@@ -3,7 +3,7 @@
#include <uapi/asm/unistd.h>
-#define NR_SYSCALLS 514
+#define NR_SYSCALLS 517
#define __ARCH_WANT_OLD_READDIR
#define __ARCH_WANT_STAT64
@@ -38,6 +38,8 @@
#define MCL_CURRENT 8192 /* lock all currently mapped pages */
#define MCL_FUTURE 16384 /* lock all additions to address space */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
@@ -532,6 +532,9 @@ sys_call_table:
.quad sys_getrandom
.quad sys_memfd_create
.quad sys_execveat
+ .quad sys_mlock2
+ .quad sys_munlock2 /* 515 */
+ .quad sys_munlockall2
.size sys_call_table, . - sys_call_table
.type sys_call_table, @object
@@ -397,6 +397,9 @@
/* 385 */ CALL(sys_memfd_create)
CALL(sys_bpf)
CALL(sys_execveat)
+ CALL(sys_mlock2)
+ CALL(sys_munlock2)
+/* 400 */ CALL(sys_munlockall2)
#ifndef syscalls_counted
.equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
#define syscalls_counted
@@ -797,3 +797,9 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create)
__SYSCALL(__NR_bpf, sys_bpf)
#define __NR_execveat 387
__SYSCALL(__NR_execveat, compat_sys_execveat)
+#define __NR_mlock2 388
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_munlock2 389
+__SYSCALL(__NR_munlock2, sys_munlock2)
+#define __NR_munlockall2 390
+__SYSCALL(__NR_munlockall2, sys_munlockall2)
@@ -334,4 +334,7 @@ sys_call_table:
.long sys_memfd_create
.long sys_bpf
.long sys_execveat /* 320 */
+ .long sys_mlock2
+ .long sys_munlock2
+ .long sys_munlockall2
.long sys_ni_syscall /* r8 is saturated at nr_syscalls */
@@ -1704,6 +1704,9 @@ ENTRY(_sys_call_table)
.long _sys_memfd_create /* 390 */
.long _sys_bpf
.long _sys_execveat
+ .long _sys_mlock2
+ .long _sys_munlock2
+ .long _sys_munlockall2 /* 395 */
.rept NR_syscalls-(.-_sys_call_table)/4
.long _sys_ni_syscall
@@ -955,6 +955,9 @@ sys_call_table:
.long sys_process_vm_writev
.long sys_kcmp /* 350 */
.long sys_finit_module
+ .long sys_mlock2
+ .long sys_munlock2
+ .long sys_munlockall2
/*
* NOTE!! This doesn't have to be exact - we just have
@@ -875,6 +875,9 @@ sys_call_table:
.long sys_process_vm_writev
.long sys_kcmp /* 350 */
.long sys_finit_module
+ .long sys_mlock2
+ .long sys_munlock2
+ .long sys_munlockall2
/*
* NOTE!! This doesn't have to be exact - we just have
@@ -1515,5 +1515,8 @@ sys_call_table:
.long sys_rt_tgsigqueueinfo /* 335 */
.long sys_perf_event_open
.long sys_setns
+ .long sys_mlock2
+ .long sys_munlock2
+ .long sys_munlockall2 /* 340 */
syscall_table_size = (. - sys_call_table)
@@ -1768,5 +1768,8 @@ sys_call_table:
data8 sys_memfd_create // 1340
data8 sys_bpf
data8 sys_execveat
+ data8 sys_mlock2
+ data8 sys_munlock2
+ data8 sys_munlockall2 // 1345
.org sys_call_table + 8*NR_syscalls // guard against failures to increase NR_syscalls
@@ -76,6 +76,9 @@
#define sys_munlock sys_ni_syscall
#define sys_mlockall sys_ni_syscall
#define sys_munlockall sys_ni_syscall
+#define sys_mlock2 sys_ni_syscall
+#define sys_munlock2 sys_ni_syscall
+#define sys_munlockall2 sys_ni_syscall
#define sys_mremap sys_ni_syscall
#define sys_mincore sys_ni_syscall
#define sys_remap_file_pages sys_ni_syscall
@@ -325,3 +325,6 @@ ENTRY(sys_call_table)
.long sys_eventfd
.long sys_fallocate
.long sys_setns /* 325 */
+ .long sys_mlock2
+ .long sys_munlock2
+ .long sys_munlockall2
@@ -376,4 +376,7 @@ ENTRY(sys_call_table)
.long sys_memfd_create
.long sys_bpf
.long sys_execveat /* 355 */
+ .long sys_mlock2
+ .long sys_munlock2
+ .long sys_munlockall2
@@ -389,3 +389,6 @@ ENTRY(sys_call_table)
.long sys_memfd_create
.long sys_bpf
.long sys_execveat
+ .long sys_mlock2
+ .long sys_munlock2 /* 390 */
+ .long sys_munlockall2
@@ -62,6 +62,11 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+/*
+ * Flags for mlock
+ */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
@@ -582,3 +582,6 @@ EXPORT(sys_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR sys_execveat
+ PTR sys_mlock2
+ PTR sys_munlock2
+ PTR sys_munlockall2
@@ -436,4 +436,7 @@ EXPORT(sys_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 5315 */
PTR sys_execveat
+ PTR sys_mlock2
+ PTR sys_munlock2
+ PTR sys_munlockall2
.size sys_call_table,.-sys_call_table
@@ -429,4 +429,7 @@ EXPORT(sysn32_call_table)
PTR sys_memfd_create
PTR sys_bpf
PTR compat_sys_execveat /* 6320 */
+ PTR sys_mlock2
+ PTR sys_munlock2
+ PTR sys_munlockall2
.size sysn32_call_table,.-sysn32_call_table
@@ -567,4 +567,7 @@ EXPORT(sys32_call_table)
PTR sys_memfd_create
PTR sys_bpf /* 4355 */
PTR compat_sys_execveat
+ PTR sys_mlock2
+ PTR sys_munlock2
+ PTR sys_munlockall2
.size sys32_call_table,.-sys32_call_table
@@ -767,6 +767,9 @@ ENTRY(sys_call_table)
.long sys_perf_event_open
.long sys_recvmmsg
.long sys_setns
+ .long sys_mlock2 /* 340 */
+ .long sys_munlock2
+ .long sys_munlockall2
nr_syscalls=(.-sys_call_table)/4
@@ -32,6 +32,8 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
@@ -23,6 +23,8 @@
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
#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 */
@@ -363,3 +363,6 @@ SYSCALL(sys_bpf,compat_sys_bpf)
SYSCALL(sys_s390_pci_mmio_write,compat_sys_s390_pci_mmio_write)
SYSCALL(sys_s390_pci_mmio_read,compat_sys_s390_pci_mmio_read)
SYSCALL(sys_execveat,compat_sys_execveat)
+SYSCALL(sys_mlock2,compat_sys_mlock2) /* 355 */
+SYSCALL(sys_munlock2,compat_sys_munlock2)
+SYSCALL(sys_munlockall2,compat_sys_munlockall2)
@@ -386,3 +386,6 @@ ENTRY(sys_call_table)
.long sys_process_vm_writev
.long sys_kcmp
.long sys_finit_module
+ .long sys_mlock2
+ .long sys_munlock2 /* 370 */
+ .long sys_munlockall2
@@ -18,6 +18,8 @@
#define MCL_CURRENT 0x2000 /* lock all currently mapped pages */
#define MCL_FUTURE 0x4000 /* lock all additions to address space */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
#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 */
@@ -87,4 +87,4 @@ sys_call_table:
/*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
/*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
/*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/ .long sys_execveat
+/*350*/ .long sys_execveat, sys_mlock2, sys_munlock2, sys_munlockall2
@@ -88,7 +88,7 @@ sys_call_table32:
.word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev
/*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
.word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/ .word sys32_execveat
+/*350*/ .word sys32_execveat, sys_mlock2, sys_munlock2, sys_munlockall2
#endif /* CONFIG_COMPAT */
@@ -168,4 +168,4 @@ sys_call_table:
.word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev
/*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr
.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
-/*350*/ .word sys64_execveat
+/*350*/ .word sys64_execveat, sys_mlock2, sys_munlock2, sys_munlockall2
@@ -37,5 +37,10 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+/*
+ * Flags for mlock
+ */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#endif /* _ASM_TILE_MMAN_H */
@@ -365,3 +365,6 @@
356 i386 memfd_create sys_memfd_create
357 i386 bpf sys_bpf
358 i386 execveat sys_execveat stub32_execveat
+359 i386 mlock2 sys_mlock2
+360 i386 munlock2 sys_munlock2
+361 i386 munlockall2 sys_munlockall2
@@ -329,6 +329,9 @@
320 common kexec_file_load sys_kexec_file_load
321 common bpf sys_bpf
322 64 execveat stub_execveat
+323 common mlock2 sys_mlock2
+324 common munlock2 sys_munlock2
+325 common munlockall2 sys_munlockall2
#
# x32-specific system call numbers start at 512 to avoid cache impact
@@ -75,6 +75,11 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+/*
+ * Flags for mlock
+ */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#define MADV_NORMAL 0 /* no further special treatment */
#define MADV_RANDOM 1 /* expect random page references */
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
@@ -753,8 +753,14 @@ __SYSCALL(339, sys_memfd_create, 2)
__SYSCALL(340, sys_bpf, 3)
#define __NR_execveat 341
__SYSCALL(341, sys_execveat, 5)
-
-#define __NR_syscall_count 342
+#define __NR_mlock2 342
+__SYSCALL(342, sys_mlock2, 3)
+#define __NR_munlock2 343
+__SYSCALL(342, sys_munlock2, 3)
+#define __NR_munlockall2 344
+__SYSCALL(342, sys_munlock2, 1)
+
+#define __NR_syscall_count 345
/*
* sysxtensa syscall handler
@@ -884,4 +884,8 @@ 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);
+asmlinkage long sys_munlock2(unsigned long start, size_t len, int flags);
+asmlinkage long sys_munlockall2(int flags);
+
#endif
@@ -18,4 +18,6 @@
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
+#define MLOCK_LOCKED 0x01 /* Lock and populate the specified range */
+
#endif /* __ASM_GENERIC_MMAN_H */
@@ -709,9 +709,15 @@ __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)
+#define __NR_munlock2 283
+__SYSCALL(__NR_munlock2, sys_munlock2)
+#define __NR_munlockall2 284
+__SYSCALL(__NR_munlockall2, sys_munlockall2)
#undef __NR_syscalls
-#define __NR_syscalls 282
+#define __NR_syscalls 285
/*
* All syscalls below here should go away really,
@@ -193,6 +193,9 @@ cond_syscall(sys_mlock);
cond_syscall(sys_munlock);
cond_syscall(sys_mlockall);
cond_syscall(sys_munlockall);
+cond_syscall(sys_mlock2);
+cond_syscall(sys_munlock2);
+cond_syscall(sys_munlockall2);
cond_syscall(sys_mincore);
cond_syscall(sys_madvise);
cond_syscall(sys_mremap);
@@ -648,6 +648,14 @@ 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 || flags & ~MLOCK_LOCKED)
+ return -EINVAL;
+
+ return do_mlock(start, len, VM_LOCKED);
+}
+
static int do_munlock(unsigned long start, size_t len, vm_flags_t flags)
{
int ret;
@@ -667,6 +675,13 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
return do_munlock(start, len, VM_LOCKED);
}
+SYSCALL_DEFINE3(munlock2, unsigned long, start, size_t, len, int, flags)
+{
+ if (!flags || flags & ~MLOCK_LOCKED)
+ return -EINVAL;
+ return do_munlock(start, len, VM_LOCKED);
+}
+
static int do_mlockall(int flags)
{
struct vm_area_struct * vma, * prev = NULL;
@@ -756,6 +771,19 @@ SYSCALL_DEFINE0(munlockall)
return ret;
}
+SYSCALL_DEFINE1(munlockall2, int, flags)
+{
+ int ret = -EINVAL;
+
+ if (!flags || flags & ~(MCL_CURRENT | MCL_FUTURE))
+ return ret;
+
+ down_write(¤t->mm->mmap_sem);
+ ret = do_munlockall(flags);
+ up_write(¤t->mm->mmap_sem);
+ return ret;
+}
+
/*
* Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
* shm segments) get accounted against the user_struct instead.
With the refactored mlock code, introduce new system calls for mlock, munlock, and munlockall. The new calls will allow the user to specify what lock states are being added or cleared. mlock2 and munlock2 are trivial at the moment, but a follow on patch will add a new mlock state making them useful. munlock2 addresses a limitation of the current implementation. If a user calls mlockall(MCL_CURRENT | MCL_FUTURE) and then later decides that MCL_FUTURE should be removed, they would have to call munlockall() followed by mlockall(MCL_CURRENT) which could potentially be very expensive. The new munlockall2 system call allows a user to simply clear the MCL_FUTURE flag. Signed-off-by: Eric B Munson <emunson@akamai.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Vlastimil Babka <vbabka@suse.cz> 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-mips@linux-mips.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/alpha/include/asm/unistd.h | 2 +- arch/alpha/include/uapi/asm/mman.h | 2 ++ arch/alpha/kernel/systbls.S | 3 +++ arch/arm/kernel/calls.S | 3 +++ arch/arm64/include/asm/unistd32.h | 6 ++++++ arch/avr32/kernel/syscall_table.S | 3 +++ arch/blackfin/mach-common/entry.S | 3 +++ arch/cris/arch-v10/kernel/entry.S | 3 +++ arch/cris/arch-v32/kernel/entry.S | 3 +++ arch/frv/kernel/entry.S | 3 +++ arch/ia64/kernel/entry.S | 3 +++ arch/m32r/kernel/entry.S | 3 +++ arch/m32r/kernel/syscall_table.S | 3 +++ arch/m68k/kernel/syscalltable.S | 3 +++ arch/microblaze/kernel/syscall_table.S | 3 +++ arch/mips/include/uapi/asm/mman.h | 5 +++++ arch/mips/kernel/scall32-o32.S | 3 +++ arch/mips/kernel/scall64-64.S | 3 +++ arch/mips/kernel/scall64-n32.S | 3 +++ arch/mips/kernel/scall64-o32.S | 3 +++ arch/mn10300/kernel/entry.S | 3 +++ arch/parisc/include/uapi/asm/mman.h | 2 ++ arch/powerpc/include/uapi/asm/mman.h | 2 ++ arch/s390/kernel/syscalls.S | 3 +++ arch/sh/kernel/syscalls_32.S | 3 +++ arch/sparc/include/uapi/asm/mman.h | 2 ++ arch/sparc/kernel/systbls_32.S | 2 +- arch/sparc/kernel/systbls_64.S | 4 ++-- arch/tile/include/uapi/asm/mman.h | 5 +++++ arch/x86/entry/syscalls/syscall_32.tbl | 3 +++ arch/x86/entry/syscalls/syscall_64.tbl | 3 +++ arch/xtensa/include/uapi/asm/mman.h | 5 +++++ arch/xtensa/include/uapi/asm/unistd.h | 10 ++++++++-- include/linux/syscalls.h | 4 ++++ include/uapi/asm-generic/mman.h | 2 ++ include/uapi/asm-generic/unistd.h | 8 +++++++- kernel/sys_ni.c | 3 +++ mm/mlock.c | 28 ++++++++++++++++++++++++++++ 38 files changed, 148 insertions(+), 7 deletions(-)