arch/x86/kernel/sys_x86_64.c

   1 #include <linux/errno.h>
   2 #include <linux/sched.h>
   3 #include <linux/syscalls.h>
   4 #include <linux/mm.h>
   5 #include <linux/fs.h>
   6 #include <linux/smp.h>
   7 #include <linux/sem.h>
   8 #include <linux/msg.h>
   9 #include <linux/shm.h>
  10 #include <linux/stat.h>
  11 #include <linux/mman.h>
  12 #include <linux/file.h>
  13 #include <linux/utsname.h>
  14 #include <linux/personality.h>
  15 #include <linux/random.h>
  16 #include <linux/uaccess.h>
  17 #include <linux/elf.h>
  18
  19 #include <asm/ia32.h>
  20 #include <asm/syscalls.h>
  21
  22 /*
  23  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
  24  */
  25 static unsigned long get_align_mask(void)
  26 {
  27         /* handle 32- and 64-bit case with a single conditional */
  28         if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
  29                 return 0;
  30
  31         if (!(current->flags & PF_RANDOMIZE))
  32                 return 0;
  33
  34         return va_align.mask;
  35 }
  36
  37 /*
  38  * To avoid aliasing in the I$ on AMD F15h, the bits defined by the
  39  * va_align.bits, [12:upper_bit), are set to a random value instead of
  40  * zeroing them. This random value is computed once per boot. This form
  41  * of ASLR is known as "per-boot ASLR".
  42  *
  43  * To achieve this, the random value is added to the info.align_offset
  44  * value before calling vm_unmapped_area() or ORed directly to the
  45  * address.
  46  */
  47 static unsigned long get_align_bits(void)
  48 {
  49         return va_align.bits & get_align_mask();
  50 }
  51
  52 unsigned long align_vdso_addr(unsigned long addr)
  53 {
  54         unsigned long align_mask = get_align_mask();
  55         addr = (addr + align_mask) & ~align_mask;
  56         return addr | get_align_bits();
  57 }
  58
  59 static int __init control_va_addr_alignment(char *str)
  60 {
  61         /* guard against enabling this on other CPU families */
  62         if (va_align.flags < 0)
  63                 return 1;
  64
  65         if (*str == 0)
  66                 return 1;
  67
  68         if (*str == '=')
  69                 str++;
  70
  71         if (!strcmp(str, "32"))
  72                 va_align.flags = ALIGN_VA_32;
  73         else if (!strcmp(str, "64"))
  74                 va_align.flags = ALIGN_VA_64;
  75         else if (!strcmp(str, "off"))
  76                 va_align.flags = 0;
  77         else if (!strcmp(str, "on"))
  78                 va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
  79         else
  80                 return 0;
  81
  82         return 1;
  83 }
  84 __setup("align_va_addr", control_va_addr_alignment);
  85
  86 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
  87                 unsigned long, prot, unsigned long, flags,
  88                 unsigned long, fd, unsigned long, off)
  89 {
  90         long error;
  91         error = -EINVAL;
  92         if (off & ~PAGE_MASK)
  93                 goto out;
  94
  95         error = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT);
  96 out:
  97         return error;
  98 }
  99
 100 static void find_start_end(unsigned long flags, unsigned long *begin,
 101                            unsigned long *end)
 102 {
 103         if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
 104                 unsigned long new_begin;
 105                 /* This is usually used needed to map code in small
 106                    model, so it needs to be in the first 31bit. Limit
 107                    it to that.  This means we need to move the
 108                    unmapped base down for this case. This can give
 109                    conflicts with the heap, but we assume that glibc
 110                    malloc knows how to fall back to mmap. Give it 1GB
 111                    of playground for now. -AK */
 112                 *begin = 0x40000000;
 113                 *end = 0x80000000;
 114                 if (current->flags & PF_RANDOMIZE) {
 115                         new_begin = randomize_range(*begin, *begin + 0x02000000, 0);
 116                         if (new_begin)
 117                                 *begin = new_begin;
 118                 }
 119         } else {
 120                 *begin = current->mm->mmap_legacy_base;
 121                 *end = TASK_SIZE;
 122         }
 123 }
 124
 125 unsigned long
 126 arch_get_unmapped_area(struct file *filp, unsigned long addr,
 127                 unsigned long len, unsigned long pgoff, unsigned long flags)
 128 {
 129         struct mm_struct *mm = current->mm;
 130         struct vm_area_struct *vma;
 131         struct vm_unmapped_area_info info;
 132         unsigned long begin, end;
 133
 134         if (flags & MAP_FIXED)
 135                 return addr;
 136
 137         find_start_end(flags, &begin, &end);
 138
 139         if (len > end)
 140                 return -ENOMEM;
 141
 142         if (addr) {
 143                 addr = PAGE_ALIGN(addr);
 144                 vma = find_vma(mm, addr);
 145                 if (end - len >= addr &&
 146                     (!vma || addr + len <= vma->vm_start))
 147                         return addr;
 148         }
 149
 150         info.flags = 0;
 151         info.length = len;
 152         info.low_limit = begin;
 153         info.high_limit = end;
 154         info.align_mask = 0;
 155         info.align_offset = pgoff << PAGE_SHIFT;
 156         if (filp) {
 157                 info.align_mask = get_align_mask();
 158                 info.align_offset += get_align_bits();
 159         }
 160         return vm_unmapped_area(&info);
 161 }
 162
 163 unsigned long
 164 arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 165                           const unsigned long len, const unsigned long pgoff,
 166                           const unsigned long flags)
 167 {
 168         struct vm_area_struct *vma;
 169         struct mm_struct *mm = current->mm;
 170         unsigned long addr = addr0;
 171         struct vm_unmapped_area_info info;
 172
 173         /* requested length too big for entire address space */
 174         if (len > TASK_SIZE)
 175                 return -ENOMEM;
 176
 177         if (flags & MAP_FIXED)
 178                 return addr;
 179
 180         /* for MAP_32BIT mappings we force the legacy mmap base */
 181         if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
 182                 goto bottomup;
 183
 184         /* requesting a specific address */
 185         if (addr) {
 186                 addr = PAGE_ALIGN(addr);
 187                 vma = find_vma(mm, addr);
 188                 if (TASK_SIZE - len >= addr &&
 189                                 (!vma || addr + len <= vma->vm_start))
 190                         return addr;
 191         }
 192
 193         info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 194         info.length = len;
 195         info.low_limit = PAGE_SIZE;
 196         info.high_limit = mm->mmap_base;
 197         info.align_mask = 0;
 198         info.align_offset = pgoff << PAGE_SHIFT;
 199         if (filp) {
 200                 info.align_mask = get_align_mask();
 201                 info.align_offset += get_align_bits();
 202         }
 203         addr = vm_unmapped_area(&info);
 204         if (!(addr & ~PAGE_MASK))
 205                 return addr;
 206         VM_BUG_ON(addr != -ENOMEM);
 207
 208 bottomup:
 209         /*
 210          * A failed mmap() very likely causes application failure,
 211          * so fall back to the bottom-up function here. This scenario
 212          * can happen with large stack limits and large mmap()
 213          * allocations.
 214          */
 215         return arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
 216 }