[PATCHv4 33/33] x86/mm: allow to have userspace mappigs above 47-bits

@@ -250,7 +250,7 @@ extern int force_personality32;
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
 
-#define ELF_ET_DYN_BASE		(TASK_SIZE / 3 * 2)
+#define ELF_ET_DYN_BASE		(DEFAULT_MAP_WINDOW / 3 * 2)
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,

@@ -73,6 +73,9 @@ static inline void mpx_mm_init(struct mm_struct *mm)
 }
 void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long start, unsigned long end);
+
+unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
+		unsigned long flags);
 #else
 static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs)
 {

@@ -94,6 +97,12 @@ static inline void mpx_notify_unmap(struct mm_struct *mm,
 				    unsigned long start, unsigned long end)
 {
 }
+
+static inline unsigned long mpx_unmapped_area_check(unsigned long addr,
+		unsigned long len, unsigned long flags)
+{
+	return addr;
+}
 #endif /* CONFIG_X86_INTEL_MPX */
 
 #endif /* _ASM_X86_MPX_H */

@@ -799,6 +799,7 @@ static inline void spin_lock_prefetch(const void *x)
  */
 #define TASK_SIZE		PAGE_OFFSET
 #define TASK_SIZE_MAX		TASK_SIZE
+#define DEFAULT_MAP_WINDOW	TASK_SIZE
 #define STACK_TOP		TASK_SIZE
 #define STACK_TOP_MAX		STACK_TOP
 

@@ -838,7 +839,9 @@ static inline void spin_lock_prefetch(const void *x)
  * particular problem by preventing anything from being mapped
  * at the maximum canonical address.
  */
-#define TASK_SIZE_MAX	((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
+
+#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.

@@ -851,7 +854,7 @@ static inline void spin_lock_prefetch(const void *x)
 #define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 
-#define STACK_TOP		TASK_SIZE
+#define STACK_TOP		DEFAULT_MAP_WINDOW
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
 #define INIT_THREAD  {						\

@@ -873,7 +876,7 @@ 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	(PAGE_ALIGN(DEFAULT_MAP_WINDOW / 3))
 
 #define KSTK_EIP(task)		(task_pt_regs(task)->ip)
 

@@ -19,6 +19,7 @@
 
 #include <asm/ia32.h>
 #include <asm/syscalls.h>
+#include <asm/mpx.h>
 
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.

@@ -129,6 +130,10 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct vm_unmapped_area_info info;
 	unsigned long begin, end;
 
+	addr = mpx_unmapped_area_check(addr, len, flags);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
 	if (flags & MAP_FIXED)
 		return addr;
 

@@ -148,7 +153,16 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.flags = 0;
 	info.length = len;
 	info.low_limit = begin;
-	info.high_limit = end;
+
+	/*
+	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
+	 * in the full address space.
+	 */
+	if (addr > DEFAULT_MAP_WINDOW)
+		info.high_limit = min(end, TASK_SIZE);
+	else
+		info.high_limit = min(end, DEFAULT_MAP_WINDOW);
+
 	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 	if (filp) {

@@ -168,6 +182,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	unsigned long addr = addr0;
 	struct vm_unmapped_area_info info;
 
+	addr = mpx_unmapped_area_check(addr, len, flags);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
 		return -ENOMEM;

@@ -192,6 +210,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
+
+	/*
+	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
+	 * in the full address space.
+	 */
+	if (addr > DEFAULT_MAP_WINDOW)
+		info.high_limit += TASK_SIZE - DEFAULT_MAP_WINDOW;
+
 	info.align_mask = 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
 	if (filp) {

@@ -16,6 +16,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
+#include <asm/mpx.h>
 
 #if 0	/* This is just for testing */
 struct page *

@@ -83,24 +84,41 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 	info.flags = 0;
 	info.length = len;
 	info.low_limit = current->mm->mmap_legacy_base;
-	info.high_limit = TASK_SIZE;
+	info.high_limit = DEFAULT_MAP_WINDOW;
+
+	/*
+	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
+	 * in the full address space.
+	 */
+	if (addr > DEFAULT_MAP_WINDOW)
+		info.high_limit = TASK_SIZE;
+	else
+		info.high_limit = DEFAULT_MAP_WINDOW;
+
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	return vm_unmapped_area(&info);
 }
 
 static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
-		unsigned long addr0, unsigned long len,
+		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
 	struct hstate *h = hstate_file(file);
 	struct vm_unmapped_area_info info;
-	unsigned long addr;
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = current->mm->mmap_base;
+
+	/*
+	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
+	 * in the full address space.
+	 */
+	if (addr > DEFAULT_MAP_WINDOW)
+		info.high_limit += TASK_SIZE - DEFAULT_MAP_WINDOW;
+
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
 	addr = vm_unmapped_area(&info);

@@ -115,7 +133,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		VM_BUG_ON(addr != -ENOMEM);
 		info.flags = 0;
 		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = TASK_SIZE;
+		info.high_limit = DEFAULT_MAP_WINDOW;
 		addr = vm_unmapped_area(&info);
 	}
 

@@ -132,6 +150,11 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
+
+	addr = mpx_unmapped_area_check(addr, len, flags);
+	if (IS_ERR_VALUE(addr))
+		return addr;
+
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 

@@ -53,7 +53,7 @@ static unsigned long stack_maxrandom_size(void)
  * 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)
+#define MAX_GAP (DEFAULT_MAP_WINDOW/6*5)
 
 static int mmap_is_legacy(void)
 {

@@ -91,7 +91,7 @@ static unsigned long mmap_base(unsigned long rnd)
 	else if (gap > MAX_GAP)
 		gap = MAX_GAP;
 
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
+	return PAGE_ALIGN(DEFAULT_MAP_WINDOW - gap - rnd);
 }
 
 /*

@@ -355,10 +355,19 @@ int mpx_enable_management(void)
 	 */
 	bd_base = mpx_get_bounds_dir();
 	down_write(&mm->mmap_sem);
+
+	/* MPX doesn't support addresses above 47-bits yet. */
+	if (find_vma(mm, DEFAULT_MAP_WINDOW)) {
+		pr_warn_once("%s (%d): MPX cannot handle addresses "
+				"above 47-bits. Disabling.",
+				current->comm, current->pid);
+		ret = -ENXIO;
+		goto out;
+	}
 	mm->context.bd_addr = bd_base;
 	if (mm->context.bd_addr == MPX_INVALID_BOUNDS_DIR)
 		ret = -ENXIO;
-
+out:
 	up_write(&mm->mmap_sem);
 	return ret;
 }

@@ -1038,3 +1047,25 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ret)
 		force_sig(SIGSEGV, current);
 }
+
+/* MPX cannot handle addresses above 47-bits yet. */
+unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len,
+		unsigned long flags)
+{
+	if (!kernel_managing_mpx_tables(current->mm))
+		return addr;
+	if (addr + len <= DEFAULT_MAP_WINDOW)
+		return addr;
+	if (flags & MAP_FIXED)
+		return -ENOMEM;
+
+	/*
+	 * Requested len is larger than whole area we're allowed to map in.
+	 * Resetting hinting address wouldn't do much good -- fail early.
+	 */
+	if (len > DEFAULT_MAP_WINDOW)
+		return -ENOMEM;
+
+	/* Look for unmap area within DEFAULT_MAP_WINDOW */
+	return 0;
+}