summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm/boot/dts/imx35.dtsi8
-rw-r--r--arch/arm/boot/dts/k2e-clocks.dtsi5
-rw-r--r--arch/arm/boot/dts/k2hk-clocks.dtsi5
-rw-r--r--arch/arm/boot/dts/k2l-clocks.dtsi5
-rw-r--r--arch/arm/mach-omap2/omap_hwmod.c24
-rw-r--r--arch/arm64/kernel/signal32.c5
-rw-r--r--arch/mips/ath79/setup.c1
-rw-r--r--arch/mips/include/asm/mach-bcm63xx/dma-coherence.h10
-rw-r--r--arch/mips/include/asm/pgtable.h31
-rw-r--r--arch/mips/include/asm/stackframe.h25
-rw-r--r--arch/mips/kernel/mips-mt-fpaff.c5
-rw-r--r--arch/mips/kernel/relocate_kernel.S8
-rw-r--r--arch/mips/kernel/signal32.c2
-rw-r--r--arch/mips/kernel/traps.c13
-rw-r--r--arch/mips/kernel/unaligned.c2
-rw-r--r--arch/mips/lantiq/irq.c1
-rw-r--r--arch/mips/mti-malta/malta-time.c16
-rw-r--r--arch/mips/mti-sead3/sead3-time.c1
-rw-r--r--arch/mips/pistachio/time.c1
-rw-r--r--arch/mips/ralink/irq.c1
-rw-r--r--arch/powerpc/kernel/signal_32.c2
-rw-r--r--arch/sparc/include/asm/visasm.h16
-rw-r--r--arch/sparc/lib/NG4memcpy.S5
-rw-r--r--arch/sparc/lib/VISsave.S67
-rw-r--r--arch/sparc/lib/ksyms.c4
-rw-r--r--arch/tile/kernel/compat_signal.c2
-rw-r--r--arch/x86/kernel/entry_64.S286
-rw-r--r--arch/x86/kernel/nmi.c123
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/xen/enlighten.c40
30 files changed, 407 insertions, 309 deletions
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index 466bcb704..d520390cf 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -286,8 +286,8 @@
can1: can@53fe4000 {
compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
reg = <0x53fe4000 0x1000>;
- clocks = <&clks 33>;
- clock-names = "ipg";
+ clocks = <&clks 33>, <&clks 33>;
+ clock-names = "ipg", "per";
interrupts = <43>;
status = "disabled";
};
@@ -295,8 +295,8 @@
can2: can@53fe8000 {
compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
reg = <0x53fe8000 0x1000>;
- clocks = <&clks 34>;
- clock-names = "ipg";
+ clocks = <&clks 34>, <&clks 34>;
+ clock-names = "ipg", "per";
interrupts = <44>;
status = "disabled";
};
diff --git a/arch/arm/boot/dts/k2e-clocks.dtsi b/arch/arm/boot/dts/k2e-clocks.dtsi
index 4773d6af6..d56d68fe7 100644
--- a/arch/arm/boot/dts/k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/k2e-clocks.dtsi
@@ -13,9 +13,8 @@ clocks {
#clock-cells = <0>;
compatible = "ti,keystone,main-pll-clock";
clocks = <&refclksys>;
- reg = <0x02620350 4>, <0x02310110 4>;
- reg-names = "control", "multiplier";
- fixed-postdiv = <2>;
+ reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+ reg-names = "control", "multiplier", "post-divider";
};
papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2hk-clocks.dtsi b/arch/arm/boot/dts/k2hk-clocks.dtsi
index d5adee3c0..af9b71905 100644
--- a/arch/arm/boot/dts/k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/k2hk-clocks.dtsi
@@ -22,9 +22,8 @@ clocks {
#clock-cells = <0>;
compatible = "ti,keystone,main-pll-clock";
clocks = <&refclksys>;
- reg = <0x02620350 4>, <0x02310110 4>;
- reg-names = "control", "multiplier";
- fixed-postdiv = <2>;
+ reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+ reg-names = "control", "multiplier", "post-divider";
};
papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2l-clocks.dtsi b/arch/arm/boot/dts/k2l-clocks.dtsi
index eb1e3e29f..ef8464bb1 100644
--- a/arch/arm/boot/dts/k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/k2l-clocks.dtsi
@@ -22,9 +22,8 @@ clocks {
#clock-cells = <0>;
compatible = "ti,keystone,main-pll-clock";
clocks = <&refclksys>;
- reg = <0x02620350 4>, <0x02310110 4>;
- reg-names = "control", "multiplier";
- fixed-postdiv = <2>;
+ reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+ reg-names = "control", "multiplier", "post-divider";
};
papllclk: papllclk@2620358 {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 752969ff9..5286e7773 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2373,6 +2373,9 @@ static int of_dev_hwmod_lookup(struct device_node *np,
* registers. This address is needed early so the OCP registers that
* are part of the device's address space can be ioremapped properly.
*
+ * If SYSC access is not needed, the registers will not be remapped
+ * and non-availability of MPU access is not treated as an error.
+ *
* Returns 0 on success, -EINVAL if an invalid hwmod is passed, and
* -ENXIO on absent or invalid register target address space.
