May 2025 - Linux-kselftest-mirror

[PATCH] kselftests/x86: Correct grammer in VMX pairing message

by Sukrut Heroorkar

Fixes a small grammatical error in the print message. signed-off-by: Sukrut Heroorkar <hsukrut3(a)gmail.com> --- tools/testing/selftests/x86/ioperm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/x86/ioperm.c b/tools/testing/selftests/x86/ioperm.c index 69d5fb7050c2..a5099e526912 100644 --- a/tools/testing/selftests/x86/ioperm.c +++ b/tools/testing/selftests/x86/ioperm.c @@ -107,7 +107,7 @@ int main(void) err(1, "fork"); if (child == 0) { - printf("[RUN]\tchild: check that we inherited permissions\n"); + printf("[RUN]\tchild: check that if we inherited permissions\n"); expect_ok(0x80); expect_gp(0xed); printf("[RUN]\tchild: Extend permissions to 0x81\n"); -- 2.43.0

5 days, 2 hours

2
1
0 0

[PATCH] selftests/mm: compaction_test: convert comments to preferred style

by George Anthony Vernon

Convert multi-line comments to preferred style with beginning and ending almost-blank lines. Signed-off-by: George Anthony Vernon <contact(a)gvernon.com> --- tools/testing/selftests/mm/compaction_test.c | 22 +++++++++++++------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 2c3a0eb6b22d..b217ec4a434b 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 /* - * * A test for the patch "Allow compaction of unevictable pages". * With this patch we should be able to allocate at least 1/4 * of RAM in huge pages. Without the patch much less is @@ -94,8 +93,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), "%lu", initial_nr_hugepages); - /* We want to test with 80% of available memory. Else, OOM killer comes - in to play */ + /* + * We want to test with 80% of available memory. Else, OOM killer comes + * in to play + */ mem_free = mem_free * 0.8; fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); @@ -106,8 +107,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, goto out; } - /* Request a large number of huge pages. The Kernel will allocate - as much as it can */ + /* + * Request a large number of huge pages. The Kernel will allocate + * as much as it can + */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", strerror(errno)); @@ -122,8 +125,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, goto close_fd; } - /* We should have been able to request at least 1/3 rd of the memory in - huge pages */ + /* + * We should have been able to request at least 1/3 rd of the memory in + * huge pages + */ nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); if (!nr_hugepages_ul) { ksft_print_msg("ERROR: No memory is available as huge pages\n"); @@ -243,7 +248,8 @@ int main(int argc, char **argv) entry->next = list; list = entry; - /* Write something (in this case the address of the map) to + /* + * Write something (in this case the address of the map) to * ensure that KSM can't merge the mapped pages */ for (i = 0; i < MAP_SIZE; i += page_size) -- 2.49.0

5 days, 7 hours

1
0
0 0

[PATCH] selftests: net: fix spelling and grammar mistakes

by Praveen Balakrishnan

Fix several spelling and grammatical mistakes in output messages from the net selftests to improve readability. Only the message strings for the test output have been modified. No changes to the functional logic of the tests have been made. Signed-off-by: Praveen Balakrishnan <praveen.balakrishnan(a)magd.ox.ac.uk> --- .../testing/selftests/net/netfilter/conntrack_vrf.sh | 4 ++-- tools/testing/selftests/net/openvswitch/ovs-dpctl.py | 2 +- tools/testing/selftests/net/rps_default_mask.sh | 12 ++++++------ 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh index e95ecb37c2b1..806d2bfbd6e7 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_vrf.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_vrf.sh @@ -236,9 +236,9 @@ EOF ip netns exec "$ns1" ping -q -w 1 -c 1 "$DUMMYNET".2 > /dev/null if ip netns exec "$ns0" nft list counter t fibcount | grep -q "packets 1"; then - echo "PASS: fib lookup returned exepected output interface" + echo "PASS: fib lookup returned expected output interface" else - echo "FAIL: fib lookup did not return exepected output interface" + echo "FAIL: fib lookup did not return expected output interface" ret=1 return fi diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 8a0396bfaf99..b521e0dea506 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -1877,7 +1877,7 @@ class OvsPacket(GenericNetlinkSocket): elif msg["cmd"] == OvsPacket.OVS_PACKET_CMD_EXECUTE: up.execute(msg) else: - print("Unkonwn cmd: %d" % msg["cmd"]) + print("Unknown cmd: %d" % msg["cmd"]) except NetlinkError as ne: raise ne diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh index 4287a8529890..b200019b3c80 100755 --- a/tools/testing/selftests/net/rps_default_mask.sh +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -54,16 +54,16 @@ cleanup echo 1 > /proc/sys/net/core/rps_default_mask setup -chk_rps "changing rps_default_mask dont affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK +chk_rps "changing rps_default_mask doesn't affect existing devices" "" lo $INITIAL_RPS_DEFAULT_MASK echo 3 > /proc/sys/net/core/rps_default_mask -chk_rps "changing rps_default_mask dont affect existing netns" $NETNS lo 0 +chk_rps "changing rps_default_mask doesn't affect existing netns" $NETNS lo 0 ip link add name $VETH type veth peer netns $NETNS name $VETH ip link set dev $VETH up ip -n $NETNS link set dev $VETH up -chk_rps "changing rps_default_mask affect newly created devices" "" $VETH 3 -chk_rps "changing rps_default_mask don't affect newly child netns[II]" $NETNS $VETH 0 +chk_rps "changing rps_default_mask affects newly created devices" "" $VETH 3 +chk_rps "changing rps_default_mask doesn't affect newly child netns[II]" $NETNS $VETH 0 ip link del dev $VETH ip netns del $NETNS @@ -72,8 +72,8 @@ chk_rps "rps_default_mask is 0 by default in child netns" "$NETNS" lo 0 ip netns exec $NETNS sysctl -qw net.core.rps_default_mask=1 ip link add name $VETH type veth peer netns $NETNS name $VETH -chk_rps "changing rps_default_mask in child ns don't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK +chk_rps "changing rps_default_mask in child ns doesn't affect the main one" "" lo $INITIAL_RPS_DEFAULT_MASK chk_rps "changing rps_default_mask in child ns affects new childns devices" $NETNS $VETH 1 -chk_rps "changing rps_default_mask in child ns don't affect existing devices" $NETNS lo 0 +chk_rps "changing rps_default_mask in child ns doesn't affect existing devices" $NETNS lo 0 exit $ret -- 2.39.5

5 days, 7 hours

1
0
0 0

[PATCH v2] selftests: Add functional test for the abort file in fusectl

by Chen Linxuan

This patch add a simple functional test for the "abort" file in fusectlfs (/sys/fs/fuse/connections/ID/about). A simple fuse daemon is added for testing. Related discussion can be found in the link below. Link: https://lore.kernel.org/all/CAOQ4uxjKFXOKQxPpxtS6G_nR0tpw95w0GiO68UcWg_OBhm… Cc: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Chen Linxuan <chenlinxuan(a)uniontech.com> --- Changes in v2: - Apply changes suggested by Amir Goldstein - Check errno - Link to v1: https://lore.kernel.org/all/20250515073449.346774-2-chenlinxuan@uniontech.c… --- MAINTAINERS | 1 + tools/testing/selftests/Makefile | 1 + .../selftests/filesystems/fusectl/.gitignore | 3 + .../selftests/filesystems/fusectl/Makefile | 21 +++ .../selftests/filesystems/fusectl/fuse_mnt.c | 146 ++++++++++++++++++ .../filesystems/fusectl/fusectl_test.c | 116 ++++++++++++++ 6 files changed, 288 insertions(+) create mode 100644 tools/testing/selftests/filesystems/fusectl/.gitignore create mode 100644 tools/testing/selftests/filesystems/fusectl/Makefile create mode 100644 tools/testing/selftests/filesystems/fusectl/fuse_mnt.c create mode 100644 tools/testing/selftests/filesystems/fusectl/fusectl_test.c diff --git a/MAINTAINERS b/MAINTAINERS index 3563492e4eba4..bee6f7d787a33 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9740,6 +9740,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git F: Documentation/filesystems/fuse.rst F: fs/fuse/ F: include/uapi/linux/fuse.h +F: tools/testing/selftests/filesystems/fusectl FUTEX SUBSYSTEM M: Thomas Gleixner <tglx(a)linutronix.de> diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 80fb84fa3cfcb..a9bfefa961889 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -36,6 +36,7 @@ TARGETS += filesystems/fat TARGETS += filesystems/overlayfs TARGETS += filesystems/statmount TARGETS += filesystems/mount-notify +TARGETS += filesystems/fusectl TARGETS += firmware TARGETS += fpu TARGETS += ftrace diff --git a/tools/testing/selftests/filesystems/fusectl/.gitignore b/tools/testing/selftests/filesystems/fusectl/.gitignore new file mode 100644 index 0000000000000..3e72e742d08e8 --- /dev/null +++ b/tools/testing/selftests/filesystems/fusectl/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +fuse_mnt +fusectl_test diff --git a/tools/testing/selftests/filesystems/fusectl/Makefile b/tools/testing/selftests/filesystems/fusectl/Makefile new file mode 100644 index 0000000000000..612aad69a93aa --- /dev/null +++ b/tools/testing/selftests/filesystems/fusectl/Makefile @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g $(KHDR_INCLUDES) + +TEST_GEN_PROGS := fusectl_test +TEST_GEN_FILES := fuse_mnt + +include ../../lib.mk + +VAR_CFLAGS := $(shell pkg-config fuse --cflags 2>/dev/null) +ifeq ($(VAR_CFLAGS),) +VAR_CFLAGS := -D_FILE_OFFSET_BITS=64 -I/usr/include/fuse +endif + +VAR_LDLIBS := $(shell pkg-config fuse --libs 2>/dev/null) +ifeq ($(VAR_LDLIBS),) +VAR_LDLIBS := -lfuse -pthread +endif + +$(OUTPUT)/fuse_mnt: CFLAGS += $(VAR_CFLAGS) +$(OUTPUT)/fuse_mnt: LDLIBS += $(VAR_LDLIBS) diff --git a/tools/testing/selftests/filesystems/fusectl/fuse_mnt.c b/tools/testing/selftests/filesystems/fusectl/fuse_mnt.c new file mode 100644 index 0000000000000..d12b17f30fadc --- /dev/null +++ b/tools/testing/selftests/filesystems/fusectl/fuse_mnt.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fusectl test file-system + * Creates a simple FUSE filesystem with a single read-write file (/test) + */ + +#define FUSE_USE_VERSION 26 + +#include <fuse.h> +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> +#include <stdlib.h> +#include <unistd.h> + +#define MAX(a, b) ((a) > (b) ? (a) : (b)) + +static char *content; +static size_t content_size = 0; +static const char test_path[] = "/test"; + +static int test_getattr(const char *path, struct stat *st) +{ + memset(st, 0, sizeof(*st)); + + if (!strcmp(path, "/")) { + st->st_mode = S_IFDIR | 0755; + st->st_nlink = 2; + return 0; + } + + if (!strcmp(path, test_path)) { + st->st_mode = S_IFREG | 0664; + st->st_nlink = 1; + st->st_size = content_size; + return 0; + } + + return -ENOENT; +} + +static int test_readdir(const char *path, void *buf, fuse_fill_dir_t filler, + off_t offset, struct fuse_file_info *fi) +{ + if (strcmp(path, "/")) + return -ENOENT; + + filler(buf, ".", NULL, 0); + filler(buf, "..", NULL, 0); + filler(buf, test_path + 1, NULL, 0); + + return 0; +} + +static int test_open(const char *path, struct fuse_file_info *fi) +{ + if (strcmp(path, test_path)) + return -ENOENT; + + return 0; +} + +static int test_read(const char *path, char *buf, size_t size, off_t offset, + struct fuse_file_info *fi) +{ + if (strcmp(path, test_path) != 0) + return -ENOENT; + + if (!content || content_size == 0) + return 0; + + if (offset >= content_size) + return 0; + + if (offset + size > content_size) + size = content_size - offset; + + memcpy(buf, content + offset, size); + + return size; +} + +static int test_write(const char *path, const char *buf, size_t size, + off_t offset, struct fuse_file_info *fi) +{ + size_t new_size; + + if (strcmp(path, test_path) != 0) + return -ENOENT; + + if(offset > content_size) + return -EINVAL; + + new_size = MAX(offset + size, content_size); + + if (new_size > content_size) + content = realloc(content, new_size); + + content_size = new_size; + + if (!content) + return -ENOMEM; + + memcpy(content + offset, buf, size); + + return size; +} + +static int test_truncate(const char *path, off_t size) +{ + if (strcmp(path, test_path) != 0) + return -ENOENT; + + if (size == 0) { + free(content); + content = NULL; + content_size = 0; + return 0; + } + + content = realloc(content, size); + + if (!content) + return -ENOMEM; + + if (size > content_size) + memset(content + content_size, 0, size - content_size); + + content_size = size; + return 0; +} + +static struct fuse_operations memfd_ops = { + .getattr = test_getattr, + .readdir = test_readdir, + .open = test_open, + .read = test_read, + .write = test_write, + .truncate = test_truncate, +}; + +int main(int argc, char *argv[]) +{ + return fuse_main(argc, argv, &memfd_ops, NULL); +} diff --git a/tools/testing/selftests/filesystems/fusectl/fusectl_test.c b/tools/testing/selftests/filesystems/fusectl/fusectl_test.c new file mode 100644 index 0000000000000..7050fbe0970e7 --- /dev/null +++ b/tools/testing/selftests/filesystems/fusectl/fusectl_test.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +// Copyright (c) 2025 Chen Linxuan <chenlinxuan(a)uniontech.com> + +#define _GNU_SOURCE + +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> +#include <dirent.h> +#include <linux/limits.h> + +#include "../../kselftest_harness.h" + +#define FUSECTL_MOUNTPOINT "/sys/fs/fuse/connections" +#define FUSE_MOUNTPOINT "/tmp/fuse_mnt_XXXXXX" +#define FUSE_DEVICE "/dev/fuse" +#define FUSECTL_TEST_VALUE "1" + +FIXTURE(fusectl){ + char fuse_mountpoint[sizeof(FUSE_MOUNTPOINT)]; + int connection; +}; + +FIXTURE_SETUP(fusectl) +{ + const char *fuse_mnt_prog = "./fuse_mnt"; + int status, pid; + struct stat statbuf; + + strcpy(self->fuse_mountpoint, FUSE_MOUNTPOINT); + + if (!mkdtemp(self->fuse_mountpoint)) + SKIP(return, + "Failed to create FUSE mountpoint %s", + strerror(errno)); + + if (access(FUSECTL_MOUNTPOINT, F_OK)) + SKIP(return, + "FUSE control filesystem not mounted"); + + pid = fork(); + if (pid < 0) + SKIP(return, + "Failed to fork FUSE daemon process: %s", + strerror(errno)); + + if (pid == 0) { + execlp(fuse_mnt_prog, fuse_mnt_prog, self->fuse_mountpoint, NULL); + exit(errno); + } + + waitpid(pid, &status, 0); + if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) { + SKIP(return, + "Failed to start FUSE daemon %s", + strerror(WEXITSTATUS(status))); + } + + if (stat(self->fuse_mountpoint, &statbuf)) + SKIP(return, + "Failed to stat FUSE mountpoint %s", + strerror(errno)); + + self->connection = statbuf.st_dev; +} + +FIXTURE_TEARDOWN(fusectl) +{ + umount(self->fuse_mountpoint); + rmdir(self->fuse_mountpoint); +} + +TEST_F(fusectl, abort) +{ + char path_buf[PATH_MAX]; + int abort_fd, test_fd, ret; + + sprintf(path_buf, "/sys/fs/fuse/connections/%d/abort", self->connection); + + ASSERT_EQ(0, access(path_buf, F_OK)); + + abort_fd = open(path_buf, O_WRONLY); + ASSERT_GE(abort_fd, 0); + + sprintf(path_buf, "%s/test", self->fuse_mountpoint); + + test_fd = open(path_buf, O_RDWR); + ASSERT_GE(test_fd, 0); + + ret = read(test_fd, path_buf, sizeof(path_buf)); + ASSERT_EQ(ret, 0); + + ret = write(test_fd, "test", sizeof("test")); + ASSERT_EQ(ret, sizeof("test")); + + ret = lseek(test_fd, 0, SEEK_SET); + ASSERT_GE(ret, 0); + + ret = write(abort_fd, FUSECTL_TEST_VALUE, sizeof(FUSECTL_TEST_VALUE)); + ASSERT_GT(ret, 0); + + close(abort_fd); + + ret = read(test_fd, path_buf, sizeof(path_buf)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ENOTCONN); +} + +TEST_HARNESS_MAIN -- 2.43.0

