October 2024 - Linux-stable-mirror

Re: Patch "selftests: vDSO: skip getrandom test if architecture is unsupported" has been added to the 6.11-stable tree

by Jason A. Donenfeld

This is not stable material and I didn't mark it as such. Do not backport.

7 months, 1 week

3
13
0 0

[PATCH HID] HID: bpf: fix cfi stubs for hid_bpf_ops

by Benjamin Tissoires

With the introduction of commit e42ac1418055 ("bpf: Check unsupported ops from the bpf_struct_ops's cfi_stubs"), a HID-BPF struct_ops containing a .hid_hw_request() or a .hid_hw_output_report() was failing to load as the cfi stubs were not defined. Fix that by defining those simple static functions and restore HID-BPF functionality. This was detected with the HID selftests suddenly failing on Linus' tree. Cc: stable(a)vger.kernel.org # v6.11+ Fixes: 9286675a2aed ("HID: bpf: add HID-BPF hooks for hid_hw_output_report") Fixes: 8bd0488b5ea5 ("HID: bpf: add HID-BPF hooks for hid_hw_raw_requests") Signed-off-by: Benjamin Tissoires <bentiss(a)kernel.org> --- Hi, This commit should directly go in Linus tree before we start creating topic branches for 6.13 given that the CI is now failing on our HID master branch. Cheers, Benjamin --- drivers/hid/bpf/hid_bpf_struct_ops.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/hid/bpf/hid_bpf_struct_ops.c b/drivers/hid/bpf/hid_bpf_struct_ops.c index cd696c59ba0f..702c22fae136 100644 --- a/drivers/hid/bpf/hid_bpf_struct_ops.c +++ b/drivers/hid/bpf/hid_bpf_struct_ops.c @@ -276,9 +276,23 @@ static int __hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx) return 0; } +static int __hid_bpf_hw_request(struct hid_bpf_ctx *ctx, unsigned char reportnum, + enum hid_report_type rtype, enum hid_class_request reqtype, + u64 source) +{ + return 0; +} + +static int __hid_bpf_hw_output_report(struct hid_bpf_ctx *ctx, u64 source) +{ + return 0; +} + static struct hid_bpf_ops __bpf_hid_bpf_ops = { .hid_device_event = __hid_bpf_device_event, .hid_rdesc_fixup = __hid_bpf_rdesc_fixup, + .hid_hw_request = __hid_bpf_hw_request, + .hid_hw_output_report = __hid_bpf_hw_output_report, }; static struct bpf_struct_ops bpf_hid_bpf_ops = { --- base-commit: 13882369ceb9b0953f9f5ff8563bbccfd80d0ffd change-id: 20240927-fix-hid-bpf-stubs-f80591a673c2 Best regards, -- Benjamin Tissoires <bentiss(a)kernel.org>

7 months, 1 week

3
2
0 0

[PATCH 5.15.y] usb: typec: tcpm: Check for port partner validity before consuming it

by Sherry Yang

From: Badhri Jagan Sridharan <badhri(a)google.com> commit ae11f04b452b5205536e1c02d31f8045eba249dd upstream. typec_register_partner() does not guarantee partner registration to always succeed. In the event of failure, port->partner is set to the error value or NULL. Given that port->partner validity is not checked, this results in the following crash: Unable to handle kernel NULL pointer dereference at virtual address xx pc : run_state_machine+0x1bc8/0x1c08 lr : run_state_machine+0x1b90/0x1c08 .. Call trace: run_state_machine+0x1bc8/0x1c08 tcpm_state_machine_work+0x94/0xe4 kthread_worker_fn+0x118/0x328 kthread+0x1d0/0x23c ret_from_fork+0x10/0x20 To prevent the crash, check for port->partner validity before derefencing it in all the call sites. Cc: stable(a)vger.kernel.org Fixes: c97cd0b4b54e ("usb: typec: tcpm: set initial svdm version based on pd revision") Signed-off-by: Badhri Jagan Sridharan <badhri(a)google.com> Reviewed-by: Heikki Krogerus <heikki.krogerus(a)linux.intel.com> Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> Link: https://lore.kernel.org/r/20240427202812.3435268-1-badhri@google.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [Sherry: bp to 5.15.y, minor conflicts due to missing commit: 8203d26905ee ("usb: typec: tcpm: Register USB Power Delivery Capabilities"). Ignore the the part typec_partner_set_usb_power_delivery() which is not in 5.15.y.] Signed-off-by: Sherry Yang <sherry.yang(a)oracle.com> --- This is a fix for CVE-2024-36893. --- drivers/usb/typec/tcpm/tcpm.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 5a5886cb0c00..2104bb6e61f5 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -1471,7 +1471,8 @@ static void svdm_consume_identity(struct tcpm_port *port, const u32 *p, int cnt) port->partner_ident.cert_stat = p[VDO_INDEX_CSTAT]; port->partner_ident.product = product; - typec_partner_set_identity(port->partner); + if (port->partner) + typec_partner_set_identity(port->partner); tcpm_log(port, "Identity: %04x:%04x.%04x", PD_IDH_VID(vdo), @@ -1559,6 +1560,9 @@ static void tcpm_register_partner_altmodes(struct tcpm_port *port) struct typec_altmode *altmode; int i; + if (!port->partner) + return; + for (i = 0; i < modep->altmodes; i++) { altmode = typec_partner_register_altmode(port->partner, &modep->altmode_desc[i]); @@ -3577,7 +3581,10 @@ static int tcpm_init_vconn(struct tcpm_port *port) static void tcpm_typec_connect(struct tcpm_port *port) { + struct typec_partner *partner; + if (!port->connected) { + port->connected = true; /* Make sure we don't report stale identity information */ memset(&port->partner_ident, 0, sizeof(port->partner_ident)); port->partner_desc.usb_pd = port->pd_capable; @@ -3587,9 +3594,13 @@ static void tcpm_typec_connect(struct tcpm_port *port) port->partner_desc.accessory = TYPEC_ACCESSORY_AUDIO; else port->partner_desc.accessory = TYPEC_ACCESSORY_NONE; - port->partner = typec_register_partner(port->typec_port, - &port->partner_desc); - port->connected = true; + partner = typec_register_partner(port->typec_port, &port->partner_desc); + if (IS_ERR(partner)) { + dev_err(port->dev, "Failed to register partner (%ld)\n", PTR_ERR(partner)); + return; + } + + port->partner = partner; } } @@ -3658,8 +3669,10 @@ static int tcpm_src_attach(struct tcpm_port *port) static void tcpm_typec_disconnect(struct tcpm_port *port) { if (port->connected) { - typec_unregister_partner(port->partner); - port->partner = NULL; + if (port->partner) { + typec_unregister_partner(port->partner); + port->partner = NULL; + } port->connected = false; } } @@ -3868,6 +3881,9 @@ static enum typec_cc_status tcpm_pwr_opmode_to_rp(enum typec_pwr_opmode opmode) static void tcpm_set_initial_svdm_version(struct tcpm_port *port) { + if (!port->partner) + return; + switch (port->negotiated_rev) { case PD_REV30: break; -- 2.46.0

7 months, 1 week

1
0
0 0

[PATCH net] hv_netvsc: Fix VF namespace also in netvsc_open

by Haiyang Zhang

The existing code moves VF to the same namespace as the synthetic device during netvsc_register_vf(). But, if the synthetic device is moved to a new namespace after the VF registration, the VF won't be moved together. To make the behavior more consistent, add a namespace check to netvsc_open(), and move the VF if it is not in the same namespace. Cc: stable(a)vger.kernel.org Fixes: c0a41b887ce6 ("hv_netvsc: move VF to same namespace as netvsc device") Signed-off-by: Haiyang Zhang <haiyangz(a)microsoft.com> --- drivers/net/hyperv/netvsc_drv.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 153b97f8ec0d..9caade092524 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -134,6 +134,19 @@ static int netvsc_open(struct net_device *net) } if (vf_netdev) { + if (!net_eq(dev_net(net), dev_net(vf_netdev))) { + ret = dev_change_net_namespace(vf_netdev, dev_net(net), + "eth%d"); + if (ret) + netdev_err(vf_netdev, + "Cannot move to same namespace as %s: %d\n", + net->name, ret); + else + netdev_info(vf_netdev, + "Moved VF to namespace with: %s\n", + net->name); + } + /* Setting synthetic device up transparently sets * slave as up. If open fails, then slave will be * still be offline (and not used). -- 2.34.1

