* [PATCH v8 2/6] mm: mlock: Add new mlock system call
2015-08-26 18:24 [PATCH v8 0/6] Allow user to request memory to be locked on page fault Eric B Munson
@ 2015-08-26 18:24 ` Eric B Munson
2015-08-26 18:24 ` [PATCH v8 3/6] mm: Introduce VM_LOCKONFAULT Eric B Munson
` (3 subsequent siblings)
4 siblings, 0 replies; 13+ messages in thread
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Michal Hocko, Vlastimil Babka, Heiko Carstens,
Geert Uytterhoeven, Catalin Marinas, Stephen Rothwell,
Guenter Roeck, linux-alpha, linux-kernel, linux-arm-kernel,
adi-buildroot-devel, linux-cris-kernel, linux-ia64, linux-m68k,
linux-am33-list, linux-parisc, linuxppc-dev, linux-s390, linux-sh,
sparclinux, linux-xtensa, linux-api, linux-arch, linux-mm
With the refactored mlock code, introduce a new system call for mlock.
The new call will allow the user to specify what lock states are being
added. mlock2 is trivial at the moment, but a follow on patch will add
a new mlock state making it useful.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: linux-alpha@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: adi-buildroot-devel@lists.sourceforge.net
Cc: linux-cris-kernel@axis.com
Cc: linux-ia64@vger.kernel.org
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-am33-list@redhat.com
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-xtensa@linux-xtensa.org
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
---
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
include/linux/syscalls.h | 2 ++
include/uapi/asm-generic/unistd.h | 4 +++-
kernel/sys_ni.c | 1 +
mm/mlock.c | 8 ++++++++
6 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ef8187f..8e06da6 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -365,3 +365,4 @@
356 i386 memfd_create sys_memfd_create
357 i386 bpf sys_bpf
358 i386 execveat sys_execveat stub32_execveat
+360 i386 mlock2 sys_mlock2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9ef32d5..67601e7 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -329,6 +329,7 @@
320 common kexec_file_load sys_kexec_file_load
321 common bpf sys_bpf
322 64 execveat stub_execveat
+324 common mlock2 sys_mlock2
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b45c45b..56a3d59 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -884,4 +884,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename,
const char __user *const __user *argv,
const char __user *const __user *envp, int flags);
+asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
+
#endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index e016bd9..14a6013 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -709,9 +709,11 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
__SYSCALL(__NR_bpf, sys_bpf)
#define __NR_execveat 281
__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_mlock2 282
+__SYSCALL(__NR_mlock2, sys_mlock2)
#undef __NR_syscalls
-#define __NR_syscalls 282
+#define __NR_syscalls 283
/*
* All syscalls below here should go away really,
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 7995ef5..4818b71 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -193,6 +193,7 @@ cond_syscall(sys_mlock);
cond_syscall(sys_munlock);
cond_syscall(sys_mlockall);
cond_syscall(sys_munlockall);
+cond_syscall(sys_mlock2);
cond_syscall(sys_mincore);
cond_syscall(sys_madvise);
cond_syscall(sys_mremap);
diff --git a/mm/mlock.c b/mm/mlock.c
index 5692ee5..3094f27 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -643,6 +643,14 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
return do_mlock(start, len, VM_LOCKED);
}
+SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
+{
+ if (flags)
+ return -EINVAL;
+
+ return do_mlock(start, len, VM_LOCKED);
+}
+
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 3/6] mm: Introduce VM_LOCKONFAULT
2015-08-26 18:24 [PATCH v8 0/6] Allow user to request memory to be locked on page fault Eric B Munson
2015-08-26 18:24 ` [PATCH v8 2/6] mm: mlock: Add new mlock system call Eric B Munson
@ 2015-08-26 18:24 ` Eric B Munson
[not found] ` <1440613465-30393-4-git-send-email-emunson-JqFfY2XvxFXQT0dZR+AlfA@public.gmane.org>
2015-08-26 18:24 ` [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage Eric B Munson
` (2 subsequent siblings)
4 siblings, 1 reply; 13+ messages in thread
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Michal Hocko, Vlastimil Babka, Jonathan Corbet,
Kirill A. Shutemov, linux-kernel, linux-mm, linux-api
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. The VM_LOCKONFAULT flag will be used together with
VM_LOCKED and has no effect when set without VM_LOCKED. Setting the
VM_LOCKONFAULT flag for a VMA will cause pages faulted into that VMA to
be added to the unevictable LRU when they are faulted or if they are
already present, but will not cause any missing pages to be faulted in.
Exposing this new lock state means that we cannot overload the meaning
of the FOLL_POPULATE flag any longer. Prior to this patch it was used
to mean that the VMA for a fault was locked. This means we need the
new FOLL_MLOCK flag to communicate the locked state of a VMA.
FOLL_POPULATE will now only control if the VMA should be populated and
in the case of VM_LOCKONFAULT, it will not be set.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-api@vger.kernel.org
---
Changes from v7:
*Drop entries in smaps and dri code to avoid exposing VM_LOCKONFAULT to
userspace. VM_LOCKONFAULT is still exposed via mm/debug.c
*Create VM_LOCKED_CLEAR_MASK to be used anywhere we want to clear all
flags relating to locked VMAs
include/linux/mm.h | 5 +++++
kernel/fork.c | 2 +-
mm/debug.c | 1 +
mm/gup.c | 10 ++++++++--
mm/huge_memory.c | 2 +-
mm/hugetlb.c | 4 ++--
mm/mlock.c | 2 +-
mm/mmap.c | 2 +-
mm/rmap.c | 6 ++++--
9 files changed, 24 insertions(+), 10 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bf6f117..47ff851 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -136,6 +136,7 @@ extern unsigned int kobjsize(const void *objp);
#define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */
#define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */
+#define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */
#define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */
#define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */
#define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */
@@ -199,6 +200,9 @@ extern unsigned int kobjsize(const void *objp);
/* This mask defines which mm->def_flags a process can inherit its parent */
#define VM_INIT_DEF_MASK VM_NOHUGEPAGE
+/* This mask is used to clear all the VMA flags used by mlock */
+#define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT))
+
/*
* mapping from the currently active vm_flags protection bits (the
* low four bits) to a page protection mask..
