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

Pull x86 asm updates from Ingo Molnar:
 "The main changes in this development cycle were:

   - a large number of call stack dumping/printing improvements: higher
     robustness, better cross-context dumping, improved output, etc.
     (Josh Poimboeuf)

   - vDSO getcpu() performance improvement for future Intel CPUs with
     the RDPID instruction (Andy Lutomirski)

   - add two new Intel AVX512 features and the CPUID support
     infrastructure for it: AVX512IFMA and AVX512VBMI. (Gayatri Kammela,
     He Chen)

   - more copy-user unification (Borislav Petkov)

   - entry code assembly macro simplifications (Alexander Kuleshov)

   - vDSO C/R support improvements (Dmitry Safonov)

   - misc fixes and cleanups (Borislav Petkov, Paul Bolle)"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  scripts/decode_stacktrace.sh: Fix address line detection on x86
  x86/boot/64: Use defines for page size
  x86/dumpstack: Make stack name tags more comprehensible
  selftests/x86: Add test_vdso to test getcpu()
  x86/vdso: Use RDPID in preference to LSL when available
  x86/dumpstack: Handle NULL stack pointer in show_trace_log_lvl()
  x86/cpufeatures: Enable new AVX512 cpu features
  x86/cpuid: Provide get_scattered_cpuid_leaf()
  x86/cpuid: Cleanup cpuid_regs definitions
  x86/copy_user: Unify the code by removing the 64-bit asm _copy_*_user() variants
  x86/unwind: Ensure stack grows down
  x86/vdso: Set vDSO pointer only after success
  x86/prctl/uapi: Remove #ifdef for CHECKPOINT_RESTORE
  x86/unwind: Detect bad stack return address
  x86/dumpstack: Warn on stack recursion
  x86/unwind: Warn on bad frame pointer
  x86/decoder: Use stderr if insn sanity test fails
  x86/decoder: Use stdout if insn decoder test is successful
  mm/page_alloc: Remove kernel address exposure in free_reserved_area()
  x86/dumpstack: Remove raw stack dump
  ...

Documentation/kernel-parameters.txt

@@ -1963,9 +1963,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			kmemcheck=2 (one-shot mode)
 			Default: 2 (one-shot mode)
 
-	kstack=N	[X86] Print N words from the kernel stack
-			in oops dumps.
-
 	kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs.
 			Default is 0 (don't ignore, but inject #GP)
 

Documentation/sysctl/kernel.txt

@@ -40,7 +40,6 @@ show up in /proc/sys/kernel:
 - hung_task_warnings
 - kexec_load_disabled
 - kptr_restrict
-- kstack_depth_to_print       [ X86 only ]
 - l2cr                        [ PPC only ]
 - modprobe                    ==> Documentation/debugging-modules.txt
 - modules_disabled
@@ -395,13 +394,6 @@ When kptr_restrict is set to (2), kernel pointers printed using
 
 ==============================================================
 
-kstack_depth_to_print: (X86 only)
-
-Controls the number of words to print when dumping the raw
-kernel stack.
-
-==============================================================
-
 l2cr: (PPC only)
 
 This flag controls the L2 cache of G3 processor boards. If

Documentation/x86/x86_64/boot-options.txt

@@ -277,10 +277,6 @@ IOMMU (input/output memory management unit)
     space might stop working. Use this option if you have devices that
     are accessed from userspace directly on some PCI host bridge.
 
-Debugging
-
-  kstack=N	Print N words from the kernel stack in oops dumps.
-
 Miscellaneous
 
 	nogbpages

arch/x86/entry/calling.h

@@ -90,8 +90,8 @@ For 32-bit we have the following conventions - kernel is built with
 
 #define SIZEOF_PTREGS	21*8
 
-	.macro ALLOC_PT_GPREGS_ON_STACK addskip=0
-	addq	$-(15*8+\addskip), %rsp
+	.macro ALLOC_PT_GPREGS_ON_STACK
+	addq	$-(15*8), %rsp
 	.endm
 
 	.macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1
@@ -147,15 +147,6 @@ For 32-bit we have the following conventions - kernel is built with
 	movq 5*8+\offset(%rsp), %rbx
 	.endm
 
-	.macro ZERO_EXTRA_REGS
-	xorl	%r15d, %r15d
-	xorl	%r14d, %r14d
-	xorl	%r13d, %r13d
-	xorl	%r12d, %r12d
-	xorl	%ebp, %ebp
-	xorl	%ebx, %ebx
-	.endm
-
 	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
 	.if \rstor_r11
 	movq 6*8(%rsp), %r11
@@ -201,6 +192,26 @@ For 32-bit we have the following conventions - kernel is built with
 	.byte 0xf1
 	.endm
 
+/*
+ * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
+ * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
+ * is just setting the LSB, which makes it an invalid stack address and is also
+ * a signal to the unwinder that it's a pt_regs pointer in disguise.
+ *
+ * NOTE: This macro must be used *after* SAVE_EXTRA_REGS because it corrupts
+ * the original rbp.
+ */
+.macro ENCODE_FRAME_POINTER ptregs_offset=0
+#ifdef CONFIG_FRAME_POINTER
+	.if \ptregs_offset
+		leaq \ptregs_offset(%rsp), %rbp
+	.else
+		mov %rsp, %rbp
+	.endif
+	orq	$0x1, %rbp
+#endif
+.endm
+
 #endif /* CONFIG_X86_64 */
 
 /*

arch/x86/entry/entry_64.S

@@ -38,12 +38,6 @@
 #include <asm/export.h>
 #include <linux/err.h>
 
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_X86_64			(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_64BIT			0x80000000
-#define __AUDIT_ARCH_LE				0x40000000
-
 .code64
 .section .entry.text, "ax"
 
@@ -469,6 +463,7 @@ END(irq_entries_start)
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
+	ENCODE_FRAME_POINTER
 
 	testb	$3, CS(%rsp)
 	jz	1f
@@ -985,6 +980,7 @@ ENTRY(xen_failsafe_callback)
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
+	ENCODE_FRAME_POINTER
 	jmp	error_exit
 END(xen_failsafe_callback)
 
@@ -1028,6 +1024,7 @@ ENTRY(paranoid_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	ENCODE_FRAME_POINTER 8
 	movl	$1, %ebx
 	movl	$MSR_GS_BASE, %ecx
 	rdmsr
@@ -1075,6 +1072,7 @@ ENTRY(error_entry)
 	cld
 	SAVE_C_REGS 8
 	SAVE_EXTRA_REGS 8
+	ENCODE_FRAME_POINTER 8
 	xorl	%ebx, %ebx
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
@@ -1257,6 +1255,7 @@ ENTRY(nmi)
 	pushq	%r13		/* pt_regs->r13 */
 	pushq	%r14		/* pt_regs->r14 */
 	pushq	%r15		/* pt_regs->r15 */
+	ENCODE_FRAME_POINTER
 
 	/*
 	 * At this point we no longer need to worry about stack damage
@@ -1270,11 +1269,10 @@ ENTRY(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.
+	 * work, because we don't want to enable interrupts.
 	 */
 	SWAPGS
-	jmp	restore_c_regs_and_iret
+	jmp	restore_regs_and_iret
 
 .Lnmi_from_kernel:
 	/*

arch/x86/entry/vdso/vma.c

@@ -161,8 +161,6 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 	}
 
 	text_start = addr - image->sym_vvar_start;
-	current->mm->context.vdso = (void __user *)text_start;
-	current->mm->context.vdso_image = image;
 
 	/*
 	 * MAYWRITE to allow gdb to COW and set breakpoints
@@ -189,14 +187,12 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr)
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		do_munmap(mm, text_start, image->size);
+	} else {
+		current->mm->context.vdso = (void __user *)text_start;
+		current->mm->context.vdso_image = image;
 	}
 
 up_fail:
-	if (ret) {
-		current->mm->context.vdso = NULL;
-		current->mm->context.vdso_image = NULL;
-	}
-
 	up_write(&mm->mmap_sem);
 	return ret;
 }

arch/x86/events/intel/pt.c

@@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx);
 
 static struct pt_pmu pt_pmu;
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
-};
-
 /*
  * Capabilities of Intel PT hardware, such as number of address bits or
  * supported output schemes, are cached and exported to userspace as "caps"
@@ -64,21 +57,21 @@ static struct pt_cap_desc {
 	u8		reg;
 	u32		mask;
 } pt_caps[] = {
-	PT_CAP(max_subleaf,		0, CR_EAX, 0xffffffff),
-	PT_CAP(cr3_filtering,		0, CR_EBX, BIT(0)),
-	PT_CAP(psb_cyc,			0, CR_EBX, BIT(1)),
-	PT_CAP(ip_filtering,		0, CR_EBX, BIT(2)),
-	PT_CAP(mtc,			0, CR_EBX, BIT(3)),
-	PT_CAP(ptwrite,			0, CR_EBX, BIT(4)),
-	PT_CAP(power_event_trace,	0, CR_EBX, BIT(5)),
-	PT_CAP(topa_output,		0, CR_ECX, BIT(0)),
-	PT_CAP(topa_multiple_entries,	0, CR_ECX, BIT(1)),
-	PT_CAP(single_range_output,	0, CR_ECX, BIT(2)),
-	PT_CAP(payloads_lip,		0, CR_ECX, BIT(31)),
-	PT_CAP(num_address_ranges,	1, CR_EAX, 0x3),
-	PT_CAP(mtc_periods,		1, CR_EAX, 0xffff0000),
-	PT_CAP(cycle_thresholds,	1, CR_EBX, 0xffff),
-	PT_CAP(psb_periods,		1, CR_EBX, 0xffff0000),
+	PT_CAP(max_subleaf,		0, CPUID_EAX, 0xffffffff),
+	PT_CAP(cr3_filtering,		0, CPUID_EBX, BIT(0)),
+	PT_CAP(psb_cyc,			0, CPUID_EBX, BIT(1)),
+	PT_CAP(ip_filtering,		0, CPUID_EBX, BIT(2)),
+	PT_CAP(mtc,			0, CPUID_EBX, BIT(3)),
+	PT_CAP(ptwrite,			0, CPUID_EBX, BIT(4)),
+	PT_CAP(power_event_trace,	0, CPUID_EBX, BIT(5)),
+	PT_CAP(topa_output,		0, CPUID_ECX, BIT(0)),
+	PT_CAP(topa_multiple_entries,	0, CPUID_ECX, BIT(1)),
+	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
+	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
+	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
+	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
+	PT_CAP(cycle_thresholds,	1, CPUID_EBX, 0xffff),
+	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
 };
 
 static u32 pt_cap_get(enum pt_capabilities cap)
@@ -213,10 +206,10 @@ static int __init pt_pmu_hw_init(void)
 
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
-			    &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM],
-			    &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]);
+			    &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM],
+			    &pt_pmu.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM]);
 	}
 
 	ret = -ENOMEM;

arch/x86/include/asm/cpufeatures.h

@@ -227,6 +227,7 @@
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
@@ -280,8 +281,10 @@
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */

arch/x86/include/asm/kdebug.h

@@ -21,7 +21,6 @@ enum die_val {
 	DIE_NMIUNKNOWN,
 };
 
-extern void printk_address(unsigned long address);
 extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);

arch/x86/include/asm/processor.h

@@ -137,6 +137,17 @@ struct cpuinfo_x86 {
 	u32			microcode;
 };
 
+struct cpuid_regs {
+	u32 eax, ebx, ecx, edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
 #define X86_VENDOR_INTEL	0
 #define X86_VENDOR_CYRIX	1
 #define X86_VENDOR_AMD		2
@@ -178,6 +189,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+				    unsigned int sub_leaf,
+				    enum cpuid_regs_idx reg);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 

arch/x86/include/asm/stacktrace.h

@@ -30,8 +30,7 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
 
-void stack_type_str(enum stack_type type, const char **begin,
-		    const char **end);
+const char *stack_type_name(enum stack_type type);
 
 static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
 {
@@ -43,8 +42,6 @@ static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
 		addr + len > begin && addr + len <= end);
 }
 
-extern int kstack_depth_to_print;
-
 #ifdef CONFIG_X86_32
 #define STACKSLOTS_PER_LINE 8
 #else
@@ -86,9 +83,6 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, char *log_lvl);
 
-void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-			unsigned long *sp, char *log_lvl);
-
 extern unsigned int code_bytes;
 
 /* The form of the top of the frame on the stack */

arch/x86/include/asm/unwind.h

@@ -13,6 +13,7 @@ struct unwind_state {
 	int graph_idx;
 #ifdef CONFIG_FRAME_POINTER
 	unsigned long *bp;
+	struct pt_regs *regs;
 #else
 	unsigned long *sp;
 #endif
@@ -47,7 +48,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	if (unwind_done(state))
 		return NULL;
 
-	return state->bp + 1;
+	return state->regs ? &state->regs->ip : state->bp + 1;
+}
+
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return NULL;
+
+	return state->regs;
 }
 
 #else /* !CONFIG_FRAME_POINTER */
@@ -58,6 +67,11 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	return NULL;
 }
 
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_FRAME_POINTER */
 
 #endif /* _ASM_X86_UNWIND_H */

arch/x86/include/asm/vgtod.h

@@ -89,8 +89,13 @@ static inline unsigned int __getcpu(void)
 	 * works on all CPUs.  This is volatile so that it orders
 	 * correctly wrt barrier() and to keep gcc from cleverly
 	 * hoisting it out of the calling function.
+	 *
+	 * If RDPID is available, use it.
 	 */
-	asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+	alternative_io ("lsl %[p],%[seg]",
+			".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */
+			X86_FEATURE_RDPID,
+			[p] "=a" (p), [seg] "r" (__PER_CPU_SEG));
 
 	return p;
 }

arch/x86/include/uapi/asm/prctl.h

@@ -6,10 +6,8 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
-#ifdef CONFIG_CHECKPOINT_RESTORE
-# define ARCH_MAP_VDSO_X32	0x2001
-# define ARCH_MAP_VDSO_32	0x2002
-# define ARCH_MAP_VDSO_64	0x2003
-#endif
+#define ARCH_MAP_VDSO_X32	0x2001
+#define ARCH_MAP_VDSO_32	0x2002
+#define ARCH_MAP_VDSO_64	0x2003
 
 #endif /* _ASM_X86_PRCTL_H */

arch/x86/kernel/cpu/scattered.c

@@ -17,11 +17,17 @@ struct cpuid_bit {
 	u32 sub_leaf;
 };
 
-enum cpuid_regs {
-	CR_EAX = 0,
-	CR_ECX,
-	CR_EDX,
-	CR_EBX
+/* Please keep the leaf sorted by cpuid_bit.level for faster search. */
+static const struct cpuid_bit cpuid_bits[] = {
+	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
+	{ X86_FEATURE_EPB,              CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_INTEL_PT,         CPUID_EBX, 25, 0x00000007, 0 },
+	{ X86_FEATURE_AVX512_4VNNIW,    CPUID_EDX,  2, 0x00000007, 0 },
+	{ X86_FEATURE_AVX512_4FMAPS,    CPUID_EDX,  3, 0x00000007, 0 },
+	{ X86_FEATURE_HW_PSTATE,        CPUID_EDX,  7, 0x80000007, 0 },
+	{ X86_FEATURE_CPB,              CPUID_EDX,  9, 0x80000007, 0 },
+	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
+	{ 0, 0, 0, 0, 0 }
 };
 
 void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
@@ -30,18 +36,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 	u32 regs[4];
 	const struct cpuid_bit *cb;
 
-	static const struct cpuid_bit cpuid_bits[] = {
-		{ X86_FEATURE_INTEL_PT,		CR_EBX,25, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4VNNIW,	CR_EDX, 2, 0x00000007, 0 },
-		{ X86_FEATURE_AVX512_4FMAPS,	CR_EDX, 3, 0x00000007, 0 },
-		{ X86_FEATURE_APERFMPERF,	CR_ECX, 0, 0x00000006, 0 },
-		{ X86_FEATURE_EPB,		CR_ECX, 3, 0x00000006, 0 },
-		{ X86_FEATURE_HW_PSTATE,	CR_EDX, 7, 0x80000007, 0 },
-		{ X86_FEATURE_CPB,		CR_EDX, 9, 0x80000007, 0 },
-		{ X86_FEATURE_PROC_FEEDBACK,	CR_EDX,11, 0x80000007, 0 },
-		{ 0, 0, 0, 0, 0 }
-	};
-
 	for (cb = cpuid_bits; cb->feature; cb++) {
 
 		/* Verify that the level is valid */
@@ -50,10 +44,35 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		    max_level > (cb->level | 0xffff))
 			continue;
 
-		cpuid_count(cb->level, cb->sub_leaf, &regs[CR_EAX],
-			    &regs[CR_EBX], &regs[CR_ECX], &regs[CR_EDX]);
+		cpuid_count(cb->level, cb->sub_leaf, &regs[CPUID_EAX],
+			    &regs[CPUID_EBX], &regs[CPUID_ECX],
+			    &regs[CPUID_EDX]);
 
 		if (regs[cb->reg] & (1 << cb->bit))
 			set_cpu_cap(c, cb->feature);
 	}
 }
+
+u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
+			     enum cpuid_regs_idx reg)
+{
+	const struct cpuid_bit *cb;
+	u32 cpuid_val = 0;
+
+	for (cb = cpuid_bits; cb->feature; cb++) {
+
+		if (level > cb->level)
+			continue;
+
+		if (level < cb->level)
+			break;
+
+		if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
+			if (cpu_has(&boot_cpu_data, cb->feature))
+				cpuid_val |= BIT(cb->bit);
+		}
+	}
+
+	return cpuid_val;
+}
+EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);

arch/x86/kernel/cpuid.c

@@ -46,10 +46,6 @@
 
 static struct class *cpuid_class;
 
-struct cpuid_regs {
-	u32 eax, ebx, ecx, edx;
-};
-
 static void cpuid_smp_cpuid(void *cmd_block)
 {
 	struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block;

arch/x86/kernel/dumpstack.c

@@ -22,7 +22,6 @@
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
 unsigned int code_bytes = 64;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
 static int die_counter;
 
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
@@ -46,14 +45,7 @@ static void printk_stack_address(unsigned long address, int reliable,
 				 char *log_lvl)
 {
 	touch_nmi_watchdog();
-	printk("%s [<%p>] %s%pB\n",
-		log_lvl, (void *)address, reliable ? "" : "? ",
-		(void *)address);
-}
-
-void printk_address(unsigned long address)
-{
-	pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address);
+	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
@@ -67,6 +59,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	printk("%sCall Trace:\n", log_lvl);
 
 	unwind_start(&state, task, regs, stack);
+	stack = stack ? : get_stack_pointer(task, regs);
 
 	/*
 	 * Iterate through the stacks, starting with the current stack pointer.
@@ -82,8 +75,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - softirq stack
 	 * - hardirq stack
 	 */
-	for (; stack; stack = stack_info.next_sp) {
-		const char *str_begin, *str_end;
+	for (regs = NULL; stack; stack = stack_info.next_sp) {
+		const char *stack_name;
 
 		/*
 		 * If we overflowed the task stack into a guard page, jump back
@@ -95,9 +88,9 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		if (get_stack_info(stack, task, &stack_info, &visit_mask))
 			break;
 
-		stack_type_str(stack_info.type, &str_begin, &str_end);
-		if (str_begin)
-			printk("%s <%s> ", log_lvl, str_begin);
+		stack_name = stack_type_name(stack_info.type);
+		if (stack_name)
+			printk("%s <%s>\n", log_lvl, stack_name);
 
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
@@ -119,6 +112,15 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			if (!__kernel_text_address(addr))
 				continue;
 
+			/*
+			 * Don't print regs->ip again if it was already printed
+			 * by __show_regs() below.
+			 */
+			if (regs && stack == &regs->ip) {
+				unwind_next_frame(&state);
+				continue;
+			}
+
 			if (stack == ret_addr_p)
 				reliable = 1;
 
@@ -146,10 +148,15 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			 * of the addresses will just be printed as unreliable.
 			 */
 			unwind_next_frame(&state);
+
+			/* if the frame has entry regs, print them */
+			regs = unwind_get_entry_regs(&state);
+			if (regs)
+				__show_regs(regs, 0);
 		}
 
-		if (str_end)
-			printk("%s <%s> ", log_lvl, str_end);
+		if (stack_name)
+			printk("%s </%s>\n", log_lvl, stack_name);
 	}
 }
 
@@ -164,12 +171,12 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 	if (!sp && task == current)
 		sp = get_stack_pointer(current, NULL);
 
-	show_stack_log_lvl(task, NULL, sp, "");
+	show_trace_log_lvl(task, NULL, sp, KERN_DEFAULT);
 }
 
 void show_stack_regs(struct pt_regs *regs)
 {
-	show_stack_log_lvl(current, regs, NULL, "");
+	show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
 }
 
 static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -261,14 +268,11 @@ int __die(const char *str, struct pt_regs *regs, long err)
 		sp = kernel_stack_pointer(regs);
 		savesegment(ss, ss);
 	}
-	printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
-	print_symbol("%s", regs->ip);
-	printk(" SS:ESP %04x:%08lx\n", ss, sp);
+	printk(KERN_EMERG "EIP: %pS SS:ESP: %04x:%08lx\n",
+	       (void *)regs->ip, ss, sp);
 #else
 	/* Executive summary in case the oops scrolled away */
-	printk(KERN_ALERT "RIP ");
-	printk_address(regs->ip);
-	printk(" RSP <%016lx>\n", regs->sp);
+	printk(KERN_ALERT "RIP: %pS RSP: %016lx\n", (void *)regs->ip, regs->sp);
 #endif
 	return 0;
 }
@@ -291,22 +295,6 @@ void die(const char *str, struct pt_regs *regs, long err)
 	oops_end(flags, regs, sig);
 }
 
