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

[PATCH v8 6/6] selftest/x86/signal: Include test cases for validating sigaltstack

by Chang S. Bae

The test measures the kernel's signal delivery with different (enough vs. insufficient) stack sizes. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Reviewed-by: Len Brown <len.brown(a)intel.com> Cc: x86(a)kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- Changes from v3: * Revised test messages again (Borislav Petkov) Changes from v2: * Revised test messages (Borislav Petkov) --- tools/testing/selftests/x86/Makefile | 2 +- tools/testing/selftests/x86/sigaltstack.c | 128 ++++++++++++++++++++++ 2 files changed, 129 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/x86/sigaltstack.c diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 333980375bc7..65bba2ae86ee 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -13,7 +13,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie) TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \ check_initial_reg_state sigreturn iopl ioperm \ test_vsyscall mov_ss_trap \ - syscall_arg_fault fsgsbase_restore + syscall_arg_fault fsgsbase_restore sigaltstack TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/sigaltstack.c b/tools/testing/selftests/x86/sigaltstack.c new file mode 100644 index 000000000000..f689af75e979 --- /dev/null +++ b/tools/testing/selftests/x86/sigaltstack.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <signal.h> +#include <stdio.h> +#include <stdbool.h> +#include <string.h> +#include <err.h> +#include <errno.h> +#include <limits.h> +#include <sys/mman.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/resource.h> +#include <setjmp.h> + +/* sigaltstack()-enforced minimum stack */ +#define ENFORCED_MINSIGSTKSZ 2048 + +#ifndef AT_MINSIGSTKSZ +# define AT_MINSIGSTKSZ 51 +#endif + +static int nerrs; + +static bool sigalrm_expected; + +static unsigned long at_minstack_size; + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static void clearhandler(int sig) +{ + struct sigaction sa; + + memset(&sa, 0, sizeof(sa)); + sa.sa_handler = SIG_DFL; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +static int setup_altstack(void *start, unsigned long size) +{ + stack_t ss; + + memset(&ss, 0, sizeof(ss)); + ss.ss_size = size; + ss.ss_sp = start; + + return sigaltstack(&ss, NULL); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + if (sigalrm_expected) { + printf("[FAIL]\tWrong signal delivered: SIGSEGV (expected SIGALRM)."); + nerrs++; + } else { + printf("[OK]\tSIGSEGV signal delivered.\n"); + } + + siglongjmp(jmpbuf, 1); +} + +static void sigalrm(int sig, siginfo_t *info, void *ctx_void) +{ + if (!sigalrm_expected) { + printf("[FAIL]\tWrong signal delivered: SIGALRM (expected SIGSEGV)."); + nerrs++; + } else { + printf("[OK]\tSIGALRM signal delivered.\n"); + } +} + +static void test_sigaltstack(void *altstack, unsigned long size) +{ + if (setup_altstack(altstack, size)) + err(1, "sigaltstack()"); + + sigalrm_expected = (size > at_minstack_size) ? true : false; + + sethandler(SIGSEGV, sigsegv, 0); + sethandler(SIGALRM, sigalrm, SA_ONSTACK); + + if (!sigsetjmp(jmpbuf, 1)) { + printf("[RUN]\tTest an alternate signal stack of %ssufficient size.\n", + sigalrm_expected ? "" : "in"); + printf("\tRaise SIGALRM. %s is expected to be delivered.\n", + sigalrm_expected ? "It" : "SIGSEGV"); + raise(SIGALRM); + } + + clearhandler(SIGALRM); + clearhandler(SIGSEGV); +} + +int main(void) +{ + void *altstack; + + at_minstack_size = getauxval(AT_MINSIGSTKSZ); + + altstack = mmap(NULL, at_minstack_size + SIGSTKSZ, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (altstack == MAP_FAILED) + err(1, "mmap()"); + + if ((ENFORCED_MINSIGSTKSZ + 1) < at_minstack_size) + test_sigaltstack(altstack, ENFORCED_MINSIGSTKSZ + 1); + + test_sigaltstack(altstack, at_minstack_size + SIGSTKSZ); + + return nerrs == 0 ? 0 : 1; +} -- 2.17.1

