[PATCH v6 09/12] mm/mempolicy: add set_mempolicy2 syscall
From: Gregory Price
Date: Wed Jan 03 2024 - 17:46:22 EST
set_mempolicy2 is an extensible set_mempolicy interface which allows
a user to set the per-task memory policy.
Defined as:
set_mempolicy2(struct mpol_param *param, size_t usize,
unsigned long flags);
relevant mpol_param fields include the following:
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.
home_node: ignored (see note below)
pol_nodes: the nodemask to apply for the memory policy
pol_maxnodes: The max number of nodes described by pol_nodes
The usize arg is intended for the user to pass in sizeof(mpol_param)
to allow forward/backward compatibility whenever possible.
The flags argument is intended to future proof the syscall against
future extensions which may require interpreting the arguments in
the structure differently.
Semantics of `set_mempolicy` are otherwise the same as `set_mempolicy`
as of this patch.
As of this patch, setting the home node of a task-policy is not
supported, as this functionality was not supported by set_mempolicy.
Additional research should be done to determine whether adding this
functionality is safe, but doing so would only require setting
MPOL_MF_HOME_NODE and providing a valid home node value.
Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
Acked-by: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
---
.../admin-guide/mm/numa_memory_policy.rst | 10 ++++++
arch/alpha/kernel/syscalls/syscall.tbl | 1 +
arch/arm/tools/syscall.tbl | 1 +
arch/arm64/include/asm/unistd.h | 2 +-
arch/arm64/include/asm/unistd32.h | 2 ++
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 ++-
kernel/sys_ni.c | 1 +
mm/mempolicy.c | 36 +++++++++++++++++++
.../arch/mips/entry/syscalls/syscall_n64.tbl | 1 +
.../arch/powerpc/entry/syscalls/syscall.tbl | 1 +
.../perf/arch/s390/entry/syscalls/syscall.tbl | 1 +
.../arch/x86/entry/syscalls/syscall_64.tbl | 1 +
25 files changed, 73 insertions(+), 2 deletions(-)
diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
index cbfc5f65ed77..62a4ea14c646 100644
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -430,6 +430,8 @@ Set [Task] Memory Policy::
long set_mempolicy(int mode, const unsigned long *nmask,
unsigned long maxnode);
+ long set_mempolicy2(struct mpol_param *param, size_t size,
+ unsigned long flags);
Set's the calling task's "task/process memory policy" to mode
specified by the 'mode' argument and the set of nodes defined by
@@ -438,6 +440,12 @@ specified by the 'mode' argument and the set of nodes defined by
'mode' argument with the flag (for example: MPOL_INTERLEAVE |
MPOL_F_STATIC_NODES).
+set_mempolicy2() is an extended version of set_mempolicy() capable
+of setting a mempolicy which requires more information than can be
+passed via get_mempolicy(). For example, weighted interleave with
+task-local weights requires a weight array to be passed via the
+'mpol_param->il_weights' parameter.
+
See the set_mempolicy(2) man page for more details
@@ -493,6 +501,8 @@ 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) use 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
field may only apply to specific extended interfaces. See the respective
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 18c842ca6c32..0dc288a1118a 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -496,3 +496,4 @@
564 common futex_wake sys_futex_wake
565 common futex_wait sys_futex_wait
566 common futex_requeue sys_futex_requeue
+567 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 584f9528c996..50172ec0e1f5 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -470,3 +470,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 531effca5f1f..298313d2e0af 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 457
+#define __NR_compat_syscalls 458
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 9f7c1bf99526..cee8d669c342 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -919,6 +919,8 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
__SYSCALL(__NR_futex_wait, sys_futex_wait)
#define __NR_futex_requeue 456
__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_set_mempolicy2 457
+__SYSCALL(__NR_set_mempolicy2, sys_set_mempolicy2)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 7a4b780e82cb..839d90c535f2 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -456,3 +456,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 5b6a0b02b7de..567c8b883735 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -462,3 +462,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index a842b41c8e06..cc0640e16f2f 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -395,3 +395,4 @@
454 n32 futex_wake sys_futex_wake
455 n32 futex_wait sys_futex_wait
456 n32 futex_requeue sys_futex_requeue
+457 n32 set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 525cc54bc63b..f7262fde98d9 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -444,3 +444,4 @@
454 o32 futex_wake sys_futex_wake
455 o32 futex_wait sys_futex_wait
456 o32 futex_requeue sys_futex_requeue
+457 o32 set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index a47798fed54e..e10f0e8bd064 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -455,3 +455,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 7fab411378f2..4f03f5f42b78 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -543,3 +543,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 86fec9b080f6..f98dadc2e9df 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -459,3 +459,4 @@
454 common futex_wake sys_futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 363fae0fe9bf..f47ba9f2d05d 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -459,3 +459,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 7bcaa3d5ea44..53fb16616728 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -502,3 +502,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c8fac5205803..4b4dc41b24ee 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -461,3 +461,4 @@
454 i386 futex_wake sys_futex_wake
455 i386 futex_wait sys_futex_wait
456 i386 futex_requeue sys_futex_requeue
+457 i386 set_mempolicy2 sys_set_mempolicy2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..1bc2190bec27 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -378,6 +378,7 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
#
# 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 06eefa9c1458..e26dc89399eb 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -427,3 +427,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fb0b4b2b9bea..b37ea6715456 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -823,6 +823,8 @@ asmlinkage long sys_get_mempolicy(int __user *policy,
unsigned long addr, unsigned long flags);
asmlinkage long sys_set_mempolicy(int mode, const unsigned long __user *nmask,
unsigned long maxnode);
+asmlinkage long sys_set_mempolicy2(struct mpol_param __user *param, size_t size,
+ unsigned long flags);
asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
const unsigned long __user *from,
const unsigned long __user *to);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 756b013fb832..55486aba099f 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -828,9 +828,11 @@ __SYSCALL(__NR_futex_wake, sys_futex_wake)
__SYSCALL(__NR_futex_wait, sys_futex_wait)
#define __NR_futex_requeue 456
__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
+#define __NR_set_mempolicy2 457
+__SYSCALL(__NR_set_mempolicy2, sys_set_mempolicy2)
#undef __NR_syscalls
-#define __NR_syscalls 457
+#define __NR_syscalls 458
/*
* 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 9a846439b36a..fa1373c8bff8 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -189,6 +189,7 @@ COND_SYSCALL(remap_file_pages);
COND_SYSCALL(mbind);
COND_SYSCALL(get_mempolicy);
COND_SYSCALL(set_mempolicy);
+COND_SYSCALL(set_mempolicy2);
COND_SYSCALL(migrate_pages);
COND_SYSCALL(move_pages);
COND_SYSCALL(set_mempolicy_home_node);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4a566341cf43..84d877195deb 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1645,6 +1645,42 @@ SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask,
return kernel_set_mempolicy(mode, nmask, maxnode);
}
+SYSCALL_DEFINE3(set_mempolicy2, struct mpol_param __user *, uparam,
+ size_t, usize, unsigned long, flags)
+{
+ struct mpol_param kparam;
+ struct mempolicy_param mparam;
+ int err;
+ nodemask_t policy_nodemask;
+ unsigned long __user *nodes_ptr;
+
+ if (flags)
+ return -EINVAL;
+
+ err = copy_struct_from_user(&kparam, sizeof(kparam), uparam, usize);
+ if (err)
+ return err;
+
+ err = validate_mpol_flags(kparam.mode, &kparam.mode_flags);
+ if (err)
+ return err;
+
+ memset(&mparam, 0, sizeof(mparam));
+ mparam.mode = kparam.mode;
+ mparam.mode_flags = kparam.mode_flags;
+ if (kparam.pol_nodes) {
+ nodes_ptr = u64_to_user_ptr(kparam.pol_nodes);
+ err = get_nodes(&policy_nodemask, nodes_ptr,
+ kparam.pol_maxnodes);
+ if (err)
+ return err;
+ mparam.policy_nodes = &policy_nodemask;
+ } else
+ mparam.policy_nodes = NULL;
+
+ return do_set_mempolicy(&mparam);
+}
+
static int kernel_migrate_pages(pid_t pid, unsigned long maxnode,
const unsigned long __user *old_nodes,
const unsigned long __user *new_nodes)
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 116ff501bf92..bb1351df51d9 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -371,3 +371,4 @@
454 n64 futex_wake sys_futex_wake
455 n64 futex_wait sys_futex_wait
456 n64 futex_requeue sys_futex_requeue
+457 n64 set_mempolicy2 sys_set_mempolicy2
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 7fab411378f2..4f03f5f42b78 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -543,3 +543,4 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 86fec9b080f6..f98dadc2e9df 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -459,3 +459,4 @@
454 common futex_wake sys_futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2 sys_set_mempolicy2
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 8cb8bf68721c..21f2579679d4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -378,6 +378,7 @@
454 common futex_wake sys_futex_wake
455 common futex_wait sys_futex_wait
456 common futex_requeue sys_futex_requeue
+457 common set_mempolicy2 sys_set_mempolicy2
#
# Due to a historical design error, certain syscalls are numbered differently
--
2.39.1