5 days, 8 hours

1
0
0 0

[PATCH 1/1] Fix typo in cpu-on-off-test selftest script:

by Jihed Chaibi

Fix typo in hotplaggable_offline_cpus function name: "hotplaggable" is replaced by "hotpluggable" Signed-off-by: Jihed Chaibi <jihed.chaibi.dev(a)gmail.com> --- tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index d5dc7e0dc..6232a46ca 100755 --- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh @@ -67,7 +67,7 @@ hotpluggable_cpus() done } -hotplaggable_offline_cpus() +hotpluggable_offline_cpus() { hotpluggable_cpus 0 } @@ -151,7 +151,7 @@ offline_cpu_expect_fail() online_all_hot_pluggable_cpus() { - for cpu in `hotplaggable_offline_cpus`; do + for cpu in `hotpluggable_offline_cpus`; do online_cpu_expect_success $cpu done } -- 2.39.5

5 days, 8 hours

1
0
0 0

[PATCH v2 00/15] Consolidate iommu page table implementations (AMD)

by Jason Gunthorpe

Currently each of the iommu page table formats duplicates all of the logic to maintain the page table and perform map/unmap/etc operations. There are several different versions of the algorithms between all the different formats. The io-pgtable system provides an interface to help isolate the page table code from the iommu driver, but doesn't provide tools to implement the common algorithms. This makes it very hard to improve the state of the pagetable code under the iommu domains as any proposed improvement needs to alter a large number of different driver code paths. Combined with a lack of software based testing this makes improvement in this area very hard. iommufd wants several new page table operations: - More efficient map/unmap operations, using iommufd's batching logic - unmap that returns the physical addresses into a batch as it progresses - cut that allows splitting areas so large pages can have holes poked in them dynamically (ie guestmemfd hitless shared/private transitions) - More agressive freeing of table memory to avoid waste - Fragmenting large pages so that dirty tracking can be more granular - Reassembling large pages so that VMs can run at full IO performance in migration/dirty tracking error flows - KHO integration for kernel live upgrade Together these are algorithmically complex enough to be a very significant task to go and implement in all the page table formats we support. Just the "server" focused drivers use almost all the formats (ARMv8 S1&S2 / x86 PAE / AMDv1 / VT-D SS / RISCV) Instead of doing the duplicated work, this series takes the first step to consolidate the algorithms into one places. In spirit it is similar to the work Christoph did a few years back to pull the redundant get_user_pages() implementations out of the arch code into core MM. This unlocked a great deal of improvement in that space in the following years. I would like to see the same benefit in iommu as well. My first RFC showed a bigger picture with all most all formats and more algorithms. This series reorganizes that to be narrowly focused on just enough to convert the AMD driver to use the new mechanism. kunit tests are provided that allow good testing of the algorithms and all formats on x86, nothing is arch specific. AMD is one of the simpler options as the HW is quite uniform with few different options/bugs while still requiring the complicated contiguous pages support. The HW also has a very simple range based invalidation approach that is easy to implement. The AMD v1 and AMD v2 page table formats are implemented bit for bit identical to the current code, tested using a compare kunit test that checks against the io-pgtable version (on github, see below). Updating the AMD driver to replace the io-pgtable layer with the new stuff is fairly straightforward now. The layering is fixed up in the new version so that all the invalidation goes through function pointers. Several small fixing patches have come out of this as I've been fixing the problems that the test suite uncovers in the current code, and implementing the fixed version in iommupt. On performance, there is a quite wide variety of implementation designs across all the drivers. Looking at some key performance across the main formats: iommu_map(): pgsz ,avg new,old ns, min new,old ns , min % (+ve is better) 2^12, 53,66 , 51,63 , 19.19 (AMDV1) 256*2^12, 386,1909 , 367,1795 , 79.79 256*2^21, 362,1633 , 355,1556 , 77.77 2^12, 56,62 , 52,59 , 11.11 (AMDv2) 256*2^12, 405,1355 , 357,1292 , 72.72 256*2^21, 393,1160 , 358,1114 , 67.67 2^12, 55,65 , 53,62 , 14.14 (VTD second stage) 256*2^12, 391,518 , 332,512 , 35.35 256*2^21, 383,635 , 336,624 , 46.46 2^12, 57,65 , 55,63 , 12.12 (ARM 64 bit) 256*2^12, 380,389 , 361,369 , 2.02 256*2^21, 358,419 , 345,400 , 13.13 iommu_unmap(): pgsz ,avg new,old ns, min new,old ns , min % (+ve is better) 2^12, 69,88 , 65,85 , 23.23 (AMDv1) 256*2^12, 353,6498 , 331,6029 , 94.94 256*2^21, 373,6014 , 360,5706 , 93.93 2^12, 71,72 , 66,69 , 4.04 (AMDv2) 256*2^12, 228,891 , 206,871 , 76.76 256*2^21, 254,721 , 245,711 , 65.65 2^12, 69,87 , 65,82 , 20.20 (VTD second stage) 256*2^12, 210,321 , 200,315 , 36.36 256*2^21, 255,349 , 238,342 , 30.30 2^12, 72,77 , 68,74 , 8.08 (ARM 64 bit) 256*2^12, 521,357 , 447,346 , -29.29 256*2^21, 489,358 , 433,345 , -25.25 * Above numbers include additional patches to remove the iommu_pgsize() overheads. gcc 13.3.0, i7-12700 This version provides fairly consistent performance across formats. ARM unmap performance is quite different because this version supports contiguous pages and uses a very different