Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull spectre/meltdown updates from Thomas Gleixner:
 "The next round of updates related to melted spectrum:

   - The initial set of spectre V1 mitigations:

       - Array index speculation blocker and its usage for syscall,
         fdtable and the n180211 driver.

       - Speculation barrier and its usage in user access functions

   - Make indirect calls in KVM speculation safe

   - Blacklisting of known to be broken microcodes so IPBP/IBSR are not
     touched.

   - The initial IBPB support and its usage in context switch

   - The exposure of the new speculation MSRs to KVM guests.

   - A fix for a regression in x86/32 related to the cpu entry area

   - Proper whitelisting for known to be safe CPUs from the mitigations.

   - objtool fixes to deal proper with retpolines and alternatives

   - Exclude __init functions from retpolines which speeds up the boot
     process.

   - Removal of the syscall64 fast path and related cleanups and
     simplifications

   - Removal of the unpatched paravirt mode which is yet another source
     of indirect unproteced calls.

   - A new and undisputed version of the module mismatch warning

   - A couple of cleanup and correctness fixes all over the place

  Yet another step towards full mitigation. There are a few things still
  missing like the RBS underflow mitigation for Skylake and other small
  details, but that's being worked on.

  That said, I'm taking a belated christmas vacation for a week and hope
  that everything is magically solved when I'm back on Feb 12th"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  KVM/SVM: Allow direct access to MSR_IA32_SPEC_CTRL
  KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL
  KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES
  KVM/x86: Add IBPB support
  KVM/x86: Update the reverse_cpuid list to include CPUID_7_EDX
  x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL
  x86/pti: Mark constant arrays as __initconst
  x86/spectre: Simplify spectre_v2 command line parsing
  x86/retpoline: Avoid retpolines for built-in __init functions
  x86/kvm: Update spectre-v1 mitigation
  KVM: VMX: make MSR bitmaps per-VCPU
  x86/paravirt: Remove 'noreplace-paravirt' cmdline option
  x86/speculation: Use Indirect Branch Prediction Barrier in context switch
  x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel
  x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable"
  x86/spectre: Report get_user mitigation for spectre_v1
  nl80211: Sanitize array index in parse_txq_params
  vfs, fdtable: Prevent bounds-check bypass via speculative execution
  x86/syscall: Sanitize syscall table de-references under speculation
  x86/get_user: Use pointer masking to limit speculation
  ...

12 files changed, 65 insertions, 25 deletions

diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 7fb336210e1b..30d406146016 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -24,6 +24,34 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
+/**
+ * array_index_mask_nospec() - generate a mask that is ~0UL when the
+ * 	bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * Returns:
+ *     0 - (index < size)
+ */
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+		unsigned long size)
+{
+	unsigned long mask;
+
+	asm ("cmp %1,%2; sbb %0,%0;"
+			:"=r" (mask)
+			:"r"(size),"r" (index)
+			:"cc");
+	return mask;
+}
+
+/* Override the default implementation from linux/nospec.h. */
+#define array_index_mask_nospec array_index_mask_nospec
+
+/* Prevent speculative execution past this barrier. */
+#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
+					   "lfence", X86_FEATURE_LFENCE_RDTSC)
+
 #ifdef CONFIG_X86_PPRO_FENCE
 #define dma_rmb()	rmb()
 #else
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 64c4a30e0d39..e203169931c7 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -137,8 +137,10 @@ enum fixed_addresses {
 
 extern void reserve_top_address(unsigned long reserve);
 
-#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_SIZE		(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_TOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_TOT_START	(FIXADDR_TOP - FIXADDR_TOT_SIZE)
 
 extern int fixmaps_set;
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 07962f5f6fba..30df295f6d94 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -214,8 +214,7 @@ static __always_inline unsigned long long rdtsc_ordered(void)
 	 * that some other imaginary CPU is updating continuously with a
 	 * time stamp.
 	 */
-	alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
-			  "lfence", X86_FEATURE_LFENCE_RDTSC);
+	barrier_nospec();
 	return rdtsc();
 }
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index d15d471348b8..4d57894635f2 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -150,7 +150,7 @@ extern char __indirect_thunk_end[];
  * On VMEXIT we must ensure that no RSB predictions learned in the guest
  * can be followed in the host, by overwriting the RSB completely. Both
  * retpoline and IBRS mitigations for Spectre v2 need this; only on future
- * CPUs with IBRS_ATT *might* it be avoided.
+ * CPUs with IBRS_ALL *might* it be avoided.
  */
 static inline void vmexit_fill_RSB(void)
 {
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index ce245b0cdfca..0777e18a1d23 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -44,8 +44,9 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
  */
 #define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
 
-#define CPU_ENTRY_AREA_BASE				\
-	((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+#define CPU_ENTRY_AREA_BASE						\
+	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
+	 & PMD_MASK)
 
 #define PKMAP_BASE		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 6207f2f740b6..793bae7e7ce3 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -460,8 +460,6 @@ struct thread_struct {
 	unsigned short		gsindex;
 #endif
 
-	u32			status;		/* thread synchronous flags */
-
 #ifdef CONFIG_X86_64
 	unsigned long		fsbase;
 	unsigned long		gsbase;
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index e3c95e8e61c5..03eedc21246d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task,
 	 * TS_COMPAT is set for 32-bit syscall entries and then
 	 * remains set until we return to user mode.
 	 */
-	if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED))
 		/*
 		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
 		 * and will match correctly in comparisons.
@@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread.status & TS_COMPAT)
+	if (task->thread_info.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
@@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 const unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread.status & TS_COMPAT)
+	if (task->thread_info.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index d25a638a2720..a5d9521bb2cb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -55,6 +55,7 @@ struct task_struct;
 
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
+	u32			status;		/* thread synchronous flags */
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -219,7 +220,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #define in_ia32_syscall() true
 #else
 #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \
-			   current->thread.status & TS_COMPAT)
+			   current_thread_info()->status & TS_COMPAT)
 #endif
 
 /*
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index d33e4a26dc7e..2b8f18ca5874 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -174,6 +174,8 @@ struct tlb_state {
 	struct mm_struct *loaded_mm;
 	u16 loaded_mm_asid;
 	u16 next_asid;
+	/* last user mm's ctx id */
+	u64 last_ctx_id;
 
 	/*
 	 * We can be in one of several states:
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 574dff4d2913..aae77eb8491c 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -124,6 +124,11 @@ extern int __get_user_bad(void);
 
 #define __uaccess_begin() stac()
 #define __uaccess_end()   clac()
+#define __uaccess_begin_nospec()	\
+({					\
+	stac();				\
+	barrier_nospec();		\
+})
 
 /*
  * This is a type: either unsigned long, if the argument fits into
@@ -445,7 +450,7 @@ do {									\
 ({									\
 	int __gu_err;							\
 	__inttype(*(ptr)) __gu_val;					\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	__uaccess_end();						\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -487,6 +492,10 @@ struct __large_struct { unsigned long buf[100]; };
 	__uaccess_begin();						\
 	barrier();
 
+#define uaccess_try_nospec do {						\
+	current->thread.uaccess_err = 0;				\
+	__uaccess_begin_nospec();					\
+
 #define uaccess_catch(err)						\
 	__uaccess_end();						\
 	(err) |= (current->thread.uaccess_err ? -EFAULT : 0);		\
@@ -548,7 +557,7 @@ struct __large_struct { unsigned long buf[100]; };
  *	get_user_ex(...);
  * } get_user_catch(err)
  */
-#define get_user_try		uaccess_try
+#define get_user_try		uaccess_try_nospec
 #define get_user_catch(err)	uaccess_catch(err)
 
 #define get_user_ex(x, ptr)	do {					\
@@ -582,7 +591,7 @@ extern void __cmpxchg_wrong_size(void)
 	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	switch (size) {							\
 	case 1:								\
 	{								\
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 72950401b223..ba2dc1930630 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -29,21 +29,21 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 		switch (n) {
 		case 1:
 			ret = 0;
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_asm_nozero(*(u8 *)to, from, ret,
 					      "b", "b", "=q", 1);
 			__uaccess_end();
 			return ret;
 		case 2:
 			ret = 0;
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_asm_nozero(*(u16 *)to, from, ret,
 					      "w", "w", "=r", 2);
 			__uaccess_end();
 			return ret;
 		case 4:
 			ret = 0;
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_asm_nozero(*(u32 *)to, from, ret,
 					      "l", "k", "=r", 4);
 			__uaccess_end();
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f07ef3c575db..62546b3a398e 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -55,31 +55,31 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
 	case 1:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
 		__uaccess_end();
 		return ret;
 	case 2:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 4:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
 	case 8:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
 		__uaccess_end();
 		return ret;
 	case 10:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
 		if (likely(!ret))
@@ -89,7 +89,7 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 		__uaccess_end();
 		return ret;
 	case 16:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
 		if (likely(!ret))