Merge remote-tracking branch 'origin/x86/mm' into x86/mm2

Explicitly merging these two branches due to nontrivial conflicts and
to allow further work.

Resolved Conflicts:
	arch/x86/kernel/head32.c
	arch/x86/kernel/head64.c
	arch/x86/mm/init_64.c
	arch/x86/realmode/init.c

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

8 files changed, 110 insertions, 228 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e2fcbc34c9df..edaa2daf4b37 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -804,12 +804,10 @@ void set_kernel_text_ro(void)
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long rodata_start =
-		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
+	unsigned long rodata_start = PFN_ALIGN(__start_rodata);
 	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
-	unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table);
-	unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata);
-	unsigned long data_start = (unsigned long) &_sdata;
+	unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
+	unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
 	unsigned long all_end = PFN_ALIGN(&_end);
 
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
@@ -835,12 +833,12 @@ void mark_rodata_ro(void)
 #endif
 
 	free_init_pages("unused kernel memory",
-			(unsigned long) page_address(virt_to_page(text_end)),
-			(unsigned long)
-				 page_address(virt_to_page(rodata_start)));
+			(unsigned long) __va(__pa_symbol(text_end)),
+			(unsigned long) __va(__pa_symbol(rodata_start)));
+
 	free_init_pages("unused kernel memory",
-			(unsigned long) page_address(virt_to_page(rodata_end)),
-			(unsigned long) page_address(virt_to_page(data_start)));
+			(unsigned long) __va(__pa_symbol(rodata_end)),
+			(unsigned long) __va(__pa_symbol(_sdata)));
 }
 
 #endif
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 2d125be1bae9..8504f3698753 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -193,7 +193,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 static void __init setup_node_data(int nid, u64 start, u64 end)
 {
 	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
-	bool remapped = false;
 	u64 nd_pa;
 	void *nd;
 	int tnid;
@@ -205,37 +204,28 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	if (end && (end - start) < NODE_MIN_SIZE)
 		return;
 
-	/* initialize remap allocator before aligning to ZONE_ALIGN */
-	init_alloc_remap(nid, start, end);
-
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
 	       nid, start, end - 1);
 
 	/*
-	 * Allocate node data.  Try remap allocator first, node-local
-	 * memory and then any node.  Never allocate in DMA zone.
+	 * Allocate node data.  Try node-local memory and then any node.
+	 * Never allocate in DMA zone.
 	 */
-	nd = alloc_remap(nid, nd_size);
-	if (nd) {
-		nd_pa = __pa(nd);
-		remapped = true;
-	} else {
-		nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
-		if (!nd_pa) {
-			pr_err("Cannot find %zu bytes in node %d\n",
-			       nd_size, nid);
-			return;
-		}
-		nd = __va(nd_pa);
+	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
+	if (!nd_pa) {
+		pr_err("Cannot find %zu bytes in node %d\n",
+		       nd_size, nid);
+		return;
 	}
+	nd = __va(nd_pa);
 
 	/* report and initialize */
-	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]%s\n",
-	       nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
+	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	       nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
-	if (!remapped && tnid != nid)
+	if (tnid != nid)
 		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nid, tnid);
 
 	node_data[nid] = nd;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 534255a36b6b..73a6d7395bd3 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -73,167 +73,6 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
 
 extern unsigned long highend_pfn, highstart_pfn;
 
-#define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
-
-static void *node_remap_start_vaddr[MAX_NUMNODES];
-void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
-
-/*
- * Remap memory allocator
- */
-static unsigned long node_remap_start_pfn[MAX_NUMNODES];
-static void *node_remap_end_vaddr[MAX_NUMNODES];
-static void *node_remap_alloc_vaddr[MAX_NUMNODES];
-
-/**
- * alloc_remap - Allocate remapped memory
- * @nid: NUMA node to allocate memory from
- * @size: The size of allocation
- *
- * Allocate @size bytes from the remap area of NUMA node @nid.  The
- * size of the remap area is predetermined by init_alloc_remap() and
- * only the callers considered there should call this function.  For
- * more info, please read the comment on top of init_alloc_remap().
- *
- * The caller must be ready to handle allocation failure from this
- * function and fall back to regular memory allocator in such cases.
- *
- * CONTEXT:
- * Single CPU early boot context.
- *
- * RETURNS:
- * Pointer to the allocated memory on success, %NULL on failure.
- */
-void *alloc_remap(int nid, unsigned long size)
-{
-	void *allocation = node_remap_alloc_vaddr[nid];
-
-	size = ALIGN(size, L1_CACHE_BYTES);
-
-	if (!allocation || (allocation + size) > node_remap_end_vaddr[nid])
-		return NULL;
-
-	node_remap_alloc_vaddr[nid] += size;
-	memset(allocation, 0, size);
-
-	return allocation;
-}
-
-#ifdef CONFIG_HIBERNATION
-/**
- * resume_map_numa_kva - add KVA mapping to the temporary page tables created
- *                       during resume from hibernation
- * @pgd_base - temporary resume page directory
- */
-void resume_map_numa_kva(pgd_t *pgd_base)
-{
-	int node;
-
-	for_each_online_node(node) {
-		unsigned long start_va, start_pfn, nr_pages, pfn;
-
-		start_va = (unsigned long)node_remap_start_vaddr[node];
-		start_pfn = node_remap_start_pfn[node];
-		nr_pages = (node_remap_end_vaddr[node] -
-			    node_remap_start_vaddr[node]) >> PAGE_SHIFT;
-
-		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
-
-		for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) {
-			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
-			pgd_t *pgd = pgd_base + pgd_index(vaddr);
-			pud_t *pud = pud_offset(pgd, vaddr);
-			pmd_t *pmd = pmd_offset(pud, vaddr);
-
-			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
-						PAGE_KERNEL_LARGE_EXEC));
-
-			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
-				__func__, vaddr, start_pfn + pfn);
-		}
-	}
-}
-#endif
-
-/**
- * init_alloc_remap - Initialize remap allocator for a NUMA node
- * @nid: NUMA node to initizlie remap allocator for
- *
- * NUMA nodes may end up without any lowmem.  As allocating pgdat and
- * memmap on a different node with lowmem is inefficient, a special
- * remap allocator is implemented which can be used by alloc_remap().
- *
- * For each node, the amount of memory which will be necessary for
- * pgdat and memmap is calculated and two memory areas of the size are
- * allocated - one in the node and the other in lowmem; then, the area
- * in the node is remapped to the lowmem area.
- *
- * As pgdat and memmap must be allocated in lowmem anyway, this
- * doesn't waste lowmem address space; however, the actual lowmem
- * which gets remapped over is wasted.  The amount shouldn't be
- * problematic on machines this feature will be used.
- *
- * Initialization failure isn't fatal.  alloc_remap() is used
- * opportunistically and the callers will fall back to other memory
- * allocation mechanisms on failure.
- */
-void __init init_alloc_remap(int nid, u64 start, u64 end)
-{
-	unsigned long start_pfn = start >> PAGE_SHIFT;
-	unsigned long end_pfn = end >> PAGE_SHIFT;
-	unsigned long size, pfn;
-	u64 node_pa, remap_pa;
-	void *remap_va;
-
-	/*
-	 * The acpi/srat node info can show hot-add memroy zones where
-	 * memory could be added but not currently present.
-	 */
-	printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n",
-	       nid, start_pfn, end_pfn);
-
-	/* calculate the necessary space aligned to large page size */
-	size = node_memmap_size_bytes(nid, start_pfn, end_pfn);
-	size += ALIGN(sizeof(pg_data_t), PAGE_SIZE);
-	size = ALIGN(size, LARGE_PAGE_BYTES);
-
-	/* allocate node memory and the lowmem remap area */
-	node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES);
-	if (!node_pa) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n",
-			   size, nid);
-		return;
-	}
-	memblock_reserve(node_pa, size);
-
-	remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT,
-					  max_low_pfn << PAGE_SHIFT,
-					  size, LARGE_PAGE_BYTES);
-	if (!remap_pa) {
-		pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n",
-			   size, nid);
-		memblock_free(node_pa, size);
-		return;
-	}
-	memblock_reserve(remap_pa, size);
-	remap_va = phys_to_virt(remap_pa);
-
-	/* perform actual remap */
-	for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE)
-		set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT),
-			    (node_pa >> PAGE_SHIFT) + pfn,
-			    PAGE_KERNEL_LARGE);
-
-	/* initialize remap allocator parameters */
-	node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT;
-	node_remap_start_vaddr[nid] = remap_va;
-	node_remap_end_vaddr[nid] = remap_va + size;
-	node_remap_alloc_vaddr[nid] = remap_va;
-
-	printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n",
-	       nid, node_pa, node_pa + size, remap_va, remap_va + size);
-}
-
 void __init initmem_init(void)
 {
 	x86_numa_init();
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index 7178c3afe05e..ad86ec91e640 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -21,12 +21,6 @@ void __init numa_reset_distance(void);
 
 void __init x86_numa_init(void);
 
-#ifdef CONFIG_X86_64
-static inline void init_alloc_remap(int nid, u64 start, u64 end)	{ }
-#else
-void __init init_alloc_remap(int nid, u64 start, u64 end);
-#endif
-
 #ifdef CONFIG_NUMA_EMU
 void __init numa_emulation(struct numa_meminfo *numa_meminfo,
 			   int numa_dist_cnt);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 44acfcd6c16f..a1b1c88f9caf 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -94,12 +94,12 @@ static inline void split_page_count(int level) { }
 
 static inline unsigned long highmap_start_pfn(void)
 {
-	return __pa(_text) >> PAGE_SHIFT;
+	return __pa_symbol(_text) >> PAGE_SHIFT;
 }
 
 static inline unsigned long highmap_end_pfn(void)
 {
-	return __pa(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
+	return __pa_symbol(roundup(_brk_end, PMD_SIZE)) >> PAGE_SHIFT;
 }
 
 #endif
@@ -276,8 +276,8 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	 * The .rodata section needs to be read-only. Using the pfn
 	 * catches all aliases.
 	 */
-	if (within(pfn, __pa((unsigned long)__start_rodata) >> PAGE_SHIFT,
-		   __pa((unsigned long)__end_rodata) >> PAGE_SHIFT))
+	if (within(pfn, __pa_symbol(__start_rodata) >> PAGE_SHIFT,
+		   __pa_symbol(__end_rodata) >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_RW;
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
@@ -364,6 +364,37 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 EXPORT_SYMBOL_GPL(lookup_address);
 
 /*
+ * This is necessary because __pa() does not work on some
+ * kinds of memory, like vmalloc() or the alloc_remap()
+ * areas on 32-bit NUMA systems.  The percpu areas can
+ * end up in this kind of memory, for instance.
+ *
+ * This could be optimized, but it is only intended to be
+ * used at inititalization time, and keeping it
+ * unoptimized should increase the testing coverage for
+ * the more obscure platforms.
+ */
+phys_addr_t slow_virt_to_phys(void *__virt_addr)
+{
+	unsigned long virt_addr = (unsigned long)__virt_addr;
+	phys_addr_t phys_addr;
+	unsigned long offset;
+	enum pg_level level;
+	unsigned long psize;
+	unsigned long pmask;
+	pte_t *pte;
+
+	pte = lookup_address(virt_addr, &level);
+	BUG_ON(!pte);
+	psize = page_level_size(level);
+	pmask = page_level_mask(level);
+	offset = virt_addr & ~pmask;
+	phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+	return (phys_addr | offset);
+}
+EXPORT_SYMBOL_GPL(slow_virt_to_phys);
+
+/*
  * Set the new pmd in all the pgds we know about:
  */
 static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
@@ -396,7 +427,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	pte_t new_pte, old_pte, *tmp;
 	pgprot_t old_prot, new_prot, req_prot;
 	int i, do_split = 1;
-	unsigned int level;
+	enum pg_level level;
 
 	if (cpa->force_split)
 		return 1;
@@ -412,15 +443,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 
 	switch (level) {
 	case PG_LEVEL_2M:
-		psize = PMD_PAGE_SIZE;
-		pmask = PMD_PAGE_MASK;
-		break;
 #ifdef CONFIG_X86_64
 	case PG_LEVEL_1G:
-		psize = PUD_PAGE_SIZE;
-		pmask = PUD_PAGE_MASK;
-		break;
 #endif
+		psize = page_level_size(level);
+		pmask = page_level_mask(level);
+		break;
 	default:
 		do_split = -EINVAL;
 		goto out_unlock;
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 0eb572eda406..2610bd93c896 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -560,10 +560,10 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 {
 	unsigned long id_sz;
 
-	if (base >= __pa(high_memory))
+	if (base > __pa(high_memory-1))
 		return 0;
 
-	id_sz = (__pa(high_memory) < base + size) ?
+	id_sz = (__pa(high_memory-1) <= base + size) ?
 				__pa(high_memory) - base :
 				size;
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index e27fbf887f3b..193350b51f90 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -334,7 +334,12 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
 	if (changed && dirty) {
 		*pmdp = entry;
 		pmd_update_defer(vma->vm_mm, address, pmdp);
-		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+		/*
+		 * We had a write-protection fault here and changed the pmd
+		 * to to more permissive. No need to flush the TLB for that,
+		 * #PF is architecturally guaranteed to do that and in the
+		 * worst-case we'll generate a spurious fault.
+		 */
 	}
 
 	return changed;
diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c
index d2e2735327b4..e666cbbb9261 100644
--- a/arch/x86/mm/physaddr.c
+++ b/arch/x86/mm/physaddr.c
@@ -1,3 +1,4 @@
+#include <linux/bootmem.h>
 #include <linux/mmdebug.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -8,33 +9,54 @@
 
 #ifdef CONFIG_X86_64
 
+#ifdef CONFIG_DEBUG_VIRTUAL
 unsigned long __phys_addr(unsigned long x)
 {
-	if (x >= __START_KERNEL_map) {
-		x -= __START_KERNEL_map;
-		VIRTUAL_BUG_ON(x >= KERNEL_IMAGE_SIZE);
-		x += phys_base;
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* use the carry flag to determine if x was < __START_KERNEL_map */
+	if (unlikely(x > y)) {
+		x = y + phys_base;
+
+		VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE);
 	} else {
-		VIRTUAL_BUG_ON(x < PAGE_OFFSET);
-		x -= PAGE_OFFSET;
-		VIRTUAL_BUG_ON(!phys_addr_valid(x));
+		x = y + (__START_KERNEL_map - PAGE_OFFSET);
+
+		/* carry flag will be set if starting x was >= PAGE_OFFSET */
+		VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x));
 	}
+
 	return x;
 }
 EXPORT_SYMBOL(__phys_addr);
 
+unsigned long __phys_addr_symbol(unsigned long x)
+{
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* only check upper bounds since lower bounds will trigger carry */
+	VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE);
+
+	return y + phys_base;
+}
+EXPORT_SYMBOL(__phys_addr_symbol);
+#endif
+
 bool __virt_addr_valid(unsigned long x)
 {
-	if (x >= __START_KERNEL_map) {
-		x -= __START_KERNEL_map;
-		if (x >= KERNEL_IMAGE_SIZE)
+	unsigned long y = x - __START_KERNEL_map;
+
+	/* use the carry flag to determine if x was < __START_KERNEL_map */
+	if (unlikely(x > y)) {
+		x = y + phys_base;
+
+		if (y >= KERNEL_IMAGE_SIZE)
 			return false;
-		x += phys_base;
 	} else {
-		if (x < PAGE_OFFSET)
-			return false;
-		x -= PAGE_OFFSET;
-		if (!phys_addr_valid(x))
+		x = y + (__START_KERNEL_map - PAGE_OFFSET);
+
+		/* carry flag will be set if starting x was >= PAGE_OFFSET */
+		if ((x > y) || !phys_addr_valid(x))
 			return false;
 	}
 
@@ -47,10 +69,16 @@ EXPORT_SYMBOL(__virt_addr_valid);
 #ifdef CONFIG_DEBUG_VIRTUAL
 unsigned long __phys_addr(unsigned long x)
 {
+	unsigned long phys_addr = x - PAGE_OFFSET;
 	/* VMALLOC_* aren't constants  */
 	VIRTUAL_BUG_ON(x < PAGE_OFFSET);
 	VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x));
-	return x - PAGE_OFFSET;
+	/* max_low_pfn is set early, but not _that_ early */
+	if (max_low_pfn) {
+		VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn);
+		BUG_ON(slow_virt_to_phys((void *)x) != phys_addr);
+	}
+	return phys_addr;
 }
 EXPORT_SYMBOL(__phys_addr);
 #endif