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

Pull x86 boot updates from Ingo Molnar:
 "The main changes:

   - add initial commits to randomize kernel memory section virtual
     addresses, enabled via a new kernel option: RANDOMIZE_MEMORY
     (Thomas Garnier, Kees Cook, Baoquan He, Yinghai Lu)

   - enhance KASLR (RANDOMIZE_BASE) physical memory randomization (Kees
     Cook)

   - EBDA/BIOS region boot quirk cleanups (Andy Lutomirski, Ingo Molnar)

   - misc cleanups/fixes"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot: Simplify EBDA-vs-BIOS reservation logic
  x86/boot: Clarify what x86_legacy_features.reserve_bios_regions does
  x86/boot: Reorganize and clean up the BIOS area reservation code
  x86/mm: Do not reference phys addr beyond kernel
  x86/mm: Add memory hotplug support for KASLR memory randomization
  x86/mm: Enable KASLR for vmalloc memory regions
  x86/mm: Enable KASLR for physical mapping memory regions
  x86/mm: Implement ASLR for kernel memory regions
  x86/mm: Separate variable for trampoline PGD
  x86/mm: Add PUD VA support for physical mapping
  x86/mm: Update physical mapping variable names
  x86/mm: Refactor KASLR entropy functions
  x86/KASLR: Fix boot crash with certain memory configurations
  x86/boot/64: Add forgotten end of function marker
  x86/KASLR: Allow randomization below the load address
  x86/KASLR: Extend kernel image physical address randomization to addresses larger than 4G
  x86/KASLR: Randomize virtual address separately
  x86/KASLR: Clarify identity map interface
  x86/boot: Refuse to build with data relocations
  x86/KASLR, x86/power: Remove x86 hibernation restrictions

6 files changed, 79 insertions, 49 deletions

diff --git a/arch/x86/kernel/ebda.c b/arch/x86/kernel/ebda.c
index afe65dffee80..4312f8ae71b7 100644
--- a/arch/x86/kernel/ebda.c
+++ b/arch/x86/kernel/ebda.c
@@ -6,66 +6,92 @@
 #include <asm/bios_ebda.h>
 
 /*
+ * This function reserves all conventional PC system BIOS related
+ * firmware memory areas (some of which are data, some of which
+ * are code), that must not be used by the kernel as available
+ * RAM.
+ *
  * The BIOS places the EBDA/XBDA at the top of conventional
  * memory, and usually decreases the reported amount of
- * conventional memory (int 0x12) too. This also contains a
- * workaround for Dell systems that neglect to reserve EBDA.
- * The same workaround also avoids a problem with the AMD768MPX
- * chipset: reserve a page before VGA to prevent PCI prefetch
- * into it (errata #56). Usually the page is reserved anyways,
- * unless you have no PS/2 mouse plugged in.
+ * conventional memory (int 0x12) too.
+ *
+ * This means that as a first approximation on most systems we can
+ * guess the reserved BIOS area by looking at the low BIOS RAM size
+ * value and assume that everything above that value (up to 1MB) is
+ * reserved.
+ *
+ * But life in firmware country is not that simple:
+ *
+ * - This code also contains a quirk for Dell systems that neglect
+ *   to reserve the EBDA area in the 'RAM size' value ...
+ *
+ * - The same quirk also avoids a problem with the AMD768MPX
+ *   chipset: reserve a page before VGA to prevent PCI prefetch
+ *   into it (errata #56). (Usually the page is reserved anyways,
+ *   unless you have no PS/2 mouse plugged in.)
+ *
+ * - Plus paravirt systems don't have a reliable value in the
+ *   'BIOS RAM size' pointer we can rely on, so we must quirk
+ *   them too.
+ *
+ * Due to those various problems this function is deliberately
+ * very conservative and tries to err on the side of reserving
+ * too much, to not risk reserving too little.
+ *
+ * Losing a small amount of memory in the bottom megabyte is
+ * rarely a problem, as long as we have enough memory to install
+ * the SMP bootup trampoline which *must* be in this area.
  *
- * This functions is deliberately very conservative.  Losing
- * memory in the bottom megabyte is rarely a problem, as long
- * as we have enough memory to install the trampoline.  Using
- * memory that is in use by the BIOS or by some DMA device
- * the BIOS didn't shut down *is* a big problem.
+ * Using memory that is in use by the BIOS or by some DMA device
+ * the BIOS didn't shut down *is* a big problem to the kernel,
+ * obviously.
  */
 
-#define BIOS_LOWMEM_KILOBYTES   0x413
-#define LOWMEM_CAP              0x9f000U        /* Absolute maximum */
-#define INSANE_CUTOFF           0x20000U        /* Less than this = insane */
+#define BIOS_RAM_SIZE_KB_PTR    0x413
 
-void __init reserve_ebda_region(void)
+#define BIOS_START_MIN          0x20000U        /* 128K, less than this is insane */
+#define BIOS_START_MAX          0x9f000U        /* 640K, absolute maximum */
+
+void __init reserve_bios_regions(void)
 {
-        unsigned int lowmem, ebda_addr;
+        unsigned int bios_start, ebda_start;
 
         /*
-         * To determine the position of the EBDA and the
-         * end of conventional memory, we need to look at
-         * the BIOS data area. In a paravirtual environment
-         * that area is absent. We'll just have to assume
-         * that the paravirt case can handle memory setup
-         * correctly, without our help.
+         * NOTE: In a paravirtual environment the BIOS reserved
+         * area is absent. We'll just have to assume that the
+         * paravirt case can handle memory setup correctly,
+         * without our help.
          */
-        if (!x86_platform.legacy.ebda_search)
+        if (!x86_platform.legacy.reserve_bios_regions)
                 return;
 
-        /* end of low (conventional) memory */
-        lowmem = *(unsigned short *)__va(BIOS_LOWMEM_KILOBYTES);
-        lowmem <<= 10;
-
-        /* start of EBDA area */
-        ebda_addr = get_bios_ebda();
-
         /*
-         * Note: some old Dells seem to need 4k EBDA without
-         * reporting so, so just consider the memory above 0x9f000
-         * to be off limits (bugzilla 2990).
+         * BIOS RAM size is encoded in kilobytes, convert it
+         * to bytes to get a first guess at where the BIOS
+         * firmware area starts:
          */
+        bios_start = *(unsigned short *)__va(BIOS_RAM_SIZE_KB_PTR);
+        bios_start <<= 10;
 
-        /* If the EBDA address is below 128K, assume it is bogus */
-        if (ebda_addr < INSANE_CUTOFF)
-                ebda_addr = LOWMEM_CAP;
+        /*
+         * If bios_start is less than 128K, assume it is bogus
+         * and bump it up to 640K.  Similarly, if bios_start is above 640K,
+         * don't trust it.
+         */
+        if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX)
+                bios_start = BIOS_START_MAX;
 
-        /* If lowmem is less than 128K, assume it is bogus */
-        if (lowmem < INSANE_CUTOFF)
-                lowmem = LOWMEM_CAP;
+        /* Get the start address of the EBDA page: */
+        ebda_start = get_bios_ebda();
 
-        /* Use the lower of the lowmem and EBDA markers as the cutoff */
-        lowmem = min(lowmem, ebda_addr);
-        lowmem = min(lowmem, LOWMEM_CAP); /* Absolute cap */
+        /*
+         * If the EBDA start address is sane and is below the BIOS region,
+         * then also reserve everything from the EBDA start address up to
+         * the BIOS region.
+         */
+        if (ebda_start >= BIOS_START_MIN && ebda_start < bios_start)
+                bios_start = ebda_start;
 
-        /* reserve all memory between lowmem and the 1MB mark */
-        memblock_reserve(lowmem, 0x100000 - lowmem);
+        /* Reserve all memory between bios_start and the 1MB mark: */
+        memblock_reserve(bios_start, 0x100000 - bios_start);
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index d784bb547a9d..2dda0bc4576e 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -26,7 +26,7 @@ static void __init i386_default_early_setup(void)
         x86_init.resources.reserve_resources = i386_reserve_resources;
         x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
 
-        reserve_ebda_region();
+        reserve_bios_regions();
 }
 
 asmlinkage __visible void __init i386_start_kernel(void)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b72fb0b71dd1..99d48e7d2974 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -183,7 +183,7 @@ void __init x86_64_start_reservations(char *real_mode_data)
                 copy_bootdata(__va(real_mode_data));
 
         x86_early_init_platform_quirks();
-        reserve_ebda_region();
+        reserve_bios_regions();
 
         switch (boot_params.hdr.hardware_subarch) {
         case X86_SUBARCH_INTEL_MID:
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 5df831ef1442..9f8efc9f0075 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -38,7 +38,7 @@
 
 #define pud_index(x)    (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
 
-L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET)
+L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE)
 L4_START_KERNEL = pgd_index(__START_KERNEL_map)
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
@@ -299,6 +299,7 @@ ENTRY(secondary_startup_64)
         pushq   $__KERNEL_CS    # set correct cs
         pushq   %rax            # target address in negative space
         lretq
+ENDPROC(secondary_startup_64)
 
 #include "verify_cpu.S"
 
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index b2f8a33b36ff..24a50301f150 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -7,12 +7,12 @@
 void __init x86_early_init_platform_quirks(void)
 {
         x86_platform.legacy.rtc = 1;
-        x86_platform.legacy.ebda_search = 0;
+        x86_platform.legacy.reserve_bios_regions = 0;
         x86_platform.legacy.devices.pnpbios = 1;
 
         switch (boot_params.hdr.hardware_subarch) {
         case X86_SUBARCH_PC:
-                x86_platform.legacy.ebda_search = 1;
+                x86_platform.legacy.reserve_bios_regions = 1;
                 break;
         case X86_SUBARCH_XEN:
         case X86_SUBARCH_LGUEST:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c4e7b3991b60..a2616584b6e9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -113,6 +113,7 @@
 #include <asm/prom.h>
 #include <asm/microcode.h>
 #include <asm/mmu_context.h>
+#include <asm/kaslr.h>
 
 /*
  * max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -942,6 +943,8 @@ void __init setup_arch(char **cmdline_p)
 
         x86_init.oem.arch_setup();
 
+        kernel_randomize_memory();
+
         iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
         setup_memory_map();
         parse_setup_data();