gart_end = end; - - /* Not expecting more than 1 gart aperture */ - return 1; -} - /* Gather all the required information to prepare elf headers for ram regions */ static void fill_up_crash_elf_data(struct crash_elf_data *ced, @@ -226,22 +214,6 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->max_nr_ranges = nr_ranges; - /* - * We don't create ELF headers for GART aperture as an attempt - * to dump this memory in second kernel leads to hang/crash. - * If gart aperture is present, one needs to exclude that region - * and that could lead to need of extra phdr. - */ - walk_iomem_res("GART", IORESOURCE_MEM, 0, -1, - ced, get_gart_ranges_callback); - - /* - * If we have gart region, excluding that could potentially split - * a memory range, resulting in extra header. Account for that. - */ - if (ced->gart_end) - ced->max_nr_ranges++; - /* Exclusion of crash region could split memory ranges */ ced->max_nr_ranges++; @@ -350,13 +322,6 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced, return ret; } - /* Exclude GART region */ - if (ced->gart_end) { - ret = exclude_mem_range(cmem, ced->gart_start, ced->gart_end); - if (ret) - return ret; - } - return ret; } @@ -599,12 +564,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) /* Add ACPI tables */ cmd.type = E820_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; - walk_iomem_res("ACPI Tables", flags, 0, -1, &cmd, + walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ cmd.type = E820_NVS; - walk_iomem_res("ACPI Non-volatile Storage", flags, 0, -1, &cmd, + walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); /* Add crashk_low_res region */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b3c2a69..621b501 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -926,6 +926,41 @@ static const char *e820_type_to_string(int e820_type) } } +static unsigned long e820_type_to_iomem_type(int e820_type) +{ + switch (e820_type) { + case E820_RESERVED_KERN: + case E820_RAM: + return IORESOURCE_SYSTEM_RAM; + case E820_ACPI: + case E820_NVS: + case E820_UNUSABLE: + case E820_PRAM: + case E820_PMEM: + default: + return IORESOURCE_MEM; + } +} + +static unsigned long e820_type_to_iores_desc(int e820_type) +{ + switch (e820_type) { + case E820_ACPI: + return IORES_DESC_ACPI_TABLES; + case E820_NVS: + return IORES_DESC_ACPI_NV_STORAGE; + case E820_PMEM: + return IORES_DESC_PERSISTENT_MEMORY; + case E820_PRAM: + return IORES_DESC_PERSISTENT_MEMORY_LEGACY; + case E820_RESERVED_KERN: + case E820_RAM: + case E820_UNUSABLE: + default: + return IORES_DESC_NONE; + } +} + static bool do_mark_busy(u32 type, struct resource *res) { /* this is the legacy bios/dos rom-shadow + mmio region */ @@ -968,7 +1003,8 @@ void __init e820_reserve_resources(void) res->start = e820.map[i].addr; res->end = end; - res->flags = IORESOURCE_MEM; + res->flags = e820_type_to_iomem_type(e820.map[i].type); + res->desc = e820_type_to_iores_desc(e820.map[i].type); /* * don't register the region that could be conflicted with diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d25097c..d5804ad 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -409,8 +409,10 @@ static inline void copy_init_fpstate_to_fpregs(void) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, -1); - else + else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); + else + copy_kernel_to_fregs(&init_fpstate.fsave); } /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 6d9f0a7..bd08fb7 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -78,13 +78,15 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) cr0 &= ~(X86_CR0_TS | X86_CR0_EM); write_cr0(cr0); - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); + if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) { + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + } #ifndef CONFIG_MATH_EMULATION if (!cpu_has_fpu) { @@ -132,7 +134,7 @@ static void __init fpu__init_system_generic(void) * Set up the legacy init FPU context. (xstate init might overwrite this * with a more modern format, if the CPU supports it.) */ - fpstate_init_fxstate(&init_fpstate.fxsave); + fpstate_init(&init_fpstate); fpu__init_system_mxcsr(); } @@ -300,12 +302,6 @@ u64 __init fpu__get_supported_xfeatures_mask(void) static void __init fpu__clear_eager_fpu_features(void) { setup_clear_cpu_cap(X86_FEATURE_MPX); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - setup_clear_cpu_cap(X86_FEATURE_AVX512F); - setup_clear_cpu_cap(X86_FEATURE_AVX512PF); - setup_clear_cpu_cap(X86_FEATURE_AVX512ER); - setup_clear_cpu_cap(X86_FEATURE_AVX512CD); } /* diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 04f9641e..702547c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -81,9 +81,9 @@ within(unsigned long addr, unsigned long start, unsigned long end) static unsigned long text_ip_addr(unsigned long ip) { /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. + * On x86_64, kernel text mappings are mapped read-only, so we use + * the kernel identity mapping instead of the kernel text mapping + * to modify the kernel text. * * For 32bit kernels, these mappings are same and we can use * kernel identity mapping to modify code. diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 44256a6..ed15cd48 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -750,9 +750,7 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { int err; -#ifdef CONFIG_DEBUG_RODATA char opc[BREAK_INSTR_SIZE]; -#endif /* CONFIG_DEBUG_RODATA */ bpt->type = BP_BREAKPOINT; err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, @@ -761,7 +759,6 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) return err; err = probe_kernel_write((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); -#ifdef CONFIG_DEBUG_RODATA if (!err) return err; /* @@ -778,13 +775,12 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE)) return -EINVAL; bpt->type = BP_POKE_BREAKPOINT; -#endif /* CONFIG_DEBUG_RODATA */ + return err; } int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) { -#ifdef CONFIG_DEBUG_RODATA int err; char opc[BREAK_INSTR_SIZE]; @@ -801,8 +797,8 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE)) goto knl_write; return err; + knl_write: -#endif /* CONFIG_DEBUG_RODATA */ return probe_kernel_write((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 1deffe6..0f05dee 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -988,7 +988,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * In case the user-specified fault handler returned * zero, try to fix up. */ - if (fixup_exception(regs)) + if (fixup_exception(regs, trapnr)) return 1; /* diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 30ca760..97340f2 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -408,7 +408,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type) processor.cpuflag = CPU_ENABLED; processor.cpufeature = (boot_cpu_data.x86 << 8) | (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; - processor.featureflag = boot_cpu_data.x86_capability[0]; + processor.featureflag = boot_cpu_data.x86_capability[CPUID_1_EDX]; processor.reserved[0] = 0; processor.reserved[1] = 0; for (i = 0; i < 2; i++) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 8a2cdd7..04b132a 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -30,6 +30,7 @@ #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/reboot.h> +#include <asm/cache.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -69,7 +70,7 @@ struct nmi_stats { static DEFINE_PER_CPU(struct nmi_stats, nmi_stats); -static int ignore_nmis; +static int ignore_nmis __read_mostly; int unknown_nmi_panic; /* diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c index 14415af..92f7014 100644 --- a/arch/x86/kernel/pmem.c +++ b/arch/x86/kernel/pmem.c @@ -13,11 +13,11 @@ static int found(u64 start, u64 end, void *data) static __init int register_e820_pmem(void) { - char *pmem = "Persistent Memory (legacy)"; struct platform_device *pdev; int rc; - rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found); + rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY, + IORESOURCE_MEM, 0, -1, NULL, found); if (rc <= 0) return 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ee9a979..2915d54 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -421,9 +421,9 @@ static void mwait_idle(void) if (!current_set_polling_and_test()) { trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { - smp_mb(); /* quirk */ + mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); - smp_mb(); /* quirk */ + mb(); /* quirk */ } __monitor((void *)¤t_thread_info()->flags, 0, 0); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d3d80e6..aa52c10 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -152,21 +152,21 @@ static struct resource data_resource = { .name = "Kernel data", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource code_resource = { .name = "Kernel code", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; static struct resource bss_resource = { .name = "Kernel bss", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM }; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 24d57f7..3bf1e0b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -97,6 +97,14 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); +/* Logical package management. We might want to allocate that dynamically */ +static int *physical_to_logical_pkg __read_mostly; +static unsigned long *physical_package_map __read_mostly;; +static unsigned long *logical_package_map __read_mostly; +static unsigned int max_physical_pkg_id __read_mostly; +unsigned int __max_logical_packages __read_mostly; +EXPORT_SYMBOL(__max_logical_packages); + static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; @@ -251,6 +259,97 @@ static void notrace start_secondary(void *unused) cpu_startup_entry(CPUHP_ONLINE); } +int topology_update_package_map(unsigned int apicid, unsigned int cpu) +{ + unsigned int new, pkg = apicid >> boot_cpu_data.x86_coreid_bits; + + /* Called from early boot ? */ + if (!physical_package_map) + return 0; + + if (pkg >= max_physical_pkg_id) + return -EINVAL; + + /* Set the logical package id */ + if (test_and_set_bit(pkg, physical_package_map)) + goto found; + + if (pkg < __max_logical_packages) { + set_bit(pkg, logical_package_map); + physical_to_logical_pkg[pkg] = pkg; + goto found; + } + new = find_first_zero_bit(logical_package_map, __max_logical_packages); + if (new >= __max_logical_packages) { + physical_to_logical_pkg[pkg] = -1; + pr_warn("APIC(%x) Package %u exceeds logical package map\n", + apicid, pkg); + return -ENOSPC; + } + set_bit(new, logical_package_map); + pr_info("APIC(%x) Converting physical %u to logical package %u\n", + apicid, pkg, new); + physical_to_logical_pkg[pkg] = new; + +found: + cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg]; + return 0; +} + +/** + * topology_phys_to_logical_pkg - Map a physical package id to a logical + * + * Returns logical package id or -1 if not found + */ +int topology_phys_to_logical_pkg(unsigned int phys_pkg) +{ + if (phys_pkg >= max_physical_pkg_id) + return -1; + return physical_to_logical_pkg[phys_pkg]; +} +EXPORT_SYMBOL(topology_phys_to_logical_pkg); + +static void __init smp_init_package_map(void) +{ + unsigned int ncpus, cpu; + size_t size; + + /* + * Today neither Intel nor AMD support heterogenous systems. That + * might change in the future.... + */ + ncpus = boot_cpu_data.x86_max_cores * smp_num_siblings; + __max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus); + + /* + * Possibly larger than what we need as the number of apic ids per + * package can be smaller than the actual used apic ids. + */ + max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus); + size = max_physical_pkg_id * sizeof(unsigned int); + physical_to_logical_pkg = kmalloc(size, GFP_KERNEL); + memset(physical_to_logical_pkg, 0xff, size); + size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); + physical_package_map = kzalloc(size, GFP_KERNEL); + size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long); + logical_package_map = kzalloc(size, GFP_KERNEL); + + pr_info("Max logical packages: %u\n", __max_logical_packages); + + for_each_present_cpu(cpu) { + unsigned int apicid = apic->cpu_present_to_apicid(cpu); + + if (apicid == BAD_APICID || !apic->apic_id_valid(apicid)) + continue; + if (!topology_update_package_map(apicid, cpu)) + continue; + pr_warn("CPU %u APICId %x disabled\n", cpu, apicid); + per_cpu(x86_bios_cpu_apicid, cpu) = BAD_APICID; + set_cpu_possible(cpu, false); + set_cpu_present(cpu, false); + } +} + void __init smp_store_boot_cpu_info(void) { int id = 0; /* CPU 0 */ @@ -258,6 +357,7 @@ void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; + smp_init_package_map(); } /* diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c index 3f92ce0..27538f1 100644 --- a/arch/x86/kernel/test_nx.c +++ b/arch/x86/kernel/test_nx.c @@ -142,7 +142,6 @@ static int test_NX(void) * by the error message */ -#ifdef CONFIG_DEBUG_RODATA /* Test 3: Check if the .rodata section is executable */ if (rodata_test_data != 0xC3) { printk(KERN_ERR "test_nx: .rodata marker has invalid value\n"); @@ -151,7 +150,6 @@ static int test_NX(void) printk(KERN_ERR "test_nx: .rodata section is executable\n"); ret = -ENODEV; } -#endif #if 0 /* Test 4: Check if the .data section of a module is executable */ diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c index 5ecbfe5..cb4a01b 100644 --- a/arch/x86/kernel/test_rodata.c +++ b/arch/x86/kernel/test_rodata.c @@ -76,5 +76,5 @@ int rodata_test(void) } MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Testcase for the DEBUG_RODATA infrastructure"); +MODULE_DESCRIPTION("Testcase for marking rodata as read-only"); MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1baf081..5c9ca2b 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -185,7 +185,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, } if (!user_mode(regs)) { - if (!fixup_exception(regs)) { + if (!fixup_exception(regs, trapnr)) { tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; die(str, regs, error_code); @@ -437,7 +437,7 @@ do_general_protection(struct pt_regs *regs, long error_code) tsk = current; if (!user_mode(regs)) { - if (fixup_exception(regs)) + if (fixup_exception(regs, X86_TRAP_GP)) return; tsk->thread.error_code = error_code; @@ -741,7 +741,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (!fixup_exception(regs)) { + if (!fixup_exception(regs, trapnr)) { task->thread.error_code = error_code; task->thread.trap_nr = trapnr; die(str, regs, error_code); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 92dc211..5af9958 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -41,29 +41,28 @@ ENTRY(phys_startup_64) jiffies_64 = jiffies; #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) /* - * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA - * we retain large page mappings for boundaries spanning kernel text, rodata - * and data sections. + * On 64-bit, align RODATA to 2MB so we retain large page mappings for + * boundaries spanning kernel text, rodata and data sections. * * However, kernel identity mappings will have different RWX permissions * to the pages mapping to text and to the pages padding (which are freed) the * text section. Hence kernel identity mappings will be broken to smaller * pages. For 64-bit, kernel text and kernel identity mappings are different, - * so we can enable protection checks that come with CONFIG_DEBUG_RODATA, - * as well as retain 2MB large page mappings for kernel text. + * so we can enable protection checks as well as retain 2MB large page + * mappings for kernel text. */ -#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); +#define X64_ALIGN_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); -#define X64_ALIGN_DEBUG_RODATA_END \ +#define X64_ALIGN_RODATA_END \ . = ALIGN(HPAGE_SIZE); \ __end_rodata_hpage_align = .; #else -#define X64_ALIGN_DEBUG_RODATA_BEGIN -#define X64_ALIGN_DEBUG_RODATA_END +#define X64_ALIGN_RODATA_BEGIN +#define X64_ALIGN_RODATA_END #endif @@ -112,13 +111,11 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 -#if defined(CONFIG_DEBUG_RODATA) /* .text should occupy whole number of pages */ . = ALIGN(PAGE_SIZE); -#endif - X64_ALIGN_DEBUG_RODATA_BEGIN + X64_ALIGN_RODATA_BEGIN RO_DATA(PAGE_SIZE) - X64_ALIGN_DEBUG_RODATA_END + X64_ALIGN_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c index a0695be..cd05942 100644 --- a/arch/x86/kernel/x8664_ksyms_64.c +++ b/arch/x86/kernel/x8664_ksyms_64.c @@ -37,6 +37,8 @@ EXPORT_SYMBOL(__copy_user_nocache); EXPORT_SYMBOL(_copy_from_user); EXPORT_SYMBOL(_copy_to_user); +EXPORT_SYMBOL_GPL(memcpy_mcsafe); + EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 36591fa..3a045f3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1195,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; - wait_queue_head_t *q = &vcpu->wq; + struct swait_queue_head *q = &vcpu->wq; struct kvm_timer *ktimer = &apic->lapic_timer; if (atomic_read(&apic->lapic_timer.pending)) @@ -1204,8 +1204,8 @@ static void apic_timer_expired(struct kvm_lapic *apic) atomic_inc(&apic->lapic_timer.pending); kvm_set_pending_timer(vcpu); - if (waitqueue_active(q)) - wake_up_interruptible(q); + if (swait_active(q)) + swake_up(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 95a955d..1e7a49b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3721,13 +3721,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 0ff4537..9bd8f44 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -1813,6 +1813,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1850,26 +1857,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1880,16 +1892,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 4ba229a..fd57d3a 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1520,12 +1520,6 @@ __init void lguest_init(void) */ reserve_top_address(lguest_data.reserve_mem); - /* - * If we don't initialize the lock dependency checker now, it crashes - * atomic_notifier_chain_register, then paravirt_disable_iospace. - */ - lockdep_init(); - /* Hook in our special panic hypercall code. */ atomic_notifier_chain_register(&panic_notifier_list, &paniced); @@ -1535,7 +1529,7 @@ __init void lguest_init(void) */ cpu_detect(&new_cpu_data); /* head.S usually sets up the first capability word, so do it here. */ - new_cpu_data.x86_capability[0] = cpuid_edx(1); + new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); /* Math is always hard! */ set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index e912b2f..2f07c29 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -102,7 +102,7 @@ static void delay_mwaitx(unsigned long __loops) * Use cpu_tss as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(this_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index a0de849..cbb8ee5 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -177,3 +177,120 @@ ENTRY(memcpy_orig) .Lend: retq ENDPROC(memcpy_orig) + +#ifndef CONFIG_UML +/* + * memcpy_mcsafe - memory copy with machine check exception handling + * Note that we only catch machine checks when reading the source addresses. + * Writes to target are posted and don't generate machine checks. + */ +ENTRY(memcpy_mcsafe) + cmpl $8, %edx + /* Less than 8 bytes? Go to byte copy loop */ + jb .L_no_whole_words + + /* Check for bad alignment of source */ + testl $7, %esi + /* Already aligned */ + jz .L_8byte_aligned + + /* Copy one byte at a time until source is 8-byte aligned */ + movl %esi, %ecx + andl $7, %ecx + subl $8, %ecx + negl %ecx + subl %ecx, %edx +.L_copy_leading_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_leading_bytes + +.L_8byte_aligned: + /* Figure out how many whole cache lines (64-bytes) to copy */ + movl %edx, %ecx + andl $63, %edx + shrl $6, %ecx + jz .L_no_whole_cache_lines + + /* Loop copying whole cache lines */ +.L_cache_w0: movq (%rsi), %r8 +.L_cache_w1: movq 1*8(%rsi), %r9 +.L_cache_w2: movq 2*8(%rsi), %r10 +.L_cache_w3: movq 3*8(%rsi), %r11 + movq %r8, (%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) +.L_cache_w4: movq 4*8(%rsi), %r8 +.L_cache_w5: movq 5*8(%rsi), %r9 +.L_cache_w6: movq 6*8(%rsi), %r10 +.L_cache_w7: movq 7*8(%rsi), %r11 + movq %r8, 4*8(%rdi) + movq %r9, 5*8(%rdi) + movq %r10, 6*8(%rdi) + movq %r11, 7*8(%rdi) + leaq 64(%rsi), %rsi + leaq 64(%rdi), %rdi + decl %ecx + jnz .L_cache_w0 + + /* Are there any trailing 8-byte words? */ +.L_no_whole_cache_lines: + movl %edx, %ecx + andl $7, %edx + shrl $3, %ecx + jz .L_no_whole_words + + /* Copy trailing words */ +.L_copy_trailing_words: + movq (%rsi), %r8 + mov %r8, (%rdi) + leaq 8(%rsi), %rsi + leaq 8(%rdi), %rdi + decl %ecx + jnz .L_copy_trailing_words + + /* Any trailing bytes? */ +.L_no_whole_words: + andl %edx, %edx + jz .L_done_memcpy_trap + + /* Copy trailing bytes */ + movl %edx, %ecx +.L_copy_trailing_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_trailing_bytes + + /* Copy successful. Return true */ +.L_done_memcpy_trap: + xorq %rax, %rax + ret +ENDPROC(memcpy_mcsafe) + + .section .fixup, "ax" + /* Return false for any failure */ +.L_memcpy_mcsafe_fail: + mov $1, %rax + ret + + .previous + + _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) +#endif diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 903ec1e..9dd7e4b 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -3,6 +3,9 @@ #include <linux/sort.h> #include <asm/uaccess.h> +typedef bool (*ex_handler_t)(const struct exception_table_entry *, + struct pt_regs *, int); + static inline unsigned long ex_insn_addr(const struct exception_table_entry *x) { @@ -13,11 +16,56 @@ ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } +static inline ex_handler_t +ex_fixup_handler(const struct exception_table_entry *x) +{ + return (ex_handler_t)((unsigned long)&x->handler + x->handler); +} -int fixup_exception(struct pt_regs *regs) +bool ex_handler_default(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) { - const struct exception_table_entry *fixup; - unsigned long new_ip; + regs->ip = ex_fixup_addr(fixup); + return true; +} +EXPORT_SYMBOL(ex_handler_default); + +bool ex_handler_fault(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + regs->ip = ex_fixup_addr(fixup); + regs->ax = trapnr; + return true; +} +EXPORT_SYMBOL_GPL(ex_handler_fault); + +bool ex_handler_ext(const struct exception_table_entry *fixup, + struct pt_regs *regs, int trapnr) +{ + /* Special hack for uaccess_err */ + current_thread_info()->uaccess_err = 1; + regs->ip = ex_fixup_addr(fixup); + return true; +} +EXPORT_SYMBOL(ex_handler_ext); + +bool ex_has_fault_handler(unsigned long ip) +{ + const struct exception_table_entry *e; + ex_handler_t handler; + + e = search_exception_tables(ip); + if (!e) + return false; + handler = ex_fixup_handler(e); + + return handler == ex_handler_fault; +} + +int fixup_exception(struct pt_regs *regs, int trapnr) +{ + const struct exception_table_entry *e; + ex_handler_t handler; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { @@ -33,42 +81,34 @@ int fixup_exception(struct pt_regs *regs) } #endif - fixup = search_exception_tables(regs->ip); - if (fixup) { - new_ip = ex_fixup_addr(fixup); - - if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) { - /* Special hack for uaccess_err */ - current_thread_info()->uaccess_err = 1; - new_ip -= 0x7ffffff0; - } - regs->ip = new_ip; - return 1; - } + e = search_exception_tables(regs->ip); + if (!e) + return 0; - return 0; + handler = ex_fixup_handler(e); + return handler(e, regs, trapnr); } /* Restricted version used during very early boot */ int __init early_fixup_exception(unsigned long *ip) { - const struct exception_table_entry *fixup; + const struct exception_table_entry *e; unsigned long new_ip; + ex_handler_t handler; - fixup = search_exception_tables(*ip); - if (fixup) { - new_ip = ex_fixup_addr(fixup); + e = search_exception_tables(*ip); + if (!e) + return 0; - if (fixup->fixup - fixup->insn >= 0x7ffffff0 - 4) { - /* uaccess handling not supported during early boot */ - return 0; - } + new_ip = ex_fixup_addr(e); + handler = ex_fixup_handler(e); - *ip = new_ip; - return 1; - } + /* special handling not supported during early boot */ + if (handler != ex_handler_default) + return 0; - return 0; + *ip = new_ip; + return 1; } /* @@ -133,6 +173,8 @@ void sort_extable(struct exception_table_entry *start, i += 4; p->fixup += i; i += 4; + p->handler += i; + i += 4; } sort(start, finish - start, sizeof(struct exception_table_entry), @@ -145,6 +187,8 @@ void sort_extable(struct exception_table_entry *start, i += 4; p->fixup -= i; i += 4; + p->handler -= i; + i += 4; } } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e830c71..03898ae 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -663,7 +663,7 @@ no_context(struct pt_regs *regs, unsigned long error_code, int sig; /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) { + if (fixup_exception(regs, X86_TRAP_PF)) { /* * Any interrupt that takes a fault gets the fixup. This makes * the below recursive fault logic only apply to a faults from diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index cb4ef3d..2ebfbaf 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -871,7 +871,6 @@ static noinline int do_test_wp_bit(void) return flag; } -#ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); @@ -960,5 +959,3 @@ void mark_rodata_ro(void) if (__supported_pte_mask & _PAGE_NX) debug_checkwx(); } -#endif - diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 5488d21..a40b755 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1074,7 +1074,6 @@ void __init mem_init(void) mem_init_print_info(NULL); } -#ifdef CONFIG_DEBUG_RODATA const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); @@ -1166,8 +1165,6 @@ void mark_rodata_ro(void) debug_checkwx(); } -#endif - int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 9cf96d8..1c37e65 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -283,7 +283,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, __pa_symbol(__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; -#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +#if defined(CONFIG_X86_64) /* * Once the kernel maps the text as RO (kernel_set_to_readonly is set), * kernel text mappings for the large page aligned text, rodata sections diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 2d66db8..ed30e79 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -131,6 +131,27 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) EXPORT_SYMBOL_GPL(efi_query_variable_store); /* + * Helper function for efi_reserve_boot_services() to figure out if we + * can free regions in efi_free_boot_services(). + * + * Use this function to ensure we do not free regions owned by somebody + * else. We must only reserve (and then free) regions: + * + * - Not within any part of the kernel + * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc) + */ +static bool can_free_region(u64 start, u64 size) +{ + if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) + return false; + + if (!e820_all_mapped(start, start+size, E820_RAM)) + return false; + + return true; +} + +/* * The UEFI specification makes it clear that the operating system is free to do * whatever it wants with boot services code after ExitBootServices() has been * called. Ignoring this recommendation a significant bunch of EFI implementations @@ -147,26 +168,50 @@ void __init efi_reserve_boot_services(void) efi_memory_desc_t *md = p; u64 start = md->phys_addr; u64 size = md->num_pages << EFI_PAGE_SHIFT; + bool already_reserved; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Only reserve where possible: - * - Not within any already allocated areas - * - Not over any memory area (really needed, if above?) - * - Not within any part of the kernel - * - Not the bios reserved area - */ - if ((start + size > __pa_symbol(_text) - && start <= __pa_symbol(_end)) || - !e820_all_mapped(start, start+size, E820_RAM) || - memblock_is_region_reserved(start, size)) { - /* Could not reserve, skip it */ - md->num_pages = 0; - memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", - start, start+size-1); - } else + + already_reserved = memblock_is_region_reserved(start, size); + + /* + * Because the following memblock_reserve() is paired + * with free_bootmem_late() for this region in + * efi_free_boot_services(), we must be extremely + * careful not to reserve, and subsequently free, + * critical regions of memory (like the kernel image) or + * those regions that somebody else has already + * reserved. + * + * A good example of a critical region that must not be + * freed is page zero (first 4Kb of memory), which may + * contain boot services code/data but is marked + * E820_RESERVED by trim_bios_range(). + */ + if (!already_reserved) { memblock_reserve(start, size); + + /* + * If we are the first to reserve the region, no + * one else cares about it. We own it and can + * free it later. + */ + if (can_free_region(start, size)) + continue; + } + + /* + * We don't own the region. We must not free it. + * + * Setting this bit for a boot services region really + * doesn't make sense as far as the firmware is + * concerned, but it does provide us with a way to tag + * those regions that must not be paired with + * free_bootmem_late(). + */ + md->attribute |= EFI_MEMORY_RUNTIME; } } @@ -183,8 +228,8 @@ void __init efi_free_boot_services(void) md->type != EFI_BOOT_SERVICES_DATA) continue; - /* Could not reserve boot area */ - if (!size) + /* Do not free, someone else owns it: */ + if (md->attribute & EFI_MEMORY_RUNTIME) continue; free_bootmem_late(start, size); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index d09e4c9..2c26108 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1654,7 +1654,7 @@ asmlinkage __visible void __init xen_start_kernel(void) cpu_detect(&new_cpu_data); set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); new_cpu_data.wp_works_ok = 1; - new_cpu_data.x86_capability[0] = cpuid_edx(1); + new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); #endif if (xen_start_info->mod_start) { diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 724a087..9466354 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -11,7 +11,7 @@ #include "pmu.h" /* x86_pmu.handle_irq definition */ -#include "../kernel/cpu/perf_event.h" +#include "../events/perf_event.h" #define XENPMU_IRQ_PROCESSING 1 struct xenpmu { |