Merge branch 'x86-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (246 commits)
  x86: traps.c replace #if CONFIG_X86_32 with #ifdef CONFIG_X86_32
  x86: PAT: fix address types in track_pfn_vma_new()
  x86: prioritize the FPU traps for the error code
  x86: PAT: pfnmap documentation update changes
  x86: PAT: move track untrack pfnmap stubs to asm-generic
  x86: PAT: remove follow_pfnmap_pte in favor of follow_phys
  x86: PAT: modify follow_phys to return phys_addr prot and return value
  x86: PAT: clarify is_linear_pfn_mapping() interface
  x86: ia32_signal: remove unnecessary declaration
  x86: common.c boot_cpu_stack and boot_exception_stacks should be static
  x86: fix intel x86_64 llc_shared_map/cpu_llc_id anomolies
  x86: fix warning in arch/x86/kernel/microcode_amd.c
  x86: ia32.h: remove unused struct sigfram32 and rt_sigframe32
  x86: asm-offset_64: use rt_sigframe_ia32
  x86: sigframe.h: include headers for dependency
  x86: traps.c declare functions before they get used
  x86: PAT: update documentation to cover pgprot and remap_pfn related changes - v3
  x86: PAT: add pgprot_writecombine() interface for drivers - v3
  x86: PAT: change pgprot_noncached to uc_minus instead of strong uc - v3
  x86: PAT: implement track/untrack of pfnmap regions for x86 - v3
  ...

5 files changed, 266 insertions, 18 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 3a1b6ef4f05d..46b5f753ff81 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -413,6 +413,7 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
 				 unsigned long error_code)
 {
 	unsigned long flags = oops_begin();
+	int sig = SIGKILL;
 	struct task_struct *tsk;
 
 	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
@@ -423,8 +424,8 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
 	if (__die("Bad pagetable", regs, error_code))
-		regs = NULL;
-	oops_end(flags, regs, SIGKILL);
+		sig = 0;
+	oops_end(flags, regs, sig);
 }
 #endif
 
@@ -590,6 +591,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	int fault;
 #ifdef CONFIG_X86_64
 	unsigned long flags;
+	int sig;
 #endif
 
 	tsk = current;
@@ -849,11 +851,12 @@ no_context:
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
 #else
+	sig = SIGKILL;
 	if (__die("Oops", regs, error_code))
-		regs = NULL;
+		sig = 0;
 	/* Executive summary in case the body of the oops scrolled away */
 	printk(KERN_EMERG "CR2: %016lx\n", address);
-	oops_end(flags, regs, SIGKILL);
+	oops_end(flags, regs, sig);
 #endif
 
 /*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c483f4242079..800e1d94c1b5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -67,7 +67,7 @@ static unsigned long __meminitdata table_top;
 
 static int __initdata after_init_bootmem;
 
-static __init void *alloc_low_page(unsigned long *phys)
+static __init void *alloc_low_page(void)
 {
 	unsigned long pfn = table_end++;
 	void *adr;
@@ -77,7 +77,6 @@ static __init void *alloc_low_page(unsigned long *phys)
 
 	adr = __va(pfn * PAGE_SIZE);
 	memset(adr, 0, PAGE_SIZE);
-	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
 
@@ -92,16 +91,17 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 	pmd_t *pmd_table;
 
 #ifdef CONFIG_X86_PAE
-	unsigned long phys;
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
 		if (after_init_bootmem)
 			pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 		else
-			pmd_table = (pmd_t *)alloc_low_page(&phys);
+			pmd_table = (pmd_t *)alloc_low_page();
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+		return pmd_table;
 	}
 #endif
 	pud = pud_offset(pgd, 0);
@@ -126,10 +126,8 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 			if (!page_table)
 				page_table =
 				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
-		} else {
-			unsigned long phys;
-			page_table = (pte_t *)alloc_low_page(&phys);
-		}
+		} else
+			page_table = (pte_t *)alloc_low_page();
 
 		paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -969,8 +967,6 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
-	start_periodic_check_for_corruption();
-
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif
@@ -1040,11 +1036,25 @@ void __init mem_init(void)
 		(unsigned long)&_text, (unsigned long)&_etext,
 		((unsigned long)&_etext - (unsigned long)&_text) >> 10);
 
+	/*
+	 * Check boundaries twice: Some fundamental inconsistencies can
+	 * be detected at build time already.
+	 */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+#ifdef CONFIG_HIGHMEM
+	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
+	BUILD_BUG_ON(VMALLOC_END			> PKMAP_BASE);
+#endif
+#define high_memory (-128UL << 20)
+	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
+#undef high_memory
+#undef __FIXADDR_TOP
+
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
 	BUG_ON(VMALLOC_END				> PKMAP_BASE);
 #endif
-	BUG_ON(VMALLOC_START				> VMALLOC_END);
+	BUG_ON(VMALLOC_START				>= VMALLOC_END);
 	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
 
 	if (boot_cpu_data.wp_works_ok < 0)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9db01db6e3cd..9f7a0d24d42a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -902,8 +902,6 @@ void __init mem_init(void)
 	long codesize, reservedpages, datasize, initsize;
 	unsigned long absent_pages;
 
-	start_periodic_check_for_corruption();
-
 	pci_iommu_alloc();
 
 	/* clear_bss() already clear the empty_zero_page */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4c4307ff3e0..bd85d42819e1 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -223,7 +223,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	 * Check if the request spans more than any BAR in the iomem resource
 	 * tree.
 	 */
-	WARN_ON(iomem_map_sanity_check(phys_addr, size));
+	WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
+		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
 
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index eb1bf000d12e..85cbd3cd3723 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -596,6 +596,242 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
 	free_memtype(addr, addr + size);
 }
 
+/*
+ * Internal interface to reserve a range of physical memory with prot.
+ * Reserved non RAM regions only and after successful reserve_memtype,
+ * this func also keeps identity mapping (if any) in sync with this new prot.
+ */
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+{
+	int is_ram = 0;
+	int id_sz, ret;
+	unsigned long flags;
+	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+
+	is_ram = pagerange_is_ram(paddr, paddr + size);
+
+	if (is_ram != 0) {
+		/*
+		 * For mapping RAM pages, drivers need to call
+		 * set_memory_[uc|wc|wb] directly, for reserve and free, before
+		 * setting up the PTE.
+		 */
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
+	if (ret)
+		return ret;
+
+	if (flags != want_flags) {
+		free_memtype(paddr, paddr + size);
+		printk(KERN_ERR
+		"%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
+			current->comm, current->pid,
+			cattr_name(want_flags),
+			(unsigned long long)paddr,
+			(unsigned long long)(paddr + size),
+			cattr_name(flags));
+		return -EINVAL;
+	}
+
+	/* Need to keep identity mapping in sync */
+	if (paddr >= __pa(high_memory))
+		return 0;
+
+	id_sz = (__pa(high_memory) < paddr + size) ?
+				__pa(high_memory) - paddr :
+				size;
+
+	if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+		free_memtype(paddr, paddr + size);
+		printk(KERN_ERR
+			"%s:%d reserve_pfn_range ioremap_change_attr failed %s "
+			"for %Lx-%Lx\n",
+			current->comm, current->pid,
+			cattr_name(flags),
+			(unsigned long long)paddr,
+			(unsigned long long)(paddr + size));
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Internal interface to free a range of physical memory.
+ * Frees non RAM regions only.
+ */
+static void free_pfn_range(u64 paddr, unsigned long size)
+{
+	int is_ram;
+
+	is_ram = pagerange_is_ram(paddr, paddr + size);
+	if (is_ram == 0)
+		free_memtype(paddr, paddr + size);
+}
+
+/*
+ * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * copied through copy_page_range().
+ *
+ * If the vma has a linear pfn mapping for the entire range, we get the prot
+ * from pte and reserve the entire vma range with single reserve_pfn_range call.
+ * Otherwise, we reserve the entire vma range, my ging through the PTEs page
+ * by page to get physical address and protection.
+ */
+int track_pfn_vma_copy(struct vm_area_struct *vma)
+{
+	int retval = 0;
+	unsigned long i, j;
+	resource_size_t paddr;
+	unsigned long prot;
+	unsigned long vma_start = vma->vm_start;
+	unsigned long vma_end = vma->vm_end;
+	unsigned long vma_size = vma_end - vma_start;
+
+	if (!pat_enabled)
+		return 0;
+
+	if (is_linear_pfn_mapping(vma)) {
+		/*
+		 * reserve the whole chunk covered by vma. We need the
+		 * starting address and protection from pte.
+		 */
+		if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
+		return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+	}
+
+	/* reserve entire vma page by page, using pfn and prot from pte */
+	for (i = 0; i < vma_size; i += PAGE_SIZE) {
+		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+			continue;
+
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+		if (retval)
+			goto cleanup_ret;
+	}
+	return 0;
+
+cleanup_ret:
+	/* Reserve error: Cleanup partial reservation and return error */
+	for (j = 0; j < i; j += PAGE_SIZE) {
+		if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
+			continue;
+
+		free_pfn_range(paddr, PAGE_SIZE);
+	}
+
+	return retval;
+}
+
+/*
+ * track_pfn_vma_new is called when a _new_ pfn mapping is being established
+ * for physical range indicated by pfn and size.
+ *
+ * prot is passed in as a parameter for the new mapping. If the vma has a
+ * linear pfn mapping for the entire range reserve the entire vma range with
+ * single reserve_pfn_range call.
+ * Otherwise, we look t the pfn and size and reserve only the specified range
+ * page by page.
+ *
+ * Note that this function can be called with caller trying to map only a
+ * subrange/page inside the vma.
+ */
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+			unsigned long pfn, unsigned long size)
+{
+	int retval = 0;
+	unsigned long i, j;
+	resource_size_t base_paddr;
+	resource_size_t paddr;
+	unsigned long vma_start = vma->vm_start;
+	unsigned long vma_end = vma->vm_end;
+	unsigned long vma_size = vma_end - vma_start;
+
+	if (!pat_enabled)
+		return 0;
+
+	if (is_linear_pfn_mapping(vma)) {
+		/* reserve the whole chunk starting from vm_pgoff */
+		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		return reserve_pfn_range(paddr, vma_size, prot);
+	}
+
+	/* reserve page by page using pfn and size */
+	base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		paddr = base_paddr + i;
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+		if (retval)
+			goto cleanup_ret;
+	}
+	return 0;
+
+cleanup_ret:
+	/* Reserve error: Cleanup partial reservation and return error */
+	for (j = 0; j < i; j += PAGE_SIZE) {
+		paddr = base_paddr + j;
+		free_pfn_range(paddr, PAGE_SIZE);
+	}
+
+	return retval;
+}
+
+/*
+ * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack can be called for a specific region indicated by pfn and size or
+ * can be for the entire vma (in which case size can be zero).
+ */
+void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
+			unsigned long size)
+{
+	unsigned long i;
+	resource_size_t paddr;
+	unsigned long prot;
+	unsigned long vma_start = vma->vm_start;
+	unsigned long vma_end = vma->vm_end;
+	unsigned long vma_size = vma_end - vma_start;
+
+	if (!pat_enabled)
+		return;
+
+	if (is_linear_pfn_mapping(vma)) {
+		/* free the whole chunk starting from vm_pgoff */
+		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		free_pfn_range(paddr, vma_size);
+		return;
+	}
+
+	if (size != 0 && size != vma_size) {
+		/* free page by page, using pfn and size */
+		paddr = (resource_size_t)pfn << PAGE_SHIFT;
+		for (i = 0; i < size; i += PAGE_SIZE) {
+			paddr = paddr + i;
+			free_pfn_range(paddr, PAGE_SIZE);
+		}
+	} else {
+		/* free entire vma, page by page, using the pfn from pte */
+		for (i = 0; i < vma_size; i += PAGE_SIZE) {
+			if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+				continue;
+
+			free_pfn_range(paddr, PAGE_SIZE);
+		}
+	}
+}
+
+pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	if (pat_enabled)
+		return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
+	else
+		return pgprot_noncached(prot);
+}
+
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
 /* get Nth element of the linked list */