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

[PATCH net-next v3 7/7] selftests: net: extend SCM_PIDFD test to cover stale pidfds

by Alexander Mikhalitsyn

Extend SCM_PIDFD test scenarios to also cover dead task's pidfd retrieval and reading its exit info. Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: Shuah Khan <shuah(a)kernel.org> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Simon Horman <horms(a)kernel.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)google.com> Cc: Lennart Poettering <mzxreary(a)0pointer.de> Cc: Luca Boccassi <bluca(a)debian.org> Cc: David Rheinsberg <david(a)readahead.eu> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> Reviewed-by: Christian Brauner <brauner(a)kernel.org> --- .../testing/selftests/net/af_unix/scm_pidfd.c | 217 ++++++++++++++---- 1 file changed, 173 insertions(+), 44 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..37e034874034 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include <sys/wait.h> +#include "../../pidfd/pidfd.h" #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -26,6 +27,8 @@ #define SCM_PIDFD 0x04 #endif +#define CHILD_EXIT_CODE_OK 123 + static void child_die() { exit(1); @@ -126,16 +129,65 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } +struct cmsg_data { + struct ucred *ucred; + int *pidfd; +}; + +static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res) +{ + struct cmsghdr *cmsg; + int data = 0; + + if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*res->pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + res->pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*res->ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + res->ucred = (void *)CMSG_DATA(cmsg); + } + } + + if (!res->pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!res->ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + return 0; +} + static int cmsg_check(int fd) { struct msghdr msg = { 0 }; - struct cmsghdr *cmsg; + struct cmsg_data res; struct iovec iov; - struct ucred *ucred = NULL; int data = 0; char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; - int *pidfd = NULL; pid_t parent_pid; int err; @@ -158,53 +210,99 @@ static int cmsg_check(int fd) return 1; } - for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; - cmsg = CMSG_NXTHDR(&msg, cmsg)) { - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_PIDFD) { - if (cmsg->cmsg_len < sizeof(*pidfd)) { - log_err("CMSG parse: SCM_PIDFD wrong len"); - return 1; - } + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } - pidfd = (void *)CMSG_DATA(cmsg); - } + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); + return 1; + } - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_CREDENTIALS) { - if (cmsg->cmsg_len < sizeof(*ucred)) { - log_err("CMSG parse: SCM_CREDENTIALS wrong len"); - return 1; - } + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + close(*res.pidfd); + return 1; + } - ucred = (void *)CMSG_DATA(cmsg); - } + close(*res.pidfd); + return 0; +} + +static int cmsg_check_dead(int fd, int expected_pid) +{ + int err; + struct msghdr msg = { 0 }; + struct cmsg_data res; + struct iovec iov; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + pid_t client_pid; + struct pidfd_info info = { + .mask = PIDFD_INFO_EXIT, + }; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; } - /* send(pfd, "x", sizeof(char), 0) */ - if (data != 'x') { + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + /* send(cfd, "y", sizeof(char), 0) */ + if (data != 'y') { log_err("recvmsg: data corruption"); return 1; } - if (!pidfd) { - log_err("CMSG parse: SCM_PIDFD not found"); + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); return 1; } - if (!ucred) { - log_err("CMSG parse: SCM_CREDENTIALS not found"); + /* + * pidfd from SCM_PIDFD should point to the client_pid. + * Let's read exit information and check if it's what + * we expect to see. + */ + if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) { + log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__); + close(*res.pidfd); return 1; } - /* pidfd from SCM_PIDFD should point to the parent process PID */ - parent_pid = - get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); - if (parent_pid != getppid()) { - log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + if (!(info.mask & PIDFD_INFO_EXIT)) { + log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__); + close(*res.pidfd); return 1; } + err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1; + if (err != CHILD_EXIT_CODE_OK) { + log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK); + close(*res.pidfd); + return 1; + } + + close(*res.pidfd); return 0; } @@ -291,6 +389,24 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract) memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); } +static int sk_enable_cred_pass(int sk) +{ + int on = 0; + + on = 1; + if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + return 1; + } + + if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + return 1; + } + + return 0; +} + static void client(FIXTURE_DATA(scm_pidfd) *self, const FIXTURE_VARIANT(scm_pidfd) *variant) { @@ -299,7 +415,6 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, struct ucred peer_cred; int peer_pidfd; pid_t peer_pid; - int on = 0; cfd = socket(AF_UNIX, variant->type, 0); if (cfd < 0) { @@ -322,14 +437,8 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } - on = 1; - if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { - log_err("Failed to set SO_PASSCRED"); - child_die(); - } - - if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { - log_err("Failed to set SO_PASSPIDFD"); + if (sk_enable_cred_pass(cfd)) { + log_err("sk_enable_cred_pass() failed"); child_die(); } @@ -340,6 +449,12 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } + /* send something to the parent so it can receive SCM_PIDFD too and validate it */ + if (send(cfd, "y", sizeof(char), 0) == -1) { + log_err("Failed to send(cfd, \"y\", sizeof(char), 0)"); + child_die(); + } + /* skip further for SOCK_DGRAM as it's not applicable */ if (variant->type == SOCK_DGRAM) return; @@ -398,7 +513,13 @@ TEST_F(scm_pidfd, test) close(self->server); close(self->startup_pipe[0]); client(self, variant); - exit(0); + + /* + * It's a bit unusual, but in case of success we return non-zero + * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it + * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead(). + */ + exit(CHILD_EXIT_CODE_OK); } close(self->startup_pipe[1]); @@ -421,9 +542,17 @@ TEST_F(scm_pidfd, test) ASSERT_NE(-1, err); } - close(pfd); waitpid(self->client_pid, &child_status, 0); - ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + /* see comment before exit(CHILD_EXIT_CODE_OK) */ + ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + + err = sk_enable_cred_pass(pfd); + ASSERT_EQ(0, err); + + err = cmsg_check_dead(pfd, self->client_pid); + ASSERT_EQ(0, err); + + close(pfd); } TEST_HARNESS_MAIN -- 2.43.0

2 months, 2 weeks

1
0
0 0

[PATCH v2] selftests/powerpc: fix "for a while" typo

by Ahelenia Ziemiańska

Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli(a)nabijaczleweli.xyz> --- v1: https://lore.kernel.org/lkml/h2ieddqja5jfrnuh3mvlxt6njrvp352t5rfzp2cvnrufop… tools/testing/selftests/powerpc/tm/tm-tmspr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index dd5ddffa28b7..0d64988ffb40 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -14,7 +14,7 @@ * (1) create more threads than cpus * (2) in each thread: * (a) set TFIAR and TFHAR a unique value - * (b) loop for awhile, continually checking to see if + * (b) loop for a while, continually checking to see if * either register has been corrupted. * * (3) Loop: -- 2.39.5

2 months, 2 weeks

1
0
0 0

[PATCH v6 00/28] KVM: arm64: Implement support for SME

by Mark Brown

I've removed the RFC tag from this version of the series, but the items that I'm looking for feedback on remains the same: - The userspace ABI, in particular: - The vector length used for the SVE registers, access to the SVE registers and access to ZA and (if available) ZT0 depending on the current state of PSTATE.{SM,ZA}. - The use of a single finalisation for both SVE and SME. - The addition of control for enabling fine grained traps in a similar manner to FGU but without the UNDEF, I'm not clear if this is desired at all and at present this requires symmetric read and write traps like FGU. That seemed like it might be desired from an implementation point of view but we already have one case where we enable an asymmetric trap (for ARM64_WORKAROUND_AMPERE_AC03_CPU_38) and it seems generally useful to enable asymmetrically. This series implements support for SME use in non-protected KVM guests. Much of this is very similar to SVE, the main additional challenge that SME presents is that it introduces a new vector length similar to the SVE vector length and two new controls which change the registers seen by guests: - PSTATE.ZA enables the ZA matrix register and, if SME2 is supported, the ZT0 LUT register. - PSTATE.SM enables streaming mode, a new floating point mode which uses the SVE register set with the separately configured SME vector length. In streaming mode implementation of the FFR register is optional. It is also permitted to build systems which support SME without SVE, in this case when not in streaming mode no SVE registers or instructions are available. Further, there is no requirement that there be any overlap in the set of vector lengths supported by SVE and SME in a system, this is expected to be a common situation in practical systems. Since there is a new vector length to configure we introduce a new feature parallel to the existing SVE one with a new pseudo register for the streaming mode vector length. Due to the overlap with SVE caused by streaming mode rather than finalising SME as a separate feature we use the existing SVE finalisation to also finalise SME, a new define KVM_ARM_VCPU_VEC is provided to help make user code clearer. Finalising SVE and SME separately would introduce complication with register access since finalising SVE makes the SVE registers writeable by userspace and doing multiple finalisations results in an error being reported. Dealing with a state where the SVE registers are writeable due to one of SVE or SME being finalised but may have their VL changed by the other being finalised seems like needless complexity with minimal practical utility, it seems clearer to just express directly that only one finalisation can be done in the ABI. Access to the floating point registers follows the architecture: - When both SVE and SME are present: - If PSTATE.SM == 0 the vector length used for the Z and P registers is the SVE vector length. - If PSTATE.SM == 1 the vector length used for the Z and P registers is the SME vector length. - If only SME is present: - If PSTATE.SM == 0 the Z and P registers are inaccessible and the floating point state accessed via the encodings for the V registers. - If PSTATE.SM == 1 the vector length used for the Z and P registers - The SME specific ZA and ZT0 registers are only accessible if SVCR.ZA is 1. The VMM must understand this, in particular when loading state SVCR should be configured before other state. It should be noted that while the architecture refers to PSTATE.SM and PSTATE.ZA these PSTATE bits are not preserved in SPSR_ELx, they are only accessible via SVCR. There are a large number of subfeatures for SME, most of which only offer additional instructions but some of which (SME2 and FA64) add architectural state. These are configured via the ID registers as per usual. Protected KVM supported, with the implementation maintaining the existing restriction that the hypervisor will refuse to run if streaming mode or ZA is enabled. This both simplfies the code and avoids the need to allocate storage for host ZA and ZT0 state, there seems to be little practical use case for supporting this and the memory usage would be non-trivial. The new KVM_ARM_VCPU_VEC feature and ZA and ZT0 registers have not been added to the get-reg-list selftest, the idea of supporting additional features there without restructuring the program to generate all possible feature combinations has been rejected. I will post a separate series which does that restructuring. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v6: - Rebase onto v6.16-rc3. - Link to v5: https://lore.kernel.org/r/20250417-kvm-arm64-sme-v5-0-f469a2d5f574@kernel.o… Changes in v5: - Rebase onto v6.15-rc2. - Add pKVM guest support. - Always restore SVCR. - Link to v4: https://lore.kernel.org/r/20250214-kvm-arm64-sme-v4-0-d64a681adcc2@kernel.o… Changes in v4: - Rebase onto v6.14-rc2 and Mark Rutland's fixes. - Expose SME to nested guests. - Additional cleanups and test fixes following on from the rebase. - Flush register state on VMM PSTATE.{SM,ZA}. - Link to v3: https://lore.kernel.org/r/20241220-kvm-arm64-sme-v3-0-05b018c1ffeb@kernel.o… Changes in v3: - Rebase onto v6.12-rc2. - Link to v2: https://lore.kernel.org/r/20231222-kvm-arm64-sme-v2-0-da226cb180bb@kernel.o… Changes in v2: - Rebase onto v6.7-rc3. - Configure subfeatures based on host system only. - Complete nVHE support. - There was some snafu with sending v1 out, it didn't make it to the lists but in case it hit people's inboxes I'm sending as v2. --- Mark Brown (28): arm64/fpsimd: Update FA64 and ZT0 enables when loading SME state arm64/fpsimd: Decide to save ZT0 and streaming mode FFR at bind time arm64/fpsimd: Check enable bit for FA64 when saving EFI state arm64/fpsimd: Determine maximum virtualisable SME vector length KVM: arm64: Introduce non-UNDEF FGT control KVM: arm64: Pay attention to FFR parameter in SVE save and load KVM: arm64: Pull ctxt_has_ helpers to start of sysreg-sr.h KVM: arm64: Move SVE state access macros after feature test macros KVM: arm64: Rename SVE finalization constants to be more general KVM: arm64: Document the KVM ABI for SME KVM: arm64: Define internal features for SME KVM: arm64: Rename sve_state_reg_region KVM: arm64: Store vector lengths in an array KVM: arm64: Implement SME vector length configuration KVM: arm64: Support SME control registers KVM: arm64: Support TPIDR2_EL0 KVM: arm64: Support SME identification registers for guests KVM: arm64: Support SME priority registers KVM: arm64: Provide assembly for SME register access KVM: arm64: Support userspace access to streaming mode Z and P registers KVM: arm64: Flush register state on writes to SVCR.SM and SVCR.ZA KVM: arm64: Expose SME specific state to userspace KVM: arm64: Context switch SME state for guests KVM: arm64: Handle SME exceptions KVM: arm64: Expose SME to nested guests KVM: arm64: Provide interface for configuring and enabling SME for guests KVM: arm64: selftests: Add SME system registers to get-reg-list KVM: arm64: selftests: Add SME to set_id_regs test Documentation/virt/kvm/api.rst | 117 +++++++---- arch/arm64/include/asm/fpsimd.h | 26 +++ arch/arm64/include/asm/kvm_emulate.h | 6 + arch/arm64/include/asm/kvm_host.h | 168 ++++++++++++--- arch/arm64/include/asm/kvm_hyp.h | 5 +- arch/arm64/include/asm/kvm_pkvm.h | 2 +- arch/arm64/include/asm/vncr_mapping.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 33 +++ arch/arm64/kernel/cpufeature.c | 2 - arch/arm64/kernel/fpsimd.c | 89 ++++---- arch/arm64/kvm/arm.c | 10 + arch/arm64/kvm/fpsimd.c | 28 ++- arch/arm64/kvm/guest.c | 252 ++++++++++++++++++++--- arch/arm64/kvm/handle_exit.c | 14 ++ arch/arm64/kvm/hyp/fpsimd.S | 28 ++- arch/arm64/kvm/hyp/include/hyp/switch.h | 175 ++++++++++++++-- arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 97 +++++---- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 86 ++++++-- arch/arm64/kvm/hyp/nvhe/pkvm.c | 81 ++++++-- arch/arm64/kvm/hyp/nvhe/switch.c | 4 +- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 6 + arch/arm64/kvm/hyp/vhe/switch.c | 17 +- arch/arm64/kvm/nested.c | 3 +- arch/arm64/kvm/reset.c | 156 ++++++++++---- arch/arm64/kvm/sys_regs.c | 140 ++++++++++++- include/uapi/linux/kvm.h | 1 + tools/testing/selftests/kvm/arm64/get-reg-list.c | 32 ++- tools/testing/selftests/kvm/arm64/set_id_regs.c | 29 ++- 28 files changed, 1315 insertions(+), 294 deletions(-) --- base-commit: 7204503c922cfdb4fcfce4a4ab61f4558a01a73b change-id: 20230301-kvm-arm64-sme-06a1246d3636 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 months, 2 weeks

2
31
0 0

[PATCH v2 0/3] kselftest/arm64: Update sve-ptrace for ABI changes

by Mark Brown

Mark Rutland's recent SME fixes updated the SME ABI to reject any attempt to write FPSIMD register data via the streaming mode SVE register set but did not update the sve-ptrace test to take account of this, resulting in spurious failures. Update the test for this, and also fix another preexisting issue I noticed while looking at this. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Rebase onto v6.16-rc1. - Update fixes tag for patch 1. - Link to v1: https://lore.kernel.org/r/20250523-kselftest-arm64-ssve-fixups-v1-0-65069a2… --- Mark Brown (3): kselftest/arm64: Fix check for setting new VLs in sve-ptrace kselftest/arm64: Fix test for streaming FPSIMD write in sve-ptrace kselftest/arm64: Specify SVE data when testing VL set in sve-ptrace tools/testing/selftests/arm64/fp/sve-ptrace.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250523-kselftest-arm64-ssve-fixups-b68ae61c1ebf Best regards, -- Mark Brown <broonie(a)kernel.org>

2 months, 2 weeks

2
4
0 0

[PATCH] kselftest/arm64: Convert tpidr2 test to use kselftest.h

by Mark Brown

Recent work by Thomas Weißschuh means that it is now possible to use kselftest.h with nolibc. Convert the tpidr2 test which is nolibc specific to use kselftest.h, making it look more standard and ensuring it gets the benefit of any work done on kselftest.h. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/abi/Makefile | 2 +- tools/testing/selftests/arm64/abi/tpidr2.c | 140 ++++++++--------------------- 2 files changed, 38 insertions(+), 104 deletions(-) diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile index a6d30c620908..483488f8c2ad 100644 --- a/tools/testing/selftests/arm64/abi/Makefile +++ b/tools/testing/selftests/arm64/abi/Makefile @@ -12,4 +12,4 @@ $(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S $(OUTPUT)/tpidr2: tpidr2.c $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \ -static -include ../../../../include/nolibc/nolibc.h \ - -ffreestanding -Wall $^ -o $@ -lgcc + -I../.. -ffreestanding -Wall $^ -o $@ -lgcc diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c index eb19dcc37a75..f58a9f89b952 100644 --- a/tools/testing/selftests/arm64/abi/tpidr2.c +++ b/tools/testing/selftests/arm64/abi/tpidr2.c @@ -3,31 +3,12 @@ #include <linux/sched.h> #include <linux/wait.h> +#include "kselftest.h" + #define SYS_TPIDR2 "S3_3_C13_C0_5" #define EXPECTED_TESTS 5 -static void putstr(const char *str) -{ - write(1, str, strlen(str)); -} - -static void putnum(unsigned int num) -{ - char c; - - if (num / 10) - putnum(num / 10); - - c = '0' + (num % 10); - write(1, &c, 1); -} - -static int tests_run; -static int tests_passed; -static int tests_failed; -static int tests_skipped; - static void set_tpidr2(uint64_t val) { asm volatile ( @@ -50,20 +31,6 @@ static uint64_t get_tpidr2(void) return val; } -static void print_summary(void) -{ - if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS) - putstr("# UNEXPECTED TEST COUNT: "); - - putstr("# Totals: pass:"); - putnum(tests_passed); - putstr(" fail:"); - putnum(tests_failed); - putstr(" xfail:0 xpass:0 skip:"); - putnum(tests_skipped); - putstr(" error:0\n"); -} - /* Processes should start with TPIDR2 == 0 */ static int default_value(void) { @@ -105,9 +72,8 @@ static int write_fork_read(void) if (newpid == 0) { /* In child */ if (get_tpidr2() != oldpid) { - putstr("# TPIDR2 changed in child: "); - putnum(get_tpidr2()); - putstr("\n"); + ksft_print_msg("TPIDR2 changed in child: %llx\n", + get_tpidr2()); exit(0); } @@ -115,14 +81,12 @@ static int write_fork_read(void) if (get_tpidr2() == getpid()) { exit(1); } else { - putstr("# Failed to set TPIDR2 in child\n"); + ksft_print_msg("Failed to set TPIDR2 in child\n"); exit(0); } } if (newpid < 0) { - putstr("# fork() failed: -"); - putnum(-newpid); - putstr("\n"); + ksft_print_msg("fork() failed: %d\n", newpid); return 0; } @@ -132,23 +96,22 @@ static int write_fork_read(void) if (waiting < 0) { if (errno == EINTR) continue; - putstr("# waitpid() failed: "); - putnum(errno); - putstr("\n"); + ksft_print_msg("waitpid() failed: %d\n", errno); return 0; } if (waiting != newpid) { - putstr("# waitpid() returned wrong PID\n"); + ksft_print_msg("waitpid() returned wrong PID: %d != %d\n", + waiting, newpid); return 0; } if (!WIFEXITED(status)) { - putstr("# child did not exit\n"); + ksft_print_msg("child did not exit\n"); return 0; } if (getpid() != get_tpidr2()) { - putstr("# TPIDR2 corrupted in parent\n"); + ksft_print_msg("TPIDR2 corrupted in parent\n"); return 0; } @@ -188,35 +151,32 @@ static int write_clone_read(void) stack = malloc(__STACK_SIZE); if (!stack) { - putstr("# malloc() failed\n"); + ksft_print_msg("malloc() failed\n"); return 0; } ret = sys_clone(CLONE_VM, (unsigned long)stack + __STACK_SIZE, &parent_tid, 0, &child_tid); if (ret == -1) { - putstr("# clone() failed\n"); - putnum(errno); - putstr("\n"); + ksft_print_msg("clone() failed: %d\n", errno); return 0; } if (ret == 0) { /* In child */ if (get_tpidr2() != 0) { - putstr("# TPIDR2 non-zero in child: "); - putnum(get_tpidr2()); - putstr("\n"); + ksft_print_msg("TPIDR2 non-zero in child: %llx\n", + get_tpidr2()); exit(0); } if (gettid() == 0) - putstr("# Child TID==0\n"); + ksft_print_msg("Child TID==0\n"); set_tpidr2(gettid()); if (get_tpidr2() == gettid()) { exit(1); } else { - putstr("# Failed to set TPIDR2 in child\n"); + ksft_print_msg("Failed to set TPIDR2 in child\n"); exit(0); } } @@ -227,25 +187,22 @@ static int write_clone_read(void) if (waiting < 0) { if (errno == EINTR) continue; - putstr("# wait4() failed: "); - putnum(errno); - putstr("\n"); + ksft_print_msg("wait4() failed: %d\n", errno); return 0; } if (waiting != ret) { - putstr("# wait4() returned wrong PID "); - putnum(waiting); - putstr("\n"); + ksft_print_msg("wait4() returned wrong PID %d\n", + waiting); return 0; } if (!WIFEXITED(status)) { - putstr("# child did not exit\n"); + ksft_print_msg("child did not exit\n"); return 0; } if (parent != get_tpidr2()) { - putstr("# TPIDR2 corrupted in parent\n"); + ksft_print_msg("TPIDR2 corrupted in parent\n"); return 0; } @@ -253,35 +210,14 @@ static int write_clone_read(void) } } -#define run_test(name) \ - if (name()) { \ - tests_passed++; \ - } else { \ - tests_failed++; \ - putstr("not "); \ - } \ - putstr("ok "); \ - putnum(++tests_run); \ - putstr(" " #name "\n"); - -#define skip_test(name) \ - tests_skipped++; \ - putstr("ok "); \ - putnum(++tests_run); \ - putstr(" # SKIP " #name "\n"); - int main(int argc, char **argv) { int ret; - putstr("TAP version 13\n"); - putstr("1.."); - putnum(EXPECTED_TESTS); - putstr("\n"); + ksft_print_header(); + ksft_set_plan(5); - putstr("# PID: "); - putnum(getpid()); - putstr("\n"); + ksft_print_msg("PID: %d\n", getpid()); /* * This test is run with nolibc which doesn't support hwcap and @@ -290,23 +226,21 @@ int main(int argc, char **argv) */ ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); if (ret >= 0) { - run_test(default_value); - run_test(write_read); - run_test(write_sleep_read); - run_test(write_fork_read); - run_test(write_clone_read); + ksft_test_result(default_value(), "default_value\n"); + ksft_test_result(write_read, "write_read\n"); + ksft_test_result(write_sleep_read, "write_sleep_read\n"); + ksft_test_result(write_fork_read, "write_fork_read\n"); + ksft_test_result(write_clone_read, "write_clone_read\n"); } else { - putstr("# SME support not present\n"); + ksft_print_msg("SME support not present\n"); - skip_test(default_value); - skip_test(write_read); - skip_test(write_sleep_read); - skip_test(write_fork_read); - skip_test(write_clone_read); + ksft_test_result_skip("default_value\n"); + ksft_test_result_skip("write_read\n"); + ksft_test_result_skip("write_sleep_read\n"); + ksft_test_result_skip("write_fork_read\n"); + ksft_test_result_skip("write_clone_read\n"); } - print_summary(); - - return 0; + ksft_finished(); } --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250527-kselftest-arm64-nolibc-header-b650a457f7f4 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 months, 2 weeks

2
1
0 0

[PATCH v2 0/3] arm64: Support FEAT_LSFE (Large System Float Extension)

by Mark Brown

FEAT_LSFE is optional from v9.5, it adds new instructions for atomic memory operations with floating point values. We have no immediate use for it in kernel, provide a hwcap so userspace can discover it and allow the ID register field to be exposed to KVM guests. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Fix result of vi dropping in hwcap test. - Link to v1: https://lore.kernel.org/r/20250627-arm64-lsfe-v1-0-68351c4bf741@kernel.org --- Mark Brown (3): arm64/hwcap: Add hwcap for FEAT_LSFE KVM: arm64: Expose FEAT_LSFE to guests kselftest/arm64: Add lsfe to the hwcaps test Documentation/arch/arm64/elf_hwcaps.rst | 4 ++++ arch/arm64/include/asm/hwcap.h | 1 + arch/arm64/include/uapi/asm/hwcap.h | 1 + arch/arm64/kernel/cpufeature.c | 2 ++ arch/arm64/kernel/cpuinfo.c | 1 + arch/arm64/kvm/sys_regs.c | 4 +++- tools/testing/selftests/arm64/abi/hwcap.c | 21 +++++++++++++++++++++ 7 files changed, 33 insertions(+), 1 deletion(-) --- base-commit: 86731a2a651e58953fc949573895f2fa6d456841 change-id: 20250625-arm64-lsfe-0810cf98adc2 Best regards, -- Mark Brown <broonie(a)kernel.org>

2 months, 2 weeks

1
3
0 0

[RFC PATCH v1 0/2] kselftest/resctrl: CAT functional tests

by Ilpo Järvinen

Hi all, In the last Fall Reinette mentioned functional tests of resctrl would be preferred over selftests that are based on performance measurement. This series tries to address that shortcoming by adding some functional tests for resctrl FS interface and another that checks MSRs match to what is written through resctrl FS. The MSR test is only available for Intel CPUs at the moment. Why RFC? The new functional selftest itself works, AFAIK. However, calling ksft_test_result_skip() in cat.c if MSR reading is found to be unavailable is problematic because of how kselftest harness is architected. The kselftest.h header itself defines some variables, so including it into different .c files results in duplicating the test framework related variables (duplication of ksft_count matters in this case). The duplication problem could be worked around by creating a resctrl selftest specific wrapper for ksft_test_result_skip() into resctrl_tests.c so the accounting would occur in the "correct" .c file, but perhaps that is considered hacky and the selftest framework/build systems should be reworked to avoid duplicating variables? Ilpo Järvinen (2): kselftest/resctrl: CAT L3 resctrl FS function tests kselftest/resctrl: Add CAT L3 CBM functional test for Intel RDT tools/testing/selftests/resctrl/cat_test.c | 210 ++++++++++++++++++ tools/testing/selftests/resctrl/msr.c | 55 +++++ tools/testing/selftests/resctrl/resctrl.h | 6 + .../testing/selftests/resctrl/resctrl_tests.c | 2 + tools/testing/selftests/resctrl/resctrlfs.c | 48 ++++ 5 files changed, 321 insertions(+) create mode 100644 tools/testing/selftests/resctrl/msr.c base-commit: c1d7e19c70cbb8a19f63c190cf53e71b5f970514 -- 2.39.5

2 months, 2 weeks

2
5
0 0

[PATCH v2 0/7] selftests/mm: Fix false positives and skip unsupported tests

by Aboorva Devarajan

Hi all, This patch series addresses false positives in the generic mm selftests and skips tests that cannot run correctly due to missing features or system limitations. --- v1: https://lore.kernel.org/all/20250616160632.35250-1-aboorvad@linux.ibm.com/ Changes in v2: - Rebased onto the mm-new branch, top commit of the base is 3b4a8ad89f7e ("mm: add zblock allocator"). - Split some patches for clarity. - Updated virtual_address_range test to support testing 4PB VA on PPC64. - Added proper Fixes: tags. - Included a patch to skip a failing userfaultfd test when unsupported, instead of reporting a failure. --- Please let us know if you have any further comments. Thanks, Aboorva Aboorva Devarajan (3): selftests/mm: Fix child process exit codes in ksm_functional_tests selftests/mm: Skip thuge-gen if shmmax is too small or no 1G huge pages selftests/mm: Skip hugepage-mremap test if userfaultfd unavailable Donet Tom (4): mm/selftests: Fix incorrect pointer being passed to mark_range() selftests/mm: Add support to test 4PB VA on PPC64 selftest/mm: Fix ksm_funtional_test failures mm/selftests: Fix split_huge_page_test failure on systems with 64KB page size tools/testing/selftests/mm/hugepage-mremap.c | 16 ++++++++++--- .../selftests/mm/ksm_functional_tests.c | 24 +++++++++++++------ .../selftests/mm/split_huge_page_test.c | 23 +++++++++++++----- tools/testing/selftests/mm/thuge-gen.c | 11 +++++---- .../selftests/mm/virtual_address_range.c | 8 ++++++- 5 files changed, 61 insertions(+), 21 deletions(-) -- 2.43.5

2 months, 2 weeks

5
33
0 0

[PATCH net-next v2 0/2] Add IPIP flowtable SW acceleratio

by Lorenzo Bianconi

Introduce SW acceleration for IPIP tunnels in the netfilter flowtable infrastructure. --- Changes in v2: - Introduce IPIP flowtable selftest - Link to v1: https://lore.kernel.org/r/20250623-nf-flowtable-ipip-v1-1-2853596e3941@kern… --- Lorenzo Bianconi (2): net: netfilter: Add IPIP flowtable SW acceleration selftests: netfilter: nft_flowtable.sh: Add IPIP flowtable selftest net/ipv4/ipip.c | 21 ++++++++++++ net/netfilter/nf_flow_table_ip.c | 28 +++++++++++++-- .../selftests/net/netfilter/nft_flowtable.sh | 40 ++++++++++++++++++++++ 3 files changed, 87 insertions(+), 2 deletions(-) --- base-commit: 8efa26fcbf8a7f783fd1ce7dd2a409e9b7758df0 change-id: 20250623-nf-flowtable-ipip-1b3d7b08d067 Best regards, -- Lorenzo Bianconi <lorenzo(a)kernel.org>

2 months, 2 weeks

4
6
0 0

[PATCH bpf-next v2 18/18] selftests/bpf: add bench tests for tracing_multi

by Menglong Dong

Add bench testcase for fentry_multi, fexit_multi and fmodret_multi in bench_trigger.c. Signed-off-by: Menglong Dong <dongml2(a)chinatelecom.cn> --- v2: - use the existing bpf bench framework instead of introducing new one --- tools/testing/selftests/bpf/bench.c | 8 +++ .../selftests/bpf/benchs/bench_trigger.c | 72 +++++++++++++++++++ .../selftests/bpf/benchs/run_bench_trigger.sh | 1 + .../selftests/bpf/progs/trigger_bench.c | 22 ++++++ 4 files changed, 103 insertions(+) diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index ddd73d06a1eb..32f1e2e936c0 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -510,8 +510,12 @@ extern const struct bench bench_trig_kretprobe; extern const struct bench bench_trig_kprobe_multi; extern const struct bench bench_trig_kretprobe_multi; extern const struct bench bench_trig_fentry; +extern const struct bench bench_trig_fentry_multi; +extern const struct bench bench_trig_fentry_multi_all; extern const struct bench bench_trig_fexit; +extern const struct bench bench_trig_fexit_multi; extern const struct bench bench_trig_fmodret; +extern const struct bench bench_trig_fmodret_multi; extern const struct bench bench_trig_tp; extern const struct bench bench_trig_rawtp; @@ -578,8 +582,12 @@ static const struct bench *benchs[] = { &bench_trig_kprobe_multi, &bench_trig_kretprobe_multi, &bench_trig_fentry, + &bench_trig_fentry_multi, + &bench_trig_fentry_multi_all, &bench_trig_fexit, + &bench_trig_fexit_multi, &bench_trig_fmodret, + &bench_trig_fmodret_multi, &bench_trig_tp, &bench_trig_rawtp, /* uprobes */ diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 82327657846e..a1844ee358f1 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -226,6 +226,54 @@ static void trigger_fentry_setup(void) attach_bpf(ctx.skel->progs.bench_trigger_fentry); } +static void trigger_fentry_multi_setup(void) +{ + setup_ctx(); + bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fentry_multi, true); + load_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_fentry_multi); +} + +static void trigger_fentry_multi_all_setup(void) +{ + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + struct bpf_program *prog; + struct bpf_link *link; + char **syms = NULL; + size_t cnt = 0; + int i; + + setup_ctx(); + prog = ctx.skel->progs.bench_trigger_fentry_multi; + bpf_program__set_autoload(prog, true); + load_ctx(); + + if (bpf_get_ksyms(&syms, &cnt, true)) { + printf("failed to get ksyms\n"); + exit(1); + } + + for (i = 0; i < cnt; i++) { + if (strcmp(syms[i], "bpf_get_numa_node_id") == 0) + break; + } + if (i == cnt) { + printf("bpf_get_numa_node_id not found in ksyms\n"); + exit(1); + } + + printf("found %zu ksyms\n", cnt); + opts.syms = (const char **) syms; + opts.cnt = cnt; + opts.skip_invalid = true; + link = bpf_program__attach_trace_multi_opts(prog, &opts); + if (!link) { + printf("failed to attach bench_trigger_fentry_multi to all\n"); + exit(1); + } + ctx.skel->links.bench_trigger_fentry_multi = link; +} + static void trigger_fexit_setup(void) { setup_ctx(); @@ -234,6 +282,14 @@ static void trigger_fexit_setup(void) attach_bpf(ctx.skel->progs.bench_trigger_fexit); } +static void trigger_fexit_multi_setup(void) +{ + setup_ctx(); + bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fexit_multi, true); + load_ctx(); + attach_bpf(ctx.skel->progs.bench_trigger_fexit_multi); +} + static void trigger_fmodret_setup(void) { setup_ctx(); @@ -246,6 +302,18 @@ static void trigger_fmodret_setup(void) attach_bpf(ctx.skel->progs.bench_trigger_fmodret); } +static void trigger_fmodret_multi_setup(void) +{ + setup_ctx(); + bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false); + bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true); + bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fmodret_multi, true); + load_ctx(); + /* override driver program */ + ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc); + attach_bpf(ctx.skel->progs.bench_trigger_fmodret_multi); +} + static void trigger_tp_setup(void) { setup_ctx(); @@ -512,8 +580,12 @@ BENCH_TRIG_KERNEL(kretprobe, "kretprobe"); BENCH_TRIG_KERNEL(kprobe_multi, "kprobe-multi"); BENCH_TRIG_KERNEL(kretprobe_multi, "kretprobe-multi"); BENCH_TRIG_KERNEL(fentry, "fentry"); +BENCH_TRIG_KERNEL(fentry_multi, "fentry-multi"); +BENCH_TRIG_KERNEL(fentry_multi_all, "fentry-multi-all"); BENCH_TRIG_KERNEL(fexit, "fexit"); +BENCH_TRIG_KERNEL(fexit_multi, "fexit-multi"); BENCH_TRIG_KERNEL(fmodret, "fmodret"); +BENCH_TRIG_KERNEL(fmodret_multi, "fmodret-multi"); BENCH_TRIG_KERNEL(tp, "tp"); BENCH_TRIG_KERNEL(rawtp, "rawtp"); diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh index a690f5a68b6b..48a7f809d053 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh @@ -5,6 +5,7 @@ set -eufo pipefail def_tests=( \ usermode-count kernel-count syscall-count \ fentry fexit fmodret \ + fentry-multi fentry-multi-all fexit-multi fmodret-multi \ rawtp tp \ kprobe kprobe-multi \ kretprobe kretprobe-multi \ diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 044a6d78923e..2ff1a7568080 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -111,6 +111,13 @@ int bench_trigger_fentry(void *ctx) return 0; } +SEC("?fentry.multi/bpf_get_numa_node_id") +int bench_trigger_fentry_multi(void *ctx) +{ + inc_counter(); + return 0; +} + SEC("?fexit/bpf_get_numa_node_id") int bench_trigger_fexit(void *ctx) { @@ -118,6 +125,14 @@ int bench_trigger_fexit(void *ctx) return 0; } +SEC("?fexit.multi/bpf_get_numa_node_id") +int bench_trigger_fexit_multi(void *ctx) +{ + inc_counter(); + + return 0; +} + SEC("?fmod_ret/bpf_modify_return_test_tp") int bench_trigger_fmodret(void *ctx) { @@ -125,6 +140,13 @@ int bench_trigger_fmodret(void *ctx) return -22; } +SEC("?fmod_ret.multi/bpf_modify_return_test_tp") +int bench_trigger_fmodret_multi(void *ctx) +{ + inc_counter(); + return -22; +} + SEC("?tp/bpf_test_run/bpf_trigger_tp") int bench_trigger_tp(void *ctx) { -- 2.39.5

2 months, 2 weeks

1
0
0 0

[PATCH bpf-next v2 17/18] selftests/bpf: add basic testcases for tracing_multi

by Menglong Dong

In this commit, we add some testcases for the following attach types: BPF_TRACE_FENTRY_MULTI BPF_TRACE_FEXIT_MULTI BPF_MODIFY_RETURN_MULTI We reuse the testings in fentry_test.c, fexit_test.c and modify_return.c by attach the tracing bpf prog as tracing_multi. We add some functions to skip for tracing progs to bpf_get_ksyms(). The functions that in the "btf_id_deny" should be skipped. What's more, the kernel can't find the right function address according to the btf type id when duplicated function name exist. So we skip such functions that we meet. The list is not whole, so we still can fail during attaching the FENTRY_MULTI to all the kernel functions. This is something that we need to fix in the feature. Signed-off-by: Menglong Dong <dongml2(a)chinatelecom.cn> --- tools/testing/selftests/bpf/Makefile | 2 +- .../selftests/bpf/prog_tests/fentry_fexit.c | 22 +- .../selftests/bpf/prog_tests/fentry_test.c | 79 +++++-- .../selftests/bpf/prog_tests/fexit_test.c | 79 +++++-- .../selftests/bpf/prog_tests/modify_return.c | 60 +++++ .../bpf/prog_tests/tracing_multi_link.c | 210 ++++++++++++++++++ .../selftests/bpf/progs/fentry_multi_empty.c | 13 ++ .../selftests/bpf/progs/tracing_multi_test.c | 181 +++++++++++++++ .../selftests/bpf/test_kmods/bpf_testmod.c | 24 ++ tools/testing/selftests/bpf/test_progs.c | 50 +++++ tools/testing/selftests/bpf/test_progs.h | 3 + tools/testing/selftests/bpf/trace_helpers.c | 69 ++++++ 12 files changed, 744 insertions(+), 48 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c create mode 100644 tools/testing/selftests/bpf/progs/fentry_multi_empty.c create mode 100644 tools/testing/selftests/bpf/progs/tracing_multi_test.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4863106034df..1fa0da096262 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -496,7 +496,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ test_subskeleton.skel.h test_subskeleton_lib.skel.h \ test_usdt.skel.h -LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c \ +LSKELS := fexit_sleep.c atomics.c \ trace_printk.c trace_vprintk.c map_ptr_kern.c \ core_kern.c core_kern_overflow.c test_ringbuf.c \ test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 130f5b82d2e6..84cc8b669684 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,32 +1,32 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fentry_test.lskel.h" -#include "fexit_test.lskel.h" +#include "fentry_test.skel.h" +#include "fexit_test.skel.h" void test_fentry_fexit(void) { - struct fentry_test_lskel *fentry_skel = NULL; - struct fexit_test_lskel *fexit_skel = NULL; + struct fentry_test *fentry_skel = NULL; + struct fexit_test *fexit_skel = NULL; __u64 *fentry_res, *fexit_res; int err, prog_fd, i; LIBBPF_OPTS(bpf_test_run_opts, topts); - fentry_skel = fentry_test_lskel__open_and_load(); + fentry_skel = fentry_test__open_and_load(); if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto close_prog; - fexit_skel = fexit_test_lskel__open_and_load(); + fexit_skel = fexit_test__open_and_load(); if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto close_prog; - err = fentry_test_lskel__attach(fentry_skel); + err = fentry_test__attach(fentry_skel); if (!ASSERT_OK(err, "fentry_attach")) goto close_prog; - err = fexit_test_lskel__attach(fexit_skel); + err = fexit_test__attach(fexit_skel); if (!ASSERT_OK(err, "fexit_attach")) goto close_prog; - prog_fd = fexit_skel->progs.test1.prog_fd; + prog_fd = bpf_program__fd(fexit_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "ipv6 test_run"); ASSERT_OK(topts.retval, "ipv6 test retval"); @@ -40,6 +40,6 @@ void test_fentry_fexit(void) } close_prog: - fentry_test_lskel__destroy(fentry_skel); - fexit_test_lskel__destroy(fexit_skel); + fentry_test__destroy(fentry_skel); + fexit_test__destroy(fexit_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index aee1bc77a17f..9edd383feabd 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,26 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fentry_test.lskel.h" +#include "fentry_test.skel.h" #include "fentry_many_args.skel.h" -static int fentry_test_common(struct fentry_test_lskel *fentry_skel) +static int fentry_test_check(struct fentry_test *fentry_skel) { + LIBBPF_OPTS(bpf_test_run_opts, topts); int err, prog_fd, i; - int link_fd; __u64 *result; - LIBBPF_OPTS(bpf_test_run_opts, topts); - - err = fentry_test_lskel__attach(fentry_skel); - if (!ASSERT_OK(err, "fentry_attach")) - return err; - /* Check that already linked program can't be attached again. */ - link_fd = fentry_test_lskel__test1__attach(fentry_skel); - if (!ASSERT_LT(link_fd, 0, "fentry_attach_link")) - return -1; - - prog_fd = fentry_skel->progs.test1.prog_fd; + prog_fd = bpf_program__fd(fentry_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); ASSERT_EQ(topts.retval, 0, "test_run"); @@ -31,7 +21,28 @@ static int fentry_test_common(struct fentry_test_lskel *fentry_skel) return -1; } - fentry_test_lskel__detach(fentry_skel); + return 0; +} + +static int fentry_test_common(struct fentry_test *fentry_skel) +{ + struct bpf_link *link; + int err; + + err = fentry_test__attach(fentry_skel); + if (!ASSERT_OK(err, "fentry_attach")) + return err; + + /* Check that already linked program can't be attached again. */ + link = bpf_program__attach(fentry_skel->progs.test1); + if (!ASSERT_ERR_PTR(link, "fentry_attach_link")) + return -1; + + err = fentry_test_check(fentry_skel); + if (!ASSERT_OK(err, "fentry_test_check")) + return err; + + fentry_test__detach(fentry_skel); /* zero results for re-attach test */ memset(fentry_skel->bss, 0, sizeof(*fentry_skel->bss)); @@ -40,10 +51,10 @@ static int fentry_test_common(struct fentry_test_lskel *fentry_skel) static void fentry_test(void) { - struct fentry_test_lskel *fentry_skel = NULL; + struct fentry_test *fentry_skel = NULL; int err; - fentry_skel = fentry_test_lskel__open_and_load(); + fentry_skel = fentry_test__open_and_load(); if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load")) goto cleanup; @@ -55,7 +66,7 @@ static void fentry_test(void) ASSERT_OK(err, "fentry_second_attach"); cleanup: - fentry_test_lskel__destroy(fentry_skel); + fentry_test__destroy(fentry_skel); } static void fentry_many_args(void) @@ -84,10 +95,42 @@ static void fentry_many_args(void) fentry_many_args__destroy(fentry_skel); } +static void fentry_multi_test(void) +{ + struct fentry_test *fentry_skel = NULL; + int err, prog_cnt; + + fentry_skel = fentry_test__open(); + if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_open")) + goto cleanup; + + prog_cnt = sizeof(fentry_skel->progs) / sizeof(long); + err = bpf_to_tracing_multi((void *)&fentry_skel->progs, prog_cnt); + if (!ASSERT_OK(err, "fentry_to_multi")) + goto cleanup; + + err = fentry_test__load(fentry_skel); + if (!ASSERT_OK(err, "fentry_skel_load")) + goto cleanup; + + err = bpf_attach_as_tracing_multi((void *)&fentry_skel->progs, + prog_cnt, + (void *)&fentry_skel->links); + if (!ASSERT_OK(err, "fentry_attach_multi")) + goto cleanup; + + err = fentry_test_check(fentry_skel); + ASSERT_OK(err, "fentry_first_attach"); +cleanup: + fentry_test__destroy(fentry_skel); +} + void test_fentry_test(void) { if (test__start_subtest("fentry")) fentry_test(); + if (test__start_subtest("fentry_multi")) + fentry_multi_test(); if (test__start_subtest("fentry_many_args")) fentry_many_args(); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index 1c13007e37dd..5652d02b3ad9 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -1,26 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -#include "fexit_test.lskel.h" +#include "fexit_test.skel.h" #include "fexit_many_args.skel.h" -static int fexit_test_common(struct fexit_test_lskel *fexit_skel) +static int fexit_test_check(struct fexit_test *fexit_skel) { + LIBBPF_OPTS(bpf_test_run_opts, topts); int err, prog_fd, i; - int link_fd; __u64 *result; - LIBBPF_OPTS(bpf_test_run_opts, topts); - - err = fexit_test_lskel__attach(fexit_skel); - if (!ASSERT_OK(err, "fexit_attach")) - return err; - /* Check that already linked program can't be attached again. */ - link_fd = fexit_test_lskel__test1__attach(fexit_skel); - if (!ASSERT_LT(link_fd, 0, "fexit_attach_link")) - return -1; - - prog_fd = fexit_skel->progs.test1.prog_fd; + prog_fd = bpf_program__fd(fexit_skel->progs.test1); err = bpf_prog_test_run_opts(prog_fd, &topts); ASSERT_OK(err, "test_run"); ASSERT_EQ(topts.retval, 0, "test_run"); @@ -31,7 +21,28 @@ static int fexit_test_common(struct fexit_test_lskel *fexit_skel) return -1; } - fexit_test_lskel__detach(fexit_skel); + return 0; +} + +static int fexit_test_common(struct fexit_test *fexit_skel) +{ + struct bpf_link *link; + int err; + + err = fexit_test__attach(fexit_skel); + if (!ASSERT_OK(err, "fexit_attach")) + return err; + + /* Check that already linked program can't be attached again. */ + link = bpf_program__attach(fexit_skel->progs.test1); + if (!ASSERT_ERR_PTR(link, "fexit_attach_link")) + return -1; + + err = fexit_test_check(fexit_skel); + if (!ASSERT_OK(err, "fexit_test_check")) + return err; + + fexit_test__detach(fexit_skel); /* zero results for re-attach test */ memset(fexit_skel->bss, 0, sizeof(*fexit_skel->bss)); @@ -40,10 +51,10 @@ static int fexit_test_common(struct fexit_test_lskel *fexit_skel) static void fexit_test(void) { - struct fexit_test_lskel *fexit_skel = NULL; + struct fexit_test *fexit_skel = NULL; int err; - fexit_skel = fexit_test_lskel__open_and_load(); + fexit_skel = fexit_test__open_and_load(); if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load")) goto cleanup; @@ -55,7 +66,7 @@ static void fexit_test(void) ASSERT_OK(err, "fexit_second_attach"); cleanup: - fexit_test_lskel__destroy(fexit_skel); + fexit_test__destroy(fexit_skel); } static void fexit_many_args(void) @@ -84,10 +95,42 @@ static void fexit_many_args(void) fexit_many_args__destroy(fexit_skel); } +static void fexit_test_multi(void) +{ + struct fexit_test *fexit_skel = NULL; + int err, prog_cnt; + + fexit_skel = fexit_test__open(); + if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_open")) + goto cleanup; + + prog_cnt = sizeof(fexit_skel->progs) / sizeof(long); + err = bpf_to_tracing_multi((void *)&fexit_skel->progs, prog_cnt); + if (!ASSERT_OK(err, "fexit_to_multi")) + goto cleanup; + + err = fexit_test__load(fexit_skel); + if (!ASSERT_OK(err, "fexit_skel_load")) + goto cleanup; + + err = bpf_attach_as_tracing_multi((void *)&fexit_skel->progs, + prog_cnt, + (void *)&fexit_skel->links); + if (!ASSERT_OK(err, "fexit_attach_multi")) + goto cleanup; + + err = fexit_test_check(fexit_skel); + ASSERT_OK(err, "fexit_first_attach"); +cleanup: + fexit_test__destroy(fexit_skel); +} + void test_fexit_test(void) { if (test__start_subtest("fexit")) fexit_test(); + if (test__start_subtest("fexit_multi")) + fexit_test_multi(); if (test__start_subtest("fexit_many_args")) fexit_many_args(); } diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c index a70c99c2f8c8..3ca454379e90 100644 --- a/tools/testing/selftests/bpf/prog_tests/modify_return.c +++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c @@ -49,6 +49,56 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) modify_return__destroy(skel); } +static void run_multi_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret) +{ + struct modify_return *skel = NULL; + int err, prog_fd, prog_cnt; + __u16 side_effect; + __s16 ret; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + skel = modify_return__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + /* stack function args is not supported by tracing multi-link yet, + * so we only enable the bpf progs without stack function args. + */ + bpf_program__set_expected_attach_type(skel->progs.fentry_test, + BPF_TRACE_FENTRY_MULTI); + bpf_program__set_expected_attach_type(skel->progs.fexit_test, + BPF_TRACE_FEXIT_MULTI); + bpf_program__set_expected_attach_type(skel->progs.fmod_ret_test, + BPF_MODIFY_RETURN_MULTI); + + err = modify_return__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + prog_cnt = sizeof(skel->progs) / sizeof(long); + err = bpf_attach_as_tracing_multi((void *)&skel->progs, + prog_cnt, + (void *)&skel->links); + if (!ASSERT_OK(err, "modify_return__attach failed")) + goto cleanup; + + skel->bss->input_retval = input_retval; + prog_fd = bpf_program__fd(skel->progs.fmod_ret_test); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + + side_effect = UPPER(topts.retval); + ret = LOWER(topts.retval); + + ASSERT_EQ(ret, want_ret, "test_run ret"); + ASSERT_EQ(side_effect, want_side_effect, "modify_return side_effect"); + ASSERT_EQ(skel->bss->fentry_result, 1, "modify_return fentry_result"); + ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result"); + ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result"); +cleanup: + modify_return__destroy(skel); +} + /* TODO: conflict with get_func_ip_test */ void serial_test_modify_return(void) { @@ -59,3 +109,13 @@ void serial_test_modify_return(void) 0 /* want_side_effect */, -EINVAL * 2 /* want_ret */); } + +void serial_test_modify_return_multi(void) +{ + run_multi_test(0 /* input_retval */, + 2 /* want_side_effect */, + 33 /* want_ret */); + run_multi_test(-EINVAL /* input_retval */, + 1 /* want_side_effect */, + -EINVAL + 29 /* want_ret */); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c b/tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c new file mode 100644 index 000000000000..1cbe6089472f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tracing_multi_link.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 ChinaTelecom */ + +#include <test_progs.h> + +#include "tracing_multi_test.skel.h" +#include "fentry_multi_empty.skel.h" + +static void test_run(struct tracing_multi_test *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err, prog_fd; + + skel->bss->pid = getpid(); + prog_fd = bpf_program__fd(skel->progs.fentry_cookie_test1); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, 0, "test_run"); + + ASSERT_EQ(skel->bss->fentry_test1_result, 1, "fentry_test1_result"); + ASSERT_EQ(skel->bss->fentry_test2_result, 1, "fentry_test2_result"); + ASSERT_EQ(skel->bss->fentry_test3_result, 1, "fentry_test3_result"); + ASSERT_EQ(skel->bss->fentry_test4_result, 1, "fentry_test4_result"); + ASSERT_EQ(skel->bss->fentry_test5_result, 1, "fentry_test5_result"); + ASSERT_EQ(skel->bss->fentry_test6_result, 1, "fentry_test6_result"); + ASSERT_EQ(skel->bss->fentry_test7_result, 1, "fentry_test7_result"); + ASSERT_EQ(skel->bss->fentry_test8_result, 1, "fentry_test8_result"); +} + +static void test_skel_auto_api(void) +{ + struct tracing_multi_test *skel; + int err; + + skel = tracing_multi_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_multi_test__open_and_load")) + return; + + /* disable all programs that should fail */ + bpf_program__set_autoattach(skel->progs.fentry_fail_test1, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test2, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test3, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test4, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test5, false); + bpf_program__set_autoattach(skel->progs.fentry_fail_test6, false); + + bpf_program__set_autoattach(skel->progs.fexit_fail_test1, false); + bpf_program__set_autoattach(skel->progs.fexit_fail_test2, false); + bpf_program__set_autoattach(skel->progs.fexit_fail_test3, false); + + err = tracing_multi_test__attach(skel); + if (!ASSERT_OK(err, "tracing_multi_test__attach")) + goto cleanup; + + test_run(skel); + +cleanup: + tracing_multi_test__destroy(skel); +} + +static int attach_bpf(struct bpf_program *prog, struct bpf_link **link_ptr, + bool success) +{ + struct bpf_link *link; + int err; + + link = bpf_program__attach(prog); + err = libbpf_get_error(link); + if (!ASSERT_OK(success ? err : !err, "attach_bpf")) + return err; + *link_ptr = link; + + return 0; +} + +#define attach_skel_bpf(name, success) \ + attach_bpf(skel->progs.name, &skel->links.name, success) + +static void test_skel_manual_api(void) +{ + struct tracing_multi_test *skel; + + skel = tracing_multi_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_multi_test__open_and_load")) + return; + + if (attach_skel_bpf(fentry_success_test1, true) || + attach_skel_bpf(fentry_success_test2, true) || + attach_skel_bpf(fentry_success_test3, true) || + attach_skel_bpf(fentry_success_test4, true) || + attach_skel_bpf(fexit_success_test1, true) || + attach_skel_bpf(fexit_success_test2, true) || + attach_skel_bpf(fentry_fail_test1, false) || + attach_skel_bpf(fentry_fail_test2, false) || + attach_skel_bpf(fentry_fail_test3, false) || + attach_skel_bpf(fentry_fail_test4, false) || + attach_skel_bpf(fentry_fail_test5, false) || + attach_skel_bpf(fentry_fail_test6, false) || + attach_skel_bpf(fexit_fail_test1, false) || + attach_skel_bpf(fexit_fail_test2, false) || + attach_skel_bpf(fexit_fail_test3, false) || + attach_skel_bpf(fentry_cookie_test1, true)) + goto cleanup; + + test_run(skel); + +cleanup: + tracing_multi_test__destroy(skel); +} + +static void test_attach_api(void) +{ + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + struct tracing_multi_test *skel; + struct bpf_link *link; + const char *syms[8] = { + "bpf_fentry_test1", + "bpf_fentry_test2", + "bpf_fentry_test3", + "bpf_fentry_test4", + "bpf_fentry_test5", + "bpf_fentry_test6", + "bpf_fentry_test7", + "bpf_fentry_test8", + }; + __u64 cookies[] = {1, 7, 2, 3, 4, 5, 6, 8}; + + skel = tracing_multi_test__open_and_load(); + if (!ASSERT_OK_PTR(skel, "tracing_multi_test__open_and_load")) + return; + + opts.syms = syms; + opts.cookies = cookies; + opts.cnt = ARRAY_SIZE(syms); + link = bpf_program__attach_trace_multi_opts(skel->progs.fentry_cookie_test1, + &opts); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_trace_multi_opts")) + goto cleanup; + skel->links.fentry_cookie_test1 = link; + + skel->bss->test_cookie = true; + test_run(skel); +cleanup: + tracing_multi_test__destroy(skel); +} + +static void test_attach_bench(bool kernel) +{ + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + struct fentry_multi_empty *skel; + long attach_start_ns, attach_end_ns; + long detach_start_ns, detach_end_ns; + double attach_delta, detach_delta; + struct bpf_link *link = NULL; + char **syms = NULL; + size_t cnt = 0; + + if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "get_syms")) + return; + + skel = fentry_multi_empty__open_and_load(); + if (!ASSERT_OK_PTR(skel, "fentry_multi_empty__open_and_load")) + goto cleanup; + + opts.syms = (const char **) syms; + opts.cnt = cnt; + opts.skip_invalid = true; + + attach_start_ns = get_time_ns(); + link = bpf_program__attach_trace_multi_opts(skel->progs.fentry_multi_empty, + &opts); + attach_end_ns = get_time_ns(); + + if (!ASSERT_OK_PTR(link, "bpf_program__attach_trace_multi_opts")) + return; + + detach_start_ns = get_time_ns(); + bpf_link__destroy(link); + detach_end_ns = get_time_ns(); + + attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0; + detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0; + + printf("%s: found %lu functions\n", __func__, opts.cnt); + printf("%s: attached in %7.3lfs\n", __func__, attach_delta); + printf("%s: detached in %7.3lfs\n", __func__, detach_delta); + +cleanup: + fentry_multi_empty__destroy(skel); + if (syms) + free(syms); +} + +void serial_test_tracing_multi_attach_bench(void) +{ + if (test__start_subtest("kernel")) + test_attach_bench(true); + if (test__start_subtest("modules")) + test_attach_bench(false); +} + +void test_tracing_multi_attach_test(void) +{ + if (test__start_subtest("skel_auto_api")) + test_skel_auto_api(); + if (test__start_subtest("skel_manual_api")) + test_skel_manual_api(); + if (test__start_subtest("attach_api")) + test_attach_api(); +} diff --git a/tools/testing/selftests/bpf/progs/fentry_multi_empty.c b/tools/testing/selftests/bpf/progs/fentry_multi_empty.c new file mode 100644 index 000000000000..a09ba216dff8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fentry_multi_empty.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 ChinaTelecom */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +SEC("fentry.multi/bpf_fentry_test1") +int BPF_PROG(fentry_multi_empty) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tracing_multi_test.c b/tools/testing/selftests/bpf/progs/tracing_multi_test.c new file mode 100644 index 000000000000..fa27851896b9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tracing_multi_test.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 ChinaTelecom */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct bpf_testmod_struct_arg_1 { + int a; +}; +struct bpf_testmod_struct_arg_2 { + long a; + long b; +}; + +__u64 test_result = 0; + +int pid = 0; +int test_cookie = 0; + +__u64 fentry_test1_result = 0; +__u64 fentry_test2_result = 0; +__u64 fentry_test3_result = 0; +__u64 fentry_test4_result = 0; +__u64 fentry_test5_result = 0; +__u64 fentry_test6_result = 0; +__u64 fentry_test7_result = 0; +__u64 fentry_test8_result = 0; + +extern const void bpf_fentry_test1 __ksym; +extern const void bpf_fentry_test2 __ksym; +extern const void bpf_fentry_test3 __ksym; +extern const void bpf_fentry_test4 __ksym; +extern const void bpf_fentry_test5 __ksym; +extern const void bpf_fentry_test6 __ksym; +extern const void bpf_fentry_test7 __ksym; +extern const void bpf_fentry_test8 __ksym; + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_13") +int BPF_PROG2(fentry_success_test1, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_10") +int BPF_PROG2(fentry_success_test2, int, a, struct bpf_testmod_struct_arg_2, b) +{ + test_result = a + b.a + b.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_4") +int BPF_PROG2(fentry_success_test3, struct bpf_testmod_struct_arg_2, a, int, b, + int, c) +{ + test_result = c; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_2") +int BPF_PROG2(fentry_success_test4, struct bpf_testmod_struct_arg_2, a, int, b, + int, c) +{ + test_result = c; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_1") +int BPF_PROG2(fentry_fail_test1, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_2") +int BPF_PROG2(fentry_fail_test2, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_4") +int BPF_PROG2(fentry_fail_test3, struct bpf_testmod_struct_arg_2, a) +{ + test_result = a.a + a.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_2") +int BPF_PROG2(fentry_fail_test4, int, a, struct bpf_testmod_struct_arg_2, b) +{ + test_result = a + b.a + b.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_13") +int BPF_PROG2(fentry_fail_test5, int, a, struct bpf_testmod_struct_arg_2, b) +{ + test_result = a + b.a + b.b; + return 0; +} + +SEC("fentry.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_12") +int BPF_PROG2(fentry_fail_test6, struct bpf_testmod_struct_arg_2, a, int, b, + int, c) +{ + test_result = c; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_3") +int BPF_PROG2(fexit_success_test1, struct bpf_testmod_struct_arg_2, a, int, b, + int, c, int, retval) +{ + test_result = retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_12") +int BPF_PROG2(fexit_success_test2, int, a, struct bpf_testmod_struct_arg_2, b, + int, c, int, retval) +{ + test_result = a + b.a + b.b + retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_1,bpf_testmod_test_struct_arg_4") +int BPF_PROG2(fexit_fail_test1, struct bpf_testmod_struct_arg_2, a, int, b, + int, c, int, retval) +{ + test_result = retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_10") +int BPF_PROG2(fexit_fail_test2, int, a, struct bpf_testmod_struct_arg_2, b, + int, c, int, retval) +{ + test_result = a + b.a + b.b + retval; + return 0; +} + +SEC("fexit.multi/bpf_testmod_test_struct_arg_2,bpf_testmod_test_struct_arg_11") +int BPF_PROG2(fexit_fail_test3, int, a, struct bpf_testmod_struct_arg_2, b, + int, c, int, retval) +{ + test_result = a + b.a + b.b + retval; + return 0; +} + +static void tracing_multi_check_cookie(unsigned long long *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return; + + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; + __u64 addr = bpf_get_func_ip(ctx); + +#define SET(__var, __addr, __cookie) ({ \ + if (((const void *) addr == __addr) && \ + (!test_cookie || (cookie == __cookie))) \ + __var = 1; \ +}) + SET(fentry_test1_result, &bpf_fentry_test1, 1); + SET(fentry_test2_result, &bpf_fentry_test2, 7); + SET(fentry_test3_result, &bpf_fentry_test3, 2); + SET(fentry_test4_result, &bpf_fentry_test4, 3); + SET(fentry_test5_result, &bpf_fentry_test5, 4); + SET(fentry_test6_result, &bpf_fentry_test6, 5); + SET(fentry_test7_result, &bpf_fentry_test7, 6); + SET(fentry_test8_result, &bpf_fentry_test8, 8); +} + +SEC("fentry.multi/bpf_fentry_test1,bpf_fentry_test2,bpf_fentry_test3,bpf_fentry_test4,bpf_fentry_test5,bpf_fentry_test6,bpf_fentry_test7,bpf_fentry_test8") +int BPF_PROG(fentry_cookie_test1) +{ + tracing_multi_check_cookie(ctx); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index e9e918cdf31f..07ea1d5d3795 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -128,6 +128,30 @@ bpf_testmod_test_struct_arg_9(u64 a, void *b, short c, int d, void *e, char f, return bpf_testmod_test_struct_arg_result; } +noinline int +bpf_testmod_test_struct_arg_10(int a, struct bpf_testmod_struct_arg_2 b) { + bpf_testmod_test_struct_arg_result = a + b.a + b.b; + return bpf_testmod_test_struct_arg_result; +} + +noinline struct bpf_testmod_struct_arg_2 * +bpf_testmod_test_struct_arg_11(int a, struct bpf_testmod_struct_arg_2 b, int c) { + bpf_testmod_test_struct_arg_result = a + b.a + b.b + c; + return (void *)bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_struct_arg_12(int a, struct bpf_testmod_struct_arg_2 b, int *c) { + bpf_testmod_test_struct_arg_result = a + b.a + b.b + *c; + return bpf_testmod_test_struct_arg_result; +} + +noinline int +bpf_testmod_test_struct_arg_13(struct bpf_testmod_struct_arg_2 b) { + bpf_testmod_test_struct_arg_result = b.a + b.b; + return bpf_testmod_test_struct_arg_result; +} + noinline int bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) { bpf_testmod_test_struct_arg_result = a->a; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 309d9d4a8ace..533b714f1ca6 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -667,6 +667,56 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) return bpf_map__fd(map); } +int bpf_to_tracing_multi(struct bpf_program **progs, int prog_cnt) +{ + enum bpf_attach_type type; + int i, err; + + for (i = 0; i < prog_cnt; i++) { + type = bpf_program__get_expected_attach_type(progs[i]); + if (type == BPF_TRACE_FENTRY) + type = BPF_TRACE_FENTRY_MULTI; + else if (type == BPF_TRACE_FEXIT) + type = BPF_TRACE_FEXIT_MULTI; + else if (type == BPF_MODIFY_RETURN) + type = BPF_MODIFY_RETURN_MULTI; + else + continue; + err = bpf_program__set_expected_attach_type(progs[i], type); + if (err) + return err; + } + + return 0; +} + +int bpf_attach_as_tracing_multi(struct bpf_program **progs, int prog_cnt, + struct bpf_link **link) +{ + struct bpf_link *__link; + int err, type; + + for (int i = 0; i < prog_cnt; i++) { + LIBBPF_OPTS(bpf_trace_multi_opts, opts); + + type = bpf_program__get_expected_attach_type(progs[i]); + if (type != BPF_TRACE_FENTRY_MULTI && + type != BPF_TRACE_FEXIT_MULTI && + type != BPF_MODIFY_RETURN_MULTI) + continue; + + opts.attach_tracing = true; + __link = bpf_program__attach_trace_multi_opts(progs[i], &opts); + err = libbpf_get_error(link); + if (err) + return err; + + link[i] = __link; + } + + return 0; +} + int compare_map_keys(int map1_fd, int map2_fd) { __u32 key, next_key; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index df2222a1806f..7e30c6dbf35c 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -496,6 +496,9 @@ int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); int get_bpf_max_tramp_links_from(struct btf *btf); int get_bpf_max_tramp_links(void); +int bpf_to_tracing_multi(struct bpf_program **progs, int prog_cnt); +int bpf_attach_as_tracing_multi(struct bpf_program **progs, int prog_cnt, + struct bpf_link **link); struct netns_obj; struct netns_obj *netns_new(const char *name, bool open); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index d24baf244d1f..a9e9dd3be226 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -559,6 +559,75 @@ static bool skip_entry(char *name) if (!strncmp(name, "__ftrace_invalid_address__", sizeof("__ftrace_invalid_address__") - 1)) return true; + + /* skip functions in "btf_id_deny" */ + if (!strcmp(name, "migrate_disable")) + return true; + if (!strcmp(name, "migrate_enable")) + return true; + if (!strcmp(name, "rcu_read_unlock_strict")) + return true; + if (!strcmp(name, "preempt_count_add")) + return true; + if (!strcmp(name, "preempt_count_sub")) + return true; + if (!strcmp(name, "__rcu_read_lock")) + return true; + if (!strcmp(name, "__rcu_read_unlock")) + return true; + + /* Following symbols have multi definition in kallsyms, take + * "t_next" for example: + * + * ffffffff813c10d0 t t_next + * ffffffff813d31b0 t t_next + * ffffffff813e06b0 t t_next + * ffffffff813eb360 t t_next + * ffffffff81613360 t t_next + * + * but only one of them have corresponding mrecord: + * ffffffff81613364 t_next + * + * The kernel search the target function address by the symbol + * name "t_next" with kallsyms_lookup_name() during attaching + * and the function "0xffffffff813c10d0" can be matched, which + * doesn't have a corresponding mrecord. And this will make + * the attach failing. Skip the functions like this. + * + * The list maybe not whole, so we still can fail......We need a + * way to make the whole things right. Yes, we need fix it :/ + */ + if (!strcmp(name, "kill_pid_usb_asyncio")) + return true; + if (!strcmp(name, "t_next")) + return true; + if (!strcmp(name, "t_stop")) + return true; + if (!strcmp(name, "t_start")) + return true; + if (!strcmp(name, "p_next")) + return true; + if (!strcmp(name, "p_stop")) + return true; + if (!strcmp(name, "p_start")) + return true; + if (!strcmp(name, "mem32_serial_out")) + return true; + if (!strcmp(name, "mem32_serial_in")) + return true; + if (!strcmp(name, "io_serial_in")) + return true; + if (!strcmp(name, "io_serial_out")) + return true; + if (!strcmp(name, "event_callback")) + return true; + if (!strcmp(name, "amd_pmu_init")) + return true; + if (!strcmp(name, "sync_regs")) + return true; + if (!strcmp(name, "empty")) + return true; + return false; } -- 2.39.5

2 months, 2 weeks

1
0
0 0

[PATCH bpf-next v2 16/18] selftests/bpf: move get_ksyms and get_addrs to trace_helpers.c

by Menglong Dong

We need to get all the kernel function that can be traced sometimes, so we move the get_syms() and get_addrs() in kprobe_multi_test.c to trace_helpers.c and rename it to bpf_get_ksyms() and bpf_get_addrs(). Signed-off-by: Menglong Dong <dongml2(a)chinatelecom.cn> --- .../bpf/prog_tests/kprobe_multi_test.c | 220 +----------------- tools/testing/selftests/bpf/trace_helpers.c | 214 +++++++++++++++++ tools/testing/selftests/bpf/trace_helpers.h | 3 + 3 files changed, 220 insertions(+), 217 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index e19ef509ebf8..171706e78da8 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -422,220 +422,6 @@ static void test_unique_match(void) kprobe_multi__destroy(skel); } -static size_t symbol_hash(long key, void *ctx __maybe_unused) -{ - return str_hash((const char *) key); -} - -static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) -{ - return strcmp((const char *) key1, (const char *) key2) == 0; -} - -static bool is_invalid_entry(char *buf, bool kernel) -{ - if (kernel && strchr(buf, '[')) - return true; - if (!kernel && !strchr(buf, '[')) - return true; - return false; -} - -static bool skip_entry(char *name) -{ - /* - * We attach to almost all kernel functions and some of them - * will cause 'suspicious RCU usage' when fprobe is attached - * to them. Filter out the current culprits - arch_cpu_idle - * default_idle and rcu_* functions. - */ - if (!strcmp(name, "arch_cpu_idle")) - return true; - if (!strcmp(name, "default_idle")) - return true; - if (!strncmp(name, "rcu_", 4)) - return true; - if (!strcmp(name, "bpf_dispatcher_xdp_func")) - return true; - if (!strncmp(name, "__ftrace_invalid_address__", - sizeof("__ftrace_invalid_address__") - 1)) - return true; - return false; -} - -/* Do comparision by ignoring '.llvm.<hash>' suffixes. */ -static int compare_name(const char *name1, const char *name2) -{ - const char *res1, *res2; - int len1, len2; - - res1 = strstr(name1, ".llvm."); - res2 = strstr(name2, ".llvm."); - len1 = res1 ? res1 - name1 : strlen(name1); - len2 = res2 ? res2 - name2 : strlen(name2); - - if (len1 == len2) - return strncmp(name1, name2, len1); - if (len1 < len2) - return strncmp(name1, name2, len1) <= 0 ? -1 : 1; - return strncmp(name1, name2, len2) >= 0 ? 1 : -1; -} - -static int load_kallsyms_compare(const void *p1, const void *p2) -{ - return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); -} - -static int search_kallsyms_compare(const void *p1, const struct ksym *p2) -{ - return compare_name(p1, p2->name); -} - -static int get_syms(char ***symsp, size_t *cntp, bool kernel) -{ - size_t cap = 0, cnt = 0; - char *name = NULL, *ksym_name, **syms = NULL; - struct hashmap *map; - struct ksyms *ksyms; - struct ksym *ks; - char buf[256]; - FILE *f; - int err = 0; - - ksyms = load_kallsyms_custom_local(load_kallsyms_compare); - if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_custom_local")) - return -EINVAL; - - /* - * The available_filter_functions contains many duplicates, - * but other than that all symbols are usable in kprobe multi - * interface. - * Filtering out duplicates by using hashmap__add, which won't - * add existing entry. - */ - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); - - if (!f) - return -EINVAL; - - map = hashmap__new(symbol_hash, symbol_equal, NULL); - if (IS_ERR(map)) { - err = libbpf_get_error(map); - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) - continue; - if (skip_entry(name)) - continue; - - ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); - if (!ks) { - err = -EINVAL; - goto error; - } - - ksym_name = ks->name; - err = hashmap__add(map, ksym_name, 0); - if (err == -EEXIST) { - err = 0; - continue; - } - if (err) - goto error; - - err = libbpf_ensure_mem((void **) &syms, &cap, - sizeof(*syms), cnt + 1); - if (err) - goto error; - - syms[cnt++] = ksym_name; - } - - *symsp = syms; - *cntp = cnt; - -error: - free(name); - fclose(f); - hashmap__free(map); - if (err) - free(syms); - return err; -} - -static int get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) -{ - unsigned long *addr, *addrs, *tmp_addrs; - int err = 0, max_cnt, inc_cnt; - char *name = NULL; - size_t cnt = 0; - char buf[256]; - FILE *f; - - if (access("/sys/kernel/tracing/trace", F_OK) == 0) - f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); - else - f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); - - if (!f) - return -ENOENT; - - /* In my local setup, the number of entries is 50k+ so Let us initially - * allocate space to hold 64k entries. If 64k is not enough, incrementally - * increase 1k each time. - */ - max_cnt = 65536; - inc_cnt = 1024; - addrs = malloc(max_cnt * sizeof(long)); - if (addrs == NULL) { - err = -ENOMEM; - goto error; - } - - while (fgets(buf, sizeof(buf), f)) { - if (is_invalid_entry(buf, kernel)) - continue; - - free(name); - if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) - continue; - if (skip_entry(name)) - continue; - - if (cnt == max_cnt) { - max_cnt += inc_cnt; - tmp_addrs = realloc(addrs, max_cnt); - if (!tmp_addrs) { - err = -ENOMEM; - goto error; - } - addrs = tmp_addrs; - } - - addrs[cnt++] = (unsigned long)addr; - } - - *addrsp = addrs; - *cntp = cnt; - -error: - free(name); - fclose(f); - if (err) - free(addrs); - return err; -} - static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts) { long attach_start_ns, attach_end_ns; @@ -670,7 +456,7 @@ static void test_kprobe_multi_bench_attach(bool kernel) char **syms = NULL; size_t cnt = 0; - if (!ASSERT_OK(get_syms(&syms, &cnt, kernel), "get_syms")) + if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms")) return; skel = kprobe_multi_empty__open_and_load(); @@ -696,13 +482,13 @@ static void test_kprobe_multi_bench_attach_addr(bool kernel) size_t cnt = 0; int err; - err = get_addrs(&addrs, &cnt, kernel); + err = bpf_get_addrs(&addrs, &cnt, kernel); if (err == -ENOENT) { test__skip(); return; } - if (!ASSERT_OK(err, "get_addrs")) + if (!ASSERT_OK(err, "bpf_get_addrs")) return; skel = kprobe_multi_empty__open_and_load(); diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 81943c6254e6..d24baf244d1f 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -17,6 +17,7 @@ #include <linux/limits.h> #include <libelf.h> #include <gelf.h> +#include "bpf/hashmap.h" #include "bpf/libbpf_internal.h" #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" @@ -519,3 +520,216 @@ void read_trace_pipe(void) { read_trace_pipe_iter(trace_pipe_cb, NULL, 0); } + +static size_t symbol_hash(long key, void *ctx __maybe_unused) +{ + return str_hash((const char *) key); +} + +static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused) +{ + return strcmp((const char *) key1, (const char *) key2) == 0; +} + +static bool is_invalid_entry(char *buf, bool kernel) +{ + if (kernel && strchr(buf, '[')) + return true; + if (!kernel && !strchr(buf, '[')) + return true; + return false; +} + +static bool skip_entry(char *name) +{ + /* + * We attach to almost all kernel functions and some of them + * will cause 'suspicious RCU usage' when fprobe is attached + * to them. Filter out the current culprits - arch_cpu_idle + * default_idle and rcu_* functions. + */ + if (!strcmp(name, "arch_cpu_idle")) + return true; + if (!strcmp(name, "default_idle")) + return true; + if (!strncmp(name, "rcu_", 4)) + return true; + if (!strcmp(name, "bpf_dispatcher_xdp_func")) + return true; + if (!strncmp(name, "__ftrace_invalid_address__", + sizeof("__ftrace_invalid_address__") - 1)) + return true; + return false; +} + +/* Do comparison by ignoring '.llvm.<hash>' suffixes. */ +static int compare_name(const char *name1, const char *name2) +{ + const char *res1, *res2; + int len1, len2; + + res1 = strstr(name1, ".llvm."); + res2 = strstr(name2, ".llvm."); + len1 = res1 ? res1 - name1 : strlen(name1); + len2 = res2 ? res2 - name2 : strlen(name2); + + if (len1 == len2) + return strncmp(name1, name2, len1); + if (len1 < len2) + return strncmp(name1, name2, len1) <= 0 ? -1 : 1; + return strncmp(name1, name2, len2) >= 0 ? 1 : -1; +} + +static int load_kallsyms_compare(const void *p1, const void *p2) +{ + return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name); +} + +static int search_kallsyms_compare(const void *p1, const struct ksym *p2) +{ + return compare_name(p1, p2->name); +} + +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) +{ + size_t cap = 0, cnt = 0; + char *name = NULL, *ksym_name, **syms = NULL; + struct hashmap *map; + struct ksyms *ksyms; + struct ksym *ks; + char buf[256]; + FILE *f; + int err = 0; + + ksyms = load_kallsyms_custom_local(load_kallsyms_compare); + if (!ksyms) + return -EINVAL; + + /* + * The available_filter_functions contains many duplicates, + * but other than that all symbols are usable to trace. + * Filtering out duplicates by using hashmap__add, which won't + * add existing entry. + */ + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); + + if (!f) + return -EINVAL; + + map = hashmap__new(symbol_hash, symbol_equal, NULL); + if (IS_ERR(map)) { + err = libbpf_get_error(map); + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1) + continue; + if (skip_entry(name)) + continue; + + ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare); + if (!ks) { + err = -EINVAL; + goto error; + } + + ksym_name = ks->name; + err = hashmap__add(map, ksym_name, 0); + if (err == -EEXIST) { + err = 0; + continue; + } + if (err) + goto error; + + err = libbpf_ensure_mem((void **) &syms, &cap, + sizeof(*syms), cnt + 1); + if (err) + goto error; + + syms[cnt++] = ksym_name; + } + + *symsp = syms; + *cntp = cnt; + +error: + free(name); + fclose(f); + hashmap__free(map); + if (err) + free(syms); + return err; +} + +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel) +{ + unsigned long *addr, *addrs, *tmp_addrs; + int err = 0, max_cnt, inc_cnt; + char *name = NULL; + size_t cnt = 0; + char buf[256]; + FILE *f; + + if (access("/sys/kernel/tracing/trace", F_OK) == 0) + f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r"); + else + f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r"); + + if (!f) + return -ENOENT; + + /* In my local setup, the number of entries is 50k+ so Let us initially + * allocate space to hold 64k entries. If 64k is not enough, incrementally + * increase 1k each time. + */ + max_cnt = 65536; + inc_cnt = 1024; + addrs = malloc(max_cnt * sizeof(long)); + if (addrs == NULL) { + err = -ENOMEM; + goto error; + } + + while (fgets(buf, sizeof(buf), f)) { + if (is_invalid_entry(buf, kernel)) + continue; + + free(name); + if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2) + continue; + if (skip_entry(name)) + continue; + + if (cnt == max_cnt) { + max_cnt += inc_cnt; + tmp_addrs = realloc(addrs, max_cnt); + if (!tmp_addrs) { + err = -ENOMEM; + goto error; + } + addrs = tmp_addrs; + } + + addrs[cnt++] = (unsigned long)addr; + } + + *addrsp = addrs; + *cntp = cnt; + +error: + free(name); + fclose(f); + if (err) + free(addrs); + return err; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index 2ce873c9f9aa..9437bdd4afa5 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -41,4 +41,7 @@ ssize_t get_rel_offset(uintptr_t addr); int read_build_id(const char *path, char *build_id, size_t size); +int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel); +int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel); + #endif -- 2.39.5

2 months, 2 weeks

1
0
0 0

[PATCH v2 0/4] kselftest/arm64: Add coverage for the interaction of vfork() and GCS

by Mark Brown

I had cause to look at the vfork() support for GCS and realised that we don't have any direct test coverage, this series does so by adding vfork() to nolibc and then using that in basic-gcs to provide some simple vfork() coverage. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- Changes in v2: - Add replacement of ifdef with if defined() in nolibc since the code doesn't reflect the coding style. - Remove check for arch specific vfork(). - Link to v1: https://lore.kernel.org/r/20250609-arm64-gcs-vfork-exit-v1-0-baad0f085747@k… --- Mark Brown (4): tools/nolibc: Replace ifdef with if defined() in sys.h tools/nolibc: Provide vfork() kselftest/arm64: Add a test for vfork() with GCS selftests/nolibc: Add coverage of vfork() tools/include/nolibc/sys.h | 57 +++++++++++++++++------- tools/testing/selftests/arm64/gcs/basic-gcs.c | 63 +++++++++++++++++++++++++++ tools/testing/selftests/nolibc/nolibc-test.c | 23 ++++++++-- 3 files changed, 124 insertions(+), 19 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250528-arm64-gcs-vfork-exit-4a7daf7652ee Best regards, -- Mark Brown <broonie(a)kernel.org>

2 months, 2 weeks

3
7
0 0

[PATCH] selftests: net: fix resource leak in napi_id_helper.c

by Malaya Kumar Rout

Resolve minor resource leaks reported by cppcheck in napi_id_helper.c cppcheck output before this patch: tools/testing/selftests/drivers/net/napi_id_helper.c:37:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:46:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:51:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:59:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:67:3: error: Resource leak: server [resourceLeak] tools/testing/selftests/drivers/net/napi_id_helper.c:76:3: error: Resource leak: server [resourceLeak] cppcheck output after this patch: No resource leaks found Signed-off-by: Malaya Kumar Rout <malayarout91(a)gmail.com> --- tools/testing/selftests/drivers/net/napi_id_helper.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c index eecd610c2109..1441b8d49b91 100644 --- a/tools/testing/selftests/drivers/net/napi_id_helper.c +++ b/tools/testing/selftests/drivers/net/napi_id_helper.c @@ -34,6 +34,7 @@ int main(int argc, char *argv[]) if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) { perror("setsockopt"); + close(server); return 1; } @@ -43,11 +44,13 @@ int main(int argc, char *argv[]) if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) { perror("bind failed"); + close(server); return 1; } if (listen(server, 1) < 0) { perror("listen"); + close(server); return 1; } @@ -56,6 +59,7 @@ int main(int argc, char *argv[]) client = accept(server, NULL, 0); if (client < 0) { perror("accept"); + close(server); return 1; } @@ -64,6 +68,7 @@ int main(int argc, char *argv[]) &optlen); if (ret != 0) { perror("getsockopt"); + close(server); return 1; } @@ -73,6 +78,7 @@ int main(int argc, char *argv[]) if (napi_id == 0) { fprintf(stderr, "napi ID is 0\n"); + close(server); return 1; } -- 2.43.0

2 months, 2 weeks

5
6
0 0

[PATCH] global: fix misapplications of "awhile"

by Ahelenia Ziemiańska

Of these: 7 "for a while" typos 5 "take a while" typos 1 misreading of "once in a while"? 3 awhiles used correctly remain in the tree Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli(a)nabijaczleweli.xyz> --- Documentation/trace/histogram.rst | 2 +- arch/sh/drivers/pci/common.c | 2 +- arch/sh/drivers/pci/pci-sh7780.c | 2 +- drivers/atm/lanai.c | 2 +- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/request.c | 2 +- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 +- drivers/scsi/hpsa.c | 2 +- drivers/tty/serial/jsm/jsm_neo.c | 2 +- fs/ocfs2/dlm/dlmrecovery.c | 2 +- sound/pci/emu10k1/emu10k1_main.c | 2 +- sound/pci/emu10k1/emupcm.c | 2 +- tools/testing/selftests/powerpc/tm/tm-tmspr.c | 2 +- 13 files changed, 13 insertions(+), 13 deletions(-) diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index 0aada18c38c6..2b98c1720a54 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -249,7 +249,7 @@ Extended error information table, it should keep a running total of the number of bytes requested by that call_site. - We'll let it run for awhile and then dump the contents of the 'hist' + We'll let it run for a while and then dump the contents of the 'hist' file in the kmalloc event's subdirectory (for readability, a number of entries have been omitted):: diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c index 9633b6147a05..f95004c67e6c 100644 --- a/arch/sh/drivers/pci/common.c +++ b/arch/sh/drivers/pci/common.c @@ -148,7 +148,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr, cmd |= PCI_STATUS_PARITY | PCI_STATUS_DETECTED_PARITY; - /* Now back off of the IRQ for awhile */ + /* Now back off of the IRQ for a while */ if (hose->err_irq) { disable_irq_nosync(hose->err_irq); hose->err_timer.expires = jiffies + HZ; diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c index 9a624a6ee354..f41d6939a3d9 100644 --- a/arch/sh/drivers/pci/pci-sh7780.c +++ b/arch/sh/drivers/pci/pci-sh7780.c @@ -153,7 +153,7 @@ static irqreturn_t sh7780_pci_serr_irq(int irq, void *dev_id) /* Deassert SERR */ __raw_writel(SH4_PCIINTM_SDIM, hose->reg_base + SH4_PCIINTM); - /* Back off the IRQ for awhile */ + /* Back off the IRQ for a while */ disable_irq_nosync(irq); hose->serr_timer.expires = jiffies + HZ; add_timer(&hose->serr_timer); diff --git a/drivers/atm/lanai.c b/drivers/atm/lanai.c index 2a1fe3080712..0dfa2cdc897c 100644 --- a/drivers/atm/lanai.c +++ b/drivers/atm/lanai.c @@ -755,7 +755,7 @@ static void lanai_shutdown_rx_vci(const struct lanai_vcc *lvcc) /* Shutdown transmitting on card. * Unfortunately the lanai needs us to wait until all the data * drains out of the buffer before we can dealloc it, so this - * can take awhile -- up to 370ms for a full 128KB buffer + * can take a while -- up to 370ms for a full 128KB buffer * assuming everone else is quiet. In theory the time is * boundless if there's a CBR VCC holding things up. */ diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 1d33e40d26ea..7318d9800370 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -499,7 +499,7 @@ struct gc_stat { * won't automatically reattach). * * CACHE_SET_STOPPING always gets set first when we're closing down a cache set; - * we'll continue to run normally for awhile with CACHE_SET_STOPPING set (i.e. + * we'll continue to run normally for a while with CACHE_SET_STOPPING set (i.e. * flushing dirty data). * * CACHE_SET_RUNNING means all cache devices have been registered and journal diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index af345dc6fde1..87b4341cb42c 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -257,7 +257,7 @@ static CLOSURE_CALLBACK(bch_data_insert_start) /* * But if it's not a writeback write we'd rather just bail out if - * there aren't any buckets ready to write to - it might take awhile and + * there aren't any buckets ready to write to - it might take a while and * we might be starving btree writes for gc or something. */ diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index dcb0545baa50..6a0be54f1c81 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -608,7 +608,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, buf_len = compl_desc->packet_len; hdr_len = compl_desc->header_len; - /* Page might have not been used for awhile and was likely last written + /* Page might have not been used for a while and was likely last written * by a different thread. */ if (rx->dqo.page_pool) { diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index c73a71ac3c29..0066f15153a7 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -7795,7 +7795,7 @@ static int hpsa_wait_for_mode_change_ack(struct ctlr_info *h) u32 doorbell_value; unsigned long flags; - /* under certain very rare conditions, this can take awhile. + /* under certain very rare conditions, this can take a while. * (e.g.: hot replace a failed 144GB drive in a RAID 5 set right * as we enter this code.) */ diff --git a/drivers/tty/serial/jsm/jsm_neo.c b/drivers/tty/serial/jsm/jsm_neo.c index e8e13bf056e2..2eb9ff26d6e8 100644 --- a/drivers/tty/serial/jsm/jsm_neo.c +++ b/drivers/tty/serial/jsm/jsm_neo.c @@ -1189,7 +1189,7 @@ static irqreturn_t neo_intr(int irq, void *voidbrd) /* * The UART triggered us with a bogus interrupt type. * It appears the Exar chip, when REALLY bogged down, will throw - * these once and awhile. + * these periodically. * Its harmless, just ignore it and move on. */ jsm_dbg(INTR, &brd->pci_dev, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 67fc62a49a76..00f52812dbb0 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2632,7 +2632,7 @@ static int dlm_pick_recovery_master(struct dlm_ctxt *dlm) dlm_reco_master_ready(dlm), msecs_to_jiffies(1000)); if (!dlm_reco_master_ready(dlm)) { - mlog(0, "%s: reco master taking awhile\n", + mlog(0, "%s: reco master taking a while\n", dlm->name); goto again; } diff --git a/sound/pci/emu10k1/emu10k1_main.c b/sound/pci/emu10k1/emu10k1_main.c index bbe252b8916c..6050201851b1 100644 --- a/sound/pci/emu10k1/emu10k1_main.c +++ b/sound/pci/emu10k1/emu10k1_main.c @@ -606,7 +606,7 @@ static int snd_emu10k1_ecard_init(struct snd_emu10k1 *emu) /* Step 2: Calibrate the ADC and DAC */ snd_emu10k1_ecard_write(emu, EC_DACCAL | EC_LEDN | EC_TRIM_CSN); - /* Step 3: Wait for awhile; XXX We can't get away with this + /* Step 3: Wait for a while; XXX We can't get away with this * under a real operating system; we'll need to block and wait that * way. */ snd_emu10k1_wait(emu, 48000); diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 1bf6e3d652f8..ca4b03317539 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -991,7 +991,7 @@ static snd_pcm_uframes_t snd_emu10k1_capture_pointer(struct snd_pcm_substream *s if (!epcm->running) return 0; if (epcm->first_ptr) { - udelay(50); /* hack, it takes awhile until capture is started */ + udelay(50); /* hack, it takes a while until capture is started */ epcm->first_ptr = 0; } ptr = snd_emu10k1_ptr_read(emu, epcm->capture_idx_reg, 0) & 0x0000ffff; diff --git a/tools/testing/selftests/powerpc/tm/tm-tmspr.c b/tools/testing/selftests/powerpc/tm/tm-tmspr.c index dd5ddffa28b7..0d64988ffb40 100644 --- a/tools/testing/selftests/powerpc/tm/tm-tmspr.c +++ b/tools/testing/selftests/powerpc/tm/tm-tmspr.c @@ -14,7 +14,7 @@ * (1) create more threads than cpus * (2) in each thread: * (a) set TFIAR and TFHAR a unique value - * (b) loop for awhile, continually checking to see if + * (b) loop for a while, continually checking to see if * either register has been corrupted. * * (3) Loop: -- 2.39.5

2 months, 2 weeks

2
1
0 0

[PATCH v11 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v10 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v11 (04-Jul-2025) - Fix compilation issue of some intermediate patches in v10 v10 (03-Jul-2025) - Add new patch of separated header file include/net/tcp_ecn.h to include ECN and AccECN functions (Eric Dumazet <edumazet(a)google.com>) - Add comments on the AccECN helper functions in tcp_ecn.h (Eric Dumazet <edumazet(a)google.com>) - Add documentation of tcp_ecn, tcp_ecn_option, tcp_ecn_beacon in ip-sysctl.rst to the corresponding patch (Eric Dumazet <edumazet(a)google.com>) - Split wait third ACK functionality into a separated patch from AccECN negotiation patch (Eric Dumazet <edumazet(a)google.com>) - Add READ_ONCE() over every reads of sysctl for all patches in the series (Eric Dumazet <edumazet(a)google.com>) - Merge heuristics of AccECN option ceb/cep and ACE field multi-wrap into a single patch - Add a table of SACK block reduction and required AccECN field in patch #15 commit message (Eric Dumazet <edumazet(a)google.com>) v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (6): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: ecn functions in separated include file tcp: Add wait_third_ack flag for ECN negotiation in simultaneous connect tcp: accecn: AccECN option send control tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (9): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics Documentation/networking/ip-sysctl.rst | 55 +- .../networking/net_cachelines/tcp_sock.rst | 13 + include/linux/tcp.h | 33 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 87 ++- include/net/tcp_ecn.h | 648 ++++++++++++++++++ include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 29 +- net/ipv4/tcp_input.c | 371 ++++++++-- net/ipv4/tcp_ipv4.c | 8 +- net/ipv4/tcp_minisocks.c | 40 +- net/ipv4/tcp_output.c | 297 ++++++-- net/ipv6/syncookies.c | 2 + net/ipv6/tcp_ipv6.c | 1 + 16 files changed, 1429 insertions(+), 187 deletions(-) create mode 100644 include/net/tcp_ecn.h -- 2.34.1

2 months, 2 weeks

1
15
0 0

[PATCH v6 14/14] selftests/sched_ext: Add test for DL server total_bw consistency

by Joel Fernandes

Add a new kselftest to verify that the total_bw value in /sys/kernel/debug/sched/debug remains consistent across all CPUs under different sched_ext BPF program states: 1. Before a BPF scheduler is loaded 2. While a BPF scheduler is loaded and active 3. After a BPF scheduler is unloaded The test runs CPU stress threads to ensure DL server bandwidth values stabilize before checking consistency. This helps catch potential issues with DL server bandwidth accounting during sched_ext transitions. Signed-off-by: Joel Fernandes <joelagnelf(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + tools/testing/selftests/sched_ext/total_bw.c | 286 +++++++++++++++++++ 2 files changed, 287 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/total_bw.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index f0a8cba3a99f..d48be158b0a1 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -184,6 +184,7 @@ auto-test-targets := \ select_cpu_vtime \ rt_stall \ test_example \ + total_bw \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/total_bw.c b/tools/testing/selftests/sched_ext/total_bw.c new file mode 100644 index 000000000000..6b81d6c51054 --- /dev/null +++ b/tools/testing/selftests/sched_ext/total_bw.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test to verify that total_bw value remains consistent across all CPUs + * in different BPF program states. + * + * Copyright (C) 2025 Nvidia Corporation. + */ +#include <bpf/bpf.h> +#include <errno.h> +#include <pthread.h> +#include <scx/common.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/wait.h> +#include <unistd.h> +#include "minimal.bpf.skel.h" +#include "scx_test.h" + +#define MAX_CPUS 512 +#define STABILIZATION_TIME_SEC 5 +#define STRESS_DURATION_SEC 5 + +struct total_bw_ctx { + struct minimal *skel; + long baseline_bw[MAX_CPUS]; + int nr_cpus; +}; + +static void *cpu_stress_thread(void *arg) +{ + volatile int i; + time_t end_time = time(NULL) + STRESS_DURATION_SEC; + + while (time(NULL) < end_time) { + for (i = 0; i < 1000000; i++); + } + + return NULL; +} + +/* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ +static int run_cpu_stress(int nr_cpus) +{ + pthread_t *threads; + int i, ret = 0; + + threads = calloc(nr_cpus, sizeof(pthread_t)); + if (!threads) + return -ENOMEM; + + /* Create threads to run on each CPU */ + for (i = 0; i < nr_cpus; i++) { + if (pthread_create(&threads[i], NULL, cpu_stress_thread, NULL)) { + ret = -errno; + fprintf(stderr, "Failed to create thread %d: %s\n", i, strerror(-ret)); + break; + } + } + + /* Wait for all threads to complete */ + for (i = 0; i < nr_cpus; i++) { + if (threads[i]) + pthread_join(threads[i], NULL); + } + + free(threads); + return ret; +} + +static int read_total_bw_values(long *bw_values, int max_cpus) +{ + FILE *fp; + char line[256]; + int cpu_count = 0; + + fp = fopen("/sys/kernel/debug/sched/debug", "r"); + if (!fp) { + SCX_ERR("Failed to open debug file"); + return -1; + } + + while (fgets(line, sizeof(line), fp)) { + char *bw_str = strstr(line, "total_bw"); + if (bw_str) { + bw_str = strchr(bw_str, ':'); + if (bw_str) { + /* Only store up to max_cpus values */ + if (cpu_count < max_cpus) { + bw_values[cpu_count] = atol(bw_str + 1); + } + cpu_count++; + } + } + } + + fclose(fp); + return cpu_count; +} + +static bool verify_total_bw_consistency(long *bw_values, int count) +{ + int i; + long first_value; + + if (count <= 0) + return false; + + first_value = bw_values[0]; + + for (i = 1; i < count; i++) { + if (bw_values[i] != first_value) { + SCX_ERR("Inconsistent total_bw: CPU0=%ld, CPU%d=%ld", + first_value, i, bw_values[i]); + return false; + } + } + + return true; +} + +static int fetch_verify_total_bw(long *bw_values, int nr_cpus) +{ + int attempts = 0; + int max_attempts = 10; + int count; + + /* + * The first enqueue on a CPU causes the DL server to start, for that + * reason run stressor threads in the hopes it schedules on all CPUs. + */ + if (run_cpu_stress(nr_cpus) < 0) { + SCX_ERR("Failed to run CPU stress"); + return -1; + } + + /* Let things settle down */ + sleep(STABILIZATION_TIME_SEC); + + /* Try multiple times to get stable values */ + while (attempts < max_attempts) { + count = read_total_bw_values(bw_values, nr_cpus); + fprintf(stderr, "Read %d total_bw values (testing %d CPUs)\n", count, nr_cpus); + /* If system has more CPUs than we're testing, that's OK */ + if (count < nr_cpus) { + SCX_ERR("Expected at least %d CPUs, got %d", nr_cpus, count); + attempts++; + sleep(1); + continue; + } + + /* Only verify the CPUs we're testing */ + if (verify_total_bw_consistency(bw_values, nr_cpus)) { + fprintf(stderr, "Values are consistent: %ld\n", bw_values[0]); + return 0; + } + + attempts++; + sleep(1); + } + + return -1; +} + +static enum scx_test_status setup(void **ctx) +{ + struct total_bw_ctx *test_ctx; + + if (access("/sys/kernel/debug/sched/debug", R_OK) != 0) { + fprintf(stderr, "Skipping test: debugfs sched/debug not accessible\n"); + return SCX_TEST_SKIP; + } + + test_ctx = calloc(1, sizeof(*test_ctx)); + if (!test_ctx) + return SCX_TEST_FAIL; + + test_ctx->nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + if (test_ctx->nr_cpus <= 0) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* If system has more CPUs than MAX_CPUS, just test the first MAX_CPUS */ + if (test_ctx->nr_cpus > MAX_CPUS) { + test_ctx->nr_cpus = MAX_CPUS; + } + + /* Test scenario 1: BPF program not loaded */ + /* Read and verify baseline total_bw before loading BPF program */ + fprintf(stderr, "BPF prog initially not loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(test_ctx->baseline_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable baseline values"); + free(test_ctx); + return SCX_TEST_FAIL; + } + + /* Load the BPF skeleton */ + test_ctx->skel = minimal__open(); + if (!test_ctx->skel) { + free(test_ctx); + return SCX_TEST_FAIL; + } + + SCX_ENUM_INIT(test_ctx->skel); + if (minimal__load(test_ctx->skel)) { + minimal__destroy(test_ctx->skel); + free(test_ctx); + return SCX_TEST_FAIL; + } + + *ctx = test_ctx; + return SCX_TEST_PASS; +} + +static enum scx_test_status run(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + struct bpf_link *link; + long loaded_bw[MAX_CPUS]; + long unloaded_bw[MAX_CPUS]; + int i; + + /* Test scenario 2: BPF program loaded */ + link = bpf_map__attach_struct_ops(test_ctx->skel->maps.minimal_ops); + if (!link) { + SCX_ERR("Failed to attach scheduler"); + return SCX_TEST_FAIL; + } + + fprintf(stderr, "BPF program loaded, reading total_bw values\n"); + if (fetch_verify_total_bw(loaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values with BPF loaded"); + bpf_link__destroy(link); + return SCX_TEST_FAIL; + } + bpf_link__destroy(link); + + /* Test scenario 3: BPF program unloaded */ + fprintf(stderr, "BPF program unloaded, reading total_bw values\n"); + if (fetch_verify_total_bw(unloaded_bw, test_ctx->nr_cpus) < 0) { + SCX_ERR("Failed to get stable values after BPF unload"); + return SCX_TEST_FAIL; + } + + /* Verify all three scenarios have the same total_bw values */ + for (i = 0; i < test_ctx->nr_cpus; i++) { + if (test_ctx->baseline_bw[i] != loaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != loaded_bw=%ld", + i, test_ctx->baseline_bw[i], loaded_bw[i]); + return SCX_TEST_FAIL; + } + + if (test_ctx->baseline_bw[i] != unloaded_bw[i]) { + SCX_ERR("CPU%d: baseline_bw=%ld != unloaded_bw=%ld", + i, test_ctx->baseline_bw[i], unloaded_bw[i]); + return SCX_TEST_FAIL; + } + } + + fprintf(stderr, "All total_bw values are consistent across all scenarios\n"); + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct total_bw_ctx *test_ctx = ctx; + + if (test_ctx) { + if (test_ctx->skel) + minimal__destroy(test_ctx->skel); + free(test_ctx); + } +} + +struct scx_test total_bw = { + .name = "total_bw", + .description = "Verify total_bw consistency across BPF program states", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&total_bw) -- 2.34.1

2 months, 2 weeks

1
0
0 0

[PATCH v6 12/14] selftests/sched_ext: Add test for sched_ext dl_server

by Joel Fernandes

From: Andrea Righi <arighi(a)nvidia.com> Add a selftest to validate the correct behavior of the deadline server for the ext_sched_class. [ Joel: Replaced occurences of CFS in the test with EXT. ] Signed-off-by: Joel Fernandes <joelagnelf(a)nvidia.com> Signed-off-by: Andrea Righi <arighi(a)nvidia.com> --- tools/testing/selftests/sched_ext/Makefile | 1 + .../selftests/sched_ext/rt_stall.bpf.c | 23 ++ tools/testing/selftests/sched_ext/rt_stall.c | 213 ++++++++++++++++++ 3 files changed, 237 insertions(+) create mode 100644 tools/testing/selftests/sched_ext/rt_stall.bpf.c create mode 100644 tools/testing/selftests/sched_ext/rt_stall.c diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 9d9d6b4c38b0..f0a8cba3a99f 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -182,6 +182,7 @@ auto-test-targets := \ select_cpu_dispatch_bad_dsq \ select_cpu_dispatch_dbl_dsp \ select_cpu_vtime \ + rt_stall \ test_example \ testcase-targets := $(addsuffix .o,$(addprefix $(SCXOBJ_DIR)/,$(auto-test-targets))) diff --git a/tools/testing/selftests/sched_ext/rt_stall.bpf.c b/tools/testing/selftests/sched_ext/rt_stall.bpf.c new file mode 100644 index 000000000000..80086779dd1e --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.bpf.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A scheduler that verified if RT tasks can stall SCHED_EXT tasks. + * + * Copyright (c) 2025 NVIDIA Corporation. + */ + +#include <scx/common.bpf.h> + +char _license[] SEC("license") = "GPL"; + +UEI_DEFINE(uei); + +void BPF_STRUCT_OPS(rt_stall_exit, struct scx_exit_info *ei) +{ + UEI_RECORD(uei, ei); +} + +SEC(".struct_ops.link") +struct sched_ext_ops rt_stall_ops = { + .exit = (void *)rt_stall_exit, + .name = "rt_stall", +}; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c new file mode 100644 index 000000000000..d4cb545ebfd8 --- /dev/null +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 NVIDIA Corporation. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sched.h> +#include <sys/prctl.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <time.h> +#include <linux/sched.h> +#include <signal.h> +#include <bpf/bpf.h> +#include <scx/common.h> +#include <sys/wait.h> +#include <unistd.h> +#include "rt_stall.bpf.skel.h" +#include "scx_test.h" +#include "../kselftest.h" + +#define CORE_ID 0 /* CPU to pin tasks to */ +#define RUN_TIME 5 /* How long to run the test in seconds */ + +/* Simple busy-wait function for test tasks */ +static void process_func(void) +{ + while (1) { + /* Busy wait */ + for (volatile unsigned long i = 0; i < 10000000UL; i++); + } +} + +/* Set CPU affinity to a specific core */ +static void set_affinity(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask) != 0) { + perror("sched_setaffinity"); + exit(EXIT_FAILURE); + } +} + +/* Set task scheduling policy and priority */ +static void set_sched(int policy, int priority) +{ + struct sched_param param; + + param.sched_priority = priority; + if (sched_setscheduler(0, policy, &param) != 0) { + perror("sched_setscheduler"); + exit(EXIT_FAILURE); + } +} + +/* Get process runtime from /proc/<pid>/stat */ +static float get_process_runtime(int pid) +{ + char path[256]; + FILE *file; + long utime, stime; + int fields; + + snprintf(path, sizeof(path), "/proc/%d/stat", pid); + file = fopen(path, "r"); + if (file == NULL) { + perror("Failed to open stat file"); + return -1; + } + + /* Skip the first 13 fields and read the 14th and 15th */ + fields = fscanf(file, + "%*d %*s %*c %*d %*d %*d %*d %*d %*u %*u %*u %*u %*u %lu %lu", + &utime, &stime); + fclose(file); + + if (fields != 2) { + fprintf(stderr, "Failed to read stat file\n"); + return -1; + } + + /* Calculate the total time spent in the process */ + long total_time = utime + stime; + long ticks_per_second = sysconf(_SC_CLK_TCK); + float runtime_seconds = total_time * 1.0 / ticks_per_second; + + return runtime_seconds; +} + +static enum scx_test_status setup(void **ctx) +{ + struct rt_stall *skel; + + skel = rt_stall__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(rt_stall__load(skel), "Failed to load skel"); + + *ctx = skel; + + return SCX_TEST_PASS; +} + +static bool sched_stress_test(void) +{ + float cfs_runtime, rt_runtime; + int cfs_pid, rt_pid; + float expected_min_ratio = 0.04; /* 4% */ + + ksft_print_header(); + ksft_set_plan(1); + + /* Create and set up a EXT task */ + cfs_pid = fork(); + if (cfs_pid == 0) { + set_affinity(CORE_ID); + process_func(); + exit(0); + } else if (cfs_pid < 0) { + perror("fork for EXT task"); + ksft_exit_fail(); + } + + /* Create an RT task */ + rt_pid = fork(); + if (rt_pid == 0) { + set_affinity(CORE_ID); + set_sched(SCHED_FIFO, 50); + process_func(); + exit(0); + } else if (rt_pid < 0) { + perror("fork for RT task"); + ksft_exit_fail(); + } + + /* Let the processes run for the specified time */ + sleep(RUN_TIME); + + /* Get runtime for the EXT task */ + cfs_runtime = get_process_runtime(cfs_pid); + if (cfs_runtime != -1) + ksft_print_msg("Runtime of EXT task (PID %d) is %f seconds\n", cfs_pid, cfs_runtime); + else + ksft_exit_fail_msg("Error getting runtime for EXT task (PID %d)\n", cfs_pid); + + /* Get runtime for the RT task */ + rt_runtime = get_process_runtime(rt_pid); + if (rt_runtime != -1) + ksft_print_msg("Runtime of RT task (PID %d) is %f seconds\n", rt_pid, rt_runtime); + else + ksft_exit_fail_msg("Error getting runtime for RT task (PID %d)\n", rt_pid); + + /* Kill the processes */ + kill(cfs_pid, SIGKILL); + kill(rt_pid, SIGKILL); + waitpid(cfs_pid, NULL, 0); + waitpid(rt_pid, NULL, 0); + + /* Verify that the scx task got enough runtime */ + float actual_ratio = cfs_runtime / (cfs_runtime + rt_runtime); + ksft_print_msg("EXT task got %.2f%% of total runtime\n", actual_ratio * 100); + + if (actual_ratio >= expected_min_ratio) { + ksft_test_result_pass("PASS: EXT task got more than %.2f%% of runtime\n", + expected_min_ratio * 100); + return true; + } else { + ksft_test_result_fail("FAIL: EXT task got less than %.2f%% of runtime\n", + expected_min_ratio * 100); + return false; + } +} + +static enum scx_test_status run(void *ctx) +{ + struct rt_stall *skel = ctx; + struct bpf_link *link; + bool res; + + link = bpf_map__attach_struct_ops(skel->maps.rt_stall_ops); + SCX_FAIL_IF(!link, "Failed to attach scheduler"); + + res = sched_stress_test(); + + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE)); + bpf_link__destroy(link); + + if (!res) + ksft_exit_fail(); + + return SCX_TEST_PASS; +} + +static void cleanup(void *ctx) +{ + struct rt_stall *skel = ctx; + + rt_stall__destroy(skel); +} + +struct scx_test rt_stall = { + .name = "rt_stall", + .description = "Verify that RT tasks cannot stall SCHED_EXT tasks", + .setup = setup, + .run = run, + .cleanup = cleanup, +}; +REGISTER_SCX_TEST(&rt_stall) -- 2.34.1

2 months, 2 weeks

1
0
0 0

[PATCH net-next v12 0/8] Support rate management on traffic classes in devlink and mlx5

by Mark Bloch

V12: - Fixed YAML indentation in devlink.yaml. - Removed unused total variable from devlink_nl_rate_tc_bw_set(). - Quoted shell variables in devlink.sh and split declarations to fix shellcheck warnings. - Added missing DevlinkFamily imports in selftests to fix pylint warnings. - Pulled changes from net-next to enable these adjustments: Inclusion of DevlinkFamily in YNL test libs. Introduction of nlmsg_for_each_attr_type() macro and its use in nfsd. V11: - Refactored the devlink code to accept relative TC bandwidth share values instead of percentages. - Updated documentation to clarify that values are interpreted as relative shares. - Refactored the logic in mlx5 to support proportional scaling for tc-bw values. - Switched to `nlmsg_for_each_attr_type()` for cleaner attribute parsing. - Added a hardware selftest to validate TC bandwidth behavior. - Refactored esw_qos_is_node_empty for readability. V10: - Added netdevsim selftest for tc-bw ops. - Dropped header: field as it’s unnecessary for local constants in devlink.yaml. V9: - Defined DEVLINK_RATE_TCS_MAX as 8 in uapi/linux/devlink.h. - Replaced IEEE_8021QAZ_MAX_TCS with DEVLINK_RATE_TCS_MAX throughout the code. - Updated devlink-rate-tc-index-max spec to reference the correct UAPI header. V8: - Limit line width to 80 characters in mlx5 changes instead of 100. - Increase the scheduling node levels to support TC arbitration. - Ensure parent nodes are set correctly in all code paths that extend the hierarchy depth for TC arbitration. - Extended the cover letter with the ongoing discussion on devlink-rate and net-shapers. - Extended the cover letter with the Netdev talk link on this series. V7: - Fixed disabling tc-bw on leaf nodes that did not have tc-bw configured. - Fixed an issue where tc-bw was disabled on a node with assigned vports, ensuring that vport->qos.sched_node->parent is correctly updated with the cloned node. - Declared a constant for the maximum allowed Traffic Class index in devlink rate. - Added a range check to validate rate-tc-index. - Added documentation for the tc-bw argument. - Add a validation check to ensure that the total bandwidth assigned to all traffic classes sums to 100. V6: - Addressed comments on devlink patch #3. - Removed first 4 IFC patches, to be pulled from mlx5-next. V5: - Fix warning in devlink_nl_rate_tc_bw_set(). - Fix target branch of patch #4. V4: - Renamed the nested attribute for traffic class bandwidth to DEVLINK_ATTR_RATE_TC_BWS. - Changed the order of the attributes in `devlink.h`. - Refactored the initialization tc-bw array in devlink_nl_rate_tc_bw_set(). - Added extack messages to provide clear feedback on issues with tc-bw arguments. - Updated `rate-tc-bws` to support a multi-attr set, where each attribute includes an index and the corresponding bandwidth for that traffic class. - Handled the issue where the user could provide DEVLINK_ATTR_RATE_TC_BWS with duplicate indices. - Provided ynl exmaples in patch [1/5] commit message. - Take IFC patches to beginning of the series, targeted for mlx5-next. V3: - Dropped rate-tc-index, using tc-bw array index instead. - Renamed rate-bw to rate-tc-bw. - Documneted what the rate-tc-bw represents and added a range check for validation. - Intorduced devlink_nl_rate_tc_bw_set() to parse and set the TC bandwidth values. - Updated the user API in the commit message of patch 1/6 to ensure bandwidths sum equals 100. - Fixed missing filling of rate-parent in devlink_nl_rate_fill(). V2: - Included <linux/dcbnl.h> in devlink.h to resolve missing IEEE_8021QAZ_MAX_TCS definition. - Refactored the rate-tc-bw attribute structure to use a separate rate-tc-index. - Updated patch 2/6 title. This patch series extends the devlink-rate API to support traffic class (TC) bandwidth management, enabling more granular control over traffic shaping and rate limiting across multiple TCs. The API now allows users to specify bandwidth proportions for different traffic classes in a single command. This is particularly useful for managing Enhanced Transmission Selection (ETS) for groups of Virtual Functions (VFs), allowing precise bandwidth allocation across traffic classes. Additionally the series refines the QoS handling in net/mlx5 to support TC arbitration and bandwidth management on vports and rate nodes. Discussions on traffic class shaping in net-shapers began in V5 [1], where we discussed with maintainers whether net-shapers should support traffic classes and how this could be implemented. Later, after further conversations with Paolo Abeni and Simon Horman, Cosmin provided an update [2], confirming that net-shapers' tree-based hierarchy aligns well with traffic classes when treated as distinct subsets of netdev queues. Since mlx5 enforces a 1:1 mapping between TX queues and traffic classes, this approach seems feasible, though some open questions remain regarding queue reconfiguration and certain mlx5 scheduling behaviors. Building on that discussion, Cosmin has now shared a concrete implementation plan on the netdev mailing list [3]. The plan, developed in collaboration with Paolo and Simon, outlines how net-shapers can be extended to support the same use cases currently covered by devlink-rate, with the eventual goal of aligning both and simplifying the shaping infrastructure in the kernel. This work was presented at Netdev 0x19 in Zagreb [4]. There we presented how TC scheduling is enforced in mlx5 hardware, which led to discussions on the mailing list. A summary of how things work: Classification means labeling a packet with a traffic class based on the packet's DSCP or VLAN PCP field, then treating packets with different traffic classes differently during transmit processing. In a virtualized setup, VFs are untrusted and do not control classification or shaping. Classification is done by the hardware using a prio-to-TC mapping set by the hypervisor. VFs only select which send queue to use and are expected to respect the classification logic by sending each traffic class on its dedicated queue. As stated in the net-shapers plan [3], each transmit queue should carry only a single traffic class. Mixing classes in a single queue can lead to HOL blocking. In the mlx5 implementation, if the queue used does not match the classified traffic class, the hardware moves the queue to the correct TC scheduler. This movement is not a reclassification; it’s a necessary enforcement step to ensure traffic class isolation is maintained. Extend devlink-rate API to support rate management on TCs: - devlink: Extend the devlink rate API to support traffic class bandwidth management Introduce a no-op implementation: - net/mlx5: Add no-op implementation for setting tc-bw on rate objects Add support for enabling and disabling TC QoS on vports and nodes: - net/mlx5: Add support for setting tc-bw on nodes - net/mlx5: Add traffic class scheduling support for vport QoS Support for setting tc-bw on rate objects: - net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw [1] https://lore.kernel.org/netdev/20241204220931.254964-1-tariqt@nvidia.com/ [2] https://lore.kernel.org/netdev/67df1a562614b553dcab043f347a0d7c5393ff83.cam… [3] https://lore.kernel.org/netdev/d9831d0c940a7b77419abe7c7330e822bbfd1cfb.cam… [4] https://netdevconf.info/0x19/sessions/talk/optimizing-bandwidth-allocation-… Carolina Jubran (8): netlink: introduce type-checking attribute iteration for nlmsg devlink: Extend devlink rate API with traffic classes bandwidth management selftest: netdevsim: Add devlink rate tc-bw test net/mlx5: Add no-op implementation for setting tc-bw on rate objects net/mlx5: Add support for setting tc-bw on nodes net/mlx5: Add traffic class scheduling support for vport QoS net/mlx5: Manage TC arbiter nodes and implement full support for tc-bw selftests: drv-net: Add test for devlink-rate traffic class bandwidth distribution Documentation/netlink/specs/devlink.yaml | 32 +- .../networking/devlink/devlink-port.rst | 8 + .../net/ethernet/mellanox/mlx5/core/devlink.c | 2 + .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 1037 ++++++++++++++++- .../net/ethernet/mellanox/mlx5/core/esw/qos.h | 8 + .../net/ethernet/mellanox/mlx5/core/eswitch.h | 14 +- drivers/net/netdevsim/dev.c | 43 + drivers/net/netdevsim/netdevsim.h | 1 + drivers/net/vxlan/vxlan_vnifilter.c | 13 +- fs/nfsd/nfsctl.c | 36 +- include/net/devlink.h | 8 + include/net/netlink.h | 14 + include/uapi/linux/devlink.h | 9 + net/devlink/netlink_gen.c | 15 +- net/devlink/netlink_gen.h | 1 + net/devlink/rate.c | 127 ++ .../drivers/net/hw/devlink_rate_tc_bw.py | 466 ++++++++ .../drivers/net/hw/lib/py/__init__.py | 2 +- .../selftests/drivers/net/lib/py/__init__.py | 2 +- .../drivers/net/netdevsim/devlink.sh | 53 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/ynl.py | 5 + 22 files changed, 1825 insertions(+), 73 deletions(-) create mode 100755 tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py base-commit: 20a0c20f82acf46d5731a11743e7c7ac4de25db8 -- 2.34.1

2 months, 2 weeks

2
9
0 0

[PATCH] selftests/futex: Add futex_numa to .gitignore

by Terry Tritton

futex_numa was never added to the .gitignore file. Add it. Signed-off-by: Terry Tritton <terry.tritton(a)linaro.org> --- tools/testing/selftests/futex/functional/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore index 7b24ae89594a..776ad658f75e 100644 --- a/tools/testing/selftests/futex/functional/.gitignore +++ b/tools/testing/selftests/futex/functional/.gitignore @@ -11,3 +11,4 @@ futex_wait_timeout futex_wait_uninitialized_heap futex_wait_wouldblock futex_waitv +futex_numa -- 2.39.5

2 months, 2 weeks

2
1
0 0

[PATCH] selftests/kexec: fix test_kexec_jump build and ignore generated binary

by Moon Hee Lee

The test_kexec_jump program builds correctly when invoked from the top-level selftests/Makefile, which explicitly sets the OUTPUT variable. However, building directly in tools/testing/selftests/kexec fails with: make: *** No rule to make target '/test_kexec_jump', needed by 'test_kexec_jump.sh'. Stop. This failure occurs because the Makefile rule relies on $(OUTPUT), which is undefined in direct builds. Fix this by listing test_kexec_jump in TEST_GEN_PROGS, the standard way to declare generated test binaries in the kselftest framework. This ensures the binary is built regardless of invocation context and properly removed by make clean. Also add the binary to .gitignore to avoid tracking it in version control. Signed-off-by: Moon Hee Lee <moonhee.lee.ca(a)gmail.com> --- tools/testing/selftests/kexec/.gitignore | 2 ++ tools/testing/selftests/kexec/Makefile | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/kexec/.gitignore diff --git a/tools/testing/selftests/kexec/.gitignore b/tools/testing/selftests/kexec/.gitignore new file mode 100644 index 000000000000..5f3d9e089ae8 --- /dev/null +++ b/tools/testing/selftests/kexec/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +test_kexec_jump diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile index e3000ccb9a5d..874cfdd3b75b 100644 --- a/tools/testing/selftests/kexec/Makefile +++ b/tools/testing/selftests/kexec/Makefile @@ -12,7 +12,7 @@ include ../../../scripts/Makefile.arch ifeq ($(IS_64_BIT)$(ARCH_PROCESSED),1x86) TEST_PROGS += test_kexec_jump.sh -test_kexec_jump.sh: $(OUTPUT)/test_kexec_jump +TEST_GEN_PROGS := test_kexec_jump endif include ../lib.mk -- 2.43.0

2 months, 2 weeks

3
2
0 0

[kvm-unit-tests PATCH v3 1/2] riscv: Add RV_INSN_LEN to processor.h

by Jesse Taube

When handeling traps and faults it is offten necessary to know the size of the instruction at epc. Add RV_INSN_LEN to calculate the instruction size. Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> --- lib/riscv/asm/processor.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/riscv/asm/processor.h b/lib/riscv/asm/processor.h index 40104272..631ce226 100644 --- a/lib/riscv/asm/processor.h +++ b/lib/riscv/asm/processor.h @@ -7,6 +7,8 @@ #define EXCEPTION_CAUSE_MAX 24 #define INTERRUPT_CAUSE_MAX 16 +#define RV_INSN_LEN(insn) ((((insn) & 0x3) < 0x3) ? 2 : 4) + typedef void (*exception_fn)(struct pt_regs *); struct thread_info { -- 2.43.0

2 months, 2 weeks

2
4
0 0

[kvm-unit-tests PATCH v2] riscv: Allow SBI_CONSOLE with no uart in device tree

by Jesse Taube

When CONFIG_SBI_CONSOLE is enabled and there is no uart defined in the device tree kvm-unit-tests fails to start. Only abort when uart is not found in device tree if SBI_CONSOLE is false Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> --- lib/riscv/io.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/lib/riscv/io.c b/lib/riscv/io.c index fb40adb7..e64e9253 100644 --- a/lib/riscv/io.c +++ b/lib/riscv/io.c @@ -30,7 +30,6 @@ static u32 uart0_reg_width = 1; static u32 uart0_reg_shift; static struct spinlock uart_lock; -#ifndef CONFIG_SBI_CONSOLE static u32 uart0_read(u32 num) { u32 offset = num << uart0_reg_shift; @@ -54,7 +53,6 @@ static void uart0_write(u32 num, u32 val) else writel(val, uart0_base + offset); } -#endif static void uart0_init_fdt(void) { @@ -73,11 +71,16 @@ static void uart0_init_fdt(void) break; } +#ifdef CONFIG_SBI_CONSOLE + uart0_base = NULL; + return; +#else if (ret) { printf("%s: Compatible uart not found in the device tree, aborting...\n", __func__); abort(); } +#endif } else { const fdt32_t *val; int len; @@ -116,8 +119,8 @@ void io_init(void) } } -#ifdef CONFIG_SBI_CONSOLE -void puts(const char *s) +void sbi_puts(const char *s); +void sbi_puts(const char *s) { phys_addr_t addr = virt_to_phys((void *)s); unsigned long hi = upper_32_bits(addr); @@ -127,9 +130,11 @@ void puts(const char *s) sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE, strlen(s), lo, hi, 0, 0, 0); spin_unlock(&uart_lock); } -#else -void puts(const char *s) + +void uart0_puts(const char *s); +void uart0_puts(const char *s) { + assert(uart0_base); spin_lock(&uart_lock); while (*s) { while (!(uart0_read(UART_LSR_OFFSET) & UART_LSR_THRE)) @@ -138,7 +143,15 @@ void puts(const char *s) } spin_unlock(&uart_lock); } + +void puts(const char *s) +{ +#ifdef CONFIG_SBI_CONSOLE + sbi_puts(s); +#else + uart0_puts(s); #endif +} /* * Defining halt to take 'code' as an argument guarantees that it will -- 2.43.0

2 months, 2 weeks

2
2
0 0

[kvm-unit-tests PATCH v2] riscv: lib: sbi_shutdown add pass/fail exit code.

by Jesse Taube

When exiting it may be useful for the sbi implementation to know if kvm-unit-tests passed or failed. Add exit code to sbi_shutdown, and use it in exit() to pass success/failure (0/1) to sbi. Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> --- lib/riscv/asm/sbi.h | 2 +- lib/riscv/io.c | 2 +- lib/riscv/sbi.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/lib/riscv/asm/sbi.h b/lib/riscv/asm/sbi.h index a5738a5c..de11c109 100644 --- a/lib/riscv/asm/sbi.h +++ b/lib/riscv/asm/sbi.h @@ -250,7 +250,7 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, unsigned long arg3, unsigned long arg4, unsigned long arg5); -void sbi_shutdown(void); +void sbi_shutdown(unsigned int code); struct sbiret sbi_hart_start(unsigned long hartid, unsigned long entry, unsigned long sp); struct sbiret sbi_hart_stop(void); struct sbiret sbi_hart_get_status(unsigned long hartid); diff --git a/lib/riscv/io.c b/lib/riscv/io.c index fb40adb7..0bde25d4 100644 --- a/lib/riscv/io.c +++ b/lib/riscv/io.c @@ -150,7 +150,7 @@ void halt(int code); void exit(int code) { printf("\nEXIT: STATUS=%d\n", ((code) << 1) | 1); - sbi_shutdown(); + sbi_shutdown(!!code); halt(code); __builtin_unreachable(); } diff --git a/lib/riscv/sbi.c b/lib/riscv/sbi.c index 2959378f..9dd11e9d 100644 --- a/lib/riscv/sbi.c +++ b/lib/riscv/sbi.c @@ -107,9 +107,9 @@ struct sbiret sbi_sse_inject(unsigned long event_id, unsigned long hart_id) return sbi_ecall(SBI_EXT_SSE, SBI_EXT_SSE_INJECT, event_id, hart_id, 0, 0, 0, 0); } -void sbi_shutdown(void) +void sbi_shutdown(unsigned int code) { - sbi_ecall(SBI_EXT_SRST, 0, 0, 0, 0, 0, 0, 0); + sbi_ecall(SBI_EXT_SRST, 0, 0, code, 0, 0, 0, 0); puts("SBI shutdown failed!\n"); } -- 2.43.0

2 months, 2 weeks

2
4
0 0

[kvm-unit-tests PATCH v8] riscv: sbi: Add SBI Debug Triggers Extension tests

by Jesse Taube

Add tests for the DBTR SBI extension. Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> Reviewed-by: Charlie Jenkins <charlie(a)rivosinc.com> Tested-by: Charlie Jenkins <charlie(a)rivosinc.com> --- V1 -> V2: - Call report_prefix_pop before returning - Disable compressed instructions in exec_call, update related comment - Remove extra "| 1" in dbtr_test_load - Remove extra newlines - Remove extra tabs in check_exec - Remove typedefs from enums - Return when dbtr_install_trigger fails - s/avalible/available/g - s/unistall/uninstall/g V2 -> V3: - Change SBI_DBTR_SHMEM_INVALID_ADDR to -1UL - Move all dbtr functions to sbi-dbtr.c - Move INSN_LEN to processor.h - Update include list - Use C-style comments V3 -> V4: - Include libcflat.h - Remove #define SBI_DBTR_SHMEM_INVALID_ADDR V4 -> V5: - Sort includes - Add kfail for update triggers V5 -> V6: - Add assert in gen_tdata1 - Add prefix to dbtr_test_type - Add TRIG_STATE_DMODE - Add TRIG_STATE_RESERVED - Align function paramaters with opening parenthesis - Change OpenSBI < v1.7 to < v1.5 - Constantly use spaces in prefix rather than _ - Export split_phys_addr - Fix MCONTROL_U and MCONTROL_M mix up - Fix swapped VU and VS - Move /* to own line - Print type in dbtr_test_type - Remove _BIT suffix from macros - Remove duplicate MODE_S - Remove spaces before include - Rename tdata1,2 to trigger and control in dbtr_install_trigger - Report skip in dbtr_test_multiple - Report variables in info not pass or fail - s/save/store/g - sbi_debug_set_shmem use split_phys_addr - Use if (!report(... in dbtr_test_disable_enable V6 -> V7: - Alphabetize Makefile - Only print read info on failure - Remove return after assert - Remove unnecessary OpenSBI version check - Rename error to exit_test in check_dbtr - Use prefix in dbtr_test_num_triggers and dbtr_test_type V7 -> V8: - Add mcontrol_size mcontrol6_size - Cast McontrolType to int for assert - Set trigger size to 32BIT using mcontrol_size Debug triggers allow traps on different access sizes, which was set to any. QEMU was triggering on a 32BIT access next to the trigger address causing an erroneous trap. Set the size to 32BITs to avoid this. --- lib/riscv/asm/sbi.h | 1 + riscv/Makefile | 1 + riscv/sbi-dbtr.c | 867 ++++++++++++++++++++++++++++++++++++++++++++ riscv/sbi-tests.h | 2 + riscv/sbi.c | 3 +- 5 files changed, 873 insertions(+), 1 deletion(-) create mode 100644 riscv/sbi-dbtr.c diff --git a/lib/riscv/asm/sbi.h b/lib/riscv/asm/sbi.h index a5738a5c..78fd6e2a 100644 --- a/lib/riscv/asm/sbi.h +++ b/lib/riscv/asm/sbi.h @@ -51,6 +51,7 @@ enum sbi_ext_id { SBI_EXT_SUSP = 0x53555350, SBI_EXT_FWFT = 0x46574654, SBI_EXT_SSE = 0x535345, + SBI_EXT_DBTR = 0x44425452, }; enum sbi_ext_base_fid { diff --git a/riscv/Makefile b/riscv/Makefile index 11e68eae..9309ac12 100644 --- a/riscv/Makefile +++ b/riscv/Makefile @@ -18,6 +18,7 @@ tests += $(TEST_DIR)/sieve.$(exe) all: $(tests) $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-asm.o +$(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-dbtr.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-fwft.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-sse.o diff --git a/riscv/sbi-dbtr.c b/riscv/sbi-dbtr.c new file mode 100644 index 00000000..13f64015 --- /dev/null +++ b/riscv/sbi-dbtr.c @@ -0,0 +1,867 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SBI DBTR testsuite + * + * Copyright (C) 2025, Rivos Inc., Jesse Taube <jesse(a)rivosinc.com> + */ + +#include <libcflat.h> +#include <bitops.h> + +#include <asm/io.h> +#include <asm/processor.h> + +#include "sbi-tests.h" + +#define RV_MAX_TRIGGERS 32 + +#define SBI_DBTR_TRIG_STATE_MAPPED BIT(0) +#define SBI_DBTR_TRIG_STATE_U BIT(1) +#define SBI_DBTR_TRIG_STATE_S BIT(2) +#define SBI_DBTR_TRIG_STATE_VU BIT(3) +#define SBI_DBTR_TRIG_STATE_VS BIT(4) +#define SBI_DBTR_TRIG_STATE_HAVE_HW_TRIG BIT(5) +#define SBI_DBTR_TRIG_STATE_RESERVED GENMASK(7, 6) + +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT 8 +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX(trig_state) (trig_state >> SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT) + +#define SBI_DBTR_TDATA1_TYPE_SHIFT (__riscv_xlen - 4) +#define SBI_DBTR_TDATA1_DMODE BIT_UL(__riscv_xlen - 5) + +#define SBI_DBTR_TDATA1_MCONTROL6_LOAD BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL6_STORE BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL6_EXECUTE BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL6_U BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL6_S BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL6_M BIT(6) +#define SBI_DBTR_TDATA1_MCONTROL6_SIZE_SHIFT 16 +#define SBI_DBTR_TDATA1_MCONTROL6_SIZE_MASK 0x7 +#define SBI_DBTR_TDATA1_MCONTROL6_SELECT BIT(21) +#define SBI_DBTR_TDATA1_MCONTROL6_VU BIT(23) +#define SBI_DBTR_TDATA1_MCONTROL6_VS BIT(24) + +#define SBI_DBTR_TDATA1_MCONTROL_LOAD BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL_STORE BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL_EXECUTE BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL_U BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL_S BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL_M BIT(6) +#define SBI_DBTR_TDATA1_MCONTROL_SIZELO_SHIFT 16 +#define SBI_DBTR_TDATA1_MCONTROL_SIZELO_MASK 0x3 +#define SBI_DBTR_TDATA1_MCONTROL_SELECT BIT(19) +#define SBI_DBTR_TDATA1_MCONTROL_SIZEHI_SHIFT 21 +#define SBI_DBTR_TDATA1_MCONTROL_SIZEHI_MASK 0x3 + +enum McontrolType { + SBI_DBTR_TDATA1_TYPE_NONE = (0UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_LEGACY = (1UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL = (2UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ICOUNT = (3UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ITRIGGER = (4UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ETRIGGER = (5UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL6 = (6UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_TMEXTTRIGGER = (7UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED0 = (8UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED1 = (9UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED2 = (10UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED3 = (11UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM0 = (12UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM1 = (13UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM2 = (14UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_DISABLED = (15UL << SBI_DBTR_TDATA1_TYPE_SHIFT), +}; + +enum Tdata1Size { + SIZE_ANY = 0, + SIZE_8BIT, + SIZE_16BIT, + SIZE_32BIT, + SIZE_48BIT, + SIZE_64BIT, +}; + +enum Tdata1Value { + VALUE_NONE = 0, + VALUE_LOAD = BIT(0), + VALUE_STORE = BIT(1), + VALUE_EXECUTE = BIT(2), +}; + +enum Tdata1Mode { + MODE_NONE = 0, + MODE_M = BIT(0), + MODE_U = BIT(1), + MODE_S = BIT(2), + MODE_VU = BIT(3), + MODE_VS = BIT(4), +}; + +enum sbi_ext_dbtr_fid { + SBI_EXT_DBTR_NUM_TRIGGERS = 0, + SBI_EXT_DBTR_SETUP_SHMEM, + SBI_EXT_DBTR_TRIGGER_READ, + SBI_EXT_DBTR_TRIGGER_INSTALL, + SBI_EXT_DBTR_TRIGGER_UPDATE, + SBI_EXT_DBTR_TRIGGER_UNINSTALL, + SBI_EXT_DBTR_TRIGGER_ENABLE, + SBI_EXT_DBTR_TRIGGER_DISABLE, +}; + +struct sbi_dbtr_data_msg { + unsigned long tstate; + unsigned long tdata1; + unsigned long tdata2; + unsigned long tdata3; +}; + +struct sbi_dbtr_id_msg { + unsigned long idx; +}; + +/* SBI shared mem messages layout */ +struct sbi_dbtr_shmem_entry { + union { + struct sbi_dbtr_data_msg data; + struct sbi_dbtr_id_msg id; + }; +}; + +static bool dbtr_handled; + +/* Expected to be leaf function as not to disrupt frame-pointer */ +static __attribute__((naked)) void exec_call(void) +{ + /* skip over nop when triggered instead of ret. */ + asm volatile (".option push\n" + ".option arch, -c\n" + "nop\n" + "ret\n" + ".option pop\n"); +} + +static void dbtr_exception_handler(struct pt_regs *regs) +{ + dbtr_handled = true; + + /* Reading *epc may cause a fault, skip over nop */ + if ((void *)regs->epc == exec_call) { + regs->epc += 4; + return; + } + + /* WARNING: Skips over the trapped intruction */ + regs->epc += RV_INSN_LEN(readw((void *)regs->epc)); +} + +static bool do_store(void *tdata2) +{ + bool ret; + + writel(0, tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_load(void *tdata2) +{ + bool ret; + + readl(tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_exec(void) +{ + bool ret; + + exec_call(); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static unsigned long mcontrol_size(enum Tdata1Size mode) +{ + unsigned long ret = 0; + + ret |= ((mode >> 2) & SBI_DBTR_TDATA1_MCONTROL_SIZEHI_MASK) + << SBI_DBTR_TDATA1_MCONTROL_SIZEHI_SHIFT; + ret |= (mode & SBI_DBTR_TDATA1_MCONTROL_SIZELO_MASK) + << SBI_DBTR_TDATA1_MCONTROL_SIZELO_SHIFT; + + return ret; +} + +static unsigned long mcontrol6_size(enum Tdata1Size mode) +{ + return (mode & SBI_DBTR_TDATA1_MCONTROL6_SIZE_MASK) + << SBI_DBTR_TDATA1_MCONTROL6_SIZE_SHIFT; +} + +static unsigned long gen_tdata1_mcontrol(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_LOAD; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_STORE; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_EXECUTE; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_M; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_U; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_S; + + return tdata1; +} + +static unsigned long gen_tdata1_mcontrol6(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_LOAD; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_STORE; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_EXECUTE; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_M; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_U; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_S; + + if (mode & MODE_VU) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VU; + + if (mode & MODE_VS) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VS; + + return tdata1; +} + +static unsigned long gen_tdata1(enum McontrolType type, enum Tdata1Value value, enum Tdata1Mode mode) +{ + switch (type) { + case SBI_DBTR_TDATA1_TYPE_MCONTROL: + return gen_tdata1_mcontrol(mode, value) | mcontrol_size(SIZE_32BIT); + case SBI_DBTR_TDATA1_TYPE_MCONTROL6: + return gen_tdata1_mcontrol6(mode, value) | mcontrol6_size(SIZE_32BIT); + default: + assert_msg(false, "Invalid mcontrol type: %u", (int)type); + } +} + +static struct sbiret sbi_debug_num_triggers(unsigned long trig_tdata1) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_NUM_TRIGGERS, trig_tdata1, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_set_shmem_raw(unsigned long shmem_phys_lo, + unsigned long shmem_phys_hi, + unsigned long flags) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_SETUP_SHMEM, shmem_phys_lo, + shmem_phys_hi, flags, 0, 0, 0); +} + +static struct sbiret sbi_debug_set_shmem(void *shmem) +{ + unsigned long base_addr_lo, base_addr_hi; + + split_phys_addr(virt_to_phys(shmem), &base_addr_hi, &base_addr_lo); + return sbi_debug_set_shmem_raw(base_addr_lo, base_addr_hi, 0); +} + +static struct sbiret sbi_debug_read_triggers(unsigned long trig_idx_base, + unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_READ, trig_idx_base, + trig_count, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_install_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_INSTALL, trig_count, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_update_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UPDATE, trig_count, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_uninstall_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UNINSTALL, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_enable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_ENABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_disable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_DISABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static bool dbtr_install_trigger(struct sbi_dbtr_shmem_entry *shmem, void *trigger, + unsigned long control) +{ + struct sbiret sbi_ret; + bool ret; + + shmem->data.tdata1 = control; + shmem->data.tdata2 = (unsigned long)trigger; + + sbi_ret = sbi_debug_install_triggers(1); + ret = sbiret_report_error(&sbi_ret, SBI_SUCCESS, "sbi_debug_install_triggers"); + if (ret) + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + return ret; +} + +static bool dbtr_uninstall_trigger(void) +{ + struct sbiret ret; + + install_exception_handler(EXC_BREAKPOINT, NULL); + + ret = sbi_debug_uninstall_triggers(0, 1); + return sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static unsigned long dbtr_test_num_triggers(void) +{ + struct sbiret ret; + unsigned long tdata1 = 0; + /* sbi_debug_num_triggers will return trig_max in sbiret.value when trig_tdata1 == 0 */ + + report_prefix_push("available triggers"); + + /* should be at least one trigger. */ + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_num_triggers"); + + if (ret.value == 0) { + report_fail("Returned 0 triggers available"); + } else { + report_pass("Returned triggers available"); + report_info("Returned %lu triggers available", ret.value); + } + + report_prefix_pop(); + return ret.value; +} + +static enum McontrolType dbtr_test_type(unsigned long *num_trig) +{ + struct sbiret ret; + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + report_prefix_push("test type"); + report_prefix_push("sbi_debug_num_triggers"); + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "mcontrol6"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("Returned mcontrol6 triggers available"); + report_info("Returned %lu mcontrol6 triggers available", + ret.value); + report_prefix_popn(2); + return tdata1; + } + + tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "mcontrol"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("Returned mcontrol triggers available"); + report_info("Returned %lu mcontrol triggers available", + ret.value); + report_prefix_popn(2); + return tdata1; + } + + report_fail("Returned 0 mcontrol(6) triggers available"); + report_prefix_popn(2); + + return SBI_DBTR_TDATA1_TYPE_NONE; +} + +static struct sbiret dbtr_test_store_install_uninstall(struct sbi_dbtr_shmem_entry *shmem, + enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("store trigger"); + + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_install_triggers(1); + if (!sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_install_triggers")) { + report_prefix_pop(); + return ret; + } + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(do_store(&test), "triggered"); + + if (do_load(&test)) + report_fail("triggered by load"); + + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_store(&test)) + report_fail("triggered after uninstall"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); + + return ret; +} + +static void dbtr_test_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + bool kfail; + + report_prefix_push("update trigger"); + + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_update_triggers(1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_update_triggers"); + + /* + * Known broken update_triggers. + * https://lore.kernel.org/opensbi/aDdp1UeUh7GugeHp@ghost/T/#t + */ + kfail = __sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 7); + report_kfail(kfail, do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_load(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("load trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_LOAD, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "triggered"); + + if (do_store(&test)) + report_fail("triggered by store"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + if (!report(!do_store(&test), "should not trigger")) { + dbtr_uninstall_trigger(); + report_prefix_pop(); + report_skip("enable trigger: no disable"); + + return; + } + + report_prefix_pop(); + report_prefix_push("enable trigger"); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + report(do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_exec(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("exec trigger"); + /* check if loads and stores trigger exec */ + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + + if (do_load(&test)) + report_fail("triggered by load"); + + if (do_store(&test)) + report_fail("triggered by store"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + report(do_exec(), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("read trigger"); + if (!dbtr_install_trigger(shmem, &test, tdata1)) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + if (!report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx", tdata1)) + report_info("tdata1 found: 0x%016lx", shmem->data.tdata1); + if (!report(shmem->data.tdata2 == ((unsigned long)&test), "tdata2 expected: 0x%016lx", + (unsigned long)&test)) + report_info("tdata2 found: 0x%016lx", shmem->data.tdata2); + if (!report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx", tstatus_expected)) + report_info("tstate found: 0x%016lx", shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void check_exec(unsigned long base) +{ + struct sbiret ret; + + report(do_exec(), "exec triggered"); + + ret = sbi_debug_uninstall_triggers(base, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static void dbtr_test_multiple(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type, + unsigned long num_trigs) +{ + static unsigned long test[2]; + struct sbiret ret; + bool have_three = num_trigs > 2; + + if (num_trigs < 2) { + report_skip("test multiple"); + return; + } + + report_prefix_push("test multiple"); + + if (!dbtr_install_trigger(shmem, &test[0], gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + if (!dbtr_install_trigger(shmem, &test[1], gen_tdata1(type, VALUE_LOAD, MODE_S))) + goto error; + if (have_three && + !dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + goto error; + } + + report(do_store(&test[0]), "store triggered"); + + if (do_load(&test[0])) + report_fail("store triggered by load"); + + report(do_load(&test[1]), "load triggered"); + + if (do_store(&test[1])) + report_fail("load triggered by store"); + + if (have_three) + check_exec(2); + + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_load(&test[1])) + report_fail("load triggered after uninstall"); + + report(do_store(&test[0]), "store triggered"); + + if (!have_three && + dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) + check_exec(1); + +error: + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_multiple_types(struct sbi_dbtr_shmem_entry *shmem, unsigned long type) +{ + static unsigned long test; + + report_prefix_push("test multiple types"); + + /* check if loads and stores trigger exec */ + if (!dbtr_install_trigger(shmem, &test, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "load triggered"); + + report(do_store(&test), "store triggered"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_exec(), "exec triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_uninstall(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable uninstall"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + dbtr_uninstall_trigger(); + + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("uninstall enable"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + dbtr_uninstall_trigger(); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_store(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + bool kfail; + + report_prefix_push("uninstall update"); + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + dbtr_uninstall_trigger(); + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + /* + * Known broken update_triggers. + * https://lore.kernel.org/opensbi/aDdp1UeUh7GugeHp@ghost/T/#t + */ + kfail = __sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 7); + ret = sbi_debug_update_triggers(1); + sbiret_kfail_error(kfail, &ret, SBI_ERR_FAILURE, "sbi_debug_update_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_store(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_disable_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_NONE); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable read"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + if (!report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx", tdata1)) + report_info("tdata1 found: 0x%016lx", shmem->data.tdata1); + if (!report(shmem->data.tdata2 == ((unsigned long)&test), "tdata2 expected: 0x%016lx", + (unsigned long)&test)) + report_info("tdata2 found: 0x%016lx", shmem->data.tdata2); + if (!report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx", tstatus_expected)) + report_info("tstate found: 0x%016lx", shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +void check_dbtr(void) +{ + static struct sbi_dbtr_shmem_entry shmem[RV_MAX_TRIGGERS] = {}; + unsigned long num_trigs; + enum McontrolType trig_type; + struct sbiret ret; + + report_prefix_push("dbtr"); + + if (!sbi_probe(SBI_EXT_DBTR)) { + report_skip("extension not available"); + goto exit_test; + } + + num_trigs = dbtr_test_num_triggers(); + if (!num_trigs) + goto exit_test; + + trig_type = dbtr_test_type(&num_trigs); + if (trig_type == SBI_DBTR_TDATA1_TYPE_NONE) + goto exit_test; + + ret = sbi_debug_set_shmem(shmem); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_set_shmem"); + + ret = dbtr_test_store_install_uninstall(&shmem[0], trig_type); + /* install or uninstall failed */ + if (ret.error != SBI_SUCCESS) + goto exit_test; + + dbtr_test_load(&shmem[0], trig_type); + dbtr_test_exec(&shmem[0], trig_type); + dbtr_test_read(&shmem[0], trig_type); + dbtr_test_disable_enable(&shmem[0], trig_type); + dbtr_test_update(&shmem[0], trig_type); + dbtr_test_multiple_types(&shmem[0], trig_type); + dbtr_test_multiple(shmem, trig_type, num_trigs); + dbtr_test_disable_uninstall(&shmem[0], trig_type); + dbtr_test_uninstall_enable(&shmem[0], trig_type); + dbtr_test_uninstall_update(&shmem[0], trig_type); + dbtr_test_disable_read(&shmem[0], trig_type); + +exit_test: + report_prefix_pop(); +} diff --git a/riscv/sbi-tests.h b/riscv/sbi-tests.h index d5c4ae70..c1ebf016 100644 --- a/riscv/sbi-tests.h +++ b/riscv/sbi-tests.h @@ -97,8 +97,10 @@ static inline bool env_enabled(const char *env) return s && (*s == '1' || *s == 'y' || *s == 'Y'); } +void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo); void sbi_bad_fid(int ext); void check_sse(void); +void check_dbtr(void); #endif /* __ASSEMBLER__ */ #endif /* _RISCV_SBI_TESTS_H_ */ diff --git a/riscv/sbi.c b/riscv/sbi.c index edb1a6be..3b8aadce 100644 --- a/riscv/sbi.c +++ b/riscv/sbi.c @@ -105,7 +105,7 @@ static int rand_online_cpu(prng_state *ps) return cpu; } -static void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo) +void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo) { *lo = (unsigned long)paddr; *hi = 0; @@ -1561,6 +1561,7 @@ int main(int argc, char **argv) check_susp(); check_sse(); check_fwft(); + check_dbtr(); return report_summary(); } -- 2.43.0

2 months, 2 weeks

2
2
0 0

[PATCH] selftests/mm: pagemap_scan ioctl: add PFN ZERO test cases

by Muhammad Usama Anjum

Add test cases to test the correctness of PFN ZERO flag of pagemap_scan ioctl. Test with normal pages backed memory and huge pages backed memory. Cc: David Hildenbrand <david(a)redhat.com> Signed-off-by: Muhammad Usama Anjum <usama.anjum(a)collabora.com> --- The bug has been fixed [1]. [1] https://lore.kernel.org/all/20250617143532.2375383-1-david@redhat.com --- tools/testing/selftests/mm/pagemap_ioctl.c | 57 +++++++++++++++++++++- 1 file changed, 56 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 57b4bba2b45f3..6138de0087edf 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 + #define _GNU_SOURCE #include <stdio.h> #include <fcntl.h> @@ -1480,6 +1481,57 @@ static void transact_test(int page_size) extra_thread_faults); } +void zeropfn_tests(void) +{ + unsigned long long mem_size; + struct page_region vec; + int i, ret; + char *mem; + + /* Test with page backed memory */ + mem_size = 10 * page_size; + mem = mmap(NULL, mem_size, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); + if (mem == MAP_FAILED) + ksft_exit_fail_msg("error nomem\n"); + + /* Touch each page to ensure it's mapped */ + for (i = 0; i < mem_size; i += page_size) + (void)((volatile char *)mem)[i]; + + ret = pagemap_ioctl(mem, mem_size, &vec, 1, 0, + (mem_size / page_size), PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO); + if (ret < 0) + ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + + ksft_test_result(ret == 1 && LEN(vec) == (mem_size / page_size), + "%s all pages must have PFNZERO set\n", __func__); + + munmap(mem, mem_size); + + /* Test with huge page */ + mem_size = 10 * hpage_size; + mem = memalign(hpage_size, mem_size); + if (!mem) + ksft_exit_fail_msg("error nomem\n"); + + ret = madvise(mem, mem_size, MADV_HUGEPAGE); + if (ret) + ksft_exit_fail_msg("madvise failed %d %s\n", errno, strerror(errno)); + + for (i = 0; i < mem_size; i += hpage_size) + (void)((volatile char *)mem)[i]; + + ret = pagemap_ioctl(mem, mem_size, &vec, 1, 0, + (mem_size / page_size), PAGE_IS_PFNZERO, 0, 0, PAGE_IS_PFNZERO); + if (ret < 0) + ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + + ksft_test_result(ret == 1 && LEN(vec) == (mem_size / page_size), + "%s all huge pages must have PFNZERO set\n", __func__); + + free(mem); +} + int main(int __attribute__((unused)) argc, char *argv[]) { int shmid, buf_size, fd, i, ret; @@ -1494,7 +1546,7 @@ int main(int __attribute__((unused)) argc, char *argv[]) if (init_uffd()) ksft_exit_pass(); - ksft_set_plan(115); + ksft_set_plan(117); page_size = getpagesize(); hpage_size = read_pmd_pagesize(); @@ -1669,6 +1721,9 @@ int main(int __attribute__((unused)) argc, char *argv[]) /* 16. Userfaultfd tests */ userfaultfd_tests(); + /* 17. ZEROPFN tests */ + zeropfn_tests(); + close(pagemap_fd); ksft_exit_pass(); } -- 2.43.0

2 months, 2 weeks

2
4
0 0

[PATCH v4 0/2] kunit: qemu_configs: Add MIPS configurations

by Thomas Weißschuh

Add basic support to run various MIPS variants via kunit_tool using the virtualized malta platform. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- Changes in v4: - Rebase on v6.16-rc1 - Pick up reviews from David - Clarify that GIC page is linked to vDSO - Link to v3: https://lore.kernel.org/r/20250415-kunit-mips-v3-0-4ec2461b5a7e@linutronix.… Changes in v3: - Also skip VDSO_RANDOMIZE_SIZE adjustment for kthreads - Link to v2: https://lore.kernel.org/r/20250414-kunit-mips-v2-0-4cf01e1a29e6@linutronix.… Changes in v2: - Fix usercopy kunit test by handling ABI-less tasks in stack_top() - Drop change to mm initialization. The broken test is not built by default anymore. - Link to v1: https://lore.kernel.org/r/20250212-kunit-mips-v1-0-eb49c9d76615@linutronix.… --- Thomas Weißschuh (2): MIPS: Don't crash in stack_top() for tasks without ABI or vDSO kunit: qemu_configs: Add MIPS configurations arch/mips/kernel/process.c | 16 +++++++++------- tools/testing/kunit/qemu_configs/mips.py | 18 ++++++++++++++++++ tools/testing/kunit/qemu_configs/mips64.py | 19 +++++++++++++++++++ tools/testing/kunit/qemu_configs/mips64el.py | 19 +++++++++++++++++++ tools/testing/kunit/qemu_configs/mipsel.py | 18 ++++++++++++++++++ 5 files changed, 83 insertions(+), 7 deletions(-) --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20241014-kunit-mips-e4fe1c265ed7 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

2 months, 2 weeks

3
4
0 0

[PATCH v2] selftests/futex: Convert 32bit timespec struct to 64bit version for 32bit compatibility mode

by Terry Tritton

Futex_waitv can not accept old_timespec32 struct, so userspace should convert it from 32bit to 64bit before syscall in 32bit compatible mode. This fix is based off [1] Link: https://lore.kernel.org/all/20231203235117.29677-1-wegao@suse.com/ [1] Signed-off-by: Wei Gao <wegao(a)suse.com> Signed-off-by: Terry Tritton <terry.tritton(a)linaro.org> --- .../testing/selftests/futex/include/futex2test.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h index ea79662405bc..6780e51eb2d6 100644 --- a/tools/testing/selftests/futex/include/futex2test.h +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -55,6 +55,13 @@ struct futex32_numa { futex_t numa; }; +#if !defined(__LP64__) +struct timespec64 { + int64_t tv_sec; + int64_t tv_nsec; +}; +#endif + /** * futex_waitv - Wait at multiple futexes, wake on any * @waiters: Array of waiters @@ -65,7 +72,15 @@ struct futex32_numa { static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, unsigned long flags, struct timespec *timo, clockid_t clockid) { +#if !defined(__LP64__) + struct timespec64 timo64 = {0}; + + timo64.tv_sec = timo->tv_sec; + timo64.tv_nsec = timo->tv_nsec; + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, &timo64, clockid); +#else return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); +#endif } /* -- 2.39.5

2 months, 2 weeks

3
5
0 0

[PATCH net-next 0/7] netpoll: Factor out functions from netpoll_send_udp() and add ipv6 selftest

by Breno Leitao

Refactors the netpoll UDP transmit path to improve code clarity, maintainability, and protocol-layer encapsulation. Function netpoll_send_udp() has more than 100 LoC, which is hard to understand and review. After this patchset, it has only 32 LoC, which is more manageable. The series systematically moves the construction of protocol headers (UDP, IPv4, IPv6, Ethernet) out of the core `netpoll_send_udp()` function into dedicated static helpers: - `push_udp()` for UDP header setup - `push_ipv4()` and `push_ipv6()` for IP header setup - `push_eth()` for Ethernet header setup This results in a clean, layered abstraction that mirrors the protocol stack, reduces code duplication, and improves readability. Also, to make sure this is not breaking anything, add IPv6 selftest to netconsole tests, which will exercise this code. This test would also pick problems similiar to the one fixed by f599020702698 ("net: netpoll: Initialize UDP checksum field before checksumming"), which was embarrassin we didn't have a selftest catch it. Anyway, there are **no functional changes** intended in this patchset. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- Breno Leitao (7): netpoll: Improve code clarity with explicit struct size calculations netpoll: factor out UDP checksum calculation into helper netpoll: factor out IPv6 header setup into push_ipv6() helper netpoll: factor out IPv4 header setup into push_ipv4() helper netpoll: factor out UDP header setup into push_udp() helper netpoll: move Ethernet setup to push_eth() helper selftests: net: Add IPv6 support to netconsole basic tests net/core/netpoll.c | 196 +++++++++++++-------- .../selftests/drivers/net/lib/sh/lib_netcons.sh | 74 +++++++- .../testing/selftests/drivers/net/netcons_basic.sh | 52 +++--- 3 files changed, 216 insertions(+), 106 deletions(-) --- base-commit: 8efa26fcbf8a7f783fd1ce7dd2a409e9b7758df0 change-id: 20250620-netpoll_untagle_ip-e37c799a6925 Best regards, -- Breno Leitao <leitao(a)debian.org>

2 months, 2 weeks

2
9
0 0

[PATCH bpf-next v2 0/3] bpf: Fix and test aux usage after do_check_insn()

by Luis Gerhorst

Fix cur_aux()->nospec_result test after do_check_insn() referring to the to-be-analyzed (potentially unsafe) instruction, not the already-analyzed (safe) instruction. This might allow a unsafe insn to slip through on a speculative path. Create some tests from the reproducer [1]. Commit d6f1c85f2253 ("bpf: Fall back to nospec for Spectre v1") should not be in any stable kernel yet, therefore bpf-next should suffice. [1] https://lore.kernel.org/bpf/685b3c1b.050a0220.2303ee.0010.GAE@google.com/ Changes since v1: - Fix compiler error due to missed rename of prev_insn_idx in first patch - v1: https://lore.kernel.org/bpf/20250628125927.763088-1-luis.gerhorst@fau.de/ Changes since RFC: - Introduce prev_aux() as suggested by Alexei. For this, we must move the env->prev_insn_idx assignment to happen directly after do_check_insn(), for which I have created a separate commit. This patch could be simplified by using a local prev_aux variable as sugested by Eduard, but I figured one might find the new assignment-strategy easier to understand (before, prev_insn_idx and env->prev_insn_idx were out-of-sync for the latter part of the loop). Also, like this we do not have an additional prev_* variable that must be kept in-sync and the local variable's usage (old prev_insn_idx, new tmp) is much more local. If you think it would be better to not take the risk and keep the fix simple by just introducing the prev_aux variable, let me know. - Change WARN_ON_ONCE() to verifier_bug_if() as suggested by Alexei - Change assertion to check instruction is BPF_JMP[32] as suggested by Eduard - RFC: https://lore.kernel.org/bpf/8734bmoemx.fsf@fau.de/ Luis Gerhorst (3): bpf: Update env->prev_insn_idx after do_check_insn() bpf: Fix aux usage after do_check_insn() selftests/bpf: Add Spectre v4 tests kernel/bpf/verifier.c | 30 ++-- tools/testing/selftests/bpf/progs/bpf_misc.h | 4 + .../selftests/bpf/progs/verifier_unpriv.c | 149 ++++++++++++++++++ 3 files changed, 174 insertions(+), 9 deletions(-) base-commit: d69bafe6ee2b5eff6099fa26626ecc2963f0f363 -- 2.49.0

2 months, 2 weeks

2
5
0 0

[PATCH] tools/testing/selftests: add mremap() unfaulted/faulted test cases

by Lorenzo Stoakes

Assert that mremap() behaviour is as expected when moving around unfaulted VMAs immediately adjacent to faulted ones, as well as moving around faulted VMAs and placing them back immediately adjacent to the VMA from which they were moved. This also introduces a shared helper for the syscall version of mremap() so we don't encounter any issues with libc filtering parameters. Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> --- tools/testing/selftests/mm/merge.c | 599 ++++++++++++++++++++++++++- tools/testing/selftests/mm/vm_util.c | 8 + tools/testing/selftests/mm/vm_util.h | 3 + 3 files changed, 608 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index 150dd5baed2b..cc4253f47f10 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -13,6 +13,7 @@ #include <sys/wait.h> #include <linux/perf_event.h> #include "vm_util.h" +#include <linux/mman.h> FIXTURE(merge) { @@ -25,7 +26,7 @@ FIXTURE_SETUP(merge) { self->page_size = psize(); /* Carve out PROT_NONE region to map over. */ - self->carveout = mmap(NULL, 12 * self->page_size, PROT_NONE, + self->carveout = mmap(NULL, 30 * self->page_size, PROT_NONE, MAP_ANON | MAP_PRIVATE, -1, 0); ASSERT_NE(self->carveout, MAP_FAILED); /* Setup PROCMAP_QUERY interface. */ @@ -34,7 +35,7 @@ FIXTURE_SETUP(merge) FIXTURE_TEARDOWN(merge) { - ASSERT_EQ(munmap(self->carveout, 12 * self->page_size), 0); + ASSERT_EQ(munmap(self->carveout, 30 * self->page_size), 0); ASSERT_EQ(close_procmap(&self->procmap), 0); /* * Clear unconditionally, as some tests set this. It is no issue if this @@ -576,4 +577,598 @@ TEST_F(merge, ksm_merge) ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 2 * page_size); } +TEST_F(merge, mremap_unfaulted_to_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + + /* + * Map two distinct areas: + * + * |-----------| |-----------| + * | unfaulted | | unfaulted | + * |-----------| |-----------| + * ptr ptr2 + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[7 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr: + * \ + * |-----------| / |-----------| + * | faulted | \ | unfaulted | + * |-----------| / |-----------| + * ptr \ ptr2 + */ + ptr[0] = 'x'; + + /* + * Now move ptr2 adjacent to ptr: + * + * |-----------|-----------| + * | faulted | unfaulted | + * |-----------|-----------| + * ptr ptr2 + * + * It should merge: + * + * |----------------------| + * | faulted | + * |----------------------| + * ptr + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); +} + +TEST_F(merge, mremap_unfaulted_behind_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + + /* + * Map two distinct areas: + * + * |-----------| |-----------| + * | unfaulted | | unfaulted | + * |-----------| |-----------| + * ptr ptr2 + */ + ptr = mmap(&carveout[6 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[14 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr: + * \ + * |-----------| / |-----------| + * | faulted | \ | unfaulted | + * |-----------| / |-----------| + * ptr \ ptr2 + */ + ptr[0] = 'x'; + + /* + * Now move ptr2 adjacent, but behind, ptr: + * + * |-----------|-----------| + * | unfaulted | faulted | + * |-----------|-----------| + * ptr2 ptr + * + * It should merge: + * + * |----------------------| + * | faulted | + * |----------------------| + * ptr2 + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &carveout[page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr2)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr2); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr2 + 10 * page_size); +} + +TEST_F(merge, mremap_unfaulted_between_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2, *ptr3; + + /* + * Map three distinct areas: + * + * |-----------| |-----------| |-----------| + * | unfaulted | | unfaulted | | unfaulted | + * |-----------| |-----------| |-----------| + * ptr ptr2 ptr3 + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[7 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ptr3 = mmap(&carveout[14 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Offset ptr3 further away. */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 2000); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr, ptr3: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | unfaulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr \ ptr2 \ ptr3 + */ + ptr[0] = 'x'; + ptr3[0] = 'x'; + + /* + * Move ptr3 back into place, leaving a place for ptr2: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | faulted | \ | unfaulted | + * |-----------| |-----------| / |-----------| + * ptr ptr3 \ ptr2 + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[10 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + /* + * Finally, move ptr2 into place: + * + * |-----------|-----------|-----------| + * | faulted | unfaulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge, but only ptr, ptr2: + * + * |-----------------------|-----------| + * | faulted | unfaulted | + * |-----------------------|-----------| + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr3)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr3); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr3 + 5 * page_size); +} + +TEST_F(merge, mremap_unfaulted_between_faulted_unfaulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2, *ptr3; + + /* + * Map three distinct areas: + * + * |-----------| |-----------| |-----------| + * | unfaulted | | unfaulted | | unfaulted | + * |-----------| |-----------| |-----------| + * ptr ptr2 ptr3 + */ + ptr = mmap(&carveout[page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + ptr2 = mmap(&carveout[7 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + ptr3 = mmap(&carveout[14 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr3, MAP_FAILED); + + /* Offset ptr3 further away. */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 2000); + ASSERT_NE(ptr3, MAP_FAILED); + + + /* Offset ptr2 further away. */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Fault in ptr: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | unfaulted | \ | unfaulted | + * |-----------| / |-----------| / |-----------| + * ptr \ ptr2 \ ptr3 + */ + ptr[0] = 'x'; + + /* + * Move ptr3 back into place, leaving a place for ptr2: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | unfaulted | \ | unfaulted | + * |-----------| |-----------| / |-----------| + * ptr ptr3 \ ptr2 + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[10 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + /* + * Finally, move ptr2 into place: + * + * |-----------|-----------|-----------| + * | faulted | unfaulted | unfaulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); +} + +TEST_F(merge, mremap_unfaulted_between_correctly_placed_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2; + + /* + * Map one larger area: + * + * |-----------------------------------| + * | unfaulted | + * |-----------------------------------| + */ + ptr = mmap(&carveout[page_size], 15 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Fault in ptr: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr[0] = 'x'; + + /* + * Unmap middle: + * + * |-----------| |-----------| + * | faulted | | faulted | + * |-----------| |-----------| + * + * Now the faulted areas are compatible with each other (anon_vma the + * same, vma->vm_pgoff equal to virtual page offset). + */ + ASSERT_EQ(munmap(&ptr[5 * page_size], 5 * page_size), 0); + + /* + * Map a new area, ptr2: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | faulted | \ | unfaulted | + * |-----------| |-----------| / |-----------| + * ptr \ ptr2 + */ + ptr2 = mmap(&carveout[20 * page_size], 5 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Finally, move ptr2 into place: + * + * |-----------|-----------|-----------| + * | faulted | unfaulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); +} + +TEST_F(merge, mremap_correct_placed_faulted) +{ + unsigned int page_size = self->page_size; + char *carveout = self->carveout; + struct procmap_fd *procmap = &self->procmap; + char *ptr, *ptr2, *ptr3; + + /* + * Map one larger area: + * + * |-----------------------------------| + * | unfaulted | + * |-----------------------------------| + */ + ptr = mmap(&carveout[page_size], 15 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE | MAP_FIXED, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Fault in ptr: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + */ + ptr[0] = 'x'; + + /* + * Offset the final and middle 5 pages further away: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | faulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr \ ptr2 \ ptr3 + */ + ptr3 = &ptr[10 * page_size]; + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 2000); + ASSERT_NE(ptr3, MAP_FAILED); + ptr2 = &ptr[5 * page_size]; + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Move ptr2 into its correct place: + * \ + * |-----------|-----------| / |-----------| + * | faulted | faulted | \ | faulted | + * |-----------|-----------| / |-----------| + * ptr ptr2 \ ptr3 + * + * It should merge: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr \ ptr3 + */ + + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); + + /* + * Now move ptr out of place: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | faulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr2 \ ptr \ ptr3 + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr + page_size * 1000); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Now move ptr back into place: + * \ + * |-----------|-----------| / |-----------| + * | faulted | faulted | \ | faulted | + * |-----------|-----------| / |-----------| + * ptr ptr2 \ ptr3 + * + * It should merge: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr \ ptr3 + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &carveout[page_size]); + ASSERT_NE(ptr, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 10 * page_size); + + /* + * Now move ptr out of place again: + * \ \ + * |-----------| / |-----------| / |-----------| + * | faulted | \ | faulted | \ | faulted | + * |-----------| / |-----------| / |-----------| + * ptr2 \ ptr \ ptr3 + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr + page_size * 1000); + ASSERT_NE(ptr, MAP_FAILED); + + /* + * Now move ptr3 back into place: + * \ + * |-----------|-----------| / |-----------| + * | faulted | faulted | \ | faulted | + * |-----------|-----------| / |-----------| + * ptr2 ptr3 \ ptr + * + * It should merge: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr2 \ ptr + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr2[5 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr2)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr2); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr2 + 10 * page_size); + + /* + * Now move ptr back into place: + * + * |-----------|-----------------------| + * | faulted | faulted | + * |-----------|-----------------------| + * ptr ptr2 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + * ptr + */ + ptr = sys_mremap(ptr, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &carveout[page_size]); + ASSERT_NE(ptr, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); + + /* + * Now move ptr2 out of the way: + * \ + * |-----------| |-----------| / |-----------| + * | faulted | | faulted | \ | faulted | + * |-----------| |-----------| / |-----------| + * ptr ptr3 \ ptr2 + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr2 + page_size * 1000); + ASSERT_NE(ptr2, MAP_FAILED); + + /* + * Now move it back: + * + * |-----------|-----------|-----------| + * | faulted | faulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + * ptr + */ + ptr2 = sys_mremap(ptr2, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[5 * page_size]); + ASSERT_NE(ptr2, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); + + /* + * Move ptr3 out of place: + * \ + * |-----------------------| / |-----------| + * | faulted | \ | faulted | + * |-----------------------| / |-----------| + * ptr \ ptr3 + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, ptr3 + page_size * 1000); + ASSERT_NE(ptr3, MAP_FAILED); + + /* + * Now move it back: + * + * |-----------|-----------|-----------| + * | faulted | faulted | faulted | + * |-----------|-----------|-----------| + * ptr ptr2 ptr3 + * + * It should merge: + * + * |-----------------------------------| + * | faulted | + * |-----------------------------------| + * ptr + */ + ptr3 = sys_mremap(ptr3, 5 * page_size, 5 * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, &ptr[10 * page_size]); + ASSERT_NE(ptr3, MAP_FAILED); + + ASSERT_TRUE(find_vma_procmap(procmap, ptr)); + ASSERT_EQ(procmap->query.vma_start, (unsigned long)ptr); + ASSERT_EQ(procmap->query.vma_end, (unsigned long)ptr + 15 * page_size); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 5492e3f784df..1d434772fa54 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -524,3 +524,11 @@ int read_sysfs(const char *file_path, unsigned long *val) return 0; } + +void *sys_mremap(void *old_address, unsigned long old_size, + unsigned long new_size, int flags, void *new_address) +{ + return (void *)syscall(__NR_mremap, (unsigned long)old_address, + old_size, new_size, flags, + (unsigned long)new_address); +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b8136d12a0f8..797c24215b17 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -117,6 +117,9 @@ static inline void log_test_result(int result) ksft_test_result_report(result, "%s\n", test_name); } +void *sys_mremap(void *old_address, unsigned long old_size, + unsigned long new_size, int flags, void *new_address); + /* * On ppc64 this will only work with radix 2M hugepage size */ -- 2.50.0

2 months, 2 weeks

1
0
0 0

[PATCH v2 0/5] binder: Set up KUnit tests for alloc

by Tiffany Yang

Hello, binder_alloc_selftest provides a robust set of checks for the binder allocator, but it rarely runs because it must hook into a running binder process and block all other binder threads until it completes. The test itself is a good candidate for conversion to KUnit, and it can be further isolated from user processes by using a test-specific lru freelist instead of the global one. This series converts the selftest to KUnit to make it less burdensome to run and to set up a foundation for unit testing future binder_alloc changes. Thanks, Tiffany Tiffany Yang (5): binder: Fix selftest page indexing binder: Store lru freelist in binder_alloc binder: Scaffolding for binder_alloc KUnit tests binder: Convert binder_alloc selftests to KUnit binder: encapsulate individual alloc test cases drivers/android/Kconfig | 15 +- drivers/android/Makefile | 2 +- drivers/android/binder.c | 10 +- drivers/android/binder_alloc.c | 39 +- drivers/android/binder_alloc.h | 14 +- drivers/android/binder_alloc_selftest.c | 306 ----------- drivers/android/binder_internal.h | 4 + drivers/android/tests/.kunitconfig | 3 + drivers/android/tests/Makefile | 3 + drivers/android/tests/binder_alloc_kunit.c | 573 +++++++++++++++++++++ include/kunit/test.h | 12 + lib/kunit/user_alloc.c | 4 +- 12 files changed, 645 insertions(+), 340 deletions(-) delete mode 100644 drivers/android/binder_alloc_selftest.c create mode 100644 drivers/android/tests/.kunitconfig create mode 100644 drivers/android/tests/Makefile create mode 100644 drivers/android/tests/binder_alloc_kunit.c -- 2.50.0.727.gbf7dc18ff4-goog

2 months, 2 weeks

2
6
0 0

[PATCH v10 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v10 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v10 (03-Jul-2025) - Add new patch of separated header file include/net/tcp_ecn.h to include ECN and AccECN functions (Eric Dumazet <edumazet(a)google.com>) - Add comments on the AccECN helper functions in tcp_ecn.h (Eric Dumazet <edumazet(a)google.com>) - Add documentation of tcp_ecn, tcp_ecn_option, tcp_ecn_beacon in ip-sysctl.rst to the corresponding patch (Eric Dumazet <edumazet(a)google.com>) - Split wait third ACK functionality into a separated patch from AccECN negotiation patch (Eric Dumazet <edumazet(a)google.com>) - Add READ_ONCE() over every reads of sysctl for all patches in the series (Eric Dumazet <edumazet(a)google.com>) - Merge heuristics of AccECN option ceb/cep and ACE field multi-wrap into a single patch - Add a table of SACK block reduction and required AccECN field in patch #15 commit message (Eric Dumazet <edumazet(a)google.com>) v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (6): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: ecn functions in separated include file tcp: Add wait_third_ack flag for ECN negotiation in simultaneous connect tcp: accecn: AccECN option send control tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (9): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics Documentation/networking/ip-sysctl.rst | 55 +- .../networking/net_cachelines/tcp_sock.rst | 13 + include/linux/tcp.h | 33 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 87 ++- include/net/tcp_ecn.h | 647 ++++++++++++++++++ include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 29 +- net/ipv4/tcp_input.c | 371 ++++++++-- net/ipv4/tcp_ipv4.c | 8 +- net/ipv4/tcp_minisocks.c | 40 +- net/ipv4/tcp_output.c | 297 ++++++-- net/ipv6/syncookies.c | 2 + net/ipv6/tcp_ipv6.c | 1 + 16 files changed, 1428 insertions(+), 187 deletions(-) create mode 100644 include/net/tcp_ecn.h -- 2.34.1

2 months, 2 weeks

1
15
0 0

[PATCH v10 iproute2-next 0/1] DUALPI2 iproute2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find DUALPI2 iproute2 patch v10. For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best Regards, Chia-Yu --- v10 (02-Jul-2025) - Replace STEP_THRESH and STEP_PACKETS w/ STEP_THRESH_PKTS and STEP_THRESH_US of net-next patch (Jakub Kicinski <kuba(a)kernel.org>) v9 (13-Jun-2025) - Fix space issue and typos (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Change 'rtt_typical' to 'typical_rtt' in tc/q_dualpi2.c (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Add the num of enum used by DualPI2 in pkt_sched.h v8 (09-May-2025) - Update pkt_sched.h with the one in nex-next - Correct a typo in the comment within pkt_sched.h (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Update manual content in man/man8/tc-dualpi2.8 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Update tc/q_dualpi2.c to fix missing blank lines and add missing case (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) v7 (05-May-2025) - Align pkt_sched.h with the v14 version of net-next due to spec modification in tc.yaml - Reorganize dualpi2_print_opt() to match the order in tc.yaml - Remove credit-queue in PRINT_JSON v6 (26-Apr-2025) - Update JSON file output due to spec modification in tc.yaml of net-next v5 (25-Mar-2025) - Use matches() to replace current strcmp() (Stephen Hemminger <stephen(a)networkplumber.org>) - Use general parse_percent() for handling scaled percentage values (Stephen Hemminger <stephen(a)networkplumber.org>) - Add print function for JSON of dualpi2 stats (Stephen Hemminger <stephen(a)networkplumber.org>) v4 (16-Mar-2025) - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step marking. v3 (21-Feb-2025) - Add memlimit to the dualpi2 attribute, and add memory_used, max_memory_used, and memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update the manual to align with the latest implementation and clarify the queue naming and default unit - Use common "get_scaled_alpha_beta" and clean print_opt for Dualpi2 v2 (23-Oct-2024) - Rename get_float in dualpi2 to get_float_min_max in utils.c - Move get_float from iplink_can.c in utils.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Add print function for JSON of dualpi2 (Stephen Hemminger <stephen(a)networkplumber.org>) --- Chia-Yu Chang (1): tc: add dualpi2 scheduler module bash-completion/tc | 11 +- include/uapi/linux/pkt_sched.h | 68 +++++ include/utils.h | 2 + ip/iplink_can.c | 14 - lib/utils.c | 30 ++ man/man8/tc-dualpi2.8 | 249 ++++++++++++++++ tc/Makefile | 1 + tc/q_dualpi2.c | 528 +++++++++++++++++++++++++++++++++ 8 files changed, 888 insertions(+), 15 deletions(-) create mode 100644 man/man8/tc-dualpi2.8 create mode 100644 tc/q_dualpi2.c -- 2.34.1

2 months, 2 weeks

1
1
0 0

[PATCH bpf-next,v2 0/2] Clarify and Enhance XDP Rx Metadata Handling

by Song Yoong Siang

This patch set improves the documentation and selftests for XDP Rx metadata handling. The first patch clarifies the documentation around XDP metadata layout and the use of bpf_xdp_adjust_meta. The second patch enhances the BPF selftests to make XDP metadata handling more robust and portable across different NICs. Prior to this patch set, the user application retrieved the xdp_meta by calculating backward from the data pointer, while the XDP program fill in the xdp_meta by calculating backward from data_meta. This approach will cause mismatch if there is device-reserved metadata. |<---sizeof(xdp_meta)--| | | struct xdp_meta rx_desc->address ^ ^ | | +----------+----------------------+------------+------+ | headroom | custom metadata | reserved | data | +----------+----------------------+------------+------+ ^ ^ ^ | | | struct xdp_meta xdp_buff->data_meta xdp_buff->data | | |<---sizeof(xdp_meta)--| V2: - unconditionally do bpf_xdp_adjust_meta with -XDP_METADATA_SIZE (Stanislav) V1: https://lore.kernel.org/netdev/20250701042940.3272325-1-yoong.siang.song@in… Song Yoong Siang (2): doc: clarify XDP Rx metadata layout and bpf_xdp_adjust_meta usage selftests/bpf: Enhance XDP Rx Metadata Handling Documentation/networking/xdp-rx-metadata.rst | 38 +++++++++++++++++++ .../selftests/bpf/prog_tests/xdp_metadata.c | 2 +- .../selftests/bpf/progs/xdp_hw_metadata.c | 2 +- .../selftests/bpf/progs/xdp_metadata.c | 2 +- tools/testing/selftests/bpf/xdp_hw_metadata.c | 2 +- tools/testing/selftests/bpf/xdp_metadata.h | 7 ++++ 6 files changed, 49 insertions(+), 4 deletions(-) -- 2.34.1

2 months, 2 weeks

1
2
0 0

[PATCH net-next] selftests/tc-testing: Enable CONFIG_IP_SET

by Sebastian Andrzej Siewior

The config snippet specifies CONFIG_NET_EMATCH_IPSET. This option depends on CONFIG_IP_SET. Set CONFIG_IP_SET to be enabled at part for tc-testing. Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> --- tools/testing/selftests/tc-testing/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index db176fe7d0c3f..8e902f7f1a181 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -21,6 +21,7 @@ CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NET_SCHED=y +CONFIG_IP_SET=m # # Queueing/Scheduling -- 2.50.0

2 months, 2 weeks

4
3
0 0

[PATCH net-next v1 1/2] selftests: pp-bench: remove unneeded linux/version.h

by Mina Almasry

linux/version.h was used by the out-of-tree version, but not needed in the upstream one anymore. While I'm at it, sort the includes. Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202506271434.Gk0epC9H-lkp@intel.com/ Signed-off-by: Mina Almasry <almasrymina(a)google.com> --- .../selftests/net/bench/page_pool/bench_page_pool_simple.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c index f183d5e30dc6..1cd3157fb6a9 100644 --- a/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c +++ b/tools/testing/selftests/net/bench/page_pool/bench_page_pool_simple.c @@ -5,15 +5,12 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/interrupt.h> +#include <linux/limits.h> #include <linux/module.h> #include <linux/mutex.h> - -#include <linux/version.h> #include <net/page_pool/helpers.h> -#include <linux/interrupt.h> -#include <linux/limits.h> - #include "time_bench.h" static int verbose = 1; base-commit: 8efa26fcbf8a7f783fd1ce7dd2a409e9b7758df0 -- 2.50.0.727.gbf7dc18ff4-goog

2 months, 2 weeks

6
10
0 0

[PATCH v20 net-next 0/6] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the DualPI2 patch v20. This patch serise adds DualPI Improved with a Square (DualPI2) with following features: * Supports congestion controls that comply with the Prague requirements in RFC9331 (e.g. TCP-Prague) * Coupled dual-queue that separates the L4S traffic in a low latency queue (L-queue), without harming remaining traffic that is scheduled in classic queue (C-queue) due to congestion-coupling using PI2 as defined in RFC9332 * Configurable overload strategies * Use of sojourn time to reliably estimate queue delay * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into respective queues For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu --- v20 (21-Jun-2025) - Add one more commit to fix warning and style check on tdc.sh reported by shellcheck - Remove double-prefixed of "tc_tc_dualpi2_attrs" in tc-user.h (Donald Hunter <donald.hunter(a)gmail.com>) v19 (14-Jun-2025) - Fix one typo in the comment of #1 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Update commit message of #4 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Wrap long lines of Documentation/netlink/specs/tc.yaml to within 80 characters (Jakub Kicinski <kuba(a)kernel.org>) v18 (13-Jun-2025) - Add the num of enum used by DualPI2 and fix name and name-prefix of DualPI2 enum and attribute - Replace from_timer() with timer_container_of() (Pedro Tammela <pctammela(a)mojatatu.com>) v17 (25-May-2025, Resent at 11-Jun-2025) - Replace 0xffffffff with U32_MAX (Paolo Abeni <pabeni(a)redhat.com>) - Use helper function qdisc_dequeue_internal() and add new helper function skb_apply_step() (Paolo Abeni <pabeni(a)redhat.com>) - Add s64 casting when calculating the delta of the PI controller (Paolo Abeni <pabeni(a)redhat.com>) - Change the drop reason into SKB_DROP_REASON_QDISC_CONGESTED for drop_early (Paolo Abeni <pabeni(a)redhat.com>) - Modify the condition to remove the original skb when enqueuing multiple GSO segments (Paolo Abeni <pabeni(a)redhat.com>) - Add READ_ONCE() in dualpi2_dump_stat() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments, brackets, and brackets for readability (Paolo Abeni <pabeni(a)redhat.com>) v16 (16-MAy-2025) - Add qdisc_lock() to dualpi2_timer() in dualpi2_timer (Paolo Abeni <pabeni(a)redhat.com>) - Introduce convert_ns_to_usec() to convert usec to nsec without overflow in #1 (Paolo Abeni <pabeni(a)redhat.com>) - Update convert_us_tonsec() to convert nsec to usec without overflow in #2 (Paolo Abeni <pabeni(a)redhat.com>) - Add more descriptions with respect to DualPI2 in the cover ltter and add changelog in each patch (Paolo Abeni <pabeni(a)redhat.com>) v15 (09-May-2025) - Add enum of TCA_DUALPI2_ECN_MASK_CLA_ECT to remove potential leakeage in #1 (Simon Horman <horms(a)kernel.org>) - Fix one typo in comment of #2 - Update tc.yaml in #5 to aligh with the updated enum of pkt_sched.h v14 (05-May-2025) - Modify tc.yaml: (1) Replace flags with enum and remove enum-as-flags, (2) Remove credit-queue in xstats, and (3) Change attribute types (Donald Hunter <donald.hun - Add enum and fix the ordering of variables in pkt_sched.h to align with the modified tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add validators for DROP_OVERLOAD, DROP_EARLY, ECN_MASK, and SPLIT_GSO in sch_dualpi2.c (Donald Hunter <donald.hunter(a)gmail.com>) - Update dualpi2.json to align with the updated variable order in pkt_sched.h - Reorder patches (Donald Hunter <donald.hunter(a)gmail.com>) v13 (26-Apr-2025) - Use dashes in member names to follow YNL conventions in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Define enumerations separately for flags of drop-early, drop-overload, ecn-mask, credit-queue in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Change the types of split-gso and step-packets into flag in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Revert to u32/u8 types for tc-dualpi2-xstats members in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add new test cases in tc-tests/qdiscs/dualpi2.json to cover all dualpi2 parameters (Donald Hunter <donald.hunter(a)gmail.com>) - Change the type of TCA_DUALPI2_STEP_PACKETS into NLA_FLAG (Donald Hunter <donald.hunter(a)gmail.com>) v12 (22-Apr-2025) - Remove anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Replace u32/u8 with uint and s32 with int in tc spec document (Paolo Abeni <pabeni(a)redhat.com>) - Introduce get_memory_limit function to handle potential overflow when multipling limit with MTU (Paolo Abeni <pabeni(a)redhat.com>) - Double the packet length to further include packet overhead in memory_limit (Paolo Abeni <pabeni(a)redhat.com>) - Remove the check of qdisc_qlen(sch) when calling qdisc_tree_reduce_backlog (Paolo Abeni <pabeni(a)redhat.com>) v11 (15-Apr-2025) - Replace hstimer_init with hstimer_setup in sch_dualpi2.c v10 (25-Mar-2025) - Remove leftover include in include/linux/netdevice.h and anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split sch_dualpi2.c into 3 patches (and overall 5 patches): Struct definition & parsing, Dump stats & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 (16-Mar-2025) - Fix mem_usage error in previous version - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so the step threshold was applied to mark packets in the L queue only when the queue length of the L queue was greater than or equal to 2 packets. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparison of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 v8 (11-Mar-2025) - Fix warning messages in v7 v7 (07-Mar-2025) - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 (04-Mar-2025) - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 (22-Feb-2025) - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in the dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add descriptions of packet counter statistics and the reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 (22-Oct-2024) - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning. v3 (19-Oct-2024) - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Oct-2024) - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning --- Chia-Yu Chang (5): sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc selftests/tc-testing: Fix warning and style check on tdc.sh selftests/tc-testing: Add selftests for qdisc DualPI2 Documentation: netlink: specs: tc: Add DualPI2 specification Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 166 +++ include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 70 +- net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1146 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 254 ++++ tools/testing/selftests/tc-testing/tdc.sh | 6 +- 9 files changed, 1658 insertions(+), 4 deletions(-) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

2 months, 2 weeks

7
25
0 0

[PATCH][next] selftests/bpf: Fix spelling mistake "subtration" -> "subtraction"

by Colin Ian King

There are spelling mistakes in description text. Fix these. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/bpf/progs/verifier_bounds.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index e52a24e15b34..6f986ae5085e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1474,7 +1474,7 @@ __naked void sub64_full_overflow(void) } SEC("socket") -__description("64-bit subtration, partial overflow, result in unbounded reg") +__description("64-bit subtraction, partial overflow, result in unbounded reg") __success __log_level(2) __msg("3: (1f) r3 -= r2 {{.*}} R3_w=scalar()") __retval(0) @@ -1514,7 +1514,7 @@ __naked void sub32_full_overflow(void) } SEC("socket") -__description("32-bit subtration, partial overflow, result in unbounded u32 bounds") +__description("32-bit subtraction, partial overflow, result in unbounded u32 bounds") __success __log_level(2) __msg("3: (1c) w3 -= w2 {{.*}} R3_w=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))") __retval(0) -- 2.50.0

2 months, 2 weeks

2
1
0 0

[PATCH 0/5] binder: Set up KUnit tests for alloc

by Tiffany Yang

Hello, binder_alloc_selftest provides a robust set of checks for the binder allocator, but it rarely runs because it must hook into a running binder process and block all other binder threads until it completes. The test itself is a good candidate for conversion to KUnit, and it can be further isolated from user processes by using a test-specific lru freelist instead of the global one. This series converts the selftest to KUnit to make it less burdensome to run and to set up a foundation for testing future binder_alloc changes. Thanks, Tiffany Tiffany Yang (5): binder: Fix selftest page indexing binder: Store lru freelist in binder_alloc binder: Scaffolding for binder_alloc KUnit tests binder: Convert binder_alloc selftests to KUnit binder: encapsulate individual alloc test cases drivers/android/Kconfig | 15 +- drivers/android/Makefile | 2 +- drivers/android/binder.c | 10 +- drivers/android/binder_alloc.c | 39 +- drivers/android/binder_alloc.h | 14 +- drivers/android/binder_alloc_selftest.c | 306 ----------- drivers/android/binder_internal.h | 4 + drivers/android/tests/.kunitconfig | 3 + drivers/android/tests/Makefile | 3 + drivers/android/tests/binder_alloc_kunit.c | 572 +++++++++++++++++++++ include/kunit/test.h | 12 + lib/kunit/user_alloc.c | 4 +- 12 files changed, 644 insertions(+), 340 deletions(-) delete mode 100644 drivers/android/binder_alloc_selftest.c create mode 100644 drivers/android/tests/.kunitconfig create mode 100644 drivers/android/tests/Makefile create mode 100644 drivers/android/tests/binder_alloc_kunit.c -- 2.50.0.727.gbf7dc18ff4-goog

2 months, 2 weeks

3
8
0 0

[PATCH] selftests: ptrace: add set_syscall_info to .gitignore

by Moon Hee Lee

Add the set_syscall_info test binary to .gitignore to avoid tracking build artifacts in the ptrace selftests directory. Signed-off-by: Moon Hee Lee <moonhee.lee.ca(a)gmail.com> --- tools/testing/selftests/ptrace/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore index b7dde152e75a..f6be8efd57ea 100644 --- a/tools/testing/selftests/ptrace/.gitignore +++ b/tools/testing/selftests/ptrace/.gitignore @@ -3,3 +3,4 @@ get_syscall_info get_set_sud peeksiginfo vmaccess +set_syscall_info -- 2.43.0

2 months, 2 weeks

2
1
0 0

[RESEND PATCH v2] kallsyms: fix build without execinfo

by Achill Gilgenast

Some libc's like musl libc don't provide execinfo.h since it's not part of POSIX. In order to fix compilation on musl, only include execinfo.h if available (HAVE_BACKTRACE_SUPPORT) This was discovered with c104c16073b7 ("Kunit to check the longest symbol length") which starts to include linux/kallsyms.h with Alpine Linux' configs. Signed-off-by: Achill Gilgenast <fossdd(a)pwned.life> Cc: stable(a)vger.kernel.org --- tools/include/linux/kallsyms.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h index 5a37ccbec54f..f61a01dd7eb7 100644 --- a/tools/include/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr, return NULL; } +#ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #include <stdlib.h> static inline void print_ip_sym(const char *loglvl, unsigned long ip) @@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip) free(name); } +#else +static inline void print_ip_sym(const char *loglvl, unsigned long ip) {} +#endif #endif -- 2.50.0

2 months, 2 weeks

3
5
0 0

[PATCH v2 1/2] selftests: cachestat: add tests for mmap

by Suresh K C

From: Suresh K C <suresh.k.chandrappa(a)gmail.com> Add a test case to verify cachestat behavior with memory-mapped files using mmap(). This ensures that pages accessed via mmap are correctly accounted for in the page cache. Tested on x86_64 with default kernel config Signed-off-by: Suresh K C <suresh.k.chandrappa(a)gmail.com> --- .../selftests/cachestat/test_cachestat.c | 39 ++++++++++++++++--- 1 file changed, 33 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c index 632ab44737ec..b6452978dae0 100644 --- a/tools/testing/selftests/cachestat/test_cachestat.c +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -33,6 +33,11 @@ void print_cachestat(struct cachestat *cs) cs->nr_evicted, cs->nr_recently_evicted); } +enum file_type { + FILE_MMAP, + FILE_SHMEM +}; + bool write_exactly(int fd, size_t filesize) { int random_fd = open("/dev/urandom", O_RDONLY); @@ -202,7 +207,7 @@ static int test_cachestat(const char *filename, bool write_random, bool create, return ret; } -bool test_cachestat_shmem(void) +bool run_cachestat_test(enum file_type type) { size_t PS = sysconf(_SC_PAGESIZE); size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */ @@ -212,27 +217,43 @@ bool test_cachestat_shmem(void) char *filename = "tmpshmcstat"; struct cachestat cs; bool ret = true; + int fd; unsigned long num_pages = compute_len / PS; - int fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + if (type == FILE_SHMEM) + fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + else + fd = open(filename, O_RDWR | O_CREAT | O_TRUNC, 0666); if (fd < 0) { - ksft_print_msg("Unable to create shmem file.\n"); + ksft_print_msg("Unable to create file.\n"); ret = false; goto out; } if (ftruncate(fd, filesize)) { - ksft_print_msg("Unable to truncate shmem file.\n"); + ksft_print_msg("Unable to truncate file.\n"); ret = false; goto close_fd; } if (!write_exactly(fd, filesize)) { - ksft_print_msg("Unable to write to shmem file.\n"); + ksft_print_msg("Unable to write to file.\n"); ret = false; goto close_fd; } + if (type == FILE_MMAP){ + char *map = mmap(NULL, filesize, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (map == MAP_FAILED) { + ksft_print_msg("mmap failed.\n"); + ret = false; + goto close_fd; + } + for (int i = 0; i < filesize; i++) { + map[i] = 'A'; + } + map[filesize - 1] = 'X'; + } syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); if (syscall_ret) { @@ -308,12 +329,18 @@ int main(void) break; } - if (test_cachestat_shmem()) + if (run_cachestat_test(FILE_SHMEM)) ksft_test_result_pass("cachestat works with a shmem file\n"); else { ksft_test_result_fail("cachestat fails with a shmem file\n"); ret = 1; } + if (run_cachestat_test(FILE_MMAP)) + ksft_test_result_pass("cachestat works with a mmap file\n"); + else { + ksft_test_result_fail("cachestat fails with a mmap file\n"); + ret = 1; + } return ret; } -- 2.43.0

2 months, 2 weeks

1
1
0 0

[PATCH v12 0/5] rust: replace kernel::str::CStr w/ core::ffi::CStr

by Tamir Duberstein

This picks up from Michal Rostecki's work[0]. Per Michal's guidance I have omitted Co-authored tags, as the end result is quite different. Link: https://lore.kernel.org/rust-for-linux/20240819153656.28807-2-vadorovsky@pr… [0] Closes: https://github.com/Rust-for-Linux/linux/issues/1075 Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v12: - Introduce `kernel::fmt::Display` to allow implementations on foreign types. - Tidy up doc comment on `str_to_cstr`. (Alice Ryhl). - Link to v11: https://lore.kernel.org/r/20250530-cstr-core-v11-0-cd9c0cbcb902@gmail.com Changes in v11: - Use `quote_spanned!` to avoid `use<'a, T>` and generally reduce manual token construction. - Add a commit to simplify `quote_spanned!`. - Drop first commit in favor of https://lore.kernel.org/rust-for-linux/20240906164448.2268368-1-paddymills@…. (Miguel Ojeda) - Correctly handle expressions such as `pr_info!("{a}", a = a = a)`. (Benno Lossin) - Avoid dealing with `}}` escapes, which is not needed. (Benno Lossin) - Revert some unnecessary changes. (Benno Lossin) - Rename `c_str_avoid_literals!` to `str_to_cstr!`. (Benno Lossin & Alice Ryhl). - Link to v10: https://lore.kernel.org/r/20250524-cstr-core-v10-0-6412a94d9d75@gmail.com Changes in v10: - Rebase on cbeaa41dfe26b72639141e87183cb23e00d4b0dd. - Implement Alice's suggestion to use a proc macro to work around orphan rules otherwise preventing `core::ffi::CStr` to be directly printed with `{}`. - Link to v9: https://lore.kernel.org/r/20250317-cstr-core-v9-0-51d6cc522f62@gmail.com Changes in v9: - Rebase on rust-next. - Restore `impl Display for BStr` which exists upstream[1]. - Link: https://doc.rust-lang.org/nightly/std/bstr/struct.ByteStr.html#impl-Display… [1] - Link to v8: https://lore.kernel.org/r/20250203-cstr-core-v8-0-cb3f26e78686@gmail.com Changes in v8: - Move `{from,as}_char_ptr` back to `CStrExt`. This reduces the diff some. - Restore `from_bytes_with_nul_unchecked_mut`, `to_cstring`. - Link to v7: https://lore.kernel.org/r/20250202-cstr-core-v7-0-da1802520438@gmail.com Changes in v7: - Rebased on mainline. - Restore functionality added in commit a321f3ad0a5d ("rust: str: add {make,to}_{upper,lower}case() to CString"). - Used `diff.algorithm patience` to improve diff readability. - Link to v6: https://lore.kernel.org/r/20250202-cstr-core-v6-0-8469cd6d29fd@gmail.com Changes in v6: - Split the work into several commits for ease of review. - Restore `{from,as}_char_ptr` to allow building on ARM (see commit message). - Add `CStrExt` to `kernel::prelude`. (Alice Ryhl) - Remove `CStrExt::from_bytes_with_nul_unchecked_mut` and restore `DerefMut for CString`. (Alice Ryhl) - Rename and hide `kernel::c_str!` to encourage use of C-String literals. - Drop implementation and invocation changes in kunit.rs. (Trevor Gross) - Drop docs on `Display` impl. (Trevor Gross) - Rewrite docs in the style of the standard library. - Restore the `test_cstr_debug` unit tests to demonstrate that the implementation has changed. Changes in v5: - Keep the `test_cstr_display*` unit tests. Changes in v4: - Provide the `CStrExt` trait with `display()` method, which returns a `CStrDisplay` wrapper with `Display` implementation. This addresses the lack of `Display` implementation for `core::ffi::CStr`. - Provide `from_bytes_with_nul_unchecked_mut()` method in `CStrExt`, which might be useful and is going to prevent manual, unsafe casts. - Fix a typo (s/preffered/prefered/). Changes in v3: - Fix the commit message. - Remove redundant braces in `use`, when only one item is imported. Changes in v2: - Do not remove `c_str` macro. While it's preferred to use C-string literals, there are two cases where `c_str` is helpful: - When working with macros, which already return a Rust string literal (e.g. `stringify!`). - When building macros, where we want to take a Rust string literal as an argument (for caller's convenience), but still use it as a C-string internally. - Use Rust literals as arguments in macros (`new_mutex`, `new_condvar`, `new_mutex`). Use the `c_str` macro to convert these literals to C-string literals. - Use `c_str` in kunit.rs for converting the output of `stringify!` to a `CStr`. - Remove `DerefMut` implementation for `CString`. --- Tamir Duberstein (5): rust: macros: reduce collections in `quote!` macro rust: support formatting of foreign types rust: replace `CStr` with `core::ffi::CStr` rust: replace `kernel::c_str!` with C-Strings rust: remove core::ffi::CStr reexport drivers/block/rnull.rs | 4 +- drivers/cpufreq/rcpufreq_dt.rs | 5 +- drivers/gpu/drm/drm_panic_qr.rs | 5 +- drivers/gpu/drm/nova/driver.rs | 10 +- drivers/gpu/nova-core/driver.rs | 6 +- drivers/gpu/nova-core/firmware.rs | 2 +- drivers/gpu/nova-core/gpu.rs | 4 +- drivers/gpu/nova-core/nova_core.rs | 2 +- drivers/net/phy/ax88796b_rust.rs | 8 +- drivers/net/phy/qt2025.rs | 6 +- rust/kernel/auxiliary.rs | 6 +- rust/kernel/block/mq.rs | 2 +- rust/kernel/clk.rs | 9 +- rust/kernel/configfs.rs | 14 +- rust/kernel/cpufreq.rs | 6 +- rust/kernel/device.rs | 9 +- rust/kernel/devres.rs | 2 +- rust/kernel/driver.rs | 4 +- rust/kernel/drm/device.rs | 4 +- rust/kernel/drm/driver.rs | 3 +- rust/kernel/drm/ioctl.rs | 2 +- rust/kernel/error.rs | 10 +- rust/kernel/faux.rs | 5 +- rust/kernel/firmware.rs | 16 +- rust/kernel/fmt.rs | 89 +++++++ rust/kernel/kunit.rs | 21 +- rust/kernel/lib.rs | 3 +- rust/kernel/miscdevice.rs | 5 +- rust/kernel/net/phy.rs | 12 +- rust/kernel/of.rs | 5 +- rust/kernel/pci.rs | 2 +- rust/kernel/platform.rs | 6 +- rust/kernel/prelude.rs | 5 +- rust/kernel/print.rs | 4 +- rust/kernel/seq_file.rs | 6 +- rust/kernel/str.rs | 444 ++++++++++------------------------ rust/kernel/sync.rs | 7 +- rust/kernel/sync/condvar.rs | 4 +- rust/kernel/sync/lock.rs | 4 +- rust/kernel/sync/lock/global.rs | 6 +- rust/kernel/sync/poll.rs | 1 + rust/kernel/workqueue.rs | 9 +- rust/macros/fmt.rs | 99 ++++++++ rust/macros/kunit.rs | 10 +- rust/macros/lib.rs | 19 ++ rust/macros/module.rs | 2 +- rust/macros/quote.rs | 111 ++++----- samples/rust/rust_configfs.rs | 9 +- samples/rust/rust_driver_auxiliary.rs | 7 +- samples/rust/rust_driver_faux.rs | 4 +- samples/rust/rust_driver_pci.rs | 4 +- samples/rust/rust_driver_platform.rs | 4 +- samples/rust/rust_misc_device.rs | 3 +- scripts/rustdoc_test_gen.rs | 6 +- 54 files changed, 540 insertions(+), 515 deletions(-) --- base-commit: e04c78d86a9699d136910cfc0bdcf01087e3267e change-id: 20250201-cstr-core-d4b9b69120cf Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

2 months, 2 weeks

5
11
0 0

[PATCH v2] selftests/mm: Add process_madvise() tests

by wang lian

This patch adds tests for the process_madvise(), focusing on verifying behavior under various conditions including valid usage and error cases. Signed-off-by: wang lian<lianux.mm(a)gmail.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: David Hildenbrand <david(a)redhat.com> --- Changelog v2: - Drop MADV_DONTNEED tests based on feedback - Focus solely on process_madvise() syscall - Improve error handling and structure - Add future-proof flag test - Style and comment cleanups tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/process_madv.c | 414 ++++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + 4 files changed, 421 insertions(+) create mode 100644 tools/testing/selftests/mm/process_madv.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 911f39d634be..a8c3be02188c 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -42,6 +42,7 @@ memfd_secret hugetlb_dio pkey_sighandler_tests_32 pkey_sighandler_tests_64 +process_madv soft-dirty split_huge_page_test ksm_tests diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 2352252f3914..725612e09582 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -86,6 +86,7 @@ TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += pfnmap +TEST_GEN_FILES += process_madv TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..73999c8e3570 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,414 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <errno.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <sched.h> +#include <sys/pidfd.h> +#include "vm_util.h" + +#include "../pidfd/pidfd.h" + +/* + * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: + * + * "If the signal occurs other than as the result of calling the abort or raise + * function, the behavior is undefined if the signal handler refers to any + * object with static storage duration other than by assigning a value to an + * object declared as volatile sig_atomic_t" + */ +static volatile sig_atomic_t signal_jump_set; +static sigjmp_buf signal_jmp_buf; + +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(volatile typeof(x) *)x) + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +FIXTURE(process_madvise) +{ + int pidfd; + int flag; +}; + +static void setup_sighandler(void) +{ + struct sigaction act = { + .sa_handler = &handle_fatal, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction"); +} + +static void teardown_sighandler(void) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + sigaction(SIGSEGV, &act, NULL); +} + +FIXTURE_SETUP(process_madvise) +{ + self->pidfd = PIDFD_SELF; + self->flag = 0; + setup_sighandler(); +}; + +FIXTURE_TEARDOWN_PARENT(process_madvise) +{ + teardown_sighandler(); +} + +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t vlen, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags); +} + +/* + * Enable our signal catcher and try to read/write the specified buffer. The + * return value indicates whether the read/write succeeds without a fatal + * signal. + */ +static bool try_access_buf(char *ptr, bool write) +{ + bool failed; + + /* Tell signal handler to jump back here on fatal signal. */ + signal_jump_set = true; + /* If a fatal signal arose, we will jump back here and failed is set. */ + failed = sigsetjmp(signal_jmp_buf, 0) != 0; + + if (!failed) { + if (write) + *ptr = 'x'; + else + FORCE_READ(ptr); + } + + signal_jump_set = false; + return !failed; +} + +/* Try and read from a buffer, return true if no fatal signal. */ +static bool try_read_buf(char *ptr) +{ + return try_access_buf(ptr, false); +} + +TEST_F(process_madvise, basic) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + const int madvise_pages = 4; + char *map; + ssize_t ret; + struct iovec vec[madvise_pages]; + + /* + * Create a single large mapping. We will pick pages from this + * mapping to advise on. This ensures we test non-contiguous iovecs. + */ + map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fill the entire region with a known pattern. */ + memset(map, 'A', pagesize * 10); + + /* + * Setup the iovec to point to 4 non-contiguous pages + * within the mapping. + */ + vec[0].iov_base = &map[0 * pagesize]; + vec[0].iov_len = pagesize; + vec[1].iov_base = &map[3 * pagesize]; + vec[1].iov_len = pagesize; + vec[2].iov_base = &map[5 * pagesize]; + vec[2].iov_len = pagesize; + vec[3].iov_base = &map[8 * pagesize]; + vec[3].iov_len = pagesize; + + ret = sys_process_madvise(PIDFD_SELF, vec, madvise_pages, MADV_DONTNEED, + 0); + if (ret == -1 && errno == EPERM) + ksft_exit_skip( + "process_madvise() unsupported or permission denied, try running as root.\n"); + else if (errno == EINVAL) + ksft_exit_skip( + "process_madvise() unsupported or parameter invalid, please check arguments.\n"); + + /* The call should succeed and report the total bytes processed. */ + ASSERT_EQ(ret, madvise_pages * pagesize); + + /* Check that advised pages are now zero. */ + for (int i = 0; i < madvise_pages; i++) { + char *advised_page = (char *)vec[i].iov_base; + + /* Access should be successful (kernel provides a new page). */ + ASSERT_TRUE(try_read_buf(advised_page)); + /* Content must be 0, not 'A'. */ + ASSERT_EQ(*advised_page, 0); + } + + /* Check that an un-advised page in between is still 'A'. */ + char *unadvised_page = &map[1 * pagesize]; + + ASSERT_TRUE(try_read_buf(unadvised_page)); + ASSERT_EQ(*unadvised_page, 'A'); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize * 10), 0); +} + +static long get_smaps_anon_huge_pages(pid_t pid, void *addr) +{ + char smaps_path[64]; + char *line = NULL; + unsigned long start, end; + long anon_huge_kb; + size_t len; + FILE *f; + bool in_vma; + + in_vma = false; + sprintf(smaps_path, "/proc/%d/smaps", pid); + f = fopen(smaps_path, "r"); + if (!f) + return -1; + + while (getline(&line, &len, f) != -1) { + /* Check if the line describes a VMA range */ + if (sscanf(line, "%lx-%lx", &start, &end) == 2) { + if ((unsigned long)addr >= start && + (unsigned long)addr < end) + in_vma = true; + else + in_vma = false; + continue; + } + + /* If we are in the correct VMA, look for the AnonHugePages field */ + if (in_vma && + sscanf(line, "AnonHugePages: %ld kB", &anon_huge_kb) == 1) + break; + } + + free(line); + fclose(f); + + return (anon_huge_kb > 0) ? (anon_huge_kb * 1024) : 0; +} + +/** + * TEST_F(process_madvise, remote_collapse) + * + * This test deterministically validates process_madvise() with MADV_COLLAPSE + * on a remote process, other advices are difficult to verify reliably. + * + * The test verifies that a memory region in a child process, initially + * backed by small pages, can be collapsed into a Transparent Huge Page by a + * request from the parent. The result is verified by parsing the child's + * /proc/<pid>/smaps file. + */ +TEST_F(process_madvise, remote_collapse) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + pid_t child_pid; + int pidfd; + long huge_page_size; + int pipe_info[2]; + ssize_t ret; + struct iovec vec; + + struct child_info { + pid_t pid; + void *map_addr; + } info; + + huge_page_size = default_huge_page_size(); + if (huge_page_size <= 0) + ksft_exit_skip("Could not determine a valid huge page size.\n"); + + ASSERT_EQ(pipe(pipe_info), 0); + + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) { + char *map; + size_t map_size = 2 * huge_page_size; + + close(pipe_info[0]); + + map = mmap(NULL, map_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fault in as small pages */ + for (size_t i = 0; i < map_size; i += pagesize) + map[i] = 'A'; + + /* Send info and pause */ + info.pid = getpid(); + info.map_addr = map; + ret = write(pipe_info[1], &info, sizeof(info)); + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[1]); + + pause(); + exit(0); + } + + close(pipe_info[1]); + + /* Receive child info */ + ret = read(pipe_info[0], &info, sizeof(info)); + if (ret <= 0) { + waitpid(child_pid, NULL, 0); + ksft_exit_skip("Failed to read child info from pipe.\n"); + } + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[0]); + child_pid = info.pid; + + pidfd = pidfd_open(child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Baseline Check from Parent's perspective */ + ASSERT_EQ(get_smaps_anon_huge_pages(child_pid, info.map_addr), 0); + + vec.iov_base = info.map_addr; + vec.iov_len = huge_page_size; + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, 0); + if (ret == -1) { + if (errno == EINVAL) + ksft_exit_skip( + "PROCESS_MADV_ADVISE is not supported.\n"); + else if (errno == EPERM) + ksft_exit_skip( + "No process_madvise() permissions, try running as root.\n"); + goto cleanup; + } + ASSERT_EQ(ret, huge_page_size); + + ASSERT_EQ(get_smaps_anon_huge_pages(child_pid, info.map_addr), + huge_page_size); + + ksft_test_result_pass( + "MADV_COLLAPSE successfully verified via smaps.\n"); + +cleanup: + /* Cleanup */ + kill(child_pid, SIGKILL); + waitpid(child_pid, NULL, 0); + if (pidfd >= 0) + close(pidfd); +} + +/* + * Test process_madvise() with various invalid pidfds to ensure correct error + * handling. This includes negative fds, non-pidfd fds, and pidfds for + * processes that no longer exist. + */ +TEST_F(process_madvise, invalid_pidfd) +{ + struct iovec vec; + pid_t child_pid; + ssize_t ret; + int pidfd; + + vec.iov_base = (void *)0x1234; + vec.iov_len = 4096; + + /* Using an invalid fd number (-1) should fail with EBADF. */ + ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a valid fd that is not a pidfd (e.g. stdin) should fail + * with EBADF. + */ + ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a pidfd for a process that has already exited should fail + * with ESRCH. + */ + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) + exit(0); + + pidfd = pidfd_open(child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Wait for the child to ensure it has terminated. */ + waitpid(child_pid, NULL, 0); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ESRCH); + close(pidfd); +} + +/* + * Test process_madvise() with an invalid flag value. Now we only support flag=0 + * future we will use it support sync so reserve this test. + */ +TEST_F(process_madvise, flag) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + unsigned int invalid_flag; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + ASSERT_NE(map, MAP_FAILED); + + vec.iov_base = map; + vec.iov_len = pagesize; + + invalid_flag = 0x80000000; + + ret = sys_process_madvise(PIDFD_SELF, &vec, 1, MADV_DONTNEED, + invalid_flag); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +TEST_HARNESS_MAIN \ No newline at end of file diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index f96d43153fc0..5c28ebcf1ea9 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -61,6 +61,8 @@ separated by spaces: ksm tests that require >=2 NUMA nodes - pkey memory protection key tests +- process_madvise + test process_madvise - soft_dirty test soft dirty page bit semantics - pagemap @@ -424,6 +426,9 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests CATEGORY="madv_guard" run_test ./guard-regions +# PROCESS_MADVISE TEST +CATEGORY="process_madv" run_test ./process_madv + # MADV_DONTNEED and PROCESS_DONTNEED tests CATEGORY="madv_dontneed" run_test ./madv_dontneed -- 2.43.0

2 months, 2 weeks

3
3
0 0

[PATCH v3 0/7] Add support for FEAT_{LS64, LS64_V} and related tests

by Yicong Yang

From: Yicong Yang <yangyicong(a)hisilicon.com> Armv8.7 introduces single-copy atomic 64-byte loads and stores instructions and its variants named under FEAT_{LS64, LS64_V}. Add support for Armv8.7 FEAT_{LS64, LS64_V}: - Add identifying and enabling in the cpufeature list - Expose the support of these features to userspace through HWCAP3 and cpuinfo - Add related hwcap test - Handle the trap of unsupported memory (normal/uncacheable) access in a VM A real scenario for this feature is that the userspace driver can make use of this to implement direct WQE (workqueue entry) - a mechanism to fill WQE directly into the hardware. Picked Marc's 2 patches form [1] for handling the LS64 trap in a VM on emulated MMIO and the introduce of KVM_EXIT_ARM_LDST64B. [1] https://lore.kernel.org/linux-arm-kernel/20240815125959.2097734-1-maz@kerne… Tested with hwcap test [*]: [*] https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-5-yangyicong@… On host: root@localhost:/tmp# dmesg | grep "All CPU(s) started" [ 0.504846] CPU: All CPU(s) started at EL2 root@localhost:/tmp# ./hwcap [...] # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 On guest: root@localhost:/# dmesg | grep "All CPU(s) started" [ 0.451482] CPU: All CPU(s) started at EL1 root@localhost:/mnt# ./hwcap [...] # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 Change since v2: - Handle the LS64 fault to userspace and allow userspace to inject LS64 fault - Reorder the patches to make KVM handling prior to feature support Link: https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-1-yangyicong@… Change since v1: - Drop the support for LS64_ACCDATA - handle the DABT of unsupported memory type after checking the memory attributes Link: https://lore.kernel.org/linux-arm-kernel/20241202135504.14252-1-yangyicong@… Marc Zyngier (2): KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B Yicong Yang (5): KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory KVM: arm/arm64: Allow user injection of unsupported exclusive/atomic DABT arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1 arm64: Add support for FEAT_{LS64, LS64_V} KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest Documentation/arch/arm64/booting.rst | 12 ++++++ Documentation/arch/arm64/elf_hwcaps.rst | 6 +++ Documentation/virt/kvm/api.rst | 43 +++++++++++++++++---- arch/arm64/include/asm/el2_setup.h | 12 +++++- arch/arm64/include/asm/esr.h | 8 ++++ arch/arm64/include/asm/hwcap.h | 2 + arch/arm64/include/asm/kvm_emulate.h | 7 ++++ arch/arm64/include/uapi/asm/hwcap.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 3 +- arch/arm64/kernel/cpufeature.c | 51 +++++++++++++++++++++++++ arch/arm64/kernel/cpuinfo.c | 2 + arch/arm64/kvm/guest.c | 4 ++ arch/arm64/kvm/inject_fault.c | 29 ++++++++++++++ arch/arm64/kvm/mmio.c | 27 ++++++++++++- arch/arm64/kvm/mmu.c | 21 +++++++++- arch/arm64/tools/cpucaps | 2 + include/uapi/linux/kvm.h | 3 +- 17 files changed, 222 insertions(+), 12 deletions(-) -- 2.24.0

2 months, 2 weeks

2
12
0 0

[RFC PATCH 0/7] platform/chrome: Add Kunit tests for protocol device drivers

by Tzung-Bi Shih

The protocol device drivers under drivers/platform/chrome/ are responsible to communicate to the ChromeOS EC (Embedded Controller). They need to pack the data in a pre-defined format and check if the EC responds accordingly. The series adds some fundamental unit tests for the protocol. It calls the .cmd_xfer() and .pkt_xfer() callbacks (which are the most crucial parts for the protocol), mocks the rest of the system, and checks if the interactions are all correct. The series isn't ready for landing. It's more like a PoC for the binary-level function redirection and its use cases. The 1st patch adds ftrace stub which is originally from [1][2]. There is no follow-up discussion about the ftrace stub. As a result, the patch is still on the mailing list. The 2nd patch adds Kunit tests for cros_ec_i2c. It relies on the ftrace stub for redirecting cros_ec_{un,}register(). The 3rd patch uses static stub instead (if ftrace stub isn't really an option). However, I'm not a big fan to change the production code (i.e. adding the prologue in cros_ec_{un,}register()) for testing. The 4th patch adds Kunit tests for cros_ec_spi. It relies on the ftrace stub for redirecting cros_ec_{un,}register() again. The 5th patch calls .probe() directly instead of forcing the driver probe needs to be synchronous. In comparison with the 4th patch, I don't think this is simpler. I'd prefer to the way in the 4th patch. After talked to Masami about the work, he suggested to use Kprobes for function redirection. The 6th patch adds kprobes stub. The 7th patch uses kprobes stub instead for cros_ec_spi. Questions: - Are we going to support ftrace stub so that tests can use it? - If ftrace stub isn't on the plate (e.g. due to too many dependencies), how about the kprobes stub? Is it something we could pursue? - (minor) I'm unsure if people would prefer 'kprobes stub' vs. 'kprobe stub'. [1]: https://kunit.dev/mocking.html#binary-level-ftrace-et-al [2]: https://lore.kernel.org/linux-kselftest/20220318021314.3225240-3-davidgow@g… Daniel Latypov (1): kunit: expose ftrace-based API for stubbing out functions during tests Tzung-Bi Shih (6): platform/chrome: kunit: cros_ec_i2c: Add tests with ftrace stub platform/chrome: kunit: cros_ec_i2c: Use static stub instead platform/chrome: kunit: cros_ec_spi: Add tests with ftrace stub platform/chrome: kunit: cros_ec_spi: Call .probe() directly kunit: Expose 'kprobes stub' API to redirect functions platform/chrome: kunit: cros_ec_spi: Use kprobes stub instead drivers/platform/chrome/Kconfig | 17 + drivers/platform/chrome/Makefile | 2 + drivers/platform/chrome/cros_ec.c | 6 + drivers/platform/chrome/cros_ec_i2c_test.c | 479 +++++++++++++++++++++ drivers/platform/chrome/cros_ec_spi_test.c | 355 +++++++++++++++ include/kunit/ftrace_stub.h | 84 ++++ include/kunit/kprobes_stub.h | 19 + kernel/trace/ftrace.c | 3 + lib/kunit/Kconfig | 18 + lib/kunit/Makefile | 8 + lib/kunit/ftrace_stub.c | 139 ++++++ lib/kunit/kprobes_stub.c | 113 +++++ lib/kunit/kunit-example-test.c | 27 +- lib/kunit/stubs_example.kunitconfig | 11 + 14 files changed, 1280 insertions(+), 1 deletion(-) create mode 100644 drivers/platform/chrome/cros_ec_i2c_test.c create mode 100644 drivers/platform/chrome/cros_ec_spi_test.c create mode 100644 include/kunit/ftrace_stub.h create mode 100644 include/kunit/kprobes_stub.h create mode 100644 lib/kunit/ftrace_stub.c create mode 100644 lib/kunit/kprobes_stub.c create mode 100644 lib/kunit/stubs_example.kunitconfig -- 2.49.0.1101.gccaa498523-goog

2 months, 2 weeks

2
11
0 0

[PATCH v5 0/7] futex: Create set_robust_list2

by André Almeida

This patch adds a new robust_list() syscall. The current syscall can't be expanded to cover the following use case, so a new one is needed. This new syscall allows users to set multiple robust lists per process and to have either 32bit or 64bit pointers in the list. * Use case FEX-Emu[1] is an application that runs x86 and x86-64 binaries on an AArch64 Linux host. One of the tasks of FEX-Emu is to translate syscalls from one platform to another. Existing set_robust_list() can't be easily translated because of two limitations: 1) x86 apps can have 32bit pointers robust lists. For a x86-64 kernel this is not a problem, because of the compat entry point. But there's no such compat entry point for AArch64, so the kernel would do the pointer arithmetic wrongly. Is also unviable to userspace to keep track every addition/removal to the robust list and keep a 64bit version of it somewhere else to feed the kernel. Thus, the new interface has an option of telling the kernel if the list is filled with 32bit or 64bit pointers. 2) Apps can set just one robust list (in theory, x86-64 can set two if they also use the compat entry point). That means that when a x86 app asks FEX-Emu to call set_robust_list(), FEX have two options: to overwrite their own robust list pointer and make the app robust, or to ignore the app robust list and keep the emulator robust. The new interface allows for multiple robust lists per application, solving this. * Interface This is the proposed interface: long set_robust_list2(void *head, int index, unsigned int flags) `head` is the head of the userspace struct robust_list_head, just as old set_robust_list(). It needs to be a void pointer since it can point to a normal robust_list_head or a compat_robust_list_head. `flags` can be used for defining the list type: enum robust_list_type { ROBUST_LIST_32BIT, ROBUST_LIST_64BIT, }; `index` is the index in the internal robust_list's linked list (the naming starts to get confusing, I reckon). If `index == -1`, that means that user wants to set a new robust_list, and the kernel will append it in the end of the list, assign a new index and return this index to the user. If `index >= 0`, that means that user wants to re-set `*head` of an already existing list (similarly to what happens when you call set_robust_list() twice with different `*head`). If `index` is out of range, or it points to a non-existing robust_list, or if the internal list is full, an error is returned. * Implementation The implementation re-uses most of the existing robust list interface as possible. The new task_struct member `struct list_head robust_list2` is just a linked list where new lists are appended as the user requests more lists, and by futex_cleanup(), the kernel walks through the internal list feeding exit_robust_list() with the robust_list's. This implementation supports up to 10 lists (defined at ROBUST_LISTS_PER_TASK), but it was an arbitrary number for this RFC. For the described use case above, 4 should be enough, I'm not sure which should be the limit. It doesn't support list removal (should it support?). It doesn't have a proper get_robust_list2() yet as well, but I can add it in a next revision. We could also have a generic robust_list() syscall that can be used to set/get and be controlled by flags. The new interface has a `unsigned int flags` argument, making it extensible for future use cases as well. It refuses unaligned `head` addresses. It doesn't have a limit for elements in a single list (like ROBUST_LIST_LIMIT), it destroys the list as it is parsed to be safe against circular lists. * Testing This patcheset has a selftest patch that expands this one: https://lore.kernel.org/lkml/20250212131123.37431-1-andrealmeid@igalia.com/ Also, FEX-Emu added support for this interface to validate it: https://github.com/FEX-Emu/FEX/pull/3966 Feedback is very welcomed! Thanks, André [1] https://github.com/FEX-Emu/FEX Changelog: - Fixed compilation issues when CONFIG_COMPAT or CONFIG_FUTEX are not set - Rebased on top of new futex work (private hash) v4: https://lore.kernel.org/lkml/20250225183531.682556-1-andrealmeid@igalia.com/ - Refuse unaligned head pointers - Ignore ROBUST_LIST_LIMIT for lists created with this interface and make it robust against circular lists - Fix a get_robust_list() syscall bug for getting the list from another thread - Adapt selftest to use the new interface v3: https://lore.kernel.org/lkml/20241217174958.477692-1-andrealmeid@igalia.com/ - Old syscall set_robust_list() adds new head to the internal linked list of robust lists pointers, instead of having a field just for them. Remove tsk->robust_list and use only tsk->robust_list2 v2: https://lore.kernel.org/lkml/20241101162147.284993-1-andrealmeid@igalia.com/ - Added a patch to properly deal with exit_robust_list() in 64bit vs 32bit - Wired-up syscall for all archs - Added more of the cover letter to the commit message v1: https://lore.kernel.org/lkml/20241024145735.162090-1-andrealmeid@igalia.com/ --- André Almeida (7): selftests/futex: Add ASSERT_ macros selftests/futex: Create test for robust list futex: Use explicit sizes for compat_exit_robust_list futex: Create set_robust_list2 futex: Remove the limit of elements for sys_set_robust_list2 lists futex: Wire up set_robust_list2 syscall selftests: futex: Expand robust list test for the new interface arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/compat.h | 12 +- include/linux/futex.h | 30 +- include/linux/sched.h | 5 +- include/uapi/asm-generic/unistd.h | 2 + include/uapi/linux/futex.h | 10 + kernel/futex/core.c | 156 ++++- kernel/futex/futex.h | 5 + kernel/futex/syscalls.c | 85 ++- kernel/sys_ni.c | 1 + scripts/syscall.tbl | 1 + .../testing/selftests/futex/functional/.gitignore | 1 + tools/testing/selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/robust_list.c | 706 +++++++++++++++++++++ tools/testing/selftests/futex/include/logging.h | 38 ++ 29 files changed, 1021 insertions(+), 49 deletions(-) --- base-commit: a24cc6ce1933eade12aa2b9859de0fcd2dac2c06 change-id: 20250225-tonyk-robust_futex-60adeedac695 Best regards, -- André Almeida <andrealmeid(a)igalia.com>

2 months, 2 weeks

3
17
0 0

[RESEND PATCH net-next 6/6] selftests: net: extend SCM_PIDFD test to cover stale pidfds

by Alexander Mikhalitsyn

Extend SCM_PIDFD test scenarios to also cover dead task's pidfd retrieval and reading its exit info. Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: Shuah Khan <shuah(a)kernel.org> Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Simon Horman <horms(a)kernel.org> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)google.com> Cc: Lennart Poettering <mzxreary(a)0pointer.de> Cc: Luca Boccassi <bluca(a)debian.org> Cc: David Rheinsberg <david(a)readahead.eu> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- .../testing/selftests/net/af_unix/scm_pidfd.c | 217 ++++++++++++++---- 1 file changed, 173 insertions(+), 44 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..37e034874034 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include <sys/wait.h> +#include "../../pidfd/pidfd.h" #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -26,6 +27,8 @@ #define SCM_PIDFD 0x04 #endif +#define CHILD_EXIT_CODE_OK 123 + static void child_die() { exit(1); @@ -126,16 +129,65 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } +struct cmsg_data { + struct ucred *ucred; + int *pidfd; +}; + +static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res) +{ + struct cmsghdr *cmsg; + int data = 0; + + if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*res->pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + res->pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*res->ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + res->ucred = (void *)CMSG_DATA(cmsg); + } + } + + if (!res->pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!res->ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + return 0; +} + static int cmsg_check(int fd) { struct msghdr msg = { 0 }; - struct cmsghdr *cmsg; + struct cmsg_data res; struct iovec iov; - struct ucred *ucred = NULL; int data = 0; char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; - int *pidfd = NULL; pid_t parent_pid; int err; @@ -158,53 +210,99 @@ static int cmsg_check(int fd) return 1; } - for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; - cmsg = CMSG_NXTHDR(&msg, cmsg)) { - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_PIDFD) { - if (cmsg->cmsg_len < sizeof(*pidfd)) { - log_err("CMSG parse: SCM_PIDFD wrong len"); - return 1; - } + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } - pidfd = (void *)CMSG_DATA(cmsg); - } + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); + return 1; + } - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_CREDENTIALS) { - if (cmsg->cmsg_len < sizeof(*ucred)) { - log_err("CMSG parse: SCM_CREDENTIALS wrong len"); - return 1; - } + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + close(*res.pidfd); + return 1; + } - ucred = (void *)CMSG_DATA(cmsg); - } + close(*res.pidfd); + return 0; +} + +static int cmsg_check_dead(int fd, int expected_pid) +{ + int err; + struct msghdr msg = { 0 }; + struct cmsg_data res; + struct iovec iov; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + pid_t client_pid; + struct pidfd_info info = { + .mask = PIDFD_INFO_EXIT, + }; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; } - /* send(pfd, "x", sizeof(char), 0) */ - if (data != 'x') { + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + /* send(cfd, "y", sizeof(char), 0) */ + if (data != 'y') { log_err("recvmsg: data corruption"); return 1; } - if (!pidfd) { - log_err("CMSG parse: SCM_PIDFD not found"); + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); return 1; } - if (!ucred) { - log_err("CMSG parse: SCM_CREDENTIALS not found"); + /* + * pidfd from SCM_PIDFD should point to the client_pid. + * Let's read exit information and check if it's what + * we expect to see. + */ + if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) { + log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__); + close(*res.pidfd); return 1; } - /* pidfd from SCM_PIDFD should point to the parent process PID */ - parent_pid = - get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); - if (parent_pid != getppid()) { - log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + if (!(info.mask & PIDFD_INFO_EXIT)) { + log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__); + close(*res.pidfd); return 1; } + err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1; + if (err != CHILD_EXIT_CODE_OK) { + log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK); + close(*res.pidfd); + return 1; + } + + close(*res.pidfd); return 0; } @@ -291,6 +389,24 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract) memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); } +static int sk_enable_cred_pass(int sk) +{ + int on = 0; + + on = 1; + if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + return 1; + } + + if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + return 1; + } + + return 0; +} + static void client(FIXTURE_DATA(scm_pidfd) *self, const FIXTURE_VARIANT(scm_pidfd) *variant) { @@ -299,7 +415,6 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, struct ucred peer_cred; int peer_pidfd; pid_t peer_pid; - int on = 0; cfd = socket(AF_UNIX, variant->type, 0); if (cfd < 0) { @@ -322,14 +437,8 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } - on = 1; - if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { - log_err("Failed to set SO_PASSCRED"); - child_die(); - } - - if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { - log_err("Failed to set SO_PASSPIDFD"); + if (sk_enable_cred_pass(cfd)) { + log_err("sk_enable_cred_pass() failed"); child_die(); } @@ -340,6 +449,12 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } + /* send something to the parent so it can receive SCM_PIDFD too and validate it */ + if (send(cfd, "y", sizeof(char), 0) == -1) { + log_err("Failed to send(cfd, \"y\", sizeof(char), 0)"); + child_die(); + } + /* skip further for SOCK_DGRAM as it's not applicable */ if (variant->type == SOCK_DGRAM) return; @@ -398,7 +513,13 @@ TEST_F(scm_pidfd, test) close(self->server); close(self->startup_pipe[0]); client(self, variant); - exit(0); + + /* + * It's a bit unusual, but in case of success we return non-zero + * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it + * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead(). + */ + exit(CHILD_EXIT_CODE_OK); } close(self->startup_pipe[1]); @@ -421,9 +542,17 @@ TEST_F(scm_pidfd, test) ASSERT_NE(-1, err); } - close(pfd); waitpid(self->client_pid, &child_status, 0); - ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + /* see comment before exit(CHILD_EXIT_CODE_OK) */ + ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + + err = sk_enable_cred_pass(pfd); + ASSERT_EQ(0, err); + + err = cmsg_check_dead(pfd, self->client_pid); + ASSERT_EQ(0, err); + + close(pfd); } TEST_HARNESS_MAIN -- 2.43.0

2 months, 2 weeks

3
2
0 0

[kvm-unit-tests PATCH v7] riscv: sbi: Add SBI Debug Triggers Extension tests

by Jesse Taube

Add tests for the DBTR SBI extension. Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> Reviewed-by: Charlie Jenkins <charlie(a)rivosinc.com> Tested-by: Charlie Jenkins <charlie(a)rivosinc.com> --- V1 -> V2: - Call report_prefix_pop before returning - Disable compressed instructions in exec_call, update related comment - Remove extra "| 1" in dbtr_test_load - Remove extra newlines - Remove extra tabs in check_exec - Remove typedefs from enums - Return when dbtr_install_trigger fails - s/avalible/available/g - s/unistall/uninstall/g V2 -> V3: - Change SBI_DBTR_SHMEM_INVALID_ADDR to -1UL - Move all dbtr functions to sbi-dbtr.c - Move INSN_LEN to processor.h - Update include list - Use C-style comments V3 -> V4: - Include libcflat.h - Remove #define SBI_DBTR_SHMEM_INVALID_ADDR V4 -> V5: - Sort includes - Add kfail for update triggers V5 -> V6: - Add assert in gen_tdata1 - Add prefix to dbtr_test_type - Add TRIG_STATE_DMODE - Add TRIG_STATE_RESERVED - Align function paramaters with opening parenthesis - Change OpenSBI < v1.7 to < v1.5 - Constantly use spaces in prefix rather than _ - Export split_phys_addr - Fix MCONTROL_U and MCONTROL_M mix up - Fix swapped VU and VS - Move /* to own line - Print type in dbtr_test_type - Remove _BIT suffix from macros - Remove duplicate MODE_S - Remove spaces before include - Rename tdata1,2 to trigger and control in dbtr_install_trigger - Report skip in dbtr_test_multiple - Report variables in info not pass or fail - s/save/store/g - sbi_debug_set_shmem use split_phys_addr - Use if (!report(... in dbtr_test_disable_enable V6 -> V7: - Alphabetize Makefile - Only print read info on failure - Remove return after assert - Remove unnecessary OpenSBI version check - Rename error to exit_test in check_dbtr - Use prefix in dbtr_test_num_triggers and dbtr_test_type --- lib/riscv/asm/sbi.h | 1 + riscv/Makefile | 1 + riscv/sbi-dbtr.c | 834 ++++++++++++++++++++++++++++++++++++++++++++ riscv/sbi-tests.h | 2 + riscv/sbi.c | 3 +- 5 files changed, 840 insertions(+), 1 deletion(-) create mode 100644 riscv/sbi-dbtr.c diff --git a/lib/riscv/asm/sbi.h b/lib/riscv/asm/sbi.h index a5738a5c..78fd6e2a 100644 --- a/lib/riscv/asm/sbi.h +++ b/lib/riscv/asm/sbi.h @@ -51,6 +51,7 @@ enum sbi_ext_id { SBI_EXT_SUSP = 0x53555350, SBI_EXT_FWFT = 0x46574654, SBI_EXT_SSE = 0x535345, + SBI_EXT_DBTR = 0x44425452, }; enum sbi_ext_base_fid { diff --git a/riscv/Makefile b/riscv/Makefile index 11e68eae..9309ac12 100644 --- a/riscv/Makefile +++ b/riscv/Makefile @@ -18,6 +18,7 @@ tests += $(TEST_DIR)/sieve.$(exe) all: $(tests) $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-asm.o +$(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-dbtr.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-fwft.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-sse.o diff --git a/riscv/sbi-dbtr.c b/riscv/sbi-dbtr.c new file mode 100644 index 00000000..71ffcd32 --- /dev/null +++ b/riscv/sbi-dbtr.c @@ -0,0 +1,834 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SBI DBTR testsuite + * + * Copyright (C) 2025, Rivos Inc., Jesse Taube <jesse(a)rivosinc.com> + */ + +#include <libcflat.h> +#include <bitops.h> + +#include <asm/io.h> +#include <asm/processor.h> + +#include "sbi-tests.h" + +#define RV_MAX_TRIGGERS 32 + +#define SBI_DBTR_TRIG_STATE_MAPPED BIT(0) +#define SBI_DBTR_TRIG_STATE_U BIT(1) +#define SBI_DBTR_TRIG_STATE_S BIT(2) +#define SBI_DBTR_TRIG_STATE_VU BIT(3) +#define SBI_DBTR_TRIG_STATE_VS BIT(4) +#define SBI_DBTR_TRIG_STATE_HAVE_HW_TRIG BIT(5) +#define SBI_DBTR_TRIG_STATE_RESERVED GENMASK(7, 6) + +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT 8 +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX(trig_state) (trig_state >> SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT) + +#define SBI_DBTR_TDATA1_TYPE_SHIFT (__riscv_xlen - 4) +#define SBI_DBTR_TDATA1_DMODE BIT_UL(__riscv_xlen - 5) + +#define SBI_DBTR_TDATA1_MCONTROL6_LOAD BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL6_STORE BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL6_EXECUTE BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL6_U BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL6_S BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL6_M BIT(6) +#define SBI_DBTR_TDATA1_MCONTROL6_SELECT BIT(21) +#define SBI_DBTR_TDATA1_MCONTROL6_VU BIT(23) +#define SBI_DBTR_TDATA1_MCONTROL6_VS BIT(24) + +#define SBI_DBTR_TDATA1_MCONTROL_LOAD BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL_STORE BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL_EXECUTE BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL_U BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL_S BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL_M BIT(6) +#define SBI_DBTR_TDATA1_MCONTROL_SELECT BIT(19) + +enum McontrolType { + SBI_DBTR_TDATA1_TYPE_NONE = (0UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_LEGACY = (1UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL = (2UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ICOUNT = (3UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ITRIGGER = (4UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ETRIGGER = (5UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL6 = (6UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_TMEXTTRIGGER = (7UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED0 = (8UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED1 = (9UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED2 = (10UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED3 = (11UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM0 = (12UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM1 = (13UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM2 = (14UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_DISABLED = (15UL << SBI_DBTR_TDATA1_TYPE_SHIFT), +}; + +enum Tdata1Value { + VALUE_NONE = 0, + VALUE_LOAD = BIT(0), + VALUE_STORE = BIT(1), + VALUE_EXECUTE = BIT(2), +}; + +enum Tdata1Mode { + MODE_NONE = 0, + MODE_M = BIT(0), + MODE_U = BIT(1), + MODE_S = BIT(2), + MODE_VU = BIT(3), + MODE_VS = BIT(4), +}; + +enum sbi_ext_dbtr_fid { + SBI_EXT_DBTR_NUM_TRIGGERS = 0, + SBI_EXT_DBTR_SETUP_SHMEM, + SBI_EXT_DBTR_TRIGGER_READ, + SBI_EXT_DBTR_TRIGGER_INSTALL, + SBI_EXT_DBTR_TRIGGER_UPDATE, + SBI_EXT_DBTR_TRIGGER_UNINSTALL, + SBI_EXT_DBTR_TRIGGER_ENABLE, + SBI_EXT_DBTR_TRIGGER_DISABLE, +}; + +struct sbi_dbtr_data_msg { + unsigned long tstate; + unsigned long tdata1; + unsigned long tdata2; + unsigned long tdata3; +}; + +struct sbi_dbtr_id_msg { + unsigned long idx; +}; + +/* SBI shared mem messages layout */ +struct sbi_dbtr_shmem_entry { + union { + struct sbi_dbtr_data_msg data; + struct sbi_dbtr_id_msg id; + }; +}; + +static bool dbtr_handled; + +/* Expected to be leaf function as not to disrupt frame-pointer */ +static __attribute__((naked)) void exec_call(void) +{ + /* skip over nop when triggered instead of ret. */ + asm volatile (".option push\n" + ".option arch, -c\n" + "nop\n" + "ret\n" + ".option pop\n"); +} + +static void dbtr_exception_handler(struct pt_regs *regs) +{ + dbtr_handled = true; + + /* Reading *epc may cause a fault, skip over nop */ + if ((void *)regs->epc == exec_call) { + regs->epc += 4; + return; + } + + /* WARNING: Skips over the trapped intruction */ + regs->epc += RV_INSN_LEN(readw((void *)regs->epc)); +} + +static bool do_store(void *tdata2) +{ + bool ret; + + writel(0, tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_load(void *tdata2) +{ + bool ret; + + readl(tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_exec(void) +{ + bool ret; + + exec_call(); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static unsigned long gen_tdata1_mcontrol(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_LOAD; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_STORE; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_EXECUTE; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_M; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_U; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_S; + + return tdata1; +} + +static unsigned long gen_tdata1_mcontrol6(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_LOAD; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_STORE; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_EXECUTE; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_M; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_U; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_S; + + if (mode & MODE_VU) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VU; + + if (mode & MODE_VS) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VS; + + return tdata1; +} + +static unsigned long gen_tdata1(enum McontrolType type, enum Tdata1Value value, enum Tdata1Mode mode) +{ + switch (type) { + case SBI_DBTR_TDATA1_TYPE_MCONTROL: + return gen_tdata1_mcontrol(mode, value); + case SBI_DBTR_TDATA1_TYPE_MCONTROL6: + return gen_tdata1_mcontrol6(mode, value); + default: + assert_msg(false, "Invalid mcontrol type: %lu", type); + } +} + +static struct sbiret sbi_debug_num_triggers(unsigned long trig_tdata1) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_NUM_TRIGGERS, trig_tdata1, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_set_shmem_raw(unsigned long shmem_phys_lo, + unsigned long shmem_phys_hi, + unsigned long flags) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_SETUP_SHMEM, shmem_phys_lo, + shmem_phys_hi, flags, 0, 0, 0); +} + +static struct sbiret sbi_debug_set_shmem(void *shmem) +{ + unsigned long base_addr_lo, base_addr_hi; + + split_phys_addr(virt_to_phys(shmem), &base_addr_hi, &base_addr_lo); + return sbi_debug_set_shmem_raw(base_addr_lo, base_addr_hi, 0); +} + +static struct sbiret sbi_debug_read_triggers(unsigned long trig_idx_base, + unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_READ, trig_idx_base, + trig_count, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_install_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_INSTALL, trig_count, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_update_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UPDATE, trig_count, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_uninstall_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UNINSTALL, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_enable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_ENABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_disable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_DISABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static bool dbtr_install_trigger(struct sbi_dbtr_shmem_entry *shmem, void *trigger, + unsigned long control) +{ + struct sbiret sbi_ret; + bool ret; + + shmem->data.tdata1 = control; + shmem->data.tdata2 = (unsigned long)trigger; + + sbi_ret = sbi_debug_install_triggers(1); + ret = sbiret_report_error(&sbi_ret, SBI_SUCCESS, "sbi_debug_install_triggers"); + if (ret) + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + return ret; +} + +static bool dbtr_uninstall_trigger(void) +{ + struct sbiret ret; + + install_exception_handler(EXC_BREAKPOINT, NULL); + + ret = sbi_debug_uninstall_triggers(0, 1); + return sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static unsigned long dbtr_test_num_triggers(void) +{ + struct sbiret ret; + unsigned long tdata1 = 0; + /* sbi_debug_num_triggers will return trig_max in sbiret.value when trig_tdata1 == 0 */ + + report_prefix_push("available triggers"); + + /* should be at least one trigger. */ + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_num_triggers"); + + if (ret.value == 0) { + report_fail("Returned 0 triggers available"); + } else { + report_pass("Returned triggers available"); + report_info("Returned %lu triggers available", ret.value); + } + + report_prefix_pop(); + return ret.value; +} + +static enum McontrolType dbtr_test_type(unsigned long *num_trig) +{ + struct sbiret ret; + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + report_prefix_push("test type"); + report_prefix_push("sbi_debug_num_triggers"); + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "mcontrol6"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("Returned mcontrol6 triggers available"); + report_info("Returned %lu mcontrol6 triggers available", + ret.value); + report_prefix_popn(2); + return tdata1; + } + + tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "mcontrol"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("Returned mcontrol triggers available"); + report_info("Returned %lu mcontrol triggers available", + ret.value); + report_prefix_popn(2); + return tdata1; + } + + report_fail("Returned 0 mcontrol(6) triggers available"); + report_prefix_popn(2); + + return SBI_DBTR_TDATA1_TYPE_NONE; +} + +static struct sbiret dbtr_test_store_install_uninstall(struct sbi_dbtr_shmem_entry *shmem, + enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("store trigger"); + + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_install_triggers(1); + if (!sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_install_triggers")) { + report_prefix_pop(); + return ret; + } + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(do_store(&test), "triggered"); + + if (do_load(&test)) + report_fail("triggered by load"); + + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_store(&test)) + report_fail("triggered after uninstall"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); + + return ret; +} + +static void dbtr_test_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + bool kfail; + + report_prefix_push("update trigger"); + + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_update_triggers(1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_update_triggers"); + + /* + * Known broken update_triggers. + * https://lore.kernel.org/opensbi/aDdp1UeUh7GugeHp@ghost/T/#t + */ + kfail = __sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 7); + report_kfail(kfail, do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_load(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("load trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_LOAD, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "triggered"); + + if (do_store(&test)) + report_fail("triggered by store"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + if (!report(!do_store(&test), "should not trigger")) { + dbtr_uninstall_trigger(); + report_prefix_pop(); + report_skip("enable trigger: no disable"); + + return; + } + + report_prefix_pop(); + report_prefix_push("enable trigger"); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + report(do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_exec(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("exec trigger"); + /* check if loads and stores trigger exec */ + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + + if (do_load(&test)) + report_fail("triggered by load"); + + if (do_store(&test)) + report_fail("triggered by store"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + report(do_exec(), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("read trigger"); + if (!dbtr_install_trigger(shmem, &test, tdata1)) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + if (!report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx", tdata1)) + report_info("tdata1 found: 0x%016lx", shmem->data.tdata1); + if (!report(shmem->data.tdata2 == ((unsigned long)&test), "tdata2 expected: 0x%016lx", + (unsigned long)&test)) + report_info("tdata2 found: 0x%016lx", shmem->data.tdata2); + if (!report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx", tstatus_expected)) + report_info("tstate found: 0x%016lx", shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void check_exec(unsigned long base) +{ + struct sbiret ret; + + report(do_exec(), "exec triggered"); + + ret = sbi_debug_uninstall_triggers(base, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static void dbtr_test_multiple(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type, + unsigned long num_trigs) +{ + static unsigned long test[2]; + struct sbiret ret; + bool have_three = num_trigs > 2; + + if (num_trigs < 2) { + report_skip("test multiple"); + return; + } + + report_prefix_push("test multiple"); + + if (!dbtr_install_trigger(shmem, &test[0], gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + if (!dbtr_install_trigger(shmem, &test[1], gen_tdata1(type, VALUE_LOAD, MODE_S))) + goto error; + if (have_three && + !dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + goto error; + } + + report(do_store(&test[0]), "store triggered"); + + if (do_load(&test[0])) + report_fail("store triggered by load"); + + report(do_load(&test[1]), "load triggered"); + + if (do_store(&test[1])) + report_fail("load triggered by store"); + + if (have_three) + check_exec(2); + + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_load(&test[1])) + report_fail("load triggered after uninstall"); + + report(do_store(&test[0]), "store triggered"); + + if (!have_three && + dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) + check_exec(1); + +error: + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_multiple_types(struct sbi_dbtr_shmem_entry *shmem, unsigned long type) +{ + static unsigned long test; + + report_prefix_push("test multiple types"); + + /* check if loads and stores trigger exec */ + if (!dbtr_install_trigger(shmem, &test, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "load triggered"); + + report(do_store(&test), "store triggered"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_exec(), "exec triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_uninstall(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable uninstall"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + dbtr_uninstall_trigger(); + + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("uninstall enable"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + dbtr_uninstall_trigger(); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_store(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + bool kfail; + + report_prefix_push("uninstall update"); + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + dbtr_uninstall_trigger(); + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + /* + * Known broken update_triggers. + * https://lore.kernel.org/opensbi/aDdp1UeUh7GugeHp@ghost/T/#t + */ + kfail = __sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 7); + ret = sbi_debug_update_triggers(1); + sbiret_kfail_error(kfail, &ret, SBI_ERR_FAILURE, "sbi_debug_update_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_store(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_disable_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_NONE); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable read"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + if (!report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx", tdata1)) + report_info("tdata1 found: 0x%016lx", shmem->data.tdata1); + if (!report(shmem->data.tdata2 == ((unsigned long)&test), "tdata2 expected: 0x%016lx", + (unsigned long)&test)) + report_info("tdata2 found: 0x%016lx", shmem->data.tdata2); + if (!report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx", tstatus_expected)) + report_info("tstate found: 0x%016lx", shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +void check_dbtr(void) +{ + static struct sbi_dbtr_shmem_entry shmem[RV_MAX_TRIGGERS] = {}; + unsigned long num_trigs; + enum McontrolType trig_type; + struct sbiret ret; + + report_prefix_push("dbtr"); + + if (!sbi_probe(SBI_EXT_DBTR)) { + report_skip("extension not available"); + goto exit_test; + } + + num_trigs = dbtr_test_num_triggers(); + if (!num_trigs) + goto exit_test; + + trig_type = dbtr_test_type(&num_trigs); + if (trig_type == SBI_DBTR_TDATA1_TYPE_NONE) + goto exit_test; + + ret = sbi_debug_set_shmem(shmem); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_set_shmem"); + + ret = dbtr_test_store_install_uninstall(&shmem[0], trig_type); + /* install or uninstall failed */ + if (ret.error != SBI_SUCCESS) + goto exit_test; + + dbtr_test_load(&shmem[0], trig_type); + dbtr_test_exec(&shmem[0], trig_type); + dbtr_test_read(&shmem[0], trig_type); + dbtr_test_disable_enable(&shmem[0], trig_type); + dbtr_test_update(&shmem[0], trig_type); + dbtr_test_multiple_types(&shmem[0], trig_type); + dbtr_test_multiple(shmem, trig_type, num_trigs); + dbtr_test_disable_uninstall(&shmem[0], trig_type); + dbtr_test_uninstall_enable(&shmem[0], trig_type); + dbtr_test_uninstall_update(&shmem[0], trig_type); + dbtr_test_disable_read(&shmem[0], trig_type); + +exit_test: + report_prefix_pop(); +} diff --git a/riscv/sbi-tests.h b/riscv/sbi-tests.h index d5c4ae70..c1ebf016 100644 --- a/riscv/sbi-tests.h +++ b/riscv/sbi-tests.h @@ -97,8 +97,10 @@ static inline bool env_enabled(const char *env) return s && (*s == '1' || *s == 'y' || *s == 'Y'); } +void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo); void sbi_bad_fid(int ext); void check_sse(void); +void check_dbtr(void); #endif /* __ASSEMBLER__ */ #endif /* _RISCV_SBI_TESTS_H_ */ diff --git a/riscv/sbi.c b/riscv/sbi.c index edb1a6be..3b8aadce 100644 --- a/riscv/sbi.c +++ b/riscv/sbi.c @@ -105,7 +105,7 @@ static int rand_online_cpu(prng_state *ps) return cpu; } -static void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo) +void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo) { *lo = (unsigned long)paddr; *hi = 0; @@ -1561,6 +1561,7 @@ int main(int argc, char **argv) check_susp(); check_sse(); check_fwft(); + check_dbtr(); return report_summary(); } -- 2.43.0

2 months, 2 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror