diff options
Diffstat (limited to 'arch/x86')
48 files changed, 683 insertions, 664 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d43e7e1c784b..226d5696e1d1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,6 +22,7 @@ config X86_64 ### Arch settings config X86 def_bool y + select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_FAST_MULTIPLIER @@ -178,7 +179,7 @@ config SBUS config NEED_DMA_MAP_STATE def_bool y - depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG + depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB config NEED_SG_DMA_LENGTH def_bool y @@ -1421,6 +1422,16 @@ config ILLEGAL_POINTER_VALUE source "mm/Kconfig" +config X86_PMEM_LEGACY + bool "Support non-standard NVDIMMs and ADR protected memory" + help + Treat memory marked using the non-standard e820 type of 12 as used + by the Intel Sandy Bridge-EP reference BIOS as protected memory. + The kernel will offer these regions to the 'pmem' driver so + they can be used for persistent storage. + + Say Y if unsure. + config HIGHPTE bool "Allocate 3rd-level pagetables from highmem" depends on HIGHMEM diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 20028da8ae18..72484a645f05 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -43,10 +43,6 @@ config EARLY_PRINTK with klogd/syslogd or the X server. You should normally N here, unless you want to debug such a crash. -config EARLY_PRINTK_INTEL_MID - bool "Early printk for Intel MID platform support" - depends on EARLY_PRINTK && X86_INTEL_MID - config EARLY_PRINTK_DBGP bool "Early printk via EHCI debug port" depends on EARLY_PRINTK && PCI diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index a821b1cd4fa7..72bf2680f819 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -427,6 +427,13 @@ sysretl_from_sys_call: * cs and ss are loaded from MSRs. * (Note: 32bit->32bit SYSRET is different: since r11 * does not exist, it merely sets eflags.IF=1). + * + * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss + * descriptor is not reinitialized. This means that we must + * avoid SYSRET with SS == NULL, which could happen if we schedule, + * exit the kernel, and re-enter using an interrupt vector. (All + * interrupt entries on x86_64 set SS to NULL.) We prevent that + * from happening by reloading SS in __switch_to. */ USERGS_SYSRET32 diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7ee9b94d9921..3d6606fb97d0 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -265,6 +265,7 @@ #define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h index 705d35708a50..7c5af123bdbd 100644 --- a/arch/x86/include/asm/intel-mid.h +++ b/arch/x86/include/asm/intel-mid.h @@ -136,9 +136,6 @@ extern enum intel_mid_timer_options intel_mid_timer_options; #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 -extern struct console early_hsu_console; -extern void hsu_early_console_init(const char *); - extern void intel_scu_devices_create(void); extern void intel_scu_devices_destroy(void); diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h index e2d4a4afa8c3..3bbc07a57a31 100644 --- a/arch/x86/include/asm/lguest.h +++ b/arch/x86/include/asm/lguest.h @@ -20,13 +20,10 @@ extern unsigned long switcher_addr; /* Found in switcher.S */ extern unsigned long default_idt_entries[]; -/* Declarations for definitions in lguest_guest.S */ -extern char lguest_noirq_start[], lguest_noirq_end[]; +/* Declarations for definitions in arch/x86/lguest/head_32.S */ +extern char lguest_noirq_iret[]; extern const char lgstart_cli[], lgend_cli[]; -extern const char lgstart_sti[], lgend_sti[]; -extern const char lgstart_popf[], lgend_popf[]; extern const char lgstart_pushf[], lgend_pushf[]; -extern const char lgstart_iret[], lgend_iret[]; extern void lguest_iret(void); extern void lguest_init(void); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 25b1cc07d496..d6b078e9fa28 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; - u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h index 0f3d7f099224..0c8c7c8861b4 100644 --- a/arch/x86/include/asm/seccomp.h +++ b/arch/x86/include/asm/seccomp.h @@ -1,5 +1,20 @@ +#ifndef _ASM_X86_SECCOMP_H +#define _ASM_X86_SECCOMP_H + +#include <asm/unistd.h> + #ifdef CONFIG_X86_32 -# include <asm/seccomp_32.h> -#else -# include <asm/seccomp_64.h> +#define __NR_seccomp_sigreturn __NR_sigreturn #endif + +#ifdef CONFIG_COMPAT +#include <asm/ia32_unistd.h> +#define __NR_seccomp_read_32 __NR_ia32_read +#define __NR_seccomp_write_32 __NR_ia32_write +#define __NR_seccomp_exit_32 __NR_ia32_exit +#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn +#endif + +#include <asm-generic/seccomp.h> + +#endif /* _ASM_X86_SECCOMP_H */ diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h deleted file mode 100644 index b811d6f5780c..000000000000 --- a/arch/x86/include/asm/seccomp_32.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_SECCOMP_32_H -#define _ASM_X86_SECCOMP_32_H - -#include <linux/unistd.h> - -#define __NR_seccomp_read __NR_read -#define __NR_seccomp_write __NR_write -#define __NR_seccomp_exit __NR_exit -#define __NR_seccomp_sigreturn __NR_sigreturn - -#endif /* _ASM_X86_SECCOMP_32_H */ diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h deleted file mode 100644 index 84ec1bd161a5..000000000000 --- a/arch/x86/include/asm/seccomp_64.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _ASM_X86_SECCOMP_64_H -#define _ASM_X86_SECCOMP_64_H - -#include <linux/unistd.h> -#include <asm/ia32_unistd.h> - -#define __NR_seccomp_read __NR_read -#define __NR_seccomp_write __NR_write -#define __NR_seccomp_exit __NR_exit -#define __NR_seccomp_sigreturn __NR_rt_sigreturn - -#define __NR_seccomp_read_32 __NR_ia32_read -#define __NR_seccomp_write_32 __NR_ia32_write -#define __NR_seccomp_exit_32 __NR_ia32_exit -#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn - -#endif /* _ASM_X86_SECCOMP_64_H */ diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h index 460b84f64556..8378b8c9109c 100644 --- a/arch/x86/include/asm/serial.h +++ b/arch/x86/include/asm/serial.h @@ -12,11 +12,11 @@ /* Standard COM flags (except for COM4, because of the 8514 problem) */ #ifdef CONFIG_SERIAL_DETECT_IRQ -# define STD_COMX_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ) -# define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | 0 | ASYNC_AUTO_IRQ) +# define STD_COMX_FLAGS (UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_AUTO_IRQ) +# define STD_COM4_FLAGS (UPF_BOOT_AUTOCONF | 0 | UPF_AUTO_IRQ) #else -# define STD_COMX_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | 0 ) -# define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | 0 | 0 ) +# define STD_COMX_FLAGS (UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | 0 ) +# define STD_COM4_FLAGS (UPF_BOOT_AUTOCONF | 0 | 0 ) #endif #define SERIAL_PORT_DFNS \ diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index d993e33f5236..960a8a9dc4ab 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -33,6 +33,16 @@ #define E820_NVS 4 #define E820_UNUSABLE 5 +/* + * This is a non-standardized way to represent ADR or NVDIMM regions that + * persist over a reboot. The kernel will ignore their special capabilities + * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * + * ( Note that older platforms also used 6 for the same type of memory, + * but newer versions switched to 12 as 6 was assigned differently. Some + * time they will learn... ) + */ +#define E820_PRAM 12 /* * reserved RAM used by kernel itself diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 90c458e66e13..ce6068dbcfbc 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -225,6 +225,8 @@ #define HV_STATUS_INVALID_HYPERCALL_CODE 2 #define HV_STATUS_INVALID_HYPERCALL_INPUT 3 #define HV_STATUS_INVALID_ALIGNMENT 4 +#define HV_STATUS_INSUFFICIENT_MEMORY 11 +#define HV_STATUS_INVALID_CONNECTION_ID 18 #define HV_STATUS_INSUFFICIENT_BUFFERS 19 typedef struct _HV_REFERENCE_TSC_PAGE { diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 1a4eae695ca8..c469490db4a8 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -61,6 +61,9 @@ #define MSR_OFFCORE_RSP_1 0x000001a7 #define MSR_NHM_TURBO_RATIO_LIMIT 0x000001ad #define MSR_IVT_TURBO_RATIO_LIMIT 0x000001ae +#define MSR_TURBO_RATIO_LIMIT 0x000001ad +#define MSR_TURBO_RATIO_LIMIT1 0x000001ae +#define MSR_TURBO_RATIO_LIMIT2 0x000001af #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -165,6 +168,11 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 +#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 +#define MSR_PKG_ANY_CORE_C0_RES 0x00000659 +#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A +#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B + #define MSR_CORE_C1_RES 0x00000660 #define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index c887cd944f0c..9bcd0b56ca17 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -95,6 +95,7 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o +obj-$(CONFIG_X86_PMEM_LEGACY) += pmem.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 803b684676ff..dbe76a14c3c9 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -757,7 +757,7 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) } /* wrapper to silence section mismatch warning */ -int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu) +int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) { return _acpi_map_lsapic(handle, physid, pcpu); } diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index d9d0bd2faaf4..ab3219b3fbda 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -171,8 +171,8 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu) for_each_online_cpu(cpu) { if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) continue; - __cpu_clear(this_cpu, per_cpu(cpus_in_cluster, cpu)); - __cpu_clear(cpu, per_cpu(cpus_in_cluster, this_cpu)); + cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); + cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); } free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu)); free_cpumask_var(per_cpu(ipi_mask, this_cpu)); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index fd470ebf924e..e4cf63301ff4 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -720,6 +720,9 @@ static void init_amd(struct cpuinfo_x86 *c) if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH)) if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH); + + /* AMD CPUs don't reset SS attributes on SYSRET */ + set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 329f0356ad4a..6ac5cb7a9e14 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -65,15 +65,15 @@ struct event_constraint { /* * struct hw_perf_event.flags flags */ -#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ -#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x40 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x80 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x40 /* grant rdpmc permission */ +#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ +#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ +#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ struct amd_nb { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 9da2400c2ec3..219d3fb423a1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -3275,7 +3275,7 @@ __init int intel_pmu_init(void) hw_cache_extra_regs[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = HSW_DEMAND_WRITE| BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM; - intel_pmu_lbr_init_snb(); + intel_pmu_lbr_init_hsw(); x86_pmu.event_constraints = intel_bdw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index ca69ea56c712..813f75d71175 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -558,6 +558,8 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -565,6 +567,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -588,6 +592,8 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -603,6 +609,8 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index f2770641c0fd..ffe666c2c6b5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -988,39 +988,36 @@ static int pt_event_add(struct perf_event *event, int mode) int ret = -EBUSY; if (pt->handle.event) - goto out; + goto fail; buf = perf_aux_output_begin(&pt->handle, event); - if (!buf) { - ret = -EINVAL; - goto out; - } + ret = -EINVAL; + if (!buf) + goto fail_stop; pt_buffer_reset_offsets(buf, pt->handle.head); if (!buf->snapshot) { ret = pt_buffer_reset_markers(buf, &pt->handle); - if (ret) { - perf_aux_output_end(&pt->handle, 0, true); - goto out; - } + if (ret) + goto fail_end_stop; } if (mode & PERF_EF_START) { pt_event_start(event, 0); - if (hwc->state == PERF_HES_STOPPED) { - pt_event_del(event, 0); - ret = -EBUSY; - } + ret = -EBUSY; + if (hwc->state == PERF_HES_STOPPED) + goto fail_end_stop; } else { hwc->state = PERF_HES_STOPPED; } - ret = 0; -out: - - if (ret) - hwc->state = PERF_HES_STOPPED; + return 0; +fail_end_stop: + perf_aux_output_end(&pt->handle, 0, true); +fail_stop: + hwc->state = PERF_HES_STOPPED; +fail: return ret; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index c4bb8b8e5017..999289b94025 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -62,6 +62,14 @@ #define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ +#define NR_RAPL_DOMAINS 0x4 +static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { + "pp0-core", + "package", + "dram", + "pp1-gpu", +}; + /* Clients have PP0, PKG */ #define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ 1<<RAPL_IDX_PKG_NRG_STAT|\ @@ -112,7 +120,6 @@ static struct perf_pmu_events_attr event_attr_##v = { \ struct rapl_pmu { spinlock_t lock; - int hw_unit; /* 1/2^hw_unit Joule */ int n_active; /* number of active events */ struct list_head active_list; struct pmu *pmu; /* pointer to rapl_pmu_class */ @@ -120,6 +127,7 @@ struct rapl_pmu { struct hrtimer hrtimer; }; +static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; /* 1/2^hw_unit Joule */ static struct pmu rapl_pmu_class; static cpumask_t rapl_cpu_mask; static int rapl_cntr_mask; @@ -127,6 +135,7 @@ static int rapl_cntr_mask; static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); +static struct x86_pmu_quirk *rapl_quirks; static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; @@ -134,15 +143,28 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -static inline u64 rapl_scale(u64 v) +#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); + return v; + } /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit); + return v << (32 - rapl_hw_unit[cfg - 1]); } static u64 rapl_event_update(struct perf_event *event) @@ -173,7 +195,7 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - sdelta = rapl_scale(delta); + sdelta = rapl_scale(delta, event->hw.config); local64_add(sdelta, &event->count); @@ -546,12 +568,22 @@ static void rapl_cpu_init(int cpu) 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 " + */ + rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; +} + 