7 months, 1 week

3
4
0 0

[PATCH net] xfrm: fix one more kernel-infoleak in algo dumping

by Petr Vaganov

During fuzz testing, the following issue was discovered: BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x598/0x2a30 _copy_to_iter+0x598/0x2a30 __skb_datagram_iter+0x168/0x1060 skb_copy_datagram_iter+0x5b/0x220 netlink_recvmsg+0x362/0x1700 sock_recvmsg+0x2dc/0x390 __sys_recvfrom+0x381/0x6d0 __x64_sys_recvfrom+0x130/0x200 x64_sys_call+0x32c8/0x3cc0 do_syscall_64+0xd8/0x1c0 entry_SYSCALL_64_after_hwframe+0x79/0x81 Uninit was stored to memory at: copy_to_user_state_extra+0xcc1/0x1e00 dump_one_state+0x28c/0x5f0 xfrm_state_walk+0x548/0x11e0 xfrm_dump_sa+0x1e0/0x840 netlink_dump+0x943/0x1c40 __netlink_dump_start+0x746/0xdb0 xfrm_user_rcv_msg+0x429/0xc00 netlink_rcv_skb+0x613/0x780 xfrm_netlink_rcv+0x77/0xc0 netlink_unicast+0xe90/0x1280 netlink_sendmsg+0x126d/0x1490 __sock_sendmsg+0x332/0x3d0 ____sys_sendmsg+0x863/0xc30 ___sys_sendmsg+0x285/0x3e0 __x64_sys_sendmsg+0x2d6/0x560 x64_sys_call+0x1316/0x3cc0 do_syscall_64+0xd8/0x1c0 entry_SYSCALL_64_after_hwframe+0x79/0x81 Uninit was created at: __kmalloc+0x571/0xd30 attach_auth+0x106/0x3e0 xfrm_add_sa+0x2aa0/0x4230 xfrm_user_rcv_msg+0x832/0xc00 netlink_rcv_skb+0x613/0x780 xfrm_netlink_rcv+0x77/0xc0 netlink_unicast+0xe90/0x1280 netlink_sendmsg+0x126d/0x1490 __sock_sendmsg+0x332/0x3d0 ____sys_sendmsg+0x863/0xc30 ___sys_sendmsg+0x285/0x3e0 __x64_sys_sendmsg+0x2d6/0x560 x64_sys_call+0x1316/0x3cc0 do_syscall_64+0xd8/0x1c0 entry_SYSCALL_64_after_hwframe+0x79/0x81 Bytes 328-379 of 732 are uninitialized Memory access of size 732 starts at ffff88800e18e000 Data copied to user address 00007ff30f48aff0 CPU: 2 PID: 18167 Comm: syz-executor.0 Not tainted 6.8.11 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Fixes copying of xfrm algorithms where some random data of the structure fields can end up in userspace. Padding in structures may be filled with random (possibly sensitve) data and should never be given directly to user-space. A similar issue was resolved in the commit 8222d5910dae ("xfrm: Zero padding when dumping algos and encap") Found by Linux Verification Center (linuxtesting.org) with Syzkaller. Fixes: c7a5899eb26e ("xfrm: redact SA secret with lockdown confidentiality") Cc: stable(a)vger.kernel.org Co-developed-by: Boris Tonofa <b.tonofa(a)ideco.ru> Signed-off-by: Boris Tonofa <b.tonofa(a)ideco.ru> Signed-off-by: Petr Vaganov <p.vaganov(a)ideco.ru> --- net/xfrm/xfrm_user.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 55f039ec3d59..97faeb3574ea 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1098,7 +1098,9 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) if (!nla) return -EMSGSIZE; ap = nla_data(nla); - memcpy(ap, auth, sizeof(struct xfrm_algo_auth)); + strscpy_pad(ap->alg_name, auth->alg_name, sizeof(sizeof(ap->alg_name))); + ap->alg_key_len = auth->alg_key_len; + ap->alg_trunc_len = auth->alg_trunc_len; if (redact_secret && auth->alg_key_len) memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8); else -- 2.46.1

7 months, 1 week

2
1
0 0

[PATCH v4 0/4] ov08x40: Enable use of ov08x40 on Qualcomm X1E80100 CRD

by Bryan O'Donoghue

Changes in v4: - Drops link-frequencies from properties: as discussed here: https://lore.kernel.org/r/Zv6STSKeNNlT83ux@kekkonen.localdomain - Link to v3: https://lore.kernel.org/r/20241002-b4-master-24-11-25-ov08x40-v3-0-483bcdcf… Changes in v3: - Drops assigned-clock-* from description retains in example - Sakari, Krzysztof - Updates example fake clock names to ov08x40_* instead of copy/paste ov9282_clk -> ov08x40_clk, ov9282_clk_parent -> ov08x40_clk_parent - bod - Link to v2: https://lore.kernel.org/r/20241001-b4-master-24-11-25-ov08x40-v2-0-e478976b… Changes in v2: - Drops "-" in ovti,ov08x40.yaml after description: - Rob - Adds ":" after first line of description text - Rob - dts -> DT in commit log - Rob - Removes dependency on 'xvclk' as a name in yaml and driver - Sakari - Uses assigned-clock, assigned-clock-parents and assigned-clock-rates - Sakari - Drops clock-frequency - Sakarai, Krzysztof - Drops dovdd-supply, avdd-supply, dvdd-supply and reset-gpios as required, its perfectly possible not to have the reset GPIO or the power rails under control of the SoC. - bod - Link to v1: https://lore.kernel.org/r/20240926-b4-master-24-11-25-ov08x40-v1-0-e4d5fbd3… V1: This series brings fixes and updates to ov08x40 which allows for use of this sensor on the Qualcomm x1e80100 CRD but also on any other dts based system. Firstly there's a fix for the pseudo burst mode code that was added in 8f667d202384 ("media: ov08x40: Reduce start streaming time"). Not every I2C controller can handle an arbitrary sized write, this is the case on Qualcomm CAMSS/CCI I2C sensor interfaces which limit the transaction size and communicate this limit via I2C quirks. A simple fix to optionally break up the large submitted burst into chunks not exceeding adapter->quirk size fixes. Secondly then is addition of a yaml description for the ov08x40 and extension of the driver to support OF probe and powering on of the power rails from the driver instead of from ACPI. Once done the sensor works without further modification on the Qualcomm x1e80100 CRD. Signed-off-by: Bryan O'Donoghue <bryan.odonoghue(a)linaro.org> --- Bryan O'Donoghue (4): media: ov08x40: Fix burst write sequence media: dt-bindings: Add OmniVision OV08X40 media: ov08x40: Rename ext_clk to xvclk media: ov08x40: Add OF probe support .../bindings/media/i2c/ovti,ov08x40.yaml | 114 +++++++++++++ drivers/media/i2c/ov08x40.c | 179 ++++++++++++++++++--- 2 files changed, 270 insertions(+), 23 deletions(-) --- base-commit: 2b7275670032a98cba266bd1b8905f755b3e650f change-id: 20240926-b4-master-24-11-25-ov08x40-c6f477aaa6a4 Best regards, -- Bryan O'Donoghue <bryan.odonoghue(a)linaro.org>

7 months, 1 week

1
1
0 0

[PATCH v5 2/5] tpm: Implement tpm2_load_null() rollback

by Jarkko Sakkinen

tpm2_load_null() has weak and broken error handling: - The return value of tpm2_create_primary() is ignored. - Leaks TPM return codes from tpm2_load_context() to the caller. - If the key name comparison succeeds returns previous error instead of zero to the caller. Implement a proper error rollback. Cc: stable(a)vger.kernel.org # v6.10+ Fixes: eb24c9788cd9 ("tpm: disable the TPM if NULL name changes") Signed-off-by: Jarkko Sakkinen <jarkko(a)kernel.org> --- v5: - Fix the TPM error code leak from tpm2_load_context(). v4: - No changes. v3: - Update log messages. Previously the log message incorrectly stated on load failure that integrity check had been failed, even tho the check is done *after* the load operation. v2: - Refined the commit message. - Reverted tpm2_create_primary() changes. They are not required if tmp_null_key is used as the parameter. --- drivers/char/tpm/tpm2-sessions.c | 43 +++++++++++++++++--------------- 1 file changed, 23 insertions(+), 20 deletions(-) diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index 0f09ac33ae99..a856adef18d3 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -915,33 +915,36 @@ static int tpm2_parse_start_auth_session(struct tpm2_auth *auth, static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key) { - int rc; unsigned int offset = 0; /* dummy offset for null seed context */ u8 name[SHA256_DIGEST_SIZE + 2]; + u32 tmp_null_key; + int rc; rc = tpm2_load_context(chip, chip->null_key_context, &offset, - null_key); - if (rc != -EINVAL) - return rc; + &tmp_null_key); + if (rc != -EINVAL) { + if (!rc) + *null_key = tmp_null_key; + goto err; + } - /* an integrity failure may mean the TPM has been reset */ - dev_err(&chip->dev, "NULL key integrity failure!\n"); - /* check the null name against what we know */ - tpm2_create_primary(chip, TPM2_RH_NULL, NULL, name); - if (memcmp(name, chip->null_key_name, sizeof(name)) == 0) - /* name unchanged, assume transient integrity failure */ - return rc; - /* - * Fatal TPM failure: the NULL seed has actually changed, so - * the TPM must have been illegally reset. All in-kernel TPM - * operations will fail because the NULL primary can't be - * loaded to salt the sessions, but disable the TPM anyway so - * userspace programmes can't be compromised by it. - */ - dev_err(&chip->dev, "NULL name has changed, disabling TPM due to interference\n"); + rc = tpm2_create_primary(chip, TPM2_RH_NULL, &tmp_null_key, name); + if (rc) + goto err; + + /* Return the null key if the name has not been changed: */ + if (memcmp(name, chip->null_key_name, sizeof(name)) == 0) { + *null_key = tmp_null_key; + return 0; + } + + /* Deduce from the name change TPM interference: */ + dev_err(&chip->dev, "the null key integrity check failedh\n"); + tpm2_flush_context(chip, tmp_null_key); chip->flags |= TPM_CHIP_FLAG_DISABLE; - return rc; +err: + return rc ? -ENODEV : rc; } /** -- 2.46.1

7 months, 1 week

2
1
0 0

[PATCH -fixes] riscv: Fix kernel stack size when KASAN is enabled

by Alexandre Ghiti

We use Kconfig to select the kernel stack size, doubling the default size if KASAN is enabled. But that actually only works if KASAN is selected from the beginning, meaning that if KASAN config is added later (for example using menuconfig), CONFIG_THREAD_SIZE_ORDER won't be updated, keeping the default size, which is not enough for KASAN as reported in [1]. So fix this by moving the logic to compute the right kernel stack into a header. Fixes: a7555f6b62e7 ("riscv: stack: Add config of thread stack size") Reported-by: syzbot+ba9eac24453387a9d502(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/000000000000eb301906222aadc2@google.com/ [1] Cc: stable(a)vger.kernel.org Signed-off-by: Alexandre Ghiti <alexghiti(a)rivosinc.com> --- arch/riscv/Kconfig | 3 +-- arch/riscv/include/asm/thread_info.h | 7 ++++++- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index ccbfd28f4982..b65846d02622 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -759,8 +759,7 @@ config IRQ_STACKS config THREAD_SIZE_ORDER int "Kernel stack size (in power-of-two numbers of page size)" if VMAP_STACK && EXPERT range 0 4 - default 1 if 32BIT && !KASAN - default 3 if 64BIT && KASAN + default 1 if 32BIT default 2 help Specify the Pages of thread stack size (from 4KB to 64KB), which also diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index fca5c6be2b81..385b43211a71 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -13,7 +13,12 @@ #include <linux/sizes.h> /* thread information allocation */ -#define THREAD_SIZE_ORDER CONFIG_THREAD_SIZE_ORDER +#ifdef CONFIG_KASAN +#define KASAN_STACK_ORDER 1 +#else +#define KASAN_STACK_ORDER 0 +#endif +#define THREAD_SIZE_ORDER (CONFIG_THREAD_SIZE_ORDER + KASAN_STACK_ORDER) #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) /* -- 2.39.2

7 months, 1 week

2
1
0 0

[PATCH v2] bus: mhi: host: free buffer on error in mhi_alloc_bhie_table

by Fedor Pchelkin

img_info->mhi_buf should be freed on error path in mhi_alloc_bhie_table(). This error case is rare but still needs to be fixed. Found by Linux Verification Center (linuxtesting.org). Fixes: 3000f85b8f47 ("bus: mhi: core: Add support for basic PM operations") Cc: stable(a)vger.kernel.org Signed-off-by: Fedor Pchelkin <pchelkin(a)ispras.ru> --- v2: add missing Cc: stable, as Greg Kroah-Hartman's bot reported drivers/bus/mhi/host/boot.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bus/mhi/host/boot.c b/drivers/bus/mhi/host/boot.c index edc0ec5a0933..738dcd11b66f 100644 --- a/drivers/bus/mhi/host/boot.c +++ b/drivers/bus/mhi/host/boot.c @@ -357,6 +357,7 @@ int mhi_alloc_bhie_table(struct mhi_controller *mhi_cntrl, for (--i, --mhi_buf; i >= 0; i--, mhi_buf--) dma_free_coherent(mhi_cntrl->cntrl_dev, mhi_buf->len, mhi_buf->buf, mhi_buf->dma_addr); + kfree(img_info->mhi_buf); error_alloc_mhi_buf: kfree(img_info); -- 2.39.2

7 months, 1 week

2
2
0 0

[PATCH] sched: psi: fix bogus pressure spikes from aggregation race

by Johannes Weiner

Brandon reports sporadic, non-sensical spikes in cumulative pressure time (total=) when reading cpu.pressure at a high rate. This is due to a race condition between reader aggregation and tasks changing states. While it affects all states and all resources captured by PSI, in practice it most likely triggers with CPU pressure, since scheduling events are so frequent compared to other resource events. The race context is the live snooping of ongoing stalls during a pressure read. The read aggregates per-cpu records for stalls that have concluded, but will also incorporate ad-hoc the duration of any active state that hasn't been recorded yet. This is important to get timely measurements of ongoing stalls. Those ad-hoc samples are calculated on-the-fly up to the current time on that CPU; since the stall hasn't concluded, it's expected that this is the minimum amount of stall time that will enter the per-cpu records once it does. The problem is that the path that concludes the state uses a CPU clock read that is not synchronized against aggregators; the clock is read outside of the seqlock protection. This allows aggregators to race and snoop a stall with a longer duration than will actually be recorded. With the recorded stall time being less than the last snapshot remembered by the aggregator, a subsequent sample will underflow and observe a bogus delta value, resulting in an erratic jump in pressure. Fix this by moving the clock read of the state change into the seqlock protection. This ensures no aggregation can snoop live stalls past the time that's recorded when the state concludes. Reported-by: Brandon Duffany <brandon(a)buildbuddy.io> Link: https://bugzilla.kernel.org/show_bug.cgi?id=219194 Link: https://lore.kernel.org/lkml/20240827121851.GB438928@cmpxchg.org/ Fixes: df77430639c9 ("psi: Reduce calls to sched_clock() in psi") Cc: stable(a)vger.kernel.org Signed-off-by: Johannes Weiner <hannes(a)cmpxchg.org> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> --- kernel/sched/psi.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 020d58967d4e..84dad1511d1e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -769,12 +769,13 @@ static void record_times(struct psi_group_cpu *groupc, u64 now) } static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set, u64 now, + unsigned int clear, unsigned int set, bool wake_clock) { struct psi_group_cpu *groupc; unsigned int t, m; u32 state_mask; + u64 now; lockdep_assert_rq_held(cpu_rq(cpu)); groupc = per_cpu_ptr(group->pcpu, cpu); @@ -789,6 +790,7 @@ static void psi_group_change(struct psi_group *group, int cpu, * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); /* * Start with TSK_ONCPU, which doesn't have a corresponding @@ -899,18 +901,15 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; - u64 now; if (!task->pid) return; psi_flags_change(task, clear, set); - now = cpu_clock(cpu); - group = task_psi_group(task); do { - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, true); } while ((group = group->parent)); } @@ -919,7 +918,6 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - u64 now = cpu_clock(cpu); if (next->pid) { psi_flags_change(next, 0, TSK_ONCPU); @@ -936,7 +934,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, break; } - psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); + psi_group_change(group, cpu, 0, TSK_ONCPU, true); } while ((group = group->parent)); } @@ -974,7 +972,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, do { if (group == common) break; - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); } while ((group = group->parent)); /* @@ -986,7 +984,7 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; for (; group; group = group->parent) - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); } } } @@ -997,8 +995,8 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st int cpu = task_cpu(curr); struct psi_group *group; struct psi_group_cpu *groupc; - u64 now, irq; s64 delta; + u64 irq; if (static_branch_likely(&psi_disabled)) return; @@ -1011,7 +1009,6 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st if (prev && task_psi_group(prev) == group) return; - now = cpu_clock(cpu); irq = irq_time_read(cpu); delta = (s64)(irq - rq->psi_irq_time); if (delta < 0) @@ -1019,12 +1016,15 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st rq->psi_irq_time = irq; do { + u64 now; + if (!group->enabled) continue; groupc = per_cpu_ptr(group->pcpu, cpu); write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); record_times(groupc, now); groupc->times[PSI_IRQ_FULL] += delta; @@ -1223,11 +1223,9 @@ void psi_cgroup_restart(struct psi_group *group) for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); struct rq_flags rf; - u64 now; rq_lock_irq(rq, &rf); - now = cpu_clock(cpu); - psi_group_change(group, cpu, 0, 0, now, true); + psi_group_change(group, cpu, 0, 0, true); rq_unlock_irq(rq, &rf); } } -- 2.46.2

7 months, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror October 2024