| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20160111145347.GA24804@gmail.com>
Date: Mon, 11 Jan 2016 15:53:47 +0100
From: Ingo Molnar <mingo@...nel.org>
To: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
"H. Peter Anvin" <hpa@...or.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>
Subject: [GIT PULL] x86/asm changes for v4.5
Linus,
Please pull the latest x86-asm-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-asm-for-linus
# HEAD: 8705d603edd49f1cff165cd3b7998f4c7f098d27 x86/vsdo: Fix build on PARAVIRT_CLOCK=y, KVM_GUEST=n
The main changes in this cycle were:
- vDSO and asm entry improvements (Andy Lutomirski)
- Xen paravirt entry enhancements (Boris Ostrovsky)
- asm entry labels enhancement (Borislav Petkov)
- and other misc changes (Thomas Gleixner, me)
out-of-topic modifications in x86-asm-for-linus:
--------------------------------------------------
include/linux/context_tracking_state.h# ed11a7f1b3bd: context_tracking: Switch to
kernel/context_tracking.c # ed11a7f1b3bd: context_tracking: Switch to
Thanks,
Ingo
------------------>
Andy Lutomirski (10):
context_tracking: Switch to new static_branch API
x86/asm: Error out if asm/jump_label.h is included inappropriately
x86/asm: Add asm macros for static keys/jump labels
x86/entry/64: Bypass enter_from_user_mode on non-context-tracking boots
x86/kvm: On KVM re-enable (e.g. after suspend), update clocks
x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader
x86/vdso: Get pvclock data from the vvar VMA instead of the fixmap
x86/vdso: Remove pvclock fixmap machinery
x86/vdso: Enable vdso pvclock access on all vdso variants
x86/vsdo: Fix build on PARAVIRT_CLOCK=y, KVM_GUEST=n
Boris Ostrovsky (3):
x86/xen: Avoid fast syscall path for Xen PV guests
x86/paravirt: Remove the unused irq_enable_sysexit pv op
x86/entry, x86/paravirt: Remove the unused usergs_sysret32 PV op
Borislav Petkov (1):
x86/entry/64_compat: Make labels local
Ingo Molnar (1):
x86/platform/uv: Include clocksource.h for clocksource_touch_watchdog()
Thomas Gleixner (1):
Revert "x86/kvm: On KVM re-enable (e.g. after suspend), update clocks"
arch/x86/entry/calling.h | 15 ++++
arch/x86/entry/entry_32.S | 13 ++-
arch/x86/entry/entry_64.S | 8 +-
arch/x86/entry/entry_64_compat.S | 30 +++----
arch/x86/entry/vdso/vclock_gettime.c | 151 ++++++++++++++++-----------------
arch/x86/entry/vdso/vdso-layout.lds.S | 3 +-
arch/x86/entry/vdso/vdso2c.c | 3 +
arch/x86/entry/vdso/vma.c | 14 +++
arch/x86/include/asm/cpufeature.h | 1 +
arch/x86/include/asm/fixmap.h | 5 --
arch/x86/include/asm/jump_label.h | 63 ++++++++++++--
arch/x86/include/asm/paravirt.h | 12 ---
arch/x86/include/asm/paravirt_types.h | 17 ----
arch/x86/include/asm/pvclock.h | 14 +--
arch/x86/include/asm/vdso.h | 1 +
arch/x86/kernel/asm-offsets.c | 3 -
arch/x86/kernel/asm-offsets_64.c | 1 -
arch/x86/kernel/kvmclock.c | 11 ++-
arch/x86/kernel/paravirt.c | 12 ---
arch/x86/kernel/paravirt_patch_32.c | 2 -
arch/x86/kernel/paravirt_patch_64.c | 3 -
arch/x86/kernel/pvclock.c | 24 ------
arch/x86/platform/uv/uv_nmi.c | 1 +
arch/x86/xen/enlighten.c | 7 +-
arch/x86/xen/xen-asm_32.S | 14 ---
arch/x86/xen/xen-asm_64.S | 19 -----
arch/x86/xen/xen-ops.h | 3 -
include/linux/context_tracking_state.h | 4 +-
kernel/context_tracking.c | 4 +-
29 files changed, 207 insertions(+), 251 deletions(-)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3c71dd947c7b..e32206e09868 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,3 +1,5 @@
+#include <linux/jump_label.h>
+
/*
x86 function call convention, 64-bit:
@@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with
#endif /* CONFIG_X86_64 */
+/*
+ * This does 'call enter_from_user_mode' unless we can avoid it based on
+ * kernel config or using the static jump infrastructure.
