- Linux-kselftest-mirror - lists.linaro.org

[PATCH v1] selftests/mm: two fixes for the pfnmap test

by David Hildenbrand

When unregistering the signal handler, we have to pass SIG_DFL, and blindly reading from PFN 0 and PFN 1 seems to be problematic on !x86 systems. In particularly, on arm64 tx2 machines where noting resides at these physical memory locations, we can generate RAS errors. Let's fix it by scanning /proc/iomem for actual "System RAM". Reported-by: Ryan Roberts <ryan.roberts(a)arm.com> Closes: https://lore.kernel.org/all/232960c2-81db-47ca-a337-38c4bce5f997@arm.com/T/… Fixes: 2616b370323a ("selftests/mm: add simple VM_PFNMAP tests based on mmap'ing /dev/mem") Reviewed-by: Ryan Roberts <ryan.roberts(a)arm.com> Tested-by: Aishwarya TCV <aishwarya.tcv(a)arm.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> --- tools/testing/selftests/mm/pfnmap.c | 61 +++++++++++++++++++++++++++-- 1 file changed, 57 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c index 8a9d19b6020c7..866ac023baf5c 100644 --- a/tools/testing/selftests/mm/pfnmap.c +++ b/tools/testing/selftests/mm/pfnmap.c @@ -12,6 +12,8 @@ #include <stdint.h> #include <unistd.h> #include <errno.h> +#include <stdio.h> +#include <ctype.h> #include <fcntl.h> #include <signal.h> #include <setjmp.h> @@ -43,14 +45,62 @@ static int test_read_access(char *addr, size_t size, size_t pagesize) /* Force a read that the compiler cannot optimize out. */ *((volatile char *)(addr + offs)); } - if (signal(SIGSEGV, signal_handler) == SIG_ERR) + if (signal(SIGSEGV, SIG_DFL) == SIG_ERR) return -EINVAL; return ret; } +static int find_ram_target(off_t *phys_addr, + unsigned long long pagesize) +{ + unsigned long long start, end; + char line[80], *end_ptr; + FILE *file; + + /* Search /proc/iomem for the first suitable "System RAM" range. */ + file = fopen("/proc/iomem", "r"); + if (!file) + return -errno; + + while (fgets(line, sizeof(line), file)) { + /* Ignore any child nodes. */ + if (!isalnum(line[0])) + continue; + + if (!strstr(line, "System RAM\n")) + continue; + + start = strtoull(line, &end_ptr, 16); + /* Skip over the "-" */ + end_ptr++; + /* Make end "exclusive". */ + end = strtoull(end_ptr, NULL, 16) + 1; + + /* Actual addresses are not exported */ + if (!start && !end) + break; + + /* We need full pages. */ + start = (start + pagesize - 1) & ~(pagesize - 1); + end &= ~(pagesize - 1); + + if (start != (off_t)start) + break; + + /* We need two pages. */ + if (end > start + 2 * pagesize) { + fclose(file); + *phys_addr = start; + return 0; + } + } + return -ENOENT; +} + FIXTURE(pfnmap) { + off_t phys_addr; size_t pagesize; int dev_mem_fd; char *addr1; @@ -63,14 +113,17 @@ FIXTURE_SETUP(pfnmap) { self->pagesize = getpagesize(); + /* We'll require two physical pages throughout our tests ... */ + if (find_ram_target(&self->phys_addr, self->pagesize)) + SKIP(return, "Cannot find ram target in '/proc/iomem'\n"); + self->dev_mem_fd = open("/dev/mem", O_RDONLY); if (self->dev_mem_fd < 0) SKIP(return, "Cannot open '/dev/mem'\n"); - /* We'll require the first two pages throughout our tests ... */ self->size1 = self->pagesize * 2; self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED, - self->dev_mem_fd, 0); + self->dev_mem_fd, self->phys_addr); if (self->addr1 == MAP_FAILED) SKIP(return, "Cannot mmap '/dev/mem'\n"); @@ -129,7 +182,7 @@ TEST_F(pfnmap, munmap_split) */ self->size2 = self->pagesize; self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED, - self->dev_mem_fd, 0); + self->dev_mem_fd, self->phys_addr); ASSERT_NE(self->addr2, MAP_FAILED); } -- 2.49.0

51 minutes

1
0
0 0

[PATCH v2] selftests/mm: add simple VM_PFNMAP tests based on mmap'ing /dev/mem

by David Hildenbrand

Let's test some basic functionality using /dev/mem. These tests will implicitly cover some PAT (Page Attribute Handling) handling on x86. These tests will only run when /dev/mem access to the first two pages in physical address space is possible and allowed; otherwise, the tests are skipped. On current x86-64 with PAT inside a VM, all tests pass: TAP version 13 1..6 # Starting 6 tests from 1 test cases. # RUN pfnmap.madvise_disallowed ... # OK pfnmap.madvise_disallowed ok 1 pfnmap.madvise_disallowed # RUN pfnmap.munmap_split ... # OK pfnmap.munmap_split ok 2 pfnmap.munmap_split # RUN pfnmap.mremap_fixed ... # OK pfnmap.mremap_fixed ok 3 pfnmap.mremap_fixed # RUN pfnmap.mremap_shrink ... # OK pfnmap.mremap_shrink ok 4 pfnmap.mremap_shrink # RUN pfnmap.mremap_expand ... # OK pfnmap.mremap_expand ok 5 pfnmap.mremap_expand # RUN pfnmap.fork ... # OK pfnmap.fork ok 6 pfnmap.fork # PASSED: 6 / 6 tests passed. # Totals: pass:6 fail:0 xfail:0 xpass:0 skip:0 error:0 However, we are able to trigger: [ 27.888251] x86/PAT: pfnmap:1790 freeing invalid memtype [mem 0x00000000-0x00000fff] There are probably more things worth testing in the future, such as MAP_PRIVATE handling. But this set of tests is sufficient to cover most of the things we will rework regarding PAT handling. Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Dev Jain <dev.jain(a)arm.com> Signed-off-by: David Hildenbrand <david(a)redhat.com> --- Hopefully I didn't miss any review feedback. v1 -> v2: * Rewrite using kselftest_harness, which simplifies a lot of things * Add to .gitignore and run_vmtests.sh * Register signal handler on demand * Use volatile trick to force a read (not factoring out FORCE_READ just yet) * Drop mprotect() test case * Add some more comments why we test certain things * Use NULL for mmap() first parameter instead of 0 * Smaller fixes --- tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/pfnmap.c | 196 ++++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 4 + 4 files changed, 202 insertions(+) create mode 100644 tools/testing/selftests/mm/pfnmap.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 91db34941a143..824266982aa36 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -20,6 +20,7 @@ mremap_test on-fault-limit transhuge-stress pagemap_ioctl +pfnmap *.tmp* protection_keys protection_keys_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ad4d6043a60f0..ae6f994d3add7 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -84,6 +84,7 @@ TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl +TEST_GEN_FILES += pfnmap TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c new file mode 100644 index 0000000000000..8a9d19b6020c7 --- /dev/null +++ b/tools/testing/selftests/mm/pfnmap.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Basic VM_PFNMAP tests relying on mmap() of '/dev/mem' + * + * Copyright 2025, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david(a)redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <signal.h> +#include <setjmp.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/wait.h> + +#include "../kselftest_harness.h" +#include "vm_util.h" + +static sigjmp_buf sigjmp_buf_env; + +static void signal_handler(int sig) +{ + siglongjmp(sigjmp_buf_env, -EFAULT); +} + +static int test_read_access(char *addr, size_t size, size_t pagesize) +{ + size_t offs; + int ret; + + if (signal(SIGSEGV, signal_handler) == SIG_ERR) + return -EINVAL; + + ret = sigsetjmp(sigjmp_buf_env, 1); + if (!ret) { + for (offs = 0; offs < size; offs += pagesize) + /* Force a read that the compiler cannot optimize out. */ + *((volatile char *)(addr + offs)); + } + if (signal(SIGSEGV, signal_handler) == SIG_ERR) + return -EINVAL; + + return ret; +} + +FIXTURE(pfnmap) +{ + size_t pagesize; + int dev_mem_fd; + char *addr1; + size_t size1; + char *addr2; + size_t size2; +}; + +FIXTURE_SETUP(pfnmap) +{ + self->pagesize = getpagesize(); + + self->dev_mem_fd = open("/dev/mem", O_RDONLY); + if (self->dev_mem_fd < 0) + SKIP(return, "Cannot open '/dev/mem'\n"); + + /* We'll require the first two pages throughout our tests ... */ + self->size1 = self->pagesize * 2; + self->addr1 = mmap(NULL, self->size1, PROT_READ, MAP_SHARED, + self->dev_mem_fd, 0); + if (self->addr1 == MAP_FAILED) + SKIP(return, "Cannot mmap '/dev/mem'\n"); + + /* ... and want to be able to read from them. */ + if (test_read_access(self->addr1, self->size1, self->pagesize)) + SKIP(return, "Cannot read-access mmap'ed '/dev/mem'\n"); + + self->size2 = 0; + self->addr2 = MAP_FAILED; +} + +FIXTURE_TEARDOWN(pfnmap) +{ + if (self->addr2 != MAP_FAILED) + munmap(self->addr2, self->size2); + if (self->addr1 != MAP_FAILED) + munmap(self->addr1, self->size1); + if (self->dev_mem_fd >= 0) + close(self->dev_mem_fd); +} + +TEST_F(pfnmap, madvise_disallowed) +{ + int advices[] = { + MADV_DONTNEED, + MADV_DONTNEED_LOCKED, + MADV_FREE, + MADV_WIPEONFORK, + MADV_COLD, + MADV_PAGEOUT, + MADV_POPULATE_READ, + MADV_POPULATE_WRITE, + }; + int i; + + /* All these advices must be rejected. */ + for (i = 0; i < ARRAY_SIZE(advices); i++) { + EXPECT_LT(madvise(self->addr1, self->pagesize, advices[i]), 0); + EXPECT_EQ(errno, EINVAL); + } +} + +TEST_F(pfnmap, munmap_split) +{ + /* + * Unmap the first page. This munmap() call is not really expected to + * fail, but we might be able to trigger other internal issues. + */ + ASSERT_EQ(munmap(self->addr1, self->pagesize), 0); + + /* + * Remap the first page while the second page is still mapped. This + * makes sure that any PAT tracking on x86 will allow for mmap()'ing + * a page again while some parts of the first mmap() are still + * around. + */ + self->size2 = self->pagesize; + self->addr2 = mmap(NULL, self->pagesize, PROT_READ, MAP_SHARED, + self->dev_mem_fd, 0); + ASSERT_NE(self->addr2, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_fixed) +{ + char *ret; + + /* Reserve a destination area. */ + self->size2 = self->size1; + self->addr2 = mmap(NULL, self->size2, PROT_READ, MAP_ANON | MAP_PRIVATE, + -1, 0); + ASSERT_NE(self->addr2, MAP_FAILED); + + /* mremap() over our destination. */ + ret = mremap(self->addr1, self->size1, self->size2, + MREMAP_FIXED | MREMAP_MAYMOVE, self->addr2); + ASSERT_NE(ret, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_shrink) +{ + char *ret; + + /* Shrinking is expected to work. */ + ret = mremap(self->addr1, self->size1, self->size1 - self->pagesize, 0); + ASSERT_NE(ret, MAP_FAILED); +} + +TEST_F(pfnmap, mremap_expand) +{ + /* + * Growing is not expected to work, and getting it right would + * be challenging. So this test primarily serves as an early warning + * that something that probably should never work suddenly works. + */ + self->size2 = self->size1 + self->pagesize; + self->addr2 = mremap(self->addr1, self->size1, self->size2, MREMAP_MAYMOVE); + ASSERT_EQ(self->addr2, MAP_FAILED); +} + +TEST_F(pfnmap, fork) +{ + pid_t pid; + int ret; + + /* fork() a child and test if the child can access the pages. */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (!pid) { + EXPECT_EQ(test_read_access(self->addr1, self->size1, + self->pagesize), 0); + exit(0); + } + + wait(&ret); + if (WIFEXITED(ret)) + ret = WEXITSTATUS(ret); + else + ret = -EINVAL; + ASSERT_EQ(ret, 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 188b125bf1f6b..dddd1dd8af145 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -63,6 +63,8 @@ separated by spaces: test soft dirty page bit semantics - pagemap test pagemap_scan IOCTL +- pfnmap + tests for VM_PFNMAP handling - cow test copy-on-write semantics - thp @@ -472,6 +474,8 @@ fi CATEGORY="pagemap" run_test ./pagemap_ioctl +CATEGORY="pfnmap" run_test ./pfnmap + # COW tests CATEGORY="cow" run_test ./cow -- 2.49.0

56 minutes

4
12
0 0

[PATCH RFC net-next v2] page_pool: import Jesper's page_pool benchmark

by Mina Almasry

From: Jesper Dangaard Brouer <hawk(a)kernel.org> We frequently consult with Jesper's out-of-tree page_pool benchmark to evaluate page_pool changes. Import the benchmark into the upstream linux kernel tree so that (a) we're all running the same version, (b) pave the way for shared improvements, and (c) maybe one day integrate it with nipa, if possible. Import bench_page_pool_simple from commit 35b1716d0c30 ("Add page_bench06_walk_all"), from this repository: https://github.com/netoptimizer/prototype-kernel.git Changes done during upstreaming: - Fix checkpatch issues. - Remove the tasklet logic not needed. - Move under tools/testing - Create ksft for the benchmark. - Changed slightly how the benchmark gets build. Out of tree, time_bench is built as an independent .ko. Here it is included in bench_page_pool.ko Steps to run: ``` mkdir -p /tmp/run-pp-bench make -C ./tools/testing/selftests/net/bench make -C ./tools/testing/selftests/net/bench install INSTALL_PATH=/tmp/run-pp-bench rsync --delete -avz --progress /tmp/run-pp-bench mina@$SERVER:~/ ssh mina@$SERVER << EOF cd ~/run-pp-bench && sudo ./test_bench_page_pool.sh EOF ``` Output: ``` (benchmrk dmesg logs) Fast path results: no-softirq-page_pool01 Per elem: 11 cycles(tsc) 4.368 ns ptr_ring results: no-softirq-page_pool02 Per elem: 527 cycles(tsc) 195.187 ns slow path results: no-softirq-page_pool03 Per elem: 549 cycles(tsc) 203.466 ns ``` Cc: Jesper Dangaard Brouer <hawk(a)kernel.org> Cc: Ilias Apalodimas <ilias.apalodimas(a)linaro.org> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Toke Høiland-Jørgensen <toke(a)toke.dk> Signed-off-by: Mina Almasry <almasrymina(a)google.com> --- v2: - Move under tools/selftests (Jakub) - Create ksft for it. - Remove the tasklet logic no longer needed (Jesper + Toke) RFC discussion points: - Desirable to import it? - Can the benchmark be imported as-is for an initial version? Or needs lots of modifications? - Code location. I retained the location in Jesper's tree, but a path like net/core/bench/ may make more sense. --- tools/testing/selftests/net/bench/Makefile | 7 + .../selftests/net/bench/page_pool/Makefile | 17 + .../bench/page_pool/bench_page_pool_simple.c | 275 ++++++++++++ .../bench/page_pool/test_bench_page_pool.sh | 32 ++ .../net/bench/page_pool/time_bench.c | 406 ++++++++++++++++++ .../net/bench/page_pool/time_bench.h | 259 +++++++++++ 6 files changed, 996 insertions(+) create mode 100644 tools/testing/selftests/net/bench/Makefile create mode 100644 tools/testing/selftests/net/bench/page_pool/Makefile create mode 100644 tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c create mode 100755 tools/testing/selftests/net/bench/page_pool/test_bench_page_pool.sh create mode 100644 tools/testing/selftests/net/bench/page_pool/time_bench.c create mode 100644 tools/testing/selftests/net/bench/page_pool/time_bench.h diff --git a/tools/testing/selftests/net/bench/Makefile b/tools/testing/selftests/net/bench/Makefile new file mode 100644 index 000000000000..4ebce5d71b18 --- /dev/null +++ b/tools/testing/selftests/net/bench/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +TEST_GEN_MODS_DIR := page_pool + +TEST_PROGS += page_pool/test_bench_page_pool.sh + +include ../../lib.mk diff --git a/tools/testing/selftests/net/bench/page_pool/Makefile b/tools/testing/selftests/net/bench/page_pool/Makefile new file mode 100644 index 000000000000..0549a16ba275 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/Makefile @@ -0,0 +1,17 @@ +BENCH_PAGE_POOL_SIMPLE_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= /lib/modules/$(shell uname -r)/build + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +obj-m += bench_page_pool.o +bench_page_pool-y += bench_page_pool_simple.o time_bench.o + +all: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BENCH_PAGE_POOL_SIMPLE_TEST_DIR) clean diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c new file mode 100644 index 000000000000..53d168cce27d --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -0,0 +1,275 @@ +/* + * Benchmark module for page_pool. + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/mutex.h> + +#include <linux/version.h> +#include <net/page_pool/helpers.h> + +#include <linux/interrupt.h> +#include <linux/limits.h> + +#include "time_bench.h" + +static int verbose = 1; +#define MY_POOL_SIZE 1024 + +static inline void _page_pool_put_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + +/* Makes tests selectable. Useful for perf-record to analyze a single test. + * Hint: Bash shells support writing binary number like: $((2#101010) + * + * # modprobe bench_page_pool_simple run_flags=$((2#100)) + */ +static unsigned long run_flags = 0xFFFFFFFF; +module_param(run_flags, ulong, 0); +MODULE_PARM_DESC(run_flags, "Limit which bench test that runs"); +/* Count the bit number from the enum */ +enum benchmark_bit { + bit_run_bench_baseline, + bit_run_bench_no_softirq01, + bit_run_bench_no_softirq02, + bit_run_bench_no_softirq03, +}; +#define bit(b) (1 << (b)) +#define enabled(b) ((run_flags & (bit(b)))) + +/* notice time_bench is limited to U32_MAX nr loops */ +static unsigned long loops = 10000000; +module_param(loops, ulong, 0); +MODULE_PARM_DESC(loops, "Specify loops bench will run"); + +/* Timing at the nanosec level, we need to know the overhead + * introduced by the for loop itself */ +static int time_bench_for_loop(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + int i; + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +static int time_bench_atomic_inc(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + atomic_t cnt; + int i; + + atomic_set(&cnt, 0); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + atomic_inc(&cnt); + barrier(); /* avoid compiler to optimize this loop */ + } + loops_cnt = atomic_read(&cnt); + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* The ptr_ping in page_pool uses a spinlock. We need to know the minimum + * overhead of taking+releasing a spinlock, to know the cycles that can be saved + * by e.g. amortizing this via bulking. + */ +static int time_bench_lock(struct time_bench_record *rec, void *data) +{ + uint64_t loops_cnt = 0; + spinlock_t lock; + int i; + + spin_lock_init(&lock); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + spin_lock(&lock); + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + spin_unlock(&lock); + } + time_bench_stop(rec, loops_cnt); + return loops_cnt; +} + +/* Helper for filling some page's into ptr_ring */ +static void pp_fill_ptr_ring(struct page_pool *pp, int elems) +{ + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC needed when under run softirq */ + struct page **array; + int i; + + array = kzalloc(sizeof(struct page *) * elems, gfp_mask); + + for (i = 0; i < elems; i++) { + array[i] = page_pool_alloc_pages(pp, gfp_mask); + } + for (i = 0; i < elems; i++) { + _page_pool_put_page(pp, array[i], false); + } + + kfree(array); +} + +enum test_type { type_fast_path, type_ptr_ring, type_page_allocator }; + +/* Depends on compile optimizing this function */ +static __always_inline int time_bench_page_pool(struct time_bench_record *rec, + void *data, enum test_type type, + const char *func) +{ + uint64_t loops_cnt = 0; + gfp_t gfp_mask = GFP_ATOMIC; /* GFP_ATOMIC is not really needed */ + int i, err; + + struct page_pool *pp; + struct page *page; + + struct page_pool_params pp_params = { + .order = 0, + .flags = 0, + .pool_size = MY_POOL_SIZE, + .nid = NUMA_NO_NODE, + .dev = NULL, /* Only use for DMA mapping */ + .dma_dir = DMA_BIDIRECTIONAL, + }; + + pp = page_pool_create(&pp_params); + if (IS_ERR(pp)) { + err = PTR_ERR(pp); + pr_warn("%s: Error(%d) creating page_pool\n", func, err); + goto out; + } + pp_fill_ptr_ring(pp, 64); + + if (in_serving_softirq()) + pr_warn("%s(): in_serving_softirq fast-path\n", func); + else + pr_warn("%s(): Cannot use page_pool fast-path\n", func); + + time_bench_start(rec); + /** Loop to measure **/ + for (i = 0; i < rec->loops; i++) { + /* Common fast-path alloc, that depend on in_serving_softirq() */ + page = page_pool_alloc_pages(pp, gfp_mask); + if (!page) + break; + loops_cnt++; + barrier(); /* avoid compiler to optimize this loop */ + + /* The benchmarks purpose it to test different return paths. + * Compiler should inline optimize other function calls out + */ + if (type == type_fast_path) { + /* Fast-path recycling e.g. XDP_DROP use-case */ + page_pool_recycle_direct(pp, page); + + } else if (type == type_ptr_ring) { + /* Normal return path */ + _page_pool_put_page(pp, page, false); + + } else if (type == type_page_allocator) { + /* Test if not pages are recycled, but instead + * returned back into systems page allocator + */ + get_page(page); /* cause no-recycling */ + _page_pool_put_page(pp, page, false); + put_page(page); + } else { + BUILD_BUG(); + } + } + time_bench_stop(rec, loops_cnt); +out: + page_pool_destroy(pp); + return loops_cnt; +} + +static int time_bench_page_pool01_fast_path(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_fast_path, __func__); +} + +static int time_bench_page_pool02_ptr_ring(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_ptr_ring, __func__); +} + +static int time_bench_page_pool03_slow(struct time_bench_record *rec, + void *data) +{ + return time_bench_page_pool(rec, data, type_page_allocator, __func__); +} + +static int run_benchmark_tests(void) +{ + uint32_t nr_loops = loops; + int passed_count = 0; + + /* Baseline tests */ + if (enabled(bit_run_bench_baseline)) { + time_bench_loop(nr_loops * 10, 0, "for_loop", NULL, + time_bench_for_loop); + time_bench_loop(nr_loops * 10, 0, "atomic_inc", NULL, + time_bench_atomic_inc); + time_bench_loop(nr_loops, 0, "lock", NULL, time_bench_lock); + } + + /* This test cannot activate correct code path, due to no-softirq ctx */ + if (enabled(bit_run_bench_no_softirq01)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool01", NULL, + time_bench_page_pool01_fast_path); + if (enabled(bit_run_bench_no_softirq02)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool02", NULL, + time_bench_page_pool02_ptr_ring); + if (enabled(bit_run_bench_no_softirq03)) + time_bench_loop(nr_loops, 0, "no-softirq-page_pool03", NULL, + time_bench_page_pool03_slow); + + return passed_count; +} + +static int __init bench_page_pool_simple_module_init(void) +{ + if (verbose) + pr_info("Loaded\n"); + + if (loops > U32_MAX) { + pr_err("Module param loops(%lu) exceeded U32_MAX(%u)\n", loops, + U32_MAX); + return -ECHRNG; + } + + run_benchmark_tests(); + + return 0; +} +module_init(bench_page_pool_simple_module_init); + +static void __exit bench_page_pool_simple_module_exit(void) +{ + if (verbose) + pr_info("Unloaded\n"); +} +module_exit(bench_page_pool_simple_module_exit); + +MODULE_DESCRIPTION("Benchmark of page_pool simple cases"); +MODULE_AUTHOR("Jesper Dangaard Brouer <netoptimizer(a)brouer.com>"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/net/bench/page_pool/test_bench_page_pool.sh b/tools/testing/selftests/net/bench/page_pool/test_bench_page_pool.sh new file mode 100755 index 000000000000..5eb48f28b659 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/test_bench_page_pool.sh @@ -0,0 +1,32 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# + +set -e + +DRIVER="./page_pool/bench_page_pool.ko" +result="" + +function run_test() +{ + rmmod "bench_page_pool.ko" || true + insmod $DRIVER > /dev/null 2>&1 + result=$(dmesg | tail -10) + echo "$result" + + echo + echo "Fast path results:" + echo ${result} | grep -o -E "no-softirq-page_pool01 Per elem: ([0-9]+) cycles$tsc$ ([0-9]+\.[0-9]+) ns" + + echo + echo "ptr_ring results:" + echo ${result} | grep -o -E "no-softirq-page_pool02 Per elem: ([0-9]+) cycles$tsc$ ([0-9]+\.[0-9]+) ns" + + echo + echo "slow path results:" + echo ${result} | grep -o -E "no-softirq-page_pool03 Per elem: ([0-9]+) cycles$tsc$ ([0-9]+\.[0-9]+) ns" +} + +run_test + +exit 0 diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.c b/tools/testing/selftests/net/bench/page_pool/time_bench.c new file mode 100644 index 000000000000..257b1515c64e --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.c @@ -0,0 +1,406 @@ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/time.h> + +#include <linux/perf_event.h> /* perf_event_create_kernel_counter() */ + +/* For concurrency testing */ +#include <linux/completion.h> +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> + +#include "time_bench.h" + +static int verbose = 1; + +/** TSC (Time-Stamp Counter) based ** + * See: linux/time_bench.h + * tsc_start_clock() and tsc_stop_clock() + */ + +/** Wall-clock based ** + */ + +/** PMU (Performance Monitor Unit) based ** + */ +#define PERF_FORMAT \ + (PERF_FORMAT_GROUP | PERF_FORMAT_ID | PERF_FORMAT_TOTAL_TIME_ENABLED | \ + PERF_FORMAT_TOTAL_TIME_RUNNING) + +struct raw_perf_event { + uint64_t config; /* event */ + uint64_t config1; /* umask */ + struct perf_event *save; + char *desc; +}; + +/* if HT is enable a maximum of 4 events (5 if one is instructions + * retired can be specified, if HT is disabled a maximum of 8 (9 if + * one is instructions retired) can be specified. + * + * From Table 19-1. Architectural Performance Events + * Architectures Software Developer’s Manual Volume 3: System Programming Guide + */ +struct raw_perf_event perf_events[] = { + { 0x3c, 0x00, NULL, "Unhalted CPU Cycles" }, + { 0xc0, 0x00, NULL, "Instruction Retired" } +}; + +#define NUM_EVTS (sizeof(perf_events) / sizeof(struct raw_perf_event)) + +/* WARNING: PMU config is currently broken! + */ +bool time_bench_PMU_config(bool enable) +{ + int i; + struct perf_event_attr perf_conf; + struct perf_event *perf_event; + int cpu; + + preempt_disable(); + cpu = smp_processor_id(); + pr_info("DEBUG: cpu:%d\n", cpu); + preempt_enable(); + + memset(&perf_conf, 0, sizeof(struct perf_event_attr)); + perf_conf.type = PERF_TYPE_RAW; + perf_conf.size = sizeof(struct perf_event_attr); + perf_conf.read_format = PERF_FORMAT; + perf_conf.pinned = 1; + perf_conf.exclude_user = 1; /* No userspace events */ + perf_conf.exclude_kernel = 0; /* Only kernel events */ + + for (i = 0; i < NUM_EVTS; i++) { + perf_conf.disabled = enable; + //perf_conf.disabled = (i == 0) ? 1 : 0; + perf_conf.config = perf_events[i].config; + perf_conf.config1 = perf_events[i].config1; + if (verbose) + pr_info("%s() enable PMU counter: %s\n", + __func__, perf_events[i].desc); + perf_event = perf_event_create_kernel_counter(&perf_conf, cpu, + NULL /* task */, + NULL /* overflow_handler*/, + NULL /* context */); + if (perf_event) { + perf_events[i].save = perf_event; + pr_info("%s():DEBUG perf_event success\n", __func__); + + perf_event_enable(perf_event); + } else { + pr_info("%s():DEBUG perf_event is NULL\n", __func__); + } + } + + return true; +} + +/** Generic functions ** + */ + +/* Calculate stats, store results in record */ +bool time_bench_calc_stats(struct time_bench_record *rec) +{ +#define NANOSEC_PER_SEC 1000000000 /* 10^9 */ + uint64_t ns_per_call_tmp_rem = 0; + uint32_t ns_per_call_remainder = 0; + uint64_t pmc_ipc_tmp_rem = 0; + uint32_t pmc_ipc_remainder = 0; + uint32_t pmc_ipc_div = 0; + uint32_t invoked_cnt_precision = 0; + uint32_t invoked_cnt = 0; /* 32-bit due to div_u64_rem() */ + + if (rec->flags & TIME_BENCH_LOOP) { + if (rec->invoked_cnt < 1000) { + pr_err("ERR: need more(>1000) loops(%llu) for timing\n", + rec->invoked_cnt); + return false; + } + if (rec->invoked_cnt > ((1ULL << 32) - 1)) { + /* div_u64_rem() can only support div with 32bit*/ + pr_err("ERR: Invoke cnt(%llu) too big overflow 32bit\n", + rec->invoked_cnt); + return false; + } + invoked_cnt = (uint32_t)rec->invoked_cnt; + } + + /* TSC (Time-Stamp Counter) records */ + if (rec->flags & TIME_BENCH_TSC) { + rec->tsc_interval = rec->tsc_stop - rec->tsc_start; + if (rec->tsc_interval == 0) { + pr_err("ABORT: timing took ZERO TSC time\n"); + return false; + } + /* Calculate stats */ + if (rec->flags & TIME_BENCH_LOOP) + rec->tsc_cycles = rec->tsc_interval / invoked_cnt; + else + rec->tsc_cycles = rec->tsc_interval; + } + + /* Wall-clock time calc */ + if (rec->flags & TIME_BENCH_WALLCLOCK) { + rec->time_start = rec->ts_start.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_start.tv_sec); + rec->time_stop = rec->ts_stop.tv_nsec + + (NANOSEC_PER_SEC * rec->ts_stop.tv_sec); + rec->time_interval = rec->time_stop - rec->time_start; + if (rec->time_interval == 0) { + pr_err("ABORT: timing took ZERO wallclock time\n"); + return false; + } + /* Calculate stats */ + /*** Division in kernel it tricky ***/ + /* Orig: time_sec = (time_interval / NANOSEC_PER_SEC); */ + /* remainder only correct because NANOSEC_PER_SEC is 10^9 */ + rec->time_sec = div_u64_rem(rec->time_interval, NANOSEC_PER_SEC, + &rec->time_sec_remainder); + //TODO: use existing struct timespec records instead of div? + + if (rec->flags & TIME_BENCH_LOOP) { + /*** Division in kernel it tricky ***/ + /* Orig: ns = ((double)time_interval / invoked_cnt); */ + /* First get quotient */ + rec->ns_per_call_quotient = + div_u64_rem(rec->time_interval, invoked_cnt, + &ns_per_call_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + ns_per_call_tmp_rem = ns_per_call_remainder; + invoked_cnt_precision = invoked_cnt / 1000; + if (invoked_cnt_precision > 0) { + rec->ns_per_call_decimal = + div_u64_rem(ns_per_call_tmp_rem, + invoked_cnt_precision, + &ns_per_call_remainder); + } + } + } + + /* Performance Monitor Unit (PMU) counters */ + if (rec->flags & TIME_BENCH_PMU) { + //FIXME: Overflow handling??? + rec->pmc_inst = rec->pmc_inst_stop - rec->pmc_inst_start; + rec->pmc_clk = rec->pmc_clk_stop - rec->pmc_clk_start; + + /* Calc Instruction Per Cycle (IPC) */ + /* First get quotient */ + rec->pmc_ipc_quotient = div_u64_rem(rec->pmc_inst, rec->pmc_clk, + &pmc_ipc_remainder); + /* Now get decimals .xxx precision (incorrect roundup)*/ + pmc_ipc_tmp_rem = pmc_ipc_remainder; + pmc_ipc_div = rec->pmc_clk / 1000; + if (pmc_ipc_div > 0) { + rec->pmc_ipc_decimal = div_u64_rem(pmc_ipc_tmp_rem, + pmc_ipc_div, + &pmc_ipc_remainder); + } + } + + return true; +} + +/* Generic function for invoking a loop function and calculating + * execution time stats. The function being called/timed is assumed + * to perform a tight loop, and update the timing record struct. + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *record, void *data)) +{ + struct time_bench_record rec; + + /* Setup record */ + memset(&rec, 0, sizeof(rec)); /* zero func might not update all */ + rec.version_abi = 1; + rec.loops = loops; + rec.step = step; + rec.flags = (TIME_BENCH_LOOP|TIME_BENCH_TSC|TIME_BENCH_WALLCLOCK); +// rec.flags = (TIME_BENCH_LOOP|TIME_BENCH_TSC| +// TIME_BENCH_WALLCLOCK|TIME_BENCH_PMU); + //TODO: Add/copy txt to rec + + /*** Loop function being timed ***/ + if (!func(&rec, data)) { + pr_err("ABORT: function being timed failed\n"); + return false; + } + + if (rec.invoked_cnt < loops) + pr_warn("WARNING: Invoke count(%llu) smaller than loops(%d)\n", + rec.invoked_cnt, loops); + + /* Calculate stats */ + time_bench_calc_stats(&rec); + + pr_info("Type:%s Per elem: %llu cycles(tsc) %llu.%03llu ns (step:%d)" + " - (measurement period time:%llu.%09u sec time_interval:%llu)" + " - (invoke count:%llu tsc_interval:%llu)\n", + txt, rec.tsc_cycles, + rec.ns_per_call_quotient, rec.ns_per_call_decimal, rec.step, + rec.time_sec, rec.time_sec_remainder, rec.time_interval, + rec.invoked_cnt, rec.tsc_interval); +/* pr_info("DEBUG check is %llu/%llu == %llu.%03llu ?\n", + rec.time_interval, rec.invoked_cnt, + rec.ns_per_call_quotient, rec.ns_per_call_decimal); +*/ + if (rec.flags & TIME_BENCH_PMU) { + pr_info("Type:%s PMU inst/clock" + "%llu/%llu = %llu.%03llu IPC (inst per cycle)\n", + txt, rec.pmc_inst, rec.pmc_clk, + rec.pmc_ipc_quotient, rec.pmc_ipc_decimal); + } + return true; +} + +/* Function getting invoked by kthread */ +static int invoke_test_on_cpu_func(void *private) +{ + struct time_bench_cpu *cpu = private; + struct time_bench_sync *sync = cpu->sync; + cpumask_t newmask = CPU_MASK_NONE; + void *data = cpu->data; + + /* Restrict CPU */ + cpumask_set_cpu(cpu->rec.cpu, &newmask); + set_cpus_allowed_ptr(current, &newmask); + + /* Synchronize start of concurrency test */ + atomic_inc(&sync->nr_tests_running); + wait_for_completion(&sync->start_event); + + /* Start benchmark function */ + if (!cpu->bench_func(&cpu->rec, data)) { + pr_err("ERROR: function being timed failed on CPU:%d(%d)\n", + cpu->rec.cpu, smp_processor_id()); + } else { + if (verbose) + pr_info("SUCCESS: ran on CPU:%d(%d)\n", cpu->rec.cpu, + smp_processor_id()); + } + cpu->did_bench_run = true; + + /* End test */ + atomic_dec(&sync->nr_tests_running); + /* Wait for kthread_stop() telling us to stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask) +{ + uint64_t average = 0; + int cpu; + int step = 0; + struct sum { + uint64_t tsc_cycles; + int records; + } sum = { 0 }; + + /* Get stats */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + struct time_bench_record *rec = &c->rec; + + /* Calculate stats */ + time_bench_calc_stats(rec); + + pr_info("Type:%s CPU(%d) %llu cycles(tsc) %llu.%03llu ns" + " (step:%d)" + " - (measurement period time:%llu.%09u sec time_interval:%llu)" + " - (invoke count:%llu tsc_interval:%llu)\n", + desc, cpu, rec->tsc_cycles, rec->ns_per_call_quotient, + rec->ns_per_call_decimal, rec->step, rec->time_sec, + rec->time_sec_remainder, rec->time_interval, + rec->invoked_cnt, rec->tsc_interval); + + /* Collect average */ + sum.records++; + sum.tsc_cycles += rec->tsc_cycles; + step = rec->step; + } + + if (sum.records) /* avoid div-by-zero */ + average = sum.tsc_cycles / sum.records; + pr_info("Sum Type:%s Average: %llu cycles(tsc) CPUs:%d step:%d\n", desc, + average, sum.records, step); +} + +void time_bench_run_concurrent( + uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)) +{ + int cpu, running = 0; + + if (verbose) // DEBUG + pr_warn("%s() Started on CPU:%d\n", __func__, + smp_processor_id()); + + /* Reset sync conditions */ + atomic_set(&sync->nr_tests_running, 0); + init_completion(&sync->start_event); + + /* Spawn off jobs on all CPUs */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + + running++; + c->sync = sync; /* Send sync variable along */ + c->data = data; /* Send opaque along */ + + /* Init benchmark record */ + memset(&c->rec, 0, sizeof(struct time_bench_record)); + c->rec.version_abi = 1; + c->rec.loops = loops; + c->rec.step = step; + c->rec.flags = (TIME_BENCH_LOOP|TIME_BENCH_TSC| + TIME_BENCH_WALLCLOCK); + c->rec.cpu = cpu; + c->bench_func = func; + c->task = kthread_run(invoke_test_on_cpu_func, c, + "time_bench%d", cpu); + if (IS_ERR(c->task)) { + pr_err("%s(): Failed to start test func\n", __func__); + return; /* Argh, what about cleanup?! */ + } + } + + /* Wait until all processes are running */ + while (atomic_read(&sync->nr_tests_running) < running) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + /* Kick off all CPU concurrently on completion event */ + complete_all(&sync->start_event); + + /* Wait for CPUs to finish */ + while (atomic_read(&sync->nr_tests_running)) { + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(10); + } + + /* Stop the kthreads */ + for_each_cpu(cpu, mask) { + struct time_bench_cpu *c = &cpu_tasks[cpu]; + kthread_stop(c->task); + } + + if (verbose) // DEBUG - happens often, finish on another CPU + pr_warn("%s() Finished on CPU:%d\n", __func__, + smp_processor_id()); +} diff --git a/tools/testing/selftests/net/bench/page_pool/time_bench.h b/tools/testing/selftests/net/bench/page_pool/time_bench.h new file mode 100644 index 000000000000..7331b5789490 --- /dev/null +++ b/tools/testing/selftests/net/bench/page_pool/time_bench.h @@ -0,0 +1,259 @@ +/* + * Benchmarking code execution time inside the kernel + * + * Copyright (C) 2014, Red Hat, Inc., Jesper Dangaard Brouer + * for licensing details see kernel-base/COPYING + */ +#ifndef _LINUX_TIME_BENCH_H +#define _LINUX_TIME_BENCH_H + +/* Main structure used for recording a benchmark run */ +struct time_bench_record { + uint32_t version_abi; + uint32_t loops; /* Requested loop invocations */ + uint32_t step; /* option for e.g. bulk invocations */ + + uint32_t flags; /* Measurements types enabled */ +#define TIME_BENCH_LOOP (1<<0) +#define TIME_BENCH_TSC (1<<1) +#define TIME_BENCH_WALLCLOCK (1<<2) +#define TIME_BENCH_PMU (1<<3) + + uint32_t cpu; /* Used when embedded in time_bench_cpu */ + + /* Records */ + uint64_t invoked_cnt; /* Returned actual invocations */ + uint64_t tsc_start; + uint64_t tsc_stop; + struct timespec64 ts_start; + struct timespec64 ts_stop; + /** PMU counters for instruction and cycles + * instructions counter including pipelined instructions */ + uint64_t pmc_inst_start; + uint64_t pmc_inst_stop; + /* CPU unhalted clock counter */ + uint64_t pmc_clk_start; + uint64_t pmc_clk_stop; + + /* Result records */ + uint64_t tsc_interval; + uint64_t time_start, time_stop, time_interval; /* in nanosec */ + uint64_t pmc_inst, pmc_clk; + + /* Derived result records */ + uint64_t tsc_cycles; // +decimal? + uint64_t ns_per_call_quotient, ns_per_call_decimal; + uint64_t time_sec; + uint32_t time_sec_remainder; + uint64_t pmc_ipc_quotient, pmc_ipc_decimal; /* inst per cycle */ +}; + +/* For synchronizing parallel CPUs to run concurrently */ +struct time_bench_sync { + atomic_t nr_tests_running; + struct completion start_event; +}; + +/* Keep track of CPUs executing our bench function. + * + * Embed a time_bench_record for storing info per cpu + */ +struct time_bench_cpu { + struct time_bench_record rec; + struct time_bench_sync *sync; /* back ptr */ + struct task_struct *task; + /* "data" opaque could have been placed in time_bench_sync, + * but to avoid any false sharing, place it per CPU + */ + void *data; + /* Support masking outsome CPUs, mark if it ran */ + bool did_bench_run; + /* int cpu; // note CPU stored in time_bench_record */ + int (*bench_func)(struct time_bench_record *record, void *data); +}; + +/* + * Below TSC assembler code is not compatible with other archs, and + * can also fail on guests if cpu-flags are not correct. + * + * The way TSC reading is used, many iterations, does not require as + * high accuracy as described below (in Intel Doc #324264). + * + * Considering changing to use get_cycles() (#include <asm/timex.h>). + */ + +/** TSC (Time-Stamp Counter) based ** + * Recommend reading, to understand details of reading TSC accurately: + * Intel Doc #324264, "How to Benchmark Code Execution Times on Intel" + * + * Consider getting exclusive ownership of CPU by using: + * unsigned long flags; + * preempt_disable(); + * raw_local_irq_save(flags); + * _your_code_ + * raw_local_irq_restore(flags); + * preempt_enable(); + * + * Clobbered registers: "%rax", "%rbx", "%rcx", "%rdx" + * RDTSC only change "%rax" and "%rdx" but + * CPUID clears the high 32-bits of all (rax/rbx/rcx/rdx) + */ +static __always_inline uint64_t tsc_start_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned hi, lo; + asm volatile("CPUID\n\t" + "RDTSC\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + //FIXME: on 32bit use clobbered %eax + %edx + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +static __always_inline uint64_t tsc_stop_clock(void) +{ + /* See: Intel Doc #324264 */ + unsigned hi, lo; + asm volatile("RDTSCP\n\t" + "mov %%edx, %0\n\t" + "mov %%eax, %1\n\t" + "CPUID\n\t" + : "=r"(hi), "=r"(lo)::"%rax", "%rbx", "%rcx", "%rdx"); + return ((uint64_t)lo) | (((uint64_t)hi) << 32); +} + +/* Notes for RDTSC and RDTSCP + * + * Hannes found out that __builtin_ia32_rdtsc and + * __builtin_ia32_rdtscp are undocumented available in gcc, so there + * is no need to write inline assembler functions for them any more. + * + * unsigned long long __builtin_ia32_rdtscp(unsigned int *foo); + * (where foo is set to: numa_node << 12 | cpu) + * and + * unsigned long long __builtin_ia32_rdtsc(void); + * + * Above we combine the calls with CPUID, thus I don't see how this is + * directly appreciable. + */ + +/* +inline uint64_t rdtsc(void) +{ + uint32_t low, high; + asm volatile("rdtsc" : "=a" (low), "=d" (high)); + return low | (((uint64_t )high ) << 32); +} +*/ + +/** Wall-clock based ** + * + * use: getnstimeofday() + * getnstimeofday(&rec->ts_start); + * getnstimeofday(&rec->ts_stop); + * + * API changed see: Documentation/core-api/timekeeping.rst + * https://www.kernel.org/doc/html/latest/core-api/timekeeping.html#c.getnstim… + * + * We should instead use: ktime_get_real_ts64() is a direct + * replacement, but consider using monotonic time (ktime_get_ts64()) + * and/or a ktime_t based interface (ktime_get()/ktime_get_real()). + */ + +/** PMU (Performance Monitor Unit) based ** + * + * Needed for calculating: Instructions Per Cycle (IPC) + * - The IPC number tell how efficient the CPU pipelining were + */ +//lookup: perf_event_create_kernel_counter() + +bool time_bench_PMU_config(bool enable); + +/* Raw reading via rdpmc() using fixed counters + * + * From: https://github.com/andikleen/simple-pmu + */ +enum { + FIXED_SELECT = (1U << 30), /* == 0x40000000 */ + FIXED_INST_RETIRED_ANY = 0, + FIXED_CPU_CLK_UNHALTED_CORE = 1, + FIXED_CPU_CLK_UNHALTED_REF = 2, +}; + +static __always_inline unsigned long long p_rdpmc(unsigned in) +{ + unsigned d, a; + + asm volatile("rdpmc" : "=d"(d), "=a"(a) : "c"(in) : "memory"); + return ((unsigned long long)d << 32) | a; +} + +/* These PMU counter needs to be enabled, but I don't have the + * configure code implemented. My current hack is running: + * sudo perf stat -e cycles:k -e instructions:k insmod lib/ring_queue_test.ko + */ +/* Reading all pipelined instruction */ +static __always_inline unsigned long long pmc_inst(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_INST_RETIRED_ANY); +} + +/* Reading CPU clock cycles */ +static __always_inline unsigned long long pmc_clk(void) +{ + return p_rdpmc(FIXED_SELECT | FIXED_CPU_CLK_UNHALTED_CORE); +} + +/* Raw reading via MSR rdmsr() is likely wrong + * FIXME: How can I know which raw MSR registers are conf for what? + */ +#define MSR_IA32_PCM0 0x400000C1 /* PERFCTR0 */ +#define MSR_IA32_PCM1 0x400000C2 /* PERFCTR1 */ +#define MSR_IA32_PCM2 0x400000C3 +static inline uint64_t msr_inst(unsigned long long *msr_result) +{ + return rdmsrl_safe(MSR_IA32_PCM0, msr_result); +} + +/** Generic functions ** + */ +bool time_bench_loop(uint32_t loops, int step, char *txt, void *data, + int (*func)(struct time_bench_record *rec, void *data)); +bool time_bench_calc_stats(struct time_bench_record *rec); + +void time_bench_run_concurrent( + uint32_t loops, int step, void *data, + const struct cpumask *mask, /* Support masking outsome CPUs*/ + struct time_bench_sync *sync, struct time_bench_cpu *cpu_tasks, + int (*func)(struct time_bench_record *record, void *data)); +void time_bench_print_stats_cpumask(const char *desc, + struct time_bench_cpu *cpu_tasks, + const struct cpumask *mask); + +//FIXME: use rec->flags to select measurement, should be MACRO +static __always_inline void time_bench_start(struct time_bench_record *rec) +{ + //getnstimeofday(&rec->ts_start); + ktime_get_real_ts64(&rec->ts_start); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_start = pmc_inst(); + rec->pmc_clk_start = pmc_clk(); + } + rec->tsc_start = tsc_start_clock(); +} + +static __always_inline void time_bench_stop(struct time_bench_record *rec, + uint64_t invoked_cnt) +{ + rec->tsc_stop = tsc_stop_clock(); + if (rec->flags & TIME_BENCH_PMU) { + rec->pmc_inst_stop = pmc_inst(); + rec->pmc_clk_stop = pmc_clk(); + } + //getnstimeofday(&rec->ts_stop); + ktime_get_real_ts64(&rec->ts_stop); + rec->invoked_cnt = invoked_cnt; +} + +#endif /* _LINUX_TIME_BENCH_H */ base-commit: ea15e046263b19e91ffd827645ae5dfa44ebd044 -- 2.49.0.1151.ga128411c76-goog

57 minutes

3
6
0 0

[PATCH v7 0/8] ublk: decouple server threads from ublk_queues/hctxs

by Uday Shankar

This patch set aims to allow ublk server threads to better balance load amongst themselves by decoupling server threads from ublk_queues/hctxs, so that multiple threads can service I/Os that are issued from a single CPU. This can improve performance for workloads in which ublk server CPU is a bottleneck, and for which load is issued from CPUs which are not balanced across ublk_queues/hctxs. Performance ----------- First create two ublk devices with: ublkb0: ./kublk add -t null -q 2 --nthreads 2 ublkb1: ./kublk add -t null -q 2 --nthreads 2 --per_io_tasks Then run load with: taskset -c 1 fio/t/io_uring -r5 -p0 /dev/ublkb0: 1.90M IOPS taskset -c 1 fio/t/io_uring -r5 -p0 /dev/ublkb1: 2.18M IOPS Since ublkb1 has per-io-tasks, the second command is able to make use of both ublk server worker threads and therefore has increased max throughput. Caveats: - This testing was done on a system with 2 numa nodes, but the penalty of having I/O cross a numa (or LLC) boundary in the per_io_tasks case is quite high. So these numbers were obtained after moving all ublk server threads and the application threads to CPUs on the same numa node/LLC. - One might expect the scaling to be linear - because ublkb1 can make use of twice as many ublk server threads, it should be able to drive twice the throughput. However this is not true (the improvement is ~15%), and needs further investigation. Signed-off-by: Uday Shankar <ushankar(a)purestorage.com> --- Changes in v7: - Fix queue_rqs batch dispatch for per-io daemons - Kick round-robin tag allocation changes to a followup - Add explicit feature flag for per-task daemons (Ming Lei, Caleb Sander Mateos) - Move some variable assignments to avoid redundant computation (Caleb Sander Mateos) - Switch from storing pointers in ublk_io to computing based on address with container_of in a couple places (Ming Lei) - Link to v6: https://lore.kernel.org/r/20250507-ublk_task_per_io-v6-0-a2a298783c01@pures… Changes in v6: - Add a feature flag for this feature, called UBLK_F_RR_TAGS (Ming Lei) - Add test for this feature (Ming Lei) - Add documentation for this feature (Ming Lei) - Link to v5: https://lore.kernel.org/r/20250416-ublk_task_per_io-v5-0-9261ad7bff20@pures… Changes in v5: - Set io->task before ublk_mark_io_ready (Caleb Sander Mateos) - Set io->task atomically, read it atomically when needed - Return 0 on success from command-specific helpers in __ublk_ch_uring_cmd (Caleb Sander Mateos) - Rename ublk_handle_need_get_data to ublk_get_data (Caleb Sander Mateos) - Link to v4: https://lore.kernel.org/r/20250415-ublk_task_per_io-v4-0-54210b91a46f@pures… Changes in v4: - Drop "ublk: properly serialize all FETCH_REQs" since Ming is taking it in another set - Prevent data races by marking data structures which should be read-only in the I/O path as const (Ming Lei) - Link to v3: https://lore.kernel.org/r/20250410-ublk_task_per_io-v3-0-b811e8f4554a@pures… Changes in v3: - Check for UBLK_IO_FLAG_ACTIVE on I/O again after taking lock to ensure that two concurrent FETCH_REQs on the same I/O can't succeed (Caleb Sander Mateos) - Link to v2: https://lore.kernel.org/r/20250408-ublk_task_per_io-v2-0-b97877e6fd50@pures… Changes in v2: - Remove changes split into other patches - To ease error handling/synchronization, associate each I/O (instead of each queue) to the last task that issues a FETCH_REQ against it. Only that task is allowed to operate on the I/O. - Link to v1: https://lore.kernel.org/r/20241002224437.3088981-1-ushankar@purestorage.com --- Uday Shankar (8): ublk: have a per-io daemon instead of a per-queue daemon selftests: ublk: kublk: plumb q_id in io_uring user_data selftests: ublk: kublk: tie sqe allocation to io instead of queue selftests: ublk: kublk: lift queue initialization out of thread selftests: ublk: kublk: move per-thread data out of ublk_queue selftests: ublk: kublk: decouple ublk_queues from ublk server threads selftests: ublk: add test for per io daemons Documentation: ublk: document UBLK_F_PER_IO_DAEMON Documentation/block/ublk.rst | 35 ++- drivers/block/ublk_drv.c | 108 +++---- include/uapi/linux/ublk_cmd.h | 9 + tools/testing/selftests/ublk/Makefile | 1 + tools/testing/selftests/ublk/fault_inject.c | 4 +- tools/testing/selftests/ublk/file_backed.c | 20 +- tools/testing/selftests/ublk/kublk.c | 345 ++++++++++++++------- tools/testing/selftests/ublk/kublk.h | 73 +++-- tools/testing/selftests/ublk/null.c | 22 +- tools/testing/selftests/ublk/stripe.c | 17 +- tools/testing/selftests/ublk/test_generic_12.sh | 55 ++++ .../selftests/ublk/trace/count_ios_per_tid.bt | 11 + 12 files changed, 470 insertions(+), 230 deletions(-) --- base-commit: 533c87e2ed742454957f14d7bef9f48d5a72e72d change-id: 20250408-ublk_task_per_io-c693cf608d7a Best regards, -- Uday Shankar <ushankar(a)purestorage.com>

2 hours, 18 minutes

2
10
0 0

[PATCH v5 00/29] iommufd: Add vIOMMU infrastructure (Part-4 HW QUEUE)

by Nicolin Chen

The vIOMMU object is designed to represent a slice of an IOMMU HW for its virtualization features shared with or passed to user space (a VM mostly) in a way of HW acceleration. This extended the HWPT-based design for more advanced virtualization feature. HW QUEUE introduced by this series as a part of the vIOMMU infrastructure represents a HW accelerated queue/buffer for VM to use exclusively, e.g. - NVIDIA's Virtual Command Queue - AMD vIOMMU's Command Buffer, Event Log Buffer, and PPR Log Buffer each of which allows its IOMMU HW to directly access a queue memory owned by a guest VM and allows a guest OS to control the HW queue direclty, to avoid VM Exit overheads to improve the performance. Introduce IOMMUFD_OBJ_HW_QUEUE and its pairing IOMMUFD_CMD_HW_QUEUE_ALLOC allowing VMM to forward the IOMMU-specific queue info, such as queue base address, size, and etc. Meanwhile, a guest-owned queue needs the guest kernel to control the queue by reading/writing its consumer and producer indexes, via MMIO acceses to the hardware MMIO registers. Introduce an mmap infrastructure for iommufd to support passing through a piece of MMIO region from the host physical address space to the guest physical address space. The mmap info (offset/ length) used by an mmap syscall must be pre-allocated and returned to the user space via an output driver-data during an IOMMUFD_CMD_HW_QUEUE_ALLOC call. Thus, it requires a driver-specific user data support in the vIOMMU allocation flow. As a real-world use case, this series implements a HW QUEUE support in the tegra241-cmdqv driver for VCMDQs on NVIDIA Grace CPU. In another word, it is also the Tegra CMDQV series Part-2 (user-space support), reworked from Previous RFCv1: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This enables the HW accelerated feature for NVIDIA Grace CPU. Compared to the standard SMMUv3 operating in the nested translation mode trapping CMDQ for TLBI and ATC_INV commands, this gives a huge performance improvement: 70% to 90% reductions of invalidation time were measured by various DMA unmap tests running in a guest OS. // Unmap latencies from "dma_map_benchmark -g @granule -t @threads", // by toggling "/sys/kernel/debug/iommu/tegra241_cmdqv/bypass_vcmdq" @granule | @threads | bypass_vcmdq=1 | bypass_vcmdq=0 4KB 1 35.7 us 5.3 us 16KB 1 41.8 us 6.8 us 64KB 1 68.9 us 9.9 us 128KB 1 109.0 us 12.6 us 256KB 1 187.1 us 18.0 us 4KB 2 96.9 us 6.8 us 16KB 2 97.8 us 7.5 us 64KB 2 151.5 us 10.7 us 128KB 2 257.8 us 12.7 us 256KB 2 443.0 us 17.9 us This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_hw_queue-v5 Paring QEMU branch for testing: https://github.com/nicolinc/qemu/commits/wip/for_iommufd_hw_queue-v5 Changelog v5 * Rebase on v6.15-rc6 * Add Reviewed-by from Jason and Kevin * Correct typos in kdoc and update commit logs * [iommufd] Add a cosmetic fix * [iommufd] Drop unused num_pfns * [iommufd] Drop unnecessary check * [iommufd] Reorder patch sequence * [iommufd] Use io_remap_pfn_range() * [iommufd] Use success oriented flow * [iommufd] Fix max_npages calculation * [iommufd] Add more selftest coverage * [iommufd] Drop redundant static_assert * [iommufd] Fix mmap pfn range validation * [iommufd] Reject unmap on pinned iovas * [iommufd] Drop redundant vm_flags_set() * [iommufd] Drop iommufd_struct_destroy() * [iommufd] Drop redundant queue iova test * [iommufd] Use "mmio_addr" and "mmio_pfn" * [iommufd] Rename to "nesting_parent_iova" * [iommufd] Make iopt_pin_pages call option * [iommufd] Add ictx comparison in depend() * [iommufd] Add iommufd_object_alloc_ucmd() * [iommufd] Move kcalloc() after validations * [iommufd] Replace ictx setting with WARN_ON * [iommufd] Make hw_info's type bidirectional * [smmu] Add supported_vsmmu_type in impl_ops * [smmu] Drop impl report in smmu vendor struct * [tegra] Add IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV * [tegra] Replace "number of VINTFs" with a note * [tegra] Drop the redundant lvcmdq pointer setting * [tegra] Flag IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA * [tegra] Use "vintf_alloc_vsid" for vdevice_alloc op v4 https://lore.kernel.org/all/cover.1746757630.git.nicolinc@nvidia.com/ * Rebase on v6.15-rc5 * Add Reviewed-by from Vasant * Rename "vQUEUE" to "HW QUEUE" * Use "offset" and "length" for all mmap-related variables * [iommufd] Use u64 for guest PA * [iommufd] Fix typo in uAPI doc * [iommufd] Rename immap_id to offset * [iommufd] Drop the partial-size mmap support * [iommufd] Do not replace WARN_ON with WARN_ON_ONCE * [iommufd] Use "u64 base_addr" for queue base address * [iommufd] Use u64 base_pfn/num_pfns for immap structure * [iommufd] Correct the size passed in to mtree_alloc_range() * [iommufd] Add IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA to viommu_ops v3 https://lore.kernel.org/all/cover.1746139811.git.nicolinc@nvidia.com/ * Add Reviewed-by from Baolu, Pranjal, and Alok * Revise kdocs, uAPI docs, and commit logs * Rename "vCMDQ" back to "vQUEUE" for AMD cases * [tegra] Add tegra241_vcmdq_hw_flush_timeout() * [tegra] Rename vsmmu_alloc to alloc_vintf_user * [tegra] Use writel for SID replacement registers * [tegra] Move mmap removal call to vsmmu_destroy op * [tegra] Fix revert in tegra241_vintf_alloc_lvcmdq_user() * [iommufd] Replace "& ~PAGE_MASK" with PAGE_ALIGNED() * [iommufd] Add an object-type "owner" to immap structure * [iommufd] Drop the ictx input in the new for-driver APIs * [iommufd] Add iommufd_vma_ops to keep track of mmap lifecycle * [iommufd] Add viommu-based iommufd_viommu_alloc/destroy_mmap helpers * [iommufd] Rename iommufd_ctx_alloc/free_mmap to _iommufd_alloc/destroy_mmap v2 https://lore.kernel.org/all/cover.1745646960.git.nicolinc@nvidia.com/ * Add Reviewed-by from Jason * [smmu] Fix vsmmu initial value * [smmu] Support impl for hw_info * [tegra] Rename "slot" to "vsid" * [tegra] Update kdocs and commit logs * [tegra] Map/unmap LVCMDQ dynamically * [tegra] Refcount the previous LVCMDQ * [tegra] Return -EEXIST if LVCMDQ exists * [tegra] Simplify VINTF cleanup routine * [tegra] Use vmid and s2_domain in vsmmu * [tegra] Rename "mmap_pgoff" to "immap_id" * [tegra] Add more addr and length validation * [iommufd] Add more narrative to mmap's kdoc * [iommufd] Add iommufd_struct_depend/undepend() * [iommufd] Rename vcmdq_free op to vcmdq_destroy * [iommufd] Fix bug in iommu_copy_struct_to_user() * [iommufd] Drop is_io from iommufd_ctx_alloc_mmap() * [iommufd] Test the queue memory for its contiguity * [iommufd] Return -ENXIO if address or length fails * [iommufd] Do not change @min_last in mock_viommu_alloc() * [iommufd] Generalize TEGRA241_VCMDQ data in core structure * [iommufd] Add selftest coverage for IOMMUFD_CMD_VCMDQ_ALLOC * [iommufd] Add iopt_pin_pages() to prevent queue memory from unmapping v1 https://lore.kernel.org/all/cover.1744353300.git.nicolinc@nvidia.com/ Thanks Nicolin Nicolin Chen (29): iommufd: Apply obvious cosmetic fixes iommufd: Introduce iommufd_object_alloc_ucmd helper iommu: Apply the new iommufd_object_alloc_ucmd helper iommu: Add iommu_copy_struct_to_user helper iommu: Pass in a driver-level user data structure to viommu_alloc op iommufd/viommu: Allow driver-specific user data for a vIOMMU object iommufd/selftest: Support user_data in mock_viommu_alloc iommufd/selftest: Add coverage for viommu data iommufd: Do not unmap an owned iopt_area iommufd: Abstract iopt_pin_pages and iopt_unpin_pages helpers iommufd/driver: Let iommufd_viommu_alloc helper save ictx to viommu->ictx iommufd/viommu: Add driver-allocated vDEVICE support iommufd/viommu: Introduce IOMMUFD_OBJ_HW_QUEUE and its related struct iommufd/viommu: Add IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl iommufd/driver: Add iommufd_hw_queue_depend/undepend() helpers iommufd/selftest: Add coverage for IOMMUFD_CMD_HW_QUEUE_ALLOC iommufd: Add mmap interface iommufd/selftest: Add coverage for the new mmap interface Documentation: userspace-api: iommufd: Update HW QUEUE iommu: Allow an input type in hw_info op iommufd: Allow an input data_type via iommu_hw_info iommufd/selftest: Update hw_info coverage for an input data_type iommu/arm-smmu-v3-iommufd: Add vsmmu_alloc impl op iommu/arm-smmu-v3-iommufd: Add hw_info to impl_ops iommu/tegra241-cmdqv: Use request_threaded_irq iommu/tegra241-cmdqv: Simplify deinit flow in tegra241_cmdqv_remove_vintf() iommu/tegra241-cmdqv: Do not statically map LVCMDQs iommu/tegra241-cmdqv: Add user-space use support iommu/tegra241-cmdqv: Add IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV support drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 28 +- drivers/iommu/iommufd/io_pagetable.h | 15 +- drivers/iommu/iommufd/iommufd_private.h | 41 +- drivers/iommu/iommufd/iommufd_test.h | 20 + include/linux/iommu.h | 53 +- include/linux/iommufd.h | 221 +++++++- include/uapi/linux/iommufd.h | 150 +++++- tools/testing/selftests/iommu/iommufd_utils.h | 91 +++- .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 33 +- .../iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 496 +++++++++++++++++- drivers/iommu/intel/iommu.c | 4 + drivers/iommu/iommufd/device.c | 137 +---- drivers/iommu/iommufd/driver.c | 97 ++++ drivers/iommu/iommufd/eventq.c | 14 +- drivers/iommu/iommufd/hw_pagetable.c | 6 +- drivers/iommu/iommufd/io_pagetable.c | 106 +++- drivers/iommu/iommufd/iova_bitmap.c | 1 - drivers/iommu/iommufd/main.c | 80 ++- drivers/iommu/iommufd/pages.c | 19 +- drivers/iommu/iommufd/selftest.c | 158 +++++- drivers/iommu/iommufd/viommu.c | 146 +++++- tools/testing/selftests/iommu/iommufd.c | 146 +++++- .../selftests/iommu/iommufd_fail_nth.c | 15 +- Documentation/userspace-api/iommufd.rst | 12 + 24 files changed, 1794 insertions(+), 295 deletions(-) -- 2.43.0

2 hours, 36 minutes

3
52
0 0

[PATCH v3] rust: kunit: use crate-level mapping for `c_void`

by Jesung Yang

Remove `use core::ffi::c_void`, which shadows `kernel::ffi::c_void` brought in via `use crate::prelude::*`, to maintain consistency and centralize the abstraction. Since `kernel::ffi::c_void` is a straightforward re-export of `core::ffi::c_void`, both are functionally equivalent. However, using `kernel::ffi::c_void` improves consistency across the kernel's Rust code and provides a unified reference point in case the definition ever needs to change, even if such a change is unlikely. Reviewed-by: Benno Lossin <lossin(a)kernel.org> Signed-off-by: Jesung Yang <y.j3ms.n(a)gmail.com> Link: https://rust-for-linux.zulipchat.com/#narrow/channel/288089/topic/x/near/52… --- Changes in v3: - Rebase on a3b2347343e0 - Remove the explicit import of `kernel::ffi::c_void` - Reword the commit message accordingly - Link to v2: https://lore.kernel.org/rust-for-linux/20250528155147.2793921-1-y.j3ms.n@gm… Changes in v2: - Add "Link" tag to the related discussion on Zulip - Reword the commit message to clarify `kernel::ffi::c_void` is a re-export - Link to v1: https://lore.kernel.org/rust-for-linux/20250526162429.1114862-1-y.j3ms.n@gm… --- rust/kernel/kunit.rs | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 4b8cdcb21e77..603330f247c7 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -7,7 +7,7 @@ //! Reference: <https://docs.kernel.org/dev-tools/kunit/index.html> use crate::prelude::*; -use core::{ffi::c_void, fmt}; +use core::fmt; /// Prints a KUnit error-level message. /// base-commit: a3b2347343e077e81d3c169f32c9b2cb1364f4cc -- 2.39.5

2 hours, 53 minutes

1
0
0 0

[PATCH v2] rust: kunit: use crate-level mapping for `c_void`

by Jesung Yang

Use `kernel::ffi::c_void` instead of `core::ffi::c_void` for consistency and to centralize abstraction. Since `kernel::ffi::c_void` is a straightforward re-export of `core::ffi::c_void`, both are functionally equivalent. However, using `kernel::ffi::c_void` improves consistency across the kernel's Rust code and provides a unified reference point in case the definition ever needs to change, even if such a change is unlikely. Signed-off-by: Jesung Yang <y.j3ms.n(a)gmail.com> Link: https://rust-for-linux.zulipchat.com/#narrow/channel/288089/topic/x/near/52… --- So in sum, I believe it's reasonable to keep the diff unchanged... but I'm happy to adjust if you'd prefer a different approach. --- Changes in v2: - Add "Link" tag to the related discussion on Zulip - Reword the commit message to clarify `kernel::ffi::c_void` is a re-export - Link to v1: https://lore.kernel.org/rust-for-linux/20250526162429.1114862-1-y.j3ms.n@gm… --- rust/kernel/kunit.rs | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 81833a687b75..bd6fc712dd79 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -6,7 +6,8 @@ //! //! Reference: <https://docs.kernel.org/dev-tools/kunit/index.html> -use core::{ffi::c_void, fmt}; +use core::fmt; +use kernel::ffi::c_void; /// Prints a KUnit error-level message. /// base-commit: f4daa80d6be7d3c55ca72a8e560afc4e21f886aa -- 2.39.5

4 hours, 1 minute

3
2
0 0

[PATCH] selftests/seccomp: report errno and add hints on failure

by Sameeksha Sankpal

Signed-off-by: Sameeksha Sankpal <sameekshasankpal(a)gmail.com> --- tools/testing/selftests/seccomp/seccomp_bpf.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 14ba51b52095..d6a85d7b26da 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -4508,7 +4508,11 @@ static char get_proc_stat(struct __test_metadata *_metadata, pid_t pid) snprintf(proc_path, sizeof(proc_path), "/proc/%d/stat", pid); ASSERT_EQ(get_nth(_metadata, proc_path, 3, &line), 1); - + int rc = get_nth(_metadata, proc_path, 3, &line); + if (rc != 1) { + printf("[ERROR] user_notification_fifo: failed to read stat for PID %d (rc=%d)\n", pid, rc); + } + ASSERT_EQ(rc, 1); status = *line; free(line); @@ -4518,6 +4522,7 @@ static char get_proc_stat(struct __test_metadata *_metadata, pid_t pid) TEST(user_notification_fifo) { struct seccomp_notif_resp resp = {}; + ksft_print_msg("[INFO] Starting FIFO notification test\n"); struct seccomp_notif req = {}; int i, status, listener; pid_t pid, pids[3]; @@ -4535,6 +4540,7 @@ TEST(user_notification_fifo) listener = user_notif_syscall(__NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER); ASSERT_GE(listener, 0); + ksft_print_msg("[INFO] user_notification_fifo: listener PID is %d\n", listener); pid = fork(); ASSERT_GE(pid, 0); -- 2.43.0

4 hours, 7 minutes

2
3
0 0

[PATCH] rust: replace length checks with match

by Tamir Duberstein

Use a match expression with slice patterns instead of length checks and indexing. The result is more idiomatic, which is a better example for future Rust code authors. Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- scripts/rustdoc_test_gen.rs | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs index 1ca253594d38..a3dc251221e0 100644 --- a/scripts/rustdoc_test_gen.rs +++ b/scripts/rustdoc_test_gen.rs @@ -85,24 +85,25 @@ fn find_candidates( } } - assert!( - valid_paths.len() > 0, - "No path candidates found for `{file}`. This is likely a bug in the build system, or some \ - files went away while compiling." - ); - - if valid_paths.len() > 1 { - eprintln!("Several path candidates found:"); - for path in valid_paths { - eprintln!(" {path:?}"); + match valid_paths.as_slice() { + [] => panic!( + "No path candidates found for `{file}`. This is likely a bug in the build system, or \ + some files went away while compiling." + ), + [valid_path] => { + valid_path.to_str().unwrap() + } + valid_paths => { + eprintln!("Several path candidates found:"); + for path in valid_paths { + eprintln!(" {path:?}"); + } + panic!( + "Several path candidates found for `{file}`, please resolve the ambiguity by \ + renaming a file or folder." + ); } - panic!( - "Several path candidates found for `{file}`, please resolve the ambiguity by renaming \ - a file or folder." - ); } - - valid_paths[0].to_str().unwrap() } fn main() { --- base-commit: bfc3cd87559bc593bb32bb1482f9cae3308b6398 change-id: 20250527-idiomatic-match-slice-26a79d100e4d Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

4 hours, 23 minutes

3
3
0 0

[PATCH bpf-next v1 1/2] bpf: Restrict usage scope of bpf_get_cgroup_classid

by Jiayuan Chen

A previous commit expanded the usage scope of bpf_get_cgroup_classid() to all contexts (see Fixes tag), but this was inappropriate. First, syzkaller reported a bug [1]. Second, it uses skb as an argument, but its implementation varies across different bpf prog types. For example, in sock_filter and sock_addr, it retrieves the classid from the current context (bpf_get_cgroup_classid_curr_proto) instead of from skb. In tc egress and lwt, it fetches the classid from skb->sk, but in tc ingress, it returns 0. In summary, the definition of bpf_get_cgroup_classid() is ambiguous and its usage scenarios are limited. It should not be treated as a general-purpose helper. This patch reverts part of the previous commit. [1] https://syzkaller.appspot.com/bug?extid=9767c7ed68b95cfa69e6 Fixes: ee971630f20f ("bpf: Allow some trace helpers for all prog types") Reported-by: syzbot+9767c7ed68b95cfa69e6(a)syzkaller.appspotmail.com Signed-off-by: Jiayuan Chen <jiayuan.chen(a)linux.dev> --- include/linux/bpf-cgroup.h | 8 ++++++++ kernel/bpf/cgroup.c | 25 +++++++++++++++++++++++++ kernel/bpf/helpers.c | 4 ---- 3 files changed, 33 insertions(+), 4 deletions(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 4847dcade917..9de7adb68294 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -427,6 +427,8 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); +const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); #else static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } @@ -463,6 +465,12 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } +static inline const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return NULL; +} + static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 62a1d8deb3dc..a99b72e6f1c9 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1653,6 +1653,10 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; @@ -2200,6 +2204,10 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; @@ -2343,6 +2351,10 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) if (func_proto) return func_proto; + func_proto = cgroup_current_func_proto(func_id, prog); + if (func_proto) + return func_proto; + switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_get_netns_cookie: @@ -2589,3 +2601,16 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } } + +const struct bpf_func_proto * +cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_get_cgroup_classid: + return &bpf_get_cgroup_classid_curr_proto; +#endif + default: + return NULL; + } +} diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b71e428ad936..9d0d54f4f0de 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2024,10 +2024,6 @@ bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_ancestor_cgroup_id_proto; case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; -#endif -#ifdef CONFIG_CGROUP_NET_CLASSID - case BPF_FUNC_get_cgroup_classid: - return &bpf_get_cgroup_classid_curr_proto; #endif case BPF_FUNC_task_storage_get: if (bpf_prog_check_recur(prog)) -- 2.47.1

4 hours, 27 minutes

1
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror