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

[PATCH v2 1/3] selftests/mm: make file-backed THP split work by writing PMD size data

by Zi Yan

Commit acd7ccb284b8 ("mm: shmem: add large folio support for tmpfs") changes huge=always to allocate THP/mTHP based on write size and split_huge_page_test does not write PMD size data, so file-back THP is not created during the test. Fix it by writing PMD size data. Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- V1 -> V2: write PMD size data instead of setting /sys/kernel/mm/transparent_hugepage/shmem_enabled to "force". .../selftests/mm/split_huge_page_test.c | 52 ++++++++++++++++--- 1 file changed, 44 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 3f353f3d070f..ba498aaaf857 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -265,14 +265,28 @@ void split_file_backed_thp(void) { int status; int fd; - ssize_t num_written; char tmpfs_template[] = "/tmp/thp_split_XXXXXX"; const char *tmpfs_loc = mkdtemp(tmpfs_template); char testfile[INPUT_MAX]; + ssize_t num_written, num_read; + char *file_buf1, *file_buf2; uint64_t pgoff_start = 0, pgoff_end = 1024; + int i; ksft_print_msg("Please enable pr_debug in split_huge_pages_in_file() for more info.\n"); + file_buf1 = (char *)malloc(pmd_pagesize); + file_buf2 = (char *)malloc(pmd_pagesize); + + if (!file_buf1 || !file_buf2) { + ksft_print_msg("cannot allocate file buffers\n"); + goto out; + } + + for (i = 0; i < pmd_pagesize; i++) + file_buf1[i] = (char)i; + memset(file_buf2, 0, pmd_pagesize); + status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m"); if (status) @@ -281,26 +295,45 @@ void split_file_backed_thp(void) status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc); if (status >= INPUT_MAX) { ksft_exit_fail_msg("Fail to create file-backed THP split testing file\n"); + goto cleanup; } - fd = open(testfile, O_CREAT|O_WRONLY, 0664); + fd = open(testfile, O_CREAT|O_RDWR, 0664); if (fd == -1) { ksft_perror("Cannot open testing file"); goto cleanup; } - /* write something to the file, so a file-backed THP can be allocated */ - num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1); - close(fd); + /* write pmd size data to the file, so a file-backed THP can be allocated */ + num_written = write(fd, file_buf1, pmd_pagesize); - if (num_written < 1) { - ksft_perror("Fail to write data to testing file"); - goto cleanup; + if (num_written == -1 || num_written != pmd_pagesize) { + ksft_perror("Failed to write data to testing file"); + goto close_file; } /* split the file-backed THP */ write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, 0); + /* check file content after split */ + status = lseek(fd, 0, SEEK_SET); + if (status == -1) { + ksft_perror("Cannot lseek file"); + goto close_file; + } + + num_read = read(fd, file_buf2, num_written); + if (num_read == -1 || num_read != num_written) { + ksft_perror("Cannot read file content back"); + goto close_file; + } + + if (strncmp(file_buf1, file_buf2, pmd_pagesize) != 0) { + ksft_print_msg("File content changed\n"); + goto close_file; + } + + close(fd); status = unlink(testfile); if (status) { ksft_perror("Cannot remove testing file"); @@ -321,9 +354,12 @@ void split_file_backed_thp(void) ksft_test_result_pass("File-backed THP split test done\n"); return; +close_file: + close(fd); cleanup: umount(tmpfs_loc); rmdir(tmpfs_loc); +out: ksft_exit_fail_msg("Error occurred\n"); } -- 2.45.2

5 months, 2 weeks

2
3
0 0

[PATCH 1/3] selftests/mm: make file-backed THP split work by setting force option

by Zi Yan

Commit acd7ccb284b8 ("mm: shmem: add large folio support for tmpfs") changes huge=always to allocate THP/mTHP based on write size and split_huge_page_test does not write PMD size data, so file-back THP is not created during the test. Set /sys/kernel/mm/transparent_hugepage/shmem_enabled to "force" to force THP allocation. Signed-off-by: Zi Yan <ziy(a)nvidia.com> Reviewed-by: Baolin Wang <baolin.wang(a)linux.alibaba.com> Tested-by: Baolin Wang <baolin.wang(a)linux.alibaba.com> --- .../selftests/mm/split_huge_page_test.c | 48 +++++++++++++++++-- 1 file changed, 45 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 3f353f3d070f..8e15fc9dce3a 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -264,15 +264,46 @@ void split_pte_mapped_thp(void) void split_file_backed_thp(void) { int status; - int fd; - ssize_t num_written; + int fd, shmem_sysctl_fd; + ssize_t num_written, num_read; char tmpfs_template[] = "/tmp/thp_split_XXXXXX"; const char *tmpfs_loc = mkdtemp(tmpfs_template); - char testfile[INPUT_MAX]; + char testfile[INPUT_MAX], sysctl_buf[INPUT_MAX] = {0}; uint64_t pgoff_start = 0, pgoff_end = 1024; + const char *shmem_sysctl = "/sys/kernel/mm/transparent_hugepage/shmem_enabled"; + char *opt1, *opt2; ksft_print_msg("Please enable pr_debug in split_huge_pages_in_file() for more info.\n"); + shmem_sysctl_fd = open(shmem_sysctl, O_RDWR); + if (shmem_sysctl_fd == -1) { + ksft_perror("cannot open shmem sysctl"); + goto out; + } + + num_read = read(shmem_sysctl_fd, sysctl_buf, INPUT_MAX); + if (num_read < 1) { + ksft_perror("Failed to read shmem sysctl"); + goto cleanup_sysctl; + } + + opt1 = strchr(sysctl_buf, '['); + opt2 = strchr(sysctl_buf, ']'); + if (!opt1 || !opt2) { + ksft_perror("cannot read shmem sysctl config"); + goto cleanup_sysctl; + } + + /* get existing shmem sysctl config into sysctl_buf */ + strncpy(sysctl_buf, opt1 + 1, opt2 - opt1 - 1); + memset(sysctl_buf + (opt2 - opt1 - 1), 0, INPUT_MAX); + + num_written = write(shmem_sysctl_fd, "force", sizeof("force")); + if (num_written < 1) { + ksft_perror("Fail to write force to shmem sysctl"); + goto cleanup_sysctl; + } + status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m"); if (status) @@ -317,13 +348,24 @@ void split_file_backed_thp(void) if (status) ksft_exit_fail_msg("cannot remove tmp dir: %s\n", strerror(errno)); + num_written = write(shmem_sysctl_fd, sysctl_buf, strlen(sysctl_buf) + 1); + if (num_written < 1) + ksft_perror("Fail to restore shmem sysctl"); + + close(shmem_sysctl_fd); ksft_print_msg("Please check dmesg for more information\n"); ksft_test_result_pass("File-backed THP split test done\n"); return; cleanup: + num_written = write(shmem_sysctl_fd, sysctl_buf, strlen(sysctl_buf) + 1); + if (num_written < 1) + ksft_perror("Fail to restore shmem sysctl"); umount(tmpfs_loc); rmdir(tmpfs_loc); +cleanup_sysctl: + close(shmem_sysctl_fd); +out: ksft_exit_fail_msg("Error occurred\n"); } -- 2.45.2

5 months, 2 weeks

2
7
0 0

[PATCH net-next v1 0/5] Some pktgen fixes/improvments

by Peter Seiderer

While taking a look at '[PATCH net] pktgen: Avoid out-of-range in get_imix_entries' ([1]) and '[PATCH net v2] pktgen: Avoid out-of-bounds access in get_imix_entries' ([2], [3]) and doing some tests and code review I detected that the /proc/net/pktgen/... parsing logic does not honour the user given buffer bounds (resulting in out-of-bounds access). This can be observed e.g. by the following simple test (sometimes the old/'longer' previous value is re-read from the buffer): $ echo add_device lo@0 > /proc/net/pktgen/kpktgend_0 $ echo "min_pkt_size 12345" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo -n "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 12345 max_pkt_size: 0 Result: OK: min_pkt_size=12345 $ echo "min_pkt_size 123" > /proc/net/pktgen/lo\@0 && grep min_pkt_size /proc/net/pktgen/lo\@0 Params: count 1000 min_pkt_size: 123 max_pkt_size: 0 Result: OK: min_pkt_size=123 So fix the out-of-bounds access (and two minor findings) and add a simple proc_net_pktgen selftest... Regards, Peter [1] https://lore.kernel.org/netdev/20241006221221.3744995-1-artem.chernyshev@re… [2] https://lore.kernel.org/netdev/20250109083039.14004-1-pchelkin@ispras.ru/ [3] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… Peter Seiderer (5): net: pktgen: replace ENOTSUPP with EOPNOTSUPP net: pktgen: enable 'param=value' parsing net: pktgen: fix access outside of user given buffer in pktgen_thread_write() net: pktgen: fix access outside of user given buffer in pktgen_if_write() selftest: net: add proc_net_pktgen net/core/pktgen.c | 210 ++++--- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/proc_net_pktgen.c | 575 ++++++++++++++++++ 3 files changed, 712 insertions(+), 74 deletions(-) create mode 100644 tools/testing/selftests/net/proc_net_pktgen.c -- 2.48.0

5 months, 2 weeks

2
7
0 0

[PATCH v5 00/10] Buddy allocator like folio split

by Zi Yan

Hi all This patchset adds a new buddy allocator like large folio split to the total number of resulting folios, the amount of memory needed for multi-index xarray split, and keep more large folios after a split. It is on top of mm-everything-2025-01-16-06-37. It is ready to be merged. Instead of duplicating existing split_huge_page*() code, __folio_split() is introduced as the shared backend code for both split_huge_page_to_list_to_order() and folio_split(). __folio_split() can support both uniform split and buddy allocator like split. All existing split_huge_page*() users can be gradually converted to use folio_split() if possible. In this patchset, I converted truncate_inode_partial_folio() to use folio_split(). xfstests quick group passed for both tmpfs and xfs. Changelog === From V4[6]: 1. Enabled shmem support in both uniform and buddy allocator like split and added selftests for it. 2. Added functions to check if uniform split and buddy allocator like split are supported for the given folio and order. 3. Made truncate fall back to uniform split if buddy allocator split is not supported (CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio). 4. Added the missing folio_clear_has_hwpoisoned() to __split_unmapped_folio(). From V3[5]: 1. Used xas_split_alloc(GFP_NOWAIT) instead of xas_nomem(), since extra operations inside xas_split_alloc() are needed for correctness. 2. Enabled folio_split() for shmem and no issue was found with xfstests quick test group. 3. Split both ends of a truncate range in truncate_inode_partial_folio() to avoid wasting memory in shmem truncate (per David Hildenbrand). 4. Removed page_in_folio_offset() since page_folio() does the same thing. 5. Finished truncate related tests from xfstests quick test group on XFS and tmpfs without issues. 6. Disabled buddy allocator like split on CONFIG_READ_ONLY_THP_FOR_FS and FS without large folio. This check was missed in the prior versions. From V2[3]: 1. Incorporated all the feedback from Kirill[4]. 2. Used GFP_NOWAIT for xas_nomem(). 3. Tested the code path when xas_nomem() fails. 4. Added selftests for folio_split(). 5. Fixed no THP config build error. From V1[2]: 1. Split the original patch 1 into multiple ones for easy review (per Kirill). 2. Added xas_destroy() to avoid memory leak. 3. Fixed nr_dropped not used error (per kernel test robot). 4. Added proper error handling when xas_nomem() fails to allocate memory for xas_split() during buddy allocator like split. From RFC[1]: 1. Merged backend code of split_huge_page_to_list_to_order() and folio_split(). The same code is used for both uniform split and buddy allocator like split. 2. Use xas_nomem() instead of xas_split_alloc() for folio_split(). 3. folio_split() now leaves the first after-split folio unlocked, instead of the one containing the given page, since the caller of truncate_inode_partial_folio() locks and unlocks the first folio. 4. Extended split_huge_page debugfs to use folio_split(). 5. Added truncate_inode_partial_folio() as first user of folio_split(). Design === folio_split() splits a large folio in the same way as buddy allocator splits a large free page for allocation. The purpose is to minimize the number of folios after the split. For example, if user wants to free the 3rd subpage in a order-9 folio, folio_split() will split the order-9 folio as: O-0, O-0, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-8 if it is anon O-1, O-0, O-0, O-2, O-3, O-4, O-5, O-6, O-7, O-9 if it is pagecache Since anon folio does not support order-1 yet. The split process is similar to existing approach: 1. Unmap all page mappings (split PMD mappings if exist); 2. Split meta data like memcg, page owner, page alloc tag; 3. Copy meta data in struct folio to sub pages, but instead of spliting the whole folio into multiple smaller ones with the same order in a shot, this approach splits the folio iteratively. Taking the example above, this approach first splits the original order-9 into two order-8, then splits left part of order-8 to two order-7 and so on; 4. Post-process split folios, like write mapping->i_pages for pagecache, adjust folio refcounts, add split folios to corresponding list; 5. Remap split folios 6. Unlock split folios. __split_unmapped_folio() and __split_folio_to_order() replace __split_huge_page() and __split_huge_page_tail() respectively. __split_unmapped_folio() uses different approaches to perform uniform split and buddy allocator like split: 1. uniform split: one single call to __split_folio_to_order() is used to uniformly split the given folio. All resulting folios are put back to the list after split. The folio containing the given page is left to caller to unlock and others are unlocked. 2. buddy allocator like split: old_order - new_order calls to __split_folio_to_order() are used to split the given folio at order N to order N-1. After each call, the target folio is changed to the one containing the page, which is given via folio_split() parameters. After each call, folios not containing the page are put back to the list. The folio containing the page is put back to the list when its order is new_order. All folios are unlocked except the first folio, which is left to caller to unlock. Patch Overview === 1. Patch 1 made file-backed THP split work in split_huge_page_test, patch 2 enabled shmem large folio split to any lower order, and patch 3 added tests for splitting file-backed THP to any lower order. They can be picked independent of this patchset. 2. Patch 4 added __split_unmapped_folio() and __split_folio_to_order() to prepare for moving to new backend split code. 3. Patch 5 moved common code in split_huge_page_to_list_to_order() to __folio_split(). 4. Patch 6 added new folio_split() and made split_huge_page_to_list_to_order() share the new __split_unmapped_folio() with folio_split(). 5. Patch 7 removed no longer used __split_huge_page() and __split_huge_page_tail(). 6. Patch 8 added a new in_folio_offset to split_huge_page debugfs for folio_split() test. 7. Patch 9 used folio_split() for truncate operation. 8. Patch 10 added folio_split() tests. Any comments and/or suggestions are welcome. Thanks. [1] https://lore.kernel.org/linux-mm/20241008223748.555845-1-ziy@nvidia.com/ [2] https://lore.kernel.org/linux-mm/20241028180932.1319265-1-ziy@nvidia.com/ [3] https://lore.kernel.org/linux-mm/20241101150357.1752726-1-ziy@nvidia.com/ [4] https://lore.kernel.org/linux-mm/e6ppwz5t4p4kvir6eqzoto4y5fmdjdxdyvxvtw43nc… [5] https://lore.kernel.org/linux-mm/20241205001839.2582020-1-ziy@nvidia.com/ [6] https://lore.kernel.org/linux-mm/20250106165513.104899-1-ziy@nvidia.com/ Zi Yan (10): selftests/mm: make file-backed THP split work by setting force option mm/huge_memory: allow split shmem large folio to any lower order selftests/mm: test splitting file-backed THP to any lower order. mm/huge_memory: add two new (not yet used) functions for folio_split() mm/huge_memory: move folio split common code to __folio_split() mm/huge_memory: add buddy allocator like folio_split() mm/huge_memory: remove the old, unused __split_huge_page() mm/huge_memory: add folio_split() to debugfs testing interface. mm/truncate: use folio_split() for truncate operation. selftests/mm: add tests for folio_split(), buddy allocator like split. include/linux/huge_mm.h | 24 + mm/huge_memory.c | 755 ++++++++++++------ mm/truncate.c | 31 +- .../selftests/mm/split_huge_page_test.c | 105 ++- 4 files changed, 633 insertions(+), 282 deletions(-) -- 2.45.2

5 months, 2 weeks

2
14
0 0

[PATCH RFC v3 00/27] KVM: arm64: Implement support for SME in non-protected guests

