6 files changed, 69 insertions, 52 deletions

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index cb4ef3de61f9..a4bb1c7ab65e 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -388,7 +388,6 @@ repeat:
 }
 
 pte_t *kmap_pte;
-pgprot_t kmap_prot;
 
 static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
 {
@@ -405,8 +404,6 @@ static void __init kmap_init(void)
 	 */
 	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
 	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
-
-	kmap_prot = PAGE_KERNEL;
 }
 
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5488d21123bd..9686535edfb5 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -53,6 +53,7 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 #include <asm/init.h>
+#include <asm/uv/uv.h>
 #include <asm/setup.h>
 
 #include "mm_internal.h"
@@ -1206,26 +1207,13 @@ int kern_addr_valid(unsigned long addr)
 
 static unsigned long probe_memory_block_size(void)
 {
-	/* start from 2g */
-	unsigned long bz = 1UL<<31;
+	unsigned long bz = MIN_MEMORY_BLOCK_SIZE;
 
-	if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) {
-		pr_info("Using 2GB memory block size for large-memory system\n");
-		return 2UL * 1024 * 1024 * 1024;
-	}
-
-	/* less than 64g installed */
-	if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
-		return MIN_MEMORY_BLOCK_SIZE;
-
-	/* get the tail size */
-	while (bz > MIN_MEMORY_BLOCK_SIZE) {
-		if (!((max_pfn << PAGE_SHIFT) & (bz - 1)))
-			break;
-		bz >>= 1;
-	}
+	/* if system is UV or has 64GB of RAM or more, use large blocks */
+	if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30)))
+		bz = 2UL << 30; /* 2GB */
 
-	printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20);
+	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
 
 	return bz;
 }
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index d470cf219a2d..1b1110fa0057 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -120,11 +120,22 @@ void __init kasan_init(void)
 	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
 			(void *)KASAN_SHADOW_END);
 
-	memset(kasan_zero_page, 0, PAGE_SIZE);
-
 	load_cr3(init_level4_pgt);
 	__flush_tlb_all();
-	init_task.kasan_depth = 0;
 
+	/*
+	 * kasan_zero_page has been used as early shadow memory, thus it may
+	 * contain some garbage. Now we can clear and write protect it, since
+	 * after the TLB flush no one should write to it.
+	 */
+	memset(kasan_zero_page, 0, PAGE_SIZE);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte_t pte = __pte(__pa(kasan_zero_page) | __PAGE_KERNEL_RO);
+		set_pte(&kasan_zero_pte[i], pte);
+	}
+	/* Flush TLBs again to be sure that write protection applied. */
+	__flush_tlb_all();
+
+	init_task.kasan_depth = 0;
 	pr_info("KernelAddressSanitizer initialized\n");
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index d04f8094bc23..f70c1ff46125 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -465,46 +465,67 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 	return true;
 }
 
+/*
+ * Mark all currently memblock-reserved physical memory (which covers the
+ * kernel's own memory ranges) as hot-unswappable.
+ */
 static void __init numa_clear_kernel_node_hotplug(void)
 {
-	int i, nid;
-	nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
-	phys_addr_t start, end;
-	struct memblock_region *r;
+	nodemask_t reserved_nodemask = NODE_MASK_NONE;
+	struct memblock_region *mb_region;
+	int i;
 
 	/*
+	 * We have to do some preprocessing of memblock regions, to
+	 * make them suitable for reservation.
+	 *
 	 * At this time, all memory regions reserved by memblock are
-	 * used by the kernel. Set the nid in memblock.reserved will
-	 * mark out all the nodes the kernel resides in.
+	 * used by the kernel, but those regions are not split up
+	 * along node boundaries yet, and don't necessarily have their
+	 * node ID set yet either.
+	 *
+	 * So iterate over all memory known to the x86 architecture,
+	 * and use those ranges to set the nid in memblock.reserved.
+	 * This will split up the memblock regions along node
+	 * boundaries and will set the node IDs as well.
 	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		struct numa_memblk *mb = &numa_meminfo.blk[i];
+		struct numa_memblk *mb = numa_meminfo.blk + i;
+		int ret;
 
-		memblock_set_node(mb->start, mb->end - mb->start,
-				  &memblock.reserved, mb->nid);
+		ret = memblock_set_node(mb->start, mb->end - mb->start, &memblock.reserved, mb->nid);
+		WARN_ON_ONCE(ret);
 	}
 
 	/*
-	 * Mark all kernel nodes.
+	 * Now go over all reserved memblock regions, to construct a
+	 * node mask of all kernel reserved memory areas.
 	 *
-	 * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo
-	 * may not include all the memblock.reserved memory ranges because
-	 * trim_snb_memory() reserves specific pages for Sandy Bridge graphics.
+	 * [ Note, when booting with mem=nn[kMG] or in a kdump kernel,
+	 *   numa_meminfo might not include all memblock.reserved
+	 *   memory ranges, because quirks such as trim_snb_memory()
+	 *   reserve specific pages for Sandy Bridge graphics. ]
 	 */
-	for_each_memblock(reserved, r)
-		if (r->nid != MAX_NUMNODES)
-			node_set(r->nid, numa_kernel_nodes);
+	for_each_memblock(reserved, mb_region) {
+		if (mb_region->nid != MAX_NUMNODES)
+			node_set(mb_region->nid, reserved_nodemask);
+	}
 
-	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	/*
+	 * Finally, clear the MEMBLOCK_HOTPLUG flag for all memory
+	 * belonging to the reserved node mask.
+	 *
+	 * Note that this will include memory regions that reside
+	 * on nodes that contain kernel memory - entire nodes
+	 * become hot-unpluggable:
+	 */
 	for (i = 0; i < numa_meminfo.nr_blks; i++) {
-		nid = numa_meminfo.blk[i].nid;
-		if (!node_isset(nid, numa_kernel_nodes))
-			continue;
+		struct numa_memblk *mb = numa_meminfo.blk + i;
 
-		start = numa_meminfo.blk[i].start;
-		end = numa_meminfo.blk[i].end;
+		if (!node_isset(mb->nid, reserved_nodemask))
+			continue;
 
-		memblock_clear_hotplug(start, end - start);
+		memblock_clear_hotplug(mb->start, mb->end - mb->start);
 	}
 }
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index f4ae536b0914..04e2e7144bee 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -943,7 +943,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			return -EINVAL;
 	}
 
-	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
 	return 0;
@@ -959,7 +959,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 
 	/* Set prot based on lookup */
 	pcm = lookup_memtype(pfn_t_to_phys(pfn));
-	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
 			 cachemode2protval(pcm));
 
 	return 0;
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index 92e2eacb3321..8bea84724a7d 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -4,6 +4,7 @@
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
+#include <asm/cpufeature.h>
 
 static int disable_nx;
 
@@ -31,9 +32,8 @@ early_param("noexec", noexec_setup);
 
 void x86_configure_nx(void)
 {
-	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
-		__supported_pte_mask |= _PAGE_NX;
-	else
+	/* If disable_nx is set, clear NX on all new mappings going forward. */
+	if (disable_nx)
 		__supported_pte_mask &= ~_PAGE_NX;
 }