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:

   - two boot crash fixes
   - unwinder fixes
   - kexec related kernel direct mappings enhancements/fixes
   - more Clang support quirks
   - minor cleanups
   - Documentation fixes"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/intel_rdt: Fix a typo in Documentation
  x86/build: Don't add -maccumulate-outgoing-args w/o compiler support
  x86/boot/32: Fix UP boot on Quark and possibly other platforms
  x86/mm/32: Set the '__vmalloc_start_set' flag in initmem_init()
  x86/kexec/64: Use gbpages for identity mappings if available
  x86/mm: Add support for gbpages to kernel_ident_mapping_init()
  x86/boot: Declare error() as noreturn
  x86/mm/kaslr: Use the _ASM_MUL macro for multiplication to work around Clang incompatibility
  x86/mm: Fix boot crash caused by incorrect loop count calculation in sync_global_pgds()
  x86/asm: Don't use RBP as a temporary register in csum_partial_copy_generic()
  x86/microcode/AMD: Remove redundant NULL check on mc

16 files changed, 64 insertions, 28 deletions

diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index 0f6d8477b66c..c491a1b82de2 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -295,7 +295,7 @@ kernel and the tasks running there get 50% of the cache. They should
 also get 50% of memory bandwidth assuming that the cores 4-7 are SMT
 siblings and only the real time threads are scheduled on the cores 4-7.
 
-# echo C0 > p0/cpus
+# echo F0 > p0/cpus
 
 4) Locking between applications
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 4430dd489620..5851411e60fb 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -179,7 +179,8 @@ ifdef CONFIG_JUMP_LABEL
 endif
 
 ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
-	KBUILD_CFLAGS += -maccumulate-outgoing-args
+	# This compiler flag is not supported by Clang:
+	KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,)
 endif
 
 # Stackpointer is addressed different for 32 bit and 64 bit x86
diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h
index 2e59dac07f9e..d732e608e3af 100644
--- a/arch/x86/boot/compressed/error.h
+++ b/arch/x86/boot/compressed/error.h
@@ -1,7 +1,9 @@
 #ifndef BOOT_COMPRESSED_ERROR_H
 #define BOOT_COMPRESSED_ERROR_H
 
+#include <linux/compiler.h>
+
 void warn(char *m);
-void error(char *m);
+void error(char *m) __noreturn;
 
 #endif /* BOOT_COMPRESSED_ERROR_H */
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index 56589d0a804b..1d78f1739087 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -70,7 +70,7 @@ static unsigned long level4p;
  * Due to relocation, pointers must be assigned at run time not build time.
  */
 static struct x86_mapping_info mapping_info = {
-	.pmd_flag       = __PAGE_KERNEL_LARGE_EXEC,
+	.page_flag       = __PAGE_KERNEL_LARGE_EXEC,
 };
 
 /* Locates and clears a region for a new top level page table. */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7acb51c49fec..7a9df3beb89b 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -32,6 +32,7 @@
 #define _ASM_ADD	__ASM_SIZE(add)
 #define _ASM_SUB	__ASM_SIZE(sub)
 #define _ASM_XADD	__ASM_SIZE(xadd)
+#define _ASM_MUL	__ASM_SIZE(mul)
 
 #define _ASM_AX		__ASM_REG(ax)
 #define _ASM_BX		__ASM_REG(bx)
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 737da62bfeb0..474eb8c66fee 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -4,8 +4,9 @@
 struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
 	void *context;			 /* context for alloc_pgt_page */
-	unsigned long pmd_flag;		 /* page flag for PMD entry */
+	unsigned long page_flag;	 /* page flag for PMD or PUD entry */
 	unsigned long offset;		 /* ident mapping offset */
+	bool direct_gbpages;		 /* PUD level 1GB page support */
 };
 
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 7889ae492af0..1d38e53c2d5c 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -352,8 +352,6 @@ void reload_ucode_amd(void)
 	u32 rev, dummy;
 
 	mc = (struct microcode_amd *)amd_ucode_patch;
-	if (!mc)
-		return;
 
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index ce640428d6fe..6f5ca4ebe6e5 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -114,7 +114,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 	struct x86_mapping_info info = {
 		.alloc_pgt_page	= alloc_pgt_page,
 		.context	= image,
-		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
 	};
 	unsigned long mstart, mend;
 	pgd_t *level4p;
@@ -123,6 +123,10 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 
 	level4p = (pgd_t *)__va(start_pgtable);
 	clear_page(level4p);
+
+	if (direct_gbpages)
+		info.direct_gbpages = true;
+
 	for (i = 0; i < nr_pfn_mapped; i++) {
 		mstart = pfn_mapped[i].start << PAGE_SHIFT;
 		mend   = pfn_mapped[i].end << PAGE_SHIFT;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 603a1669a2ec..0b4d3c686b1e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1225,6 +1225,21 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
+#ifdef CONFIG_X86_32
+	/* sync back kernel address range */
+	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			KERNEL_PGD_PTRS);
+
+	/*
+	 * sync back low identity map too.  It is used for example
+	 * in the 32-bit EFI stub.
+	 */
+	clone_pgd_range(initial_page_table,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+#endif
+
 	tboot_probe();
 
 	map_vsyscall();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index bb1e8cc0bc84..10edd1e69a68 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -291,11 +291,11 @@ void __init setup_per_cpu_areas(void)
 
 #ifdef CONFIG_X86_32
 	/*
-	 * Sync back kernel address range.  We want to make sure that
-	 * all kernel mappings, including percpu mappings, are available
-	 * in the smpboot asm.  We can't reliably pick up percpu
-	 * mappings using vmalloc_fault(), because exception dispatch
-	 * needs percpu data.
+	 * Sync back kernel address range again.  We already did this in
+	 * setup_arch(), but percpu data also needs to be available in
+	 * the smpboot asm.  We can't reliably pick up percpu mappings
+	 * using vmalloc_fault(), because exception dispatch needs
+	 * percpu data.
 	 */
 	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
 			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 7e48807b2fa1..45a53dfe1859 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -55,7 +55,7 @@ ENTRY(csum_partial_copy_generic)
 	movq  %r12, 3*8(%rsp)
 	movq  %r14, 4*8(%rsp)
 	movq  %r13, 5*8(%rsp)
-	movq  %rbp, 6*8(%rsp)
+	movq  %r15, 6*8(%rsp)
 
 	movq  %r8, (%rsp)
 	movq  %r9, 1*8(%rsp)
@@ -74,7 +74,7 @@ ENTRY(csum_partial_copy_generic)
 	/* main loop. clear in 64 byte blocks */
 	/* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
 	/* r11:	temp3, rdx: temp4, r12 loopcnt */
-	/* r10:	temp5, rbp: temp6, r14 temp7, r13 temp8 */
+	/* r10:	temp5, r15: temp6, r14 temp7, r13 temp8 */
 	.p2align 4
 .Lloop:
 	source
@@ -89,7 +89,7 @@ ENTRY(csum_partial_copy_generic)
 	source
 	movq  32(%rdi), %r10
 	source
-	movq  40(%rdi), %rbp
+	movq  40(%rdi), %r15
 	source
 	movq  48(%rdi), %r14
 	source
@@ -103,7 +103,7 @@ ENTRY(csum_partial_copy_generic)
 	adcq  %r11, %rax
 	adcq  %rdx, %rax
 	adcq  %r10, %rax
-	adcq  %rbp, %rax
+	adcq  %r15, %rax
 	adcq  %r14, %rax
 	adcq  %r13, %rax
 
@@ -121,7 +121,7 @@ ENTRY(csum_partial_copy_generic)
 	dest
 	movq %r10, 32(%rsi)
 	dest
-	movq %rbp, 40(%rsi)
+	movq %r15, 40(%rsi)
 	dest
 	movq %r14, 48(%rsi)
 	dest
@@ -203,7 +203,7 @@ ENTRY(csum_partial_copy_generic)
 	movq 3*8(%rsp), %r12
 	movq 4*8(%rsp), %r14
 	movq 5*8(%rsp), %r13
-	movq 6*8(%rsp), %rbp
+	movq 6*8(%rsp), %r15
 	addq $7*8, %rsp
 	ret
 
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 5761a4f19455..ab2d1d73e9e7 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -5,6 +5,7 @@
  * kernel starts. This file is included in the compressed kernel and
  * normally linked in the regular.
  */
+#include <asm/asm.h>
 #include <asm/kaslr.h>
 #include <asm/msr.h>
 #include <asm/archrandom.h>
@@ -79,7 +80,7 @@ unsigned long kaslr_get_random_long(const char *purpose)
 	}
 
 	/* Circular multiply for better bit diffusion */
-	asm("mul %3"
+	asm(_ASM_MUL "%3"
 	    : "=a" (random), "=d" (raw)
 	    : "a" (random), "rm" (mix_const));
 	random += raw;
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 04210a29dd60..adab1595f4bd 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -13,7 +13,7 @@ static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
 		if (pmd_present(*pmd))
 			continue;
 
-		set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag));
+		set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag));
 	}
 }
 
@@ -30,6 +30,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 		if (next > end)
 			next = end;
 
+		if (info->direct_gbpages) {
+			pud_t pudval;
+
+			if (pud_present(*pud))
+				continue;
+
+			addr &= PUD_MASK;
+			pudval = __pud((addr - info->offset) | info->page_flag);
+			set_pud(pud, pudval);
+			continue;
+		}
+
 		if (pud_present(*pud)) {
 			pmd = pmd_offset(pud, 0);
 			ident_pmd_init(info, pmd, addr, next);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 41270b96403d..95651dc58e09 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -94,10 +94,10 @@ __setup("noexec32=", nonx32_setup);
  */
 void sync_global_pgds(unsigned long start, unsigned long end)
 {
-	unsigned long address;
+	unsigned long addr;
 
-	for (address = start; address <= end; address += PGDIR_SIZE) {
-		pgd_t *pgd_ref = pgd_offset_k(address);
+	for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+		pgd_t *pgd_ref = pgd_offset_k(addr);
 		const p4d_t *p4d_ref;
 		struct page *page;
 
@@ -106,7 +106,7 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		 * handle synchonization on p4d level.
 		 */
 		BUILD_BUG_ON(pgd_none(*pgd_ref));
-		p4d_ref = p4d_offset(pgd_ref, address);
+		p4d_ref = p4d_offset(pgd_ref, addr);
 
 		if (p4d_none(*p4d_ref))
 			continue;
@@ -117,8 +117,8 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 			p4d_t *p4d;
 			spinlock_t *pgt_lock;
 
-			pgd = (pgd_t *)page_address(page) + pgd_index(address);
-			p4d = p4d_offset(pgd, address);
+			pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+			p4d = p4d_offset(pgd, addr);
 			/* the pgt_lock only for Xen */
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 			spin_lock(pgt_lock);
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 6b7ce6279133..aca6295350f3 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -100,5 +100,6 @@ void __init initmem_init(void)
 	printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
 			(ulong) pfn_to_kaddr(highstart_pfn));
 
+	__vmalloc_start_set = true;
 	setup_bootmem_allocator();
 }
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 6a61194ffd58..a6e21fee22ea 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -104,7 +104,7 @@ static int set_up_temporary_mappings(void)
 {
 	struct x86_mapping_info info = {
 		.alloc_pgt_page	= alloc_pgt_page,
-		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
 		.offset		= __PAGE_OFFSET,
 	};
 	unsigned long mstart, mend;