by Mark Brown

Given the time of year and point in the release cycle this is an RFC series, there's a few areas where I'm particularly expecting that people might have feedback: - The userspace ABI, in particular: - The vector length used for the SVE registers, access to the SVE registers and access to ZA and (if available) ZT0 depending on the current state of PSTATE.{SM,ZA}. - The use of a single finalisation for both SVE and SME. - The addition of control for enabling fine grained traps in a similar manner to FGU but without the UNDEF, I'm not clear if this is desired at all and at present this requires symmetric read and write traps like FGU. That seemed like it might be desired from an implementation point of view but we already have one case where we enable an asymmetric trap (for ARM64_WORKAROUND_AMPERE_AC03_CPU_38) and it seems generally useful to enable asymmetrically. There is some nested virtualisation support in the code but it is not enabled or complete, this will be completed before the RFC tag is removed. I am anticipating having a vastly better test environment soon which will make this much easier to complete and there is no SME specific ABI for nested virtualisation. This series implements support for SME use in non-protected KVM guests. Much of this is very similar to SVE, the main additional challenge that SME presents is that it introduces a new vector length similar to the SVE vector length and two new controls which change the registers seen by guests: - PSTATE.ZA enables the ZA matrix register and, if SME2 is supported, the ZT0 LUT register. - PSTATE.SM enables streaming mode, a new floating point mode which uses the SVE register set with the separately configured SME vector length. In streaming mode implementation of the FFR register is optional. It is also permitted to build systems which support SME without SVE, in this case when not in streaming mode no SVE registers or instructions are available. Further, there is no requirement that there be any overlap in the set of vector lengths supported by SVE and SME in a system, this is expected to be a common situation in practical systems. Since there is a new vector length to configure we introduce a new feature parallel to the existing SVE one with a new pseudo register for the streaming mode vector length. Due to the overlap with SVE caused by streaming mode rather than finalising SME as a separate feature we use the existing SVE finalisation to also finalise SME, a new define KVM_ARM_VCPU_VEC is provided to help make user code clearer. Finalising SVE and SME separately would introduce complication with register access since finalising SVE makes the SVE regsiters writeable by userspace and doing multiple finalisations results in an error being reported. Dealing with a state where the SVE registers are writeable due to one of SVE or SME being finalised but may have their VL changed by the other being finalised seems like needless complexity with minimal practical utility, it seems clearer to just express directly that only one finalisation can be done in the ABI. Access to the floating point registers follows the architecture: - When both SVE and SME are present: - If PSTATE.SM == 0 the vector length used for the Z and P registers is the SVE vector length. - If PSTATE.SM == 1 the vector length used for the Z and P registers is the SME vector length. - If only SME is present: - If PSTATE.SM == 0 the Z and P registers are inaccessible and the floating point state accessed via the encodings for the V registers. - If PSTATE.SM == 1 the vector length used for the Z and P registers - The SME specific ZA and ZT0 registers are only accessible if SVCR.ZA is 1. The VMM must understand this, in particular when loading state SVCR should be configured before other state. There are a large number of subfeatures for SME, most of which only offer additional instructions but some of which (SME2 and FA64) add architectural state. These are configured via the ID registers as per usual. The new KVM_ARM_VCPU_VEC feature and ZA and ZT0 registers have not been added to the get-reg-list selftest, the idea of supporting additional features there without restructuring the program to generate all possible feature combinations has been rejected. I will post a separate series which does that restructuring. No support is present for protected guests, this is expected to be added separately. The series is based on Fuad's series: https://lore.kernel.org/r/20241216105057.579031-1-tabba@google.com/ It will need a rebase on: https://lore.kernel.org/r/20241219173351.1123087-1-maz@kernel.org (as will Fuad's.) Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v3: - Rebase onto v6.12-rc2. - Link to v2: https://lore.kernel.org/r/20231222-kvm-arm64-sme-v2-0-da226cb180bb@kernel.o… Changes in v2: - Rebase onto v6.7-rc3. - Configure subfeatures based on host system only. - Complete nVHE support. - There was some snafu with sending v1 out, it didn't make it to the lists but in case it hit people's inboxes I'm sending as v2. --- Mark Brown (27): arm64/fpsimd: Update FA64 and ZT0 enables when loading SME state arm64/fpsimd: Decide to save ZT0 and streaming mode FFR at bind time arm64/fpsimd: Check enable bit for FA64 when saving EFI state arm64/fpsimd: Determine maximum virtualisable SME vector length KVM: arm64: Introduce non-UNDEF FGT control KVM: arm64: Pull ctxt_has_ helpers to start of sysreg-sr.h KVM: arm64: Convert cpacr_clear_set() to a static inline KVM: arm64: Move SVE state access macros after feature test macros KVM: arm64: Factor SVE guest exit handling out into a function KVM: arm64: Rename SVE finalization constants to be more general KVM: arm64: Document the KVM ABI for SME KVM: arm64: Define internal features for SME KVM: arm64: Rename sve_state_reg_region KVM: arm64: Store vector lengths in an array KVM: arm64: Implement SME vector length configuration KVM: arm64: Add definitions for SME control register KVM: arm64: Support TPIDR2_EL0 KVM: arm64: Support SMIDR_EL1 for guests KVM: arm64: Support SME priority registers KVM: arm64: Provide assembly for SME state restore KVM: arm64: Support Z and P registers in streaming mode KVM: arm64: Expose SME specific state to userspace KVM: arm64: Context switch SME state for normal guests KVM: arm64: Handle SME exceptions KVM: arm64: Provide interface for configuring and enabling SME for guests KVM: arm64: selftests: Add SME system registers to get-reg-list KVM: arm64: selftests: Add SME to set_id_regs test Documentation/virt/kvm/api.rst | 117 ++++++--- arch/arm64/include/asm/fpsimd.h | 22 ++ arch/arm64/include/asm/kvm_emulate.h | 37 ++- arch/arm64/include/asm/kvm_host.h | 135 ++++++++--- arch/arm64/include/asm/kvm_hyp.h | 4 +- arch/arm64/include/asm/kvm_pkvm.h | 2 +- arch/arm64/include/asm/vncr_mapping.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 33 +++ arch/arm64/kernel/cpufeature.c | 2 - arch/arm64/kernel/fpsimd.c | 86 ++++--- arch/arm64/kvm/arm.c | 10 + arch/arm64/kvm/fpsimd.c | 156 +++++++----- arch/arm64/kvm/guest.c | 262 ++++++++++++++++++--- arch/arm64/kvm/handle_exit.c | 14 ++ arch/arm64/kvm/hyp/fpsimd.S | 16 ++ arch/arm64/kvm/hyp/include/hyp/switch.h | 104 ++++++-- arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 47 ++-- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 17 +- arch/arm64/kvm/hyp/nvhe/pkvm.c | 4 +- arch/arm64/kvm/hyp/nvhe/switch.c | 11 +- arch/arm64/kvm/hyp/vhe/switch.c | 21 +- arch/arm64/kvm/reset.c | 154 +++++++++--- arch/arm64/kvm/sys_regs.c | 118 +++++++++- include/uapi/linux/kvm.h | 1 + tools/testing/selftests/kvm/aarch64/get-reg-list.c | 32 ++- tools/testing/selftests/kvm/aarch64/set_id_regs.c | 29 ++- 26 files changed, 1117 insertions(+), 319 deletions(-) --- base-commit: e32a80927434907f973f38a88cd19d7e51991d24 change-id: 20230301-kvm-arm64-sme-06a1246d3636 prerequisite-message-id: 20241216105057.579031-1-tabba(a)google.com prerequisite-patch-id: 10a23279fc1aa942c363d66df0e95414342b614b prerequisite-patch-id: 670db72b1987d2591e23db072fd27db7f65ffb0f prerequisite-patch-id: c6bc6f799cebe5010bf3d734eb06e39d5dfab0d6 prerequisite-patch-id: 5555cde0b025483c2318d006a0324fd95bd06268 prerequisite-patch-id: a73738d5bbc5e694c92b7a5654f78eb79ed23c09 prerequisite-patch-id: 6194857db22ccaefe13e88b3155b6e761c9b7692 prerequisite-patch-id: 5dca3992c2ffa5bf2edb45f68be45edfae9b41b3 prerequisite-patch-id: b048e799d816c9c6750ed4f264fd38cb6e31f968 prerequisite-patch-id: 07fea6c2207f8cd2d35d4c171a97d28397db9a79 prerequisite-patch-id: f330e82665af9f223e838511bd4a95faad56e3ac prerequisite-patch-id: 060a6061eaedb7fd02c18e898bfd9652c991b9af prerequisite-patch-id: fc31d9f0e7812a8f962876fdb311414122895389 prerequisite-patch-id: ae675f63215a211c42a497789ee5e092fd461279 prerequisite-patch-id: ff3c533043a1fa3a13827ea5c70459b228aa95ee prerequisite-patch-id: de489d2d73f49d74b75c628828a6b56dbac751e2 prerequisite-patch-id: 92f4a1249e3a1ff32eb16c25af56930762c5697d prerequisite-patch-id: ac1248b4e10dce15672e02b366a359d634297877 Best regards, -- Mark Brown <broonie(a)kernel.org>

5 months, 2 weeks

3
31
0 0

[PATCH bpf v8 0/5] bpf: fix wrong copied_seq calculation and add tests

by Jiayuan Chen

A previous commit described in this topic http://lore.kernel.org/bpf/20230523025618.113937-9-john.fastabend@gmail.com directly updated 'sk->copied_seq' in the tcp_eat_skb() function when the action of a BPF program was SK_REDIRECT. For other actions, like SK_PASS, the update logic for 'sk->copied_seq' was moved to tcp_bpf_recvmsg_parser() to ensure the accuracy of the 'fionread' feature. That commit works for a single stream_verdict scenario, as it also modified 'sk_data_ready->sk_psock_verdict_data_ready->tcp_read_skb' to remove updating 'sk->copied_seq'. However, for programs where both stream_parser and stream_verdict are active(strparser purpose), tcp_read_sock() was used instead of tcp_read_skb() (sk_data_ready->strp_data_ready->tcp_read_sock) tcp_read_sock() now still update 'sk->copied_seq', leading to duplicated updates. In summary, for strparser + SK_PASS, copied_seq is redundantly calculated in both tcp_read_sock() and tcp_bpf_recvmsg_parser(). The issue causes incorrect copied_seq calculations, which prevent correct data reads from the recv() interface in user-land. Also we added test cases for bpf + strparser and separated them from sockmap_basic, as strparser has more encapsulation and parsing capabilities compared to sockmap. Fixes: e5c6de5fa025 ("bpf, sockmap: Incorrectly handling copied_seq") --- V8 -> V7: https://lore.kernel.org/bpf/20250116140531.108636-1-mrpre@163.com/ Avoid using add read_sock to psock. (Jakub Sitnicki) Avoid using warpper function to check whether strparser is supported. V3 -> V7: https://lore.kernel.org/bpf/20250109094402.50838-1-mrpre@163.com/ https://lore.kernel.org/bpf/20241218053408.437295-1-mrpre@163.com/ Avoid introducing new proto_ops. (Jakub Sitnicki). Add more edge test cases for strparser + bpf. Fix patchwork fail of test cases code. Fix psock fetch without rcu lock. Move code of modifying to tcp_bpf.c. V1 -> V3: https://lore.kernel.org/bpf/20241209152740.281125-1-mrpre@163.com/ Fix patchwork fail by adding Fixes tag. Save skb data offset for ENOMEM. (John Fastabend) --- Jiayuan Chen (5): strparser: add read_sock callback bpf: fix wrong copied_seq calculation bpf: disable non stream socket for strparser selftests/bpf: fix invalid flag of recv() selftests/bpf: add strparser test for bpf Documentation/networking/strparser.rst | 9 +- include/linux/skmsg.h | 2 + include/net/strparser.h | 2 + include/net/tcp.h | 8 + net/core/skmsg.c | 7 + net/core/sock_map.c | 5 +- net/ipv4/tcp.c | 29 +- net/ipv4/tcp_bpf.c | 42 ++ net/strparser/strparser.c | 11 +- .../selftests/bpf/prog_tests/sockmap_basic.c | 59 +-- .../selftests/bpf/prog_tests/sockmap_strp.c | 452 ++++++++++++++++++ .../selftests/bpf/progs/test_sockmap_strp.c | 53 ++ 12 files changed, 614 insertions(+), 65 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/sockmap_strp.c create mode 100644 tools/testing/selftests/bpf/progs/test_sockmap_strp.c -- 2.43.5

5 months, 2 weeks

2
11
0 0

[PATCH v6 00/15] integrity: Introduce the Integrity Digest Cache

by Roberto Sassu

From: Roberto Sassu <roberto.sassu(a)huawei.com> Integrity detection and protection has long been a desirable feature, to reach a large user base and mitigate the risk of flaws in the software and attacks. However, while solutions exist, they struggle to reach a large user base, due to requiring higher than desired constraints on performance, flexibility and configurability, that only security conscious people are willing to accept. For example, IMA measurement requires the target platform to collect integrity measurements, and to protect them with the TPM, which introduces a noticeable overhead (up to 10x slower in a microbenchmark) on frequently used system calls, like the open(). IMA Appraisal currently requires individual files to be signed and verified, and Linux distributions to rebuild all packages to include file signatures (this approach has been adopted from Fedora 39+). Like a TPM, also signature verification introduces a significant overhead, especially if it is used to check the integrity of many files. This is where the new Integrity Digest Cache comes into play, it offers additional support for new and existing integrity solutions, to make them faster and easier to deploy. The Integrity Digest Cache can help IMA to reduce the number of TPM operations and to make them happen in a deterministic way. If IMA knows that a file comes from a Linux distribution, it can measure files in a different way: measure the list of digests coming from the distribution (e.g. RPM package headers), and subsequently measure a file if it is not found in that list. The performance improvement comes at the cost of IMA not reporting which files from installed packages were accessed, and in which temporal sequence. This approach might not be suitable for all use cases. The Integrity Digest Cache can also help IMA for appraisal. IMA can simply lookup the calculated digest of an accessed file in the list of digests extracted from package headers, after verifying the header signature. It is sufficient to verify only one signature for all files in the package, as opposed to verifying a signature for each file. The same approach can be followed by other LSMs, such as Integrity Policy Enforcement (IPE), and BPF LSM. The Integrity Digest Cache is not tied to a specific package format. The kernel supports a TLV-based digest list format. More can be added through third-party kernel modules. The TLV parser has been verified for memory safety with the Frama-C static analyzer. The version with the Frama-C assertions is available here: https://github.com/robertosassu/rpm-formal/blob/main/validate_tlv.c Integrating the Integrity Digest Cache in IMA brings significant performance improvements: up to 67% and 79% for measurement respectively in sequential and parallel file reads; up to 65% and 43% for appraisal respectively in sequential and parallel file reads. The performance can be further enhanced by using fsverity digests instead of conventional file digests, which would make IMA verify only the portion of the file to be read. However, at the moment, fsverity digests are not included in RPM packages. In this case, once rpm is extended to include them, Linux distributions still have to rebuild their packages. The Integrity Digest Cache can support both digest types, so that the functionality is immediately available without waiting for Linux distributions to do the transition. This patch set only includes the patches necessary to extract digests from a TLV-based data format, and exposes an API for LSMs to query them. A separate patch set will be provided to integrate it in IMA. This patch set and the follow-up IMA integration can be tested by following the instructions at: https://github.com/linux-integrity/digest-cache-tools This patch set applies on top of: https://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity.git/l… with commit 08ae3e5f5fc8 ("integrity: Use static_assert() to check struct sizes"). Changelog v5: - Remove the RPM parser and selftests (suggested by Linus) - Return digest cache pointer from digest_cache_lookup() - Export new Parser API, and allow registration of third-party digest list parsers (suggested by Mimi) - Reduce sizes in TLV format and remove TLV header (suggested by Jani Nikula) - Introduce new DIGEST_LIST_NUM_ENTRIES TLV field - Pass file descriptor instead of dentry in digest_cache_get() to properly detect potential deadlocks - Introduce digest_cache_opened_fd() to tell lockdep when it is safe to nest a mutex if digest_cache_get() is called with that mutex held - Add new patch to introduce ksys_finit_module() - Make the TLV parser as configurable (Y/N/m) with Kconfig (suggested by Mimi) - Don't store the path structure in the digest cache and pass it between creation and initialization of the digest cache - Remove digest_cache_dir_update_dig_user() and keep the digest cache retrieved during digest_cache_get() - Fail with an error pointer in digest_cache_dir_lookup_digest() if the current and passed directory digest cache don't match, or the digest cache was reset - Handle num_digest = 0 in digest_cache_htable_init() - Accept -EOPNOTSUPP error in digest_cache_new() - Implement inode_free_security_rcu LSM hook instead of inode_free_security - Move reservation of file descriptor security blob inside the #ifdef in init_ima_lsm() - Add test file_reset_again to check the error pointer returned by digest_cache_lookup() - Remove TLV_FAILURE_HDR_LEN TLV error test - Add missing MODULE_DESCRIPTION in kselftest kernel module (suggested by Jeff Johnson) - Replace dentry_open() with kernel_file_open() in populate.c and dir.c - Skip affected tests when CONFIG_DYNAMIC_FTRACE_WITH_ARGS=n v4: - Rename digest_cache LSM to Integrity Digest Cache (suggested by Paul Moore) - Update documentation - Remove forward declaration of struct digest_cache in include/linux/digest_cache.h (suggested by Jarkko) - Add DIGEST_CACHE_FREE digest cache event for notification - Remove digest_cache_found_t typedef and use uintptr_t instead - Add header callback in TLV parser and unexport tlv_parse_hdr() and tlv_parse_data() - Plug the Integrity Digest Cache into the 'ima' LSM - Switch from constructor to zeroing the object cache - Remove notifier and detect digest cache changes by comparing pointers - Rename digest_cache_dir_create() to digest_cache_dir_add_entries() - Introduce digest_cache_dir_create() to create and initialize a directory digest cache - Introduce digest_cache_dir_update_dig_user() to update dig_user with a file digest cache on positive digest lookup - Use up to date directory digest cache, to take into account possible inode eviction for the old ones - Introduce digest_cache_dir_prefetch() to prefetch digest lists - Adjust component name in debug messages (suggested by Jarkko) - Add FILE_PREFETCH and FILE_READ digest cache flags, remove RESET_USER - Reintroduce spin lock for digest cache verification data (needed for the selftests) - Get inode and file descriptor security blob offsets from outside (IMA) - Avoid user-after-free in digest_cache_unref() by decrementing the ref. count after printing the debug message - Check for digest list lookup loops also for the parent directory - Put and clear dig_owner directly in digest_cache_reset_clear_owner() - Move digest cache initialization code from digest_cache_create() to digest_cache_init() - Hold the digest list path until the digest cache is initialized (to avoid premature inode eviction) - Avoid race condition on setting DIR_PREFETCH in the directory digest cache - Introduce digest_cache_dir_prefetch() and do it between digest cache creation and initialization (to avoid lock inversion) - Avoid unnecessary length check in digest_list_parse_rpm() - Declare arrays of strings in tlv parser as static - Emit reset for parent directory on directory entry modification - Rename digest_cache_reset_owner() to digest_cache_reset_clear_owner() and digest_cache_reset_user() to digest_cache_clear_user() - Execute digest_cache_file_release() either if FMODE_WRITE or FMODE_CREATED are set in the file descriptor f_mode - Determine in digest_cache_verif_set() which gfp flag to use depending on verifier ID - Update selftests v3: - Rewrite documentation, and remove the installation instructions since they are now included in the README of digest-cache-tools - Add digest cache event notifier - Drop digest_cache_was_reset(), and send instead to asynchronous notifications - Fix digest_cache LSM Kconfig style issues (suggested by Randy Dunlap) - Propagate digest cache reset to directory entries - Destroy per directory entry mutex - Introduce RESET_USER bit, to clear the dig_user pointer on set/removexattr - Replace 'file content' with 'file data' (suggested by Mimi) - Introduce per digest cache mutex and replace verif_data_lock spinlock - Track changes of security.digest_list xattr - Stop tracking file_open and use file_release instead also for file writes - Add error messages in digest_cache_create() - Load/unload testing kernel module automatically during execution of test - Add tests for digest cache event notifier - Add test for ftruncate() - Remove DIGEST_CACHE_RESET_PREFETCH_BUF command in test and clear the buffer on read instead v2: - Include the TLV parser in this patch set (from user asymmetric keys and signatures) - Move from IMA and make an independent LSM - Remove IMA-specific stuff from this patch set - Add per algorithm hash table - Expect all digest lists to be in the same directory and allow changing the default directory - Support digest lookup on directories, when there is no security.digest_list xattr - Add seq num to digest list file name, to impose ordering on directory iteration - Add a new data type DIGEST_LIST_ENTRY_DATA for the nested data in the tlv digest list format - Add the concept of verification data attached to digest caches - Add the reset mechanism to track changes on digest lists and directory containing the digest lists - Add kernel selftests v1: - Add documentation in Documentation/security/integrity-digest-cache.rst - Pass the mask of IMA actions to digest_cache_alloc() - Add a reference count to the digest cache - Remove the path parameter from digest_cache_get(), and rely on the reference count to avoid the digest cache disappearing while being used - Rename the dentry_to_check parameter of digest_cache_get() to dentry - Rename digest_cache_get() to digest_cache_new() and add digest_cache_get() to set the digest cache in the iint of the inode for which the digest cache was requested - Add dig_owner and dig_user to the iint, to distinguish from which inode the digest cache was created from, and which is using it; consequently it makes the digest cache usable to measure/appraise other digest caches (support not yet enabled) - Add dig_owner_mutex and dig_user_mutex to serialize accesses to dig_owner and dig_user until they are initialized - Enforce strong synchronization and make the contenders wait until dig_owner and dig_user are assigned to the iint the first time - Move checking IMA actions on the digest list earlier, and fail if no action were performed (digest cache not usable) - Remove digest_cache_put(), not needed anymore with the introduction of the reference count - Fail immediately in digest_cache_lookup() if the digest algorithm is not set in the digest cache - Use 64 bit mask for IMA actions on the digest list instead of 8 bit - Return NULL in the inline version of digest_cache_get() - Use list_add_tail() instead of list_add() in the iterator - Copy the digest list path to a separate buffer in digest_cache_iter_dir() - Use digest list parsers verified with Frama-C - Explicitly disable (for now) the possibility in the IMA policy to use the digest cache to measure/appraise other digest lists - Replace exit(<value>) with return <value> in manage_digest_lists.c Roberto Sassu (15): lib: Add TLV parser module: Introduce ksys_finit_module() integrity: Introduce the Integrity Digest Cache digest_cache: Initialize digest caches digest_cache: Add securityfs interface digest_cache: Add hash tables and operations digest_cache: Allow registration of digest list parsers digest_cache: Parse tlv digest lists digest_cache: Populate the digest cache from a digest list digest_cache: Add management of verification data digest_cache: Add support for directories digest cache: Prefetch digest lists if requested digest_cache: Reset digest cache on file/directory change selftests/digest_cache: Add selftests for the Integrity Digest Cache docs: Add documentation of the Integrity Digest Cache Documentation/security/digest_cache.rst | 850 ++++++++++++++++++ Documentation/security/index.rst | 1 + MAINTAINERS | 10 + include/linux/digest_cache.h | 131 +++ include/linux/kernel_read_file.h | 1 + include/linux/syscalls.h | 10 + include/linux/tlv_parser.h | 32 + include/uapi/linux/tlv_digest_list.h | 47 + include/uapi/linux/tlv_parser.h | 41 + include/uapi/linux/xattr.h | 6 + kernel/module/main.c | 43 +- lib/Kconfig | 3 + lib/Makefile | 2 + lib/tlv_parser.c | 87 ++ lib/tlv_parser.h | 18 + security/integrity/Kconfig | 1 + security/integrity/Makefile | 1 + security/integrity/digest_cache/Kconfig | 43 + security/integrity/digest_cache/Makefile | 11 + security/integrity/digest_cache/dir.c | 400 +++++++++ security/integrity/digest_cache/htable.c | 260 ++++++ security/integrity/digest_cache/internal.h | 283 ++++++ security/integrity/digest_cache/main.c | 597 ++++++++++++ security/integrity/digest_cache/modsig.c | 66 ++ security/integrity/digest_cache/parsers.c | 257 ++++++ security/integrity/digest_cache/parsers/tlv.c | 341 +++++++ security/integrity/digest_cache/populate.c | 104 +++ security/integrity/digest_cache/reset.c | 227 +++++ security/integrity/digest_cache/secfs.c | 104 +++ security/integrity/digest_cache/verif.c | 135 +++ security/integrity/ima/ima.h | 1 + security/integrity/ima/ima_fs.c | 6 + security/integrity/ima/ima_main.c | 10 +- tools/testing/selftests/Makefile | 1 + .../testing/selftests/digest_cache/.gitignore | 3 + tools/testing/selftests/digest_cache/Makefile | 24 + .../testing/selftests/digest_cache/all_test.c | 769 ++++++++++++++++ tools/testing/selftests/digest_cache/common.c | 78 ++ tools/testing/selftests/digest_cache/common.h | 93 ++ .../selftests/digest_cache/common_user.c | 33 + .../selftests/digest_cache/common_user.h | 15 + tools/testing/selftests/digest_cache/config | 2 + .../selftests/digest_cache/generators.c | 130 +++ .../selftests/digest_cache/generators.h | 16 + .../selftests/digest_cache/testmod/Makefile | 16 + .../selftests/digest_cache/testmod/kern.c | 551 ++++++++++++ 46 files changed, 5849 insertions(+), 11 deletions(-) create mode 100644 Documentation/security/digest_cache.rst create mode 100644 include/linux/digest_cache.h create mode 100644 include/linux/tlv_parser.h create mode 100644 include/uapi/linux/tlv_digest_list.h create mode 100644 include/uapi/linux/tlv_parser.h create mode 100644 lib/tlv_parser.c create mode 100644 lib/tlv_parser.h create mode 100644 security/integrity/digest_cache/Kconfig create mode 100644 security/integrity/digest_cache/Makefile create mode 100644 security/integrity/digest_cache/dir.c create mode 100644 security/integrity/digest_cache/htable.c create mode 100644 security/integrity/digest_cache/internal.h create mode 100644 security/integrity/digest_cache/main.c create mode 100644 security/integrity/digest_cache/modsig.c create mode 100644 security/integrity/digest_cache/parsers.c create mode 100644 security/integrity/digest_cache/parsers/tlv.c create mode 100644 security/integrity/digest_cache/populate.c create mode 100644 security/integrity/digest_cache/reset.c create mode 100644 security/integrity/digest_cache/secfs.c create mode 100644 security/integrity/digest_cache/verif.c create mode 100644 tools/testing/selftests/digest_cache/.gitignore create mode 100644 tools/testing/selftests/digest_cache/Makefile create mode 100644 tools/testing/selftests/digest_cache/all_test.c create mode 100644 tools/testing/selftests/digest_cache/common.c create mode 100644 tools/testing/selftests/digest_cache/common.h create mode 100644 tools/testing/selftests/digest_cache/common_user.c create mode 100644 tools/testing/selftests/digest_cache/common_user.h create mode 100644 tools/testing/selftests/digest_cache/config create mode 100644 tools/testing/selftests/digest_cache/generators.c create mode 100644 tools/testing/selftests/digest_cache/generators.h create mode 100644 tools/testing/selftests/digest_cache/testmod/Makefile create mode 100644 tools/testing/selftests/digest_cache/testmod/kern.c -- 2.47.0.118.gfd3785337b

5 months, 2 weeks

7
53
0 0

[PATCH v2 0/6] Extend pmu_counters_test to AMD CPUs

by Colton Lewis

Extend pmu_counters_test to AMD CPUs. As the AMD PMU is quite different from Intel with different events and feature sets, this series introduces a new code path to test it, specifically focusing on the core counters including the PerfCtrExtCore and PerfMonV2 features. Northbridge counters and cache counters exist, but are not as important and can be deferred to a later series. The first patch is a bug fix that could be submitted separately. The series has been tested on both Intel and AMD machines, but I have not found an AMD machine old enough to lack PerfCtrExtCore. I have made efforts that no part of the code has any dependency on its presence. I am aware of similar work in this direction done by Jinrong Liang [1]. He told me he is not working on it currently and I am not intruding by making my own submission. [1] https://lore.kernel.org/kvm/20231121115457.76269-1-cloudliang@tencent.com/ v2: * Test all combinations of VM setup rather than only the maximum allowed by hardware * Add fixes tag to bug fix in patch 1 * Refine some names v1: https://lore.kernel.org/kvm/20240813164244.751597-1-coltonlewis@google.com/ Colton Lewis (6): KVM: x86: selftests: Fix typos in macro variable use KVM: x86: selftests: Define AMD PMU CPUID leaves KVM: x86: selftests: Set up AMD VM in pmu_counters_test KVM: x86: selftests: Test read/write core counters KVM: x86: selftests: Test core events KVM: x86: selftests: Test PerfMonV2 .../selftests/kvm/include/x86_64/processor.h | 7 + .../selftests/kvm/x86_64/pmu_counters_test.c | 304 ++++++++++++++++-- 2 files changed, 277 insertions(+), 34 deletions(-) base-commit: da3ea35007d0af457a0afc87e84fddaebc4e0b63 -- 2.46.0.662.g92d0881bb0-goog

5 months, 2 weeks

2
20
0 0

[PATCH net v3 0/9] tun: Unify vnet implementation

by Akihiko Odaki

When I implemented virtio's hash-related features to tun/tap [1], I found tun/tap does not fill the entire region reserved for the virtio header, leaving some uninitialized hole in the middle of the buffer after read()/recvmesg(). This series fills the uninitialized hole. More concretely, the num_buffers field will be initialized with 1, and the other fields will be inialized with 0. Setting the num_buffers field to 1 is mandated by virtio 1.0 [2]. The change to virtio header is preceded by another change that refactors tun and tap to unify their virtio-related code. [1]: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com [2]: https://lore.kernel.org/r/20241227084256-mutt-send-email-mst@kernel.org/ Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v3: - Dropped changes to fill the vnet header. - Splitted patch "tun: Unify vnet implementation". - Reverted spurious changes in patch "tun: Unify vnet implementation". - Merged tun_vnet.c into TAP. - Link to v2: https://lore.kernel.org/r/20250109-tun-v2-0-388d7d5a287a@daynix.com Changes in v2: - Fixed num_buffers endian. - Link to v1: https://lore.kernel.org/r/20250108-tun-v1-0-67d784b34374@daynix.com --- Akihiko Odaki (9): tun: Refactor CONFIG_TUN_VNET_CROSS_LE tun: Avoid double-tracking iov_iter length changes tun: Keep hdr_len in tun_get_user() tun: Decouple vnet from tun_struct tun: Decouple vnet handling tun: Extract the vnet handling code tap: Avoid double-tracking iov_iter length changes tap: Keep hdr_len in tap_get_user() tap: Use tun's vnet-related code MAINTAINERS | 2 +- drivers/net/Kconfig | 1 + drivers/net/Makefile | 3 +- drivers/net/tap.c | 172 ++++++------------------------------------ drivers/net/tun.c | 200 +++++++------------------------------------------ drivers/net/tun_vnet.c | 180 ++++++++++++++++++++++++++++++++++++++++++++ drivers/net/tun_vnet.h | 25 +++++++ 7 files changed, 260 insertions(+), 323 deletions(-) --- base-commit: a32e14f8aef69b42826cf0998b068a43d486a9e9 change-id: 20241230-tun-66e10a49b0c7 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

5 months, 2 weeks

5
25
0 0

[PATCH net-next v4 0/9] tun: Unify vnet implementation

by Akihiko Odaki

When I implemented virtio's hash-related features to tun/tap [1], I found tun/tap does not fill the entire region reserved for the virtio header, leaving some uninitialized hole in the middle of the buffer after read()/recvmesg(). This series fills the uninitialized hole. More concretely, the num_buffers field will be initialized with 1, and the other fields will be inialized with 0. Setting the num_buffers field to 1 is mandated by virtio 1.0 [2]. The change to virtio header is preceded by another change that refactors tun and tap to unify their virtio-related code. [1]: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com [2]: https://lore.kernel.org/r/20241227084256-mutt-send-email-mst@kernel.org/ Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v4: - s/sz/vnet_hdr_len_sz/ for patch "tun: Decouple vnet handling" (Willem de Bruijn) - Reverted to add CONFIG_TUN_VNET. - Link to v3: https://lore.kernel.org/r/20250116-tun-v3-0-c6b2871e97f7@daynix.com Changes in v3: - Dropped changes to fill the vnet header. - Splitted patch "tun: Unify vnet implementation". - Reverted spurious changes in patch "tun: Unify vnet implementation". - Merged tun_vnet.c into TAP. - Link to v2: https://lore.kernel.org/r/20250109-tun-v2-0-388d7d5a287a@daynix.com Changes in v2: - Fixed num_buffers endian. - Link to v1: https://lore.kernel.org/r/20250108-tun-v1-0-67d784b34374@daynix.com --- Akihiko Odaki (9): tun: Refactor CONFIG_TUN_VNET_CROSS_LE tun: Avoid double-tracking iov_iter length changes tun: Keep hdr_len in tun_get_user() tun: Decouple vnet from tun_struct tun: Decouple vnet handling tun: Extract the vnet handling code tap: Avoid double-tracking iov_iter length changes tap: Keep hdr_len in tap_get_user() tap: Use tun's vnet-related code MAINTAINERS | 2 +- drivers/net/Kconfig | 5 ++ drivers/net/Makefile | 1 + drivers/net/tap.c | 172 ++++++------------------------------------ drivers/net/tun.c | 200 +++++++------------------------------------------ drivers/net/tun_vnet.c | 184 +++++++++++++++++++++++++++++++++++++++++++++ drivers/net/tun_vnet.h | 25 +++++++ 7 files changed, 267 insertions(+), 322 deletions(-) --- base-commit: a32e14f8aef69b42826cf0998b068a43d486a9e9 change-id: 20241230-tun-66e10a49b0c7 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

5 months, 2 weeks

2
16
0 0

[PATCH v10 00/14] riscv: Add support for xtheadvector

by Charlie Jenkins

xtheadvector is a custom extension that is based upon riscv vector version 0.7.1 [1]. All of the vector routines have been modified to support this alternative vector version based upon whether xtheadvector was determined to be supported at boot. vlenb is not supported on the existing xtheadvector hardware, so a devicetree property thead,vlenb is added to provide the vlenb to Linux. There is a new hwprobe key RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 that is used to request which thead vendor extensions are supported on the current platform. This allows future vendors to allocate hwprobe keys for their vendor. Support for xtheadvector is also added to the vector kselftests. Signed-off-by: Charlie Jenkins <charlie(a)rivosinc.com> [1] https://github.com/T-head-Semi/thead-extension-spec/blob/95358cb2cca9489361… --- This series is a continuation of a different series that was fragmented into two other series in an attempt to get part of it merged in the 6.10 merge window. The split-off series did not get merged due to a NAK on the series that added the generic riscv,vlenb devicetree entry. This series has converted riscv,vlenb to thead,vlenb to remedy this issue. The original series is titled "riscv: Support vendor extensions and xtheadvector" [3]. The series titled "riscv: Extend cpufeature.c to detect vendor extensions" is still under development and this series is based on that series! [4] I have tested this with an Allwinner Nezha board. I used SkiffOS [1] to manage building the image, but upgraded the U-Boot version to Samuel Holland's more up-to-date version [2] and changed out the device tree used by U-Boot with the device trees that are present in upstream linux and this series. Thank you Samuel for all of the work you did to make this task possible. [1] https://github.com/skiffos/SkiffOS/tree/master/configs/allwinner/nezha [2] https://github.com/smaeul/u-boot/commit/2e89b706f5c956a70c989cd31665f1429e9… [3] https://lore.kernel.org/all/20240503-dev-charlie-support_thead_vector_6_9-v… [4] https://lore.kernel.org/lkml/20240719-support_vendor_extensions-v3-4-0af758… --- Changes in v10: - In DT probing disable vector with new function to clear vendor extension bits for xtheadvector - Add ghostwrite mitigations for c9xx CPUs. This disables xtheadvector unless mitigations=off is set as a kernel boot arg - Link to v9: https://lore.kernel.org/r/20240806-xtheadvector-v9-0-62a56d2da5d0@rivosinc.… Changes in v9: - Rebase onto palmer's for-next - Fix sparse error in arch/riscv/kernel/vendor_extensions/thead.c - Fix maybe-uninitialized warning in arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h - Wrap some long lines - Link to v8: https://lore.kernel.org/r/20240724-xtheadvector-v8-0-cf043168e137@rivosinc.… Changes in v8: - Rebase onto palmer's for-next - Link to v7: https://lore.kernel.org/r/20240724-xtheadvector-v7-0-b741910ada3e@rivosinc.… Changes in v7: - Add defs for has_xtheadvector_no_alternatives() and has_xtheadvector() when vector disabled. (Palmer) - Link to v6: https://lore.kernel.org/r/20240722-xtheadvector-v6-0-c9af0130fa00@rivosinc.… Changes in v6: - Fix return type of is_vector_supported()/is_xthead_supported() to be bool - Link to v5: https://lore.kernel.org/r/20240719-xtheadvector-v5-0-4b485fc7d55f@rivosinc.… Changes in v5: - Rebase on for-next - Link to v4: https://lore.kernel.org/r/20240702-xtheadvector-v4-0-2bad6820db11@rivosinc.… Changes in v4: - Replace inline asm with C (Samuel) - Rename VCSRs to CSRs (Samuel) - Replace .insn directives with .4byte directives - Link to v3: https://lore.kernel.org/r/20240619-xtheadvector-v3-0-bff39eb9668e@rivosinc.… Changes in v3: - Add back Heiko's signed-off-by (Conor) - Mark RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 as a bitmask - Link to v2: https://lore.kernel.org/r/20240610-xtheadvector-v2-0-97a48613ad64@rivosinc.… Changes in v2: - Removed extraneous references to "riscv,vlenb" (Jess) - Moved declaration of "thead,vlenb" into cpus.yaml and added restriction that it's only applicable to thead cores (Conor) - Check CONFIG_RISCV_ISA_XTHEADVECTOR instead of CONFIG_RISCV_ISA_V for thead,vlenb (Jess) - Fix naming of hwprobe variables (Evan) - Link to v1: https://lore.kernel.org/r/20240609-xtheadvector-v1-0-3fe591d7f109@rivosinc.… --- Charlie Jenkins (13): dt-bindings: riscv: Add xtheadvector ISA extension description dt-bindings: cpus: add a thead vlen register length property riscv: dts: allwinner: Add xtheadvector to the D1/D1s devicetree riscv: Add thead and xtheadvector as a vendor extension riscv: vector: Use vlenb from DT for thead riscv: csr: Add CSR encodings for CSR_VXRM/CSR_VXSAT riscv: Add xtheadvector instruction definitions riscv: vector: Support xtheadvector save/restore riscv: hwprobe: Add thead vendor extension probing riscv: hwprobe: Document thead vendor extensions and xtheadvector extension selftests: riscv: Fix vector tests selftests: riscv: Support xtheadvector in vector tests riscv: Add ghostwrite vulnerability Heiko Stuebner (1): RISC-V: define the elements of the VCSR vector CSR Documentation/arch/riscv/hwprobe.rst | 10 + Documentation/devicetree/bindings/riscv/cpus.yaml | 19 ++ .../devicetree/bindings/riscv/extensions.yaml | 10 + arch/riscv/Kconfig.errata | 11 + arch/riscv/Kconfig.vendor | 26 ++ arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi | 3 +- arch/riscv/errata/thead/errata.c | 28 ++ arch/riscv/include/asm/bugs.h | 22 ++ arch/riscv/include/asm/cpufeature.h | 2 + arch/riscv/include/asm/csr.h | 15 + arch/riscv/include/asm/errata_list.h | 3 +- arch/riscv/include/asm/hwprobe.h | 3 +- arch/riscv/include/asm/switch_to.h | 2 +- arch/riscv/include/asm/vector.h | 225 +++++++++++---- arch/riscv/include/asm/vendor_extensions/thead.h | 48 ++++ .../include/asm/vendor_extensions/thead_hwprobe.h | 19 ++ .../include/asm/vendor_extensions/vendor_hwprobe.h | 37 +++ arch/riscv/include/uapi/asm/hwprobe.h | 3 +- arch/riscv/include/uapi/asm/vendor/thead.h | 3 + arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/bugs.c | 55 ++++ arch/riscv/kernel/cpufeature.c | 58 +++- arch/riscv/kernel/kernel_mode_vector.c | 8 +- arch/riscv/kernel/process.c | 4 +- arch/riscv/kernel/signal.c | 6 +- arch/riscv/kernel/sys_hwprobe.c | 5 + arch/riscv/kernel/vector.c | 24 +- arch/riscv/kernel/vendor_extensions.c | 10 + arch/riscv/kernel/vendor_extensions/Makefile | 2 + arch/riscv/kernel/vendor_extensions/thead.c | 29 ++ .../riscv/kernel/vendor_extensions/thead_hwprobe.c | 19 ++ drivers/base/cpu.c | 3 + include/linux/cpu.h | 1 + tools/testing/selftests/riscv/vector/.gitignore | 3 +- tools/testing/selftests/riscv/vector/Makefile | 17 +- .../selftests/riscv/vector/v_exec_initval_nolibc.c | 94 +++++++ tools/testing/selftests/riscv/vector/v_helpers.c | 68 +++++ tools/testing/selftests/riscv/vector/v_helpers.h | 8 + tools/testing/selftests/riscv/vector/v_initval.c | 22 ++ .../selftests/riscv/vector/v_initval_nolibc.c | 68 ----- .../selftests/riscv/vector/vstate_exec_nolibc.c | 20 +- .../testing/selftests/riscv/vector/vstate_prctl.c | 305 +++++++++++++-------- 42 files changed, 1048 insertions(+), 272 deletions(-) --- base-commit: 0e3f3649d44bf1b388a7613ade14c29cbdedf075 change-id: 20240530-xtheadvector-833d3d17b423 -- - Charlie

5 months, 2 weeks

9
35
0 0

[PATCH bpf-next 00/10] selftests/bpf: Migrate test_xdp_redirect_multi.sh to test_progs

by Bastien Curutchet (eBPF Foundation)

Hi all, This patch series continues the work to migrate the *.sh tests into prog_tests framework. test_xdp_redirect_multi.sh tests the XDP redirections done through bpf_redirect_map(). This is already partly covered by test_xdp_veth.c that already tests map redirections at XDP level. What isn't covered yet by test_xdp_veth is the use of the broadcast flags (BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS) and XDP egress programs. Hence, this patch series add test cases to test_xdp_veth.c to get rid of the test_xdp_redirect_multi.sh: - PATCH 1 to 5 rework test_xdp_veth to make it more generic and allow to configure different test cases - PATCH 6 adds test cases for 'classic' bpf_redirect_map() - PATCH 7 & 8 covers the broadcast flags - PATCH 9 covers the XDP egress programs - PATCH 10 removes test_xdp_redirect_multi.sh Signed-off-by: Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com> --- Bastien Curutchet (eBPF Foundation) (10): selftests/bpf: test_xdp_veth: Split network configuration selftests/bpf: Remove unused argument selftests/bpf: test_xdp_veth: Rename config[] selftests/bpf: test_xdp_veth: Add prog_config[] table selftests/bpf: test_xdp_veth: Add XDP flags to prog_configuration selftests/bpf: test_xdp_veth: Add new test cases for XDP flags selftests/bpf: Optionally select broadcasting flags selftests/bpf: test_xdp_veth: Add XDP broadcast redirection tests selftests/bpf: test_xdp_veth: Add XDP program on egress test selftests/bpf: Remove test_xdp_redirect_multi.sh tools/testing/selftests/bpf/Makefile | 2 - .../selftests/bpf/prog_tests/test_xdp_veth.c | 534 +++++++++++++++++---- .../testing/selftests/bpf/progs/xdp_redirect_map.c | 89 ++++ .../selftests/bpf/progs/xdp_redirect_multi_kern.c | 41 +- .../selftests/bpf/test_xdp_redirect_multi.sh | 214 --------- tools/testing/selftests/bpf/xdp_redirect_multi.c | 226 --------- 6 files changed, 553 insertions(+), 553 deletions(-) --- base-commit: 075d2f15ddfc67f27601c8f861dd5d3b189af401 change-id: 20250103-redirect-multi-245d6eafb5d1 Best regards, -- Bastien Curutchet (eBPF Foundation) <bastien.curutchet(a)bootlin.com>

5 months, 2 weeks

1
10
0 0

[PATCH net] Bonding: Fix support for gso_partial_features

by Hangbin Liu

The fixed commit adds NETIF_F_GSO_ESP bit for bonding gso_partial_features. However, if we don't set the dev NETIF_F_GSO_PARTIAL bit, the later netdev_change_features() -> netdev_fix_features() will remove the NETIF_F_GSO_ESP bit from the dev features. This causes ethtool to show that the bond does not support tx-esp-segmentation. For example # ethtool -k bond0 | grep esp tx-esp-segmentation: off [requested on] esp-hw-offload: on esp-tx-csum-hw-offload: on Add the NETIF_F_GSO_PARTIAL bit to bond dev features when set gso_partial_features to fix this issue. Fixes: 4861333b4217 ("bonding: add ESP offload features when slaves support") Reported-by: Liang Li <liali(a)redhat.com> Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- drivers/net/bonding/bond_main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 7b78c2bada81..e1c054416d5e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1598,10 +1598,12 @@ static void bond_compute_features(struct bonding *bond) } bond_dev->hard_header_len = max_hard_header_len; - if (gso_partial_features & NETIF_F_GSO_ESP) + if (gso_partial_features & NETIF_F_GSO_ESP) { bond_dev->gso_partial_features |= NETIF_F_GSO_ESP; - else + bond_dev->features |= NETIF_F_GSO_PARTIAL; + } else { bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP; + } done: bond_dev->vlan_features = vlan_features; -- 2.39.5 (Apple Git-154)

5 months, 2 weeks

1
1
0 0

[PATCH net-next, v6 1/2] netlink: support dumping IPv4 multicast addresses

by Yuyang Huang

Extended RTM_GETMULTICAST to support dumping joined IPv4 multicast addresses, in addition to the existing IPv6 functionality. This allows userspace applications to retrieve both IPv4 and IPv6 multicast addresses through similar netlink command and then monitor future changes by registering to RTNLGRP_IPV4_MCADDR and RTNLGRP_IPV6_MCADDR. Cc: Maciej Żenczykowski <maze(a)google.com> Cc: Lorenzo Colitti <lorenzo(a)google.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: Yuyang Huang <yuyanghuang(a)google.com> --- Changelog since v5: - Move the test case to a separate patch. - Refactor the code to remove the dependency on `enum addr_type_t type`. - Return error if `fillargs->event` is not set properly. - Return -EINVAL in an unreachable code path. Changelog since v4: - Fixes a bug where fillargs->event was not initialized in the code path for dumping ifaddr. - Fixes a bug where reply messages contain the wrong sequence number. - Minor style fixes. - Adds a ynl selftest. Changelog since v3: - Refactor in_dev_dump_addr() to break down the logic into two separate functions to simplify the logic. Changelog since v2: - Fix checkpatch.pl warnings. - Remove one redundant EXPORT_SYMBOL(). Changelog since v1: - Minor style fixes. - Use for_each_pmc_rcu() instead of for_each_pmc_rtnl(). include/linux/igmp.h | 12 +++++++ net/ipv4/devinet.c | 76 ++++++++++++++++++++++++++++++++++++-------- net/ipv4/igmp.c | 13 +++++--- 3 files changed, 83 insertions(+), 18 deletions(-) diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 073b30a9b850..47c3ab54d79e 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -92,6 +92,15 @@ struct ip_mc_list { struct rcu_head rcu; }; +struct inet_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; + int ifindex; +}; + /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ @@ -142,4 +151,7 @@ extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); +int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, + struct inet_fill_args *args); #endif diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c8b3cf5fba4c..5b561cdab31e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -107,15 +107,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_PROTO] = { .type = NLA_U8 }, }; -struct inet_fill_args { - u32 portid; - u32 seq; - int event; - unsigned int flags; - int netnsid; - int ifindex; -}; - #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) @@ -1846,9 +1837,38 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, return 0; } -static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, - struct netlink_callback *cb, int *s_ip_idx, - struct inet_fill_args *fillargs) +static int in_dev_dump_ifmcaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + struct ip_mc_list *im; + int ip_idx = 0; + int err; + + for (im = rcu_dereference(in_dev->mc_list); + im; + im = rcu_dereference(im->next_rcu)) { + if (ip_idx < *s_ip_idx) { + ip_idx++; + continue; + } + err = inet_fill_ifmcaddr(skb, in_dev->dev, im, fillargs); + if (err < 0) + goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; + } + err = 0; + ip_idx = 0; +done: + *s_ip_idx = ip_idx; + return err; +} + +static int in_dev_dump_ifaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; @@ -1874,6 +1894,21 @@ static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, return err; } +static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + switch (fillargs->event) { + case RTM_NEWADDR: + return in_dev_dump_ifaddr(in_dev, skb, cb, s_ip_idx, fillargs); + case RTM_GETMULTICAST: + return in_dev_dump_ifmcaddr(in_dev, skb, cb, s_ip_idx, + fillargs); + default: + return -EINVAL; + } +} + /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) @@ -1889,13 +1924,14 @@ static u32 inet_base_seq(const struct net *net) return res; } -static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +static int inet_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, + int event) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, - .event = RTM_NEWADDR, + .event = event, .flags = NLM_F_MULTI, .netnsid = -1, }; @@ -1949,6 +1985,16 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) return err; } +static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + return inet_dump_addr(skb, cb, RTM_NEWADDR); +} + +static int inet_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + return inet_dump_addr(skb, cb, RTM_GETMULTICAST); +} + static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { @@ -2845,6 +2891,8 @@ static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, + {.owner = THIS_MODULE, .protocol = PF_INET, .msgtype = RTM_GETMULTICAST, + .dumpit = inet_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3da126cea884..756db3ca3e34 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1432,14 +1432,16 @@ static void ip_mc_hash_remove(struct in_device *in_dev, *mc_hash = im->next_hash; } -static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, - const struct ip_mc_list *im, int event) +int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, + struct inet_fill_args *args) { struct ifa_cacheinfo ci; struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct ifaddrmsg), 0); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; @@ -1468,6 +1470,9 @@ static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, static void inet_ifmcaddr_notify(struct net_device *dev, const struct ip_mc_list *im, int event) { + struct inet_fill_args fillargs = { + .event = event, + }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; @@ -1479,7 +1484,7 @@ static void inet_ifmcaddr_notify(struct net_device *dev, if (!skb) goto error; - err = inet_fill_ifmcaddr(skb, dev, im, event); + err = inet_fill_ifmcaddr(skb, dev, im, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); -- 2.48.0.rc2.279.g1de40edade-goog

5 months, 2 weeks

2
4
0 0

[PATCH] selftests/.gitignore include missing log file

by Khaled Elnaggar

Add tpm2/AsyncTest.log to .gitignore Signed-off-by: Khaled Elnaggar <eng.khaled.elnaggar(a)gmail.com> --- Hello After running kselftests, AsyncTest.log file showed when running git status. I just added it. --- tools/testing/selftests/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore index cb24124ac5b9..87d532c08a3e 100644 --- a/tools/testing/selftests/.gitignore +++ b/tools/testing/selftests/.gitignore @@ -4,6 +4,7 @@ gpiogpio-hammer gpioinclude/ gpiolsgpio kselftest_install/ +tpm2/AsyncTest.log tpm2/SpaceTest.log # Python bytecode and cache -- 2.45.2

5 months, 2 weeks

2
1
0 0

[PATCH] selftests/mm/cow : Fix memory leak in child_vmsplice_memcmp_fn()

by liuye

Release memory before exception branch returns to prevent memory leaks. Signed-off-by: liuye <liuye(a)kylinos.cn> --- tools/testing/selftests/mm/cow.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 1238e1c5aae1..959327ba6258 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -167,19 +167,30 @@ static int child_vmsplice_memcmp_fn(char *mem, size_t size, /* Backup the original content. */ memcpy(old, mem, size); - if (pipe(fds) < 0) + if (pipe(fds) < 0) { + free(old); + free(new); return -errno; - + } /* Trigger a read-only pin. */ transferred = vmsplice(fds[1], &iov, 1, 0); - if (transferred < 0) + if (transferred < 0) { + free(old); + free(new); return -errno; - if (transferred == 0) + } + if (transferred == 0) { + free(old); + free(new); return -EINVAL; + } /* Unmap it from our page tables. */ - if (munmap(mem, size) < 0) + if (munmap(mem, size) < 0) { + free(old); + free(new); return -errno; + } /* Wait until the parent modified it. */ write(comm_pipes->child_ready[1], "0", 1); -- 2.25.1

5 months, 2 weeks

2
3
0 0

[PATCH net V3] selftests/net/ipsec: Fix Null pointer dereference in rtattr_pack()

by Liu Ye

From: Liu Ye <liuye(a)kylinos.cn> Address Null pointer dereference in rtattr_pack. Flagged by cppcheck as: tools/testing/selftests/net/ipsec.c:230:25: warning: Possible null pointer dereference: payload [nullPointer] memcpy(RTA_DATA(attr), payload, size); ^ tools/testing/selftests/net/ipsec.c:1618:54: note: Calling function 'rtattr_pack', 4th argument 'NULL' value is 0 if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) { ^ tools/testing/selftests/net/ipsec.c:230:25: note: Null pointer dereference memcpy(RTA_DATA(attr), payload, size); ^ Fixes: 70bfdf62e93a ("selftests/net/ipsec: Add test for xfrm_spdattr_type_t") Signed-off-by: Liu Ye <liuye(a)kylinos.cn> --- V3: Remove the redundant from. Sign-off after fixes. V2: Modify description. Add code checking tools. Separating family and given name in Signed-off-by line. Modify code format. Add fixes. --- --- tools/testing/selftests/net/ipsec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index be4a30a0d02a..9b44a091802c 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -227,7 +227,8 @@ static int rtattr_pack(struct nlmsghdr *nh, size_t req_sz, attr->rta_len = RTA_LENGTH(size); attr->rta_type = rta_type; - memcpy(RTA_DATA(attr), payload, size); + if (payload) + memcpy(RTA_DATA(attr), payload, size); return 0; } -- 2.25.1

5 months, 2 weeks

2
1
0 0

[PATCH RFC v3 00/10] extensible syscalls: CHECK_FIELDS to allow for easier feature detection

by Aleksa Sarai

This is something that I've been thinking about for a while. We had a discussion at LPC 2020 about this[1] but the proposals suggested there never materialised. In short, it is quite difficult for userspace to detect the feature capability of syscalls at runtime. This is something a lot of programs want to do, but they are forced to create elaborate scenarios to try to figure out if a feature is supported without causing damage to the system. For the vast majority of cases, each individual feature also needs to be tested individually (because syscall results are all-or-nothing), so testing even a single syscall's feature set can easily inflate the startup time of programs. This patchset implements the fairly minimal design I proposed in this talk[2] and in some old LKML threads (though I can't find the exact references ATM). The general flow looks like: 1. Userspace will indicate to the kernel that a syscall should a be no-op by setting the top bit of the extensible struct size argument. We will almost certainly never support exabyte sized structs, so the top bits are free for us to use as makeshift flag bits. This is preferable to using the per-syscall flag field inside the structure because seccomp can easily detect the bit in the flag and allow the probe or forcefully return -EEXTSYS_NOOP. 2. The kernel will then fill the provided structure with every valid bit pattern that the current kernel understands. For flags or other bitflag-like fields, this is the set of valid flags or bits. For pointer fields or fields that take an arbitrary value, the field has every bit set (0xFF... to fill the field) to indicate that any value is valid in the field. 3. The syscall then returns -EEXTSYS_NOOP which is an errno that will only ever be used for this purpose (so userspace can be sure that the request succeeded). On older kernels, the syscall will return a different error (usually -E2BIG or -EFAULT) and userspace can do their old-fashioned checks. 4. Userspace can then check which flags and fields are supported by looking at the fields in the returned structure. Flags are checked by doing an AND with the flags field, and field support can checked by comparing to 0. In principle you could just AND the entire structure if you wanted to do this check generically without caring about the structure contents (this is what libraries might consider doing). Userspace can even find out the internal kernel structure size by passing a PAGE_SIZE buffer and seeing how many bytes are non-zero. As with copy_struct_from_user(), this is designed to be forward- and backwards- compatible. This allows programas to get a one-shot understanding of what features a syscall supports without having to do any elaborate setups or tricks to detect support for destructive features. Flags can simply be ANDed to check if they are in the supported set, and fields can just be checked to see if they are non-zero. This patchset is IMHO the simplest way we can add the ability to introspect the feature set of extensible struct (copy_struct_from_user) syscalls. It doesn't preclude the chance of a more generic mechanism being added later. The intended way of using this interface to get feature information looks something like the following (imagine that openat2 has gained a new field and a new flag in the future): static bool openat2_no_automount_supported; static bool openat2_cwd_fd_supported; int check_openat2_support(void) { int err; struct open_how how = {}; err = openat2(AT_FDCWD, ".", &how, CHECK_FIELDS | sizeof(how)); assert(err < 0); switch (errno) { case EFAULT: case E2BIG: /* Old kernel... */ check_support_the_old_way(); break; case EEXTSYS_NOOP: openat2_no_automount_supported = (how.flags & RESOLVE_NO_AUTOMOUNT); openat2_cwd_fd_supported = (how.cwd_fd != 0); break; } } This series adds CHECK_FIELDS support for the following extensible struct syscalls, as they are quite likely to grow flags in the near future: * openat2 * clone3 * mount_setattr [1]: https://lwn.net/Articles/830666/ [2]: https://youtu.be/ggD-eb3yPVs Signed-off-by: Aleksa Sarai <cyphar(a)cyphar.com> --- Changes in v3: - Fix copy_struct_to_user() return values in case of clear_user() failure. - v2: <https://lore.kernel.org/r/20240906-extensible-structs-check_fields-v2-0-0f4…> Changes in v2: - Add CHECK_FIELDS support to mount_setattr(2). - Fix build failure on architectures with custom errno values. - Rework selftests to use the tools/ uAPI headers rather than custom defining EEXTSYS_NOOP. - Make sure we return -EINVAL and -E2BIG for invalid sizes even if CHECK_FIELDS is set, and add some tests for that. - v1: <https://lore.kernel.org/r/20240902-extensible-structs-check_fields-v1-0-545…> --- Aleksa Sarai (10): uaccess: add copy_struct_to_user helper sched_getattr: port to copy_struct_to_user openat2: explicitly return -E2BIG for (usize > PAGE_SIZE) openat2: add CHECK_FIELDS flag to usize argument selftests: openat2: add 0xFF poisoned data after misaligned struct selftests: openat2: add CHECK_FIELDS selftests clone3: add CHECK_FIELDS flag to usize argument selftests: clone3: add CHECK_FIELDS selftests mount_setattr: add CHECK_FIELDS flag to usize argument selftests: mount_setattr: add CHECK_FIELDS selftest arch/alpha/include/uapi/asm/errno.h | 3 + arch/mips/include/uapi/asm/errno.h | 3 + arch/parisc/include/uapi/asm/errno.h | 3 + arch/sparc/include/uapi/asm/errno.h | 3 + fs/namespace.c | 17 ++ fs/open.c | 18 ++ include/linux/uaccess.h | 97 ++++++++ include/uapi/asm-generic/errno.h | 3 + include/uapi/linux/openat2.h | 2 + kernel/fork.c | 30 ++- kernel/sched/syscalls.c | 42 +--- tools/arch/alpha/include/uapi/asm/errno.h | 3 + tools/arch/mips/include/uapi/asm/errno.h | 3 + tools/arch/parisc/include/uapi/asm/errno.h | 3 + tools/arch/sparc/include/uapi/asm/errno.h | 3 + tools/include/uapi/asm-generic/errno.h | 3 + tools/include/uapi/asm-generic/posix_types.h | 101 ++++++++ tools/testing/selftests/clone3/.gitignore | 1 + tools/testing/selftests/clone3/Makefile | 4 +- .../testing/selftests/clone3/clone3_check_fields.c | 264 +++++++++++++++++++++ tools/testing/selftests/mount_setattr/Makefile | 2 +- .../selftests/mount_setattr/mount_setattr_test.c | 53 ++++- tools/testing/selftests/openat2/Makefile | 2 + tools/testing/selftests/openat2/openat2_test.c | 165 ++++++++++++- 24 files changed, 777 insertions(+), 51 deletions(-) --- base-commit: 98f7e32f20d28ec452afb208f9cffc08448a2652 change-id: 20240803-extensible-structs-check_fields-a47e94cef691 Best regards, -- Aleksa Sarai <cyphar(a)cyphar.com>

5 months, 2 weeks

6
21
0 0

[PATCH] selftests/capabilities/test_execve: Initialize the variable have_outer_privilege

by liuye

Uninitialized variable: have_outer_privilege. Fix it. Signed-off-by: liuye <liuye(a)kylinos.cn> --- tools/testing/selftests/capabilities/test_execve.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c index 47bad7ddc5bc..c9617b38d6f7 100644 --- a/tools/testing/selftests/capabilities/test_execve.c +++ b/tools/testing/selftests/capabilities/test_execve.c @@ -83,7 +83,7 @@ static bool create_and_enter_ns(uid_t inner_uid) uid_t outer_uid; gid_t outer_gid; int i, ret; - bool have_outer_privilege; + bool have_outer_privilege = false; outer_uid = getuid(); outer_gid = getgid(); -- 2.25.1

5 months, 2 weeks

2
1
0 0

[PATCH v2 0/3] tun: Unify vnet implementation and fill full vnet header

by Akihiko Odaki

When I implemented virtio's hash-related features to tun/tap [1], I found tun/tap does not fill the entire region reserved for the virtio header, leaving some uninitialized hole in the middle of the buffer after read()/recvmesg(). This series fills the uninitialized hole. More concretely, the num_buffers field will be initialized with 1, and the other fields will be inialized with 0. Setting the num_buffers field to 1 is mandated by virtio 1.0 [2]. The change to virtio header is preceded by another change that refactors tun and tap to unify their virtio-related code. [1]: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com [2]: https://lore.kernel.org/r/20241227084256-mutt-send-email-mst@kernel.org/ Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v2: - Fixed num_buffers endian. - Link to v1: https://lore.kernel.org/r/20250108-tun-v1-0-67d784b34374@daynix.com --- Akihiko Odaki (3): tun: Unify vnet implementation tun: Pad virtio header with zero tun: Set num_buffers for virtio 1.0 MAINTAINERS | 1 + drivers/net/Kconfig | 5 ++ drivers/net/Makefile | 1 + drivers/net/tap.c | 174 ++++++---------------------------------- drivers/net/tun.c | 214 +++++++++---------------------------------------- drivers/net/tun_vnet.c | 191 +++++++++++++++++++++++++++++++++++++++++++ drivers/net/tun_vnet.h | 24 ++++++ 7 files changed, 283 insertions(+), 327 deletions(-) --- base-commit: a32e14f8aef69b42826cf0998b068a43d486a9e9 change-id: 20241230-tun-66e10a49b0c7 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

5 months, 2 weeks

5
35
0 0

[PATCH 0/1] selftests: Clear -Wimplicit-function-declaration warnings

by Ariel Otilibili

Hello, This patch clears out warnings seen while compiling the tests; at the time, it closes a test report. Thank you, Link: https://lore.kernel.org/oe-kbuild-all/202412222015.lMBH62zB-lkp@intel.com/ Ariel Otilibili (1): selftests: Clear -Wimplicit-function-declaration warnings tools/testing/selftests/pid_namespace/pid_max.c | 1 + tools/testing/selftests/pidfd/pidfd_fdinfo_test.c | 1 + 2 files changed, 2 insertions(+) -- 2.43.0

5 months, 2 weeks

2
2
0 0

[PATCH net-next] selftests: net: give up on the cmsg_time accuracy on slow machines

by Jakub Kicinski

Commit b9d5f5711dd8 ("selftests: net: increase the delay for relative cmsg_time.sh test") widened the accepted value range 8x but we still see flakes (at a rate of around 7%). Return XFAIL for the most timing sensitive test on slow machines. Before: # ./cmsg_time.sh Case UDPv4 - TXTIME rel returned '8074us - 7397us < 4000', expected 'OK' FAIL - 1/36 cases failed After: # ./cmsg_time.sh Case UDPv4 - TXTIME rel returned '1123us - 941us < 500', expected 'OK' (XFAIL) Case UDPv6 - TXTIME rel returned '1227us - 776us < 500', expected 'OK' (XFAIL) OK Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org CC: willemdebruijn.kernel(a)gmail.com --- tools/testing/selftests/net/cmsg_time.sh | 35 +++++++++++++++++------- 1 file changed, 25 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh index 1d7e756644bc..478af0aefa97 100755 --- a/tools/testing/selftests/net/cmsg_time.sh +++ b/tools/testing/selftests/net/cmsg_time.sh @@ -34,13 +34,28 @@ BAD=0 TOTAL=0 check_result() { + local ret=$1 + local got=$2 + local exp=$3 + local case=$4 + local xfail=$5 + local xf= + local inc= + + if [ "$xfail" == "xfail" ]; then + xf="(XFAIL)" + inc=0 + else + inc=1 + fi + ((TOTAL++)) - if [ $1 -ne 0 ]; then - echo " Case $4 returned $1, expected 0" - ((BAD++)) + if [ $ret -ne 0 ]; then + echo " Case $case returned $ret, expected 0 $xf" + ((BAD+=inc)) elif [ "$2" != "$3" ]; then - echo " Case $4 returned '$2', expected '$3'" - ((BAD++)) + echo " Case $case returned '$got', expected '$exp' $xf" + ((BAD+=inc)) fi } @@ -66,14 +81,14 @@ for i in "-4 $TGT4" "-6 $TGT6"; do awk '/SND/ { if ($3 > 1000) print "OK"; }') check_result $? "$ts" "OK" "$prot - TXTIME abs" - [ "$KSFT_MACHINE_SLOW" = yes ] && delay=8000 || delay=1000 + [ "$KSFT_MACHINE_SLOW" = yes ] && xfail=xfail - ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d $delay | + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | awk '/SND/ {snd=$3} /SCHED/ {sch=$3} - END { if (snd - sch > '$((delay/2))') print "OK"; - else print snd, "-", sch, "<", '$((delay/2))'; }') - check_result $? "$ts" "OK" "$prot - TXTIME rel" + END { if (snd - sch > 500) print "OK"; + else print snd, "-", sch, "<", 500; }') + check_result $? "$ts" "OK" "$prot - TXTIME rel" $xfail done done -- 2.48.0

5 months, 2 weeks

5
6
0 0

[for-next][PATCH 3/3] selftests/ftrace: Add test that tests event :mod: commands

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Now that here's a :mod: command that can be sent into set_event, add a test that tests its use. Both setting events for a loaded module, as well as caching what events to set for a module that is not loaded yet. Cc: Shuah Khan <shuah(a)kernel.org> Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: linux-kselftest(a)vger.kernel.org Link: https://lore.kernel.org/20250116143533.819228058@goodmis.org Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- .../ftrace/test.d/event/event-mod.tc | 191 ++++++++++++++++++ 1 file changed, 191 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/event/event-mod.tc diff --git a/tools/testing/selftests/ftrace/test.d/event/event-mod.tc b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc new file mode 100644 index 000000000000..175243cd9ab7 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc @@ -0,0 +1,191 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event tracing - enable/disable with module event +# requires: set_event "Can enable module events via: :mod:":README +# flags: instance + +rmmod trace-events-sample ||: +if ! modprobe trace-events-sample ; then + echo "No trace-events sample module - please make CONFIG_SAMPLE_TRACE_EVENTS=m" + exit_unresolved; +fi +trap "rmmod trace-events-sample" EXIT + +# Set events for the module +echo ":mod:trace-events-sample" > set_event + +test_all_enabled() { + + # Check if more than one is enabled + grep -q sample-trace:foo_bar set_event + grep -q sample-trace:foo_bar_with_cond set_event + grep -q sample-trace:foo_bar_with_fn set_event + + # All of them should be enabled. Check via the enable file + val=`cat events/sample-trace/enable` + if [ $val -ne 1 ]; then + exit_fail + fi +} + +clear_events() { + echo > set_event + val=`cat events/enable` + if [ "$val" != "0" ]; then + exit_fail + fi + count=`cat set_event | wc -l` + if [ $count -ne 0 ]; then + exit_fail + fi +} + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo And the set_event file is empty + +cnt=`wc -l set_event` +if [ $cnt -ne 0 ]; then + exit_fail +fi + +echo now enable all events +echo 1 > events/enable + +echo Confirm the events are enabled again +val=`cat events/sample-trace/enable` +if [ $val -ne 1 ]; then + exit_fail +fi + +echo disable just the module events +echo '!:mod:trace-events-sample' >> set_event + +echo Should have mix of events enabled +val=`cat events/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +echo Confirm the module events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo 0 > events/enable + +echo now enable the system events +echo 'sample-trace:mod:trace-events-sample' > set_event + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo Test enabling foo_bar only +echo 'foo_bar:mod:trace-events-sample' > set_event + +grep -q sample-trace:foo_bar set_event + +echo make sure nothing is found besides foo_bar +if grep -q -v sample-trace:foo_bar set_event ; then + exit_fail +fi + +echo Append another using the system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event + +grep -q sample-trace:foo_bar set_event +grep -q sample-trace:foo_bar_with_cond set_event + +count=`cat set_event | wc -l` + +if [ $count -ne 2 ]; then + exit_fail +fi + +clear_events + +rmmod trace-events-sample + +echo ':mod:trace-events-sample' > set_event + +echo make sure that the module shows up, and '-' is converted to '_' +grep -q '\*:\*:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable just the system events +echo 'sample-trace:mod:trace-events-sample' > set_event +grep -q 'sample-trace:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable event with just event name +echo 'foo_bar:mod:trace-events-sample' > set_event +grep -q 'foo_bar:mod:trace_events_sample' set_event + +echo Enable another event with both system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event +grep -q 'sample-trace:foo_bar_with_cond:mod:trace_events_sample' set_event +echo Make sure the other event was still there +grep -q 'foo_bar:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +echo There should be no :mod: cached events +if grep -q ':mod:' set_event; then + exit_fail +fi + +echo two events should be enabled +count=`cat set_event | wc -l` +if [ $count -ne 2 ]; then + exit_fail +fi + +echo only two events should be enabled +val=`cat events/sample-trace/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar_with_cond/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +clear_trace -- 2.45.2

5 months, 2 weeks

1
0
0 0

[PATCH v1 1/3] selftests: pidfd: add missing sys/mount.h include in pidfd_fdinfo_test.c

by Peter Seiderer

Fix compile on openSUSE Tumbleweed (gcc-14.2.1, glibc-2.40): - add missing sys/mount.h include Fixes: pidfd_fdinfo_test.c: In function ‘child_fdinfo_nspid_test’: pidfd_fdinfo_test.c:230:13: error: implicit declaration of function ‘mount’ [-Wimplicit-function-declaration] 230 | r = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); | ^~~~~ Signed-off-by: Peter Seiderer <ps.report(a)gmx.net> --- tools/testing/selftests/pidfd/pidfd_fdinfo_test.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index f062a986e382..f718aac75068 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -13,6 +13,7 @@ #include <syscall.h> #include <sys/wait.h> #include <sys/mman.h> +#include <sys/mount.h> #include "pidfd.h" #include "../kselftest.h" -- 2.47.1

5 months, 2 weeks

1
1
0 0

[PATCH] selftests: livepatch: handle PRINTK_CALLER in check_result()

by Madhavan Srinivasan

Some arch configs (like ppc64) enable CONFIG_PRINTK_CALLER, which adds the caller id as part of the dmesg. Due to this, even though the expected vs observed are same, end testcase results are failed. -% insmod test_modules/test_klp_livepatch.ko -livepatch: enabling patch 'test_klp_livepatch' -livepatch: 'test_klp_livepatch': initializing patching transition -livepatch: 'test_klp_livepatch': starting patching transition -livepatch: 'test_klp_livepatch': completing patching transition -livepatch: 'test_klp_livepatch': patching complete -% echo 0 > /sys/kernel/livepatch/test_klp_livepatch/enabled -livepatch: 'test_klp_livepatch': initializing unpatching transition -livepatch: 'test_klp_livepatch': starting unpatching transition -livepatch: 'test_klp_livepatch': completing unpatching transition -livepatch: 'test_klp_livepatch': unpatching complete -% rmmod test_klp_livepatch +[ T3659] % insmod test_modules/test_klp_livepatch.ko +[ T3682] livepatch: enabling patch 'test_klp_livepatch' +[ T3682] livepatch: 'test_klp_livepatch': initializing patching transition +[ T3682] livepatch: 'test_klp_livepatch': starting patching transition +[ T826] livepatch: 'test_klp_livepatch': completing patching transition +[ T826] livepatch: 'test_klp_livepatch': patching complete +[ T3659] % echo 0 > /sys/kernel/livepatch/test_klp_livepatch/enabled +[ T3659] livepatch: 'test_klp_livepatch': initializing unpatching transition +[ T3659] livepatch: 'test_klp_livepatch': starting unpatching transition +[ T789] livepatch: 'test_klp_livepatch': completing unpatching transition +[ T789] livepatch: 'test_klp_livepatch': unpatching complete +[ T3659] % rmmod test_klp_livepatch ERROR: livepatch kselftest(s) failed not ok 1 selftests: livepatch: test-livepatch.sh # exit=1 Currently the check_result() handles the "[time]" removal from the dmesg. Enhance the check to handle removal of "[Tid]" also. Signed-off-by: Madhavan Srinivasan <maddy(a)linux.ibm.com> --- tools/testing/selftests/livepatch/functions.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index e5d06fb40233..a1730c1864a4 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -306,7 +306,8 @@ function check_result { result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \ grep -e 'livepatch:' -e 'test_klp' | \ grep -v '$tainting\|taints$ kernel' | \ - sed 's/^\[[ 0-9.]*\] //') + sed 's/^\[[ 0-9.]*\] //' | \ + sed 's/^\[[ ]*T[0-9]*\] //') if [[ "$expect" == "$result" ]] ; then echo "ok" -- 2.47.0

5 months, 2 weeks

4
6
0 0

[PATCH v1] selftests/landlock: Fix build with non-default pthread linking

by Mickaël Salaün

Old toolchains require explicit -lpthread (e.g. on Debian 11). Cc: Günther Noack <gnoack(a)google.com> Cc: Nathan Chancellor <nathan(a)kernel.org> Cc: Tahera Fahimi <fahimitahera(a)gmail.com> Fixes: c8994965013e ("selftests/landlock: Test signal scoping for threads") Signed-off-by: Mickaël Salaün <mic(a)digikod.net> --- tools/testing/selftests/landlock/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 348e2dbdb4e0..480f13e77fcc 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -13,11 +13,11 @@ TEST_GEN_PROGS := $(src_test:.c=) TEST_GEN_PROGS_EXTENDED := true # Short targets: -$(TEST_GEN_PROGS): LDLIBS += -lcap +$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static include ../lib.mk # Targets with $(OUTPUT)/ prefix: -$(TEST_GEN_PROGS): LDLIBS += -lcap +$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static -- 2.48.1

5 months, 2 weeks

2
1
0 0

[PATCH net-next] selftests/net: packetdrill: make tcp buf limited timing tests benign

by Jakub Kicinski

The following tests are failing on debug kernels: tcp_tcp_info_tcp-info-rwnd-limited.pkt tcp_tcp_info_tcp-info-sndbuf-limited.pkt with reports like: assert 19000 <= tcpi_sndbuf_limited <= 21000, tcpi_sndbuf_limited; \ AssertionError: 18000 and: assert 348000 <= tcpi_busy_time <= 360000, tcpi_busy_time AssertionError: 362000 Extend commit 912d6f669725 ("selftests/net: packetdrill: report benign debug flakes as xfail") to cover them. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: willemb(a)google.com CC: matttbe(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/packetdrill/ksft_runner.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index ff989c325eef..e15c43b7359b 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -43,6 +43,7 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" "tcp_zerocopy_epoll_.*.pkt" + "tcp_tcp_info_tcp-info-*-limited.pkt" ) readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail -- 2.48.0

5 months, 2 weeks

4
4
0 0

[PATCH net-next, v5] netlink: support dumping IPv4 multicast addresses

by Yuyang Huang

Extended RTM_GETMULTICAST to support dumping joined IPv4 multicast addresses, in addition to the existing IPv6 functionality. This allows userspace applications to retrieve both IPv4 and IPv6 multicast addresses through similar netlink command and then monitor future changes by registering to RTNLGRP_IPV4_MCADDR and RTNLGRP_IPV6_MCADDR. This change includes a new ynl based selftest case. To run the test, execute the following command: $ vng -v --user root --cpus 16 -- \ make -C tools/testing/selftests TARGETS=net \ TEST_PROGS=rtnetlink.py TEST_GEN_PROGS="" run_tests Cc: Maciej Żenczykowski <maze(a)google.com> Cc: Lorenzo Colitti <lorenzo(a)google.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Signed-off-by: Yuyang Huang <yuyanghuang(a)google.com> --- Changelog since v4: - Fixes a bug where fillargs->event was not initialized in the code path for dumping ifaddr. - Fixes a bug where reply messages contain the wrong sequence number. - Minor style fixes. - Adds a ynl selftest. Changelog since v3: - Refactor in_dev_dump_addr() to break down the logic into two separate functions to simplify the logic. Changelog since v2: - Fix checkpatch.pl warnings. - Remove one redundant EXPORT_SYMBOL(). Changelog since v1: - Minor style fixes. - Use for_each_pmc_rcu() instead of for_each_pmc_rtnl(). Documentation/netlink/specs/rt_link.yaml | 70 ++++++++++++++++++++ include/linux/igmp.h | 14 ++++ net/ipv4/devinet.c | 82 ++++++++++++++++++++---- net/ipv4/igmp.c | 13 ++-- tools/testing/selftests/net/Makefile | 1 + tools/testing/selftests/net/rtnetlink.py | 30 +++++++++ 6 files changed, 192 insertions(+), 18 deletions(-) create mode 100755 tools/testing/selftests/net/rtnetlink.py diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index 0d492500c7e5..7dcd5fddac9d 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -92,6 +92,41 @@ definitions: - name: ifi-change type: u32 + - + name: ifaddrmsg + type: struct + members: + - + name: ifa-family + type: u8 + - + name: ifa-prefixlen + type: u8 + - + name: ifa-flags + type: u8 + - + name: ifa-scope + type: u8 + - + name: ifa-index + type: u32 + - + name: ifacacheinfo + type: struct + members: + - + name: ifa-prefered + type: u32 + - + name: ifa-valid + type: u32 + - + name: cstamp + type: u32 + - + name: tstamp + type: u32 - name: ifla-bridge-id type: struct @@ -2253,6 +2288,18 @@ attribute-sets: - name: tailroom type: u16 + - + name: ifmcaddr-attrs + attributes: + - + name: addr + type: binary + value: 7 + - + name: cacheinfo + type: binary + struct: ifacacheinfo + value: 6 sub-messages: - @@ -2493,6 +2540,29 @@ operations: reply: value: 92 attributes: *link-stats-attrs + - + name: getmaddrs + doc: Get / dump IPv4/IPv6 multicast addresses. + attribute-set: ifmcaddr-attrs + fixed-header: ifaddrmsg + do: + request: + value: 58 + attributes: + - ifa-family + - ifa-index + reply: + value: 58 + attributes: &mcaddr-attrs + - addr + - cacheinfo + dump: + request: + value: 58 + - ifa-family + reply: + value: 58 + attributes: *mcaddr-attrs mcast-groups: list: diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 073b30a9b850..a460e1ef0524 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -16,6 +16,7 @@ #include <linux/ip.h> #include <linux/refcount.h> #include <linux/sockptr.h> +#include <net/addrconf.h> #include <uapi/linux/igmp.h> static inline struct igmphdr *igmp_hdr(const struct sk_buff *skb) @@ -92,6 +93,16 @@ struct ip_mc_list { struct rcu_head rcu; }; +struct inet_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; + int ifindex; + enum addr_type_t type; +}; + /* V3 exponential field decoding */ #define IGMPV3_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) #define IGMPV3_EXP(thresh, nbmant, nbexp, value) \ @@ -142,4 +153,7 @@ extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); +int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, + struct inet_fill_args *args); #endif diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c8b3cf5fba4c..d90b2442e17b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -107,15 +107,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_PROTO] = { .type = NLA_U8 }, }; -struct inet_fill_args { - u32 portid; - u32 seq; - int event; - unsigned int flags; - int netnsid; - int ifindex; -}; - #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) @@ -1846,9 +1837,38 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, return 0; } -static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, - struct netlink_callback *cb, int *s_ip_idx, - struct inet_fill_args *fillargs) +static int in_dev_dump_ifmcaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + struct ip_mc_list *im; + int ip_idx = 0; + int err; + + for (im = rcu_dereference(in_dev->mc_list); + im; + im = rcu_dereference(im->next_rcu)) { + if (ip_idx < *s_ip_idx) { + ip_idx++; + continue; + } + err = inet_fill_ifmcaddr(skb, in_dev->dev, im, fillargs); + if (err < 0) + goto done; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; + } + err = 0; + ip_idx = 0; +done: + *s_ip_idx = ip_idx; + return err; +} + +static int in_dev_dump_ifaddr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) { struct in_ifaddr *ifa; int ip_idx = 0; @@ -1874,6 +1894,23 @@ static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, return err; } +static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, + struct inet_fill_args *fillargs) +{ + switch (fillargs->type) { + case UNICAST_ADDR: + fillargs->event = RTM_NEWADDR; + return in_dev_dump_ifaddr(in_dev, skb, cb, s_ip_idx, fillargs); + case MULTICAST_ADDR: + fillargs->event = RTM_GETMULTICAST; + return in_dev_dump_ifmcaddr(in_dev, skb, cb, s_ip_idx, + fillargs); + default: + return 0; + } +} + /* Combine dev_addr_genid and dev_base_seq to detect changes. */ static u32 inet_base_seq(const struct net *net) @@ -1889,15 +1926,16 @@ static u32 inet_base_seq(const struct net *net) return res; } -static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +static int inet_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, + enum addr_type_t type) { const struct nlmsghdr *nlh = cb->nlh; struct inet_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = nlh->nlmsg_seq, - .event = RTM_NEWADDR, .flags = NLM_F_MULTI, .netnsid = -1, + .type = type, }; struct net *net = sock_net(skb->sk); struct net *tgt_net = net; @@ -1949,6 +1987,20 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) return err; } +static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + enum addr_type_t type = UNICAST_ADDR; + + return inet_dump_addr(skb, cb, type); +} + +static int inet_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb) +{ + enum addr_type_t type = MULTICAST_ADDR; + + return inet_dump_addr(skb, cb, type); +} + static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { @@ -2845,6 +2897,8 @@ static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_GETNETCONF, .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, + {.owner = THIS_MODULE, .protocol = PF_INET, .msgtype = RTM_GETMULTICAST, + .dumpit = inet_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; void __init devinet_init(void) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3da126cea884..756db3ca3e34 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1432,14 +1432,16 @@ static void ip_mc_hash_remove(struct in_device *in_dev, *mc_hash = im->next_hash; } -static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, - const struct ip_mc_list *im, int event) +int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, + const struct ip_mc_list *im, + struct inet_fill_args *args) { struct ifa_cacheinfo ci; struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct ifaddrmsg), 0); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; @@ -1468,6 +1470,9 @@ static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, static void inet_ifmcaddr_notify(struct net_device *dev, const struct ip_mc_list *im, int event) { + struct inet_fill_args fillargs = { + .event = event, + }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; @@ -1479,7 +1484,7 @@ static void inet_ifmcaddr_notify(struct net_device *dev, if (!skb) goto error; - err = inet_fill_ifmcaddr(skb, dev, im, event); + err = inet_fill_ifmcaddr(skb, dev, im, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 73ee88d6b043..e2f03211f9b3 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -36,6 +36,7 @@ TEST_PROGS += cmsg_so_priority.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += netns-name.sh TEST_PROGS += nl_netdev.py +TEST_PROGS += rtnetlink.py TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py new file mode 100755 index 000000000000..9b9dfbe4dd7b --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink.py @@ -0,0 +1,30 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +from lib.py import ksft_exit, ksft_run, ksft_ge, RtnlFamily +import socket + +IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01' + +def dump_mcaddr_check(rtnl: RtnlFamily) -> None: + """ + Verify that at least one interface has the IPv4 all-hosts multicast address. + At least the loopback interface should have this address. + """ + + addresses = rtnl.getmaddrs({"ifa-family": socket.AF_INET}, dump=True) + + all_host_multicasts = [ + addr for addr in addresses if addr['addr'] == IPV4_ALL_HOSTS_MULTICAST + ] + + ksft_ge(len(all_host_multicasts), 1, + "No interface found with the IPv4 all-hosts multicast address") + +def main() -> None: + rtnl = RtnlFamily() + ksft_run([dump_mcaddr_check], args=(rtnl, )) + ksft_exit() + +if __name__ == "__main__": + main() -- 2.48.0.rc2.279.g1de40edade-goog

5 months, 2 weeks

2
4
0 0

[bug report] selftests: ALSA: Cover userspace-driven timers with test

by Dan Carpenter

Hello Ivan Orlov, Commit 1026392d10af ("selftests: ALSA: Cover userspace-driven timers with test") from Aug 13, 2024 (linux-next), leads to the following Smatch static checker warning: tools/testing/selftests/alsa/utimer-test.c:135 timer_f_utimer() error: uninitialized symbol 'ticking_thread'. tools/testing/selftests/alsa/utimer-test.c 106 TEST_F(timer_f, utimer) { 107 char command[64]; 108 pthread_t ticking_thread; 109 int total_ticks = 0; 110 FILE *rfp; 111 char *buf = malloc(TIMER_OUTPUT_BUF_LEN); 112 113 ASSERT_NE(buf, NULL); 114 115 /* The timeout should be the ticks interval * count of ticks + some delta */ 116 sprintf(command, "./global-timer %d %d %d", SNDRV_TIMER_GLOBAL_UDRIVEN, 117 self->utimer_info->id, TICKS_COUNT * TIMER_FREQ_SEC + TICKS_RECORDING_DELTA); 118 119 rfp = popen(command, "r"); 120 while (fgets(buf, TIMER_OUTPUT_BUF_LEN, rfp)) { 121 buf[TIMER_OUTPUT_BUF_LEN - 1] = 0; 122 switch (parse_timer_output(buf)) { 123 case TIMER_APP_STARTED: 124 /* global-timer waits for timer to trigger, so start the ticking thread */ 125 pthread_create(&ticking_thread, NULL, ticking_func, ^^^^^^^^^^^^^^ ticking_thread is only initialized here, not on other paths. 126 &self->utimer_info->fd); 127 break; 128 case TIMER_APP_RESULT: 129 total_ticks = parse_timer_result(buf); 130 break; 131 case TIMER_NO_EVENT: 132 break; 133 } 134 } 135 pthread_join(ticking_thread, NULL); ^^^^^^^^^^^^^^ uninitialized. 136 ASSERT_EQ(total_ticks, TICKS_COUNT); 137 pclose(rfp); 138 } regards, dan carpenter

5 months, 2 weeks

1
0
0 0

[PATCH net-next 0/1] selftests: drv-net-hw: fix pp_alloc_fail test error

by John Daley

The tool pp_alloc_fail.py tested error recovery by injecting errors into page_pool_alloc_pages(). Perhaps due to the netmems conversion, page_pool_put_full_page() does not end up calling that function. page_pool_alloc_netmems() seems to be the base function for all the the allocation functions in the API call, so put the error injection there instead. Signed-off-by: John Daley <johndale(a)cisco.com> John Daley (1): page_pool: inject pp_alloc_fail errors in the right place net/core/page_pool.c | 2 +- tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) -- 2.44.0

5 months, 2 weeks

2
2
0 0

[PATCH 0/3] Fix test_bpf_syscall_macro selftest on powerpc

by Saket Kumar Bhaskar

Since, syscall wrapper is supported on powerpc with syscall entry symbols as sys_*, changes done to fix selftests like test_bpf_syscall_macro, attach_probe/auto, etc. Saket Kumar Bhaskar (3): libbpf: Fix accessing the syscall argument on powerpc libbpf: Remove powerpc prefix from syscall function names selftests/bpf: Define SYS_PREFIX for powerpc tools/lib/bpf/bpf_tracing.h | 9 +++++++-- tools/lib/bpf/libbpf.c | 10 ++++++++-- tools/testing/selftests/bpf/progs/bpf_misc.h | 3 +++ 3 files changed, 18 insertions(+), 4 deletions(-) -- 2.43.5

5 months, 2 weeks

2
12
0 0

[PATCH v3 2/2] selftests/lib.mk: Introduce check to validate required dependencies

by Siddharth Menon

Currently, kselftests does not have a generalised mechanism to skip compilation and run tests when required kernel configuration flags are missing. This patch introduces a check to validate the presence of required config flags specified in the selftest config files. In case scripts/config or the current kernel config is not found, this check is skipped. In order to skip checking for config options required to compile the test, set the environment variable SKIP_CHECKS=1. example usage: ``` make SKIP_CHECKS=1 -C livepatch/ ``` Suggested-by: Petr Mladek <pmladek(a)suse.com> Suggested-by: Miroslav Benes <mbenes(a)suse.cz> Signed-off-by: Siddharth Menon <simeddon(a)gmail.com> --- v1->v2: - Moved the logic to check for required configurations to an external script v2 -> v3: - Add SKIP_CHECKS flag to skip checking the dependencies if required - Updated the test skip statement to be more meaningful tools/testing/selftests/lib.mk | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) mode change 100644 => 100755 tools/testing/selftests/lib.mk diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk old mode 100644 new mode 100755 index d6edcfcb5be8..0e11d1d3bab8 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -97,7 +97,18 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \ +TEST_DIR := $(shell pwd) + +check_kselftest_deps: +ifneq ($(SKIP_CHECKS),1) + @$(selfdir)/check_kselftest_deps.pl $(TEST_DIR) $(CC) || { \ + echo "Skipping test: $(notdir $(TEST_DIR)) (missing required kernel features)"; \ + exit 1; \ + } +endif + + +all: check_kselftest_deps $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) \ $(if $(TEST_GEN_MODS_DIR),gen_mods_dir) define RUN_TESTS @@ -228,4 +239,4 @@ $(OUTPUT)/%:%.S $(LINK.S) $^ $(LDLIBS) -o $@ endif -.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir +.PHONY: run_tests all clean install emit_tests gen_mods_dir clean_mods_dir check_kselftest_deps -- 2.39.5

5 months, 2 weeks

1
0
0 0

[PATCH v3 1/2] selftests: Introduce script to validate required dependencies

by Siddharth Menon

This patch adds a script to validate that the current kernel configuration satisfies the requirements for selftests by comparing the current kernel configs against the required selftest configs. The script also runs kselftest_deps.sh to check for any missing libraries required by the selftest. A config mismatch exits with error value 1 while matching configs or missing config files exit with value 0. In order to silence missing dependency output, set the environment variable SILENCE=1. The code for extracting the current kernel configs is adapted from scripts/kconfig/streamline_config.pl. Suggested-by: Petr Mladek <pmladek(a)suse.com> Suggested-by: Miroslav Benes <mbenes(a)suse.cz> Signed-off-by: Siddharth Menon <simeddon(a)gmail.com> --- v1->v2: - check selftest/config directly rather than a separate set in the test makefile v2->v3: - Integrate kselftest_deps.sh to check for missing libraries (I have not set it to skip the tests here, as it sometimes throws outputs such as missing $(LIB) or $(MNL_LDLIBS)) - Replaced spaces with tabs, removed trailing spaces and other minor formatting changes - Introduced flag to silence the missing dependencies debug statements - Rename script to a more meaningful name .../testing/selftests/check_kselftest_deps.pl | 170 ++++++++++++++++++ 1 file changed, 170 insertions(+) create mode 100755 tools/testing/selftests/check_kselftest_deps.pl diff --git a/tools/testing/selftests/check_kselftest_deps.pl b/tools/testing/selftests/check_kselftest_deps.pl new file mode 100755 index 000000000000..5d2298e3ffea --- /dev/null +++ b/tools/testing/selftests/check_kselftest_deps.pl @@ -0,0 +1,170 @@ +#!/usr/bin/env perl +# SPDX-License-Identifier: GPL-2.0 +use warnings; +use strict; +use Getopt::Long; +use File::Spec; +use File::Basename; + +# set the environment variable SILENCE to silence +# debug output. + +# Check if required arguments are provided +die "Usage: $0 <selftest_path> <compiler>\n" unless @ARGV >= 2; + +my $test_path = $ARGV[0]; +my $cc = join(' ', @ARGV[1..$#ARGV]); +my $script_dir = dirname(__FILE__); + +my $silenceprint; +$silenceprint = 1 if (defined($ENV{SILENCE})); + +sub dprint { + return if ($silenceprint); + print STDERR @_; +} + +my $uname = `uname -r`; +chomp $uname; + +my @searchconfigs = ( + { + "file" => ".config", + "exec" => "cat", + }, + { + "file" => "/proc/config.gz", + "exec" => "zcat", + }, + { + "file" => "/boot/config-$uname", + "exec" => "cat", + }, + { + "file" => "/boot/vmlinuz-$uname", + "exec" => "scripts/extract-ikconfig", + "test" => "scripts/extract-ikconfig", + }, + { + "file" => "vmlinux", + "exec" => "scripts/extract-ikconfig", + "test" => "scripts/extract-ikconfig", + }, + { + "file" => "/lib/modules/$uname/kernel/kernel/configs.ko", + "exec" => "scripts/extract-ikconfig", + "test" => "scripts/extract-ikconfig", + }, + { + "file" => "/lib/modules/$uname/build/.config", + "exec" => "cat", + }, + { + "file" => "kernel/configs.ko", + "exec" => "scripts/extract-ikconfig", + "test" => "scripts/extract-ikconfig", + }, + { + "file" => "kernel/configs.o", + "exec" => "scripts/extract-ikconfig", + "test" => "scripts/extract-ikconfig", + }, +); + +sub read_config { + foreach my $conf (@searchconfigs) { + my $file = $conf->{"file"}; + + next unless -f $file; + + if (defined $conf->{"test"}) { + `$conf->{"test"} $file 2>/dev/null`; + next if $?; + } + + my $exec = $conf->{"exec"}; + + # dprint "Kernel config: '$file'\n"; + + open(my $infile, '-|', "$exec $file") or die "Failed to run $exec $file"; + my @config_content = <$infile>; + close $infile; + + return @config_content; + } + + dprint "Unable to find kernel config file, skipping check\n"; + exit 0; +} + +sub check_libs { + my $command = "cd $script_dir && ./kselftest_deps.sh \"$cc\" $test_path"; + my $lib_test = `$command 2>&1`; + my $exit_code = $? >> 8; + + if ($exit_code != 0) { + die "Error: Failed to run kselftest_deps.sh with exit code $exit_code\n"; + } + + return $lib_test; +} + +# Check for missing libraries +my $lib_test = check_libs(); +my $fail_libs; + +if ($lib_test =~ +/(--------------------------------------------------------\s +*Missing libraries system.*? +--------------------------------------------------------)/s) { + $fail_libs = $1; +} + +dprint("$fail_libs\n") if $fail_libs; + +# Read and parse kernel config +my @config_file = read_config(); +my %kern_configs; +foreach my $line (@config_file) { + chomp $line; + next if $line =~ /^\s*$/ || $line =~ /^#/; + + if ($line =~ /^(CONFIG_\w+)=(.+)$/) { + $kern_configs{$1} = $2; + } +} + +# Read and parse test config +my %test_configs; +open(my $fh, '<', "$test_path/config") or exit 0; + +while (my $line = <$fh>) { + chomp $line; + next if $line =~ /^\s*$/ || $line =~ /^#/; + + if ($line =~ /^(CONFIG_\w+)=(.+)$/) { + $test_configs{$1} = $2; + } +} +close $fh; + +# Compare selftest configs with kernel configs +my $all_match = 1; +my @missing_or_mismatched; + +foreach my $key (keys %test_configs) { + if (!exists $kern_configs{$key} || $kern_configs{$key} ne $test_configs{$key}) { + push @missing_or_mismatched, "Required: $key=$test_configs{$key}"; + $all_match = 0; + } +} + +if ($all_match && !$fail_libs) { + exit 0; +} else { + dprint("--------------------------------------------------------\n") unless $fail_libs; + dprint("$_\n") for @missing_or_mismatched; + dprint("--------------------------------------------------------\n") if @missing_or_mismatched; + + exit 1; +} -- 2.39.5

5 months, 2 weeks

1
0
0 0

[PATCH v5 0/4] Migrate PCI Endpoint Subsystem tests to Kselftest

by Manivannan Sadhasivam

Hi, This series carries forward the effort to add Kselftest for PCI Endpoint Subsystem started by Aman Gupta [1] a while ago. I reworked the initial version based on another patch that fixes the return values of IOCTLs in pci_endpoint_test driver and did many cleanups. Since the resulting work modified the initial version substantially, I took over the authorship. This series also incorporates the review comment by Shuah Khan [2] to move the existing tests from 'tools/pci' to 'tools/testing/kselftest/pci_endpoint' before migrating to Kselftest framework. I made sure that the tests are executable in each commit and updated documentation accordingly. - Mani [1] https://lore.kernel.org/linux-pci/20221007053934.5188-1-aman1.gupta@samsung… [2] https://lore.kernel.org/linux-pci/b2a5db97-dc59-33ab-71cd-f591e0b1b34d@linu… Changes in v5: * Incorporated comments from Niklas * Added a patch to fix the DMA MEMCPY check in pci-epf-test driver * Collected tags * Rebased on top of pci/next 0333f56dbbf7ef6bb46d2906766c3e1b2a04a94d Changes in v4: * Dropped the BAR fix patches and submitted them separately: https://lore.kernel.org/linux-pci/20241231130224.38206-1-manivannan.sadhasi… * Rebased on top of pci/next 9e1b45d7a5bc0ad20f6b5267992da422884b916e Changes in v3: * Collected tags. * Added a note about failing testcase 10 and command to skip it in documentation. * Removed Aman Gupta and Padmanabhan Rajanbabu from CC as their addresses are bouncing. Changes in v2: * Added a patch that fixes return values of IOCTL in pci_endpoint_test driver * Moved the existing tests to new location before migrating * Added a fix for BARs on Qcom devices * Updated documentation and also added fixture variants for memcpy & DMA modes Manivannan Sadhasivam (4): PCI: endpoint: pci-epf-test: Fix the check for DMA MEMCPY test misc: pci_endpoint_test: Fix the return value of IOCTL selftests: Move PCI Endpoint tests from tools/pci to Kselftests selftests: pci_endpoint: Migrate to Kselftest framework Documentation/PCI/endpoint/pci-test-howto.rst | 170 +++++------ MAINTAINERS | 2 +- drivers/misc/pci_endpoint_test.c | 255 +++++++++-------- drivers/pci/endpoint/functions/pci-epf-test.c | 4 +- tools/pci/Build | 1 - tools/pci/Makefile | 58 ---- tools/pci/pcitest.c | 264 ------------------ tools/pci/pcitest.sh | 73 ----- tools/testing/selftests/Makefile | 1 + .../testing/selftests/pci_endpoint/.gitignore | 2 + tools/testing/selftests/pci_endpoint/Makefile | 7 + tools/testing/selftests/pci_endpoint/config | 4 + .../pci_endpoint/pci_endpoint_test.c | 221 +++++++++++++++ 13 files changed, 435 insertions(+), 627 deletions(-) delete mode 100644 tools/pci/Build delete mode 100644 tools/pci/Makefile delete mode 100644 tools/pci/pcitest.c delete mode 100644 tools/pci/pcitest.sh create mode 100644 tools/testing/selftests/pci_endpoint/.gitignore create mode 100644 tools/testing/selftests/pci_endpoint/Makefile create mode 100644 tools/testing/selftests/pci_endpoint/config create mode 100644 tools/testing/selftests/pci_endpoint/pci_endpoint_test.c -- 2.25.1

5 months, 2 weeks

2
11
0 0

selftests: arm64: pac.c:237:pac_instructions_not_nop:Expected 0 (0) != keyia (35747322042253312)

by Naresh Kamboju

The selftests: arm64: pac getting failed on FVP, Graviton-vm and Qemu-arm64 running Linux next-20250113..next-20250116. Started noticing from next-20250113. Bad: next-20250110 Bad: next-20250113 Test failed: pac global.pac_instructions_not_nop global.pac_instructions_not_nop_generic Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> Test regression: kselftest-arm64/arm64_pac Test output log: -------------- # selftests: arm64: pac # TAP version 13 # 1..7 # # Starting 7 tests from 1 test cases. # # RUN global.corrupt_pac ... # # OK global.corrupt_pac # ok 1 global.corrupt_pac # # RUN global.pac_instructions_not_nop ... # # pac.c:237:pac_instructions_not_nop:Expected 0 (0) != keyia (35747322042253312) # # pac.c:237:pac_instructions_not_nop:keyia instructions did nothing # # pac_instructions_not_nop: Test terminated by assertion # # FAIL global.pac_instructions_not_nop # not ok 2 global.pac_instructions_not_nop # # RUN global.pac_instructions_not_nop_generic ... # # pac.c:252:pac_instructions_not_nop_generic:Expected 0 (0) != keyg (35747322042253312) # # pac.c:252:pac_instructions_not_nop_generic:keyg instructions did nothing # # pac_instructions_not_nop_generic: Test terminated by assertion # # FAIL global.pac_instructions_not_nop_generic # not ok 3 global.pac_instructions_not_nop_generic # # RUN global.single_thread_different_keys ... # # OK global.single_thread_different_keys # ok 4 global.single_thread_different_keys # # RUN global.exec_changed_keys ... # # OK global.exec_changed_keys # ok 5 global.exec_changed_keys # # RUN global.context_switch_keep_keys ... # # OK global.context_switch_keep_keys # ok 6 global.context_switch_keep_keys # # RUN global.context_switch_keep_keys_generic ... # # OK global.context_switch_keep_keys_generic # ok 7 global.context_switch_keep_keys_generic # # FAILED: 5 / 7 tests passed. # # Totals: pass:5 fail:2 xfail:0 xpass:0 skip:0 error:0 not ok 37 selftests: arm64: pac # exit=1 Links: - https://qa-reports.linaro.org/lkft/linux-next-master/tests/kselftest-arm64/… - https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250116/te… - https://qa-reports.linaro.org/lkft/linux-next-master/build/next-20250116/te… -- Linaro LKFT https://lkft.linaro.org

5 months, 2 weeks

2
1
0 0

[PATCH 3/3] selftests/ftrace: Add test that tests event :mod: commands

by Steven Rostedt

From: Steven Rostedt <rostedt(a)goodmis.org> Now that here's a :mod: command that can be sent into set_event, add a test that tests its use. Both setting events for a loaded module, as well as caching what events to set for a module that is not loaded yet. Cc: Shuah Khan <shuah(a)kernel.org> Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- .../ftrace/test.d/event/event-mod.tc | 192 ++++++++++++++++++ 1 file changed, 192 insertions(+) create mode 100644 tools/testing/selftests/ftrace/test.d/event/event-mod.tc diff --git a/tools/testing/selftests/ftrace/test.d/event/event-mod.tc b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc new file mode 100644 index 000000000000..6f7601c4b54b --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc @@ -0,0 +1,192 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event tracing - enable/disable with module event +# requires: set_event "Can enable module events via: :mod:":README +# flags: instance + +rmmod trace-events-sample ||: +if ! modprobe trace-events-sample ; then + echo "No trace-events sample module - please make CONFIG_SAMPLE_TRACE_EVENTS=m" + exit_unresolved; +fi +trap "rmmod trace-events-sample" EXIT + +# Set events for the module +echo ":mod:trace-events-sample" > set_event + +test_all_enabled() { + + # Check if more than one is enabled + grep -q sample-trace:foo_bar set_event + grep -q sample-trace:foo_bar_with_cond set_event + grep -q sample-trace:foo_bar_with_fn set_event + + # All of them should be enabled. Check via the enable file + val=`cat events/sample-trace/enable` + if [ $val -ne 1 ]; then + exit_fail + fi +} + +clear_events() { + echo > set_event + val=`cat events/enable` + if [ "$val" != "0" ]; then + exit_fail + fi + count=`cat set_event | wc -l` + if [ $count -ne 0 ]; then + exit_fail + fi +} + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo And the set_event file is empty + +cnt=`wc -l set_event` +if [ $cnt -ne 0 ]; then + exit_fail +fi + +echo now enable all events +echo 1 > events/enable + +echo Confirm the events are enabled again +val=`cat events/sample-trace/enable` +if [ $val -ne 1 ]; then + exit_fail +fi + +echo disable just the module events +echo '!:mod:trace-events-sample' >> set_event + +echo Should have mix of events enabled +val=`cat events/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +echo Confirm the module events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo 0 > events/enable + +echo now enable the system events +echo 'sample-trace:mod:trace-events-sample' > set_event + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo Test enabling foo_bar only +echo 'foo_bar:mod:trace-events-sample' > set_event + +grep -q sample-trace:foo_bar set_event + +echo make sure nothing is found besides foo_bar +if grep -q -v sample-trace:foo_bar set_event ; then + exit_fail +fi + +echo Append another using the system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event + +grep -q sample-trace:foo_bar set_event +grep -q sample-trace:foo_bar_with_cond set_event + +count=`cat set_event | wc -l` + +if [ $count -ne 2 ]; then + exit_fail +fi + +clear_events + +rmmod trace-events-sample + +echo ':mod:trace-events-sample' > set_event + +echo make sure that the module shows up, and '-' is converted to '_' +grep -q '\*:\*:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable just the system events +echo 'sample-trace:mod:trace-events-sample' > set_event +grep -q 'sample-trace:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable event with just event name +echo 'foo_bar:mod:trace-events-sample' > set_event +grep -q 'foo_bar:mod:trace_events_sample' set_event + +echo Enable another event with both system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event +grep -q 'sample-trace:foo_bar_with_cond:mod:trace_events_sample' set_event +echo Make sure the other event was still there +grep -q 'foo_bar:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +echo There should be no :mod: cached events +if grep -q ':mod:' set_event; then + exit_fail +fi + +echo two events should be enabled +count=`cat set_event | wc -l` +if [ $count -ne 2 ]; then + exit_fail +fi + +echo only two events should be enabled +val=`cat events/sample-trace/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar_with_cond/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +clear_trace + -- 2.45.2

