November 2024 - Linux-kselftest-mirror

[PATCH net-next v23 1/7] mm: page_frag: add a test module for page_frag

by Yunsheng Lin

The testing is done by ensuring that the fragment allocated from a frag_frag_cache instance is pushed into a ptr_ring instance in a kthread binded to a specified cpu, and a kthread binded to a specified cpu will pop the fragment from the ptr_ring and free the fragment. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexander.duyck(a)gmail.com> CC: Linux-MM <linux-mm(a)kvack.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> --- tools/testing/selftests/mm/Makefile | 3 + tools/testing/selftests/mm/page_frag/Makefile | 18 ++ .../selftests/mm/page_frag/page_frag_test.c | 198 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 8 + tools/testing/selftests/mm/test_page_frag.sh | 175 ++++++++++++++++ 5 files changed, 402 insertions(+) create mode 100644 tools/testing/selftests/mm/page_frag/Makefile create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c create mode 100755 tools/testing/selftests/mm/test_page_frag.sh diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..acec529baaca 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +TEST_GEN_MODS_DIR := page_frag + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm @@ -126,6 +128,7 @@ TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh TEST_FILES += charge_reserved_hugetlb.sh TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh # required by charge_reserved_hugetlb.sh TEST_FILES += write_hugetlb_memory.sh diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..58dda74d50a3 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..912d97b99107 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> + +#define TEST_FAILED_PREFIX "page_frag_test failed: " + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; +static int test_popped; +static int test_pushed; +static bool force_exit; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_frag_free(obj); + } else { + if (force_exit) + break; + + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test && !force_exit) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); + } + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + test_pushed++; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + int last_pushed = 0, last_popped = 0; + ktime_t start; + u64 duration; + int ret; + + test_nc.va = NULL; + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) { + /* exit if there is no progress for push or pop size */ + if (last_pushed == test_pushed || last_popped == test_popped) { + WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n"); + force_exit = true; + continue; + } + + last_pushed = test_pushed; + last_popped = test_popped; + pr_info("page_frag_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + } + + if (force_exit) { + pr_err(TEST_FAILED_PREFIX "exit with error\n"); + goto out; + } + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + +out: + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng(a)huawei.com>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c5797ad1d37b..2c5394584af4 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -75,6 +75,8 @@ separated by spaces: read-only VMAs - mdwe test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty CATEGORY="mdwe" run_test ./mdwe_test +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..f55b105084cf --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki(a)gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +check_test_failed_prefix() { + if dmesg | grep -q 'page_frag_test failed:';then + echo "page_frag_test failed, please check dmesg" + exit $exitcode + fi +} + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi + + check_test_failed_prefix + + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +check_test_requirements +run_test $@ + +exit 0 -- 2.33.0

