12 files changed, 75 insertions, 14 deletions

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f46c340..069ce7c 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
-#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
 #include <asm/mman.h>
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e71c5cb..b278535 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/gfp.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
@@ -331,11 +332,23 @@ int devmem_is_allowed(unsigned long pagenr)
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)
 {
-	unsigned long addr = begin;
+	unsigned long addr;
+	unsigned long begin_aligned, end_aligned;
 
-	if (addr >= end)
+	/* Make sure boundaries are page aligned */
+	begin_aligned = PAGE_ALIGN(begin);
+	end_aligned   = end & PAGE_MASK;
+
+	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
+		begin = begin_aligned;
+		end   = end_aligned;
+	}
+
+	if (begin >= end)
 		return;
 
+	addr = begin;
+
 	/*
 	 * If debugging page accesses then do not free this memory but
 	 * mark them not present - any buggy init-section access will
@@ -343,7 +356,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	 */
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
+		begin, end);
 	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
 	/*
@@ -358,8 +371,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	for (; addr < end; addr += PAGE_SIZE) {
 		ClearPageReserved(virt_to_page(addr));
 		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
+		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
 		free_page(addr);
 		totalram_pages++;
 	}
@@ -376,6 +388,15 @@ void free_initmem(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	/*
+	 * end could be not aligned, and We can not align that,
+	 * decompresser could be confused by aligned initrd_end
+	 * We already reserve the end partial page before in
+	 *   - i386_start_kernel()
+	 *   - x86_64_start_kernel()
+	 *   - relocate_initrd()
+	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
+	 */
+	free_init_pages("initrd memory", start, PAGE_ALIGN(end));
 }
 #endif
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5cb3f0f..bca7909 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,11 +25,11 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
-#include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
+#include <linux/gfp.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e9b040e..ee41bba 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
 #include <linux/nmi.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 5eb1ba7..12e4d2d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -448,6 +448,20 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
 static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 
+void __init fixup_early_ioremap(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i]) {
+			WARN_ON(1);
+			break;
+		}
+	}
+
+	early_ioremap_init();
+}
+
 static int __init check_early_ioremap_leak(void)
 {
 	int count = 0;
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 536fb68..5d0e67f 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -21,6 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/mutex.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <linux/errno.h>
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 34a3291..3adff7d 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -26,6 +26,7 @@
 
 #include <linux/module.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/version.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1d4eb93..28195c3 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -6,13 +6,13 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/pfn.h>
 #include <linux/percpu.h>
+#include <linux/gfp.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
@@ -291,8 +291,29 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	 */
 	if (kernel_set_to_readonly &&
 	    within(address, (unsigned long)_text,
-		   (unsigned long)__end_rodata_hpage_align))
-		pgprot_val(forbidden) |= _PAGE_RW;
+		   (unsigned long)__end_rodata_hpage_align)) {
+		unsigned int level;
+
+		/*
+		 * Don't enforce the !RW mapping for the kernel text mapping,
+		 * if the current mapping is already using small page mapping.
+		 * No need to work hard to preserve large page mappings in this
+		 * case.
+		 *
+		 * This also fixes the Linux Xen paravirt guest boot failure
+		 * (because of unexpected read-only mappings for kernel identity
+		 * mappings). In this paravirt guest case, the kernel text
+		 * mapping and the kernel identity mapping share the same
+		 * page-table pages. Thus we can't really use different
+		 * protections for the kernel text and identity mappings. Also,
+		 * these shared mappings are made of small page mappings.
+		 * Thus this don't enforce !RW mapping for small page kernel
+		 * text mapping logic will help Linux Xen parvirt guest boot
+		 * aswell.
+		 */
+		if (lookup_address(address, &level) && (level != PG_LEVEL_4K))
+			pgprot_val(forbidden) |= _PAGE_RW;
+	}
 #endif
 
 	prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden));
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ae9648e..edc8b95 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -12,7 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index c9ba9de..5c4ee42 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/gfp.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 46c8834..7928540 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -6,7 +6,6 @@
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
@@ -19,6 +18,7 @@
 #include <asm/e820.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -129,6 +129,7 @@ static int __init parse_reservetop(char *arg)
 
 	address = memparse(arg, &arg);
 	reserve_top_address(address);
+	fixup_early_ioremap();
 	return 0;
 }
 early_param("reservetop", parse_reservetop);
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 28c6876..38512d0 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -461,7 +461,8 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 		 * node, it must now point to the fake node ID.
 		 */
 		for (j = 0; j < MAX_LOCAL_APIC; j++)
-			if (apicid_to_node[j] == nid)
+			if (apicid_to_node[j] == nid &&
+			    fake_apicid_to_node[j] == NUMA_NO_NODE)
 				fake_apicid_to_node[j] = i;
 	}
 	for (i = 0; i < num_nodes; i++)