Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/phy/bcm7xxx.c
	drivers/net/phy/marvell.c
	drivers/net/vxlan.c

All three conflicts were cases of simple overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 123 insertions, 53 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9af2e63..c46662f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -475,6 +475,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
+	depends on EFI
 	depends on X86_X2APIC
 	depends on PCI
 	---help---
@@ -777,8 +778,8 @@ config HPET_TIMER
 	  HPET is the next generation timer replacing legacy 8254s.
 	  The HPET provides a stable time base on SMP
 	  systems, unlike the TSC, but it is more expensive to access,
-	  as it is off-chip.  You can find the HPET spec at
-	  <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>.
+	  as it is off-chip.  The interface used is documented
+	  in the HPET spec, revision 1.
 
 	  You can safely choose Y here.  However, HPET will only be
 	  activated if the platform and the BIOS support this feature.
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index 19c099a..e795f52 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -41,7 +41,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 #else
-#error Live patching support is disabled; check CONFIG_LIVEPATCH
+#error Include linux/livepatch.h, not asm/livepatch.h
 #endif
 
 #endif /* _ASM_X86_LIVEPATCH_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2d5a50c..20c11d1 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -766,7 +766,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
  * Return saved PC of a blocked thread.
  * What is this good for? it will be always the scheduler or ret_from_fork.
  */
-#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
+#define thread_saved_pc(t)	READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 4974274..8836fc9 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -323,6 +323,8 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 	return 0;
 
 fail:
+	if (amd_uncore_nb)
+		*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
 	kfree(uncore_nb);
 	return -ENOMEM;
 }
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 982ce34..27f89c7 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
+
+	/* If size is less than 8 bytes, go to 4-byte copy */
 	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	jb .L_4b_nocache_copy_entry
+
+	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
+
+	/* Set 4x8-byte copy count and remainder */
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_8b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
 	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
+	jnz .L_4x8b_nocache_copy_loop
+
+	/* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
+	jz .L_4b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:	movq (%rsi),%r8
+21:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
 	leaq 8(%rdi),%rdi
 	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
+	jnz .L_8b_nocache_copy_loop
+
+	/* If no byte left, we're done */
+.L_4b_nocache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* If destination is not 4-byte aligned, go to byte copy: */
+	movl %edi,%ecx
+	andl $3,%ecx
+	jnz .L_1b_cache_copy_entry
+
+	/* Set 4-byte copy count (1 or 0) and remainder */
 	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
+	andl $3,%edx
+	shrl $2,%ecx
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4-byte nocache copy: */
+30:	movl (%rsi),%r8d
+31:	movnti %r8d,(%rdi)
+	leaq 4(%rsi),%rsi
+	leaq 4(%rdi),%rdi
+
+	/* If no bytes left, we're done: */
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
+	movl %edx,%ecx
+.L_1b_cache_copy_loop:
+40:	movb (%rsi),%al
+41:	movb %al,(%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
+	jnz .L_1b_cache_copy_loop
+
+	/* Finished copying; fence the prior stores */
+.L_finish_copy:
+	xorl %eax,%eax
 	ASM_CLAC
 	sfence
 	ret
 
 	.section .fixup,"ax"
-30:	shll $6,%ecx
+.L_fixup_4x8b_copy:
+	shll $6,%ecx
 	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
+	jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+	lea (%rdx,%rcx,8),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+	lea (%rdx,%rcx,4),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+	movl %ecx,%edx
+.L_fixup_handle_tail:
+	sfence
 	jmp copy_user_handle_tail
 	.previous
 
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
+	_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(30b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(31b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
+	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index eef44d9..e830c71 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
+	if (pmd_huge(*pmd_k))
+		return 0;
+
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -360,8 +363,6 @@ void vmalloc_sync_all(void)
  * 64-bit:
  *
  *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
  */
 static noinline int vmalloc_fault(unsigned long address)
 {
@@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud_ref))
 		return -1;
 
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
+	if (pud_huge(*pud))
+		return 0;
+
 	pmd = pmd_offset(pud, address);
 	pmd_ref = pmd_offset(pud_ref, address);
 	if (pmd_none(*pmd_ref))
 		return -1;
 
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
+	if (pmd_huge(*pmd))
+		return 0;
+
 	pte_ref = pte_offset_kernel(pmd_ref, address);
 	if (!pte_present(*pte_ref))
 		return -1;
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 6d5eb59..d8a798d 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -102,7 +102,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 
-		page = pte_page(pte);
 		if (pte_devmap(pte)) {
 			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
 			if (unlikely(!pgmap)) {
@@ -115,6 +114,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 			return 0;
 		}
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
 		get_page(page);
 		put_dev_pagemap(pgmap);
 		SetPageReferenced(page);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 42982b2..740d7ac 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -173,10 +173,10 @@ static __init int setup_hugepagesz(char *opt)
 }
 __setup("hugepagesz=", setup_hugepagesz);
 
-#ifdef CONFIG_CMA
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 static __init int gigantic_pages_init(void)
 {
-	/* With CMA we can allocate gigantic pages at runtime */
+	/* With compaction or CMA we can allocate gigantic pages at runtime */
 	if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	return 0;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f65..d04f809 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -469,7 +469,7 @@ static void __init numa_clear_kernel_node_hotplug(void)
 {
 	int i, nid;
 	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	unsigned long start, end;
+	phys_addr_t start, end;
 	struct memblock_region *r;
 
 	/*