5 months, 2 weeks

1
0
0 0

[PATCH v4 0/3] Migrate PCI Endpoint Subsystem tests to Kselftest

by Manivannan Sadhasivam

Hi, This series carries forward the effort to add Kselftest for PCI Endpoint Subsystem started by Aman Gupta [1] a while ago. I reworked the initial version based on another patch that fixes the return values of IOCTLs in pci_endpoint_test driver and did many cleanups. Since the resulting work modified the initial version substantially, I took over the authorship. This series also incorporates the review comment by Shuah Khan [2] to move the existing tests from 'tools/pci' to 'tools/testing/kselftest/pci_endpoint' before migrating to Kselftest framework. I made sure that the tests are executable in each commit and updated documentation accordingly. - Mani [1] https://lore.kernel.org/linux-pci/20221007053934.5188-1-aman1.gupta@samsung… [2] https://lore.kernel.org/linux-pci/b2a5db97-dc59-33ab-71cd-f591e0b1b34d@linu… Changes in v4: * Dropped the BAR fix patches and submitted them separately: https://lore.kernel.org/linux-pci/20241231130224.38206-1-manivannan.sadhasi… * Rebased on top of pci/next 9e1b45d7a5bc0ad20f6b5267992da422884b916e Changes in v3: * Collected tags. * Added a note about failing testcase 10 and command to skip it in documentation. * Removed Aman Gupta and Padmanabhan Rajanbabu from CC as their addresses are bouncing. Changes in v2: * Added a patch that fixes return values of IOCTL in pci_endpoint_test driver * Moved the existing tests to new location before migrating * Added a fix for BARs on Qcom devices * Updated documentation and also added fixture variants for memcpy & DMA modes Manivannan Sadhasivam (3): misc: pci_endpoint_test: Fix the return value of IOCTL selftests: Move PCI Endpoint tests from tools/pci to Kselftests selftests: pci_endpoint: Migrate to Kselftest framework Documentation/PCI/endpoint/pci-test-howto.rst | 155 ++++------ MAINTAINERS | 2 +- drivers/misc/pci_endpoint_test.c | 250 ++++++++--------- tools/pci/Build | 1 - tools/pci/Makefile | 58 ---- tools/pci/pcitest.c | 264 ------------------ tools/pci/pcitest.sh | 73 ----- tools/testing/selftests/Makefile | 1 + .../testing/selftests/pci_endpoint/.gitignore | 2 + tools/testing/selftests/pci_endpoint/Makefile | 7 + tools/testing/selftests/pci_endpoint/config | 4 + .../pci_endpoint/pci_endpoint_test.c | 194 +++++++++++++ 12 files changed, 386 insertions(+), 625 deletions(-) delete mode 100644 tools/pci/Build delete mode 100644 tools/pci/Makefile delete mode 100644 tools/pci/pcitest.c delete mode 100644 tools/pci/pcitest.sh create mode 100644 tools/testing/selftests/pci_endpoint/.gitignore create mode 100644 tools/testing/selftests/pci_endpoint/Makefile create mode 100644 tools/testing/selftests/pci_endpoint/config create mode 100644 tools/testing/selftests/pci_endpoint/pci_endpoint_test.c -- 2.25.1

5 months, 2 weeks

2
14
0 0

[PATCH 1/2] selftests/mm: use selftests framework to print test result.

by Zi Yan

Otherwise the number of tests does not match the reality. Fixes: 391e86971161 ("mm: selftest to verify zero-filled pages are mapped to zeropage") Signed-off-by: Zi Yan <ziy(a)nvidia.com> --- .../selftests/mm/split_huge_page_test.c | 34 +++++++------------ 1 file changed, 12 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 84b1251666aa..128004308233 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -108,38 +108,28 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, size_t le unsigned long rss_anon_before, rss_anon_after; size_t i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); rss_anon_before = rss_anon(); - if (!rss_anon_before) { - printf("No RssAnon is allocated before split\n"); - exit(EXIT_FAILURE); - } + if (!rss_anon_before) + ksft_exit_fail_msg("No RssAnon is allocated before split\n"); /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, (uint64_t)one_page + len, 0); for (i = 0; i < len; i++) - if (one_page[i] != (char)0) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } + if (one_page[i] != (char)0) + ksft_exit_fail_msg("%ld byte corrupted\n", i); - if (!check_huge_anon(one_page, 0, pmd_pagesize)) { - printf("Still AnonHugePages not split\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 0, pmd_pagesize)) + ksft_exit_fail_msg("Still AnonHugePages not split\n"); rss_anon_after = rss_anon(); - if (rss_anon_after >= rss_anon_before) { - printf("Incorrect RssAnon value. Before: %ld After: %ld\n", + if (rss_anon_after >= rss_anon_before) + ksft_exit_fail_msg("Incorrect RssAnon value. Before: %ld After: %ld\n", rss_anon_before, rss_anon_after); - exit(EXIT_FAILURE); - } } void split_pmd_zero_pages(void) @@ -150,7 +140,7 @@ void split_pmd_zero_pages(void) one_page = allocate_zero_filled_hugepage(len); verify_rss_anon_split_huge_page_all_zeroes(one_page, len); - printf("Split zero filled huge pages successful\n"); + ksft_test_result_pass("Split zero filled huge pages successful\n"); free(one_page); } @@ -491,7 +481,7 @@ int main(int argc, char **argv) if (argc > 1) optional_xfs_path = argv[1]; - ksft_set_plan(3+9); + ksft_set_plan(4+9); pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; -- 2.45.2

5 months, 2 weeks

1
3
0 0

[PATCH bpf-next v5 0/4] xsk: TX metadata Launch Time support

by Song Yoong Siang

This series expands the XDP TX metadata framework to allow user applications to pass per packet 64-bit launch time directly to the kernel driver, requesting launch time hardware offload support. The XDP TX metadata framework will not perform any clock conversion or packet reordering. Please note that the role of Tx metadata is just to pass the launch time, not to enable the offload feature. Users will need to enable the launch time hardware offload feature of the device by using the respective command, such as the tc-etf command. Although some devices use the tc-etf command to enable their launch time hardware offload feature, xsk packets will not go through the etf qdisc. Therefore, in my opinion, the launch time should always be based on the PTP Hardware Clock (PHC). Thus, i did not include a clock ID to indicate the clock source. To simplify the test steps, I modified the xdp_hw_metadata bpf self-test tool in such a way that it will set the launch time based on the offset provided by the user and the value of the Receive Hardware Timestamp, which is against the PHC. This will eliminate the need to discipline System Clock with the PHC and then use clock_gettime() to get the time. Please note that AF_XDP lacks a feedback mechanism to inform the application if the requested launch time is invalid. So, users are expected to familiar with the horizon of the launch time of the device they use and not request a launch time that is beyond the horizon. Otherwise, the driver might interpret the launch time incorrectly and react wrongly. For stmmac and igc, where modulo computation is used, a launch time larger than the horizon will cause the device to transmit the packet earlier that the requested launch time. Although there is no feedback mechanism for the launch time request for now, user still can check whether the requested launch time is working or not, by requesting the Transmit Completion Hardware Timestamp. Changes since v1: - renamed to use Earliest TxTime First (Willem) - renamed to use txtime (Willem) Changes since v2: - renamed to use launch time (Jesper & Willem) - changed the default launch time in xdp_hw_metadata apps from 1s to 0.1s because some NICs do not support such a large future time. Changes since v3: - added XDP launch time support to the igc driver (Jesper & Florian) - added per-driver launch time limitation on xsk-tx-metadata.rst (Jesper) - added explanation on FIFO behavior on xsk-tx-metadata.rst (Jakub) - added step to enable launch time in the commit message (Jesper & Willem) - explicitly documented the type of launch_time and which clock source it is against (Willem) Changes since v4: - change netdev feature name from tx-launch-time to tx-launch-time-fifo to explicitly state the FIFO behaviour (Stanislav) - improve the looping of xdp_hw_metadata app to wait for packet tx completion to be more readable by using clock_gettime() (Stanislav) - add launch time setup steps into xdp_hw_metadata app (Stanislav) v1: https://patchwork.kernel.org/project/netdevbpf/cover/20231130162028.852006-… v2: https://patchwork.kernel.org/project/netdevbpf/cover/20231201062421.1074768… v3: https://patchwork.kernel.org/project/netdevbpf/cover/20231203165129.1740512… v4: https://patchwork.kernel.org/project/netdevbpf/cover/20250106135506.9687-1-… Song Yoong Siang (4): xsk: Add launch time hardware offload support to XDP Tx metadata selftests/bpf: Add launch time request to xdp_hw_metadata net: stmmac: Add launch time support to XDP ZC igc: Add launch time support to XDP ZC Documentation/netlink/specs/netdev.yaml | 4 + Documentation/networking/xsk-tx-metadata.rst | 62 +++++++++ drivers/net/ethernet/intel/igc/igc_main.c | 78 +++++++---- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 2 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 13 ++ include/net/xdp_sock.h | 10 ++ include/net/xdp_sock_drv.h | 1 + include/uapi/linux/if_xdp.h | 10 ++ include/uapi/linux/netdev.h | 3 + net/core/netdev-genl.c | 2 + net/xdp/xsk.c | 3 + tools/include/uapi/linux/if_xdp.h | 10 ++ tools/include/uapi/linux/netdev.h | 3 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 121 +++++++++++++++++- 14 files changed, 298 insertions(+), 24 deletions(-) -- 2.34.1

5 months, 2 weeks

4
8
0 0

[PATCH v2] selftests/net/forwarding: teamd command not found

by Alessandro Zanni

Running "make kselftest TARGETS=net/forwarding" results in multiple ccurrences of the same error: - ./lib.sh: line 787: teamd: command not found This patch adds the variable $REQUIRE_TEAMD in every test that uses the command teamd and checks the $REQUIRE_TEAMD variable in the file "lib.sh" to skip the test if the command is not installed. Signed-off-by: Alessandro Zanni <alessandro.zanni87(a)gmail.com> --- Notes: v2: added variable REQUIRED_TEAMD to check if teamd is required tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh | 1 + tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh | 1 + tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh | 1 + tools/testing/selftests/net/forwarding/lib.sh | 4 ++++ .../selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh | 1 + tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh | 1 + .../testing/selftests/net/forwarding/router_bridge_1d_lag.sh | 1 + tools/testing/selftests/net/forwarding/router_bridge_lag.sh | 1 + 8 files changed, 11 insertions(+) diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh index b79542a4dcc7..4a11bf1d514a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh @@ -12,6 +12,7 @@ ALL_TESTS=" bridge_rif_remaster_port " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh index e28f978104f3..b8bbe94f4736 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh @@ -10,6 +10,7 @@ ALL_TESTS=" lag_rif_nomaster_addr " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh index 6318cfa6434c..d1a9d379eaf3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh @@ -10,6 +10,7 @@ ALL_TESTS=" lag_rif_nomaster_addr " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7337f398f9cc..996a866ed6de 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -68,6 +68,7 @@ declare -A NETIFS=( : "${REQUIRE_JQ:=yes}" : "${REQUIRE_MZ:=yes}" : "${REQUIRE_MTOOLS:=no}" +: "${REQUIRE_TEAMD:=no}" # Whether to override MAC addresses on interfaces participating in the test. : "${STABLE_MAC_ADDRS:=no}" @@ -321,6 +322,9 @@ fi if [[ "$REQUIRE_MZ" = "yes" ]]; then require_command $MZ fi +if [[ "$REQUIRE_TEAMD" = "yes" ]]; then + require_command $TEAMD +fi if [[ "$REQUIRE_MTOOLS" = "yes" ]]; then # https://github.com/troglobit/mtools require_command msend diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index fe4d7c906a70..a20d22d1df36 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -49,6 +49,7 @@ ALL_TESTS=" test_mirror_gretap_second " +REQUIRE_TEAMD="yes" NUM_NETIFS=6 source lib.sh source mirror_lib.sh diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh index 1261e6f46e34..ff7049582d35 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh @@ -53,6 +53,7 @@ ALL_TESTS=" test_mirror_gretap_second " +REQUIRE_TEAMD="yes" NUM_NETIFS=6 source lib.sh source mirror_lib.sh diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh index e064b946e821..16583a470ec3 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh @@ -109,6 +109,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 " +REQUIRE_TEAMD="yes" NUM_NETIFS=8 source lib.sh diff --git a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh index f05ffe213c46..2a4cd1af1b85 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh @@ -76,6 +76,7 @@ ping_ipv4 ping_ipv6 "} +REQUIRE_TEAMD="yes" NUM_NETIFS=8 : ${lib_dir:=.} source $lib_dir/lib.sh -- 2.43.0

5 months, 2 weeks

2
1
0 0

[PATCH v6 0/3] riscv/ptrace: add new regset to access original a0 register

by Celeste Liu

The orig_a0 is missing in struct user_regs_struct of riscv, and there is no way to add it without breaking UAPI. (See Link tag below) Like NT_ARM_SYSTEM_CALL do, we add a new regset name NT_RISCV_ORIG_A0 to access original a0 register from userspace via ptrace API. Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Signed-off-by: Celeste Liu <uwu(a)coelacanthus.name> --- Changes in v6: - Fix obsolute comment. - Copy include/linux/stddef.h to tools/include to use offsetofend in selftests. - Link to v5: https://lore.kernel.org/r/20250115-riscv-new-regset-v5-0-d0e6ec031a23@coela… Changes in v5: - Fix wrong usage in selftests. - Link to v4: https://lore.kernel.org/r/20241226-riscv-new-regset-v4-0-4496a29d0436@coela… Changes in v4: - Fix a copy paste error in selftest. (Forget to commit...) - Link to v3: https://lore.kernel.org/r/20241226-riscv-new-regset-v3-0-f5b96465826b@coela… Changes in v3: - Use return 0 directly for readability. - Fix test for modify a0. - Add Fixes: tag - Remove useless Cc: stable. - Selftest will check both a0 and orig_a0, but depends on the correctness of PTRACE_GET_SYSCALL_INFO. - Link to v2: https://lore.kernel.org/r/20241203-riscv-new-regset-v2-0-d37da8c0cba6@coela… Changes in v2: - Fix integer width. - Add selftest. - Link to v1: https://lore.kernel.org/r/20241201-riscv-new-regset-v1-1-c83c58abcc7b@coela… --- Celeste Liu (3): riscv/ptrace: add new regset to access original a0 register tools: copy include/linux/stddef.h to tools/include riscv: selftests: Add a ptrace test to verify a0 and orig_a0 access arch/riscv/kernel/ptrace.c | 32 +++++ include/uapi/linux/elf.h | 1 + tools/include/linux/stddef.h | 85 ++++++++++++ tools/include/uapi/linux/stddef.h | 6 +- tools/testing/selftests/riscv/abi/.gitignore | 1 + tools/testing/selftests/riscv/abi/Makefile | 6 +- tools/testing/selftests/riscv/abi/ptrace.c | 193 +++++++++++++++++++++++++++ 7 files changed, 319 insertions(+), 5 deletions(-) --- base-commit: 0e287d31b62bb53ad81d5e59778384a40f8b6f56 change-id: 20241201-riscv-new-regset-d529b952ad0d Best regards, -- Celeste Liu <uwu(a)coelacanthus.name>

5 months, 2 weeks

3
8
0 0

[PATCH] selftests/net/ipsec: Fix Null pointer dereference in rtattr_pack()

by liuye

Fix the following warning. tools/testing/selftests/net/ipsec.c:230:25: warning: Possible null pointer dereference: payload [nullPointer] memcpy(RTA_DATA(attr), payload, size); ^ tools/testing/selftests/net/ipsec.c:1618:54: note: Calling function 'rtattr_pack', 4th argument 'NULL' value is 0 if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) { ^ tools/testing/selftests/net/ipsec.c:230:25: note: Null pointer dereference memcpy(RTA_DATA(attr), payload, size); ^ Signed-off-by: liuye <liuye(a)kylinos.cn> --- tools/testing/selftests/net/ipsec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index be4a30a0d02a..725310ac26a9 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -227,7 +227,8 @@ static int rtattr_pack(struct nlmsghdr *nh, size_t req_sz, attr->rta_len = RTA_LENGTH(size); attr->rta_type = rta_type; - memcpy(RTA_DATA(attr), payload, size); + if (payload != NULL) + memcpy(RTA_DATA(attr), payload, size); return 0; } -- 2.25.1

5 months, 2 weeks

4
3
0 0

[PATCH net-next 0/6] mptcp: selftests: more debug in case of errors

by Matthieu Baerts (NGI0)

Here are just a bunch of small improvements for the MPTCP selftests: Patch 1: Unify errors messages in simult_flows: print MIB and 'ss -Me'. Patch 2: Unify errors messages in sockopt: print MIB. Patch 3: Move common code to print debug info to mptcp_lib.sh. Patch 4: Use 'ss' with '-m' in case of errors. Patch 5: Remove an unused variable. Patch 6: Print only the size instead of size + filename again. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (1): selftests: mptcp: sockopt: save nstat infos Matthieu Baerts (NGI0) (5): selftests: mptcp: simult_flows: unify errors msgs selftests: mptcp: move stats info in case of errors to lib.sh selftests: mptcp: add -m with ss in case of errors selftests: mptcp: connect: remove unused variable selftests: mptcp: connect: better display the files size tools/testing/selftests/net/mptcp/mptcp_connect.sh | 13 ++++--------- tools/testing/selftests/net/mptcp/mptcp_join.sh | 9 ++------- tools/testing/selftests/net/mptcp/mptcp_lib.sh | 21 +++++++++++++++++++++ tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 17 ++++++++++++----- tools/testing/selftests/net/mptcp/simult_flows.sh | 21 ++++++++++++++------- 5 files changed, 53 insertions(+), 28 deletions(-) --- base-commit: 9c7ad35632297edc08d0f2c7b599137e9fb5f9ff change-id: 20250114-net-next-mptcp-st-more-debug-err-3f3f1aa15a10 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

5 months, 2 weeks

2
7
0 0

[PATCH] selftests/rseq: Fix handling of glibc without rseq support

by Mathieu Desnoyers

When porting librseq commit: commit c7b45750fa85 ("Adapt to glibc __rseq_size feature detection") from librseq to the kernel selftests, the following line was missed at the end of rseq_init(): rseq_size = get_rseq_kernel_feature_size(); which effectively leaves rseq_size initialized to -1U when glibc does not have rseq support. glibc supports rseq from version 2.35 onwards. In a following librseq commit commit c67d198627c2 ("Only set 'rseq_size' on first thread registration") to mimic the libc behavior, a new approach is taken: don't set the feature size in 'rseq_size' until at least one thread has successfully registered. This allows using 'rseq_size' in fast-paths to test for both registration status and available features. The caveat is that on libc either all threads are registered or none are, while with bare librseq it is the responsability of the user to register all threads using rseq. This combines the changes from the following librseq commits: commit c7b45750fa85 ("Adapt to glibc __rseq_size feature detection") commit c67d198627c2 ("Only set 'rseq_size' on first thread registration") Fixes: 73a4f5a704a2 ("selftests/rseq: Fix mm_cid test failure") Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Raghavendra Rao Ananta <rananta(a)google.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Boqun Feng <boqun.feng(a)gmail.com> Cc: "Paul E. McKenney" <paulmck(a)kernel.org> Cc: Carlos O'Donell <carlos(a)redhat.com> Cc: Florian Weimer <fweimer(a)redhat.com> Cc: Michael Jeanson <mjeanson(a)efficios.com> Cc: linux-kselftest(a)vger.kernel.org Cc: stable(a)vger.kernel.org --- tools/testing/selftests/rseq/rseq.c | 32 ++++++++++++++++++++++------- tools/testing/selftests/rseq/rseq.h | 9 +++++++- 2 files changed, 33 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 5b9772cdf265..f6156790c3b4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -61,7 +61,6 @@ unsigned int rseq_size = -1U; unsigned int rseq_flags; static int rseq_ownership; -static int rseq_reg_success; /* At least one rseq registration has succeded. */ /* Allocate a large area for the TLS. */ #define RSEQ_THREAD_AREA_ALLOC_SIZE 1024 @@ -152,14 +151,27 @@ int rseq_register_current_thread(void) } rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); if (rc) { - if (RSEQ_READ_ONCE(rseq_reg_success)) { + /* + * After at least one thread has registered successfully + * (rseq_size > 0), the registration of other threads should + * never fail. + */ + if (RSEQ_READ_ONCE(rseq_size) > 0) { /* Incoherent success/failure within process. */ abort(); } return -1; } assert(rseq_current_cpu_raw() >= 0); - RSEQ_WRITE_ONCE(rseq_reg_success, 1); + + /* + * The first thread to register sets the rseq_size to mimic the libc + * behavior. + */ + if (RSEQ_READ_ONCE(rseq_size) == 0) { + RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size()); + } + return 0; } @@ -235,12 +247,18 @@ void rseq_init(void) return; } rseq_ownership = 1; - if (!rseq_available()) { - rseq_size = 0; - return; - } + + /* Calculate the offset of the rseq area from the thread pointer. */ rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + + /* rseq flags are deprecated, always set to 0. */ rseq_flags = 0; + + /* + * Set the size to 0 until at least one thread registers to mimic the + * libc behavior. + */ + rseq_size = 0; } static __attribute__((destructor)) diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 4e217b620e0c..062d10925a10 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -60,7 +60,14 @@ extern ptrdiff_t rseq_offset; /* - * Size of the registered rseq area. 0 if the registration was + * The rseq ABI is composed of extensible feature fields. The extensions + * are done by appending additional fields at the end of the structure. + * The rseq_size defines the size of the active feature set which can be + * used by the application for the current rseq registration. Features + * starting at offset >= rseq_size are inactive and should not be used. + * + * The rseq_size is the intersection between the available allocation + * size for the rseq area and the feature size supported by the kernel. * unsuccessful. */ extern unsigned int rseq_size; -- 2.39.5

