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

[PATCH v2] kselftest/arm64: signal: fix/refactor SVE vector length enumeration

by Andre Przywara

Currently a number of SVE/SME related tests have almost identical functions to enumerate all supported vector lengths. However over time the copy&pasted code has diverged, allowing some bugs to creep in: - fake_sigreturn_sme_change_vl reports a failure, not a SKIP if only one vector length is supported (but the SVE version is fine) - fake_sigreturn_sme_change_vl tries to set the SVE vector length, not the SME one (but the other SME tests are fine) - za_no_regs keeps iterating forever if only one vector length is supported (but za_regs is correct) Since those bugs seem to be mostly copy&paste ones, let's consolidate the enumeration loop into one shared function, and just call that from each test. That should fix the above bugs, and prevent similar issues from happening again. Fixes: 4963aeb35a9e ("kselftest/arm64: signal: Add SME signal handling tests") Signed-off-by: Andre Przywara <andre.przywara(a)arm.com> --- Hi, a small update, making the SME VL loop check more generic, and adding a comment about the reason we have that in the first place. Cheers, Andre tools/testing/selftests/arm64/signal/Makefile | 2 +- .../selftests/arm64/signal/sve_helpers.c | 56 +++++++++++++++++++ .../selftests/arm64/signal/sve_helpers.h | 21 +++++++ .../testcases/fake_sigreturn_sme_change_vl.c | 31 +++------- .../testcases/fake_sigreturn_sve_change_vl.c | 30 ++-------- .../arm64/signal/testcases/ssve_regs.c | 36 +++--------- .../arm64/signal/testcases/ssve_za_regs.c | 36 +++--------- .../arm64/signal/testcases/sve_regs.c | 32 +++-------- .../arm64/signal/testcases/za_no_regs.c | 32 +++-------- .../arm64/signal/testcases/za_regs.c | 36 +++--------- 10 files changed, 131 insertions(+), 181 deletions(-) create mode 100644 tools/testing/selftests/arm64/signal/sve_helpers.c create mode 100644 tools/testing/selftests/arm64/signal/sve_helpers.h diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile index 37c8207b99cfc..1381039fb36f9 100644 --- a/tools/testing/selftests/arm64/signal/Makefile +++ b/tools/testing/selftests/arm64/signal/Makefile @@ -23,7 +23,7 @@ $(TEST_GEN_PROGS): $(PROGS) # Common test-unit targets to build common-layout test-cases executables # Needs secondary expansion to properly include the testcase c-file in pre-reqs COMMON_SOURCES := test_signals.c test_signals_utils.c testcases/testcases.c \ - signals.S + signals.S sve_helpers.c COMMON_HEADERS := test_signals.h test_signals_utils.h testcases/testcases.h .SECONDEXPANSION: diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.c b/tools/testing/selftests/arm64/signal/sve_helpers.c new file mode 100644 index 0000000000000..f57265354eaed --- /dev/null +++ b/tools/testing/selftests/arm64/signal/sve_helpers.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 ARM Limited + * + * Common helper functions for SVE and SME functionality. + */ + +#include <stdbool.h> +#include <kselftest.h> +#include <asm/sigcontext.h> +#include <sys/prctl.h> + +unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls; + +int sve_fill_vls(bool use_sme, int min_vls) +{ + int vq, vl; + int pr_set_vl = use_sme ? PR_SME_SET_VL : PR_SVE_SET_VL; + int len_mask = use_sme ? PR_SME_VL_LEN_MASK : PR_SVE_VL_LEN_MASK; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(pr_set_vl, vq * 16); + if (vl == -1) + return KSFT_FAIL; + + vl &= len_mask; + + /* + * Unlike SVE, SME does not require the minimum vector length + * to be implemented, or the VLs to be consecutive, so any call + * to the prctl might return the single implemented VL, which + * might be larger than 16. So to avoid this loop never + * terminating, bail out here when we find a higher VL than + * we asked for. + * See the ARM ARM, DDI 0487K.a, B1.4.2: I_QQRNR and I_NWYBP. + */ + if (vq < sve_vq_from_vl(vl)) + break; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + if (nvls < min_vls) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return KSFT_SKIP; + } + + return KSFT_PASS; +} diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.h b/tools/testing/selftests/arm64/signal/sve_helpers.h new file mode 100644 index 0000000000000..50948ce471cc6 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/sve_helpers.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 ARM Limited + * + * Common helper functions for SVE and SME functionality. + */ + +#ifndef __SVE_HELPERS_H__ +#define __SVE_HELPERS_H__ + +#include <stdbool.h> + +#define VLS_USE_SVE false +#define VLS_USE_SME true + +extern unsigned int vls[]; +extern unsigned int nvls; + +int sve_fill_vls(bool use_sme, int min_vls); + +#endif diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c index ebd5815b54bba..bc10585062d57 100644 --- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c @@ -11,39 +11,22 @@ #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" struct fake_sigframe sf; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sme_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SME, 2); - /* - * Enumerate up to SVE_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SVE_SET_VL, vq * 16); - if (vl == -1) - return false; + if (!res) + return true; - vl &= PR_SME_VL_LEN_MASK; + if (res == KSFT_SKIP) + td->result = KSFT_SKIP; - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); - - vls[nvls++] = vl; - } - - /* We need at least two VLs */ - if (nvls < 2) { - fprintf(stderr, "Only %d VL supported\n", nvls); - return false; - } - - return true; + return false; } static int fake_sigreturn_ssve_change_vl(struct tdescr *td, diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c index e2a452190511f..e1ccf8f85a70c 100644 --- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c +++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c @@ -12,40 +12,22 @@ #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" struct fake_sigframe sf; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sve_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SVE, 2); - /* - * Enumerate up to SVE_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SVE_SET_VL, vq * 16); - if (vl == -1) - return false; + if (!res) + return true; - vl &= PR_SVE_VL_LEN_MASK; - - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); - - vls[nvls++] = vl; - } - - /* We need at least two VLs */ - if (nvls < 2) { - fprintf(stderr, "Only %d VL supported\n", nvls); + if (res == KSFT_SKIP) td->result = KSFT_SKIP; - return false; - } - return true; + return false; } static int fake_sigreturn_sve_change_vl(struct tdescr *td, diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c index 3d37daafcff51..6dbe48cf8b09e 100644 --- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c @@ -6,51 +6,31 @@ * set up as expected. */ +#include <kselftest.h> #include <signal.h> #include <ucontext.h> #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" static union { ucontext_t uc; char buf[1024 * 64]; } context; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sme_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SME, 1); - /* - * Enumerate up to SVE_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SME_SET_VL, vq * 16); - if (vl == -1) - return false; - - vl &= PR_SME_VL_LEN_MASK; - - /* Did we find the lowest supported VL? */ - if (vq < sve_vq_from_vl(vl)) - break; + if (!res) + return true; - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); - - vls[nvls++] = vl; - } - - /* We need at least one VL */ - if (nvls < 1) { - fprintf(stderr, "Only %d VL supported\n", nvls); - return false; - } + if (res == KSFT_SKIP) + td->result = KSFT_SKIP; - return true; + return false; } static void setup_ssve_regs(void) diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c index 9dc5f128bbc0d..5557e116e9736 100644 --- a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c @@ -6,51 +6,31 @@ * signal frames is set up as expected when enabled simultaneously. */ +#include <kselftest.h> #include <signal.h> #include <ucontext.h> #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" static union { ucontext_t uc; char buf[1024 * 128]; } context; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sme_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SME, 1); - /* - * Enumerate up to SVE_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SME_SET_VL, vq * 16); - if (vl == -1) - return false; - - vl &= PR_SME_VL_LEN_MASK; - - /* Did we find the lowest supported VL? */ - if (vq < sve_vq_from_vl(vl)) - break; + if (!res) + return true; - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); - - vls[nvls++] = vl; - } - - /* We need at least one VL */ - if (nvls < 1) { - fprintf(stderr, "Only %d VL supported\n", nvls); - return false; - } + if (res == KSFT_SKIP) + td->result = KSFT_SKIP; - return true; + return false; } static void setup_regs(void) diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c index 8b16eabbb7697..8143eb1c58c18 100644 --- a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c @@ -6,47 +6,31 @@ * expected. */ +#include <kselftest.h> #include <signal.h> #include <ucontext.h> #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" static union { ucontext_t uc; char buf[1024 * 64]; } context; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sve_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SVE, 1); - /* - * Enumerate up to SVE_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SVE_SET_VL, vq * 16); - if (vl == -1) - return false; - - vl &= PR_SVE_VL_LEN_MASK; - - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); + if (!res) + return true; - vls[nvls++] = vl; - } - - /* We need at least one VL */ - if (nvls < 1) { - fprintf(stderr, "Only %d VL supported\n", nvls); - return false; - } + if (res == KSFT_SKIP) + td->result = KSFT_SKIP; - return true; + return false; } static void setup_sve_regs(void) diff --git a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c index 4d6f94b6178f3..ce26e9c2fa5e3 100644 --- a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c @@ -6,47 +6,31 @@ * expected. */ +#include <kselftest.h> #include <signal.h> #include <ucontext.h> #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" static union { ucontext_t uc; char buf[1024 * 128]; } context; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sme_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SME, 1); - /* - * Enumerate up to SME_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SME_SET_VL, vq * 16); - if (vl == -1) - return false; - - vl &= PR_SME_VL_LEN_MASK; - - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); + if (!res) + return true; - vls[nvls++] = vl; - } - - /* We need at least one VL */ - if (nvls < 1) { - fprintf(stderr, "Only %d VL supported\n", nvls); - return false; - } + if (res == KSFT_SKIP) + td->result = KSFT_SKIP; - return true; + return false; } static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c index 174ad66566964..b9e13f27f1f9a 100644 --- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c @@ -6,51 +6,31 @@ * expected. */ +#include <kselftest.h> #include <signal.h> #include <ucontext.h> #include <sys/prctl.h> #include "test_signals_utils.h" +#include "sve_helpers.h" #include "testcases.h" static union { ucontext_t uc; char buf[1024 * 128]; } context; -static unsigned int vls[SVE_VQ_MAX]; -unsigned int nvls = 0; static bool sme_get_vls(struct tdescr *td) { - int vq, vl; + int res = sve_fill_vls(VLS_USE_SME, 1); - /* - * Enumerate up to SME_VQ_MAX vector lengths - */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { - vl = prctl(PR_SME_SET_VL, vq * 16); - if (vl == -1) - return false; - - vl &= PR_SME_VL_LEN_MASK; - - /* Did we find the lowest supported VL? */ - if (vq < sve_vq_from_vl(vl)) - break; + if (!res) + return true; - /* Skip missing VLs */ - vq = sve_vq_from_vl(vl); - - vls[nvls++] = vl; - } - - /* We need at least one VL */ - if (nvls < 1) { - fprintf(stderr, "Only %d VL supported\n", nvls); - return false; - } + if (res == KSFT_SKIP) + td->result = KSFT_SKIP; - return true; + return false; } static void setup_za_regs(void) -- 2.25.1

10 months, 2 weeks

2
2
0 0

[PATCH v2 0/5] KVM: s390: selftests: Add regression tests for CPU subfunctions

by Hariharan Mari

This patch series introduces a set of regression tests for various s390x CPU subfunctions in KVM. The tests ensure that the KVM implementation accurately reflects the behavior of actual CPU instructions for these subfunctions. The series adds tests for a total of 15 instructions across five patches, covering a range of operations including sorting, compression, and various cryptographic functions. Each patch follows a consistent testing pattern: 1. Obtain the KVM_S390_VM_CPU_MACHINE_SUBFUNC attribute for the VM. 2. Execute the relevant asm instructions. 3. Compare KVM-reported results with direct instruction execution results. Testing has been performed on s390x hardware with KVM support. All tests pass successfully, verifying the correct implementation of these subfunctions in KVM. --- v2: * Fix facility_bit type from bool to int --- Hariharan Mari (5): KVM: s390: selftests: Add regression tests for SORTL and DFLTCC CPU subfunctions KVM: s390: selftests: Add regression tests for PRNO, KDSA and KMA crypto subfunctions KVM: s390: selftests: Add regression tests for KMCTR, KMF, KMO and PCC crypto subfunctions KVM: s390: selftests: Add regression tests for KMAC, KMC, KM, KIMD and KLMD crypto subfunctions KVM: s390: selftests: Add regression tests for PLO subfunctions tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/s390x/facility.h | 50 +++ .../kvm/s390x/cpumodel_subfuncs_test.c | 343 ++++++++++++++++++ 3 files changed, 394 insertions(+) create mode 100644 tools/testing/selftests/kvm/include/s390x/facility.h create mode 100644 tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c -- 2.45.2

10 months, 2 weeks

3
12
0 0

[PATCH v1 0/2] mremap refactor: check src address for vma boundaries first.

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> mremap doesn't allow relocate, expand, shrink across VMA boundaries, refactor the code to check src address range before doing anything on the destination, i.e. destination won't be unmapped, if src address failed the boundaries check. This also allows us to remove can_modify_mm from mremap.c, since the src address must be single VMA, can_modify_vma is used. It is likely this will improve the performance on mremap, previously the code does sealing check using can_modify_mm for the src address range, and the new code removed the loop (used by can_modify_mm). In order to verify this patch doesn't regress on mremap, I added tests in mseal_test, the test patch can be applied before mremap refactor patch or checkin independently. Also this patch doesn't change mseal's existing schematic: if sealing fail, user can expect the src/dst address isn't updated. So this patch can be applied regardless if we decided to go with current out-of-loop approach or in-loop approach currently in discussion. Regarding the perf test report by stress-ng [1] title: 8be7258aad: stress-ng.pagemove.page_remaps_per_sec -4.4% regression The test is using below for testing: stress-ng --timeout 60 --times --verify --metrics --no-rand-seed --pagemove 64 I can't repro this using ChromeOS, the pagemove test shows large value of stddev and stderr, and can't reasonably refect the performance impact. For example: I write a c program [2] to run the above pagemove test 10 times and calculate the stddev, stderr, for 3 commits: 1> before mseal feature is added: Ops/sec: Mean : 3564.40 Std Dev : 2737.35 (76.80% of Mean) Std Err : 865.63 (24.29% of Mean) 2> after mseal feature is added: Ops/sec: Mean : 2703.84 Std Dev : 2085.13 (77.12% of Mean) Std Err : 659.38 (24.39% of Mean) 3> after current patch (mremap refactor) Ops/sec: Mean : 3603.67 Std Dev : 2422.22 (67.22% of Mean) Std Err : 765.97 (21.26% of Mean) The result shows 21%-24% stderr, this means whatever perf improvment/impact there might be won't be measured correctly by this test. This test machine has 32G memory, Intel(R) Celeron(R) 7305, 5 CPU. And I reboot the machine before each test, and take the first 10 runs with run_stress_ng 10 (I will run longer duration to see if test still shows large stdDev,StdErr) [1] https://lore.kernel.org/lkml/202408041602.caa0372-oliver.sang@intel.com/ [2] https://github.com/peaktocreek/mmperf/blob/main/run_stress_ng.c Jeff Xu (2): mseal:selftest mremap across VMA boundaries. mseal: refactor mremap to remove can_modify_mm mm/internal.h | 24 ++ mm/mremap.c | 77 +++---- mm/mseal.c | 17 -- tools/testing/selftests/mm/mseal_test.c | 293 +++++++++++++++++++++++- 4 files changed, 353 insertions(+), 58 deletions(-) -- 2.46.0.76.ge559c4bf1a-goog

10 months, 2 weeks

5
20
0 0

[PATCH net-next v13 04/14] mm: page_frag: add '_va' suffix to page_frag API

by Yunsheng Lin

Currently the page_frag API is returning 'virtual address' or 'va' when allocing and expecting 'virtual address' or 'va' as input when freeing. As we are about to support new use cases that the caller need to deal with 'struct page' or need to deal with both 'va' and 'struct page'. In order to differentiate the API handling between 'va' and 'struct page', add '_va' suffix to the corresponding API mirroring the page_pool_alloc_va() API of the page_pool. So that callers expecting to deal with va, page or both va and page may call page_frag_alloc_va*, page_frag_alloc_pg*, or page_frag_alloc* API accordingly. CC: Alexander Duyck <alexander.duyck(a)gmail.com> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Reviewed-by: Subbaraya Sundeep <sbhatta(a)marvell.com> Acked-by: Chuck Lever <chuck.lever(a)oracle.com> Acked-by: Sagi Grimberg <sagi(a)grimberg.me> --- drivers/net/ethernet/google/gve/gve_rx.c | 4 ++-- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.h | 2 +- drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 2 +- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 4 ++-- .../marvell/octeontx2/nic/otx2_common.c | 2 +- drivers/net/ethernet/mediatek/mtk_wed_wo.c | 4 ++-- drivers/nvme/host/tcp.c | 8 +++---- drivers/nvme/target/tcp.c | 22 +++++++++---------- drivers/vhost/net.c | 6 ++--- include/linux/page_frag_cache.h | 21 +++++++++--------- include/linux/skbuff.h | 2 +- kernel/bpf/cpumap.c | 2 +- mm/page_frag_cache.c | 12 +++++----- net/core/skbuff.c | 16 +++++++------- net/core/xdp.c | 2 +- net/rxrpc/txbuf.c | 15 +++++++------ net/sunrpc/svcsock.c | 6 ++--- .../selftests/mm/page_frag/page_frag_test.c | 13 ++++++----- 19 files changed, 75 insertions(+), 70 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index acb73d4d0de6..b6c10100e462 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -729,7 +729,7 @@ static int gve_xdp_redirect(struct net_device *dev, struct gve_rx_ring *rx, total_len = headroom + SKB_DATA_ALIGN(len) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - frame = page_frag_alloc(&rx->page_cache, total_len, GFP_ATOMIC); + frame = page_frag_alloc_va(&rx->page_cache, total_len, GFP_ATOMIC); if (!frame) { u64_stats_update_begin(&rx->statss); rx->xdp_alloc_fails++; @@ -742,7 +742,7 @@ static int gve_xdp_redirect(struct net_device *dev, struct gve_rx_ring *rx, err = xdp_do_redirect(dev, &new, xdp_prog); if (err) - page_frag_free(frame); + page_frag_free_va(frame); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 8d25b6981269..00c706de2b82 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -126,7 +126,7 @@ ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) dev_kfree_skb_any(tx_buf->skb); break; case ICE_TX_BUF_XDP_TX: - page_frag_free(tx_buf->raw_buf); + page_frag_free_va(tx_buf->raw_buf); break; case ICE_TX_BUF_XDP_XMIT: xdp_return_frame(tx_buf->xdpf); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index feba314a3fe4..6379f57d8228 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -148,7 +148,7 @@ static inline int ice_skb_pad(void) * @ICE_TX_BUF_DUMMY: dummy Flow Director packet, unmap and kfree() * @ICE_TX_BUF_FRAG: mapped skb OR &xdp_buff frag, only unmap DMA * @ICE_TX_BUF_SKB: &sk_buff, unmap and consume_skb(), update stats - * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free(), stats + * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free_va(), stats * @ICE_TX_BUF_XDP_XMIT: &xdp_frame, unmap and xdp_return_frame(), stats * @ICE_TX_BUF_XSK_TX: &xdp_buff on XSk queue, xsk_buff_free(), stats */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 2719f0e20933..a1a41a14df0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -250,7 +250,7 @@ ice_clean_xdp_tx_buf(struct device *dev, struct ice_tx_buf *tx_buf, switch (tx_buf->type) { case ICE_TX_BUF_XDP_TX: - page_frag_free(tx_buf->raw_buf); + page_frag_free_va(tx_buf->raw_buf); break; case ICE_TX_BUF_XDP_XMIT: xdp_return_frame_bulk(tx_buf->xdpf, bq); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 149911e3002a..eef16a909f85 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -302,7 +302,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, /* free the skb */ if (ring_is_xdp(tx_ring)) - page_frag_free(tx_buffer->data); + page_frag_free_va(tx_buffer->data); else napi_consume_skb(tx_buffer->skb, napi_budget); @@ -2412,7 +2412,7 @@ static void ixgbevf_clean_tx_ring(struct ixgbevf_ring *tx_ring) /* Free all the Tx ring sk_buffs */ if (ring_is_xdp(tx_ring)) - page_frag_free(tx_buffer->data); + page_frag_free_va(tx_buffer->data); else dev_kfree_skb_any(tx_buffer->skb); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 87d5776e3b88..a485e988fa1d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -553,7 +553,7 @@ static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, *dma = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); if (unlikely(dma_mapping_error(pfvf->dev, *dma))) { - page_frag_free(buf); + page_frag_free_va(buf); return -ENOMEM; } diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index 7063c78bd35f..c4228719f8a4 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -142,8 +142,8 @@ mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, dma_addr_t addr; void *buf; - buf = page_frag_alloc(&q->cache, q->buf_size, - GFP_ATOMIC | GFP_DMA32); + buf = page_frag_alloc_va(&q->cache, q->buf_size, + GFP_ATOMIC | GFP_DMA32); if (!buf) break; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index a2a47d3ab99f..86906bc505de 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -506,7 +506,7 @@ static void nvme_tcp_exit_request(struct blk_mq_tag_set *set, { struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq); - page_frag_free(req->pdu); + page_frag_free_va(req->pdu); } static int nvme_tcp_init_request(struct blk_mq_tag_set *set, @@ -520,7 +520,7 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set, struct nvme_tcp_queue *queue = &ctrl->queues[queue_idx]; u8 hdgst = nvme_tcp_hdgst_len(queue); - req->pdu = page_frag_alloc(&queue->pf_cache, + req->pdu = page_frag_alloc_va(&queue->pf_cache, sizeof(struct nvme_tcp_cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!req->pdu) @@ -1337,7 +1337,7 @@ static void nvme_tcp_free_async_req(struct nvme_tcp_ctrl *ctrl) { struct nvme_tcp_request *async = &ctrl->async_req; - page_frag_free(async->pdu); + page_frag_free_va(async->pdu); } static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) @@ -1346,7 +1346,7 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) struct nvme_tcp_request *async = &ctrl->async_req; u8 hdgst = nvme_tcp_hdgst_len(queue); - async->pdu = page_frag_alloc(&queue->pf_cache, + async->pdu = page_frag_alloc_va(&queue->pf_cache, sizeof(struct nvme_tcp_cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!async->pdu) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 5bff0d5464d1..560df3db2f82 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1463,24 +1463,24 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue, c->queue = queue; c->req.port = queue->port->nport; - c->cmd_pdu = page_frag_alloc(&queue->pf_cache, + c->cmd_pdu = page_frag_alloc_va(&queue->pf_cache, sizeof(*c->cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!c->cmd_pdu) return -ENOMEM; c->req.cmd = &c->cmd_pdu->cmd; - c->rsp_pdu = page_frag_alloc(&queue->pf_cache, + c->rsp_pdu = page_frag_alloc_va(&queue->pf_cache, sizeof(*c->rsp_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!c->rsp_pdu) goto out_free_cmd; c->req.cqe = &c->rsp_pdu->cqe; - c->data_pdu = page_frag_alloc(&queue->pf_cache, + c->data_pdu = page_frag_alloc_va(&queue->pf_cache, sizeof(*c->data_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!c->data_pdu) goto out_free_rsp; - c->r2t_pdu = page_frag_alloc(&queue->pf_cache, + c->r2t_pdu = page_frag_alloc_va(&queue->pf_cache, sizeof(*c->r2t_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!c->r2t_pdu) goto out_free_data; @@ -1495,20 +1495,20 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue, return 0; out_free_data: - page_frag_free(c->data_pdu); + page_frag_free_va(c->data_pdu); out_free_rsp: - page_frag_free(c->rsp_pdu); + page_frag_free_va(c->rsp_pdu); out_free_cmd: - page_frag_free(c->cmd_pdu); + page_frag_free_va(c->cmd_pdu); return -ENOMEM; } static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c) { - page_frag_free(c->r2t_pdu); - page_frag_free(c->data_pdu); - page_frag_free(c->rsp_pdu); - page_frag_free(c->cmd_pdu); + page_frag_free_va(c->r2t_pdu); + page_frag_free_va(c->data_pdu); + page_frag_free_va(c->rsp_pdu); + page_frag_free_va(c->cmd_pdu); } static int nvmet_tcp_alloc_cmds(struct nvmet_tcp_queue *queue) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f16279351db5..6691fac01e0d 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -686,8 +686,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); - buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, - SMP_CACHE_BYTES); + buf = page_frag_alloc_va_align(&net->pf_cache, buflen, GFP_KERNEL, + SMP_CACHE_BYTES); if (unlikely(!buf)) return -ENOMEM; @@ -734,7 +734,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, return 0; err: - page_frag_free(buf); + page_frag_free_va(buf); return ret; } diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h index a758cb65a9b3..ef038a07925c 100644 --- a/include/linux/page_frag_cache.h +++ b/include/linux/page_frag_cache.h @@ -9,23 +9,24 @@ void page_frag_cache_drain(struct page_frag_cache *nc); void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, - gfp_t gfp_mask, unsigned int align_mask); +void *__page_frag_alloc_va_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask); -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) +static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc, + unsigned int fragsz, + gfp_t gfp_mask, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); + return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, -align); } -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) +static inline void *page_frag_alloc_va(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) { - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); + return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, ~0u); } -void page_frag_free(void *addr); +void page_frag_free_va(void *addr); #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7482997c719f..f9f0393e6b12 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3381,7 +3381,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, static inline void skb_free_frag(void *addr) { - page_frag_free(addr); + page_frag_free_va(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index fbdf5a1aabfe..3b70b6b071b9 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -323,7 +323,7 @@ static int cpu_map_kthread_run(void *data) /* Bring struct page memory area to curr CPU. Read by * build_skb_around via page_is_pfmemalloc(), and when - * freed written by page_frag_free call. + * freed written by page_frag_free_va call. */ prefetchw(page); } diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c index c5bc72cf018a..70fb6dead624 100644 --- a/mm/page_frag_cache.c +++ b/mm/page_frag_cache.c @@ -59,9 +59,9 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) } EXPORT_SYMBOL(__page_frag_cache_drain); -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void *__page_frag_alloc_va_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) { #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) unsigned int size = nc->size; @@ -130,16 +130,16 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc, return nc->va + (size - remaining); } -EXPORT_SYMBOL(__page_frag_alloc_align); +EXPORT_SYMBOL(__page_frag_alloc_va_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. */ -void page_frag_free(void *addr) +void page_frag_free_va(void *addr) { struct page *page = virt_to_head_page(addr); if (unlikely(put_page_testzero(page))) free_unref_page(page, compound_order(page)); } -EXPORT_SYMBOL(page_frag_free); +EXPORT_SYMBOL(page_frag_free_va); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index de2a044cc665..6cf2c51a34e1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -314,8 +314,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) fragsz = SKB_DATA_ALIGN(fragsz); local_lock_nested_bh(&napi_alloc_cache.bh_lock); - data = __page_frag_alloc_align(&nc->page, fragsz, - GFP_ATOMIC | __GFP_NOWARN, align_mask); + data = __page_frag_alloc_va_align(&nc->page, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return data; @@ -330,9 +330,9 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); fragsz = SKB_DATA_ALIGN(fragsz); - data = __page_frag_alloc_align(nc, fragsz, - GFP_ATOMIC | __GFP_NOWARN, - align_mask); + data = __page_frag_alloc_va_align(nc, fragsz, + GFP_ATOMIC | __GFP_NOWARN, + align_mask); } else { local_bh_disable(); data = __napi_alloc_frag_align(fragsz, align_mask); @@ -751,14 +751,14 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, if (in_hardirq() || irqs_disabled()) { nc = this_cpu_ptr(&netdev_alloc_cache); - data = page_frag_alloc(nc, len, gfp_mask); + data = page_frag_alloc_va(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; } else { local_bh_disable(); local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache.page); - data = page_frag_alloc(nc, len, gfp_mask); + data = page_frag_alloc_va(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; local_unlock_nested_bh(&napi_alloc_cache.bh_lock); @@ -848,7 +848,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) } else { len = SKB_HEAD_ALIGN(len); - data = page_frag_alloc(&nc->page, len, gfp_mask); + data = page_frag_alloc_va(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); diff --git a/net/core/xdp.c b/net/core/xdp.c index bcc5551c6424..7d4e09fb478f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -387,7 +387,7 @@ void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, page_pool_put_full_page(page->pp, page, napi_direct); break; case MEM_TYPE_PAGE_SHARED: - page_frag_free(data); + page_frag_free_va(data); break; case MEM_TYPE_PAGE_ORDER0: page = virt_to_page(data); /* Assumes order0 page*/ diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index c3913d8a50d3..dccb0353ee84 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -33,8 +33,8 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ data_align = umax(data_align, L1_CACHE_BYTES); mutex_lock(&call->conn->tx_data_alloc_lock); - buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, - data_align); + buf = page_frag_alloc_va_align(&call->conn->tx_data_alloc, total, gfp, + data_align); mutex_unlock(&call->conn->tx_data_alloc_lock); if (!buf) { kfree(txb); @@ -96,17 +96,18 @@ struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_s if (!txb) return NULL; - buf = page_frag_alloc(&call->local->tx_alloc, - sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); + buf = page_frag_alloc_va(&call->local->tx_alloc, + sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); if (!buf) { kfree(txb); return NULL; } if (sack_size) { - buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp); + buf2 = page_frag_alloc_va(&call->local->tx_alloc, sack_size, + gfp); if (!buf2) { - page_frag_free(buf); + page_frag_free_va(buf); kfree(txb); return NULL; } @@ -180,7 +181,7 @@ static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb) rxrpc_txbuf_free); for (i = 0; i < txb->nr_kvec; i++) if (txb->kvec[i].iov_base) - page_frag_free(txb->kvec[i].iov_base); + page_frag_free_va(txb->kvec[i].iov_base); kfree(txb); atomic_dec(&rxrpc_nr_txbuf); } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 6b3f01beb294..42d20412c1c3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1222,8 +1222,8 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, /* The stream record marker is copied into a temporary page * fragment buffer so that it can be included in rq_bvec. */ - buf = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker), - GFP_KERNEL); + buf = page_frag_alloc_va(&svsk->sk_frag_cache, sizeof(marker), + GFP_KERNEL); if (!buf) return -ENOMEM; memcpy(buf, &marker, sizeof(marker)); @@ -1235,7 +1235,7 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp, iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec, 1 + count, sizeof(marker) + rqstp->rq_res.len); ret = sock_sendmsg(svsk->sk_sock, &msg); - page_frag_free(buf); + page_frag_free_va(buf); if (ret < 0) return ret; *sentp += ret; diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index 4a009122991e..e522611452c9 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -52,7 +52,7 @@ static int page_frag_pop_thread(void *arg) if (obj) { nr--; - page_frag_free(obj); + page_frag_free_va(obj); } else { cond_resched(); } @@ -80,13 +80,16 @@ static int page_frag_push_thread(void *arg) int ret; if (test_align) { - va = page_frag_alloc_align(&test_frag, test_alloc_len, - GFP_KERNEL, SMP_CACHE_BYTES); + va = page_frag_alloc_va_align(&test_frag, + test_alloc_len, + GFP_KERNEL, + SMP_CACHE_BYTES); WARN_ONCE((unsigned long)va & (SMP_CACHE_BYTES - 1), "unaligned va returned\n"); } else { - va = page_frag_alloc(&test_frag, test_alloc_len, GFP_KERNEL); + va = page_frag_alloc_va(&test_frag, test_alloc_len, + GFP_KERNEL); } if (!va) @@ -94,7 +97,7 @@ static int page_frag_push_thread(void *arg) ret = __ptr_ring_produce(ring, va); if (ret) { - page_frag_free(va); + page_frag_free_va(va); cond_resched(); } else { nr--; -- 2.33.0

10 months, 2 weeks

3
8
0 0

[PATCH net-next v5] net: netconsole: selftests: Create a new netconsole selftest

by Breno Leitao

Adds a selftest that creates two virtual interfaces, assigns one to a new namespace, and assigns IP addresses to both. It listens on the destination interface using socat and configures a dynamic target on netconsole, pointing to the destination IP address. The test then checks if the message was received properly on the destination interface. Signed-off-by: Breno Leitao <leitao(a)debian.org> Acked-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Changelog: v5: * Replace check_file_size() by "test -s" (Matthieu) v4: * Avoid sleeping in waiting for sockets and files (Matthieu Baerts) * Some other improvements (Matthieu Baerts) * Add configfs as a dependency (Jakub) * https://lore.kernel.org/all/20240816132450.346744-1-leitao@debian.org/ v3: * Defined CONFIGs in config file (Jakub) * Identention fixes (Petr Machata) * Use setup_ns in a better way (Matthieu Baerts) * Add dependencies in TEST_INCLUDES (Hangbin Liu) * https://lore.kernel.org/all/20240815095157.3064722-1-leitao@debian.org/ v2: * Change the location of the path (Jakub) * Move from veth to netdevsim * Other small changes in dependency checks and cleanup * https://lore.kernel.org/all/20240813183825.837091-1-leitao@debian.org/ v1: * https://lore.kernel.org/all/ZqyUHN770pjSofTC@gmail.com/ MAINTAINERS | 1 + tools/testing/selftests/drivers/net/Makefile | 5 +- tools/testing/selftests/drivers/net/config | 4 + .../selftests/drivers/net/netcons_basic.sh | 225 ++++++++++++++++++ 4 files changed, 234 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/drivers/net/netcons_basic.sh diff --git a/MAINTAINERS b/MAINTAINERS index 5dbf23cf11c8..9a371ddd8719 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15772,6 +15772,7 @@ M: Breno Leitao <leitao(a)debian.org> S: Maintained F: Documentation/networking/netconsole.rst F: drivers/net/netconsole.c +F: tools/testing/selftests/drivers/net/netcons_basic.sh NETDEVSIM M: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index e54f382bcb02..39fb97a8c1df 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,8 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_INCLUDES := $(wildcard lib/py/*.py) +TEST_INCLUDES := $(wildcard lib/py/*.py) \ + ../../net/net_helper.sh \ + ../../net/lib.sh \ TEST_PROGS := \ + netcons_basic.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index f6a58ce8a230..a2d8af60876d 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -1,2 +1,6 @@ CONFIG_IPV6=y CONFIG_NETDEVSIM=m +CONFIG_CONFIGFS_FS=y +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETCONSOLE_EXTENDED_LOG=y diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh new file mode 100755 index 000000000000..137875505663 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -0,0 +1,225 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test creates two netdevsim virtual interfaces, assigns one of them (the +# "destination interface") to a new namespace, and assigns IP addresses to both +# interfaces. +# +# It listens on the destination interface using socat and configures a dynamic +# target on netconsole, pointing to the destination IP address. +# +# Finally, it checks whether the message was received properly on the +# destination interface. Note that this test may pollute the kernel log buffer +# (dmesg) and relies on dynamic configuration and namespaces being configured. +# +# Author: Breno Leitao <leitao(a)debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +# Simple script to test dynamic targets in netconsole +SRCIF="" # to be populated later +SRCIP=192.168.1.1 +DSTIF="" # to be populated later +DSTIP=192.168.1.2 + +PORT="6666" +MSG="netconsole selftest" +TARGET=$(mktemp -u netcons_XXXXX) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# NAMESPACE will be populated by setup_ns with a random value +NAMESPACE="" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) + +# Used to create and delete namespaces +source "${SCRIPTDIR}"/../../net/lib.sh +source "${SCRIPTDIR}"/../../net/net_helper.sh + +# Create netdevsim interfaces +create_ifaces() { + local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle 2> /dev/null || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" + exec {INITNS_FD}</proc/self/ns/net + + # Bind the dst interface to namespace + ip link set "${DSTIF}" netns "${NAMESPACE}" + + # Linking one device to the other one (on the other namespace} + if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK + then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit "${ksft_skip}" + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # setup_ns function is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + exit "${ksft_pass}" +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This test must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi +} + +# ========== # +# Start here # +# ========== # +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2 > /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + +# Make sure the message was received in the dst part +# and exit +validate_result "${OUTPUT_FILE}" -- 2.43.5

10 months, 2 weeks

3
3
0 0

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-15-gc049acee3c71c)

by kernelci.org bot

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-15-gc049acee3c71c) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.11-rc1-15-gc049a… Tree: kselftest Branch: next Git Describe: v6.11-rc1-15-gc049acee3c71c Git Commit: c049acee3c71cfc26c739f82617a84e13e471a45 Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 --- For more info write to <info(a)kernelci.org>

10 months, 2 weeks

1
0
0 0

[PATCH] selftests/ftrace: Fix test to handle both old and new kernels

by Steven Rostedt

From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> The function "scheduler_tick" was renamed to "sched_tick" and a selftest that used that function for testing function trace filtering used that function as part of the test. But the change causes it to fail when run on older kernels. As tests should not fail on older kernels, add a check to see which name is available before testing. Fixes: 86dd6c04ef9f2 ("sched/balancing: Rename scheduler_tick() => sched_tick()") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- .../ftrace/test.d/ftrace/func_set_ftrace_file.tc | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc index 073a748b9380..263f6b798c85 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc @@ -19,7 +19,14 @@ fail() { # mesg FILTER=set_ftrace_filter FUNC1="schedule" -FUNC2="sched_tick" +if grep '^sched_tick\b' available_filter_functions; then + FUNC2="sched_tick" +elif grep '^scheduler_tick\b' available_filter_functions; then + FUNC2="scheduler_tick" +else + exit_unresolved +fi + ALL_FUNCS="#### all functions enabled ####" -- 2.43.0

10 months, 2 weeks

2
3
0 0

[PATCH net-next v2] selftests: net: add helper for checking if nettest is available

by Jakub Kicinski

A few tests check if nettest exists in the $PATH before adding $PWD to $PATH and re-checking. They don't discard stderr on the first check (and nettest is built as part of selftests, so it's pretty normal for it to not be available in system $PATH). This leads to output noise: which: no nettest in (/home/virtme/tools/fs/bin:/home/virtme/tools/fs/sbin:/home/virtme/tools/fs/usr/bin:/home/virtme/tools/fs/usr/sbin:/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin) Add a common helper for the check which does silence stderr. There is another small functional change hiding here, because pmtu.sh and fib_rule_tests.sh used to return from the test case rather than completely exit. Building nettest is not hard, there should be no need to maintain the ability to selectively skip cases in its absence. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- v2: - fold in the changes from Ido v1: https://lore.kernel.org/20240817183848.658443-1-kuba@kernel.org CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org CC: Ido Schimmel <idosch(a)idosch.org> --- tools/testing/selftests/net/fcnal-test.sh | 9 +---- tools/testing/selftests/net/fib_rule_tests.sh | 37 +------------------ tools/testing/selftests/net/lib.sh | 15 ++++++++ tools/testing/selftests/net/pmtu.sh | 8 +--- tools/testing/selftests/net/settings | 1 + .../selftests/net/unicast_extensions.sh | 9 +---- .../selftests/net/vrf_route_leaking.sh | 3 +- 7 files changed, 23 insertions(+), 59 deletions(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 386ebd829df5..899dbad0104b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4304,14 +4304,7 @@ elif [ "$TESTS" = "ipv6" ]; then TESTS="$TESTS_IPV6" fi -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" declare -i nfail=0 declare -i nsuccess=0 diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 89034c5b69dc..53c5c1ad437e 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -51,31 +51,6 @@ log_test() fi } -check_nettest() -{ - if which nettest > /dev/null 2>&1; then - return 0 - fi - - # Add the selftest directory to PATH if not already done - if [ "${SELFTEST_PATH}" = "" ]; then - SELFTEST_PATH="$(dirname $0)" - PATH="${PATH}:${SELFTEST_PATH}" - - # Now retry with the new path - if which nettest > /dev/null 2>&1; then - return 0 - fi - - if [ "${ret}" -eq 0 ]; then - ret="${ksft_skip}" - fi - echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')" - fi - - return 1 -} - setup() { set -e @@ -317,11 +292,6 @@ fib_rule6_connect_test() echo echo "IPv6 FIB rule connect tests" - if ! check_nettest; then - echo "SKIP: Could not run test without nettest tool" - return - fi - setup_peer $IP -6 rule add dsfield 0x04 table $RTABLE_PEER @@ -516,11 +486,6 @@ fib_rule4_connect_test() echo echo "IPv4 FIB rule connect tests" - if ! check_nettest; then - echo "SKIP: Could not run test without nettest tool" - return - fi - setup_peer $IP -4 rule add dsfield 0x04 table $RTABLE_PEER @@ -584,6 +549,8 @@ if [ ! -x "$(command -v ip)" ]; then exit $ksft_skip fi +check_gen_prog "nettest" + # start clean cleanup &> /dev/null setup diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8ee4489238ca..be8707bfb46e 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -125,6 +125,21 @@ slowwait_for_counter() slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +# Check for existence of tools which are built as part of selftests +# but may also already exist in $PATH +check_gen_prog() +{ + local prog_name=$1; shift + + if ! which $prog_name >/dev/null 2>/dev/null; then + PATH=$PWD:$PATH + if ! which $prog_name >/dev/null; then + echo "'$prog_name' command not found; skipping tests" + exit $ksft_skip + fi + fi +} + remove_ns_list() { local item=$1 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 24a50622406c..569bce8b6383 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -681,13 +681,7 @@ setup_xfrm() { } setup_nettest_xfrm() { - if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - return 1 - fi - fi + check_gen_prog "nettest" [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings index ed8418e8217a..a38764182822 100644 --- a/tools/testing/selftests/net/settings +++ b/tools/testing/selftests/net/settings @@ -1 +1,2 @@ timeout=3600 +profile=1 diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index f52aa5f7da52..3e751234ccfe 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -30,14 +30,7 @@ source lib.sh -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" result=0 diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index 152171fb1fc8..e9c2f71da207 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -59,7 +59,6 @@ # while it is forwarded between different vrfs. source lib.sh -PATH=$PWD:$PWD/tools/testing/selftests/net:$PATH VERBOSE=0 PAUSE_ON_FAIL=no DEFAULT_TTYPE=sym @@ -636,6 +635,8 @@ EOF # Some systems don't have a ping6 binary anymore command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping) +check_gen_prog "nettest" + TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_local ipv4_tcp_local ipv4_udp_local ipv4_ping_ttl_asym ipv4_traceroute_asym" TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_local ipv6_tcp_local ipv6_udp_local -- 2.46.0

10 months, 2 weeks

3
5
0 0

[PATCH net 00/14] mptcp: pm: fix IDs not being reusable

by Matthieu Baerts (NGI0)

Here are more fixes for the MPTCP in-kernel path-manager. In this series, the fixes are around the endpoint IDs not being reusable for on-going connections when re-creating endpoints with previously used IDs. - Patch 1 fixes this case for endpoints being used to send ADD_ADDR. Patch 2 validates this fix. The issue is present since v5.10. - Patch 3 fixes this case for endpoints being used to establish new subflows. Patch 4 validates this fix. The issue is present since v5.10. - Patch 5 fixes this case when all endpoints are flushed. Patch 6 validates this fix. The issue is present since v5.13. - Patch 7 removes a helper that is confusing, and introduced in v5.10. It helps simplifying the next patches. - Patch 8 makes sure a 'subflow' counter is only decremented when removing a 'subflow' endpoint. Can be backported up to v5.13. - Patch 9 is similar, but for a 'signal' counter. Can be backported up to v5.10. - Patch 10 checks the last max accepted ADD_ADDR limit before accepting new ADD_ADDR. For v5.10 as well. - Patch 11 removes a wrong restriction for the userspace PM, added during a refactoring in v6.5. - Patch 12 makes sure the fullmesh mode sets the ID 0 when a new subflow using the source address of the initial subflow is created. Patch 13 covers this case. This issue is present since v5.15. - Patch 14 avoid possible UaF when selecting an address from the endpoints list. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (14): mptcp: pm: re-using ID of unused removed ADD_ADDR selftests: mptcp: join: check re-using ID of unused ADD_ADDR mptcp: pm: re-using ID of unused removed subflows selftests: mptcp: join: check re-using ID of closed subflow mptcp: pm: re-using ID of unused flushed subflows selftests: mptcp: join: test for flush/re-add endpoints mptcp: pm: remove mptcp_pm_remove_subflow() mptcp: pm: only mark 'subflow' endp as available mptcp: pm: only decrement add_addr_accepted for MPJ req mptcp: pm: check add_addr_accept_max before accepting new ADD_ADDR mptcp: pm: only in-kernel cannot have entries with ID 0 mptcp: pm: fullmesh: select the right ID later selftests: mptcp: join: validate fullmesh endp on 1st sf mptcp: pm: avoid possible UaF when selecting endp net/mptcp/pm.c | 13 --- net/mptcp/pm_netlink.c | 142 ++++++++++++++++-------- net/mptcp/protocol.h | 3 - tools/testing/selftests/net/mptcp/mptcp_join.sh | 76 +++++++++++-- 4 files changed, 160 insertions(+), 74 deletions(-) --- base-commit: 565d121b69980637f040eb4d84289869cdaabedf change-id: 20240819-net-mptcp-pm-reusing-id-eb08827b7be6 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

10 months, 2 weeks

2
15
0 0

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-13-g41f37c852ac3f)

by kernelci.org bot

kselftest/next kselftest-lkdtm: 1 runs, 1 regressions (v6.11-rc1-13-g41f37c852ac3f) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-13-g41… Test: kselftest-lkdtm Tree: kselftest Branch: next Describe: v6.11-rc1-13-g41f37c852ac3f URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 41f37c852ac3fbfd072a00281b60dc7ba056be8c Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66c5128498efe3795cc86925 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-13-g41f37c852ac3f/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-13-g41f37c852ac3f/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lkdtm.login: https://kernelci.org/test/case/id/66c5128498efe3795cc86926 failing since 21 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

10 months, 2 weeks

1
0
0 0

kselftest/next kselftest-seccomp: 1 runs, 1 regressions (v6.11-rc1-13-g41f37c852ac3f)

by kernelci.org bot

kselftest/next kselftest-seccomp: 1 runs, 1 regressions (v6.11-rc1-13-g41f37c852ac3f) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-13-g41… Test: kselftest-seccomp Tree: kselftest Branch: next Describe: v6.11-rc1-13-g41f37c852ac3f URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 41f37c852ac3fbfd072a00281b60dc7ba056be8c Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66c5157c7ea50df009c86855 Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-13-g41f37c852ac3f/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-13-g41f37c852ac3f/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-seccomp.login: https://kernelci.org/test/case/id/66c5157c7ea50df009c86856 failing since 21 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

10 months, 2 weeks

1
0
0 0

kselftest/next kselftest-lib: 1 runs, 1 regressions (v6.11-rc1-13-g41f37c852ac3f)

by kernelci.org bot

kselftest/next kselftest-lib: 1 runs, 1 regressions (v6.11-rc1-13-g41f37c852ac3f) Regressions Summary ------------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/job/kselftest/branch/next/kernel/v6.11-rc1-13-g41… Test: kselftest-lib Tree: kselftest Branch: next Describe: v6.11-rc1-13-g41f37c852ac3f URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git SHA: 41f37c852ac3fbfd072a00281b60dc7ba056be8c Test Regressions ---------------- platform | arch | lab | compiler | defconfig | regressions ----------------------------+------+-------------+----------+------------------------------+------------ stm32mp157a-dhcor-avenger96 | arm | lab-broonie | gcc-12 | multi_v7_defconfig+kselftest | 1 Details: https://kernelci.org/test/plan/id/66c5140122b4b11599c8685e Results: 0 PASS, 1 FAIL, 0 SKIP Full config: multi_v7_defconfig+kselftest Compiler: gcc-12 (arm-linux-gnueabihf-gcc (Debian 12.2.0-14) 12.2.0) Plain log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-13-g41f37c852ac3f/ar… HTML log: https://storage.kernelci.org//kselftest/next/v6.11-rc1-13-g41f37c852ac3f/ar… Rootfs: http://storage.kernelci.org/images/rootfs/debian/bookworm-kselftest/2024031… * kselftest-lib.login: https://kernelci.org/test/case/id/66c5140122b4b11599c8685f failing since 21 days (last pass: v6.10-rc7-29-gdf09b0bb09ea, first fail: v6.11-rc1)

10 months, 2 weeks

1
0
0 0

[PATCH net-next] selftests: net/forwarding: spawn sh inside vrf to speed up ping loop

by Jakub Kicinski

Looking at timestamped output of netdev CI reveals that most of the time in forwarding tests for custom route hashing is spent on a single case, namely the test which uses ping (mausezahn does not support flow labels). On a non-debug kernel we spend 714 of 730 total test runtime (97%) on this test case. While having flow label support in a traffic gen tool / mausezahn would be best, we can significantly speed up the loop by putting ip vrf exec outside of the iteration. In a test of 1000 pings using a normal loop takes 50 seconds to finish. While using: ip vrf exec $vrf sh -c "$loop-body" takes 12 seconds (1/4 of the time). Some of the slowness is likely due to our inefficient virtualization setup, but even on my laptop running "ip link help" 16k times takes 25-30 seconds, so I think it's worth optimizing even for fastest setups. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: idosch(a)nvidia.com CC: linux-kselftest(a)vger.kernel.org --- .../selftests/net/forwarding/custom_multipath_hash.sh | 8 ++++---- .../selftests/net/forwarding/gre_custom_multipath_hash.sh | 8 ++++---- .../net/forwarding/ip6gre_custom_multipath_hash.sh | 8 ++++---- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh index 1783c10215e5..7d531f7091e6 100755 --- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -224,10 +224,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh index 9788bd0f6e8b..dda11a4a9450 100755 --- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -319,10 +319,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh index 2ab9eaaa5532..e28b4a079e52 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -321,10 +321,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() -- 2.46.0

10 months, 2 weeks

4
3
0 0

[PATCH v2] kunit: Device wrappers should also manage driver name

by David Gow

kunit_driver_create() accepts a name for the driver, but does not copy it, so if that name is either on the stack, or otherwise freed, we end up with a use-after-free when the driver is cleaned up. Instead, strdup() the name, and manage it as another KUnit allocation. As there was no existing kunit_kstrdup(), we add one. Further, add a kunit_ variant of strdup_const() and kfree_const(), so we don't need to allocate and manage the string in the majority of cases where it's a constant. However, these are inline functions, and is_kernel_rodata() only works for built-in code. This causes problems in two cases: - If kunit is built as a module, __{start,end}_rodata is not defined. - If a kunit test using these functions is built as a module, it will suffer the same fate. This fixes a KASAN splat with overflow.overflow_allocation_test, when built as a module. Restrict the is_kernel_rodata() case to when KUnit is built as a module, which fixes the first case, at the cost of losing the optimisation. Also, make kunit_{kstrdup,kfree}_const non-inline, so that other modules using them will not accidentally depend on is_kernel_rodata(). If KUnit is built-in, they'll benefit from the optimisation, if KUnit is not, they won't, but the string will be properly duplicated. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Reported-by: Nico Pache <npache(a)redhat.com> Closes: https://groups.google.com/g/kunit-dev/c/81V9b9QYON0 Reviewed-by: Kees Cook <kees(a)kernel.org> Reviewed-by: Maxime Ripard <mripard(a)kernel.org> Reviewed-by: Rae Moar <rmoar(a)google.com> Signed-off-by: David Gow <davidgow(a)google.com> --- This is a combination of the previous version of this patch with the follow-up fix "kunit: Fix kunit_kstrdup_const() with modules". kunit_kstrdup_const() now falls back to kstrdup() if KUnit is built as a module, and is no longer inlined. This should fix the issues we'd seen before. I've not tried doing something fancy by looking at module rodata sections: it might be a possible optimisation, but it seems like it'd overcomplicate things for this initial change. If we hit a KUnit test where this is a bottleneck (or if I have some more spare time), we can look into it. The overflow_kunit test has been fixed independently to not rely on this anyway, so there shouldn't be any current cases of this causing issues, but it's worth making the API robust regardless. Changes since previous version: https://lore.kernel.org/linux-kselftest/20240731070207.3918687-1-davidgow@g… - Fix module support by integrating: https://lore.kernel.org/linux-kselftest/20240806020136.3481593-1-davidgow@g… --- include/kunit/test.h | 48 ++++++++++++++++++++++++++++++++++++++++++++ lib/kunit/device.c | 7 +++++-- lib/kunit/test.c | 19 ++++++++++++++++++ 3 files changed, 72 insertions(+), 2 deletions(-) diff --git a/include/kunit/test.h b/include/kunit/test.h index e2a1f0928e8b..5ac237c949a0 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -28,6 +28,7 @@ #include <linux/types.h> #include <asm/rwonce.h> +#include <asm/sections.h> /* Static key: true if any KUnit tests are currently running */ DECLARE_STATIC_KEY_FALSE(kunit_running); @@ -480,6 +481,53 @@ static inline void *kunit_kcalloc(struct kunit *test, size_t n, size_t size, gfp return kunit_kmalloc_array(test, n, size, gfp | __GFP_ZERO); } + +/** + * kunit_kfree_const() - conditionally free test managed memory + * @x: pointer to the memory + * + * Calls kunit_kfree() only if @x is not in .rodata section. + * See kunit_kstrdup_const() for more information. + */ +void kunit_kfree_const(struct kunit *test, const void *x); + +/** + * kunit_kstrdup() - Duplicates a string into a test managed allocation. + * + * @test: The test context object. + * @str: The NULL-terminated string to duplicate. + * @gfp: flags passed to underlying kmalloc(). + * + * See kstrdup() and kunit_kmalloc_array() for more information. + */ +static inline char *kunit_kstrdup(struct kunit *test, const char *str, gfp_t gfp) +{ + size_t len; + char *buf; + + if (!str) + return NULL; + + len = strlen(str) + 1; + buf = kunit_kmalloc(test, len, gfp); + if (buf) + memcpy(buf, str, len); + return buf; +} + +/** + * kunit_kstrdup_const() - Conditionally duplicates a string into a test managed allocation. + * + * @test: The test context object. + * @str: The NULL-terminated string to duplicate. + * @gfp: flags passed to underlying kmalloc(). + * + * Calls kunit_kstrdup() only if @str is not in the rodata section. Must be freed with + * kunit_kfree_const() -- not kunit_kfree(). + * See kstrdup_const() and kunit_kmalloc_array() for more information. + */ +const char *kunit_kstrdup_const(struct kunit *test, const char *str, gfp_t gfp); + /** * kunit_vm_mmap() - Allocate KUnit-tracked vm_mmap() area * @test: The test context object. diff --git a/lib/kunit/device.c b/lib/kunit/device.c index 25c81ed465fb..520c1fccee8a 100644 --- a/lib/kunit/device.c +++ b/lib/kunit/device.c @@ -89,7 +89,7 @@ struct device_driver *kunit_driver_create(struct kunit *test, const char *name) if (!driver) return ERR_PTR(err); - driver->name = name; + driver->name = kunit_kstrdup_const(test, name, GFP_KERNEL); driver->bus = &kunit_bus_type; driver->owner = THIS_MODULE; @@ -192,8 +192,11 @@ void kunit_device_unregister(struct kunit *test, struct device *dev) const struct device_driver *driver = to_kunit_device(dev)->driver; kunit_release_action(test, device_unregister_wrapper, dev); - if (driver) + if (driver) { + const char *driver_name = driver->name; kunit_release_action(test, driver_unregister_wrapper, (void *)driver); + kunit_kfree_const(test, driver_name); + } } EXPORT_SYMBOL_GPL(kunit_device_unregister); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index e8b1b52a19ab..089c832e3cdb 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -874,6 +874,25 @@ void kunit_kfree(struct kunit *test, const void *ptr) } EXPORT_SYMBOL_GPL(kunit_kfree); +void kunit_kfree_const(struct kunit *test, const void *x) +{ +#if !IS_MODULE(CONFIG_KUNIT) + if (!is_kernel_rodata((unsigned long)x)) +#endif + kunit_kfree(test, x); +} +EXPORT_SYMBOL_GPL(kunit_kfree_const); + +const char *kunit_kstrdup_const(struct kunit *test, const char *str, gfp_t gfp) +{ +#if !IS_MODULE(CONFIG_KUNIT) + if (is_kernel_rodata((unsigned long)str)) + return str; +#endif + return kunit_kstrdup(test, str, gfp); +} +EXPORT_SYMBOL_GPL(kunit_kstrdup_const); + void kunit_cleanup(struct kunit *test) { struct kunit_resource *res; -- 2.46.0.184.g6999bdac58-goog