algorithm for unmapping. Though why it is so worse compared to AMDv1 I haven't figured out yet. The per-format commits include a more detailed chart. There is a second branch: https://github.com/jgunthorpe/linux/commits/iommu_pt_all Containing supporting work and future steps: - ARM short descriptor (32 bit), ARM long descriptor (64 bit) formats - VT-D second stage format - DART v1 & v2 format - Draft of a iommufd 'cut' operation to break down huge pages - Draft of support for a DMA incoherent HW page table walker - A compare test that checks the iommupt formats against the iopgtable interface, including updating AMD to have a working iopgtable and patches to make VT-D have an iopgtable for testing. - A performance test to micro-benchmark map and unmap against iogptable My strategy is to go one by one for the drivers: - AMD driver conversion - RISCV page table and driver - Intel VT-D driver and VTDSS page table - ARM SMMUv3 And concurrently work on the algorithm side: - debugfs content dump, like VT-D has - Cut support - Increase/Decrease page size support - map/unmap batching - KHO As we make more algorithm improvements the value to convert the drivers increases. This is on github: https://github.com/jgunthorpe/linux/commits/iommu_pt v1: - AMD driver only, many code changes RFC: https://lore.kernel.org/all/0-v1-01fa10580981+1d-iommu_pt_jgg@nvidia.com/ Alejandro Jimenez (1): iommu/amd: Use the generic iommu page table Jason Gunthorpe (14): genpt: Generic Page Table base API genpt: Add Documentation/ files iommupt: Add the basic structure of the iommu implementation iommupt: Add the AMD IOMMU v1 page table format iommupt: Add iova_to_phys op iommupt: Add unmap_pages op iommupt: Add map_pages op iommupt: Add read_and_clear_dirty op iommupt: Add a kunit test for Generic Page Table iommupt: Add a mock pagetable format for iommufd selftest to use iommufd: Change the selftest to use iommupt instead of xarray iommupt: Add the x86 64 bit page table format iommu/amd: Remove AMD io_pgtable support iommupt: Add a kunit test for the IOMMU implementation .clang-format | 1 + Documentation/driver-api/generic_pt.rst | 105 ++ Documentation/driver-api/index.rst | 1 + drivers/iommu/Kconfig | 2 + drivers/iommu/Makefile | 1 + drivers/iommu/amd/Kconfig | 5 +- drivers/iommu/amd/Makefile | 2 +- drivers/iommu/amd/amd_iommu.h | 1 - drivers/iommu/amd/amd_iommu_types.h | 109 +- drivers/iommu/amd/io_pgtable.c | 560 -------- drivers/iommu/amd/io_pgtable_v2.c | 370 ------ drivers/iommu/amd/iommu.c | 493 ++++--- drivers/iommu/generic_pt/.kunitconfig | 13 + drivers/iommu/generic_pt/Kconfig | 72 ++ drivers/iommu/generic_pt/fmt/Makefile | 26 + drivers/iommu/generic_pt/fmt/amdv1.h | 407 ++++++ drivers/iommu/generic_pt/fmt/defs_amdv1.h | 21 + drivers/iommu/generic_pt/fmt/defs_x86_64.h | 21 + drivers/iommu/generic_pt/fmt/iommu_amdv1.c | 15 + drivers/iommu/generic_pt/fmt/iommu_mock.c | 10 + drivers/iommu/generic_pt/fmt/iommu_template.h | 48 + drivers/iommu/generic_pt/fmt/iommu_x86_64.c | 12 + drivers/iommu/generic_pt/fmt/x86_64.h | 241 ++++ drivers/iommu/generic_pt/iommu_pt.h | 1146 +++++++++++++++++ drivers/iommu/generic_pt/kunit_generic_pt.h | 721 +++++++++++ drivers/iommu/generic_pt/kunit_iommu.h | 183 +++ drivers/iommu/generic_pt/kunit_iommu_pt.h | 451 +++++++ drivers/iommu/generic_pt/pt_common.h | 351 +++++ drivers/iommu/generic_pt/pt_defs.h | 312 +++++ drivers/iommu/generic_pt/pt_fmt_defaults.h | 193 +++ drivers/iommu/generic_pt/pt_iter.h | 638 +++++++++ drivers/iommu/generic_pt/pt_log2.h | 130 ++ drivers/iommu/io-pgtable.c | 4 - drivers/iommu/iommufd/Kconfig | 1 + drivers/iommu/iommufd/iommufd_test.h | 11 +- drivers/iommu/iommufd/selftest.c | 439 +++---- include/linux/generic_pt/common.h | 166 +++ include/linux/generic_pt/iommu.h | 264 ++++ include/linux/io-pgtable.h | 2 - tools/testing/selftests/iommu/iommufd.c | 60 +- tools/testing/selftests/iommu/iommufd_utils.h | 12 + 41 files changed, 6046 insertions(+), 1574 deletions(-) create mode 100644 Documentation/driver-api/generic_pt.rst delete mode 100644 drivers/iommu/amd/io_pgtable.c delete mode 100644 drivers/iommu/amd/io_pgtable_v2.c create mode 100644 drivers/iommu/generic_pt/.kunitconfig create mode 100644 drivers/iommu/generic_pt/Kconfig create mode 100644 drivers/iommu/generic_pt/fmt/Makefile create mode 100644 drivers/iommu/generic_pt/fmt/amdv1.h create mode 100644 drivers/iommu/generic_pt/fmt/defs_amdv1.h create mode 100644 drivers/iommu/generic_pt/fmt/defs_x86_64.h create mode 100644 drivers/iommu/generic_pt/fmt/iommu_amdv1.c create mode 100644 drivers/iommu/generic_pt/fmt/iommu_mock.c create mode 100644 drivers/iommu/generic_pt/fmt/iommu_template.h create mode 100644 drivers/iommu/generic_pt/fmt/iommu_x86_64.c create mode 100644 drivers/iommu/generic_pt/fmt/x86_64.h create mode 100644 drivers/iommu/generic_pt/iommu_pt.h create mode 100644 drivers/iommu/generic_pt/kunit_generic_pt.h create mode 100644 drivers/iommu/generic_pt/kunit_iommu.h create mode 100644 drivers/iommu/generic_pt/kunit_iommu_pt.h create mode 100644 drivers/iommu/generic_pt/pt_common.h create mode 100644 drivers/iommu/generic_pt/pt_defs.h create mode 100644 drivers/iommu/generic_pt/pt_fmt_defaults.h create mode 100644 drivers/iommu/generic_pt/pt_iter.h create mode 100644 drivers/iommu/generic_pt/pt_log2.h create mode 100644 include/linux/generic_pt/common.h create mode 100644 include/linux/generic_pt/iommu.h base-commit: db37090502f67e46541e53b91f00bbd565c96bd0 -- 2.43.0

