May 2024 - Linux-stable-mirror

[PATCH] drm/mst: Fix NULL pointer dereference at drm_dp_add_payload_part2

by Wayne Lin

[Why] Commit: - commit 5aa1dfcdf0a4 ("drm/mst: Refactor the flow for payload allocation/removement") accidently overwrite the commit - commit 54d217406afe ("drm: use mgr->dev in drm_dbg_kms in drm_dp_add_payload_part2") which cause regression. [How] Recover the original NULL fix and remove the unnecessary input parameter 'state' for drm_dp_add_payload_part2(). Fixes: 5aa1dfcdf0a4 ("drm/mst: Refactor the flow for payload allocation/removement") Reported-by: Leon Weiß <leon.weiss(a)ruhr-uni-bochum.de> Link: https://lore.kernel.org/r/38c253ea42072cc825dc969ac4e6b9b600371cc8.camel@ru… Cc: lyude(a)redhat.com Cc: imre.deak(a)intel.com Cc: stable(a)vger.kernel.org Cc: regressions(a)lists.linux.dev Signed-off-by: Wayne Lin <Wayne.Lin(a)amd.com> --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 2 +- drivers/gpu/drm/display/drm_dp_mst_topology.c | 4 +--- drivers/gpu/drm/i915/display/intel_dp_mst.c | 2 +- drivers/gpu/drm/nouveau/dispnv50/disp.c | 2 +- include/drm/display/drm_dp_mst_helper.h | 1 - 5 files changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index c27063305a13..2c36f3d00ca2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -363,7 +363,7 @@ void dm_helpers_dp_mst_send_payload_allocation( mst_state = to_drm_dp_mst_topology_state(mst_mgr->base.state); new_payload = drm_atomic_get_mst_payload_state(mst_state, aconnector->mst_output_port); - ret = drm_dp_add_payload_part2(mst_mgr, mst_state->base.state, new_payload); + ret = drm_dp_add_payload_part2(mst_mgr, new_payload); if (ret) { amdgpu_dm_set_mst_status(&aconnector->mst_status, diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 03d528209426..95fd18f24e94 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3421,7 +3421,6 @@ EXPORT_SYMBOL(drm_dp_remove_payload_part2); /** * drm_dp_add_payload_part2() - Execute payload update part 2 * @mgr: Manager to use. - * @state: The global atomic state * @payload: The payload to update * * If @payload was successfully assigned a starting time slot by drm_dp_add_payload_part1(), this @@ -3430,14 +3429,13 @@ EXPORT_SYMBOL(drm_dp_remove_payload_part2); * Returns: 0 on success, negative error code on failure. */ int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, - struct drm_atomic_state *state, struct drm_dp_mst_atomic_payload *payload) { int ret = 0; /* Skip failed payloads */ if (payload->payload_allocation_status != DRM_DP_MST_PAYLOAD_ALLOCATION_DFP) { - drm_dbg_kms(state->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", + drm_dbg_kms(mgr->dev, "Part 1 of payload creation for %s failed, skipping part 2\n", payload->port->connector->name); return -EIO; } diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 53aec023ce92..2fba66aec038 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -1160,7 +1160,7 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, if (first_mst_stream) intel_ddi_wait_for_fec_status(encoder, pipe_config, true); - drm_dp_add_payload_part2(&intel_dp->mst_mgr, &state->base, + drm_dp_add_payload_part2(&intel_dp->mst_mgr, drm_atomic_get_mst_payload_state(mst_state, connector->port)); if (DISPLAY_VER(dev_priv) >= 12) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 0c3d88ad0b0e..88728a0b2c25 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -915,7 +915,7 @@ nv50_msto_cleanup(struct drm_atomic_state *state, msto->disabled = false; drm_dp_remove_payload_part2(mgr, new_mst_state, old_payload, new_payload); } else if (msto->enabled) { - drm_dp_add_payload_part2(mgr, state, new_payload); + drm_dp_add_payload_part2(mgr, new_payload); msto->enabled = false; } } diff --git a/include/drm/display/drm_dp_mst_helper.h b/include/drm/display/drm_dp_mst_helper.h index 9b19d8bd520a..6c9145abc7e2 100644 --- a/include/drm/display/drm_dp_mst_helper.h +++ b/include/drm/display/drm_dp_mst_helper.h @@ -851,7 +851,6 @@ int drm_dp_add_payload_part1(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state, struct drm_dp_mst_atomic_payload *payload); int drm_dp_add_payload_part2(struct drm_dp_mst_topology_mgr *mgr, - struct drm_atomic_state *state, struct drm_dp_mst_atomic_payload *payload); void drm_dp_remove_payload_part1(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_topology_state *mst_state, -- 2.37.3

11 months, 1 week

8
10
0 0

[PATCH v2 bpf 1/5] bpf: fix multi-uprobe PID filtering logic

by Andrii Nakryiko

Current implementation of PID filtering logic for multi-uprobes in uprobe_prog_run() is filtering down to exact *thread*, while the intent for PID filtering it to filter by *process* instead. The check in uprobe_prog_run() also differs from the analogous one in uprobe_multi_link_filter() for some reason. The latter is correct, checking task->mm, not the task itself. Fix the check in uprobe_prog_run() to perform the same task->mm check. While doing this, we also update get_pid_task() use to use PIDTYPE_TGID type of lookup, given the intent is to get a representative task of an entire process. This doesn't change behavior, but seems more logical. It would hold task group leader task now, not any random thread task. Last but not least, given multi-uprobe support is half-broken due to this PID filtering logic (depending on whether PID filtering is important or not), we need to make it easy for user space consumers (including libbpf) to easily detect whether PID filtering logic was already fixed. We do it here by adding an early check on passed pid parameter. If it's negative (and so has no chance of being a valid PID), we return -EINVAL. Previous behavior would eventually return -ESRCH ("No process found"), given there can't be any process with negative PID. This subtle change won't make any practical change in behavior, but will allow applications to detect PID filtering fixes easily. Libbpf fixes take advantage of this in the next patch. Cc: stable(a)vger.kernel.org Acked-by: Jiri Olsa <jolsa(a)kernel.org> Fixes: b733eeade420 ("bpf: Add pid filter support for uprobe_multi link") Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> --- kernel/trace/bpf_trace.c | 8 ++++---- .../testing/selftests/bpf/prog_tests/uprobe_multi_test.c | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f5154c051d2c..1baaeb9ca205 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3295,7 +3295,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0; - if (link->task && current != link->task) + if (link->task && current->mm != link->task->mm) return 0; if (sleepable) @@ -3396,8 +3396,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; + pid = attr->link_create.uprobe_multi.pid; - if (!upath || !uoffsets || !cnt) + if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3421,10 +3422,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; } - pid = attr->link_create.uprobe_multi.pid; if (pid) { rcu_read_lock(); - task = get_pid_task(find_vpid(pid), PIDTYPE_PID); + task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); rcu_read_unlock(); if (!task) { err = -ESRCH; diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 8269cdee33ae..38fda42fd70f 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -397,7 +397,7 @@ static void test_attach_api_fails(void) link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); if (!ASSERT_ERR(link_fd, "link_fd")) goto cleanup; - ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong"); + ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong"); cleanup: if (link_fd >= 0) -- 2.43.0

11 months, 1 week

1
0
0 0

Railway Interchange Expo

by Deanne Walton

Hi There, Would you be interested in acquiring an attendees list of Railway Interchange Expo? No. of Attendees: 8,500 Date : May 20th to 22nd Location: Indianapolis, USA List Contains - Attendee name, Job Title, Business Name, Web Address, Physical Address, Phone Number, Official Email address, etc., Interested? I will send you more details and cost. Regards, Deanne Walton |Demand Generation Executive

11 months, 1 week

1
0
0 0

[REGRESSION] ETXTBSY when running Yarn (Node) since af5d68f

by Andrew Udvare

#regzbot introduced: v6.8..v6.9-rc1 https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… Since the above commit present in 6.9+, Node running a Yarn installation that executes a subprocess always shows the following: /test # yarn --offline install yarn install v1.22.22 warning package.json: "test" is also the name of a node core module warning test(a)1.0.0: "test" is also the name of a node core module [1/4] Resolving packages... [2/4] Fetching packages... [3/4] Linking dependencies... [4/4] Building fresh packages... error /test/node_modules/snyk: Command failed. Exit code: 126 Command: node wrapper_dist/bootstrap.js exec Arguments: Directory: /test/node_modules/snyk Output: /bin/sh: node: Text file busy The commit was found by bisection with a simple initramfs that just runs 'yarn --offline install' with a test project and cached Yarn packages. To reproduce: npm install -g yarn mkdir test cd test cat > package.json <<EOF { "name": "test", "version": "1.0.0", "main": "index.js", "license": "MIT", "dependencies": { "snyk": "^1.1291.0" } } EOF yarn install Modern Yarn will give the same result but with slightly different output. This also appears to affect node-gyp: https://github.com/nodejs/node/issues/53051 See also: https://bugs.gentoo.org/931942 -- Andrew

11 months, 1 week

1
0
0 0

[PATCH 6.1.y] net: tls: handle backlogging of crypto requests

by Srish Srinivasan

From: Jakub Kicinski <kuba(a)kernel.org> commit 8590541473188741055d27b955db0777569438e3 upstream Since we're setting the CRYPTO_TFM_REQ_MAY_BACKLOG flag on our requests to the crypto API, crypto_aead_{encrypt,decrypt} can return -EBUSY instead of -EINPROGRESS in valid situations. For example, when the cryptd queue for AESNI is full (easy to trigger with an artificially low cryptd.cryptd_max_cpu_qlen), requests will be enqueued to the backlog but still processed. In that case, the async callback will also be called twice: first with err == -EINPROGRESS, which it seems we can just ignore, then with err == 0. Compared to Sabrina's original patch this version uses the new tls_*crypt_async_wait() helpers and converts the EBUSY to EINPROGRESS to avoid having to modify all the error handling paths. The handling is identical. Fixes: a54667f6728c ("tls: Add support for encryption using async offload accelerator") Fixes: 94524d8fc965 ("net/tls: Add support for async decryption of tls records") Co-developed-by: Sabrina Dubroca <sd(a)queasysnail.net> Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> Link: https://lore.kernel.org/netdev/9681d1febfec295449a62300938ed2ae66983f28.169… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> [Srish: fixed merge-conflict in stable branch linux-6.1.y, needs to go on top of https://lore.kernel.org/stable/20240307155930.913525-1-lee@kernel.org/] Signed-off-by: Srish Srinivasan <srish.srinivasan(a)broadcom.com> --- net/tls/tls_sw.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2bd27b777..61b01dfc6 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -195,6 +195,17 @@ static void tls_decrypt_done(crypto_completion_data_t *data, int err) struct sock *sk; int aead_size; + /* If requests get too backlogged crypto API returns -EBUSY and calls + * ->complete(-EINPROGRESS) immediately followed by ->complete(0) + * to make waiting for backlog to flush with crypto_wait_req() easier. + * First wait converts -EBUSY -> -EINPROGRESS, and the second one + * -EINPROGRESS -> 0. + * We have a single struct crypto_async_request per direction, this + * scheme doesn't help us, so just ignore the first ->complete(). + */ + if (err == -EINPROGRESS) + return; + aead_size = sizeof(*aead_req) + crypto_aead_reqsize(aead); aead_size = ALIGN(aead_size, __alignof__(*dctx)); dctx = (void *)((u8 *)aead_req + aead_size); @@ -268,6 +279,10 @@ static int tls_do_decryption(struct sock *sk, } ret = crypto_aead_decrypt(aead_req); + if (ret == -EBUSY) { + ret = tls_decrypt_async_wait(ctx); + ret = ret ?: -EINPROGRESS; + } if (ret == -EINPROGRESS) { if (darg->async) return 0; @@ -452,6 +467,9 @@ static void tls_encrypt_done(crypto_completion_data_t *data, int err) bool ready = false; struct sock *sk; + if (err == -EINPROGRESS) /* see the comment in tls_decrypt_done() */ + return; + rec = container_of(aead_req, struct tls_rec, aead_req); msg_en = &rec->msg_encrypted; @@ -560,6 +578,10 @@ static int tls_do_encryption(struct sock *sk, atomic_inc(&ctx->encrypt_pending); rc = crypto_aead_encrypt(aead_req); + if (rc == -EBUSY) { + rc = tls_encrypt_async_wait(ctx); + rc = rc ?: -EINPROGRESS; + } if (!rc || rc != -EINPROGRESS) { atomic_dec(&ctx->encrypt_pending); sge->offset -= prot->prepend_size; -- 2.34.1

11 months, 1 week

3
7
0 0

[PATCH] usb: typec: tcpm: Ignore received Hard Reset in TOGGLING state

by Kyle Tso

Similar to what fixed in Commit a6fe37f428c1 ("usb: typec: tcpm: Skip hard reset when in error recovery"), the handling of the received Hard Reset has to be skipped during TOGGLING state. [ 4086.021288] VBUS off [ 4086.021295] pending state change SNK_READY -> SNK_UNATTACHED @ 650 ms [rev2 NONE_AMS] [ 4086.022113] VBUS VSAFE0V [ 4086.022117] state change SNK_READY -> SNK_UNATTACHED [rev2 NONE_AMS] [ 4086.022447] VBUS off [ 4086.022450] state change SNK_UNATTACHED -> SNK_UNATTACHED [rev2 NONE_AMS] [ 4086.023060] VBUS VSAFE0V [ 4086.023064] state change SNK_UNATTACHED -> SNK_UNATTACHED [rev2 NONE_AMS] [ 4086.023070] disable BIST MODE TESTDATA [ 4086.023766] disable vbus discharge ret:0 [ 4086.023911] Setting usb_comm capable false [ 4086.028874] Setting voltage/current limit 0 mV 0 mA [ 4086.028888] polarity 0 [ 4086.030305] Requesting mux state 0, usb-role 0, orientation 0 [ 4086.033539] Start toggling [ 4086.038496] state change SNK_UNATTACHED -> TOGGLING [rev2 NONE_AMS] // This Hard Reset is unexpected [ 4086.038499] Received hard reset [ 4086.038501] state change TOGGLING -> HARD_RESET_START [rev2 HARD_RESET] Fixes: f0690a25a140 ("staging: typec: USB Type-C Port Manager (tcpm)") Cc: stable(a)vger.kernel.org Signed-off-by: Kyle Tso <kyletso(a)google.com> --- drivers/usb/typec/tcpm/tcpm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 8a1af08f71b6..9c1cb8c11bd6 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -6172,6 +6172,7 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port) port->tcpc->set_bist_data(port->tcpc, false); switch (port->state) { + case TOGGLING: case ERROR_RECOVERY: case PORT_RESET: case PORT_RESET_WAIT_OFF: -- 2.45.0.rc1.225.g2a3ae87e7f-goog

11 months, 1 week

2
1
0 0

[PATCH v1] usb: typec: tcpm: fix use-after-free case in tcpm_register_source_caps

by Amit Sunil Dhamne

There could be a potential use-after-free case in tcpm_register_source_caps(). This could happen when: * new (say invalid) source caps are advertised * the existing source caps are unregistered * tcpm_register_source_caps() returns with an error as usb_power_delivery_register_capabilities() fails This causes port->partner_source_caps to hold on to the now freed source caps. Reset port->partner_source_caps value to NULL after unregistering existing source caps. Fixes: 230ecdf71a64 ("usb: typec: tcpm: unregister existing source caps before re-registration") Cc: stable(a)vger.kernel.org Signed-off-by: Amit Sunil Dhamne <amitsd(a)google.com> --- drivers/usb/typec/tcpm/tcpm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 8a1af08f71b6..be4127ef84e9 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -3014,8 +3014,10 @@ static int tcpm_register_source_caps(struct tcpm_port *port) memcpy(caps.pdo, port->source_caps, sizeof(u32) * port->nr_source_caps); caps.role = TYPEC_SOURCE; - if (cap) + if (cap) { usb_power_delivery_unregister_capabilities(cap); + port->partner_source_caps = NULL; + } cap = usb_power_delivery_register_capabilities(port->partner_pd, &caps); if (IS_ERR(cap)) base-commit: 51474ab44abf907023a8a875e799b07de461e466 -- 2.45.0.rc1.225.g2a3ae87e7f-goog

11 months, 1 week

4
3
0 0

[PATCH] btrfs: re-introduce 'norecovery' mount option

by Qu Wenruo

Although 'norecovery' mount option is marked deprecated for a long time and a warning message is introduced during the deprecation window, it's still actively utilized by several projects that need a safely way to mount a btrfs without any writes. Furthermore this 'norecovery' mount option is supported by most major filesystems, which makes it harder to validate our motivation. This patch would re-introduce the 'norecovery' mount option, and output a message to recommend 'rescue=nologreplay' option. Link: https://lore.kernel.org/linux-btrfs/ZkxZT0J-z0GYvfy8@gardel-login/#t Link: https://github.com/systemd/systemd/pull/32892 Link: https://bugzilla.suse.com/show_bug.cgi?id=1222429 Reported-by: Lennart Poettering <lennart(a)poettering.net> Reported-by: Jiri Slaby <jslaby(a)suse.com> Fixes: a1912f712188 ("btrfs: remove code for inode_cache and recovery mount options") Cc: stable(a)vger.kernel.org # 6.8+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> --- fs/btrfs/super.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 2dbc930a20f7..f05cce7c8b8d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -119,6 +119,7 @@ enum { Opt_thread_pool, Opt_treelog, Opt_user_subvol_rm_allowed, + Opt_norecovery, /* Rescue options */ Opt_rescue, @@ -245,6 +246,8 @@ static const struct fs_parameter_spec btrfs_fs_parameters[] = { __fsparam(NULL, "nologreplay", Opt_nologreplay, fs_param_deprecated, NULL), /* Deprecated, with alias rescue=usebackuproot */ __fsparam(NULL, "usebackuproot", Opt_usebackuproot, fs_param_deprecated, NULL), + /* For compatibility only, alias for "rescue=nologreplay". */ + fsparam_flag("norecovery", Opt_norecovery), /* Debugging options. */ fsparam_flag_no("enospc_debug", Opt_enospc_debug), @@ -438,6 +441,11 @@ static int btrfs_parse_param(struct fs_context *fc, struct fs_parameter *param) "'nologreplay' is deprecated, use 'rescue=nologreplay' instead"); btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY); break; + case Opt_norecovery: + btrfs_info(NULL, +"'norecovery' is for compatibility only, recommended to use 'rescue=nologreplay'"); + btrfs_set_opt(ctx->mount_opt, NOLOGREPLAY); + break; case Opt_flushoncommit: if (result.negated) btrfs_clear_opt(ctx->mount_opt, FLUSHONCOMMIT); -- 2.45.1

11 months, 1 week

4
4
0 0

[tip: x86/urgent] x86/topology: Handle bogus ACPI tables correctly

by tip-bot2 for Thomas Gleixner

The following commit has been merged into the x86/urgent branch of tip: Commit-ID: 9d22c96316ac59ed38e80920c698fed38717b91b Gitweb: https://git.kernel.org/tip/9d22c96316ac59ed38e80920c698fed38717b91b Author: Thomas Gleixner <tglx(a)linutronix.de> AuthorDate: Fri, 17 May 2024 16:40:36 +02:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Tue, 21 May 2024 14:52:35 +02:00 x86/topology: Handle bogus ACPI tables correctly The ACPI specification clearly states how the processors should be enumerated in the MADT: "To ensure that the boot processor is supported post initialization, two guidelines should be followed. The first is that OSPM should initialize processors in the order that they appear in the MADT. The second is that platform firmware should list the boot processor as the first processor entry in the MADT. ... Failure of OSPM implementations and platform firmware to abide by these guidelines can result in both unpredictable and non optimal platform operation." The kernel relies on that ordering to detect the real BSP on crash kernels which is important to avoid sending a INIT IPI to it as that would cause a full machine reset. On a Dell XPS 16 9640 the BIOS ignores this rule and enumerates the CPUs in the wrong order. As a consequence the kernel falsely detects a crash kernel and disables the corresponding CPU. Prevent this by checking the IA32_APICBASE MSR for the BSP bit on the boot CPU. If that bit is set, then the MADT based BSP detection can be safely ignored. If the kernel detects a mismatch between the BSP bit and the first enumerated MADT entry then emit a firmware bug message. This obviously also has to be taken into account when the boot APIC ID and the first enumerated APIC ID match. If the boot CPU does not have the BSP bit set in the APICBASE MSR then there is no way for the boot CPU to determine which of the CPUs is the real BSP. Sending an INIT to the real BSP would reset the machine so the only sane way to deal with that is to limit the number of CPUs to one and emit a corresponding warning message. Fixes: 5c5682b9f87a ("x86/cpu: Detect real BSP on crash kernels") Reported-by: Carsten Tolkmit <ctolkmit(a)ennit.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Carsten Tolkmit <ctolkmit(a)ennit.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/87le48jycb.ffs@tglx Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218837 --- arch/x86/kernel/cpu/topology.c | 53 +++++++++++++++++++++++++++++++-- 1 file changed, 50 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index d17c9b7..621a151 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -128,6 +128,9 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) static __init bool check_for_real_bsp(u32 apic_id) { + bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6; + u64 msr; + /* * There is no real good way to detect whether this a kdump() * kernel, but except on the Voyager SMP monstrosity which is not @@ -144,17 +147,61 @@ static __init bool check_for_real_bsp(u32 apic_id) if (topo_info.real_bsp_apic_id != BAD_APICID) return false; + /* + * Check whether the enumeration order is broken by evaluating the + * BSP bit in the APICBASE MSR. If the CPU does not have the + * APICBASE MSR then the BSP detection is not possible and the + * kernel must rely on the firmware enumeration order. + */ + if (has_apic_base) { + rdmsrl(MSR_IA32_APICBASE, msr); + is_bsp = !!(msr & MSR_IA32_APICBASE_BSP); + } + if (apic_id == topo_info.boot_cpu_apic_id) { - topo_info.real_bsp_apic_id = apic_id; - return false; + /* + * If the boot CPU has the APIC BSP bit set then the + * firmware enumeration is agreeing. If the CPU does not + * have the APICBASE MSR then the only choice is to trust + * the enumeration order. + */ + if (is_bsp || !has_apic_base) { + topo_info.real_bsp_apic_id = apic_id; + return false; + } + /* + * If the boot APIC is enumerated first, but the APICBASE + * MSR does not have the BSP bit set, then there is no way + * to discover the real BSP here. Assume a crash kernel and + * limit the number of CPUs to 1 as an INIT to the real BSP + * would reset the machine. + */ + pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id); + pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n"); + set_nr_cpu_ids(1); + goto fwbug; } - pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x > %x\n", + pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n", topo_info.boot_cpu_apic_id, apic_id); + + if (is_bsp) { + /* + * The boot CPU has the APIC BSP bit set. Use it and complain + * about the broken firmware enumeration. + */ + topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id; + goto fwbug; + } + pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); topo_info.real_bsp_apic_id = apic_id; return true; + +fwbug: + pr_warn(FW_BUG "APIC enumeration order not specification compliant\n"); + return false; } static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level,

11 months, 1 week

1
0
0 0

[PATCH v2 3/3] selftests/mm: compaction_test: Fix bogus test success and reduce probability of OOM-killer invocation

by Dev Jain

Reset nr_hugepages to zero before the start of the test. If a non-zero number of hugepages is already set before the start of the test, the following problems arise: - The probability of the test getting OOM-killed increases. Proof: The test wants to run on 80% of available memory to prevent OOM-killing (see original code comments). Let the value of mem_free at the start of the test, when nr_hugepages = 0, be x. In the other case, when nr_hugepages > 0, let the memory consumed by hugepages be y. In the former case, the test operates on 0.8 * x of memory. In the latter, the test operates on 0.8 * (x - y) of memory, with y already filled, hence, memory consumed is y + 0.8 * (x - y) = 0.8 * x + 0.2 * y > 0.8 * x. Q.E.D - The probability of a bogus test success increases. Proof: Let the memory consumed by hugepages be greater than 25% of x, with x and y defined as above. The definition of compaction_index is c_index = (x - y)/z where z is the memory consumed by hugepages after trying to increase them again. In check_compaction(), we set the number of hugepages to zero, and then increase them back; the probability that they will be set back to consume at least y amount of memory again is very high (since there is not much delay between the two attempts of changing nr_hugepages). Hence, z >= y > (x/4) (by the 25% assumption). Therefore, c_index = (x - y)/z <= (x - y)/y = x/y - 1 < 4 - 1 = 3 hence, c_index can always be forced to be less than 3, thereby the test succeeding always. Q.E.D Changes in v2: - Handle unsigned long number of hugepages v1: - https://lore.kernel.org/all/20240515093633.54814-3-dev.jain@arm.com/ NOTE: This patch depends on the previous one. Fixes: bd67d5c15cc1 ("Test compaction of mlocked memory") Cc: stable(a)vger.kernel.org Signed-off-by: Dev Jain <dev.jain(a)arm.com> --- tools/testing/selftests/mm/compaction_test.c | 71 ++++++++++++++------ 1 file changed, 49 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 5e9bd1da9370..e140558e6f53 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -82,13 +82,16 @@ int prereq(void) return -1; } -int check_compaction(unsigned long mem_free, unsigned long hugepage_size) +int check_compaction(unsigned long mem_free, unsigned long hugepage_size, + unsigned long initial_nr_hugepages) { unsigned long nr_hugepages_ul; int fd, ret = -1; int compaction_index = 0; - char initial_nr_hugepages[20] = {0}; char nr_hugepages[20] = {0}; + char init_nr_hugepages[20] = {0}; + + sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -102,23 +105,6 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size) goto out; } - if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - lseek(fd, 0, SEEK_SET); - - /* Start with the initial condition of 0 huge pages*/ - if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - lseek(fd, 0, SEEK_SET); - /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { @@ -146,8 +132,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size) lseek(fd, 0, SEEK_SET); - if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) - != strlen(initial_nr_hugepages)) { + if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) + != strlen(init_nr_hugepages)) { ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", strerror(errno)); goto close_fd; @@ -171,6 +157,41 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size) return ret; } +int set_zero_hugepages(unsigned long *initial_nr_hugepages) +{ + int fd, ret = -1; + char nr_hugepages[20] = {0}; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto out; + } + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + /* Start with the initial condition of 0 huge pages */ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + *initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10); + ret = 0; + + close_fd: + close(fd); + + out: + return ret; +} int main(int argc, char **argv) { @@ -181,6 +202,7 @@ int main(int argc, char **argv) unsigned long mem_free = 0; unsigned long hugepage_size = 0; long mem_fragmentable_MB = 0; + unsigned long initial_nr_hugepages; ksft_print_header(); @@ -189,6 +211,10 @@ int main(int argc, char **argv) ksft_set_plan(1); + /* Start the test without hugepages reducing mem_free */ + if (set_zero_hugepages(&initial_nr_hugepages)) + ksft_exit_fail(); + lim.rlim_cur = RLIM_INFINITY; lim.rlim_max = RLIM_INFINITY; if (setrlimit(RLIMIT_MEMLOCK, &lim)) @@ -232,7 +258,8 @@ int main(int argc, char **argv) entry = entry->next; } - if (check_compaction(mem_free, hugepage_size) == 0) + if (check_compaction(mem_free, hugepage_size, + initial_nr_hugepages) == 0) ksft_exit_pass(); ksft_exit_fail(); -- 2.34.1

11 months, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2024