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

Pull x86 fixes from Thomas Gleixner:
 "This update contains:

   - the manual revert of the SYSCALL32 changes which caused a
     regression

   - a fix for the MPX vma handling

   - three fixes for the ioremap 'is ram' checks.

   - PAT warning fixes

   - a trivial fix for the size calculation of TLB tracepoints

   - handle old EFI structures gracefully

  This also contains a PAT fix from Jan plus a revert thereof.  Toshi
  explained why the code is correct"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm/pat: Revert 'Adjust default caching mode translation tables'
  x86/asm/entry/32: Revert 'Do not use R9 in SYSCALL32' commit
  x86/mm: Fix newly introduced printk format warnings
  mm: Fix bugs in region_is_ram()
  x86/mm: Remove region_is_ram() call from ioremap
  x86/mm: Move warning from __ioremap_check_ram() to the call site
  x86/mm/pat, drivers/media/ivtv: Move the PAT warning and replace WARN() with pr_warn()
  x86/mm/pat, drivers/infiniband/ipath: Replace WARN() with pr_warn()
  x86/mm/pat: Adjust default caching mode translation tables
  x86/fpu: Disable dependent CPU features on "noxsave"
  x86/mpx: Do not set ->vm_ops on MPX VMAs
  x86/mm: Add parenthesis for TLB tracepoint size calculation
  efi: Handle memory error structures produced based on old versions of standard

arch/x86/entry/entry_64_compat.S

@@ -205,7 +205,6 @@ sysexit_from_sys_call:
 	movl	RDX(%rsp), %edx		/* arg3 */
 	movl	RSI(%rsp), %ecx		/* arg4 */
 	movl	RDI(%rsp), %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
 	.endm
 
 	.macro auditsys_exit exit
@@ -236,6 +235,7 @@ sysexit_from_sys_call:
 
 sysenter_auditsys:
 	auditsys_entry_common
+	movl	%ebp, %r9d		/* reload 6th syscall arg */
 	jmp	sysenter_dispatch
 
 sysexit_audit:
@@ -336,7 +336,7 @@ ENTRY(entry_SYSCALL_compat)
 	 * 32-bit zero extended:
 	 */
 	ASM_STAC
-1:	movl	(%r8), %ebp
+1:	movl	(%r8), %r9d
 	_ASM_EXTABLE(1b, ia32_badarg)
 	ASM_CLAC
 	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
@@ -346,7 +346,7 @@ ENTRY(entry_SYSCALL_compat)
 cstar_do_call:
 	/* 32-bit syscall -> 64-bit C ABI argument conversion */
 	movl	%edi, %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
+	/* r9 already loaded */		/* arg6 */
 	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
 	movl	%ebx, %edi		/* arg1 */
 	movl	%edx, %edx		/* arg3 (zero extension) */
@@ -358,7 +358,6 @@ cstar_dispatch:
 	call	*ia32_sys_call_table(, %rax, 8)
 	movq	%rax, RAX(%rsp)
 1:
-	movl	RCX(%rsp), %ebp
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
@@ -392,7 +391,9 @@ sysretl_from_sys_call:
 
 #ifdef CONFIG_AUDITSYSCALL
 cstar_auditsys:
+	movl	%r9d, R9(%rsp)		/* register to be clobbered by call */
 	auditsys_entry_common
+	movl	R9(%rsp), %r9d		/* reload 6th syscall arg */
 	jmp	cstar_dispatch
 
 sysretl_audit:
@@ -404,14 +405,16 @@ cstar_tracesys:
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
 	jz	cstar_auditsys
 #endif
+	xchgl	%r9d, %ebp
 	SAVE_EXTRA_REGS
 	xorl	%eax, %eax		/* Do not leak kernel information */
 	movq	%rax, R11(%rsp)
 	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
+	movq	%r9, R9(%rsp)
 	movq	%rax, R8(%rsp)
 	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
 	call	syscall_trace_enter
+	movl	R9(%rsp), %r9d
 
 	/* Reload arg registers from stack. (see sysenter_tracesys) */
 	movl	RCX(%rsp), %ecx
@@ -421,6 +424,7 @@ cstar_tracesys:
 	movl	%eax, %eax		/* zero extension */
 
 	RESTORE_EXTRA_REGS
+	xchgl	%ebp, %r9d
 	jmp	cstar_do_call
 END(entry_SYSCALL_compat)
 

arch/x86/kernel/fpu/init.c

@@ -351,9 +351,15 @@ static int __init x86_noxsave_setup(char *s)
 
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEC);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 	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_AVX512PF);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
 
 	return 1;
 }

arch/x86/mm/ioremap.c

@@ -63,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
 		    !PageReserved(pfn_to_page(start_pfn + i)))
 			return 1;
 
-	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
-
 	return 0;
 }
 
@@ -94,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
-	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -117,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	/* First check if whole region can be identified as RAM or not */
-	ram_region = region_is_ram(phys_addr, size);
-	if (ram_region > 0) {
-		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
-				(unsigned long int)phys_addr,
-				(unsigned long int)last_addr);
-		return NULL;
-	}
-
-	/* If could not be identified(-1), check page by page */
-	if (ram_region < 0) {
 	pfn      = phys_addr >> PAGE_SHIFT;
 	last_pfn = last_addr >> PAGE_SHIFT;
 	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-					  __ioremap_check_ram) == 1)
+					  __ioremap_check_ram) == 1) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
 		return NULL;
 	}
+
 	/*
 	 * Mappings have to be page-aligned
 	 */

arch/x86/mm/mmap.c

@@ -126,3 +126,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_MPX)
+		return "[mpx]";
+	return NULL;
+}

arch/x86/mm/mpx.c

@@ -20,20 +20,6 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/mpx.h>
 
-static const char *mpx_mapping_name(struct vm_area_struct *vma)
-{
-	return "[mpx]";
-}
-
-static struct vm_operations_struct mpx_vma_ops = {
-	.name = mpx_mapping_name,
-};
-
-static int is_mpx_vma(struct vm_area_struct *vma)
-{
-	return (vma->vm_ops == &mpx_vma_ops);
-}
-
 static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
 {
 	if (is_64bit_mm(mm))
@@ -53,9 +39,6 @@ static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm)
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
- *
- * Later on, we use the vma->vm_ops to uniquely identify these
- * VMAs.
  */
 static unsigned long mpx_mmap(unsigned long len)
 {
@@ -101,7 +84,6 @@ static unsigned long mpx_mmap(unsigned long len)
 		ret = -ENOMEM;
 		goto out;
 	}
-	vma->vm_ops = &mpx_vma_ops;
 
 	if (vm_flags & VM_LOCKED) {
 		up_write(&mm->mmap_sem);
@@ -812,7 +794,7 @@ static noinline int zap_bt_entries_mapping(struct mm_struct *mm,
 		 * so stop immediately and return an error.  This
 		 * probably results in a SIGSEGV.
 		 */
-		if (!is_mpx_vma(vma))
+		if (!(vma->vm_flags & VM_MPX))
 			return -EINVAL;
 
 		len = min(vma->vm_end, end) - addr;
@@ -945,9 +927,9 @@ static int try_unmap_single_bt(struct mm_struct *mm,
 	 * lots of tables even though we have no actual table
 	 * entries in use.
 	 */
-	while (next && is_mpx_vma(next))
+	while (next && (next->vm_flags & VM_MPX))
 		next = next->vm_next;
-	while (prev && is_mpx_vma(prev))
+	while (prev && (prev->vm_flags & VM_MPX))
 		prev = prev->vm_prev;
 	/*
 	 * We know 'start' and 'end' lie within an area controlled

arch/x86/mm/tlb.c

@@ -117,7 +117,7 @@ static void flush_tlb_func(void *info)
 		} else {
 			unsigned long addr;
 			unsigned long nr_pages =
-				f->flush_end - f->flush_start / PAGE_SIZE;
+				(f->flush_end - f->flush_start) / PAGE_SIZE;
 			addr = f->flush_start;
 			while (addr < f->flush_end) {
 				__flush_tlb_single(addr);

drivers/firmware/efi/cper.c

@@ -305,10 +305,17 @@ const char *cper_mem_err_unpack(struct trace_seq *p,
 	return ret;
 }
 
-static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
+	int len)
 {
 	struct cper_mem_err_compact cmem;
 
+	/* Don't trust UEFI 2.1/2.2 structure with bad validation bits */
+	if (len == sizeof(struct cper_sec_mem_err_old) &&
+	    (mem->validation_bits & ~(CPER_MEM_VALID_RANK_NUMBER - 1))) {
+		pr_err(FW_WARN "valid bits set for fields beyond structure\n");
+		return;
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
 	if (mem->validation_bits & CPER_MEM_VALID_PA)
@@ -405,8 +412,10 @@ static void cper_estatus_print_section(
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
 		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
 		printk("%s""section_type: memory error\n", newpfx);
-		if (gdata->error_data_length >= sizeof(*mem_err))
-			cper_print_mem(newpfx, mem_err);
+		if (gdata->error_data_length >=
+		    sizeof(struct cper_sec_mem_err_old))
+			cper_print_mem(newpfx, mem_err,
+				       gdata->error_data_length);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {

drivers/infiniband/hw/ipath/ipath_driver.c

@@ -31,6 +31,8 @@
  * SOFTWARE.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>
@@ -399,8 +401,8 @@ static int ipath_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	u32 bar0 = 0, bar1 = 0;
 
 #ifdef CONFIG_X86_64
-	if (WARN(pat_enabled(),
-		 "ipath needs PAT disabled, boot with nopat kernel parameter\n")) {
+	if (pat_enabled()) {
+		pr_warn("ipath needs PAT disabled, boot with nopat kernel parameter\n");
 		ret = -ENODEV;
 		goto bail;
 	}

drivers/media/pci/ivtv/ivtvfb.c

@@ -38,6 +38,8 @@
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fb.h>
@@ -1171,6 +1173,13 @@ static int ivtvfb_init_card(struct ivtv *itv)
 {
 	int rc;
 
+#ifdef CONFIG_X86_64
+	if (pat_enabled()) {
+		pr_warn("ivtvfb needs PAT disabled, boot with nopat kernel parameter\n");
+		return -ENODEV;
+	}
+#endif
+
 	if (itv->osd_info) {
 		IVTVFB_ERR("Card %d already initialised\n", ivtvfb_card_id);
 		return -EBUSY;
@@ -1265,12 +1274,6 @@ static int __init ivtvfb_init(void)
 	int registered = 0;
 	int err;
 
-#ifdef CONFIG_X86_64
-	if (WARN(pat_enabled(),
-		 "ivtvfb needs PAT disabled, boot with nopat kernel parameter\n")) {
-		return -ENODEV;
-	}
-#endif
 
 	if (ivtvfb_card_id < -1 || ivtvfb_card_id >= IVTV_MAX_CARDS) {
 		printk(KERN_ERR "ivtvfb:  ivtvfb_card_id parameter is out of range (valid range: -1 - %d)\n",

include/linux/cper.h

@@ -340,7 +340,27 @@ struct cper_ia_proc_ctx {
 	__u64	mm_reg_addr;
 };
 
-/* Memory Error Section */
+/* Old Memory Error Section UEFI 2.1, 2.2 */
+struct cper_sec_mem_err_old {
+	__u64	validation_bits;
+	__u64	error_status;
+	__u64	physical_addr;
+	__u64	physical_addr_mask;
+	__u16	node;
+	__u16	card;
+	__u16	module;
+	__u16	bank;
+	__u16	device;
+	__u16	row;
+	__u16	column;
+	__u16	bit_pos;
+	__u64	requestor_id;
+	__u64	responder_id;
+	__u64	target_id;
+	__u8	error_type;
+};
+
+/* Memory Error Section UEFI >= 2.3 */
 struct cper_sec_mem_err {
 	__u64	validation_bits;
 	__u64	error_status;

kernel/resource.c

@@ -504,13 +504,13 @@ int region_is_ram(resource_size_t start, unsigned long size)
 {
 	struct resource *p;
 	resource_size_t end = start + size - 1;
-	int flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	const char *name = "System RAM";
 	int ret = -1;
 
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
-		if (end < p->start)
+		if (p->end < start)
 			continue;
 
 		if (p->start <= start && end <= p->end) {
@@ -521,7 +521,7 @@ int region_is_ram(resource_size_t start, unsigned long size)
 				ret = 1;
 			break;
 		}
-		if (p->end < start)
+		if (end < p->start)
 			break;	/* not found */
 	}
 	read_unlock(&resource_lock);