June 2025 - Linux-kselftest-mirror

[PATCH] selftests/timers: Fix integer overlow errors on 32 bit systems

by Terry Tritton

The use of NSEC_PER_SEC (1000000000L) as defined in include/vdso/time64.h causes several integer overflow warnings and test errors on 32 bit architectures. Use a long long instead of long to prevent integer overflow when converting seconds to nanoseconds. Signed-off-by: Terry Tritton <terry.tritton(a)linaro.org> --- tools/testing/selftests/timers/adjtick.c | 5 ++++- tools/testing/selftests/timers/alarmtimer-suspend.c | 4 +++- tools/testing/selftests/timers/inconsistency-check.c | 4 +++- tools/testing/selftests/timers/leap-a-day.c | 4 +++- tools/testing/selftests/timers/mqueue-lat.c | 3 ++- tools/testing/selftests/timers/nanosleep.c | 4 +++- tools/testing/selftests/timers/nsleep-lat.c | 4 +++- tools/testing/selftests/timers/posix_timers.c | 5 ++++- tools/testing/selftests/timers/raw_skew.c | 4 +++- tools/testing/selftests/timers/set-2038.c | 4 +++- tools/testing/selftests/timers/set-timer-lat.c | 4 +++- tools/testing/selftests/timers/valid-adjtimex.c | 5 ++++- 12 files changed, 38 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c index 777d9494b683..b5929c33b632 100644 --- a/tools/testing/selftests/timers/adjtick.c +++ b/tools/testing/selftests/timers/adjtick.c @@ -22,10 +22,13 @@ #include <sys/time.h> #include <sys/timex.h> #include <time.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + #define MILLION 1000000 long systick; diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c index a9ef76ea6051..b5799df271ae 100644 --- a/tools/testing/selftests/timers/alarmtimer-suspend.c +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -28,10 +28,12 @@ #include <signal.h> #include <stdlib.h> #include <pthread.h> -#include <include/vdso/time64.h> #include <errno.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define UNREASONABLE_LAT (NSEC_PER_SEC * 5) /* hopefully we resume in 5 secs */ #define SUSPEND_SECS 15 diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c index 9d1573769d55..2b2d7293b313 100644 --- a/tools/testing/selftests/timers/inconsistency-check.c +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -28,9 +28,11 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c index 04004a7c0934..008c38ce4b2f 100644 --- a/tools/testing/selftests/timers/leap-a-day.c +++ b/tools/testing/selftests/timers/leap-a-day.c @@ -48,9 +48,11 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define CLOCK_TAI 11 time_t next_leap; diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c index 63de2334a291..1a6d26f86137 100644 --- a/tools/testing/selftests/timers/mqueue-lat.c +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -29,9 +29,10 @@ #include <signal.h> #include <errno.h> #include <mqueue.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL #define TARGET_TIMEOUT 100000000 /* 100ms in nanoseconds */ #define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c index 252c6308c569..55ea67478fdd 100644 --- a/tools/testing/selftests/timers/nanosleep.c +++ b/tools/testing/selftests/timers/nanosleep.c @@ -27,9 +27,11 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c index de23dc0c9f97..347d622987c8 100644 --- a/tools/testing/selftests/timers/nsleep-lat.c +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -24,9 +24,11 @@ #include <sys/timex.h> #include <string.h> #include <signal.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index f0eceb0faf34..555bf161f420 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -16,11 +16,14 @@ #include <string.h> #include <unistd.h> #include <time.h> -#include <include/vdso/time64.h> #include <pthread.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + #define DELAY 2 static void __fatal_error(const char *test, const char *name, const char *what) diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index 957f7cd29cb1..ff7675d98560 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -25,9 +25,11 @@ #include <sys/time.h> #include <sys/timex.h> #include <time.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ __typeof__(s) __s = (s); \ diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c index ed244315e11c..8130d551a11c 100644 --- a/tools/testing/selftests/timers/set-2038.c +++ b/tools/testing/selftests/timers/set-2038.c @@ -27,9 +27,11 @@ #include <unistd.h> #include <time.h> #include <sys/time.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + #define KTIME_MAX ((long long)~((unsigned long long)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9d8437c13929..79a6a6cba186 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -28,9 +28,11 @@ #include <signal.h> #include <stdlib.h> #include <pthread.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL + /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 6b7801055ad1..e4f31e678630 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -29,9 +29,12 @@ #include <string.h> #include <signal.h> #include <unistd.h> -#include <include/vdso/time64.h> #include "../kselftest.h" +/* define NSEC_PER_SEC as long long to avoid overflow on 32 bit architectures*/ +#define NSEC_PER_SEC 1000000000LL +#define USEC_PER_SEC 1000000LL + #define ADJ_SETOFFSET 0x0100 #include <sys/syscall.h> -- 2.39.5

2 weeks, 5 days

2
2
0 0

[PATCH v2 0/6] VMM can handle guest SEA via KVM_EXIT_ARM_SEA

by Jiaqi Yan

Problem ======= When host APEI is unable to claim synchronous external abort (SEA) during stage-2 guest abort, today KVM directly injects an async SError into the VCPU then resumes it. The injected SError usually results in unpleasant guest kernel panic. One of the major situation of guest SEA is when VCPU consumes recoverable uncorrected memory error (UER), which is not uncommon at all in modern datacenter servers with large amounts of physical memory. Although SError and guest panic is sufficient to stop the propagation of corrupted memory there is room to recover from an UER in a more graceful manner. Proposed Solution ================= Alternatively KVM can replay the SEA to the faulting VCPU, via existing KVM_SET_VCPU_EVENTS API. If the memory poison consumption or the fault that cause SEA is not from guest kernel, the blast radius can be limited to the consuming or faulting guest userspace process, so the VM can keep running. In addition, instead of doing under the hood without involving userspace, there are benefits to redirect the SEA to VMM: - VM customers care about the disruptions caused by memory errors, and VMM usually has the responsibility to start the process of notifying the customers of memory error events in their VMs. For example some cloud provider emits a critical log in their observability UI [1], and provides playbook for customers on how to mitigate disruptions to their workloads. - VMM can protect future memory error consumption by unmapping the poisoned pages from stage-2 page table with KVM userfault, or by splitting the memslot that contains the poisoned guest pages [2]. - VMM can keep track of SEA events in the VM. When VMM thinks the status on the host or the VM is bad enough, e.g. number of distinct SEAs exceeds a threshold, it can restart the VM on another healthy host. - Behavior parity with x86 architecture. When machine check exception (MCE) is caused by VCPU, kernel or KVM signals userspace SIGBUS to let VMM either recover from the MCE, or terminate itself with VM. The prior RFC proposes to implement SIGBUS on arm64 as well, but Marc preferred VCPU exit over signal [3]. However, implementation aside, returning SEA to VMM is on par with returning MCE to VMM. Once SEA is redirected to VMM, among other actions, VMM is encouraged to inject external aborts into the faulting VCPU, which is already supported by KVM on arm64. We notice injecting instruction abort is not fully supported by KVM_SET_VCPU_EVENTS. Complement it in the patchset. New UAPIs ========= This patchset introduces following userspace-visiable changes to empower VMM to control what happens next for SEA on guest memory: - KVM_CAP_ARM_SEA_TO_USER. While taking SEA, if userspace has enabled this new capability at VM creation, and the SEA is not caused by memory allocated for stage-2 translation table, instead of injecting SError, return KVM_EXIT_ARM_SEA to userspace. - KVM_EXIT_ARM_SEA. This is the VM exit reason VMM gets. The details about the SEA is provided in arm_sea as much as possible, including sanitized ESR value at EL2, if guest virtual and physical addresses (GPA and GVA) are available and the values if available. - KVM_CAP_ARM_INJECT_EXT_IABT. VMM today can inject external data abort to VCPU via KVM_SET_VCPU_EVENTS API. However, in case of instruction abort, VMM cannot inject it via KVM_SET_VCPU_EVENTS. KVM_CAP_ARM_INJECT_EXT_IABT is just a natural extend to KVM_CAP_ARM_INJECT_EXT_DABT that tells VMM KVM_SET_VCPU_EVENTS now supports external instruction abort. * From v1 [4]: - Rebased on commit 4d62121ce9b5 ("KVM: arm64: vgic-debug: Avoid dereferencing NULL ITE pointer"). - Sanitize ESR_EL2 before reporting it to userspace. - Do not do KVM_EXIT_ARM_SEA when SEA is caused by memory allocated to stage-2 translation table. [1] https://cloud.google.com/solutions/sap/docs/manage-host-errors [2] https://lore.kernel.org/kvm/20250109204929.1106563-1-jthoughton@google.com [3] https://lore.kernel.org/kvm/86pljbqqh0.wl-maz@kernel.org [4] https://lore.kernel.org/kvm/20250505161412.1926643-1-jiaqiyan@google.com Jiaqi Yan (5): KVM: arm64: VM exit to userspace to handle SEA KVM: arm64: Set FnV for VCPU when FAR_EL2 is invalid KVM: selftests: Test for KVM_EXIT_ARM_SEA and KVM_CAP_ARM_SEA_TO_USER KVM: selftests: Test for KVM_CAP_INJECT_EXT_IABT Documentation: kvm: new uAPI for handling SEA Raghavendra Rao Ananta (1): KVM: arm64: Allow userspace to inject external instruction aborts Documentation/virt/kvm/api.rst | 128 ++++++- arch/arm64/include/asm/kvm_emulate.h | 67 ++++ arch/arm64/include/asm/kvm_host.h | 8 + arch/arm64/include/asm/kvm_ras.h | 2 +- arch/arm64/include/uapi/asm/kvm.h | 3 +- arch/arm64/kvm/arm.c | 6 + arch/arm64/kvm/guest.c | 13 +- arch/arm64/kvm/inject_fault.c | 3 + arch/arm64/kvm/mmu.c | 59 ++- include/uapi/linux/kvm.h | 12 + tools/arch/arm64/include/asm/esr.h | 2 + tools/arch/arm64/include/uapi/asm/kvm.h | 3 +- tools/testing/selftests/kvm/Makefile.kvm | 2 + .../testing/selftests/kvm/arm64/inject_iabt.c | 98 +++++ .../testing/selftests/kvm/arm64/sea_to_user.c | 340 ++++++++++++++++++ tools/testing/selftests/kvm/lib/kvm_util.c | 1 + 16 files changed, 718 insertions(+), 29 deletions(-) create mode 100644 tools/testing/selftests/kvm/arm64/inject_iabt.c create mode 100644 tools/testing/selftests/kvm/arm64/sea_to_user.c -- 2.49.0.1266.g31b7d2e469-goog

2 weeks, 5 days

1
6
0 0

[PATCH] selftests: ublk: kublk: improve behavior on init failure

by Uday Shankar

Some failure modes are handled poorly by kublk. For example, if ublk_drv is built as a module but not currently loaded into the kernel, ./kublk add ... just hangs forever. This happens because in this case (and a few others), the worker process does not notify its parent (via a write to the shared eventfd) that it has tried and failed to initialize, so the parent hangs forever. Fix this by ensuring that we always notify the parent process of any initialization failure, and have the parent print a (not very descriptive) log line when this happens. Signed-off-by: Uday Shankar <ushankar(a)purestorage.com> --- tools/testing/selftests/ublk/kublk.c | 34 +++++++++++++++++++++++----------- 1 file changed, 23 insertions(+), 11 deletions(-) diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index a98e14e4c245965d817b93843ff9a4011291223b..e2d2042810d4bb472e48a0ed91317d2bdf6e2f2a 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -1112,7 +1112,7 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) __u64 features; const struct ublk_tgt_ops *ops; struct ublksrv_ctrl_dev_info *info; - struct ublk_dev *dev; + struct ublk_dev *dev = NULL; int dev_id = ctx->dev_id; int ret, i; @@ -1120,13 +1120,15 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) if (!ops) { ublk_err("%s: no such tgt type, type %s\n", __func__, tgt_type); - return -ENODEV; + ret = -ENODEV; + goto fail; } if (nr_queues > UBLK_MAX_QUEUES || depth > UBLK_QUEUE_DEPTH) { ublk_err("%s: invalid nr_queues or depth queues %u depth %u\n", __func__, nr_queues, depth); - return -EINVAL; + ret = -EINVAL; + goto fail; } /* default to 1:1 threads:queues if nthreads is unspecified */ @@ -1136,30 +1138,37 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) if (nthreads > UBLK_MAX_THREADS) { ublk_err("%s: %u is too many threads (max %u)\n", __func__, nthreads, UBLK_MAX_THREADS); - return -EINVAL; + ret = -EINVAL; + goto fail; } if (nthreads != nr_queues && !ctx->per_io_tasks) { ublk_err("%s: threads %u must be same as queues %u if " "not using per_io_tasks\n", __func__, nthreads, nr_queues); - return -EINVAL; + ret = -EINVAL; + goto fail; } dev = ublk_ctrl_init(); if (!dev) { ublk_err("%s: can't alloc dev id %d, type %s\n", __func__, dev_id, tgt_type); - return -ENOMEM; + ret = -ENOMEM; + goto fail; } /* kernel doesn't support get_features */ ret = ublk_ctrl_get_features(dev, &features); - if (ret < 0) - return -EINVAL; + if (ret < 0) { + ret = -EINVAL; + goto fail; + } - if (!(features & UBLK_F_CMD_IOCTL_ENCODE)) - return -ENOTSUP; + if (!(features & UBLK_F_CMD_IOCTL_ENCODE)) { + ret = -ENOTSUP; + goto fail; + } info = &dev->dev_info; info->dev_id = ctx->dev_id; @@ -1200,7 +1209,8 @@ static int __cmd_dev_add(const struct dev_ctx *ctx) fail: if (ret < 0) ublk_send_dev_event(ctx, dev, -1); - ublk_ctrl_deinit(dev); + if (dev) + ublk_ctrl_deinit(dev); return ret; } @@ -1262,6 +1272,8 @@ static int cmd_dev_add(struct dev_ctx *ctx) shmctl(ctx->_shmid, IPC_RMID, NULL); /* wait for child and detach from it */ wait(NULL); + if (exit_code == EXIT_FAILURE) + ublk_err("%s: command failed\n", __func__); exit(exit_code); } else { exit(EXIT_FAILURE); --- base-commit: c09a8b00f850d3ca0af998bff1fac4a3f6d11768 change-id: 20250603-ublk_init_fail-b498905159eb Best regards, -- Uday Shankar <ushankar(a)purestorage.com>

2 weeks, 5 days

3
2
0 0

[PATCH v2] selftests: ir_decoder: Convert header comment to proper multi-line block

by Abdelrahman Fekry

well, i checked the script using checkpatch.pl and it shows that the patch has no warnings or errors and its ready to be sent v2: - fixed multiple trailing whitespace errors and - the Signed-off-by mismatch The test file for the IR decoder used single-line comments at the top to document its purpose and licensing, which is inconsistent with the style used throughout the Linux kernel. In this patch i converted the file header to a proper multi-line comment block (/*) that aligns with standard kernel practices. This improves readability, consistency across selftests, and ensures the license and documentation are clearly visible in a familiar format. No functional changes have been made. Signed-off-by: Abdelrahman Fekry <abdelrahmanfekry375(a)gmail.com> --- tools/testing/selftests/ir/ir_loopback.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index f4a15cbdd5ea..c94faa975630 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -1,14 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -// test ir decoder -// -// Copyright (C) 2018 Sean Young <sean(a)mess.org> - -// When sending LIRC_MODE_SCANCODE, the IR will be encoded. rc-loopback -// will send this IR to the receiver side, where we try to read the decoded -// IR. Decoding happens in a separate kernel thread, so we will need to -// wait until that is scheduled, hence we use poll to check for read -// readiness. - +/* Copyright (C) 2018 Sean Young <sean(a)mess.org> + * + * Selftest for IR decoder + * + * + * When sending LIRC_MODE_SCANCODE, the IR will be encoded. + * rc-loopback will send this IR to the receiver side, + * where we try to read the decoded IR. + * Decoding happens in a separate kernel thread, + * so we will need to wait until that is scheduled, + * hence we use poll to check for read + * readiness. + */ #include <linux/lirc.h> #include <errno.h> #include <stdio.h> -- 2.25.1

2 weeks, 5 days

1
0
0 0

[PATCH bpf-next v3 00/11] bpf: Mitigate Spectre v1 using barriers

by Luis Gerhorst

This improves the expressiveness of unprivileged BPF by inserting speculation barriers instead of rejecting the programs. The approach was previously presented at LPC'24 [1] and RAID'24 [2]. To mitigate the Spectre v1 (PHT) vulnerability, the kernel rejects potentially-dangerous unprivileged BPF programs as of commit 9183671af6db ("bpf: Fix leakage under speculation on mispredicted branches"). In [2], we have analyzed 364 object files from open source projects (Linux Samples and Selftests, BCC, Loxilb, Cilium, libbpf Examples, Parca, and Prevail) and found that this affects 31% to 54% of programs. To resolve this in the majority of cases this patchset adds a fall-back for mitigating Spectre v1 using speculation barriers. The kernel still optimistically attempts to verify all speculative paths but uses speculation barriers against v1 when unsafe behavior is detected. This allows for more programs to be accepted without disabling the BPF Spectre mitigations (e.g., by setting cpu_mitigations_off()). For this, it relies on the fact that speculation barriers prevent all later instructions if the speculation was not correct: * On x86_64, lfence acts as full speculation barrier, not only as a load fence [3]: An LFENCE instruction or a serializing instruction will ensure that no later instructions execute, even speculatively, until all prior instructions complete locally. [...] Inserting an LFENCE instruction after a bounds check prevents later operations from executing before the bound check completes. This was experimentally confirmed in [4]. * ARM's SB speculation barrier instruction also affects "any instruction that appears later in the program order than the barrier" [5]. In [1] we have measured the overhead of this approach relative to having mitigations off and including the upstream Spectre v4 mitigations. For event tracing and stack-sampling profilers, we found that mitigations increase BPF program execution time by 0% to 62%. For the Loxilb network load balancer, we have measured a 14% slowdown in SCTP performance but no significant slowdown for TCP. This overhead only applies to programs that were previously rejected. I reran the expressiveness-evaluation with v6.14 and made sure the main results still match those from [1] and [2] (which used v6.5). Main design decisions are: * Do not use separate bytecode insns for v1 and v4 barriers (inspired by Daniel Borkmann's question at LPC). This simplifies the verifier significantly and has the only downside that performance on PowerPC is not as high as it could be. * Allow archs to still disable v1/v4 mitigations separately by setting bpf_jit_bypass_spec_v1/v4(). This has the benefit that archs can benefit from improved BPF expressiveness / performance if they are not vulnerable (e.g., ARM64 for v4 in the kernel). * Do not remove the empty BPF_NOSPEC implementation for backends for which it is unknown whether they are vulnerable to Spectre v1. [1] https://lpc.events/event/18/contributions/1954/ ("Mitigating Spectre-PHT using Speculation Barriers in Linux eBPF") [2] https://arxiv.org/pdf/2405.00078 ("VeriFence: Lightweight and Precise Spectre Defenses for Untrusted Linux Kernel Extensions") [3] https://www.intel.com/content/www/us/en/developer/articles/technical/softwa… ("Managed Runtime Speculative Execution Side Channel Mitigations") [4] https://dl.acm.org/doi/pdf/10.1145/3359789.3359837 ("Speculator: a tool to analyze speculative execution attacks and mitigations" - Section 4.6 "Stopping Speculative Execution") [5] https://developer.arm.com/documentation/ddi0597/2020-12/Base-Instructions/S… ("SB - Speculation Barrier - Arm Armv8-A A32/T32 Instruction Set Architecture (2020-12)") Changes: * v2 -> v3: - Fix https://lore.kernel.org/oe-kbuild-all/202504212030.IF1SLhz6-lkp@intel.com/ and similar by moving the bpf_jit_bypass_spec_v1/v4() prototypes out of the #ifdef CONFIG_BPF_SYSCALL. Decided not to move them to filter.h (where similar bpf_jit_*() prototypes live) as they would still have to be duplicated in bpf.h to be usable to bpf_bypass_spec_v1/v4() (unless including filter.h in bpf.h is an option). - Fix https://lore.kernel.org/oe-kbuild-all/202504220035.SoGveGpj-lkp@intel.com/ by moving the variable declarations out of the switch-case. - Build touched C files with W=2 and bpf config on x86 to check that there are no other warnings introduced. - Found 3 more checkpatch warnings that can be fixed without degrading readability. - Rebase to bpf-next 2025-05-01 - Link to v2: https://lore.kernel.org/bpf/20250421091802.3234859-1-luis.gerhorst@fau.de/ * v1 -> v2: - Drop former commits 9 ("bpf: Return PTR_ERR from push_stack()") and 11 ("bpf: Fall back to nospec for spec path verification") as suggested by Alexei. This series therefore no longer changes push_stack() to return PTR_ERR. - Add detailed explanation of how lfence works internally and how it affects the algorithm. - Add tests checking that nospec instructions are inserted in expected locations using __xlated_unpriv as suggested by Eduard (also, include a fix for __xlated_unpriv) - Add a test for the mitigations from the description of commit 9183671af6db ("bpf: Fix leakage under speculation on mispredicted branches") - Remove unused variables from do_check[_insn]() as suggested by Eduard. - Remove INSN_IDX_MODIFIED to improve readability as suggested by Eduard. This also causes the nospec_result-check to run (and fail) for jumping-ops. Add a warning to assert that this check must never succeed in that case. - Add details on the safety of patch 10 ("bpf: Allow nospec-protected var-offset stack access") based on the feedback on v1. - Rebase to bpf-next-250420 - Link to v1: https://lore.kernel.org/all/20250313172127.1098195-1-luis.gerhorst@fau.de/ * RFC -> v1: - rebase to bpf-next-250313 - tests: mark expected successes/new errors - add bpt_jit_bypass_spec_v1/v4() to avoid #ifdef in bpf_bypass_spec_v1/v4() - ensure that nospec with v1-support is implemented for archs for which GCC supports speculation barriers, except for MIPS - arm64: emit speculation barrier - powerpc: change nospec to include v1 barrier - discuss potential security (archs that do not impl. BPF nospec) and performance (only PowerPC) regressions - Link to RFC: https://lore.kernel.org/bpf/20250224203619.594724-1-luis.gerhorst@fau.de/ Luis Gerhorst (11): selftests/bpf: Fix caps for __xlated/jited_unpriv bpf: Move insn if/else into do_check_insn() bpf: Return -EFAULT on misconfigurations bpf: Return -EFAULT on internal errors bpf, arm64, powerpc: Add bpf_jit_bypass_spec_v1/v4() bpf, arm64, powerpc: Change nospec to include v1 barrier bpf: Rename sanitize_stack_spill to nospec_result bpf: Fall back to nospec for Spectre v1 selftests/bpf: Add test for Spectre v1 mitigation bpf: Allow nospec-protected var-offset stack access bpf: Fall back to nospec for sanitization-failures arch/arm64/net/bpf_jit.h | 5 + arch/arm64/net/bpf_jit_comp.c | 28 +- arch/powerpc/net/bpf_jit_comp64.c | 80 ++- include/linux/bpf.h | 11 +- include/linux/bpf_verifier.h | 3 +- include/linux/filter.h | 2 +- kernel/bpf/core.c | 32 +- kernel/bpf/verifier.c | 653 ++++++++++-------- tools/testing/selftests/bpf/progs/bpf_misc.h | 4 + .../selftests/bpf/progs/verifier_and.c | 8 +- .../selftests/bpf/progs/verifier_bounds.c | 66 +- .../bpf/progs/verifier_bounds_deduction.c | 45 +- .../selftests/bpf/progs/verifier_map_ptr.c | 20 +- .../selftests/bpf/progs/verifier_movsx.c | 16 +- .../selftests/bpf/progs/verifier_unpriv.c | 65 +- .../bpf/progs/verifier_value_ptr_arith.c | 101 ++- tools/testing/selftests/bpf/test_loader.c | 14 +- .../selftests/bpf/verifier/dead_code.c | 3 +- tools/testing/selftests/bpf/verifier/jmp32.c | 33 +- tools/testing/selftests/bpf/verifier/jset.c | 10 +- 20 files changed, 771 insertions(+), 428 deletions(-) base-commit: 358b1c0f56ebb6996fcec7dcdcf6bae5dcbc8b6c -- 2.49.0

2 weeks, 5 days

6
34
0 0

[PATCH v2 1/2] libbpf: add support for printing BTF character arrays as strings

by Blake Jones

The BTF dumper code currently displays arrays of characters as just that - arrays, with each character formatted individually. Sometimes this is what makes sense, but it's nice to be able to treat that array as a string. This change adds a special case to the btf_dump functionality to allow arrays of single-byte integer values to be printed as character strings. Characters for which isprint() returns false are printed as hex-escaped values. This is enabled when the new ".emit_strings" is set to 1 in the btf_dump_type_data_opts structure. As an example, here's what it looks like to dump the string "hello" using a few different field values for btf_dump_type_data_opts (.compact = 1): - .emit_strings = 0, .skip_names = 0: (char[6])['h','e','l','l','o',] - .emit_strings = 0, .skip_names = 1: ['h','e','l','l','o',] - .emit_strings = 1, .skip_names = 0: (char[6])"hello" - .emit_strings = 1, .skip_names = 1: "hello" Here's the string "h\xff", dumped with .compact = 1 and .skip_names = 1: - .emit_strings = 0: ['h',-1,] - .emit_strings = 1: "h\xff" Signed-off-by: Blake Jones <blakejones(a)google.com> --- tools/lib/bpf/btf.h | 3 ++- tools/lib/bpf/btf_dump.c | 44 +++++++++++++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 2 deletions(-) diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 4392451d634b..ccfd905f03df 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -326,9 +326,10 @@ struct btf_dump_type_data_opts { bool compact; /* no newlines/indentation */ bool skip_names; /* skip member/type names */ bool emit_zeroes; /* show 0-valued fields */ + bool emit_strings; /* print char arrays as strings */ size_t :0; }; -#define btf_dump_type_data_opts__last_field emit_zeroes +#define btf_dump_type_data_opts__last_field emit_strings LIBBPF_API int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 460c3e57fadb..336a6646e0fa 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -68,6 +68,7 @@ struct btf_dump_data { bool compact; bool skip_names; bool emit_zeroes; + bool emit_strings; __u8 indent_lvl; /* base indent level */ char indent_str[BTF_DATA_INDENT_STR_LEN]; /* below are used during iteration */ @@ -2028,6 +2029,43 @@ static int btf_dump_var_data(struct btf_dump *d, return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0); } +static int btf_dump_string_data(struct btf_dump *d, + const struct btf_type *t, + __u32 id, + const void *data) +{ + const struct btf_array *array = btf_array(t); + __u32 i; + + btf_dump_data_pfx(d); + btf_dump_printf(d, "\""); + + for (i = 0; i < array->nelems; i++, data++) { + char c; + + if (data >= d->typed_dump->data_end) + return -E2BIG; + + c = *(char *)data; + if (c == '\0') { + /* + * When printing character arrays as strings, NUL bytes + * are always treated as string terminators; they are + * never printed. + */ + break; + } + if (isprint(c)) + btf_dump_printf(d, "%c", c); + else + btf_dump_printf(d, "\\x%02x", *(__u8 *)data); + } + + btf_dump_printf(d, "\""); + + return 0; +} + static int btf_dump_array_data(struct btf_dump *d, const struct btf_type *t, __u32 id, @@ -2055,8 +2093,11 @@ static int btf_dump_array_data(struct btf_dump *d, * char arrays, so if size is 1 and element is * printable as a char, we'll do that. */ - if (elem_size == 1) + if (elem_size == 1) { + if (d->typed_dump->emit_strings) + return btf_dump_string_data(d, t, id, data); d->typed_dump->is_array_char = true; + } } /* note that we increment depth before calling btf_dump_print() below; @@ -2544,6 +2585,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id, d->typed_dump->compact = OPTS_GET(opts, compact, false); d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false); d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false); + d->typed_dump->emit_strings = OPTS_GET(opts, emit_strings, false); ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0); -- 2.49.0.1204.g71687c7c1d-goog

2 weeks, 5 days

3
5
0 0

[RESEND PATCH] selftests/bpf: Fix bpf selftest build error

by Saket Kumar Bhaskar

On linux-next, build for bpf selftest displays an error due to mismatch in the expected function signature of bpf_testmod_test_read and bpf_testmod_test_write. Commit 97d06802d10a ("sysfs: constify bin_attribute argument of bin_attribute::read/write()") changed the required type for struct bin_attribute to const struct bin_attribute. To resolve the error, update corresponding signature for the callback. Fixes: 97d06802d10a ("sysfs: constify bin_attribute argument of bin_attribute::read/write()") Reported-by: Venkat Rao Bagalkote <venkat88(a)linux.ibm.com> Closes: https://lore.kernel.org/all/e915da49-2b9a-4c4c-a34f-877f378129f6@linux.ibm.… Tested-by: Venkat Rao Bagalkote <venkat88(a)linux.ibm.com> Signed-off-by: Saket Kumar Bhaskar <skb99(a)linux.ibm.com> --- [RESEND]: - Added Fixes and Tested-by tag. - Added Greg as receipent for driver-core tree. Original patch: https://lore.kernel.org/all/20250509122348.649064-1-skb99@linux.ibm.com/ tools/testing/selftests/bpf/test_kmods/bpf_testmod.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index 2e54b95ad898..194c442580ee 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -385,7 +385,7 @@ int bpf_testmod_fentry_ok; noinline ssize_t bpf_testmod_test_read(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { struct bpf_testmod_test_read_ctx ctx = { @@ -465,7 +465,7 @@ ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO); noinline ssize_t bpf_testmod_test_write(struct file *file, struct kobject *kobj, - struct bin_attribute *bin_attr, + const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { struct bpf_testmod_test_write_ctx ctx = { -- 2.43.5

2 weeks, 5 days

4
4
0 0

[PATCH net] selftests: drv-net: add configs for the TSO test

by Jakub Kicinski

Add missing config options for the tso.py test, specifically to make sure the kernel is built with vxlan and gre tunnels. I noticed this while adding a TSO-capable device QEMU to the CI. Previously we only run virtio tests and it doesn't report LSO stats on the QEMU we have. Fixes: 0d0f4174f6c8 ("selftests: drv-net: add a simple TSO test") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: shuah(a)kernel.org CC: willemb(a)google.com CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/drivers/net/hw/config | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 tools/testing/selftests/drivers/net/hw/config diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config new file mode 100644 index 000000000000..ea4b70d71563 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/config @@ -0,0 +1,6 @@ +CONFIG_IPV6=y +CONFIG_IPV6_GRE=y +CONFIG_NET_IP_TUNNEL=y +CONFIG_NET_IPGRE=y +CONFIG_NET_IPGRE_DEMUX=y +CONFIG_VXLAN=y -- 2.49.0

2 weeks, 5 days

2
2
0 0

[PATCH net v3] selftests: net: build net/lib dependency in all target

by Bui Quang Minh

We have the logic to include net/lib automatically for net related selftests. However, currently, this logic is only in install target which means only `make install` will have net/lib included. This commit adds the logic to all target so that all `make`, `make run_tests` and `make install` will have net/lib included in net related selftests. Signed-off-by: Bui Quang Minh <minhquangbui99(a)gmail.com> --- Changes in v3: - Don't remove INSTALL_DEP_TARGETS in install target so that net/lib is copied to INSTALL_PATH Changes in v2: - Make the commit message clearer. tools/testing/selftests/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 6aa11cd3db42..339b31e6a6b5 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -205,7 +205,7 @@ export KHDR_INCLUDES all: @ret=1; \ - for TARGET in $(TARGETS); do \ + for TARGET in $(TARGETS) $(INSTALL_DEP_TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ mkdir $$BUILD_TARGET -p; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET \ -- 2.43.0

2 weeks, 5 days

2
1
0 0

[PATCH] selftests: ipc: Replace fail print statements with ksft_test_result_fail

by Nick Huang

Use the standard kselftest failure report function to ensure consistent test output formatting. This improves readability and integration with automated test frameworks. Signed-off-by: Nick Huang <sef1548(a)gmail.com> --- tools/testing/selftests/ipc/msgque.c | 47 ++++++++++++++-------------- 1 file changed, 23 insertions(+), 24 deletions(-) diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index e9dbb84c100a..5e36aeeb9901 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -39,26 +39,26 @@ int restore_queue(struct msgque_data *msgque) fd = open("/proc/sys/kernel/msg_next_id", O_WRONLY); if (fd == -1) { - printf("Failed to open /proc/sys/kernel/msg_next_id\n"); + ksft_test_result_fail("Failed to open /proc/sys/kernel/msg_next_id\n"); return -errno; } sprintf(buf, "%d", msgque->msq_id); ret = write(fd, buf, strlen(buf)); if (ret != strlen(buf)) { - printf("Failed to write to /proc/sys/kernel/msg_next_id\n"); + ksft_test_result_fail("Failed to write to /proc/sys/kernel/msg_next_id\n"); return -errno; } id = msgget(msgque->key, msgque->mode | IPC_CREAT | IPC_EXCL); if (id == -1) { - printf("Failed to create queue\n"); + ksft_test_result_fail("Failed to create queue\n"); return -errno; } if (id != msgque->msq_id) { - printf("Restored queue has wrong id (%d instead of %d)\n", - id, msgque->msq_id); + ksft_test_result_fail("Restored queue has wrong id (%d instead of %d)\n" + , id, msgque->msq_id); ret = -EFAULT; goto destroy; } @@ -66,7 +66,7 @@ int restore_queue(struct msgque_data *msgque) for (i = 0; i < msgque->qnum; i++) { if (msgsnd(msgque->msq_id, &msgque->messages[i].mtype, msgque->messages[i].msize, IPC_NOWAIT) != 0) { - printf("msgsnd failed (%m)\n"); + ksft_test_result_fail("msgsnd failed (%m)\n"); ret = -errno; goto destroy; } @@ -90,23 +90,22 @@ int check_and_destroy_queue(struct msgque_data *msgque) if (ret < 0) { if (errno == ENOMSG) break; - printf("Failed to read IPC message: %m\n"); + ksft_test_result_fail("Failed to read IPC message: %m\n"); ret = -errno; goto err; } if (ret != msgque->messages[cnt].msize) { - printf("Wrong message size: %d (expected %d)\n", ret, - msgque->messages[cnt].msize); + ksft_test_result_fail("Wrong message size: %d (expected %d)\n", ret, msgque->messages[cnt].msize); ret = -EINVAL; goto err; } if (message.mtype != msgque->messages[cnt].mtype) { - printf("Wrong message type\n"); + ksft_test_result_fail("Wrong message type\n"); ret = -EINVAL; goto err; } if (memcmp(message.mtext, msgque->messages[cnt].mtext, ret)) { - printf("Wrong message content\n"); + ksft_test_result_fail("Wrong message content\n"); ret = -EINVAL; goto err; } @@ -114,7 +113,7 @@ int check_and_destroy_queue(struct msgque_data *msgque) } if (cnt != msgque->qnum) { - printf("Wrong message number\n"); + ksft_test_result_fail("Wrong message number\n"); ret = -EINVAL; goto err; } @@ -139,7 +138,7 @@ int dump_queue(struct msgque_data *msgque) if (ret < 0) { if (errno == EINVAL) continue; - printf("Failed to get stats for IPC queue with id %d\n", + ksft_test_result_fail("Failed to get stats for IPC queue with id %d\n", kern_id); return -errno; } @@ -150,7 +149,7 @@ int dump_queue(struct msgque_data *msgque) msgque->messages = malloc(sizeof(struct msg1) * ds.msg_qnum); if (msgque->messages == NULL) { - printf("Failed to get stats for IPC queue\n"); + ksft_test_result_fail("Failed to get stats for IPC queue\n"); return -ENOMEM; } @@ -162,7 +161,7 @@ int dump_queue(struct msgque_data *msgque) ret = msgrcv(msgque->msq_id, &msgque->messages[i].mtype, MAX_MSG_SIZE, i, IPC_NOWAIT | MSG_COPY); if (ret < 0) { - printf("Failed to copy IPC message: %m (%d)\n", errno); + ksft_test_result_fail("Failed to copy IPC message: %m (%d)\n", errno); return -errno; } msgque->messages[i].msize = ret; @@ -178,7 +177,7 @@ int fill_msgque(struct msgque_data *msgque) memcpy(msgbuf.mtext, TEST_STRING, sizeof(TEST_STRING)); if (msgsnd(msgque->msq_id, &msgbuf.mtype, sizeof(TEST_STRING), IPC_NOWAIT) != 0) { - printf("First message send failed (%m)\n"); + ksft_test_result_fail("First message send failed (%m)\n"); return -errno; } @@ -186,7 +185,7 @@ int fill_msgque(struct msgque_data *msgque) memcpy(msgbuf.mtext, ANOTHER_TEST_STRING, sizeof(ANOTHER_TEST_STRING)); if (msgsnd(msgque->msq_id, &msgbuf.mtype, sizeof(ANOTHER_TEST_STRING), IPC_NOWAIT) != 0) { - printf("Second message send failed (%m)\n"); + ksft_test_result_fail("Second message send failed (%m)\n"); return -errno; } return 0; @@ -202,44 +201,44 @@ int main(int argc, char **argv) msgque.key = ftok(argv[0], 822155650); if (msgque.key == -1) { - printf("Can't make key: %d\n", -errno); + ksft_test_result_fail("Can't make key: %d\n", -errno); ksft_exit_fail(); } msgque.msq_id = msgget(msgque.key, IPC_CREAT | IPC_EXCL | 0666); if (msgque.msq_id == -1) { err = -errno; - printf("Can't create queue: %d\n", err); + ksft_test_result_fail("Can't create queue: %d\n", err); goto err_out; } err = fill_msgque(&msgque); if (err) { - printf("Failed to fill queue: %d\n", err); + ksft_test_result_fail("Failed to fill queue: %d\n", err); goto err_destroy; } err = dump_queue(&msgque); if (err) { - printf("Failed to dump queue: %d\n", err); + ksft_test_result_fail("Failed to dump queue: %d\n", err); goto err_destroy; } err = check_and_destroy_queue(&msgque); if (err) { - printf("Failed to check and destroy queue: %d\n", err); + ksft_test_result_fail("Failed to check and destroy queue: %d\n", err); goto err_out; } err = restore_queue(&msgque); if (err) { - printf("Failed to restore queue: %d\n", err); + ksft_test_result_fail("Failed to restore queue: %d\n", err); goto err_destroy; } err = check_and_destroy_queue(&msgque); if (err) { - printf("Failed to test queue: %d\n", err); + ksft_test_result_fail("Failed to test queue: %d\n", err); goto err_out; } ksft_exit_pass(); -- 2.48.1

2 weeks, 5 days

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror June 2025