*/
@@ -2387,6 +2390,11 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data,
_save_mpu_port_index(oh);
+ /* if we don't need sysc access we don't need to ioremap */
+ if (!oh->class->sysc)
+ return 0;
+
+ /* we can't continue without MPU PORT if we need sysc access */
if (oh->_int_flags & _HWMOD_NO_MPU_PORT)
return -ENXIO;
@@ -2396,8 +2404,10 @@ static int __init _init_mpu_rt_base(struct omap_hwmod *oh, void *data,
oh->name);
/* Extract the IO space from device tree blob */
- if (!np)
+ if (!np) {
+ pr_err("omap_hwmod: %s: no dt node\n", oh->name);
return -ENXIO;
+ }
va_start = of_iomap(np, index + oh->mpu_rt_idx);
} else {
@@ -2456,13 +2466,11 @@ static int __init _init(struct omap_hwmod *oh, void *data)
oh->name, np->name);
}
- if (oh->class->sysc) {
- r = _init_mpu_rt_base(oh, NULL, index, np);
- if (r < 0) {
- WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
- oh->name);
- return 0;
- }
+ r = _init_mpu_rt_base(oh, NULL, index, np);
+ if (r < 0) {
+ WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
+ oh->name);
+ return 0;
}
r = _init_clocks(oh, NULL);
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index d26fcd4cd..c0cff3410 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -168,7 +168,8 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
* Other callers might not initialize the si_lsb field,
* so check explicitely for the right codes here.
*/
- if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+ if (from->si_signo == SIGBUS &&
+ (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
#endif
break;
@@ -201,8 +202,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
{
- memset(to, 0, sizeof *to);
-
if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
copy_from_user(to->_sifields._pad,
from->_sifields._pad, SI_PAD_SIZE))
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 7fc8397d1..fd2a36a79 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -186,6 +186,7 @@ int get_c0_perfcount_int(void)
{
return ATH79_MISC_IRQ(5);
}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
unsigned int get_c0_compare_int(void)
{
diff --git a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h b/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
deleted file mode 100644
index 11d3b572b..000000000
--- a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-
-#define plat_post_dma_flush bmips_post_dma_flush
-
-#include <asm/mach-generic/dma-coherence.h>
-
-#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 819af9d05..70f6e7f07 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -182,8 +182,39 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
* Make sure the buddy is global too (if it's !none,
* it better already be global)
*/
+#ifdef CONFIG_SMP
+ /*
+ * For SMP, multiple CPUs can race, so we need to do
+ * this atomically.
+ */
+#ifdef CONFIG_64BIT
+#define LL_INSN "lld"
+#define SC_INSN "scd"
+#else /* CONFIG_32BIT */
+#define LL_INSN "ll"
+#define SC_INSN "sc"
+#endif
+ unsigned long page_global = _PAGE_GLOBAL;
+ unsigned long tmp;
+
+ __asm__ __volatile__ (
+ " .set push\n"
+ " .set noreorder\n"
+ "1: " LL_INSN " %[tmp], %[buddy]\n"
+ " bnez %[tmp], 2f\n"
+ " or %[tmp], %[tmp], %[global]\n"
+ " " SC_INSN " %[tmp], %[buddy]\n"
+ " beqz %[tmp], 1b\n"
+ " nop\n"
+ "2:\n"
+ " .set pop"
+ : [buddy] "+m" (buddy->pte),
+ [tmp] "=&r" (tmp)
+ : [global] "r" (page_global));
+#else /* !CONFIG_SMP */
if (pte_none(*buddy))
pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
}
#endif
}
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index 28d6d9364..a71da5768 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -152,6 +152,31 @@
.set noreorder
bltz k0, 8f
move k1, sp
+#ifdef CONFIG_EVA
+ /*
+ * Flush interAptiv's Return Prediction Stack (RPS) by writing
+ * EntryHi. Toggling Config7.RPS is slower and less portable.
+ *
+ * The RPS isn't automatically flushed when exceptions are
+ * taken, which can result in kernel mode speculative accesses
+ * to user addresses if the RPS mispredicts. That's harmless
+ * when user and kernel share the same address space, but with
+ * EVA the same user segments may be unmapped to kernel mode,
+ * even containing sensitive MMIO regions or invalid memory.
+ *
+ * This can happen when the kernel sets the return address to
+ * ret_from_* and jr's to the exception handler, which looks
+ * more like a tail call than a function call. If nested calls
+ * don't evict the last user address in the RPS, it will
+ * mispredict the return and fetch from a user controlled
+ * address into the icache.
+ *
+ * More recent EVA-capable cores with MAAR to restrict
+ * speculative accesses aren't affected.
+ */
+ MFC0 k0, CP0_ENTRYHI
+ MTC0 k0, CP0_ENTRYHI
+#endif
.set reorder
/* Called from user mode, new stack. */
get_saved_sp
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 3e4491aa6..789d7bf4f 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -154,7 +154,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
unsigned long __user *user_mask_ptr)
{
unsigned int real_len;
- cpumask_t mask;
+ cpumask_t allowed, mask;
int retval;
struct task_struct *p;
@@ -173,7 +173,8 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
if (retval)
goto out_unlock;
- cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
+ cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+ cpumask_and(&mask, &allowed, cpu_active_mask);
out_unlock:
read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 74bab9ddd..c6bbf2165 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -24,7 +24,7 @@ LEAF(relocate_new_kernel)
process_entry:
PTR_L s2, (s0)
- PTR_ADD s0, s0, SZREG
+ PTR_ADDIU s0, s0, SZREG
/*
* In case of a kdump/crash kernel, the indirection page is not
@@ -61,9 +61,9 @@ copy_word:
/* copy page word by word */
REG_L s5, (s2)
REG_S s5, (s4)
- PTR_ADD s4, s4, SZREG
- PTR_ADD s2, s2, SZREG
- LONG_SUB s6, s6, 1
+ PTR_ADDIU s4, s4, SZREG
+ PTR_ADDIU s2, s2, SZREG
+ LONG_ADDIU s6, s6, -1
beq s6, zero, process_entry
b copy_word
b process_entry
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 19a7705f2..5d7f26349 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -409,8 +409,6 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
{
- memset(to, 0, sizeof *to);
-
if (copy_from_user(to, from, 3*sizeof(int)) ||
copy_from_user(to->_sifields._pad,
from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d2d1c1933..5f5f44edc 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -192,6 +192,7 @@ static void show_stacktrace(struct task_struct *task,
void show_stack(struct task_struct *task, unsigned long *sp)
{
struct pt_regs regs;
+ mm_segment_t old_fs = get_fs();
if (sp) {
regs.regs[29] = (unsigned long)sp;
regs.regs[31] = 0;
@@ -210,7 +211,13 @@ void show_stack(struct task_struct *task, unsigned long *sp)
prepare_frametrace(&regs);
}
}
+ /*
+ * show_stack() deals exclusively with kernel mode, so be sure to access
+ * the stack in the kernel (not user) address space.
+ */
+ set_fs(KERNEL_DS);
show_stacktrace(task, &regs);
+ set_fs(old_fs);
}
static void show_code(unsigned int __user *pc)
@@ -1518,6 +1525,7 @@ asmlinkage void do_mcheck(struct pt_regs *regs)
const int field = 2 * sizeof(unsigned long);
int multi_match = regs->cp0_status & ST0_TS;
enum ctx_state prev_state;
+ mm_segment_t old_fs = get_fs();
prev_state = exception_enter();
show_regs(regs);
@@ -1539,8 +1547,13 @@ asmlinkage void do_mcheck(struct pt_regs *regs)
dump_tlb_all();
}
+ if (!user_mode(regs))
+ set_fs(KERNEL_DS);
+
show_code((unsigned int __user *) regs->cp0_epc);
+ set_fs(old_fs);
+
/*
* Some chips may have other causes of machine check (e.g. SB1
* graduation timer)
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index af84bef0c..eb3efd137 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -438,7 +438,7 @@ do { \
: "memory"); \
} while(0)
-#define StoreDW(addr, value, res) \
+#define _StoreDW(addr, value, res) \
do { \
__asm__ __volatile__ ( \
".set\tpush\n\t" \
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 6ab105734..d01ade634 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -466,6 +466,7 @@ int get_c0_perfcount_int(void)
{
return ltq_perfcount_irq;
}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
unsigned int get_c0_compare_int(void)
{
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 185e68261..a7f7d9ffb 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -148,6 +148,7 @@ int get_c0_perfcount_int(void)
return mips_cpu_perf_irq;
}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
unsigned int get_c0_compare_int(void)
{
@@ -165,14 +166,17 @@ unsigned int get_c0_compare_int(void)
static void __init init_rtc(void)
{
- /* stop the clock whilst setting it up */
- CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL);
+ unsigned char freq, ctrl;
- /* 32KHz time base */
- CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
+ /* Set 32KHz time base if not already set */
+ freq = CMOS_READ(RTC_FREQ_SELECT);
+ if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ)
+ CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
- /* start the clock */
- CMOS_WRITE(RTC_24H, RTC_CONTROL);
+ /* Ensure SET bit is clear so RTC can run */
+ ctrl = CMOS_READ(RTC_CONTROL);
+ if (ctrl & RTC_SET)
+ CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
}
void __init plat_time_init(void)
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
index e1d69895f..a120b7a5a 100644
--- a/arch/mips/mti-sead3/sead3-time.c
+++ b/arch/mips/mti-sead3/sead3-time.c
@@ -77,6 +77,7 @@ int get_c0_perfcount_int(void)
return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
return -1;
}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
unsigned int get_c0_compare_int(void)
{
diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c
index 67889fcea..ab73f6f40 100644
--- a/arch/mips/pistachio/time.c
+++ b/arch/mips/pistachio/time.c
@@ -26,6 +26,7 @@ int get_c0_perfcount_int(void)
{
return gic_get_c0_perfcount_int();
}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
void __init plat_time_init(void)
{
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 7cf91b92e..199ace4ca 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -89,6 +89,7 @@ int get_c0_perfcount_int(void)
{
return rt_perfcount_irq;
}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
unsigned int get_c0_compare_int(void)
{
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index d3a831ac0..da50e0c9c 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -966,8 +966,6 @@ int copy_siginfo_to_user32(struct compat_siginfo __user *d, const siginfo_t *s)
int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
{
- memset(to, 0, sizeof *to);
-
if (copy_from_user(to, from, 3*sizeof(int)) ||
copy_from_user(to->_sifields._pad,
from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 1f0aa2024..6424249d5 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,16 +28,10 @@
* Must preserve %o5 between VISEntryHalf and VISExitHalf */
#define VISEntryHalf \
- rd %fprs, %o5; \
- andcc %o5, FPRS_FEF, %g0; \
- be,pt %icc, 297f; \
- sethi %hi(298f), %g7; \
- sethi %hi(VISenterhalf), %g1; \
- jmpl %g1 + %lo(VISenterhalf), %g0; \
- or %g7, %lo(298f), %g7; \
- clr %o5; \
-297: wr %o5, FPRS_FEF, %fprs; \
-298:
+ VISEntry
+
+#define VISExitHalf \
+ VISExit
#define VISEntryHalfFast(fail_label) \
rd %fprs, %o5; \
@@ -47,7 +41,7 @@
ba,a,pt %xcc, fail_label; \
297: wr %o5, FPRS_FEF, %fprs;
-#define VISExitHalf \
+#define VISExitHalfFast \
wr %o5, 0, %fprs;
#ifndef __ASSEMBLY__
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 140527a20..83aeeb1df 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -240,8 +240,11 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
add %o0, 0x40, %o0
bne,pt %icc, 1b
LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+ VISExitHalfFast
+#else
VISExitHalf
-
+#endif
brz,pn %o2, .Lexit
cmp %o2, 19
ble,pn %icc, .Lsmall_unaligned
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9e2..a063d8433 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3
stx %g3, [%g6 + TI_GSR]
2: add %g6, %g1, %g3
- cmp %o5, FPRS_DU
- be,pn %icc, 6f
- sll %g1, 3, %g1
+ mov FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+ sll %g1, 3, %g1
stb %o5, [%g3 + TI_FPSAVED]
rd %gsr, %g2
add %g6, %g1, %g3
@@ -80,65 +79,3 @@ vis1: ldub [%g6 + TI_FPSAVED], %g3
.align 32
80: jmpl %g7 + %g0, %g0
nop
-
-6: ldub [%g3 + TI_FPSAVED], %o5
- or %o5, FPRS_DU, %o5
- add %g6, TI_FPREGS+0x80, %g2
- stb %o5, [%g3 + TI_FPSAVED]
-
- sll %g1, 5, %g1
- add %g6, TI_FPREGS+0xc0, %g3
- wr %g0, FPRS_FEF, %fprs
- membar #Sync
- stda %f32, [%g2 + %g1] ASI_BLK_P
- stda %f48, [%g3 + %g1] ASI_BLK_P
- membar #Sync
- ba,pt %xcc, 80f
- nop
-
- .align 32
-80: jmpl %g7 + %g0, %g0
- nop
-
- .align 32
-VISenterhalf:
- ldub [%g6 + TI_FPDEPTH], %g1
- brnz,a,pn %g1, 1f
- cmp %g1, 1
- stb %g0, [%g6 + TI_FPSAVED]
- stx %fsr, [%g6 + TI_XFSR]
- clr %o5
- jmpl %g7 + %g0, %g0
- wr %g0, FPRS_FEF, %fprs
-
-1: bne,pn %icc, 2f
- srl %g1, 1, %g1
- ba,pt %xcc, vis1
- sub %g7, 8, %g7
-2: addcc %g6, %g1, %g3
- sll %g1, 3, %g1
- andn %o5, FPRS_DU, %g2
- stb %g2, [%g3 + TI_FPSAVED]
-
- rd %gsr, %g2
- add %g6, %g1, %g3
- stx %g2, [%g3 + TI_GSR]
- add %g6, %g1, %g2
- stx %fsr, [%g2 + TI_XFSR]
- sll %g1, 5, %g1
-3: andcc %o5, FPRS_DL, %g0
- be,pn %icc, 4f
- add %g6, TI_FPREGS, %g2
-
- add %g6, TI_FPREGS+0x40, %g3
- membar #Sync
- stda %f0, [%g2 + %g1] ASI_BLK_P
- stda %f16, [%g3 + %g1] ASI_BLK_P
- membar #Sync
- ba,pt %xcc, 4f
- nop
-
- .align 32
-4: and %o5, FPRS_DU, %o5
- jmpl %g7 + %g0, %g0
- wr %o5, FPRS_FEF, %fprs
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1d649a956..8069ce12f 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -135,10 +135,6 @@ EXPORT_SYMBOL(copy_user_page);
void VISenter(void);
EXPORT_SYMBOL(VISenter);
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
unsigned long *);
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index e8c2c0414..c667e104a 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -113,8 +113,6 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
return -EFAULT;
- memset(to, 0, sizeof(*to));
-
err = __get_user(to->si_signo, &from->si_signo);
err |= __get_user(to->si_errno, &from->si_errno);
err |= __get_user(to->si_code, &from->si_code);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 02c2eff74..4bd6c1975 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -793,8 +793,6 @@ retint_kernel:
restore_c_regs_and_iret:
RESTORE_C_REGS
REMOVE_PT_GPREGS_FROM_STACK 8
-
-irq_return:
INTERRUPT_RETURN
ENTRY(native_iret)
@@ -1413,11 +1411,12 @@ ENTRY(nmi)
* If the variable is not set and the stack is not the NMI
* stack then:
* o Set the special variable on the stack
- * o Copy the interrupt frame into a "saved" location on the stack
- * o Copy the interrupt frame into a "copy" location on the stack
+ * o Copy the interrupt frame into an "outermost" location on the
+ * stack
+ * o Copy the interrupt frame into an "iret" location on the stack
* o Continue processing the NMI
* If the variable is set or the previous stack is the NMI stack:
- * o Modify the "copy" location to jump to the repeate_nmi
+ * o Modify the "iret" location to jump to the repeat_nmi
* o return back to the first NMI
*
* Now on exit of the first NMI, we first clear the stack variable
@@ -1426,32 +1425,151 @@ ENTRY(nmi)
* a nested NMI that updated the copy interrupt stack frame, a
* jump will be made to the repeat_nmi code that will handle the second
* NMI.
+ *
+ * However, espfix prevents us from directly returning to userspace
+ * with a single IRET instruction. Similarly, IRET to user mode
+ * can fault. We therefore handle NMIs from user space like
+ * other IST entries.
*/
/* Use %rdx as our temp variable throughout */
pushq_cfi %rdx
CFI_REL_OFFSET rdx, 0
+ testb $3, CS-RIP+8(%rsp)
+ jz .Lnmi_from_kernel
+
/*
- * If %cs was not the kernel segment, then the NMI triggered in user
- * space, which means it is definitely not nested.
+ * NMI from user mode. We need to run on the thread stack, but we
+ * can't go through the normal entry paths: NMIs are masked, and
+ * we don't want to enable interrupts, because then we'll end
+ * up in an awkward situation in which IRQs are on but NMIs
+ * are off.
*/
- cmpl $__KERNEL_CS, 16(%rsp)
- jne first_nmi
+
+ SWAPGS
+ cld
+ movq %rsp, %rdx
+ movq PER_CPU_VAR(kernel_stack), %rsp
+ pushq 5*8(%rdx) /* pt_regs->ss */
+ pushq 4*8(%rdx) /* pt_regs->rsp */
+ pushq 3*8(%rdx) /* pt_regs->flags */
+ pushq 2*8(%rdx) /* pt_regs->cs */
+ pushq 1*8(%rdx) /* pt_regs->rip */
+ pushq $-1 /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ pushq (%rdx) /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq %rax /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 */
+ pushq %r9 /* pt_regs->r9 */
+ pushq %r10 /* pt_regs->r10 */
+ pushq %r11 /* pt_regs->r11 */
+ pushq %rbx /* pt_regs->rbx */
+ pushq %rbp /* pt_regs->rbp */
+ pushq %r12 /* pt_regs->r12 */
+ pushq %r13 /* pt_regs->r13 */
+ pushq %r14 /* pt_regs->r14 */
+ pushq %r15 /* pt_regs->r15 */
/*
- * Check the special variable on the stack to see if NMIs are
- * executing.
+ * At this point we no longer need to worry about stack damage
+ * due to nesting -- we're on the normal thread stack and we're
+ * done with the NMI stack.
+ */
+ movq %rsp, %rdi
+ movq $-1, %rsi
+ call do_nmi
+
+ /*
+ * Return back to user mode. We must *not* do the normal exit
+ * work, because we don't want to enable interrupts. Fortunately,
+ * do_nmi doesn't modify pt_regs.
+ */
+ SWAPGS
+ jmp restore_c_regs_and_iret
+
+.Lnmi_from_kernel:
+ /*
+ * Here's what our stack frame will look like:
+ * +---------------------------------------------------------+
+ * | original SS |
+ * | original Return RSP |
+ * | original RFLAGS |
+ * | original CS |
+ * | original RIP |
+ * +---------------------------------------------------------+
+ * | temp storage for rdx |
+ * +---------------------------------------------------------+
+ * | "NMI executing" variable |
+ * +---------------------------------------------------------+
+ * | iret SS } Copied from "outermost" frame |
+ * | iret Return RSP } on each loop iteration; overwritten |
+ * | iret RFLAGS } by a nested NMI to force another |
+ * | iret CS } iteration if needed. |
+ * | iret RIP } |
+ * +---------------------------------------------------------+
+ * | outermost SS } initialized in first_nmi; |
+ * | outermost Return RSP } will not be changed before |
+ * | outermost RFLAGS } NMI processing is done. |
+ * | outermost CS } Copied to "iret" frame on each |
+ * | outermost RIP } iteration. |
+ * +---------------------------------------------------------+
+ * | pt_regs |
+ * +---------------------------------------------------------+
+ *
+ * The "original" frame is used by hardware. Before re-enabling
+ * NMIs, we need to be done with it, and we need to leave enough
+ * space for the asm code here.
+ *
+ * We return by executing IRET while RSP points to the "iret" frame.
+ * That will either return for real or it will loop back into NMI
+ * processing.
+ *
+ * The "outermost" frame is copied to the "iret" frame on each
+ * iteration of the loop, so each iteration starts with the "iret"
+ * frame pointing to the final return target.
+ */
+
+ /*
+ * Determine whether we're a nested NMI.
+ *
+ * If we interrupted kernel code between repeat_nmi and
+ * end_repeat_nmi, then we are a nested NMI. We must not
+ * modify the "iret" frame because it's being written by
+ * the outer NMI. That's okay; the outer NMI handler is
+ * about to about to call do_nmi anyway, so we can just
+ * resume the outer NMI.
+ */
+
+ movq $repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja 1f
+ movq $end_repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja nested_nmi_out
+1:
+
+ /*
+ * Now check "NMI executing". If it's set, then we're nested.
+ * This will not detect if we interrupted an outer NMI just
+ * before IRET.
*/
cmpl $1, -8(%rsp)
je nested_nmi
/*
- * Now test if the previous stack was an NMI stack.
- * We need the double check. We check the NMI stack to satisfy the
- * race when the first NMI clears the variable before returning.
- * We check the variable because the first NMI could be in a
- * breakpoint routine using a breakpoint stack.
+ * Now test if the previous stack was an NMI stack. This covers
+ * the case where we interrupt an outer NMI after it clears
+ * "NMI executing" but before IRET. We need to be careful, though:
+ * there is one case in which RSP could point to the NMI stack
+ * despite there being no NMI active: naughty userspace controls
+ * RSP at the very beginning of the SYSCALL targets. We can
+ * pull a fast one on naughty userspace, though: we program
+ * SYSCALL to mask DF, so userspace cannot cause DF to be set
+ * if it controls the kernel's RSP. We set DF before we clear
+ * "NMI executing".
*/
lea 6*8(%rsp), %rdx
/* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
@@ -1462,25 +1580,21 @@ ENTRY(nmi)
cmpq %rdx, 4*8(%rsp)
/* If it is below the NMI stack, it is a normal NMI */
jb first_nmi
- /* Ah, it is within the NMI stack, treat it as nested */
+
+ /* Ah, it is within the NMI stack. */
+
+ testb $(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp)
+ jz first_nmi /* RSP was user controlled. */
+
+ /* This is a nested NMI. */
CFI_REMEMBER_STATE
nested_nmi:
/*
- * Do nothing if we interrupted the fixup in repeat_nmi.
- * It's about to repeat the NMI handler, so we are fine
- * with ignoring this one.
+ * Modify the "iret" frame to point to repeat_nmi, forcing another
+ * iteration of NMI handling.
*/
- movq $repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja 1f
- movq $end_repeat_nmi, %rdx
- cmpq 8(%rsp), %rdx
- ja nested_nmi_out
-
-1:
- /* Set up the interrupted NMIs stack to jump to repeat_nmi */
leaq -1*8(%rsp), %rdx
movq %rdx, %rsp
CFI_ADJUST_CFA_OFFSET 1*8
@@ -1499,60 +1613,23 @@ nested_nmi_out:
popq_cfi %rdx
CFI_RESTORE rdx
- /* No need to check faults here */
+ /* We are returning to kernel mode, so this cannot result in a fault. */
INTERRUPT_RETURN
CFI_RESTORE_STATE
first_nmi:
- /*
- * Because nested NMIs will use the pushed location that we
- * stored in rdx, we must keep that space available.
- * Here's what our stack frame will look like:
- * +-------------------------+
- * | original SS |
- * | original Return RSP |
- * | original RFLAGS |
- * | original CS |
- * | original RIP |
- * +-------------------------+
- * | temp storage for rdx |
- * +-------------------------+
- * | NMI executing variable |
- * +-------------------------+
- * | copied SS |
- * | copied Return RSP |
- * | copied RFLAGS |
- * | copied CS |
- * | copied RIP |
- * +-------------------------+
- * | Saved SS |
- * | Saved Return RSP |
- * | Saved RFLAGS |
- * | Saved CS |
- * | Saved RIP |
- * +-------------------------+
- * | pt_regs |
- * +-------------------------+
- *
- * The saved stack frame is used to fix up the copied stack frame
- * that a nested NMI may change to make the interrupted NMI iret jump
- * to the repeat_nmi. The original stack frame and the temp storage
- * is also used by nested NMIs and can not be trusted on exit.
- */
- /* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+ /* Restore rdx. */
movq (%rsp), %rdx
CFI_RESTORE rdx
- /* Set the NMI executing variable on the stack. */
+ /* Set "NMI executing" on the stack. */
pushq_cfi $1
- /*
- * Leave room for the "copied" frame
- */
+ /* Leave room for the "iret" frame */
subq $(5*8), %rsp
CFI_ADJUST_CFA_OFFSET 5*8
- /* Copy the stack frame to the Saved frame */
+ /* Copy the "original" frame to the "outermost" frame */
.rept 5
pushq_cfi 11*8(%rsp)
.endr
@@ -1560,6 +1637,7 @@ first_nmi:
/* Everything up to here is safe from nested NMIs */
+repeat_nmi:
/*
* If there was a nested NMI, the first NMI's iret will return
* here. But NMIs are still enabled and we can take another
@@ -1568,16 +1646,21 @@ first_nmi:
* it will just return, as we are about to repeat an NMI anyway.
* This makes it safe to copy to the stack frame that a nested
* NMI will update.
- */
-repeat_nmi:
- /*
- * Update the stack variable to say we are still in NMI (the update
- * is benign for the non-repeat case, where 1 was pushed just above
- * to this very stack slot).
+ *
+ * RSP is pointing to "outermost RIP". gsbase is unknown, but, if
+ * we're repeating an NMI, gsbase has the same value that it had on
+ * the first iteration. paranoid_entry will load the kernel
+ * gsbase if needed before we call do_nmi.
+ *
+ * Set "NMI executing" in case we came back here via IRET.
*/
movq $1, 10*8(%rsp)
- /* Make another copy, this one may be modified by nested NMIs */
+ /*
+ * Copy the "outermost" frame to the "iret" frame. NMIs that nest
+ * here must not modify the "iret" frame while we're writing to
+ * it or it will end up containing garbage.
+ */
addq $(10*8), %rsp
CFI_ADJUST_CFA_OFFSET -10*8
.rept 5
@@ -1588,9 +1671,9 @@ repeat_nmi:
end_repeat_nmi:
/*
- * Everything below this point can be preempted by a nested
- * NMI if the first NMI took an exception and reset our iret stack
- * so that we repeat another NMI.
+ * Everything below this point can be preempted by a nested NMI.
+ * If this happens, then the inner NMI will change the "iret"
+ * frame to point back to repeat_nmi.
*/
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
ALLOC_PT_GPREGS_ON_STACK
@@ -1605,29 +1688,11 @@ end_repeat_nmi:
call paranoid_entry
DEFAULT_FRAME 0
- /*
- * Save off the CR2 register. If we take a page fault in the NMI then
- * it could corrupt the CR2 value. If the NMI preempts a page fault
- * handler before it was able to read the CR2 register, and then the
- * NMI itself takes a page fault, the page fault that was preempted
- * will read the information from the NMI page fault and not the
- * origin fault. Save it off and restore it if it changes.
- * Use the r12 callee-saved register.
- */
- movq %cr2, %r12
-
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
movq %rsp,%rdi
movq $-1,%rsi
call do_nmi
- /* Did the NMI take a page fault? Restore cr2 if it did */
- movq %cr2, %rcx
- cmpq %rcx, %r12
- je 1f
- movq %r12, %cr2
-1:
-
testl %ebx,%ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
@@ -1635,12 +1700,27 @@ nmi_swapgs:
nmi_restore:
RESTORE_EXTRA_REGS
RESTORE_C_REGS
- /* Pop the extra iret frame at once */
+
+ /* Point RSP at the "iret" frame. */
REMOVE_PT_GPREGS_FROM_STACK 6*8
- /* Clear the NMI executing stack variable */
- movq $0, 5*8(%rsp)
- jmp irq_return
+ /*
+ * Clear "NMI executing". Set DF first so that we can easily
+ * distinguish the remaining code between here and IRET from
+ * the SYSCALL entry and exit paths. On a native kernel, we
+ * could just inspect RIP, but, on paravirt kernels,
+ * INTERRUPT_RETURN can translate into a jump into a
+ * hypercall page.
+ */
+ std
+ movq $0, 5*8(%rsp) /* clear "NMI executing" */
+
+ /*
+ * INTERRUPT_RETURN reads the "iret" frame and exits the NMI
+ * stack in a single instruction. We are returning to kernel
+ * mode, so this cannot result in a fault.
+ */
+ INTERRUPT_RETURN
CFI_ENDPROC
END(nmi)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index c3e985d17..d05bd2e2e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -408,15 +408,15 @@ static void default_do_nmi(struct pt_regs *regs)
NOKPROBE_SYMBOL(default_do_nmi);
/*
- * NMIs can hit breakpoints which will cause it to lose its
- * NMI context with the CPU when the breakpoint does an iret.
- */
-#ifdef CONFIG_X86_32
-/*
- * For i386, NMIs use the same stack as the kernel, and we can
- * add a workaround to the iret problem in C (preventing nested
- * NMIs if an NMI takes a trap). Simply have 3 states the NMI
- * can be in:
+ * NMIs can page fault or hit breakpoints which will cause it to lose
+ * its NMI context with the CPU when the breakpoint or page fault does an IRET.
+ *
+ * As a result, NMIs can nest if NMIs get unmasked due an IRET during
+ * NMI processing. On x86_64, the asm glue protects us from nested NMIs
+ * if the outer NMI came from kernel mode, but we can still nest if the
+ * outer NMI came from user mode.
+ *
+ * To handle these nested NMIs, we have three states:
*
* 1) not running
* 2) executing
@@ -430,15 +430,14 @@ NOKPROBE_SYMBOL(default_do_nmi);
* (Note, the latch is binary, thus multiple NMIs triggering,
* when one is running, are ignored. Only one NMI is restarted.)
*
- * If an NMI hits a breakpoint that executes an iret, another
- * NMI can preempt it. We do not want to allow this new NMI
- * to run, but we want to execute it when the first one finishes.
- * We set the state to "latched", and the exit of the first NMI will
- * perform a dec_return, if the result is zero (NOT_RUNNING), then
- * it will simply exit the NMI handler. If not, the dec_return
- * would have set the state to NMI_EXECUTING (what we want it to
- * be when we are running). In this case, we simply jump back
- * to rerun the NMI handler again, and restart the 'latched' NMI.
+ * If an NMI executes an iret, another NMI can preempt it. We do not
+ * want to allow this new NMI to run, but we want to execute it when the
+ * first one finishes. We set the state to "latched", and the exit of
+ * the first NMI will perform a dec_return, if the result is zero
+ * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the
+ * dec_return would have set the state to NMI_EXECUTING (what we want it
+ * to be when we are running). In this case, we simply jump back to
+ * rerun the NMI handler again, and restart the 'latched' NMI.
*
* No trap (breakpoint or page fault) should be hit before nmi_restart,
* thus there is no race between the first check of state for NOT_RUNNING
@@ -461,49 +460,36 @@ enum nmi_states {
static DEFINE_PER_CPU(enum nmi_states, nmi_state);
static DEFINE_PER_CPU(unsigned long, nmi_cr2);
-#define nmi_nesting_preprocess(regs) \
- do { \
- if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \
- this_cpu_write(nmi_state, NMI_LATCHED); \
- return; \
- } \
- this_cpu_write(nmi_state, NMI_EXECUTING); \
- this_cpu_write(nmi_cr2, read_cr2()); \
- } while (0); \
- nmi_restart:
-
-#define nmi_nesting_postprocess() \
- do { \
- if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \
- write_cr2(this_cpu_read(nmi_cr2)); \
- if (this_cpu_dec_return(nmi_state)) \
- goto nmi_restart; \
- } while (0)
-#else /* x86_64 */
+#ifdef CONFIG_X86_64
/*
- * In x86_64 things are a bit more difficult. This has the same problem
- * where an NMI hitting a breakpoint that calls iret will remove the
- * NMI context, allowing a nested NMI to enter. What makes this more
- * difficult is that both NMIs and breakpoints have their own stack.
- * When a new NMI or breakpoint is executed, the stack is set to a fixed
- * point. If an NMI is nested, it will have its stack set at that same
- * fixed address that the first NMI had, and will start corrupting the
- * stack. This is handled in entry_64.S, but the same problem exists with
- * the breakpoint stack.