-static int __init kstack_setup(char *s)
-{
-	ssize_t ret;
-	unsigned long val;
-
-	if (!s)
-		return -EINVAL;
-
-	ret = kstrtoul(s, 0, &val);
-	if (ret)
-		return ret;
-	kstack_depth_to_print = val;
-	return 0;
-}
-early_param("kstack", kstack_setup);
-
 static int __init code_bytes_setup(char *s)
 {
 	ssize_t ret;

arch/x86/kernel/dumpstack_32.c

@@ -16,18 +16,15 @@
 
 #include <asm/stacktrace.h>
 
-void stack_type_str(enum stack_type type, const char **begin, const char **end)
+const char *stack_type_name(enum stack_type type)
 {
-	switch (type) {
-	case STACK_TYPE_IRQ:
-	case STACK_TYPE_SOFTIRQ:
-		*begin = "IRQ";
-		*end   = "EOI";
-		break;
-	default:
-		*begin = NULL;
-		*end   = NULL;
-	}
+	if (type == STACK_TYPE_IRQ)
+		return "IRQ";
+
+	if (type == STACK_TYPE_SOFTIRQ)
+		return "SOFTIRQ";
+
+	return NULL;
 }
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
@@ -109,8 +106,10 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	 * just break out and report an unknown stack type.
 	 */
 	if (visit_mask) {
-		if (*visit_mask & (1UL << info->type))
+		if (*visit_mask & (1UL << info->type)) {
+			printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
 			goto unknown;
+		}
 		*visit_mask |= 1UL << info->type;
 	}
 
@@ -121,36 +120,6 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	return -EINVAL;
 }
 
-void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-			unsigned long *sp, char *log_lvl)
-{
-	unsigned long *stack;
-	int i;
-
-	if (!try_get_task_stack(task))
-		return;
-
-	sp = sp ? : get_stack_pointer(task, regs);
-
-	stack = sp;
-	for (i = 0; i < kstack_depth_to_print; i++) {
-		if (kstack_end(stack))
-			break;
-		if ((i % STACKSLOTS_PER_LINE) == 0) {
-			if (i != 0)
-				pr_cont("\n");
-			printk("%s %08lx", log_lvl, *stack++);
-		} else
-			pr_cont(" %08lx", *stack++);
-		touch_nmi_watchdog();
-	}
-	pr_cont("\n");
-	show_trace_log_lvl(task, regs, sp, log_lvl);
-
-	put_task_stack(task);
-}
-
-
 void show_regs(struct pt_regs *regs)
 {
 	int i;
@@ -168,8 +137,7 @@ void show_regs(struct pt_regs *regs)
 		unsigned char c;
 		u8 *ip;
 
-		pr_emerg("Stack:\n");
-		show_stack_log_lvl(current, regs, NULL, KERN_EMERG);
+		show_trace_log_lvl(current, regs, NULL, KERN_EMERG);
 
 		pr_emerg("Code:");
 

arch/x86/kernel/dumpstack_64.c

@@ -28,23 +28,17 @@ static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
 	[DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
-void stack_type_str(enum stack_type type, const char **begin, const char **end)
+const char *stack_type_name(enum stack_type type)
 {
 	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
 
-	switch (type) {
-	case STACK_TYPE_IRQ:
-		*begin = "IRQ";
-		*end   = "EOI";
-		break;
-	case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST:
-		*begin = exception_stack_names[type - STACK_TYPE_EXCEPTION];
-		*end   = "EOE";
-		break;
-	default:
-		*begin = NULL;
-		*end   = NULL;
-	}
+	if (type == STACK_TYPE_IRQ)
+		return "IRQ";
+
+	if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
+		return exception_stack_names[type - STACK_TYPE_EXCEPTION];
+
+	return NULL;
 }
 
 static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
@@ -128,8 +122,10 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	 * just break out and report an unknown stack type.
 	 */
 	if (visit_mask) {
-		if (*visit_mask & (1UL << info->type))
+		if (*visit_mask & (1UL << info->type)) {
+			printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type);
 			goto unknown;
+		}
 		*visit_mask |= 1UL << info->type;
 	}
 
@@ -140,56 +136,6 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	return -EINVAL;
 }
 
-void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-			unsigned long *sp, char *log_lvl)
-{
-	unsigned long *irq_stack_end;
-	unsigned long *irq_stack;
-	unsigned long *stack;
-	int i;
-
-	if (!try_get_task_stack(task))
-		return;
-
-	irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr);
-	irq_stack     = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long));
-
-	sp = sp ? : get_stack_pointer(task, regs);
-
-	stack = sp;
-	for (i = 0; i < kstack_depth_to_print; i++) {
-		unsigned long word;
-
-		if (stack >= irq_stack && stack <= irq_stack_end) {
-			if (stack == irq_stack_end) {
-				stack = (unsigned long *) (irq_stack_end[-1]);
-				pr_cont(" <EOI> ");
-			}
-		} else {
-		if (kstack_end(stack))
-			break;
-		}
-
-		if (probe_kernel_address(stack, word))
-			break;
-
-		if ((i % STACKSLOTS_PER_LINE) == 0) {
-			if (i != 0)
-				pr_cont("\n");
-			printk("%s %016lx", log_lvl, word);
-		} else
-			pr_cont(" %016lx", word);
-
-		stack++;
-		touch_nmi_watchdog();
-	}
-
-	pr_cont("\n");
-	show_trace_log_lvl(task, regs, sp, log_lvl);
-
-	put_task_stack(task);
-}
-
 void show_regs(struct pt_regs *regs)
 {
 	int i;
@@ -207,8 +153,7 @@ void show_regs(struct pt_regs *regs)
 		unsigned char c;
 		u8 *ip;
 
-		printk(KERN_DEFAULT "Stack:\n");
-		show_stack_log_lvl(current, regs, NULL, KERN_DEFAULT);
+		show_trace_log_lvl(current, regs, NULL, KERN_DEFAULT);
 
 		printk(KERN_DEFAULT "Code: ");
 

arch/x86/kernel/fpu/xstate.c

@@ -65,6 +65,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
 	setup_clear_cpu_cap(X86_FEATURE_AVX2);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512F);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512IFMA);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
@@ -73,6 +74,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_AVX512VL);
 	setup_clear_cpu_cap(X86_FEATURE_MPX);
 	setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512VBMI);
 	setup_clear_cpu_cap(X86_FEATURE_PKU);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);

arch/x86/kernel/head_32.S

@@ -63,6 +63,8 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
+#define SIZEOF_PTREGS 17*4
+
 /*
  * Number of possible pages in the lowmem region.
  *
@@ -248,19 +250,19 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 #ifdef CONFIG_PARAVIRT
 	/* This is can only trip for a broken bootloader... */
 	cmpw $0x207, pa(boot_params + BP_version)
-	jb default_entry
+	jb .Ldefault_entry
 
 	/* Paravirt-compatible boot parameters.  Look to see what architecture
 		we're booting under. */
 	movl pa(boot_params + BP_hardware_subarch), %eax
 	cmpl $num_subarch_entries, %eax
-	jae bad_subarch
+	jae .Lbad_subarch
 
 	movl pa(subarch_entries)(,%eax,4), %eax
 	subl $__PAGE_OFFSET, %eax
 	jmp *%eax
 
-bad_subarch:
+.Lbad_subarch:
 WEAK(lguest_entry)
 WEAK(xen_entry)
 	/* Unknown implementation; there's really
@@ -270,14 +272,14 @@ WEAK(xen_entry)
 	__INITDATA
 
 subarch_entries:
-	.long default_entry		/* normal x86/PC */
+	.long .Ldefault_entry		/* normal x86/PC */
 	.long lguest_entry		/* lguest hypervisor */
 	.long xen_entry			/* Xen hypervisor */
-	.long default_entry		/* Moorestown MID */
+	.long .Ldefault_entry		/* Moorestown MID */
 num_subarch_entries = (. - subarch_entries) / 4
 .previous
 #else
-	jmp default_entry
+	jmp .Ldefault_entry
 #endif /* CONFIG_PARAVIRT */
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -289,7 +291,8 @@ num_subarch_entries = (. - subarch_entries) / 4
 ENTRY(start_cpu0)
 	movl initial_stack, %ecx
 	movl %ecx, %esp
-	jmp  *(initial_code)
+	call *(initial_code)
+1:	jmp 1b
 ENDPROC(start_cpu0)
 #endif
 
@@ -317,7 +320,7 @@ ENTRY(startup_32_smp)
 	call load_ucode_ap
 #endif
 
-default_entry:
+.Ldefault_entry:
 #define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
 			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
 			 X86_CR0_PG)
@@ -347,7 +350,7 @@ default_entry:
 	pushfl
 	popl %eax			# get EFLAGS
 	testl $X86_EFLAGS_ID,%eax	# did EFLAGS.ID remained set?
-	jz enable_paging		# hw disallowed setting of ID bit
+	jz .Lenable_paging		# hw disallowed setting of ID bit
 					# which means no CPUID and no CR4
 
 	xorl %eax,%eax
@@ -357,13 +360,13 @@ default_entry:
 	movl $1,%eax
 	cpuid
 	andl $~1,%edx			# Ignore CPUID.FPU
-	jz enable_paging		# No flags or only CPUID.FPU = no CR4
+	jz .Lenable_paging		# No flags or only CPUID.FPU = no CR4
 
 	movl pa(mmu_cr4_features),%eax
 	movl %eax,%cr4
 
 	testb $X86_CR4_PAE, %al		# check if PAE is enabled
-	jz enable_paging
+	jz .Lenable_paging
 
 	/* Check if extended functions are implemented */
 	movl $0x80000000, %eax
@@ -371,7 +374,7 @@ default_entry:
 	/* Value must be in the range 0x80000001 to 0x8000ffff */
 	subl $0x80000001, %eax
 	cmpl $(0x8000ffff-0x80000001), %eax
-	ja enable_paging
+	ja .Lenable_paging
 
 	/* Clear bogus XD_DISABLE bits */
 	call verify_cpu
@@ -380,7 +383,7 @@ default_entry:
 	cpuid
 	/* Execute Disable bit supported? */
 	btl $(X86_FEATURE_NX & 31), %edx
-	jnc enable_paging
+	jnc .Lenable_paging
 
 	/* Setup EFER (Extended Feature Enable Register) */
 	movl $MSR_EFER, %ecx
@@ -390,7 +393,7 @@ default_entry:
 	/* Make changes effective */
 	wrmsr
 
-enable_paging:
+.Lenable_paging:
 
 /*
  * Enable paging
@@ -419,7 +422,7 @@ enable_paging:
  */
 	movb $4,X86			# at least 486
 	cmpl $-1,X86_CPUID
-	je is486
+	je .Lis486
 
 	/* get vendor info */
 	xorl %eax,%eax			# call CPUID with 0 -> return vendor ID
@@ -430,7 +433,7 @@ enable_paging:
 	movl %ecx,X86_VENDOR_ID+8	# last 4 chars
 
 	orl %eax,%eax			# do we have processor info as well?
-	je is486
+	je .Lis486
 
 	movl $1,%eax		# Use the CPUID instruction to get CPU type
 	cpuid
@@ -444,7 +447,7 @@ enable_paging:
 	movb %cl,X86_MASK
 	movl %edx,X86_CAPABILITY
 
-is486:
+.Lis486:
 	movl $0x50022,%ecx	# set AM, WP, NE and MP
 	movl %cr0,%eax
 	andl $0x80000011,%eax	# Save PG,PE,ET
@@ -470,8 +473,9 @@ is486:
 	xorl %eax,%eax			# Clear LDT
 	lldt %ax
 
-	pushl $0		# fake return address for unwinder
-	jmp *(initial_code)
+	call *(initial_code)
+1:	jmp 1b
+ENDPROC(startup_32_smp)
 
 #include "verify_cpu.S"
 
@@ -709,7 +713,12 @@ ENTRY(initial_page_table)
 .data
 .balign 4
 ENTRY(initial_stack)
-	.long init_thread_union+THREAD_SIZE
+	/*
+	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
+	 * unwinder reliably detect the end of the stack.
+	 */
+	.long init_thread_union + THREAD_SIZE - SIZEOF_PTREGS - \
+	      TOP_OF_KERNEL_STACK_PADDING;
 
 __INITRODATA
 int_msg:

arch/x86/kernel/head_64.S

@@ -66,13 +66,8 @@ startup_64:
 	 * tables and then reload them.
 	 */
 
-	/*
-	 * Setup stack for verify_cpu(). "-8" because initial_stack is defined
-	 * this way, see below. Our best guess is a NULL ptr for stack
-	 * termination heuristics and we don't want to break anything which
-	 * might depend on it (kgdb, ...).
-	 */
-	leaq	(__end_init_task - 8)(%rip), %rsp
+	/* Set up the stack for verify_cpu(), similar to initial_stack below */
+	leaq	(__end_init_task - SIZEOF_PTREGS)(%rip), %rsp
 
 	/* Sanitize CPU configuration */
 	call verify_cpu
@@ -117,20 +112,20 @@ startup_64:
 	movq	%rdi, %rax
 	shrq	$PGDIR_SHIFT, %rax
 
-	leaq	(4096 + _KERNPG_TABLE)(%rbx), %rdx
+	leaq	(PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx
 	movq	%rdx, 0(%rbx,%rax,8)
 	movq	%rdx, 8(%rbx,%rax,8)
 
-	addq	$4096, %rdx
+	addq	$PAGE_SIZE, %rdx
 	movq	%rdi, %rax
 	shrq	$PUD_SHIFT, %rax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, 4096(%rbx,%rax,8)
+	movq	%rdx, PAGE_SIZE(%rbx,%rax,8)
 	incl	%eax
 	andl	$(PTRS_PER_PUD-1), %eax
-	movq	%rdx, 4096(%rbx,%rax,8)
+	movq	%rdx, PAGE_SIZE(%rbx,%rax,8)
 
-	addq	$8192, %rbx
+	addq	$PAGE_SIZE * 2, %rbx
 	movq	%rdi, %rax
 	shrq	$PMD_SHIFT, %rdi
 	addq	$(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax
@@ -265,13 +260,17 @@ ENTRY(secondary_startup_64)
 	movl	$MSR_GS_BASE,%ecx
 	movl	initial_gs(%rip),%eax
 	movl	initial_gs+4(%rip),%edx
-	wrmsr	
+	wrmsr
 
 	/* rsi is pointer to real mode structure with interesting info.
 	   pass it to C */
 	movq	%rsi, %rdi
-	
-	/* Finally jump to run C code and to be on real kernel address
+	jmp	start_cpu
+ENDPROC(secondary_startup_64)
+
+ENTRY(start_cpu)
+	/*
+	 * Jump to run C code and to be on a real kernel address.
 	 * Since we are running on identity-mapped space we have to jump
 	 * to the full 64bit address, this is only possible as indirect
 	 * jump.  In addition we need to ensure %cs is set so we make this
@@ -295,12 +294,13 @@ ENTRY(secondary_startup_64)
 	 *	REX.W + FF /5 JMP m16:64 Jump far, absolute indirect,
 	 *		address given in m16:64.
 	 */
-	movq	initial_code(%rip),%rax
-	pushq	$0		# fake return address to stop unwinder
+	call	1f		# put return address on stack for unwinder
+1:	xorq	%rbp, %rbp	# clear frame pointer
+	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
 	lretq
-ENDPROC(secondary_startup_64)
+ENDPROC(start_cpu)
 
 #include "verify_cpu.S"
 
@@ -308,15 +308,11 @@ ENDPROC(secondary_startup_64)
 /*
  * Boot CPU0 entry point. It's called from play_dead(). Everything has been set
  * up already except stack. We just set up stack here. Then call
- * start_secondary().
+ * start_secondary() via start_cpu().
  */
 ENTRY(start_cpu0)
-	movq initial_stack(%rip),%rsp
-	movq	initial_code(%rip),%rax
-	pushq	$0		# fake return address to stop unwinder
-	pushq	$__KERNEL_CS	# set correct cs
-	pushq	%rax		# target address in negative space
-	lretq
+	movq	initial_stack(%rip), %rsp
+	jmp	start_cpu
 ENDPROC(start_cpu0)
 #endif
 
@@ -328,7 +324,11 @@ ENDPROC(start_cpu0)
 	GLOBAL(initial_gs)
 	.quad	INIT_PER_CPU_VAR(irq_stack_union)
 	GLOBAL(initial_stack)
-	.quad  init_thread_union+THREAD_SIZE-8
+	/*
+	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
+	 * unwinder reliably detect the end of the stack.
+	 */
+	.quad  init_thread_union + THREAD_SIZE - SIZEOF_PTREGS
 	__FINITDATA
 
 bad_address:

arch/x86/kernel/process_32.c

@@ -72,10 +72,9 @@ void __show_regs(struct pt_regs *regs, int all)
 		savesegment(gs, gs);
 	}
 
-	printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
-			(u16)regs->cs, regs->ip, regs->flags,
-			smp_processor_id());
-	print_symbol("EIP is at %s\n", regs->ip);
+	printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
+	printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
+		smp_processor_id());
 
 	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);

arch/x86/kernel/process_64.c

@@ -61,10 +61,15 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
 
-	printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
-	printk_address(regs->ip);
-	printk(KERN_DEFAULT "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
-			regs->sp, regs->flags);
+	printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs & 0xffff,
+		(void *)regs->ip);
+	printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
+		regs->sp, regs->flags);
+	if (regs->orig_ax != -1)
+		pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
+	else
+		pr_cont("\n");
+
 	printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n",
 	       regs->ax, regs->bx, regs->cx);
 	printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n",

arch/x86/kernel/smpboot.c

@@ -987,9 +987,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 	int cpu0_nmi_registered = 0;
 	unsigned long timeout;
 
-	idle->thread.sp = (unsigned long) (((struct pt_regs *)
-			  (THREAD_SIZE +  task_stack_page(idle))) - 1);
-
+	idle->thread.sp = (unsigned long)task_pt_regs(idle);
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;
 	initial_stack  = idle->thread.sp;

arch/x86/kernel/unwind_frame.c

@@ -14,13 +14,55 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
 	if (unwind_done(state))
 		return 0;
 
+	if (state->regs && user_mode(state->regs))
+		return 0;
+
 	addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
 				     addr_p);
 
-	return __kernel_text_address(addr) ? addr : 0;
+	if (!__kernel_text_address(addr)) {
+		printk_deferred_once(KERN_WARNING
+			"WARNING: unrecognized kernel stack return address %p at %p in %s:%d\n",
+			(void *)addr, addr_p, state->task->comm,
+			state->task->pid);
+		return 0;
+	}
+
+	return addr;
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
+static size_t regs_size(struct pt_regs *regs)
+{
+	/* x86_32 regs from kernel mode are two words shorter: */
+	if (IS_ENABLED(CONFIG_X86_32) && !user_mode(regs))
+		return sizeof(*regs) - 2*sizeof(long);
+
+	return sizeof(*regs);
+}
+
+static bool is_last_task_frame(struct unwind_state *state)
+{
+	unsigned long bp = (unsigned long)state->bp;
+	unsigned long regs = (unsigned long)task_pt_regs(state->task);
+
+	return bp == regs - FRAME_HEADER_SIZE;
+}
+
+/*
+ * This determines if the frame pointer actually contains an encoded pointer to
+ * pt_regs on the stack.  See ENCODE_FRAME_POINTER.
+ */
+static struct pt_regs *decode_frame_pointer(unsigned long *bp)
+{
+	unsigned long regs = (unsigned long)bp;
+
+	if (!(regs & 0x1))
+		return NULL;
+
+	return (struct pt_regs *)(regs & ~0x1);
+}
+
 static bool update_stack_state(struct unwind_state *state, void *addr,
 			       size_t len)
 {
@@ -43,26 +85,117 @@ static bool update_stack_state(struct unwind_state *state, void *addr,
 
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long *next_bp;
+	struct pt_regs *regs;
+	unsigned long *next_bp, *next_frame;
+	size_t next_len;
+	enum stack_type prev_type = state->stack_info.type;
 
 	if (unwind_done(state))
 		return false;
 
-	next_bp = (unsigned long *)*state->bp;
+	/* have we reached the end? */
+	if (state->regs && user_mode(state->regs))
+		goto the_end;
+
+	if (is_last_task_frame(state)) {
+		regs = task_pt_regs(state->task);
+
+		/*
+		 * kthreads (other than the boot CPU's idle thread) have some
+		 * partial regs at the end of their stack which were placed
+		 * there by copy_thread_tls().  But the regs don't have any
+		 * useful information, so we can skip them.
+		 *
+		 * This user_mode() check is slightly broader than a PF_KTHREAD
+		 * check because it also catches the awkward situation where a
+		 * newly forked kthread transitions into a user task by calling
+		 * do_execve(), which eventually clears PF_KTHREAD.
+		 */
+		if (!user_mode(regs))
+			goto the_end;
+
+		/*
+		 * We're almost at the end, but not quite: there's still the
+		 * syscall regs frame.  Entry code doesn't encode the regs
+		 * pointer for syscalls, so we have to set it manually.
+		 */
+		state->regs = regs;
+		state->bp = NULL;
+		return true;
+	}
+
+	/* get the next frame pointer */
+	if (state->regs)
+		next_bp = (unsigned long *)state->regs->bp;
+	else
+		next_bp = (unsigned long *)*state->bp;
+
+	/* is the next frame pointer an encoded pointer to pt_regs? */
+	regs = decode_frame_pointer(next_bp);
+	if (regs) {
+		next_frame = (unsigned long *)regs;
+		next_len = sizeof(*regs);
+	} else {
+		next_frame = next_bp;
+		next_len = FRAME_HEADER_SIZE;
+	}
 
 	/* make sure the next frame's data is accessible */
-	if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE))
-		return false;
+	if (!update_stack_state(state, next_frame, next_len)) {
+		/*
+		 * Don't warn on bad regs->bp.  An interrupt in entry code
+		 * might cause a false positive warning.
+		 */
+		if (state->regs)
+			goto the_end;
+
+		goto bad_address;
+	}
+
+	/* Make sure it only unwinds up and doesn't overlap the last frame: */
+	if (state->stack_info.type == prev_type) {
+		if (state->regs && (void *)next_frame < (void *)state->regs + regs_size(state->regs))
+			goto bad_address;
+
+		if (state->bp && (void *)next_frame < (void *)state->bp + FRAME_HEADER_SIZE)
+			goto bad_address;
+	}
 
 	/* move to the next frame */
-	state->bp = next_bp;
+	if (regs) {
+		state->regs = regs;
+		state->bp = NULL;
+	} else {
+		state->bp = next_bp;
+		state->regs = NULL;
+	}
+
 	return true;
+
+bad_address:
+	if (state->regs) {
+		printk_deferred_once(KERN_WARNING
+			"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
+			state->regs, state->task->comm,
+			state->task->pid, next_frame);
+	} else {
+		printk_deferred_once(KERN_WARNING
+			"WARNING: kernel stack frame pointer at %p in %s:%d has bad value %p\n",
+			state->bp, state->task->comm,
+			state->task->pid, next_frame);
+	}
+the_end:
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
+	return false;
 }
 EXPORT_SYMBOL_GPL(unwind_next_frame);
 
 void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		    struct pt_regs *regs, unsigned long *first_frame)
 {
+	unsigned long *bp, *frame;
+	size_t len;
+
 	memset(state, 0, sizeof(*state));
 	state->task = task;
 
@@ -73,12 +206,22 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	}
 
 	/* set up the starting stack frame */
-	state->bp = get_frame_pointer(task, regs);
+	bp = get_frame_pointer(task, regs);
+	regs = decode_frame_pointer(bp);
+	if (regs) {
+		state->regs = regs;
+		frame = (unsigned long *)regs;
+		len = sizeof(*regs);
+	} else {
+		state->bp = bp;
+		frame = bp;
+		len = FRAME_HEADER_SIZE;
+	}
 
 	/* initialize stack info and make sure the frame data is accessible */
-	get_stack_info(state->bp, state->task, &state->stack_info,
+	get_stack_info(frame, state->task, &state->stack_info,
 		       &state->stack_mask);
-	update_stack_state(state, state->bp, FRAME_HEADER_SIZE);
+	update_stack_state(state, frame, len);
 
 	/*
 	 * The caller can provide the address of the first frame directly

arch/x86/kernel/vmlinux.lds.S

@@ -91,10 +91,10 @@ SECTIONS
 	/* Text and read-only data */
 	.text :  AT(ADDR(.text) - LOAD_OFFSET) {
 		_text = .;
+		_stext = .;
 		/* bootstrapping code */
 		HEAD_TEXT
 		. = ALIGN(8);
-		_stext = .;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT

arch/x86/lib/copy_user_64.S

@@ -16,53 +16,6 @@
 #include <asm/smap.h>
 #include <asm/export.h>
 
-/* Standard copy_to_user with segment limit checking */
-ENTRY(_copy_to_user)
-	mov PER_CPU_VAR(current_task), %rax
-	movq %rdi,%rcx
-	addq %rdx,%rcx
-	jc bad_to_user
-	cmpq TASK_addr_limit(%rax),%rcx
-	ja bad_to_user
-	ALTERNATIVE_2 "jmp copy_user_generic_unrolled",		\
-		      "jmp copy_user_generic_string",		\
-		      X86_FEATURE_REP_GOOD,			\
-		      "jmp copy_user_enhanced_fast_string",	\
-		      X86_FEATURE_ERMS
-ENDPROC(_copy_to_user)
-EXPORT_SYMBOL(_copy_to_user)
-
-/* Standard copy_from_user with segment limit checking */
-ENTRY(_copy_from_user)
-	mov PER_CPU_VAR(current_task), %rax
-	movq %rsi,%rcx
-	addq %rdx,%rcx
-	jc bad_from_user
-	cmpq TASK_addr_limit(%rax),%rcx
-	ja bad_from_user
-	ALTERNATIVE_2 "jmp copy_user_generic_unrolled",		\
-		      "jmp copy_user_generic_string",		\
-		      X86_FEATURE_REP_GOOD,			\
-		      "jmp copy_user_enhanced_fast_string",	\
-		      X86_FEATURE_ERMS
-ENDPROC(_copy_from_user)
-EXPORT_SYMBOL(_copy_from_user)
-
-
-	.section .fixup,"ax"
-	/* must zero dest */
-ENTRY(bad_from_user)
-bad_from_user:
-	movl %edx,%ecx
-	xorl %eax,%eax
-	rep
-	stosb
-bad_to_user:
-	movl %edx,%eax
-	ret
-ENDPROC(bad_from_user)
-	.previous
-
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
  * This version is for CPUs like P4 that don't have efficient micro

arch/x86/lib/usercopy.c

@@ -34,3 +34,52 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
+
+/**
+ * copy_to_user: - Copy a block of data into user space.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
+ *
+ * Copy data from kernel space to user space.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+unsigned long _copy_to_user(void __user *to, const void *from, unsigned n)
+{
+	if (access_ok(VERIFY_WRITE, to, n))
+		n = __copy_to_user(to, from, n);
+	return n;
+}
+EXPORT_SYMBOL(_copy_to_user);
+
+/**
+ * copy_from_user: - Copy a block of data from user space.
+ * @to:   Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
+ *
+ * Copy data from user space to kernel space.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ */
+unsigned long _copy_from_user(void *to, const void __user *from, unsigned n)
+{
+	if (access_ok(VERIFY_READ, from, n))
+		n = __copy_from_user(to, from, n);
+	else
+		memset(to, 0, n);
+	return n;
+}
+EXPORT_SYMBOL(_copy_from_user);

arch/x86/lib/usercopy_32.c

@@ -640,52 +640,3 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
-
-/**
- * copy_to_user: - Copy a block of data into user space.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from kernel space to user space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-unsigned long _copy_to_user(void __user *to, const void *from, unsigned n)
-{
-	if (access_ok(VERIFY_WRITE, to, n))
-		n = __copy_to_user(to, from, n);
-	return n;
-}
-EXPORT_SYMBOL(_copy_to_user);
-
-/**
- * copy_from_user: - Copy a block of data from user space.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * Copy data from user space to kernel space.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-unsigned long _copy_from_user(void *to, const void __user *from, unsigned n)
-{
-	if (access_ok(VERIFY_READ, from, n))
-		n = __copy_from_user(to, from, n);
-	else
-		memset(to, 0, n);
-	return n;
-}
-EXPORT_SYMBOL(_copy_from_user);

arch/x86/mm/fault.c

@@ -679,8 +679,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		printk(KERN_CONT "paging request");
 
 	printk(KERN_CONT " at %p\n", (void *) address);
-	printk(KERN_ALERT "IP:");
-	printk_address(regs->ip);
+	printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip);
 
 	dump_pagetable(address);
 }

arch/x86/platform/uv/uv_nmi.c

@@ -387,8 +387,8 @@ static void uv_nmi_dump_cpu_ip_hdr(void)
 /* Dump Instruction Pointer info */
 static void uv_nmi_dump_cpu_ip(int cpu, struct pt_regs *regs)
 {
-	pr_info("UV: %4d %6d %-32.32s ", cpu, current->pid, current->comm);
-	printk_address(regs->ip);
+	pr_info("UV: %4d %6d %-32.32s %pS",
+		cpu, current->pid, current->comm, (void *)regs->ip);
 }
 