@@ -2071,6 +2075,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
#define FOLL_NUMA 0x200 /* force NUMA hinting page fault */
#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */
#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */
+#define FOLL_MLOCK 0x1000 /* lock present pages */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff --git a/kernel/fork.c b/kernel/fork.c
index dbd9b8d..eee1cc5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -454,7 +454,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
tmp->vm_mm = mm;
if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
- tmp->vm_flags &= ~VM_LOCKED;
+ tmp->vm_flags &= VM_LOCKED_CLEAR_MASK;
tmp->vm_next = tmp->vm_prev = NULL;
file = tmp->vm_file;
if (file) {
diff --git a/mm/debug.c b/mm/debug.c
index 76089dd..25176bb 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -121,6 +121,7 @@ static const struct trace_print_flags vmaflags_names[] = {
{VM_GROWSDOWN, "growsdown" },
{VM_PFNMAP, "pfnmap" },
{VM_DENYWRITE, "denywrite" },
+ {VM_LOCKONFAULT, "lockonfault" },
{VM_LOCKED, "locked" },
{VM_IO, "io" },
{VM_SEQ_READ, "seqread" },
diff --git a/mm/gup.c b/mm/gup.c
index 6297f6b..dce6ccd 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -92,7 +92,7 @@ retry:
*/
mark_page_accessed(page);
}
- if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) {
+ if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
/*
* The preliminary mapping check is mainly to avoid the
* pointless overhead of lock_page on the ZERO_PAGE
@@ -265,6 +265,9 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
unsigned int fault_flags = 0;
int ret;
+ /* mlock all present pages, but do not fault in new pages */
+ if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK)
+ return -ENOENT;
/* For mm_populate(), just skip the stack guard page. */
if ((*flags & FOLL_POPULATE) &&
(stack_guard_page_start(vma, address) ||
@@ -850,7 +853,10 @@ long populate_vma_page_range(struct vm_area_struct *vma,
VM_BUG_ON_VMA(end > vma->vm_end, vma);
VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
- gup_flags = FOLL_TOUCH | FOLL_POPULATE;
+ gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
+ if (vma->vm_flags & VM_LOCKONFAULT)
+ gup_flags &= ~FOLL_POPULATE;
+
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 097c7a4..cba783e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1238,7 +1238,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
pmd, _pmd, 1))
update_mmu_cache_pmd(vma, addr, pmd);
}
- if ((flags & FOLL_POPULATE) && (vma->vm_flags & VM_LOCKED)) {
+ if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
if (page->mapping && trylock_page(page)) {
lru_add_drain();
if (page->mapping)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a8c3087..a01ccc3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3764,8 +3764,8 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
unsigned long s_end = sbase + PUD_SIZE;
/* Allow segments to share if only one is marked locked */
- unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
- unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+ unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+ unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK;
/*
* match the virtual addresses, permission and the alignment of the
diff --git a/mm/mlock.c b/mm/mlock.c
index 3094f27..7efe27d 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -422,7 +422,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- vma->vm_flags &= ~VM_LOCKED;
+ vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
while (start < end) {
struct page *page = NULL;
diff --git a/mm/mmap.c b/mm/mmap.c
index aa632ad..019dcd6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1651,7 +1651,7 @@ out:
vma == get_gate_vma(current->mm)))
mm->locked_vm += (len >> PAGE_SHIFT);
else
- vma->vm_flags &= ~VM_LOCKED;
+ vma->vm_flags &= VM_LOCKED_CLEAR_MASK;
}
if (file)
diff --git a/mm/rmap.c b/mm/rmap.c
index 171b687..14ce002 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -744,7 +744,8 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
if (vma->vm_flags & VM_LOCKED) {
spin_unlock(ptl);
- pra->vm_flags |= VM_LOCKED;
+ pra->vm_flags |=
+ (vma->vm_flags & (VM_LOCKED | VM_LOCKONFAULT));
return SWAP_FAIL; /* To break the loop */
}
@@ -765,7 +766,8 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
if (vma->vm_flags & VM_LOCKED) {
pte_unmap_unlock(pte, ptl);
- pra->vm_flags |= VM_LOCKED;
+ pra->vm_flags |=
+ (vma->vm_flags & (VM_LOCKED | VM_LOCKONFAULT));
return SWAP_FAIL; /* To break the loop */
}
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage
2015-08-26 18:24 [PATCH v8 0/6] Allow user to request memory to be locked on page fault Eric B Munson
2015-08-26 18:24 ` [PATCH v8 2/6] mm: mlock: Add new mlock system call Eric B Munson
2015-08-26 18:24 ` [PATCH v8 3/6] mm: Introduce VM_LOCKONFAULT Eric B Munson
@ 2015-08-26 18:24 ` Eric B Munson
2015-08-28 14:31 ` Michal Hocko
2015-08-26 18:24 ` [PATCH v8 5/6] selftests: vm: Add tests for lock on fault Eric B Munson
2015-08-26 18:24 ` [PATCH v8 6/6] mips: Add entry for new mlock2 syscall Eric B Munson
4 siblings, 1 reply; 13+ messages in thread
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Michal Hocko, Vlastimil Babka, Jonathan Corbet,
Kirill A. Shutemov, linux-alpha, linux-kernel, linux-mips,
linux-parisc, linuxppc-dev, sparclinux, linux-xtensa, linux-arch,
linux-api, linux-mm
The previous patch introduced a flag that specified pages in a VMA
should be placed on the unevictable LRU, but they should not be made
present when the area is created. This patch adds the ability to set
this state via the new mlock system calls.
We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall.
MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED.
MCL_ONFAULT should be used as a modifier to the two other mlockall
flags. When used with MCL_CURRENT, all current mappings will be marked
with VM_LOCKED | VM_LOCKONFAULT. When used with MCL_FUTURE, the
mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT. When used
with both MCL_CURRENT and MCL_FUTURE, all current mappings and
mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT.
Prior to this patch, mlockall() will unconditionally clear the
mm->def_flags any time it is called without MCL_FUTURE. This behavior
is maintained after adding MCL_ONFAULT. If a call to
mlockall(MCL_FUTURE) is followed by mlockall(MCL_CURRENT), the
mm->def_flags will be cleared and new VMAs will be unlocked. This
remains true with or without MCL_ONFAULT in either mlockall()
invocation.