+ * In x86_64, we need to handle breakpoint -> NMI -> breakpoint. Without
+ * some care, the inner breakpoint will clobber the outer breakpoint's
+ * stack.
*
- * If a breakpoint is being processed, and the debug stack is being used,
- * if an NMI comes in and also hits a breakpoint, the stack pointer
- * will be set to the same fixed address as the breakpoint that was
- * interrupted, causing that stack to be corrupted. To handle this case,
- * check if the stack that was interrupted is the debug stack, and if
- * so, change the IDT so that new breakpoints will use the current stack
- * and not switch to the fixed address. On return of the NMI, switch back
- * to the original IDT.
+ * If a breakpoint is being processed, and the debug stack is being
+ * used, if an NMI comes in and also hits a breakpoint, the stack
+ * pointer will be set to the same fixed address as the breakpoint that
+ * was interrupted, causing that stack to be corrupted. To handle this
+ * case, check if the stack that was interrupted is the debug stack, and
+ * if so, change the IDT so that new breakpoints will use the current
+ * stack and not switch to the fixed address. On return of the NMI,
+ * switch back to the original IDT.
*/
static DEFINE_PER_CPU(int, update_debug_stack);
+#endif
-static inline void nmi_nesting_preprocess(struct pt_regs *regs)
+dotraplinkage notrace void
+do_nmi(struct pt_regs *regs, long error_code)
{
+ if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
+ this_cpu_write(nmi_state, NMI_LATCHED);
+ return;
+ }
+ this_cpu_write(nmi_state, NMI_EXECUTING);
+ this_cpu_write(nmi_cr2, read_cr2());
+nmi_restart:
+
+#ifdef CONFIG_X86_64
/*
* If we interrupted a breakpoint, it is possible that
* the nmi handler will have breakpoints too. We need to
@@ -514,22 +500,8 @@ static inline void nmi_nesting_preprocess(struct pt_regs *regs)
debug_stack_set_zero();
this_cpu_write(update_debug_stack, 1);
}
-}
-
-static inline void nmi_nesting_postprocess(void)
-{
- if (unlikely(this_cpu_read(update_debug_stack))) {
- debug_stack_reset();
- this_cpu_write(update_debug_stack, 0);
- }
-}
#endif
-dotraplinkage notrace void
-do_nmi(struct pt_regs *regs, long error_code)
-{
- nmi_nesting_preprocess(regs);
-
nmi_enter();
inc_irq_stat(__nmi_count);
@@ -539,8 +511,17 @@ do_nmi(struct pt_regs *regs, long error_code)
nmi_exit();
- /* On i386, may loop back to preprocess */
- nmi_nesting_postprocess();
+#ifdef CONFIG_X86_64
+ if (unlikely(this_cpu_read(update_debug_stack))) {
+ debug_stack_reset();
+ this_cpu_write(update_debug_stack, 0);
+ }
+#endif
+
+ if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+ write_cr2(this_cpu_read(nmi_cr2));
+ if (this_cpu_dec_return(nmi_state))
+ goto nmi_restart;
}
NOKPROBE_SYMBOL(do_nmi);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 9d28383fc..c4ea87eed 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -150,7 +150,7 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.apic->pending_events;
+ return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events;
}
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 46957ead3..a671e8372 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -483,6 +483,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
pte_t pte;
unsigned long pfn;
struct page *page;
+ unsigned char dummy;
ptep = lookup_address((unsigned long)v, &level);
BUG_ON(ptep == NULL);
@@ -492,6 +493,32 @@ static void set_aliased_prot(void *v, pgprot_t prot)
pte = pfn_pte(pfn, prot);
+ /*
+ * Careful: update_va_mapping() will fail if the virtual address
+ * we're poking isn't populated in the page tables. We don't
+ * need to worry about the direct map (that's always in the page
+ * tables), but we need to be careful about vmap space. In
+ * particular, the top level page table can lazily propagate
+ * entries between processes, so if we've switched mms since we
+ * vmapped the target in the first place, we might not have the
+ * top-level page table entry populated.
+ *
+ * We disable preemption because we want the same mm active when
+ * we probe the target and when we issue the hypercall. We'll
+ * have the same nominal mm, but if we're a kernel thread, lazy
+ * mm dropping could change our pgd.
+ *
+ * Out of an abundance of caution, this uses __get_user() to fault
+ * in the target address just in case there's some obscure case
+ * in which the target address isn't readable.
+ */
+
+ preempt_disable();
+
+ pagefault_disable(); /* Avoid warnings due to being atomic. */
+ __get_user(dummy, (unsigned char __user __force *)v);
+ pagefault_enable();
+
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
@@ -503,6 +530,8 @@ static void set_aliased_prot(void *v, pgprot_t prot)
BUG();
} else
kmap_flush_unused();
+
+ preempt_enable();
}
static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +539,17 @@ static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
int i;
+ /*
+ * We need to mark the all aliases of the LDT pages RO. We
+ * don't need to call vm_flush_aliases(), though, since that's
+ * only responsible for flushing aliases out the TLBs, not the
+ * page tables, and Xen will flush the TLB for us if needed.
+ *
+ * To avoid confusing future readers: none of this is necessary
+ * to load the LDT. The hypervisor only checks this when the
+ * LDT is faulted in due to subsequent descriptor access.
+ */
+
for(i = 0; i < entries; i += entries_per_page)
set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
}