 /*

arch/x86/tools/insn_sanity.c

@@ -269,7 +269,8 @@ int main(int argc, char **argv)
 		insns++;
 	}
 
-	fprintf(stdout, "%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
+	fprintf((errors) ? stderr : stdout,
+		"%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
 		prog,
 		(errors) ? "Failure" : "Success",
 		insns,

arch/x86/tools/test_get_len.c

@@ -167,7 +167,7 @@ int main(int argc, char **argv)
 		fprintf(stderr, "Warning: decoded and checked %d"
 			" instructions with %d warnings\n", insns, warnings);
 	else
-		fprintf(stderr, "Succeed: decoded and checked %d"
+		fprintf(stdout, "Success: decoded and checked %d"
 			" instructions\n", insns);
 	return 0;
 }

kernel/sysctl.c

@@ -982,13 +982,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "kstack_depth_to_print",
-		.data		= &kstack_depth_to_print,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "io_delay_type",
 		.data		= &io_delay_type,

mm/page_alloc.c

@@ -6399,8 +6399,8 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 	}
 
 	if (pages && s)
-		pr_info("Freeing %s memory: %ldK (%p - %p)\n",
-			s, pages << (PAGE_SHIFT - 10), start, end);
+		pr_info("Freeing %s memory: %ldK\n",
+			s, pages << (PAGE_SHIFT - 10));
 
 	return pages;
 }

scripts/decode_stacktrace.sh

@@ -139,7 +139,8 @@ handle_line() {
 
 while read line; do
 	# Let's see if we have an address in the line
-	if [[ $line =~ \[\<([^]]+)\>\]  ]]; then
+	if [[ $line =~ \[\<([^]]+)\>\] ]] ||
+	   [[ $line =~ [^+\ ]+\+0x[0-9a-f]+/0x[0-9a-f]+ ]]; then
 		# Translate address to line numbers
 		handle_line "$line"
 	# Is it a code line?

scripts/faddr2line

@@ -105,9 +105,18 @@ __faddr2line() {
 	# In rare cases there might be duplicates.
 	while read symbol; do
 		local fields=($symbol)
-		local sym_base=0x${fields[1]}
-		local sym_size=${fields[2]}
-		local sym_type=${fields[3]}
+		local sym_base=0x${fields[0]}
+		local sym_type=${fields[1]}
+		local sym_end=0x${fields[3]}
+
+		# calculate the size
+		local sym_size=$(($sym_end - $sym_base))
+		if [[ -z $sym_size ]] || [[ $sym_size -le 0 ]]; then
+			warn "bad symbol size: base: $sym_base end: $sym_end"
+			DONE=1
+			return
+		fi
+		sym_size=0x$(printf %x $sym_size)
 
 		# calculate the address
 		local addr=$(($sym_base + $offset))
@@ -116,26 +125,26 @@ __faddr2line() {
 			DONE=1
 			return
 		fi
-		local hexaddr=0x$(printf %x $addr)
+		addr=0x$(printf %x $addr)
 
 		# weed out non-function symbols
-		if [[ $sym_type != "FUNC" ]]; then
+		if [[ $sym_type != t ]] && [[ $sym_type != T ]]; then
 			[[ $print_warnings = 1 ]] &&
-				echo "skipping $func address at $hexaddr due to non-function symbol"
+				echo "skipping $func address at $addr due to non-function symbol of type '$sym_type'"
 			continue
 		fi
 
 		# if the user provided a size, make sure it matches the symbol's size
 		if [[ -n $size ]] && [[ $size -ne $sym_size ]]; then
 			[[ $print_warnings = 1 ]] &&
-				echo "skipping $func address at $hexaddr due to size mismatch ($size != $sym_size)"
+				echo "skipping $func address at $addr due to size mismatch ($size != $sym_size)"
 			continue;
 		fi
 
 		# make sure the provided offset is within the symbol's range
 		if [[ $offset -gt $sym_size ]]; then
 			[[ $print_warnings = 1 ]] &&
-				echo "skipping $func address at $hexaddr due to size mismatch ($offset > $sym_size)"
+				echo "skipping $func address at $addr due to size mismatch ($offset > $sym_size)"
 			continue
 		fi
 
@@ -143,12 +152,12 @@ __faddr2line() {
 		[[ $FIRST = 0 ]] && echo
 		FIRST=0
 
-		local hexsize=0x$(printf %x $sym_size)
-		echo "$func+$offset/$hexsize:"
-		addr2line -fpie $objfile $hexaddr | sed "s; $dir_prefix\(\./\)*; ;"
+		# pass real address to addr2line
+		echo "$func+$offset/$sym_size:"
+		addr2line -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;"
 		DONE=1
 
-	done < <(readelf -sW $objfile | awk -v f=$func '$8 == f {print}')
+	done < <(nm -n $objfile | awk -v fn=$func '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, $1 }')
 }
 
 [[ $# -lt 2 ]] && usage

tools/testing/selftests/x86/Makefile

@@ -6,7 +6,7 @@ include ../lib.mk
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
 			check_initial_reg_state sigreturn ldt_gdt iopl \
-			protection_keys
+			protection_keys test_vdso
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer

tools/testing/selftests/x86/test_vdso.c

+/*
+ * ldt_gdt.c - Test cases for LDT and GDT access
+ * Copyright (c) 2011-2015 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <sys/time.h>
+#include <time.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <dlfcn.h>
+#include <string.h>
+#include <errno.h>
+#include <sched.h>
+#include <stdbool.h>
+
+#ifndef SYS_getcpu
+# ifdef __x86_64__
+#  define SYS_getcpu 309
+# else
+#  define SYS_getcpu 318
+# endif
+#endif
+
+int nerrs = 0;
+
+#ifdef __x86_64__
+# define VSYS(x) (x)
+#else
+# define VSYS(x) 0
+#endif
+
+typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
+
+const getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800);
+getcpu_t vdso_getcpu;
+
+void fill_function_pointers()
+{
+	void *vdso = dlopen("linux-vdso.so.1",
+			    RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+	if (!vdso)
+		vdso = dlopen("linux-gate.so.1",
+			      RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+	if (!vdso) {
+		printf("[WARN]\tfailed to find vDSO\n");
+		return;
+	}
+
+	vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu");
+	if (!vdso_getcpu)
+		printf("Warning: failed to find getcpu in vDSO\n");
+}
+
+static long sys_getcpu(unsigned * cpu, unsigned * node,
+		       void* cache)
+{
+	return syscall(__NR_getcpu, cpu, node, cache);
+}
+
+static void test_getcpu(void)
+{
+	printf("[RUN]\tTesting getcpu...\n");
+
+	for (int cpu = 0; ; cpu++) {
+		cpu_set_t cpuset;
+		CPU_ZERO(&cpuset);
+		CPU_SET(cpu, &cpuset);
+		if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+			return;
+
+		unsigned cpu_sys, cpu_vdso, cpu_vsys,
+			node_sys, node_vdso, node_vsys;
+		long ret_sys, ret_vdso = 1, ret_vsys = 1;
+		unsigned node;
+
+		ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0);
+		if (vdso_getcpu)
+			ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0);
+		if (vgetcpu)
+			ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0);
+
+		if (!ret_sys)
+			node = node_sys;
+		else if (!ret_vdso)
+			node = node_vdso;
+		else if (!ret_vsys)
+			node = node_vsys;
+
+		bool ok = true;
+		if (!ret_sys && (cpu_sys != cpu || node_sys != node))
+			ok = false;
+		if (!ret_vdso && (cpu_vdso != cpu || node_vdso != node))
+			ok = false;
+		if (!ret_vsys && (cpu_vsys != cpu || node_vsys != node))
+			ok = false;
+
+		printf("[%s]\tCPU %u:", ok ? "OK" : "FAIL", cpu);
+		if (!ret_sys)
+			printf(" syscall: cpu %u, node %u", cpu_sys, node_sys);
+		if (!ret_vdso)
+			printf(" vdso: cpu %u, node %u", cpu_vdso, node_vdso);
+		if (!ret_vsys)
+			printf(" vsyscall: cpu %u, node %u", cpu_vsys,
+			       node_vsys);
+		printf("\n");
+
+		if (!ok)
+			nerrs++;
+	}
+}
+
+int main(int argc, char **argv)
+{
+	fill_function_pointers();
+
+	test_getcpu();
+
+	return nerrs ? 1 : 0;
+}