summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/include/asm/mce.h8
-rw-r--r--arch/x86/include/asm/perf_event.h11
-rw-r--r--arch/x86/kernel/acpi/sleep.c4
-rw-r--r--arch/x86/kernel/acpi/sleep.h2
-rw-r--r--arch/x86/kernel/acpi/wakeup_32.S4
-rw-r--r--arch/x86/kernel/acpi/wakeup_64.S4
-rw-r--r--arch/x86/kernel/alternative.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c7
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c43
-rw-r--r--arch/x86/kernel/cpu/perf_event.c89
-rw-r--r--arch/x86/kernel/cpu/perf_event.h20
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c4
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c7
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h2
-rw-r--r--arch/x86/kernel/irq.c1
-rw-r--r--arch/x86/kernel/kdebugfs.c6
-rw-r--r--arch/x86/kvm/i8259.c17
-rw-r--r--arch/x86/kvm/vmx.c20
-rw-r--r--arch/x86/kvm/x86.c4
-rw-r--r--arch/x86/mm/srat.c15
-rw-r--r--arch/x86/syscalls/syscall_64.tbl2
-rw-r--r--arch/x86/xen/p2m.c5
24 files changed, 226 insertions, 57 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ba2657c4921..8ec3a1aa4ab 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1527,7 +1527,7 @@ config SECCOMP
If unsure, say Y. Only embedded should say N here.
config CC_STACKPROTECTOR
- bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
+ bool "Enable -fstack-protector buffer overflow detection"
---help---
This option turns on the -fstack-protector GCC feature. This
feature puts, at the beginning of functions, a canary value on
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 441520e4174..a3ac52b29cb 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -33,6 +33,14 @@
#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */
#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
+#define MCACOD 0xffff /* MCA Error Code */
+
+/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
+#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
+#define MCACOD_SCRUBMSK 0xfff0
+#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
+#define MCACOD_DATA 0x0134 /* Data Load */
+#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
/* MCi_MISC register defines */
#define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index dab39350e51..cb4e43bce98 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -196,11 +196,16 @@ static inline u32 get_ibs_caps(void) { return 0; }
extern void perf_events_lapic_init(void);
/*
- * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
- * This flag is otherwise unused and ABI specified to be 0, so nobody should
- * care what we do with it.
+ * Abuse bits {3,5} of the cpu eflags register. These flags are otherwise
+ * unused and ABI specified to be 0, so nobody should care what we do with
+ * them.
+ *
+ * EXACT - the IP points to the exact instruction that triggered the
+ * event (HW bugs exempt).
+ * VM - original X86_VM_MASK; see set_linear_ip().
*/
#define PERF_EFLAGS_EXACT (1UL << 3)
+#define PERF_EFLAGS_VM (1UL << 5)
struct pt_regs;
extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 95bf99de905..1b8e5a03d94 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -25,10 +25,6 @@ unsigned long acpi_realmode_flags;
static char temp_stack[4096];
#endif
-asmlinkage void acpi_enter_s3(void)
-{
- acpi_enter_sleep_state(3, wake_sleep_flags);
-}
/**
* acpi_suspend_lowlevel - save kernel state
*
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index 5653a5791ec..67f59f8c695 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -2,7 +2,6 @@
* Variables and functions used by the code in sleep.c
*/
-#include <linux/linkage.h>
#include <asm/realmode.h>
extern unsigned long saved_video_mode;
@@ -11,7 +10,6 @@ extern long saved_magic;
extern int wakeup_pmode_return;
extern u8 wake_sleep_flags;
-extern asmlinkage void acpi_enter_s3(void);
extern unsigned long acpi_copy_wakeup_routine(unsigned long);
extern void wakeup_long64(void);
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 72610839f03..13ab720573e 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -74,7 +74,9 @@ restore_registers:
ENTRY(do_suspend_lowlevel)
call save_processor_state
call save_registers
- call acpi_enter_s3
+ pushl $3
+ call acpi_enter_sleep_state
+ addl $4, %esp
# In case of S3 failure, we'll emerge here. Jump
# to ret_point to recover
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 014d1d28c39..8ea5164cbd0 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -71,7 +71,9 @@ ENTRY(do_suspend_lowlevel)
movq %rsi, saved_rsi
addq $8, %rsp
- call acpi_enter_s3
+ movl $3, %edi
+ xorl %eax, %eax
+ call acpi_enter_sleep_state
/* in case something went wrong, restore the machine status and go on */
jmp resume_point
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 931280ff829..afb7ff79a29 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -224,7 +224,7 @@ void __init arch_init_ideal_nops(void)
ideal_nops = intel_nops;
#endif
}
-
+ break;
default:
#ifdef CONFIG_X86_64
ideal_nops = k8_nops;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 406eee78468..a6c64aaddf9 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1204,7 +1204,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
BUG_ON(!cfg->vector);
vector = cfg->vector;
- for_each_cpu(cpu, cfg->domain)
+ for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
per_cpu(vector_irq, cpu)[vector] = -1;
cfg->vector = 0;
@@ -1212,7 +1212,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
if (likely(!cfg->move_in_progress))
return;
- for_each_cpu(cpu, cfg->old_domain) {
+ for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 413c2ced887..13017626f9a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -55,13 +55,6 @@ static struct severity {
#define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S)
#define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR)
#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV)
-#define MCACOD 0xffff
-/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
-#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK 0xfff0
-#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
-#define MCACOD_DATA 0x0134 /* Data Load */
-#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
MCESEV(
NO, "Invalid",
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 5e095f873e3..292d0258311 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -103,6 +103,8 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
static DEFINE_PER_CPU(struct work_struct, mce_work);
+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.
@@ -650,14 +652,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
*/
-static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp)
+static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
+ struct pt_regs *regs)
{
int i, ret = 0;
for (i = 0; i < banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
- if (m->status & MCI_STATUS_VAL)
+ if (m->status & MCI_STATUS_VAL) {
__set_bit(i, validp);
+ if (quirk_no_way_out)
+ quirk_no_way_out(i, m, regs);
+ }
if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY)
ret = 1;
}
@@ -1040,7 +1046,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
*final = m;
memset(valid_banks, 0, sizeof(valid_banks));
- no_way_out = mce_no_way_out(&m, &msg, valid_banks);
+ no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs);
barrier();
@@ -1418,6 +1424,34 @@ static void __mcheck_cpu_init_generic(void)
}
}
+/*
+ * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and
+ * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM
+ * Vol 3B Table 15-20). But this confuses both the code that determines
+ * whether the machine check occurred in kernel or user mode, and also
+ * the severity assessment code. Pretend that EIPV was set, and take the
+ * ip/cs values from the pt_regs that mce_gather_info() ignored earlier.
+ */
+static void quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
+{
+ if (bank != 0)
+ return;
+ if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0)
+ return;
+ if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC|
+ MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV|
+ MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR|
+ MCACOD)) !=
+ (MCI_STATUS_UC|MCI_STATUS_EN|
+ MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S|
+ MCI_STATUS_AR|MCACOD_INSTR))
+ return;
+
+ m->mcgstatus |= MCG_STATUS_EIPV;
+ m->ip = regs->ip;
+ m->cs = regs->cs;
+}
+
/* Add per CPU specific workarounds here */
static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
{
@@ -1515,6 +1549,9 @@ static int __cpuinit __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
*/
if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
mce_bootlog = 0;
+
+ if (c->x86 == 6 && c->x86_model == 45)
+ quirk_no_way_out = quirk_sandybridge_ifu;
}
if (monarch_timeout < 0)
monarch_timeout = 0;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 29557aa06dd..915b876edd1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -32,6 +32,8 @@
#include <asm/smp.h>
#include <asm/alternative.h>
#include <asm/timer.h>
+#include <asm/desc.h>
+#include <asm/ldt.h>
#include "perf_event.h"
@@ -1738,6 +1740,29 @@ valid_user_frame(const void __user *fp, unsigned long size)
return (__range_not_ok(fp, size, TASK_SIZE) == 0);
}
+static unsigned long get_segment_base(unsigned int segment)
+{
+ struct desc_struct *desc;
+ int idx = segment >> 3;
+
+ if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+ if (idx > LDT_ENTRIES)
+ return 0;
+
+ if (idx > current->active_mm->context.size)
+ return 0;
+
+ desc = current->active_mm->context.ldt;
+ } else {
+ if (idx > GDT_ENTRIES)
+ return 0;
+
+ desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+ }
+
+ return get_desc_base(desc + idx);
+}
+
#ifdef CONFIG_COMPAT
#include <asm/compat.h>
@@ -1746,13 +1771,17 @@ static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
/* 32-bit process in 64-bit kernel. */
+ unsigned long ss_base, cs_base;
struct stack_frame_ia32 frame;
const void __user *fp;
if (!test_thread_flag(TIF_IA32))
return 0;
- fp = compat_ptr(regs->bp);
+ cs_base = get_segment_base(regs->cs);
+ ss_base = get_segment_base(regs->ss);
+
+ fp = compat_ptr(ss_base + regs->bp);
while (entry->nr < PERF_MAX_STACK_DEPTH) {
unsigned long bytes;
frame.next_frame = 0;
@@ -1765,8 +1794,8 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
if (!valid_user_frame(fp, sizeof(frame)))
break;
- perf_callchain_store(entry, frame.return_address);
- fp = compat_ptr(frame.next_frame);
+ perf_callchain_store(entry, cs_base + frame.return_address);
+ fp = compat_ptr(ss_base + frame.next_frame);
}
return 1;
}
@@ -1789,6 +1818,12 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
return;
}
+ /*
+ * We don't know what to do with VM86 stacks.. ignore them for now.
+ */
+ if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
+ return;
+
fp = (void __user *)regs->bp;
perf_callchain_store(entry, regs->ip);
@@ -1816,16 +1851,50 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
}
}
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+/*
+ * Deal with code segment offsets for the various execution modes:
+ *
+ * VM86 - the good olde 16 bit days, where the linear address is
+ * 20 bits and we use regs->ip + 0x10 * regs->cs.
+ *
+ * IA32 - Where we need to look at GDT/LDT segment descriptor tables
+ * to figure out what the 32bit base address is.
+ *
+ * X32 - has TIF_X32 set, but is running in x86_64
+ *
+ * X86_64 - CS,DS,SS,ES are all zero based.
+ */
+static unsigned long code_segment_base(struct pt_regs *regs)
{
- unsigned long ip;
+ /*
+ * If we are in VM86 mode, add the segment offset to convert to a
+ * linear address.
+ */
+ if (regs->flags & X86_VM_MASK)
+ return 0x10 * regs->cs;
+
+ /*
+ * For IA32 we look at the GDT/LDT segment base to convert the
+ * effective IP to a linear address.
+ */
+#ifdef CONFIG_X86_32
+ if (user_mode(regs) && regs->cs != __USER_CS)
+ return get_segment_base(regs->cs);
+#else
+ if (test_thread_flag(TIF_IA32)) {
+ if (user_mode(regs) && regs->cs != __USER32_CS)
+ return get_segment_base(regs->cs);
+ }
+#endif
+ return 0;
+}
+unsigned long perf_instruction_pointer(struct pt_regs *regs)
+{
if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
- ip = perf_guest_cbs->get_guest_ip();
- else
- ip = instruction_pointer(regs);
+ return perf_guest_cbs->get_guest_ip();
- return ip;
+ return regs->ip + code_segment_base(regs);
}
unsigned long perf_misc_flags(struct pt_regs *regs)
@@ -1838,7 +1907,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
else
misc |= PERF_RECORD_MISC_GUEST_KERNEL;
} else {
- if (!kernel_ip(regs->ip))
+ if (user_mode(regs))
misc |= PERF_RECORD_MISC_USER;
else
misc |= PERF_RECORD_MISC_KERNEL;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 821d53b696d..6605a81ba33 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -516,6 +516,26 @@ static inline bool kernel_ip(unsigned long ip)
#endif
}
+/*
+ * Not all PMUs provide the right context information to place the reported IP
+ * into full context. Specifically segment registers are typically not
+ * supplied.
+ *
+ * Assuming the address is a linear address (it is for IBS), we fake the CS and
+ * vm86 mode using the known zero-based code segment and 'fix up' the registers
+ * to reflect this.
+ *
+ * Intel PEBS/LBR appear to typically provide the effective address, nothing
+ * much we can do about that but pray and treat it like a linear address.
+ */
+static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
+{
+ regs->cs = kernel_ip(ip) ? __KERNEL_CS : __USER_CS;
+ if (regs->flags & X86_VM_MASK)
+ regs->flags ^= (PERF_EFLAGS_VM | X86_VM_MASK);
+ regs->ip = ip;
+}
+
#ifdef CONFIG_CPU_SUP_AMD
int amd_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index da9bcdcd985..7bfb5bec863 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -13,6 +13,8 @@
#include <asm/apic.h>
+#include "perf_event.h"
+
static u32 ibs_caps;
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
@@ -536,7 +538,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
regs.flags &= ~PERF_EFLAGS_EXACT;
} else {
- instruction_pointer_set(&regs, ibs_data.regs[1]);
+ set_linear_ip(&regs, ibs_data.regs[1]);
regs.flags |= PERF_EFLAGS_EXACT;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 629ae0b7ad9..e38d97bf425 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -499,7 +499,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
* We sampled a branch insn, rewind using the LBR stack
*/
if (ip == to) {
- regs->ip = from;
+ set_linear_ip(regs, from);
return 1;
}
@@ -529,7 +529,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
} while (to < ip);
if (to == ip) {
- regs->ip = old_to;
+ set_linear_ip(regs, old_to);
return 1;
}
@@ -569,7 +569,8 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
* A possible PERF_SAMPLE_REGS will have to transfer all regs.
*/
regs = *iregs;
- regs.ip = pebs->ip;
+ regs.flags = pebs->flags;
+ set_linear_ip(&regs, pebs->ip);
regs.bp = pebs->bp;
regs.sp = pebs->sp;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index f3851892e07..c9e5dc56630 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -5,7 +5,7 @@
#include "perf_event.h"
#define UNCORE_PMU_NAME_LEN 32
-#define UNCORE_PMU_HRTIMER_INTERVAL (60 * NSEC_PER_SEC)
+#define UNCORE_PMU_HRTIMER_INTERVAL (60LL * NSEC_PER_SEC)
#define UNCORE_FIXED_EVENT 0xff
#define UNCORE_PMC_IDX_MAX_GENERIC 8
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 1f5f1d5d2a0..7ad683d7864 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -328,6 +328,7 @@ void fixup_irqs(void)
chip->irq_retrigger(data);
raw_spin_unlock(&desc->lock);
}
+ __this_cpu_write(vector_irq[vector], -1);
}
}
#endif
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 1d5d31ea686..dc1404bf8e4 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -107,7 +107,7 @@ static int __init create_setup_data_nodes(struct dentry *parent)
{
struct setup_data_node *node;
struct setup_data *data;
- int error = -ENOMEM;
+ int error;
struct dentry *d;
struct page *pg;
u64 pa_data;
@@ -121,8 +121,10 @@ static int __init create_setup_data_nodes(struct dentry *parent)
while (pa_data) {
node = kmalloc(sizeof(*node), GFP_KERNEL);
- if (!node)
+ if (!node) {
+ error = -ENOMEM;
goto err_dir;
+ }
pg = pfn_to_page((pa_data+sizeof(*data)-1) >> PAGE_SHIFT);
if (PageHighMem(pg)) {
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 1df8fb9e1d5..e498b18f010 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -316,6 +316,11 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
addr &= 1;
if (addr == 0) {
if (val & 0x10) {
+ u8 edge_irr = s->irr & ~s->elcr;
+ int i;
+ bool found;
+ struct kvm_vcpu *vcpu;
+
s->init4 = val & 1;
s->last_irr = 0;
s->irr &= s->elcr;
@@ -333,6 +338,18 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
if (val & 0x08)
pr_pic_unimpl(
"level sensitive irq not supported");
+
+ kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
+ if (kvm_apic_accept_pic_intr(vcpu)) {
+ found = true;
+ break;
+ }
+
+
+ if (found)
+ for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
+ if (edge_irr & (1 << irq))
+ pic_clear_isr(s, irq);
} else if (val & 0x08) {
if (val & 0x04)
s->poll = 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c39b60707e0..c00f03de1b7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1488,13 +1488,6 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
loadsegment(ds, vmx->host_state.ds_sel);
loadsegment(es, vmx->host_state.es_sel);
}
-#else
- /*
- * The sysexit path does not restore ds/es, so we must set them to
- * a reasonable value ourselves.
- */
- loadsegment(ds, __USER_DS);
- loadsegment(es, __USER_DS);
#endif
reload_tss();
#ifdef CONFIG_X86_64
@@ -6370,6 +6363,19 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
#endif
);
+#ifndef CONFIG_X86_64
+ /*
+ * The sysexit path does not restore ds/es, so we must set them to
+ * a reasonable value ourselves.
+ *
+ * We can't defer this to vmx_load_host_state() since that function
+ * may be executed in interrupt context, which saves and restore segments
+ * around it, nullifying its effect.
+ */
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+#endif
+
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
| (1 << VCPU_EXREG_RFLAGS)
| (1 << VCPU_EXREG_CPL)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 59b59508ff0..42bce48f692 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -925,6 +925,10 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
*/
getboottime(&boot);
+ if (kvm->arch.kvmclock_offset) {
+ struct timespec ts = ns_to_timespec(kvm->arch.kvmclock_offset);
+ boot = timespec_sub(boot, ts);
+ }
wc.sec = boot.tv_sec;
wc.nsec = boot.tv_nsec;
wc.version = version;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 4599c3e8bcb..4ddf497ca65 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -142,23 +142,23 @@ static inline int save_add_info(void) {return 0;}
#endif
/* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
-void __init
+int __init
acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
{
u64 start, end;
int node, pxm;
if (srat_disabled())
- return;
+ return -1;
if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) {
bad_srat();
- return;
+ return -1;
}
if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
- return;
+ return -1;
if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
- return;
+ return -1;
start = ma->base_address;
end = start + ma->length;
pxm = ma->proximity_domain;
@@ -168,12 +168,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains.\n");
bad_srat();
- return;
+ return -1;
}
if (numa_add_memblk(node, start, end) < 0) {
bad_srat();
- return;
+ return -1;
}
node_set(node, numa_nodes_parsed);
@@ -181,6 +181,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1);
+ return 0;
}
void __init acpi_numa_arch_fixup(void) {}
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 51171aeff0d..29aed7ac2c0 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -318,7 +318,7 @@
309 common getcpu sys_getcpu
310 64 process_vm_readv sys_process_vm_readv
311 64 process_vm_writev sys_process_vm_writev
-312 64 kcmp sys_kcmp
+312 common kcmp sys_kcmp
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 64effdc6da9..b2e91d40a4c 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -194,6 +194,11 @@ RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID
* boundary violation will require three middle nodes. */
RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
+/* When we populate back during bootup, the amount of pages can vary. The
+ * max we have is seen is 395979, but that does not mean it can't be more.
+ * But some machines can have 3GB I/O holes even. So lets reserve enough
+ * for 4GB of I/O and E820 holes. */
+RESERVE_BRK(p2m_populated, PMD_SIZE * 4);
static inline unsigned p2m_top_index(unsigned long pfn)
{
BUG_ON(pfn >= MAX_P2M_PFN);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-13 09:09:00 +0000