diff options
author | Dave Airlie <airlied@redhat.com> | 2016-07-26 17:26:29 +1000 |
---|---|---|
committer | Dave Airlie <airlied@redhat.com> | 2016-07-26 17:26:29 +1000 |
commit | 5e580523d9128a4d8364fe89d36c38fc7819c8dd (patch) | |
tree | 852fb2427d980830ae8686a91e4ca5873f259ab9 /arch/x86 | |
parent | c11dea5b0290984fa48111957ba3fdc5b3bdae5a (diff) | |
parent | 523d939ef98fd712632d93a5a2b588e477a7565e (diff) | |
download | op-kernel-dev-5e580523d9128a4d8364fe89d36c38fc7819c8dd.zip op-kernel-dev-5e580523d9128a4d8364fe89d36c38fc7819c8dd.tar.gz |
Backmerge tag 'v4.7' into drm-next
Linux 4.7
As requested by Daniel Vetter as the conflicts were getting messy.
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/events/core.c | 13 | ||||
-rw-r--r-- | arch/x86/events/intel/Makefile | 4 | ||||
-rw-r--r-- | arch/x86/events/intel/core.c | 29 | ||||
-rw-r--r-- | arch/x86/include/asm/cpufeatures.h | 6 | ||||
-rw-r--r-- | arch/x86/include/asm/pvclock.h | 25 | ||||
-rw-r--r-- | arch/x86/kernel/amd_nb.c | 4 | ||||
-rw-r--r-- | arch/x86/kernel/early-quirks.c | 105 | ||||
-rw-r--r-- | arch/x86/kernel/pvclock.c | 11 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 23 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 6 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 7 | ||||
-rw-r--r-- | arch/x86/mm/kasan_init_64.c | 4 | ||||
-rw-r--r-- | arch/x86/pci/acpi.c | 1 | ||||
-rw-r--r-- | arch/x86/power/hibernate_64.c | 97 | ||||
-rw-r--r-- | arch/x86/power/hibernate_asm_64.S | 55 |
16 files changed, 284 insertions, 109 deletions
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee..91eac39 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -263,7 +263,7 @@ static bool check_hw_exists(void) msr_fail: pr_cont("Broken PMU hardware detected, using software events only.\n"); - pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -2319,7 +2319,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const void __user *fp; + const unsigned long __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (void __user *)regs->bp; + fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; + frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 16)) + if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); + bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 3660b2c..06c2baa 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o -obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o -intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o +intel-rapl-perf-objs := rapl.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7c66695..9b4f9d3 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = { /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4a41348..c64b1e9 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,10 +301,6 @@ #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 */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +308,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index fdcc040..7c1c895 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -69,29 +69,22 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) } static __always_inline -u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) -{ - u64 delta = rdtsc_ordered() - src->tsc_timestamp; - return pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); -} - -static __always_inline unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, cycle_t *cycles, u8 *flags) { unsigned version; - cycle_t ret, offset; - u8 ret_flags; + cycle_t offset; + u64 delta; version = src->version; + /* Make the latest version visible */ + smp_rmb(); - offset = pvclock_get_nsec_offset(src); - ret = src->system_time + offset; - ret_flags = src->flags; - - *cycles = ret; - *flags = ret_flags; + delta = rdtsc_ordered() - src->tsc_timestamp; + offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + *cycles = src->system_time + offset; + *flags = src->flags; return version; } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index a147e67..e991d5c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 757390e..de7501e 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/dmi.h> #include <linux/pci_ids.h> +#include <linux/bcma/bcma.h> +#include <linux/bcma/bcma_regs.h> #include <drm/i915_drm.h> #include <asm/pci-direct.h> #include <asm/dma.h> @@ -21,6 +25,9 @@ #include <asm/iommu.h> #include <asm/gart.h> #include <asm/irq_remapping.h> +#include <asm/early_ioremap.h> + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -76,6 +83,13 @@ static void __init nvidia_bugs(int num, int slot, int func) #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. * Unfortunately that's not true on many Asus boards. @@ -574,6 +588,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -587,12 +656,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -622,9 +685,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -633,7 +700,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -642,6 +709,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -669,25 +737,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 99bfc02..06c58ce 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -61,11 +61,16 @@ void pvclock_resume(void) u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret; u8 flags; do { - version = __pvclock_read_cycles(src, &ret, &flags); + version = src->version; + /* Make the latest version visible */ + smp_rmb(); + + flags = src->flags; + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bbb5b28..a397200 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(tsc_deadline - guest_tsc); + __delay(min(tsc_deadline - guest_tsc, + nsec_to_cycles(vcpu, lapic_timer_advance_ns))); } static void start_apic_timer(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 003618e..64a79f2 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6671,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6688,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 902d9da..7da5dd2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) -{ - return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, - vcpu->arch.virtual_tsc_shift); -} - static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7ce3634..a82ca46 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_X86_H #include <linux/kvm_host.h> +#include <asm/pvclock.h> #include "kvm_cache_regs.h" #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL @@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns; extern struct static_key kvm_no_apic_vcpu; +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + /* Same "calling convention" as do_div: * - divide (n << 32) by base * - put result in n diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1b1110f..0493c17 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -54,8 +54,8 @@ static int kasan_die_handler(struct notifier_block *self, void *data) { if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access"); + pr_emerg("CONFIG_KASAN_INLINE enabled\n"); + pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); } return NOTIFY_OK; } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a..3cd6983 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 009947d..f2b5e6a 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -19,6 +19,7 @@ #include <asm/mtrr.h> #include <asm/sections.h> #include <asm/suspend.h> +#include <asm/tlbflush.h> /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); @@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void); * kernel's text (this value is passed in the image header). */ unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; /* * Value of the cr3 register from before the hibernation (this value is passed @@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible; pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code __visible; +unsigned long relocated_restore_code __visible; + +static int set_up_temporary_text_mapping(void) +{ + pmd_t *pmd; + pud_t *pud; + + /* + * The new mapping only has to cover the page containing the image + * kernel's entry point (jump_address_phys), because the switch over to + * it is carried out by relocated code running from a page allocated + * specifically for this purpose and covered by the identity mapping, so + * the temporary kernel text mapping is only needed for the final jump. + * Moreover, in that mapping the virtual address of the image kernel's + * entry point must be the same as its virtual address in the image + * kernel (restore_jump_address), so the image kernel's + * restore_registers() code doesn't find itself in a different area of + * the virtual address space after switching over to the original page + * tables used by the image kernel. + */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); + set_pud(pud + pud_index(restore_jump_address), + __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + __pgd(__pa(pud) | _KERNPG_TABLE)); + + return 0; +} static void *alloc_pgt_page(void *context) { @@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void) if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); + /* Prepare a temporary mapping for the kernel text */ + result = set_up_temporary_text_mapping(); + if (result) + return result; /* Set up the direct mapping from scratch */ for (i = 0; i < nr_pfn_mapped; i++) { @@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void) return 0; } +static int relocate_restore_code(void) +{ + pgd_t *pgd; + pud_t *pud; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pud = pud_offset(pgd, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + } else { + pmd_t *pmd = pmd_offset(pud, relocated_restore_code); + + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + } else { + pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); + + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); + } + } + __flush_tlb_all(); + + return 0; +} + int swsusp_arch_resume(void) { int error; /* We have got enough memory and from now on we cannot recover */ - if ((error = set_up_temporary_mappings())) + error = set_up_temporary_mappings(); + if (error) return error; - relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - memcpy(relocated_restore_code, &core_restore_code, - &restore_registers - &core_restore_code); + error = relocate_restore_code(); + if (error) + return error; restore_image(); return 0; @@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn) struct restore_data_record { unsigned long jump_address; + unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; }; -#define RESTORE_MAGIC 0x0123456789ABCDEFUL +#define RESTORE_MAGIC 0x123456789ABCDEF0UL /** * arch_hibernation_header_save - populate the architecture specific part @@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = restore_jump_address; + rdr->jump_address = (unsigned long)&restore_registers; + rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; return 0; @@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr) struct restore_data_record *rdr = addr; restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43..3177c2b 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend) pushfq popq pt_regs_flags(%rax) - /* save the address of restore_registers */ - movq $restore_registers, %rax - movq %rax, restore_jump_address(%rip) /* save cr3 */ movq %cr3, %rax movq %rax, restore_cr3(%rip) @@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend) ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) - /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rdx - movq temp_level4_pgt(%rip), %rax - subq %rdx, %rax - movq %rax, %cr3 - /* Flush TLB */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3; - movq %rax, %cr4; # turn PGE back on - /* prepare to jump to the image kernel */ - movq restore_jump_address(%rip), %rax - movq restore_cr3(%rip), %rbx + movq restore_jump_address(%rip), %r8 + movq restore_cr3(%rip), %r9 + + /* prepare to switch to temporary page tables */ + movq temp_level4_pgt(%rip), %rax + movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + + /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx /* code below has been relocated to a safe page */ ENTRY(core_restore_code) + /* switch to temporary page tables */ + movq $__PAGE_OFFSET, %rcx + subq %rcx, %rax + movq %rax, %cr3 + /* flush TLB */ + movq %rbx, %rcx + andq $~(X86_CR4_PGE), %rcx + movq %rcx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3; + movq %rbx, %cr4; # turn PGE back on .Lloop: testq %rdx, %rdx jz .Ldone @@ -96,24 +96,17 @@ ENTRY(core_restore_code) /* progress to the next pbe */ movq pbe_next(%rdx), %rdx jmp .Lloop + .Ldone: /* jump to the restore_registers address from the image header */ - jmpq *%rax - /* - * NOTE: This assumes that the boot kernel's text mapping covers the - * image kernel's page containing restore_registers and the address of - * this page is the same as in the image kernel's text mapping (it - * should always be true, because the text mapping is linear, starting - * from 0, and is supposed to cover the entire kernel text for every - * kernel). - * - * code below belongs to the image kernel - */ + jmpq *%r8 + /* code below belongs to the image kernel */ + .align PAGE_SIZE ENTRY(restore_registers) FRAME_BEGIN /* go back to the original page tables */ - movq %rbx, %cr3 + movq %r9, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax |