summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Makefile43
-rw-r--r--arch/x86/Makefile_32.cpu18
-rw-r--r--arch/x86/boot/compressed/error.c1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/entry/vdso/vdso32-setup.c11
-rw-r--r--arch/x86/events/amd/core.c2
-rw-r--r--arch/x86/events/core.c25
-rw-r--r--arch/x86/events/intel/cstate.c2
-rw-r--r--arch/x86/events/intel/lbr.c3
-rw-r--r--arch/x86/events/intel/rapl.c2
-rw-r--r--arch/x86/events/intel/uncore.h6
-rw-r--r--arch/x86/hyperv/hv_init.c2
-rw-r--r--arch/x86/include/asm/cpufeatures.h3
-rw-r--r--arch/x86/include/asm/elf.h2
-rw-r--r--arch/x86/include/asm/kvm_page_track.h1
-rw-r--r--arch/x86/include/asm/pgtable-3level.h3
-rw-r--r--arch/x86/include/asm/pgtable.h2
-rw-r--r--arch/x86/include/asm/pgtable_types.h4
-rw-r--r--arch/x86/include/asm/pkeys.h15
-rw-r--r--arch/x86/include/asm/pmem.h42
-rw-r--r--arch/x86/include/asm/purgatory.h20
-rw-r--r--arch/x86/include/asm/timer.h2
-rw-r--r--arch/x86/include/asm/tlbflush.h2
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h8
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h2
-rw-r--r--arch/x86/kernel/acpi/boot.c9
-rw-r--r--arch/x86/kernel/apic/apic.c49
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c3
-rw-r--r--arch/x86/kernel/cpu/amd.c4
-rw-r--r--arch/x86/kernel/cpu/centaur.c2
-rw-r--r--arch/x86/kernel/cpu/common.c3
-rw-r--r--arch/x86/kernel/cpu/cyrix.c1
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c3
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_schemata.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-genpool.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c24
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c2
-rw-r--r--arch/x86/kernel/cpu/transmeta.c2
-rw-r--r--arch/x86/kernel/cpu/vmware.c1
-rw-r--r--arch/x86/kernel/ftrace.c14
-rw-r--r--arch/x86/kernel/head64.c1
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/kdebugfs.c2
-rw-r--r--arch/x86/kernel/kprobes/common.h2
-rw-r--r--arch/x86/kernel/kprobes/core.c6
-rw-r--r--arch/x86/kernel/kprobes/opt.c2
-rw-r--r--arch/x86/kernel/machine_kexec_64.c9
-rw-r--r--arch/x86/kernel/nmi.c17
-rw-r--r--arch/x86/kernel/reboot.c16
-rw-r--r--arch/x86/kernel/signal.c2
-rw-r--r--arch/x86/kernel/signal_compat.c4
-rw-r--r--arch/x86/kernel/traps.c4
-rw-r--r--arch/x86/kernel/tsc.c37
-rw-r--r--arch/x86/kernel/unwind_frame.c36
-rw-r--r--arch/x86/kvm/i8259.c3
-rw-r--r--arch/x86/kvm/ioapic.c3
-rw-r--r--arch/x86/kvm/page_track.c8
-rw-r--r--arch/x86/kvm/svm.c3
-rw-r--r--arch/x86/kvm/vmx.c89
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--arch/x86/lib/delay.c7
-rw-r--r--arch/x86/lib/memcpy_64.S2
-rw-r--r--arch/x86/mm/gup.c37
-rw-r--r--arch/x86/mm/init.c41
-rw-r--r--arch/x86/mm/kasan_init_64.c1
-rw-r--r--arch/x86/mm/kaslr.c4
-rw-r--r--arch/x86/mm/mpx.c2
-rw-r--r--arch/x86/pci/common.c9
-rw-r--r--arch/x86/pci/xen.c23
-rw-r--r--arch/x86/platform/efi/quirks.c4
-rw-r--r--arch/x86/platform/intel-mid/device_libs/Makefile1
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c82
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c2
-rw-r--r--arch/x86/platform/intel-mid/mfld.c15
-rw-r--r--arch/x86/platform/uv/tlb_uv.c1
-rw-r--r--arch/x86/purgatory/Makefile1
-rw-r--r--arch/x86/purgatory/purgatory.c36
-rw-r--r--arch/x86/purgatory/setup-x86_64.S1
-rw-r--r--arch/x86/purgatory/sha256.h1
81 files changed, 567 insertions, 305 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d449337a360..49d160b781f0 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -120,10 +120,6 @@ else
# -funit-at-a-time shrinks the kernel .text considerably
# unfortunately it makes reading oopses harder.
KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
-
- # this works around some issues with generating unwind tables in older gccs
- # newer gccs do it by default
- KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
endif
ifdef CONFIG_X86_X32
@@ -147,6 +143,45 @@ ifeq ($(CONFIG_KMEMCHECK),y)
KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
endif
+#
+# If the function graph tracer is used with mcount instead of fentry,
+# '-maccumulate-outgoing-args' is needed to prevent a GCC bug
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=42109)
+#
+ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ ifndef CONFIG_HAVE_FENTRY
+ ACCUMULATE_OUTGOING_ARGS := 1
+ else
+ ifeq ($(call cc-option-yn, -mfentry), n)
+ ACCUMULATE_OUTGOING_ARGS := 1
+
+ # GCC ignores '-maccumulate-outgoing-args' when used with '-Os'.
+ # If '-Os' is enabled, disable it and print a warning.
+ ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
+ undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
+ $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
+ endif
+
+ endif
+ endif
+endif
+
+#
+# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a
+# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way
+# to test for this bug at compile-time because the test case needs to execute,
+# which is a no-go for cross compilers. So check the GCC version instead.
+#
+ifdef CONFIG_JUMP_LABEL
+ ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+ ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1)
+ endif
+endif
+
+ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
+ KBUILD_CFLAGS += -maccumulate-outgoing-args
+endif
+
# Stackpointer is addressed different for 32 bit and 64 bit x86
sp-$(CONFIG_X86_32) := esp
sp-$(CONFIG_X86_64) := rsp
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 6647ed49c66c..a45eb15b7cf2 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -45,24 +45,6 @@ cflags-$(CONFIG_MGEODE_LX) += $(call cc-option,-march=geode,-march=pentium-mmx)
# cpu entries
cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686))
-# Work around the pentium-mmx code generator madness of gcc4.4.x which
-# does stack alignment by generating horrible code _before_ the mcount
-# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
-# tracer assumptions. For i686, generic, core2 this is set by the
-# compiler anyway
-ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-# Work around to a bug with asm goto with first implementations of it
-# in gcc causing gcc to mess up the push and pop of the stack in some
-# uses of asm goto.
-ifeq ($(CONFIG_JUMP_LABEL), y)
-ADD_ACCUMULATE_OUTGOING_ARGS := y
-endif
-
-cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
-
# Bug fix for binutils: this option is required in order to keep
# binutils from generating NOPL instructions against our will.
ifneq ($(CONFIG_X86_P6_NOP),y)
diff --git a/arch/x86/boot/compressed/error.c b/arch/x86/boot/compressed/error.c
index 6248740b68b5..31922023de49 100644
--- a/arch/x86/boot/compressed/error.c
+++ b/arch/x86/boot/compressed/error.c
@@ -4,6 +4,7 @@
* memcpy() and memmove() are defined for the compressed boot environment.
*/
#include "misc.h"
+#include "error.h"
void warn(char *m)
{
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 7ef4a099defc..6205d3b81e6d 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -176,6 +176,7 @@ CONFIG_E1000E=y
CONFIG_SKY2=y
CONFIG_FORCEDETH=y
CONFIG_8139TOO=y
+CONFIG_R8169=y
CONFIG_FDDI=y
CONFIG_INPUT_POLLDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index 7853b53959cd..3f9d1a83891a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -30,8 +30,10 @@ static int __init vdso32_setup(char *s)
{
vdso32_enabled = simple_strtoul(s, NULL, 0);
- if (vdso32_enabled > 1)
+ if (vdso32_enabled > 1) {
pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+ vdso32_enabled = 0;
+ }
return 1;
}
@@ -62,13 +64,18 @@ subsys_initcall(sysenter_setup);
/* Register vsyscall32 into the ABI table */
#include <linux/sysctl.h>
+static const int zero;
+static const int one = 1;
+
static struct ctl_table abi_table2[] = {
{
.procname = "vsyscall32",
.data = &vdso32_enabled,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (int *)&zero,
+ .extra2 = (int *)&one,
},
{}
};
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index afb222b63cae..c84584bb9402 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
return &amd_f15_PMC20;
}
case AMD_EVENT_NB:
- /* moved to perf_event_amd_uncore.c */
+ /* moved to uncore.c */
return &emptyconstraint;
default:
return &emptyconstraint;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 349d4d17aa7f..580b60f5ac83 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2101,8 +2101,8 @@ static int x86_pmu_event_init(struct perf_event *event)
static void refresh_pce(void *ignored)
{
- if (current->mm)
- load_mm_cr4(current->mm);
+ if (current->active_mm)
+ load_mm_cr4(current->active_mm);
}
static void x86_pmu_event_mapped(struct perf_event *event)
@@ -2110,6 +2110,18 @@ static void x86_pmu_event_mapped(struct perf_event *event)
if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED))
return;
+ /*
+ * This function relies on not being called concurrently in two
+ * tasks in the same mm. Otherwise one task could observe
+ * perf_rdpmc_allowed > 1 and return all the way back to
+ * userspace with CR4.PCE clear while another task is still
+ * doing on_each_cpu_mask() to propagate CR4.PCE.
+ *
+ * For now, this can't happen because all callers hold mmap_sem
+ * for write. If this changes, we'll need a different solution.
+ */
+ lockdep_assert_held_exclusive(&current->mm->mmap_sem);
+
if (atomic_inc_return(&current->mm->context.perf_rdpmc_allowed) == 1)
on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1);
}
@@ -2244,6 +2256,7 @@ void arch_perf_update_userpage(struct perf_event *event,
struct perf_event_mmap_page *userpg, u64 now)
{
struct cyc2ns_data *data;
+ u64 offset;
userpg->cap_user_time = 0;
userpg->cap_user_time_zero = 0;
@@ -2251,11 +2264,13 @@ void arch_perf_update_userpage(struct perf_event *event,
!!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED);
userpg->pmc_width = x86_pmu.cntval_bits;
- if (!sched_clock_stable())
+ if (!using_native_sched_clock() || !sched_clock_stable())
return;
data = cyc2ns_read_begin();
+ offset = data->cyc2ns_offset + __sched_clock_offset;
+
/*
* Internal timekeeping for enabled/running/stopped times
* is always in the local_clock domain.
@@ -2263,7 +2278,7 @@ void arch_perf_update_userpage(struct perf_event *event,
userpg->cap_user_time = 1;
userpg->time_mult = data->cyc2ns_mul;
userpg->time_shift = data->cyc2ns_shift;
- userpg->time_offset = data->cyc2ns_offset - now;
+ userpg->time_offset = offset - now;
/*
* cap_user_time_zero doesn't make sense when we're using a different
@@ -2271,7 +2286,7 @@ void arch_perf_update_userpage(struct perf_event *event,
*/
if (!event->attr.use_clockid) {
userpg->cap_user_time_zero = 1;
- userpg->time_zero = data->cyc2ns_offset;
+ userpg->time_zero = offset;
}
cyc2ns_read_end(data);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index aff4b5b69d40..238ae3248ba5 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -1,5 +1,5 @@
/*
- * perf_event_intel_cstate.c: support cstate residency counters
+ * Support cstate residency counters
*
* Copyright (C) 2015, Intel Corp.
* Author: Kan Liang (kan.liang@intel.com)
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 81b321ace8e0..f924629836a8 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -507,6 +507,9 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
cpuc->lbr_entries[i].to = msr_lastbranch.to;
cpuc->lbr_entries[i].mispred = 0;
cpuc->lbr_entries[i].predicted = 0;
+ cpuc->lbr_entries[i].in_tx = 0;
+ cpuc->lbr_entries[i].abort = 0;
+ cpuc->lbr_entries[i].cycles = 0;
cpuc->lbr_entries[i].reserved = 0;
}
cpuc->lbr_stack.nr = i;
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 22054ca49026..9d05c7e67f60 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -1,5 +1,5 @@
/*
- * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Support Intel RAPL energy consumption counters
* Copyright (C) 2013 Google, Inc., Stephane Eranian
*
* Intel RAPL interface is specified in the IA-32 Manual Vol3b
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index ad986c1e29bc..df5989f27b1b 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head;
extern struct pci_extra_dev *uncore_extra_pci_dev;
extern struct event_constraint uncore_constraint_empty;
-/* perf_event_intel_uncore_snb.c */
+/* uncore_snb.c */
int snb_uncore_pci_init(void);
int ivb_uncore_pci_init(void);
int hsw_uncore_pci_init(void);
@@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void);
void skl_uncore_cpu_init(void);
int snb_pci2phy_map_init(int devid);
-/* perf_event_intel_uncore_snbep.c */
+/* uncore_snbep.c */
int snbep_uncore_pci_init(void);
void snbep_uncore_cpu_init(void);
int ivbep_uncore_pci_init(void);
@@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void);
int skx_uncore_pci_init(void);
void skx_uncore_cpu_init(void);
-/* perf_event_intel_uncore_nhmex.c */
+/* uncore_nhmex.c */
void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index db64baf0e500..8bef70e7f3cc 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -158,13 +158,13 @@ void hyperv_init(void)
clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
return;
}
+register_msr_cs:
#endif
/*
* For 32 bit guests just use the MSR based mechanism for reading
* the partition counter.
*/
-register_msr_cs:
hyperv_cs = &hyperv_cs_msr;
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4e7772387c6e..b04bb6dfed7f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -289,7 +289,8 @@
#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */
#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_RDPID (16*32+ 22) /* RDPID instruction */
+#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 9d49c18b5ea9..3762536619f8 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -287,7 +287,7 @@ struct task_struct;
#define ARCH_DLINFO_IA32 \
do { \
- if (vdso32_enabled) { \
+ if (VDSO_CURRENT_BASE) { \
NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \
} \
diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b031ec..c4eda791f877 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
};
void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont);
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 72277b1028a5..50d35e3185f5 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -121,12 +121,9 @@ static inline void native_pmd_clear(pmd_t *pmd)
*(tmp + 1) = 0;
}
-#if !defined(CONFIG_SMP) || (defined(CONFIG_HIGHMEM64G) && \
- defined(CONFIG_PARAVIRT))
static inline void native_pud_clear(pud_t *pudp)
{
}
-#endif
static inline void pud_clear(pud_t *pudp)
{
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1cfb36b8c024..585ee0d42d18 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -62,7 +62,7 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page);
# define set_pud(pudp, pud) native_set_pud(pudp, pud)
#endif
-#ifndef __PAGETABLE_PMD_FOLDED
+#ifndef __PAGETABLE_PUD_FOLDED
#define pud_clear(pud) native_pud_clear(pud)
#endif
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 8b4de22d6429..62484333673d 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -273,6 +273,8 @@ static inline pgdval_t pgd_flags(pgd_t pgd)
}
#if CONFIG_PGTABLE_LEVELS > 3
+#include <asm-generic/5level-fixup.h>
+
typedef struct { pudval_t pud; } pud_t;
static inline pud_t native_make_pud(pmdval_t val)
@@ -285,6 +287,7 @@ static inline pudval_t native_pud_val(pud_t pud)
return pud.pud;
}
#else
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
static inline pudval_t native_pud_val(pud_t pud)
@@ -306,6 +309,7 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
return pmd.pmd;
}
#else
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
static inline pmdval_t native_pmd_val(pmd_t pmd)
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 34684adb6899..b3b09b98896d 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
static inline
bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
{
+ /*
+ * "Allocated" pkeys are those that have been returned
+ * from pkey_alloc(). pkey 0 is special, and never
+ * returned from pkey_alloc().
+ */
+ if (pkey <= 0)
+ return false;
+ if (pkey >= arch_max_pkey())
+ return false;
return mm_pkey_allocation_map(mm) & (1U << pkey);
}
@@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm)
static inline
int mm_pkey_free(struct mm_struct *mm, int pkey)
{
- /*
- * pkey 0 is special, always allocated and can never
- * be freed.
- */
- if (!pkey)
- return -EINVAL;
if (!mm_pkey_is_allocated(mm, pkey))
return -EINVAL;
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 2c1ebeb4d737..529bb4a6487a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
* @size: number of bytes to write back
*
* Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
*/
static inline void arch_wb_cache_pmem(void *addr, size_t size)
{
@@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
clwb(p);
}
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
- return iter_is_iovec(i) == false;
-}
-
/**
* arch_copy_from_iter_pmem - copy data from an iterator to PMEM
* @addr: PMEM destination address
@@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
/* TODO: skip the write-back by always using non-temporal stores */
len = copy_from_iter_nocache(addr, bytes, i);
- if (__iter_needs_pmem_wb(i))
+ /*
+ * In the iovec case on x86_64 copy_from_iter_nocache() uses
+ * non-temporal stores for the bulk of the transfer, but we need
+ * to manually flush if the transfer is unaligned. A cached
+ * memory copy is used when destination or size is not naturally
+ * aligned. That is:
+ * - Require 8-byte alignment when size is 8 bytes or larger.
+ * - Require 4-byte alignment when size is 4 bytes.
+ *
+ * In the non-iovec case the entire destination needs to be
+ * flushed.
+ */
+ if (iter_is_iovec(i)) {
+ unsigned long flushed, dest = (unsigned long) addr;
+
+ if (bytes < 8) {
+ if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+ arch_wb_cache_pmem(addr, 1);
+ } else {
+ if (!IS_ALIGNED(dest, 8)) {
+ dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+ arch_wb_cache_pmem(addr, 1);
+ }
+
+ flushed = dest - (unsigned long) addr;
+ if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+ arch_wb_cache_pmem(addr + bytes - 1, 1);
+ }
+ } else
arch_wb_cache_pmem(addr, bytes);
return len;
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
new file mode 100644
index 000000000000..d7da2729903d
--- /dev/null
+++ b/arch/x86/include/asm/purgatory.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_PURGATORY_H
+#define _ASM_X86_PURGATORY_H
+
+#ifndef __ASSEMBLY__
+#include <linux/purgatory.h>
+
+extern void purgatory(void);
+/*
+ * These forward declarations serve two purposes:
+ *
+ * 1) Make sparse happy when checking arch/purgatory
+ * 2) Document that these are required to be global so the symbol
+ * lookup in kexec works
+ */
+extern unsigned long purgatory_backup_dest;
+extern unsigned long purgatory_backup_src;
+extern unsigned long purgatory_backup_sz;
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index a04eabd43d06..27e9f9d769b8 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,8 @@ extern int recalibrate_cpu_khz(void);
extern int no_timer_check;
+extern bool using_native_sched_clock(void);
+
/*
* We use the full linear equation: f(x) = a + b*x, in order to allow
* a continuous function in the face of dynamic freq changes.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa85944af83..fc5abff9b7fd 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -188,7 +188,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
static inline void __flush_tlb_all(void)
{
- if (static_cpu_has(X86_FEATURE_PGE))
+ if (boot_cpu_has(X86_FEATURE_PGE))
__flush_tlb_global();
else
__flush_tlb();
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 72e8300b1e8a..9cffb44a3cf5 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -485,15 +485,17 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
if (paddr < uv_hub_info->lowmem_remap_top)
paddr |= uv_hub_info->lowmem_remap_base;
- paddr |= uv_hub_info->gnode_upper;
- if (m_val)
+
+ if (m_val) {
+ paddr |= uv_hub_info->gnode_upper;
paddr = ((paddr << uv_hub_info->m_shift)
>> uv_hub_info->m_shift) |
((paddr >> uv_hub_info->m_val)
<< uv_hub_info->n_lshift);
- else
+ } else {
paddr |= uv_soc_phys_ram_to_nasid(paddr)
<< uv_hub_info->gpa_shift;
+ }
return paddr;
}
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 5138dacf8bb8..07244ea16765 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -58,7 +58,7 @@ struct setup_header {
__u32 header;
__u16 version;
__u32 realmode_swtch;
- __u16 start_sys;
+ __u16 start_sys_seg;
__u16 kernel_version;
__u8 type_of_loader;
__u8 loadflags;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ae32838cac5f..b2879cc23db4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -179,10 +179,15 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
return -EINVAL;
}
+ if (!enabled) {
+ ++disabled_cpus;
+ return -EINVAL;
+ }
+
if (boot_cpu_physical_apicid != -1U)
ver = boot_cpu_apic_version;
- cpu = __generic_processor_info(id, ver, enabled);
+ cpu = generic_processor_info(id, ver);
if (cpu >= 0)
early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid;
@@ -710,7 +715,7 @@ static void __init acpi_set_irq_model_ioapic(void)
#ifdef CONFIG_ACPI_HOTPLUG_CPU
#include <acpi/processor.h>
-int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
{
#ifdef CONFIG_ACPI_NUMA
int nid;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4261b3282ad9..8ccb7ef512e0 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1610,24 +1610,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { }
static inline void __x2apic_enable(void) { }
#endif /* !CONFIG_X86_X2APIC */
-static int __init try_to_enable_IR(void)
-{
-#ifdef CONFIG_X86_IO_APIC
- if (!x2apic_enabled() && skip_ioapic_setup) {
- pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
- return -1;
- }
-#endif
- return irq_remapping_enable();
-}
-
void __init enable_IR_x2apic(void)
{
unsigned long flags;
int ret, ir_stat;
- if (skip_ioapic_setup)
+ if (skip_ioapic_setup) {
+ pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
return;
+ }
ir_stat = irq_remapping_prepare();
if (ir_stat < 0 && !x2apic_supported())
@@ -1645,7 +1636,7 @@ void __init enable_IR_x2apic(void)
/* If irq_remapping_prepare() succeeded, try to enable it */
if (ir_stat >= 0)
- ir_stat = try_to_enable_IR();
+ ir_stat = irq_remapping_enable();
/* ir_stat contains the remap mode or an error code */
try_to_enable_x2apic(ir_stat);
@@ -2062,17 +2053,17 @@ static int allocate_logical_cpuid(int apicid)
/* Allocate a new cpuid. */
if (nr_logical_cpuids >= nr_cpu_ids) {
- WARN_ONCE(1, "Only %d processors supported."
+ WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. "
"Processor %d/0x%x and the rest are ignored.\n",
- nr_cpu_ids - 1, nr_logical_cpuids, apicid);
- return -1;
+ nr_cpu_ids, nr_logical_cpuids, apicid);
+ return -EINVAL;
}
cpuid_to_apicid[nr_logical_cpuids] = apicid;
return nr_logical_cpuids++;
}
-int __generic_processor_info(int apicid, int version, bool enabled)
+int generic_processor_info(int apicid, int version)
{
int cpu, max = nr_cpu_ids;
bool boot_cpu_detected = physid_isset(boot_cpu_physical_apicid,
@@ -2130,11 +2121,9 @@ int __generic_processor_info(int apicid, int version, bool enabled)
if (num_processors >= nr_cpu_ids) {
int thiscpu = max + disabled_cpus;
- if (enabled) {
- pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
- "reached. Processor %d/0x%x ignored.\n",
- max, thiscpu, apicid);
- }
+ pr_warning("APIC: NR_CPUS/possible_cpus limit of %i "
+ "reached. Processor %d/0x%x ignored.\n",
+ max, thiscpu, apicid);
disabled_cpus++;
return -EINVAL;
@@ -2186,23 +2175,13 @@ int __generic_processor_info(int apicid, int version, bool enabled)
apic->x86_32_early_logical_apicid(cpu);
#endif
set_cpu_possible(cpu, true);
-
- if (enabled) {
- num_processors++;
- physid_set(apicid, phys_cpu_present_map);
- set_cpu_present(cpu, true);
- } else {
- disabled_cpus++;
- }
+ physid_set(apicid, phys_cpu_present_map);
+ set_cpu_present(cpu, true);
+ num_processors++;
return cpu;
}
-int generic_processor_info(int apicid, int version)
-{
- return __generic_processor_info(apicid, version, true);
-}
-
int hard_smp_processor_id(void)
{
return read_apic_id();
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index e9f8f8cdd570..86f20cc0a65e 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1105,7 +1105,8 @@ void __init uv_init_hub_info(struct uv_hub_info_s *hi)
node_id.v = uv_read_local_mmr(UVH_NODE_ID);
uv_cpuid.gnode_shift = max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val);
hi->gnode_extra = (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1;
- hi->gnode_upper = (unsigned long)hi->gnode_extra << mn.m_val;
+ if (mn.m_val)
+ hi->gnode_upper = (u64)hi->gnode_extra << mn.m_val;
if (uv_gp_table) {
hi->global_mmr_base = uv_gp_table->mmr_base;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 35a5d5dca2fa..c36140d788fe 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (check_tsc_unstable())
- clear_sched_clock_stable();
- } else {
- clear_sched_clock_stable();
}
/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index adc0ebd8bed0..43955ee6715b 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
#ifdef CONFIG_X86_64
set_cpu_cap(c, X86_FEATURE_SYSENTER32);
#endif
-
- clear_sched_clock_stable();
}
static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b11b38c3b0bd..58094a1f9e9d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c)
strcpy(c->x86_model_id, "386");
}
#endif
- clear_sched_clock_stable();
}
static const struct cpu_dev default_cpu = {
@@ -1077,8 +1076,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
*/
if (this_cpu->c_init)
this_cpu->c_init(c);
- else
- clear_sched_clock_stable();
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 0a3bc19de017..a70fd61095f8 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
break;
}
- clear_sched_clock_stable();
}
static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fe0a615a051b..063197771b8d 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -162,10 +162,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
if (c->x86_power & (1 << 8)) {
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
- if (check_tsc_unstable())
- clear_sched_clock_stable();
- } else {
- clear_sched_clock_stable();
}
/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 0bbe0f3a039f..9ac2a5cdd9c2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -28,7 +28,6 @@
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/slab.h>
-#include <linux/cpu.h>
#include <linux/task_work.h>
#include <uapi/linux/magic.h>
@@ -728,7 +727,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
if (atomic_dec_and_test(&rdtgrp->waitcount) &&
(rdtgrp->flags & RDT_DELETED)) {
kernfs_unbreak_active_protection(kn);
- kernfs_put(kn);
+ kernfs_put(rdtgrp->kn);
kfree(rdtgrp);
} else {
kernfs_unbreak_active_protection(kn);
diff --git a/arch/x86/kernel/cpu/intel_rdt_schemata.c b/arch/x86/kernel/cpu/intel_rdt_schemata.c
index f369cb8db0d5..badd2b31a560 100644
--- a/arch/x86/kernel/cpu/intel_rdt_schemata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_schemata.c
@@ -200,11 +200,11 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
}
out:
- rdtgroup_kn_unlock(of->kn);
for_each_enabled_rdt_resource(r) {
kfree(r->tmp_cbms);
r->tmp_cbms = NULL;
}
+ rdtgroup_kn_unlock(of->kn);
return ret ?: nbytes;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 1e5a50c11d3c..217cd4449bc9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -85,7 +85,7 @@ void mce_gen_pool_process(struct work_struct *__unused)
head = llist_reverse_order(head);
llist_for_each_entry_safe(node, tmp, head, llnode) {
mce = &node->mce;
- atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
+ blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
}
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 903043e6a62b..19592ba1a320 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -13,7 +13,7 @@ enum severity_level {
MCE_PANIC_SEVERITY,
};
-extern struct atomic_notifier_head x86_mce_decoder_chain;
+extern struct blocking_notifier_head x86_mce_decoder_chain;
#define ATTR_LEN 16
#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8e9725c607ea..af44ebeb593f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -54,6 +54,8 @@
static DEFINE_MUTEX(mce_chrdev_read_mutex);
+static int mce_chrdev_open_count; /* #times opened */
+
#define mce_log_get_idx_check(p) \
({ \
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
@@ -121,7 +123,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
* CPU/chipset specific EDAC code can register a notifier call here to print
* MCE errors in a human-readable form.
*/
-ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain);
/* Do initial initialization of a struct mce */
void mce_setup(struct mce *m)
@@ -218,7 +220,7 @@ void mce_register_decode_chain(struct notifier_block *nb)
WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
- atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
+ blocking_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_register_decode_chain);
@@ -226,7 +228,7 @@ void mce_unregister_decode_chain(struct notifier_block *nb)
{
atomic_dec(&num_notifiers);
- atomic_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
+ blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb);
}
EXPORT_SYMBOL_GPL(mce_unregister_decode_chain);
@@ -319,18 +321,7 @@ static void __print_mce(struct mce *m)
static void print_mce(struct mce *m)
{
- int ret = 0;
-
__print_mce(m);
-
- /*
- * Print out human-readable details about the MCE error,
- * (if the CPU has an implementation for that)
- */
- ret = atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
- if (ret == NOTIFY_STOP)
- return;
-
pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n");
}
@@ -598,6 +589,10 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
if (atomic_read(&num_notifiers) > 2)
return NOTIFY_DONE;
+ /* Don't print when mcelog is running */
+ if (mce_chrdev_open_count > 0)
+ return NOTIFY_DONE;
+
__print_mce(m);
return NOTIFY_DONE;
@@ -1828,7 +1823,6 @@ void mcheck_cpu_clear(struct cpuinfo_x86 *c)
*/
static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_count; /* #times opened */
static int mce_chrdev_open_exclu; /* already open exclusive? */
static int mce_chrdev_open(struct inode *inode, struct file *file)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 524cc5780a77..6e4a047e4b68 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -60,7 +60,7 @@ static const char * const th_names[] = {
"load_store",
"insn_fetch",
"combined_unit",
- "",
+ "decode_unit",
"northbridge",
"execution_unit",
};
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 8457b4978668..d77d07ab310b 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
if (xlvl >= 0x80860001)
c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
}
-
- clear_sched_clock_stable();
}
static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 891f4dad7b2c..22403a28caf5 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,7 +30,6 @@
#include <asm/hypervisor.h>
#include <asm/timer.h>
#include <asm/apic.h>
-#include <asm/timer.h>
#undef pr_fmt
#define pr_fmt(fmt) "vmware: " fmt
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8639bb2ae058..5b7153540727 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -535,7 +535,7 @@ static void run_sync(void)
{
int enable_irqs = irqs_disabled();
- /* We may be called with interrupts disbled (on bootup). */
+ /* We may be called with interrupts disabled (on bootup). */
if (enable_irqs)
local_irq_enable();
on_each_cpu(do_sync_core, NULL, 1);
@@ -983,6 +983,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
unsigned long return_hooker = (unsigned long)
&return_to_handler;
+ /*
+ * When resuming from suspend-to-ram, this function can be indirectly
+ * called from early CPU startup code while the CPU is in real mode,
+ * which would fail miserably. Make sure the stack pointer is a
+ * virtual address.
