Automatic merge with /usr/src/ntfs-2.6.git.

8 files changed, 40 insertions, 55 deletions

diff --git a/arch/x86_64/ia32/ia32_aout.c b/arch/x86_64/ia32/ia32_aout.c
index 1965efc974dc..c12edf5d97f0 100644
--- a/arch/x86_64/ia32/ia32_aout.c
+++ b/arch/x86_64/ia32/ia32_aout.c
@@ -312,6 +312,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
         current->mm->brk = ex.a_bss +
                 (current->mm->start_brk = N_BSSADDR(ex));
         current->mm->free_area_cache = TASK_UNMAPPED_BASE;
+        current->mm->cached_hole_size = 0;
 
         set_mm_counter(current->mm, rss, 0);
         current->mm->mmap = NULL;
diff --git a/arch/x86_64/ia32/ia32_binfmt.c b/arch/x86_64/ia32/ia32_binfmt.c
index 99b522052d16..c8131f342cfc 100644
--- a/arch/x86_64/ia32/ia32_binfmt.c
+++ b/arch/x86_64/ia32/ia32_binfmt.c
@@ -46,7 +46,7 @@ struct elf_phdr;
 
 #define IA32_EMULATOR 1
 
-#define ELF_ET_DYN_BASE         (TASK_UNMAPPED_32 + 0x1000000)
+#define ELF_ET_DYN_BASE         (TASK_UNMAPPED_BASE + 0x1000000)
 
 #undef ELF_ARCH
 #define ELF_ARCH EM_386
@@ -307,9 +307,6 @@ MODULE_AUTHOR("Eric Youngdale, Andi Kleen");
 
 #define elf_addr_t __u32
 
-#undef TASK_SIZE
-#define TASK_SIZE 0xffffffff
-
 static void elf32_init(struct pt_regs *);
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c
index a491f72cc966..504e63474993 100644
--- a/arch/x86_64/kernel/aperture.c
+++ b/arch/x86_64/kernel/aperture.c
@@ -33,12 +33,10 @@ int fallback_aper_force __initdata = 0;
 
 int fix_aperture __initdata = 1;
 
-#define NB_ID_3 (PCI_VENDOR_ID_AMD | (0x1103<<16))
+/* This code runs before the PCI subsystem is initialized, so just
+   access the northbridge directly. */
 
-static struct resource aper_res = {
-        .name = "Aperture",
-        .flags = IORESOURCE_MEM,
-};
+#define NB_ID_3 (PCI_VENDOR_ID_AMD | (0x1103<<16))
 
 static u32 __init allocate_aperture(void) 
 {
@@ -55,24 +53,11 @@ static u32 __init allocate_aperture(void)
         aper_size = (32 * 1024 * 1024) << fallback_aper_order; 
 
         /* 
-         * Aperture has to be naturally aligned. This means an 2GB
-         * aperture won't have much chances to find a place in the
-         * lower 4GB of memory.  Unfortunately we cannot move it up
-         * because that would make the IOMMU useless.
+         * Aperture has to be naturally aligned. This means an 2GB aperture won't
+         * have much chances to find a place in the lower 4GB of memory.
+         * Unfortunately we cannot move it up because that would make the
+         * IOMMU useless.
          */
-
-        /* First try to find some free unused space */
-        if (!allocate_resource(&iomem_resource, &aper_res,
-                               aper_size,
-                               0, 0xffffffff,
-                               aper_size,
-                               NULL, NULL)) {
-                printk(KERN_INFO "Putting aperture at %lx-%lx\n",
-                       aper_res.start, aper_res.end);
-                return aper_res.start;
-        }
-
-        /* No free space found. Go on to waste some memory... */
         p = __alloc_bootmem_node(nd0, aper_size, aper_size, 0); 
         if (!p || __pa(p)+aper_size > 0xffffffff) {
                 printk("Cannot allocate aperture memory hole (%p,%uK)\n",
@@ -81,7 +66,7 @@ static u32 __init allocate_aperture(void)
                         free_bootmem_node(nd0, (unsigned long)p, aper_size); 
                 return 0;
         }
-        printk("Mapping aperture over %d KB of precious RAM @ %lx\n",
+        printk("Mapping aperture over %d KB of RAM @ %lx\n",
                aper_size >> 10, __pa(p)); 
         return (u32)__pa(p); 
 }
@@ -102,16 +87,10 @@ static int __init aperture_valid(char *name, u64 aper_base, u32 aper_size)
                 printk("Aperture from %s pointing to e820 RAM. Ignoring.\n",name);
                 return 0; 
         } 
-        /* Don't check the resource here because the aperture is usually
-           in an e820 reserved area, and we allocated these earlier. */
         return 1;
 } 
 
-/*
- * Find a PCI capability.
- * This code runs before the PCI subsystem is initialized, so just
- * access the northbridge directly.
- */
+/* Find a PCI capability */
 static __u32 __init find_cap(int num, int slot, int func, int cap) 
 { 
         u8 pos;
@@ -276,6 +255,8 @@ void __init iommu_hole_init(void)
                    fallback_aper_force) { 
                 printk("Your BIOS doesn't leave a aperture memory hole\n");
                 printk("Please enable the IOMMU option in the BIOS setup\n");
+                printk("This costs you %d MB of RAM\n",
+                       32 << fallback_aper_order);
 
                 aper_order = fallback_aper_order;
                 aper_alloc = allocate_aperture();
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 761b6d35e338..dce8bab4306c 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -656,7 +656,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 
         switch (code) { 
         case ARCH_SET_GS:
-                if (addr >= TASK_SIZE) 
+                if (addr >= TASK_SIZE_OF(task))
                         return -EPERM; 
                 cpu = get_cpu();
                 /* handle small bases via the GDT because that's faster to 
@@ -682,7 +682,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
         case ARCH_SET_FS:
                 /* Not strictly needed for fs, but do it for symmetry
                    with gs */
-                if (addr >= TASK_SIZE)
+                if (addr >= TASK_SIZE_OF(task))
                         return -EPERM; 
                 cpu = get_cpu();
                 /* handle small bases via the GDT because that's faster to 
diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c
index 525f6a128a27..bbf64b59a21e 100644
--- a/arch/x86_64/kernel/ptrace.c
+++ b/arch/x86_64/kernel/ptrace.c
@@ -257,12 +257,12 @@ static int putreg(struct task_struct *child,
                         value &= 0xffff;
                         return 0;
                 case offsetof(struct user_regs_struct,fs_base):
-                        if (value >= TASK_SIZE)
+                        if (value >= TASK_SIZE_OF(child))
                                 return -EIO;
                         child->thread.fs = value;
                         return 0;
                 case offsetof(struct user_regs_struct,gs_base):
-                        if (value >= TASK_SIZE)
+                        if (value >= TASK_SIZE_OF(child))
                                 return -EIO;
                         child->thread.gs = value;
                         return 0;
@@ -279,7 +279,7 @@ static int putreg(struct task_struct *child,
                         break;
                 case offsetof(struct user_regs_struct, rip):
                         /* Check if the new RIP address is canonical */
-                        if (value >= TASK_SIZE)
+                        if (value >= TASK_SIZE_OF(child))
                                 return -EIO;
                         break;
         }
@@ -419,6 +419,8 @@ asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, long data
                 break;
 
         case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
+        {
+                int dsize = test_tsk_thread_flag(child, TIF_IA32) ? 3 : 7;
                 ret = -EIO;
                 if ((addr & 7) ||
                     addr > sizeof(struct user) - 7)
@@ -430,22 +432,22 @@ asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, long data
                         break;
                 /* Disallows to set a breakpoint into the vsyscall */
                 case offsetof(struct user, u_debugreg[0]):
-                        if (data >= TASK_SIZE-7) break;
+                        if (data >= TASK_SIZE_OF(child) - dsize) break;
                         child->thread.debugreg0 = data;
                         ret = 0;
                         break;
                 case offsetof(struct user, u_debugreg[1]):
-                        if (data >= TASK_SIZE-7) break;
+                        if (data >= TASK_SIZE_OF(child) - dsize) break;
                         child->thread.debugreg1 = data;
                         ret = 0;
                         break;
                 case offsetof(struct user, u_debugreg[2]):
-                        if (data >= TASK_SIZE-7) break;
+                        if (data >= TASK_SIZE_OF(child) - dsize) break;
                         child->thread.debugreg2 = data;
                         ret = 0;
                         break;
                 case offsetof(struct user, u_debugreg[3]):
-                        if (data >= TASK_SIZE-7) break;
+                        if (data >= TASK_SIZE_OF(child) - dsize) break;
                         child->thread.debugreg3 = data;
                         ret = 0;
                         break;
@@ -469,6 +471,7 @@ asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, long data
                   break;
                 }
                 break;
+        }
         case PTRACE_SYSCALL: /* continue and stop at next (return from) syscall */
         case PTRACE_CONT:    /* restart after signal. */
 
diff --git a/arch/x86_64/kernel/sys_x86_64.c b/arch/x86_64/kernel/sys_x86_64.c
index dbebd5ccba6b..cc7821c68851 100644
--- a/arch/x86_64/kernel/sys_x86_64.c
+++ b/arch/x86_64/kernel/sys_x86_64.c
@@ -68,13 +68,7 @@ out:
 static void find_start_end(unsigned long flags, unsigned long *begin,
                            unsigned long *end)
 {
-#ifdef CONFIG_IA32_EMULATION
-        if (test_thread_flag(TIF_IA32)) { 
-                *begin = TASK_UNMAPPED_32;
-                *end = IA32_PAGE_OFFSET; 
-        } else 
-#endif
-        if (flags & MAP_32BIT) { 
+        if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) {
                 /* This is usually used needed to map code in small
                    model, so it needs to be in the first 31bit. Limit
                    it to that.  This means we need to move the
@@ -84,10 +78,10 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
                    of playground for now. -AK */ 
                 *begin = 0x40000000; 
                 *end = 0x80000000;              
-        } else { 
-                *begin = TASK_UNMAPPED_64; 
+        } else {
+                *begin = TASK_UNMAPPED_BASE;
                 *end = TASK_SIZE; 
-                }
+        }
 } 
 
 unsigned long
@@ -111,6 +105,11 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
                     (!vma || addr + len <= vma->vm_start))
                         return addr;
         }
+        if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
+            && len <= mm->cached_hole_size) {
+                mm->cached_hole_size = 0;
+                mm->free_area_cache = begin;
+        }
         addr = mm->free_area_cache;
         if (addr < begin) 
                 addr = begin; 
@@ -126,6 +125,7 @@ full_search:
                          */
                         if (start_addr != begin) {
                                 start_addr = addr = begin;
+                                mm->cached_hole_size = 0;
                                 goto full_search;
                         }
                         return -ENOMEM;
@@ -137,6 +137,9 @@ full_search:
                         mm->free_area_cache = addr + len;
                         return addr;
                 }
+                if (addr + mm->cached_hole_size < vma->vm_start)
+                        mm->cached_hole_size = vma->vm_start - addr;
+
                 addr = vma->vm_end;
         }
 }
diff --git a/arch/x86_64/lib/delay.c b/arch/x86_64/lib/delay.c
index 6e2d66472eb1..aed61a668a1b 100644
--- a/arch/x86_64/lib/delay.c
+++ b/arch/x86_64/lib/delay.c
@@ -34,7 +34,7 @@ void __delay(unsigned long loops)
 
 inline void __const_udelay(unsigned long xloops)
 {
-        __delay(((xloops * cpu_data[_smp_processor_id()].loops_per_jiffy) >> 32) * HZ);
+        __delay(((xloops * cpu_data[raw_smp_processor_id()].loops_per_jiffy) >> 32) * HZ);
 }
 
 void __udelay(unsigned long usecs)
diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index 5d6b2114cc9a..57d3ab15a5c7 100644
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -350,7 +350,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
          * (error_code & 4) == 0, and that the fault was not a
          * protection error (error_code & 1) == 0.
          */
-        if (unlikely(address >= TASK_SIZE)) {
+        if (unlikely(address >= TASK_SIZE64)) {
                 if (!(error_code & 5) &&
                       ((address >= VMALLOC_START && address < VMALLOC_END) ||
                        (address >= MODULES_VADDR && address < MODULES_END))) {