Merge branch 'linux-linaro-lsk-v3.14' into linux-linaro-lsk-v3.14-rt

Conflicts:
	arch/x86/kernel/traps.c

13 files changed, 122 insertions, 76 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 5f1296872aed..1717156f4dd1 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -203,6 +203,7 @@
 #define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
 #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 */
 
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c7678e43465b..e62cf897f781 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_KVM_PARA_H
 
 #include <asm/processor.h>
+#include <asm/alternative.h>
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
@@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 }
 #endif /* CONFIG_KVM_GUEST */
 
-/* This instruction is vmcall.  On non-VT architectures, it will generate a
- * trap that we will then rewrite to the appropriate instruction.
+#ifdef CONFIG_DEBUG_RODATA
+#define KVM_HYPERCALL \
+        ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
+#else
+/* On AMD processors, vmcall will generate a trap that we will
+ * then rewrite to the appropriate instruction.
  */
 #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
+#endif
 
 /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index f48b17df4224..3a52ee0e726d 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -20,7 +20,6 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define STACKFAULT_STACK 0
 #define DOUBLEFAULT_STACK 1
 #define NMI_STACK 0
 #define DEBUG_STACK 0
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8de6d9cf3b95..d54d1eebeffe 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,12 +14,11 @@
 #define IRQ_STACK_ORDER 2
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
 
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 5112fde9ca7e..8ad13f36b989 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -148,7 +148,7 @@ struct thread_info {
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
 	(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |	\
-	 _TIF_USER_RETURN_NOTIFY)
+	 _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 58d66fe06b61..b409b17efb48 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void);
 
 #ifdef CONFIG_TRACING
 asmlinkage void trace_page_fault(void);
+#define trace_stack_segment stack_segment
 #define trace_divide_error divide_error
 #define trace_bounds bounds
 #define trace_invalid_op invalid_op
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c67ffa686064..c005fdd52529 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -508,6 +508,13 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	}
 #endif
 
+	/*
+	 * This is only needed to tell the kernel whether to use VMCALL
+	 * and VMMCALL.  VMMCALL is never executed except under virt, so
+	 * we can set it unconditionally.
+	 */
+	set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
 	/* F16h erratum 793, CVE-2013-6885 */
 	if (c->x86 == 0x16 && c->x86_model <= 0xf) {
 		u64 val;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3f27f5fd0847..e6bddd5b9da3 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
 static int __init x86_xsave_setup(char *s)
 {
+	if (strlen(s))
+		return 0;
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207dab92..66e274a3d968 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = {
 		[ DEBUG_STACK-1			]	= "#DB",
 		[ NMI_STACK-1			]	= "NMI",
 		[ DOUBLEFAULT_STACK-1		]	= "#DF",
-		[ STACKFAULT_STACK-1		]	= "#SS",
 		[ MCE_STACK-1			]	= "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
 		[ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 9d702f33f745..460b060eb70e 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1053,9 +1053,15 @@ ENTRY(native_iret)
 	jnz native_irq_return_ldt
 #endif
 
+.global native_irq_return_iret
 native_irq_return_iret:
+	/*
+	 * This may fault.  Non-paranoid faults on return to userspace are
+	 * handled by fixup_bad_iret.  These include #SS, #GP, and #NP.
+	 * Double-faults due to espfix64 are handled in do_double_fault.
+	 * Other faults here are fatal.
+	 */
 	iretq
-	_ASM_EXTABLE(native_irq_return_iret, bad_iret)
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
@@ -1083,25 +1089,6 @@ native_irq_return_ldt:
 	jmp native_irq_return_iret
 #endif
 
-	.section .fixup,"ax"
-bad_iret:
-	/*
-	 * The iret traps when the %cs or %ss being restored is bogus.
-	 * We've lost the original trap vector and error code.
-	 * #GPF is the most likely one to get for an invalid selector.
-	 * So pretend we completed the iret and took the #GPF in user mode.
-	 *
-	 * We are now running with the kernel GS after exception recovery.
-	 * But error_entry expects us to have user GS to match the user %cs,
-	 * so swap back.
-	 */
-	pushq $0
-
-	SWAPGS
-	jmp general_protection
-
-	.previous
-
 	/* edi: workmask, edx: work */
 retint_careful:
 	CFI_RESTORE_STATE
@@ -1162,37 +1149,6 @@ check_int_off:
 	CFI_ENDPROC
 END(common_interrupt)
 
-	/*
-	 * If IRET takes a fault on the espfix stack, then we
-	 * end up promoting it to a doublefault.  In that case,
-	 * modify the stack to make it look like we just entered
-	 * the #GP handler from user space, similar to bad_iret.
-	 */
-#ifdef CONFIG_X86_ESPFIX64
-	ALIGN
-__do_double_fault:
-	XCPT_FRAME 1 RDI+8
-	movq RSP(%rdi),%rax		/* Trap on the espfix stack? */
-	sarq $PGDIR_SHIFT,%rax
-	cmpl $ESPFIX_PGD_ENTRY,%eax
-	jne do_double_fault		/* No, just deliver the fault */
-	cmpl $__KERNEL_CS,CS(%rdi)
-	jne do_double_fault
-	movq RIP(%rdi),%rax
-	cmpq $native_irq_return_iret,%rax
-	jne do_double_fault		/* This shouldn't happen... */
-	movq PER_CPU_VAR(kernel_stack),%rax
-	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
-	movq %rax,RSP(%rdi)
-	movq $0,(%rax)			/* Missing (lost) #GP error code */
-	movq $general_protection,RIP(%rdi)
-	retq
-	CFI_ENDPROC
-END(__do_double_fault)
-#else
-# define __do_double_fault do_double_fault
-#endif
-
 /*
  * End of kprobes section
  */
@@ -1394,7 +1350,7 @@ zeroentry overflow do_overflow
 zeroentry bounds do_bounds
 zeroentry invalid_op do_invalid_op
 zeroentry device_not_available do_device_not_available
-paranoiderrorentry double_fault __do_double_fault
+paranoiderrorentry double_fault do_double_fault
 zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
 errorentry invalid_TSS do_invalid_TSS
 errorentry segment_not_present do_segment_not_present
@@ -1566,7 +1522,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 
 paranoidzeroentry_ist debug do_debug DEBUG_STACK
 paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
-paranoiderrorentry stack_segment do_stack_segment
+errorentry stack_segment do_stack_segment
 #ifdef CONFIG_XEN
 zeroentry xen_debug do_debug
 zeroentry xen_int3 do_int3
@@ -1676,16 +1632,15 @@ error_sti:
 
 /*
  * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. The exception handlers after iret run with
- * kernel gs again, so don't set the user space flag. B stepping K8s
- * sometimes report an truncated RIP for IRET exceptions returning to
- * compat mode. Check for these here too.
+ * usergs. Handle them here.  B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
  */
 error_kernelspace:
 	incl %ebx
 	leaq native_irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
-	je error_swapgs
+	je error_bad_iret
 	movl %ecx,%eax	/* zero extend */
 	cmpq %rax,RIP+8(%rsp)
 	je bstep_iret
@@ -1696,7 +1651,15 @@ error_kernelspace:
 bstep_iret:
 	/* Fix truncated RIP */
 	movq %rcx,RIP+8(%rsp)
-	jmp error_swapgs
+	/* fall through */
+
+error_bad_iret:
+	SWAPGS
+	mov %rsp,%rdi
+	call fixup_bad_iret
+	mov %rax,%rsp
+	decl %ebx	/* Return to usergs */
+	jmp error_sti
 	CFI_ENDPROC
 END(error_entry)
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 48dab0ca1017..d72010a270d3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -232,13 +232,10 @@ DO_ERROR_INFO(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op,		     ILL
 DO_ERROR     (X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",	coprocessor_segment_overrun			  )
 DO_ERROR     (X86_TRAP_TS,     SIGSEGV, "invalid TSS",			invalid_TSS					  )
 DO_ERROR     (X86_TRAP_NP,     SIGBUS,  "segment not present",		segment_not_present				  )
-#ifdef CONFIG_X86_32
 DO_ERROR     (X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment					  )
-#endif
 DO_ERROR_INFO(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check,	     BUS_ADRALN, 0	  )
 
 #ifdef CONFIG_X86_64
-/* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
 	enum ctx_state prev_state;
@@ -253,11 +250,36 @@ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 	exception_exit(prev_state);
 }
 
+/* Runs on IST stack */
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
 	static const char str[] = "double fault";
 	struct task_struct *tsk = current;
 
+#ifdef CONFIG_X86_ESPFIX64
+	extern unsigned char native_irq_return_iret[];
+
+	/*
+	 * If IRET takes a non-IST fault on the espfix64 stack, then we
+	 * end up promoting it to a doublefault.  In that case, modify
+	 * the stack to make it look like we just entered the #GP
+	 * handler from user space, similar to bad_iret.
+	 */
+	if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+		regs->cs == __KERNEL_CS &&
+		regs->ip == (unsigned long)native_irq_return_iret)
+	{
+		struct pt_regs *normal_regs = task_pt_regs(current);
+
+		/* Fake a #GP(0) from userspace. */
+		memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+		normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+		regs->ip = (unsigned long)general_protection;
+		regs->sp = (unsigned long)&normal_regs->orig_ax;
+		return;
+	}
+#endif
+
 	exception_enter();
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -390,6 +412,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 		*regs = *eregs;
 	return regs;
 }
+
+struct bad_iret_stack {
+	void *error_entry_ret;
+	struct pt_regs regs;
+};
+
+asmlinkage __visible
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+	/*
+	 * This is called from entry_64.S early in handling a fault
+	 * caused by a bad iret to user mode.  To handle the fault
+	 * correctly, we want move our stack frame to task_pt_regs
+	 * and we want to pretend that the exception came from the
+	 * iret target.
+	 */
+	struct bad_iret_stack *new_stack =
+		container_of(task_pt_regs(current),
+			     struct bad_iret_stack, regs);
+
+	/* Copy the IRET target to the new stack. */
+	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+	/* Copy the remainder of the stack from the current stack. */
+	memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+	BUG_ON(!user_mode_vm(&new_stack->regs));
+	return new_stack;
+}
 #endif
 
 /*
@@ -762,7 +813,7 @@ void __init trap_init(void)
 	set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun);
 	set_intr_gate(X86_TRAP_TS, invalid_TSS);
 	set_intr_gate(X86_TRAP_NP, segment_not_present);
-	set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+	set_intr_gate(X86_TRAP_SS, stack_segment);
 	set_intr_gate(X86_TRAP_GP, general_protection);
 	set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug);
 	set_intr_gate(X86_TRAP_MF, coprocessor_error);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index f35c66c5959a..2308a401a1c5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1110,7 +1110,7 @@ void mark_rodata_ro(void)
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
 	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
 	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
-	unsigned long all_end = PFN_ALIGN(&_end);
+	unsigned long all_end;
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
@@ -1121,7 +1121,16 @@ void mark_rodata_ro(void)
 	/*
 	 * The rodata/data/bss/brk section (but not the kernel text!)
 	 * should also be not-executable.
+	 *
+	 * We align all_end to PMD_SIZE because the existing mapping
+	 * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+	 * split the PMD and the reminder between _brk_end and the end
+	 * of the PMD will remain mapped executable.
+	 *
+	 * Any PMD which was setup after the one which covers _brk_end
+	 * has been zapped already via cleanup_highmem().
 	 */
+	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
 	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
 
 	rodata_test();
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
index 0b0b124d3ece..23210baade2d 100644
--- a/arch/x86/tools/calc_run_size.pl
+++ b/arch/x86/tools/calc_run_size.pl
@@ -19,7 +19,16 @@ while (<>) {
 		if ($file_offset == 0) {
 			$file_offset = $offset;
 		} elsif ($file_offset != $offset) {
-			die ".bss and .brk lack common file offset\n";
+			# BFD linker shows the same file offset in ELF.
+			# Gold linker shows them as consecutive.
+			next if ($file_offset + $mem_size == $offset + $size);
+
+			printf STDERR "file_offset: 0x%lx\n", $file_offset;
+			printf STDERR "mem_size: 0x%lx\n", $mem_size;
+			printf STDERR "offset: 0x%lx\n", $offset;
+			printf STDERR "size: 0x%lx\n", $size;
+
+			die ".bss and .brk are non-contiguous\n";
 		}
 	}
 }