Merge branch 'master' of ssh://master.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into perf/urgent

8 files changed, 215 insertions, 10 deletions

diff --git a/arch/arm/configs/at91x40_defconfig b/arch/arm/configs/at91x40_defconfig
new file mode 100644
index 000000000000..c55e9212fcbb
--- /dev/null
+++ b/arch/arm/configs/at91x40_defconfig
@@ -0,0 +1,48 @@
+CONFIG_EXPERIMENTAL=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_EMBEDDED=y
+# CONFIG_HOTPLUG is not set
+# CONFIG_ELF_CORE is not set
+# CONFIG_FUTEX is not set
+# CONFIG_TIMERFD is not set
+# CONFIG_VM_EVENT_COUNTERS is not set
+# CONFIG_COMPAT_BRK is not set
+CONFIG_SLAB=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
+CONFIG_ARCH_AT91=y
+CONFIG_ARCH_AT91X40=y
+CONFIG_MACH_AT91EB01=y
+CONFIG_AT91_EARLY_USART0=y
+CONFIG_CPU_ARM7TDMI=y
+CONFIG_SET_MEM_PARAM=y
+CONFIG_DRAM_BASE=0x01000000
+CONFIG_DRAM_SIZE=0x00400000
+CONFIG_FLASH_MEM_BASE=0x01400000
+CONFIG_PROCESSOR_ID=0x14000040
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_BINFMT_FLAT=y
+# CONFIG_SUSPEND is not set
+# CONFIG_FW_LOADER is not set
+CONFIG_MTD=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_RAM=y
+CONFIG_MTD_ROM=y
+CONFIG_BLK_DEV_RAM=y
+# CONFIG_INPUT is not set
+# CONFIG_SERIO is not set
+# CONFIG_VT is not set
+# CONFIG_DEVKMEM is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_EXT2_FS=y
+# CONFIG_DNOTIFY is not set
+CONFIG_ROMFS_FS=y
+# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 19390231a0e9..2d299bf5d72f 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -83,6 +83,7 @@ config ARCH_AT91CAP9
         select CPU_ARM926T
         select GENERIC_CLOCKEVENTS
         select HAVE_FB_ATMEL
+        select HAVE_NET_MACB
 
 config ARCH_AT572D940HF
         bool "AT572D940HF"
diff --git a/arch/arm/mach-at91/board-eb01.c b/arch/arm/mach-at91/board-eb01.c
index 1f9d3cb64c50..d8df59a3426d 100644
--- a/arch/arm/mach-at91/board-eb01.c
+++ b/arch/arm/mach-at91/board-eb01.c
@@ -30,6 +30,11 @@
 #include <mach/board.h>
 #include "generic.h"
 
+static void __init at91eb01_init_irq(void)
+{
+        at91x40_init_interrupts(NULL);
+}
+
 static void __init at91eb01_map_io(void)
 {
         at91x40_initialize(40000000);
@@ -38,7 +43,7 @@ static void __init at91eb01_map_io(void)
 MACHINE_START(AT91EB01, "Atmel AT91 EB01")
         /* Maintainer: Greg Ungerer <gerg@snapgear.com> */
         .timer          = &at91x40_timer,
-        .init_irq       = at91x40_init_interrupts,
+        .init_irq       = at91eb01_init_irq,
         .map_io         = at91eb01_map_io,
 MACHINE_END
 
diff --git a/arch/arm/mach-at91/include/mach/cpu.h b/arch/arm/mach-at91/include/mach/cpu.h
index 3bef931d0b1c..0700f2125305 100644
--- a/arch/arm/mach-at91/include/mach/cpu.h
+++ b/arch/arm/mach-at91/include/mach/cpu.h
@@ -27,6 +27,7 @@
 #define ARCH_ID_AT91SAM9G45     0x819b05a0
 #define ARCH_ID_AT91SAM9G45MRL  0x819b05a2      /* aka 9G45-ES2 & non ES lots */
 #define ARCH_ID_AT91SAM9G45ES   0x819b05a1      /* 9G45-ES (Engineering Sample) */
+#define ARCH_ID_AT91SAM9X5      0x819a05a0
 #define ARCH_ID_AT91CAP9        0x039A03A0
 
 #define ARCH_ID_AT91SAM9XE128   0x329973a0
@@ -55,6 +56,12 @@ static inline unsigned long at91_cpu_fully_identify(void)
 #define ARCH_EXID_AT91SAM9G46   0x00000003
 #define ARCH_EXID_AT91SAM9G45   0x00000004
 
+#define ARCH_EXID_AT91SAM9G15   0x00000000
+#define ARCH_EXID_AT91SAM9G35   0x00000001
+#define ARCH_EXID_AT91SAM9X35   0x00000002
+#define ARCH_EXID_AT91SAM9G25   0x00000003
+#define ARCH_EXID_AT91SAM9X25   0x00000004
+
 static inline unsigned long at91_exid_identify(void)
 {
         return at91_sys_read(AT91_DBGU_EXID);
@@ -143,6 +150,27 @@ static inline unsigned long at91cap9_rev_identify(void)
 #define cpu_is_at91sam9m11()    (0)
 #endif
 
+#ifdef CONFIG_ARCH_AT91SAM9X5
+#define cpu_is_at91sam9x5()     (at91_cpu_identify() == ARCH_ID_AT91SAM9X5)
+#define cpu_is_at91sam9g15()    (cpu_is_at91sam9x5() && \
+                                (at91_exid_identify() == ARCH_EXID_AT91SAM9G15))
+#define cpu_is_at91sam9g35()    (cpu_is_at91sam9x5() && \
+                                (at91_exid_identify() == ARCH_EXID_AT91SAM9G35))
+#define cpu_is_at91sam9x35()    (cpu_is_at91sam9x5() && \
+                                (at91_exid_identify() == ARCH_EXID_AT91SAM9X35))
+#define cpu_is_at91sam9g25()    (cpu_is_at91sam9x5() && \
+                                (at91_exid_identify() == ARCH_EXID_AT91SAM9G25))
+#define cpu_is_at91sam9x25()    (cpu_is_at91sam9x5() && \
+                                (at91_exid_identify() == ARCH_EXID_AT91SAM9X25))
+#else
+#define cpu_is_at91sam9x5()     (0)
+#define cpu_is_at91sam9g15()    (0)
+#define cpu_is_at91sam9g35()    (0)
+#define cpu_is_at91sam9x35()    (0)
+#define cpu_is_at91sam9g25()    (0)
+#define cpu_is_at91sam9x25()    (0)
+#endif
+
 #ifdef CONFIG_ARCH_AT91CAP9
 #define cpu_is_at91cap9()       (at91_cpu_identify() == ARCH_ID_AT91CAP9)
 #define cpu_is_at91cap9_revB()  (at91cap9_rev_identify() == ARCH_REVISION_CAP9_B)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 3532d3bf8105..bb9eb29a52dd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -698,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
  */
 
 const int amd_erratum_400[] =
-        AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
+        AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
                             AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
 EXPORT_SYMBOL_GPL(amd_erratum_400);
 
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/kernel/reboot_32.S
index 29092b38d816..1d5c46df0d78 100644
--- a/arch/x86/kernel/reboot_32.S
+++ b/arch/x86/kernel/reboot_32.S
@@ -21,26 +21,26 @@ r_base = .
         /* Get our own relocated address */
         call    1f
 1:      popl    %ebx
-        subl    $1b, %ebx
+        subl    $(1b - r_base), %ebx
 
         /* Compute the equivalent real-mode segment */
         movl    %ebx, %ecx
         shrl    $4, %ecx
         
         /* Patch post-real-mode segment jump */
-        movw    dispatch_table(%ebx,%eax,2),%ax
-        movw    %ax, 101f(%ebx)
-        movw    %cx, 102f(%ebx)
+        movw    (dispatch_table - r_base)(%ebx,%eax,2),%ax
+        movw    %ax, (101f - r_base)(%ebx)
+        movw    %cx, (102f - r_base)(%ebx)
 
         /* Set up the IDT for real mode. */
-        lidtl   machine_real_restart_idt(%ebx)
+        lidtl   (machine_real_restart_idt - r_base)(%ebx)
 
         /*
          * Set up a GDT from which we can load segment descriptors for real
          * mode.  The GDT is not used in real mode; it is just needed here to
          * prepare the descriptors.
          */
-        lgdtl   machine_real_restart_gdt(%ebx)
+        lgdtl   (machine_real_restart_gdt - r_base)(%ebx)
 
         /*
          * Load the data segment registers with 16-bit compatible values
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index e8c00cc72033..85b52fc03084 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -306,7 +306,7 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
                 bi->end = min(bi->end, high);
 
                 /* and there's no empty block */
-                if (bi->start == bi->end) {
+                if (bi->start >= bi->end) {
                         numa_remove_memblk_from(i--, mi);
                         continue;
                 }
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index aef7af92b28b..55c965b38c27 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1463,6 +1463,119 @@ static int xen_pgd_alloc(struct mm_struct *mm)
         return ret;
 }
 
+#ifdef CONFIG_X86_64
+static __initdata u64 __last_pgt_set_rw = 0;
+static __initdata u64 __pgt_buf_start = 0;
+static __initdata u64 __pgt_buf_end = 0;
+static __initdata u64 __pgt_buf_top = 0;
+/*
+ * As a consequence of the commit:
+ * 
+ * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
+ * Author: Yinghai Lu <yinghai@kernel.org>
+ * Date:   Fri Dec 17 16:58:28 2010 -0800
+ * 
+ *     x86-64, mm: Put early page table high
+ * 
+ * at some point init_memory_mapping is going to reach the pagetable pages
+ * area and map those pages too (mapping them as normal memory that falls
+ * in the range of addresses passed to init_memory_mapping as argument).
+ * Some of those pages are already pagetable pages (they are in the range
+ * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
+ * everything is fine.
+ * Some of these pages are not pagetable pages yet (they fall in the range
+ * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
+ * are going to be mapped RW.  When these pages become pagetable pages and
+ * are hooked into the pagetable, xen will find that the guest has already
+ * a RW mapping of them somewhere and fail the operation.
+ * The reason Xen requires pagetables to be RO is that the hypervisor needs
+ * to verify that the pagetables are valid before using them. The validation
+ * operations are called "pinning".
+ * 
+ * In order to fix the issue we mark all the pages in the entire range
+ * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
+ * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
+ * init_memory_mapping. Hence the kernel is going to crash as soon as one
+ * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
+ * ranges are RO).
+ * 
+ * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
+ * the init_memory_mapping has completed (in a perfect world we would
+ * call this function from init_memory_mapping, but lets ignore that).
+ * 
+ * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
+ * end,top] have all changed to new values (b/c init_memory_mapping
+ * is called and setting up another new page-table). Hence, the first time
+ * we enter this function, we save away the pgt_buf_start value and update
+ * the pgt_buf_[end,top].
+ * 
+ * When we detect that the "old" pgt_buf_start through pgt_buf_end
+ * PFNs have been reserved (so memblock_x86_reserve_range has been called),
+ * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
+ * 
+ * And then we update those "old" pgt_buf_[end|top] with the new ones
+ * so that we can redo this on the next pagetable.
+ */
+static __init void mark_rw_past_pgt(void) {
+
+        if (pgt_buf_end > pgt_buf_start) {
+                u64 addr, size;
+
+                /* Save it away. */
+                if (!__pgt_buf_start) {
+                        __pgt_buf_start = pgt_buf_start;
+                        __pgt_buf_end = pgt_buf_end;
+                        __pgt_buf_top = pgt_buf_top;
+                        return;
+                }
+                /* If we get the range that starts at __pgt_buf_end that means
+                 * the range is reserved, and that in 'init_memory_mapping'
+                 * the 'memblock_x86_reserve_range' has been called with the
+                 * outdated __pgt_buf_start, __pgt_buf_end (the "new"
+                 * pgt_buf_[start|end|top] refer now to a new pagetable.
+                 * Note: we are called _after_ the pgt_buf_[..] have been
+                 * updated.*/
+
+                addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
+                                                       &size, PAGE_SIZE);
+
+                /* Still not reserved, meaning 'memblock_x86_reserve_range'
+                 * hasn't been called yet. Update the _end and _top.*/
+                if (addr == PFN_PHYS(__pgt_buf_start)) {
+                        __pgt_buf_end = pgt_buf_end;
+                        __pgt_buf_top = pgt_buf_top;
+                        return;
+                }
+
+                /* OK, the area is reserved, meaning it is time for us to
+                 * set RW for the old end->top PFNs. */
+
+                /* ..unless we had already done this. */
+                if (__pgt_buf_end == __last_pgt_set_rw)
+                        return;
+
+                addr = PFN_PHYS(__pgt_buf_end);
+                
+                /* set as RW the rest */
+                printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
+                        PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
+                
+                while (addr < PFN_PHYS(__pgt_buf_top)) {
+                        make_lowmem_page_readwrite(__va(addr));
+                        addr += PAGE_SIZE;
+                }
+                /* And update everything so that we are ready for the next
+                 * pagetable (the one created for regions past 4GB) */
+                __last_pgt_set_rw = __pgt_buf_end;
+                __pgt_buf_start = pgt_buf_start;
+                __pgt_buf_end = pgt_buf_end;
+                __pgt_buf_top = pgt_buf_top;
+        }
+        return;
+}
+#else
+static __init void mark_rw_past_pgt(void) { }
+#endif
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
@@ -1489,13 +1602,21 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
         unsigned long pfn = pte_pfn(pte);
 
         /*
+         * A bit of optimization. We do not need to call the workaround
+         * when xen_set_pte_init is called with a PTE with 0 as PFN.
+         * That is b/c the pagetable at that point are just being populated
+         * with empty values and we can save some cycles by not calling
+         * the 'memblock' code.*/
+        if (pfn)
+                mark_rw_past_pgt();
+        /*
          * If the new pfn is within the range of the newly allocated
          * kernel pagetable, and it isn't being mapped into an
          * early_ioremap fixmap slot as a freshly allocated page, make sure
          * it is RO.
          */
         if (((!is_early_ioremap_ptep(ptep) &&
-                        pfn >= pgt_buf_start && pfn < pgt_buf_end)) ||
+                        pfn >= pgt_buf_start && pfn < pgt_buf_top)) ||
                         (is_early_ioremap_ptep(ptep) && pfn != (pgt_buf_end - 1)))
                 pte = pte_wrprotect(pte);
 
@@ -1997,6 +2118,8 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
+        mark_rw_past_pgt();
+
 #ifdef CONFIG_XEN_DEBUG
         pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
 #endif