5 months, 3 weeks

2
4
0 0

[PATCH] selftests/bpf: Fix test_xdp_adjust_tail_grow2 selftest on powerpc

by Saket Kumar Bhaskar

On powerpc cache line size is 128 bytes, so skb_shared_info must be aligned accordingly. Signed-off-by: Saket Kumar Bhaskar <skb99(a)linux.ibm.com> --- tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c | 2 ++ tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c | 2 ++ 2 files changed, 4 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 53d6ad8c2257..b2b2d85dbb1b 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -82,6 +82,8 @@ static void test_xdp_adjust_tail_grow2(void) /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ #if defined(__s390x__) int tailroom = 512; +#elif defined(__powerpc__) + int tailroom = 384; #else int tailroom = 320; #endif diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 81bb38d72ced..dc74d8cf9e3f 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -10,6 +10,8 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ #if defined(__TARGET_ARCH_s390) int tailroom = 512; +#elif defined(__TARGET_ARCH_powerpc) + int tailroom = 384; #else int tailroom = 320; #endif -- 2.43.5

5 months, 3 weeks

2
1
0 0

[PATCH v5 0/2] riscv/ptrace: add new regset to access original a0 register

by Celeste Liu

The orig_a0 is missing in struct user_regs_struct of riscv, and there is no way to add it without breaking UAPI. (See Link tag below) Like NT_ARM_SYSTEM_CALL do, we add a new regset name NT_RISCV_ORIG_A0 to access original a0 register from userspace via ptrace API. Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Signed-off-by: Celeste Liu <uwu(a)coelacanthus.name> --- Changes in v5: - Fix wrong usage in selftests. - Link to v4: https://lore.kernel.org/r/20241226-riscv-new-regset-v4-0-4496a29d0436@coela… Changes in v4: - Fix a copy paste error in selftest. (Forget to commit...) - Link to v3: https://lore.kernel.org/r/20241226-riscv-new-regset-v3-0-f5b96465826b@coela… Changes in v3: - Use return 0 directly for readability. - Fix test for modify a0. - Add Fixes: tag - Remove useless Cc: stable. - Selftest will check both a0 and orig_a0, but depends on the correctness of PTRACE_GET_SYSCALL_INFO. - Link to v2: https://lore.kernel.org/r/20241203-riscv-new-regset-v2-0-d37da8c0cba6@coela… Changes in v2: - Fix integer width. - Add selftest. - Link to v1: https://lore.kernel.org/r/20241201-riscv-new-regset-v1-1-c83c58abcc7b@coela… --- Celeste Liu (2): riscv/ptrace: add new regset to access original a0 register riscv: selftests: Add a ptrace test to verify a0 and orig_a0 access arch/riscv/kernel/ptrace.c | 32 +++++ include/uapi/linux/elf.h | 1 + tools/testing/selftests/riscv/abi/.gitignore | 1 + tools/testing/selftests/riscv/abi/Makefile | 6 +- tools/testing/selftests/riscv/abi/ptrace.c | 201 +++++++++++++++++++++++++++ 5 files changed, 240 insertions(+), 1 deletion(-) --- base-commit: 0e287d31b62bb53ad81d5e59778384a40f8b6f56 change-id: 20241201-riscv-new-regset-d529b952ad0d Best regards, -- Celeste Liu <uwu(a)coelacanthus.name>

5 months, 3 weeks

2
6
0 0

[PATCH] selftests/ptrace/get_syscall_info: fix for MIPS n32

by Dmitry V. Levin

MIPS n32 is one of two ILP32 architectures supported by the kernel that have 64-bit syscall arguments (another one is x32). When this test passed 32-bit arguments to syscall(), they were sign-extended in libc, PTRACE_GET_SYSCALL_INFO reported these sign-extended 64-bit values, and the test complained about the mismatch. Fix this by passing arguments of the appropriate type to syscall(), which is "unsigned long long" on MIPS n32, and __kernel_ulong_t on other architectures. As a side effect, this also extends the test on all 64-bit architectures by choosing constants that don't fit into 32-bit integers. Signed-off-by: Dmitry V. Levin <ldv(a)strace.io> --- .../selftests/ptrace/get_syscall_info.c | 53 +++++++++++-------- 1 file changed, 32 insertions(+), 21 deletions(-) diff --git a/tools/testing/selftests/ptrace/get_syscall_info.c b/tools/testing/selftests/ptrace/get_syscall_info.c index 5bcd1c7b5be6..812f64d15955 100644 --- a/tools/testing/selftests/ptrace/get_syscall_info.c +++ b/tools/testing/selftests/ptrace/get_syscall_info.c @@ -11,8 +11,19 @@ #include <err.h> #include <signal.h> #include <asm/unistd.h> +#include <linux/types.h> #include "linux/ptrace.h" +#if defined(__mips__) && defined(_ABIN32) +/* + * MIPS N32 is the only architecture where __kernel_ulong_t + * does not match the bitness of syscall arguments. + */ +typedef unsigned long long kernel_ulong_t; +#else +typedef __kernel_ulong_t kernel_ulong_t; +#endif + static int kill_tracee(pid_t pid) { @@ -42,37 +53,37 @@ sys_ptrace(int request, pid_t pid, unsigned long addr, unsigned long data) TEST(get_syscall_info) { - static const unsigned long args[][7] = { + const kernel_ulong_t args[][7] = { /* a sequence of architecture-agnostic syscalls */ { __NR_chdir, - (unsigned long) "", - 0xbad1fed1, - 0xbad2fed2, - 0xbad3fed3, - 0xbad4fed4, - 0xbad5fed5 + (uintptr_t) "", + (kernel_ulong_t) 0xdad1bef1bad1fed1ULL, + (kernel_ulong_t) 0xdad2bef2bad2fed2ULL, + (kernel_ulong_t) 0xdad3bef3bad3fed3ULL, + (kernel_ulong_t) 0xdad4bef4bad4fed4ULL, + (kernel_ulong_t) 0xdad5bef5bad5fed5ULL }, { __NR_gettid, - 0xcaf0bea0, - 0xcaf1bea1, - 0xcaf2bea2, - 0xcaf3bea3, - 0xcaf4bea4, - 0xcaf5bea5 + (kernel_ulong_t) 0xdad0bef0caf0bea0ULL, + (kernel_ulong_t) 0xdad1bef1caf1bea1ULL, + (kernel_ulong_t) 0xdad2bef2caf2bea2ULL, + (kernel_ulong_t) 0xdad3bef3caf3bea3ULL, + (kernel_ulong_t) 0xdad4bef4caf4bea4ULL, + (kernel_ulong_t) 0xdad5bef5caf5bea5ULL }, { __NR_exit_group, 0, - 0xfac1c0d1, - 0xfac2c0d2, - 0xfac3c0d3, - 0xfac4c0d4, - 0xfac5c0d5 + (kernel_ulong_t) 0xdad1bef1fac1c0d1ULL, + (kernel_ulong_t) 0xdad2bef2fac2c0d2ULL, + (kernel_ulong_t) 0xdad3bef3fac3c0d3ULL, + (kernel_ulong_t) 0xdad4bef4fac4c0d4ULL, + (kernel_ulong_t) 0xdad5bef5fac5c0d5ULL } }; - const unsigned long *exp_args; + const kernel_ulong_t *exp_args; pid_t pid = fork(); @@ -154,7 +165,7 @@ TEST(get_syscall_info) } ASSERT_LT(0, (rc = sys_ptrace(PTRACE_GET_SYSCALL_INFO, pid, size, - (unsigned long) &info))) { + (uintptr_t) &info))) { LOG_KILL_TRACEE("PTRACE_GET_SYSCALL_INFO: %m"); } ASSERT_EQ(expected_none_size, rc) { @@ -177,7 +188,7 @@ TEST(get_syscall_info) case SIGTRAP | 0x80: ASSERT_LT(0, (rc = sys_ptrace(PTRACE_GET_SYSCALL_INFO, pid, size, - (unsigned long) &info))) { + (uintptr_t) &info))) { LOG_KILL_TRACEE("PTRACE_GET_SYSCALL_INFO: %m"); } switch (ptrace_stop) { -- ldv

5 months, 3 weeks

1
0
0 0

[PATCH v8 0/2] selftests/resctrl: SNC kernel support discovery

by Maciej Wieczor-Retman

Changes v8: - Fix Makefile changes. - Update cover letter SNC status information. - Add Reinette's reviewed by tag to patch 2/2. Changes v7: - Include fallthrough in resctrlfs.c. - Check fp after opening empty cpus file. - Correct a comment and merge strings in snprintf(). Changes v6: - Rebase onto latest kselftest-next. - Looking at the two patches with a fresh eye decided to make a split along the lines of: - Patch 1/2 contains all of the code that relates to SNC mode detection and checking that detection's reliability. - Patch 2/2 contains checking kernel support for SNC and modifying the messages at the end of affected tests. Changes v5: - Tests are skipped if snc_unreliable was set. - Moved resctrlfs.c changes from patch 2/2 to 1/2. - Removed CAT changes since it's not impacted by SNC in the selftest. - Updated various comments. - Fixed a bunch of minor issues pointed out in the review. Changes v4: - Printing SNC warnings at the start of every test. - Printing SNC warnings at the end of every relevant test. - Remove global snc_mode variable, consolidate snc detection functions into one. - Correct minor mistakes. Changes v3: - Reworked patch 2. - Changed minor things in patch 1 like function name and made corrections to the patch message. Changes v2: - Removed patches 2 and 3 since now this part will be supported by the kernel. Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory into multiple NUMA nodes. When enabled, NUMA-aware applications can achieve better performance on bigger server platforms. SNC support was merged into the kernel [1]. With SNC enabled and kernel support in place all the tests will function normally (aside from effective cache size). There might be a problem when SNC is enabled but the system is still using an older kernel version without SNC support. Currently the only message displayed in that situation is a guess that SNC might be enabled and is causing issues. That message also is displayed whenever the test fails on an Intel platform. Add a mechanism to discover kernel support for SNC which will add more meaning and certainty to the error message. Add runtime SNC mode detection and verify how reliable that information is. Series was tested on Ice Lake server platforms with SNC disabled, SNC-2 and SNC-4. The tests were also ran with and without kernel support for SNC. Series applies cleanly on kselftest/next. [1] https://lore.kernel.org/all/20240716065458.GAZpYZQhh0PBItpD1k@fat_crate.loc… Previous versions of this series: [v1] https://lore.kernel.org/all/cover.1709721159.git.maciej.wieczor-retman@inte… [v2] https://lore.kernel.org/all/cover.1715769576.git.maciej.wieczor-retman@inte… [v3] https://lore.kernel.org/all/cover.1719842207.git.maciej.wieczor-retman@inte… [v4] https://lore.kernel.org/all/cover.1720774981.git.maciej.wieczor-retman@inte… [v5] https://lore.kernel.org/all/cover.1730206468.git.maciej.wieczor-retman@inte… [v6] https://lore.kernel.org/all/cover.1733136454.git.maciej.wieczor-retman@inte… [v7] https://lore.kernel.org/all/cover.1733741950.git.maciej.wieczor-retman@inte… Maciej Wieczor-Retman (2): selftests/resctrl: Adjust effective L3 cache size with SNC enabled selftests/resctrl: Discover SNC kernel support and adjust messages tools/testing/selftests/resctrl/Makefile | 1 + tools/testing/selftests/resctrl/cmt_test.c | 4 +- tools/testing/selftests/resctrl/mba_test.c | 2 + tools/testing/selftests/resctrl/mbm_test.c | 4 +- tools/testing/selftests/resctrl/resctrl.h | 6 + .../testing/selftests/resctrl/resctrl_tests.c | 9 +- tools/testing/selftests/resctrl/resctrlfs.c | 137 ++++++++++++++++++ 7 files changed, 158 insertions(+), 5 deletions(-) -- 2.47.1

5 months, 3 weeks

3
9
0 0

[PATCH v2] kunit: Introduce autorun option

by Stanislav Kinsburskii

The new option controls tests run on boot or module load. With the new debugfs "run" dentry allowing to run tests on demand, an ability to disable automatic tests run becomes a useful option in case of intrusive tests. The option is set to true by default to preserve the existent behavior. It can be overridden by either the corresponding module option or by the corresponding config build option. Signed-off-by: Stanislav Kinsburskii <skinsburskii(a)linux.microsoft.com> --- include/kunit/test.h | 4 +++- lib/kunit/Kconfig | 12 ++++++++++++ lib/kunit/debugfs.c | 2 +- lib/kunit/executor.c | 21 +++++++++++++++++++-- lib/kunit/test.c | 6 ++++-- 5 files changed, 39 insertions(+), 6 deletions(-) diff --git a/include/kunit/test.h b/include/kunit/test.h index 34b71e42fb10..58dbab60f853 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -312,6 +312,7 @@ static inline void kunit_set_failure(struct kunit *test) } bool kunit_enabled(void); +bool kunit_autorun(void); const char *kunit_action(void); const char *kunit_filter_glob(void); char *kunit_filter(void); @@ -334,7 +335,8 @@ kunit_filter_suites(const struct kunit_suite_set *suite_set, int *err); void kunit_free_suite_set(struct kunit_suite_set suite_set); -int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites); +int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites, + bool run_tests); void __kunit_test_suites_exit(struct kunit_suite **suites, int num_suites); diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index 34d7242d526d..a97897edd964 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -81,4 +81,16 @@ config KUNIT_DEFAULT_ENABLED In most cases this should be left as Y. Only if additional opt-in behavior is needed should this be set to N. +config KUNIT_AUTORUN_ENABLED + bool "Default value of kunit.autorun" + default y + help + Sets the default value of kunit.autorun. If set to N then KUnit + tests will not run after initialization unless kunit.autorun=1 is + passed to the kernel command line. The test can still be run manually + via debugfs interface. + + In most cases this should be left as Y. Only if additional opt-in + behavior is needed should this be set to N. + endif # KUNIT diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..9df064f40d98 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -145,7 +145,7 @@ static ssize_t debugfs_run(struct file *file, struct inode *f_inode = file->f_inode; struct kunit_suite *suite = (struct kunit_suite *) f_inode->i_private; - __kunit_test_suites_init(&suite, 1); + __kunit_test_suites_init(&suite, 1, true); return count; } diff --git a/lib/kunit/executor.c b/lib/kunit/executor.c index 34b7b6833df3..3f39955cb0f1 100644 --- a/lib/kunit/executor.c +++ b/lib/kunit/executor.c @@ -29,6 +29,22 @@ const char *kunit_action(void) return action_param; } +/* + * Run KUnit tests after initialization + */ +#ifdef CONFIG_KUNIT_AUTORUN_ENABLED +static bool autorun_param = true; +#else +static bool autorun_param; +#endif +module_param_named(autorun, autorun_param, bool, 0); +MODULE_PARM_DESC(autorun, "Run KUnit tests after initialization"); + +bool kunit_autorun(void) +{ + return autorun_param; +} + static char *filter_glob_param; static char *filter_param; static char *filter_action_param; @@ -260,13 +276,14 @@ kunit_filter_suites(const struct kunit_suite_set *suite_set, void kunit_exec_run_tests(struct kunit_suite_set *suite_set, bool builtin) { size_t num_suites = suite_set->end - suite_set->start; + bool autorun = kunit_autorun(); - if (builtin || num_suites) { + if (autorun && (builtin || num_suites)) { pr_info("KTAP version 1\n"); pr_info("1..%zu\n", num_suites); } - __kunit_test_suites_init(suite_set->start, num_suites); + __kunit_test_suites_init(suite_set->start, num_suites, autorun); } void kunit_exec_list_tests(struct kunit_suite_set *suite_set, bool include_attr) diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 089c832e3cdb..146d1b48a096 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -708,7 +708,8 @@ bool kunit_enabled(void) return enable_param; } -int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites) +int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_suites, + bool run_tests) { unsigned int i; @@ -731,7 +732,8 @@ int __kunit_test_suites_init(struct kunit_suite * const * const suites, int num_ for (i = 0; i < num_suites; i++) { kunit_init_suite(suites[i]); - kunit_run_tests(suites[i]); + if (run_tests) + kunit_run_tests(suites[i]); } static_branch_dec(&kunit_running);

5 months, 3 weeks

3
2
0 0

[PATCH for-next v2] selftests/Makefile: override the srctree for out-of-tree builds

by Li Zhijian

Fixes an issue where out-of-tree kselftest builds fail when building the BPF and bpftools components. The failure occurs because the top-level Makefile passes a relative srctree path to its sub-Makefiles, which leads to errors in locating necessary files. For example, the following error is encountered: ``` $ make V=1 O=$build/ TARGETS=hid kselftest-all ... make -C ../tools/testing/selftests all make[4]: Entering directory '/path/to/linux/tools/testing/selftests/hid' make -C /path/to/linux/tools/testing/selftests/../../../tools/lib/bpf OUTPUT=/path/to/linux/O/kselftest/hid/tools/build/libbpf/ \ EXTRA_CFLAGS='-g -O0' \ DESTDIR=/path/to/linux/O/kselftest/hid/tools prefix= all install_headers make[5]: Entering directory '/path/to/linux/tools/lib/bpf' ... make[5]: Entering directory '/path/to/linux/tools/bpf/bpftool' Makefile:127: ../tools/build/Makefile.feature: No such file or directory make[5]: *** No rule to make target '../tools/build/Makefile.feature'. Stop. ``` To resolve this, override the srctree in the kselftests's top Makefile when performing an out-of-tree build. This ensures that all sub-Makefiles have the correct path to the source tree, preventing directory resolution errors. Signed-off-by: Li Zhijian <lizhijian(a)fujitsu.com> --- Cc: Masahiro Yamada <masahiroy(a)kernel.org> V2: - handle srctree in selftests itself rather than the linux' top Makefile # Masahiro Yamada <masahiroy(a)kernel.org> V1: https://lore.kernel.org/lkml/20241217031052.69744-1-lizhijian@fujitsu.com/ --- tools/testing/selftests/Makefile | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3d8a80abd4f0..ab82278353cf 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -154,15 +154,19 @@ override LDFLAGS = override MAKEFLAGS = endif +top_srcdir ?= ../../.. + # Append kselftest to KBUILD_OUTPUT and O to avoid cluttering # KBUILD_OUTPUT with selftest objects and headers installed # by selftests Makefile or lib.mk. +# Override the `srctree` variable to ensure it is correctly resolved in +# sub-Makefiles, such as those within `bpf`, when managing targets like +# `net` and `hid`. ifdef building_out_of_srctree override LDFLAGS = +override srctree := $(top_srcdir) endif -top_srcdir ?= ../../.. - ifeq ("$(origin O)", "command line") KBUILD_OUTPUT := $(O) endif -- 2.44.0

5 months, 3 weeks

4
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror