January 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] bpf: Fix out of bounds access for ringbuf helpers" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 64620e0a1e712a778095bd35cbb277dc2259281f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann <daniel(a)iogearbox.net> Date: Tue, 11 Jan 2022 14:43:41 +0000 Subject: [PATCH] bpf: Fix out of bounds access for ringbuf helpers Both bpf_ringbuf_submit() and bpf_ringbuf_discard() have ARG_PTR_TO_ALLOC_MEM in their bpf_func_proto definition as their first argument. They both expect the result from a prior bpf_ringbuf_reserve() call which has a return type of RET_PTR_TO_ALLOC_MEM_OR_NULL. Meaning, after a NULL check in the code, the verifier will promote the register type in the non-NULL branch to a PTR_TO_MEM and in the NULL branch to a known zero scalar. Generally, pointer arithmetic on PTR_TO_MEM is allowed, so the latter could have an offset. The ARG_PTR_TO_ALLOC_MEM expects a PTR_TO_MEM register type. However, the non- zero result from bpf_ringbuf_reserve() must be fed into either bpf_ringbuf_submit() or bpf_ringbuf_discard() but with the original offset given it will then read out the struct bpf_ringbuf_hdr mapping. The verifier missed to enforce a zero offset, so that out of bounds access can be triggered which could be used to escalate privileges if unprivileged BPF was enabled (disabled by default in kernel). Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it") Reported-by: <tr3e.wang(a)gmail.com> (SecCoder Security Lab) Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Acked-by: Alexei Starovoitov <ast(a)kernel.org> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e0b3f4d683eb..c72c57a6684f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5318,9 +5318,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: case PTR_TO_STACK: + /* Some of the argument types nevertheless require a + * zero register offset. + */ + if (arg_type == ARG_PTR_TO_ALLOC_MEM) + goto force_off_check; break; /* All the rest must be rejected: */ default: +force_off_check: err = __check_ptr_off_reg(env, reg, regno, type == PTR_TO_BTF_ID); if (err < 0)

8 months, 1 week

3
19
0 0

[PATCH v4] media: ucvideo: Add quirk for Logitech Rally Bar

by Ricardo Ribalda

Logitech Rally Bar devices, despite behaving as UVC cameras, have a different power management system that the other cameras from Logitech. USB_QUIRK_RESET_RESUME is applied to all the UVC cameras from Logitech at the usb core. Unfortunately, USB_QUIRK_RESET_RESUME causes undesired USB disconnects, that make them completely unusable. Instead of creating a list for this family of devices in the core, let's create a quirk in the UVC driver. Fixes: e387ef5c47dd ("usb: Add USB_QUIRK_RESET_RESUME for all Logitech UVC webcams") Cc: stable(a)vger.kernel.org Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Alan Stern <stern(a)rowland.harvard.edu> Acked-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Ricardo Ribalda <ribalda(a)chromium.org> --- Tested with a Rallybar Mini with an Acer Chromebook Spin 513 --- Changes in v4: - Include Logi Rally Bar Huddle (Thanks Kyle!) - Link to v3: https://lore.kernel.org/r/20240102-rallybar-v3-1-0ab197ce4aa2@chromium.org Changes in v3: - Move quirk to uvc driver - Link to v2: https://lore.kernel.org/r/20231222-rallybar-v2-1-5849d62a9514@chromium.org Changes in v2: - Add Fixes tag - Add UVC maintainer as Cc - Link to v1: https://lore.kernel.org/r/20231222-rallybar-v1-1-82b2a4d3106f@chromium.org --- drivers/media/usb/uvc/uvc_driver.c | 30 ++++++++++++++++++++++++++++++ drivers/media/usb/uvc/uvcvideo.h | 1 + 2 files changed, 31 insertions(+) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 08fcd2ffa727..9663bcac6843 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/usb.h> +#include <linux/usb/quirks.h> #include <linux/usb/uvc.h> #include <linux/videodev2.h> #include <linux/vmalloc.h> @@ -2233,6 +2234,8 @@ static int uvc_probe(struct usb_interface *intf, } uvc_dbg(dev, PROBE, "UVC device initialized\n"); + if (dev->quirks & UVC_QUIRK_FORCE_RESUME) + udev->quirks &= ~USB_QUIRK_RESET_RESUME; usb_enable_autosuspend(udev); return 0; @@ -2574,6 +2577,33 @@ static const struct usb_device_id uvc_ids[] = { .bInterfaceSubClass = 1, .bInterfaceProtocol = 0, .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_RESTORE_CTRLS_ON_INIT) }, + /* Logitech Rally Bar Huddle */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x087c, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_FORCE_RESUME) }, + /* Logitech Rally Bar */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x089b, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_FORCE_RESUME) }, + /* Logitech Rally Bar Mini */ + { .match_flags = USB_DEVICE_ID_MATCH_DEVICE + | USB_DEVICE_ID_MATCH_INT_INFO, + .idVendor = 0x046d, + .idProduct = 0x08d3, + .bInterfaceClass = USB_CLASS_VIDEO, + .bInterfaceSubClass = 1, + .bInterfaceProtocol = 0, + .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_FORCE_RESUME) }, /* Chicony CNF7129 (Asus EEE 100HE) */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | USB_DEVICE_ID_MATCH_INT_INFO, diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h index 6fb0a78b1b00..fa59a21d2a28 100644 --- a/drivers/media/usb/uvc/uvcvideo.h +++ b/drivers/media/usb/uvc/uvcvideo.h @@ -73,6 +73,7 @@ #define UVC_QUIRK_FORCE_Y8 0x00000800 #define UVC_QUIRK_FORCE_BPP 0x00001000 #define UVC_QUIRK_WAKE_AUTOSUSPEND 0x00002000 +#define UVC_QUIRK_FORCE_RESUME 0x00004000 /* Format flags */ #define UVC_FMT_FLAG_COMPRESSED 0x00000001 --- base-commit: c0f65a7c112b3cfa691cead54bcf24d6cc2182b5 change-id: 20231222-rallybar-19ce0c64d5e6 Best regards, -- Ricardo Ribalda <ribalda(a)chromium.org>