munlock() will unconditionally clear both vma flags. munlockall()
unconditionally clears for VMA flags on all VMAs and in the
mm->def_flags field.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
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-arch@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: linux-mm@kvack.org
---
arch/alpha/include/uapi/asm/mman.h | 3 ++
arch/mips/include/uapi/asm/mman.h | 6 ++++
arch/parisc/include/uapi/asm/mman.h | 3 ++
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 | 6 ++++
include/uapi/asm-generic/mman-common.h | 5 ++++
include/uapi/asm-generic/mman.h | 1 +
mm/mlock.c | 52 +++++++++++++++++++++++++---------
10 files changed, 66 insertions(+), 13 deletions(-)
diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
index 0086b47..f2f9496 100644
--- a/arch/alpha/include/uapi/asm/mman.h
+++ b/arch/alpha/include/uapi/asm/mman.h
@@ -37,6 +37,9 @@
#define MCL_CURRENT 8192 /* lock all currently mapped pages */
#define MCL_FUTURE 16384 /* lock all additions to address space */
+#define MCL_ONFAULT 32768 /* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
index cfcb876..97c03f4 100644
--- a/arch/mips/include/uapi/asm/mman.h
+++ b/arch/mips/include/uapi/asm/mman.h
@@ -61,6 +61,12 @@
*/
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index 294d251..ecc3ae1 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -31,6 +31,9 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 6ea26df..03c06ba 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -22,6 +22,7 @@
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
+#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h
index 0b14df3..9765896 100644
--- a/arch/sparc/include/uapi/asm/mman.h
+++ b/arch/sparc/include/uapi/asm/mman.h
@@ -17,6 +17,7 @@
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
+#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
#define MAP_NONBLOCK 0x10000 /* do not block on IO */
diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h
index 81b8fc3..63ee13f 100644
--- a/arch/tile/include/uapi/asm/mman.h
+++ b/arch/tile/include/uapi/asm/mman.h
@@ -36,6 +36,7 @@
*/
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
#endif /* _ASM_TILE_MMAN_H */
diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
index 201aec0..360944e 100644
--- a/arch/xtensa/include/uapi/asm/mman.h
+++ b/arch/xtensa/include/uapi/asm/mman.h
@@ -74,6 +74,12 @@
*/
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
+
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36..a74dd84 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -25,6 +25,11 @@
# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
#endif
+/*
+ * Flags for mlock
+ */
+#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
+
#define MS_ASYNC 1 /* sync memory asynchronously */
#define MS_INVALIDATE 2 /* invalidate the caches */
#define MS_SYNC 4 /* synchronous memory sync */
diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
index e9fe6fd..7162cd4 100644
--- a/include/uapi/asm-generic/mman.h
+++ b/include/uapi/asm-generic/mman.h
@@ -17,5 +17,6 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
#endif /* __ASM_GENERIC_MMAN_H */
diff --git a/mm/mlock.c b/mm/mlock.c
index 7efe27d..0747663 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
- goto out; /* don't set VM_LOCKED, don't count */
+ /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
+ goto out;
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
@@ -576,7 +577,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
prev = vma;
for (nstart = start ; ; ) {
- vm_flags_t newflags = vma->vm_flags & ~VM_LOCKED;
+ vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
newflags |= flags;
@@ -645,10 +646,15 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
{
- if (flags)
+ vm_flags_t vm_flags = VM_LOCKED;
+
+ if (flags & ~MLOCK_ONFAULT)
return -EINVAL;
- return do_mlock(start, len, VM_LOCKED);
+ if (flags & MLOCK_ONFAULT)
+ vm_flags |= VM_LOCKONFAULT;
+
+ return do_mlock(start, len, vm_flags);
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
@@ -665,24 +671,43 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
return ret;
}
+/*
+ * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
+ * and translate into the appropriate modifications to mm->def_flags and/or the
+ * flags for all current VMAs.
+ *
+ * There are a couple of subtleties with this. If mlockall() is called multiple
+ * times with different flags, the values do not necessarily stack. If mlockall
+ * is called once including the MCL_FUTURE flag and then a second time without
+ * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
+ */
static int apply_mlockall_flags(int flags)
{
struct vm_area_struct * vma, * prev = NULL;
+ vm_flags_t to_add = 0;
- if (flags & MCL_FUTURE)
+ current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
+ if (flags & MCL_FUTURE) {
current->mm->def_flags |= VM_LOCKED;
- else
- current->mm->def_flags &= ~VM_LOCKED;
- if (flags == MCL_FUTURE)
- goto out;
+ if (flags & MCL_ONFAULT)
+ current->mm->def_flags |= VM_LOCKONFAULT;
+
+ if (!(flags & MCL_CURRENT))
+ goto out;
+ }
+
+ if (flags & MCL_CURRENT) {
+ to_add |= VM_LOCKED;
+ if (flags & MCL_ONFAULT)
+ to_add |= VM_LOCKONFAULT;
+ }
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
vm_flags_t newflags;
- newflags = vma->vm_flags & ~VM_LOCKED;
- if (flags & MCL_CURRENT)
- newflags |= VM_LOCKED;
+ newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+ newflags |= to_add;
/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
@@ -697,7 +722,8 @@ SYSCALL_DEFINE1(mlockall, int, flags)
unsigned long lock_limit;
int ret = -EINVAL;
- if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
+ if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
+ flags == MCL_ONFAULT)
goto out;
ret = -EPERM;
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 13+ messages in thread* Re: [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage
2015-08-26 18:24 ` [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage Eric B Munson
@ 2015-08-28 14:31 ` Michal Hocko
2015-08-28 14:32 ` Michal Hocko
0 siblings, 1 reply; 13+ messages in thread
From: Michal Hocko @ 2015-08-28 14:31 UTC (permalink / raw)
To: Eric B Munson
Cc: Andrew Morton, Vlastimil Babka, Jonathan Corbet,
Kirill A. Shutemov, linux-alpha, linux-kernel, linux-mips,
linux-parisc, linuxppc-dev, sparclinux, linux-xtensa, linux-arch,
linux-api, linux-mm
On Wed 26-08-15 14:24:23, Eric B Munson wrote:
> The previous patch introduced a flag that specified pages in a VMA
> should be placed on the unevictable LRU, but they should not be made
> present when the area is created. This patch adds the ability to set
> this state via the new mlock system calls.
>
> We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall.
> MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED.
> MCL_ONFAULT should be used as a modifier to the two other mlockall
> flags. When used with MCL_CURRENT, all current mappings will be marked
> with VM_LOCKED | VM_LOCKONFAULT. When used with MCL_FUTURE, the
> mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT. When used
> with both MCL_CURRENT and MCL_FUTURE, all current mappings and
> mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT.
>
> Prior to this patch, mlockall() will unconditionally clear the
> mm->def_flags any time it is called without MCL_FUTURE. This behavior
> is maintained after adding MCL_ONFAULT. If a call to
> mlockall(MCL_FUTURE) is followed by mlockall(MCL_CURRENT), the
> mm->def_flags will be cleared and new VMAs will be unlocked. This
> remains true with or without MCL_ONFAULT in either mlockall()
> invocation.
>
> munlock() will unconditionally clear both vma flags. munlockall()
> unconditionally clears for VMA flags on all VMAs and in the
> mm->def_flags field.
>
> Signed-off-by: Eric B Munson <emunson@akamai.com>
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
> Cc: Michal Hocko <mhocko@suse.cz>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Jonathan Corbet <corbet@lwn.net>
> Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
> 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-arch@vger.kernel.org
> Cc: linux-api@vger.kernel.org
> Cc: linux-mm@kvack.org
I haven't checked the arch specific bits but the core part looks good to
me.
Acked-by: Michal Hocko <mhocko@suse.com>
> ---
> arch/alpha/include/uapi/asm/mman.h | 3 ++
> arch/mips/include/uapi/asm/mman.h | 6 ++++
> arch/parisc/include/uapi/asm/mman.h | 3 ++
> 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 | 6 ++++
> include/uapi/asm-generic/mman-common.h | 5 ++++
> include/uapi/asm-generic/mman.h | 1 +
> mm/mlock.c | 52 +++++++++++++++++++++++++---------
> 10 files changed, 66 insertions(+), 13 deletions(-)
>
> diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h
> index 0086b47..f2f9496 100644
> --- a/arch/alpha/include/uapi/asm/mman.h
> +++ b/arch/alpha/include/uapi/asm/mman.h
> @@ -37,6 +37,9 @@
>
> #define MCL_CURRENT 8192 /* lock all currently mapped pages */
> #define MCL_FUTURE 16384 /* lock all additions to address space */
> +#define MCL_ONFAULT 32768 /* lock all pages that are faulted in */
> +
> +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
>
> #define MADV_NORMAL 0 /* no further special treatment */
> #define MADV_RANDOM 1 /* expect random page references */
> diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h
> index cfcb876..97c03f4 100644
> --- a/arch/mips/include/uapi/asm/mman.h
> +++ b/arch/mips/include/uapi/asm/mman.h
> @@ -61,6 +61,12 @@
> */
> #define MCL_CURRENT 1 /* lock all current mappings */
> #define MCL_FUTURE 2 /* lock all future mappings */
> +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
> +
> +/*
> + * Flags for mlock
> + */
> +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
>
> #define MADV_NORMAL 0 /* no further special treatment */
> #define MADV_RANDOM 1 /* expect random page references */
> diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
> index 294d251..ecc3ae1 100644
> --- a/arch/parisc/include/uapi/asm/mman.h
> +++ b/arch/parisc/include/uapi/asm/mman.h
> @@ -31,6 +31,9 @@
>
> #define MCL_CURRENT 1 /* lock all current mappings */
> #define MCL_FUTURE 2 /* lock all future mappings */
> +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
> +
> +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
>
> #define MADV_NORMAL 0 /* no further special treatment */
> #define MADV_RANDOM 1 /* expect random page references */
> diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
> index 6ea26df..03c06ba 100644
> --- a/arch/powerpc/include/uapi/asm/mman.h
> +++ b/arch/powerpc/include/uapi/asm/mman.h
> @@ -22,6 +22,7 @@
>
> #define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
> #define MCL_FUTURE 0x4000 /* lock all additions to address space */
> +#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */
>
> #define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
> #define MAP_NONBLOCK 0x10000 /* do not block on IO */
> diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h
> index 0b14df3..9765896 100644
> --- a/arch/sparc/include/uapi/asm/mman.h
> +++ b/arch/sparc/include/uapi/asm/mman.h
> @@ -17,6 +17,7 @@
>
> #define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
> #define MCL_FUTURE 0x4000 /* lock all additions to address space */
> +#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */
>
> #define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
> #define MAP_NONBLOCK 0x10000 /* do not block on IO */
> diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h
> index 81b8fc3..63ee13f 100644
> --- a/arch/tile/include/uapi/asm/mman.h
> +++ b/arch/tile/include/uapi/asm/mman.h
> @@ -36,6 +36,7 @@
> */
> #define MCL_CURRENT 1 /* lock all current mappings */
> #define MCL_FUTURE 2 /* lock all future mappings */
> +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
>
>
> #endif /* _ASM_TILE_MMAN_H */
> diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h
> index 201aec0..360944e 100644
> --- a/arch/xtensa/include/uapi/asm/mman.h
> +++ b/arch/xtensa/include/uapi/asm/mman.h
> @@ -74,6 +74,12 @@
> */
> #define MCL_CURRENT 1 /* lock all current mappings */
> #define MCL_FUTURE 2 /* lock all future mappings */
> +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
> +
> +/*
> + * Flags for mlock
> + */
> +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
>
> #define MADV_NORMAL 0 /* no further special treatment */
> #define MADV_RANDOM 1 /* expect random page references */
> diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
> index ddc3b36..a74dd84 100644
> --- a/include/uapi/asm-generic/mman-common.h
> +++ b/include/uapi/asm-generic/mman-common.h
> @@ -25,6 +25,11 @@
> # define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
> #endif
>
> +/*
> + * Flags for mlock
> + */
> +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */
> +
> #define MS_ASYNC 1 /* sync memory asynchronously */
> #define MS_INVALIDATE 2 /* invalidate the caches */
> #define MS_SYNC 4 /* synchronous memory sync */
> diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h
> index e9fe6fd..7162cd4 100644
> --- a/include/uapi/asm-generic/mman.h
> +++ b/include/uapi/asm-generic/mman.h
> @@ -17,5 +17,6 @@
>
> #define MCL_CURRENT 1 /* lock all current mappings */
> #define MCL_FUTURE 2 /* lock all future mappings */
> +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */
>
> #endif /* __ASM_GENERIC_MMAN_H */
> diff --git a/mm/mlock.c b/mm/mlock.c
> index 7efe27d..0747663 100644
> --- a/mm/mlock.c
> +++ b/mm/mlock.c
> @@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
>
> if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
> is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
> - goto out; /* don't set VM_LOCKED, don't count */
> + /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
> + goto out;
>
> pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
> *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
> @@ -576,7 +577,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len,
> prev = vma;
>
> for (nstart = start ; ; ) {
> - vm_flags_t newflags = vma->vm_flags & ~VM_LOCKED;
> + vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
>
> newflags |= flags;
>
> @@ -645,10 +646,15 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
>
> SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
> {
> - if (flags)
> + vm_flags_t vm_flags = VM_LOCKED;
> +
> + if (flags & ~MLOCK_ONFAULT)
> return -EINVAL;
>
> - return do_mlock(start, len, VM_LOCKED);
> + if (flags & MLOCK_ONFAULT)
> + vm_flags |= VM_LOCKONFAULT;
> +
> + return do_mlock(start, len, vm_flags);
> }
>
> SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
> @@ -665,24 +671,43 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
> return ret;
> }
>
> +/*
> + * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
> + * and translate into the appropriate modifications to mm->def_flags and/or the
> + * flags for all current VMAs.
