Merge branch 'x86/urgent' into x86/asm, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

7 files changed, 41 insertions, 28 deletions

diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index fe91c25092da..77f28ce9c646 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -5,6 +5,8 @@
 OBJECT_FILES_NON_STANDARD_entry_$(BITS).o   := y
 OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
 
+CFLAGS_syscall_64.o		+= -Wno-override-init
+CFLAGS_syscall_32.o		+= -Wno-override-init
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index a1e71d431fed..1433f6b4607d 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -204,8 +204,12 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	 * handling, because syscall restart has a fixup for compat
 	 * syscalls.  The fixup is exercised by the ptrace_syscall_32
 	 * selftest.
+	 *
+	 * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
+	 * special case only applies after poking regs and before the
+	 * very next return to user mode.
 	 */
-	ti->status &= ~TS_COMPAT;
+	ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
 #endif
 
 	user_enter_irqoff();
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8956eae04c25..f6b40e5c88f1 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -288,11 +288,15 @@ return_from_SYSCALL_64:
 	jne	opportunistic_sysret_failed
 
 	/*
-	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
-	 * restoring TF results in a trap from userspace immediately after
-	 * SYSRET.  This would cause an infinite loop whenever #DB happens
-	 * with register state that satisfies the opportunistic SYSRET
-	 * conditions.  For example, single-stepping this user code:
+	 * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
+	 * restore RF properly. If the slowpath sets it for whatever reason, we
+	 * need to restore it correctly.
+	 *
+	 * SYSRET can restore TF, but unlike IRET, restoring TF results in a
+	 * trap from userspace immediately after SYSRET.  This would cause an
+	 * infinite loop whenever #DB happens with register state that satisfies
+	 * the opportunistic SYSRET conditions.  For example, single-stepping
+	 * this user code:
 	 *
 	 *           movq	$stuck_here, %rcx
 	 *           pushfq
@@ -600,9 +604,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym)
 .endm
 #endif
 
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+# define PUSH_SECTION_IRQENTRY	.pushsection .irqentry.text, "ax"
+# define POP_SECTION_IRQENTRY	.popsection
+#else
+# define PUSH_SECTION_IRQENTRY
+# define POP_SECTION_IRQENTRY
+#endif
+
 .macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
 apicinterrupt3 \num \sym \do_sym
 trace_apicinterrupt \num \sym
+POP_SECTION_IRQENTRY
 .endm
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 4cddd17153fb..f848572169ea 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -294,7 +294,7 @@
 # 285 sys_setaltroot
 286	i386	add_key			sys_add_key
 287	i386	request_key		sys_request_key
-288	i386	keyctl			sys_keyctl
+288	i386	keyctl			sys_keyctl			compat_sys_keyctl
 289	i386	ioprio_set		sys_ioprio_set
 290	i386	ioprio_get		sys_ioprio_get
 291	i386	inotify_init		sys_inotify_init
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 6ba89a1ab0e5..d5409660f5de 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -75,7 +75,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
        -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
-$(vobjs): KBUILD_CFLAGS += $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
@@ -145,6 +145,7 @@ KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 2f02d23a05ef..94d54d0defa7 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -96,9 +96,8 @@ static notrace cycle_t vread_pvclock(int *mode)
 {
 	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;
+	u64 last;
+	u32 version;
 
 	/*
 	 * Note: The kernel and hypervisor must guarantee that cpu ID
@@ -123,29 +122,15 @@ static notrace cycle_t vread_pvclock(int *mode)
 	 */
 
 	do {
-		version = pvti->version;
-
-		smp_rmb();
+		version = pvclock_read_begin(pvti);
 
 		if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
 			*mode = VCLOCK_NONE;
 			return 0;
 		}
 
-		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);
+		ret = __pvclock_read_cycles(pvti);
+	} while (pvclock_read_retry(pvti, version));
 
 	/* refer to vread_tsc() comment for rationale */
 	last = gtod->cycle_last;
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index 63a03bb91497..4f741192846d 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -22,6 +22,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 
 	ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
 
+	if (hdr->e_type != ET_DYN)
+		fail("input is not a shared object\n");
+
 	/* Walk the segment table. */
 	for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
 		if (GET_LE(&pt[i].p_type) == PT_LOAD) {
@@ -49,6 +52,9 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	if (stripped_len < load_size)
 		fail("stripped input is too short\n");
 
+	if (!dyn)
+		fail("input has no PT_DYNAMIC section -- your toolchain is buggy\n");
+
 	/* Walk the dynamic table */
 	for (i = 0; dyn + i < dyn_end &&
 		     GET_LE(&dyn[i].d_tag) != DT_NULL; i++) {