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; - u64 msr_rapl_power_unit_bits; if (pmu) return 0; @@ -559,24 +591,13 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; - /* protect rdmsrl() to handle virtualization */ - if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) - return -1; - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -1; - spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); - /* - * grab power unit as: 1/2^unit Joules - * - * we cache in local PMU instance - */ - pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -586,8 +607,8 @@ static int rapl_cpu_prepare(int cpu) * divide interval by 2 to avoid lockstep (2 * 100) * if hw unit is 32, then we use 2 ms 1/200/2 */ - if (pmu->hw_unit < 32) - ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1)); + if (rapl_hw_unit[0] < 32) + ms = (1000 / (2 * 100)) * (1ULL << (32 - rapl_hw_unit[0] - 1)); else ms = 2; @@ -655,6 +676,20 @@ static int rapl_cpu_notifier(struct notifier_block *self, return NOTIFY_OK; } +static int rapl_check_hw_unit(void) +{ + u64 msr_rapl_power_unit_bits; + int i; + + /* protect rdmsrl() to handle virtualization */ + if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + for (i = 0; i < NR_RAPL_DOMAINS; i++) + rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + + return 0; +} + static const struct x86_cpu_id rapl_cpu_match[] = { [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, [1] = {}, @@ -664,6 +699,8 @@ static int __init rapl_pmu_init(void) { struct rapl_pmu *pmu; int cpu, ret; + struct x86_pmu_quirk *quirk; + int i; /* * check for Intel processor family 6 @@ -678,6 +715,11 @@ static int __init rapl_pmu_init(void) rapl_cntr_mask = RAPL_IDX_CLN; rapl_pmu_events_group.attrs = rapl_events_cln_attr; break; + case 63: /* Haswell-Server */ + rapl_add_quirk(rapl_hsw_server_quirk); + rapl_cntr_mask = RAPL_IDX_SRV; + rapl_pmu_events_group.attrs = rapl_events_srv_attr; + break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ rapl_cntr_mask = RAPL_IDX_HSW; @@ -693,7 +735,13 @@ static int __init rapl_pmu_init(void) /* unsupported */ return 0; } + ret = rapl_check_hw_unit(); + if (ret) + return ret; + /* run cpu model quirks */ + for (quirk = rapl_quirks; quirk; quirk = quirk->next) + quirk->func(); cpu_notifier_register_begin(); for_each_online_cpu(cpu) { @@ -714,14 +762,18 @@ static int __init rapl_pmu_init(void) pmu = __this_cpu_read(rapl_pmu); - pr_info("RAPL PMU detected, hw unit 2^-%d Joules," + pr_info("RAPL PMU detected," " API unit is 2^-32 Joules," " %d fixed counters" " %llu ms ovfl timer\n", - pmu->hw_unit, 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: cpu_notifier_register_done(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7d46bb260334..e2ce85db2283 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,6 +149,9 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PRAM: + printk(KERN_CONT "persistent (type %u)", type); + break; default: printk(KERN_CONT "type %u", type); break; @@ -343,7 +346,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, * continue building up new bios map based on this * information */ - if (current_type != last_type) { + if (current_type != last_type || current_type == E820_PRAM) { if (last_type != 0) { new_bios[new_bios_entry].size = change_point[chgidx]->addr - last_addr; @@ -688,6 +691,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) register_nosave_region(pfn, PFN_UP(ei->addr)); pfn = PFN_DOWN(ei->addr + ei->size); + if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) register_nosave_region(PFN_UP(ei->addr), pfn); @@ -748,7 +752,7 @@ u64 __init early_reserve_e820(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +static unsigned long __init e820_end_pfn(unsigned long limit_pfn) { int i; unsigned long last_pfn = 0; @@ -759,7 +763,11 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) unsigned long start_pfn; unsigned long end_pfn; - if (ei->type != type) + /* + * Persistent memory is accounted as ram for purposes of + * establishing max_pfn and mem_map. + */ + if (ei->type != E820_RAM && ei->type != E820_PRAM) continue; start_pfn = ei->addr >> PAGE_SHIFT; @@ -784,12 +792,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) } unsigned long __init e820_end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); + return e820_end_pfn(MAX_ARCH_PFN); } unsigned long __init e820_end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM); + return e820_end_pfn(1UL << (32-PAGE_SHIFT)); } static void early_panic(char *msg) @@ -866,6 +874,9 @@ static int __init parse_memmap_one(char *p) } else if (*p == '$') { start_at = memparse(p+1, &p); e820_add_region(start_at, mem_size, E820_RESERVED); + } else if (*p == '!') { + start_at = memparse(p+1, &p); + e820_add_region(start_at, mem_size, E820_PRAM); } else e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); @@ -907,6 +918,7 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; + case E820_PRAM: return "Persistent RAM"; default: return "reserved"; } } @@ -940,7 +952,9 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) { + if (((e820.map[i].type != E820_RESERVED) && + (e820.map[i].type != E820_PRAM)) || + res->start < (1ULL<<20)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 49ff55ef9b26..89427d8d4fc5 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -375,12 +375,6 @@ static int __init setup_early_printk(char *buf) if (!strncmp(buf, "xen", 3)) early_console_register(&xenboot_console, keep); #endif -#ifdef CONFIG_EARLY_PRINTK_INTEL_MID - if (!strncmp(buf, "hsu", 3)) { - hsu_early_console_init(buf + 3); - early_console_register(&early_hsu_console, keep); - } -#endif #ifdef CONFIG_EARLY_PRINTK_EFI if (!strncmp(buf, "efi", 3)) early_console_register(&early_efi_console, keep); diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index c7b238494b31..02c2eff7478d 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -295,6 +295,15 @@ system_call_fastpath: * rflags from r11 (but RF and VM bits are forced to 0), * cs and ss are loaded from MSRs. * Restoration of rflags re-enables interrupts. + * + * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss + * descriptor is not reinitialized. This means that we should + * avoid SYSRET with SS == NULL, which could happen if we schedule, + * exit the kernel, and re-enter using an interrupt vector. (All + * interrupt entries on x86_64 set SS to NULL.) We prevent that + * from happening by reloading SS in __switch_to. (Actually + * detecting the failure in 64-bit userspace is tricky but can be + * done.) */ USERGS_SYSRET64 diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 367f39d35e9c..009183276bb7 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -341,7 +341,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct xsave_struct *xsave = &target->thread.fpu.state->xsave; + struct xsave_struct *xsave; int ret; if (!cpu_has_xsave) @@ -351,6 +351,8 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + xsave = &target->thread.fpu.state->xsave; + /* * Copy the 48bytes defined by the software first into the xstate * memory layout in the thread struct, so that we can copy the entire @@ -369,7 +371,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct xsave_struct *xsave = &target->thread.fpu.state->xsave; + struct xsave_struct *xsave; int ret; if (!cpu_has_xsave) @@ -379,6 +381,8 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + xsave = &target->thread.fpu.state->xsave; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c new file mode 100644 index 000000000000..3420c874ddc5 --- /dev/null +++ b/arch/x86/kernel/pmem.c @@ -0,0 +1,53 @@ +/* + * Copyright (c) 2015, Christoph Hellwig. + */ +#include <linux/memblock.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <asm/e820.h> +#include <asm/page_types.h> +#include <asm/setup.h> + +static __init void register_pmem_device(struct resource *res) +{ + struct platform_device *pdev; + int error; + + pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); + if (!pdev) + return; + + error = platform_device_add_resources(pdev, res, 1); + if (error) + goto out_put_pdev; + + error = platform_device_add(pdev); + if (error) + goto out_put_pdev; + return; + +out_put_pdev: + dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); + platform_device_put(pdev); +} + +static __init int register_pmem_devices(void) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (ei->type == E820_PRAM) { + struct resource res = { + .flags = IORESOURCE_MEM, + .start = ei->addr, + .end = ei->addr + ei->size - 1, + }; + register_pmem_device(&res); + } + } + + return 0; +} +device_initcall(register_pmem_devices); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4baaa972f52a..ddfdbf74f174 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -419,6 +419,34 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { + /* + * AMD CPUs have a misfeature: SYSRET sets the SS selector but + * does not update the cached descriptor. As a result, if we + * do SYSRET while SS is NULL, we'll end up in user mode with + * SS apparently equal to __USER_DS but actually unusable. + * + * The straightforward workaround would be to fix it up just + * before SYSRET, but that would slow down the system call + * fast paths. Instead, we ensure that SS is never NULL in + * system call context. We do this by replacing NULL SS + * selectors at every context switch. SYSCALL sets up a valid + * SS, so the only way to get NULL is to re-enter the kernel + * from CPL 3 through an interrupt. Since that can't happen + * in the same task as a running syscall, we are guaranteed to + * context switch between every interrupt vector entry and a + * subsequent SYSRET. + * + * We read SS first because SS reads are much faster than + * writes. Out of caution, we force SS to __KERNEL_DS even if + * it previously had a different non-NULL value. + */ + unsigned short ss_sel; + savesegment(ss, ss_sel); + if (ss_sel != __KERNEL_DS) + loadsegment(ss, __KERNEL_DS); + } + return prev_p; } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index e5ecd20e72dd..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index f9804080ccb3..1ea14fd53933 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -616,7 +616,8 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - bool failed; + bool stepping, failed; + /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { /* If so, check system call restarting.. */ @@ -640,12 +641,13 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) } /* - * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF - * flag so that register information in the sigcontext is correct. + * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now + * so that register information in the sigcontext is correct and + * then notify the tracer before entering the signal handler. */ - if (unlikely(regs->flags & X86_EFLAGS_TF) && - likely(test_and_clear_thread_flag(TIF_FORCED_TF))) - regs->flags &= ~X86_EFLAGS_TF; + stepping = test_thread_flag(TIF_SINGLESTEP); + if (stepping) + user_disable_single_step(current); failed = (setup_rt_frame(ksig, regs) < 0); if (!failed) { @@ -656,10 +658,8 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * it might disable possible debug exception from the * signal handler. * - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. + * Clear TF for the case when it wasn't set by debugger to + * avoid the recursive send_sigtrap() in SIGTRAP handler. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF); /* @@ -668,7 +668,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) if (used_math()) fpu_reset_state(current); } - signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); + signal_setup_done(failed, ksig, stepping); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c index 6eb5c20ee373..d090ecf08809 100644 --- a/arch/x86/kvm/assigned-dev.c +++ b/arch/x86/kvm/assigned-dev.c @@ -666,7 +666,7 @@ static int probe_sysfs_permissions(struct pci_dev *dev) if (r) return r; - inode = path.dentry->d_inode; + inode = d_backing_inode(path.dentry); r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS); path_put(&path); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d67206a7b99a..629af0f1c5c4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -683,8 +683,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, unsigned long bitmap = 1; struct kvm_lapic **dst; int i; - bool ret = false; - bool x2apic_ipi = src && apic_x2apic_mode(src); + bool ret, x2apic_ipi; *r = -1; @@ -696,16 +695,18 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, if (irq->shorthand) return false; + x2apic_ipi = src && apic_x2apic_mode(src); if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) return false; + ret = true; rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); - if (!map) + if (!map) { + ret = false; goto out; - - ret = true; + } if (irq->dest_mode == APIC_DEST_PHYSICAL) { if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 146f295ee322..d43867c33bc4 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4481,9 +4481,11 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, pfn = spte_to_pfn(*sptep); /* - * Only EPT supported for now; otherwise, one would need to - * find out efficiently whether the guest page tables are - * also using huge pages. + * We cannot do huge page mapping for indirect shadow pages, + * which are found on the last rmap (level = 1) when not using + * tdp; such shadow pages are synced with the page table in + * the guest, and the guest page table is using 4K page size + * mapping if the indirect sp has level = 1. */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && @@ -4504,19 +4506,12 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, bool flush = false; unsigned long *rmapp; unsigned long last_index, index; - gfn_t gfn_start, gfn_end; spin_lock(&kvm->mmu_lock); - gfn_start = memslot->base_gfn; - gfn_end = memslot->base_gfn + memslot->npages - 1; - - if (gfn_start >= gfn_end) - goto out; - rmapp = memslot->arch.rmap[0]; - last_index = gfn_to_index(gfn_end, memslot->base_gfn, - PT_PAGE_TABLE_LEVEL); + last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1, + memslot->base_gfn, PT_PAGE_TABLE_LEVEL); for (index = 0; index <= last_index; ++index, ++rmapp) { if (*rmapp) @@ -4534,7 +4529,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, if (flush) kvm_flush_remote_tlbs(kvm); -out: spin_unlock(&kvm->mmu_lock); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index f5e8dce8046c..f7b61687bd79 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3622,8 +3622,16 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ? - KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); + /* + * Pass through host's Machine Check Enable value to hw_cr4, which + * is in force while we are in guest mode. Do not let guests control + * this bit, even if host CR4.MCE == 0. + */ + unsigned long hw_cr4 = + (cr4_read_shadow() & X86_CR4_MCE) | + (cr4 & ~X86_CR4_MCE) | + (to_vmx(vcpu)->rmode.vm86_active ? + KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON); if (cr4 & X86_CR4_VMXE) { /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e1a81267f3f6..c73efcd03e29 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1669,12 +1669,28 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &guest_hv_clock, sizeof(guest_hv_clock)))) return 0; - /* - * The interface expects us to write an even number signaling that the - * update is finished. Since the guest won't see the intermediate - * state, we just increase by 2 at the end. + /* This VCPU is paused, but it's legal for a guest to read another + * VCPU's kvmclock, so we really have to follow the specification where + * it says that version is odd if data is being modified, and even after + * it is consistent. + * + * Version field updates must be kept separate. This is because + * kvm_write_guest_cached might use a "rep movs" instruction, and + * writes within a string instruction are weakly ordered. So there + * are three writes overall. + * + * As a small optimization, only write the version field in the first + * and third write. The vcpu->pv_time cache is still valid, because the + * version field is the first in the struct. */ - vcpu->hv_clock.version = guest_hv_clock.version + 2; + BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); + + vcpu->hv_clock.version = guest_hv_clock.version + 1; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); + + smp_wmb(); /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); @@ -1695,6 +1711,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kvm_write_guest_cached(v->kvm, &vcpu->pv_time, &vcpu->hv_clock, sizeof(vcpu->hv_clock)); + + smp_wmb(); + + vcpu->hv_clock.version++; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); return 0; } @@ -5799,7 +5822,6 @@ int kvm_arch_init(void *opaque) kvm_set_mmio_spte_mask(); kvm_x86_ops = ops; - kvm_init_msr_list(); kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); @@ -7253,7 +7275,14 @@ void kvm_arch_hardware_disable(void) int kvm_arch_hardware_setup(void) { - return kvm_x86_ops->hardware_setup(); + int r; + + r = kvm_x86_ops->hardware_setup(); + if (r != 0) + return r; + + kvm_init_msr_list(); + return 0; } void kvm_arch_hardware_unsetup(void) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 717908b16037..8f9a133cc099 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -87,8 +87,7 @@ struct lguest_data lguest_data = { .hcall_status = { [0 ... LHCALL_RING_SIZE-1] = 0xFF }, - .noirq_start = (u32)lguest_noirq_start, - .noirq_end = (u32)lguest_noirq_end, + .noirq_iret = (u32)lguest_noirq_iret, .kernel_address = PAGE_OFFSET, .blocked_interrupts = { 1 }, /* Block timer interrupts */ .syscall_vec = SYSCALL_VECTOR, @@ -262,7 +261,7 @@ PV_CALLEE_SAVE_REGS_THUNK(lguest_save_fl); PV_CALLEE_SAVE_REGS_THUNK(lguest_irq_disable); /*:*/ -/* These are in i386_head.S */ +/* These are in head_32.S */ extern void lg_irq_enable(void); extern void lg_restore_fl(unsigned long flags); @@ -1368,7 +1367,7 @@ static void lguest_restart(char *reason) * fit comfortably. * * First we need assembly templates of each of the patchable Guest operations, - * and these are in i386_head.S. + * and these are in head_32.S. */ /*G:060 We construct a table from the assembler templates: */ diff --git a/arch/x86/lguest/head_32.S b/arch/x86/lguest/head_32.S index 6ddfe4fc23c3..d5ae63f5ec5d 100644 --- a/arch/x86/lguest/head_32.S +++ b/arch/x86/lguest/head_32.S @@ -84,7 +84,7 @@ ENTRY(lg_irq_enable) * set lguest_data.irq_pending to X86_EFLAGS_IF. If it's not zero, we * jump to send_interrupts, otherwise we're done. */ - testl $0, lguest_data+LGUEST_DATA_irq_pending + cmpl $0, lguest_data+LGUEST_DATA_irq_pending jnz send_interrupts /* * One cool thing about x86 is that you can do many things without using @@ -133,9 +133,8 @@ ENTRY(lg_restore_fl) ret /*:*/ -/* These demark the EIP range where host should never deliver interrupts. */ -.global lguest_noirq_start -.global lguest_noirq_end +/* These demark the EIP where host should never deliver interrupts. */ +.global lguest_noirq_iret /*M:004 * When the Host reflects a trap or injects an interrupt into the Guest, it @@ -168,29 +167,26 @@ ENTRY(lg_restore_fl) * So we have to copy eflags from the stack to lguest_data.irq_enabled before * we do the "iret". * - * There are two problems with this: firstly, we need to use a register to do - * the copy and secondly, the whole thing needs to be atomic. The first - * problem is easy to solve: push %eax on the stack so we can use it, and then - * restore it at the end just before the real "iret". + * There are two problems with this: firstly, we can't clobber any registers + * and secondly, the whole thing needs to be atomic. The first problem + * is solved by using "push memory"/"pop memory" instruction pair for copying. * * The second is harder: copying eflags to lguest_data.irq_enabled will turn * interrupts on before we're finished, so we could be interrupted before we - * return to userspace or wherever. Our solution to this is to surround the - * code with lguest_noirq_start: and lguest_noirq_end: labels. We tell the + * return to userspace or wherever. Our solution to this is to tell the * Host that it is *never* to interrupt us there, even if interrupts seem to be - * enabled. + * enabled. (It's not necessary to protect pop instruction, since + * data gets updated only after it completes, so we only need to protect + * one instruction, iret). */ ENTRY(lguest_iret) - pushl %eax - movl 12(%esp), %eax -lguest_noirq_start: + pushl 2*4(%esp) /* * Note the %ss: segment prefix here. Normal data accesses use the * "ds" segment, but that will have already been restored for whatever * we're returning to (such as userspace): we can't trust it. The %ss: * prefix makes sure we use the stack segment, which is still valid. */ - movl %eax,%ss:lguest_data+LGUEST_DATA_irq_enabled - popl %eax + popl %ss:lguest_data+LGUEST_DATA_irq_enabled +lguest_noirq_iret: iret -lguest_noirq_end: diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 1f33b3d1fd68..0a42327a59d7 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -82,7 +82,7 @@ copy_user_handle_tail(char *to, char *from, unsigned len) clac(); /* If the destination is a kernel buffer, we always clear the end */ - if ((unsigned long)to >= TASK_SIZE_MAX) + if (!__addr_ok(to)) memset(to, 0, len); return len; } diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile index 0a8ee703b9fa..0ce1b1913673 100644 --- a/arch/x86/platform/intel-mid/Makefile +++ b/arch/x86/platform/intel-mid/Makefile @@ -1,5 +1,4 @@ obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfl.o -obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_intel_mid.o # SFI specific code ifdef CONFIG_X86_INTEL_MID diff --git a/arch/x86/platform/intel-mid/early_printk_intel_mid.c b/arch/x86/platform/intel-mid/early_printk_intel_mid.c deleted file mode 100644 index 4e720829ab90..000000000000 --- a/arch/x86/platform/intel-mid/early_printk_intel_mid.c +++ /dev/null @@ -1,112 +0,0 @@ -/* - * early_printk_intel_mid.c - early consoles for Intel MID platforms - * - * Copyright (c) 2008-2010, Intel Corporation - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -/* - * This file implements early console named hsu. - * hsu is based on a High Speed UART device which only exists in the Medfield - * platform - */ - -#include <linux/serial_reg.h> -#include <linux/serial_mfd.h> -#include <linux/console.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/io.h> - -#include <asm/fixmap.h> -#include <asm/pgtable.h> -#include <asm/intel-mid.h> - -/* - * Following is the early console based on Medfield HSU (High - * Speed UART) device. - */ -#define HSU_PORT_BASE 0xffa28080 - -static void __iomem *phsu; - -void hsu_early_console_init(const char *s) -{ - unsigned long paddr, port = 0; - u8 lcr; - - /* - * Select the early HSU console port if specified by user in the - * kernel command line. - */ - if (*s && !kstrtoul(s, 10, &port)) - port = clamp_val(port, 0, 2); - - paddr = HSU_PORT_BASE + port * 0x80; - phsu = (void __iomem *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE, paddr); - - /* Disable FIFO */ - writeb(0x0, phsu + UART_FCR); - - /* Set to default 115200 bps, 8n1 */ - lcr = readb(phsu + UART_LCR); - writeb((0x80 | lcr), phsu + UART_LCR); - writeb(0x18, phsu + UART_DLL); - writeb(lcr, phsu + UART_LCR); - writel(0x3600, phsu + UART_MUL*4); - - writeb(0x8, phsu + UART_MCR); - writeb(0x7, phsu + UART_FCR); - writeb(0x3, phsu + UART_LCR); - - /* Clear IRQ status */ - readb(phsu + UART_LSR); - readb(phsu + UART_RX); - readb(phsu + UART_IIR); - readb(phsu + UART_MSR); - - /* Enable FIFO */ - writeb(0x7, phsu + UART_FCR); -} - -#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) - -static void early_hsu_putc(char ch) -{ - unsigned int timeout = 10000; /* 10ms */ - u8 status; - - while (--timeout) { - status = readb(phsu + UART_LSR); - if (status & BOTH_EMPTY) - break; - udelay(1); - } - - /* Only write the char when there was no timeout */ - if (timeout) - writeb(ch, phsu + UART_TX); -} - -static void early_hsu_write(struct console *con, const char *str, unsigned n) -{ - int i; - - for (i = 0; i < n && *str; i++) { - if (*str == '\n') - early_hsu_putc('\r'); - early_hsu_putc(*str); - str++; - } -} - -struct console early_hsu_console = { - .name = "earlyhsu", - .write = early_hsu_write, - .flags = CON_PRINTBUFFER, - .index = -1, -}; diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile index 3323c2745248..a55abb9f6c5e 100644 --- a/arch/x86/syscalls/Makefile +++ b/arch/x86/syscalls/Makefile @@ -19,6 +19,9 @@ quiet_cmd_syshdr = SYSHDR $@ quiet_cmd_systbl = SYSTBL $@ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ +quiet_cmd_hypercalls = HYPERCALLS $@ + cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^) + syshdr_abi_unistd_32 := i386 $(uapi)/unistd_32.h: $(syscall32) $(syshdr) $(call if_changed,syshdr) @@ -47,10 +50,16 @@ $(out)/syscalls_32.h: $(syscall32) $(systbl) $(out)/syscalls_64.h: $(syscall64) $(systbl) $(call if_changed,systbl) +$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh + $(call if_changed,hypercalls) + +$(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h + uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h syshdr-y += syscalls_32.h syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h +syshdr-$(CONFIG_XEN) += xen-hypercalls.h targets += $(uapisyshdr-y) $(syshdr-y) diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 40d2473836c9..9793322751e0 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; - u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * When looping to get a consistent (time-info, tsc) pair, we - * also need to deal with the possibility we can switch vcpus, - * so make sure we always re-fetch time-info for the current vcpu. + * Note: hypervisor must guarantee that: + * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. + * 2. that per-CPU pvclock time info is updated if the + * underlying CPU changes. + * 3. that version is increased whenever underlying CPU + * changes. + * */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - /* Make sure migrate_count will change if we leave the VCPU. */ - do { - pvti = get_pvti(cpu); - migrate_count = pvti->migrate_count; - - cpu1 = cpu; - cpu = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1)); + pvti = get_pvti(cpu); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * - We must read TSC of pvti's VCPU. - * - KVM doesn't follow the versioning protocol, so data could - * change before version if we left the VCPU. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. */ - smp_rmb(); - } while (unlikely((pvti->pvti.version & 1) || - pvti->pvti.version != version || - pvti->migrate_count != migrate_count)); + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 7005ced5d1ad..70e060ad879a 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -7,6 +7,7 @@ #include <xen/xen.h> #include <xen/interface/physdev.h> #include "xen-ops.h" +#include "smp.h" static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) { @@ -28,7 +29,186 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) return 0xfd; } +static unsigned long xen_set_apic_id(unsigned int x) +{ + WARN_ON(1); + return x; +} + +static unsigned int xen_get_apic_id(unsigned long x) +{ + return ((x)>>24) & 0xFFu; +} + +static u32 xen_apic_read(u32 reg) +{ + struct xen_platform_op op = { + .cmd = XENPF_get_cpuinfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.pcpu_info.xen_cpuid = 0, + }; + int ret = 0; + + /* Shouldn't need this as APIC is turned off for PV, and we only + * get called on the bootup processor. But just in case. */ + if (!xen_initial_domain() || smp_processor_id()) + return 0; + + if (reg == APIC_LVR) + return 0x10; +#ifdef CONFIG_X86_32 + if (reg == APIC_LDR) + return SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); +#endif + if (reg != APIC_ID) + return 0; + + ret = HYPERVISOR_dom0_op(&op); + if (ret) + return 0; + + return op.u.pcpu_info.apic_id << 24; +} + +static void xen_apic_write(u32 reg, u32 val) +{ + /* Warn to see if there's any stray references */ + WARN(1,"register: %x, value: %x\n", reg, val); +} + +static u64 xen_apic_icr_read(void) +{ + return 0; +} + +static void xen_apic_icr_write(u32 low, u32 id) +{ + /* Warn to see if there's any stray references */ + WARN_ON(1); +} + +static u32 xen_safe_apic_wait_icr_idle(void) +{ + return 0; +} + +static int xen_apic_probe_pv(void) +{ + if (xen_pv_domain()) + return 1; + + return 0; +} + +static int xen_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return xen_pv_domain(); +} + +static int xen_id_always_valid(int apicid) +{ + return 1; +} + +static int xen_id_always_registered(void) +{ + return 1; +} + +static int xen_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return initial_apic_id >> index_msb; +} + +#ifdef CONFIG_X86_32 +static int xen_x86_32_early_logical_apicid(int cpu) +{ + /* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */ + return 1 << cpu; +} +#endif + +static void xen_noop(void) +{ +} + +static void xen_silent_inquire(int apicid) +{ +} + +static struct apic xen_pv_apic = { + .name = "Xen PV", + .probe = xen_apic_probe_pv, + .acpi_madt_oem_check = xen_madt_oem_check, + .apic_id_valid = xen_id_always_valid, + .apic_id_registered = xen_id_always_registered, + + /* .irq_delivery_mode - used in native_compose_msi_msg only */ + /* .irq_dest_mode - used in native_compose_msi_msg only */ + + .target_cpus = default_target_cpus, + .disable_esr = 0, + /* .dest_logical - default_send_IPI_ use it but we use our own. */ + .check_apicid_used = default_check_apicid_used, /* Used on 32-bit */ + + .vector_allocation_domain = flat_vector_allocation_domain, + .init_apic_ldr = xen_noop, /* setup_local_APIC calls it */ + + .ioapic_phys_id_map = default_ioapic_phys_id_map, /* Used on 32-bit */ + .setup_apic_routing = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = physid_set_mask_of_physid, /* Used on 32-bit */ + .check_phys_apicid_present = default_check_phys_apicid_present, /* smp_sanity_check needs it */ + .phys_pkg_id = xen_phys_pkg_id, /* detect_ht */ + + .get_apic_id = xen_get_apic_id, + .set_apic_id = xen_set_apic_id, /* Can be NULL on 32-bit. */ + .apic_id_mask = 0xFF << 24, /* Used by verify_local_APIC. Match with what xen_get_apic_id does. */ + + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + +#ifdef CONFIG_SMP + .send_IPI_mask = xen_send_IPI_mask, + .send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself, + .send_IPI_allbutself = xen_send_IPI_allbutself, + .send_IPI_all = xen_send_IPI_all, + .send_IPI_self = xen_send_IPI_self, +#endif + /* .wait_for_init_deassert- used by AP bootup - smp_callin which we don't use */ + .inquire_remote_apic = xen_silent_inquire, + + .read = xen_apic_read, + .write = xen_apic_write, + .eoi_write = xen_apic_write, + + .icr_read = xen_apic_icr_read, + .icr_write = xen_apic_icr_write, + .wait_icr_idle = xen_noop, + .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle, + +#ifdef CONFIG_X86_32 + /* generic_processor_info and setup_local_APIC. */ + .x86_32_early_logical_apicid = xen_x86_32_early_logical_apicid, +#endif +}; + +static void __init xen_apic_check(void) +{ + if (apic == &xen_pv_apic) + return; + + pr_info("Switched APIC routing from %s to %s.\n", apic->name, + xen_pv_apic.name); + apic = &xen_pv_apic; +} void __init xen_init_apic(void) { x86_io_apic_ops.read = xen_io_apic_read; + /* On PV guests the APIC CPUID bit is disabled so none of the + * routines end up executing. */ + if (!xen_initial_domain()) + apic = &xen_pv_apic; + + x86_platform.apic_post_init = xen_apic_check; } +apic_driver(xen_pv_apic); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 81665c9f2132..94578efd3067 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -928,92 +928,6 @@ static void xen_io_delay(void) { } -#ifdef CONFIG_X86_LOCAL_APIC -static unsigned long xen_set_apic_id(unsigned int x) -{ - WARN_ON(1); - return x; -} -static unsigned int xen_get_apic_id(unsigned long x) -{ - return ((x)>>24) & 0xFFu; -} -static u32 xen_apic_read(u32 reg) -{ - struct xen_platform_op op = { - .cmd = XENPF_get_cpuinfo, - .interface_version = XENPF_INTERFACE_VERSION, - .u.pcpu_info.xen_cpuid = 0, - }; - int ret = 0; - - /* Shouldn't need this as APIC is turned off for PV, and we only - * get called on the bootup processor. But just in case. */ - if (!xen_initial_domain() || smp_processor_id()) - return 0; - - if (reg == APIC_LVR) - return 0x10; - - if (reg != APIC_ID) - return 0; - - ret = HYPERVISOR_dom0_op(&op); - if (ret) - return 0; - - return op.u.pcpu_info.apic_id << 24; -} - -static void xen_apic_write(u32 reg, u32 val) -{ - /* Warn to see if there's any stray references */ - WARN_ON(1); -} - -static u64 xen_apic_icr_read(void) -{ - return 0; -} - -static void xen_apic_icr_write(u32 low, u32 id) -{ - /* Warn to see if there's any stray references */ - WARN_ON(1); -} - -static void xen_apic_wait_icr_idle(void) -{ - return; -} - -static u32 xen_safe_apic_wait_icr_idle(void) -{ - return 0; -} - -static void set_xen_basic_apic_ops(void) -{ - apic->read = xen_apic_read; - apic->write = xen_apic_write; - apic->icr_read = xen_apic_icr_read; - apic->icr_write = xen_apic_icr_write; - apic->wait_icr_idle = xen_apic_wait_icr_idle; - apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle; - apic->set_apic_id = xen_set_apic_id; - apic->get_apic_id = xen_get_apic_id; - -#ifdef CONFIG_SMP - apic->send_IPI_allbutself = xen_send_IPI_allbutself; - apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself; - apic->send_IPI_mask = xen_send_IPI_mask; - apic->send_IPI_all = xen_send_IPI_all; - apic->send_IPI_self = xen_send_IPI_self; -#endif -} - -#endif - static void xen_clts(void) { struct multicall_space mcs; @@ -1619,7 +1533,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* * set up the basic apic ops. */ - set_xen_basic_apic_ops(); + xen_init_apic(); #endif if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) { @@ -1732,8 +1646,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (HYPERVISOR_dom0_op(&op) == 0) boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; - xen_init_apic(); - /* Make sure ACS will be enabled */ pci_request_acs(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 65083ad63b6f..dd151b2045b0 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2436,99 +2436,11 @@ void __init xen_hvm_init_mmu_ops(void) } #endif -#ifdef CONFIG_XEN_PVH -/* - * Map foreign gfn (fgfn), to local pfn (lpfn). This for the user - * space creating new guest on pvh dom0 and needing to map domU pages. - */ -static int xlate_add_to_p2m(unsigned long lpfn, unsigned long fgfn, - unsigned int domid) -{ - int rc, err = 0; - xen_pfn_t gpfn = lpfn; - xen_ulong_t idx = fgfn; - - struct xen_add_to_physmap_range xatp = { - .domid = DOMID_SELF, - .foreign_domid = domid, - .size = 1, - .space = XENMAPSPACE_gmfn_foreign, - }; - set_xen_guest_handle(xatp.idxs, &idx); - set_xen_guest_handle(xatp.gpfns, &gpfn); - set_xen_guest_handle(xatp.errs, &err); - - rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp); - if (rc < 0) - return rc; - return err; -} - -static int xlate_remove_from_p2m(unsigned long spfn, int count) -{ - struct xen_remove_from_physmap xrp; - int i, rc; - - for (i = 0; i < count; i++) { - xrp.domid = DOMID_SELF; - xrp.gpfn = spfn+i; - rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp); - if (rc) - break; - } - return rc; -} - -struct xlate_remap_data { - unsigned long fgfn; /* foreign domain's gfn */ - pgprot_t prot; - domid_t domid; - int index; - struct page **pages; -}; - -static int xlate_map_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) -{ - int rc; - struct xlate_remap_data *remap = data; - unsigned long pfn = page_to_pfn(remap->pages[remap->index++]); - pte_t pteval = pte_mkspecial(pfn_pte(pfn, remap->prot)); - - rc = xlate_add_to_p2m(pfn, remap->fgfn, remap->domid); - if (rc) - return rc; - native_set_pte(ptep, pteval); - - return 0; -} - -static int xlate_remap_gfn_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long mfn, - int nr, pgprot_t prot, unsigned domid, - struct page **pages) -{ - int err; - struct xlate_remap_data pvhdata; - - BUG_ON(!pages); - - pvhdata.fgfn = mfn; - pvhdata.prot = prot; - pvhdata.domid = domid; - pvhdata.index = 0; - pvhdata.pages = pages; - err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT, - xlate_map_pte_fn, &pvhdata); - flush_tlb_all(); - return err; -} -#endif - #define REMAP_BATCH_SIZE 16 struct remap_data { - unsigned long mfn; + xen_pfn_t *mfn; + bool contiguous; pgprot_t prot; struct mmu_update *mmu_update; }; @@ -2537,7 +2449,14 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct remap_data *rmd = data; - pte_t pte = pte_mkspecial(mfn_pte(rmd->mfn++, rmd->prot)); + pte_t pte = pte_mkspecial(mfn_pte(*rmd->mfn, rmd->prot)); + + /* If we have a contigious range, just update the mfn itself, + else update pointer to be "next mfn". */ + if (rmd->contiguous) + (*rmd->mfn)++; + else + rmd->mfn++; rmd->mmu_update->ptr = virt_to_machine(ptep).maddr; rmd->mmu_update->val = pte_val_ma(pte); @@ -2546,26 +2465,26 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, return 0; } -int xen_remap_domain_mfn_range(struct vm_area_struct *vma, - unsigned long addr, - xen_pfn_t mfn, int nr, - pgprot_t prot, unsigned domid, - struct page **pages) - +static int do_remap_mfn(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *mfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned domid, + struct page **pages) { + int err = 0; struct remap_data rmd; struct mmu_update mmu_update[REMAP_BATCH_SIZE]; - int batch; unsigned long range; - int err = 0; + int mapped = 0; BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO))); if (xen_feature(XENFEAT_auto_translated_physmap)) { #ifdef CONFIG_XEN_PVH /* We need to update the local page tables and the xen HAP */ - return xlate_remap_gfn_range(vma, addr, mfn, nr, prot, - domid, pages); + return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr, + prot, domid, pages); #else return -EINVAL; #endif @@ -2573,9 +2492,15 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, rmd.mfn = mfn; rmd.prot = prot; + /* We use the err_ptr to indicate if there we are doing a contigious + * mapping or a discontigious mapping. */ + rmd.contiguous = !err_ptr; while (nr) { - batch = min(REMAP_BATCH_SIZE, nr); + int index = 0; + int done = 0; + int batch = min(REMAP_BATCH_SIZE, nr); + int batch_left = batch; range = (unsigned long)batch << PAGE_SHIFT; rmd.mmu_update = mmu_update; @@ -2584,23 +2509,72 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, if (err) goto out; - err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid); - if (err < 0) - goto out; + /* We record the error for each page that gives an error, but + * continue mapping until the whole set is done */ + do { + int i; + + err = HYPERVISOR_mmu_update(&mmu_update[index], + batch_left, &done, domid); + + /* + * @err_ptr may be the same buffer as @mfn, so + * only clear it after each chunk of @mfn is + * used. + */ + if (err_ptr) { + for (i = index; i < index + done; i++) + err_ptr[i] = 0; + } + if (err < 0) { + if (!err_ptr) + goto out; + err_ptr[i] = err; + done++; /* Skip failed frame. */ + } else + mapped += done; + batch_left -= done; + index += done; + } while (batch_left); nr -= batch; addr += range; + if (err_ptr) + err_ptr += batch; } - - err = 0; out: xen_flush_tlb_all(); - return err; + return err < 0 ? err : mapped; +} + +int xen_remap_domain_mfn_range(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t mfn, int nr, + pgprot_t prot, unsigned domid, + struct page **pages) +{ + return do_remap_mfn(vma, addr, &mfn, nr, NULL, prot, domid, pages); } EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); +int xen_remap_domain_mfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *mfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned domid, struct page **pages) +{ + /* We BUG_ON because it's a programmer error to pass a NULL err_ptr, + * and the consequences later is quite hard to detect what the actual + * cause of "wrong memory was mapped in". + */ + BUG_ON(err_ptr == NULL); + return do_remap_mfn(vma, addr, mfn, nr, err_ptr, prot, domid, pages); +} +EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array); + + /* Returns: 0 success */ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, int numpgs, struct page **pages) @@ -2609,22 +2583,7 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, return 0; #ifdef CONFIG_XEN_PVH - while (numpgs--) { - /* - * The mmu has already cleaned up the process mmu - * resources at this point (lookup_address will return - * NULL). - */ - unsigned long pfn = page_to_pfn(pages[numpgs]); - - xlate_remove_from_p2m(pfn, 1); - } - /* - * We don't need to flush tlbs because as part of - * xlate_remove_from_p2m, the hypervisor will do tlb flushes - * after removing the p2m entries from the EPT/NPT - */ - return 0; + return xen_xlate_unmap_gfn_range(vma, numpgs, pages); #else return -EINVAL; #endif diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c index 520022d1a181..a702ec2f5931 100644 --- a/arch/x86/xen/trace.c +++ b/arch/x86/xen/trace.c @@ -1,54 +1,12 @@ #include <linux/ftrace.h> #include <xen/interface/xen.h> +#include <xen/interface/xen-mca.h> -#define N(x) [__HYPERVISOR_##x] = "("#x")" +#define HYPERCALL(x) [__HYPERVISOR_##x] = "("#x")", static const char *xen_hypercall_names[] = { - N(set_trap_table), - N(mmu_update), - N(set_gdt), - N(stack_switch), - N(set_callbacks), - N(fpu_taskswitch), - N(sched_op_compat), - N(dom0_op), - N(set_debugreg), - N(get_debugreg), - N(update_descriptor), - N(memory_op), - N(multicall), - N(update_va_mapping), - N(set_timer_op), - N(event_channel_op_compat), - N(xen_version), - N(console_io), - N(physdev_op_compat), - N(grant_table_op), - N(vm_assist), - N(update_va_mapping_otherdomain), - N(iret), - N(vcpu_op), - N(set_segment_base), - N(mmuext_op), - N(acm_op), - N(nmi_op), - N(sched_op), - N(callback_op), - N(xenoprof_op), - N(event_channel_op), - N(physdev_op), - N(hvm_op), - -/* Architecture-specific hypercall definitions. */ - N(arch_0), - N(arch_1), - N(arch_2), - N(arch_3), - N(arch_4), - N(arch_5), - N(arch_6), - N(arch_7), +#include <asm/xen-hypercalls.h> }; -#undef N +#undef HYPERCALL static const char *xen_hypercall_name(unsigned op) { diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 674b222544b7..8afdfccf6086 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -12,6 +12,8 @@ #include <xen/interface/elfnote.h> #include <xen/interface/features.h> +#include <xen/interface/xen.h> +#include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> #ifdef CONFIG_XEN_PVH @@ -85,59 +87,14 @@ ENTRY(xen_pvh_early_cpu_init) .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) -#define NEXT_HYPERCALL(x) \ - ENTRY(xen_hypercall_##x) \ - .skip 32 - -NEXT_HYPERCALL(set_trap_table) -NEXT_HYPERCALL(mmu_update) -NEXT_HYPERCALL(set_gdt) -NEXT_HYPERCALL(stack_switch) -NEXT_HYPERCALL(set_callbacks) -NEXT_HYPERCALL(fpu_taskswitch) -NEXT_HYPERCALL(sched_op_compat) -NEXT_HYPERCALL(platform_op) -NEXT_HYPERCALL(set_debugreg) -NEXT_HYPERCALL(get_debugreg) -NEXT_HYPERCALL(update_descriptor) -NEXT_HYPERCALL(ni) -NEXT_HYPERCALL(memory_op) -NEXT_HYPERCALL(multicall) -NEXT_HYPERCALL(update_va_mapping) -NEXT_HYPERCALL(set_timer_op) -NEXT_HYPERCALL(event_channel_op_compat) -NEXT_HYPERCALL(xen_version) -NEXT_HYPERCALL(console_io) -NEXT_HYPERCALL(physdev_op_compat) -NEXT_HYPERCALL(grant_table_op) -NEXT_HYPERCALL(vm_assist) -NEXT_HYPERCALL(update_va_mapping_otherdomain) -NEXT_HYPERCALL(iret) -NEXT_HYPERCALL(vcpu_op) -NEXT_HYPERCALL(set_segment_base) -NEXT_HYPERCALL(mmuext_op) -NEXT_HYPERCALL(xsm_op) -NEXT_HYPERCALL(nmi_op) -NEXT_HYPERCALL(sched_op) -NEXT_HYPERCALL(callback_op) -NEXT_HYPERCALL(xenoprof_op) -NEXT_HYPERCALL(event_channel_op) -NEXT_HYPERCALL(physdev_op) -NEXT_HYPERCALL(hvm_op) -NEXT_HYPERCALL(sysctl) -NEXT_HYPERCALL(domctl) -NEXT_HYPERCALL(kexec_op) -NEXT_HYPERCALL(tmem_op) /* 38 */ -ENTRY(xen_hypercall_rsvr) - .skip 320 -NEXT_HYPERCALL(mca) /* 48 */ -NEXT_HYPERCALL(arch_1) -NEXT_HYPERCALL(arch_2) -NEXT_HYPERCALL(arch_3) -NEXT_HYPERCALL(arch_4) -NEXT_HYPERCALL(arch_5) -NEXT_HYPERCALL(arch_6) - .balign PAGE_SIZE + .skip PAGE_SIZE + +#define HYPERCALL(n) \ + .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ + .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 +#include <asm/xen-hypercalls.h> +#undef HYPERCALL + .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") |