> + *
> + * There are a couple of subtleties with this. If mlockall() is called multiple
> + * times with different flags, the values do not necessarily stack. If mlockall
> + * is called once including the MCL_FUTURE flag and then a second time without
> + * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
> + */
> static int apply_mlockall_flags(int flags)
> {
> struct vm_area_struct * vma, * prev = NULL;
> + vm_flags_t to_add = 0;
>
> - if (flags & MCL_FUTURE)
> + current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
> + if (flags & MCL_FUTURE) {
> current->mm->def_flags |= VM_LOCKED;
> - else
> - current->mm->def_flags &= ~VM_LOCKED;
>
> - if (flags == MCL_FUTURE)
> - goto out;
> + if (flags & MCL_ONFAULT)
> + current->mm->def_flags |= VM_LOCKONFAULT;
> +
> + if (!(flags & MCL_CURRENT))
> + goto out;
> + }
> +
> + if (flags & MCL_CURRENT) {
> + to_add |= VM_LOCKED;
> + if (flags & MCL_ONFAULT)
> + to_add |= VM_LOCKONFAULT;
> + }
>
> for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
> vm_flags_t newflags;
>
> - newflags = vma->vm_flags & ~VM_LOCKED;
> - if (flags & MCL_CURRENT)
> - newflags |= VM_LOCKED;
> + newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
> + newflags |= to_add;
>
> /* Ignore errors */
> mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
> @@ -697,7 +722,8 @@ SYSCALL_DEFINE1(mlockall, int, flags)
> unsigned long lock_limit;
> int ret = -EINVAL;
>
> - if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
> + if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
> + flags == MCL_ONFAULT)
> goto out;
>
> ret = -EPERM;
> --
> 1.9.1
--
Michal Hocko
SUSE Labs
^ permalink raw reply [flat|nested] 13+ messages in thread* Re: [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage
2015-08-28 14:31 ` Michal Hocko
@ 2015-08-28 14:32 ` Michal Hocko
0 siblings, 0 replies; 13+ messages in thread
From: Michal Hocko @ 2015-08-28 14:32 UTC (permalink / raw)
To: Eric B Munson
Cc: Andrew Morton, Vlastimil Babka, Jonathan Corbet,
Kirill A. Shutemov, linux-alpha, linux-kernel, linux-mips,
linux-parisc, linuxppc-dev, sparclinux, linux-xtensa, linux-arch,
linux-api, linux-mm
On Fri 28-08-15 16:31:30, Michal Hocko wrote:
> On Wed 26-08-15 14:24:23, Eric B Munson wrote:
> > The previous patch introduced a flag that specified pages in a VMA
> > should be placed on the unevictable LRU, but they should not be made
> > present when the area is created. This patch adds the ability to set
> > this state via the new mlock system calls.
> >
> > We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall.
> > MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED.
> > MCL_ONFAULT should be used as a modifier to the two other mlockall
> > flags. When used with MCL_CURRENT, all current mappings will be marked
> > with VM_LOCKED | VM_LOCKONFAULT. When used with MCL_FUTURE, the
> > mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT. When used
> > with both MCL_CURRENT and MCL_FUTURE, all current mappings and
> > mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT.
> >
> > Prior to this patch, mlockall() will unconditionally clear the
> > mm->def_flags any time it is called without MCL_FUTURE. This behavior
> > is maintained after adding MCL_ONFAULT. If a call to
> > mlockall(MCL_FUTURE) is followed by mlockall(MCL_CURRENT), the
> > mm->def_flags will be cleared and new VMAs will be unlocked. This
> > remains true with or without MCL_ONFAULT in either mlockall()
> > invocation.
Btw. I think we really want a man page for this new mlock call.
--
Michal Hocko
SUSE Labs
^ permalink raw reply [flat|nested] 13+ messages in thread
* [PATCH v8 5/6] selftests: vm: Add tests for lock on fault
2015-08-26 18:24 [PATCH v8 0/6] Allow user to request memory to be locked on page fault Eric B Munson
` (2 preceding siblings ...)
2015-08-26 18:24 ` [PATCH v8 4/6] mm: mlock: Add mlock flags to enable VM_LOCKONFAULT usage Eric B Munson
@ 2015-08-26 18:24 ` Eric B Munson
2015-08-26 18:24 ` [PATCH v8 6/6] mips: Add entry for new mlock2 syscall Eric B Munson
4 siblings, 0 replies; 13+ messages in thread
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Thierry Reding, Shuah Khan, Michal Hocko,
Vlastimil Babka, Jonathan Corbet, linux-mm, linux-kernel,
linux-api
Test the mmap() flag, and the mlockall() flag. These tests ensure that
pages are not faulted in until they are accessed, that the pages are
unevictable once faulted in, and that VMA splitting and merging works
with the new VM flag. The second test ensures that mlock limits are
respected. Note that the limit test needs to be run a normal user.
Also add tests to use the new mlock2 family of system calls.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-api@vger.kernel.org
---
Changes from v7:
*Incorporate Thierry Reding's fixes
*Rework the lock on fault tests to use Rss vs size to identify lock on
fault regions now that the vma flag is not shown to user space
tools/testing/selftests/vm/Makefile | 2 +
tools/testing/selftests/vm/mlock2-tests.c | 737 ++++++++++++++++++++++++++++
tools/testing/selftests/vm/on-fault-limit.c | 47 ++
tools/testing/selftests/vm/run_vmtests | 22 +
4 files changed, 808 insertions(+)
create mode 100644 tools/testing/selftests/vm/mlock2-tests.c
create mode 100644 tools/testing/selftests/vm/on-fault-limit.c
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 231b9a0..71a4e9f 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -6,6 +6,8 @@ BINARIES += hugepage-mmap
BINARIES += hugepage-shm
BINARIES += hugetlbfstest
BINARIES += map_hugetlb
+BINARIES += mlock2-tests
+BINARIES += on-fault-limit
BINARIES += thuge-gen
BINARIES += transhuge-stress
diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c
new file mode 100644
index 0000000..909802e
--- /dev/null
+++ b/tools/testing/selftests/vm/mlock2-tests.c
@@ -0,0 +1,737 @@
+#include <sys/mman.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <syscall.h>
+#include <errno.h>
+#include <stdbool.h>
+
+#ifndef MLOCK_ONFAULT
+#define MLOCK_ONFAULT 1
+#endif
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int mlock2_(void *start, size_t len, int flags)
+{
+#ifdef __NR_mlock2
+ return syscall(__NR_mlock2, start, len, flags);
+#else
+ errno = ENOSYS;
+ return -1;
+#endif
+}
+
+struct vm_boundaries {
+ unsigned long start;
+ unsigned long end;
+};
+
+static int get_vm_area(unsigned long addr, struct vm_boundaries *area)
+{
+ FILE *file;
+ int ret = 1;
+ char line[1024] = {0};
+ char *end_addr;
+ char *stop;
+ unsigned long start;
+ unsigned long end;
+
+ if (!area)
+ return ret;
+
+ file = fopen("/proc/self/maps", "r");
+ if (!file) {
+ perror("fopen");
+ return ret;
+ }
+
+ memset(area, 0, sizeof(struct vm_boundaries));
+
+ while(fgets(line, 1024, file)) {
+ end_addr = strchr(line, '-');
+ if (!end_addr) {
+ printf("cannot parse /proc/self/maps\n");
+ goto out;
+ }
+ *end_addr = '\0';
+ end_addr++;
+ stop = strchr(end_addr, ' ');
+ if (!stop) {
+ printf("cannot parse /proc/self/maps\n");
+ goto out;
+ }
+ stop = '\0';
+
+ sscanf(line, "%lx", &start);
+ sscanf(end_addr, "%lx", &end);
+
+ if (start <= addr && end > addr) {
+ area->start = start;
+ area->end = end;
+ ret = 0;
+ goto out;
+ }
+ }
+out:
+ fclose(file);
+ return ret;
+}
+
+static uint64_t get_pageflags(unsigned long addr)
+{
+ FILE *file;
+ uint64_t pfn;
+ unsigned long offset;
+
+ file = fopen("/proc/self/pagemap", "r");
+ if (!file) {
+ perror("fopen pagemap");
+ _exit(1);
+ }
+
+ offset = addr / getpagesize() * sizeof(pfn);
+
+ if (fseek(file, offset, SEEK_SET)) {
+ perror("fseek pagemap");
+ _exit(1);
+ }
+
+ if (fread(&pfn, sizeof(pfn), 1, file) != 1) {
+ perror("fread pagemap");
+ _exit(1);
+ }
+
+ fclose(file);
+ return pfn;
+}
+
+static uint64_t get_kpageflags(unsigned long pfn)
+{
+ uint64_t flags;
+ FILE *file;
+
+ file = fopen("/proc/kpageflags", "r");
+ if (!file) {
+ perror("fopen kpageflags");
+ _exit(1);
+ }
+
+ if (fseek(file, pfn * sizeof(flags), SEEK_SET)) {
+ perror("fseek kpageflags");
+ _exit(1);
+ }
+
+ if (fread(&flags, sizeof(flags), 1, file) != 1) {
+ perror("fread kpageflags");
+ _exit(1);
+ }
+
+ fclose(file);
+ return flags;
+}
+
+static FILE *seek_to_smaps_entry(unsigned long addr)
+{
+ FILE *file;
+ char *line = NULL;
+ size_t size = 0;
+ unsigned long start, end;
+ char perms[5];
+ unsigned long offset;
+ char dev[32];
+ unsigned long inode;
+ char path[BUFSIZ];
+
+ file = fopen("/proc/self/smaps", "r");
+ if (!file) {
+ perror("fopen smaps");
+ _exit(1);
+ }
+
+ while (getline(&line, &size, file) > 0) {
+ if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n",
+ &start, &end, perms, &offset, dev, &inode, path) < 6)
+ goto next;
+
+ if (start <= addr && addr < end)
+ goto out;
+
+next:
+ free(line);
+ line = NULL;
+ size = 0;
+ }
+
+ fclose(file);
+ file = NULL;
+
+out:
+ free(line);
+ return file;
+}
+
+#define VMFLAGS "VmFlags:"
+
+static bool is_vmflag_set(unsigned long addr, const char *vmflag)
+{
+ char *line = NULL;
+ char *flags;
+ size_t size = 0;
+ bool ret = false;
+ FILE *smaps;
+
+ smaps = seek_to_smaps_entry(addr);
+ if (!smaps) {
+ printf("Unable to parse /proc/self/smaps\n");
+ goto out;
+ }
+
+ while (getline(&line, &size, smaps) > 0) {
+ if (!strstr(line, VMFLAGS)) {
+ free(line);
+ line = NULL;
+ size = 0;
+ continue;
+ }
+
+ flags = line + strlen(VMFLAGS);
+ ret = (strstr(flags, vmflag) != NULL);
+ goto out;
+ }
+
+out:
+ free(line);
+ fclose(smaps);
+ return ret;
+}
+
+#define SIZE "Size:"
+#define RSS "Rss:"
+#define LOCKED "lo"
+
+static bool is_vma_lock_on_fault(unsigned long addr)
+{
+ bool ret = false;
+ bool locked;
+ FILE *smaps = NULL;
+ unsigned long vma_size, vma_rss;
+ char *line = NULL;
+ char *value;
+ size_t size = 0;
+
+ locked = is_vmflag_set(addr, LOCKED);
+ if (!locked)
+ goto out;
+
+ smaps = seek_to_smaps_entry(addr);
+ if (!smaps) {
+ printf("Unable to parse /proc/self/smaps\n");
+ goto out;
+ }
+
+ while (getline(&line, &size, smaps) > 0) {
+ if (!strstr(line, SIZE)) {
+ free(line);
+ line = NULL;
+ size = 0;
+ continue;
+ }
+
+ value = line + strlen(SIZE);
+ if (sscanf(value, "%lu kB", &vma_size) < 1) {
+ printf("Unable to parse smaps entry for Size\n");
+ goto out;
+ }
+ break;
+ }
+
+ while (getline(&line, &size, smaps) > 0) {
+ if (!strstr(line, RSS)) {
+ free(line);
+ line = NULL;
+ size = 0;
+ continue;
+ }
+
+ value = line + strlen(RSS);
+ if (sscanf(value, "%lu kB", &vma_rss) < 1) {
+ printf("Unable to parse smaps entry for Rss\n");
+ goto out;
+ }
+ break;
+ }
+
+ ret = locked && (vma_rss < vma_size);
+out:
+ free(line);
+ if (smaps)
+ fclose(smaps);
+ return ret;
+}
+
+#define PRESENT_BIT 0x8000000000000000
+#define PFN_MASK 0x007FFFFFFFFFFFFF
+#define UNEVICTABLE_BIT (1UL << 18)
+
+static int lock_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+
+ /* Both pages should be present */
+ if (((page1_flags & PRESENT_BIT) == 0) ||
+ ((page2_flags & PRESENT_BIT) == 0)) {
+ printf("Failed to make both pages present\n");
+ return 1;
+ }
+
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+ page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+ /* Both pages should be unevictable */
+ if (((page1_flags & UNEVICTABLE_BIT) == 0) ||
+ ((page2_flags & UNEVICTABLE_BIT) == 0)) {
+ printf("Failed to make both pages unevictable\n");
+ return 1;
+ }
+
+ if (!is_vmflag_set((unsigned long)map, LOCKED)) {
+ printf("VMA flag %s is missing on page 1\n", LOCKED);
+ return 1;
+ }
+
+ if (!is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+ printf("VMA flag %s is missing on page 2\n", LOCKED);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int unlock_lock_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+ page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+ if ((page1_flags & UNEVICTABLE_BIT) || (page2_flags & UNEVICTABLE_BIT)) {
+ printf("A page is still marked unevictable after unlock\n");
+ return 1;
+ }
+
+ if (is_vmflag_set((unsigned long)map, LOCKED)) {
+ printf("VMA flag %s is present on page 1 after unlock\n", LOCKED);
+ return 1;
+ }
+
+ if (is_vmflag_set((unsigned long)map + page_size, LOCKED)) {
+ printf("VMA flag %s is present on page 2 after unlock\n", LOCKED);
+ return 1;
+ }
+
+ return 0;
+}
+
+static int test_mlock_lock()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("test_mlock_locked mmap");
+ goto out;
+ }
+
+ if (mlock2_(map, 2 * page_size, 0)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock2(0)");
+ goto unmap;
+ }
+
+ if (lock_check(map))
+ goto unmap;
+
+ /* Now unlock and recheck attributes */
+ if (munlock(map, 2 * page_size)) {
+ perror("munlock()");
+ goto unmap;
+ }
+
+ ret = unlock_lock_check(map);
+
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ return ret;
+}
+
+static int onfault_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+
+ /* Neither page should be present */
+ if ((page1_flags & PRESENT_BIT) || (page2_flags & PRESENT_BIT)) {
+ printf("Pages were made present by MLOCK_ONFAULT\n");
+ return 1;
+ }
+
+ *map = 'a';
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+
+ /* Only page 1 should be present */
+ if ((page1_flags & PRESENT_BIT) == 0) {
+ printf("Page 1 is not present after fault\n");
+ return 1;
+ } else if (page2_flags & PRESENT_BIT) {
+ printf("Page 2 was made present\n");
+ return 1;
+ }
+
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+ /* Page 1 should be unevictable */
+ if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+ printf("Failed to make faulted page unevictable\n");
+ return 1;
+ }
+
+ if (!is_vma_lock_on_fault((unsigned long)map)) {
+ printf("VMA is not marked for lock on fault\n");
+ return 1;
+ }
+
+ if (!is_vma_lock_on_fault((unsigned long)map + page_size)) {
+ printf("VMA is not marked for lock on fault\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+static int unlock_onfault_check(char *map)
+{
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags;
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+
+ if (page1_flags & UNEVICTABLE_BIT) {
+ printf("Page 1 is still marked unevictable after unlock\n");
+ return 1;
+ }
+
+ if (is_vma_lock_on_fault((unsigned long)map) ||
+ is_vma_lock_on_fault((unsigned long)map + page_size)) {
+ printf("VMA is still lock on fault after unlock\n");
+ return 1;
+ }
+
+ return 0;
+}
+
+static int test_mlock_onfault()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("test_mlock_locked mmap");
+ goto out;
+ }
+
+ if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock2(MLOCK_ONFAULT)");
+ goto unmap;
+ }
+
+ if (onfault_check(map))
+ goto unmap;
+
+ /* Now unlock and recheck attributes */
+ if (munlock(map, 2 * page_size)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("munlock()");
+ goto unmap;
+ }
+
+ ret = unlock_onfault_check(map);
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ return ret;
+}
+
+static int test_lock_onfault_of_present()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+ uint64_t page1_flags, page2_flags;
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("test_mlock_locked mmap");
+ goto out;
+ }
+
+ *map = 'a';
+
+ if (mlock2_(map, 2 * page_size, MLOCK_ONFAULT)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock2(MLOCK_ONFAULT)");
+ goto unmap;
+ }
+
+ page1_flags = get_pageflags((unsigned long)map);
+ page2_flags = get_pageflags((unsigned long)map + page_size);
+ page1_flags = get_kpageflags(page1_flags & PFN_MASK);
+ page2_flags = get_kpageflags(page2_flags & PFN_MASK);
+
+ /* Page 1 should be unevictable */
+ if ((page1_flags & UNEVICTABLE_BIT) == 0) {
+ printf("Failed to make present page unevictable\n");
+ goto unmap;
+ }
+
+ if (!is_vma_lock_on_fault((unsigned long)map) ||
+ !is_vma_lock_on_fault((unsigned long)map + page_size)) {
+ printf("VMA with present pages is not marked lock on fault\n");
+ goto unmap;
+ }
+ ret = 0;
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ return ret;
+}
+
+static int test_munlockall()
+{
+ char *map;
+ int ret = 1;
+ unsigned long page_size = getpagesize();
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+ if (map == MAP_FAILED) {
+ perror("test_munlockall mmap");
+ goto out;
+ }
+
+ if (mlockall(MCL_CURRENT)) {
+ perror("mlockall(MCL_CURRENT)");
+ goto out;
+ }
+
+ if (lock_check(map))
+ goto unmap;
+
+ if (munlockall()) {
+ perror("munlockall()");
+ goto unmap;
+ }
+
+ if (unlock_lock_check(map))
+ goto unmap;
+
+ munmap(map, 2 * page_size);
+
+ map = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+
+ if (map == MAP_FAILED) {
+ perror("test_munlockall second mmap");
+ goto out;
+ }
+
+ if (mlockall(MCL_CURRENT | MCL_ONFAULT)) {
+ perror("mlockall(MCL_CURRENT | MCL_ONFAULT)");
+ goto unmap;
+ }
+
+ if (onfault_check(map))
+ goto unmap;
+
+ if (munlockall()) {
+ perror("munlockall()");
+ goto unmap;
+ }
+
+ if (unlock_onfault_check(map))
+ goto unmap;
+
+ if (mlockall(MCL_CURRENT | MCL_FUTURE)) {
+ perror("mlockall(MCL_CURRENT | MCL_FUTURE)");
+ goto out;
+ }
+
+ if (lock_check(map))
+ goto unmap;
+
+ if (munlockall()) {
+ perror("munlockall()");
+ goto unmap;
+ }
+
+ ret = unlock_lock_check(map);
+
+unmap:
+ munmap(map, 2 * page_size);
+out:
+ munlockall();
+ return ret;
+}
+
+static int test_vma_management(bool call_mlock)
+{
+ int ret = 1;
+ void *map;
+ unsigned long page_size = getpagesize();
+ struct vm_boundaries page1;
+ struct vm_boundaries page2;
+ struct vm_boundaries page3;
+
+ map = mmap(NULL, 3 * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
+ if (map == MAP_FAILED) {
+ perror("mmap()");
+ return ret;
+ }
+
+ if (call_mlock && mlock2_(map, 3 * page_size, MLOCK_ONFAULT)) {
+ if (errno == ENOSYS) {
+ printf("Cannot call new mlock family, skipping test\n");
+ _exit(0);
+ }
+ perror("mlock(ONFAULT)\n");
+ goto out;
+ }
+
+ if (get_vm_area((unsigned long)map, &page1) ||
+ get_vm_area((unsigned long)map + page_size, &page2) ||
+ get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+ printf("couldn't find mapping in /proc/self/maps\n");
+ goto out;
+ }
+
+ /*
+ * Before we unlock a portion, we need to that all three pages are in
+ * the same VMA. If they are not we abort this test (Note that this is
+ * not a failure)
+ */
+ if (page1.start != page2.start || page2.start != page3.start) {
+ printf("VMAs are not merged to start, aborting test\n");
+ ret = 0;
+ goto out;
+ }
+
+ if (munlock(map + page_size, page_size)) {
+ perror("munlock()");
+ goto out;
+ }
+
+ if (get_vm_area((unsigned long)map, &page1) ||
+ get_vm_area((unsigned long)map + page_size, &page2) ||
+ get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+ printf("couldn't find mapping in /proc/self/maps\n");
+ goto out;
+ }
+
+ /* All three VMAs should be different */
+ if (page1.start == page2.start || page2.start == page3.start) {
+ printf("failed to split VMA for munlock\n");
+ goto out;
