A task in the kernel (task_mm_cid_work) runs somewhat periodically to
compact the mm_cid for each process. Add a test to validate that it runs
correctly and timely.
The test spawns 1 thread pinned to each CPU, then each thread, including
the main one, runs in short bursts for some time. During this period, the
mm_cids should be spanning all numbers between 0 and nproc.
At the end of this phase, a thread with high enough mm_cid (>= nproc/2)
is selected to be the new leader, all other threads terminate.
After some time, the only running thread should see 0 as mm_cid, if that
doesn't happen, the compaction mechanism didn't work and the test fails.
The test never fails if only 1 core is available, in which case, we
cannot test anything as the only available mm_cid is 0.
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com>
Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com>
---
tools/testing/selftests/rseq/.gitignore | 1 +
tools/testing/selftests/rseq/Makefile | 2 +-
.../selftests/rseq/mm_cid_compaction_test.c | 200 ++++++++++++++++++
3 files changed, 202 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c
diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore
index 16496de5f6ce4..2c89f97e4f737 100644
--- a/tools/testing/selftests/rseq/.gitignore
+++ b/tools/testing/selftests/rseq/.gitignore
@@ -3,6 +3,7 @@ basic_percpu_ops_test
basic_percpu_ops_mm_cid_test
basic_test
basic_rseq_op_test
+mm_cid_compaction_test
param_test
param_test_benchmark
param_test_compare_twice
diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile
index 5a3432fceb586..ce1b38f46a355 100644
--- a/tools/testing/selftests/rseq/Makefile
+++ b/tools/testing/selftests/rseq/Makefile
@@ -16,7 +16,7 @@ OVERRIDE_TARGETS = 1
TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \
param_test_benchmark param_test_compare_twice param_test_mm_cid \
- param_test_mm_cid_benchmark param_test_mm_cid_compare_twice
+ param_test_mm_cid_benchmark param_test_mm_cid_compare_twice mm_cid_compaction_test
TEST_GEN_PROGS_EXTENDED = librseq.so
diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c
new file mode 100644
index 0000000000000..7ddde3b657dd6
--- /dev/null
+++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: LGPL-2.1
+#define _GNU_SOURCE
+#include <assert.h>
+#include <pthread.h>
+#include <sched.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+
+#include "../kselftest.h"
+#include "rseq.h"
+
+#define VERBOSE 0
+#define printf_verbose(fmt, ...) \
+ do { \
+ if (VERBOSE) \
+ printf(fmt, ##__VA_ARGS__); \
+ } while (0)
+
+/* 0.5 s */
+#define RUNNER_PERIOD 500000
+/* Number of runs before we terminate or get the token */
+#define THREAD_RUNS 5
+
+/*
+ * Number of times we check that the mm_cid were compacted.
+ * Checks are repeated every RUNNER_PERIOD.
+ */
+#define MM_CID_COMPACT_TIMEOUT 10
+
+struct thread_args {
+ int cpu;
+ int num_cpus;
+ pthread_mutex_t *token;
+ pthread_barrier_t *barrier;
+ pthread_t *tinfo;
+ struct thread_args *args_head;
+};
+
+static void __noreturn *thread_runner(void *arg)
+{
+ struct thread_args *args = arg;
+ int i, ret, curr_mm_cid;
+ cpu_set_t cpumask;
+
+ CPU_ZERO(&cpumask);
+ CPU_SET(args->cpu, &cpumask);
+ ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask);
+ if (ret) {
+ errno = ret;
+ perror("Error: failed to set affinity");
+ abort();
+ }
+ pthread_barrier_wait(args->barrier);
+
+ for (i = 0; i < THREAD_RUNS; i++)
+ usleep(RUNNER_PERIOD);
+ curr_mm_cid = rseq_current_mm_cid();
+ /*
+ * We select one thread with high enough mm_cid to be the new leader.
+ * All other threads (including the main thread) will terminate.
+ * After some time, the mm_cid of the only remaining thread should
+ * converge to 0, if not, the test fails.
+ */
+ if (curr_mm_cid >= args->num_cpus / 2 &&
+ !pthread_mutex_trylock(args->token)) {
+ printf_verbose(
+ "cpu%d has mm_cid=%d and will be the new leader.\n",
+ sched_getcpu(), curr_mm_cid);
+ for (i = 0; i < args->num_cpus; i++) {
+ if (args->tinfo[i] == pthread_self())
+ continue;
+ ret = pthread_join(args->tinfo[i], NULL);
+ if (ret) {
+ errno = ret;
+ perror("Error: failed to join thread");
+ abort();
+ }
+ }
+ pthread_barrier_destroy(args->barrier);
+ free(args->tinfo);
+ free(args->token);
+ free(args->barrier);
+ free(args->args_head);
+
+ for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) {
+ curr_mm_cid = rseq_current_mm_cid();
+ printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i,
+ curr_mm_cid, sched_getcpu());
+ if (curr_mm_cid == 0)
+ exit(EXIT_SUCCESS);
+ usleep(RUNNER_PERIOD);
+ }
+ exit(EXIT_FAILURE);
+ }
+ printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n",
+ sched_getcpu(), curr_mm_cid);
+ pthread_exit(NULL);
+}
+
+int test_mm_cid_compaction(void)
+{
+ cpu_set_t affinity;
+ int i, j, ret = 0, num_threads;
+ pthread_t *tinfo;
+ pthread_mutex_t *token;
+ pthread_barrier_t *barrier;
+ struct thread_args *args;
+
+ sched_getaffinity(0, sizeof(affinity), &affinity);
+ num_threads = CPU_COUNT(&affinity);
+ tinfo = calloc(num_threads, sizeof(*tinfo));
+ if (!tinfo) {
+ perror("Error: failed to allocate tinfo");
+ return -1;
+ }
+ args = calloc(num_threads, sizeof(*args));
+ if (!args) {
+ perror("Error: failed to allocate args");
+ ret = -1;
+ goto out_free_tinfo;
+ }
+ token = malloc(sizeof(*token));
+ if (!token) {
+ perror("Error: failed to allocate token");
+ ret = -1;
+ goto out_free_args;
+ }
+ barrier = malloc(sizeof(*barrier));
+ if (!barrier) {
+ perror("Error: failed to allocate barrier");
+ ret = -1;
+ goto out_free_token;
+ }
+ if (num_threads == 1) {
+ fprintf(stderr, "Cannot test on a single cpu. "
+ "Skipping mm_cid_compaction test.\n");
+ /* only skipping the test, this is not a failure */
+ goto out_free_barrier;
+ }
+ pthread_mutex_init(token, NULL);
+ ret = pthread_barrier_init(barrier, NULL, num_threads);
+ if (ret) {
+ errno = ret;
+ perror("Error: failed to initialise barrier");
+ goto out_free_barrier;
+ }
+ for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) {
+ if (!CPU_ISSET(i, &affinity))
+ continue;
+ args[j].num_cpus = num_threads;
+ args[j].tinfo = tinfo;
+ args[j].token = token;
+ args[j].barrier = barrier;
+ args[j].cpu = i;
+ args[j].args_head = args;
+ if (!j) {
+ /* The first thread is the main one */
+ tinfo[0] = pthread_self();
+ ++j;
+ continue;
+ }
+ ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]);
+ if (ret) {
+ errno = ret;
+ perror("Error: failed to create thread");
+ abort();
+ }
+ ++j;
+ }
+ printf_verbose("Started %d threads.\n", num_threads);
+
+ /* Also main thread will terminate if it is not selected as leader */
+ thread_runner(&args[0]);
+
+ /* only reached in case of errors */
+out_free_barrier:
+ free(barrier);
+out_free_token:
+ free(token);
+out_free_args:
+ free(args);
+out_free_tinfo:
+ free(tinfo);
+
+ return ret;
+}
+
+int main(int argc, char **argv)
+{
+ if (!rseq_mm_cid_available()) {
+ fprintf(stderr, "Error: rseq_mm_cid unavailable\n");
+ return -1;
+ }
+ if (test_mm_cid_compaction())
+ return -1;
+ return 0;
+}
--
2.48.1
While taking a look at '[PATCH net] pktgen: Avoid out-of-range in
get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds
access in get_imix_entries' ([2], [3]) and doing some tests and code review
I detected that the /proc/net/pktgen/... parsing logic does not honour the
user given buffer bounds (resulting in out-of-bounds access).
