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

Pull x86 fixes from Ingo Molnar:
 "Misc fixes: EFI, entry code, pkeys and MPX fixes, TASK_SIZE cleanups
  and a tsc frequency table fix"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Switch from TASK_SIZE to TASK_SIZE_MAX in the page fault code
  x86/fsgsbase/64: Use TASK_SIZE_MAX for FSBASE/GSBASE upper limits
  x86/mm/mpx: Work around MPX erratum SKD046
  x86/entry/64: Fix stack return address retrieval in thunk
  x86/efi: Fix 7-parameter efi_call()s
  x86/cpufeature, x86/mm/pkeys: Fix broken compile-time disabling of pkeys
  x86/tsc: Add missing Cherrytrail frequency to the table

arch/x86/entry/thunk_64.S

@@ -8,16 +8,15 @@
 #include <linux/linkage.h>
 #include "calling.h"
 #include <asm/asm.h>
-#include <asm/frame.h>
 
 	/* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 	.macro THUNK name, func, put_ret_addr_in_rdi=0
 	.globl \name
 	.type \name, @function
 \name:
-	FRAME_BEGIN
+	pushq %rbp
+	movq %rsp, %rbp
 
-	/* this one pushes 9 elems, the next one would be %rIP */
 	pushq %rdi
 	pushq %rsi
 	pushq %rdx
@@ -29,8 +28,8 @@
 	pushq %r11
 
 	.if \put_ret_addr_in_rdi
-	/* 9*8(%rsp) is return addr on stack */
-	movq 9*8(%rsp), %rdi
+	/* 8(%rbp) is return addr on stack */
+	movq 8(%rbp), %rdi
 	.endif
 
 	call \func
@@ -65,7 +64,7 @@ restore:
 	popq %rdx
 	popq %rsi
 	popq %rdi
-	FRAME_END
+	popq %rbp
 	ret
 	_ASM_NOKPROBE(restore)
 #endif

arch/x86/include/asm/bugs.h

@@ -1,8 +1,16 @@
 #ifndef _ASM_X86_BUGS_H
 #define _ASM_X86_BUGS_H
 
+#include <asm/processor.h>
+
 extern void check_bugs(void);
 
+#if defined(CONFIG_CPU_SUP_INTEL)
+void check_mpx_erratum(struct cpuinfo_x86 *c);
+#else
+static inline void check_mpx_erratum(struct cpuinfo_x86 *c) {}
+#endif
+
 #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
 int ppro_with_ram_bug(void);
 #else

arch/x86/include/asm/cpufeature.h

@@ -64,9 +64,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
 	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
 	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
+	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
+	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
 
 #define DISABLED_MASK_BIT_SET(bit)					\
 	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
@@ -83,9 +83,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
 	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
 	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
+	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
+	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\

arch/x86/include/asm/disabled-features.h

@@ -29,11 +29,11 @@
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE))
-#else
 # define DISABLE_PKU		0
 # define DISABLE_OSPKE		0
+#else
+# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
+# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
 #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
 
 /*

arch/x86/kernel/cpu/common.c

@@ -37,6 +37,7 @@
 #include <asm/mtrr.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
+#include <asm/bugs.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
@@ -270,6 +271,8 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
 static __init int setup_disable_smep(char *arg)
 {
 	setup_clear_cpu_cap(X86_FEATURE_SMEP);
+	/* Check for things that depend on SMEP being enabled: */
+	check_mpx_erratum(&boot_cpu_data);
 	return 1;
 }
 __setup("nosmep", setup_disable_smep);
@@ -310,6 +313,10 @@ static bool pku_disabled;
 
 static __always_inline void setup_pku(struct cpuinfo_x86 *c)
 {
+	/* check the boot processor, plus compile options for PKU: */
+	if (!cpu_feature_enabled(X86_FEATURE_PKU))
+		return;
+	/* checks the actual processor's cpuid bits: */
 	if (!cpu_has(c, X86_FEATURE_PKU))
 		return;
 	if (pku_disabled)

arch/x86/kernel/cpu/intel.c

@@ -25,6 +25,41 @@
 #include <asm/apic.h>
 #endif
 
+/*
+ * Just in case our CPU detection goes bad, or you have a weird system,
+ * allow a way to override the automatic disabling of MPX.
+ */
+static int forcempx;
+
+static int __init forcempx_setup(char *__unused)
+{
+	forcempx = 1;
+
+	return 1;
+}
+__setup("intel-skd-046-workaround=disable", forcempx_setup);
+
+void check_mpx_erratum(struct cpuinfo_x86 *c)
+{
+	if (forcempx)
+		return;
+	/*
+	 * Turn off the MPX feature on CPUs where SMEP is not
+	 * available or disabled.
+	 *
+	 * Works around Intel Erratum SKD046: "Branch Instructions
+	 * May Initialize MPX Bound Registers Incorrectly".
+	 *
+	 * This might falsely disable MPX on systems without
+	 * SMEP, like Atom processors without SMEP.  But there
+	 * is no such hardware known at the moment.
+	 */
+	if (cpu_has(c, X86_FEATURE_MPX) && !cpu_has(c, X86_FEATURE_SMEP)) {
+		setup_clear_cpu_cap(X86_FEATURE_MPX);
+		pr_warn("x86/mpx: Disabling MPX since SMEP not present\n");
+	}
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -173,6 +208,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		if (edx & (1U << 28))
 			c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
 	}
+
+	check_mpx_erratum(c);
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/process_64.c

@@ -532,7 +532,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 
 	switch (code) {
 	case ARCH_SET_GS:
-		if (addr >= TASK_SIZE_OF(task))
+		if (addr >= TASK_SIZE_MAX)
 			return -EPERM;
 		cpu = get_cpu();
 		task->thread.gsindex = 0;
@@ -546,7 +546,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 	case ARCH_SET_FS:
 		/* Not strictly needed for fs, but do it for symmetry
 		   with gs */
-		if (addr >= TASK_SIZE_OF(task))
+		if (addr >= TASK_SIZE_MAX)
 			return -EPERM;
 		cpu = get_cpu();
 		task->thread.fsindex = 0;

arch/x86/kernel/ptrace.c

@@ -392,7 +392,7 @@ static int putreg(struct task_struct *child,
 
 #ifdef CONFIG_X86_64
 	case offsetof(struct user_regs_struct,fs_base):
-		if (value >= TASK_SIZE_OF(child))
+		if (value >= TASK_SIZE_MAX)
 			return -EIO;
 		/*
 		 * When changing the segment base, use do_arch_prctl
@@ -406,7 +406,7 @@ static int putreg(struct task_struct *child,
 		/*
 		 * Exactly the same here as the %fs handling above.
 		 */
-		if (value >= TASK_SIZE_OF(child))
+		if (value >= TASK_SIZE_MAX)
 			return -EIO;
 		if (child->thread.gsbase != value)
 			return do_arch_prctl(child, ARCH_SET_GS, value);

arch/x86/kernel/tsc_msr.c

@@ -23,6 +23,7 @@
 #include <asm/param.h>
 
 /* CPU reference clock frequency: in KHz */
+#define FREQ_80		80000
 #define FREQ_83		83200
 #define FREQ_100	99840
 #define FREQ_133	133200
@@ -56,6 +57,8 @@ static struct freq_desc freq_desc_tables[] = {
 	{ 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
 	/* ANN */
 	{ 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } },
+	/* AIRMONT */
+	{ 6, 0x4c, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, FREQ_80,	0, 0, 0 } },
 };
 
 static int match_cpu(u8 family, u8 model)

arch/x86/mm/fault.c

@@ -292,7 +292,7 @@ void vmalloc_sync_all(void)
 		return;
 
 	for (address = VMALLOC_START & PMD_MASK;
-	     address >= TASK_SIZE && address < FIXADDR_TOP;
+	     address >= TASK_SIZE_MAX && address < FIXADDR_TOP;
 	     address += PMD_SIZE) {
 		struct page *page;
 
@@ -854,8 +854,13 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
 				return;
 		}
 #endif
-		/* Kernel addresses are always protection faults: */
-		if (address >= TASK_SIZE)
+
+		/*
+		 * To avoid leaking information about the kernel page table
+		 * layout, pretend that user-mode accesses to kernel addresses
+		 * are always protection faults.
+		 */
+		if (address >= TASK_SIZE_MAX)
 			error_code |= PF_PROT;
 
 		if (likely(show_unhandled_signals))

arch/x86/platform/efi/efi_stub_64.S

@@ -11,7 +11,6 @@
 #include <asm/msr.h>
 #include <asm/processor-flags.h>
 #include <asm/page_types.h>
-#include <asm/frame.h>
 
 #define SAVE_XMM			\
 	mov %rsp, %rax;			\
@@ -40,10 +39,10 @@
 	mov (%rsp), %rsp
 
 ENTRY(efi_call)
-	FRAME_BEGIN
+	pushq %rbp
+	movq %rsp, %rbp
 	SAVE_XMM
-	mov (%rsp), %rax
-	mov 8(%rax), %rax
+	mov 16(%rbp), %rax
 	subq $48, %rsp
 	mov %r9, 32(%rsp)
 	mov %rax, 40(%rsp)
@@ -53,6 +52,6 @@ ENTRY(efi_call)
 	call *%rdi
 	addq $48, %rsp
 	RESTORE_XMM
-	FRAME_END
+	popq %rbp
 	ret
 ENDPROC(efi_call)