mbind2 is an extensible mbind interface which allows a user to
set the mempolicy for one or more address ranges.
Defined as:
mbind2(struct mpol_args *args, size_t size, unsigned long flags)
Input values include the following fields of mpl_args:
mode: The MPOL_* policy (DEFAULT, INTERLEAVE, etc.)
mode_flags: The MPOL_F_* flags that were previously passed in or'd
into the mode. This was split to hopefully allow future
extensions additional mode/flag space.
pol_nodes: the nodemask to apply for the memory policy
pol_maxnodes: The max number of nodes described by pol_nodes
home_node: if MPOL_MF_HOME_NODE, set home node of policy to this
vec: the vector of (address, len) memory ranges to operate on
vlen: the number of entries in vec
The semantics are otherwise the same as mbind(), except that
the home_node can be set, and all address ranges defined by
vec/vlen will be operated on.
Valid flags for mbind2 include the same flags as mbind, plus
MPOL_MF_HOME_NODE, which informs the syscall to utilize the value
of mpol_args->home_node to set the mempolicy home node.
Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Suggested-by: Frank van der Linden <fvdl@xxxxxxxxxx>
Suggested-by: Vinicius Tavares Petrucci <vtavarespetr@xxxxxxxxxx>
Suggested-by: Rakie Kim <rakie.kim@xxxxxx>
Suggested-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
Suggested-by: Honggyu Kim <honggyu.kim@xxxxxx>
Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
Co-developed-by: Vinicius Tavares Petrucci <vtavarespetr@xxxxxxxxxx>
---
.../admin-guide/mm/numa_memory_policy.rst | 12 +++-
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
arch/arm/tools/syscall.tbl | 1 +
arch/m68k/kernel/syscalls/syscall.tbl | 1 +
arch/microblaze/kernel/syscalls/syscall.tbl | 1 +
arch/mips/kernel/syscalls/syscall_n32.tbl | 1 +
arch/mips/kernel/syscalls/syscall_o32.tbl | 1 +
arch/parisc/kernel/syscalls/syscall.tbl | 1 +
arch/powerpc/kernel/syscalls/syscall.tbl | 1 +
arch/s390/kernel/syscalls/syscall.tbl | 1 +
arch/sh/kernel/syscalls/syscall.tbl | 1 +
arch/sparc/kernel/syscalls/syscall.tbl | 1 +
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
arch/xtensa/kernel/syscalls/syscall.tbl | 1 +
include/linux/syscalls.h | 2 +
include/uapi/asm-generic/unistd.h | 4 +-
include/uapi/linux/mempolicy.h | 5 +-
mm/mempolicy.c | 65 +++++++++++++++++++
19 files changed, 98 insertions(+), 4 deletions(-)
diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
index 82cdb765dd58..72ab21e24ec2 100644
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -481,12 +481,18 @@ Install VMA/Shared Policy for a Range of Task's Address Space::
long mbind(void *start, unsigned long len, int mode,
const unsigned long *nmask, unsigned long maxnode,
unsigned flags);
+ long mbind2(struct mpol_args args, size_t size,
+ unsigned long flags);
mbind() installs the policy specified by (mode, nmask, maxnodes) as a
VMA policy for the range of the calling task's address space specified
by the 'start' and 'len' arguments. Additional actions may be
requested via the 'flags' argument.
+mbind2() is an extended version of mbind() capable of operating on multiple
+memory ranges in one scall, and which is capable of setting the home node
+for the memory policy without an additional call to set_mempolicy_home_node()
+
See the mbind(2) man page for more details.
Set home node for a Range of Task's Address Spacec::
@@ -502,6 +508,9 @@ closest to which page allocation will come from. Specifying the home node overri
the default allocation policy to allocate memory close to the local node for an
executing CPU.
+mbind2() also provides a way for the home node to be set at the time the
+mempolicy is set. See the mbind(2) man page for more details.
+
Extended Mempolicy Arguments::
struct mpol_args {
@@ -529,7 +538,8 @@ Extended Mempolicy Arguments::
The extended mempolicy argument structure is defined to allow the mempolicy
interfaces future extensibility without the need for additional system calls.
-Extended interfaces (set_mempolicy2 and get_mempolicy2) use this structure.
+Extended interfaces (set_mempolicy2, get_mempolicy2, and mbind2) use this
+this argument structure.
The core arguments (mode, mode_flags, pol_nodes, and pol_maxnodes) apply to
all interfaces relative to their non-extended counterparts. Each additional
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 0301a8b0a262..e8239293c35a 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -498,3 +498,4 @@
566 common futex_requeue sys_futex_requeue
567 common set_mempolicy2 sys_set_mempolicy2
568 common get_mempolicy2 sys_get_mempolicy2
+569 common mbind2 sys_mbind2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 771a33446e8e..a3f39750257a 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -472,3 +472,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 048a409e684c..9a12dface18e 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -458,3 +458,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 327b01bd6793..6cb740123137 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -464,3 +464,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 921d58e1da23..52cf720f8ae2 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -397,3 +397,4 @@
456 n32 futex_requeue sys_futex_requeue
457 n32 set_mempolicy2 sys_set_mempolicy2
458 n32 get_mempolicy2 sys_get_mempolicy2
+459 n32 mbind2 sys_mbind2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 9271c83c9993..fd37c5301a48 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -446,3 +446,4 @@
456 o32 futex_requeue sys_futex_requeue
457 o32 set_mempolicy2 sys_set_mempolicy2
458 o32 get_mempolicy2 sys_get_mempolicy2
+459 o32 mbind2 sys_mbind2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 0654f3f89fc7..fcd67bc405b1 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -457,3 +457,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index ac11d2064e7a..89715417014c 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -545,3 +545,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 1cdcafe1ccca..c8304e0d0aa7 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -461,3 +461,4 @@
456 common futex_requeue sys_futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2 sys_mbind2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index f71742024c29..e5c51b6c367f 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -461,3 +461,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 2fbf5dbe0620..74527f585500 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -504,3 +504,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 0af813b9a118..be2e2aa17dd8 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -463,3 +463,4 @@
456 i386 futex_requeue sys_futex_requeue
457 i386 set_mempolicy2 sys_set_mempolicy2
458 i386 get_mempolicy2 sys_get_mempolicy2
+459 i386 mbind2 sys_mbind2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 0b777876fc15..6e2347eb8773 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -380,6 +380,7 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 4536c9a4227d..f00a21317dc0 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -429,3 +429,4 @@
456 common futex_requeue sys_futex_requeue
457 common set_mempolicy2 sys_set_mempolicy2
458 common get_mempolicy2 sys_get_mempolicy2
+459 common mbind2 sys_mbind2
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 774512b7934e..a49a67e496bc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -816,6 +816,8 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len,
const unsigned long __user *nmask,
unsigned long maxnode,
unsigned flags);
+asmlinkage long sys_mbind2(struct mpol_args *args, size_t size,
+ unsigned long flags);
asmlinkage long sys_get_mempolicy(int __user *policy,
unsigned long __user *nmask,
unsigned long maxnode,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 719accc731db..cd31599bb9cc 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -832,9 +832,11 @@ __SYSCALL(__NR_futex_requeue, sys_futex_requeue)
__SYSCALL(__NR_set_mempolicy2, sys_set_mempolicy2)
#define __NR_get_mempolicy2 458
__SYSCALL(__NR_get_mempolicy2, sys_get_mempolicy2)
+#define __NR_mbind2 459
+__SYSCALL(__NR_mbind2, sys_mbind2)
#undef __NR_syscalls
-#define __NR_syscalls 459
+#define __NR_syscalls 460
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index e6b50903047c..3e463442fe28 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -62,13 +62,14 @@ struct mpol_args {
#define MPOL_F_ADDR (1<<1) /* look up vma using address */
#define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */
-/* Flags for mbind */
+/* Flags for mbind/mbind2 */
#define MPOL_MF_STRICT (1<<0) /* Verify existing pages in the mapping */
#define MPOL_MF_MOVE (1<<1) /* Move pages owned by this process to conform
to policy */
#define MPOL_MF_MOVE_ALL (1<<2) /* Move every page to conform to policy */
#define MPOL_MF_LAZY (1<<3) /* UNSUPPORTED FLAG: Lazy migrate on fault */
-#define MPOL_MF_INTERNAL (1<<4) /* Internal flags start here */
+#define MPOL_MF_HOME_NODE (1<<4) /* mbind2: set home node */
+#define MPOL_MF_INTERNAL (1<<5) /* Internal flags start here */
#define MPOL_MF_VALID (MPOL_MF_STRICT | \
MPOL_MF_MOVE | \
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d1d10b2746e3..c203cea52ce9 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1603,6 +1603,71 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
return kernel_mbind(start, len, mode, nmask, maxnode, flags);
}
+SYSCALL_DEFINE3(mbind2, struct mpol_args __user *, uargs, size_t, usize,
+ unsigned long, flags)
+{
+ struct mpol_args kargs;
+ struct mempolicy_args margs;
+ nodemask_t policy_nodes;
+ struct iovec iovstack[UIO_FASTIOV];
+ struct iovec *iov = iovstack;
+ struct iov_iter iter;
+ int err;
+
+ err = copy_struct_from_user(&kargs, sizeof(kargs), uargs, usize);
+ if (err)
+ return -EINVAL;
+
+ err = validate_mpol_flags(kargs.mode, &kargs.mode_flags);
+ if (err)
+ return err;
+
+ if (!kargs.vec || !kargs.vlen)
+ return -EINVAL;
+
+ margs.mode = kargs.mode;
+ margs.mode_flags = kargs.mode_flags;
+ margs.addr = kargs.addr;
+
+ /* if home node given, validate it is online */
+ if (flags & MPOL_MF_HOME_NODE) {
+ if ((kargs.home_node >= MAX_NUMNODES) ||
+ !node_online(kargs.home_node))
+ return -EINVAL;
+ margs.home_node = kargs.home_node;
+ } else
+ margs.home_node = NUMA_NO_NODE;
+ flags &= ~MPOL_MF_HOME_NODE;
+
+ if (kargs.pol_nodes) {
+ err = get_nodes(&policy_nodes, kargs.pol_nodes,
+ kargs.pol_maxnodes);
+ if (err)
+ return err;
+ margs.policy_nodes = &policy_nodes;
+ } else
+ margs.policy_nodes = NULL;
+
+ /* For each address range in vector, do_mbind */
+ err = import_iovec(ITER_DEST, kargs.vec, kargs.vlen,
+ ARRAY_SIZE(iovstack), &iov, &iter);
+ if (err)
+ return err;
+ while (iov_iter_count(&iter)) {
+ unsigned long start, len;
+
+ start = untagged_addr((unsigned long)iter_iov_addr(&iter));
+ len = iter_iov_len(&iter);
+ err = do_mbind(start, len, &margs, flags);
+ if (err)
+ break;
+ iov_iter_advance(&iter, iter_iov_len(&iter));
+ }
+
+ kfree(iov);
+ return err;
+}
+
/* Set the process memory policy */
static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask,
unsigned long maxnode)
--
2.39.1