9 months, 1 week

6
10
0 0

[PATCH v2] irqchip/sifive-plic: enable interrupt if needed before EOI

by Nam Cao

RISC-V PLIC cannot "end-of-interrupt" (EOI) disabled interrupts, as explained in the description of Interrupt Completion in the PLIC spec: "The PLIC signals it has completed executing an interrupt handler by writing the interrupt ID it received from the claim to the claim/complete register. The PLIC does not check whether the completion ID is the same as the last claim ID for that target. If the completion ID does not match an interrupt source that *is currently enabled* for the target, the completion is silently ignored." Commit 69ea463021be ("irqchip/sifive-plic: Fixup EOI failed when masked") ensured that EOI is successful by enabling interrupt first, before EOI. Commit a1706a1c5062 ("irqchip/sifive-plic: Separate the enable and mask operations") removed the interrupt enabling code from the previous commit, because it assumes that interrupt should already be enabled at the point of EOI. However, this is incorrect: there is a window after a hart claiming an interrupt and before irq_desc->lock getting acquired, interrupt can be disabled during this window. Thus, EOI can be invoked while the interrupt is disabled, effectively nullify this EOI. This results in the interrupt never gets asserted again, and the device who uses this interrupt appears frozen. Make sure that interrupt is really enabled before EOI. Fixes: a1706a1c5062 ("irqchip/sifive-plic: Separate the enable and mask operations") Cc: <stable(a)vger.kernel.org> Signed-off-by: Nam Cao <namcao(a)linutronix.de> --- v2: - add unlikely() for optimization - re-word commit message to make it clearer drivers/irqchip/irq-sifive-plic.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index e1484905b7bd..0a233e9d9607 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -148,7 +148,13 @@ static void plic_irq_eoi(struct irq_data *d) { struct plic_handler *handler = this_cpu_ptr(&plic_handlers); - writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + if (unlikely(irqd_irq_disabled(d))) { + plic_toggle(handler, d->hwirq, 1); + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + plic_toggle(handler, d->hwirq, 0); + } else { + writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); + } } #ifdef CONFIG_SMP -- 2.39.2

9 months, 1 week

4
4
0 0

[PATCH v3 1/1] driver core: Keep the supplier fwnode consistent with the device

by Herve Codina

The commit 3a2dbc510c43 ("driver core: fw_devlink: Don't purge child fwnode's consumer links") introduces the possibility to use the supplier's parent device instead of the supplier itself. In that case the supplier fwnode used is not updated and is no more consistent with the supplier device used. Use the fwnode consistent with the supplier device when checking flags. Fixes: 3a2dbc510c43 ("driver core: fw_devlink: Don't purge child fwnode's consumer links") Cc: stable(a)vger.kernel.org Signed-off-by: Herve Codina <herve.codina(a)bootlin.com> --- Changes v2 -> v3: Do not update the supplier handle in order to keep the original handle for debug traces. Changes v1 -> v2: Remove sup_handle check and related pr_debug() call as sup_handle cannot be invalid if sup_dev is valid. drivers/base/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 4d8b315c48a1..440b52ec027f 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2082,7 +2082,7 @@ static int fw_devlink_create_devlink(struct device *con, * supplier device indefinitely. */ if (sup_dev->links.status == DL_DEV_NO_DRIVER && - sup_handle->flags & FWNODE_FLAG_INITIALIZED) { + sup_dev->fwnode->flags & FWNODE_FLAG_INITIALIZED) { dev_dbg(con, "Not linking %pfwf - dev might never probe\n", sup_handle); -- 2.41.0

9 months, 1 week

2
3
0 0

[REGRESSION] 6.7.1: md: raid5 hang and unresponsive system; successfully bisected

by Dan Moulding

After upgrading from 6.7.0 to 6.7.1 a couple of my systems with md RAID-5 arrays started experiencing hangs. It starts with some processes which write to the array getting stuck. The whole system eventually becomes unresponsive and unclean shutdown must be performed (poweroff and reboot don't work). While trying to diagnose the issue, I noticed that the md0_raid5 kernel thread consumes 100% CPU after the issue occurs. No relevant warnings or errors were found in dmesg. On 6.7.1, I can reproduce the issue somewhat reliably by copying a large amount of data to the array. I am unable to reproduce the issue at all on 6.7.0. The bisection was a bit difficult since I don't have a 100% reliable method to reproduce the problem, but with some perseverence I eventually managed to whittle it down to commit 0de40f76d567 ("Revert "md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d"). After reverting that commit (i.e. reapplying the reverted commit) on top of 6.7.1 I can no longer reproduce the problem at all. Some details that might be relevant: - Both systems are running MD RAID-5 with a journal device. - mdadm in monitor mode is always running on both systems. - Both systems were previously running 6.7.0 and earlier just fine. - The older of the two systems has been running a raid5 array without incident for many years (kernel going back to at least 5.1) -- this is the first raid5 issue it has encountered. Please let me know if there is any other helpful information that I might be able to provide. -- Dan #regzbot introduced: 0de40f76d567133b871cd6ad46bb87afbce46983

9 months, 1 week

9
52
0 0

[PATCH] powerpc: xor_vmx: Add '-mhard-float' to CFLAGS

by Nathan Chancellor

arch/powerpc/lib/xor_vmx.o is built with '-msoft-float' (from the main powerpc Makefile) and '-maltivec' (from its CFLAGS), which causes an error when building with clang after a recent change in main: error: option '-msoft-float' cannot be specified with '-maltivec' make[6]: *** [scripts/Makefile.build:243: arch/powerpc/lib/xor_vmx.o] Error 1 Explicitly add '-mhard-float' before '-maltivec' in xor_vmx.o's CFLAGS to override the previous inclusion of '-msoft-float' (as the last option wins), which matches how other areas of the kernel use '-maltivec', such as AMDGPU. Cc: stable(a)vger.kernel.org Closes: https://github.com/ClangBuiltLinux/linux/issues/1986 Link: https://github.com/llvm/llvm-project/commit/4792f912b232141ecba4cbae538873b… Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> --- arch/powerpc/lib/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 6eac63e79a89..0ab65eeb93ee 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -76,7 +76,7 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o obj-$(CONFIG_ALTIVEC) += xor_vmx.o xor_vmx_glue.o -CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec) +CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec) # Enable <altivec.h> CFLAGS_xor_vmx.o += -isystem $(shell $(CC) -print-file-name=include) --- base-commit: 6613476e225e090cc9aad49be7fa504e290dd33d change-id: 20240127-ppc-xor_vmx-drop-msoft-float-ad68b437f86c Best regards, -- Nathan Chancellor <nathan(a)kernel.org>

9 months, 2 weeks

3
4
0 0

[PATCH v3 2/6] usb: dwc3: gadget: cancel requests instead of release after missed isoc

by Dan Vacura

From: Jeff Vanhoof <qjv001(a)motorola.com> arm-smmu related crashes seen after a Missed ISOC interrupt when no_interrupt=1 is used. This can happen if the hardware is still using the data associated with a TRB after the usb_request's ->complete call has been made. Instead of immediately releasing a request when a Missed ISOC interrupt has occurred, this change will add logic to cancel the request instead where it will eventually be released when the END_TRANSFER command has completed. This logic is similar to some of the cleanup done in dwc3_gadget_ep_dequeue. Fixes: 6d8a019614f3 ("usb: dwc3: gadget: check for Missed Isoc from event status") Cc: <stable(a)vger.kernel.org> Signed-off-by: Jeff Vanhoof <qjv001(a)motorola.com> Co-developed-by: Dan Vacura <w36195(a)motorola.com> Signed-off-by: Dan Vacura <w36195(a)motorola.com> --- V1 -> V3: - no change, new patch in series drivers/usb/dwc3/core.h | 1 + drivers/usb/dwc3/gadget.c | 38 ++++++++++++++++++++++++++------------ 2 files changed, 27 insertions(+), 12 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 8f9959ba9fd4..9b005d912241 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -943,6 +943,7 @@ struct dwc3_request { #define DWC3_REQUEST_STATUS_DEQUEUED 3 #define DWC3_REQUEST_STATUS_STALLED 4 #define DWC3_REQUEST_STATUS_COMPLETED 5 +#define DWC3_REQUEST_STATUS_MISSED_ISOC 6 #define DWC3_REQUEST_STATUS_UNKNOWN -1 u8 epnum; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 079cd333632e..411532c5c378 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2021,6 +2021,9 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) case DWC3_REQUEST_STATUS_STALLED: dwc3_gadget_giveback(dep, req, -EPIPE); break; + case DWC3_REQUEST_STATUS_MISSED_ISOC: + dwc3_gadget_giveback(dep, req, -EXDEV); + break; default: dev_err(dwc->dev, "request cancelled with wrong reason:%d\n", req->status); dwc3_gadget_giveback(dep, req, -ECONNRESET); @@ -3402,21 +3405,32 @@ static bool dwc3_gadget_endpoint_trbs_complete(struct dwc3_ep *dep, struct dwc3 *dwc = dep->dwc; bool no_started_trb = true; - dwc3_gadget_ep_cleanup_completed_requests(dep, event, status); + if (status == -EXDEV) { + struct dwc3_request *tmp; + struct dwc3_request *req; - if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) - goto out; + if (!(dep->flags & DWC3_EP_END_TRANSFER_PENDING)) + dwc3_stop_active_transfer(dep, true, true); - if (!dep->endpoint.desc) - return no_started_trb; + list_for_each_entry_safe(req, tmp, &dep->started_list, list) + dwc3_gadget_move_cancelled_request(req, + DWC3_REQUEST_STATUS_MISSED_ISOC); + } else { + dwc3_gadget_ep_cleanup_completed_requests(dep, event, status); - if (usb_endpoint_xfer_isoc(dep->endpoint.desc) && - list_empty(&dep->started_list) && - (list_empty(&dep->pending_list) || status == -EXDEV)) - dwc3_stop_active_transfer(dep, true, true); - else if (dwc3_gadget_ep_should_continue(dep)) - if (__dwc3_gadget_kick_transfer(dep) == 0) - no_started_trb = false; + if (dep->flags & DWC3_EP_END_TRANSFER_PENDING) + goto out; + + if (!dep->endpoint.desc) + return no_started_trb; + + if (usb_endpoint_xfer_isoc(dep->endpoint.desc) && + list_empty(&dep->started_list) && list_empty(&dep->pending_list)) + dwc3_stop_active_transfer(dep, true, true); + else if (dwc3_gadget_ep_should_continue(dep)) + if (__dwc3_gadget_kick_transfer(dep) == 0) + no_started_trb = false; + } out: /* -- 2.34.1

9 months, 3 weeks

3
12
0 0

FAILED: patch "[PATCH] mptcp: move __mptcp_error_report in protocol.c" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x d5fbeff1ab812b6c473b6924bee8748469462e2c # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100421-divisible-bacterium-18b5@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From d5fbeff1ab812b6c473b6924bee8748469462e2c Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Sat, 16 Sep 2023 12:52:46 +0200 Subject: [PATCH] mptcp: move __mptcp_error_report in protocol.c This will simplify the next patch ("mptcp: process pending subflow error on close"). No functional change intended. Cc: stable(a)vger.kernel.org # v5.12+ Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts <matthieu.baerts(a)tessares.net> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index a7fc16f5175d..915860027b1a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -770,6 +770,42 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) return moved; } +void __mptcp_error_report(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int err = sock_error(ssk); + int ssk_state; + + if (!err) + continue; + + /* only propagate errors on fallen-back sockets or + * on MPC connect + */ + if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) + continue; + + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); + WRITE_ONCE(sk->sk_err, -err); + + /* This barrier is coupled with smp_rmb() in mptcp_poll() */ + smp_wmb(); + sk_error_report(sk); + break; + } +} + /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9bf3c7bc1762..2f40c23fdb0d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1362,42 +1362,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -void __mptcp_error_report(struct sock *sk) -{ - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - int err = sock_error(ssk); - int ssk_state; - - if (!err) - continue; - - /* only propagate errors on fallen-back sockets or - * on MPC connect - */ - if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) - continue; - - /* We need to propagate only transition to CLOSE state. - * Orphaned socket will see such state change via - * subflow_sched_work_if_closed() and that path will properly - * destroy the msk as needed. - */ - ssk_state = inet_sk_state_load(ssk); - if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) - inet_sk_state_store(sk, ssk_state); - WRITE_ONCE(sk->sk_err, -err); - - /* This barrier is coupled with smp_rmb() in mptcp_poll() */ - smp_wmb(); - sk_error_report(sk); - break; - } -} - static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn;

9 months, 3 weeks

3
2
0 0

[PATCH] block: Remove special-casing of compound pages

by Matthew Wilcox (Oracle)

The special casing was originally added in pre-git history; reproducing the commit log here: > commit a318a92567d77 > Author: Andrew Morton <akpm(a)osdl.org> > Date: Sun Sep 21 01:42:22 2003 -0700 > > [PATCH] Speed up direct-io hugetlbpage handling > > This patch short-circuits all the direct-io page dirtying logic for > higher-order pages. Without this, we pointlessly bounce BIOs up to > keventd all the time. In the last twenty years, compound pages have become used for more than just hugetlb. Rewrite these functions to operate on folios instead of pages and remove the special case for hugetlbfs; I don't think it's needed any more (and if it is, we can put it back in as a call to folio_test_hugetlb()). This was found by inspection; as far as I can tell, this bug can lead to pages used as the destination of a direct I/O read not being marked as dirty. If those pages are then reclaimed by the MM without being dirtied for some other reason, they won't be written out. Then when they're faulted back in, they will not contain the data they should. It'll take a pretty unusual setup to produce this problem with several races all going the wrong way. This problem predates the folio work; it could for example have been triggered by mmaping a THP in tmpfs and using that as the target of an O_DIRECT read. Fixes: 800d8c63b2e98 ("shmem: add huge pages support") Cc: stable(a)vger.kernel.org Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> --- block/bio.c | 46 ++++++++++++++++++++++++---------------------- 1 file changed, 24 insertions(+), 22 deletions(-) diff --git a/block/bio.c b/block/bio.c index 8672179213b9..f46d8ec71fbd 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1171,13 +1171,22 @@ EXPORT_SYMBOL(bio_add_folio); void __bio_release_pages(struct bio *bio, bool mark_dirty) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; + struct folio_iter fi; + + bio_for_each_folio_all(fi, bio) { + struct page *page; + size_t done = 0; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (mark_dirty && !PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); - bio_release_page(bio, bvec->bv_page); + if (mark_dirty) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); + } + page = folio_page(fi.folio, fi.offset / PAGE_SIZE); + do { + bio_release_page(bio, page++); + done += PAGE_SIZE; + } while (done < fi.length); } } EXPORT_SYMBOL_GPL(__bio_release_pages); @@ -1455,18 +1464,12 @@ EXPORT_SYMBOL(bio_free_pages); * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions * for performing direct-IO in BIOs. * - * The problem is that we cannot run set_page_dirty() from interrupt context + * The problem is that we cannot run folio_mark_dirty() from interrupt context * because the required locks are not interrupt-safe. So what we can do is to * mark the pages dirty _before_ performing IO. And in interrupt context, * check that the pages are still dirty. If so, fine. If not, redirty them * in process context. * - * We special-case compound pages here: normally this means reads into hugetlb - * pages. The logic in here doesn't really work right for compound pages - * because the VM does not uniformly chase down the head page in all cases. - * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't - * handle them at all. So we skip compound pages here at an early stage. - * * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. @@ -1482,12 +1485,12 @@ EXPORT_SYMBOL(bio_free_pages); */ void bio_set_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; - struct bvec_iter_all iter_all; + struct folio_iter fi; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); + bio_for_each_folio_all(fi, bio) { + folio_lock(fi.folio); + folio_mark_dirty(fi.folio); + folio_unlock(fi.folio); } } @@ -1530,12 +1533,11 @@ static void bio_dirty_fn(struct work_struct *work) void bio_check_pages_dirty(struct bio *bio) { - struct bio_vec *bvec; + struct folio_iter fi; unsigned long flags; - struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, iter_all) { - if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page)) + bio_for_each_folio_all(fi, bio) { + if (!folio_test_dirty(fi.folio)) goto defer; } -- 2.40.1

9 months, 4 weeks

7
10
0 0

FAILED: patch "[PATCH] mptcp: rename timer related helper to less confusing names" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x f6909dc1c1f4452879278128012da6c76bc186a5 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023100402-launder-percent-3d59@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f6909dc1c1f4452879278128012da6c76bc186a5 Mon Sep 17 00:00:00 2001 From: Paolo Abeni <pabeni(a)redhat.com> Date: Sat, 16 Sep 2023 12:52:48 +0200 Subject: [PATCH] mptcp: rename timer related helper to less confusing names The msk socket uses to different timeout to track close related events and retransmissions. The existing helpers do not indicate clearly which timer they actually touch, making the related code quite confusing. Change the existing helpers name to avoid such confusion. No functional change intended. This patch is linked to the next one ("mptcp: fix dangling connection hang-up"). The two patches are supposed to be backported together. Cc: stable(a)vger.kernel.org # v5.11+ Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts(a)tessares.net> Reviewed-by: Mat Martineau <martineau(a)kernel.org> Signed-off-by: Matthieu Baerts <matthieu.baerts(a)tessares.net> Signed-off-by: David S. Miller <davem(a)davemloft.net> diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1c96b8da71df..c8f38f303a90 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -405,7 +405,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, return false; } -static void mptcp_stop_timer(struct sock *sk) +static void mptcp_stop_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -911,12 +911,12 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list } } -static bool mptcp_timer_pending(struct sock *sk) +static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); } -static void mptcp_reset_timer(struct sock *sk) +static void mptcp_reset_rtx_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; @@ -1050,10 +1050,10 @@ static void __mptcp_clean_una(struct sock *sk) out: if (snd_una == READ_ONCE(msk->snd_nxt) && snd_una == READ_ONCE(msk->write_seq)) { - if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) - mptcp_stop_timer(sk); + if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) + mptcp_stop_rtx_timer(sk); } else { - mptcp_reset_timer(sk); + mptcp_reset_rtx_timer(sk); } } @@ -1626,8 +1626,8 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) mptcp_push_release(ssk, &info); /* ensure the rtx timer is running */ - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (do_check_data_fin) mptcp_check_send_data_fin(sk); } @@ -1690,8 +1690,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) @@ -2260,7 +2260,7 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static void mptcp_timeout_timer(struct timer_list *t) +static void mptcp_tout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2629,14 +2629,14 @@ static void __mptcp_retrans(struct sock *sk) reset_timer: mptcp_check_and_set_pending(sk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; @@ -2669,7 +2669,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); - mptcp_reset_timeout(msk, 0); + mptcp_reset_tout_timer(msk, 0); } static void mptcp_do_fastclose(struct sock *sk) @@ -2758,7 +2758,7 @@ static void __mptcp_init_sock(struct sock *sk) /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); - timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0); + timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) @@ -2849,8 +2849,8 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) } else { pr_debug("Sending DATA_FIN on subflow %p", ssk); tcp_send_ack(ssk); - if (!mptcp_timer_pending(sk)) - mptcp_reset_timer(sk); + if (!mptcp_rtx_timer_pending(sk)) + mptcp_reset_rtx_timer(sk); } break; } @@ -2933,7 +2933,7 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); msk->pm.status = 0; mptcp_release_sched(msk); @@ -3053,7 +3053,7 @@ bool __mptcp_close(struct sock *sk, long timeout) __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - mptcp_reset_timeout(msk, 0); + mptcp_reset_tout_timer(msk, 0); } return do_cancel_work; @@ -3116,7 +3116,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) mptcp_check_listen_stop(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_stop_timer(sk); + mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &sk->sk_timer); if (msk->token) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7254b3562575..5e2026815c8e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -718,7 +718,7 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); -void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); +void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 2f40c23fdb0d..433f290984c8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1226,7 +1226,7 @@ static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) WRITE_ONCE(subflow->fail_tout, fail_tout); tcp_send_ack(ssk); - mptcp_reset_timeout(msk, subflow->fail_tout); + mptcp_reset_tout_timer(msk, subflow->fail_tout); } static bool subflow_check_data_avail(struct sock *ssk)

10 months

2
1
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2024