This can be observed e.g. by the following simple test (sometimes the
old/'longer' previous value is re-read from the buffer):
$ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0
$ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0
Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0
Result: OK: min_pkt_size=12345
$ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0
Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0
Result: OK: min_pkt_size=12345
$ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0
Params: count 1000 min_pkt_size: 123 max_pkt_size: 0
Result: OK: min_pkt_size=123
So fix the out-of-bounds access (and some minor findings) and add a simple
proc_net_pktgen selftest...
Patch set splited into part I (now already applied to net-next)
- net: pktgen: replace ENOTSUPP with EOPNOTSUPP
- net: pktgen: enable 'param=value' parsing
- net: pktgen: fix hex32_arg parsing for short reads
- net: pktgen: fix 'rate 0' error handling (return -EINVAL)
- net: pktgen: fix 'ratep 0' error handling (return -EINVAL)
- net: pktgen: fix ctrl interface command parsing
- net: pktgen: fix access outside of user given buffer in pktgen_thread_write()
And part II (this one):
- net: pktgen: use defines for the various dec/hex number parsing digits lengths
- net: pktgen: fix mix of int/long
- net: pktgen: remove extra tmp variable (re-use len instead)
- net: pktgen: remove some superfluous variable initializing
- net: pktgen: fix mpls maximum labels list parsing
- net: pktgen: fix access outside of user given buffer in pktgen_if_write()
- net: pktgen: fix mpls reset parsing
- net: pktgen: remove all superfluous index assignements
- selftest: net: add proc_net_pktgen
Regards,
Peter
Changes v6 -> v7:
- rebased on actual net-next/main
- selftest: net: add proc_net_pktgen
- fixed conflict in tools/testing/selftests/net/config
Changes v5 -> v6:
- add rev-by Simon Horman
- drop patch 'net: pktgen: use defines for the various dec/hex number
parsing digits lengths'
- adjust to dropped patch ''net: pktgen: use defines for the various
dec/hex number parsing digits lengths'
- net: pktgen: fix mix of int/long
- fix line break (suggested by Simon Horman)
Changes v4 -> v5:
- split up patchset into part i/ii (suggested by Simon Horman)
- add rev-by Simon Horman
- net: pktgen: align some variable declarations to the most common pattern
-> net: pktgen: fix mix of int/long
- instead of align to most common pattern (int) adjust all usages to
size_t for i and max and ssize_t for len and adjust function signatures
of hex32_arg(), count_trail_chars(), num_arg() and strn_len() accordingly
- respect reverse xmas tree order for local variable declarations (where
possible without too much code churn)
- update subject line and patch description
- dropped net: pktgen: hex32_arg/num_arg error out in case no characters are
available
- keep empty hex/num arg is implicit assumed as zero value
- dropped net: pktgen: num_arg error out in case no valid character is parsed
- keep empty hex/num arg is implicit assumed as zero value
- Change patch description ('Fixes:' -> 'Addresses the following:',
suggested by Simon Horman)
- net: pktgen: remove all superfluous index assignements
- new patch (suggested by Simon Horman)
- selftest: net: add proc_net_pktgen
- addapt to dropped patch 'net: pktgen: hex32_arg/num_arg error out in case
no characters are available', empty hex/num arg is now implicit assumed as
zero value (instead of failure)
Changes v3 -> v4:
- add rev-by Simon Horman
- new patch 'net: pktgen: use defines for the various dec/hex number parsing
digits lengths' (suggested by Simon Horman)
- replace C99 comment (suggested by Paolo Abeni)
- drop available characters check in strn_len() (suggested by Paolo Abeni)
- factored out patch 'net: pktgen: align some variable declarations to the
most common pattern' (suggested by Paolo Abeni)
- factored out patch 'net: pktgen: remove extra tmp variable (re-use len
instead)' (suggested by Paolo Abeni)
- factored out patch 'net: pktgen: remove some superfluous variable
initializing' (suggested by Paolo Abeni)
- factored out patch 'net: pktgen: fix mpls maximum labels list parsing'
(suggested by Paolo Abeni)
- factored out 'net: pktgen: hex32_arg/num_arg error out in case no
characters are available' (suggested by Paolo Abeni)
- factored out 'net: pktgen: num_arg error out in case no valid character
is parsed' (suggested by Paolo Abeni)
Changes v2 -> v3:
- new patch: 'net: pktgen: fix ctrl interface command parsing'
- new patch: 'net: pktgen: fix mpls reset parsing'
- tools/testing/selftests/net/proc_net_pktgen.c:
- fix typo in change description ('v1 -> v1' and tyop)
- rename some vars to better match usage
add_loopback_0 -> thr_cmd_add_loopback_0
rm_loopback_0 -> thr_cmd_rm_loopback_0
wrong_ctrl_cmd -> wrong_thr_cmd
legacy_ctrl_cmd -> legacy_thr_cmd
ctrl_fd -> thr_fd
- add ctrl interface tests
Changes v1 -> v2:
- new patch: 'net: pktgen: fix hex32_arg parsing for short reads'
- new patch: 'net: pktgen: fix 'rate 0' error handling (return -EINVAL)'
- new patch: 'net: pktgen: fix 'ratep 0' error handling (return -EINVAL)'
- net/core/pktgen.c: additional fix get_imix_entries() and get_labels()
- tools/testing/selftests/net/proc_net_pktgen.c:
- fix tyop not vs. nod (suggested by Jakub Kicinski)
- fix misaligned line (suggested by Jakub Kicinski)
- enable fomerly commented out CONFIG_XFRM dependent test (command spi),
as CONFIG_XFRM is enabled via tools/testing/selftests/net/config
CONFIG_XFRM_INTERFACE/CONFIG_XFRM_USER (suggestex by Jakub Kicinski)
- add CONFIG_NET_PKTGEN=m to tools/testing/selftests/net/config
(suggested by Jakub Kicinski)
- add modprobe pktgen to FIXTURE_SETUP() (suggested by Jakub Kicinski)
- fix some checkpatch warnings (Missing a blank line after declarations)
- shrink line length by re-naming some variables (command -> cmd,
device -> dev)
- add 'rate 0' testcase
- add 'ratep 0' testcase
[1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re…
[2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/
[3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?…
Peter Seiderer (8):
net: pktgen: fix mix of int/long
net: pktgen: remove extra tmp variable (re-use len instead)
net: pktgen: remove some superfluous variable initializing
net: pktgen: fix mpls maximum labels list parsing
net: pktgen: fix access outside of user given buffer in
pktgen_if_write()
net: pktgen: fix mpls reset parsing
net: pktgen: remove all superfluous index assignements
selftest: net: add proc_net_pktgen
net/core/pktgen.c | 288 ++++----
tools/testing/selftests/net/Makefile | 1 +
tools/testing/selftests/net/config | 1 +
tools/testing/selftests/net/proc_net_pktgen.c | 646 ++++++++++++++++++
4 files changed, 805 insertions(+), 131 deletions(-)
create mode 100644 tools/testing/selftests/net/proc_net_pktgen.c
--
2.48.1
There is a spelling mistake in a sig_print message. Fix it.
Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com>
---
tools/testing/selftests/x86/xstate.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/x86/xstate.c b/tools/testing/selftests/x86/xstate.c
index 875777911d82..23c1d6c964ea 100644
--- a/tools/testing/selftests/x86/xstate.c
+++ b/tools/testing/selftests/x86/xstate.c
@@ -391,7 +391,7 @@ static void validate_sigfpstate(int sig, siginfo_t *si, void *ctx_void)
if (get_xstatebv(xbuf) & xstate.mask)
sig_print("[OK]\t'xfeatures' in XSAVE header is valid\n");
else
- sig_print("[FAIL]\t'xfeatures' in XSAVE hader is not valid\n");
+ sig_print("[FAIL]\t'xfeatures' in XSAVE header is not valid\n");
if (validate_xstate_same(stashed_xbuf, xbuf))
sig_print("[OK]\txstate delivery was successful\n");
--
2.47.2
Fix grammar such as "number amount of times is
recommended" etc -> "the recommended number of
times".
Signed-off-by: Bharadwaj Raju <bharadwaj.raju777(a)gmail.com>
---
tools/testing/selftests/sysctl/sysctl.sh | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index f6e129a82ffd..db1616857d89 100755
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -857,7 +857,7 @@ list_tests()
echo
echo "TEST_ID x NUM_TEST"
echo "TEST_ID: Test ID"
- echo "NUM_TESTS: Number of recommended times to run the test"
+ echo "NUM_TESTS: Recommended number of times to run the test"
echo
echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()"
echo "0002 x $(get_test_count 0002) - tests proc_dostring()"
@@ -884,7 +884,7 @@ usage()
echo "Valid tests: 0001-$MAX_TEST"
echo ""
echo " all Runs all tests (default)"
- echo " -t Run test ID the number amount of times is recommended"
+ echo " -t Run test ID the recommended number of times"
echo " -w Watch test ID run until it runs into an error"
echo " -c Run test ID once"
echo " -s Run test ID x test-count number of times"
@@ -898,7 +898,7 @@ usage()
echo Example uses:
echo
echo "$TEST_NAME.sh -- executes all tests"
- echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 number of times is recommended"
+ echo "$TEST_NAME.sh -t 0002 -- Executes test ID 0002 the recommended number of times"
echo "$TEST_NAME.sh -w 0002 -- Watch test ID 0002 run until an error occurs"
echo "$TEST_NAME.sh -s 0002 -- Run test ID 0002 once"
echo "$TEST_NAME.sh -c 0002 3 -- Run test ID 0002 three times"
--
2.48.1
From: Willem de Bruijn <willemb(a)google.com>
Expand IPV6_TCLASS to also cover IP_TOS.
Expand IPV6_HOPLIMIT to also cover IP_TTL.
A series of two patches for basic readability (patch 1 is a noop),
and so that git does not interpret code changes + file rename as
a whole file del + add.
Willem de Bruijn (2):
selftests/net: prepare cmsg_ipv6.sh for ipv4
selftests/net: expand cmsg_ipv6.sh with ipv4
tools/testing/selftests/net/Makefile | 2 +-
tools/testing/selftests/net/cmsg_ip.sh | 184 ++++++++++++++++++++++
tools/testing/selftests/net/cmsg_ipv6.sh | 154 ------------------
tools/testing/selftests/net/cmsg_sender.c | 90 +++++++----
4 files changed, 240 insertions(+), 190 deletions(-)
create mode 100755 tools/testing/selftests/net/cmsg_ip.sh
delete mode 100755 tools/testing/selftests/net/cmsg_ipv6.sh
--
2.48.1.658.g4767266eb4-goog
Commit 14be4e6f3522 ("selftests: vDSO: fix ELF hash table entry size for s390x")
changed the type of the ELF hash table entries to 64bit on s390x.
However the *GNU* hash tables entries are always 32bit.
The "bucket" pointer is shared between both hash algorithms.
On s390x the GNU algorithm assigns and dereferences this pointer to a
64bit value as a pointer to a 32bit value, leading to compiler warnings and
runtime crashes.
Introduce a new dedicated "gnu_bucket" pointer which is used by the GNU hash.
Fixes: e0746bde6f82 ("selftests/vDSO: support DT_GNU_HASH")
Reviewed-by: Jens Remus <jremus(a)linux.ibm.com>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>
---
Changes in v2:
- Fix wording around the width of pointers vs the pointed-to values
- Link to v1: https://lore.kernel.org/r/20250213-selftests-vdso-s390-gnu-hash-v1-1-ace3bc…
---
tools/testing/selftests/vDSO/parse_vdso.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 2fe5e983cb22f1ed066d0310a54f6aef2ed77ed8..f89d052c730eb43eea28d69ca27b56e897503e16 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -53,7 +53,7 @@ static struct vdso_info
/* Symbol table */
ELF(Sym) *symtab;
const char *symstrings;
- ELF(Word) *gnu_hash;
+ ELF(Word) *gnu_hash, *gnu_bucket;
ELF_HASH_ENTRY *bucket, *chain;
ELF_HASH_ENTRY nbucket, nchain;
@@ -185,8 +185,8 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
/* The bucket array is located after the header (4 uint32) and the bloom
* filter (size_t array of gnu_hash[2] elements).
*/
- vdso_info.bucket = vdso_info.gnu_hash + 4 +
- sizeof(size_t) / 4 * vdso_info.gnu_hash[2];
+ vdso_info.gnu_bucket = vdso_info.gnu_hash + 4 +
+ sizeof(size_t) / 4 * vdso_info.gnu_hash[2];
} else {
vdso_info.nbucket = hash[0];
vdso_info.nchain = hash[1];
@@ -268,11 +268,11 @@ void *vdso_sym(const char *version, const char *name)
if (vdso_info.gnu_hash) {
uint32_t h1 = gnu_hash(name), h2, *hashval;
- i = vdso_info.bucket[h1 % vdso_info.nbucket];
+ i = vdso_info.gnu_bucket[h1 % vdso_info.nbucket];
if (i == 0)
return 0;
h1 |= 1;
- hashval = vdso_info.bucket + vdso_info.nbucket +
+ hashval = vdso_info.gnu_bucket + vdso_info.nbucket +
(i - vdso_info.gnu_hash[1]);
for (;; i++) {
ELF(Sym) *sym = &vdso_info.symtab[i];
---
base-commit: 2014c95afecee3e76ca4a56956a936e23283f05b
change-id: 20250213-selftests-vdso-s390-gnu-hash-7206671abc85
Best regards,
--
Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>
The implementation is limited and only supports numeric arguments.
Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net>
---
Changes in v2:
- Return __LINE__ from different testcases to directly point to the
failed testcase
- Add some comments
- Expand commit message
- Link to v1: https://lore.kernel.org/r/20240731-nolibc-scanf-v1-0-f71bcc4abb9e@weissschu…
---
Thomas Weißschuh (2):
tools/nolibc: add support for [v]sscanf()
Revert "selftests: kselftest: Fix build failure with NOLIBC"
tools/include/nolibc/stdio.h | 98 ++++++++++++++++++++++++++++
tools/testing/selftests/kselftest.h | 5 --
tools/testing/selftests/nolibc/nolibc-test.c | 68 +++++++++++++++++++
3 files changed, 166 insertions(+), 5 deletions(-)
---
base-commit: 665fa8dea90d9fbc0e7137c7e1315d6f7e15757e
change-id: 20240414-nolibc-scanf-f1db6930d0c6
Best regards,
--
Thomas Weißschuh <linux(a)weissschuh.net>
Hi all,
This patchset adds a new buddy allocator like (or non-uniform) large folio
split from a order-n folio to order-m with m < n. It reduces
1. the total number of after-split folios from 2^(n-m) to n-m+1;
2. the amount of memory needed for multi-index xarray split from 2^(n/6-m/6) to
n/6-m/6, assuming XA_CHUNK_SHIFT=6;
3. keep more large folios after a split from all order-m folios to
order-(n-1) to order-m folios.
For example, to split an order-9 to order-0, folio split generates 10
(or 11 for anonymous memory) folios instead of 512, allocates 1 xa_node
instead of 8, and leaves 1 order-8, 1 order-7, ..., 1 order-1 and 2 order-0
folios (or 4 order-0 for anonymous memory) instead of 512 order-0 folios.
It is on top of mm-everything-2025-02-15-05-49 with V7 reverted. It is ready to
be merged.
Instead of duplicating existing split_huge_page*() code, __folio_split()
is introduced as the shared backend code for both
split_huge_page_to_list_to_order() and folio_split(). __folio_split()
can support both uniform split and buddy allocator like (or non-uniform) split.
All existing split_huge_page*() users can be gradually converted to use
folio_split() if possible. In this patchset, I converted
truncate_inode_partial_folio() to use folio_split().
xfstests quick group passed for both tmpfs and xfs.
Changelog
===
From V7[9]:
1. Fixed a wrong function name in lib/test_xarray.c.
2. Made __split_folio_to_order() never fail, since the old order check
is already done in __folio_split(). (per David Hildenbrand)
3. Fixed an issue reported by syzbot[10] by not dropping the original
folio during truncate.
4. Fixed a WARNING when READ_ONLY_THP_FOR_FS is enabled. (Thank David
Hildenbrand for reporting the issue)
5. Used two separate struct page* parameters, split_at and lock_at, to
specify at which subpage the non-uniform split happens and which subpage
to keep locked after the split, respectively. It improves code
readability.
From V6[8]:
1. Added an xarray function xas_try_split() to support iterative folio split,
removing the need of using xas_split_alloc() and xas_split(). The
function guarantees that at most one xa_node is allocated for each
call.
2. Added concrete numbers of after-split folios and xa_node savings to
cover letter, commit log. (per Andrew)
From V5[7]:
1. Split shmem to any lower order patches are in mm tree, so dropped
from this series.
2. Rename split_folio_at() to try_folio_split() to clarify that
non-uniform split will not be used if it is not supported.
From V4[6]:
1. Enabled shmem support in both uniform and buddy allocator like split
and added selftests for it.
2. Added functions to check if uniform split and buddy allocator like
split are supported for the given folio and order.
3. Made truncate fall back to uniform split if buddy allocator split is
not supported (CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio).
4. Added the missing folio_clear_has_hwpoisoned() to
__split_unmapped_folio().
From V3[5]:
1. Used xas_split_alloc(GFP_NOWAIT) instead of xas_nomem(), since extra
operations inside xas_split_alloc() are needed for correctness.
2. Enabled folio_split() for shmem and no issue was found with xfstests
quick test group.
3. Split both ends of a truncate range in truncate_inode_partial_folio()
to avoid wasting memory in shmem truncate (per David Hildenbrand).
4. Removed page_in_folio_offset() since page_folio() does the same
thing.
5. Finished truncate related tests from xfstests quick test group on XFS and
tmpfs without issues.
6. Disabled buddy allocator like split on CONFIG_READ_ONLY_THP_FOR_FS
and FS without large folio. This check was missed in the prior
versions.
From V2[3]:
1. Incorporated all the feedback from Kirill[4].
2. Used GFP_NOWAIT for xas_nomem().
3. Tested the code path when xas_nomem() fails.
4. Added selftests for folio_split().
5. Fixed no THP config build error.
From V1[2]:
1. Split the original patch 1 into multiple ones for easy review (per
Kirill).
2. Added xas_destroy() to avoid memory leak.
3. Fixed nr_dropped not used error (per kernel test robot).
4. Added proper error handling when xas_nomem() fails to allocate memory
for xas_split() during buddy allocator like split.
From RFC[1]:
1. Merged backend code of split_huge_page_to_list_to_order() and
folio_split(). The same code is used for both uniform split and buddy
allocator like split.
2. Use xas_nomem() instead of xas_split_alloc() for folio_split().
3. folio_split() now leaves the first after-split folio unlocked,
instead of the one containing the given page, since
the caller of truncate_inode_partial_folio() locks and unlocks the
first folio.
4. Extended split_huge_page debugfs to use folio_split().
5. Added truncate_inode_partial_folio() as first user of folio_split().
Design
===
folio_split() splits a large folio in the same way as buddy allocator
splits a large free page for allocation. The purpose is to minimize the
number of folios after the split. For example, if user wants to free the
3rd subpage in a order-9 folio, folio_split() will split the order-9 folio
as:
O-0, O-0, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-8 if it is anon
O-1, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache
Since anon folio does not support order-1 yet.
The split process is similar to existing approach:
1. Unmap all page mappings (split PMD mappings if exist);
2. Split meta data like memcg, page owner, page alloc tag;
3. Copy meta data in struct folio to sub pages, but instead of spliting
the whole folio into multiple smaller ones with the same order in a
shot, this approach splits the folio iteratively. Taking the example
above, this approach first splits the original order-9 into two order-8,
then splits left part of order-8 to two order-7 and so on;
4. Post-process split folios, like write mapping->i_pages for pagecache,
adjust folio refcounts, add split folios to corresponding list;
5. Remap split folios
6. Unlock split folios.
__split_unmapped_folio() and __split_folio_to_order() replace
__split_huge_page() and __split_huge_page_tail() respectively.
__split_unmapped_folio() uses different approaches to perform
uniform split and buddy allocator like split:
1. uniform split: one single call to __split_folio_to_order() is used to
uniformly split the given folio. All resulting folios are put back to
the list after split. The folio containing the given page is left to
caller to unlock and others are unlocked.
2. buddy allocator like (or non-uniform) split: (old_order - new_order) calls
to __split_folio_to_order() are used to split the given folio at order N to
order N-1. After each call, the target folio is changed to the one
containing the page, which is given as a folio_split() parameter.
After each call, folios not containing the page are put back to the list.
The folio containing the page is put back to the list when its order
is new_order. All folios are unlocked except the first folio, which
is left to caller to unlock.
Patch Overview
===
1. Patch 1 added a new xarray function xas_try_split() to perform
iterative xarray split.
2. Patch 2 added __split_unmapped_folio() and __split_folio_to_order() to
prepare for moving to new backend split code.
3. Patch 3 moved common code in split_huge_page_to_list_to_order() to
__folio_split().
4. Patch 4 added new folio_split() and made
split_huge_page_to_list_to_order() share the new
__split_unmapped_folio() with folio_split().
5. Patch 5 removed no longer used __split_huge_page() and
__split_huge_page_tail().
6. Patch 6 added a new in_folio_offset to split_huge_page debugfs for
folio_split() test.
7. Patch 7 used try_folio_split() for truncate operation.
8. Patch 8 added folio_split() tests.
Any comments and/or suggestions are welcome. Thanks.
[1] https://lore.kernel.org/linux-mm/20241008223748.555845-1-ziy@nvidia.com/
[2] https://lore.kernel.org/linux-mm/20241028180932.1319265-1-ziy@nvidia.com/
[3] https://lore.kernel.org/linux-mm/20241101150357.1752726-1-ziy@nvidia.com/
[4] https://lore.kernel.org/linux-mm/e6ppwz5t4p4kvir6eqzoto4y5fmdjdxdyvxvtw43nc…
[5] https://lore.kernel.org/linux-mm/20241205001839.2582020-1-ziy@nvidia.com/
[6] https://lore.kernel.org/linux-mm/20250106165513.104899-1-ziy@nvidia.com/
[7] https://lore.kernel.org/linux-mm/20250116211042.741543-1-ziy@nvidia.com/
[8] https://lore.kernel.org/linux-mm/20250205031417.1771278-1-ziy@nvidia.com/
[9] https://lore.kernel.org/linux-mm/20250211155034.268962-1-ziy@nvidia.com/
[10] https://lore.kernel.org/all/67af65cb.050a0220.21dd3.004a.GAE@google.com/
Zi Yan (8):
xarray: add xas_try_split() to split a multi-index entry
mm/huge_memory: add two new (not yet used) functions for folio_split()
mm/huge_memory: move folio split common code to __folio_split()
mm/huge_memory: add buddy allocator like (non-uniform) folio_split()
mm/huge_memory: remove the old, unused __split_huge_page()
mm/huge_memory: add folio_split() to debugfs testing interface
mm/truncate: use buddy allocator like folio split for truncate
operation
selftests/mm: add tests for folio_split(), buddy allocator like split
Documentation/core-api/xarray.rst | 14 +-
include/linux/huge_mm.h | 36 +
include/linux/xarray.h | 7 +
lib/test_xarray.c | 47 ++
lib/xarray.c | 138 +++-
mm/huge_memory.c | 756 ++++++++++++------
mm/truncate.c | 31 +-
tools/testing/radix-tree/Makefile | 1 +
.../selftests/mm/split_huge_page_test.c | 34 +-
9 files changed, 783 insertions(+), 281 deletions(-)
--
2.47.2
The uprobe events test fails on s390, but also on x86 (Fedora 41). The
problem appears to be that there is an assumption that adding a uprobe to
the beginning of the executable mapping of /bin/sh is sufficient to trigger
a uprobe event when /bin/sh is executed.
This assumption is not necessarily true. Therefore use "readelf -h" to find
the entry point address of /bin/sh and use this address when adding the
uprobe event.
This adds a dependency to readelf which is not always installed. Therefore
add a check and exit with exit_unresolved if it is not installed.
Signed-off-by: Heiko Carstens <hca(a)linux.ibm.com>
---
.../ftrace/test.d/dynevent/add_remove_uprobe.tc | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc
index 86c76679c56e..f2048c244526 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc
@@ -3,14 +3,18 @@
# description: Generic dynamic event - add/remove/test uprobe events
# requires: uprobe_events
+if ! which readelf > /dev/null 2>&1 ; then
+ echo "No readelf found. skipped."
+ exit_unresolved
+fi
+
echo 0 > events/enable
echo > dynamic_events
REALBIN=`readlink -f /bin/sh`
+ENTRYPOINT=`readelf -h ${REALBIN} | grep Entry | sed -e 's/[^0]*//'`
-echo 'cat /proc/$$/maps' | /bin/sh | \
- grep "r-xp .*${REALBIN}$" | \
- awk '{printf "p:myevent %s:0x%s\n", $6,$3 }' >> uprobe_events
+echo "p:myevent ${REALBIN}:${ENTRYPOINT}" >> uprobe_events
grep -q myevent uprobe_events
test -d events/uprobes/myevent
--
2.45.2