3 years, 9 months

1
0
0 0

[PATCH v8 4/6] selftest/sigaltstack: Use the AT_MINSIGSTKSZ aux vector if available

by Chang S. Bae

The SIGSTKSZ constant may not represent enough stack size in some architectures as the hardware state size grows. Use getauxval(AT_MINSIGSTKSZ) to increase the stack size. Signed-off-by: Chang S. Bae <chang.seok.bae(a)intel.com> Reviewed-by: Len Brown <len.brown(a)intel.com> Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org --- Changes from v5: * Added as a new patch. --- tools/testing/selftests/sigaltstack/sas.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/sigaltstack/sas.c b/tools/testing/selftests/sigaltstack/sas.c index 8934a3766d20..c53b070755b6 100644 --- a/tools/testing/selftests/sigaltstack/sas.c +++ b/tools/testing/selftests/sigaltstack/sas.c @@ -17,6 +17,7 @@ #include <string.h> #include <assert.h> #include <errno.h> +#include <sys/auxv.h> #include "../kselftest.h" @@ -24,6 +25,11 @@ #define SS_AUTODISARM (1U << 31) #endif +#ifndef AT_MINSIGSTKSZ +#define AT_MINSIGSTKSZ 51 +#endif + +static unsigned int stack_size; static void *sstack, *ustack; static ucontext_t uc, sc; static const char *msg = "[OK]\tStack preserved"; @@ -47,7 +53,7 @@ void my_usr1(int sig, siginfo_t *si, void *u) #endif if (sp < (unsigned long)sstack || - sp >= (unsigned long)sstack + SIGSTKSZ) { + sp >= (unsigned long)sstack + stack_size) { ksft_exit_fail_msg("SP is not on sigaltstack\n"); } /* put some data on stack. other sighandler will try to overwrite it */ @@ -108,6 +114,10 @@ int main(void) stack_t stk; int err; + /* Make sure more than the required minimum. */ + stack_size = getauxval(AT_MINSIGSTKSZ) + SIGSTKSZ; + ksft_print_msg("[NOTE]\tthe stack size is %lu\n", stack_size); + ksft_print_header(); ksft_set_plan(3); @@ -117,7 +127,7 @@ int main(void) sigaction(SIGUSR1, &act, NULL); act.sa_sigaction = my_usr2; sigaction(SIGUSR2, &act, NULL); - sstack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + sstack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (sstack == MAP_FAILED) { ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); @@ -139,7 +149,7 @@ int main(void) } stk.ss_sp = sstack; - stk.ss_size = SIGSTKSZ; + stk.ss_size = stack_size; stk.ss_flags = SS_ONSTACK | SS_AUTODISARM; err = sigaltstack(&stk, NULL); if (err) { @@ -161,7 +171,7 @@ int main(void) } } - ustack = mmap(NULL, SIGSTKSZ, PROT_READ | PROT_WRITE, + ustack = mmap(NULL, stack_size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); if (ustack == MAP_FAILED) { ksft_exit_fail_msg("mmap() - %s\n", strerror(errno)); @@ -170,7 +180,7 @@ int main(void) getcontext(&uc); uc.uc_link = NULL; uc.uc_stack.ss_sp = ustack; - uc.uc_stack.ss_size = SIGSTKSZ; + uc.uc_stack.ss_size = stack_size; makecontext(&uc, switch_fn, 0); raise(SIGUSR1); -- 2.17.1

3 years, 9 months

1
0
0 0

[PATCH] selftests: timens: Fix gettime_perf to work on powerpc

by Christophe Leroy

On powerpc: - VDSO library is named linux-vdso32.so.1 or linux-vdso64.so.1 - clock_gettime is named __kernel_clock_gettime() Ensure gettime_perf tries these names before giving up. Signed-off-by: Christophe Leroy <christophe.leroy(a)csgroup.eu> --- tools/testing/selftests/timens/gettime_perf.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/timens/gettime_perf.c b/tools/testing/selftests/timens/gettime_perf.c index 7bf841a3967b..6b13dc277724 100644 --- a/tools/testing/selftests/timens/gettime_perf.c +++ b/tools/testing/selftests/timens/gettime_perf.c @@ -25,12 +25,20 @@ static void fill_function_pointers(void) if (!vdso) vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-vdso32.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-vdso64.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); if (!vdso) { pr_err("[WARN]\tfailed to find vDSO\n"); return; } vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_clock_gettime) + vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__kernel_clock_gettime"); if (!vdso_clock_gettime) pr_err("Warning: failed to find clock_gettime in vDSO\n"); -- 2.25.0

3 years, 9 months

2
1
0 0

[PATCH v3] Documentation: dev-tools: Add Testing Overview

by David Gow

The kernel now has a number of testing and debugging tools, and we've seen a bit of confusion about what the differences between them are. Add a basic documentation outlining the testing tools, when to use each, and how they interact. This is a pretty quick overview rather than the idealised "kernel testing guide" that'd probably be optimal, but given the number of times questions like "When do you use KUnit and when do you use Kselftest?" are being asked, it seemed worth at least having something. Hopefully this can form the basis for more detailed documentation later. Signed-off-by: David Gow <davidgow(a)google.com> Reviewed-by: Marco Elver <elver(a)google.com> Reviewed-by: Daniel Latypov <dlatypov(a)google.com> --- Thanks again. Assuming no-one has any objections, I think this is good to go. -- David Changes since v2: https://lore.kernel.org/linux-kselftest/20210414081428.337494-1-davidgow@go… - A few typo fixes (Thanks Daniel) - Reworded description of dynamic analysis tools. - Updated dev-tools index page to not use ':doc:' syntax, but to provide a path instead. - Added Marco and Daniel's Reviewed-by tags. Changes since v1: https://lore.kernel.org/linux-kselftest/20210410070529.4113432-1-davidgow@g… - Note KUnit's speed and that one should provide selftests for syscalls - Mention lockdep as a Dynamic Analysis Tool - Refer to "Dynamic Analysis Tools" instead of "Sanitizers" - A number of minor formatting tweaks and rewordings for clarity Documentation/dev-tools/index.rst | 4 + Documentation/dev-tools/testing-overview.rst | 117 +++++++++++++++++++ 2 files changed, 121 insertions(+) create mode 100644 Documentation/dev-tools/testing-overview.rst diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index 1b1cf4f5c9d9..929d916ffd4c 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -7,6 +7,9 @@ be used to work on the kernel. For now, the documents have been pulled together without any significant effort to integrate them into a coherent whole; patches welcome! +A brief overview of testing-specific tools can be found in +Documentation/dev-tools/testing-overview.rst + .. class:: toc-title Table of contents @@ -14,6 +17,7 @@ whole; patches welcome! .. toctree:: :maxdepth: 2 + testing-overview coccinelle sparse kcov diff --git a/Documentation/dev-tools/testing-overview.rst b/Documentation/dev-tools/testing-overview.rst new file mode 100644 index 000000000000..b5b46709969c --- /dev/null +++ b/Documentation/dev-tools/testing-overview.rst @@ -0,0 +1,117 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +Kernel Testing Guide +==================== + + +There are a number of different tools for testing the Linux kernel, so knowing +when to use each of them can be a challenge. This document provides a rough +overview of their differences, and how they fit together. + + +Writing and Running Tests +========================= + +The bulk of kernel tests are written using either the kselftest or KUnit +frameworks. These both provide infrastructure to help make running tests and +groups of tests easier, as well as providing helpers to aid in writing new +tests. + +If you're looking to verify the behaviour of the Kernel — particularly specific +parts of the kernel — then you'll want to use KUnit or kselftest. + + +The Difference Between KUnit and kselftest +------------------------------------------ + +KUnit (Documentation/dev-tools/kunit/index.rst) is an entirely in-kernel system +for "white box" testing: because test code is part of the kernel, it can access +internal structures and functions which aren't exposed to userspace. + +KUnit tests therefore are best written against small, self-contained parts +of the kernel, which can be tested in isolation. This aligns well with the +concept of 'unit' testing. + +For example, a KUnit test might test an individual kernel function (or even a +single codepath through a function, such as an error handling case), rather +than a feature as a whole. + +This also makes KUnit tests very fast to build and run, allowing them to be +run frequently as part of the development process. + +There is a KUnit test style guide which may give further pointers in +Documentation/dev-tools/kunit/style.rst + + +kselftest (Documentation/dev-tools/kselftest.rst), on the other hand, is +largely implemented in userspace, and tests are normal userspace scripts or +programs. + +This makes it easier to write more complicated tests, or tests which need to +manipulate the overall system state more (e.g., spawning processes, etc.). +However, it's not possible to call kernel functions directly from kselftest. +This means that only kernel functionality which is exposed to userspace somehow +(e.g. by a syscall, device, filesystem, etc.) can be tested with kselftest. To +work around this, some tests include a companion kernel module which exposes +more information or functionality. If a test runs mostly or entirely within the +kernel, however, KUnit may be the more appropriate tool. + +kselftest is therefore suited well to tests of whole features, as these will +expose an interface to userspace, which can be tested, but not implementation +details. This aligns well with 'system' or 'end-to-end' testing. + +For example, all new system calls should be accompanied by kselftest tests. + +Code Coverage Tools +=================== + +The Linux Kernel supports two different code coverage measurement tools. These +can be used to verify that a test is executing particular functions or lines +of code. This is useful for determining how much of the kernel is being tested, +and for finding corner-cases which are not covered by the appropriate test. + +:doc:`gcov` is GCC's coverage testing tool, which can be used with the kernel +to get global or per-module coverage. Unlike KCOV, it does not record per-task +coverage. Coverage data can be read from debugfs, and interpreted using the +usual gcov tooling. + +:doc:`kcov` is a feature which can be built in to the kernel to allow +capturing coverage on a per-task level. It's therefore useful for fuzzing and +other situations where information about code executed during, for example, a +single syscall is useful. + + +Dynamic Analysis Tools +====================== + +The kernel also supports a number of dynamic analysis tools, which attempt to +detect classes of issues when they occur in a running kernel. These typically +each look for a different class of bugs, such as invalid memory accesses, +concurrency issues such as data races, or other undefined behaviour like +integer overflows. + +Some of these tools are listed below: + +* kmemleak detects possible memory leaks. See + Documentation/dev-tools/kmemleak.rst +* KASAN detects invalid memory accesses such as out-of-bounds and + use-after-free errors. See Documentation/dev-tools/kasan.rst +* UBSAN detects behaviour that is undefined by the C standard, like integer + overflows. See Documentation/dev-tools/ubsan.rst +* KCSAN detects data races. See Documentation/dev-tools/kcsan.rst +* KFENCE is a low-overhead detector of memory issues, which is much faster than + KASAN and can be used in production. See Documentation/dev-tools/kfence.rst +* lockdep is a locking correctness validator. See + Documentation/locking/lockdep-design.rst +* There are several other pieces of debug instrumentation in the kernel, many + of which can be found in lib/Kconfig.debug + +These tools tend to test the kernel as a whole, and do not "pass" like +kselftest or KUnit tests. They can be combined with KUnit or kselftest by +running tests on a kernel with these tools enabled: you can then be sure +that none of these errors are occurring during the test. + +Some of these tools integrate with KUnit or kselftest and will +automatically fail tests if an issue is detected. + -- 2.31.1.295.g9ea45b61b8-goog

3 years, 9 months

3
3
0 0

[PATCH][next] selftests: add missing void in MREMAP_DONTUNMAP selftest function prototypes

by Colin King

From: Colin Ian King <colin.king(a)canonical.com> There are a few function prototypes that are missing a void parameter, fix this by adding it in. Signed-off-by: Colin Ian King <colin.king(a)canonical.com> --- tools/testing/selftests/vm/mremap_dontunmap.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/vm/mremap_dontunmap.c b/tools/testing/selftests/vm/mremap_dontunmap.c index f01dc4a85b0b..78baaf0e85d9 100644 --- a/tools/testing/selftests/vm/mremap_dontunmap.c +++ b/tools/testing/selftests/vm/mremap_dontunmap.c @@ -42,7 +42,7 @@ static void dump_maps(void) // Try a simple operation for to "test" for kernel support this prevents // reporting tests as failed when it's run on an older kernel. -static int kernel_support_for_mremap_dontunmap() +static int kernel_support_for_mremap_dontunmap(void) { int ret = 0; unsigned long num_pages = 1; @@ -95,7 +95,7 @@ static int check_region_contains_byte(void *addr, unsigned long size, char byte) // this test validates that MREMAP_DONTUNMAP moves the pagetables while leaving // the source mapping mapped. -static void mremap_dontunmap_simple() +static void mremap_dontunmap_simple(void) { unsigned long num_pages = 5; @@ -128,7 +128,7 @@ static void mremap_dontunmap_simple() } // This test validates that MREMAP_DONTUNMAP on a shared mapping works as expected. -static void mremap_dontunmap_simple_shmem() +static void mremap_dontunmap_simple_shmem(void) { unsigned long num_pages = 5; @@ -181,7 +181,7 @@ static void mremap_dontunmap_simple_shmem() // This test validates MREMAP_DONTUNMAP will move page tables to a specific // destination using MREMAP_FIXED, also while validating that the source // remains intact. -static void mremap_dontunmap_simple_fixed() +static void mremap_dontunmap_simple_fixed(void) { unsigned long num_pages = 5; @@ -226,7 +226,7 @@ static void mremap_dontunmap_simple_fixed() // This test validates that we can MREMAP_DONTUNMAP for a portion of an // existing mapping. -static void mremap_dontunmap_partial_mapping() +static void mremap_dontunmap_partial_mapping(void) { /* * source mapping: -- 2.30.2

3 years, 9 months

1
0
0 0

[PATCH v3 00/10] userfaultfd: add minor fault handling for shmem

by Axel Rasmussen

Base ==== This series is based on (and therefore should apply cleanly to) the tag "v5.12-rc7-mmots-2021-04-11-20-49", additionally with Peter's selftest cleanup series applied first: https://lore.kernel.org/patchwork/cover/1412450/ Changelog ========= v2->v3: - Picked up {Reviewed,Acked}-by's. - Reorder commits: introduce CONTINUE before MINOR registration. [Hugh, Peter] - Don't try to {unlock,put}_page an xarray value in shmem_getpage_gfp. [Hugh] - Move enum mcopy_atomic_mode forward declare out of CONFIG_HUGETLB_PAGE. [Hugh] - Keep mistakenly removed UFFD_USER_MODE_ONLY in selftest. [Peter] - Cleanup context management in self test (make clear implicit, remove unneeded return values now that we have err()). [Peter] - Correct dst_pte argument to dst_pmd in shmem_mcopy_atomic_pte macro. [Hugh] - Mention the new shmem support feature in documentation. [Hugh] v1->v2: - Pick up Reviewed-by's. - Don't swapin page when a minor fault occurs. Notice that it needs to be swapped in, and just immediately fire the minor fault. Let a future CONTINUE deal with swapping in the page. [Peter] - Clarify comment about i_size checks in mm/userfaultfd.c. [Peter] - Only forward declare once (out of #ifdef) in hugetlb.h. [Peter] Changes since [2]: - Squash the fixes ([2]) in with the original series ([1]). This makes reviewing easier, as we no longer have to sift through deltas undoing what we had done before. [Hugh, Peter] - Modify shmem_mcopy_atomic_pte() to use the new mcopy_atomic_install_ptes() helper, reducing code duplication. [Hugh] - Properly trigger handle_userfault() in the shmem_swapin_page() case. [Hugh] - Use shmem_getpage() instead of find_lock_page() to lookup the existing page in for continue. This properly deals with swapped-out pages. [Hugh] - Unconditionally pte_mkdirty() for anon memory (as before). [Peter] - Don't include userfaultfd_k.h in either hugetlb.h or shmem_fs.h. [Hugh] - Add comment for UFFD_FEATURE_MINOR_SHMEM (to match _HUGETLBFS). [Hugh] - Fix some small cleanup issues (parens, reworded conditionals, reduced plumbing of some parameters, simplify labels/gotos, ...). [Hugh, Peter] Overview ======== See the series which added minor faults for hugetlbfs [3] for a detailed overview of minor fault handling in general. This series adds the same support for shmem-backed areas. This series is structured as follows: - Commits 1 and 2 are cleanups. - Commits 3 and 4 implement the new feature (minor fault handling for shmem). - Commits 5, 6, 7, 8 update the userfaultfd selftest to exercise the feature. - Commit 9 is one final cleanup, modifying an existing code path to re-use a new helper we've introduced. We rely on the selftest to show that this change doesn't break anything. Use Case ======== In some cases it is useful to have VM memory backed by tmpfs instead of hugetlbfs. So, this feature will be used to support the same VM live migration use case described in my original series. Additionally, Android folks (Lokesh Gidra <lokeshgidra(a)google.com>) hope to optimize the Android Runtime garbage collector using this feature: "The plan is to use userfaultfd for concurrently compacting the heap. With this feature, the heap can be shared-mapped at another location where the GC-thread(s) could continue the compaction operation without the need to invoke userfault ioctl(UFFDIO_COPY) each time. OTOH, if and when Java threads get faults on the heap, UFFDIO_CONTINUE can be used to resume execution. Furthermore, this feature enables updating references in the 'non-moving' portion of the heap efficiently. Without this feature, uneccessary page copying (ioctl(UFFDIO_COPY)) would be required." [1] https://lore.kernel.org/patchwork/cover/1388144/ [2] https://lore.kernel.org/patchwork/patch/1408161/ [3] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen… Axel Rasmussen (10): userfaultfd/hugetlbfs: avoid including userfaultfd_k.h in hugetlb.h userfaultfd/shmem: combine shmem_{mcopy_atomic,mfill_zeropage}_pte userfaultfd/shmem: support UFFDIO_CONTINUE for shmem userfaultfd/shmem: support minor fault registration for shmem userfaultfd/selftests: use memfd_create for shmem test type userfaultfd/selftests: create alias mappings in the shmem test userfaultfd/selftests: reinitialize test context in each test userfaultfd/selftests: exercise minor fault handling shmem support userfaultfd/shmem: modify shmem_mcopy_atomic_pte to use install_ptes userfaultfd: update documentation to mention shmem minor faults Documentation/admin-guide/mm/userfaultfd.rst | 3 +- fs/userfaultfd.c | 6 +- include/linux/hugetlb.h | 4 +- include/linux/shmem_fs.h | 17 +- include/linux/userfaultfd_k.h | 5 + include/uapi/linux/userfaultfd.h | 7 +- mm/hugetlb.c | 1 + mm/memory.c | 8 +- mm/shmem.c | 114 +++----- mm/userfaultfd.c | 183 +++++++++---- tools/testing/selftests/vm/userfaultfd.c | 274 ++++++++++++------- 11 files changed, 371 insertions(+), 251 deletions(-) -- 2.31.1.368.gbe11c130af-goog

3 years, 9 months

2
12
0 0

[PATCH v2 0/9] userfaultfd: add minor fault handling for shmem

by Axel Rasmussen

Base ==== This series is based on (and therefore should apply cleanly to) the tag "v5.12-rc7-mmots-2021-04-11-20-49", additionally with Peter's selftest cleanup series applied *first*: https://lore.kernel.org/patchwork/cover/1412450/ Changelog ========= v1->v2: - Pick up Reviewed-by's. - Don't swapin page when a minor fault occurs. Notice that it needs to be swapped in, and just immediately fire the minor fault. Let a future CONTINUE deal with swapping in the page. [Peter] - Clarify comment about i_size checks in mm/userfaultfd.c. [Peter] - Only forward declare once (out of #ifdef) in hugetlb.h. [Peter] Changes since [2]: - Squash the fixes ([2]) in with the original series ([1]). This makes reviewing easier, as we no longer have to sift through deltas undoing what we had done before. [Hugh, Peter] - Modify shmem_mcopy_atomic_pte() to use the new mcopy_atomic_install_ptes() helper, reducing code duplication. [Hugh] - Properly trigger handle_userfault() in the shmem_swapin_page() case. [Hugh] - Use shmem_getpage() instead of find_lock_page() to lookup the existing page in for continue. This properly deals with swapped-out pages. [Hugh] - Unconditionally pte_mkdirty() for anon memory (as before). [Peter] - Don't include userfaultfd_k.h in either hugetlb.h or shmem_fs.h. [Hugh] - Add comment for UFFD_FEATURE_MINOR_SHMEM (to match _HUGETLBFS). [Hugh] - Fix some small cleanup issues (parens, reworded conditionals, reduced plumbing of some parameters, simplify labels/gotos, ...). [Hugh, Peter] Overview ======== See the series which added minor faults for hugetlbfs [3] for a detailed overview of minor fault handling in general. This series adds the same support for shmem-backed areas. This series is structured as follows: - Commits 1 and 2 are cleanups. - Commits 3 and 4 implement the new feature (minor fault handling for shmem). - Commits 5, 6, 7, 8 update the userfaultfd selftest to exercise the feature. - Commit 9 is one final cleanup, modifying an existing code path to re-use a new helper we've introduced. We rely on the selftest to show that this change doesn't break anything. Use Case ======== In some cases it is useful to have VM memory backed by tmpfs instead of hugetlbfs. So, this feature will be used to support the same VM live migration use case described in my original series. Additionally, Android folks (Lokesh Gidra <lokeshgidra(a)google.com>) hope to optimize the Android Runtime garbage collector using this feature: "The plan is to use userfaultfd for concurrently compacting the heap. With this feature, the heap can be shared-mapped at another location where the GC-thread(s) could continue the compaction operation without the need to invoke userfault ioctl(UFFDIO_COPY) each time. OTOH, if and when Java threads get faults on the heap, UFFDIO_CONTINUE can be used to resume execution. Furthermore, this feature enables updating references in the 'non-moving' portion of the heap efficiently. Without this feature, uneccessary page copying (ioctl(UFFDIO_COPY)) would be required." [1] https://lore.kernel.org/patchwork/cover/1388144/ [2] https://lore.kernel.org/patchwork/patch/1408161/ [3] https://lore.kernel.org/linux-fsdevel/20210301222728.176417-1-axelrasmussen… Axel Rasmussen (9): userfaultfd/hugetlbfs: avoid including userfaultfd_k.h in hugetlb.h userfaultfd/shmem: combine shmem_{mcopy_atomic,mfill_zeropage}_pte userfaultfd/shmem: support minor fault registration for shmem userfaultfd/shmem: support UFFDIO_CONTINUE for shmem userfaultfd/selftests: use memfd_create for shmem test type userfaultfd/selftests: create alias mappings in the shmem test userfaultfd/selftests: reinitialize test context in each test userfaultfd/selftests: exercise minor fault handling shmem support userfaultfd/shmem: modify shmem_mcopy_atomic_pte to use install_ptes fs/userfaultfd.c | 6 +- include/linux/hugetlb.h | 4 +- include/linux/shmem_fs.h | 15 +- include/linux/userfaultfd_k.h | 5 + include/uapi/linux/userfaultfd.h | 7 +- mm/hugetlb.c | 1 + mm/memory.c | 8 +- mm/shmem.c | 112 +++------ mm/userfaultfd.c | 183 ++++++++++----- tools/testing/selftests/vm/userfaultfd.c | 280 +++++++++++++++-------- 10 files changed, 377 insertions(+), 244 deletions(-) -- 2.31.1.295.g9ea45b61b8-goog

3 years, 9 months

3
22
0 0

[PATCH v2 0/2] secretmem: optimize page_is_secretmem()

by Mike Rapoport

From: Mike Rapoport <rppt(a)linux.ibm.com> Hi, This is an updated version of page_is_secretmem() changes. This is based on v5.12-rc7-mmots-2021-04-15-16-28. @Andrew, please let me know if you'd like me to rebase it differently or resend the entire set. v2: * move the check for secretmem page in gup_pte_range after we get a reference to the page, per Matthew. Mike Rapoport (2): secretmem/gup: don't check if page is secretmem without reference secretmem: optimize page_is_secretmem() include/linux/secretmem.h | 26 +++++++++++++++++++++++++- mm/gup.c | 6 +++--- mm/secretmem.c | 12 +----------- 3 files changed, 29 insertions(+), 15 deletions(-) -- 2.28.0