11 months, 2 weeks

4
6
0 0

[PATCH v1] selftest/mm: remove seal_elf

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> Remove seal_elf, which is a demo of mseal, we no longer need this. Signed-off-by: Jeff Xu <jeffxu(a)chromium.org> --- tools/testing/selftests/mm/.gitignore | 1 - tools/testing/selftests/mm/Makefile | 1 - tools/testing/selftests/mm/seal_elf.c | 137 -------------------------- 3 files changed, 139 deletions(-) delete mode 100644 tools/testing/selftests/mm/seal_elf.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8f01f4da1c0d..6a273bdbc70b 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -49,7 +49,6 @@ va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test -seal_elf droppable hugetlb_dio pkey_sighandler_tests_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 72ec4403032d..869b6a40f290 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -64,7 +64,6 @@ TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test -TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c deleted file mode 100644 index d9f8ba8d5050..000000000000 --- a/tools/testing/selftests/mm/seal_elf.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <sys/mman.h> -#include <stdint.h> -#include <asm-generic/unistd.h> -#include <string.h> -#include <sys/time.h> -#include <sys/resource.h> -#include <stdbool.h> -#include "../kselftest.h" -#include <syscall.h> -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <fcntl.h> -#include <sys/ioctl.h> -#include <sys/vfs.h> -#include <sys/stat.h> -#include "mseal_helpers.h" - -/* - * define sys_xyx to call syscall directly. - */ -static int sys_mseal(void *start, size_t len) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mseal, start, len, 0); - return sret; -} - -static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mprotect, ptr, size, prot); - return sret; -} - -static bool seal_support(void) -{ - int ret; - void *ptr; - unsigned long page_size = getpagesize(); - - ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (ptr == (void *) -1) - return false; - - ret = sys_mseal(ptr, page_size); - if (ret < 0) - return false; - - return true; -} - -const char somestr[4096] = {"READONLY"}; - -static void test_seal_elf(void) -{ - int ret; - FILE *maps; - char line[512]; - uintptr_t addr_start, addr_end; - char prot[5]; - char filename[256]; - unsigned long page_size = getpagesize(); - unsigned long long ptr = (unsigned long long) somestr; - char *somestr2 = (char *)somestr; - - /* - * Modify the protection of readonly somestr - */ - if (((unsigned long long)ptr % page_size) != 0) - ptr = (unsigned long long)ptr & ~(page_size - 1); - - ksft_print_msg("somestr = %s\n", somestr); - ksft_print_msg("change protection to rw\n"); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); - FAIL_TEST_IF_FALSE(!ret); - *somestr2 = 'A'; - ksft_print_msg("somestr is modified to: %s\n", somestr); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ); - FAIL_TEST_IF_FALSE(!ret); - - maps = fopen("/proc/self/maps", "r"); - FAIL_TEST_IF_FALSE(maps); - - /* - * apply sealing to elf binary - */ - while (fgets(line, sizeof(line), maps)) { - if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", - &addr_start, &addr_end, prot, filename) == 4) { - if (strlen(filename)) { - /* - * seal the mapping if read only. - */ - if (strstr(prot, "r-")) { - ret = sys_mseal((void *)addr_start, addr_end - addr_start); - FAIL_TEST_IF_FALSE(!ret); - ksft_print_msg("sealed: %lx-%lx %s %s\n", - addr_start, addr_end, prot, filename); - if ((uintptr_t) somestr >= addr_start && - (uintptr_t) somestr <= addr_end) - ksft_print_msg("mapping for somestr found\n"); - } - } - } - } - fclose(maps); - - ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); - FAIL_TEST_IF_FALSE(ret < 0); - ksft_print_msg("somestr is sealed, mprotect is rejected\n"); - - REPORT_TEST_PASS(); -} - -int main(int argc, char **argv) -{ - bool test_seal = seal_support(); - - ksft_print_header(); - ksft_print_msg("pid=%d\n", getpid()); - - if (!test_seal) - ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); - - ksft_set_plan(1); - - test_seal_elf(); - - ksft_finished(); -} -- 2.47.0.338.g60cca15819-goog

11 months, 2 weeks

1
0
0 0

[PATCH net-next v3 0/6] net: Improve netns handling in RTNL and ip_tunnel

by Xiao Liang

This patch series includes some netns-related improvements and fixes for RTNL and ip_tunnel, to make link creation more intuitive: - Creating link in another net namespace doesn't conflict with link names in current one. - Refector rtnetlink link creation. Create link in target namespace directly. Pass both source and link netns to drivers via newlink() callback. So that # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. Patch 1 from Donald is included just as a dependency. --- v3: - Drop "netns_atomic" flag and module parameter. Add netns parameter to newlink() instead, and convert drivers accordingly. - Move python NetNSEnter helper to net selftest lib. v2: link: https://lore.kernel.org/all/20241107133004.7469-1-shaw.leon@gmail.com/ - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Donald Hunter (1): Revert "tools/net/ynl: improve async notification handling" Xiao Liang (5): net: ip_tunnel: Build flow in underlay net namespace rtnetlink: Lookup device in target netns when creating link rtnetlink: Decouple net namespaces in rtnl_newlink_create() selftests: net: Add python context manager for netns entering selftests: net: Add two test cases for link netns drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 6 ++- drivers/net/amt.c | 6 +-- drivers/net/bareudp.c | 4 +- drivers/net/bonding/bond_netlink.c | 3 +- drivers/net/can/dev/netlink.c | 2 +- drivers/net/can/vxcan.c | 4 +- .../ethernet/qualcomm/rmnet/rmnet_config.c | 5 +- drivers/net/geneve.c | 4 +- drivers/net/gtp.c | 4 +- drivers/net/ipvlan/ipvlan.h | 2 +- drivers/net/ipvlan/ipvlan_main.c | 5 +- drivers/net/ipvlan/ipvtap.c | 4 +- drivers/net/macsec.c | 5 +- drivers/net/macvlan.c | 5 +- drivers/net/macvtap.c | 5 +- drivers/net/netkit.c | 4 +- drivers/net/pfcp.c | 4 +- drivers/net/ppp/ppp_generic.c | 4 +- drivers/net/team/team_core.c | 2 +- drivers/net/veth.c | 4 +- drivers/net/vrf.c | 2 +- drivers/net/vxlan/vxlan_core.c | 4 +- drivers/net/wireguard/device.c | 4 +- drivers/net/wireless/virtual/virt_wifi.c | 5 +- drivers/net/wwan/wwan_core.c | 6 ++- include/net/ip_tunnels.h | 5 +- include/net/rtnetlink.h | 22 ++++++++- net/8021q/vlan_netlink.c | 5 +- net/batman-adv/soft-interface.c | 5 +- net/bridge/br_netlink.c | 2 +- net/caif/chnl_net.c | 2 +- net/core/rtnetlink.c | 25 ++++++---- net/hsr/hsr_netlink.c | 8 +-- net/ieee802154/6lowpan/core.c | 5 +- net/ipv4/ip_gre.c | 13 +++-- net/ipv4/ip_tunnel.c | 16 +++--- net/ipv4/ip_vti.c | 5 +- net/ipv4/ipip.c | 5 +- net/ipv6/ip6_gre.c | 17 ++++--- net/ipv6/ip6_tunnel.c | 11 ++--- net/ipv6/ip6_vti.c | 11 ++--- net/ipv6/sit.c | 11 ++--- net/xfrm/xfrm_interface_core.c | 13 +++-- tools/net/ynl/cli.py | 10 ++-- tools/net/ynl/lib/ynl.py | 49 ++++++++----------- tools/testing/selftests/net/Makefile | 1 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/netns.py | 18 +++++++ tools/testing/selftests/net/netns-name.sh | 10 ++++ tools/testing/selftests/net/netns_atomic.py | 38 ++++++++++++++ 50 files changed, 255 insertions(+), 157 deletions(-) create mode 100755 tools/testing/selftests/net/netns_atomic.py -- 2.47.0

11 months, 2 weeks

2
7
0 0

[PATCH] kunit: debugfs: Use IS_ERR() for alloc_string_stream() error check

by Kuan-Wei Chiu

The alloc_string_stream() function only returns ERR_PTR(-ENOMEM) on failure and never returns NULL. Therefore, switching the error check in the caller from IS_ERR_OR_NULL to IS_ERR improves clarity, indicating that this function will return an error pointer (not NULL) when an error occurs. This change avoids any ambiguity regarding the function's return behavior. Link: https://lore.kernel.org/lkml/Zy9deU5VK3YR+r9N@visitorckw-System-Product-Name Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> --- lib/kunit/debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..6273fa9652df 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -181,7 +181,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) * successfully. */ stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) return; string_stream_set_append_newlines(stream, true); @@ -189,7 +189,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) kunit_suite_for_each_test_case(suite, test_case) { stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) goto err; string_stream_set_append_newlines(stream, true); -- 2.34.1

11 months, 2 weeks

2
1
0 0

[PATCH v2] kunit: Fix potential null dereference in kunit_device_driver_test()

by Gax-c

From: Zichen Xie <zichenxie0106(a)gmail.com> kunit_kzalloc() may return a NULL pointer, dereferencing it without NULL check may lead to NULL dereference. Add a NULL check for test_state. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: Zichen Xie <zichenxie0106(a)gmail.com> Cc: stable(a)vger.kernel.org --- v2: Add Cc tag. --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); -- 2.34.1

11 months, 2 weeks

2
1
0 0

[PATCH v1] MAINTAINERS: Update KUnit email address for Brendan Higgins

by Brendan Higgins

Update Brendan's email address for the KUnit entry. Signed-off-by: Brendan Higgins <brendanhiggins(a)google.com> --- I am leaving Google and am going through and cleaning up my @google.com address in the relevant places. This patch updates my email address for the KUnit entry. I am removing myself from the ASPEED I2C entry in a separate patch. Do note that Friday, November 15 2024 is my last day at Google after which I will lose access to this email account so any future updates or comments after Friday will come from my @linux.dev account. --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b878ddc99f94e..d077a3deeb386 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12405,7 +12405,7 @@ F: fs/smb/common/ F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) -M: Brendan Higgins <brendanhiggins(a)google.com> +M: Brendan Higgins <brendan.higgins(a)linux.dev> M: David Gow <davidgow(a)google.com> R: Rae Moar <rmoar(a)google.com> L: linux-kselftest(a)vger.kernel.org base-commit: cfaaa7d010d1fc58f9717fcc8591201e741d2d49 -- 2.47.0.338.g60cca15819-goog

11 months, 2 weeks

2
1
0 0

[RFC PATCH v3 0/6] Direct Map Removal for guest_memfd

by Patrick Roy

Unmapping virtual machine guest memory from the host kernel's direct map is a successful mitigation against Spectre-style transient execution issues: If the kernel page tables do not contain entries pointing to guest memory, then any attempted speculative read through the direct map will necessarily be blocked by the MMU before any observable microarchitectural side-effects happen. This means that Spectre-gadgets and similar cannot be used to target virtual machine memory. Roughly 60% of speculative execution issues fall into this category [1, Table 1]. This patch series extends guest_memfd with the ability to remove its memory from the host kernel's direct map, to be able to attain the above protection for KVM guests running inside guest_memfd. === Changes to v2 === - Handle direct map removal for physically contiguous pages in arch code (Mike R.) - Track the direct map state in guest_memfd itself instead of at the folio level, to prepare for huge pages support (Sean C.) - Allow configuring direct map state of not-yet faulted in memory (Vishal A.) - Pay attention to alignment in ftrace structs (Steven R.) Most significantly, I've reduced the patch series to focus only on direct map removal for guest_memfd for now, leaving the whole "how to do non-CoCo VMs in guest_memfd" for later. If this separation is acceptable, then I think I can drop the RFC tag in the next revision (I've mainly kept it here because I'm not entirely sure what to do with patches 3 and 4). === Implementation === This patch series introduces a new flag to the KVM_CREATE_GUEST_MEMFD that causes guest_memfd to remove its pages from the host kernel's direct map immediately after population/preparation. It also adds infrastructure for tracking the direct map state of all gmem folios inside the guest_memfd inode. Storing this information in the inode has the advantage that the code is ready for future hugepages extensions, where only removing/reinserting direct map entries for sub-ranges of a huge folio is a valid usecase, and it allows pre-configuring the direct map state of not-yet faulted in parts of memory (for example, when the VMM is receiving a RX virtio buffer from the guest). === Summary === Patch 1 (from Mike Rapoport) adds arch APIs for manipulating the direct map for ranges of physically contiguous pages, which are used by guest_memfd in follow up patches. Patch 2 adds the KVM_GMEM_NO_DIRECT_MAP flag and the logic for configuring direct map state of freshly prepared folios. Patches 3 and 4 mainly serve an illustrative purpose, to show how the framework from patch 2 can be extended with routines for runtime direct map manipulation. Patches 5 and 6 deal with documentation and self-tests respectively. [1]: https://download.vusec.net/papers/quarantine_raid23.pdf [RFC v1]: https://lore.kernel.org/kvm/20240709132041.3625501-1-roypat@amazon.co.uk/ [RFC v2]: https://lore.kernel.org/kvm/20240910163038.1298452-1-roypat@amazon.co.uk/ Mike Rapoport (Microsoft) (1): arch: introduce set_direct_map_valid_noflush() Patrick Roy (5): kvm: gmem: add flag to remove memory from kernel direct map kvm: gmem: implement direct map manipulation routines kvm: gmem: add trace point for direct map state changes kvm: document KVM_GMEM_NO_DIRECT_MAP flag kvm: selftests: run gmem tests with KVM_GMEM_NO_DIRECT_MAP set Documentation/virt/kvm/api.rst | 14 + arch/arm64/include/asm/set_memory.h | 1 + arch/arm64/mm/pageattr.c | 10 + arch/loongarch/include/asm/set_memory.h | 1 + arch/loongarch/mm/pageattr.c | 21 ++ arch/riscv/include/asm/set_memory.h | 1 + arch/riscv/mm/pageattr.c | 15 + arch/s390/include/asm/set_memory.h | 1 + arch/s390/mm/pageattr.c | 11 + arch/x86/include/asm/set_memory.h | 1 + arch/x86/mm/pat/set_memory.c | 8 + include/linux/set_memory.h | 6 + include/trace/events/kvm.h | 22 ++ include/uapi/linux/kvm.h | 2 + .../testing/selftests/kvm/guest_memfd_test.c | 2 +- .../kvm/x86_64/private_mem_conversions_test.c | 7 +- virt/kvm/guest_memfd.c | 280 +++++++++++++++++- 17 files changed, 384 insertions(+), 19 deletions(-) base-commit: 5cb1659f412041e4780f2e8ee49b2e03728a2ba6 -- 2.47.0

11 months, 2 weeks

9
35
0 0

LKFT CI: improving Networking selftests results when validating stable kernels

by Matthieu Baerts

Hello LKFT maintainers, CI operators, First, I would like to say thank you to the people behind the LKFT project for validating stable kernels (and more), and including some Network selftests in their tests suites. A lot of improvements around the networking kselftests have been done this year. At the last Netconf [1], we discussed how these tests were validated on stable kernels from CIs like the LKFT one, and we have some suggestions to improve the situation. KSelftests from the same version -------------------------------- According to the doc [2], kselftests should support all previous kernel versions. The LKFT CI is then using the kselftests from the last stable release to validate all stable versions. Even if there are good reasons to do that, we would like to ask for an opt-out for this policy for the networking tests: this is hard to maintain with the increased complexity, hard to validate on all stable kernels before applying patches, and hard to put in place in some situations. As a result, many tests are failing on older kernels, and it looks like it is a lot of work to support older kernels, and to maintain this. Many networking tests are validating the internal behaviour that is not exposed to the userspace. A typical example: some tests look at the raw packets being exchanged during a test, and this behaviour can change without modifying how the userspace is interacting with the kernel. The kernel could expose capabilities, but that's not something that seems natural to put in place for internal behaviours that are not exposed to end users. Maybe workarounds could be used, e.g. looking at kernel symbols, etc. Nut that doesn't always work, increase the complexity, and often "false positive" issue will be noticed only after a patch hits stable, and will cause a bunch of tests to be ignored. Regarding fixes, ideally they will come with a new or modified test that can also be backported. So the coverage can continue to grow in stable versions too. Do you think that from the kernel v6.12 (or before?), the LKFT CI could run the networking kselftests from the version that is being validated, and not from a newer one? So validating the selftests from v6.12.1 on a v6.12.1, and not the ones from a future v6.16.y on a v6.12.42. Skipped tests ------------- It looks like many tests are skipped: - Some have been in a skip file [3] for a while: maybe they can be removed? - Some are skipped because of missing tools: maybe they can be added? e.g. iputils, tshark, ipv6toolkit, etc. - Some tests are in 'net', but in subdirectories, and hence not tested, e.g. forwarding, packetdrill, netfilter, tcp_ao. Could they be tested too? How can we change this to increase the code coverage using existing tests? KVM --- It looks like different VMs are being used to execute the different tests. Do these VMs benefit from any accelerations like KVM? If not, some tests might fail because the environment is too slow. The KSFT_MACHINE_SLOW=yes env var can be set to increase some tolerances, timeout or to skip some parts, but that might not be enough for some tests. Notifications ------------- In case of new regressions, who is being notified? Are the people from the MAINTAINERS file, and linked to the corresponding selftests being notified or do they need to do the monitoring on their side? Looking forward to improving the networking selftests results when validating stable kernels! [1] https://netdev.bots.linux.dev/netconf/2024/ [2] https://docs.kernel.org/dev-tools/kselftest.html [3] https://github.com/Linaro/test-definitions/blob/master/automated/linux/ksel… Cheers, Matt -- Sponsored by the NGI0 Core fund.

11 months, 2 weeks

3
6
0 0

[PATCH] kunit: Fix potential null dereference in kunit_device_driver_test()

by Gax-c

From: Zichen Xie <zichenxie0106(a)gmail.com> kunit_kzalloc() may return a NULL pointer, dereferencing it without NULL check may lead to NULL dereference. Add a NULL check for test_state. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: Zichen Xie <zichenxie0106(a)gmail.com> --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); -- 2.34.1

11 months, 2 weeks

2
1
0 0

[PATCH v8 00/29] riscv control-flow integrity for usermode

by Deepak Gupta

Basics and overview =================== Software with larger attack surfaces (e.g. network facing apps like databases, browsers or apps relying on browser runtimes) suffer from memory corruption issues which can be utilized by attackers to bend control flow of the program to eventually gain control (by making their payload executable). Attackers are able to perform such attacks by leveraging call-sites which rely on indirect calls or return sites which rely on obtaining return address from stack memory. To mitigate such attacks, risc-v extension zicfilp enforces that all indirect calls must land on a landing pad instruction `lpad` else cpu will raise software check exception (a new cpu exception cause code on riscv). Similarly for return flow, risc-v extension zicfiss extends architecture with - `sspush` instruction to push return address on a shadow stack - `sspopchk` instruction to pop return address from shadow stack and compare with input operand (i.e. return address on stack) - `sspopchk` to raise software check exception if comparision above was a mismatch - Protection mechanism using which shadow stack is not writeable via regular store instructions More information an details can be found at extensions github repo [1]. Equivalent to landing pad (zicfilp) on x86 is `ENDBRANCH` instruction in Intel CET [3] and branch target identification (BTI) [4] on arm. Similarly x86's Intel CET has shadow stack [5] and arm64 has guarded control stack (GCS) [6] which are very similar to risc-v's zicfiss shadow stack. x86 already supports shadow stack for user mode and arm64 support for GCS in usermode [7] is in -next. Kernel awareness for user control flow integrity ================================================ This series picks up Samuel Holland's envcfg changes [2] as well. So if those are being applied independently, they should be removed from this series. Enabling: In order to maintain compatibility and not break anything in user mode, kernel doesn't enable control flow integrity cpu extensions on binary by default. Instead exposes a prctl interface to enable, disable and lock the shadow stack or landing pad feature for a task. This allows userspace (loader) to enumerate if all objects in its address space are compiled with shadow stack and landing pad support and accordingly enable the feature. Additionally if a subsequent `dlopen` happens on a library, user mode can take a decision again to disable the feature (if incoming library is not compiled with support) OR terminate the task (if user mode policy is strict to have all objects in address space to be compiled with control flow integirty cpu feature). prctl to enable shadow stack results in allocating shadow stack from virtual memory and activating for user address space. x86 and arm64 are also following same direction due to similar reason(s). clone/fork: On clone and fork, cfi state for task is inherited by child. Shadow stack is part of virtual memory and is a writeable memory from kernel perspective (writeable via a restricted set of instructions aka shadow stack instructions) Thus kernel changes ensure that this memory is converted into read-only when fork/clone happens and COWed when fault is taken due to sspush, sspopchk or ssamoswap. In case `CLONE_VM` is specified and shadow stack is to be enabled, kernel will automatically allocate a shadow stack for that clone call. map_shadow_stack: x86 introduced `map_shadow_stack` system call to allow user space to explicitly map shadow stack memory in its address space. It is useful to allocate shadow for different contexts managed by a single thread (green threads or contexts) risc-v implements this system call as well. signal management: If shadow stack is enabled for a task, kernel performs an asynchronous control flow diversion to deliver the signal and eventually expects userspace to issue sigreturn so that original execution can be resumed. Even though resume context is prepared by kernel, it is in user space memory and is subject to memory corruption and corruption bugs can be utilized by attacker in this race window to perform arbitrary sigreturn and eventually bypass cfi mechanism. Another issue is how to ensure that cfi related state on sigcontext area is not trampled by legacy apps or apps compiled with old kernel headers. In order to mitigate control-flow hijacting, kernel prepares a token and place it on shadow stack before signal delivery and places address of token in sigcontext structure. During sigreturn, kernel obtains address of token from sigcontext struture, reads token from shadow stack and validates it and only then allow sigreturn to succeed. Compatiblity issue is solved by adopting dynamic sigcontext management introduced for vector extension. This series re-factor the code little bit to allow future sigcontext management easy (as proposed by Andy Chiu from SiFive) config and compilation: Introduce a new risc-v config option `CONFIG_RISCV_USER_CFI`. Selecting this config option picks the kernel support for user control flow integrity. This optin is presented only if toolchain has shadow stack and landing pad support. And is on purpose guarded by toolchain support. Reason being that eventually vDSO also needs to be compiled in with shadow stack and landing pad support. vDSO compile patches are not included as of now because landing pad labeling scheme is yet to settle for usermode runtime. To get more information on kernel interactions with respect to zicfilp and zicfiss, patch series adds documentation for `zicfilp` and `zicfiss` in following: Documentation/arch/riscv/zicfiss.rst Documentation/arch/riscv/zicfilp.rst How to test this series ======================= Toolchain --------- $ git clone git@github.com:sifive/riscv-gnu-toolchain.git -b cfi-dev $ riscv-gnu-toolchain/configure --prefix=<path-to-where-to-build> --with-arch=rv64gc_zicfilp_zicfiss --enable-linux --disable-gdb --with-extra-multilib-test="rv64gc_zicfilp_zicfiss-lp64d:-static" $ make -j$(nproc) Qemu ---- $ git clone git@github.com:deepak0414/qemu.git -b zicfilp_zicfiss_ratified_master_july11 $ cd qemu $ mkdir build $ cd build $ ../configure --target-list=riscv64-softmmu $ make -j$(nproc) Opensbi ------- $ git clone git@github.com:deepak0414/opensbi.git -b v6_cfi_spec_split_opensbi $ make CROSS_COMPILE=<your riscv toolchain> -j$(nproc) PLATFORM=generic Linux ----- Running defconfig is fine. CFI is enabled by default if the toolchain supports it. $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) defconfig $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) Branch where user cfi enabling patches are maintained https://github.com/deepak0414/linux-riscv-cfi/tree/vdso_user_cfi_v6.12-rc1 In case you're building your own rootfs using toolchain, please make sure you pick following patch to ensure that vDSO compiled with lpad and shadow stack. "arch/riscv: compile vdso with landing pad" Running ------- Modify your qemu command to have: -bios <path-to-cfi-opensbi>/build/platform/generic/firmware/fw_dynamic.bin -cpu rv64,zicfilp=true,zicfiss=true,zimop=true,zcmop=true vDSO related Opens (in the flux) ================================= I am listing these opens for laying out plan and what to expect in future patch sets. And of course for the sake of discussion. Shadow stack and landing pad enabling in vDSO ---------------------------------------------- vDSO must have shadow stack and landing pad support compiled in for task to have shadow stack and landing pad support. This patch series doesn't enable that (yet). Enabling shadow stack support in vDSO should be straight forward (intend to do that in next versions of patch set). Enabling landing pad support in vDSO requires some collaboration with toolchain folks to follow a single label scheme for all object binaries. This is necessary to ensure that all indirect call-sites are setting correct label and target landing pads are decorated with same label scheme. How many vDSOs --------------- Shadow stack instructions are carved out of zimop (may be operations) and if CPU doesn't implement zimop, they're illegal instructions. Kernel could be running on a CPU which may or may not implement zimop. And thus kernel will have to carry 2 different vDSOs and expose the appropriate one depending on whether CPU implements zimop or not. References ========== [1] - https://github.com/riscv/riscv-cfi [2] - https://lore.kernel.org/all/20240814081126.956287-1-samuel.holland@sifive.c… [3] - https://lwn.net/Articles/889475/ [4] - https://developer.arm.com/documentation/109576/0100/Branch-Target-Identific… [5] - https://www.intel.com/content/dam/develop/external/us/en/documents/catc17-i… [6] - https://lwn.net/Articles/940403/ [7] - https://lore.kernel.org/all/20241001-arm64-gcs-v13-0-222b78d87eee@kernel.or… --- changelog --------- v8: - rebased on palmer/for-next - dropped samuel holland's `envcfg` context switch patches. they are in parlmer/for-next v7: - Removed "riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv" Instead using `deactivate_mm` flow to clean up. see here for more context https://lore.kernel.org/all/20230908203655.543765-1-rick.p.edgecombe@intel.… - Changed the header include in `kselftest`. Hopefully this fixes compile issue faced by Zong Li at SiFive. - Cleaned up an orphaned change to `mm/mmap.c` in below patch "riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE" - Lock interfaces for shadow stack and indirect branch tracking expect arg == 0 Any future evolution of this interface should accordingly define how arg should be setup. - `mm/map.c` has an instance of using `VM_SHADOW_STACK`. Fixed it to use helper `is_shadow_stack_vma`. - Link to v6: https://lore.kernel.org/r/20241008-v5_user_cfi_series-v6-0-60d9fe073f37@riv… v6: - Picked up Samuel Holland's changes as is with `envcfg` placed in `thread` instead of `thread_info` - fixed unaligned newline escapes in kselftest - cleaned up messages in kselftest and included test output in commit message - fixed a bug in clone path reported by Zong Li - fixed a build issue if CONFIG_RISCV_ISA_V is not selected (this was introduced due to re-factoring signal context management code) v5: - rebased on v6.12-rc1 - Fixed schema related issues in device tree file - Fixed some of the documentation related issues in zicfilp/ss.rst (style issues and added index) - added `SHADOW_STACK_SET_MARKER` so that implementation can define base of shadow stack. - Fixed warnings on definitions added in usercfi.h when CONFIG_RISCV_USER_CFI is not selected. - Adopted context header based signal handling as proposed by Andy Chiu - Added support for enabling kernel mode access to shadow stack using FWFT (https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/src/ext-firmware…) - Link to v5: https://lore.kernel.org/r/20241001-v5_user_cfi_series-v1-0-3ba65b6e550f@riv… (Note: I had an issue in my workflow due to which version number wasn't picked up correctly while sending out patches) v4: - rebased on 6.11-rc6 - envcfg: Converged with Samuel Holland's patches for envcfg management on per- thread basis. - vma_is_shadow_stack is renamed to is_vma_shadow_stack - picked up Mark Brown's `ARCH_HAS_USER_SHADOW_STACK` patch - signal context: using extended context management to maintain compatibility. - fixed `-Wmissing-prototypes` compiler warnings for prctl functions - Documentation fixes and amending typos. - Link to v4: https://lore.kernel.org/all/20240912231650.3740732-1-debug@rivosinc.com/ v3: - envcfg logic to pick up base envcfg had a bug where `ENVCFG_CBZE` could have been picked on per task basis, even though CPU didn't implement it. Fixed in this series. - dt-bindings As suggested, split into separate commit. fixed the messaging that spec is in public review - arch_is_shadow_stack change arch_is_shadow_stack changed to vma_is_shadow_stack - hwprobe zicfiss / zicfilp if present will get enumerated in hwprobe - selftests As suggested, added object and binary filenames to .gitignore Selftest binary anyways need to be compiled with cfi enabled compiler which will make sure that landing pad and shadow stack are enabled. Thus removed separate enable/disable tests. Cleaned up tests a bit. - Link to v3: https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ v2: - Using config `CONFIG_RISCV_USER_CFI`, kernel support for riscv control flow integrity for user mode programs can be compiled in the kernel. - Enabling of control flow integrity for user programs is left to user runtime - This patch series introduces arch agnostic `prctls` to enable shadow stack and indirect branch tracking. And implements them on riscv. --- Changes in v8: - EDITME: describe what is new in this series revision. - EDITME: use bulletpoints and terse descriptions. - Link to v7: https://lore.kernel.org/r/20241029-v5_user_cfi_series-v7-0-2727ce9936cb@riv… --- Andy Chiu (1): riscv: signal: abstract header saving for setup_sigcontext Clément Léger (1): riscv: Add Firmware Feature SBI extensions definitions Deepak Gupta (25): mm: helper `is_shadow_stack_vma` to check shadow stack vma dt-bindings: riscv: zicfilp and zicfiss in dt-bindings (extensions.yaml) riscv: zicfiss / zicfilp enumeration riscv: zicfiss / zicfilp extension csr and bit definitions riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE riscv mm: manufacture shadow stack pte riscv mmu: teach pte_mkwrite to manufacture shadow stack PTEs riscv mmu: write protect and shadow stack riscv/mm: Implement map_shadow_stack() syscall riscv/shstk: If needed allocate a new shadow stack on clone prctl: arch-agnostic prctl for indirect branch tracking riscv: Implements arch agnostic shadow stack prctls riscv: Implements arch agnostic indirect branch tracking prctls riscv/traps: Introduce software check exception riscv/signal: save and restore of shadow stack for signal riscv/kernel: update __show_regs to print shadow stack register riscv/ptrace: riscv cfi status and state via ptrace and in core files riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe riscv: enable kernel access to shadow stack memory via FWFT sbi call riscv: kernel command line option to opt out of user cfi riscv: create a config for shadow stack and landing pad instr support riscv: Documentation for landing pad / indirect branch tracking riscv: Documentation for shadow stack on riscv kselftest/riscv: kselftest for user mode cfi Mark Brown (2): mm: Introduce ARCH_HAS_USER_SHADOW_STACK prctl: arch-agnostic prctl for shadow stack Documentation/arch/riscv/index.rst | 2 + Documentation/arch/riscv/zicfilp.rst | 115 +++++ Documentation/arch/riscv/zicfiss.rst | 176 +++++++ .../devicetree/bindings/riscv/extensions.yaml | 14 + arch/riscv/Kconfig | 20 + arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/cpufeature.h | 13 + arch/riscv/include/asm/csr.h | 16 + arch/riscv/include/asm/entry-common.h | 2 + arch/riscv/include/asm/hwcap.h | 2 + arch/riscv/include/asm/mman.h | 24 + arch/riscv/include/asm/mmu_context.h | 7 + arch/riscv/include/asm/pgtable.h | 30 +- arch/riscv/include/asm/processor.h | 2 + arch/riscv/include/asm/sbi.h | 27 ++ arch/riscv/include/asm/thread_info.h | 3 + arch/riscv/include/asm/usercfi.h | 89 ++++ arch/riscv/include/asm/vector.h | 3 + arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/include/uapi/asm/ptrace.h | 22 + arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/asm-offsets.c | 8 + arch/riscv/kernel/cpufeature.c | 2 + arch/riscv/kernel/entry.S | 31 +- arch/riscv/kernel/head.S | 12 + arch/riscv/kernel/process.c | 26 +- arch/riscv/kernel/ptrace.c | 83 ++++ arch/riscv/kernel/signal.c | 140 +++++- arch/riscv/kernel/sys_hwprobe.c | 2 + arch/riscv/kernel/sys_riscv.c | 10 + arch/riscv/kernel/traps.c | 42 ++ arch/riscv/kernel/usercfi.c | 526 +++++++++++++++++++++ arch/riscv/mm/init.c | 2 +- arch/riscv/mm/pgtable.c | 17 + arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/cpu.h | 4 + include/linux/mm.h | 5 +- include/uapi/asm-generic/mman.h | 4 + include/uapi/linux/elf.h | 1 + include/uapi/linux/prctl.h | 48 ++ kernel/sys.c | 60 +++ mm/Kconfig | 6 + mm/gup.c | 2 +- mm/mmap.c | 2 +- mm/vma.h | 10 +- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 84 ++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 78 +++ tools/testing/selftests/riscv/cfi/shadowstack.c | 373 +++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 37 ++ 54 files changed, 2171 insertions(+), 35 deletions(-) --- base-commit: 64f7b77f0bd9271861ed9e410e9856b6b0b21c48 change-id: 20240930-v5_user_cfi_series-3dc332f8f5b2 -- - debug

11 months, 2 weeks

2
36
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror November 2024