* [PATCH 1/3] binfmt_elf_fdpic: fix AUXV size calculation for ELF_HWCAP3 and ELF_HWCAP4
2026-01-08 5:07 [PATCH 0/3 v2] exec: inherit HWCAPs from the parent process Andrei Vagin
@ 2026-01-08 5:07 ` Andrei Vagin
2026-01-08 11:31 ` Mark Brown
2026-01-08 5:07 ` [PATCH 2/3] exec: inherit HWCAPs from the parent process Andrei Vagin
2026-01-08 5:07 ` [PATCH 3/3] selftests/exec: add test for HWCAP inheritance Andrei Vagin
2 siblings, 1 reply; 5+ messages in thread
From: Andrei Vagin @ 2026-01-08 5:07 UTC (permalink / raw)
To: Kees Cook
Cc: linux-kernel, linux-fsdevel, linux-mm, criu, Andrew Morton,
Chen Ridong, Christian Brauner, David Hildenbrand,
Eric Biederman, Lorenzo Stoakes, Michal Koutny, Andrei Vagin,
Mark Brown, Max Filippov
Commit 4e6e8c2b757f ("binfmt_elf: Wire up AT_HWCAP3 at AT_HWCAP4") added
support for AT_HWCAP3 and AT_HWCAP4, but it missed updating the AUX
vector size calculation in create_elf_fdpic_tables() and
AT_VECTOR_SIZE_BASE in include/linux/auxvec.h.
Similar to the fix for ELF_HWCAP2 in commit c6a09e342f8e
("binfmt_elf_fdpic: fix AUXV size calculation when ELF_HWCAP2 is defined"),
this omission leads to a mismatch between the reserved space and the
actual number of AUX entries, eventually triggering a kernel BUG_ON(csp != sp).
Fix this by incrementing nitems when ELF_HWCAP3 or ELF_HWCAP4 are defined
and updating AT_VECTOR_SIZE_BASE.
Cc: Mark Brown <broonie@kernel.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Fixes: 4e6e8c2b757f ("binfmt_elf: Wire up AT_HWCAP3 at AT_HWCAP4")
Signed-off-by: Andrei Vagin <avagin@google.com>
---
fs/binfmt_elf_fdpic.c | 6 ++++++
include/linux/auxvec.h | 2 +-
2 files changed, 7 insertions(+), 1 deletion(-)
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 48fd2de3bca0..a3d4e6973b29 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -595,6 +595,12 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
#ifdef ELF_HWCAP2
nitems++;
#endif
+#ifdef ELF_HWCAP3
+ nitems++;
+#endif
+#ifdef ELF_HWCAP4
+ nitems++;
+#endif
csp = sp;
sp -= nitems * 2 * sizeof(unsigned long);
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h
index 407f7005e6d6..8bcb9b726262 100644
--- a/include/linux/auxvec.h
+++ b/include/linux/auxvec.h
@@ -4,6 +4,6 @@
#include <uapi/linux/auxvec.h>
-#define AT_VECTOR_SIZE_BASE 22 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 24 /* NEW_AUX_ENT entries in auxiliary table */
/* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
#endif /* _LINUX_AUXVEC_H */
--
2.52.0.351.gbe84eed79e-goog
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 2/3] exec: inherit HWCAPs from the parent process
2026-01-08 5:07 [PATCH 0/3 v2] exec: inherit HWCAPs from the parent process Andrei Vagin
2026-01-08 5:07 ` [PATCH 1/3] binfmt_elf_fdpic: fix AUXV size calculation for ELF_HWCAP3 and ELF_HWCAP4 Andrei Vagin
@ 2026-01-08 5:07 ` Andrei Vagin
2026-01-08 5:07 ` [PATCH 3/3] selftests/exec: add test for HWCAP inheritance Andrei Vagin
2 siblings, 0 replies; 5+ messages in thread
From: Andrei Vagin @ 2026-01-08 5:07 UTC (permalink / raw)
To: Kees Cook
Cc: linux-kernel, linux-fsdevel, linux-mm, criu, Andrew Morton,
Chen Ridong, Christian Brauner, David Hildenbrand,
Eric Biederman, Lorenzo Stoakes, Michal Koutny, Andrei Vagin
Introduces a mechanism to inherit hardware capabilities (AT_HWCAP,
AT_HWCAP2, etc.) from a parent process when they have been modified via
prctl.
To support C/R operations (snapshots, live migration) in heterogeneous
clusters, we must ensure that processes utilize CPU features available
on all potential target nodes. To solve this, we need to advertise a
common feature set across the cluster.
This patch adds a new mm flag MMF_USER_HWCAP, which is set when the
auxiliary vector is modified via prctl(PR_SET_MM, PR_SET_MM_AUXV). When
execve() is called, if the current process has MMF_USER_HWCAP set, the
HWCAP values are extracted from the current auxiliary vector and stored
in the linux_binprm structure. These values are then used to populate
the auxiliary vector of the new process, effectively inheriting the
hardware capabilities.
The inherited HWCAPs are masked with the hardware capabilities supported
by the current kernel to ensure that we don't report more features than
actually supported. This is important to avoid unexpected behavior,
especially for processes with additional privileges.
Signed-off-by: Andrei Vagin <avagin@google.com>
---
fs/binfmt_elf.c | 8 +++---
fs/binfmt_elf_fdpic.c | 8 +++---
fs/exec.c | 58 ++++++++++++++++++++++++++++++++++++++++
include/linux/binfmts.h | 11 ++++++++
include/linux/mm_types.h | 2 ++
kernel/fork.c | 3 +++
kernel/sys.c | 5 +++-
7 files changed, 86 insertions(+), 9 deletions(-)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3eb734c192e9..aec129e33f0b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -246,7 +246,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
*/
ARCH_DLINFO;
#endif
- NEW_AUX_ENT(AT_HWCAP, ELF_HWCAP);
+ NEW_AUX_ENT(AT_HWCAP, bprm->hwcap);
NEW_AUX_ENT(AT_PAGESZ, ELF_EXEC_PAGESIZE);
NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC);
NEW_AUX_ENT(AT_PHDR, phdr_addr);
@@ -264,13 +264,13 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
NEW_AUX_ENT(AT_SECURE, bprm->secureexec);
NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes);
#ifdef ELF_HWCAP2
- NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2);
+ NEW_AUX_ENT(AT_HWCAP2, bprm->hwcap2);
#endif
#ifdef ELF_HWCAP3
- NEW_AUX_ENT(AT_HWCAP3, ELF_HWCAP3);
+ NEW_AUX_ENT(AT_HWCAP3, bprm->hwcap3);
#endif
#ifdef ELF_HWCAP4
- NEW_AUX_ENT(AT_HWCAP4, ELF_HWCAP4);
+ NEW_AUX_ENT(AT_HWCAP4, bprm->hwcap4);
#endif
NEW_AUX_ENT(AT_EXECFN, bprm->exec);
if (k_platform) {
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index a3d4e6973b29..55b482f03c82 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -629,15 +629,15 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
*/
ARCH_DLINFO;
#endif
- NEW_AUX_ENT(AT_HWCAP, ELF_HWCAP);
+ NEW_AUX_ENT(AT_HWCAP, bprm->hwcap);
#ifdef ELF_HWCAP2
- NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2);
+ NEW_AUX_ENT(AT_HWCAP2, bprm->hwcap2);
#endif
#ifdef ELF_HWCAP3
- NEW_AUX_ENT(AT_HWCAP3, ELF_HWCAP3);
+ NEW_AUX_ENT(AT_HWCAP3, bprm->hwcap3);
#endif
#ifdef ELF_HWCAP4
- NEW_AUX_ENT(AT_HWCAP4, ELF_HWCAP4);
+ NEW_AUX_ENT(AT_HWCAP4, bprm->hwcap4);
#endif
NEW_AUX_ENT(AT_PAGESZ, PAGE_SIZE);
NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC);
diff --git a/fs/exec.c b/fs/exec.c
index 9d5ebc9d15b0..94382285eeda 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1462,6 +1462,17 @@ static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int fl
*/
bprm->is_check = !!(flags & AT_EXECVE_CHECK);
+ bprm->hwcap = ELF_HWCAP;
+#ifdef ELF_HWCAP2
+ bprm->hwcap2 = ELF_HWCAP2;
+#endif
+#ifdef ELF_HWCAP3
+ bprm->hwcap3 = ELF_HWCAP3;
+#endif
+#ifdef ELF_HWCAP4
+ bprm->hwcap4 = ELF_HWCAP4;
+#endif
+
retval = bprm_mm_init(bprm);
if (!retval)
return bprm;
@@ -1780,6 +1791,50 @@ static int bprm_execve(struct linux_binprm *bprm)
return retval;
}
+static void inherit_hwcap(struct linux_binprm *bprm)
+{
+ int i, n;
+
+#ifdef ELF_HWCAP4
+ n = 4;
+#elif defined(ELF_HWCAP3)
+ n = 3;
+#elif defined(ELF_HWCAP2)
+ n = 2;
+#else
+ n = 1;
+#endif
+
+ for (i = 0; n && i < AT_VECTOR_SIZE; i += 2) {
+ long val = current->mm->saved_auxv[i + 1];
+
+ switch (current->mm->saved_auxv[i]) {
+ case AT_HWCAP:
+ bprm->hwcap = val & ELF_HWCAP;
+ break;
+#ifdef ELF_HWCAP2
+ case AT_HWCAP2:
+ bprm->hwcap2 = val & ELF_HWCAP2;
+ break;
+#endif
+#ifdef ELF_HWCAP3
+ case AT_HWCAP3:
+ bprm->hwcap3 = val & ELF_HWCAP3;
+ break;
+#endif
+#ifdef ELF_HWCAP4
+ case AT_HWCAP4:
+ bprm->hwcap4 = val & ELF_HWCAP4;
+ break;
+#endif
+ default:
+ continue;
+ }
+ n--;
+ }
+ mm_flags_set(MMF_USER_HWCAP, bprm->mm);
+}
+
static int do_execveat_common(int fd, struct filename *filename,
struct user_arg_ptr argv,
struct user_arg_ptr envp,
@@ -1856,6 +1911,9 @@ static int do_execveat_common(int fd, struct filename *filename,
current->comm, bprm->filename);
}
+ if (mm_flags_test(MMF_USER_HWCAP, current->mm))
+ inherit_hwcap(bprm);
+
retval = bprm_execve(bprm);
out_free:
free_bprm(bprm);
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 65abd5ab8836..94a3dcf9b1d2 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -2,6 +2,7 @@
#ifndef _LINUX_BINFMTS_H
#define _LINUX_BINFMTS_H
+#include <linux/elf.h>
#include <linux/sched.h>
#include <linux/unistd.h>
#include <asm/exec.h>
@@ -67,6 +68,16 @@ struct linux_binprm {
unsigned long exec;
struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */
+ unsigned long hwcap;
+#ifdef ELF_HWCAP2
+ unsigned long hwcap2;
+#endif
+#ifdef ELF_HWCAP3
+ unsigned long hwcap3;
+#endif
+#ifdef ELF_HWCAP4
+ unsigned long hwcap4;
+#endif
char buf[BINPRM_BUF_SIZE];
} __randomize_layout;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 42af2292951d..93e7aa929fda 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1862,6 +1862,8 @@ enum {
#define MMF_TOPDOWN 31 /* mm searches top down by default */
#define MMF_TOPDOWN_MASK BIT(MMF_TOPDOWN)
+#define MMF_USER_HWCAP 32 /* user-defined HWCAPs */
+
#define MMF_INIT_LEGACY_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK)
diff --git a/kernel/fork.c b/kernel/fork.c
index b1f3915d5f8e..0091315643de 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1103,6 +1103,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
__mm_flags_overwrite_word(mm, mmf_init_legacy_flags(flags));
mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+
+ if (mm_flags_test(MMF_USER_HWCAP, current->mm))
+ mm_flags_set(MMF_USER_HWCAP, mm);
} else {
__mm_flags_overwrite_word(mm, default_dump_filter);
mm->def_flags = 0;
diff --git a/kernel/sys.c b/kernel/sys.c
index 8d199cf457ae..83283001abfb 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2157,8 +2157,10 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
* not introduce additional locks here making the kernel
* more complex.
*/
- if (prctl_map.auxv_size)
+ if (prctl_map.auxv_size) {
memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv));
+ mm_flags_set(MMF_USER_HWCAP, current->mm);
+ }
mmap_read_unlock(mm);
return 0;
@@ -2191,6 +2193,7 @@ static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr,
task_lock(current);
memcpy(mm->saved_auxv, user_auxv, len);
task_unlock(current);
+ mm_flags_set(MMF_USER_HWCAP, current->mm);
return 0;
}
--
2.52.0.351.gbe84eed79e-goog
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH 3/3] selftests/exec: add test for HWCAP inheritance
2026-01-08 5:07 [PATCH 0/3 v2] exec: inherit HWCAPs from the parent process Andrei Vagin
2026-01-08 5:07 ` [PATCH 1/3] binfmt_elf_fdpic: fix AUXV size calculation for ELF_HWCAP3 and ELF_HWCAP4 Andrei Vagin
2026-01-08 5:07 ` [PATCH 2/3] exec: inherit HWCAPs from the parent process Andrei Vagin
@ 2026-01-08 5:07 ` Andrei Vagin
2 siblings, 0 replies; 5+ messages in thread
From: Andrei Vagin @ 2026-01-08 5:07 UTC (permalink / raw)
To: Kees Cook
Cc: linux-kernel, linux-fsdevel, linux-mm, criu, Andrew Morton,
Chen Ridong, Christian Brauner, David Hildenbrand,
Eric Biederman, Lorenzo Stoakes, Michal Koutny, Andrei Vagin
Verify that HWCAPs are correctly inherited/preserved across execve() when
modified via prctl(PR_SET_MM_AUXV).
The test performs the following steps:
* reads the current AUXV using prctl(PR_GET_AUXV);
* finds an HWCAP entry and toggles its most significant bit;
* replaces the AUXV of the current process with the modified one using
prctl(PR_SET_MM, PR_SET_MM_AUXV);
* executes itself to verify that the new program sees the modified HWCAP
value.
Signed-off-by: Andrei Vagin <avagin@google.com>
---
tools/testing/selftests/exec/.gitignore | 1 +
tools/testing/selftests/exec/Makefile | 1 +
tools/testing/selftests/exec/hwcap_inherit.c | 104 +++++++++++++++++++
3 files changed, 106 insertions(+)
create mode 100644 tools/testing/selftests/exec/hwcap_inherit.c
diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore
index 7f3d1ae762ec..2ff245fd0ba6 100644
--- a/tools/testing/selftests/exec/.gitignore
+++ b/tools/testing/selftests/exec/.gitignore
@@ -19,3 +19,4 @@ null-argv
xxxxxxxx*
pipe
S_I*.test
+hwcap_inherit
\ No newline at end of file
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 45a3cfc435cf..e73005965e05 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -20,6 +20,7 @@ TEST_FILES := Makefile
TEST_GEN_PROGS += recursion-depth
TEST_GEN_PROGS += null-argv
TEST_GEN_PROGS += check-exec
+TEST_GEN_PROGS += hwcap_inherit
EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \
$(OUTPUT)/S_I*.test
diff --git a/tools/testing/selftests/exec/hwcap_inherit.c b/tools/testing/selftests/exec/hwcap_inherit.c
new file mode 100644
index 000000000000..ef80a010765d
--- /dev/null
+++ b/tools/testing/selftests/exec/hwcap_inherit.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <linux/prctl.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <elf.h>
+#include <linux/auxvec.h>
+
+#include "../kselftest.h"
+
+static int find_msb(unsigned long v)
+{
+ return sizeof(v)*8 - __builtin_clzl(v) - 1;
+}
+
+int main(int argc, char *argv[])
+{
+ unsigned long auxv[1024], hwcap, new_hwcap, hwcap_idx;
+ int size, hwcap_type = 0, hwcap_feature, count, status;
+ char hwcap_str[32], hwcap_type_str[32];
+ pid_t pid;
+
+ if (argc > 1 && strcmp(argv[1], "verify") == 0) {
+ unsigned long type = strtoul(argv[2], NULL, 16);
+ unsigned long expected = strtoul(argv[3], NULL, 16);
+ unsigned long hwcap = getauxval(type);
+
+ if (hwcap != expected) {
+ ksft_print_msg("HWCAP mismatch: type %lx, expected %lx, got %lx\n",
+ type, expected, hwcap);
+ return 1;
+ }
+ ksft_print_msg("HWCAP matched: %lx\n", hwcap);
+ return 0;
+ }
+
+ ksft_print_header();
+ ksft_set_plan(1);
+
+ size = prctl(PR_GET_AUXV, auxv, sizeof(auxv), 0, 0);
+ if (size == -1)
+ ksft_exit_fail_perror("prctl(PR_GET_AUXV)");
+
+ count = size / sizeof(unsigned long);
+
+ /* Find the "latest" feature and try to mask it out. */
+ for (int i = 0; i < count - 1; i += 2) {
+ hwcap = auxv[i + 1];
+ if (hwcap == 0)
+ continue;
+ switch (auxv[i]) {
+ case AT_HWCAP4:
+ case AT_HWCAP3:
+ case AT_HWCAP2:
+ case AT_HWCAP:
+ hwcap_type = auxv[i];
+ hwcap_feature = find_msb(hwcap);
+ hwcap_idx = i + 1;
+ break;
+ default:
+ continue;
+ }
+ }
+ if (hwcap_type == 0)
+ ksft_exit_skip("No features found, skipping test\n");
+ new_hwcap = hwcap ^ (1UL << hwcap_feature);
+ auxv[hwcap_idx] = new_hwcap;
+
+ if (prctl(PR_SET_MM, PR_SET_MM_AUXV, auxv, size, 0) < 0) {
+ if (errno == EPERM)
+ ksft_exit_skip("prctl(PR_SET_MM_AUXV) requires CAP_SYS_RESOURCE\n");
+ ksft_exit_fail_perror("prctl(PR_SET_MM_AUXV)");
+ }
+
+ pid = fork();
+ if (pid < 0)
+ ksft_exit_fail_perror("fork");
+ if (pid == 0) {
+ char *new_argv[] = { argv[0], "verify", hwcap_type_str, hwcap_str, NULL };
+
+ snprintf(hwcap_str, sizeof(hwcap_str), "%lx", new_hwcap);
+ snprintf(hwcap_type_str, sizeof(hwcap_type_str), "%x", hwcap_type);
+
+ execv(argv[0], new_argv);
+ perror("execv");
+ exit(1);
+ }
+
+ if (waitpid(pid, &status, 0) == -1)
+ ksft_exit_fail_perror("waitpid");
+ if (status != 0)
+ ksft_exit_fail_msg("HWCAP inheritance failed (status %d)\n", status);
+
+ ksft_test_result_pass("HWCAP inheritance succeeded\n");
+ ksft_exit_pass();
+ return 0;
+}
--
2.52.0.351.gbe84eed79e-goog
^ permalink raw reply [flat|nested] 5+ messages in thread