summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Makefile9
-rw-r--r--arch/x86/boot/Makefile4
-rw-r--r--arch/x86/boot/compressed/misc.c2
-rw-r--r--arch/x86/include/asm/hpet.h1
-rw-r--r--arch/x86/include/asm/hugetlb.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/include/asm/page_64_types.h2
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h2
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c7
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c18
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/threshold.c4
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c46
-rw-r--r--arch/x86/kernel/cpu/rdrand.c1
-rw-r--r--arch/x86/kernel/early-quirks.c18
-rw-r--r--arch/x86/kernel/head32.c2
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c16
-rw-r--r--arch/x86/kernel/ldt.c4
-rw-r--r--arch/x86/kernel/process_64.c2
-rw-r--r--arch/x86/kernel/reboot.c82
-rw-r--r--arch/x86/kernel/smp.c2
-rw-r--r--arch/x86/kernel/traps.c6
-rw-r--r--arch/x86/kernel/vsmp_64.c17
-rw-r--r--arch/x86/kernel/vsyscall_gtod.c2
-rw-r--r--arch/x86/kvm/cpuid.c2
-rw-r--r--arch/x86/kvm/cpuid.h8
-rw-r--r--arch/x86/kvm/mmu.c38
-rw-r--r--arch/x86/kvm/mmu.h44
-rw-r--r--arch/x86/kvm/paging_tmpl.h2
-rw-r--r--arch/x86/kvm/vmx.c71
-rw-r--r--arch/x86/kvm/x86.c18
-rw-r--r--arch/x86/lguest/boot.c4
-rw-r--r--arch/x86/lib/msr.c2
-rw-r--r--arch/x86/math-emu/errors.c16
-rw-r--r--arch/x86/net/bpf_jit_comp.c2
-rw-r--r--arch/x86/platform/efi/early_printk.c83
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-pm.c2
-rw-r--r--arch/x86/power/hibernate_64.c2
-rw-r--r--arch/x86/syscalls/Makefile2
-rw-r--r--arch/x86/syscalls/syscall_32.tbl1
-rw-r--r--arch/x86/tools/Makefile2
-rw-r--r--arch/x86/vdso/vdso-layout.lds.S19
-rw-r--r--arch/x86/vdso/vdso32-setup.c8
-rw-r--r--arch/x86/xen/enlighten.c2
-rw-r--r--arch/x86/xen/irq.c6
-rw-r--r--arch/x86/xen/smp.c3
-rw-r--r--arch/x86/xen/spinlock.c5
-rw-r--r--arch/x86/xen/xen-asm_32.S25
53 files changed, 443 insertions, 189 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 602f57e590b..33f71b01fd2 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -79,11 +79,14 @@ else
UTS_MACHINE := x86_64
CHECKFLAGS += -D__x86_64__ -m64
+ biarch := -m64
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
# Don't autogenerate traditional x87, MMX or SSE instructions
- KBUILD_CFLAGS += -mno-mmx -mno-sse -mno-80387 -mno-fp-ret-in-387
+ KBUILD_CFLAGS += -mno-mmx -mno-sse
+ KBUILD_CFLAGS += $(call cc-option,-mno-80387)
+ KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
# Use -mpreferred-stack-boundary=3 if supported.
KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
@@ -250,8 +253,8 @@ archclean:
PHONY += kvmconfig
kvmconfig:
$(if $(wildcard $(objtree)/.config),, $(error You need an existing .config for this target))
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config arch/x86/configs/kvm_guest.config
- $(Q)yes "" | $(MAKE) oldconfig
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config $(srctree)/arch/x86/configs/kvm_guest.config
+ $(Q)yes "" | $(MAKE) -f $(srctree)/Makefile oldconfig
define archhelp
echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index abb9eba61b5..dbe8dd2fe24 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -71,7 +71,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) . \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
quiet_cmd_voffset = VOFFSET $@
cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
@@ -80,7 +80,7 @@ targets += voffset.h
$(obj)/voffset.h: vmlinux FORCE
$(call if_changed,voffset)
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
quiet_cmd_zoffset = ZOFFSET $@
cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 17684615374..57ab74df7ee 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -354,7 +354,7 @@ static void parse_elf(void *output)
free(phdrs);
}
-asmlinkage void *decompress_kernel(void *rmode, memptr heap,
+asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
unsigned char *input_data,
unsigned long input_len,
unsigned char *output,
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index b18df579c0e..36f7125945e 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -63,6 +63,7 @@
/* hpet memory map physical address */
extern unsigned long hpet_address;
extern unsigned long force_hpet_address;
+extern int boot_hpet_disable;
extern u8 hpet_blockid;
extern int hpet_force_user;
extern u8 hpet_msi_disable;
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index a8091216963..68c05398bba 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
+ ptep_clear_flush(vma, addr, ptep);
}
static inline int huge_pte_none(pte_t pte)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fcaf9c96126..7de069afb38 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -60,7 +60,7 @@
| X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
| X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
| X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
- | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+ | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE | X86_CR4_SMAP))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8de6d9cf3b9..678205195ae 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,7 +1,7 @@
#ifndef _ASM_X86_PAGE_64_DEFS_H
#define _ASM_X86_PAGE_64_DEFS_H
-#define THREAD_SIZE_ORDER 1
+#define THREAD_SIZE_ORDER 2
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
#define CURRENT_MASK (~(THREAD_SIZE - 1))
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c827ace3121..fcf2b3ae1bf 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -384,7 +384,7 @@
#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18
#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT);
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23
#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 3a2ae4c8894..31368207837 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -31,7 +31,7 @@ static char temp_stack[4096];
*
* Wrapper around acpi_enter_sleep_state() to be called by assmebly.
*/
-acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state)
+acpi_status asmlinkage __visible x86_acpi_enter_sleep_state(u8 state)
{
return acpi_enter_sleep_state(state);
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6ad4658de70..992060e0989 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2189,7 +2189,7 @@ void send_cleanup_vector(struct irq_cfg *cfg)
cfg->move_in_progress = 0;
}
-asmlinkage void smp_irq_move_cleanup_interrupt(void)
+asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
{
unsigned vector, me;
@@ -3425,6 +3425,11 @@ int get_nr_irqs_gsi(void)
return nr_irqs_gsi;
}
+unsigned int arch_dynirq_lower_bound(unsigned int from)
+{
+ return from < nr_irqs_gsi ? nr_irqs_gsi : from;
+}
+
int __init arch_probe_nr_irqs(void)
{
int nr;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index eeee23ff75e..68317c80de7 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -598,7 +598,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
struct mce m;
int i;
- unsigned long *v;
this_cpu_inc(mce_poll_count);
@@ -618,8 +617,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(m.status & MCI_STATUS_VAL))
continue;
- v = &get_cpu_var(mce_polled_error);
- set_bit(0, v);
+ this_cpu_write(mce_polled_error, 1);
/*
* Uncorrected or signalled events are handled by the exception
* handler when it is enabled, so don't process those here.
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 3bdb95ae8c4..9a316b21df8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -42,7 +42,7 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
* cmci_discover_lock protects against parallel discovery attempts
* which could race against each other.
*/
-static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
+static DEFINE_SPINLOCK(cmci_discover_lock);
#define CMCI_THRESHOLD 1
#define CMCI_POLL_INTERVAL (30 * HZ)
@@ -144,14 +144,14 @@ static void cmci_storm_disable_banks(void)
int bank;
u64 val;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
owned = __get_cpu_var(mce_banks_owned);
for_each_set_bit(bank, owned, MAX_NR_BANKS) {
rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
val &= ~MCI_CTL2_CMCI_EN;
wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
}
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
static bool cmci_storm_detect(void)
@@ -211,7 +211,7 @@ static void cmci_discover(int banks)
int i;
int bios_wrong_thresh = 0;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
u64 val;
int bios_zero_thresh = 0;
@@ -266,7 +266,7 @@ static void cmci_discover(int banks)
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
pr_info_once(
"bios_cmci_threshold: Some banks do not have valid thresholds set\n");
@@ -316,10 +316,10 @@ void cmci_clear(void)
if (!cmci_supported(&banks))
return;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++)
__cmci_disable_bank(i);
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
static void cmci_rediscover_work_func(void *arg)
@@ -360,9 +360,9 @@ void cmci_disable_bank(int bank)
if (!cmci_supported(&banks))
return;
- raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ spin_lock_irqsave(&cmci_discover_lock, flags);
__cmci_disable_bank(bank);
- raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
static void intel_init_cmci(void)
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d921b7ee659..36a1bb6d1ee 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -429,14 +429,14 @@ static inline void __smp_thermal_interrupt(void)
smp_thermal_vector();
}
-asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void smp_thermal_interrupt(struct pt_regs *regs)
{
entering_irq();
__smp_thermal_interrupt();
exiting_ack_irq();
}
-asmlinkage void smp_trace_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs)
{
entering_irq();
trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index fe6b1c86645..7245980186e 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -24,14 +24,14 @@ static inline void __smp_threshold_interrupt(void)
mce_threshold_vector();
}
-asmlinkage void smp_threshold_interrupt(void)
+asmlinkage __visible void smp_threshold_interrupt(void)
{
entering_irq();
__smp_threshold_interrupt();
exiting_ack_irq();
}
-asmlinkage void smp_trace_threshold_interrupt(void)
+asmlinkage __visible void smp_trace_threshold_interrupt(void)
{
entering_irq();
trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa333d96688..adb02aa62af 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -169,7 +169,6 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
EVENT_CONSTRAINT_END
};
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 059218ed520..619f7699487 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -59,7 +59,7 @@
#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT 3 /* DRAM */
+#define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */
#define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */
/* Clients have PP0, PKG */
@@ -72,6 +72,12 @@
1<<RAPL_IDX_PKG_NRG_STAT|\
1<<RAPL_IDX_RAM_NRG_STAT)
+/* Servers have PP0, PKG, RAM, PP1 */
+#define RAPL_IDX_HSW (1<<RAPL_IDX_PP0_NRG_STAT|\
+ 1<<RAPL_IDX_PKG_NRG_STAT|\
+ 1<<RAPL_IDX_RAM_NRG_STAT|\
+ 1<<RAPL_IDX_PP1_NRG_STAT)
+
/*
* event code: LSB 8 bits, passed in attr->config
* any other bit is reserved
@@ -425,6 +431,24 @@ static struct attribute *rapl_events_cln_attr[] = {
NULL,
};
+static struct attribute *rapl_events_hsw_attr[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_gpu),
+ EVENT_PTR(rapl_ram),
+
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_gpu_unit),
+ EVENT_PTR(rapl_ram_unit),
+
+ EVENT_PTR(rapl_cores_scale),
+ EVENT_PTR(rapl_pkg_scale),
+ EVENT_PTR(rapl_gpu_scale),
+ EVENT_PTR(rapl_ram_scale),
+ NULL,
+};
+
static struct attribute_group rapl_pmu_events_group = {
.name = "events",
.attrs = NULL, /* patched at runtime */
@@ -511,6 +535,7 @@ static int rapl_cpu_prepare(int cpu)
struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
int phys_id = topology_physical_package_id(cpu);
u64 ms;
+ u64 msr_rapl_power_unit_bits;
if (pmu)
return 0;
@@ -518,6 +543,10 @@ static int rapl_cpu_prepare(int cpu)
if (phys_id < 0)
return -1;
+ /* protect rdmsrl() to handle virtualization */
+ if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+ return -1;
+
pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
if (!pmu)
return -1;
@@ -531,8 +560,7 @@ static int rapl_cpu_prepare(int cpu)
*
* we cache in local PMU instance
*/
- rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
- pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+ pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
pmu->pmu = &rapl_pmu_class;
/*
@@ -631,11 +659,14 @@ static int __init rapl_pmu_init(void)
switch (boot_cpu_data.x86_model) {
case 42: /* Sandy Bridge */
case 58: /* Ivy Bridge */
- case 60: /* Haswell */
- case 69: /* Haswell-Celeron */
rapl_cntr_mask = RAPL_IDX_CLN;
rapl_pmu_events_group.attrs = rapl_events_cln_attr;
break;
+ case 60: /* Haswell */
+ case 69: /* Haswell-Celeron */
+ rapl_cntr_mask = RAPL_IDX_HSW;
+ rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
+ break;
case 45: /* Sandy Bridge-EP */
case 62: /* IvyTown */
rapl_cntr_mask = RAPL_IDX_SRV;
@@ -650,7 +681,9 @@ static int __init rapl_pmu_init(void)
cpu_notifier_register_begin();
for_each_online_cpu(cpu) {
- rapl_cpu_prepare(cpu);
+ ret = rapl_cpu_prepare(cpu);
+ if (ret)
+ goto out;
rapl_cpu_init(cpu);
}
@@ -673,6 +706,7 @@ static int __init rapl_pmu_init(void)
hweight32(rapl_cntr_mask),
ktime_to_ms(pmu->timer_interval));
+out:
cpu_notifier_register_done();
return 0;
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 384df5105fb..136ac74dee8 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -27,6 +27,7 @@
static int __init x86_rdrand_setup(char *s)
{
setup_clear_cpu_cap(X86_FEATURE_RDRAND);
+ setup_clear_cpu_cap(X86_FEATURE_RDSEED);
return 1;
}
__setup("nordrand", x86_rdrand_setup);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index b0cc3809723..6cda0baeac9 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -17,6 +17,7 @@
#include <asm/dma.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
+#include <asm/hpet.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/irq_remapping.h>
@@ -240,7 +241,7 @@ static u32 __init intel_stolen_base(int num, int slot, int func, size_t stolen_s
return base;
}
-#define KB(x) ((x) * 1024)
+#define KB(x) ((x) * 1024UL)
#define MB(x) (KB (KB (x)))
#define GB(x) (MB (KB (x)))
@@ -530,6 +531,15 @@ static void __init intel_graphics_stolen(int num, int slot, int func)
}
}
+static void __init force_disable_hpet(int num, int slot, int func)
+{
+#ifdef CONFIG_HPET_TIMER
+ boot_hpet_disable = 1;
+ pr_info("x86/hpet: Will disable the HPET for this platform because it's not reliable\n");
+#endif
+}
+
+
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -567,6 +577,12 @@ static struct chipset early_qrk[] __initdata = {
PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
QFLAG_APPLY_ONCE, intel_graphics_stolen },
+ /*
+ * HPET on current version of Baytrail platform has accuracy
+ * problems, disable it for now:
+ */
+ { PCI_VENDOR_ID_INTEL, 0x0f00,
+ PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
{}
};
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index c61a14a4a31..d6c1b983699 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void)
reserve_ebda_region();
}
-asmlinkage void __init i386_start_kernel(void)
+asmlinkage __visible void __init i386_start_kernel(void)
{
sanitize_boot_params(&boot_params);
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 85126ccbdf6..068054f4bf2 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data)
}
}
-asmlinkage void __init x86_64_start_kernel(char * real_mode_data)
+asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
{
int i;
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 8d80ae01160..4177bfbc80b 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -88,7 +88,7 @@ static inline void hpet_clear_mapping(void)
/*
* HPET command line enable / disable
*/
-static int boot_hpet_disable;
+int boot_hpet_disable;
int hpet_force_user;
static int hpet_verbose;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 79a3f968287..61b17dc2c27 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -897,9 +897,10 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- switch (kcb->kprobe_status) {
- case KPROBE_HIT_SS:
- case KPROBE_REENTER:
+ if (unlikely(regs->ip == (unsigned long)cur->ainsn.insn)) {
+ /* This must happen on single-stepping */
+ WARN_ON(kcb->kprobe_status != KPROBE_HIT_SS &&
+ kcb->kprobe_status != KPROBE_REENTER);
/*
* We are here because the instruction being single
* stepped caused a page fault. We reset the current
@@ -914,9 +915,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
else
reset_current_kprobe();
preempt_enable_no_resched();
- break;
- case KPROBE_HIT_ACTIVE:
- case KPROBE_HIT_SSDONE:
+ } else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
+ kcb->kprobe_status == KPROBE_HIT_SSDONE) {
/*
* We increment the nmissed count for accounting,
* we can also use npre/npostfault count for accounting
@@ -945,10 +945,8 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
* fixup routine could not handle it,
* Let do_page_fault() fix it.
*/
- break;
- default:
- break;
}
+
return 0;
}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index af1d14a9ebd..dcbbaa165bd 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,6 +20,8 @@
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
+int sysctl_ldt16 = 0;
+
#ifdef CONFIG_SMP
static void flush_ldt(void *current_mm)
{
@@ -234,7 +236,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
* IRET leaking the high bits of the kernel stack address.
*/
#ifdef CONFIG_X86_64
- if (!ldt_info.seg_32bit) {
+ if (!ldt_info.seg_32bit && !sysctl_ldt16) {
error = -EINVAL;
goto out_unlock;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9c0280f93d0..898d077617a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
asmlinkage extern void ret_from_fork(void);
-asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp);
+__visible DEFINE_PER_CPU(unsigned long, old_rsp);
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 654b46574b9..52b1157c53e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -114,8 +114,8 @@ EXPORT_SYMBOL(machine_real_restart);
*/
static int __init set_pci_reboot(const struct dmi_system_id *d)
{
- if (reboot_type != BOOT_CF9) {
- reboot_type = BOOT_CF9;
+ if (reboot_type != BOOT_CF9_FORCE) {
+ reboot_type = BOOT_CF9_FORCE;
pr_info("%s series board detected. Selecting %s-method for reboots.\n",
d->ident, "PCI");
}
@@ -191,6 +191,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
},
},
+ /* Certec */
+ { /* Handle problems with rebooting on Certec BPC600 */
+ .callback = set_pci_reboot,
+ .ident = "Certec BPC600",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Certec"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "BPC600"),
+ },
+ },
+
/* Dell */
{ /* Handle problems with rebooting on Dell DXP061 */
.callback = set_bios_reboot,
@@ -458,20 +468,23 @@ void __attribute__((weak)) mach_reboot_fixups(void)
}
/*
- * Windows compatible x86 hardware expects the following on reboot:
+ * To the best of our knowledge Windows compatible x86 hardware expects
+ * the following on reboot:
*
* 1) If the FADT has the ACPI reboot register flag set, try it
* 2) If still alive, write to the keyboard controller
* 3) If still alive, write to the ACPI reboot register again
* 4) If still alive, write to the keyboard controller again
* 5) If still alive, call the EFI runtime service to reboot
- * 6) If still alive, write to the PCI IO port 0xCF9 to reboot
- * 7) If still alive, inform BIOS to do a proper reboot
+ * 6) If no EFI runtime service, call the BIOS to do a reboot
+ *
+ * We default to following the same pattern. We also have
+ * two other reboot methods: 'triple fault' and 'PCI', which
+ * can be triggered via the reboot= kernel boot option or
+ * via quirks.
*
- * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (7) we'll
- * try to force a triple fault and then cycle between hitting the keyboard
- * controller and doing that
+ * This means that this function can never return, it can misbehave
+ * by not rebooting properly and hanging.
*/
static void native_machine_emergency_restart(void)
{
@@ -492,6 +505,11 @@ static void native_machine_emergency_restart(void)
for (;;) {
/* Could also try the reset bit in the Hammer NB */
switch (reboot_type) {
+ case BOOT_ACPI:
+ acpi_reboot();
+ reboot_type = BOOT_KBD;
+ break;
+
case BOOT_KBD:
mach_reboot_fixups(); /* For board specific fixups */
@@ -509,43 +527,29 @@ static void native_machine_emergency_restart(void)
}
break;
- case BOOT_TRIPLE:
- load_idt(&no_idt);
- __asm__ __volatile__("int3");
-
- /* We're probably dead after this, but... */
- reboot_type = BOOT_KBD;
- break;
-
- case BOOT_BIOS:
- machine_real_restart(MRR_BIOS);
-
- /* We're probably dead after this, but... */
- reboot_type = BOOT_TRIPLE;
- break;
-
- case BOOT_ACPI:
- acpi_reboot();
- reboot_type = BOOT_KBD;
- break;
-
case BOOT_EFI:
if (efi_enabled(EFI_RUNTIME_SERVICES))
efi.reset_system(reboot_mode == REBOOT_WARM ?
EFI_RESET_WARM :
EFI_RESET_COLD,
EFI_SUCCESS, 0, NULL);
- reboot_type = BOOT_CF9_COND;
+ reboot_type = BOOT_BIOS;
+ break;
+
+ case BOOT_BIOS:
+ machine_real_restart(MRR_BIOS);
+
+ /* We're probably dead after this, but... */
+ reboot_type = BOOT_CF9_SAFE;
break;
- case BOOT_CF9:
+ case BOOT_CF9_FORCE:
port_cf9_safe = true;
/* Fall through */
- case BOOT_CF9_COND:
+ case BOOT_CF9_SAFE:
if (port_cf9_safe) {
- u8 reboot_code = reboot_mode == REBOOT_WARM ?
- 0x06 : 0x0E;
+ u8 reboot_code = reboot_mode == REBOOT_WARM ? 0x06 : 0x0E;
u8 cf9 = inb(0xcf9) & ~reboot_code;
outb(cf9|2, 0xcf9); /* Request hard reset */
udelay(50);
@@ -553,7 +557,15 @@ static void native_machine_emergency_restart(void)
outb(cf9|reboot_code, 0xcf9);
udelay(50);
}
- reboot_type = BOOT_BIOS;
+ reboot_type = BOOT_TRIPLE;
+ break;
+
+ case BOOT_TRIPLE:
+ load_idt(&no_idt);
+ __asm__ __volatile__("int3");
+
+ /* We're probably dead after this, but... */
+ reboot_type = BOOT_KBD;
break;
}
}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 7c3a5a61f2e..be8e1bde07a 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -168,7 +168,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
* this function calls the 'stop' function on all other CPUs in the system.
*/
-asmlinkage void smp_reboot_interrupt(void)
+asmlinkage __visible void smp_reboot_interrupt(void)
{
ack_APIC_irq();
irq_enter();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 57409f6b8c6..f73b5d435bd 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -357,7 +357,7 @@ exit:
* for scheduling or signal handling. The actual stack switch is done in
* entry.S
*/
-asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
{
struct pt_regs *regs = eregs;
/* Did already sync */
@@ -601,11 +601,11 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
#endif
}
-asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void)
+asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
{
}
-asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
+asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
{
}
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index f6584a90aba..b99b9ad8540 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -26,6 +26,9 @@
#define TOPOLOGY_REGISTER_OFFSET 0x10
+/* Flag below is initialized once during vSMP PCI initialization. */
+static int irq_routing_comply = 1;
+
#if defined CONFIG_PCI && defined CONFIG_PARAVIRT
/*
* Interrupt control on vSMPowered systems:
@@ -33,7 +36,7 @@
* and vice versa.
*/
-asmlinkage unsigned long vsmp_save_fl(void)
+asmlinkage __visible unsigned long vsmp_save_fl(void)
{
unsigned long flags = native_save_fl();
@@ -53,7 +56,7 @@ __visible void vsmp_restore_fl(unsigned long flags)
}
PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
-asmlinkage void vsmp_irq_disable(void)
+asmlinkage __visible void vsmp_irq_disable(void)
{
unsigned long flags = native_save_fl();
@@ -61,7 +64,7 @@ asmlinkage void vsmp_irq_disable(void)
}
PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
-asmlinkage void vsmp_irq_enable(void)
+asmlinkage __visible void vsmp_irq_enable(void)
{
unsigned long flags = native_save_fl();
@@ -101,6 +104,10 @@ static void __init set_vsmp_pv_ops(void)
#ifdef CONFIG_SMP
if (cap & ctl & BIT(8)) {
ctl &= ~BIT(8);
+
+ /* Interrupt routing set to ignore */
+ irq_routing_comply = 0;
+
#ifdef CONFIG_PROC_FS
/* Don't let users change irq affinity via procfs */
no_irq_affinity = 1;
@@ -218,7 +225,9 @@ static void vsmp_apic_post_init(void)
{
/* need to update phys_pkg_id */
apic->phys_pkg_id = apicid_phys_pkg_id;
- apic->vector_allocation_domain = fill_vector_allocation_domain;
+
+ if (!irq_routing_comply)
+ apic->vector_allocation_domain = fill_vector_allocation_domain;
}
void __init vsmp_init(void)
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index f9c6e56e14b..9531fbb123b 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -43,7 +43,7 @@ void update_vsyscall(struct timekeeper *tk)
vdata->monotonic_time_sec = tk->xtime_sec
+ tk->wall_to_monotonic.tv_sec;
vdata->monotonic_time_snsec = tk->xtime_nsec
- + (tk->wall_to_monotonic.tv_nsec
+ + ((u64)tk->wall_to_monotonic.tv_nsec
<< tk->shift);
while (vdata->monotonic_time_snsec >=
(((u64)NSEC_PER_SEC) << tk->shift)) {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bea60671ef8..f47a104a749 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -308,7 +308,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
const u32 kvm_supported_word9_x86_features =
F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
- F(ADX);
+ F(ADX) | F(SMAP);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a2a1bb7ed8c..eeecbed26ac 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -48,6 +48,14 @@ static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu)
return best && (best->ebx & bit(X86_FEATURE_SMEP));
}
+static inline bool guest_cpuid_has_smap(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 7, 0);
+ return best && (best->ebx & bit(X86_FEATURE_SMAP));
+}
+
static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f5704d9e5dd..813d31038b9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3601,20 +3601,27 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
}
}
-static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+void update_permission_bitmask(struct kvm_vcpu *vcpu,
struct kvm_mmu *mmu, bool ept)
{
unsigned bit, byte, pfec;
u8 map;
- bool fault, x, w, u, wf, uf, ff, smep;
+ bool fault, x, w, u, wf, uf, ff, smapf, cr4_smap, cr4_smep, smap = 0;
- smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
pfec = byte << 1;
map = 0;
wf = pfec & PFERR_WRITE_MASK;
uf = pfec & PFERR_USER_MASK;
ff = pfec & PFERR_FETCH_MASK;
+ /*
+ * PFERR_RSVD_MASK bit is set in PFEC if the access is not
+ * subject to SMAP restrictions, and cleared otherwise. The
+ * bit is only meaningful if the SMAP bit is set in CR4.
+ */
+ smapf = !(pfec & PFERR_RSVD_MASK);
for (bit = 0; bit < 8; ++bit) {
x = bit & ACC_EXEC_MASK;
w = bit & ACC_WRITE_MASK;
@@ -3626,12 +3633,33 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
/* Allow supervisor writes if !cr0.wp */
w |= !is_write_protection(vcpu) && !uf;
/* Disallow supervisor fetches of user code if cr4.smep */
- x &= !(smep && u && !uf);
+ x &= !(cr4_smep && u && !uf);
+
+ /*
+ * SMAP:kernel-mode data accesses from user-mode
+ * mappings should fault. A fault is considered
+ * as a SMAP violation if all of the following
+ * conditions are ture:
+ * - X86_CR4_SMAP is set in CR4
+ * - An user page is accessed
+ * - Page fault in kernel mode
+ * - if CPL = 3 or X86_EFLAGS_AC is clear
+ *
+ * Here, we cover the first three conditions.
+ * The fourth is computed dynamically in
+ * permission_fault() and is in smapf.
+ *
+ * Also, SMAP does not affect instruction
+ * fetches, add the !ff check here to make it
+ * clearer.
+ */
+ smap = cr4_smap && u && !uf && !ff;
} else
/* Not really needed: no U/S accesses on ept */
u = 1;
- fault = (ff && !x) || (uf && !u) || (wf && !w);
+ fault = (ff && !x) || (uf && !u) || (wf && !w) ||
+ (smapf && smap);
map |= fault << bit;
}
mmu->permissions[byte] = map;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 29261527435..3842e70bdb7 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -44,11 +44,17 @@
#define PT_DIRECTORY_LEVEL 2
#define PT_PAGE_TABLE_LEVEL 1
-#define PFERR_PRESENT_MASK (1U << 0)
-#define PFERR_WRITE_MASK (1U << 1)
-#define PFERR_USER_MASK (1U << 2)
-#define PFERR_RSVD_MASK (1U << 3)
-#define PFERR_FETCH_MASK (1U << 4)
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+
+#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
+#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
+#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
@@ -73,6 +79,8 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
bool execonly);
+void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ bool ept);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
@@ -110,10 +118,30 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
* Will a fault with a given page-fault error code (pfec) cause a permission
* fault with the given access (in ACC_* format)?
*/
-static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
- unsigned pfec)
+static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ unsigned pte_access, unsigned pfec)
{
- return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
+ int cpl = kvm_x86_ops->get_cpl(vcpu);
+ unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+
+ /*
+ * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1.
+ *
+ * If CPL = 3, SMAP applies to all supervisor-mode data accesses
+ * (these are implicit supervisor accesses) regardless of the value
+ * of EFLAGS.AC.
+ *
+ * This computes (cpl < 3) && (rflags & X86_EFLAGS_AC), leaving
+ * the result in X86_EFLAGS_AC. We then insert it in place of
+ * the PFERR_RSVD_MASK bit; this bit will always be zero in pfec,
+ * but it will be one in index if SMAP checks are being overridden.
+ * It is important to keep this branchless.
+ */
+ unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC);
+ int index = (pfec >> 1) +
+ (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+
+ return (mmu->permissions[index] >> pte_access) & 1;
}
void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index b1e6c1bf68d..123efd3ec29 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -353,7 +353,7 @@ retry_walk:
walker->ptes[walker->level - 1] = pte;
} while (!is_last_gpte(mmu, walker->level, pte));
- if (unlikely(permission_fault(mmu, pte_access, access))) {
+ if (unlikely(permission_fault(vcpu, mmu, pte_access, access))) {
errcode |= PFERR_PRESENT_MASK;
goto error;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1320e0f8e61..138ceffc637 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -503,7 +503,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
[number##_HIGH] = VMCS12_OFFSET(name)+4
-static const unsigned long shadow_read_only_fields[] = {
+static unsigned long shadow_read_only_fields[] = {
/*
* We do NOT shadow fields that are modified when L0
* traps and emulates any vmx instruction (e.g. VMPTRLD,
@@ -526,10 +526,10 @@ static const unsigned long shadow_read_only_fields[] = {
GUEST_LINEAR_ADDRESS,
GUEST_PHYSICAL_ADDRESS
};
-static const int max_shadow_read_only_fields =
+static int max_shadow_read_only_fields =
ARRAY_SIZE(shadow_read_only_fields);
-static const unsigned long shadow_read_write_fields[] = {
+static unsigned long shadow_read_write_fields[] = {
GUEST_RIP,
GUEST_RSP,
GUEST_CR0,
@@ -558,7 +558,7 @@ static const unsigned long shadow_read_write_fields[] = {
HOST_FS_SELECTOR,
HOST_GS_SELECTOR
};
-static const int max_shadow_read_write_fields =
+static int max_shadow_read_write_fields =
ARRAY_SIZE(shadow_read_write_fields);
static const unsigned short vmcs_field_to_offset_table[] = {
@@ -3009,6 +3009,41 @@ static void free_kvm_area(void)
}
}
+static void init_vmcs_shadow_fields(void)
+{
+ int i, j;
+
+ /* No checks for read only fields yet */
+
+ for (i = j = 0; i < max_shadow_read_write_fields; i++) {
+ switch (shadow_read_write_fields[i]) {
+ case GUEST_BNDCFGS:
+ if (!vmx_mpx_supported())
+ continue;
+ break;
+ default:
+ break;
+ }
+
+ if (j < i)
+ shadow_read_write_fields[j] =
+ shadow_read_write_fields[i];
+ j++;
+ }
+ max_shadow_read_write_fields = j;
+
+ /* shadowed fields guest access without vmexit */
+ for (i = 0; i < max_shadow_read_write_fields; i++) {
+ clear_bit(shadow_read_write_fields[i],
+ vmx_vmwrite_bitmap);
+ clear_bit(shadow_read_write_fields[i],
+ vmx_vmread_bitmap);
+ }
+ for (i = 0; i < max_shadow_read_only_fields; i++)
+ clear_bit(shadow_read_only_fields[i],
+ vmx_vmread_bitmap);
+}
+
static __init int alloc_kvm_area(void)
{
int cpu;
@@ -3039,6 +3074,8 @@ static __init int hardware_setup(void)
enable_vpid = 0;
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
+ if (enable_shadow_vmcs)
+ init_vmcs_shadow_fields();
if (!cpu_has_vmx_ept() ||
!cpu_has_vmx_ept_4levels()) {
@@ -3484,13 +3521,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
hw_cr4 &= ~X86_CR4_PAE;
hw_cr4 |= X86_CR4_PSE;
/*
- * SMEP is disabled if CPU is in non-paging mode in
- * hardware. However KVM always uses paging mode to
+ * SMEP/SMAP is disabled if CPU is in non-paging mode
+ * in hardware. However KVM always uses paging mode to
* emulate guest non-paging mode with TDP.
- * To emulate this behavior, SMEP needs to be manually
- * disabled when guest switches to non-paging mode.
+ * To emulate this behavior, SMEP/SMAP needs to be
+ * manually disabled when guest switches to non-paging
+ * mode.
*/
- hw_cr4 &= ~X86_CR4_SMEP;
+ hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP);
} else if (!(cr4 & X86_CR4_PAE)) {
hw_cr4 &= ~X86_CR4_PAE;
}
@@ -7740,7 +7778,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
exec_control = vmcs12->pin_based_vm_exec_control;
exec_control |= vmcs_config.pin_based_exec_ctrl;
- exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+ exec_control &= ~(PIN_BASED_VMX_PREEMPTION_TIMER |
+ PIN_BASED_POSTED_INTR);
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
vmx->nested.preemption_timer_expired = false;
@@ -7777,7 +7816,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (!vmx->rdtscp_enabled)
exec_control &= ~SECONDARY_EXEC_RDTSCP;
/* Take the following fields only from vmcs12 */
- exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+ SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
exec_control |= vmcs12->secondary_vm_exec_control;
@@ -8802,14 +8843,6 @@ static int __init vmx_init(void)
memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
- /* shadowed read/write fields */
- for (i = 0; i < max_shadow_read_write_fields; i++) {
- clear_bit(shadow_read_write_fields[i], vmx_vmwrite_bitmap);
- clear_bit(shadow_read_write_fields[i], vmx_vmread_bitmap);
- }
- /* shadowed read only fields */
- for (i = 0; i < max_shadow_read_only_fields; i++)
- clear_bit(shadow_read_only_fields[i], vmx_vmread_bitmap);
/*
* Allow direct access to the PC debug port (it is often used for I/O
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9d1b5cd4d34..20316c67b82 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -106,6 +106,8 @@ EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
static u32 tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
+static bool backwards_tsc_observed = false;
+
#define KVM_NR_SHARED_MSRS 16
struct kvm_shared_msrs_global {
@@ -280,7 +282,7 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);
-asmlinkage void kvm_spurious_fault(void)
+asmlinkage __visible void kvm_spurious_fault(void)
{
/* Fault while not rebooting. We want the trace. */
BUG();
@@ -652,6 +654,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
return 1;
+ if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP))
+ return 1;
+
if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
return 1;
@@ -680,6 +685,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
(!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
kvm_mmu_reset_context(vcpu);
+ if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
+ update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
+
if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
kvm_update_cpuid(vcpu);
@@ -1117,7 +1125,6 @@ static inline u64 get_kernel_ns(void)
{
struct timespec ts;
- WARN_ON(preemptible());
ktime_get_ts(&ts);
monotonic_to_bootbased(&ts);
return timespec_to_ns(&ts);
@@ -1481,7 +1488,8 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
&ka->master_kernel_ns,
&ka->master_cycle_now);
- ka->use_master_clock = host_tsc_clocksource & vcpus_matched;
+ ka->use_master_clock = host_tsc_clocksource && vcpus_matched
+ && !backwards_tsc_observed;
if (ka->use_master_clock)
atomic_set(&kvm_guest_has_master_clock, 1);
@@ -4164,7 +4172,8 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
| (write ? PFERR_WRITE_MASK : 0);
if (vcpu_match_mmio_gva(vcpu, gva)
- && !permission_fault(vcpu->arch.walk_mmu, vcpu->arch.access, access)) {
+ && !permission_fault(vcpu, vcpu->arch.walk_mmu,
+ vcpu->arch.access, access)) {
*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
(gva & (PAGE_SIZE - 1));
trace_vcpu_match_mmio(gva, *gpa, write, false);
@@ -6939,6 +6948,7 @@ int kvm_arch_hardware_enable(void *garbage)
*/
if (backwards_tsc) {
u64 delta_cyc = max_tsc - local_tsc;
+ backwards_tsc_observed = true;
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.tsc_offset_adjustment += delta_cyc;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index ad1fb5f5392..aae94132bc2 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -233,13 +233,13 @@ static void lguest_end_context_switch(struct task_struct *next)
* flags word contains all kind of stuff, but in practice Linux only cares
* about the interrupt flag. Our "save_flags()" just returns that.
*/
-asmlinkage unsigned long lguest_save_fl(void)
+asmlinkage __visible unsigned long lguest_save_fl(void)
{
return lguest_data.irq_enabled;
}
/* Interrupts go off... */
-asmlinkage void lguest_irq_disable(void)
+asmlinkage __visible void lguest_irq_disable(void)
{
lguest_data.irq_enabled = 0;
}
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index db9db446b71..43623739c7c 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -76,7 +76,7 @@ static inline int __flip_bit(u32 msr, u8 bit, bool set)
if (m1.q == m.q)
return 0;
- err = msr_write(msr, &m);
+ err = msr_write(msr, &m1);
if (err)
return err;
diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c
index a5449089cd9..9e6545f269e 100644
--- a/arch/x86/math-emu/errors.c
+++ b/arch/x86/math-emu/errors.c
@@ -302,7 +302,7 @@ static struct {
0x242 in div_Xsig.S
*/
-asmlinkage void FPU_exception(int n)
+asmlinkage __visible void FPU_exception(int n)
{
int i, int_type;
@@ -492,7 +492,7 @@ int real_2op_NaN(FPU_REG const *b, u_char tagb,
/* Invalid arith operation on Valid registers */
/* Returns < 0 if the exception is unmasked */
-asmlinkage int arith_invalid(int deststnr)
+asmlinkage __visible int arith_invalid(int deststnr)
{
EXCEPTION(EX_Invalid);
@@ -507,7 +507,7 @@ asmlinkage int arith_invalid(int deststnr)
}
/* Divide a finite number by zero */
-asmlinkage int FPU_divide_by_zero(int deststnr, u_char sign)
+asmlinkage __visible int FPU_divide_by_zero(int deststnr, u_char sign)
{
FPU_REG *dest = &st(deststnr);
int tag = TAG_Valid;
@@ -539,7 +539,7 @@ int set_precision_flag(int flags)
}
/* This may be called often, so keep it lean */
-asmlinkage void set_precision_flag_up(void)
+asmlinkage __visible void set_precision_flag_up(void)
{
if (control_word & CW_Precision)
partial_status |= (SW_Precision | SW_C1); /* The masked response */
@@ -548,7 +548,7 @@ asmlinkage void set_precision_flag_up(void)
}
/* This may be called often, so keep it lean */
-asmlinkage void set_precision_flag_down(void)
+asmlinkage __visible void set_precision_flag_down(void)
{
if (control_word & CW_Precision) { /* The masked response */
partial_status &= ~SW_C1;
@@ -557,7 +557,7 @@ asmlinkage void set_precision_flag_down(void)
EXCEPTION(EX_Precision);
}
-asmlinkage int denormal_operand(void)
+asmlinkage __visible int denormal_operand(void)
{
if (control_word & CW_Denormal) { /* The masked response */
partial_status |= SW_Denorm_Op;
@@ -568,7 +568,7 @@ asmlinkage int denormal_operand(void)
}
}
-asmlinkage int arith_overflow(FPU_REG *dest)
+asmlinkage __visible int arith_overflow(FPU_REG *dest)
{
int tag = TAG_Valid;
@@ -596,7 +596,7 @@ asmlinkage int arith_overflow(FPU_REG *dest)
}
-asmlinkage int arith_underflow(FPU_REG *dest)
+asmlinkage __visible int arith_underflow(FPU_REG *dest)
{
int tag = TAG_Valid;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index dc017735bb9..6d5663a599a 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -171,7 +171,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
memset(header, 0xcc, sz); /* fill whole space with int3 instructions */
header->pages = sz / PAGE_SIZE;
- hole = sz - (proglen + sizeof(*header));
+ hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header));
/* insert a random number of int3 instructions before BPF code */
*image_ptr = &header->image[prandom_u32() % hole];
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 81b506d5bef..52414211729 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -14,48 +14,92 @@
static const struct font_desc *font;
static u32 efi_x, efi_y;
+static void *efi_fb;
+static bool early_efi_keep;
-static __init void early_efi_clear_scanline(unsigned int y)
+/*
+ * efi earlyprintk need use early_ioremap to map the framebuffer.
+ * But early_ioremap is not usable for earlyprintk=efi,keep, ioremap should
+ * be used instead. ioremap will be available after paging_init() which is
+ * earlier than initcall callbacks. Thus adding this early initcall function
+ * early_efi_map_fb to map the whole efi framebuffer.
+ */
+static __init int early_efi_map_fb(void)
{
- unsigned long base, *dst;
- u16 len;
+ unsigned long base, size;
+
+ if (!early_efi_keep)
+ return 0;
base = boot_params.screen_info.lfb_base;
- len = boot_params.screen_info.lfb_linelength;
+ size = boot_params.screen_info.lfb_size;
+ efi_fb = ioremap(base, size);
+
+ return efi_fb ? 0 : -ENOMEM;
+}
+early_initcall(early_efi_map_fb);
+
+/*
+ * early_efi_map maps efi framebuffer region [start, start + len -1]
+ * In case earlyprintk=efi,keep we have the whole framebuffer mapped already
+ * so just return the offset efi_fb + start.
+ */
+static __init_refok void *early_efi_map(unsigned long start, unsigned long len)
+{
+ unsigned long base;
+
+ base = boot_params.screen_info.lfb_base;
+
+ if (efi_fb)
+ return (efi_fb + start);
+ else
+ return early_ioremap(base + start, len);
+}
- dst = early_ioremap(base + y*len, len);
+static __init_refok void early_efi_unmap(void *addr, unsigned long len)
+{
+ if (!efi_fb)
+ early_iounmap(addr, len);
+}
+
+static void early_efi_clear_scanline(unsigned int y)
+{
+ unsigned long *dst;
+ u16 len;
+
+ len = boot_params.screen_info.lfb_linelength;
+ dst = early_efi_map(y*len, len);
if (!dst)
return;
memset(dst, 0, len);
- early_iounmap(dst, len);
+ early_efi_unmap(dst, len);
}
-static __init void early_efi_scroll_up(void)
+static void early_efi_scroll_up(void)
{
- unsigned long base, *dst, *src;
+ unsigned long *dst, *src;
u16 len;
u32 i, height;
- base = boot_params.screen_info.lfb_base;
len = boot_params.screen_info.lfb_linelength;
height = boot_params.screen_info.lfb_height;
for (i = 0; i < height - font->height; i++) {
- dst = early_ioremap(base + i*len, len);
+ dst = early_efi_map(i*len, len);
if (!dst)
return;
- src = early_ioremap(base + (i + font->height) * len, len);
+ src = early_efi_map((i + font->height) * len, len);
if (!src) {
- early_iounmap(dst, len);
+ early_efi_unmap(dst, len);
return;
}
memmove(dst, src, len);
- early_iounmap(src, len);
- early_iounmap(dst, len);
+ early_efi_unmap(src, len);
+ early_efi_unmap(dst, len);
}
}
@@ -79,16 +123,14 @@ static void early_efi_write_char(u32 *dst, unsigned char c, unsigned int h)
}
}
-static __init void
+static void
early_efi_write(struct console *con, const char *str, unsigned int num)
{
struct screen_info *si;
- unsigned long base;
unsigned int len;
const char *s;
void *dst;
- base = boot_params.screen_info.lfb_base;
si = &boot_params.screen_info;
len = si->lfb_linelength;
@@ -109,7 +151,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
for (h = 0; h < font->height; h++) {
unsigned int n, x;
- dst = early_ioremap(base + (efi_y + h) * len, len);
+ dst = early_efi_map((efi_y + h) * len, len);
if (!dst)
return;
@@ -123,7 +165,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
s++;
}
- early_iounmap(dst, len);
+ early_efi_unmap(dst, len);
}
num -= count;
@@ -179,6 +221,9 @@ static __init int early_efi_setup(struct console *con, char *options)
for (i = 0; i < (yres - efi_y) / font->height; i++)
early_efi_scroll_up();
+ /* early_console_register will unset CON_BOOT in case ,keep */
+ if (!(con->flags & CON_BOOT))
+ early_efi_keep = true;
return 0;
}
diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c
index ff0174dda81..a9acde72d4e 100644
--- a/arch/x86/platform/olpc/olpc-xo1-pm.c
+++ b/arch/x86/platform/olpc/olpc-xo1-pm.c
@@ -75,7 +75,7 @@ static int xo1_power_state_enter(suspend_state_t pm_state)
return 0;
}
-asmlinkage int xo1_do_sleep(u8 sleep_state)
+asmlinkage __visible int xo1_do_sleep(u8 sleep_state)
{
void *pgd_addr = __va(read_cr3());
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 304fca20d96..35e2bb6c0f3 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -23,7 +23,7 @@
extern __visible const void __nosave_begin, __nosave_end;
/* Defined in hibernate_asm_64.S */
-extern asmlinkage int restore_image(void);
+extern asmlinkage __visible int restore_image(void);
/*
* Address to jump to in the last phase of restore in order to get to the image
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile
index f325af26107..3323c274524 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/syscalls/Makefile
@@ -54,5 +54,7 @@ syshdr-$(CONFIG_X86_64) += syscalls_64.h
targets += $(uapisyshdr-y) $(syshdr-y)
+PHONY += all
all: $(addprefix $(uapi)/,$(uapisyshdr-y))
all: $(addprefix $(out)/,$(syshdr-y))
+ @:
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 96bc506ac6d..d6b86792161 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -359,3 +359,4 @@
350 i386 finit_module sys_finit_module
351 i386 sched_setattr sys_sched_setattr
352 i386 sched_getattr sys_sched_getattr
+353 i386 renameat2 sys_renameat2
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index e8120346903..604a37efd4d 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -40,4 +40,6 @@ $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/ina
HOST_EXTRACFLAGS += -I$(srctree)/tools/include
hostprogs-y += relocs
relocs-objs := relocs_32.o relocs_64.o relocs_common.o
+PHONY += relocs
relocs: $(obj)/relocs
+ @:
diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S
index 2e263f367b1..9df017ab228 100644
--- a/arch/x86/vdso/vdso-layout.lds.S
+++ b/arch/x86/vdso/vdso-layout.lds.S
@@ -9,12 +9,9 @@ SECTIONS
#ifdef BUILD_VDSO32
#include <asm/vdso32.h>
- .hpet_sect : {
- hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE);
- } :text :hpet_sect
+ hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE);
- .vvar_sect : {
- vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE);
+ vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE);
/* Place all vvars at the offsets in asm/vvar.h. */
#define EMIT_VVAR(name, offset) vvar_ ## name = vvar + offset;
@@ -22,7 +19,6 @@ SECTIONS
#include <asm/vvar.h>
#undef __VVAR_KERNEL_LDS
#undef EMIT_VVAR
- } :text :vvar_sect
#endif
. = SIZEOF_HEADERS;
@@ -61,7 +57,12 @@ SECTIONS
*/
. = ALIGN(0x100);
- .text : { *(.text*) } :text =0x90909090
+ .text : { *(.text*) } :text =0x90909090,
+
+ /*
+ * The comma above works around a bug in gold:
+ * https://sourceware.org/bugzilla/show_bug.cgi?id=16804
+ */
/DISCARD/ : {
*(.discard)
@@ -84,8 +85,4 @@ PHDRS
dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
note PT_NOTE FLAGS(4); /* PF_R */
eh_frame_hdr PT_GNU_EH_FRAME;
-#ifdef BUILD_VDSO32
- vvar_sect PT_NULL FLAGS(4); /* PF_R */
- hpet_sect PT_NULL FLAGS(4); /* PF_R */
-#endif
}
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 00348980a3a..e1f220e3ca6 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -39,6 +39,7 @@
#ifdef CONFIG_X86_64
#define vdso_enabled sysctl_vsyscall32
#define arch_setup_additional_pages syscall32_setup_pages
+extern int sysctl_ldt16;
#endif
/*
@@ -249,6 +250,13 @@ static struct ctl_table abi_table2[] = {
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "ldt16",
+ .data = &sysctl_ldt16,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{}
};
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 201d09a7c46..c34bfc4bbe7 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1515,7 +1515,7 @@ static void __init xen_pvh_early_guest_init(void)
}
/* First C function to be called on Xen boot */
-asmlinkage void __init xen_start_kernel(void)
+asmlinkage __visible void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
int rc;
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 08f763de26f..a1207cb6472 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -23,7 +23,7 @@ void xen_force_evtchn_callback(void)
(void)HYPERVISOR_xen_version(0, NULL);
}
-asmlinkage unsigned long xen_save_fl(void)
+asmlinkage __visible unsigned long xen_save_fl(void)
{
struct vcpu_info *vcpu;
unsigned long flags;
@@ -63,7 +63,7 @@ __visible void xen_restore_fl(unsigned long flags)
}
PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
-asmlinkage void xen_irq_disable(void)
+asmlinkage __visible void xen_irq_disable(void)
{
/* There's a one instruction preempt window here. We need to
make sure we're don't switch CPUs between getting the vcpu
@@ -74,7 +74,7 @@ asmlinkage void xen_irq_disable(void)
}
PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable);
-asmlinkage void xen_irq_enable(void)
+asmlinkage __visible void xen_irq_enable(void)
{
struct vcpu_info *vcpu;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index a18eadd8bb4..7005974c3ff 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -441,10 +441,11 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle)
irq_ctx_init(cpu);
#else
clear_tsk_thread_flag(idle, TIF_FORK);
+#endif
per_cpu(kernel_stack, cpu) =
(unsigned long)task_stack_page(idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
-#endif
+
xen_setup_runstate_info(cpu);
xen_setup_timer(cpu);
xen_init_lock_cpu(cpu);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 4d3acc34a99..0ba5f3b967f 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -274,7 +274,7 @@ void __init xen_init_spinlocks(void)
printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
return;
}
-
+ printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
pv_lock_ops.unlock_kick = xen_unlock_kick;
}
@@ -290,6 +290,9 @@ static __init int xen_init_spinlocks_jump(void)
if (!xen_pvspin)
return 0;
+ if (!xen_domain())
+ return 0;
+
static_key_slow_inc(&paravirt_ticketlocks_enabled);
return 0;
}
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index 33ca6e42a4c..fd92a64d748 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -75,6 +75,17 @@ ENDPROC(xen_sysexit)
* stack state in whatever form its in, we keep things simple by only
* using a single register which is pushed/popped on the stack.
*/
+
+.macro POP_FS
+1:
+ popw %fs
+.pushsection .fixup, "ax"
+2: movw $0, (%esp)
+ jmp 1b
+.popsection
+ _ASM_EXTABLE(1b,2b)
+.endm
+
ENTRY(xen_iret)
/* test eflags for special cases */
testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp)
@@ -83,15 +94,13 @@ ENTRY(xen_iret)
push %eax
ESP_OFFSET=4 # bytes pushed onto stack
- /*
- * Store vcpu_info pointer for easy access. Do it this way to
- * avoid having to reload %fs
- */
+ /* Store vcpu_info pointer for easy access */
#ifdef CONFIG_SMP
- GET_THREAD_INFO(%eax)
- movl %ss:TI_cpu(%eax), %eax
- movl %ss:__per_cpu_offset(,%eax,4), %eax
- mov %ss:xen_vcpu(%eax), %eax
+ pushw %fs
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax, %fs
+ movl %fs:xen_vcpu, %eax
+ POP_FS
#else
movl %ss:xen_vcpu, %eax
#endif