+ */
+.macro CALL_enter_from_user_mode
+#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef HAVE_JUMP_LABEL
+ STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+#endif
+ call enter_from_user_mode
+.Lafter_call_\@:
+#endif
+.endm
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 3eb572ed3d7a..9870c972d345 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -308,8 +308,9 @@ ENTRY(entry_SYSENTER_32)
movl %esp, %eax
call do_fast_syscall_32
- testl %eax, %eax
- jz .Lsyscall_32_done
+ /* XEN PV guests always use IRET path */
+ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
/* Opportunistic SYSEXIT */
TRACE_IRQS_ON /* User mode traces as IRQs on. */
@@ -328,7 +329,8 @@ ENTRY(entry_SYSENTER_32)
* Return back to the vDSO, which will pop ecx and edx.
* Don't bother with DS and ES (they already contain __USER_DS).
*/
- ENABLE_INTERRUPTS_SYSEXIT
+ sti
+ sysexit
.pushsection .fixup, "ax"
2: movl $0, PT_FS(%esp)
@@ -551,11 +553,6 @@ ENTRY(native_iret)
iret
_ASM_EXTABLE(native_iret, iret_exc)
END(native_iret)
-
-ENTRY(native_irq_enable_sysexit)
- sti
- sysexit
-END(native_irq_enable_sysexit)
#endif
ENTRY(overflow)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a55697d19824..9d34d3cfceb6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -520,9 +520,7 @@ END(irq_entries_start)
*/
TRACE_IRQS_OFF
-#ifdef CONFIG_CONTEXT_TRACKING
- call enter_from_user_mode
-#endif
+ CALL_enter_from_user_mode
1:
/*
@@ -1066,9 +1064,7 @@ ENTRY(error_entry)
* (which can take locks).
*/
TRACE_IRQS_OFF
-#ifdef CONFIG_CONTEXT_TRACKING
- call enter_from_user_mode
-#endif
+ CALL_enter_from_user_mode
ret
.Lerror_entry_done:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index c3201830a85e..8d802a109fac 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -18,13 +18,6 @@
.section .entry.text, "ax"
-#ifdef CONFIG_PARAVIRT
-ENTRY(native_usergs_sysret32)
- swapgs
- sysretl
-ENDPROC(native_usergs_sysret32)
-#endif
-
/*
* 32-bit SYSENTER instruction entry.
*
@@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat)
* This needs to happen before enabling interrupts so that
* we don't get preempted with NT set.
*
- * NB.: sysenter_fix_flags is a label with the code under it moved
+ * NB.: .Lsysenter_fix_flags is a label with the code under it moved
* out-of-line as an optimization: NT is unlikely to be set in the
* majority of the cases and instead of polluting the I$ unnecessarily,
* we're keeping that code behind a branch which will predict as
* not-taken and therefore its instructions won't be fetched.
*/
testl $X86_EFLAGS_NT, EFLAGS(%rsp)
- jnz sysenter_fix_flags
-sysenter_flags_fixed:
+ jnz .Lsysenter_fix_flags
+.Lsysenter_flags_fixed:
/*
* User mode is traced as though IRQs are on, and SYSENTER
@@ -121,14 +114,15 @@ ENTRY(entry_SYSENTER_compat)
movq %rsp, %rdi
call do_fast_syscall_32
- testl %eax, %eax
- jz .Lsyscall_32_done
+ /* XEN PV guests always use IRET path */
+ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
jmp sysret32_from_system_call
-sysenter_fix_flags:
+.Lsysenter_fix_flags:
pushq $X86_EFLAGS_FIXED
popfq
- jmp sysenter_flags_fixed
+ jmp .Lsysenter_flags_fixed
ENDPROC(entry_SYSENTER_compat)
/*
@@ -200,8 +194,9 @@ ENTRY(entry_SYSCALL_compat)
movq %rsp, %rdi
call do_fast_syscall_32
- testl %eax, %eax
- jz .Lsyscall_32_done
+ /* XEN PV guests always use IRET path */
+ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
/* Opportunistic SYSRET */
sysret32_from_system_call:
@@ -236,7 +231,8 @@ ENTRY(entry_SYSCALL_compat)
xorq %r9, %r9
xorq %r10, %r10
movq RSP-ORIG_RAX(%rsp), %rsp
- USERGS_SYSRET32
+ swapgs
+ sysretl
END(entry_SYSCALL_compat)
/*
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index ca94fa649251..8602f06c759f 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -17,8 +17,10 @@
#include <asm/vvar.h>
#include <asm/unistd.h>
#include <asm/msr.h>
+#include <asm/pvclock.h>
#include <linux/math64.h>
#include <linux/time.h>
+#include <linux/kernel.h>
#define gtod (&VVAR(vsyscall_gtod_data))
@@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void)
}
#endif
-#ifndef BUILD_VDSO32
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page
+ __attribute__((visibility("hidden")));
+#endif
-#include <linux/kernel.h>
-#include <asm/vsyscall.h>
-#include <asm/fixmap.h>
-#include <asm/pvclock.h>
+#ifndef BUILD_VDSO32
notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
{
@@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
return ret;
}
-#ifdef CONFIG_PARAVIRT_CLOCK
-
-static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu)
-{
- const struct pvclock_vsyscall_time_info *pvti_base;
- int idx = cpu / (PAGE_SIZE/PVTI_SIZE);
- int offset = cpu % (PAGE_SIZE/PVTI_SIZE);
-
- BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END);
-
- pvti_base = (struct pvclock_vsyscall_time_info *)
- __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx);
-
- return &pvti_base[offset];
-}
-
-static notrace cycle_t vread_pvclock(int *mode)
-{
- const struct pvclock_vsyscall_time_info *pvti;
- cycle_t ret;
- u64 last;
- u32 version;
- u8 flags;
- unsigned cpu, cpu1;
-
-
- /*
- * Note: hypervisor must guarantee that:
- * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
- * 2. that per-CPU pvclock time info is updated if the
- * underlying CPU changes.
- * 3. that version is increased whenever underlying CPU
- * changes.
- *
- */
- do {
- cpu = __getcpu() & VGETCPU_CPU_MASK;
- /* TODO: We can put vcpu id into higher bits of pvti.version.
- * This will save a couple of cycles by getting rid of
- * __getcpu() calls (Gleb).
- */
-
- pvti = get_pvti(cpu);
-
- version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
-
- /*
- * Test we're still on the cpu as well as the version.
- * We could have been migrated just after the first
- * vgetcpu but before fetching the version, so we
- * wouldn't notice a version change.
- */
- cpu1 = __getcpu() & VGETCPU_CPU_MASK;
- } while (unlikely(cpu != cpu1 ||
- (pvti->pvti.version & 1) ||
- pvti->pvti.version != version));
-
- if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
- *mode = VCLOCK_NONE;
-
- /* refer to tsc.c read_tsc() comment for rationale */
- last = gtod->cycle_last;
-
- if (likely(ret >= last))
- return ret;
-
- return last;
-}
-#endif
#else
@@ -162,15 +95,77 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
return ret;
}
+#endif
+
#ifdef CONFIG_PARAVIRT_CLOCK
+static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
+{
+ return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
+}
static notrace cycle_t vread_pvclock(int *mode)
{
- *mode = VCLOCK_NONE;
- return 0;
-}
-#endif
+ const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
+ cycle_t ret;
+ u64 tsc, pvti_tsc;
+ u64 last, delta, pvti_system_time;
+ u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift;
+
+ /*
+ * Note: The kernel and hypervisor must guarantee that cpu ID
+ * number maps 1:1 to per-CPU pvclock time info.
+ *
+ * Because the hypervisor is entirely unaware of guest userspace
+ * preemption, it cannot guarantee that per-CPU pvclock time
+ * info is updated if the underlying CPU changes or that that
+ * version is increased whenever underlying CPU changes.
+ *
+ * On KVM, we are guaranteed that pvti updates for any vCPU are
+ * atomic as seen by *all* vCPUs. This is an even stronger
+ * guarantee than we get with a normal seqlock.
+ *
+ * On Xen, we don't appear to have that guarantee, but Xen still
+ * supplies a valid seqlock using the version field.
+
+ * We only do pvclock vdso timing at all if
+ * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+ * mean that all vCPUs have matching pvti and that the TSC is
+ * synced, so we can just look at vCPU 0's pvti.
+ */
+ if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
+ *mode = VCLOCK_NONE;
+ return 0;
+ }
+
+ do {
+ version = pvti->version;
+
+ smp_rmb();
+
+ tsc = rdtsc_ordered();
+ pvti_tsc_to_system_mul = pvti->tsc_to_system_mul;
+ pvti_tsc_shift = pvti->tsc_shift;
+ pvti_system_time = pvti->system_time;
+ pvti_tsc = pvti->tsc_timestamp;
+
+ /* Make sure that the version double-check is last. */
+ smp_rmb();
+ } while (unlikely((version & 1) || version != pvti->version));
+
+ delta = tsc - pvti_tsc;
+ ret = pvti_system_time +
+ pvclock_scale_delta(delta, pvti_tsc_to_system_mul,
+ pvti_tsc_shift);
+
+ /* refer to vread_tsc() comment for rationale */
+ last = gtod->cycle_last;
+
+ if (likely(ret >= last))
+ return ret;
+
+ return last;
+}
#endif
notrace static cycle_t vread_tsc(void)
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index de2c921025f5..4158acc17df0 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@ SECTIONS
* segment.
*/
- vvar_start = . - 2 * PAGE_SIZE;
+ vvar_start = . - 3 * PAGE_SIZE;
vvar_page = vvar_start;
/* Place all vvars at the offsets in asm/vvar.h. */
@@ -36,6 +36,7 @@ SECTIONS
#undef EMIT_VVAR
hpet_page = vvar_start + PAGE_SIZE;
+ pvclock_page = vvar_start + 2 * PAGE_SIZE;
. = SIZEOF_HEADERS;
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 785d9922b106..491020b2826d 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -73,6 +73,7 @@ enum {
sym_vvar_start,
sym_vvar_page,
sym_hpet_page,
+ sym_pvclock_page,
sym_VDSO_FAKE_SECTION_TABLE_START,
sym_VDSO_FAKE_SECTION_TABLE_END,
};
@@ -80,6 +81,7 @@ enum {
const int special_pages[] = {
sym_vvar_page,
sym_hpet_page,
+ sym_pvclock_page,
};
struct vdso_sym {
@@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = {
[sym_vvar_start] = {"vvar_start", true},
[sym_vvar_page] = {"vvar_page", true},
[sym_hpet_page] = {"hpet_page", true},
+ [sym_pvclock_page] = {"pvclock_page", true},
[sym_VDSO_FAKE_SECTION_TABLE_START] = {
"VDSO_FAKE_SECTION_TABLE_START", false
},
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 64df47148160..b8f69e264ac4 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -12,6 +12,7 @@
#include <linux/random.h>
#include <linux/elf.h>
#include <linux/cpu.h>
+#include <asm/pvclock.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
@@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
.name = "[vvar]",
.pages = no_pages,
};
+ struct pvclock_vsyscall_time_info *pvti;
if (calculate_addr) {
addr = vdso_addr(current->mm->start_stack,
@@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr)
}
#endif
+ pvti = pvclock_pvti_cpu0_va();
+ if (pvti && image->sym_pvclock_page) {
+ ret = remap_pfn_range(vma,
+ text_start + image->sym_pvclock_page,
+ __pa(pvti) >> PAGE_SHIFT,
+ PAGE_SIZE,
+ PAGE_READONLY);
+
+ if (ret)
+ goto up_fail;
+ }
+
up_fail:
if (ret)
current->mm->context.vdso = NULL;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e4f8010f22e0..f7ba9fbf12ee 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -216,6 +216,7 @@
#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */
+#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index f80d70009ff8..6d7d0e52ed5a 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -19,7 +19,6 @@
#include <asm/acpi.h>
#include <asm/apicdef.h>
#include <asm/page.h>
-#include <asm/pvclock.h>
#ifdef CONFIG_X86_32
#include <linux/threads.h>
#include <asm/kmap_types.h>
@@ -72,10 +71,6 @@ enum fixed_addresses {
#ifdef CONFIG_X86_VSYSCALL_EMULATION
VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
#endif
-#ifdef CONFIG_PARAVIRT_CLOCK
- PVCLOCK_FIXMAP_BEGIN,
- PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
-#endif
#endif
FIX_DBGP_BASE,
FIX_EARLYCON_MEM_BASE,
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 5daeca3d0f9e..adc54c12cbd1 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -1,12 +1,18 @@
#ifndef _ASM_X86_JUMP_LABEL_H
#define _ASM_X86_JUMP_LABEL_H
-#ifndef __ASSEMBLY__
-
-#include <linux/stringify.h>
-#include <linux/types.h>
-#include <asm/nops.h>
-#include <asm/asm.h>
+#ifndef HAVE_JUMP_LABEL
+/*
+ * For better or for worse, if jump labels (the gcc extension) are missing,
+ * then the entire static branch patching infrastructure is compiled out.
+ * If that happens, the code in here will malfunction. Raise a compiler
+ * error instead.
+ *
+ * In theory, jump labels and the static branch patching infrastructure
+ * could be decoupled to fix this.
+ */
+#error asm/jump_label.h included on a non-jump-label kernel
+#endif
#define JUMP_LABEL_NOP_SIZE 5
@@ -16,6 +22,14 @@
# define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
#endif
+#include <asm/asm.h>
+#include <asm/nops.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
asm_volatile_goto("1:"
@@ -59,5 +73,40 @@ struct jump_entry {
jump_label_t key;
};
-#endif /* __ASSEMBLY__ */
+#else /* __ASSEMBLY__ */
+
+.macro STATIC_JUMP_IF_TRUE target, key, def
+.Lstatic_jump_\@:
+ .if \def
+ /* Equivalent to "jmp.d32 \target" */
+ .byte 0xe9
+ .long \target - .Lstatic_jump_after_\@
+.Lstatic_jump_after_\@:
+ .else
+ .byte STATIC_KEY_INIT_NOP
+ .endif
+ .pushsection __jump_table, "aw"
+ _ASM_ALIGN
+ _ASM_PTR .Lstatic_jump_\@, \target, \key
+ .popsection
+.endm
+
+.macro STATIC_JUMP_IF_FALSE target, key, def
+.Lstatic_jump_\@:
+ .if \def
+ .byte STATIC_KEY_INIT_NOP
+ .else
+ /* Equivalent to "jmp.d32 \target" */
+ .byte 0xe9
+ .long \target - .Lstatic_jump_after_\@
+.Lstatic_jump_after_\@:
+ .endif
+ .pushsection __jump_table, "aw"
+ _ASM_ALIGN
+ _ASM_PTR .Lstatic_jump_\@, \target, \key + 1
+ .popsection
+.endm
+
+#endif /* __ASSEMBLY__ */
+
#endif
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 10d0596433f8..1b71c3aeae86 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -922,23 +922,11 @@ extern void default_banner(void);
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#define USERGS_SYSRET32 \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \
- CLBR_NONE, \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
-
#ifdef CONFIG_X86_32
#define GET_CR0_INTO_EAX \
push %ecx; push %edx; \
call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \
pop %edx; pop %ecx
-
-#define ENABLE_INTERRUPTS_SYSEXIT \
- PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \
- CLBR_NONE, \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
-
-
#else /* !CONFIG_X86_32 */
/*
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 31247b5bff7c..702c8bdf7b66 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -157,15 +157,6 @@ struct pv_cpu_ops {
u64 (*read_pmc)(int counter);
-#ifdef CONFIG_X86_32
- /*
- * Atomically enable interrupts and return to userspace. This
- * is only used in 32-bit kernels. 64-bit kernels use
- * usergs_sysret32 instead.
- */
- void (*irq_enable_sysexit)(void);
-#endif
-
/*
* Switch to usermode gs and return to 64-bit usermode using
* sysret. Only used in 64-bit kernels to return to 64-bit
@@ -174,14 +165,6 @@ struct pv_cpu_ops {
*/
void (*usergs_sysret64)(void);
- /*
- * Switch to usermode gs and return to 32-bit usermode using
- * sysret. Used to return to 32-on-64 compat processes.
- * Other usermode register state, including %esp, must already
- * be restored.
- */
- void (*usergs_sysret32)(void);
-
/* Normal iret. Jump to this with the standard iret stack
frame set up. */
void (*iret)(void);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 7a6bed5c08bc..fdcc04020636 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -4,6 +4,15 @@
#include <linux/clocksource.h>
#include <asm/pvclock-abi.h>
+#ifdef CONFIG_KVM_GUEST
+extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+ return NULL;
+}
+#endif
+
/* some helper functions for xen and kvm pv clock sources */
cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
@@ -91,10 +100,5 @@ struct pvclock_vsyscall_time_info {
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
-#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1)
-
-int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
- int size);
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu);
#endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 756de9190aec..deabaf9759b6 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -22,6 +22,7 @@ struct vdso_image {
long sym_vvar_page;
long sym_hpet_page;
+ long sym_pvclock_page;
long sym_VDSO32_NOTE_MASK;
long sym___kernel_sigreturn;
long sym___kernel_rt_sigreturn;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 439df975bc7a..84a7524b202c 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -65,9 +65,6 @@ void common(void) {
OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable);
OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable);
OFFSET(PV_CPU_iret, pv_cpu_ops, iret);
-#ifdef CONFIG_X86_32
- OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit);
-#endif
OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0);
OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2);
#endif
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index d8f42f902a0f..f2edafb5f24e 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -23,7 +23,6 @@ int main(void)
{
#ifdef CONFIG_PARAVIRT
OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame);
- OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32);
OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
BLANK();
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2bd81e302427..72cef58693c7 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock);
static struct pvclock_vsyscall_time_info *hv_clock;
static struct pvclock_wall_clock wall_clock;
+struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
+{
+ return hv_clock;
+}
+
/*
* The wallclock is the time of day when we booted. Since then, some time may
* have elapsed since the hypervisor wrote the data. So we try to account for
@@ -305,7 +310,6 @@ int __init kvm_setup_vsyscall_timeinfo(void)
{
#ifdef CONFIG_X86_64
int cpu;
- int ret;
u8 flags;
struct pvclock_vcpu_time_info *vcpu_time;
unsigned int size;
@@ -325,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void)
return 1;
}
- if ((ret = pvclock_init_vsyscall(hv_clock, size))) {
- put_cpu();
- return ret;
- }
-
put_cpu();
kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c2130aef3f9d..8c19b4d5e719 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -162,10 +162,6 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
ret = paravirt_patch_ident_64(insnbuf, len);
else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) ||
-#ifdef CONFIG_X86_32
- type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) ||
-#endif
- type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) ||
type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64))
/* If operation requires a jmp, then jmp */
ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len);
@@ -220,8 +216,6 @@ static u64 native_steal_clock(int cpu)
/* These are in entry.S */
extern void native_iret(void);
-extern void native_irq_enable_sysexit(void);
-extern void native_usergs_sysret32(void);
extern void native_usergs_sysret64(void);
static struct resource reserve_ioports = {
@@ -379,13 +373,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
.load_sp0 = native_load_sp0,
-#if defined(CONFIG_X86_32)
- .irq_enable_sysexit = native_irq_enable_sysexit,
-#endif
#ifdef CONFIG_X86_64
-#ifdef CONFIG_IA32_EMULATION
- .usergs_sysret32 = native_usergs_sysret32,
-#endif
.usergs_sysret64 = native_usergs_sysret64,
#endif
.iret = native_iret,
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index c89f50a76e97..158dc0650d5d 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -5,7 +5,6 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf");
DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax");
DEF_NATIVE(pv_cpu_ops, iret, "iret");
-DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit");
DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
@@ -46,7 +45,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_irq_ops, restore_fl);
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_cpu_ops, iret);
- PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_mmu_ops, read_cr2);
PATCH_SITE(pv_mmu_ops, read_cr3);
PATCH_SITE(pv_mmu_ops, write_cr3);
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 8aa05583bc42..e70087a04cc8 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
DEF_NATIVE(pv_cpu_ops, clts, "clts");
DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
-DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit");
DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
-DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl");
DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
DEF_NATIVE(, mov32, "mov %edi, %eax");
@@ -55,7 +53,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);
PATCH_SITE(pv_cpu_ops, swapgs);
PATCH_SITE(pv_mmu_ops, read_cr2);
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d229a58..99bfc025111d 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
-
-#ifdef CONFIG_X86_64
-/*
- * Initialize the generic pvclock vsyscall state. This will allocate
- * a/some page(s) for the per-vcpu pvclock information, set up a
- * fixmap mapping for the page(s)
- */
-
-int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
- int size)
-{
- int idx;
-
- WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
-
- for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
- __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
- __pa(i) + (idx*PAGE_SIZE),
- PAGE_KERNEL_VVAR);
- }
-
- return 0;
-}
-#endif
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 327f21c3bde1..8dd80050d705 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -28,6 +28,7 @@
#include <linux/nmi.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/clocksource.h>
#include <asm/apic.h>
#include <asm/current.h>
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 5774800ff583..a068e36382b7 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1229,10 +1229,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.iret = xen_iret,
#ifdef CONFIG_X86_64
- .usergs_sysret32 = xen_sysret32,
.usergs_sysret64 = xen_sysret64,
-#else
- .irq_enable_sysexit = xen_sysexit,
#endif
.load_tr_desc = paravirt_nop,
@@ -1886,8 +1883,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic);
static void xen_set_cpu_features(struct cpuinfo_x86 *c)
{
- if (xen_pv_domain())
+ if (xen_pv_domain()) {
clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+ set_cpu_cap(c, X86_FEATURE_XENPV);
+ }
}
const struct hypervisor_x86 x86_hyper_xen = {
diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S
index fd92a64d748e..feb6d40a0860 100644
--- a/arch/x86/xen/xen-asm_32.S
+++ b/arch/x86/xen/xen-asm_32.S
@@ -35,20 +35,6 @@
ret
/*
- * We can't use sysexit directly, because we're not running in ring0.
- * But we can easily fake it up using iret. Assuming xen_sysexit is
- * jumped to with a standard stack frame, we can just strip it back to
- * a standard iret frame and use iret.
- */
-ENTRY(xen_sysexit)
- movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */
- orl $X86_EFLAGS_IF, PT_EFLAGS(%esp)
- lea PT_EIP(%esp), %esp
-
- jmp xen_iret
-ENDPROC(xen_sysexit)
-
-/*
* This is run where a normal iret would be run, with the same stack setup:
* 8: eflags
* 4: cs
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index f22667abf7b9..cc8acc410ddb 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -68,25 +68,6 @@ ENTRY(xen_sysret64)
ENDPATCH(xen_sysret64)
RELOC(xen_sysret64, 1b+1)
-ENTRY(xen_sysret32)
- /*
- * We're already on the usermode stack at this point, but
- * still with the kernel gs, so we can easily switch back
- */
- movq %rsp, PER_CPU_VAR(rsp_scratch)
- movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-
- pushq $__USER32_DS
- pushq PER_CPU_VAR(rsp_scratch)
- pushq %r11
- pushq $__USER32_CS
- pushq %rcx
-
- pushq $0
-1: jmp hypercall_iret
-ENDPATCH(xen_sysret32)
-RELOC(xen_sysret32, 1b+1)
-
/*
* Xen handles syscall callbacks much like ordinary exceptions, which
* means we have:
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 1399423f3418..4140b070f2e9 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -139,9 +139,6 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long);
/* These are not functions, and cannot be called normally */
__visible void xen_iret(void);
-#ifdef CONFIG_X86_32
-__visible void xen_sysexit(void);
-#endif
__visible void xen_sysret32(void);
__visible void xen_sysret64(void);
__visible void xen_adjust_exception_frame(void);
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index ee956c528fab..1d34fe68f48a 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -22,12 +22,12 @@ struct context_tracking {
};
#ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key context_tracking_enabled;
+extern struct static_key_false context_tracking_enabled;
DECLARE_PER_CPU(struct context_tracking, context_tracking);
static inline bool context_tracking_is_enabled(void)
{
- return static_key_false(&context_tracking_enabled);
+ return static_branch_unlikely(&context_tracking_enabled);
}
static inline bool context_tracking_cpu_is_enabled(void)
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index d8560ee3bab7..9ad37b9e44a7 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -24,7 +24,7 @@
#define CREATE_TRACE_POINTS
#include <trace/events/context_tracking.h>
-struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE;
+DEFINE_STATIC_KEY_FALSE(context_tracking_enabled);
EXPORT_SYMBOL_GPL(context_tracking_enabled);
DEFINE_PER_CPU(struct context_tracking, context_tracking);
@@ -191,7 +191,7 @@ void __init context_tracking_cpu_set(int cpu)
if (!per_cpu(context_tracking.active, cpu)) {
per_cpu(context_tracking.active, cpu) = true;
- static_key_slow_inc(&context_tracking_enabled);
+ static_branch_inc(&context_tracking_enabled);
}
if (initialized)
Powered by blists - more mailing lists