x86/mm: Add task_size parameter to mmap_base()

To correctly handle 32-bit and 64-bit mmap() syscalls in 64bit applications
its required to have separate address bases to place a mapping.

The tasksize can be used as an indicator to select the proper parameters
for mmap_base().

This requires the following changes:

 - Add task_size argument to mmap_base() and make the calculation based on it.
 - Provide mmap_legacy_base() as a seperate function
 - Use the new functions in arch_pick_mmap_layout()

[ tglx: Massaged changelog ]
Signed-off-by: Dmitry Safonov <dsafonov@virtuozzo.com>
Cc: 0x7f454c46@gmail.com
Cc: linux-mm@kvack.org
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Borislav Petkov <bp@suse.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/20170306141721.9188-3-dsafonov@virtuozzo.comSigned-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/include/asm/elf.h

@@ -293,8 +293,19 @@ do {									\
 	}								\
 } while (0)
 
+/*
+ * True on X86_32 or when emulating IA32 on X86_64
+ */
+static inline int mmap_is_ia32(void)
+{
+	return IS_ENABLED(CONFIG_X86_32) ||
+	       (IS_ENABLED(CONFIG_COMPAT) &&
+		test_thread_flag(TIF_ADDR32));
+}
+
 #ifdef CONFIG_X86_32
 
+#define __STACK_RND_MASK(is32bit) (0x7ff)
 #define STACK_RND_MASK (0x7ff)
 
 #define ARCH_DLINFO		ARCH_DLINFO_IA32
@@ -304,7 +315,8 @@ do {									\
 #else /* CONFIG_X86_32 */
 
 /* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
+#define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32())
 
 #define ARCH_DLINFO							\
 do {									\
@@ -348,16 +360,6 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
 					      int uses_interp);
 #define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
 
-/*
- * True on X86_32 or when emulating IA32 on X86_64
- */
-static inline int mmap_is_ia32(void)
-{
-	return IS_ENABLED(CONFIG_X86_32) ||
-	       (IS_ENABLED(CONFIG_COMPAT) &&
-		test_thread_flag(TIF_ADDR32));
-}
-
 /* Do not change the values. See get_align_mask() */
 enum align_flags {
 	ALIGN_VA_32	= BIT(0),

arch/x86/include/asm/processor.h

@@ -797,6 +797,7 @@ static inline void spin_lock_prefetch(const void *x)
 /*
  * User space process size: 3GB (default).
  */
+#define IA32_PAGE_OFFSET	PAGE_OFFSET
 #define TASK_SIZE		PAGE_OFFSET
 #define TASK_SIZE_MAX		TASK_SIZE
 #define STACK_TOP		TASK_SIZE
@@ -873,7 +874,8 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
  * This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
+#define __TASK_UNMAPPED_BASE(task_size)	(PAGE_ALIGN(task_size / 3))
+#define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE)
 
 #define KSTK_EIP(task)		(task_pt_regs(task)->ip)
 

arch/x86/mm/mmap.c

@@ -36,25 +36,23 @@ struct va_alignment __read_mostly va_align = {
 	.flags = -1,
 };
 
-static unsigned long stack_maxrandom_size(void)
+static inline unsigned long tasksize_32bit(void)
+{
+	return IA32_PAGE_OFFSET;
+}
+
+static unsigned long stack_maxrandom_size(unsigned long task_size)
 {
 	unsigned long max = 0;
 	if ((current->flags & PF_RANDOMIZE) &&
 		!(current->personality & ADDR_NO_RANDOMIZE)) {
-		max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
+		max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit());
+		max <<= PAGE_SHIFT;
 	}
 
 	return max;
 }
 
-/*
- * Top of mmap area (just below the process stack).
- *
- * Leave an at least ~128 MB hole with possible stack randomization.
- */
-#define MIN_GAP (128*1024*1024UL + stack_maxrandom_size())
-#define MAX_GAP (TASK_SIZE/6*5)
-
 #ifdef CONFIG_COMPAT
 # define mmap32_rnd_bits  mmap_rnd_compat_bits
 # define mmap64_rnd_bits  mmap_rnd_bits
@@ -63,6 +61,8 @@ static unsigned long stack_maxrandom_size(void)
 # define mmap64_rnd_bits  mmap_rnd_bits
 #endif
 
+#define SIZE_128M    (128 * 1024 * 1024UL)
+
 static int mmap_is_legacy(void)
 {
 	if (current->personality & ADDR_COMPAT_LAYOUT)
@@ -84,16 +84,30 @@ unsigned long arch_mmap_rnd(void)
 	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 
-static unsigned long mmap_base(unsigned long rnd)
+static unsigned long mmap_base(unsigned long rnd, unsigned long task_size)
 {
 	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap_min, gap_max;
+
+	/*
+	 * Top of mmap area (just below the process stack).
+	 * Leave an at least ~128 MB hole with possible stack randomization.
+	 */
+	gap_min = SIZE_128M + stack_maxrandom_size(task_size);
+	gap_max = (task_size / 6) * 5;
+
+	if (gap < gap_min)
+		gap = gap_min;
+	else if (gap > gap_max)
+		gap = gap_max;
 
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
+	return PAGE_ALIGN(task_size - gap - rnd);
+}
 
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+static unsigned long mmap_legacy_base(unsigned long rnd,
+				      unsigned long task_size)
+{
+	return __TASK_UNMAPPED_BASE(task_size) + rnd;
 }
 
 /*
@@ -107,13 +121,13 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (current->flags & PF_RANDOMIZE)
 		random_factor = arch_mmap_rnd();
 
-	mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
+	mm->mmap_legacy_base = mmap_legacy_base(random_factor, TASK_SIZE);
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mm->mmap_legacy_base;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, TASK_SIZE);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }