@@ -30,6 +30,7 @@
#define MAP_NONBLOCK 0x40000 /* do not block on IO */
#define MAP_STACK 0x80000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x100000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x200000 /* Lock pages after they are faulted in, do not prefault */
#define MS_ASYNC 1 /* sync memory asynchronously */
#define MS_SYNC 2 /* synchronous memory sync */
@@ -48,6 +48,7 @@
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
#define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x80000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x100000 /* Lock pages after they are faulted in, do not prefault */
/*
* Flags for msync
@@ -24,6 +24,7 @@
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
#define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x80000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x100000 /* Lock pages after they are faulted in, do not prefault */
#define MS_SYNC 1 /* synchronous memory sync */
#define MS_ASYNC 2 /* sync memory asynchronously */
@@ -27,5 +27,6 @@
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x40000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x80000 /* Lock pages after they are faulted in, do not prefault */
#endif /* _UAPI_ASM_POWERPC_MMAN_H */
@@ -22,6 +22,7 @@
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x40000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x80000 /* Lock pages after they are faulted in, do not prefault */
#endif /* _UAPI__SPARC_MMAN_H__ */
@@ -29,6 +29,7 @@
#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
#define MAP_HUGETLB 0x4000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x8000 /* Lock pages after they are faulted in, do not prefault */
/*
@@ -55,6 +55,7 @@
#define MAP_NONBLOCK 0x20000 /* do not block on IO */
#define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x80000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x100000 /* Lock pages after they are faulted in, do not prefault */
#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
# define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be
* uninitialized */
@@ -126,6 +126,7 @@ extern unsigned int kobjsize(const void *objp);
#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */
#define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */
+#define VM_LOCKONFAULT 0x00001000 /* Lock the pages covered when they are faulted in */
#define VM_LOCKED 0x00002000
#define VM_IO 0x00004000 /* Memory mapped I/O or similar */
@@ -86,7 +86,8 @@ calc_vm_flag_bits(unsigned long flags)
{
return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) |
_calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) |
- _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED );
+ _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) |
+ _calc_vm_trans(flags, MAP_LOCKONFAULT,VM_LOCKONFAULT);
}
unsigned long vm_commit_limit(void);
@@ -12,6 +12,7 @@
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */
#define MAP_HUGETLB 0x40000 /* create a huge page mapping */
+#define MAP_LOCKONFAULT 0x80000 /* Lock pages after they are faulted in, do not prefault */
/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
@@ -1233,7 +1233,7 @@ static inline int mlock_future_check(struct mm_struct *mm,
unsigned long locked, lock_limit;
/* mlock MCL_FUTURE? */
- if (flags & VM_LOCKED) {
+ if (flags & (VM_LOCKED | VM_LOCKONFAULT)) {
locked = len >> PAGE_SHIFT;
locked += mm->locked_vm;
lock_limit = rlimit(RLIMIT_MEMLOCK);
@@ -1301,7 +1301,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
- if (flags & MAP_LOCKED)
+ if (flags & (MAP_LOCKED | MAP_LOCKONFAULT))
if (!can_do_mlock())
return -EPERM;
@@ -711,7 +711,8 @@ void lru_cache_add_active_or_unevictable(struct page *page,
{
VM_BUG_ON_PAGE(PageLRU(page), page);
- if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
+ if (likely((vma->vm_flags & (VM_LOCKED | VM_LOCKONFAULT)) == 0) ||
+ (vma->vm_flags & VM_SPECIAL)) {
SetPageActive(page);
lru_cache_add(page);
return;
The cost of faulting in all memory to be locked can be very high when working with large mappings. If only portions of the mapping will be used this can incur a high penalty for locking. For the example of a large file, this is the usage pattern for a large statical language model (probably applies to other statical or graphical models as well). For the security example, any application transacting in data that cannot be swapped out (credit card data, medical records, etc). This patch introduces the ability to request that pages are not pre-faulted, but are placed on the unevictable LRU when they are finally faulted in. To keep accounting checks out of the page fault path, users are billed for the entire mapping lock as if MAP_LOCKED was used. Signed-off-by: Eric B Munson <emunson@akamai.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: linux-alpha@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Cc: linux-xtensa@linux-xtensa.org Cc: linux-mm@kvack.org Cc: linux-arch@vger.kernel.org Cc: linux-api@vger.kernel.org --- arch/alpha/include/uapi/asm/mman.h | 1 + arch/mips/include/uapi/asm/mman.h | 1 + arch/parisc/include/uapi/asm/mman.h | 1 + arch/powerpc/include/uapi/asm/mman.h | 1 + arch/sparc/include/uapi/asm/mman.h | 1 + arch/tile/include/uapi/asm/mman.h | 1 + arch/xtensa/include/uapi/asm/mman.h | 1 + include/linux/mm.h | 1 + include/linux/mman.h | 3 ++- include/uapi/asm-generic/mman.h | 1 + mm/mmap.c | 4 ++-- mm/swap.c | 3 ++- 12 files changed, 15 insertions(+), 4 deletions(-)