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

Pull x86 mm changes from Peter Anvin:
 "This is a huge set of several partly interrelated (and concurrently
  developed) changes, which is why the branch history is messier than
  one would like.

  The *really* big items are two humonguous patchsets mostly developed
  by Yinghai Lu at my request, which completely revamps the way we
  create initial page tables.  In particular, rather than estimating how
  much memory we will need for page tables and then build them into that
  memory -- a calculation that has shown to be incredibly fragile -- we
  now build them (on 64 bits) with the aid of a "pseudo-linear mode" --
  a #PF handler which creates temporary page tables on demand.

  This has several advantages:

  1. It makes it much easier to support things that need access to data
     very early (a followon patchset uses this to load microcode way
     early in the kernel startup).

  2. It allows the kernel and all the kernel data objects to be invoked
     from above the 4 GB limit.  This allows kdump to work on very large
     systems.

  3. It greatly reduces the difference between Xen and native (Xen's
     equivalent of the #PF handler are the temporary page tables created
     by the domain builder), eliminating a bunch of fragile hooks.

  The patch series also gets us a bit closer to W^X.

  Additional work in this pull is the 64-bit get_user() work which you
  were also involved with, and a bunch of cleanups/speedups to
  __phys_addr()/__pa()."

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (105 commits)
  x86, mm: Move reserving low memory later in initialization
  x86, doc: Clarify the use of asm("%edx") in uaccess.h
  x86, mm: Redesign get_user with a __builtin_choose_expr hack
  x86: Be consistent with data size in getuser.S
  x86, mm: Use a bitfield to mask nuisance get_user() warnings
  x86/kvm: Fix compile warning in kvm_register_steal_time()
  x86-32: Add support for 64bit get_user()
  x86-32, mm: Remove reference to alloc_remap()
  x86-32, mm: Remove reference to resume_map_numa_kva()
  x86-32, mm: Rip out x86_32 NUMA remapping code
  x86/numa: Use __pa_nodebug() instead
  x86: Don't panic if can not alloc buffer for swiotlb
  mm: Add alloc_bootmem_low_pages_nopanic()
  x86, 64bit, mm: hibernate use generic mapping_init
  x86, 64bit, mm: Mark data/bss/brk to nx
  x86: Merge early kernel reserve for 32bit and 64bit
  x86: Add Crash kernel low reservation
  x86, kdump: Remove crashkernel range find limit for 64bit
  memblock: Add memblock_mem_size()
  x86, boot: Not need to check setup_header version for setup_data
  ...

1 files changed, 158 insertions, 102 deletions

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 8b24289cc10c..915f5efefcf5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -108,17 +108,16 @@
 #include <asm/topology.h>
 #include <asm/apicdef.h>
 #include <asm/amd_nb.h>
-#ifdef CONFIG_X86_64
-#include <asm/numa_64.h>
-#endif
 #include <asm/mce.h>
 #include <asm/alternative.h>
 #include <asm/prom.h>
 
 /*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
+ * max_low_pfn_mapped: highest direct mapped pfn under 4GB
+ * max_pfn_mapped:     highest direct mapped pfn over 4GB
+ *
+ * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * represented by pfn_mapped
  */
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
@@ -276,18 +275,7 @@ void * __init extend_brk(size_t size, size_t align)
 	return ret;
 }
 
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
-	if (direct_gbpages && cpu_has_gbpages)
-		printk(KERN_INFO "Using GB pages for direct mapping\n");
-	else
-		direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
+#ifdef CONFIG_X86_32
 static void __init cleanup_highmap(void)
 {
 }
@@ -296,8 +284,8 @@ static void __init cleanup_highmap(void)
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
-		memblock_reserve(__pa(_brk_start),
-				 __pa(_brk_end) - __pa(_brk_start));
+		memblock_reserve(__pa_symbol(_brk_start),
+				 _brk_end - _brk_start);
 
 	/* Mark brk area as locked down and no longer taking any
 	   new allocations */
@@ -306,27 +294,43 @@ static void __init reserve_brk(void)
 
 #ifdef CONFIG_BLK_DEV_INITRD
 
+static u64 __init get_ramdisk_image(void)
+{
+	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
+
+	ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32;
+
+	return ramdisk_image;
+}
+static u64 __init get_ramdisk_size(void)
+{
+	u64 ramdisk_size = boot_params.hdr.ramdisk_size;
+
+	ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32;
+
+	return ramdisk_size;
+}
+
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
 	/* Assume only end is not page aligned */
-	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
-	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_image = get_ramdisk_image();
+	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
-	/* We need to move the initrd down into lowmem */
-	ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size,
-					 PAGE_SIZE);
+	/* We need to move the initrd down into directly mapped mem */
+	ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+						 area_size, PAGE_SIZE);
 
 	if (!ramdisk_here)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
 			 ramdisk_size);
 
-	/* Note: this includes all the lowmem currently occupied by
+	/* Note: this includes all the mem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
 	memblock_reserve(ramdisk_here, area_size);
 	initrd_start = ramdisk_here + PAGE_OFFSET;
@@ -336,17 +340,7 @@ static void __init relocate_initrd(void)
 
 	q = (char *)initrd_start;
 
-	/* Copy any lowmem portion of the initrd */
-	if (ramdisk_image < end_of_lowmem) {
-		clen = end_of_lowmem - ramdisk_image;
-		p = (char *)__va(ramdisk_image);
-		memcpy(q, p, clen);
-		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
-	}
-
-	/* Copy the highmem portion of the initrd */
+	/* Copy the initrd */
 	while (ramdisk_size) {
 		slop = ramdisk_image & ~PAGE_MASK;
 		clen = ramdisk_size;
@@ -360,22 +354,35 @@ static void __init relocate_initrd(void)
 		ramdisk_image += clen;
 		ramdisk_size  -= clen;
 	}
-	/* high pages is not converted by early_res_to_bootmem */
-	ramdisk_image = boot_params.hdr.ramdisk_image;
-	ramdisk_size  = boot_params.hdr.ramdisk_size;
+
+	ramdisk_image = get_ramdisk_image();
+	ramdisk_size  = get_ramdisk_size();
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
 		ramdisk_here, ramdisk_here + ramdisk_size - 1);
 }
 
+static void __init early_reserve_initrd(void)
+{
+	/* Assume only end is not page aligned */
+	u64 ramdisk_image = get_ramdisk_image();
+	u64 ramdisk_size  = get_ramdisk_size();
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
+
+	if (!boot_params.hdr.type_of_loader ||
+	    !ramdisk_image || !ramdisk_size)
+		return;		/* No initrd provided by bootloader */
+
+	memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
+}
 static void __init reserve_initrd(void)
 {
 	/* Assume only end is not page aligned */
-	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
-	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 ramdisk_image = get_ramdisk_image();
+	u64 ramdisk_size  = get_ramdisk_size();
 	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
-	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
+	u64 mapped_size;
 
 	if (!boot_params.hdr.type_of_loader ||
 	    !ramdisk_image || !ramdisk_size)
@@ -383,22 +390,18 @@ static void __init reserve_initrd(void)
 
 	initrd_start = 0;
 
-	if (ramdisk_size >= (end_of_lowmem>>1)) {
+	mapped_size = memblock_mem_size(max_pfn_mapped);
+	if (ramdisk_size >= (mapped_size>>1))
 		panic("initrd too large to handle, "
 		       "disabling initrd (%lld needed, %lld available)\n",
-		       ramdisk_size, end_of_lowmem>>1);
-	}
+		       ramdisk_size, mapped_size>>1);
 
 	printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
 			ramdisk_end - 1);
 
-
-	if (ramdisk_end <= end_of_lowmem) {
-		/* All in lowmem, easy case */
-		/*
-		 * don't need to reserve again, already reserved early
-		 * in i386_start_kernel
-		 */
+	if (pfn_range_is_mapped(PFN_DOWN(ramdisk_image),
+				PFN_DOWN(ramdisk_end))) {
+		/* All are mapped, easy case */
 		initrd_start = ramdisk_image + PAGE_OFFSET;
 		initrd_end = initrd_start + ramdisk_size;
 		return;
@@ -409,6 +412,9 @@ static void __init reserve_initrd(void)
 	memblock_free(ramdisk_image, ramdisk_end - ramdisk_image);
 }
 #else
+static void __init early_reserve_initrd(void)
+{
+}
 static void __init reserve_initrd(void)
 {
 }
@@ -419,8 +425,6 @@ static void __init parse_setup_data(void)
 	struct setup_data *data;
 	u64 pa_data;
 
-	if (boot_params.hdr.version < 0x0209)
-		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		u32 data_len, map_len;
@@ -456,8 +460,6 @@ static void __init e820_reserve_setup_data(void)
 	u64 pa_data;
 	int found = 0;
 
-	if (boot_params.hdr.version < 0x0209)
-		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
@@ -481,8 +483,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 	struct setup_data *data;
 	u64 pa_data;
 
-	if (boot_params.hdr.version < 0x0209)
-		return;
 	pa_data = boot_params.hdr.setup_data;
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
@@ -501,17 +501,51 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
- * On 64 bits, kexec-tools currently limits us to 896 MiB; increase this
- * limit once kexec-tools are fixed.
  */
 #ifdef CONFIG_X86_32
 # define CRASH_KERNEL_ADDR_MAX	(512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX	(896 << 20)
+# define CRASH_KERNEL_ADDR_MAX	MAXMEM
+#endif
+
+static void __init reserve_crashkernel_low(void)
+{
+#ifdef CONFIG_X86_64
+	const unsigned long long alignment = 16<<20;	/* 16M */
+	unsigned long long low_base = 0, low_size = 0;
+	unsigned long total_low_mem;
+	unsigned long long base;
+	int ret;
+
+	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
+						&low_size, &base);
+	if (ret != 0 || low_size <= 0)
+		return;
+
+	low_base = memblock_find_in_range(low_size, (1ULL<<32),
+					low_size, alignment);
+
+	if (!low_base) {
+		pr_info("crashkernel low reservation failed - No suitable area found.\n");
+
+		return;
+	}
+
+	memblock_reserve(low_base, low_size);
+	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
+			(unsigned long)(low_size >> 20),
+			(unsigned long)(low_base >> 20),
+			(unsigned long)(total_low_mem >> 20));
+	crashk_low_res.start = low_base;
+	crashk_low_res.end   = low_base + low_size - 1;
+	insert_resource(&iomem_resource, &crashk_low_res);
 #endif
+}
 
 static void __init reserve_crashkernel(void)
 {
+	const unsigned long long alignment = 16<<20;	/* 16M */
 	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
 	int ret;
@@ -525,8 +559,6 @@ static void __init reserve_crashkernel(void)
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
-		const unsigned long long alignment = 16<<20;	/* 16M */
-
 		/*
 		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
@@ -537,6 +569,7 @@ static void __init reserve_crashkernel(void)
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
+
 	} else {
 		unsigned long long start;
 
@@ -558,6 +591,9 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end   = crash_base + crash_size - 1;
 	insert_resource(&iomem_resource, &crashk_res);
+
+	if (crash_base >= (1ULL<<32))
+		reserve_crashkernel_low();
 }
 #else
 static void __init reserve_crashkernel(void)
@@ -608,8 +644,6 @@ static __init void reserve_ibft_region(void)
 		memblock_reserve(addr, size);
 }
 
-static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
-
 static bool __init snb_gfx_workaround_needed(void)
 {
 #ifdef CONFIG_PCI
@@ -698,8 +732,7 @@ static void __init trim_bios_range(void)
 	 * since some BIOSes are known to corrupt low memory.  See the
 	 * Kconfig help text for X86_RESERVE_LOW.
 	 */
-	e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
-			  E820_RAM, E820_RESERVED);
+	e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
 
 	/*
 	 * special case: Some BIOSen report the PC BIOS
@@ -711,6 +744,29 @@ static void __init trim_bios_range(void)
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+/* called before trim_bios_range() to spare extra sanitize */
+static void __init e820_add_kernel_range(void)
+{
+	u64 start = __pa_symbol(_text);
+	u64 size = __pa_symbol(_end) - start;
+
+	/*
+	 * Complain if .text .data and .bss are not marked as E820_RAM and
+	 * attempt to fix it by adding the range. We may have a confused BIOS,
+	 * or the user may have used memmap=exactmap or memmap=xxM$yyM to
+	 * exclude kernel range. If we really are running on top non-RAM,
+	 * we will crash later anyways.
+	 */
+	if (e820_all_mapped(start, start + size, E820_RAM))
+		return;
+
+	pr_warn(".text .data .bss are not marked as E820_RAM!\n");
+	e820_remove_range(start, size, E820_RAM, 0);
+	e820_add_region(start, size, E820_RAM);
+}
+
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
+
 static int __init parse_reservelow(char *p)
 {
 	unsigned long long size;
@@ -733,6 +789,11 @@ static int __init parse_reservelow(char *p)
 
 early_param("reservelow", parse_reservelow);
 
+static void __init trim_low_memory_range(void)
+{
+	memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
+}
+	
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -748,6 +809,17 @@ early_param("reservelow", parse_reservelow);
 
 void __init setup_arch(char **cmdline_p)
 {
+	memblock_reserve(__pa_symbol(_text),
+			 (unsigned long)__bss_stop - (unsigned long)_text);
+
+	early_reserve_initrd();
+
+	/*
+	 * At this point everything still needed from the boot loader
+	 * or BIOS or kernel text should be early reserved or marked not
+	 * RAM in e820. All other memory is free game.
+	 */
+
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
@@ -835,12 +907,12 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = _brk_end;
 
-	code_resource.start = virt_to_phys(_text);
-	code_resource.end = virt_to_phys(_etext)-1;
-	data_resource.start = virt_to_phys(_etext);
-	data_resource.end = virt_to_phys(_edata)-1;
-	bss_resource.start = virt_to_phys(&__bss_start);
-	bss_resource.end = virt_to_phys(&__bss_stop)-1;
+	code_resource.start = __pa_symbol(_text);
+	code_resource.end = __pa_symbol(_etext)-1;
+	data_resource.start = __pa_symbol(_etext);
+	data_resource.end = __pa_symbol(_edata)-1;
+	bss_resource.start = __pa_symbol(__bss_start);
+	bss_resource.end = __pa_symbol(__bss_stop)-1;
 
 #ifdef CONFIG_CMDLINE_BOOL
 #ifdef CONFIG_CMDLINE_OVERRIDE
@@ -906,6 +978,7 @@ void __init setup_arch(char **cmdline_p)
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
+	e820_add_kernel_range();
 	trim_bios_range();
 #ifdef CONFIG_X86_32
 	if (ppro_with_ram_bug()) {
@@ -955,6 +1028,8 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_ibft_region();
 
+	early_alloc_pgt_buf();
+
 	/*
 	 * Need to conclude brk, before memblock_x86_fill()
 	 *  it could use memblock_find_in_range, could overlap with
@@ -964,7 +1039,7 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
-	memblock.current_limit = get_max_mapped();
+	memblock.current_limit = ISA_END_ADDRESS;
 	memblock_x86_fill();
 
 	/*
@@ -981,41 +1056,22 @@ void __init setup_arch(char **cmdline_p)
 	setup_bios_corruption_check();
 #endif
 
+#ifdef CONFIG_X86_32
 	printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
 			(max_pfn_mapped<<PAGE_SHIFT) - 1);
+#endif
 
-	setup_real_mode();
+	reserve_real_mode();
 
 	trim_platform_memory_ranges();
+	trim_low_memory_range();
 
-	init_gbpages();
-
-	/* max_pfn_mapped is updated here */
-	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
-	max_pfn_mapped = max_low_pfn_mapped;
-
-#ifdef CONFIG_X86_64
-	if (max_pfn > max_low_pfn) {
-		int i;
-		unsigned long start, end;
-		unsigned long start_pfn, end_pfn;
-
-		for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn,
-							 NULL) {
+	init_mem_mapping();
 
-			end = PFN_PHYS(end_pfn);
-			if (end <= (1UL<<32))
-				continue;
+	early_trap_pf_init();
 
-			start = PFN_PHYS(start_pfn);
-			max_pfn_mapped = init_memory_mapping(
-						max((1UL<<32), start), end);
-		}
+	setup_real_mode();
 
-		/* can we preseve max_low_pfn ?*/
-		max_low_pfn = max_pfn;
-	}
-#endif
 	memblock.current_limit = get_max_mapped();
 	dma_contiguous_reserve(0);