+ }
+
+ /* Now unlock the first and third page and check the VMAs again */
+ if (munlock(map, page_size * 3)) {
+ perror("munlock()");
+ goto out;
+ }
+
+ if (get_vm_area((unsigned long)map, &page1) ||
+ get_vm_area((unsigned long)map + page_size, &page2) ||
+ get_vm_area((unsigned long)map + page_size * 2, &page3)) {
+ printf("couldn't find mapping in /proc/self/maps\n");
+ goto out;
+ }
+
+ /* Now all three VMAs should be the same */
+ if (page1.start != page2.start || page2.start != page3.start) {
+ printf("failed to merge VMAs after munlock\n");
+ goto out;
+ }
+
+ ret = 0;
+out:
+ munmap(map, 3 * page_size);
+ return ret;
+}
+
+static int test_mlockall(int (test_function)(bool call_mlock))
+{
+ int ret = 1;
+
+ if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+ perror("mlockall");
+ return ret;
+ }
+
+ ret = test_function(false);
+ munlockall();
+ return ret;
+}
+
+int main(int argc, char **argv)
+{
+ int ret = 0;
+ ret += test_mlock_lock();
+ ret += test_mlock_onfault();
+ ret += test_munlockall();
+ ret += test_lock_onfault_of_present();
+ ret += test_vma_management(true);
+ ret += test_mlockall(test_vma_management);
+ return ret;
+}
+
diff --git a/tools/testing/selftests/vm/on-fault-limit.c b/tools/testing/selftests/vm/on-fault-limit.c
new file mode 100644
index 0000000..245accc
--- /dev/null
+++ b/tools/testing/selftests/vm/on-fault-limit.c
@@ -0,0 +1,47 @@
+#include <sys/mman.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+
+#ifndef MCL_ONFAULT
+#define MCL_ONFAULT (MCL_FUTURE << 1)
+#endif
+
+static int test_limit(void)
+{
+ int ret = 1;
+ struct rlimit lims;
+ void *map;
+
+ if (getrlimit(RLIMIT_MEMLOCK, &lims)) {
+ perror("getrlimit");
+ return ret;
+ }
+
+ if (mlockall(MCL_CURRENT | MCL_ONFAULT | MCL_FUTURE)) {
+ perror("mlockall");
+ return ret;
+ }
+
+ map = mmap(NULL, 2 * lims.rlim_max, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_POPULATE, 0, 0);
+ if (map != MAP_FAILED)
+ printf("mmap should have failed, but didn't\n");
+ else {
+ ret = 0;
+ munmap(map, 2 * lims.rlim_max);
+ }
+
+ munlockall();
+ return ret;
+}
+
+int main(int argc, char **argv)
+{
+ int ret = 0;
+
+ ret += test_limit();
+ return ret;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index 49ece11..877ca04a 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -102,4 +102,26 @@ else
echo "[PASS]"
fi
+echo "--------------------"
+echo "running on-fault-limit"
+echo "--------------------"
+sudo -u nobody ./on-fault-limit
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
+echo "--------------------"
+echo "running mlock2-tests"
+echo "--------------------"
+./mlock2-tests
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
exit $exitcode
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH v8 6/6] mips: Add entry for new mlock2 syscall
2015-08-26 18:24 [PATCH v8 0/6] Allow user to request memory to be locked on page fault Eric B Munson
` (3 preceding siblings ...)
2015-08-26 18:24 ` [PATCH v8 5/6] selftests: vm: Add tests for lock on fault Eric B Munson
@ 2015-08-26 18:24 ` Eric B Munson
4 siblings, 0 replies; 13+ messages in thread
From: Eric B Munson @ 2015-08-26 18:24 UTC (permalink / raw)
To: Andrew Morton
Cc: Eric B Munson, Ralf Baechle, linux-mips, linux-api, linux-arch,
linux-mm, linux-kernel
A previous commit introduced the new mlock2 syscall, add entries for the
MIPS architecture.
Signed-off-by: Eric B Munson <emunson@akamai.com>
Acked-by: Ralf Baechle <ralf@linux-mips.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
---
arch/mips/include/uapi/asm/unistd.h | 15 +++++++++------
arch/mips/kernel/scall32-o32.S | 1 +
arch/mips/kernel/scall64-64.S | 1 +
arch/mips/kernel/scall64-n32.S | 1 +
arch/mips/kernel/scall64-o32.S | 1 +
5 files changed, 13 insertions(+), 6 deletions(-)
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index c03088f..d0bdfaa 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -377,16 +377,17 @@
#define __NR_memfd_create (__NR_Linux + 354)
#define __NR_bpf (__NR_Linux + 355)
#define __NR_execveat (__NR_Linux + 356)
+#define __NR_mlock2 (__NR_Linux + 357)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 356
+#define __NR_Linux_syscalls 357
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 356
+#define __NR_O32_Linux_syscalls 357
#if _MIPS_SIM == _MIPS_SIM_ABI64
@@ -711,16 +712,17 @@
#define __NR_memfd_create (__NR_Linux + 314)
#define __NR_bpf (__NR_Linux + 315)
#define __NR_execveat (__NR_Linux + 316)
+#define __NR_mlock2 (__NR_Linux + 317)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 316
+#define __NR_Linux_syscalls 317
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 316
+#define __NR_64_Linux_syscalls 317
#if _MIPS_SIM == _MIPS_SIM_NABI32
@@ -1049,15 +1051,16 @@
#define __NR_memfd_create (__NR_Linux + 318)
#define __NR_bpf (__NR_Linux + 319)
#define __NR_execveat (__NR_Linux + 320)
+#define __NR_mlock2 (__NR_Linux + 321)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 320
+#define __NR_Linux_syscalls 321
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 320
+#define __NR_N32_Linux_syscalls 321
#endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 4cc1350..b0b377a 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -599,3 +599,4 @@ EXPORT(sys_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR sys_execveat
+ PTR sys_mlock2
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index a6f6b76..f12eb03 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -436,4 +436,5 @@ EXPORT(sys_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 5315 */
PTR sys_execveat
+ PTR sys_mlock2
.size sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 4b20106..ecdd65a 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -429,4 +429,5 @@ EXPORT(sysn32_call_table)
PTR sys_memfd_create
PTR sys_bpf
PTR compat_sys_execveat /* 6320 */
+ PTR sys_mlock2
.size sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f543ff4..7a8b2df 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -584,4 +584,5 @@ EXPORT(sys32_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR compat_sys_execveat
+ PTR sys_mlock2
.size sys32_call_table,.-sys32_call_table
--
1.9.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related [flat|nested] 13+ messages in thread