+ *
+ * This check isn't as accurate as virt_addr_valid(), but it should be
+ * good enough for this purpose, and it's fast.
+ */
+ if (unlikely((long)__builtin_frame_address(0) >= 0))
+ return;
+
if (unlikely(ftrace_graph_is_dead()))
return;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 54a2372f5dbb..b5785c197e53 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -4,6 +4,7 @@
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*/
+#define DISABLE_BRANCH_PROFILING
#include <linux/init.h>
#include <linux/linkage.h>
#include <linux/types.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dc6ba5bda9fc..89ff7af2de50 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
- disable_irq(hdev->irq);
+ disable_hardirq(hdev->irq);
irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
enable_irq(hdev->irq);
}
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index bdb83e431d89..38b64587b31b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void)
struct dentry *dbp, *version, *data;
int error = -ENOMEM;
- dbp = debugfs_create_dir("boot_params", NULL);
+ dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
if (!dbp)
return -ENOMEM;
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f927ab..d688826e5736 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
#endif
/* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
/* Recover instruction if given address is probed */
extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6384eb754a58..993fa4fe4f68 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -167,12 +167,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
* Returns non-zero if opcode is boostable.
* RIP relative instructions are adjusted at copying time in 64 bits mode
*/
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
{
kprobe_opcode_t opcode;
kprobe_opcode_t *orig_opcodes = opcodes;
- if (search_exception_tables((unsigned long)opcodes))
+ if (search_exception_tables((unsigned long)addr))
return 0; /* Page fault may occur on this address. */
retry:
@@ -417,7 +417,7 @@ static int arch_copy_kprobe(struct kprobe *p)
* __copy_instruction can modify the displacement of the instruction,
* but it doesn't affect boostable check.
*/
- if (can_boost(p->ainsn.insn))
+ if (can_boost(p->ainsn.insn, p->addr))
p->ainsn.boostable = 0;
else
p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3d1bee9d6a72..3e7c6e5a08ff 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
while (len < RELATIVEJUMP_SIZE) {
ret = __copy_instruction(dest + len, src + len);
- if (!ret || !can_boost(dest + len))
+ if (!ret || !can_boost(dest + len, src + len))
return -EINVAL;
len += ret;
}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 307b1f4543de..857cdbd02867 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -194,19 +194,22 @@ static int arch_update_purgatory(struct kimage *image)
/* Setup copying of backup region */
if (image->type == KEXEC_TYPE_CRASH) {
- ret = kexec_purgatory_get_set_symbol(image, "backup_dest",
+ ret = kexec_purgatory_get_set_symbol(image,
+ "purgatory_backup_dest",
&image->arch.backup_load_addr,
sizeof(image->arch.backup_load_addr), 0);
if (ret)
return ret;
- ret = kexec_purgatory_get_set_symbol(image, "backup_src",
+ ret = kexec_purgatory_get_set_symbol(image,
+ "purgatory_backup_src",
&image->arch.backup_src_start,
sizeof(image->arch.backup_src_start), 0);
if (ret)
return ret;
- ret = kexec_purgatory_get_set_symbol(image, "backup_sz",
+ ret = kexec_purgatory_get_set_symbol(image,
+ "purgatory_backup_sz",
&image->arch.backup_src_sz,
sizeof(image->arch.backup_src_sz), 0);
if (ret)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index f088ea4c66e7..446c8aa09b9b 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -166,11 +166,9 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
spin_lock_irqsave(&desc->lock, flags);
/*
- * most handlers of type NMI_UNKNOWN never return because
- * they just assume the NMI is theirs. Just a sanity check
- * to manage expectations
+ * Indicate if there are multiple registrations on the
+ * internal NMI handler call chains (SERR and IO_CHECK).
*/
- WARN_ON_ONCE(type == NMI_UNKNOWN && !list_empty(&desc->head));
WARN_ON_ONCE(type == NMI_SERR && !list_empty(&desc->head));
WARN_ON_ONCE(type == NMI_IO_CHECK && !list_empty(&desc->head));
@@ -224,17 +222,6 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
reason, smp_processor_id());
- /*
- * On some machines, PCI SERR line is used to report memory
- * errors. EDAC makes use of it.
- */
-#if defined(CONFIG_EDAC)
- if (edac_handler_set()) {
- edac_atomic_assert_error();
- return;
- }
-#endif
-
if (panic_on_unrecovered_nmi)
nmi_panic(regs, "NMI: Not continuing");
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e244c19a2451..067f9813fd2c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
+ { /* Handle problems with rebooting on ASUS EeeBook X205TA */
+ .callback = set_acpi_reboot,
+ .ident = "ASUS EeeBook X205TA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X205TA"),
+ },
+ },
+ { /* Handle problems with rebooting on ASUS EeeBook X205TAW */
+ .callback = set_acpi_reboot,
+ .ident = "ASUS EeeBook X205TAW",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+ },
+ },
/* Certec */
{ /* Handle problems with rebooting on Certec BPC600 */
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 396c042e9d0e..cc30a74e4adb 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -846,7 +846,7 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
me->comm, me->pid, where, frame,
regs->ip, regs->sp, regs->orig_ax);
- print_vma_addr(" in ", regs->ip);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ec1f756f9dc9..71beb28600d4 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -151,8 +151,8 @@ int __copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from,
if (from->si_signo == SIGSEGV) {
if (from->si_code == SEGV_BNDERR) {
- compat_uptr_t lower = (unsigned long)&to->si_lower;
- compat_uptr_t upper = (unsigned long)&to->si_upper;
+ compat_uptr_t lower = (unsigned long)from->si_lower;
+ compat_uptr_t upper = (unsigned long)from->si_upper;
put_user_ex(lower, &to->si_lower);
put_user_ex(upper, &to->si_upper);
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 948443e115c1..4e496379a871 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -255,7 +255,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
pr_info("%s[%d] trap %s ip:%lx sp:%lx error:%lx",
tsk->comm, tsk->pid, str,
regs->ip, regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
@@ -519,7 +519,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
pr_info("%s[%d] general protection ip:%lx sp:%lx error:%lx",
tsk->comm, task_pid_nr(tsk),
regs->ip, regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
+ print_vma_addr(KERN_CONT " in ", regs->ip);
pr_cont("\n");
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 46bcda4cb1c2..714dfba6a1e7 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -327,9 +327,16 @@ unsigned long long sched_clock(void)
{
return paravirt_sched_clock();
}
+
+bool using_native_sched_clock(void)
+{
+ return pv_time_ops.sched_clock == native_sched_clock;
+}
#else
unsigned long long
sched_clock(void) __attribute__((alias("native_sched_clock")));
+
+bool using_native_sched_clock(void) { return true; }
#endif
int check_tsc_unstable(void)
@@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
{
if (tsc_unstable)
return;
+
tsc_unstable = 1;
- clear_sched_clock_stable();
+ if (using_native_sched_clock())
+ clear_sched_clock_stable();
disable_sched_clock_irqtime();
pr_info("Marking TSC unstable due to clocksource watchdog\n");
}
@@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = {
void mark_tsc_unstable(char *reason)
{
- if (!tsc_unstable) {
- tsc_unstable = 1;
+ if (tsc_unstable)
+ return;
+
+ tsc_unstable = 1;
+ if (using_native_sched_clock())
clear_sched_clock_stable();
- disable_sched_clock_irqtime();
- pr_info("Marking TSC unstable due to %s\n", reason);
- /* Change only the rating, when not registered */
- if (clocksource_tsc.mult)
- clocksource_mark_unstable(&clocksource_tsc);
- else {
- clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
- clocksource_tsc.rating = 0;
- }
+ disable_sched_clock_irqtime();
+ pr_info("Marking TSC unstable due to %s\n", reason);
+ /* Change only the rating, when not registered */
+ if (clocksource_tsc.mult) {
+ clocksource_mark_unstable(&clocksource_tsc);
+ } else {
+ clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
+ clocksource_tsc.rating = 0;
}
}
@@ -1322,6 +1333,8 @@ static int __init init_tsc_clocksource(void)
* the refined calibration and directly register it as a clocksource.
*/
if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) {
+ if (boot_cpu_has(X86_FEATURE_ART))
+ art_related_clocksource = &clocksource_tsc;
clocksource_register_khz(&clocksource_tsc, tsc_khz);
return 0;
}
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 478d15dbaee4..08339262b666 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -82,19 +82,43 @@ static size_t regs_size(struct pt_regs *regs)
return sizeof(*regs);
}
+#ifdef CONFIG_X86_32
+#define GCC_REALIGN_WORDS 3
+#else
+#define GCC_REALIGN_WORDS 1
+#endif
+
static bool is_last_task_frame(struct unwind_state *state)
{
- unsigned long bp = (unsigned long)state->bp;
- unsigned long regs = (unsigned long)task_pt_regs(state->task);
+ unsigned long *last_bp = (unsigned long *)task_pt_regs(state->task) - 2;
+ unsigned long *aligned_bp = last_bp - GCC_REALIGN_WORDS;
/*
* We have to check for the last task frame at two different locations
* because gcc can occasionally decide to realign the stack pointer and
- * change the offset of the stack frame by a word in the prologue of a
- * function called by head/entry code.
+ * change the offset of the stack frame in the prologue of a function
+ * called by head/entry code. Examples:
+ *
+ * <start_secondary>:
+ * push %edi
+ * lea 0x8(%esp),%edi
+ * and $0xfffffff8,%esp
+ * pushl -0x4(%edi)
+ * push %ebp
+ * mov %esp,%ebp
+ *
+ * <x86_64_start_kernel>:
+ * lea 0x8(%rsp),%r10
+ * and $0xfffffffffffffff0,%rsp
+ * pushq -0x8(%r10)
+ * push %rbp
+ * mov %rsp,%rbp
+ *
+ * Note that after aligning the stack, it pushes a duplicate copy of
+ * the return address before pushing the frame pointer.
*/
- return bp == regs - FRAME_HEADER_SIZE ||
- bp == regs - FRAME_HEADER_SIZE - sizeof(long);
+ return (state->bp == last_bp ||
+ (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
}
/*
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 73ea24d4f119..047b17a26269 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm)
{
struct kvm_pic *vpic = kvm->arch.vpic;
+ if (!vpic)
+ return;
+
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 6e219e5c07d2..289270a6aecb 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ if (!ioapic)
+ return;
+
cancel_delayed_work_sync(&ioapic->eoi_inject);
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
kvm->arch.vioapic = NULL;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 37942e419c32..60168cdd0546 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
}
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+ struct kvm_page_track_notifier_head *head;
+
+ head = &kvm->arch.track_notifier_head;
+ cleanup_srcu_struct(&head->track_srcu);
+}
+
void kvm_page_track_init(struct kvm *kvm)
{
struct kvm_page_track_notifier_head *head;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d1efe2c62b3f..5fba70646c32 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1379,6 +1379,9 @@ static void avic_vm_destroy(struct kvm *kvm)
unsigned long flags;
struct kvm_arch *vm_data = &kvm->arch;
+ if (!avic)
+ return;
+
avic_free_vm_id(vm_data->avic_vm_id);
if (vm_data->avic_logical_id_table_page)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 283aa8601833..259e9b28ccf8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1239,6 +1239,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
}
+static inline bool cpu_has_vmx_invvpid(void)
+{
+ return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -2753,7 +2758,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
- SECONDARY_EXEC_ENABLE_VPID |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING |
@@ -2781,10 +2785,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
* though it is treated as global context. The alternative is
* not failing the single-context invvpid, and it is worse.
*/
- if (enable_vpid)
+ if (enable_vpid) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_VPID;
vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
VMX_VPID_EXTENT_SUPPORTED_MASK;
- else
+ } else
vmx->nested.nested_vmx_vpid_caps = 0;
if (enable_unrestricted_guest)
@@ -4024,6 +4030,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
}
+static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
+{
+ if (enable_ept)
+ vmx_flush_tlb(vcpu);
+}
+
static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -6517,8 +6529,10 @@ static __init int hardware_setup(void)
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
- if (!cpu_has_vmx_vpid())
+ if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+ !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
enable_vpid = 0;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs)
@@ -7258,9 +7272,8 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
static int handle_vmclear(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u32 zero = 0;
gpa_t vmptr;
- struct vmcs12 *vmcs12;
- struct page *page;
if (!nested_vmx_check_permission(vcpu))
return 1;
@@ -7271,22 +7284,9 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vmx);
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
- /*
- * For accurate processor emulation, VMCLEAR beyond available
- * physical memory should do nothing at all. However, it is
- * possible that a nested vmx bug, not a guest hypervisor bug,
- * resulted in this case, so let's shut down before doing any
- * more damage:
- */
- kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
- return 1;
- }
- vmcs12 = kmap(page);
- vmcs12->launch_state = 0;
- kunmap(page);
- nested_release_page(page);
+ kvm_vcpu_write_guest(vcpu,
+ vmptr + offsetof(struct vmcs12, launch_state),
+ &zero, sizeof(zero));
nested_free_vmcs02(vmx, vmptr);
@@ -8198,6 +8198,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
case EXIT_REASON_PREEMPTION_TIMER:
return false;
+ case EXIT_REASON_PML_FULL:
+ /* We don't expose PML support to L1. */
+ return false;
default:
return true;
}
@@ -8515,7 +8518,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+ vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+ exit_reason);
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
}
@@ -8561,6 +8565,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
} else {
sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ vmx_flush_tlb_ept_only(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
@@ -8586,8 +8591,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
*/
if (!is_guest_mode(vcpu) ||
!nested_cpu_has2(get_vmcs12(&vmx->vcpu),
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
vmcs_write64(APIC_ACCESS_ADDR, hpa);
+ vmx_flush_tlb_ept_only(vcpu);
+ }
}
static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
@@ -9694,10 +9701,8 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu,
return false;
page = nested_get_page(vcpu, vmcs12->msr_bitmap);
- if (!page) {
- WARN_ON(1);
+ if (!page)
return false;
- }
msr_bitmap_l1 = (unsigned long *)kmap(page);
memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
@@ -9990,7 +9995,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exec_control;
- bool nested_ept_enabled = false;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10137,8 +10141,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs12->guest_intr_status);
}
- nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
-
/*
* Write an illegal value to APIC_ACCESS_ADDR. Later,
* nested_get_vmcs12_pages will either fix it up or
@@ -10268,9 +10270,24 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
}
+ if (enable_pml) {
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit, this happens
+ * to be equivalent to simply resetting the fields in vmcs02.
+ */
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
+ } else if (nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ vmx_flush_tlb_ept_only(vcpu);
}
/*
@@ -10298,12 +10315,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmx_set_efer(vcpu, vcpu->arch.efer);
/* Shadow page tables on either EPT or shadow page tables. */
- if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+ if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
entry_failure_code))
return 1;
- kvm_mmu_reset_context(vcpu);
-
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
@@ -11072,6 +11087,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
vmx_set_virtual_x2apic_mode(vcpu,
vcpu->arch.apic_base & X2APIC_ENABLE);
+ } else if (!nested_cpu_has_ept(vmcs12) &&
+ nested_cpu_has2(vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ vmx_flush_tlb_ept_only(vcpu);
}
/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -11121,8 +11140,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
*/
static void vmx_leave_nested(struct kvm_vcpu *vcpu)
{
- if (is_guest_mode(vcpu))
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.nested_run_pending = 0;
nested_vmx_vmexit(vcpu, -1, 0, 0);
+ }
free_nested(to_vmx(vcpu));
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1faf620a6fdc..ccbd45ecd41a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
if (kvm_x86_ops->vm_destroy)
kvm_x86_ops->vm_destroy(kvm);
kvm_iommu_unmap_guest(kvm);
- kfree(kvm->arch.vpic);
- kfree(kvm->arch.vioapic);
+ kvm_pic_destroy(kvm);
+ kvm_ioapic_destroy(kvm);
kvm_free_vcpus(kvm);
kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kvm_mmu_uninit_vm(kvm);
+ kvm_page_track_cleanup(kvm);
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
{
struct x86_exception fault;
- trace_kvm_async_pf_ready(work->arch.token, work->gva);
if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+ trace_kvm_async_pf_ready(work->arch.token, work->gva);
if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
!apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index a8e91ae89fb3..29df077cb089 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -93,6 +93,13 @@ static void delay_mwaitx(unsigned long __loops)
{
u64 start, end, delay, loops = __loops;
+ /*
+ * Timer value of 0 causes MWAITX to wait indefinitely, unless there
+ * is a store on the memory monitored by MONITORX.
+ */
+ if (loops == 0)
+ return;
+
start = rdtsc_ordered();
for (;;) {
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 779782f58324..9a53a06e5a3e 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -290,7 +290,7 @@ EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled)
_ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail)
- _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
+ _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail)
_ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail)
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 99c7805a9693..1f3b6ef105cd 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -106,32 +106,35 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
- int nr_start = *nr;
- pte_t *ptep;
+ int nr_start = *nr, ret = 0;
+ pte_t *ptep, *ptem;
- ptep = pte_offset_map(&pmd, addr);
+ /*
+ * Keep the original mapped PTE value (ptem) around since we
+ * might increment ptep off the end of the page when finishing
+ * our loop iteration.
+ */
+ ptem = ptep = pte_offset_map(&pmd, addr);
do {
pte_t pte = gup_get_pte(ptep);
struct page *page;
/* Similar to the PMD case, NUMA hinting must take slow path */
- if (pte_protnone(pte)) {
- pte_unmap(ptep);
- return 0;
- }
+ if (pte_protnone(pte))
+ break;
+
+ if (!pte_allows_gup(pte_val(pte), write))
+ break;
if (pte_devmap(pte)) {
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, pages);
- pte_unmap(ptep);
- return 0;
+ break;
}
- } else if (!pte_allows_gup(pte_val(pte), write) ||
- pte_special(pte)) {
- pte_unmap(ptep);
- return 0;
- }
+ } else if (pte_special(pte))
+ break;
+
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
get_page(page);
@@ -141,9 +144,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
- pte_unmap(ptep - 1);
+ if (addr == end)
+ ret = 1;
+ pte_unmap(ptem);
- return 1;
+ return ret;
}
static inline void get_head_page_multiple(struct page *page, int nr)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 22af912d66d2..889e7619a091 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -643,21 +643,40 @@ void __init init_mem_mapping(void)
* devmem_is_allowed() checks to see if /dev/mem access to a certain address
* is valid. The argument is a physical page number.
*
- *
- * On x86, access has to be given to the first megabyte of ram because that area
- * contains BIOS code and data regions used by X and dosemu and similar apps.
- * Access has to be given to non-kernel-ram areas as well, these contain the PCI
- * mmio resources as well as potential bios/acpi data regions.
+ * On x86, access has to be given to the first megabyte of RAM because that
+ * area traditionally contains BIOS code and data regions used by X, dosemu,
+ * and similar apps. Since they map the entire memory range, the whole range
+ * must be allowed (for mapping), but any areas that would otherwise be
+ * disallowed are flagged as being "zero filled" instead of rejected.
+ * Access has to be given to non-kernel-ram areas as well, these contain the
+ * PCI mmio resources as well as potential bios/acpi data regions.
*/
int devmem_is_allowed(unsigned long pagenr)
{
- if (pagenr < 256)
- return 1;
- if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+ if (page_is_ram(pagenr)) {
+ /*
+ * For disallowed memory regions in the low 1MB range,
+ * request that the page be shown as all zeros.
+ */
+ if (pagenr < 256)
+ return 2;
+
+ return 0;
+ }
+
+ /*
+ * This must follow RAM test, since System RAM is considered a
+ * restricted resource under CONFIG_STRICT_IOMEM.
+ */
+ if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
+ /* Low 1MB bypasses iomem restrictions. */
+ if (pagenr < 256)
+ return 1;
+
return 0;
- if (!page_is_ram(pagenr))
- return 1;
- return 0;
+ }
+
+ return 1;
}
void free_init_pages(char *what, unsigned long begin, unsigned long end)
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 8d63d7a104c3..4c90cfdc128b 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define DISABLE_BRANCH_PROFILING
#define pr_fmt(fmt) "kasan: " fmt
#include <linux/bootmem.h>
#include <linux/kasan.h>
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 887e57182716..aed206475aa7 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -48,7 +48,7 @@ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE;
#if defined(CONFIG_X86_ESPFIX64)
static const unsigned long vaddr_end = ESPFIX_BASE_ADDR;
#elif defined(CONFIG_EFI)
-static const unsigned long vaddr_end = EFI_VA_START;
+static const unsigned long vaddr_end = EFI_VA_END;
#else
static const unsigned long vaddr_end = __START_KERNEL_map;
#endif
@@ -105,7 +105,7 @@ void __init kernel_randomize_memory(void)
*/
BUILD_BUG_ON(vaddr_start >= vaddr_end);
BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) &&
- vaddr_end >= EFI_VA_START);
+ vaddr_end >= EFI_VA_END);
BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) ||
IS_ENABLED(CONFIG_EFI)) &&
vaddr_end >= __START_KERNEL_map);
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 5126dfd52b18..cd44ae727df7 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -590,7 +590,7 @@ static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm,
* we might run off the end of the bounds table if we are on
* a 64-bit kernel and try to get 8 bytes.
*/
-int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+static int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
long __user *bd_entry_ptr)
{
u32 bd_entry_32;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 0cb52ae0a8f0..190e718694b1 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev)
pcibios_disable_irq(dev);
}
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pcibios_release_device(struct pci_dev *dev)
+{
+ if (atomic_dec_return(&dev->enable_cnt) >= 0)
+ pcibios_disable_device(dev);
+
+}
+#endif
+
int pci_ext_cfg_avail(void)
{
if (raw_pci_ext_ops)
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index e1fb269c87af..292ab0364a89 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -234,23 +234,14 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
return 1;
for_each_pci_msi_entry(msidesc, dev) {
- __pci_read_msi_msg(msidesc, &msg);
- pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
- ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
- if (msg.data != XEN_PIRQ_MSI_DATA ||
- xen_irq_from_pirq(pirq) < 0) {
- pirq = xen_allocate_pirq_msi(dev, msidesc);
- if (pirq < 0) {
- irq = -ENODEV;
- goto error;
- }
- xen_msi_compose_msg(dev, pirq, &msg);
- __pci_write_msi_msg(msidesc, &msg);
- dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
- } else {
- dev_dbg(&dev->dev,
- "xen: msi already bound to pirq=%d\n", pirq);
+ pirq = xen_allocate_pirq_msi(dev, msidesc);
+ if (pirq < 0) {
+ irq = -ENODEV;
+ goto error;
}
+ xen_msi_compose_msg(dev, pirq, &msg);
+ __pci_write_msi_msg(msidesc, &msg);
+ dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
irq = xen_bind_pirq_msi_to_irq(dev, msidesc, pirq,
(type == PCI_CAP_ID_MSI) ? nvec : 1,
(type == PCI_CAP_ID_MSIX) ?
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 30031d5293c4..cdfe8c628959 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -201,6 +201,10 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
return;
}
+ /* No need to reserve regions that will never be freed. */
+ if (md.attribute & EFI_MEMORY_RUNTIME)
+ return;
+
size += addr % EFI_PAGE_SIZE;
size = round_up(size, EFI_PAGE_SIZE);
addr = round_down(addr, EFI_PAGE_SIZE);
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index a7dbec4dce27..3dbde04febdc 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -26,5 +26,6 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
# MISC Devices
obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_mrfld_power_btn.o
obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
new file mode 100644
index 000000000000..a6c3705a28ad
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_power_btn.c
@@ -0,0 +1,82 @@
+/*
+ * Intel Merrifield power button support
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * 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.
+ */
+
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/platform_device.h>
+#include <linux/sfi.h>
+
+#include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
+
+static struct resource mrfld_power_btn_resources[] = {
+ {
+ .flags = IORESOURCE_IRQ,
+ },
+};
+
+static struct platform_device mrfld_power_btn_dev = {
+ .name = "msic_power_btn",
+ .id = PLATFORM_DEVID_NONE,
+ .num_resources = ARRAY_SIZE(mrfld_power_btn_resources),
+ .resource = mrfld_power_btn_resources,
+};
+
+static int mrfld_power_btn_scu_status_change(struct notifier_block *nb,
+ unsigned long code, void *data)
+{
+ if (code == SCU_DOWN) {
+ platform_device_unregister(&mrfld_power_btn_dev);
+ return 0;
+ }
+
+ return platform_device_register(&mrfld_power_btn_dev);
+}
+
+static struct notifier_block mrfld_power_btn_scu_notifier = {
+ .notifier_call = mrfld_power_btn_scu_status_change,
+};
+
+static int __init register_mrfld_power_btn(void)
+{
+ if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+ return -ENODEV;
+
+ /*
+ * We need to be sure that the SCU IPC is ready before
+ * PMIC power button device can be registered:
+ */
+ intel_scu_notifier_add(&mrfld_power_btn_scu_notifier);
+
+ return 0;
+}
+arch_initcall(register_mrfld_power_btn);
+
+static void __init *mrfld_power_btn_platform_data(void *info)
+{
+ struct resource *res = mrfld_power_btn_resources;
+ struct sfi_device_table_entry *pentry = info;
+
+ res->start = res->end = pentry->irq;
+ return NULL;
+}
+
+static const struct devs_id mrfld_power_btn_dev_id __initconst = {
+ .name = "bcove_power_btn",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .msic = 1,
+ .get_platform_data = &mrfld_power_btn_platform_data,
+};
+
+sfi_device(mrfld_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 86edd1e941eb..9e304e2ea4f5 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -19,7 +19,7 @@
#include <asm/intel_scu_ipc.h>
#include <asm/io_apic.h>
-#define TANGIER_EXT_TIMER0_MSI 15
+#define TANGIER_EXT_TIMER0_MSI 12
static struct platform_device wdt_dev = {
.name = "intel_mid_wdt",
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index e793fe509971..e42978d4deaf 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -17,16 +17,6 @@
#include "intel_mid_weak_decls.h"
-static void penwell_arch_setup(void);
-/* penwell arch ops */
-static struct intel_mid_ops penwell_ops = {
- .arch_setup = penwell_arch_setup,
-};
-
-static void mfld_power_off(void)
-{
-}
-
static unsigned long __init mfld_calibrate_tsc(void)
{
unsigned long fast_calibrate;
@@ -63,9 +53,12 @@ static unsigned long __init mfld_calibrate_tsc(void)
static void __init penwell_arch_setup(void)
{
x86_platform.calibrate_tsc = mfld_calibrate_tsc;
- pm_power_off = mfld_power_off;
}
+static struct intel_mid_ops penwell_ops = {
+ .arch_setup = penwell_arch_setup,
+};
+
void *get_penwell_ops(void)
{
return &penwell_ops;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 766d4d3529a1..f25982cdff90 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1847,7 +1847,6 @@ static void pq_init(int node, int pnode)
ops.write_payload_first(pnode, first);
ops.write_payload_last(pnode, last);
- ops.write_g_sw_ack(pnode, 0xffffUL);
/* in effect, all msg_type's are set to MSG_NOOP */
memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 555b9fa0ad43..7dbdb780264d 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -8,6 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
targets += purgatory.ro
+KASAN_SANITIZE := n
KCOV_INSTRUMENT := n
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 25e068ba3382..470edad96bb9 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -10,21 +10,19 @@
* Version 2. See the file COPYING for more details.
*/
+#include <linux/bug.h>
+#include <asm/purgatory.h>
+
#include "sha256.h"
#include "../boot/string.h"
-struct sha_region {
- unsigned long start;
- unsigned long len;
-};
-
-unsigned long backup_dest = 0;
-unsigned long backup_src = 0;
-unsigned long backup_sz = 0;
+unsigned long purgatory_backup_dest __section(.kexec-purgatory);
+unsigned long purgatory_backup_src __section(.kexec-purgatory);
+unsigned long purgatory_backup_sz __section(.kexec-purgatory);
-u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
+u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(.kexec-purgatory);
-struct sha_region sha_regions[16] = {};
+struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(.kexec-purgatory);
/*
* On x86, second kernel requries first 640K of memory to boot. Copy
@@ -33,26 +31,28 @@ struct sha_region sha_regions[16] = {};
*/
static int copy_backup_region(void)
{
- if (backup_dest)
- memcpy((void *)backup_dest, (void *)backup_src, backup_sz);
-
+ if (purgatory_backup_dest) {
+ memcpy((void *)purgatory_backup_dest,
+ (void *)purgatory_backup_src, purgatory_backup_sz);
+ }
return 0;
}
-int verify_sha256_digest(void)
+static int verify_sha256_digest(void)
{
- struct sha_region *ptr, *end;
+ struct kexec_sha_region *ptr, *end;
u8 digest[SHA256_DIGEST_SIZE];
struct sha256_state sctx;
sha256_init(&sctx);
- end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])];
- for (ptr = sha_regions; ptr < end; ptr++)
+ end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
+
+ for (ptr = purgatory_sha_regions; ptr < end; ptr++)
sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
sha256_final(&sctx, digest);
- if (memcmp(digest, sha256_digest, sizeof(digest)))
+ if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)))
return 1;
return 0;
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index fe3c91ba1bd0..dfae9b9e60b5 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -9,6 +9,7 @@
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
*/
+#include <asm/purgatory.h>
.text
.globl purgatory_start
diff --git a/arch/x86/purgatory/sha256.h b/arch/x86/purgatory/sha256.h
index bd15a4127735..2867d9825a57 100644
--- a/arch/x86/purgatory/sha256.h
+++ b/arch/x86/purgatory/sha256.h
@@ -10,7 +10,6 @@
#ifndef SHA256_H
#define SHA256_H
-
#include <linux/types.h>
#include <crypto/sha.h>