3 years, 9 months

3
7
0 0

[PATCH] secretmem: optimize page_is_secretmem()

by Mike Rapoport

From: Mike Rapoport <rppt(a)linux.ibm.com> Kernel test robot reported -4.2% regression of will-it-scale.per_thread_ops due to commit "mm: introduce memfd_secret system call to create "secret" memory areas". The perf profile of the test indicated that the regression is caused by page_is_secretmem() called from gup_pte_range() (inlined by gup_pgd_range): 27.76 +2.5 30.23 perf-profile.children.cycles-pp.gup_pgd_range 0.00 +3.2 3.19 ± 2% perf-profile.children.cycles-pp.page_mapping 0.00 +3.7 3.66 ± 2% perf-profile.children.cycles-pp.page_is_secretmem Further analysis showed that the slow down happens because neither page_is_secretmem() nor page_mapping() are not inline and moreover, multiple page flags checks in page_mapping() involve calling compound_head() several times for the same page. Make page_is_secretmem() inline and replace page_mapping() with page flag checks that do not imply page-to-head conversion. Reported-by: kernel test robot <oliver.sang(a)intel.com> Signed-off-by: Mike Rapoport <rppt(a)linux.ibm.com> --- @Andrew, The patch is vs v5.12-rc7-mmots-2021-04-15-16-28, I'd appreciate if it would be added as a fixup to the memfd_secret series. include/linux/secretmem.h | 26 +++++++++++++++++++++++++- mm/secretmem.c | 12 +----------- 2 files changed, 26 insertions(+), 12 deletions(-) diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 907a6734059c..b842b38cbeb1 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -4,8 +4,32 @@ #ifdef CONFIG_SECRETMEM +extern const struct address_space_operations secretmem_aops; + +static inline bool page_is_secretmem(struct page *page) +{ + struct address_space *mapping; + + /* + * Using page_mapping() is quite slow because of the actual call + * instruction and repeated compound_head(page) inside the + * page_mapping() function. + * We know that secretmem pages are not compound and LRU so we can + * save a couple of cycles here. + */ + if (PageCompound(page) || !PageLRU(page)) + return false; + + mapping = (struct address_space *) + ((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); + + if (mapping != page->mapping) + return false; + + return page->mapping->a_ops == &secretmem_aops; +} + bool vma_is_secretmem(struct vm_area_struct *vma); -bool page_is_secretmem(struct page *page); bool secretmem_active(void); #else diff --git a/mm/secretmem.c b/mm/secretmem.c index 3b1ba3991964..0bcd15e1b549 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -151,22 +151,12 @@ static void secretmem_freepage(struct page *page) clear_highpage(page); } -static const struct address_space_operations secretmem_aops = { +const struct address_space_operations secretmem_aops = { .freepage = secretmem_freepage, .migratepage = secretmem_migratepage, .isolate_page = secretmem_isolate_page, }; -bool page_is_secretmem(struct page *page) -{ - struct address_space *mapping = page_mapping(page); - - if (!mapping) - return false; - - return mapping->a_ops == &secretmem_aops; -} - static struct vfsmount *secretmem_mnt; static struct file *secretmem_file_create(unsigned long flags) -- 2.28.0

3 years, 9 months

3
11
0 0

[PATCH bpf-next v4 0/3] add batched ops for percpu array

by Pedro Tammela

This patchset introduces batched operations for the per-cpu variant of the array map. It also removes the percpu macros from 'bpf_util.h'. This change was suggested by Andrii in a earlier iteration of this patchset. The tests were updated to reflect all the new changes. v3 -> v4: - Prefer 'calloc()' over 'malloc()' on batch ops tests - Add missing static keyword in a couple of test functions - 'offset' to 'cpu_offset' as suggested by Martin v2 -> v3: - Remove percpu macros as suggested by Andrii - Update tests that used the per cpu macros v1 -> v2: - Amended a more descriptive commit message Pedro Tammela (3): bpf: add batched ops support for percpu array bpf: selftests: remove percpu macros from bpf_util.h bpf: selftests: update array map tests for per-cpu batched ops kernel/bpf/arraymap.c | 2 + tools/testing/selftests/bpf/bpf_util.h | 7 -- .../bpf/map_tests/array_map_batch_ops.c | 104 +++++++++++++----- .../bpf/map_tests/htab_map_batch_ops.c | 87 +++++++-------- .../selftests/bpf/prog_tests/map_init.c | 9 +- tools/testing/selftests/bpf/test_maps.c | 84 ++++++++------ 6 files changed, 173 insertions(+), 120 deletions(-) -- 2.25.1

3 years, 9 months

3
5
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror