November 2024 - Linux-stable-mirror

[PATCH v2] gpio: omap: Silence lockdep "Invalid wait context"

by A. Sverdlin

From: Alexander Sverdlin <alexander.sverdlin(a)siemens.com> The problem apparetly has been known since the conversion to raw_spin_lock() (commit 4dbada2be460 ("gpio: omap: use raw locks for locking")). Symptom: [ BUG: Invalid wait context ] 5.10.214 ----------------------------- swapper/1 is trying to lock: (enable_lock){....}-{3:3}, at: clk_enable_lock other info that might help us debug this: context-{5:5} 2 locks held by swapper/1: #0: (&dev->mutex){....}-{4:4}, at: device_driver_attach #1: (&bank->lock){....}-{2:2}, at: omap_gpio_set_config stack backtrace: CPU: 0 PID: 1 Comm: swapper Not tainted 5.10.214 Hardware name: Generic AM33XX (Flattened Device Tree) unwind_backtrace show_stack __lock_acquire lock_acquire.part.0 _raw_spin_lock_irqsave clk_enable_lock clk_enable omap_gpio_set_config gpio_keys_setup_key gpio_keys_probe platform_drv_probe really_probe driver_probe_device device_driver_attach __driver_attach bus_for_each_dev bus_add_driver driver_register do_one_initcall do_initcalls kernel_init_freeable kernel_init Reorder clk_enable()/clk_disable() calls in a way that they always happen outside of raw_spin_lock'ed sections. Cc: stable(a)vger.kernel.org Fixes: 4dbada2be460 ("gpio: omap: use raw locks for locking") Signed-off-by: Alexander Sverdlin <alexander.sverdlin(a)siemens.com> --- Changelog: v2: complete rework, I've totally missed the fact clk_enable()/clk_disable() cannot avoid clk_enable_lock() even if the clock is enabled; I had to extract all clk_*() calls out of raw_spin_lock'ed sections drivers/gpio/gpio-omap.c | 114 +++++++++++++++++++++++++++++---------- 1 file changed, 87 insertions(+), 27 deletions(-) diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 7ad4534054962..3e6c8dec7cacc 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -140,18 +140,22 @@ static void omap_set_gpio_dataout_mask(struct gpio_bank *bank, unsigned offset, BIT(offset), enable); } -static inline void omap_gpio_dbck_enable(struct gpio_bank *bank) +/* Returns true if debounce clock has to be enabled by the caller */ +static inline bool omap_gpio_dbck_enable(struct gpio_bank *bank) { if (bank->dbck_enable_mask && !bank->dbck_enabled) { - clk_enable(bank->dbck); bank->dbck_enabled = true; - writel_relaxed(bank->dbck_enable_mask, bank->base + bank->regs->debounce_en); + + return true; } + + return false; } -static inline void omap_gpio_dbck_disable(struct gpio_bank *bank) +/* Returns true if debounce clock has to be disabled by the caller */ +static inline bool omap_gpio_dbck_disable(struct gpio_bank *bank) { if (bank->dbck_enable_mask && bank->dbck_enabled) { /* @@ -160,10 +164,12 @@ static inline void omap_gpio_dbck_disable(struct gpio_bank *bank) * to detect events and generate interrupts at least on OMAP3. */ writel_relaxed(0, bank->base + bank->regs->debounce_en); - - clk_disable(bank->dbck); bank->dbck_enabled = false; + + return true; } + + return false; } /** @@ -181,9 +187,11 @@ static inline void omap_gpio_dbck_disable(struct gpio_bank *bank) static int omap2_set_gpio_debounce(struct gpio_bank *bank, unsigned offset, unsigned debounce) { + unsigned long flags; u32 val; u32 l; bool enable = !!debounce; + bool enable_clk; if (!bank->dbck_flag) return -ENOTSUPP; @@ -196,13 +204,18 @@ static int omap2_set_gpio_debounce(struct gpio_bank *bank, unsigned offset, l = BIT(offset); + /* + * Ordering is important here: clk_enable() calls spin_lock_irqsave(), + * therefore it must be outside of the following raw_spin_lock_irqsave() + */ clk_enable(bank->dbck); + raw_spin_lock_irqsave(&bank->lock, flags); + writel_relaxed(debounce, bank->base + bank->regs->debounce); val = omap_gpio_rmw(bank->base + bank->regs->debounce_en, l, enable); bank->dbck_enable_mask = val; - clk_disable(bank->dbck); /* * Enable debounce clock per module. * This call is mandatory because in omap_gpio_request() when @@ -211,12 +224,16 @@ static int omap2_set_gpio_debounce(struct gpio_bank *bank, unsigned offset, * used within _gpio_dbck_enable() is still not initialized at * that point. Therefore we have to enable dbck here. */ - omap_gpio_dbck_enable(bank); + enable_clk = omap_gpio_dbck_enable(bank); if (bank->dbck_enable_mask) { bank->context.debounce = debounce; bank->context.debounce_en = val; } + raw_spin_unlock_irqrestore(&bank->lock, flags); + if (!enable_clk) + clk_disable(bank->dbck); + return 0; } @@ -229,16 +246,19 @@ static int omap2_set_gpio_debounce(struct gpio_bank *bank, unsigned offset, * this is the only gpio in this bank using debounce, then clear the debounce * time too. The debounce clock will also be disabled when calling this function * if this is the only gpio in the bank using debounce. + * + * Return: true if bank->bdck clock has to be disabled by the caller, + * false otherwise */ -static void omap_clear_gpio_debounce(struct gpio_bank *bank, unsigned offset) +static bool omap_clear_gpio_debounce(struct gpio_bank *bank, unsigned int offset) { u32 gpio_bit = BIT(offset); if (!bank->dbck_flag) - return; + return false; if (!(bank->dbck_enable_mask & gpio_bit)) - return; + return false; bank->dbck_enable_mask &= ~gpio_bit; bank->context.debounce_en &= ~gpio_bit; @@ -249,9 +269,12 @@ static void omap_clear_gpio_debounce(struct gpio_bank *bank, unsigned offset) bank->context.debounce = 0; writel_relaxed(bank->context.debounce, bank->base + bank->regs->debounce); - clk_disable(bank->dbck); bank->dbck_enabled = false; + + return true; } + + return false; } /* @@ -646,6 +669,7 @@ static void omap_gpio_irq_shutdown(struct irq_data *d) struct gpio_bank *bank = omap_irq_data_get_bank(d); unsigned long flags; unsigned offset = d->hwirq; + bool disable_clk = false; raw_spin_lock_irqsave(&bank->lock, flags); bank->irq_usage &= ~(BIT(offset)); @@ -653,9 +677,17 @@ static void omap_gpio_irq_shutdown(struct irq_data *d) omap_clear_gpio_irqstatus(bank, offset); omap_set_gpio_irqenable(bank, offset, 0); if (!LINE_USED(bank->mod_usage, offset)) - omap_clear_gpio_debounce(bank, offset); + disable_clk = omap_clear_gpio_debounce(bank, offset); omap_disable_gpio_module(bank, offset); raw_spin_unlock_irqrestore(&bank->lock, flags); + + /* + * This has to be done outside of bank->lock'ed section, because + * spin_lock_irqsave(&enable_lock, ...) <= clk_enable_lock() + * cannot be called from raw_spin_lock'ed section. + */ + if (disable_clk) + clk_disable(bank->dbck); } static void omap_gpio_irq_bus_lock(struct irq_data *data) @@ -825,17 +857,26 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset) static void omap_gpio_free(struct gpio_chip *chip, unsigned offset) { struct gpio_bank *bank = gpiochip_get_data(chip); + bool disable_clk = false; unsigned long flags; raw_spin_lock_irqsave(&bank->lock, flags); bank->mod_usage &= ~(BIT(offset)); if (!LINE_USED(bank->irq_usage, offset)) { omap_set_gpio_direction(bank, offset, 1); - omap_clear_gpio_debounce(bank, offset); + disable_clk = omap_clear_gpio_debounce(bank, offset); } omap_disable_gpio_module(bank, offset); raw_spin_unlock_irqrestore(&bank->lock, flags); + /* + * This has to be done outside of bank->lock'ed section, because + * spin_lock_irqsave(&enable_lock, ...) <= clk_enable_lock() + * cannot be called from raw_spin_lock'ed section. + */ + if (disable_clk) + clk_disable(bank->dbck); + pm_runtime_put(chip->parent); } @@ -913,15 +954,11 @@ static int omap_gpio_debounce(struct gpio_chip *chip, unsigned offset, unsigned debounce) { struct gpio_bank *bank; - unsigned long flags; int ret; bank = gpiochip_get_data(chip); - raw_spin_lock_irqsave(&bank->lock, flags); ret = omap2_set_gpio_debounce(bank, offset, debounce); - raw_spin_unlock_irqrestore(&bank->lock, flags); - if (ret) dev_info(chip->parent, "Could not set line %u debounce to %u microseconds (%d)", @@ -1131,7 +1168,8 @@ static void omap_gpio_restore_context(struct gpio_bank *bank) writel_relaxed(bank->context.irqenable2, base + regs->irqenable2); } -static void omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) +/* Returns true if debounce clock has to be disabled by the caller */ +static bool omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) { struct device *dev = bank->chip.parent; void __iomem *base = bank->base; @@ -1175,13 +1213,15 @@ static void omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) bank->context_loss_count = bank->get_context_loss_count(dev); - omap_gpio_dbck_disable(bank); + return omap_gpio_dbck_disable(bank); } -static void omap_gpio_unidle(struct gpio_bank *bank) +/* Returns true if debounce clock has to be enabled by the caller */ +static bool omap_gpio_unidle(struct gpio_bank *bank) { struct device *dev = bank->chip.parent; u32 l = 0, gen, gen0, gen1; + bool enable_clk; int c; /* @@ -1197,7 +1237,7 @@ static void omap_gpio_unidle(struct gpio_bank *bank) bank->get_context_loss_count(dev); } - omap_gpio_dbck_enable(bank); + enable_clk = omap_gpio_dbck_enable(bank); if (bank->loses_context) { if (!bank->get_context_loss_count) { @@ -1207,7 +1247,7 @@ static void omap_gpio_unidle(struct gpio_bank *bank) if (c != bank->context_loss_count) { omap_gpio_restore_context(bank); } else { - return; + return enable_clk; } } } else { @@ -1267,6 +1307,8 @@ static void omap_gpio_unidle(struct gpio_bank *bank) writel_relaxed(old0, bank->base + bank->regs->leveldetect0); writel_relaxed(old1, bank->base + bank->regs->leveldetect1); } + + return enable_clk; } static int gpio_omap_cpu_notifier(struct notifier_block *nb, @@ -1276,6 +1318,8 @@ static int gpio_omap_cpu_notifier(struct notifier_block *nb, unsigned long flags; int ret = NOTIFY_OK; u32 isr, mask; + bool enable_clk = false; + bool disable_clk = false; bank = container_of(nb, struct gpio_bank, nb); @@ -1291,17 +1335,23 @@ static int gpio_omap_cpu_notifier(struct notifier_block *nb, ret = NOTIFY_BAD; break; } - omap_gpio_idle(bank, true); + disable_clk = omap_gpio_idle(bank, true); break; case CPU_CLUSTER_PM_ENTER_FAILED: case CPU_CLUSTER_PM_EXIT: - omap_gpio_unidle(bank); + enable_clk = omap_gpio_unidle(bank); break; } out_unlock: raw_spin_unlock_irqrestore(&bank->lock, flags); + /* This has to happen outside of raw_spin_lock'ed section */ + if (enable_clk) + clk_enable(bank->dbck); + if (disable_clk) + clk_disable(bank->dbck); + return ret; } @@ -1503,12 +1553,17 @@ static int __maybe_unused omap_gpio_runtime_suspend(struct device *dev) { struct gpio_bank *bank = dev_get_drvdata(dev); unsigned long flags; + bool disable_clk; raw_spin_lock_irqsave(&bank->lock, flags); - omap_gpio_idle(bank, true); + disable_clk = omap_gpio_idle(bank, true); bank->is_suspended = true; raw_spin_unlock_irqrestore(&bank->lock, flags); + /* This has to happen outside of raw_spin_lock'ed section */ + if (disable_clk) + clk_disable(bank->dbck); + return 0; } @@ -1516,12 +1571,17 @@ static int __maybe_unused omap_gpio_runtime_resume(struct device *dev) { struct gpio_bank *bank = dev_get_drvdata(dev); unsigned long flags; + bool enable_clk; raw_spin_lock_irqsave(&bank->lock, flags); - omap_gpio_unidle(bank); + enable_clk = omap_gpio_unidle(bank); bank->is_suspended = false; raw_spin_unlock_irqrestore(&bank->lock, flags); + /* This has to happen outside of raw_spin_lock'ed section */ + if (enable_clk) + clk_enable(bank->dbck); + return 0; } -- 2.47.0

1 month

2
1
0 0

bisected: [PATCH V4] x86/apic: Always explicitly disarm TSC-deadline timer

by Sergey Senozhatsky

Hi folks, sorry if messed something up, this email has never been in my inbox. > Disable the TSC Deadline timer in lapic_timer_shutdown() by writing to > MSR_IA32_TSC_DEADLINE when in TSC-deadline mode. Also avoid writing > to the initial-count register (APIC_TMICT) which is ignored in > TSC-deadline mode. So this commit hit stable and we now see section mismatch errors: // stripped WARNING: vmlinux.o(__ex_table+0x447c): Section mismatch in reference from the (unknown reference) (unknown) to the (unknown reference) .irqentry.text:(unknown) The relocation at __ex_table+0x447c references section ".irqentry.text" which is not in the list of authorized sections. WARNING: vmlinux.o(__ex_table+0x4480): Section mismatch in reference from the (unknown reference) (unknown) to the (unknown reference) .irqentry.text:(unknown) The relocation at __ex_table+0x4480 references section ".irqentry.text" which is not in the list of authorized sections. FATAL: modpost: Section mismatches detected. Specifically because of wrmsrl. I'm aware of the section mismatch errors on linux-5.4 (I know), not aware of any other stable versions (but I haven't checked). Is this something specific to linux-5.4?

1 month

3
9
0 0

[PATCH v5 0/2] media: uvcvideo: Support partial control reads and minor changes

by Ricardo Ribalda

Some cameras do not return all the bytes requested from a control if it can fit in less bytes. Eg: returning 0xab instead of 0x00ab. Support these devices. Also, now that we are at it, improve uvc_query_ctrl() logging. Signed-off-by: Ricardo Ribalda <ribalda(a)chromium.org> --- Changes in v5: - Improve comment. - Link to v4: https://lore.kernel.org/r/20241120-uvc-readless-v4-0-4672dbef3d46@chromium.… Changes in v4: - Improve comment. - Keep old likely(ret == size) - Link to v3: https://lore.kernel.org/r/20241118-uvc-readless-v3-0-d97c1a3084d0@chromium.… Changes in v3: - Improve documentation. - Do not change return sequence. - Use dev_ratelimit and dev_warn_once - Link to v2: https://lore.kernel.org/r/20241008-uvc-readless-v2-0-04d9d51aee56@chromium.… Changes in v2: - Rewrite error handling (Thanks Sakari) - Discard 2/3. It is not needed after rewriting the error handling. - Link to v1: https://lore.kernel.org/r/20241008-uvc-readless-v1-0-042ac4581f44@chromium.… --- Ricardo Ribalda (2): media: uvcvideo: Support partial control reads media: uvcvideo: Add more logging to uvc_query_ctrl() drivers/media/usb/uvc/uvc_video.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) --- base-commit: 9852d85ec9d492ebef56dc5f229416c925758edc change-id: 20241008-uvc-readless-23f9b8cad0b3 Best regards, -- Ricardo Ribalda <ribalda(a)chromium.org>

1 month

3
3
0 0

[net PATCH 1/2] selftests: net: lib: fix broken ping with coreutils ping util

by Christian Marangi

If the coreutils variant of ping is used instead of the busybox one, the ping_do() command is broken. This comes by the fact that for coreutils ping, the ping IP needs to be the very last elements. To handle this, reorder the ping args and make $dip last element. The use of coreutils ping might be useful for case where busybox is not compiled with float interval support and ping command doesn't support 0.1 interval. (in such case a dedicated ping utility is installed instead) Cc: stable(a)vger.kernel.org Fixes: 73bae6736b6b ("selftests: forwarding: Add initial testing framework") Signed-off-by: Christian Marangi <ansuelsmth(a)gmail.com> --- tools/testing/selftests/net/forwarding/lib.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index c992e385159c..2060f95d5c62 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1473,8 +1473,8 @@ ping_do() vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name \ - $PING $args $dip -c $PING_COUNT -i 0.1 \ - -w $PING_TIMEOUT &> /dev/null + $PING $args -c $PING_COUNT -i 0.1 \ + -w $PING_TIMEOUT $dip &> /dev/null } ping_test() @@ -1504,8 +1504,8 @@ ping6_do() vrf_name=$(master_name_get $if_name) ip vrf exec $vrf_name \ - $PING6 $args $dip -c $PING_COUNT -i 0.1 \ - -w $PING_TIMEOUT &> /dev/null + $PING6 $args -c $PING_COUNT -i 0.1 \ + -w $PING_TIMEOUT $dip &> /dev/null } ping6_test() -- 2.45.2

1 month

2
10
0 0

[PATCH] riscv/ptrace: add new regset to get original a0 register

by Celeste Liu

The orig_a0 is missing in struct user_regs_struct of riscv, and there is no way to add it without breaking UAPI. (See Link tag below) Like NT_ARM_SYSTEM_CALL do, we add a new regset name NT_RISCV_ORIG_A0 to access original a0 register from userspace via ptrace API. Link: https://lore.kernel.org/all/59505464-c84a-403d-972f-d4b2055eeaac@gmail.com/ Signed-off-by: Celeste Liu <uwu(a)coelacanthus.name> --- arch/riscv/kernel/ptrace.c | 33 +++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 2 files changed, 34 insertions(+) diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index ea67e9fb7a583683b922fe2c017ea61f3bc848db..faa46de9000376eb445a32d43a40210d7b846844 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -31,6 +31,7 @@ enum riscv_regset { #ifdef CONFIG_RISCV_ISA_SUPM REGSET_TAGGED_ADDR_CTRL, #endif + REGSET_ORIG_A0, }; static int riscv_gpr_get(struct task_struct *target, @@ -184,6 +185,30 @@ static int tagged_addr_ctrl_set(struct task_struct *target, } #endif +static int riscv_orig_a0_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + return membuf_store(&to, task_pt_regs(target)->orig_a0); +} + +static int riscv_orig_a0_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int orig_a0 = task_pt_regs(target)->orig_a0; + int ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &orig_a0, 0, -1); + if (ret) + return ret; + + task_pt_regs(target)->orig_a0 = orig_a0; + return ret; +} + + static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { .core_note_type = NT_PRSTATUS, @@ -224,6 +249,14 @@ static const struct user_regset riscv_user_regset[] = { .set = tagged_addr_ctrl_set, }, #endif + [REGSET_ORIG_A0] = { + .core_note_type = NT_RISCV_ORIG_A0, + .n = 1, + .size = sizeof(elf_greg_t), + .align = sizeof(elf_greg_t), + .regset_get = riscv_orig_a0_get, + .set = riscv_orig_a0_set, + }, }; static const struct user_regset_view riscv_user_native_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b44069d29cecc0f9de90ee66bfffd2137f4275a8..390060229601631da2fb27030d9fa2142e676c14 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -452,6 +452,7 @@ typedef struct elf64_shdr { #define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ #define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ #define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NT_RISCV_ORIG_A0 0x903 /* RISC-V original a0 register */ #define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ #define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ --- base-commit: 0e287d31b62bb53ad81d5e59778384a40f8b6f56 change-id: 20241201-riscv-new-regset-d529b952ad0d Best regards, -- Celeste Liu <uwu(a)coelacanthus.name>

1 month

4
6
0 0

[PATCH net-next] virtio_net: drop netdev_tx_reset_queue() from virtnet_enable_queue_pair()

by Koichiro Den

When virtnet_close is followed by virtnet_open, some TX completions can possibly remain unconsumed, until they are finally processed during the first NAPI poll after the netdev_tx_reset_queue(), resulting in a crash [1]. Commit b96ed2c97c79 ("virtio_net: move netdev_tx_reset_queue() call before RX napi enable") seems not sufficient to eliminate all BQL crash scenarios for virtio-net. This issue can be reproduced with the latest net-next master by running: `while :; do ip l set DEV down; ip l set DEV up; done` under heavy network TX load from inside the machine. netdev_tx_reset_queue() can actually be dropped from virtnet_open path; the device is not stopped in any case. For BQL core part, it's just like traffic nearly ceases to exist for some period. For stall detector added to BQL, even if virtnet_close could somehow lead to some TX completions delayed for long, followed by virtnet_open, we can just take it as stall as mentioned in commit 6025b9135f7a ("net: dqs: add NIC stall detector based on BQL"). Note also that users can still reset stall_max via sysfs. So, drop netdev_tx_reset_queue() from virtnet_enable_queue_pair(). This eliminates the BQL crashes. With this patch, virtio-net performs only one dql_reset() per probe. [1]: ------------[ cut here ]------------ kernel BUG at lib/dynamic_queue_limits.c:99! Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 7 UID: 0 PID: 1598 Comm: ip Tainted: G N 6.12.0net-next_main+ #2 Tainted: [N]=TEST Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), \ BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014 RIP: 0010:dql_completed+0x26b/0x290 Code: b7 c2 49 89 e9 44 89 da 89 c6 4c 89 d7 e8 ed 17 47 00 58 65 ff 0d 4d 27 90 7e 0f 85 fd fe ff ff e8 ea 53 8d ff e9 f3 fe ff ff <0f> 0b 01 d2 44 89 d1 29 d1 ba 00 00 00 00 0f 48 ca e9 28 ff ff ff RSP: 0018:ffffc900002b0d08 EFLAGS: 00010297 RAX: 0000000000000000 RBX: ffff888102398c80 RCX: 0000000080190009 RDX: 0000000000000000 RSI: 000000000000006a RDI: 0000000000000000 RBP: ffff888102398c00 R08: 0000000000000000 R09: 0000000000000000 R10: 00000000000000ca R11: 0000000000015681 R12: 0000000000000001 R13: ffffc900002b0d68 R14: ffff88811115e000 R15: ffff8881107aca40 FS: 00007f41ded69500(0000) GS:ffff888667dc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000556ccc2dc1a0 CR3: 0000000104fd8003 CR4: 0000000000772ef0 PKRU: 55555554 Call Trace: <IRQ> ? die+0x32/0x80 ? do_trap+0xd9/0x100 ? dql_completed+0x26b/0x290 ? dql_completed+0x26b/0x290 ? do_error_trap+0x6d/0xb0 ? dql_completed+0x26b/0x290 ? exc_invalid_op+0x4c/0x60 ? dql_completed+0x26b/0x290 ? asm_exc_invalid_op+0x16/0x20 ? dql_completed+0x26b/0x290 __free_old_xmit+0xff/0x170 [virtio_net] free_old_xmit+0x54/0xc0 [virtio_net] virtnet_poll+0xf4/0xe30 [virtio_net] ? __update_load_avg_cfs_rq+0x264/0x2d0 ? update_curr+0x35/0x260 ? reweight_entity+0x1be/0x260 __napi_poll.constprop.0+0x28/0x1c0 net_rx_action+0x329/0x420 ? enqueue_hrtimer+0x35/0x90 ? trace_hardirqs_on+0x1d/0x80 ? kvm_sched_clock_read+0xd/0x20 ? sched_clock+0xc/0x30 ? kvm_sched_clock_read+0xd/0x20 ? sched_clock+0xc/0x30 ? sched_clock_cpu+0xd/0x1a0 handle_softirqs+0x138/0x3e0 do_softirq.part.0+0x89/0xc0 </IRQ> <TASK> __local_bh_enable_ip+0xa7/0xb0 virtnet_open+0xc8/0x310 [virtio_net] __dev_open+0xfa/0x1b0 __dev_change_flags+0x1de/0x250 dev_change_flags+0x22/0x60 do_setlink.isra.0+0x2df/0x10b0 ? rtnetlink_rcv_msg+0x34f/0x3f0 ? netlink_rcv_skb+0x54/0x100 ? netlink_unicast+0x23e/0x390 ? netlink_sendmsg+0x21e/0x490 ? ____sys_sendmsg+0x31b/0x350 ? avc_has_perm_noaudit+0x67/0xf0 ? cred_has_capability.isra.0+0x75/0x110 ? __nla_validate_parse+0x5f/0xee0 ? __pfx___probestub_irq_enable+0x3/0x10 ? __create_object+0x5e/0x90 ? security_capable+0x3b/0x70 rtnl_newlink+0x784/0xaf0 ? avc_has_perm_noaudit+0x67/0xf0 ? cred_has_capability.isra.0+0x75/0x110 ? stack_depot_save_flags+0x24/0x6d0 ? __pfx_rtnl_newlink+0x10/0x10 rtnetlink_rcv_msg+0x34f/0x3f0 ? do_syscall_64+0x6c/0x180 ? entry_SYSCALL_64_after_hwframe+0x76/0x7e ? __pfx_rtnetlink_rcv_msg+0x10/0x10 netlink_rcv_skb+0x54/0x100 netlink_unicast+0x23e/0x390 netlink_sendmsg+0x21e/0x490 ____sys_sendmsg+0x31b/0x350 ? copy_msghdr_from_user+0x6d/0xa0 ___sys_sendmsg+0x86/0xd0 ? __pte_offset_map+0x17/0x160 ? preempt_count_add+0x69/0xa0 ? __call_rcu_common.constprop.0+0x147/0x610 ? preempt_count_add+0x69/0xa0 ? preempt_count_add+0x69/0xa0 ? _raw_spin_trylock+0x13/0x60 ? trace_hardirqs_on+0x1d/0x80 __sys_sendmsg+0x66/0xc0 do_syscall_64+0x6c/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f41defe5b34 Code: 15 e1 12 0f 00 f7 d8 64 89 02 b8 ff ff ff ff eb bf 0f 1f 44 00 00 f3 0f 1e fa 80 3d 35 95 0f 00 00 74 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 4c c3 0f 1f 00 55 48 89 e5 48 83 ec 20 89 55 RSP: 002b:00007ffe5336ecc8 EFLAGS: 00000202 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f41defe5b34 RDX: 0000000000000000 RSI: 00007ffe5336ed30 RDI: 0000000000000003 RBP: 00007ffe5336eda0 R08: 0000000000000010 R09: 0000000000000001 R10: 00007ffe5336f6f9 R11: 0000000000000202 R12: 0000000000000003 R13: 0000000067452259 R14: 0000556ccc28b040 R15: 0000000000000000 </TASK> [...] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fixes: c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits") Cc: <stable(a)vger.kernel.org> # v6.11+ Signed-off-by: Koichiro Den <koichiro.den(a)canonical.com> --- Previous attempt: https://lore.kernel.org/netdev/20241126024200.2371546-1-koichiro.den@canoni… --- drivers/net/virtio_net.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 64c87bb48a41..35a36d1289db 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3054,7 +3054,6 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); -- 2.43.0

1 month

3
4
0 0

[PATCH] drm/msm/dpu: fix x1e80100 intf_6 underrun/vsync interrupt

by Stephan Gerhold

The IRQ indexes for the intf_6 underrun/vsync interrupts are swapped. DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16) is the actual underrun interrupt and DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17) is the vsync interrupt. This causes timeout errors when using the DP2 controller, e.g. [dpu error]enc37 frame done timeout *ERROR* irq timeout id=37, intf_mode=INTF_MODE_VIDEO intf=6 wb=-1, pp=2, intr=0 *ERROR* wait disable failed: id:37 intf:6 ret:-110 Correct them to fix these errors and make DP2 work properly. Cc: stable(a)vger.kernel.org Fixes: e3b1f369db5a ("drm/msm/dpu: Add X1E80100 support") Signed-off-by: Stephan Gerhold <stephan.gerhold(a)linaro.org> --- drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index a3e60ac70689..d61895bb396f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -389,8 +389,8 @@ static const struct dpu_intf_cfg x1e80100_intf[] = { .type = INTF_DP, .controller_id = MSM_DP_CONTROLLER_2, .prog_fetch_lines_worst_case = 24, - .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), - .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), }, { .name = "intf_7", .id = INTF_7, .base = 0x3b000, .len = 0x280, --- base-commit: 744cf71b8bdfcdd77aaf58395e068b7457634b2c change-id: 20241115-x1e80100-dp2-fix-beb12c6dcac9 Best regards, -- Stephan Gerhold <stephan.gerhold(a)linaro.org>

1 month

4
3
0 0

Performance Degradation After Upgrading to Kernel 6.8

by Chenbo Lu

Hello, I am experiencing a significant performance degradation after upgrading my kernel from version 6.6 to 6.8 and would appreciate any insights or suggestions. I am running a high-load simulation system that spawns more than 1000 threads and the overall CPU usage is 30%+ . Most of the threads are using real-time scheduling (SCHED_RR), and the threads of a model are using SCHED_DEADLINE. After upgrading the kernel, I noticed that the execution time of my model has increased from 4.5ms to 6ms. What I Have Done So Far: 1. I found this [bug report](https://bugzilla.kernel.org/show_bug.cgi?id=219366#c7) and reverted the commit efa7df3e3bb5da8e6abbe37727417f32a37fba47 mentioned in the post. Unfortunately, this did not resolve the issue. 2. I performed a git bisect and found that after these two commits related to scheduling (RT and deadline) were merged, the problem happened. They are 612f769edd06a6e42f7cd72425488e68ddaeef0a, 5fe7765997b139e2d922b58359dea181efe618f9 After reverting these two commits, the model execution time improved to around 5 ms. 3. I revert two more commits, and the execution time is back to 4.7ms: 63ba8422f876e32ee564ea95da9a7313b13ff0a1, efa7df3e3bb5da8e6abbe37727417f32a37fba47 My questions are: 1.Has anyone else experienced similar performance degradation after upgrading to kernel 6.8? 2.Can anyone explain why these two commits are causing the problem? I am not very familiar with the kernel code and would appreciate any insights. 3.Are there any additional settings or configurations I need to apply when using kernel 6.8 to avoid this issue? My CPU is AMD Ryzen Threadripper 3970X, and my desktop uses Ubuntu 24.04. Thanks again for any insights or suggestions. Please let me know if any other information is needed. Best, Chenbo -- This email and any relevant attachments may include confidential and/or proprietary information. Any distribution or use by anyone other than the intended recipient(s) or other than for the intended purpose(s) is prohibited and may be unlawful. If you are not the intended recipient of this message, please notify the sender by replying to this message and then delete it from your system.

1 month

4
5
0 0

[PATCH v2] pps: Remove embedded cdev to fix a use-after-free

by Calvin Owens

On a board running ntpd and gpsd, I'm seeing a consistent use-after-free in sys_exit() from gpsd when rebooting: pps pps1: removed ------------[ cut here ]------------ kobject: '(null)' (00000000db4bec24): is not initialized, yet kobject_put() is being called. WARNING: CPU: 2 PID: 440 at lib/kobject.c:734 kobject_put+0x120/0x150 CPU: 2 UID: 299 PID: 440 Comm: gpsd Not tainted 6.11.0-rc6-00308-gb31c44928842 #1 Hardware name: Raspberry Pi 4 Model B Rev 1.1 (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : kobject_put+0x120/0x150 lr : kobject_put+0x120/0x150 sp : ffffffc0803d3ae0 x29: ffffffc0803d3ae0 x28: ffffff8042dc9738 x27: 0000000000000001 x26: 0000000000000000 x25: ffffff8042dc9040 x24: ffffff8042dc9440 x23: ffffff80402a4620 x22: ffffff8042ef4bd0 x21: ffffff80405cb600 x20: 000000000008001b x19: ffffff8040b3b6e0 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 696e6920746f6e20 x14: 7369203a29343263 x13: 205d303434542020 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: kobject_put+0x120/0x150 cdev_put+0x20/0x3c __fput+0x2c4/0x2d8 ____fput+0x1c/0x38 task_work_run+0x70/0xfc do_exit+0x2a0/0x924 do_group_exit+0x34/0x90 get_signal+0x7fc/0x8c0 do_signal+0x128/0x13b4 do_notify_resume+0xdc/0x160 el0_svc+0xd4/0xf8 el0t_64_sync_handler+0x140/0x14c el0t_64_sync+0x190/0x194 ---[ end trace 0000000000000000 ]--- ...followed by more symptoms of corruption, with similar stacks: refcount_t: underflow; use-after-free. kernel BUG at lib/list_debug.c:62! Kernel panic - not syncing: Oops - BUG: Fatal exception This happens because pps_device_destruct() frees the pps_device with the embedded cdev immediately after calling cdev_del(), but, as the comment above cdev_del() notes, fops for previously opened cdevs are still callable even after cdev_del() returns. I think this bug has always been there: I can't explain why it suddenly started happening every time I reboot this particular board. In commit d953e0e837e6 ("pps: Fix a use-after free bug when unregistering a source."), George Spelvin suggested removing the embedded cdev. That seems like the simplest way to fix this, so I've implemented his suggestion, with pps_idr becoming the source of truth for which minor corresponds to which device. But now that pps_idr defines userspace visibility instead of cdev_add(), we need to be sure the pps->dev kobject refcount can't reach zero while userspace can still find it again. So, the idr_remove() call moves to pps_unregister_cdev(), and pps_idr now holds a reference to the pps->dev kobject. pps_core: source serial1 got cdev (251:1) <...> pps pps1: removed pps_core: unregistering pps1 pps_core: deallocating pps1 Fixes: d953e0e837e6 ("pps: Fix a use-after free bug when unregistering a source.") Cc: stable(a)vger.kernel.org Signed-off-by: Calvin Owens <calvin(a)wbinvd.org> --- Changes in v2: - Don't move pr_debug() from pps_device_destruct() to pps_unregister_cdev() - Actually add stable(a)vger.kernel.org to CC --- drivers/pps/pps.c | 83 ++++++++++++++++++++------------------ include/linux/pps_kernel.h | 1 - 2 files changed, 44 insertions(+), 40 deletions(-) diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 5d19baae6a38..6980ab17f314 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -25,7 +25,7 @@ * Local variables */ -static dev_t pps_devt; +static int pps_major; static struct class *pps_class; static DEFINE_MUTEX(pps_idr_lock); @@ -296,19 +296,35 @@ static long pps_cdev_compat_ioctl(struct file *file, #define pps_cdev_compat_ioctl NULL #endif +static struct pps_device *pps_idr_get(unsigned long id) +{ + struct pps_device *pps; + + mutex_lock(&pps_idr_lock); + pps = idr_find(&pps_idr, id); + if (pps) + kobject_get(&pps->dev->kobj); + + mutex_unlock(&pps_idr_lock); + return pps; +} + static int pps_cdev_open(struct inode *inode, struct file *file) { - struct pps_device *pps = container_of(inode->i_cdev, - struct pps_device, cdev); + struct pps_device *pps = pps_idr_get(iminor(inode)); + + if (!pps) + return -ENODEV; + file->private_data = pps; - kobject_get(&pps->dev->kobj); return 0; } static int pps_cdev_release(struct inode *inode, struct file *file) { - struct pps_device *pps = container_of(inode->i_cdev, - struct pps_device, cdev); + struct pps_device *pps = file->private_data; + + WARN_ON(pps->id != iminor(inode)); kobject_put(&pps->dev->kobj); return 0; } @@ -332,14 +348,7 @@ static void pps_device_destruct(struct device *dev) { struct pps_device *pps = dev_get_drvdata(dev); - cdev_del(&pps->cdev); - - /* Now we can release the ID for re-use */ pr_debug("deallocating pps%d\n", pps->id); - mutex_lock(&pps_idr_lock); - idr_remove(&pps_idr, pps->id); - mutex_unlock(&pps_idr_lock); - kfree(dev); kfree(pps); } @@ -364,39 +373,26 @@ int pps_register_cdev(struct pps_device *pps) goto out_unlock; } pps->id = err; - mutex_unlock(&pps_idr_lock); - devt = MKDEV(MAJOR(pps_devt), pps->id); - - cdev_init(&pps->cdev, &pps_cdev_fops); - pps->cdev.owner = pps->info.owner; - - err = cdev_add(&pps->cdev, devt, 1); - if (err) { - pr_err("%s: failed to add char device %d:%d\n", - pps->info.name, MAJOR(pps_devt), pps->id); - goto free_idr; - } + devt = MKDEV(pps_major, pps->id); pps->dev = device_create(pps_class, pps->info.dev, devt, pps, "pps%d", pps->id); if (IS_ERR(pps->dev)) { err = PTR_ERR(pps->dev); - goto del_cdev; + goto free_idr; } /* Override the release function with our own */ pps->dev->release = pps_device_destruct; - pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, - MAJOR(pps_devt), pps->id); + pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, pps_major, + pps->id); + kobject_get(&pps->dev->kobj); + mutex_unlock(&pps_idr_lock); return 0; -del_cdev: - cdev_del(&pps->cdev); - free_idr: - mutex_lock(&pps_idr_lock); idr_remove(&pps_idr, pps->id); out_unlock: mutex_unlock(&pps_idr_lock); @@ -408,6 +404,12 @@ void pps_unregister_cdev(struct pps_device *pps) pr_debug("unregistering pps%d\n", pps->id); pps->lookup_cookie = NULL; device_destroy(pps_class, pps->dev->devt); + + /* Now we can release the ID for re-use */ + mutex_lock(&pps_idr_lock); + idr_remove(&pps_idr, pps->id); + kobject_put(&pps->dev->kobj); + mutex_unlock(&pps_idr_lock); } /* @@ -427,6 +429,11 @@ void pps_unregister_cdev(struct pps_device *pps) * so that it will not be used again, even if the pps device cannot * be removed from the idr due to pending references holding the minor * number in use. + * + * Since pps_idr holds a reference to the kobject, the returned + * pps_device is guaranteed to be valid until pps_unregister_cdev() is + * called on it. But after calling pps_unregister_cdev(), it may be + * freed at any time. */ struct pps_device *pps_lookup_dev(void const *cookie) { @@ -449,13 +456,11 @@ EXPORT_SYMBOL(pps_lookup_dev); static void __exit pps_exit(void) { class_destroy(pps_class); - unregister_chrdev_region(pps_devt, PPS_MAX_SOURCES); + __unregister_chrdev(pps_major, 0, PPS_MAX_SOURCES, "pps"); } static int __init pps_init(void) { - int err; - pps_class = class_create("pps"); if (IS_ERR(pps_class)) { pr_err("failed to allocate class\n"); @@ -463,8 +468,9 @@ static int __init pps_init(void) } pps_class->dev_groups = pps_groups; - err = alloc_chrdev_region(&pps_devt, 0, PPS_MAX_SOURCES, "pps"); - if (err < 0) { + pps_major = __register_chrdev(0, 0, PPS_MAX_SOURCES, "pps", + &pps_cdev_fops); + if (pps_major < 0) { pr_err("failed to allocate char device region\n"); goto remove_class; } @@ -477,8 +483,7 @@ static int __init pps_init(void) remove_class: class_destroy(pps_class); - - return err; + return pps_major; } subsys_initcall(pps_init); diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 78c8ac4951b5..8ee312788118 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -56,7 +56,6 @@ struct pps_device { unsigned int id; /* PPS source unique ID */ void const *lookup_cookie; /* For pps_lookup_dev() only */ - struct cdev cdev; struct device *dev; struct fasync_struct *async_queue; /* fasync method */ spinlock_t lock; -- 2.45.2

1 month

5
10
0 0

[PATCH 4.19.y 1/1] inet: inet_defrag: prevent sk release while still in use

by Saeed Mirzamohammadi

From: Florian Westphal <fw(a)strlen.de> commit 18685451fc4e546fc0e718580d32df3c0e5c8272 upstream. ip_local_out() and other functions can pass skb->sk as function argument. If the skb is a fragment and reassembly happens before such function call returns, the sk must not be released. This affects skb fragments reassembled via netfilter or similar modules, e.g. openvswitch or ct_act.c, when run as part of tx pipeline. Eric Dumazet made an initial analysis of this bug. Quoting Eric: Calling ip_defrag() in output path is also implying skb_orphan(), which is buggy because output path relies on sk not disappearing. A relevant old patch about the issue was : 8282f27449bf ("inet: frag: Always orphan skbs inside ip_defrag()") [..] net/ipv4/ip_output.c depends on skb->sk being set, and probably to an inet socket, not an arbitrary one. If we orphan the packet in ipvlan, then downstream things like FQ packet scheduler will not work properly. We need to change ip_defrag() to only use skb_orphan() when really needed, ie whenever frag_list is going to be used. Eric suggested to stash sk in fragment queue and made an initial patch. However there is a problem with this: If skb is refragmented again right after, ip_do_fragment() will copy head->sk to the new fragments, and sets up destructor to sock_wfree. IOW, we have no choice but to fix up sk_wmem accouting to reflect the fully reassembled skb, else wmem will underflow. This change moves the orphan down into the core, to last possible moment. As ip_defrag_offset is aliased with sk_buff->sk member, we must move the offset into the FRAG_CB, else skb->sk gets clobbered. This allows to delay the orphaning long enough to learn if the skb has to be queued or if the skb is completing the reasm queue. In the former case, things work as before, skb is orphaned. This is safe because skb gets queued/stolen and won't continue past reasm engine. In the latter case, we will steal the skb->sk reference, reattach it to the head skb, and fix up wmem accouting when inet_frag inflates truesize. Fixes: 7026b1ddb6b8 ("netfilter: Pass socket pointer down through okfn().") Diagnosed-by: Eric Dumazet <edumazet(a)google.com> Reported-by: xingwei lee <xrivendell7(a)gmail.com> Reported-by: yue sun <samsun1006219(a)gmail.com> Reported-by: syzbot+e5167d7144a62715044c(a)syzkaller.appspotmail.com Signed-off-by: Florian Westphal <fw(a)strlen.de> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://lore.kernel.org/r/20240326101845.30836-1-fw@strlen.de Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Saeed Mirzamohammadi <saeed.mirzamohammadi(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> (cherry picked from commit 1b6de5e6575b56502665c65cf93b0ae6aa0f51ab) Cc: <stable(a)vger.kernel.org> # 4.19+ Signed-off-by: Saeed Mirzamohammadi <saeed.mirzamohammadi(a)oracle.com> --- include/linux/skbuff.h | 5 +- net/core/sock_destructor.h | 12 +++++ net/ipv4/inet_fragment.c | 70 ++++++++++++++++++++----- net/ipv4/ip_fragment.c | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +- 5 files changed, 72 insertions(+), 19 deletions(-) create mode 100644 net/core/sock_destructor.h diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f97734f34746..f5f76a04fdac 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -682,10 +682,7 @@ struct sk_buff { struct list_head list; }; - union { - struct sock *sk; - int ip_defrag_offset; - }; + struct sock *sk; union { ktime_t tstamp; diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h new file mode 100644 index 000000000000..2f396e6bfba5 --- /dev/null +++ b/net/core/sock_destructor.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_CORE_SOCK_DESTRUCTOR_H +#define _NET_CORE_SOCK_DESTRUCTOR_H +#include <net/tcp.h> + +static inline bool is_skb_wmem(const struct sk_buff *skb) +{ + return skb->destructor == sock_wfree || + skb->destructor == __sock_wfree || + (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree); +} +#endif diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 9f69411251d0..9144c3cf984c 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -28,6 +28,8 @@ #include <net/ip.h> #include <net/ipv6.h> +#include "../core/sock_destructor.h" + /* Use skb->cb to track consecutive/adjacent fragments coming at * the end of the queue. Nodes in the rb-tree queue will * contain "runs" of one or more adjacent fragments. @@ -43,6 +45,7 @@ struct ipfrag_skb_cb { }; struct sk_buff *next_frag; int frag_run_len; + int ip_defrag_offset; }; #define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) @@ -319,12 +322,12 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, */ if (!last) fragrun_create(q, skb); /* First fragment. */ - else if (last->ip_defrag_offset + last->len < end) { + else if (FRAG_CB(last)->ip_defrag_offset + last->len < end) { /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ - if (offset < last->ip_defrag_offset + last->len) + if (offset < FRAG_CB(last)->ip_defrag_offset + last->len) return IPFRAG_OVERLAP; - if (offset == last->ip_defrag_offset + last->len) + if (offset == FRAG_CB(last)->ip_defrag_offset + last->len) fragrun_append_to_last(q, skb); else fragrun_create(q, skb); @@ -341,13 +344,13 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, parent = *rbn; curr = rb_to_skb(parent); - curr_run_end = curr->ip_defrag_offset + + curr_run_end = FRAG_CB(curr)->ip_defrag_offset + FRAG_CB(curr)->frag_run_len; - if (end <= curr->ip_defrag_offset) + if (end <= FRAG_CB(curr)->ip_defrag_offset) rbn = &parent->rb_left; else if (offset >= curr_run_end) rbn = &parent->rb_right; - else if (offset >= curr->ip_defrag_offset && + else if (offset >= FRAG_CB(curr)->ip_defrag_offset && end <= curr_run_end) return IPFRAG_DUP; else @@ -361,7 +364,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, rb_insert_color(&skb->rbnode, &q->rb_fragments); } - skb->ip_defrag_offset = offset; + FRAG_CB(skb)->ip_defrag_offset = offset; return IPFRAG_OK; } @@ -371,13 +374,28 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, struct sk_buff *parent) { struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); - struct sk_buff **nextp; + void (*destructor)(struct sk_buff *); + unsigned int orig_truesize = 0; + struct sk_buff **nextp = NULL; + struct sock *sk = skb->sk; int delta; + if (sk && is_skb_wmem(skb)) { + /* TX: skb->sk might have been passed as argument to + * dst->output and must remain valid until tx completes. + * + * Move sk to reassembled skb and fix up wmem accounting. + */ + orig_truesize = skb->truesize; + destructor = skb->destructor; + } + if (head != skb) { fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - return NULL; + if (!fp) { + head = skb; + goto out_restore_sk; + } FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; if (RB_EMPTY_NODE(&skb->rbnode)) FRAG_CB(parent)->next_frag = fp; @@ -386,6 +404,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, &q->rb_fragments); if (q->fragments_tail == skb) q->fragments_tail = fp; + + if (orig_truesize) { + /* prevent skb_morph from releasing sk */ + skb->sk = NULL; + skb->destructor = NULL; + } skb_morph(skb, head); FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; rb_replace_node(&head->rbnode, &skb->rbnode, @@ -393,13 +417,13 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, consume_skb(head); head = skb; } - WARN_ON(head->ip_defrag_offset != 0); + WARN_ON(FRAG_CB(head)->ip_defrag_offset != 0); delta = -head->truesize; /* Head of list must not be cloned. */ if (skb_unclone(head, GFP_ATOMIC)) - return NULL; + goto out_restore_sk; delta += head->truesize; if (delta) @@ -415,7 +439,7 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, clone = alloc_skb(0, GFP_ATOMIC); if (!clone) - return NULL; + goto out_restore_sk; skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; skb_frag_list_init(head); for (i = 0; i < skb_shinfo(head)->nr_frags; i++) @@ -432,6 +456,21 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, nextp = &skb_shinfo(head)->frag_list; } +out_restore_sk: + if (orig_truesize) { + int ts_delta = head->truesize - orig_truesize; + + /* if this reassembled skb is fragmented later, + * fraglist skbs will get skb->sk assigned from head->sk, + * and each frag skb will be released via sock_wfree. + * + * Update sk_wmem_alloc. + */ + head->sk = sk; + head->destructor = destructor; + refcount_add(ts_delta, &sk->sk_wmem_alloc); + } + return nextp; } EXPORT_SYMBOL(inet_frag_reasm_prepare); @@ -439,6 +478,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data) { + struct sock *sk = is_skb_wmem(head) ? head->sk : NULL; + const unsigned int head_truesize = head->truesize; struct sk_buff **nextp = (struct sk_buff **)reasm_data; struct rb_node *rbn; struct sk_buff *fp; @@ -484,6 +525,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, skb_mark_not_on_list(head); head->prev = NULL; head->tstamp = q->stamp; + + if (sk) + refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); } EXPORT_SYMBOL(inet_frag_reasm_finish); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 5a1d39e32196..84544e5df7fc 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -380,6 +380,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -477,7 +478,6 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user) struct ipq *qp; __IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS); - skb_orphan(skb); /* Lookup (or create) queue header */ qp = ip_find(net, ip_hdr(skb), user, vif); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 35d5a76867d0..8aab62c330ef 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -307,6 +307,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -473,7 +474,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { -- 2.46.0

1 month

2
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror November 2024