Merge branch 'linus' into x86/mm

Conflicts:
	arch/x86/mm/fault.c

7 files changed, 125 insertions, 59 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 8e9b0f1fd87..817a78d5aca 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -808,8 +808,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	/* get the address */
 	address = read_cr2();
 
-	if (unlikely(notify_page_fault(regs)))
-		return;
 	if (unlikely(kmmio_fault(regs, address)))
 		return;
 
@@ -835,6 +833,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		if (spurious_fault(error_code, address))
 			return;
 
+		/* kprobes don't want to hook the spurious faults. */
+		if (notify_page_fault(regs))
+			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
 		 * fault we could otherwise deadlock.
@@ -843,6 +844,8 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		return;
 	}
 
+	if (unlikely(notify_page_fault(regs)))
+		return;
 	/*
 	 * It's safe to allow irq's after cr2 has been saved and the
 	 * vmalloc fault has been handled.
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 88f1b10de3b..2cef0507441 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -138,6 +138,47 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	return pte_offset_kernel(pmd, 0);
 }
 
+static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
+					   unsigned long vaddr, pte_t *lastpte)
+{
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * Something (early fixmap) may already have put a pte
+	 * page here, which causes the page table allocation
+	 * to become nonlinear. Attempt to fix it, and if it
+	 * is still nonlinear then we have to bug.
+	 */
+	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+
+	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
+	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
+	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
+	    && ((__pa(pte) >> PAGE_SHIFT) < table_start
+		|| (__pa(pte) >> PAGE_SHIFT) >= table_end)) {
+		pte_t *newpte;
+		int i;
+
+		BUG_ON(after_init_bootmem);
+		newpte = alloc_low_page();
+		for (i = 0; i < PTRS_PER_PTE; i++)
+			set_pte(newpte + i, pte[i]);
+
+		paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
+		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
+		BUG_ON(newpte != pte_offset_kernel(pmd, 0));
+		__flush_tlb_all();
+
+		paravirt_release_pte(__pa(pte) >> PAGE_SHIFT);
+		pte = newpte;
+	}
+	BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1)
+	       && vaddr > fix_to_virt(FIX_KMAP_END)
+	       && lastpte && lastpte + PTRS_PER_PTE != pte);
+#endif
+	return pte;
+}
+
 /*
  * This function initializes a certain range of kernel virtual memory
  * with new bootmem page tables, everywhere page tables are missing in
@@ -154,6 +195,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 	unsigned long vaddr;
 	pgd_t *pgd;
 	pmd_t *pmd;
+	pte_t *pte = NULL;
 
 	vaddr = start;
 	pgd_idx = pgd_index(vaddr);
@@ -165,7 +207,8 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
 		pmd = pmd + pmd_index(vaddr);
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
 							pmd++, pmd_idx++) {
-			one_page_table_init(pmd);
+			pte = page_table_kmap_check(one_page_table_init(pmd),
+			                            pmd, vaddr, pte);
 
 			vaddr += PMD_SIZE;
 		}
@@ -508,7 +551,6 @@ static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base)
 	 * Fixed mappings, only the page table structure has to be
 	 * created - mappings will be set by set_fixmap():
 	 */
-	early_ioremap_clear();
 	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
 	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
 	page_table_range_init(vaddr, end, pgd_base);
@@ -801,7 +843,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse)
 	tables += PAGE_ALIGN(ptes * sizeof(pte_t));
 
 	/* for fixmap */
-	tables += PAGE_SIZE * 2;
+	tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t));
 
 	/*
 	 * RED-PEN putting page tables only on node 0 could
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 23f68e77ad1..e6d36b49025 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -596,7 +596,7 @@ static void __init init_gbpages(void)
 		direct_gbpages = 0;
 }
 
-static unsigned long __init kernel_physical_mapping_init(unsigned long start,
+static unsigned long __meminit kernel_physical_mapping_init(unsigned long start,
 						unsigned long end,
 						unsigned long page_size_mask)
 {
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index d0151d8ce45..ca53224fc56 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -17,6 +17,7 @@
  */
 
 #include <asm/iomap.h>
+#include <asm/pat.h>
 #include <linux/module.h>
 
 /* Map 'pfn' using fixed map 'type' and protections 'prot'
@@ -29,6 +30,15 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 
 	pagefault_disable();
 
+	/*
+	 * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS.
+	 * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the
+	 * MTRR is UC or WC.  UC_MINUS gets the real intention, of the
+	 * user, which is "WC if the MTRR is WC, UC if you can't do that."
+	 */
+	if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
+		prot = PAGE_KERNEL_UC_MINUS;
+
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index bd85d42819e..af750ab973b 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -557,34 +557,9 @@ void __init early_ioremap_init(void)
 	}
 }
 
-void __init early_ioremap_clear(void)
-{
-	pmd_t *pmd;
-
-	if (early_ioremap_debug)
-		printk(KERN_INFO "early_ioremap_clear()\n");
-
-	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
-	pmd_clear(pmd);
-	paravirt_release_pte(__pa(bm_pte) >> PAGE_SHIFT);
-	__flush_tlb_all();
-}
-
 void __init early_ioremap_reset(void)
 {
-	enum fixed_addresses idx;
-	unsigned long addr, phys;
-	pte_t *pte;
-
 	after_paging_init = 1;
-	for (idx = FIX_BTMAP_BEGIN; idx >= FIX_BTMAP_END; idx--) {
-		addr = fix_to_virt(idx);
-		pte = early_ioremap_pte(addr);
-		if (pte_present(*pte)) {
-			phys = pte_val(*pte) & PAGE_MASK;
-			set_fixmap(idx, phys);
-		}
-	}
 }
 
 static void __init __early_set_fixmap(enum fixed_addresses idx,
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e89d24815f2..84ba74820ad 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -534,6 +534,36 @@ out_unlock:
 	return 0;
 }
 
+static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
+			       int primary)
+{
+	/*
+	 * Ignore all non primary paths.
+	 */
+	if (!primary)
+		return 0;
+
+	/*
+	 * Ignore the NULL PTE for kernel identity mapping, as it is expected
+	 * to have holes.
+	 * Also set numpages to '1' indicating that we processed cpa req for
+	 * one virtual address page and its pfn. TBD: numpages can be set based
+	 * on the initial value and the level returned by lookup_address().
+	 */
+	if (within(vaddr, PAGE_OFFSET,
+		   PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))) {
+		cpa->numpages = 1;
+		cpa->pfn = __pa(vaddr) >> PAGE_SHIFT;
+		return 0;
+	} else {
+		WARN(1, KERN_WARNING "CPA: called for zero pte. "
+			"vaddr = %lx cpa->vaddr = %lx\n", vaddr,
+			*cpa->vaddr);
+
+		return -EFAULT;
+	}
+}
+
 static int __change_page_attr(struct cpa_data *cpa, int primary)
 {
 	unsigned long address;
@@ -549,17 +579,11 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 repeat:
 	kpte = lookup_address(address, &level);
 	if (!kpte)
-		return 0;
+		return __cpa_process_fault(cpa, address, primary);
 
 	old_pte = *kpte;
-	if (!pte_val(old_pte)) {
-		if (!primary)
-			return 0;
-		WARN(1, KERN_WARNING "CPA: called for zero pte. "
-		       "vaddr = %lx cpa->vaddr = %lx\n", address,
-		       *cpa->vaddr);
-		return -EINVAL;
-	}
+	if (!pte_val(old_pte))
+		return __cpa_process_fault(cpa, address, primary);
 
 	if (level == PG_LEVEL_4K) {
 		pte_t new_pte;
@@ -657,12 +681,7 @@ static int cpa_process_alias(struct cpa_data *cpa)
 		vaddr = *cpa->vaddr;
 
 	if (!(within(vaddr, PAGE_OFFSET,
-		    PAGE_OFFSET + (max_low_pfn_mapped << PAGE_SHIFT))
-#ifdef CONFIG_X86_64
-		|| within(vaddr, PAGE_OFFSET + (1UL<<32),
-		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT))
-#endif
-	)) {
+		    PAGE_OFFSET + (max_pfn_mapped << PAGE_SHIFT)))) {
 
 		alias_cpa = *cpa;
 		temp_cpa_vaddr = (unsigned long) __va(cpa->pfn << PAGE_SHIFT);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 8b08fb95527..7b61036427d 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -333,11 +333,23 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 					      req_type & _PAGE_CACHE_MASK);
 	}
 
-	is_range_ram = pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return reserve_ram_pages_type(start, end, req_type, new_type);
-	else if (is_range_ram < 0)
-		return -EINVAL;
+	if (new_type)
+		*new_type = actual_type;
+
+	/*
+	 * For legacy reasons, some parts of the physical address range in the
+	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+	 * the e820 tables).  So we will track the memory attributes of this
+	 * legacy 1MB region using the linear memtype_list always.
+	 */
+	if (end >= ISA_END_ADDRESS) {
+		is_range_ram = pagerange_is_ram(start, end);
+		if (is_range_ram == 1)
+			return reserve_ram_pages_type(start, end, req_type,
+						      new_type);
+		else if (is_range_ram < 0)
+			return -EINVAL;
+	}
 
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
@@ -347,9 +359,6 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	new->end	= end;
 	new->type	= actual_type;
 
-	if (new_type)
-		*new_type = actual_type;
-
 	spin_lock(&memtype_lock);
 
 	if (cached_entry && start >= cached_start)
@@ -437,11 +446,19 @@ int free_memtype(u64 start, u64 end)
 	if (is_ISA_range(start, end - 1))
 		return 0;
 
-	is_range_ram = pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return free_ram_pages_type(start, end);
-	else if (is_range_ram < 0)
-		return -EINVAL;
+	/*
+	 * For legacy reasons, some parts of the physical address range in the
+	 * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+	 * the e820 tables).  So we will track the memory attributes of this
+	 * legacy 1MB region using the linear memtype_list always.
+	 */
+	if (end >= ISA_END_ADDRESS) {
+		is_range_ram = pagerange_is_ram(start, end);
+		if (is_range_ram == 1)
+			return free_ram_pages_type(start, end);
+		else if (is_range_ram < 0)
+			return -EINVAL;
+	}
 
 	spin_lock(&memtype_lock);
 	list_for_each_entry(entry, &memtype_list, nd) {