5 days, 13 hours

7
34
0 0

[RFC PATCH v2 00/13] New KVM ioctl to link a gmem inode to a new gmem file

by Ryan Afranji

Hello, RFC v2 addresses comments in RFC v1 [1]. This series is also rebased on kvm/next (v6.15-rc4). Here's the series stitched together for your convenience: https://github.com/googleprodkernel/linux-cc/tree/kvm-gmem-link-migrate-rfc… Changes from RFC v1: + Adds patches to make guest mem use guest mem inodes instead of anonymous inodes. + Changed the name of factored out gmem allocating function to kvm_gmem_alloc_view(). + Changed the flag name vm_move_enc_ctxt_supported to use_vm_enc_ctxt_op. + Various small changes to make patchset compatible with latest version of kvm/next. As a refresher, split file/inode model was proposed in guest_mem v11, where memslot bindings belong to the file and pages belong to the inode. This model lends itself well to having different VMs use separate files pointing to the same inode. The split file/inode model has also been used by the other following recent patch series: + mmap support for guest_memfd: [2] + NUMA mempolicy support for guest_memfd: [3] + HugeTLB support for guest_memfd: [4] This RFC proposes an ioctl, KVM_LINK_GUEST_MEMFD, that takes a VM and a gmem fd, and returns another gmem fd referencing a different file and associated with VM. This RFC also includes an update to KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM to migrate memory context (slot->arch.lpage_info and kvm->mem_attr_array) from source to destination vm, intra-host. Intended usage of the two ioctls: 1. Source VM’s fd is passed to destination VM via unix sockets. 2. Destination VM uses new ioctl KVM_LINK_GUEST_MEMFD to link source VM’s fd to a new fd. 3. Destination VM will pass new fds to KVM_SET_USER_MEMORY_REGION, which will bind the new file, pointing to the same inode that the source VM’s file points to, to memslots. 4. Use KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM to move kvm->mem_attr_array and slot->arch.lpage_info to the destination VM. 5. Run the destination VM as per normal. Some other approaches considered were: + Using the linkat() syscall, but that requires a mount/directory for a source fd to be linked to + Using the dup() syscall, but that only duplicates the fd, and both fds point to the same file [1] https://lore.kernel.org/all/cover.1691446946.git.ackerleytng@google.com/T/ [2] https://lore.kernel.org/all/20250328153133.3504118-2-tabba@google.com/ [3] https://lore.kernel.org/all/20250408112402.181574-6-shivankg@amd.com/ [4] https://lore.kernel.org/all/c1ee659c212b5a8b0e7a7f4d1763699176dd3a62.174726… --- Ackerley Tng (12): KVM: guest_memfd: Make guest mem use guest mem inodes instead of anonymous inodes KVM: guest_mem: Refactor out kvm_gmem_alloc_view() KVM: guest_mem: Add ioctl KVM_LINK_GUEST_MEMFD KVM: selftests: Add tests for KVM_LINK_GUEST_MEMFD ioctl KVM: selftests: Test transferring private memory to another VM KVM: x86: Refactor sev's flag migration_in_progress to kvm struct KVM: x86: Refactor common code out of sev.c KVM: x86: Refactor common migration preparation code out of sev_vm_move_enc_context_from KVM: x86: Let moving encryption context be configurable KVM: x86: Handle moving of memory context for intra-host migration KVM: selftests: Generalize migration functions from sev_migrate_tests.c KVM: selftests: Add tests for migration of private mem David Hildenbrand (1): fs: Refactor to provide function that allocates a secure anonymous inode arch/x86/include/asm/kvm_host.h | 3 +- arch/x86/kvm/svm/sev.c | 82 +------ arch/x86/kvm/svm/svm.h | 3 +- arch/x86/kvm/x86.c | 218 ++++++++++++++++- arch/x86/kvm/x86.h | 6 + fs/anon_inodes.c | 23 +- include/linux/fs.h | 13 +- include/linux/kvm_host.h | 18 ++ include/uapi/linux/kvm.h | 8 + include/uapi/linux/magic.h | 1 + mm/secretmem.c | 9 +- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../testing/selftests/kvm/guest_memfd_test.c | 43 ++++ .../testing/selftests/kvm/include/kvm_util.h | 31 +++ .../kvm/x86/private_mem_migrate_tests.c | 93 ++++++++ .../selftests/kvm/x86/sev_migrate_tests.c | 48 ++-- virt/kvm/guest_memfd.c | 225 +++++++++++++++--- virt/kvm/kvm_main.c | 17 +- virt/kvm/kvm_mm.h | 14 +- 19 files changed, 697 insertions(+), 159 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86/private_mem_migrate_tests.c -- 2.49.0.1101.gccaa498523-goog

5 days, 14 hours

1
13
0 0

[PATCH net] selftests: net: validate team flags propagation

by Stanislav Fomichev

Cover three recent cases: 1. missing ops locking for the lowers during netdev_sync_lower_features 2. missing locking for dev_set_promiscuity (plus netdev_ops_assert_locked with a comment on why/when it's needed) 3. rcu lock during team_change_rx_flags Verified that each one triggers when the respective fix is reverted. Not sure about the placement, but since it all relies on teaming, added to the teaming directory. One ugly bit is that I add NETIF_F_LRO to netdevsim; there is no way to trigger netdev_sync_lower_features without it. Signed-off-by: Stanislav Fomichev <stfomichev(a)gmail.com> --- drivers/net/netdevsim/netdev.c | 2 + net/core/dev.c | 10 ++- .../selftests/drivers/net/team/Makefile | 2 +- .../testing/selftests/drivers/net/team/config | 1 + .../selftests/drivers/net/team/propagation.sh | 79 +++++++++++++++++++ 5 files changed, 92 insertions(+), 2 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/team/propagation.sh diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 0e0321a7ddd7..3bd1f8cffee8 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -879,11 +879,13 @@ static void nsim_setup(struct net_device *dev) NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | + NETIF_F_LRO | NETIF_F_TSO; dev->hw_features |= NETIF_F_HW_TC | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | + NETIF_F_LRO | NETIF_F_TSO; dev->max_mtu = ETH_MAX_MTU; dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD; diff --git a/net/core/dev.c b/net/core/dev.c index 0d891634c692..4debd4b8e0f5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9188,8 +9188,16 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) dev_change_rx_flags(dev, IFF_PROMISC); } - if (notify) + if (notify) { + /* The ops lock is only required to ensure consistent locking + * for `NETDEV_CHANGE` notifiers. This function is sometimes + * called without the lock, even for devices that are ops + * locked, such as in `dev_uc_sync_multiple` when using + * bonding or teaming. + */ + netdev_ops_assert_locked(dev); __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); + } return 0; } diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile index 2d5a76d99181..eaf6938f100e 100644 --- a/tools/testing/selftests/drivers/net/team/Makefile +++ b/tools/testing/selftests/drivers/net/team/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for net selftests -TEST_PROGS := dev_addr_lists.sh +TEST_PROGS := dev_addr_lists.sh propagation.sh TEST_INCLUDES := \ ../bonding/lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config index b5e3a3aad4bf..636b3525b679 100644 --- a/tools/testing/selftests/drivers/net/team/config +++ b/tools/testing/selftests/drivers/net/team/config @@ -1,5 +1,6 @@ CONFIG_DUMMY=y CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_NETDEVSIM=m CONFIG_NET_TEAM=y CONFIG_NET_TEAM_MODE_LOADBALANCE=y diff --git a/tools/testing/selftests/drivers/net/team/propagation.sh b/tools/testing/selftests/drivers/net/team/propagation.sh new file mode 100755 index 000000000000..849a5f2cb3a7 --- /dev/null +++ b/tools/testing/selftests/drivers/net/team/propagation.sh @@ -0,0 +1,79 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e + +NSIM_LRO_ID=$((256 + RANDOM % 256)) +NSIM_LRO_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_LRO_ID + +NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device +NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device + +cleanup() +{ + ip link del dummyteam &>/dev/null + ip link del team0 &>/dev/null + echo $NSIM_LRO_ID > $NSIM_DEV_SYS_DEL +} + +# Trigger LRO propagation to the lower. +# https://lore.kernel.org/netdev/aBvOpkIoxcr9PfDg@mini-arch/ +team_lro() +{ + # using netdevsim because it supports NETIF_F_LRO + NSIM_LRO_NAME=$(find $NSIM_LRO_SYS/net -maxdepth 1 -type d ! \ + -path $NSIM_LRO_SYS/net -exec basename {} \;) + + ip link add name team0 type team + ip link set $NSIM_LRO_NAME down + ip link set dev $NSIM_LRO_NAME master team0 + ip link set team0 up + ethtool -K team0 large-receive-offload off + + ip link del team0 +} + +# Trigger promisc propagation to the lower during IFLA_MASTER. +# https://lore.kernel.org/netdev/20250506032328.3003050-1-sdf@fomichev.me/ +team_promisc() +{ + ip link add name dummyteam type dummy + ip link add name team0 type team + ip link set dummyteam down + ip link set team0 promisc on + ip link set dev dummyteam master team0 + ip link set team0 up + + ip link del team0 + ip link del dummyteam +} + +# Trigger promisc propagation to the lower via netif_change_flags (aka +# ndo_change_rx_flags). +# https://lore.kernel.org/netdev/20250514220319.3505158-1-stfomichev@gmail.co… +team_change_flags() +{ + ip link add name dummyteam type dummy + ip link add name team0 type team + ip link set dummyteam down + ip link set dev dummyteam master team0 + ip link set team0 up + ip link set team0 promisc on + + # Make sure we can add more L2 addresses without any issues. + ip link add link team0 address 00:00:00:00:00:01 team0.1 type macvlan + ip link set team0.1 up + + ip link del team0.1 + ip link del team0 + ip link del dummyteam +} + +trap cleanup EXIT +modprobe netdevsim || : +echo $NSIM_LRO_ID > $NSIM_DEV_SYS_NEW +udevadm settle +team_lro +team_promisc +team_change_flags +modprobe -r netdevsim || : -- 2.49.0

5 days, 15 hours

2
2
0 0

[PATCH] [PATCH] Change pidns to pid namespace

by rodgepritesh＠gmail.com

From: Pritesh Rodge <rodgepritesh(a)gmail.com> Changed a comment in memfd_test.c , Unabbreviated pidns to pid namespace for better understanding . Signed-off-by: Pritesh Rodge <rodgepritesh(a)gmail.com> --- tools/testing/selftests/memfd/memfd_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 5b993924cc3f..4e4c46246a4e 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -1359,7 +1359,7 @@ static int sysctl_nested_child(void *arg) printf("%s nested sysctl 0\n", memfd_str); sysctl_assert_write("0"); - /* A further nested pidns works the same. */ + /* A further nested pid-namespace works the same. */ pid = spawn_thread(CLONE_NEWPID, sysctl_simple_child, NULL); join_thread(pid); -- 2.43.0

5 days, 17 hours

1
0
0 0

[PATCH] selftests: firmware: Add details in error logging

by Harshal

Specify details in logs of failed cases Use die() instead of exit() when write to sys_path fails Signed-off-by: Harshal <embedkari167(a)gmail.com> --- tools/testing/selftests/firmware/fw_namespace.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/firmware/fw_namespace.c b/tools/testing/selftests/firmware/fw_namespace.c index 04757dc7e546..deff7f57b694 100644 --- a/tools/testing/selftests/firmware/fw_namespace.c +++ b/tools/testing/selftests/firmware/fw_namespace.c @@ -38,10 +38,11 @@ static void trigger_fw(const char *fw_name, const char *sys_path) fd = open(sys_path, O_WRONLY); if (fd < 0) - die("open failed: %s\n", + die("open of sys_path failed: %s\n", strerror(errno)); if (write(fd, fw_name, strlen(fw_name)) != strlen(fw_name)) - exit(EXIT_FAILURE); + die("write to sys_path failed: %s\n", + strerror(errno)); close(fd); } @@ -52,10 +53,10 @@ static void setup_fw(const char *fw_path) fd = open(fw_path, O_WRONLY | O_CREAT, 0600); if (fd < 0) - die("open failed: %s\n", + die("open of firmware file failed: %s\n", strerror(errno)); if (write(fd, fw, sizeof(fw) -1) != sizeof(fw) -1) - die("write failed: %s\n", + die("write to firmware file failed: %s\n", strerror(errno)); close(fd); } @@ -66,7 +67,7 @@ static bool test_fw_in_ns(const char *fw_name, const char *sys_path, bool block_ if (block_fw_in_parent_ns) if (mount("test", "/lib/firmware", "tmpfs", MS_RDONLY, NULL) == -1) - die("blocking firmware in parent ns failed\n"); + die("blocking firmware in parent namespace failed\n"); child = fork(); if (child == -1) { @@ -99,11 +100,11 @@ static bool test_fw_in_ns(const char *fw_name, const char *sys_path, bool block_ strerror(errno)); } if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) == -1) - die("remount root in child ns failed\n"); + die("remount root in child namespace failed\n"); if (!block_fw_in_parent_ns) { if (mount("test", "/lib/firmware", "tmpfs", MS_RDONLY, NULL) == -1) - die("blocking firmware in child ns failed\n"); + die("blocking firmware in child namespace failed\n"); } else umount("/lib/firmware"); @@ -129,8 +130,8 @@ int main(int argc, char **argv) die("error: failed to build full fw_path\n"); setup_fw(fw_path); - setvbuf(stdout, NULL, _IONBF, 0); + /* Positive case: firmware in PID1 mount namespace */ printf("Testing with firmware in parent namespace (assumed to be same file system as PID1)\n"); if (!test_fw_in_ns(fw_name, sys_path, false)) -- 2.43.0

5 days, 18 hours

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror May 2025