10 months, 2 weeks

3
2
0 0

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-13-g41f37c852ac3f)

by kernelci.org bot

kselftest/next build: 7 builds: 2 failed, 5 passed, 1 warning (v6.11-rc1-13-g41f37c852ac3f) Full Build Summary: https://kernelci.org/build/kselftest/branch/next/kernel/v6.11-rc1-13-g41f37… Tree: kselftest Branch: next Git Describe: v6.11-rc1-13-g41f37c852ac3f Git Commit: 41f37c852ac3fbfd072a00281b60dc7ba056be8c Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 4 unique architectures Build Failures Detected: arm64: defconfig+kselftest+arm64-chromebook: (clang-16) FAIL defconfig+kselftest+arm64-chromebook: (gcc-12) FAIL Warnings Detected: arm64: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- defconfig+kselftest (arm64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, gcc-12) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- defconfig+kselftest+arm64-chromebook (arm64, clang-16) — FAIL, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x39: relocation to !ENDBR: .text+0x14ef94 -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, gcc-12) — PASS, 0 errors, 0 warnings, 0 section mismatches --- For more info write to <info(a)kernelci.org>

10 months, 2 weeks

1
0
0 0

[PATCH v9 00/13] 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 ran into issues booting the board after 6.9-rc1 so I applied these patches to 6.8. There are a couple of minor merge conflicts that do arrise when doing that, so please let me know if you have been able to boot this board with a 6.9 kernel. 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 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 (12): 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 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.vendor | 26 ++ arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi | 3 +- arch/riscv/include/asm/cpufeature.h | 2 + arch/riscv/include/asm/csr.h | 15 + 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 | 42 +++ .../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/cpufeature.c | 52 +++- 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 | 18 ++ .../riscv/kernel/vendor_extensions/thead_hwprobe.c | 19 ++ 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 +++++++++++++-------- 34 files changed, 901 insertions(+), 271 deletions(-) --- base-commit: 7c08a2615f149f64fb1bb4660997e152fb3a11a7 change-id: 20240530-xtheadvector-833d3d17b423 -- - Charlie

10 months, 2 weeks

2
18
0 0

[PATCH v2] selftests: kvm: fix mkdir error when building for unsupported arch

by Muhammad Usama Anjum

The tests are built on per architecture basis. When unsupported architecture is specified, it has no tests and TEST_GEN_PROGS is empty. The lib.mk has support for not building anything for such case. But KVM makefile doesn't handle such case correctly. It doesn't check if TEST_GEN_PROGS is empty or not and try to create directory by mkdir. Hence mkdir generates the error. mkdir: missing operand Try 'mkdir --help' for more information. This can be easily fixed by checking if TEST_GEN_PROGS isn't empty before calling mkdir. Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Sean Christopherson <seanjc(a)google.com> Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> --- Changes since v1: - Instead of ignoring error, check TEST_GEN_PROGS's validity first --- tools/testing/selftests/kvm/Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 48d32c5aa3eb7..9f8ed82ff1d65 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -317,7 +317,9 @@ $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS) $(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ +ifneq ($(strip $(TEST_GEN_PROGS)),) $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) +endif $(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS) $(TEST_GEN_PROGS): $(LIBKVM_OBJS) $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) -- 2.39.2

10 months, 2 weeks

6
5
0 0

[PATCH bpf-next] bpf: use kfunc hooks instead of program types

by Matteo Croce

From: Matteo Croce <teknoraver(a)meta.com> Pass to register_btf_kfunc_id_set() a btf_kfunc_hook directly, instead of a bpf_prog_type. Many program types share the same kfunc hook, so some calls to register_btf_kfunc_id_set() can be removed. Tested compiling the kernel with -Werror=enum-conversion to catch all the occourrences. Signed-off-by: Matteo Croce <teknoraver(a)meta.com> --- Documentation/bpf/kfuncs.rst | 2 +- drivers/hid/bpf/hid_bpf_dispatch.c | 4 +-- fs/bpf_fs_kfuncs.c | 2 +- fs/verity/measure.c | 2 +- include/linux/btf.h | 22 ++++++++++++++-- kernel/bpf/arena.c | 2 +- kernel/bpf/btf.c | 23 +---------------- kernel/bpf/cpumask.c | 6 ++--- kernel/bpf/crypto.c | 8 +++--- kernel/bpf/helpers.c | 15 +++++------ kernel/bpf/map_iter.c | 2 +- kernel/cgroup/rstat.c | 2 +- kernel/trace/bpf_trace.c | 4 +-- net/bpf/test_run.c | 6 ++--- net/core/filter.c | 25 ++++++++----------- net/core/xdp.c | 2 +- net/ipv4/bpf_tcp_ca.c | 2 +- net/ipv4/fou_bpf.c | 2 +- net/ipv4/tcp_bbr.c | 2 +- net/ipv4/tcp_cubic.c | 2 +- net/ipv4/tcp_dctcp.c | 2 +- net/netfilter/nf_conntrack_bpf.c | 4 +-- net/netfilter/nf_flow_table_bpf.c | 2 +- net/netfilter/nf_nat_bpf.c | 4 +-- net/xfrm/xfrm_interface_bpf.c | 2 +- net/xfrm/xfrm_state_bpf.c | 2 +- .../selftests/bpf/bpf_testmod/bpf_testmod.c | 8 +++--- 27 files changed, 76 insertions(+), 83 deletions(-) diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index a8f5782bd833..136c449b26d4 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -359,7 +359,7 @@ type. An example is shown below:: static int init_subsystem(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_task_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_task_kfunc_set); } late_initcall(init_subsystem); diff --git a/drivers/hid/bpf/hid_bpf_dispatch.c b/drivers/hid/bpf/hid_bpf_dispatch.c index a272a086c950..37a87d70a382 100644 --- a/drivers/hid/bpf/hid_bpf_dispatch.c +++ b/drivers/hid/bpf/hid_bpf_dispatch.c @@ -660,13 +660,13 @@ static int __init hid_bpf_init(void) * This is not a big deal: nobody will be able to use the functionality. */ - err = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &hid_bpf_kfunc_set); + err = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &hid_bpf_kfunc_set); if (err) { pr_warn("error while setting HID BPF tracing kfuncs: %d", err); return 0; } - err = register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &hid_bpf_syscall_kfunc_set); + err = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SYSCALL, &hid_bpf_syscall_kfunc_set); if (err) { pr_warn("error while setting HID BPF syscall kfuncs: %d", err); return 0; diff --git a/fs/bpf_fs_kfuncs.c b/fs/bpf_fs_kfuncs.c index 3fe9f59ef867..2661c9a4f858 100644 --- a/fs/bpf_fs_kfuncs.c +++ b/fs/bpf_fs_kfuncs.c @@ -179,7 +179,7 @@ static const struct btf_kfunc_id_set bpf_fs_kfunc_set = { static int __init bpf_fs_kfuncs_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_fs_kfunc_set); } late_initcall(bpf_fs_kfuncs_init); diff --git a/fs/verity/measure.c b/fs/verity/measure.c index 175d2f1bc089..00f1a6077a77 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -181,7 +181,7 @@ static const struct btf_kfunc_id_set bpf_fsverity_set = { void __init fsverity_init_bpf(void) { - register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fsverity_set); + register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_fsverity_set); } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/include/linux/btf.h b/include/linux/btf.h index cffb43133c68..2da205e0f923 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -114,6 +114,24 @@ struct bpf_prog; typedef int (*btf_kfunc_filter_t)(const struct bpf_prog *prog, u32 kfunc_id); +enum btf_kfunc_hook { + BTF_KFUNC_HOOK_COMMON, + BTF_KFUNC_HOOK_XDP, + BTF_KFUNC_HOOK_TC, + BTF_KFUNC_HOOK_STRUCT_OPS, + BTF_KFUNC_HOOK_TRACING, + BTF_KFUNC_HOOK_SYSCALL, + BTF_KFUNC_HOOK_FMODRET, + BTF_KFUNC_HOOK_CGROUP, + BTF_KFUNC_HOOK_SCHED_ACT, + BTF_KFUNC_HOOK_SK_SKB, + BTF_KFUNC_HOOK_SOCKET_FILTER, + BTF_KFUNC_HOOK_LWT, + BTF_KFUNC_HOOK_NETFILTER, + BTF_KFUNC_HOOK_KPROBE, + BTF_KFUNC_HOOK_MAX, +}; + struct btf_kfunc_id_set { struct module *owner; struct btf_id_set8 *set; @@ -566,7 +584,7 @@ u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id, const struct bpf_prog *prog); -int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, +int register_btf_kfunc_id_set(enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *s); int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset); s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); @@ -620,7 +638,7 @@ static inline u32 *btf_kfunc_id_set_contains(const struct btf *btf, { return NULL; } -static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, +static inline int register_btf_kfunc_id_set(enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *s) { return 0; diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index e52b3ad231b9..07bafb9327ec 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -576,6 +576,6 @@ static const struct btf_kfunc_id_set common_kfunc_set = { static int __init kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_COMMON, &common_kfunc_set); } late_initcall(kfunc_init); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index b12db397303e..975c1d61aa2d 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -204,24 +204,6 @@ DEFINE_IDR(btf_idr); DEFINE_SPINLOCK(btf_idr_lock); -enum btf_kfunc_hook { - BTF_KFUNC_HOOK_COMMON, - BTF_KFUNC_HOOK_XDP, - BTF_KFUNC_HOOK_TC, - BTF_KFUNC_HOOK_STRUCT_OPS, - BTF_KFUNC_HOOK_TRACING, - BTF_KFUNC_HOOK_SYSCALL, - BTF_KFUNC_HOOK_FMODRET, - BTF_KFUNC_HOOK_CGROUP, - BTF_KFUNC_HOOK_SCHED_ACT, - BTF_KFUNC_HOOK_SK_SKB, - BTF_KFUNC_HOOK_SOCKET_FILTER, - BTF_KFUNC_HOOK_LWT, - BTF_KFUNC_HOOK_NETFILTER, - BTF_KFUNC_HOOK_KPROBE, - BTF_KFUNC_HOOK_MAX, -}; - enum { BTF_KFUNC_SET_MAX_CNT = 256, BTF_DTOR_KFUNC_MAX_CNT = 256, @@ -8389,11 +8371,9 @@ static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, } /* This function must be invoked only from initcalls/module init functions */ -int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, +int register_btf_kfunc_id_set(enum btf_kfunc_hook hook, const struct btf_kfunc_id_set *kset) { - enum btf_kfunc_hook hook; - /* All kfuncs need to be tagged as such in BTF. * WARN() for initcall registrations that do not check errors. */ @@ -8402,7 +8382,6 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, return -EINVAL; } - hook = bpf_prog_type_to_kfunc_hook(prog_type); return __register_btf_kfunc_id_set(hook, kset); } EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 33c473d676a5..1a34689b2c3d 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -472,9 +472,9 @@ static int __init cpumask_kfunc_init(void) }; ret = bpf_mem_alloc_init(&bpf_cpumask_ma, sizeof(struct bpf_cpumask), false); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &cpumask_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &cpumask_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &cpumask_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &cpumask_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &cpumask_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SYSCALL, &cpumask_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(cpumask_dtors, ARRAY_SIZE(cpumask_dtors), THIS_MODULE); diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c index 94854cd9c4cc..1010ffbffa10 100644 --- a/kernel/bpf/crypto.c +++ b/kernel/bpf/crypto.c @@ -380,10 +380,10 @@ static int __init crypto_kfunc_init(void) }, }; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &crypt_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &crypt_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &crypt_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &crypt_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SCHED_ACT, &crypt_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &crypt_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SYSCALL, &crypt_init_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(bpf_crypto_dtors, ARRAY_SIZE(bpf_crypto_dtors), diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 12e3aa40b180..3f3b68207941 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -3070,16 +3070,17 @@ static int __init kfunc_init(void) #endif }; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &generic_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &generic_kfunc_set); + + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SYSCALL, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_CGROUP, &generic_kfunc_set); ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors, ARRAY_SIZE(generic_dtors), THIS_MODULE); - return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); + return ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_COMMON, &common_kfunc_set); } late_initcall(kfunc_init); diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 9575314f40a6..60f8133abd05 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -224,6 +224,6 @@ static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = { static int init_subsystem(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_map_iter_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_COMMON, &bpf_map_iter_kfunc_set); } late_initcall(init_subsystem); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index a06b45272411..afaa9a437c1b 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -649,7 +649,7 @@ static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { static int __init bpf_rstat_kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index b69a39316c0c..c30264e9c3cb 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1408,7 +1408,7 @@ static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = { static int __init bpf_key_sig_kfuncs_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_key_sig_kfunc_set); } @@ -3473,7 +3473,7 @@ static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = { static int __init bpf_kprobe_multi_kfuncs_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_KPROBE, &bpf_kprobe_multi_kfunc_set); } late_initcall(bpf_kprobe_multi_kfuncs_init); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6d7a442ceb89..2ce805125cb2 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1753,9 +1753,9 @@ static int __init bpf_prog_test_run_init(void) int ret; ret = register_btf_fmodret_id_set(&bpf_test_modify_return_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_prog_test_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_prog_test_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &bpf_prog_test_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_prog_test_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SYSCALL, &bpf_prog_test_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(bpf_prog_test_dtor_kfunc, ARRAY_SIZE(bpf_prog_test_dtor_kfunc), THIS_MODULE); diff --git a/net/core/filter.c b/net/core/filter.c index 78a6f746ea0b..ce764c31240c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -12095,20 +12095,15 @@ static int __init bpf_kfunc_init(void) { int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SK_SKB, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCKET_FILTER, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_OUT, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_IN, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, - &bpf_kfunc_set_sock_addr); - return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SCHED_ACT, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SK_SKB, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SOCKET_FILTER, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_CGROUP, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_LWT, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_NETFILTER, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &bpf_kfunc_set_xdp); + return ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &bpf_kfunc_set_tcp_reqsk); } late_initcall(bpf_kfunc_init); @@ -12168,6 +12163,6 @@ static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = { static int init_subsystem(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_sk_iter_kfunc_set); } late_initcall(init_subsystem); diff --git a/net/core/xdp.c b/net/core/xdp.c index bcc5551c6424..d602b9184686 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -797,7 +797,7 @@ bool bpf_dev_bound_kfunc_id(u32 btf_id) static int __init xdp_metadata_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 554804774628..a1fc378cc58c 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -341,7 +341,7 @@ static int __init bpf_tcp_ca_kfunc_init(void) { int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); ret = ret ?: register_bpf_struct_ops(&bpf_tcp_congestion_ops, tcp_congestion_ops); return ret; diff --git a/net/ipv4/fou_bpf.c b/net/ipv4/fou_bpf.c index 54984f3170a8..f9a68a20cd7c 100644 --- a/net/ipv4/fou_bpf.c +++ b/net/ipv4/fou_bpf.c @@ -112,6 +112,6 @@ static const struct btf_kfunc_id_set fou_bpf_kfunc_set = { int register_fou_bpf(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &fou_bpf_kfunc_set); } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 760941e55153..49d80dbd5f26 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1177,7 +1177,7 @@ static int __init bbr_register(void) BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_bbr_kfunc_set); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &tcp_bbr_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&tcp_bbr_cong_ops); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5dbed91c6178..2ed23f429a8c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -533,7 +533,7 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_cubic_kfunc_set); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &tcp_cubic_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&cubictcp); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 8a45a4aea933..b86007e9487d 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -291,7 +291,7 @@ static int __init dctcp_register(void) BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE); - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_dctcp_kfunc_set); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_STRUCT_OPS, &tcp_dctcp_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&dctcp); diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 4a136fc3a9c0..356559e5505f 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -531,8 +531,8 @@ int register_nf_conntrack_bpf(void) { int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_kfunc_set); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &nf_conntrack_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &nf_conntrack_kfunc_set); if (!ret) { mutex_lock(&nf_conn_btf_access_lock); nfct_btf_struct_access = _nf_conntrack_btf_struct_access; diff --git a/net/netfilter/nf_flow_table_bpf.c b/net/netfilter/nf_flow_table_bpf.c index 4a5f5195f2d2..0166882856a2 100644 --- a/net/netfilter/nf_flow_table_bpf.c +++ b/net/netfilter/nf_flow_table_bpf.c @@ -115,7 +115,7 @@ static const struct btf_kfunc_id_set nf_flow_kfunc_set = { int nf_flow_register_bpf(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &nf_flow_kfunc_set); } EXPORT_SYMBOL_GPL(nf_flow_register_bpf); diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c index 481be15609b1..a3300e3618ab 100644 --- a/net/netfilter/nf_nat_bpf.c +++ b/net/netfilter/nf_nat_bpf.c @@ -67,11 +67,11 @@ int register_nf_nat_bpf(void) { int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &nf_bpf_nat_kfunc_set); if (ret) return ret; - return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &nf_bpf_nat_kfunc_set); } diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c index 5ea15037ebd1..4c3149d22712 100644 --- a/net/xfrm/xfrm_interface_bpf.c +++ b/net/xfrm/xfrm_interface_bpf.c @@ -105,6 +105,6 @@ static const struct btf_kfunc_id_set xfrm_interface_kfunc_set = { int __init register_xfrm_interface_bpf(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &xfrm_interface_kfunc_set); } diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c index 2248eda741f8..90a3a245c6de 100644 --- a/net/xfrm/xfrm_state_bpf.c +++ b/net/xfrm/xfrm_state_bpf.c @@ -129,6 +129,6 @@ static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = { int __init register_xfrm_state_bpf(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, + return register_btf_kfunc_id_set(BTF_KFUNC_HOOK_XDP, &xfrm_state_xdp_kfunc_set); } diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 3687a40b61c6..fbb4d739597d 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1088,10 +1088,10 @@ static int bpf_testmod_init(void) void **tramp; int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set); - ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set); + ret = register_btf_kfunc_id_set(BTF_KFUNC_HOOK_COMMON, &bpf_testmod_common_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TC, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_TRACING, &bpf_testmod_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BTF_KFUNC_HOOK_SYSCALL, &bpf_testmod_kfunc_set); ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops); ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2); ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors, -- 2.45.2

10 months, 2 weeks

2
1
0 0

[PATCH net-next v21 00/13] Device Memory TCP

by Mina Almasry

v21: https://patchwork.kernel.org/project/netdevbpf/list/?series=880735&state=* ==== v20 addressed some comments and resolved a test failure, but introduced an unfortunate build error with a config edge case I wasn't testing. v21 simply resolves that error. Major Changes: - Resolve build error with CONFIG_PAGE_POOL=n && CONFIG_NET=y Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v21/ v20: https://patchwork.kernel.org/project/netdevbpf/list/?series=879373&state=* ==== v20 aims to resolve a couple of bug reports against v19, and addresses some review comments around the page_pool_check_memory_provider mechanism. Major changes: - Test edge cases such as header split disabled in selftest. - Change `offset = 0` back to `offset = offset - start` to resolve issue found in RX path by Taehee (thanks!) - Address a few comments around page_pool_check_memory_provider() from Pavel & Jakub. - Removed some unnecessary includes across various patches in the series. - Removed unnecessary EXPORT_SYMBOL(page_pool_mem_providers) (Jakub). - Fix regression caused by incorrect dev_get_max_mp_channel check, along with rename (Jakub). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v20/ v19: https://patchwork.kernel.org/project/netdevbpf/list/?series=876852&state=* ==== v18 got a thorough review (thanks!), and this iteration addresses the feedback. Major changes: - Prevent deactivating mp bound queues. - Prevent installing xdp on mp bound netdevs, or installing mps on xdp installed netdevs. - Fix corner cases in netlink API vis-a-vis missing attributes. - Iron out the unreadable netmem driver support story. To be honest, the conversation with Jakub & Pavel got a bit confusing for me. I've implemented an approach in this set that makes sense to me, and AFAICT, addresses the requirements. It may be good as-is, or it may be a conversation starter/continuer. To be honest IMO there are many ways to skin this cat and I don't see an extremely strong reason to go for one approach over another. Here is one approach you may like. - Don't reset niov dma_addr on allocation & free. - Add some tests to the selftest that catches some of the issues around missing netlink attributes or deactivating mp-bound queues. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v19/ v18: https://patchwork.kernel.org/project/netdevbpf/list/?series=874848&state=* ==== v17 got minor feedback: (a) to beef up the description on patch 1 and (b) to remove the leading underscores in the header definition. I applied (a). (b) seems to be against current conventions so I did not apply before further discussion. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v17: https://patchwork.kernel.org/project/netdevbpf/list/?series=869900&state=* ==== v16 also got a very thorough review and some testing (thanks again!). Thes version addresses all the concerns reported on v15, in terms of feedback and issues reported. Major changes: - Use ASSERT_RTNL. - Moved around some of the page_pool helpers definitions so I can hide some netmem helpers in private files as Jakub suggested. - Don't make every net_iov hold a ref on the binding as Jakub suggested. - Fix issue reported by Taehee where we access queues after they have been freed. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v16: https://patchwork.kernel.org/project/netdevbpf/list/?series=866353&state=* ==== v15 got a thorough review and some testing, and this version addresses almost all the feedback. Some more minor comments where the authors said it could be done later, I left out. Major changes: - Addition of dma-buf introspection to page-pool-get and queue-get. - Fixes to selftests suggested by Taehee. - Fixes to documentation suggested by Donald. - A couple of suggestions and fixes to TCP patches by Eric and David. - Fixes to number assignements suggested by Arnd. - Use rtnl_lock()ing to guard against queue reconfiguration while the page_pool initialization is happening. (Jakub). - Fixes to a few warnings reproduced by Taehee. - Fixes to dma-buf binding suggested by Taehee and Jakub. - Fixes to netlink UAPI suggested by Jakub - Applied a number of Reviewed-bys and Acked-bys (including ones I lost from v13+). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v16/ One caveat: Taehee reproduced a KASAN warning and reported it here: https://lore.kernel.org/netdev/CAMArcTUdCxOBYGF3vpbq=eBvqZfnc44KBaQTN7H-wqd… I estimate the issue to be minor and easily fixable: https://lore.kernel.org/netdev/CAHS8izNgaqC--GGE2xd85QB=utUnOHmioCsDd1TNxJW… I hope to be able to follow up with a fix to net tree as net-next closes imminently, but if this iteration doesn't make it in, I will repost with a fix squashed after net-next reopens, no problem. v15: https://patchwork.kernel.org/project/netdevbpf/list/?series=865481&state=* ==== No material changes in this version, only a fix to linking against libynl.a from the last version. Per Jakub's instructions I've pulled one of his patches into this series, and now use the new libynl.a correctly, I hope. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v15/ v14: https://patchwork.kernel.org/project/netdevbpf/list/?series=865135&archive=… ==== No material changes in this version. Only rebase and re-verification on top of net-next. v13, I think, raced with commit ebad6d0334793 ("net/ipv4: Use nested-BH locking for ipv4_tcp_sk.") being merged to net-next that caused a patchwork failure to apply. This series should apply cleanly on commit c4532232fa2a4 ("selftests: net: remove unneeded IP_GRE config"). I did not wait the customary 24hr as Jakub said it's OK to repost as soon as I build test the rebased version: https://lore.kernel.org/netdev/20240625075926.146d769d@kernel.org/ v13: https://patchwork.kernel.org/project/netdevbpf/list/?series=861406&archive=… ==== Major changes: -------------- This iteration addresses Pavel's review comments, applies his reviewed-by's, and seeks to fix the patchwork build error (sorry!). As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v13/ v12: https://patchwork.kernel.org/project/netdevbpf/list/?series=859747&state=* ==== Major changes: -------------- This iteration only addresses one minor comment from Pavel with regards to the trace printing of netmem, and the patchwork build error introduced in v11 because I missed doing an allmodconfig build, sorry. Other than that v11, AFAICT, received no feedback. There is one discussion about how the specifics of plugging io uring memory through the page pool, but not relevant to content in this particular patchset, AFAICT. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v12/ v11: https://patchwork.kernel.org/project/netdevbpf/list/?series=857457&state=* ==== Major Changes: -------------- v11 addresses feedback received in v10. The major change is the removal of the memory provider ops as requested by Christoph. We still accomplish the same thing, but utilizing direct function calls with if statements rather than generic ops. Additionally address sparse warnings, bugs and review comments from folks that reviewed. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v11/ Detailed changelog: ------------------- - Fixes in netdev_rx_queue_restart() from Pavel & David. - Remove commit e650e8c3a36f5 ("net: page_pool: create hooks for custom page providers") from the series to address Christoph's feedback and rebased other patches on the series on this change. - Fixed build errors with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR build. - Fixed sparse warnings pointed out by Paolo. - Drop unnecessary gro_pull_from_frag0 checks. - Added Bagas reviewed-by to docs. Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Nikolay Aleksandrov <razor(a)blackwall.org> Cc: Taehee Yoo <ap420073(a)gmail.com> Cc: Donald Hunter <donald.hunter(a)gmail.com> v10: https://patchwork.kernel.org/project/netdevbpf/list/?series=852422&state=* ==== Major Changes: -------------- v9 was sent right before the merge window closed (sorry!). v10 is almost a re-send of the series now that the merge window re-opened. Only rebased to latest net-next and addressed some minor iterative comments received on v9. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v10/ Detailed changelog: ------------------- - Fixed tokens leaking in DONTNEED setsockopt (Nikolay). - Moved net_iov_dma_addr() to devmem.c and made it a devmem specific helpers (David). - Rename hook alloc_pages to alloc_netmems as alloc_pages is now preprocessor macro defined and causes a build error. v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers the network are implemented as the following low level operations: Device-to-Host copy, Host-to-Host network transfer, and Host-to-Device copy. The implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from host memory and are processed by the TCP/IP stack normally. The NIC _must_ support header split to achieve this. Advantages: - Alleviate host memory bandwidth pressure, compared to existing network-transfer + device-copy semantics. - Alleviate PCIe BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP netdev: add dmabuf introspection Documentation/netlink/specs/netdev.yaml | 61 +++ Documentation/networking/devmem.rst | 269 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/netdevice.h | 2 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 9 +- include/linux/socket.h | 1 + include/net/devmem.h | 128 ++++++ include/net/mp_dmabuf_devmem.h | 44 ++ include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 169 ++++++- include/net/page_pool/helpers.h | 39 +- include/net/page_pool/types.h | 22 +- include/net/sock.h | 2 + include/net/tcp.h | 5 +- include/trace/events/page_pool.h | 12 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 13 + include/uapi/linux/uio.h | 17 + net/core/Makefile | 3 +- net/core/datagram.c | 6 + net/core/dev.c | 22 +- net/core/devmem.c | 374 +++++++++++++++ net/core/gro.c | 3 +- net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 118 +++++ net/core/netdev_rx_queue.c | 81 ++++ net/core/netmem_priv.h | 31 ++ net/core/page_pool.c | 117 +++-- net/core/page_pool_priv.h | 46 ++ net/core/page_pool_user.c | 29 ++ net/core/skbuff.c | 77 +++- net/core/sock.c | 68 +++ net/ethtool/common.c | 8 + net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 261 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 16 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- tools/include/uapi/linux/netdev.h | 13 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 9 + tools/testing/selftests/net/ncdevmem.c | 588 ++++++++++++++++++++++++ 51 files changed, 2699 insertions(+), 121 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 include/net/mp_dmabuf_devmem.h create mode 100644 net/core/devmem.c create mode 100644 net/core/netdev_rx_queue.c create mode 100644 net/core/netmem_priv.h create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.46.0.184.g6999bdac58-goog

10 months, 2 weeks

1
13
0 0

Re: [PATCH v3 1/3] riscv: mm: Use hint address in mmap if available

by Charlie Jenkins

On Tue, Aug 20, 2024 at 09:48:50AM +0800, Levi Zim wrote: > On 2024-08-20 01:00, Charlie Jenkins wrote: > > On Mon, Aug 19, 2024 at 01:55:57PM +0800, Levi Zim wrote: > > > On 2024-03-22 22:06, Palmer Dabbelt wrote: > > > > On Thu, 01 Feb 2024 18:28:06 PST (-0800), Charlie Jenkins wrote: > > > > > On Wed, Jan 31, 2024 at 11:59:43PM +0800, Yangyu Chen wrote: > > > > > > On Wed, 2024-01-31 at 22:41 +0800, Yangyu Chen wrote: > > > > > > > On Tue, 2024-01-30 at 17:07 -0800, Charlie Jenkins wrote: > > > > > > > > On riscv it is guaranteed that the address returned by mmap is less > > > > > > > > than > > > > > > > > the hint address. Allow mmap to return an address all the way up to > > > > > > > > addr, if provided, rather than just up to the lower address space. > > > > > > > > > > This provides a performance benefit as well, allowing > > > > > > mmap to exit > > > > > > > > after > > > > > > > > checking that the address is in range rather than searching for a > > > > > > > > valid > > > > > > > > address. > > > > > > > > > > It is possible to provide an address that uses at most the same > > > > > > > > number > > > > > > > > of bits, however it is significantly more computationally expensive > > > > > > > > to > > > > > > > > provide that number rather than setting the max to be the hint > > > > > > > > address. > > > > > > > > There is the instruction clz/clzw in Zbb that returns the highest > > > > > > > > set > > > > > > > > bit > > > > > > > > which could be used to performantly implement this, but it would > > > > > > > > still > > > > > > > > be slower than the current implementation. At worst case, half of > > > > > > > > the > > > > > > > > address would not be able to be allocated when a hint address is > > > > > > > > provided. > > > > > > > > > > Signed-off-by: Charlie Jenkins<charlie(a)rivosinc.com> > > > > > > > > --- > > > > > > > > arch/riscv/include/asm/processor.h | 27 +++++++++++--------------- > > > > > > > > - > > > > > > > > 1 file changed, 11 insertions(+), 16 deletions(-) > > > > > > > > > > diff --git a/arch/riscv/include/asm/processor.h > > > > > > > > b/arch/riscv/include/asm/processor.h > > > > > > > > index f19f861cda54..8ece7a8f0e18 100644 > > > > > > > > --- a/arch/riscv/include/asm/processor.h > > > > > > > > +++ b/arch/riscv/include/asm/processor.h > > > > > > > > @@ -14,22 +14,16 @@ > > > > > > > > > > > > > > > > #include <asm/ptrace.h> > > > > > > > > > > > > > > > > -#ifdef CONFIG_64BIT > > > > > > > > -#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1)) > > > > > > > > -#define STACK_TOP_MAX TASK_SIZE_64 > > > > > > > > - > > > > > > > > #define arch_get_mmap_end(addr, len, flags) \ > > > > > > > > ({ \ > > > > > > > > unsigned long > > > > > > > > mmap_end; \ > > > > > > > > typeof(addr) _addr = (addr); \ > > > > > > > > - if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && > > > > > > > > is_compat_task())) \ > > > > > > > > + if ((_addr) == 0 || \ > > > > > > > > + (IS_ENABLED(CONFIG_COMPAT) && is_compat_task()) || \ > > > > > > > > + ((_addr + len) > BIT(VA_BITS - > > > > > > > > 1))) \ > > > > > > > > mmap_end = STACK_TOP_MAX; \ > > > > > > > > - else if ((_addr) >= VA_USER_SV57) \ > > > > > > > > - mmap_end = STACK_TOP_MAX; \ > > > > > > > > - else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= > > > > > > > > VA_BITS_SV48)) \ > > > > > > > > - mmap_end = VA_USER_SV48; \ > > > > > > > > else \ > > > > > > > > - mmap_end = VA_USER_SV39; \ > > > > > > > > + mmap_end = (_addr + len); \ > > > > > > > > mmap_end; \ > > > > > > > > }) > > > > > > > > > > > > > > > > @@ -39,17 +33,18 @@ > > > > > > > > typeof(addr) _addr = (addr); \ > > > > > > > > typeof(base) _base = (base); \ > > > > > > > > unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base); \ > > > > > > > > - if ((_addr) == 0 || (IS_ENABLED(CONFIG_COMPAT) && > > > > > > > > is_compat_task())) \ > > > > > > > > + if ((_addr) == 0 || \ > > > > > > > > + (IS_ENABLED(CONFIG_COMPAT) && is_compat_task()) || \ > > > > > > > > + ((_addr + len) > BIT(VA_BITS - > > > > > > > > 1))) \ > > > > > > > > mmap_base = (_base); \ > > > > > > > > - else if (((_addr) >= VA_USER_SV57) && (VA_BITS >= > > > > > > > > VA_BITS_SV57)) \ > > > > > > > > - mmap_base = VA_USER_SV57 - rnd_gap; \ > > > > > > > > - else if ((((_addr) >= VA_USER_SV48)) && (VA_BITS >= > > > > > > > > VA_BITS_SV48)) \ > > > > > > > > - mmap_base = VA_USER_SV48 - rnd_gap; \ > > > > > > > > else \ > > > > > > > > - mmap_base = VA_USER_SV39 - rnd_gap; \ > > > > > > > > + mmap_base = (_addr + len) - rnd_gap; \ > > > > > > > > mmap_base; \ > > > > > > > > }) > > > > > > > > > > > > > > > > +#ifdef CONFIG_64BIT > > > > > > > > +#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1)) > > > > > > > > +#define STACK_TOP_MAX TASK_SIZE_64 > > > > > > > > #else > > > > > > > > #define DEFAULT_MAP_WINDOW TASK_SIZE > > > > > > > > #define STACK_TOP_MAX TASK_SIZE > > > > > > > > > > I have carefully tested your patch on qemu with sv57. A > > > > > > bug that > > > > > > > needs > > > > > > > to be solved is that mmap with the same hint address without > > > > > > > MAP_FIXED > > > > > > > set will fail the second time. > > > > > > > > Userspace code to reproduce the bug: > > > > > > > > #include <sys/mman.h> > > > > > > > #include <stdio.h> > > > > > > > #include <stdint.h> > > > > > > > > void test(char *addr) { > > > > > > > char *res = mmap(addr, 4096, PROT_READ | PROT_WRITE, > > > > > > > MAP_ANONYMOUS > > > > > > > > MAP_PRIVATE, -1, 0); > > > > > > > printf("hint %p got %p.\n", addr, res); > > > > > > > } > > > > > > > > int main (void) { > > > > > > > test(1<<30); > > > > > > > test(1<<30); > > > > > > > test(1<<30); > > > > > > > return 0; > > > > > > > } > > > > > > > > output: > > > > > > > > hint 0x40000000 got 0x40000000. > > > > > > > hint 0x40000000 got 0xffffffffffffffff. > > > > > > > hint 0x40000000 got 0xffffffffffffffff. > > > > > > > > output on x86: > > > > > > > > hint 0x40000000 got 0x40000000. > > > > > > > hint 0x40000000 got 0x7f9171363000. > > > > > > > hint 0x40000000 got 0x7f9171362000. > > > > > > > > It may need to implement a special arch_get_unmapped_area and > > > > > > > arch_get_unmapped_area_topdown function. > > > > > > > > > > > > > This is because hint address < rnd_gap. I have tried to let mmap_base = > > > > > > min((_addr + len), (base) + TASK_SIZE - DEFAULT_MAP_WINDOW). However it > > > > > > does not work for bottom-up while ulimit -s is unlimited. You said this > > > > > > behavior is expected from patch v2 review. However it brings a new > > > > > > regression even on sv39 systems. > > > > > > > > > > > > I still don't know the reason why use addr+len as the upper-bound. I > > > > > > think solution like x86/arm64/powerpc provide two address space switch > > > > > > based on whether hint address above the default map window is enough. > > > > > > > > > > > Yep this is expected. It is up to the maintainers to decide. > > > > Sorry I forgot to reply to this, I had a buffer sitting around somewhere > > > > but I must have lost it. > > > > > > > > I think Charlie's approach is the right way to go. Putting my userspace > > > > hat on, I'd much rather have my allocations fail rather than silently > > > > ignore the hint when there's memory pressure. > > > > > > > > If there's some real use case that needs these low hints to be silently > > > > ignored under VA pressure then we can try and figure something out that > > > > makes those applications work. > > > I could confirm that this patch has broken chromium's partition allocator on > > > riscv64. The minimal reproduction I use is chromium-mmap.c: > > > > > > #include <stdio.h> > > > #include <sys/mman.h> > > > > > > int main() { > > > void* expected = (void*)0x400000000; > > > void* addr = mmap(expected, 17179869184, PROT_NONE, > > > MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); > > > if (addr != expected) { > > It is not valid to assume that the address returned by mmap will be the > > hint address. If the hint address is not available, mmap will return a > > different address. > > Oh, sorry I didn't make it clear what is the expected behavior. > The printf here is solely for debugging purpose and I don't mean that > chromium expect it will get the hint address. The expected behavior is that > both the two mmap calls will succeed. > > > > printf("Not expected address: %p != %p\n", addr, expected); > > > } > > > expected = (void*)0x3fffff000; > > > addr = mmap(expected, 17179873280, PROT_NONE, MAP_PRIVATE|MAP_ANONYMOUS, > > > -1, 0); > > > if (addr != expected) { > > > printf("Not expected address: %p != %p\n", addr, expected); > > > } > > > return 0; > > > } > > > > > > The second mmap fails with ENOMEM. Manually reverting this commit fixes the > > > issue for me. So I think it's clearly a regression and breaks userspace. > > > > > The issue here is that overlapping memory is being requested. This > > second mmap will never be able to provide an address at 0x3fffff000 with > > a size of 0x400001000 since mmap just provided an address at 0x400000000 > > with a size of 0x400000000. > > > > Before this patch, this request causes mmap to return a completely > > arbitrary value. There is no reason to use a hint address in this manner > > because the hint can never be respected. Since an arbitrary address is > > desired, a hint of zero should be used. > > > > This patch causes the behavior to be more deterministic. Instead of > > providing an arbitrary address, it causes the address to be less than or > > equal to the hint address. This allows for applications to make > > assumptions about the returned address. > > About the overlap, of course the partition allocator's request for > overlapped vma seems unreasonable. > > But I still don't quite understand why mmap cannot use an address higher > than the hint address. > The hint address, after all, is a hint, not a requirement. Yes that is fair. A "hint" that does not guarantee anything is useless so architectures have abused the term quite a bit. > > Quoting the man page: > > > If another mapping already exists there, the kernel picks > > a new address that may or may not depend on the hint. The > > address of the new mapping is returned as the result of the call. > So for casual programmers that only reads man page but not architecture > specific kernel > documentation, the current behavior of mmap on riscv64 failing on overlapped > address ranges > are quite surprising IMO. The man pages for riscv are in desperate need of attention. I have submitted a couple of updates to them recently, but there is a lot more work to be done to help developers. > > And quoting the man page again about the errno: > > > ENOMEM No memory is available. > > > > ENOMEM The process's maximum number of mappings would have been > > exceeded. This error can also occur for munmap(), when > > unmapping a region in the middle of an existing mapping, > > since this results in two smaller mappings on either side > > of the region being unmapped. > > > > ENOMEM (since Linux 4.7) The process's RLIMIT_DATA limit, > > described in getrlimit(2), would have been exceeded. > > > > ENOMEM We don't like addr, because it exceeds the virtual address > > space of the CPU. > > > > There's no matching description for the ENOMEM returned here. > I would suggest removing "because it exceeds the virtual address > space of the CPU." from the last item if the ENOMEM behavior here > is expected. This ENOMEM means something like "no memory available in the requested region". > > > This code is unfortunately relying on the previously mostly undefined > > behavior of the hint address in mmap. > Although I haven't read the code of chromium's partition allocator to judge > whether it should > be improved or fixed for riscv64, I do know that the kernel "don't break > userspace" and > "never EVER blame the user programs". The hint address design of mmap is a tricky one because it is largely implementation defined and what the man pages say is not how it is implemented in most architectures! > > The goal of this patch is to help > > developers have more consistent mmap behavior, but maybe it is necessary > > to hide this behavior behind an mmap flag. > Thank you for helping to shape a more consistent mmap behavior. > I think this should be fixed ASAP either by allowing the hint address to be > ignored > (as suggested by the Linux man page), or hide this behavior behind an mmap > flag as you said. Having a flag could also lead to a generic way of defining this behavior. Other architectures do not provide a way for applications to guarantee that some number of bits are left unused in a virtual address, and that was one of the motivating design goals here. - Charlie > > > - Charlie > > > > > See alsohttps://github.com/riscv-forks/electron/issues/4 > > > > > > > > - Charlie > > > Sincerely, > > > Levi > > >

10 months, 2 weeks

1
0
0 0

[PATCH net-next] selftests: net: add helper for checking if nettest is available

by Jakub Kicinski

A few tests check if nettest exists in the $PATH before adding $PWD to $PATH and re-checking. They don't discard stderr on the first check (and nettest is built as part of selftests, so it's pretty normal for it to not be available in system $PATH). This leads to output noise: which: no nettest in (/home/virtme/tools/fs/bin:/home/virtme/tools/fs/sbin:/home/virtme/tools/fs/usr/bin:/home/virtme/tools/fs/usr/sbin:/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin) Add a common helper for the check which does silence stderr. There is another small functional change hiding here, because pmtu.sh used to return from the test case rather than completely exit. Building nettest is not hard, there should be no need to maintain the ability to selectively skip cases in its absence. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/fcnal-test.sh | 9 +-------- tools/testing/selftests/net/lib.sh | 15 +++++++++++++++ tools/testing/selftests/net/pmtu.sh | 8 +------- tools/testing/selftests/net/settings | 1 + tools/testing/selftests/net/unicast_extensions.sh | 9 +-------- 5 files changed, 19 insertions(+), 23 deletions(-) diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 386ebd829df5..899dbad0104b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4304,14 +4304,7 @@ elif [ "$TESTS" = "ipv6" ]; then TESTS="$TESTS_IPV6" fi -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" declare -i nfail=0 declare -i nsuccess=0 diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8ee4489238ca..be8707bfb46e 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -125,6 +125,21 @@ slowwait_for_counter() slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +# Check for existence of tools which are built as part of selftests +# but may also already exist in $PATH +check_gen_prog() +{ + local prog_name=$1; shift + + if ! which $prog_name >/dev/null 2>/dev/null; then + PATH=$PWD:$PATH + if ! which $prog_name >/dev/null; then + echo "'$prog_name' command not found; skipping tests" + exit $ksft_skip + fi + fi +} + remove_ns_list() { local item=$1 diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 24a50622406c..569bce8b6383 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -681,13 +681,7 @@ setup_xfrm() { } setup_nettest_xfrm() { - if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - return 1 - fi - fi + check_gen_prog "nettest" [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings index ed8418e8217a..a38764182822 100644 --- a/tools/testing/selftests/net/settings +++ b/tools/testing/selftests/net/settings @@ -1 +1,2 @@ timeout=3600 +profile=1 diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index f52aa5f7da52..3e751234ccfe 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -30,14 +30,7 @@ source lib.sh -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" result=0 -- 2.46.0

10 months, 2 weeks

2
2
0 0

[PATCH net-next v20 00/13] Device Memory TCP

by Mina Almasry

v20: https://patchwork.kernel.org/project/netdevbpf/list/?series=879373&state=* ==== v20 aims to resolve a couple of bug reports against v19, and addresses some review comments around the page_pool_check_memory_provider mechanism. Major changes: - Test edge cases such as header split disabled in selftest. - Change `offset = 0` back to `offset = offset - start` to resolve issue found in RX path by Taehee (thanks!) - Address a few comments around page_pool_check_memory_provider() from Pavel & Jakub. - Removed some unnecessary includes across various patches in the series. - Removed unnecessary EXPORT_SYMBOL(page_pool_mem_providers) (Jakub). - Fix regression caused by incorrect dev_get_max_mp_channel check, along with rename (Jakub). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v20/ v19: https://patchwork.kernel.org/project/netdevbpf/list/?series=876852&state=* ==== v18 got a thorough review (thanks!), and this iteration addresses the feedback. Major changes: - Prevent deactivating mp bound queues. - Prevent installing xdp on mp bound netdevs, or installing mps on xdp installed netdevs. - Fix corner cases in netlink API vis-a-vis missing attributes. - Iron out the unreadable netmem driver support story. To be honest, the conversation with Jakub & Pavel got a bit confusing for me. I've implemented an approach in this set that makes sense to me, and AFAICT, addresses the requirements. It may be good as-is, or it may be a conversation starter/continuer. To be honest IMO there are many ways to skin this cat and I don't see an extremely strong reason to go for one approach over another. Here is one approach you may like. - Don't reset niov dma_addr on allocation & free. - Add some tests to the selftest that catches some of the issues around missing netlink attributes or deactivating mp-bound queues. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v19/ v18: https://patchwork.kernel.org/project/netdevbpf/list/?series=874848&state=* ==== v17 got minor feedback: (a) to beef up the description on patch 1 and (b) to remove the leading underscores in the header definition. I applied (a). (b) seems to be against current conventions so I did not apply before further discussion. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v17: https://patchwork.kernel.org/project/netdevbpf/list/?series=869900&state=* ==== v16 also got a very thorough review and some testing (thanks again!). Thes version addresses all the concerns reported on v15, in terms of feedback and issues reported. Major changes: - Use ASSERT_RTNL. - Moved around some of the page_pool helpers definitions so I can hide some netmem helpers in private files as Jakub suggested. - Don't make every net_iov hold a ref on the binding as Jakub suggested. - Fix issue reported by Taehee where we access queues after they have been freed. Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v17/ v16: https://patchwork.kernel.org/project/netdevbpf/list/?series=866353&state=* ==== v15 got a thorough review and some testing, and this version addresses almost all the feedback. Some more minor comments where the authors said it could be done later, I left out. Major changes: - Addition of dma-buf introspection to page-pool-get and queue-get. - Fixes to selftests suggested by Taehee. - Fixes to documentation suggested by Donald. - A couple of suggestions and fixes to TCP patches by Eric and David. - Fixes to number assignements suggested by Arnd. - Use rtnl_lock()ing to guard against queue reconfiguration while the page_pool initialization is happening. (Jakub). - Fixes to a few warnings reproduced by Taehee. - Fixes to dma-buf binding suggested by Taehee and Jakub. - Fixes to netlink UAPI suggested by Jakub - Applied a number of Reviewed-bys and Acked-bys (including ones I lost from v13+). Full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v16/ One caveat: Taehee reproduced a KASAN warning and reported it here: https://lore.kernel.org/netdev/CAMArcTUdCxOBYGF3vpbq=eBvqZfnc44KBaQTN7H-wqd… I estimate the issue to be minor and easily fixable: https://lore.kernel.org/netdev/CAHS8izNgaqC--GGE2xd85QB=utUnOHmioCsDd1TNxJW… I hope to be able to follow up with a fix to net tree as net-next closes imminently, but if this iteration doesn't make it in, I will repost with a fix squashed after net-next reopens, no problem. v15: https://patchwork.kernel.org/project/netdevbpf/list/?series=865481&state=* ==== No material changes in this version, only a fix to linking against libynl.a from the last version. Per Jakub's instructions I've pulled one of his patches into this series, and now use the new libynl.a correctly, I hope. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v15/ v14: https://patchwork.kernel.org/project/netdevbpf/list/?series=865135&archive=… ==== No material changes in this version. Only rebase and re-verification on top of net-next. v13, I think, raced with commit ebad6d0334793 ("net/ipv4: Use nested-BH locking for ipv4_tcp_sk.") being merged to net-next that caused a patchwork failure to apply. This series should apply cleanly on commit c4532232fa2a4 ("selftests: net: remove unneeded IP_GRE config"). I did not wait the customary 24hr as Jakub said it's OK to repost as soon as I build test the rebased version: https://lore.kernel.org/netdev/20240625075926.146d769d@kernel.org/ v13: https://patchwork.kernel.org/project/netdevbpf/list/?series=861406&archive=… ==== Major changes: -------------- This iteration addresses Pavel's review comments, applies his reviewed-by's, and seeks to fix the patchwork build error (sorry!). As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v13/ v12: https://patchwork.kernel.org/project/netdevbpf/list/?series=859747&state=* ==== Major changes: -------------- This iteration only addresses one minor comment from Pavel with regards to the trace printing of netmem, and the patchwork build error introduced in v11 because I missed doing an allmodconfig build, sorry. Other than that v11, AFAICT, received no feedback. There is one discussion about how the specifics of plugging io uring memory through the page pool, but not relevant to content in this particular patchset, AFAICT. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v12/ v11: https://patchwork.kernel.org/project/netdevbpf/list/?series=857457&state=* ==== Major Changes: -------------- v11 addresses feedback received in v10. The major change is the removal of the memory provider ops as requested by Christoph. We still accomplish the same thing, but utilizing direct function calls with if statements rather than generic ops. Additionally address sparse warnings, bugs and review comments from folks that reviewed. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v11/ Detailed changelog: ------------------- - Fixes in netdev_rx_queue_restart() from Pavel & David. - Remove commit e650e8c3a36f5 ("net: page_pool: create hooks for custom page providers") from the series to address Christoph's feedback and rebased other patches on the series on this change. - Fixed build errors with CONFIG_DMA_SHARED_BUFFER && !CONFIG_GENERIC_ALLOCATOR build. - Fixed sparse warnings pointed out by Paolo. - Drop unnecessary gro_pull_from_frag0 checks. - Added Bagas reviewed-by to docs. Cc: Bagas Sanjaya <bagasdotme(a)gmail.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Nikolay Aleksandrov <razor(a)blackwall.org> Cc: Taehee Yoo <ap420073(a)gmail.com> Cc: Donald Hunter <donald.hunter(a)gmail.com> v10: https://patchwork.kernel.org/project/netdevbpf/list/?series=852422&state=* ==== Major Changes: -------------- v9 was sent right before the merge window closed (sorry!). v10 is almost a re-send of the series now that the merge window re-opened. Only rebased to latest net-next and addressed some minor iterative comments received on v9. As usual, the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v10/ Detailed changelog: ------------------- - Fixed tokens leaking in DONTNEED setsockopt (Nikolay). - Moved net_iov_dma_addr() to devmem.c and made it a devmem specific helpers (David). - Rename hook alloc_pages to alloc_netmems as alloc_pages is now preprocessor macro defined and causes a build error. v9: === Major Changes: -------------- GVE queue API has been merged. Submitting this version as non-RFC after rebasing on top of the merged API, and dropped the out of tree queue API I was carrying on github. Addressed the little feedback v8 has received. Detailed changelog: ------------------ - Added new patch from David Wei to this series for netdev_rx_queue_restart() - Fixed sparse error. - Removed CONFIG_ checks in netmem_is_net_iov() - Flipped skb->readable to skb->unreadable - Minor fixes to selftests & docs. RFC v8: ======= Major Changes: -------------- - Fixed build error generated by patch-by-patch build. - Applied docs suggestions from Randy. RFC v7: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the feedback RFCv6 received from folks, namely Jakub, Yunsheng, Arnd, David, & Pavel. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v7/ Detailed changelog: - Use admin-perm in netlink API. - Addressed feedback from Jakub with regards to netlink API implementation. - Renamed devmem.c functions to something more appropriate for that file. - Improve the performance seen through the page_pool benchmark. - Fix the value definition of all the SO_DEVMEM_* uapi. - Various fixes to documentation. Perf - page-pool benchmark: --------------------------- Improved performance of bench_page_pool_simple.ko tests compared to v6: https://pastebin.com/raw/v5dYRg8L net-next base: 8 cycle fast path. RFC v6: 10 cycle fast path. RFC v7: 9 cycle fast path. RFC v7 with CONFIG_DMA_SHARED_BUFFER disabled: 8 cycle fast path, same as baseline. Perf - Devmem TCP benchmark: --------------------- Perf is about the same regardless of the changes in v7, namely the removal of the static_branch_unlikely to improve the page_pool benchmark performance: 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. RFC v6: ======= Major Changes: -------------- This revision largely rebases on top of net-next and addresses the little feedback RFCv5 received. The series remains in RFC because the queue-API ndos defined in this series are not yet implemented. I have a GVE implementation I carry out of tree for my testing. A upstreamable GVE implementation is in the works. Aside from that, in my estimation all the patches are ready for review/merge. Please do take a look. As usual the full devmem TCP changes including the full GVE driver implementation is here: https://github.com/mina/linux/commits/tcpdevmem-v6/ This version also comes with some performance data recorded in the cover letter (see below changelog). Detailed changelog: - Rebased on top of the merged netmem_ref changes. - Converted skb->dmabuf to skb->readable (Pavel). Pavel's original suggestion was to remove the skb->dmabuf flag entirely, but when I looked into it closely, I found the issue that if we remove the flag we have to dereference the shinfo(skb) pointer to obtain the first frag to tell whether an skb is readable or not. This can cause a performance regression if it dirties the cache line when the shinfo(skb) was not really needed. Instead, I converted the skb->dmabuf flag into a generic skb->readable flag which can be re-used by io_uring 0-copy RX. - Squashed a few locking optimizations from Eric Dumazet in the RX path and the DEVMEM_DONTNEED setsockopt. - Expanded the tests a bit. Added validation for invalid scenarios and added some more coverage. Perf - page-pool benchmark: --------------------------- bench_page_pool_simple.ko tests with and without these changes: https://pastebin.com/raw/ncHDwAbn AFAIK the number that really matters in the perf tests is the 'tasklet_page_pool01_fast_path Per elem'. This one measures at about 8 cycles without the changes but there is some 1 cycle noise in some results. With the patches this regresses to 9 cycles with the changes but there is 1 cycle noise occasionally running this test repeatedly. Lastly I tried disable the static_branch_unlikely() in netmem_is_net_iov() check. To my surprise disabling the static_branch_unlikely() check reduces the fast path back to 8 cycles, but the 1 cycle noise remains. Perf - Devmem TCP benchmark: --------------------- 189/200gbps bi-directional throughput with RX devmem TCP and regular TCP TX i.e. ~95% line rate. Major changes in RFC v5: ======================== 1. Rebased on top of 'Abstract page from net stack' series and used the new netmem type to refer to LSB set pointers instead of re-using struct page. 2. Downgraded this series back to RFC and called it RFC v5. This is because this series is now dependent on 'Abstract page from net stack'[1] and the queue API. Both are removed from the series to reduce the patch # and those bits are fairly independent or pre-requisite work. 3. Reworked the page_pool devmem support to use netmem and for some more unified handling. 4. Reworked the reference counting of net_iov (renamed from page_pool_iov) to use pp_ref_count for refcounting. The full changes including the dependent series and GVE page pool support is here: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ [1] https://patchwork.kernel.org/project/netdevbpf/list/?series=810774 Major changes in v1: ==================== 1. Implemented MVP queue API ndos to remove the userspace-visible driver reset. 2. Fixed issues in the napi_pp_put_page() devmem frag unref path. 3. Removed RFC tag. Many smaller addressed comments across all the patches (patches have individual change log). Full tree including the rest of the GVE driver changes: https://github.com/mina/linux/commits/tcpdevmem-v1 Changes in RFC v3: ================== 1. Pulled in the memory-provider dependency from Jakub's RFC[1] to make the series reviewable and mergeable. 2. Implemented multi-rx-queue binding which was a todo in v2. 3. Fix to cmsg handling. The sticking point in RFC v2[2] was the device reset required to refill the device rx-queues after the dmabuf bind/unbind. The solution suggested as I understand is a subset of the per-queue management ops Jakub suggested or similar: https://lore.kernel.org/netdev/20230815171638.4c057dcd@kernel.org/ This is not addressed in this revision, because: 1. This point was discussed at netconf & netdev and there is openness to using the current approach of requiring a device reset. 2. Implementing individual queue resetting seems to be difficult for my test bed with GVE. My prototype to test this ran into issues with the rx-queues not coming back up properly if reset individually. At the moment I'm unsure if it's a mistake in the POC or a genuine issue in the virtualization stack behind GVE, which currently doesn't test individual rx-queue restart. 3. Our usecases are not bothered by requiring a device reset to refill the buffer queues, and we'd like to support NICs that run into this limitation with resetting individual queues. My thought is that drivers that have trouble with per-queue configs can use the support in this series, while drivers that support new netdev ops to reset individual queues can automatically reset the queue as part of the dma-buf bind/unbind. The same approach with device resets is presented again for consideration with other sticking points addressed. This proposal includes the rx devmem path only proposed for merge. For a snapshot of my entire tree which includes the GVE POC page pool support & device memory support: https://github.com/torvalds/linux/compare/master...mina:linux:tcpdevmem-v3 [1] https://lore.kernel.org/netdev/f8270765-a27b-6ccf-33ea-cda097168d79@redhat.… [2] https://lore.kernel.org/netdev/CAHS8izOVJGJH5WF68OsRWFKJid1_huzzUK+hpKbLcL4… Changes in RFC v2: ================== The sticking point in RFC v1[1] was the dma-buf pages approach we used to deliver the device memory to the TCP stack. RFC v2 is a proof-of-concept that attempts to resolve this by implementing scatterlist support in the networking stack, such that we can import the dma-buf scatterlist directly. This is the approach proposed at a high level here[2]. Detailed changes: 1. Replaced dma-buf pages approach with importing scatterlist into the page pool. 2. Replace the dma-buf pages centric API with a netlink API. 3. Removed the TX path implementation - there is no issue with implementing the TX path with scatterlist approach, but leaving out the TX path makes it easier to review. 4. Functionality is tested with this proposal, but I have not conducted perf testing yet. I'm not sure there are regressions, but I removed perf claims from the cover letter until they can be re-confirmed. 5. Added Signed-off-by: contributors to the implementation. 6. Fixed some bugs with the RX path since RFC v1. Any feedback welcome, but specifically the biggest pending questions needing feedback IMO are: 1. Feedback on the scatterlist-based approach in general. 2. Netlink API (Patch 1 & 2). 3. Approach to handle all the drivers that expect to receive pages from the page pool (Patch 6). [1] https://lore.kernel.org/netdev/dfe4bae7-13a0-3c5d-d671-f61b375cb0b4@gmail.c… [2] https://lore.kernel.org/netdev/CAHS8izPm6XRS54LdCDZVd0C75tA1zHSu6jLVO8nzTLX… ================== * TL;DR: Device memory TCP (devmem TCP) is a proposal for transferring data to and/or from device memory efficiently, without bouncing the data to a host memory buffer. * Problem: A large amount of data transfers have device memory as the source and/or destination. Accelerators drastically increased the volume of such transfers. Some examples include: - ML accelerators transferring large amounts of training data from storage into GPU/TPU memory. In some cases ML training setup time can be as long as 50% of TPU compute time, improving data transfer throughput & efficiency can help improving GPU/TPU utilization. - Distributed training, where ML accelerators, such as GPUs on different hosts, exchange data among them. - Distributed raw block storage applications transfer large amounts of data with remote SSDs, much of this data does not require host processing. Today, the majority of the Device-to-Device data transfers the network are implemented as the following low level operations: Device-to-Host copy, Host-to-Host network transfer, and Host-to-Device copy. The implementation is suboptimal, especially for bulk data transfers, and can put significant strains on system resources, such as host memory bandwidth, PCIe bandwidth, etc. One important reason behind the current state is the kernel’s lack of semantics to express device to network transfers. * Proposal: In this patch series we attempt to optimize this use case by implementing socket APIs that enable the user to: 1. send device memory across the network directly, and 2. receive incoming network packets directly into device memory. Packet _payloads_ go directly from the NIC to device memory for receive and from device memory to NIC for transmit. Packet _headers_ go to/from host memory and are processed by the TCP/IP stack normally. The NIC _must_ support header split to achieve this. Advantages: - Alleviate host memory bandwidth pressure, compared to existing network-transfer + device-copy semantics. - Alleviate PCIe BW pressure, by limiting data transfer to the lowest level of the PCIe tree, compared to traditional path which sends data through the root complex. * Patch overview: ** Part 1: netlink API Gives user ability to bind dma-buf to an RX queue. ** Part 2: scatterlist support Currently the standard for device memory sharing is DMABUF, which doesn't generate struct pages. On the other hand, networking stack (skbs, drivers, and page pool) operate on pages. We have 2 options: 1. Generate struct pages for dmabuf device memory, or, 2. Modify the networking stack to process scatterlist. Approach #1 was attempted in RFC v1. RFC v2 implements approach #2. ** part 3: page pool support We piggy back on page pool memory providers proposal: https://github.com/kuba-moo/linux/tree/pp-providers It allows the page pool to define a memory provider that provides the page allocation and freeing. It helps abstract most of the device memory TCP changes from the driver. ** part 4: support for unreadable skb frags Page pool iovs are not accessible by the host; we implement changes throughput the networking stack to correctly handle skbs with unreadable frags. ** Part 5: recvmsg() APIs We define user APIs for the user to send and receive device memory. Not included with this series is the GVE devmem TCP support, just to simplify the review. Code available here if desired: https://github.com/mina/linux/tree/tcpdevmem This series is built on top of net-next with Jakub's pp-providers changes cherry-picked. * NIC dependencies: 1. (strict) Devmem TCP require the NIC to support header split, i.e. the capability to split incoming packets into a header + payload and to put each into a separate buffer. Devmem TCP works by using device memory for the packet payload, and host memory for the packet headers. 2. (optional) Devmem TCP works better with flow steering support & RSS support, i.e. the NIC's ability to steer flows into certain rx queues. This allows the sysadmin to enable devmem TCP on a subset of the rx queues, and steer devmem TCP traffic onto these queues and non devmem TCP elsewhere. The NIC I have access to with these properties is the GVE with DQO support running in Google Cloud, but any NIC that supports these features would suffice. I may be able to help reviewers bring up devmem TCP on their NICs. * Testing: The series includes a udmabuf kselftest that show a simple use case of devmem TCP and validates the entire data path end to end without a dependency on a specific dmabuf provider. ** Test Setup Kernel: net-next with this series and memory provider API cherry-picked locally. Hardware: Google Cloud A3 VMs. NIC: GVE with header split & RSS & flow steering support. Cc: Pavel Begunkov <asml.silence(a)gmail.com> Cc: David Wei <dw(a)davidwei.uk> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Yunsheng Lin <linyunsheng(a)huawei.com> Cc: Shailend Chand <shailend(a)google.com> Cc: Harshitha Ramamurthy <hramamurthy(a)google.com> Cc: Shakeel Butt <shakeel.butt(a)linux.dev> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Praveen Kaligineedi <pkaligineedi(a)google.com> Mina Almasry (13): netdev: add netdev_rx_queue_restart() net: netdev netlink api to bind dma-buf to a net device netdev: support binding dma-buf to netdevice netdev: netdevice devmem allocator page_pool: devmem support memory-provider: dmabuf devmem memory provider net: support non paged skb frags net: add support for skbs with unreadable frags tcp: RX path for devmem TCP net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags net: add devmem TCP documentation selftests: add ncdevmem, netcat for devmem TCP netdev: add dmabuf introspection Documentation/netlink/specs/netdev.yaml | 61 +++ Documentation/networking/devmem.rst | 269 +++++++++++ Documentation/networking/index.rst | 1 + arch/alpha/include/uapi/asm/socket.h | 6 + arch/mips/include/uapi/asm/socket.h | 6 + arch/parisc/include/uapi/asm/socket.h | 6 + arch/sparc/include/uapi/asm/socket.h | 6 + include/linux/netdevice.h | 2 + include/linux/skbuff.h | 61 ++- include/linux/skbuff_ref.h | 9 +- include/linux/socket.h | 1 + include/net/devmem.h | 128 ++++++ include/net/mp_dmabuf_devmem.h | 44 ++ include/net/netdev_rx_queue.h | 5 + include/net/netmem.h | 169 ++++++- include/net/page_pool/helpers.h | 39 +- include/net/page_pool/types.h | 22 +- include/net/sock.h | 2 + include/net/tcp.h | 5 +- include/trace/events/page_pool.h | 12 +- include/uapi/asm-generic/socket.h | 6 + include/uapi/linux/netdev.h | 13 + include/uapi/linux/uio.h | 17 + net/core/Makefile | 3 +- net/core/datagram.c | 6 + net/core/dev.c | 22 +- net/core/devmem.c | 374 +++++++++++++++ net/core/gro.c | 3 +- net/core/netdev-genl-gen.c | 23 + net/core/netdev-genl-gen.h | 6 + net/core/netdev-genl.c | 118 +++++ net/core/netdev_rx_queue.c | 81 ++++ net/core/netmem_priv.h | 31 ++ net/core/page_pool.c | 117 +++-- net/core/page_pool_priv.h | 31 ++ net/core/page_pool_user.c | 29 ++ net/core/skbuff.c | 77 +++- net/core/sock.c | 68 +++ net/ethtool/common.c | 8 + net/ipv4/esp4.c | 3 +- net/ipv4/tcp.c | 261 ++++++++++- net/ipv4/tcp_input.c | 13 +- net/ipv4/tcp_ipv4.c | 16 + net/ipv4/tcp_minisocks.c | 2 + net/ipv4/tcp_output.c | 5 +- net/ipv6/esp6.c | 3 +- net/packet/af_packet.c | 4 +- tools/include/uapi/linux/netdev.h | 13 + tools/testing/selftests/net/.gitignore | 1 + tools/testing/selftests/net/Makefile | 9 + tools/testing/selftests/net/ncdevmem.c | 587 ++++++++++++++++++++++++ 51 files changed, 2683 insertions(+), 121 deletions(-) create mode 100644 Documentation/networking/devmem.rst create mode 100644 include/net/devmem.h create mode 100644 include/net/mp_dmabuf_devmem.h create mode 100644 net/core/devmem.c create mode 100644 net/core/netdev_rx_queue.c create mode 100644 net/core/netmem_priv.h create mode 100644 tools/testing/selftests/net/ncdevmem.c -- 2.46.0.184.g6999bdac58-goog

10 months, 2 weeks

2
15
0 0

[PATCH 0/3] binfmt_elf: Honor PT_LOAD alignment for static PIE

by Kees Cook

Hi, This attempts to implement PT_LOAD p_align support for static PIE builds. I intend this to go into -next after the coming merge window so we can maximize bake time. In the past we've had regressions with both the selftests and the ELF loader. Hopefully we can shake everything out over a few months. :) Thanks! -Kees Kees Cook (3): selftests/exec: Build both static and non-static load_address tests binfmt_elf: Calculate total_size earlier binfmt_elf: Honor PT_LOAD alignment for static PIE fs/binfmt_elf.c | 94 ++++++++++++++------- tools/testing/selftests/exec/Makefile | 19 +++-- tools/testing/selftests/exec/load_address.c | 67 ++++++++++++--- 3 files changed, 130 insertions(+), 50 deletions(-) -- 2.34.1

10 months, 2 weeks

3
9
0 0

[bug report] selftest: bpf: Test bpf_sk_assign_tcp_reqsk().

by Dan Carpenter

Hello Kuniyuki Iwashima, Commit a74712241b46 ("selftest: bpf: Test bpf_sk_assign_tcp_reqsk().") from Jan 15, 2024 (linux-next), leads to the following Smatch static checker warning: tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c:493 tcp_validate_cookie() warn: off by one 'mssind' == ARRAY_SIZE()? ./tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c 462 static int tcp_validate_cookie(struct tcp_syncookie *ctx) 463 { 464 u32 cookie = bpf_ntohl(ctx->tcp->ack_seq) - 1; 465 u32 seq = bpf_ntohl(ctx->tcp->seq) - 1; 466 u64 first = 0, second; 467 int mssind; 468 u32 hash; 469 470 if (ctx->ipv4) 471 first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr; 472 else if (ctx->ipv6) 473 first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 | 474 ctx->ipv6->daddr.in6_u.u6_addr32[0]; 475 476 second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest; 477 hash = siphash_2u64(first, second, &test_key_siphash); 478 479 if (ctx->attrs.tstamp_ok) 480 hash -= ctx->attrs.rcv_tsecr & COOKIE_MASK; 481 else 482 hash &= ~COOKIE_MASK; 483 484 hash -= cookie & ~COOKIE_MASK; 485 if (hash) 486 goto err; 487 488 mssind = (cookie & (3 << 6)) >> 6; 489 if (ctx->ipv4) { 490 if (mssind > ARRAY_SIZE(msstab4)) ^ Should be >= instead of >. 491 goto err; 492 --> 493 ctx->attrs.mss = msstab4[mssind]; 494 } else { 495 if (mssind > ARRAY_SIZE(msstab6)) 496 goto err; 497 498 ctx->attrs.mss = msstab6[mssind]; 499 } 500 501 ctx->attrs.snd_wscale = cookie & BPF_SYNCOOKIE_WSCALE_MASK; 502 ctx->attrs.rcv_wscale = ctx->attrs.snd_wscale; 503 ctx->attrs.wscale_ok = ctx->attrs.snd_wscale == BPF_SYNCOOKIE_WSCALE_MASK; 504 ctx->attrs.sack_ok = cookie & BPF_SYNCOOKIE_SACK; 505 ctx->attrs.ecn_ok = cookie & BPF_SYNCOOKIE_ECN; 506 507 return 0; 508 err: 509 return -1; 510 } regards, dan carpenter

10 months, 2 weeks

2
4
0 0

[bug report] selftests/bpf: Add C tests for reference tracking

by Dan Carpenter

Hello Joe Stringer, Commit de375f4e91e3 ("selftests/bpf: Add C tests for reference tracking") from Oct 2, 2018 (linux-next), leads to the following Smatch static checker warning: ./tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c:70 sk_lookup_success() warn: potential pointer math issue ('tuple' is a 288 bit pointer) ./tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c 55 SEC("?tc") 56 int sk_lookup_success(struct __sk_buff *skb) 57 { 58 void *data_end = (void *)(long)skb->data_end; 59 void *data = (void *)(long)skb->data; 60 struct ethhdr *eth = (struct ethhdr *)(data); 61 struct bpf_sock_tuple *tuple; 62 struct bpf_sock *sk; 63 size_t tuple_len; 64 bool ipv4; 65 66 if (eth + 1 > data_end) 67 return TC_ACT_SHOT; 68 69 tuple = get_tuple(data, sizeof(*eth), data_end, eth->h_proto, &ipv4); --> 70 if (!tuple || tuple + sizeof *tuple > data_end) ^^^^^^^^^^^^^^^^^^^^^ This is pointer math. It should be "tuple + 1" or (u8 *)tuple + sizeof(*tuple). 71 return TC_ACT_SHOT; 72 73 tuple_len = ipv4 ? sizeof(tuple->ipv4) : sizeof(tuple->ipv6); 74 sk = bpf_sk_lookup_tcp(skb, tuple, tuple_len, BPF_F_CURRENT_NETNS, 0); 75 bpf_printk("sk=%d\n", sk ? 1 : 0); 76 if (sk) 77 bpf_sk_release(sk); 78 return sk ? TC_ACT_OK : TC_ACT_UNSPEC; 79 } regards, dan carpenter

10 months, 2 weeks

1
0
0 0

[bug report] selftests/bpf: Factor out get_xlated_program() helper

by Dan Carpenter

Hello Hou Tao, This is a semi-automatic email about new static checker warnings. Commit b4b7a4099b8c ("selftests/bpf: Factor out get_xlated_program() helper") from Jan 5, 2024, leads to the following Smatch complaint: ./tools/testing/selftests/bpf/testing_helpers.c:455 get_xlated_program() warn: variable dereferenced before check 'buf' (see line 454) ./tools/testing/selftests/bpf/testing_helpers.c 453 *cnt = xlated_prog_len / buf_element_size; 454 *buf = calloc(*cnt, buf_element_size); 455 if (!buf) { ^^^ This should be *buf. 456 perror("can't allocate xlated program buffer"); 457 return -ENOMEM; regards, dan carpenter

10 months, 2 weeks

1
0
0 0

[PATCH v1 00/16] iommufd: Add VIOMMU infrastructure (Part-1)

by Nicolin Chen

This series introduces a new VIOMMU infrastructure and related ioctls. IOMMUFD has been using the HWPT infrastructure for all cases, including a nested IO page table support. Yet, there're limitations for an HWPT-based structure to support some advanced HW-accelerated features, such as CMDQV on NVIDIA Grace, and HW-accelerated vIOMMU on AMD. Even for a multi-IOMMU environment, it is not straightforward for nested HWPTs to share the same parent HWPT (stage-2 IO pagetable), with the HWPT infrastructure alone. The new VIOMMU object is an additional layer, between the nested HWPT and its parent HWPT, to give to both the IOMMUFD core and an IOMMU driver an additional structure to support HW-accelerated feature: ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested0 |--->| viommu0 ------------------ ---------------- | | HW-accel feats | ---------------------------- On a multi-IOMMU system, the VIOMMU object can be instanced to the number of vIOMMUs in a guest VM, while holding the same parent HWPT to share the stage-2 IO pagetable. Each VIOMMU then just need to only allocate its own VMID to attach the shared stage-2 IO pagetable to the physical IOMMU: ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested0 |--->| viommu0 ------------------ ---------------- | | VMID0 | ---------------------------- ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested1 |--->| viommu1 ------------------ ---------------- | | VMID1 | ---------------------------- As an initial part-1, add ioctls to support a VIOMMU-based invalidation: IOMMUFD_CMD_VIOMMU_ALLOC to allocate a VIOMMU object IOMMUFD_CMD_VIOMMU_SET/UNSET_VDEV_ID to set/clear device's virtual ID IOMMUFD_CMD_VIOMMU_INVALIDATE to flush cache by a given driver data Worth noting that the VDEV_ID is for a per-VIOMMU device list for drivers to look up the device's physical instance from its virtual ID in a VM. It is essential for a VIOMMU-based invalidation where the request contains a device's virtual ID for its device cache flush, e.g. ATC invalidation. As for the implementation of the series, add an IOMMU_VIOMMU_TYPE_DEFAULT type for a core-allocated-core-managed VIOMMU object, allowing drivers to simply hook a default viommu ops for viommu-based invalidation alone. And provide some viommu helpers to drivers for VDEV_ID translation and parent domain lookup. Introduce an IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3 for a real world use case. This adds supports of arm-smmuv-v3's CMDQ_OP_ATC_INV and CMDQ_OP_CFGI_CD/ALL commands, supplementing HWPT-based invalidations. In the future, drivers will also be able to choose a driver-managed type to hold its own structure by adding a new type to enum iommu_viommu_type. More VIOMMU-based structures and ioctls will be introduced in part-2/3 to support a driver-managed VIOMMU, e.g. VQUEUE object for a HW accelerated queue, VIRQ (or VEVENT) object for IRQ injections. Although we repurposed the VIOMMU object from an earlier RFC discussion, for a referece: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p1-v1 Thanks! Nicolin Jason Gunthorpe (1): iommu/arm-smmu-v3: Allow ATS for IOMMU_DOMAIN_NESTED Nicolin Chen (15): iommufd/viommu: Add IOMMUFD_OBJ_VIOMMU and IOMMU_VIOMMU_ALLOC ioctl iommu: Pass in a viommu pointer to domain_alloc_user op iommufd: Allow pt_id to carry viommu_id for IOMMU_HWPT_ALLOC iommufd/selftest: Add IOMMU_VIOMMU_ALLOC test coverage iommufd/viommu: Add IOMMU_VIOMMU_SET/UNSET_VDEV_ID ioctl iommufd/selftest: Add IOMMU_VIOMMU_SET/UNSET_VDEV_ID test coverage iommufd/viommu: Add cache_invalidate for IOMMU_VIOMMU_TYPE_DEFAULT iommufd/viommu: Add IOMMU_VIOMMU_INVALIDATE ioctl iommufd/viommu: Make iommufd_viommu_find_device a public API iommufd/selftest: Add mock_viommu_invalidate_user op iommufd/selftest: Add IOMMU_TEST_OP_DEV_CHECK_CACHE test command iommufd/selftest: Add coverage for IOMMU_VIOMMU_INVALIDATE ioctl iommufd/viommu: Add iommufd_viommu_to_parent_domain helper iommu/arm-smmu-v3: Extract an __arm_smmu_cache_invalidate_user helper iommu/arm-smmu-v3: Add viommu cache invalidation support drivers/iommu/amd/iommu.c | 1 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 90 +++++- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 2 + drivers/iommu/intel/iommu.c | 1 + drivers/iommu/iommufd/Makefile | 3 +- drivers/iommu/iommufd/device.c | 9 + drivers/iommu/iommufd/hw_pagetable.c | 27 +- drivers/iommu/iommufd/iommufd_private.h | 37 +++ drivers/iommu/iommufd/iommufd_test.h | 30 ++ drivers/iommu/iommufd/main.c | 15 + drivers/iommu/iommufd/selftest.c | 88 +++++- drivers/iommu/iommufd/viommu.c | 249 +++++++++++++++++ include/linux/iommu.h | 6 + include/linux/iommufd.h | 35 +++ include/uapi/linux/iommufd.h | 139 ++++++++- tools/testing/selftests/iommu/iommufd.c | 263 +++++++++++++++++- tools/testing/selftests/iommu/iommufd_utils.h | 126 +++++++++ 17 files changed, 1095 insertions(+), 26 deletions(-) create mode 100644 drivers/iommu/iommufd/viommu.c -- 2.43.0

10 months, 2 weeks

2
46
0 0

[PATCH] kselftest: timers: Fix const correctness

by Piotr Zalewski

Make timespec pointers, pointers to const in checklist function. As a consequence, make list parameter in checklist function pointer to const as well. Const-correctness increases readability. Improvement was found by running cppcheck tool on the patched file as follows: ``` cppcheck --enable=all \ tools/testing/selftests/timers/threadtest.c \ --suppress=missingIncludeSystem \ --suppress=unusedFunction ``` Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Piotr Zalewski <pZ010001011111(a)proton.me> --- tools/testing/selftests/timers/threadtest.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c index 76b38e41d9c7..d5564bbf0e50 100644 --- a/tools/testing/selftests/timers/threadtest.c +++ b/tools/testing/selftests/timers/threadtest.c @@ -38,10 +38,10 @@ struct timespec global_list[LISTSIZE]; int listcount = 0; -void checklist(struct timespec *list, int size) +void checklist(const struct timespec *list, int size) { int i, j; - struct timespec *a, *b; + const struct timespec *a, *b; /* scan the list */ for (i = 0; i < size-1; i++) { -- 2.46.0

10 months, 2 weeks

2
1
0 0

[PATCH v1 0/5] KVM: s390: selftests: Add regression tests for CPU subfunctions

by Hariharan Mari

This patch series introduces a set of regression tests for various s390x CPU subfunctions in KVM. The tests ensure that the KVM implementation accurately reflects the behavior of actual CPU instructions for these subfunctions. The series adds tests for a total of 15 instructions across five patches, covering a range of operations including sorting, compression, and various cryptographic functions. Each patch follows a consistent testing pattern: 1. Obtain the KVM_S390_VM_CPU_MACHINE_SUBFUNC attribute for the VM. 2. Execute the relevant asm instructions. 3. Compare KVM-reported results with direct instruction execution results. Testing has been performed on s390x hardware with KVM support. All tests pass successfully, verifying the correct implementation of these subfunctions in KVM. Hariharan Mari (5): KVM: s390: selftests: Add regression tests for SORTL and DFLTCC CPU subfunctions KVM: s390: selftests: Add regression tests for PRNO, KDSA and KMA crypto subfunctions KVM: s390: selftests: Add regression tests for KMCTR, KMF, KMO and PCC crypto subfunctions KVM: s390: selftests: Add regression tests for KMAC, KMC, KM, KIMD and KLMD crypto subfunctions KVM: s390: selftests: Add regression tests for PLO subfunctions tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/s390x/facility.h | 50 +++ .../kvm/s390x/cpumodel_subfuncs_test.c | 343 ++++++++++++++++++ 3 files changed, 394 insertions(+) create mode 100644 tools/testing/selftests/kvm/include/s390x/facility.h create mode 100644 tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c -- 2.45.2

10 months, 2 weeks

2
6
0 0

[RFC PATCH 5/5] selftests/rseq: Implement NUMA node id vs mm_cid invariant test

by Mathieu Desnoyers

This test validates that the mapping between a mm_cid and a NUMA node id remains invariant for the process lifetime for a process with a number of threads >= number of allowed CPUs. In other words, it validates that if any thread within the process running on behalf of a mm_cid N observes a NUMA node id M, all threads within this process will always observe the same NUMA node id value when running on behalf of that same mm_cid. This characteristic is important for NUMA locality. On all architectures except Power, the NUMA topology is never reconfigured after a CPU has been associated with a NUMA node in the system lifetime. Even on Power, we can assume that NUMA topology reconfiguration happens rarely, and therefore we do not expect it to happen while the NUMA test is running. As a result the NUMA node id associated with a mm_cid should be invariant as long as: - A process has a number of threads >= number of allowed CPUs, - The allowed CPUs mask is unchanged, and - The NUMA configuration is unchanged. This test is skipped on architectures that do not implement rseq_load_u32_u32. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../testing/selftests/rseq/basic_numa_test.c | 144 ++++++++++++++++++ 3 files changed, 146 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/basic_numa_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 16496de5f6ce..8a8d163cbb9f 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 5a3432fceb58..9ef1c949114a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -14,7 +14,7 @@ LDLIBS += -lpthread -ldl # still track changes to header files and depend on shared object. OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ +TEST_GEN_PROGS = basic_test basic_numa_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ param_test_mm_cid_benchmark param_test_mm_cid_compare_twice diff --git a/tools/testing/selftests/rseq/basic_numa_test.c b/tools/testing/selftests/rseq/basic_numa_test.c new file mode 100644 index 000000000000..8e51c662057d --- /dev/null +++ b/tools/testing/selftests/rseq/basic_numa_test.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* + * Basic rseq NUMA test. Validate that (mm_cid, numa_node_id) pairs are + * invariant when the number of threads >= number of allowed CPUs, as + * long as those preconditions are respected: + * + * - A process has a number of threads >= number of allowed CPUs, + * - The allowed CPUs mask is unchanged, and + * - The NUMA configuration is unchanged. + */ +#define _GNU_SOURCE +#include <assert.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <string.h> +#include <poll.h> +#include <sys/time.h> + +#include "rseq.h" + +#define NR_LOOPS 100 + +static int nr_threads, nr_active_threads, test_go, test_stop; + +#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32 + +static int cpu_numa_id[CPU_SETSIZE]; + +static int get_affinity_weight(void) +{ + cpu_set_t allowed_cpus; + + if (sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus)) { + perror("sched_getaffinity"); + abort(); + } + return CPU_COUNT(&allowed_cpus); +} + +static void numa_id_init(void) +{ + int i; + + for (i = 0; i < CPU_SETSIZE; i++) + cpu_numa_id[i] = -1; +} + +static void *test_thread(void *arg) +{ + int i; + + if (rseq_register_current_thread()) { + fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + /* + * Rendez-vous across all threads to make sure the number of + * threads >= number of possible CPUs for the entire test duration. + */ + if (__atomic_add_fetch(&nr_active_threads, 1, __ATOMIC_RELAXED) == nr_threads) + __atomic_store_n(&test_go, 1, __ATOMIC_RELAXED); + while (!__atomic_load_n(&test_go, __ATOMIC_RELAXED)) + rseq_barrier(); + + for (i = 0; i < NR_LOOPS; i++) { + uint32_t mm_cid, node; + int cached_node_id; + + while (rseq_load_u32_u32(RSEQ_MO_RELAXED, &mm_cid, + &rseq_get_abi()->mm_cid, + &node, &rseq_get_abi()->node_id) != 0) { + /* Retry. */ + } + cached_node_id = RSEQ_READ_ONCE(cpu_numa_id[mm_cid]); + if (cached_node_id == -1) { + RSEQ_WRITE_ONCE(cpu_numa_id[mm_cid], node); + } else { + if (node != cached_node_id) { + fprintf(stderr, "Error: NUMA node id discrepancy: mm_cid %u cached node id %d node id %u.\n", + mm_cid, cached_node_id, node); + fprintf(stderr, "This is likely a kernel bug, or caused by a concurrent NUMA topology reconfiguration.\n"); + abort(); + } + } + (void) poll(NULL, 0, 10); /* wait 10ms */ + } + /* + * Rendez-vous before exiting all threads to make sure the + * number of threads >= number of possible CPUs for the entire + * test duration. + */ + if (__atomic_sub_fetch(&nr_active_threads, 1, __ATOMIC_RELAXED) == 0) + __atomic_store_n(&test_stop, 1, __ATOMIC_RELAXED); + while (!__atomic_load_n(&test_stop, __ATOMIC_RELAXED)) + rseq_barrier(); + + if (rseq_unregister_current_thread()) { + fprintf(stderr, "Error: rseq_unregister_current_thread(...) failed(%d): %s\n", + errno, strerror(errno)); + abort(); + } + return NULL; +} + +static int test_numa(void) +{ + pthread_t tid[nr_threads]; + int err, i; + void *tret; + + numa_id_init(); + + printf("testing rseq (mm_cid, numa_node_id) invariant, multi-threaded (%d threads)\n", + nr_threads); + + for (i = 0; i < nr_threads; i++) { + err = pthread_create(&tid[i], NULL, test_thread, NULL); + if (err != 0) + abort(); + } + + for (i = 0; i < nr_threads; i++) { + err = pthread_join(tid[i], &tret); + if (err != 0) + abort(); + } + + return 0; +} +#else +static int test_numa(void) +{ + fprintf(stderr, "rseq_load_u32_u32 is not implemented on this architecture. Skipping numa test.\n"); + return 0; +} +#endif + +int main(int argc, char **argv) +{ + nr_threads = get_affinity_weight(); + return test_numa(); +} -- 2.39.2

10 months, 2 weeks

1
0
0 0

[RFC PATCH 4/5] selftests/rseq: x86: Implement rseq_load_u32_u32

by Mathieu Desnoyers

Allow loading a pair of u32 within a rseq critical section. It can be used in situations where both rseq_abi()->mm_cid and rseq_abi()->node_id need to be sampled atomically with respect to preemption, signal delivery and migration. Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Shuah Khan <skhan(a)linuxfoundation.org> Cc: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/rseq/rseq-x86-bits.h | 43 ++++++++++++++++++++ tools/testing/selftests/rseq/rseq.h | 14 +++++++ 2 files changed, 57 insertions(+) diff --git a/tools/testing/selftests/rseq/rseq-x86-bits.h b/tools/testing/selftests/rseq/rseq-x86-bits.h index 8a9431eec467..fdf5ef398393 100644 --- a/tools/testing/selftests/rseq/rseq-x86-bits.h +++ b/tools/testing/selftests/rseq/rseq-x86-bits.h @@ -990,4 +990,47 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trymemcpy_storev)(intptr_t *v, intptr_t #endif +#if defined(RSEQ_TEMPLATE_CPU_ID_NONE) && defined(RSEQ_TEMPLATE_MO_RELAXED) + +#define RSEQ_ARCH_HAS_LOAD_U32_U32 + +static inline __attribute__((always_inline)) +int RSEQ_TEMPLATE_IDENTIFIER(rseq_load_u32_u32)(uint32_t *dst1, uint32_t *src1, + uint32_t *dst2, uint32_t *src2) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto ( + RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */ + /* Start rseq by storing table entry pointer into rseq_cs. */ + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_INJECT_ASM(3) + "movl %[src1], %%eax\n\t" + "movl %%eax, %[dst1]\n\t" + "movl %[src2], %%eax\n\t" + "movl %%eax, %[dst2]\n\t" + "2:\n\t" + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, "", abort) + : /* gcc asm goto does not allow outputs */ + : [rseq_offset] "r" (rseq_offset), + /* final store input */ + [dst1] "m" (*dst1), + [src1] "m" (*src1), + [dst2] "m" (*dst2), + [src2] "m" (*src2) + : "memory", "cc", "rax" + RSEQ_INJECT_CLOBBER + : abort + ); + rseq_after_asm_goto(); + return 0; +abort: + rseq_after_asm_goto(); + RSEQ_INJECT_FAILED + return -1; +} + +#endif /* defined(RSEQ_TEMPLATE_CPU_ID_NONE) && defined(RSEQ_TEMPLATE_MO_RELAXED) */ + #include "rseq-bits-reset.h" diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index d7364ea4d201..b6095c2a5da6 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -381,4 +381,18 @@ int rseq_cmpeqv_trymemcpy_storev(enum rseq_mo rseq_mo, enum rseq_percpu_mode per } } +#ifdef RSEQ_ARCH_HAS_LOAD_U32_U32 + +static inline __attribute__((always_inline)) +int rseq_load_u32_u32(enum rseq_mo rseq_mo, + uint32_t *dst1, uint32_t *src1, + uint32_t *dst2, uint32_t *src2) +{ + if (rseq_mo != RSEQ_MO_RELAXED) + return -1; + return rseq_load_u32_u32_relaxed(dst1, src1, dst2, src2); +} + +#endif + #endif /* RSEQ_H_ */ -- 2.39.2

10 months, 2 weeks

1
0
0 0

[PATCH v2] lib/math: Add int_pow test suite

by Luis Felipe Hernandez

Adds test suite for integer based power function. Signed-off-by: Luis Felipe Hernandez <luis.hernandez093(a)gmail.com> --- lib/Kconfig.debug | 9 ++++++ lib/math/Makefile | 1 + lib/math/tests/Makefile | 3 ++ lib/math/tests/int_pow_kunit.c | 52 ++++++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+) create mode 100644 lib/math/tests/Makefile create mode 100644 lib/math/tests/int_pow_kunit.c diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index a30c03a66172..b0bbd30d4cba 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -3051,3 +3051,12 @@ config RUST_KERNEL_DOCTESTS endmenu # "Rust" endmenu # Kernel hacking + +config INT_POW_TEST + tristate "Integer exponentiation (int_pow) test" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this to test the int_pow maths function KUnit test. + + If unsure, say N diff --git a/lib/math/Makefile b/lib/math/Makefile index 91fcdb0c9efe..3c1f92a7459d 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -5,5 +5,6 @@ obj-$(CONFIG_CORDIC) += cordic.o obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o +obj-$(CONFIG_INT_POW_TEST) += tests/int_pow_kunit.o obj-$(CONFIG_TEST_DIV64) += test_div64.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o diff --git a/lib/math/tests/Makefile b/lib/math/tests/Makefile new file mode 100644 index 000000000000..6a169123320a --- /dev/null +++ b/lib/math/tests/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_INT_POW_TEST) += int_pow_kunit.o diff --git a/lib/math/tests/int_pow_kunit.c b/lib/math/tests/int_pow_kunit.c new file mode 100644 index 000000000000..e04dd73dabd1 --- /dev/null +++ b/lib/math/tests/int_pow_kunit.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <kunit/test.h> +#include <linux/math.h> + +struct test_case_params { + u64 base; + unsigned int exponent; + u64 expected_result; + const char *name; +}; + +static const struct test_case_params params[] = { + { 64, 0, 1, "Power of zero" }, + { 64, 1, 64, "Power of one"}, + { 0, 5, 0, "Base zero" }, + { 1, 64, 1, "Base one" }, + { 2, 2, 4, "Two squared"}, + { 2, 3, 8, "Two cubed"}, + { 5, 5, 3125, "Five raised to the fith power" }, + { U64_MAX, 1, U64_MAX, "Max base" }, + { 2, 63, 9223372036854775808, "Large result"}, +}; + +static void get_desc(const struct test_case_params *tc, char *desc) +{ + strscpy(desc, tc->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(int_pow, params, get_desc); + +static void int_pow_test(struct kunit *test) +{ + const struct test_case_params *tc = (const struct test_case_params *)test->param_value; + + KUNIT_EXPECT_EQ(test, tc->expected_result, int_pow(tc->base, tc->exponent)); +} + +static struct kunit_case math_int_pow_test_cases[] = { + KUNIT_CASE_PARAM(int_pow_test, int_pow_gen_params), + {} +}; + +static struct kunit_suite int_pow_test_suite = { + .name = "math-int_pow", + .test_cases = math_int_pow_test_cases, +}; + +kunit_test_suites(&int_pow_test_suite); + +MODULE_DESCRIPTION("math.int_pow KUnit test suite"); +MODULE_LICENSE("GPL"); -- 2.46.0

10 months, 2 weeks

2
2
0 0

[PATCHv2 net 0/2] selftests: Fix udpgro failures

by Hangbin Liu

There are 2 issues for the current udpgro test. The first one is the testing doesn't record all the failures, which may report pass but the test actually failed. e.g. https://netdev-3.bots.linux.dev/vmksft-net/results/725661/45-udpgro-sh/stdo… The other one is after commit d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP"), there is no need to load xdp program to enable GRO on veth device. Hangbin Liu (2): selftests: udpgro: report error when receive failed selftests: udpgro: no need to load xdp for gro tools/testing/selftests/net/udpgro.sh | 53 ++++++++++++++------------- 1 file changed, 28 insertions(+), 25 deletions(-) -- 2.45.0

10 months, 2 weeks

2
3
0 0

[PATCH v4 0/3] tracing: Support poll on event hist file

by Masami Hiramatsu (Google)

Hi, Here is the v4 patch to support polling on event 'hist' file. The previous version is here; https://lore.kernel.org/all/172359427367.323666.6446548762874507863.stgit@d… This version uses getopt() in poll test command in [3/3] according to Shuah's comment in the previous thread. Background ---------- There has been interest in allowing user programs to monitor kernel events in real time. Ftrace provides `trace_pipe` interface to wait on events in the ring buffer, but it is needed to wait until filling up a page with events in the ring buffer. We can also peek the `trace` file periodically, but that is inefficient way to monitor a randomely happening event. Overview -------- This patch set allows user to `poll`(or `select`, `epoll`) on event histogram interface. As you know each event has its own `hist` file which shows histograms generated by trigger action. So user can set a new hist trigger on any event you want to monitor, and poll on the `hist` file until it is updated. There are 2 poll events are supported, POLLIN and POLLPRI. POLLIN means that there are any readable update on `hist` file and this event will be flashed only when you call read(). So, this is useful if you want to read the histogram periodically. The other POLLPRI event is for monitoring trace event. Like the POLLIN, this will be returned when the histogram is updated, but you don't need to read() the file and use poll() again. Note that this waits for histogram update (not event arrival), thus you must set a histogram on the event at first. Usage ----- Here is an example usage: ---- TRACEFS=/sys/kernel/tracing EVENT=$TRACEFS/events/sched/sched_process_free # setup histogram trigger and enable event echo "hist:key=comm" >> $EVENT/trigger echo 1 > $EVENT/enable # Wait for update poll pri $EVENT/hist # Event arrived. echo "process free event is comming" tail $TRACEFS/trace ---- The 'poll' command is in the selftest patch. You can take this series also from here; https://git.kernel.org/pub/scm/linux/kernel/git/mhiramat/linux.git/log/?h=t… Thank you, --- Masami Hiramatsu (Google) (3): tracing/hist: Add poll(POLLIN) support on hist file tracing/hist: Support POLLPRI event for poll on histogram selftests/tracing: Add hist poll() support test include/linux/trace_events.h | 5 + kernel/trace/trace_events.c | 18 ++++ kernel/trace/trace_events_hist.c | 101 +++++++++++++++++++- tools/testing/selftests/ftrace/Makefile | 2 tools/testing/selftests/ftrace/poll.c | 74 +++++++++++++++ .../ftrace/test.d/trigger/trigger-hist-poll.tc | 74 +++++++++++++++ 6 files changed, 271 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/ftrace/poll.c create mode 100644 tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc -- Masami Hiramatsu (Google) <mhiramat(a)kernel.org>

10 months, 2 weeks

3
6
0 0

[PATCH v5 0/4] Introduce userspace-driven ALSA timers

by Ivan Orlov

There are multiple possible timer sources which could be useful for the sound stream synchronization: hrtimers, hardware clocks (e.g. PTP), timer wheels (jiffies). Currently, using one of them to synchronize the audio stream of snd-aloop module would require writing a kernel-space driver which exports an ALSA timer through the snd_timer interface. However, it is not really convenient for application developers, who may want to define their custom timer sources for audio synchronization. For instance, we could have a network application which receives frames and sends them to snd-aloop pcm device, and another application listening on the other end of snd-aloop. It makes sense to transfer a new period of data only when certain amount of frames is received through the network, but definitely not when a certain amount of jiffies on a local system elapses. Since all of the devices are purely virtual it won't introduce any glitches and will help the application developers to avoid using sample-rate conversion. This patch series introduces userspace-driven ALSA timers: virtual timers which are created and controlled from userspace. The timer can be created from the userspace using the new ioctl SNDRV_TIMER_IOCTL_CREATE. After creating a timer, it becomes available for use system-wide, so it can be passed to snd-aloop as a timer source (timer_source parameter would be "-1.SNDRV_TIMER_GLOBAL_UDRIVEN.{timer_id}"). When the userspace app decides to trigger a timer, it calls another ioctl SNDRV_TIMER_IOCTL_TRIGGER on the file descriptor of a timer. It initiates a transfer of a new period of data. Userspace-driven timers are associated with file descriptors. If the application wishes to destroy the timer, it can simply release the file descriptor of a virtual timer. I believe introducing new ioctl calls is quite inconvenient (as we have a limited amount of them), but other possible ways of app <-> kernel communication (like virtual FS) seem completely inappropriate for this task (but I'd love to discuss alternative solutions). This patch series also updates the snd-aloop module so the global timers can be used as a timer_source for it (it allows using userspace-driven timers as timer source). V1 -> V2: - Fix some problems found by Christophe Jaillet <christophe.jaillet(a)wanadoo.fr> V2 -> V3: - Add improvements suggested by Takashi Iwai <tiwai(a)suse.de> V3 -> V4: - Address comments from Jaroslav Kysela <perex(a)perex.cz> and Mark Brown <broonie(a)kernel.org> V4 -> V5: - Add missing error processing noticed by Takashi Iwai <tiwai(a)suse.de> - Return timer file descriptor as part of the snd_timer_uinfo structure. This is a more standard way of using ioctl interface, where the return value of the ioctl is either 0 or an error code. Please, find the patch-specific changelog in the following patches. Ivan Orlov (4): ALSA: aloop: Allow using global timers Docs/sound: Add documentation for userspace-driven ALSA timers ALSA: timer: Introduce virtual userspace-driven timers selftests: ALSA: Cover userspace-driven timers with test Documentation/sound/index.rst | 1 + Documentation/sound/utimers.rst | 126 +++++++++++ include/uapi/sound/asound.h | 17 +- sound/core/Kconfig | 10 + sound/core/timer.c | 225 ++++++++++++++++++++ sound/drivers/aloop.c | 2 + tools/testing/selftests/alsa/Makefile | 4 +- tools/testing/selftests/alsa/global-timer.c | 87 ++++++++ tools/testing/selftests/alsa/utimer-test.c | 164 ++++++++++++++ 9 files changed, 633 insertions(+), 3 deletions(-) create mode 100644 Documentation/sound/utimers.rst create mode 100644 tools/testing/selftests/alsa/global-timer.c create mode 100644 tools/testing/selftests/alsa/utimer-test.c -- 2.34.1

10 months, 2 weeks

2
5
0 0

[PATCH net-next v19 09/13] tcp: RX path for devmem TCP

by Mina Almasry

In tcp_recvmsg_locked(), detect if the skb being received by the user is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM flag - pass it to tcp_recvmsg_devmem() for custom handling. tcp_recvmsg_devmem() copies any data in the skb header to the linear buffer, and returns a cmsg to the user indicating the number of bytes returned in the linear buffer. tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags, and returns to the user a cmsg_devmem indicating the location of the data in the dmabuf device memory. cmsg_devmem contains this information: 1. the offset into the dmabuf where the payload starts. 'frag_offset'. 2. the size of the frag. 'frag_size'. 3. an opaque token 'frag_token' to return to the kernel when the buffer is to be released. The pages awaiting freeing are stored in the newly added sk->sk_user_frags, and each page passed to userspace is get_page()'d. This reference is dropped once the userspace indicates that it is done reading this page. All pages are released when the socket is destroyed. Signed-off-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Kaiyuan Zhang <kaiyuanz(a)google.com> Signed-off-by: Mina Almasry <almasrymina(a)google.com> Reviewed-by: Pavel Begunkov <asml.silence(a)gmail.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> --- v16: - Fix number assignement (Arnd). v13: - Refactored user frags cleanup into a common function to avoid __maybe_unused. (Pavel) - change to offset = 0 for some improved clarity. v11: - Refactor to common function te remove conditional lock sparse warning (Paolo) v7: - Updated the SO_DEVMEM_* uapi to use the next available entries (Arnd). - Updated dmabuf_cmsg struct to be __u64 padded (Arnd). - Squashed fix from Eric to initialize sk_user_frags for passive sockets (Eric). v6 - skb->dmabuf -> skb->readable (Pavel) - Fixed asm definitions of SO_DEVMEM_LINEAR/SO_DEVMEM_DMABUF not found on some archs. - Squashed in locking optimizations from edumazet(a)google.com. With this change we lock the xarray once per per tcp_recvmsg_dmabuf() rather than once per frag in xa_alloc(). Changes in v1: - Added dmabuf_id to dmabuf_cmsg (David/Stan). - Devmem -> dmabuf (David). - Change tcp_recvmsg_dmabuf() check to skb->dmabuf (Paolo). - Use __skb_frag_ref() & napi_pp_put_page() for refcounting (Yunsheng). RFC v3: - Fixed issue with put_cmsg() failing silently. --- arch/alpha/include/uapi/asm/socket.h | 5 + arch/mips/include/uapi/asm/socket.h | 5 + arch/parisc/include/uapi/asm/socket.h | 5 + arch/sparc/include/uapi/asm/socket.h | 5 + include/linux/socket.h | 1 + include/net/netmem.h | 13 ++ include/net/sock.h | 2 + include/uapi/asm-generic/socket.h | 5 + include/uapi/linux/uio.h | 13 ++ net/ipv4/tcp.c | 255 +++++++++++++++++++++++++- net/ipv4/tcp_ipv4.c | 16 ++ net/ipv4/tcp_minisocks.c | 2 + 12 files changed, 322 insertions(+), 5 deletions(-) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index e94f621903fe..ef4656a41058 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -140,6 +140,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 60ebaed28a4c..414807d55e33 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -151,6 +151,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index be264c2b1a11..2b817efd4544 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -132,6 +132,11 @@ #define SO_PASSPIDFD 0x404A #define SO_PEERPIDFD 0x404B +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 682da3714686..00248fc68977 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -133,6 +133,11 @@ #define SO_PASSPIDFD 0x0055 #define SO_PEERPIDFD 0x0056 +#define SO_DEVMEM_LINEAR 0x0057 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 0x0058 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) diff --git a/include/linux/socket.h b/include/linux/socket.h index df9cdb8bbfb8..d18cc47e89bd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -327,6 +327,7 @@ struct ucred { * plain text and require encryption */ +#define MSG_SOCK_DEVMEM 0x2000000 /* Receive devmem skbs as cmsg */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ diff --git a/include/net/netmem.h b/include/net/netmem.h index 284f84a312c2..84043fbdd797 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -65,6 +65,19 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov) return niov - net_iov_owner(niov)->niovs; } +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_virtual + + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding->id; +} + static inline struct net_devmem_dmabuf_binding * net_iov_binding(const struct net_iov *niov) { diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d514..f8ec869be238 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -337,6 +337,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_user_frags: xarray of pages the user is holding a reference on. */ struct sock { /* @@ -542,6 +543,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct xarray sk_user_frags; }; struct sock_bh_locked { diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 8ce8a39a1e5f..e993edc9c0ee 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -135,6 +135,11 @@ #define SO_PASSPIDFD 76 #define SO_PEERPIDFD 77 +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h index 059b1a9147f4..3a22ddae376a 100644 --- a/include/uapi/linux/uio.h +++ b/include/uapi/linux/uio.h @@ -20,6 +20,19 @@ struct iovec __kernel_size_t iov_len; /* Must be size_t (1003.1g) */ }; +struct dmabuf_cmsg { + __u64 frag_offset; /* offset into the dmabuf where the frag starts. + */ + __u32 frag_size; /* size of the frag. */ + __u32 frag_token; /* token representing this frag for + * DEVMEM_DONTNEED. + */ + __u32 dmabuf_id; /* dmabuf id this frag belongs to. */ + __u32 flags; /* Currently unused. Reserved for future + * uses. + */ +}; + /* * UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1) */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 30e0aa38ba9b..40e7335dae6e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -471,6 +471,7 @@ void tcp_init_sock(struct sock *sk) set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); @@ -2323,6 +2324,220 @@ static int tcp_inq_hint(struct sock *sk) return inq; } +/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ +struct tcp_xa_pool { + u8 max; /* max <= MAX_SKB_FRAGS */ + u8 idx; /* idx <= max */ + __u32 tokens[MAX_SKB_FRAGS]; + netmem_ref netmems[MAX_SKB_FRAGS]; +}; + +static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) +{ + int i; + + /* Commit part that has been copied to user space. */ + for (i = 0; i < p->idx; i++) + __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, + (__force void *)p->netmems[i], GFP_KERNEL); + /* Rollback what has been pre-allocated and is no longer needed. */ + for (; i < p->max; i++) + __xa_erase(&sk->sk_user_frags, p->tokens[i]); + + p->max = 0; + p->idx = 0; +} + +static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) +{ + if (!p->max) + return; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + xa_unlock_bh(&sk->sk_user_frags); +} + +static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, + unsigned int max_frags) +{ + int err, k; + + if (p->idx < p->max) + return 0; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + for (k = 0; k < max_frags; k++) { + err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); + if (err) + break; + } + + xa_unlock_bh(&sk->sk_user_frags); + + p->max = k; + p->idx = 0; + return k ? 0 : err; +} + +/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + struct tcp_xa_pool tcp_xa_pool; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + tcp_xa_pool.max = 0; + tcp_xa_pool.idx = 0; + do { + start = skb_headlen(skb); + + if (skb_frags_readable(skb)) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct net_iov *niov; + u64 frag_offset; + int end; + + /* !skb_frags_readable() should indicate that ALL the + * frags in this skb are dmabuf net_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting + * skb_frags_readable() correctly, we still don't want + * to crash here. + */ + if (!skb_frag_net_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with net_iov"); + err = -ENODEV; + goto out; + } + + niov = skb_frag_net_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = net_iov_virtual_addr(niov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = tcp_xa_pool_refill(sk, &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + /* Will perform the exchange later */ + dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; + dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + atomic_long_inc(&niov->pp_ref_count); + tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = 0; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2336,6 +2551,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2515,15 +2731,44 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, } if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != !skb_frags_readable(skb)) break; + + if (skb_frags_readable(skb)) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } } + last_copied_dmabuf = !skb_frags_readable(skb); + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fd17f25ff288..f3b2ae0823c4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -79,6 +79,7 @@ #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> +#include <linux/skbuff_ref.h> #include <crypto/hash.h> #include <linux/scatterlist.h> @@ -2507,10 +2508,25 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) } #endif +static void tcp_release_user_frags(struct sock *sk) +{ +#ifdef CONFIG_PAGE_POOL + unsigned long index; + void *netmem; + + xa_for_each(&sk->sk_user_frags, index, netmem) + WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); +#endif +} + void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + tcp_release_user_frags(sk); + + xa_destroy(&sk->sk_user_frags); + trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a19a9dbd3409..9ab87a41255d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -625,6 +625,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); -- 2.46.0.76.ge559c4bf1a-goog

10 months, 2 weeks

2
3
0 0

[PATCH net] tc-testing: don't access non-existent variable on exception

by Simon Horman

Since commit 255c1c7279ab ("tc-testing: Allow test cases to be skipped") the variable test_ordinal doesn't exist in call_pre_case(). So it should not be accessed when an exception occurs. This resolves the following splat: ... During handling of the above exception, another exception occurred: Traceback (most recent call last): File ".../tdc.py", line 1028, in <module> main() File ".../tdc.py", line 1022, in main set_operation_mode(pm, parser, args, remaining) File ".../tdc.py", line 966, in set_operation_mode catresults = test_runner_serial(pm, args, alltests) File ".../tdc.py", line 642, in test_runner_serial (index, tsr) = test_runner(pm, args, alltests) File ".../tdc.py", line 536, in test_runner res = run_one_test(pm, args, index, tidx) File ".../tdc.py", line 419, in run_one_test pm.call_pre_case(tidx) File ".../tdc.py", line 146, in call_pre_case print('test_ordinal is {}'.format(test_ordinal)) NameError: name 'test_ordinal' is not defined Fixes: 255c1c7279ab ("tc-testing: Allow test cases to be skipped") Signed-off-by: Simon Horman <horms(a)kernel.org> --- tools/testing/selftests/tc-testing/tdc.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index ee349187636f..4f255cec0c22 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -143,7 +143,6 @@ class PluginMgr: except Exception as ee: print('exception {} in call to pre_case for {} plugin'. format(ee, pgn_inst.__class__)) - print('test_ordinal is {}'.format(test_ordinal)) print('testid is {}'.format(caseinfo['id'])) raise

10 months, 2 weeks

3
2
0 0

[RFC PATCH] selftests/mm: compaction_test: Move often used filepaths to strings

by Aryabhatta Dey

Add defines for the file path names to avoid duplicate strings in print messages and make it easier to maintain. Signed-off-by: Aryabhatta Dey <aryabhattadey35(a)gmail.com> --- tools/testing/selftests/mm/compaction_test.c | 46 ++++++++++---------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..8f46431a9182 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -21,6 +21,9 @@ #define MAP_SIZE_MB 100 #define MAP_SIZE (MAP_SIZE_MB * 1024 * 1024) +#define COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH "/proc/sys/vm/compact_unevictable_allowed" +#define NR_HUGEPAGES_FILE_NAME_PATH "/proc/sys/vm/nr_hugepages" + struct map_list { void *map; struct map_list *next; @@ -59,17 +62,16 @@ int prereq(void) char allowed; int fd; - fd = open("/proc/sys/vm/compact_unevictable_allowed", - O_RDONLY | O_NONBLOCK); + fd = open(COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH, O_RDONLY | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH, strerror(errno)); return -1; } if (read(fd, &allowed, sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED_FILE_PATH, strerror(errno)); close(fd); return -1; } @@ -97,10 +99,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, in to play */ mem_free = mem_free * 0.8; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES_FILE_NAME_PATH, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); ret = -1; goto out; } @@ -108,16 +110,16 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 100000 to %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to re-read from %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } @@ -134,8 +136,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) != strlen(init_nr_hugepages)) { - ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write value to %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } @@ -162,15 +164,15 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) int fd, ret = -1; char nr_hugepages[20] = {0}; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES_FILE_NAME_PATH, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto out; } if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } @@ -178,8 +180,8 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) /* Start with the initial condition of 0 huge pages */ if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 0 to %s: %s\n", + NR_HUGEPAGES_FILE_NAME_PATH, strerror(errno)); goto close_fd; } -- 2.46.0

10 months, 2 weeks

1
0
0 0

[RFC PATCH] selftests/mm: compaction_test: Move often used filepaths to strings

by Aryabhatta Dey

Add defines for file path names to avoid duplicate strings in print messages and make it easier to maintain. Signed-off-by: Aryabhatta Dey <aryabhattadey35(a)gmail.com> --- tools/testing/selftests/mm/compaction_test.c | 46 ++++++++++---------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index e140558e6f53..541ac0373258 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -21,6 +21,9 @@ #define MAP_SIZE_MB 100 #define MAP_SIZE (MAP_SIZE_MB * 1024 * 1024) +#define COMPACT_UNEVICTABLE_ALLOWED "/proc/sys/vm/compact_unevictable_allowed" +#define NR_HUGEPAGES "/proc/sys/vm/nr_hugepages" + struct map_list { void *map; struct map_list *next; @@ -59,17 +62,16 @@ int prereq(void) char allowed; int fd; - fd = open("/proc/sys/vm/compact_unevictable_allowed", - O_RDONLY | O_NONBLOCK); + fd = open(COMPACT_UNEVICTABLE_ALLOWED, O_RDONLY | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED, strerror(errno)); return -1; } if (read(fd, &allowed, sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to read from /proc/sys/vm/compact_unevictable_allowed: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + COMPACT_UNEVICTABLE_ALLOWED, strerror(errno)); close(fd); return -1; } @@ -97,10 +99,10 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, in to play */ mem_free = mem_free * 0.8; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES, strerror(errno)); ret = -1; goto out; } @@ -108,16 +110,16 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 100000 to %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } lseek(fd, 0, SEEK_SET); if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to re-read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to re-read from %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } @@ -134,8 +136,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) != strlen(init_nr_hugepages)) { - ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write value to %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } @@ -162,15 +164,15 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) int fd, ret = -1; char nr_hugepages[20] = {0}; - fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + fd = open(NR_HUGEPAGES, O_RDWR | O_NONBLOCK); if (fd < 0) { - ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to open %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto out; } if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to read from %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } @@ -178,8 +180,8 @@ int set_zero_hugepages(unsigned long *initial_nr_hugepages) /* Start with the initial condition of 0 huge pages */ if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + ksft_print_msg("Failed to write 0 to %s: %s\n", + NR_HUGEPAGES, strerror(errno)); goto close_fd; } -- 2.46.0

10 months, 2 weeks

1
0
0 0

[PATCH RFT v8 0/9] fork: Support shadow stacks in clone3()

by Mark Brown

The kernel has recently added support for shadow stacks, currently x86 only using their CET feature but both arm64 and RISC-V have equivalent features (GCS and Zicfiss respectively), I am actively working on GCS[1]. With shadow stacks the hardware maintains an additional stack containing only the return addresses for branch instructions which is not generally writeable by userspace and ensures that any returns are to the recorded addresses. This provides some protection against ROP attacks and making it easier to collect call stacks. These shadow stacks are allocated in the address space of the userspace process. Our API for shadow stacks does not currently offer userspace any flexiblity for managing the allocation of shadow stacks for newly created threads, instead the kernel allocates a new shadow stack with the same size as the normal stack whenever a thread is created with the feature enabled. The stacks allocated in this way are freed by the kernel when the thread exits or shadow stacks are disabled for the thread. This lack of flexibility and control isn't ideal, in the vast majority of cases the shadow stack will be over allocated and the implicit allocation and deallocation is not consistent with other interfaces. As far as I can tell the interface is done in this manner mainly because the shadow stack patches were in development since before clone3() was implemented. Since clone3() is readily extensible let's add support for specifying a shadow stack when creating a new thread or process in a similar manner to how the normal stack is specified, keeping the current implicit allocation behaviour if one is not specified either with clone3() or through the use of clone(). The user must provide a shadow stack address and size, this must point to memory mapped for use as a shadow stackby map_shadow_stack() with a shadow stack token at the top of the stack. Please note that the x86 portions of this code are build tested only, I don't appear to have a system that can run CET avaible to me, I have done testing with an integration into my pending work for GCS. There is some possibility that the arm64 implementation may require the use of clone3() and explicit userspace allocation of shadow stacks, this is still under discussion. Please further note that the token consumption done by clone3() is not currently implemented in an atomic fashion, Rick indicated that he would look into fixing this if people are OK with the implementation. A new architecture feature Kconfig option for shadow stacks is added as here, this was suggested as part of the review comments for the arm64 GCS series and since we need to detect if shadow stacks are supported it seemed sensible to roll it in here. [1] https://lore.kernel.org/r/20231009-arm64-gcs-v6-0-78e55deaa4dd@kernel.org/ Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v8: - Fix token verification with user specified shadow stack. - Don't track user managed shadow stacks for child processes. - Link to v7: https://lore.kernel.org/r/20240731-clone3-shadow-stack-v7-0-a9532eebfb1d@ke… Changes in v7: - Rebase onto v6.11-rc1. - Typo fixes. - Link to v6: https://lore.kernel.org/r/20240623-clone3-shadow-stack-v6-0-9ee7783b1fb9@ke… Changes in v6: - Rebase onto v6.10-rc3. - Ensure we don't try to free the parent shadow stack in error paths of x86 arch code. - Spelling fixes in userspace API document. - Additional cleanups and improvements to the clone3() tests to support the shadow stack tests. - Link to v5: https://lore.kernel.org/r/20240203-clone3-shadow-stack-v5-0-322c69598e4b@ke… Changes in v5: - Rebase onto v6.8-rc2. - Rework ABI to have the user allocate the shadow stack memory with map_shadow_stack() and a token. - Force inlining of the x86 shadow stack enablement. - Move shadow stack enablement out into a shared header for reuse by other tests. - Link to v4: https://lore.kernel.org/r/20231128-clone3-shadow-stack-v4-0-8b28ffe4f676@ke… Changes in v4: - Formatting changes. - Use a define for minimum shadow stack size and move some basic validation to fork.c. - Link to v3: https://lore.kernel.org/r/20231120-clone3-shadow-stack-v3-0-a7b8ed3e2acc@ke… Changes in v3: - Rebase onto v6.7-rc2. - Remove stale shadow_stack in internal kargs. - If a shadow stack is specified unconditionally use it regardless of CLONE_ parameters. - Force enable shadow stacks in the selftest. - Update changelogs for RISC-V feature rename. - Link to v2: https://lore.kernel.org/r/20231114-clone3-shadow-stack-v2-0-b613f8681155@ke… Changes in v2: - Rebase onto v6.7-rc1. - Remove ability to provide preallocated shadow stack, just specify the desired size. - Link to v1: https://lore.kernel.org/r/20231023-clone3-shadow-stack-v1-0-d867d0b5d4d0@ke… --- Mark Brown (9): Documentation: userspace-api: Add shadow stack API documentation selftests: Provide helper header for shadow stack testing mm: Introduce ARCH_HAS_USER_SHADOW_STACK fork: Add shadow stack support to clone3() selftests/clone3: Remove redundant flushes of output streams selftests/clone3: Factor more of main loop into test_clone3() selftests/clone3: Explicitly handle child exits due to signals selftests/clone3: Allow tests to flag if -E2BIG is a valid error code selftests/clone3: Test shadow stack support Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/shadow_stack.rst | 41 ++++ arch/x86/Kconfig | 1 + arch/x86/include/asm/shstk.h | 11 +- arch/x86/kernel/process.c | 2 +- arch/x86/kernel/shstk.c | 105 +++++++--- fs/proc/task_mmu.c | 2 +- include/linux/mm.h | 2 +- include/linux/sched/task.h | 13 ++ include/uapi/linux/sched.h | 13 +- kernel/fork.c | 76 ++++++-- mm/Kconfig | 6 + tools/testing/selftests/clone3/clone3.c | 224 ++++++++++++++++++---- tools/testing/selftests/clone3/clone3_selftests.h | 40 +++- tools/testing/selftests/ksft_shstk.h | 63 ++++++ 15 files changed, 513 insertions(+), 87 deletions(-) --- base-commit: 8400291e289ee6b2bf9779ff1c83a291501f017b change-id: 20231019-clone3-shadow-stack-15d40d2bf536 Best regards, -- Mark Brown <broonie(a)kernel.org>

10 months, 2 weeks

5
33
0 0

[PATCH net-next v19 06/13] memory-provider: dmabuf devmem memory provider

by Mina Almasry

Implement a memory provider that allocates dmabuf devmem in the form of net_iov. The provider receives a reference to the struct netdev_dmabuf_binding via the pool->mp_priv pointer. The driver needs to set this pointer for the provider in the net_iov. The provider obtains a reference on the netdev_dmabuf_binding which guarantees the binding and the underlying mapping remains alive until the provider is destroyed. Usage of PP_FLAG_DMA_MAP is required for this memory provide such that the page_pool can provide the driver with the dma-addrs of the devmem. Support for PP_FLAG_DMA_SYNC_DEV is omitted for simplicity & p.order != 0. Signed-off-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Kaiyuan Zhang <kaiyuanz(a)google.com> Signed-off-by: Mina Almasry <almasrymina(a)google.com> Reviewed-by: Pavel Begunkov <asml.silence(a)gmail.com> --- v19: - Add PP_FLAG_ALLOW_UNREADABLE_NETMEM flag. It serves 2 purposes, (a) it guards drivers that don't support unreadable netmem (net_iov backed) from accidentally getting exposed to it, and (b) drivers that wish to create header pools can unset it for that pool to force readable netmem. - Add page_pool_check_memory_provider, which verifies that the driver has created a page_pool with the expected configuration. This is used to report to the user if the mp configuration succeeded, and also verify that the driver is doing the right thing. - Don't reset niov->dma_addr on allocation/free. v17: - Use ASSERT_RTNL (Jakub) v16: - Add DEBUG_NET_WARN_ON_ONCE(!rtnl_is_locked()), to catch cases if page_pool_init without rtnl_locking when the queue is provided. In this case, the queue configuration may be changed while we're initing the page_pool, which could be a race. v13: - Return on warning (Pavel). - Fixed pool->recycle_stats not being freed on error (Pavel). - Applied reviewed-by from Pavel. v11: - Rebase to not use the ops. (Christoph) v8: - Use skb_frag_size instead of frag->bv_len to fix patch-by-patch build error v6: - refactor new memory provider functions into net/core/devmem.c (Pavel) v2: - Disable devmem for p.order != 0 v1: - static_branch check in page_is_page_pool_iov() (Willem & Paolo). - PP_DEVMEM -> PP_IOV (David). - Require PP_FLAG_DMA_MAP (Jakub). --- include/net/mp_dmabuf_devmem.h | 44 ++++++++++++++ include/net/page_pool/types.h | 16 ++++- net/core/devmem.c | 70 ++++++++++++++++++++++ net/core/page_pool.c | 103 ++++++++++++++++++++++++--------- net/core/page_pool_priv.h | 6 ++ net/core/page_pool_user.c | 26 +++++++++ 6 files changed, 237 insertions(+), 28 deletions(-) create mode 100644 include/net/mp_dmabuf_devmem.h diff --git a/include/net/mp_dmabuf_devmem.h b/include/net/mp_dmabuf_devmem.h new file mode 100644 index 000000000000..300a2356eed0 --- /dev/null +++ b/include/net/mp_dmabuf_devmem.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Dmabuf device memory provider. + * + * Authors: Mina Almasry <almasrymina(a)google.com> + * + */ +#ifndef _NET_MP_DMABUF_DEVMEM_H +#define _NET_MP_DMABUF_DEVMEM_H + +#include <net/netmem.h> + +#if defined(CONFIG_DMA_SHARED_BUFFER) && defined(CONFIG_GENERIC_ALLOCATOR) +int mp_dmabuf_devmem_init(struct page_pool *pool); + +netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp); + +void mp_dmabuf_devmem_destroy(struct page_pool *pool); + +bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem); +#else +static inline int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + return -EOPNOTSUPP; +} + +static inline netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, + gfp_t gfp) +{ + return 0; +} + +static inline void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ +} + +static inline bool mp_dmabuf_devmem_release_page(struct page_pool *pool, + netmem_ref netmem) +{ + return false; +} +#endif + +#endif /* _NET_MP_DMABUF_DEVMEM_H */ diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 4afd6dd56351..e221521cd7f3 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -20,8 +20,17 @@ * device driver responsibility */ #define PP_FLAG_SYSTEM_POOL BIT(2) /* Global system page_pool */ +#define PP_FLAG_ALLOW_UNREADABLE_NETMEM BIT(3) /* Allow unreadable (net_iov + * backed) netmem in this + * page_pool. Drivers setting + * this must be able to support + * unreadable netmem, where + * netmem_address() would return + * NULL. This flag should not be + * set for header page_pools. + */ #define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \ - PP_FLAG_SYSTEM_POOL) + PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM) /* * Fast allocation side cache array/stack @@ -52,12 +61,14 @@ struct pp_alloc_cache { * @nid: NUMA node id to allocate from pages from * @dev: device, for DMA pre-mapping purposes * @napi: NAPI which is the sole consumer of pages, otherwise NULL + * @queue: struct netdev_rx_queue this page_pool is being created for. * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV * @slow: params with slowpath access only (initialization and Netlink) * @netdev: netdev this pool will serve (leave as NULL if none or multiple) - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL, + * PP_FLAG_ALLOW_UNREADABLE_NETMEM. */ struct page_pool_params { struct_group_tagged(page_pool_params_fast, fast, @@ -66,6 +77,7 @@ struct page_pool_params { int nid; struct device *dev; struct napi_struct *napi; + struct netdev_rx_queue *queue; enum dma_data_direction dma_dir; unsigned int max_len; unsigned int offset; diff --git a/net/core/devmem.c b/net/core/devmem.c index 301f4250ca82..2f2a7f4dee4c 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -17,6 +17,7 @@ #include <linux/genalloc.h> #include <linux/dma-buf.h> #include <net/devmem.h> +#include <net/mp_dmabuf_devmem.h> #include <net/netdev_queues.h> #include "page_pool_priv.h" @@ -153,6 +154,10 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, if (err) goto err_xa_erase; + err = page_pool_check_memory_provider(dev, rxq, binding); + if (err) + goto err_xa_erase; + return 0; err_xa_erase: @@ -305,4 +310,69 @@ void dev_dmabuf_uninstall(struct net_device *dev) xa_erase(&binding->bound_rxqs, xa_idx); } } + +/*** "Dmabuf devmem memory provider" ***/ + +int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + if (!binding) + return -EINVAL; + + if (!pool->dma_map) + return -EOPNOTSUPP; + + if (pool->dma_sync) + return -EOPNOTSUPP; + + if (pool->p.order != 0) + return -E2BIG; + + net_devmem_dmabuf_binding_get(binding); + return 0; +} + +netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + netmem_ref netmem; + struct net_iov *niov; + + niov = net_devmem_alloc_dmabuf(binding); + if (!niov) + return 0; + + netmem = net_iov_to_netmem(niov); + + page_pool_set_pp_info(pool, netmem); + + pool->pages_state_hold_cnt++; + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); + return netmem; +} + +void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + net_devmem_dmabuf_binding_put(binding); +} + +bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem) +{ + if (WARN_ON_ONCE(!netmem_is_net_iov(netmem))) + return false; + + if (WARN_ON_ONCE(atomic_long_read(netmem_get_pp_ref_count_ref(netmem)) != + 1)) + return false; + + page_pool_clear_pp_info(netmem); + + net_devmem_free_dmabuf(netmem_to_net_iov(netmem)); + + /* We don't want the page pool put_page()ing our net_iovs. */ + return false; +} #endif diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 13277f05aebd..25be3327561b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -13,6 +13,7 @@ #include <net/page_pool/helpers.h> #include <net/xdp.h> +#include <net/netdev_rx_queue.h> #include <linux/dma-direction.h> #include <linux/dma-mapping.h> @@ -21,6 +22,9 @@ #include <linux/poison.h> #include <linux/ethtool.h> #include <linux/netdevice.h> +#include <linux/genalloc.h> +#include <net/devmem.h> +#include <net/mp_dmabuf_devmem.h> #include <trace/events/page_pool.h> @@ -28,6 +32,7 @@ #include "netmem_priv.h" DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); +EXPORT_SYMBOL(page_pool_mem_providers); #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -190,6 +195,7 @@ static int page_pool_init(struct page_pool *pool, int cpuid) { unsigned int ring_qsize = 1024; /* Default */ + int err; page_pool_struct_check(); @@ -271,7 +277,36 @@ static int page_pool_init(struct page_pool *pool, if (pool->dma_map) get_device(pool->p.dev); + if (pool->p.queue && + pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) { + /* We rely on rtnl_lock()ing to make sure netdev_rx_queue + * configuration doesn't change while we're initializing the + * page_pool. + */ + ASSERT_RTNL(); + pool->mp_priv = pool->p.queue->mp_params.mp_priv; + } + + if (pool->mp_priv) { + err = mp_dmabuf_devmem_init(pool); + if (err) { + pr_warn("%s() mem-provider init failed %d\n", __func__, + err); + goto free_ptr_ring; + } + + static_branch_inc(&page_pool_mem_providers); + } + return 0; + +free_ptr_ring: + ptr_ring_cleanup(&pool->ring, NULL); +#ifdef CONFIG_PAGE_POOL_STATS + if (!pool->system) + free_percpu(pool->recycle_stats); +#endif + return err; } static void page_pool_uninit(struct page_pool *pool) @@ -455,28 +490,6 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem) return false; } -static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) -{ - netmem_set_pp(netmem, pool); - netmem_or_pp_magic(netmem, PP_SIGNATURE); - - /* Ensuring all pages have been split into one fragment initially: - * page_pool_set_pp_info() is only called once for every page when it - * is allocated from the page allocator and page_pool_fragment_page() - * is dirtying the same cache line as the page->pp_magic above, so - * the overhead is negligible. - */ - page_pool_fragment_netmem(netmem, 1); - if (pool->has_init_callback) - pool->slow.init_callback(netmem, pool->slow.init_arg); -} - -static void page_pool_clear_pp_info(netmem_ref netmem) -{ - netmem_clear_pp_magic(netmem); - netmem_set_pp(netmem, NULL); -} - static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) { @@ -572,7 +585,10 @@ netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp) return netmem; /* Slow-path: cache empty, do real allocation */ - netmem = __page_pool_alloc_pages_slow(pool, gfp); + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) + netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp); + else + netmem = __page_pool_alloc_pages_slow(pool, gfp); return netmem; } EXPORT_SYMBOL(page_pool_alloc_netmem); @@ -608,6 +624,28 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict) return inflight; } +void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) +{ + netmem_set_pp(netmem, pool); + netmem_or_pp_magic(netmem, PP_SIGNATURE); + + /* Ensuring all pages have been split into one fragment initially: + * page_pool_set_pp_info() is only called once for every page when it + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_netmem(netmem, 1); + if (pool->has_init_callback) + pool->slow.init_callback(netmem, pool->slow.init_arg); +} + +void page_pool_clear_pp_info(netmem_ref netmem) +{ + netmem_clear_pp_magic(netmem); + netmem_set_pp(netmem, NULL); +} + static __always_inline void __page_pool_release_page_dma(struct page_pool *pool, netmem_ref netmem) { @@ -636,8 +674,13 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool, void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) { int count; + bool put; - __page_pool_release_page_dma(pool, netmem); + put = true; + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) + put = mp_dmabuf_devmem_release_page(pool, netmem); + else + __page_pool_release_page_dma(pool, netmem); /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. @@ -645,8 +688,10 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, netmem, count); - page_pool_clear_pp_info(netmem); - put_page(netmem_to_page(netmem)); + if (put) { + page_pool_clear_pp_info(netmem); + put_page(netmem_to_page(netmem)); + } /* An optimization would be to call __free_pages(page, pool->p.order) * knowing page is not part of page-cache (thus avoiding a * __page_cache_release() call). @@ -965,6 +1010,12 @@ static void __page_pool_destroy(struct page_pool *pool) page_pool_unlist(pool); page_pool_uninit(pool); + + if (pool->mp_priv) { + mp_dmabuf_devmem_destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } + kfree(pool); } diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index 581501b5cd8c..fcd9c1a227bc 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -33,4 +33,10 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); } +void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem); +void page_pool_clear_pp_info(netmem_ref netmem); +int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq, + struct net_devmem_dmabuf_binding *binding); + #endif diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 3a3277ba167b..cbc54ee4f670 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -344,6 +344,32 @@ void page_pool_unlist(struct page_pool *pool) mutex_unlock(&page_pools_lock); } +int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq, + struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *binding_rxq; + struct page_pool *pool; + struct hlist_node *n; + unsigned long xa_idx; + + mutex_lock(&page_pools_lock); + hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) { + if (pool->mp_priv != binding) + continue; + + xa_for_each(&binding->bound_rxqs, xa_idx, binding_rxq) { + if (rxq != binding_rxq) + continue; + + mutex_unlock(&page_pools_lock); + return 0; + } + } + mutex_unlock(&page_pools_lock); + return -ENODATA; +} + static void page_pool_unreg_netdev_wipe(struct net_device *netdev) { struct page_pool *pool; -- 2.46.0.76.ge559c4bf1a-goog

10 months, 2 weeks

3
7
0 0

[PATCH 1/1] KVM: selftests: add kvmclock drift test

by Dongli Zhang

There is kvmclock drift issue during the vCPU hotplug. It has been fixed by the commit c52ffadc65e2 ("KVM: x86: Don't unnecessarily force masterclock update on vCPU hotplug"). This is to add the test to verify if the master clock is updated when we write 0 to MSR_IA32_TSC from the host side. Here is the usage example on the KVM with the bugfix reverted. $ ./kvm_clock_drift -v -p 5 kvmclock based on old pvclock_vcpu_time_info: 5012221999 version: 2 tsc_timestamp: 3277968 system_time: 11849519 tsc_to_system_mul: 2152530255 tsc_shift: 0 flags: 1 kvmclock based on new pvclock_vcpu_time_info: 5012222411 version: 4 tsc_timestamp: 9980576184 system_time: 5012222411 tsc_to_system_mul: 2152530255 tsc_shift: 0 flags: 1 ==== Test Assertion Failure ==== x86_64/kvm_clock_drift.c:216: clock_old == clock_new pid=14257 tid=14257 errno=4 - Interrupted system call 1 0x000000000040277b: main at kvm_clock_drift.c:216 2 0x00007f7766fa7e44: ?? ??:0 3 0x000000000040286d: _start at ??:? kvmclock drift detected, old=5012221999, new=5012222411 Signed-off-by: Dongli Zhang <dongli.zhang(a)oracle.com> --- tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/x86_64/kvm_clock_drift.c | 223 ++++++++++++++++++ 2 files changed, 224 insertions(+) create mode 100644 tools/testing/selftests/kvm/x86_64/kvm_clock_drift.c diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 4412b42d95de..c665d0d8d348 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -84,6 +84,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush +TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_drift TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_drift.c b/tools/testing/selftests/kvm/x86_64/kvm_clock_drift.c new file mode 100644 index 000000000000..324f0dbc5762 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/kvm_clock_drift.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * The kvmclock drift test. Emulate vCPU hotplug and online to verify if + * there is kvmclock drift. + * + * Adapted from steal_time.c + * + * Copyright (C) 2020, Red Hat, Inc. + * Copyright (C) 2024 Oracle and/or its affiliates. + */ + +#include <asm/kvm_para.h> +#include <asm/pvclock.h> +#include <asm/pvclock-abi.h> +#include <sys/stat.h> + +#include "kvm_util.h" +#include "processor.h" + +#define NR_VCPUS 2 +#define NR_SLOTS 2 +#define KVMCLOCK_SIZE sizeof(struct pvclock_vcpu_time_info) +/* + * KVMCLOCK_GPA is identity mapped + */ +#define KVMCLOCK_GPA (1 << 30) + +static uint64_t kvmclock_gpa = KVMCLOCK_GPA; + +static void guest_code(int cpu) +{ + struct pvclock_vcpu_time_info *kvmclock; + + /* + * vCPU#0 is to detect the change of pvclock_vcpu_time_info + */ + if (cpu == 0) { + GUEST_SYNC(0); + + kvmclock = (struct pvclock_vcpu_time_info *) kvmclock_gpa; + wrmsr(MSR_KVM_SYSTEM_TIME_NEW, kvmclock_gpa | KVM_MSR_ENABLED); + + /* + * Backup the pvclock_vcpu_time_info before vCPU#1 hotplug + */ + kvmclock[1] = kvmclock[0]; + + GUEST_SYNC(2); + /* + * Enter the guest to update pvclock_vcpu_time_info + */ + GUEST_SYNC(4); + } + + /* + * vCPU#1 is to emulate the vCPU hotplug + */ + if (cpu == 1) { + GUEST_SYNC(1); + /* + * This is after the host side MSR_IA32_TSC + */ + GUEST_SYNC(3); + } +} + +static void run_vcpu(struct kvm_vcpu *vcpu) +{ + struct ucall uc; + + vcpu_run(vcpu); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_SYNC: + case UCALL_DONE: + break; + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + default: + TEST_ASSERT(false, "Unexpected exit: %s", + exit_reason_str(vcpu->run->exit_reason)); + } +} + +static void kvmclock_dump(struct pvclock_vcpu_time_info *kvmclock) +{ + pr_info(" version: %u\n", kvmclock->version); + pr_info(" tsc_timestamp: %lu\n", kvmclock->tsc_timestamp); + pr_info(" system_time: %lu\n", kvmclock->system_time); + pr_info(" tsc_to_system_mul: %u\n", kvmclock->tsc_to_system_mul); + pr_info(" tsc_shift: %d\n", kvmclock->tsc_shift); + pr_info(" flags: %u\n", kvmclock->flags); + pr_info("\n"); +} + +#define CLOCKSOURCE_PATH "/sys/devices/system/clocksource/clocksource0/current_clocksource" + +static void check_clocksource(void) +{ + char *clk_name; + struct stat st; + FILE *fp; + + fp = fopen(CLOCKSOURCE_PATH, "r"); + if (!fp) { + pr_info("failed to open clocksource file: %d; assuming TSC.\n", + errno); + return; + } + + if (fstat(fileno(fp), &st)) { + pr_info("failed to stat clocksource file: %d; assuming TSC.\n", + errno); + goto out; + } + + clk_name = malloc(st.st_size); + TEST_ASSERT(clk_name, "failed to allocate buffer to read file\n"); + + if (!fgets(clk_name, st.st_size, fp)) { + pr_info("failed to read clocksource file: %d; assuming TSC.\n", + ferror(fp)); + goto out; + } + + TEST_ASSERT(!strncmp(clk_name, "tsc\n", st.st_size), + "clocksource not supported: %s", clk_name); +out: + fclose(fp); +} + +int main(int argc, char *argv[]) +{ + struct pvclock_vcpu_time_info *kvmclock; + struct kvm_vcpu *vcpus[NR_VCPUS]; + uint64_t clock_old, clock_new; + bool verbose = false; + unsigned int gpages; + struct kvm_vm *vm; + int period = 2; + uint64_t tsc; + int opt; + + check_clocksource(); + + while ((opt = getopt(argc, argv, "p:vh")) != -1) { + switch (opt) { + case 'p': + period = atoi_positive("The period (seconds) between vCPU hotplug", + optarg); + break; + case 'v': + verbose = true; + break; + case 'h': + default: + pr_info("usage: %s [-p period (seconds)] [-v]\n", argv[0]); + exit(1); + } + } + + vm = vm_create_with_vcpus(NR_VCPUS, guest_code, vcpus); + gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, + KVMCLOCK_SIZE * NR_SLOTS); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + KVMCLOCK_GPA, 1, gpages, 0); + virt_map(vm, KVMCLOCK_GPA, KVMCLOCK_GPA, gpages); + + vcpu_args_set(vcpus[0], 1, 0); + vcpu_args_set(vcpus[1], 1, 1); + + /* + * Run vCPU#0 and vCPU#1 to update both pvclock_vcpu_time_info and + * master clock + */ + run_vcpu(vcpus[0]); + run_vcpu(vcpus[1]); + + /* + * Run vCPU#0 to backup the current pvclock_vcpu_time_info + */ + run_vcpu(vcpus[0]); + + sleep(period); + + /* + * Emulate the hotplug of vCPU#1 + */ + vcpu_set_msr(vcpus[1], MSR_IA32_TSC, 0); + + /* + * Emulate the online of vCPU#1 + */ + run_vcpu(vcpus[1]); + + /* + * Run vCPU#0 to backup the new pvclock_vcpu_time_info to detect + * if there is any change or kvmclock drift + */ + run_vcpu(vcpus[0]); + + kvmclock = addr_gva2hva(vm, kvmclock_gpa); + tsc = kvmclock[0].tsc_timestamp; + clock_old = __pvclock_read_cycles(&kvmclock[1], tsc); + clock_new = __pvclock_read_cycles(&kvmclock[0], tsc); + + if (verbose) { + pr_info("kvmclock based on old pvclock_vcpu_time_info: %lu\n", + clock_old); + kvmclock_dump(&kvmclock[1]); + pr_info("kvmclock based on new pvclock_vcpu_time_info: %lu\n", + clock_new); + kvmclock_dump(&kvmclock[0]); + } + + TEST_ASSERT(clock_old == clock_new, + "kvmclock drift detected, old=%lu, new=%lu", + clock_old, clock_new); + + kvm_vm_free(vm); + + return 0; +} base-commit: f2a3fb7234e52f72ff4a38364dbf639cf4c7d6c6 -- 2.34.1

10 months, 2 weeks

3
3
0 0

[PATCH net-next v4] net: netconsole: selftests: Create a new netconsole selftest

by Breno Leitao

Adds a selftest that creates two virtual interfaces, assigns one to a new namespace, and assigns IP addresses to both. It listens on the destination interface using socat and configures a dynamic target on netconsole, pointing to the destination IP address. The test then checks if the message was received properly on the destination interface. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Changelog: v4: * Avoid sleeping in waiting for sockets and files (Matthieu Baerts) * Some other improvements (Matthieu Baerts) * Add configfs as a dependency (Jakub) v3: * Defined CONFIGs in config file (Jakub) * Identention fixes (Petr Machata) * Use setup_ns in a better way (Matthieu Baerts) * Add dependencies in TEST_INCLUDES (Hangbin Liu) * https://lore.kernel.org/all/20240815095157.3064722-1-leitao@debian.org/ v2: * Change the location of the path (Jakub) * Move from veth to netdevsim * Other small changes in dependency checks and cleanup * https://lore.kernel.org/all/20240813183825.837091-1-leitao@debian.org/ v1: * https://lore.kernel.org/all/ZqyUHN770pjSofTC@gmail.com/ MAINTAINERS | 1 + tools/testing/selftests/drivers/net/Makefile | 4 +- tools/testing/selftests/drivers/net/config | 4 + .../selftests/drivers/net/netcons_basic.sh | 249 ++++++++++++++++++ 4 files changed, 257 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/drivers/net/netcons_basic.sh diff --git a/MAINTAINERS b/MAINTAINERS index 5dbf23cf11c8..9a371ddd8719 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15772,6 +15772,7 @@ M: Breno Leitao <leitao(a)debian.org> S: Maintained F: Documentation/networking/netconsole.rst F: drivers/net/netconsole.c +F: tools/testing/selftests/drivers/net/netcons_basic.sh NETDEVSIM M: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index e54f382bcb02..8bee2e94049b 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_INCLUDES := $(wildcard lib/py/*.py) +TEST_INCLUDES := $(wildcard lib/py/*.py) \ + ../../net/lib.sh \ TEST_PROGS := \ + netcons_basic.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index f6a58ce8a230..a2d8af60876d 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -1,2 +1,6 @@ CONFIG_IPV6=y CONFIG_NETDEVSIM=m +CONFIG_CONFIGFS_FS=y +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETCONSOLE_EXTENDED_LOG=y diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh new file mode 100755 index 000000000000..5c3686af1fe8 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -0,0 +1,249 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test creates two netdevsim virtual interfaces, assigns one of them (the +# "destination interface") to a new namespace, and assigns IP addresses to both +# interfaces. +# +# It listens on the destination interface using socat and configures a dynamic +# target on netconsole, pointing to the destination IP address. +# +# Finally, it checks whether the message was received properly on the +# destination interface. Note that this test may pollute the kernel log buffer +# (dmesg) and relies on dynamic configuration and namespaces being configured. +# +# Author: Breno Leitao <leitao(a)debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +# Simple script to test dynamic targets in netconsole +SRCIF="" # to be populated later +SRCIP=192.168.1.1 +DSTIF="" # to be populated later +DSTIP=192.168.1.2 + +PORT="6666" +MSG="netconsole selftest" +TARGET=$(mktemp -u netcons_XXXXX) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# NAMESPACE will be populated by setup_ns with a random value +NAMESPACE="" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) + +# Used to create and delete namespaces +source "${SCRIPTDIR}"/../../net/lib.sh +source "${SCRIPTDIR}"/../../net/net_helper.sh + +# Create netdevsim interfaces +create_ifaces() { + local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle 2> /dev/null || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" + exec {INITNS_FD}</proc/self/ns/net + + # Bind the dst interface to namespace + ip link set "${DSTIF}" netns "${NAMESPACE}" + + # Linking one device to the other one (on the other namespace} + if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK + then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit "${ksft_skip}" + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # setup_ns function is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + exit "${ksft_pass}" +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This script must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi +} + +check_file_size() { + local file="$1" + + if [[ ! -f "$file" ]]; then + # File might not exist yet + return 1 + fi + + # Get file size + local size=$(stat -c %s "$file" 2>/dev/null) + # Check if stat command succeeded + if [[ $? -ne 0 ]]; then + return 1 + fi + + # Check if size is greater than zero + if [[ "$size" -gt 0 ]]; then + return 0 # file size > 0 + else + return 1 # file size == 0 + fi +} + + +# ========== # +# Start here # +# ========== # +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2 > /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" check_file_size "${OUTPUT_FILE}" + +# Make sure the message was received in the dst part +# and exit +validate_result "${OUTPUT_FILE}" -- 2.43.5

10 months, 2 weeks

2
3
0 0

[PATCH net-next v3] net: netconsole: selftests: Create a new netconsole selftest

by Breno Leitao

Adds a selftest that creates two virtual interfaces, assigns one to a new namespace, and assigns IP addresses to both. It listens on the destination interface using socat and configures a dynamic target on netconsole, pointing to the destination IP address. The test then checks if the message was received properly on the destination interface. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Changelog: v3: * Defined CONFIGs in config file (Jakub) * Identention fixes (Petr Machata) * Use setup_ns in a better way (Matthieu Baerts) * Add dependencies in TEST_INCLUDES (Hangbin Liu) v2: * Change the location of the path (Jakub) * Move from veth to netdevsim * Other small changes in dependency checks and cleanup * https://lore.kernel.org/all/20240813183825.837091-1-leitao@debian.org/ v1: * https://lore.kernel.org/all/ZqyUHN770pjSofTC@gmail.com/ MAINTAINERS | 1 + tools/testing/selftests/drivers/net/Makefile | 4 +- tools/testing/selftests/drivers/net/config | 2 + .../selftests/drivers/net/netcons_basic.sh | 226 ++++++++++++++++++ 4 files changed, 232 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/drivers/net/netcons_basic.sh diff --git a/MAINTAINERS b/MAINTAINERS index 7b291c3a9aa4..9f0be36939f9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15772,6 +15772,7 @@ M: Breno Leitao <leitao(a)debian.org> S: Maintained F: Documentation/networking/netconsole.rst F: drivers/net/netconsole.c +F: tools/testing/selftests/drivers/net/netcons_basic.sh NETDEVSIM M: Jakub Kicinski <kuba(a)kernel.org> diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index e54f382bcb02..8bee2e94049b 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_INCLUDES := $(wildcard lib/py/*.py) +TEST_INCLUDES := $(wildcard lib/py/*.py) \ + ../../net/lib.sh \ TEST_PROGS := \ + netcons_basic.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index f6a58ce8a230..8f46112263f0 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -1,2 +1,4 @@ CONFIG_IPV6=y CONFIG_NETDEVSIM=m +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh new file mode 100755 index 000000000000..929f27a0fd9c --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -0,0 +1,226 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test creates two netdevsim virtual interfaces, assigns one of them (the +# "destination interface") to a new namespace, and assigns IP addresses to both +# interfaces. +# +# It listens on the destination interface using socat and configures a dynamic +# target on netconsole, pointing to the destination IP address. +# +# Finally, it checks whether the message was received properly on the +# destination interface. Note that this test may pollute the kernel log buffer +# (dmesg) and relies on dynamic configuration and namespaces being configured. +# +# Author: Breno Leitao <leitao(a)debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +# Simple script to test dynamic targets in netconsole +SRCIF="" # to be populated later +SRCIP=192.168.1.1 +DSTIF="" # to be populated later +DSTIP=192.168.1.2 + +PORT="6666" +MSG="netconsole selftest" +TARGET=$(mktemp -u netcons_XXXXX) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# This will have some tmp values appended to it in set_network() +NAMESPACE="netconsns_dst" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) + +# Used to create and delete namespaces +source "${SCRIPTDIR}"/../../net/lib.sh + +# Create netdevsim interfaces +create_ifaces() { + local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" + exec {INITNS_FD}</proc/self/ns/net + + # Bind the dst interface to namespace + ip link set "${DSTIF}" netns "${NAMESPACE}" + + # Linking one device to the other one (on the other namespace} + echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" \ + > $NSIM_DEV_SYS_LINK + if [ $? -ne 0 ]; then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit ${ksft_skip} + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # This is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + return ${ksft_fail} + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + return ${ksft_fail} + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + return ${ksft_pass} +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This script must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi +} + +# ========== # +# Start here # +# ========== # +modprobe netdevsim || true +modprobe netconsole || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & + +# Wait for socat to start and listen to the port. +sleep 1 +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +sleep 1 + +# Make sure the message was received in the dst part +validate_result "${OUTPUT_FILE}" +ret=$? + +exit ${ret} -- 2.43.5

10 months, 2 weeks

3
3
0 0

[PATCH net 00/14] VLAN fixes for Ocelot driver

by Vladimir Oltean

This is a collection of patches I've gathered over the past several months. Patches 1-6/14 are supporting patches for selftests. Patch 9/14 fixes PTP TX from a VLAN upper of a VLAN-aware bridge port when using the "ocelot-8021q" tagging protocol. Patch 7/14 is its supporting selftest. Patch 10/14 fixes the QoS class used by PTP in the same case as above. It is hard to quantify - there is no selftest. Patch 11/14 fixes potential data corruption during PTP TX in the same case as above. Again, there is no selftest. Patch 13/14 fixes RX in the same case as above - 8021q upper of a VLAN-aware bridge port, with the "ocelot-8021q" tagging protocol. Patch 12/14 is a supporting patch for this in the DSA core, and 7/14 is also its selftest. Patch 14/14 ensures that VLAN-aware bridges offloaded to Ocelot only react to the ETH_P_8021Q TPID, and treat absolutely everything else as VLAN-untagged, including ETH_P_8021AD. Patch 8/14 is the supporting selftest. Vladimir Oltean (14): selftests: net: local_termination: refactor macvlan creation/deletion selftests: net: local_termination: parameterize sending interface selftests: net: local_termination: parameterize test name selftests: net: local_termination: add one more test for VLAN-aware bridges selftests: net: local_termination: introduce new tests which capture VLAN behavior selftests: net: local_termination: don't use xfail_on_veth() selftests: net: local_termination: add PTP frames to the mix selftests: net: bridge_vlan_aware: test that other TPIDs are seen as untagged net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and register injection net: mscc: ocelot: fix QoS class for injected packets with "ocelot-8021q" net: mscc: ocelot: serialize access to the injection/extraction groups net: dsa: provide a software untagging function on RX for VLAN-aware bridges net: dsa: felix: fix VLAN tag loss on CPU reception with ocelot-8021q net: mscc: ocelot: treat 802.1ad tagged traffic as 802.1Q-untagged drivers/net/dsa/ocelot/felix.c | 126 ++++- drivers/net/ethernet/mscc/ocelot.c | 279 +++++++++++- drivers/net/ethernet/mscc/ocelot_fdma.c | 3 +- drivers/net/ethernet/mscc/ocelot_vcap.c | 1 + drivers/net/ethernet/mscc/ocelot_vsc7514.c | 4 + include/linux/dsa/ocelot.h | 47 ++ include/net/dsa.h | 16 +- include/soc/mscc/ocelot.h | 12 +- include/soc/mscc/ocelot_vcap.h | 2 + net/dsa/tag.c | 5 +- net/dsa/tag.h | 135 ++++-- net/dsa/tag_ocelot.c | 37 +- .../net/forwarding/bridge_vlan_aware.sh | 54 ++- tools/testing/selftests/net/forwarding/lib.sh | 57 +++ .../net/forwarding/local_termination.sh | 431 +++++++++++++++--- 15 files changed, 1036 insertions(+), 173 deletions(-) -- 2.34.1

10 months, 3 weeks

3
17
0 0

[PATCH] lib/math: Add int_pow test suite

by Luis Felipe Hernandez

Adds test suite for integer based power function. Signed-off-by: Luis Felipe Hernandez <luis.hernandez093(a)gmail.com> --- lib/math/Makefile | 1 + lib/math/test_int_pow.c | 70 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) create mode 100644 lib/math/test_int_pow.c diff --git a/lib/math/Makefile b/lib/math/Makefile index 91fcdb0c9efe..ba564bf4fb00 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -6,4 +6,5 @@ obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o obj-$(CONFIG_TEST_DIV64) += test_div64.o +obj-$(CONFIG_TEST_INT_POW) += test_int_pow.o obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o diff --git a/lib/math/test_int_pow.c b/lib/math/test_int_pow.c new file mode 100644 index 000000000000..ecabe71d01cc --- /dev/null +++ b/lib/math/test_int_pow.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <kunit/test.h> +#include <kunit/static_stub.h> + +#include <linux/math.h> + + +static void test_pow_0(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, 1, int_pow(64, 0)); +} + +static void test_pow_1(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, 64, int_pow(64, 1)); +} + +static void test_base_0(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, 0, int_pow(0, 5)); +} + +static void test_base_1(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, 1, int_pow(1, 100)); + KUNIT_EXPECT_EQ(test, 1, int_pow(1, 0)); +} + +static void test_base_0_pow_0(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, 1, int_pow(0, 0)); +} + +static void test_base_2_pow_2(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, 4, int_pow(2, 2)); +} + +static void test_max_base(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, U64_MAX, int_pow(U64_MAX, 1)); +} + +static void test_large_result(struct kunit *test) +{ + UNIT_EXPECT_EQ(test, 1152921504606846976, int_pow(2, 60)); +} + +static struct kunit_case math_int_pow_test_cases[] = { + KUNIT_CASE(test_pow_0), + KUNIT_CASE(test_pow_1), + KUNIT_CASE(test_base_0), + KUNIT_CASE(test_base_1), + KUNIT_CASE(test_base_0_pow_0), + KUNIT_CASE(test_base_2_pow_2), + KUNIT_CASE(test_max_base), + KUNIT_CASE(test_large_result), + {} +}; + +static struct kunit_suite int_pow_test_suite = { + .name = "lib-math-int_pow", + .test_cases = math_int_pow_test_cases, +}; + +kunit_test_suites(&int_pow_test_suite); + +MODULE_DESCRIPTION("math.int_pow KUnit test suite"); +MODULE_LICENSE("GPL v2"); -- 2.46.0

10 months, 3 weeks

2
1
0 0

[PATCH] selftests/net/pmtu.sh: Fix typo in error message

by Abhash Jha

The word 'expected' was spelled as 'exepcted'. Fixed the typo in this patch. Signed-off-by: Abhash Jha <abhashkumarjha123(a)gmail.com> --- tools/testing/selftests/net/pmtu.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index cfc849580..62eceb385 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -1347,7 +1347,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { size=$(du -sb $tmpoutfile) size=${size%%/tmp/*} - [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + [ $size -ne 1048576 ] && err "File size $size mismatches expected value in locally bridged vxlan test" && return 1 done rm -f "$tmpoutfile" -- 2.43.0

10 months, 3 weeks

6
7
0 0

[PATCH v2 0/3] iommufd: Add selftest coverage for reserved IOVAs

by Nicolin Chen

PATCH-1 is an optional cleanup. PATCH-2 is an essential infrastructure for PATCH-3 to verify the loopback for IOMMU_RESV_SW_MSI. You can find this series applied on the other two earlier patches here: https://github.com/nicolinc/iommufd/commits/iommufd_selftest_sw_msi/ [changelog] v2: * Resent with a proper bug fix. Thanks Nicolin Nicolin Chen (2): iommufd: Reorder include files iommufd/selftest: Add coverage for reserved IOVAs Robin Murphy (1): iommu/dma: Support MSIs through nested domains drivers/iommu/dma-iommu.c | 18 +++- drivers/iommu/iommufd/device.c | 4 +- drivers/iommu/iommufd/fault.c | 4 +- drivers/iommu/iommufd/io_pagetable.c | 8 +- drivers/iommu/iommufd/io_pagetable.h | 2 +- drivers/iommu/iommufd/ioas.c | 2 +- drivers/iommu/iommufd/iommufd_private.h | 9 +- drivers/iommu/iommufd/iommufd_test.h | 6 +- drivers/iommu/iommufd/iova_bitmap.c | 2 +- drivers/iommu/iommufd/main.c | 8 +- drivers/iommu/iommufd/pages.c | 10 +- drivers/iommu/iommufd/selftest.c | 92 ++++++++++++++++++- include/linux/iommu.h | 4 + include/linux/iommufd.h | 4 +- include/uapi/linux/iommufd.h | 2 +- tools/testing/selftests/iommu/iommufd_utils.h | 9 ++ 16 files changed, 150 insertions(+), 34 deletions(-) -- 2.43.0

10 months, 3 weeks

5
19
0 0

[PATCH v7 net-next 0/3] Enhance network interface feature testing

by Abhinav Jain

This small series includes fixes for creation of veth pairs for networkless kernels & adds tests for turning the different network interface features on and off in selftests/net/netdevice.sh script. Changes in v7: Create a third patch in the series to do SKIP -> XFAIL replacement. Add logic to incorporate XFAIL on setting IP address for veth pair. Changes in v6: https://lore.kernel.org/all/20240814191517.50466-1-jain.abhinav177@gmail.com Use XFAIL for ethtool operations that are unsupported instead of SKIP. Changes in v5: https://lore.kernel.org/all/20240808122452.25683-1-jain.abhinav177@gmail.com Rectify the syntax for ip add link. Fix the veth_created condition check. Changes in v4: https://lore.kernel.org/all/20240807175717.7775-1-jain.abhinav177@gmail.com Move veth creation/removal to the main shell script. Tested using vng on a networkless kernel and the script works, sample output below the changes. Changes in v3: https://lore.kernel.org/all/20240614113240.41550-1-jain.abhinav177@gmail.com Add a check for netdev, create veth pair for testing. Restore feature to its initial state. Changes in v2: https://lore.kernel.org/all/20240609132124.51683-1-jain.abhinav177@gmail.com Remove tail usage; use read to parse the features from temp file. v1: https://lore.kernel.org/all/20240606212714.27472-1-jain.abhinav177@gmail.com ``` # selftests: net: netdevice.sh # No valid network device found, creating veth pair # PASS: veth0: set interface up # PASS: veth0: set MAC address # XFAIL: veth0: set IP address # PASS: veth0: ethtool list features # PASS: veth0: Turned off feature: rx-checksumming # PASS: veth0: Turned on feature: rx-checksumming # PASS: veth0: Restore feature rx-checksumming to initial state on # Actual changes: # tx-checksum-ip-generic: off # tx-tcp-segmentation: off [not requested] # PASS: veth0: Turned off feature: rx-udp-gro-forwarding # PASS: veth0: Turned on feature: rx-udp-gro-forwarding # PASS: veth0: Restore feature rx-udp-gro-forwarding to initial state off # Cannot get register dump: Operation not supported # XFAIL: veth0: ethtool dump not supported # PASS: veth0: ethtool stats # PASS: veth0: stop interface ``` Abhinav Jain (3): selftests: net: Create veth pair for testing in networkless kernel selftests: net: Add on/off checks for non-fixed features of interface selftests: net: Use XFAIL for operations not supported by the driver tools/testing/selftests/net/netdevice.sh | 61 ++++++++++++++++++++++-- 1 file changed, 58 insertions(+), 3 deletions(-) -- 2.34.1

10 months, 3 weeks

2
5
0 0

Re: [syzbot] [mm?] WARNING in hpage_collapse_scan_pmd (2)

by syzbot

syzbot suspects this issue was fixed by commit: commit c88033efe9a391e72ba6b5df4b01d6e628f4e734 Author: Peter Xu <peterx(a)redhat.com> Date: Mon Apr 22 13:33:11 2024 +0000 mm/userfaultfd: reset ptes when close() for wr-protected ones bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=12f2396b980000 start commit: e67572cd2204 Linux 6.9-rc6 git tree: upstream kernel config: https://syzkaller.appspot.com/x/.config?x=3310e643b6ef5d69 dashboard link: https://syzkaller.appspot.com/bug?extid=5ea2845f44caa77f5543 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=10874a40980000 If the result looks correct, please mark the issue as fixed by replying with: #syz fix: mm/userfaultfd: reset ptes when close() for wr-protected ones For information about bisection process see: https://goo.gl/tpsmEJ#bisection

10 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror