April 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] PCI/ASPM: Fix deadlock when enabling ASPM" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-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-6.1.y git checkout FETCH_HEAD git cherry-pick -x 1e560864159d002b453da42bd2c13a1805515a20 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021334-each-residence-41ce@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 1e560864159d ("PCI/ASPM: Fix deadlock when enabling ASPM") ac865f00af29 ("Merge tag 'pci-v6.7-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1e560864159d002b453da42bd2c13a1805515a20 Mon Sep 17 00:00:00 2001 From: Johan Hovold <johan+linaro(a)kernel.org> Date: Tue, 30 Jan 2024 11:02:43 +0100 Subject: [PATCH] PCI/ASPM: Fix deadlock when enabling ASPM A last minute revert in 6.7-final introduced a potential deadlock when enabling ASPM during probe of Qualcomm PCIe controllers as reported by lockdep: ============================================ WARNING: possible recursive locking detected 6.7.0 #40 Not tainted -------------------------------------------- kworker/u16:5/90 is trying to acquire lock: ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pcie_aspm_pm_state_change+0x58/0xdc but task is already holding lock: ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pci_walk_bus+0x34/0xbc other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(pci_bus_sem); lock(pci_bus_sem); *** DEADLOCK *** Call trace: print_deadlock_bug+0x25c/0x348 __lock_acquire+0x10a4/0x2064 lock_acquire+0x1e8/0x318 down_read+0x60/0x184 pcie_aspm_pm_state_change+0x58/0xdc pci_set_full_power_state+0xa8/0x114 pci_set_power_state+0xc4/0x120 qcom_pcie_enable_aspm+0x1c/0x3c [pcie_qcom] pci_walk_bus+0x64/0xbc qcom_pcie_host_post_init_2_7_0+0x28/0x34 [pcie_qcom] The deadlock can easily be reproduced on machines like the Lenovo ThinkPad X13s by adding a delay to increase the race window during asynchronous probe where another thread can take a write lock. Add a new pci_set_power_state_locked() and associated helper functions that can be called with the PCI bus semaphore held to avoid taking the read lock twice. Link: https://lore.kernel.org/r/ZZu0qx2cmn7IwTyQ@hovoldconsulting.com Link: https://lore.kernel.org/r/20240130100243.11011-1-johan+linaro@kernel.org Fixes: f93e71aea6c6 ("Revert "PCI/ASPM: Remove pcie_aspm_pm_state_change()"") Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com> Cc: <stable(a)vger.kernel.org> # 6.7 diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 9c2137dae429..826b5016a101 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -386,21 +386,8 @@ void pci_bus_add_devices(const struct pci_bus *bus) } EXPORT_SYMBOL(pci_bus_add_devices); -/** pci_walk_bus - walk devices on/under bus, calling callback. - * @top bus whose devices should be walked - * @cb callback to be called for each device found - * @userdata arbitrary pointer to be passed to callback. - * - * Walk the given bus, including any bridged devices - * on buses under this bus. Call the provided callback - * on each device found. - * - * We check the return of @cb each time. If it returns anything - * other than 0, we break out. - * - */ -void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), - void *userdata) +static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata, bool locked) { struct pci_dev *dev; struct pci_bus *bus; @@ -408,7 +395,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), int retval; bus = top; - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); next = top->devices.next; for (;;) { if (next == &bus->devices) { @@ -431,10 +419,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), if (retval) break; } - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); +} + +/** + * pci_walk_bus - walk devices on/under bus, calling callback. + * @top: bus whose devices should be walked + * @cb: callback to be called for each device found + * @userdata: arbitrary pointer to be passed to callback + * + * Walk the given bus, including any bridged devices + * on buses under this bus. Call the provided callback + * on each device found. + * + * We check the return of @cb each time. If it returns anything + * other than 0, we break out. + */ +void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) +{ + __pci_walk_bus(top, cb, userdata, false); } EXPORT_SYMBOL_GPL(pci_walk_bus); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) +{ + lockdep_assert_held(&pci_bus_sem); + + __pci_walk_bus(top, cb, userdata, true); +} +EXPORT_SYMBOL_GPL(pci_walk_bus_locked); + struct pci_bus *pci_bus_get(struct pci_bus *bus) { if (bus) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 10f2d0bb86be..2ce2a3bd932b 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -972,7 +972,7 @@ static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata) * Downstream devices need to be in D0 state before enabling PCI PM * substates. */ - pci_set_power_state(pdev, PCI_D0); + pci_set_power_state_locked(pdev, PCI_D0); pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); return 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d8f11a078924..9ab9b1008d8b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1354,6 +1354,7 @@ int pci_power_up(struct pci_dev *dev) /** * pci_set_full_power_state - Put a PCI device into D0 and update its state * @dev: PCI device to power up + * @locked: whether pci_bus_sem is held * * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register * to confirm the state change, restore its BARs if they might be lost and @@ -1363,7 +1364,7 @@ int pci_power_up(struct pci_dev *dev) * to D0, it is more efficient to use pci_power_up() directly instead of this * function. */ -static int pci_set_full_power_state(struct pci_dev *dev) +static int pci_set_full_power_state(struct pci_dev *dev, bool locked) { u16 pmcsr; int ret; @@ -1399,7 +1400,7 @@ static int pci_set_full_power_state(struct pci_dev *dev) } if (dev->bus->self) - pcie_aspm_pm_state_change(dev->bus->self); + pcie_aspm_pm_state_change(dev->bus->self, locked); return 0; } @@ -1428,10 +1429,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) pci_walk_bus(bus, __pci_dev_set_current_state, &state); } +static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked) +{ + if (!bus) + return; + + if (locked) + pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state); + else + pci_walk_bus(bus, __pci_dev_set_current_state, &state); +} + /** * pci_set_low_power_state - Put a PCI device into a low-power state. * @dev: PCI device to handle. * @state: PCI power state (D1, D2, D3hot) to put the device into. + * @locked: whether pci_bus_sem is held * * Use the device's PCI_PM_CTRL register to put it into a low-power state. * @@ -1442,7 +1455,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) * 0 if device already is in the requested state. * 0 if device's power state has been successfully changed. */ -static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) +static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { u16 pmcsr; @@ -1496,29 +1509,12 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(state)); if (dev->bus->self) - pcie_aspm_pm_state_change(dev->bus->self); + pcie_aspm_pm_state_change(dev->bus->self, locked); return 0; } -/** - * pci_set_power_state - Set the power state of a PCI device - * @dev: PCI device to handle. - * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. - * - * Transition a device to a new power state, using the platform firmware and/or - * the device's PCI PM registers. - * - * RETURN VALUE: - * -EINVAL if the requested state is invalid. - * -EIO if device does not support PCI PM or its PM capabilities register has a - * wrong version, or device doesn't support the requested state. - * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. - * 0 if device already is in the requested state. - * 0 if the transition is to D3 but D3 is not supported. - * 0 if device's power state has been successfully changed. - */ -int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { int error; @@ -1542,7 +1538,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; if (state == PCI_D0) - return pci_set_full_power_state(dev); + return pci_set_full_power_state(dev, locked); /* * This device is quirked not to be put into D3, so don't put it in @@ -1556,16 +1552,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) * To put the device in D3cold, put it into D3hot in the native * way, then put it into D3cold using platform ops. */ - error = pci_set_low_power_state(dev, PCI_D3hot); + error = pci_set_low_power_state(dev, PCI_D3hot, locked); if (pci_platform_power_transition(dev, PCI_D3cold)) return error; /* Powering off a bridge may power off the whole hierarchy */ if (dev->current_state == PCI_D3cold) - pci_bus_set_current_state(dev->subordinate, PCI_D3cold); + __pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked); } else { - error = pci_set_low_power_state(dev, state); + error = pci_set_low_power_state(dev, state, locked); if (pci_platform_power_transition(dev, state)) return error; @@ -1573,8 +1569,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; } + +/** + * pci_set_power_state - Set the power state of a PCI device + * @dev: PCI device to handle. + * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. + * + * Transition a device to a new power state, using the platform firmware and/or + * the device's PCI PM registers. + * + * RETURN VALUE: + * -EINVAL if the requested state is invalid. + * -EIO if device does not support PCI PM or its PM capabilities register has a + * wrong version, or device doesn't support the requested state. + * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. + * 0 if device already is in the requested state. + * 0 if the transition is to D3 but D3 is not supported. + * 0 if device's power state has been successfully changed. + */ +int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +{ + return __pci_set_power_state(dev, state, false); +} EXPORT_SYMBOL(pci_set_power_state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ + lockdep_assert_held(&pci_bus_sem); + + return __pci_set_power_state(dev, state, true); +} +EXPORT_SYMBOL(pci_set_power_state_locked); + #define PCI_EXP_SAVE_REGS 7 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev, diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 2336a8d1edab..e9750b1b19ba 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -571,12 +571,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); -void pcie_aspm_pm_state_change(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } -static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 5a0066ecc3c5..bc0bd86695ec 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1003,8 +1003,11 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } -/* @pdev: the root port or switch downstream port */ -void pcie_aspm_pm_state_change(struct pci_dev *pdev) +/* + * @pdev: the root port or switch downstream port + * @locked: whether pci_bus_sem is held + */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { struct pcie_link_state *link = pdev->link_state; @@ -1014,12 +1017,14 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev) * Devices changed PM state, we should recheck if latency * meets all functions' requirement */ - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); pcie_update_aspm_capable(link->root); pcie_config_aspm_path(link); mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); } void pcie_aspm_powersave_config_link(struct pci_dev *pdev) diff --git a/include/linux/pci.h b/include/linux/pci.h index add9368e6314..7ab0d13672da 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1422,6 +1422,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev, struct pci_saved_state **state); int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); @@ -1625,6 +1626,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); void pci_setup_bridge(struct pci_bus *bus); @@ -2025,6 +2028,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; } static inline void pci_restore_state(struct pci_dev *dev) { } static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state) { return 0; } +static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ return 0; } static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable) { return 0; } static inline pci_power_t pci_choose_state(struct pci_dev *dev,

8 months, 2 weeks

3
2
0 0

FAILED: patch "[PATCH] PCI/ASPM: Fix deadlock when enabling ASPM" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x 1e560864159d002b453da42bd2c13a1805515a20 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021328-stylus-ooze-f752@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 1e560864159d ("PCI/ASPM: Fix deadlock when enabling ASPM") ac865f00af29 ("Merge tag 'pci-v6.7-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 1e560864159d002b453da42bd2c13a1805515a20 Mon Sep 17 00:00:00 2001 From: Johan Hovold <johan+linaro(a)kernel.org> Date: Tue, 30 Jan 2024 11:02:43 +0100 Subject: [PATCH] PCI/ASPM: Fix deadlock when enabling ASPM A last minute revert in 6.7-final introduced a potential deadlock when enabling ASPM during probe of Qualcomm PCIe controllers as reported by lockdep: ============================================ WARNING: possible recursive locking detected 6.7.0 #40 Not tainted -------------------------------------------- kworker/u16:5/90 is trying to acquire lock: ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pcie_aspm_pm_state_change+0x58/0xdc but task is already holding lock: ffffacfa78ced000 (pci_bus_sem){++++}-{3:3}, at: pci_walk_bus+0x34/0xbc other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(pci_bus_sem); lock(pci_bus_sem); *** DEADLOCK *** Call trace: print_deadlock_bug+0x25c/0x348 __lock_acquire+0x10a4/0x2064 lock_acquire+0x1e8/0x318 down_read+0x60/0x184 pcie_aspm_pm_state_change+0x58/0xdc pci_set_full_power_state+0xa8/0x114 pci_set_power_state+0xc4/0x120 qcom_pcie_enable_aspm+0x1c/0x3c [pcie_qcom] pci_walk_bus+0x64/0xbc qcom_pcie_host_post_init_2_7_0+0x28/0x34 [pcie_qcom] The deadlock can easily be reproduced on machines like the Lenovo ThinkPad X13s by adding a delay to increase the race window during asynchronous probe where another thread can take a write lock. Add a new pci_set_power_state_locked() and associated helper functions that can be called with the PCI bus semaphore held to avoid taking the read lock twice. Link: https://lore.kernel.org/r/ZZu0qx2cmn7IwTyQ@hovoldconsulting.com Link: https://lore.kernel.org/r/20240130100243.11011-1-johan+linaro@kernel.org Fixes: f93e71aea6c6 ("Revert "PCI/ASPM: Remove pcie_aspm_pm_state_change()"") Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com> Cc: <stable(a)vger.kernel.org> # 6.7 diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 9c2137dae429..826b5016a101 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -386,21 +386,8 @@ void pci_bus_add_devices(const struct pci_bus *bus) } EXPORT_SYMBOL(pci_bus_add_devices); -/** pci_walk_bus - walk devices on/under bus, calling callback. - * @top bus whose devices should be walked - * @cb callback to be called for each device found - * @userdata arbitrary pointer to be passed to callback. - * - * Walk the given bus, including any bridged devices - * on buses under this bus. Call the provided callback - * on each device found. - * - * We check the return of @cb each time. If it returns anything - * other than 0, we break out. - * - */ -void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), - void *userdata) +static void __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata, bool locked) { struct pci_dev *dev; struct pci_bus *bus; @@ -408,7 +395,8 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), int retval; bus = top; - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); next = top->devices.next; for (;;) { if (next == &bus->devices) { @@ -431,10 +419,37 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), if (retval) break; } - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); +} + +/** + * pci_walk_bus - walk devices on/under bus, calling callback. + * @top: bus whose devices should be walked + * @cb: callback to be called for each device found + * @userdata: arbitrary pointer to be passed to callback + * + * Walk the given bus, including any bridged devices + * on buses under this bus. Call the provided callback + * on each device found. + * + * We check the return of @cb each time. If it returns anything + * other than 0, we break out. + */ +void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) +{ + __pci_walk_bus(top, cb, userdata, false); } EXPORT_SYMBOL_GPL(pci_walk_bus); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) +{ + lockdep_assert_held(&pci_bus_sem); + + __pci_walk_bus(top, cb, userdata, true); +} +EXPORT_SYMBOL_GPL(pci_walk_bus_locked); + struct pci_bus *pci_bus_get(struct pci_bus *bus) { if (bus) diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index 10f2d0bb86be..2ce2a3bd932b 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -972,7 +972,7 @@ static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata) * Downstream devices need to be in D0 state before enabling PCI PM * substates. */ - pci_set_power_state(pdev, PCI_D0); + pci_set_power_state_locked(pdev, PCI_D0); pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); return 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d8f11a078924..9ab9b1008d8b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1354,6 +1354,7 @@ int pci_power_up(struct pci_dev *dev) /** * pci_set_full_power_state - Put a PCI device into D0 and update its state * @dev: PCI device to power up + * @locked: whether pci_bus_sem is held * * Call pci_power_up() to put @dev into D0, read from its PCI_PM_CTRL register * to confirm the state change, restore its BARs if they might be lost and @@ -1363,7 +1364,7 @@ int pci_power_up(struct pci_dev *dev) * to D0, it is more efficient to use pci_power_up() directly instead of this * function. */ -static int pci_set_full_power_state(struct pci_dev *dev) +static int pci_set_full_power_state(struct pci_dev *dev, bool locked) { u16 pmcsr; int ret; @@ -1399,7 +1400,7 @@ static int pci_set_full_power_state(struct pci_dev *dev) } if (dev->bus->self) - pcie_aspm_pm_state_change(dev->bus->self); + pcie_aspm_pm_state_change(dev->bus->self, locked); return 0; } @@ -1428,10 +1429,22 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) pci_walk_bus(bus, __pci_dev_set_current_state, &state); } +static void __pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state, bool locked) +{ + if (!bus) + return; + + if (locked) + pci_walk_bus_locked(bus, __pci_dev_set_current_state, &state); + else + pci_walk_bus(bus, __pci_dev_set_current_state, &state); +} + /** * pci_set_low_power_state - Put a PCI device into a low-power state. * @dev: PCI device to handle. * @state: PCI power state (D1, D2, D3hot) to put the device into. + * @locked: whether pci_bus_sem is held * * Use the device's PCI_PM_CTRL register to put it into a low-power state. * @@ -1442,7 +1455,7 @@ void pci_bus_set_current_state(struct pci_bus *bus, pci_power_t state) * 0 if device already is in the requested state. * 0 if device's power state has been successfully changed. */ -static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) +static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { u16 pmcsr; @@ -1496,29 +1509,12 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(state)); if (dev->bus->self) - pcie_aspm_pm_state_change(dev->bus->self); + pcie_aspm_pm_state_change(dev->bus->self, locked); return 0; } -/** - * pci_set_power_state - Set the power state of a PCI device - * @dev: PCI device to handle. - * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. - * - * Transition a device to a new power state, using the platform firmware and/or - * the device's PCI PM registers. - * - * RETURN VALUE: - * -EINVAL if the requested state is invalid. - * -EIO if device does not support PCI PM or its PM capabilities register has a - * wrong version, or device doesn't support the requested state. - * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. - * 0 if device already is in the requested state. - * 0 if the transition is to D3 but D3 is not supported. - * 0 if device's power state has been successfully changed. - */ -int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +static int __pci_set_power_state(struct pci_dev *dev, pci_power_t state, bool locked) { int error; @@ -1542,7 +1538,7 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; if (state == PCI_D0) - return pci_set_full_power_state(dev); + return pci_set_full_power_state(dev, locked); /* * This device is quirked not to be put into D3, so don't put it in @@ -1556,16 +1552,16 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) * To put the device in D3cold, put it into D3hot in the native * way, then put it into D3cold using platform ops. */ - error = pci_set_low_power_state(dev, PCI_D3hot); + error = pci_set_low_power_state(dev, PCI_D3hot, locked); if (pci_platform_power_transition(dev, PCI_D3cold)) return error; /* Powering off a bridge may power off the whole hierarchy */ if (dev->current_state == PCI_D3cold) - pci_bus_set_current_state(dev->subordinate, PCI_D3cold); + __pci_bus_set_current_state(dev->subordinate, PCI_D3cold, locked); } else { - error = pci_set_low_power_state(dev, state); + error = pci_set_low_power_state(dev, state, locked); if (pci_platform_power_transition(dev, state)) return error; @@ -1573,8 +1569,38 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state) return 0; } + +/** + * pci_set_power_state - Set the power state of a PCI device + * @dev: PCI device to handle. + * @state: PCI power state (D0, D1, D2, D3hot) to put the device into. + * + * Transition a device to a new power state, using the platform firmware and/or + * the device's PCI PM registers. + * + * RETURN VALUE: + * -EINVAL if the requested state is invalid. + * -EIO if device does not support PCI PM or its PM capabilities register has a + * wrong version, or device doesn't support the requested state. + * 0 if the transition is to D1 or D2 but D1 and D2 are not supported. + * 0 if device already is in the requested state. + * 0 if the transition is to D3 but D3 is not supported. + * 0 if device's power state has been successfully changed. + */ +int pci_set_power_state(struct pci_dev *dev, pci_power_t state) +{ + return __pci_set_power_state(dev, state, false); +} EXPORT_SYMBOL(pci_set_power_state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ + lockdep_assert_held(&pci_bus_sem); + + return __pci_set_power_state(dev, state, true); +} +EXPORT_SYMBOL(pci_set_power_state_locked); + #define PCI_EXP_SAVE_REGS 7 static struct pci_cap_saved_state *_pci_find_saved_cap(struct pci_dev *pci_dev, diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 2336a8d1edab..e9750b1b19ba 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -571,12 +571,12 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); -void pcie_aspm_pm_state_change(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } -static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 5a0066ecc3c5..bc0bd86695ec 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1003,8 +1003,11 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } -/* @pdev: the root port or switch downstream port */ -void pcie_aspm_pm_state_change(struct pci_dev *pdev) +/* + * @pdev: the root port or switch downstream port + * @locked: whether pci_bus_sem is held + */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { struct pcie_link_state *link = pdev->link_state; @@ -1014,12 +1017,14 @@ void pcie_aspm_pm_state_change(struct pci_dev *pdev) * Devices changed PM state, we should recheck if latency * meets all functions' requirement */ - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); pcie_update_aspm_capable(link->root); pcie_config_aspm_path(link); mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); } void pcie_aspm_powersave_config_link(struct pci_dev *pdev) diff --git a/include/linux/pci.h b/include/linux/pci.h index add9368e6314..7ab0d13672da 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1422,6 +1422,7 @@ int pci_load_and_free_saved_state(struct pci_dev *dev, struct pci_saved_state **state); int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state); int pci_set_power_state(struct pci_dev *dev, pci_power_t state); +int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state); pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state); bool pci_pme_capable(struct pci_dev *dev, pci_power_t state); void pci_pme_active(struct pci_dev *dev, bool enable); @@ -1625,6 +1626,8 @@ int pci_scan_bridge(struct pci_bus *bus, struct pci_dev *dev, int max, void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata); +void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), + void *userdata); int pci_cfg_space_size(struct pci_dev *dev); unsigned char pci_bus_max_busnr(struct pci_bus *bus); void pci_setup_bridge(struct pci_bus *bus); @@ -2025,6 +2028,8 @@ static inline int pci_save_state(struct pci_dev *dev) { return 0; } static inline void pci_restore_state(struct pci_dev *dev) { } static inline int pci_set_power_state(struct pci_dev *dev, pci_power_t state) { return 0; } +static inline int pci_set_power_state_locked(struct pci_dev *dev, pci_power_t state) +{ return 0; } static inline int pci_wake_from_d3(struct pci_dev *dev, bool enable) { return 0; } static inline pci_power_t pci_choose_state(struct pci_dev *dev,

8 months, 2 weeks

4
3
0 0

Reset thunderbolt topologies at bootup

by Mario Limonciello

Hi, We've got a collection of bug reports about how if a Thunderbolt device is connected at bootup it doesn't behave the same as if it were hotplugged by the user after bootup. Issues range from non-functional devices or display devices working at lower performance. All of the issues stem from a pre-OS firmware initializing the USB4 controller and the OS re-using those tunnels. This has been fixed in 6.9-rc1 by resetting the controller to a fresh state and discarding whatever firmware has done. I'd like to bring it back to 6.6.y LTS and 6.8.y stable. 01da6b99d49f6 thunderbolt: Introduce tb_port_reset() b35c1d7b11da8 thunderbolt: Introduce tb_path_deactivate_hop() ec8162b3f0683 thunderbolt: Make tb_switch_reset() support Thunderbolt 2, 3 and USB4 routers 9a54c5f3dbde thunderbolt: Reset topology created by the boot firmware Thanks!

8 months, 2 weeks

3
3
0 0

[PATCH AUTOSEL 6.1 01/17] pinctrl: lochnagar: Don't build on MIPS

by Sasha Levin

From: Charles Keepax <ckeepax(a)opensource.cirrus.com> [ Upstream commit 6588732445ff19f6183f0fa72ddedf67e5a5be32 ] MIPS appears to define a RST symbol at a high level, which clashes with some register naming in the driver. Since there is currently no case for running this driver on MIPS devices simply cut off the build of this driver on MIPS. Reported-by: kernel test robot <lkp(a)intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202311071303.JJMAOjy4-lkp@intel.com/ Suggested-by: Linus Walleij <linus.walleij(a)linaro.org> Signed-off-by: Charles Keepax <ckeepax(a)opensource.cirrus.com> Link: https://lore.kernel.org/r/20231115162853.1891940-1-ckeepax@opensource.cirru… Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/pinctrl/cirrus/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pinctrl/cirrus/Kconfig b/drivers/pinctrl/cirrus/Kconfig index 530426a74f751..b3cea8d56c4f6 100644 --- a/drivers/pinctrl/cirrus/Kconfig +++ b/drivers/pinctrl/cirrus/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config PINCTRL_LOCHNAGAR tristate "Cirrus Logic Lochnagar pinctrl driver" - depends on MFD_LOCHNAGAR + # Avoid clash caused by MIPS defining RST, which is used in the driver + depends on MFD_LOCHNAGAR && !MIPS select GPIOLIB select PINMUX select PINCONF -- 2.42.0

8 months, 2 weeks

2
17
0 0

Re: [PATCH v2] usb: gadget: f_fs: Fix a race condition when processing setup packets.

by kernel test robot

Hi, Thanks for your patch. FYI: kernel test robot notices the stable kernel rule is not satisfied. The check is based on https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html#opt… Rule: add the tag "Cc: stable(a)vger.kernel.org" in the sign-off area to have the patch automatically included in the stable tree. Subject: [PATCH v2] usb: gadget: f_fs: Fix a race condition when processing setup packets. Link: https://lore.kernel.org/stable/CO1PR17MB5419BD664264A558B2395E28E1112%40CO1… -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

8 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] userfaultfd: change src_folio after ensuring it's unpinned in" failed to apply to 6.8-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.8-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-6.8.y git checkout FETCH_HEAD git cherry-pick -x c0205eaf3af9f5db14d4b5ee4abacf4a583c3c50 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024042334-agenda-nutlike-cb77@gregkh' --subject-prefix 'PATCH 6.8.y' HEAD^.. Possible dependencies: c0205eaf3af9 ("userfaultfd: change src_folio after ensuring it's unpinned in UFFDIO_MOVE") eb1521dad8f3 ("userfaultfd: handle zeropage moves by UFFDIO_MOVE") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From c0205eaf3af9f5db14d4b5ee4abacf4a583c3c50 Mon Sep 17 00:00:00 2001 From: Lokesh Gidra <lokeshgidra(a)google.com> Date: Thu, 4 Apr 2024 10:17:26 -0700 Subject: [PATCH] userfaultfd: change src_folio after ensuring it's unpinned in UFFDIO_MOVE Commit d7a08838ab74 ("mm: userfaultfd: fix unexpected change to src_folio when UFFDIO_MOVE fails") moved the src_folio->{mapping, index} changing to after clearing the page-table and ensuring that it's not pinned. This avoids failure of swapout+migration and possibly memory corruption. However, the commit missed fixing it in the huge-page case. Link: https://lkml.kernel.org/r/20240404171726.2302435-1-lokeshgidra@google.com Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Lokesh Gidra <lokeshgidra(a)google.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: Lokesh Gidra <lokeshgidra(a)google.com> Cc: Nicolas Geoffray <ngeoffray(a)google.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Qi Zheng <zhengqi.arch(a)bytedance.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9859aa4f7553..89f58c7603b2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2259,9 +2259,6 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } - folio_move_anon_rmap(src_folio, dst_vma); - WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); - src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { @@ -2270,6 +2267,9 @@ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pm goto unlock_ptls; } + folio_move_anon_rmap(src_folio, dst_vma); + WRITE_ONCE(src_folio->index, linear_page_index(dst_vma, dst_addr)); + _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma);

8 months, 2 weeks

3
2
0 0

[PATCH net v2 0/4] Fix isolation of broadcast traffic and unmatched unicast traffic with MACsec offload

by Rahul Rameshbabu

Some device drivers support devices that enable them to annotate whether a Rx skb refers to a packet that was processed by the MACsec offloading functionality of the device. Logic in the Rx handling for MACsec offload does not utilize this information to preemptively avoid forwarding to the macsec netdev currently. Because of this, things like multicast messages or unicast messages with an unmatched destination address such as ARP requests are forwarded to the macsec netdev whether the message received was MACsec encrypted or not. The goal of this patch series is to improve the Rx handling for MACsec offload for devices capable of annotating skbs received that were decrypted by the NIC offload for MACsec. Here is a summary of the issue that occurs with the existing logic today. * The current design of the MACsec offload handling path tries to use "best guess" mechanisms for determining whether a packet associated with the currently handled skb in the datapath was processed via HW offload * The best guess mechanism uses the following heuristic logic (in order of precedence) - Check if header destination MAC address matches MACsec netdev MAC address -> forward to MACsec port - Check if packet is multicast traffic -> forward to MACsec port - MACsec security channel was able to be looked up from skb offload context (mlx5 only) -> forward to MACsec port * Problem: plaintext traffic can potentially solicit a MACsec encrypted response from the offload device - Core aspect of MACsec is that it identifies unauthorized LAN connections and excludes them from communication + This behavior can be seen when not enabling offload for MACsec - The offload behavior violates this principle in MACsec I believe this behavior is a security bug since applications utilizing MACsec could be exploited using this behavior, and the correct way to resolve this is by having the hardware correctly indicate whether MACsec offload occurred for the packet or not. In the patches in this series, I leave a warning for when the problematic path occurs because I cannot figure out a secure way to fix the security issue that applies to the core MACsec offload handling in the Rx path without breaking MACsec offload for other vendors. Shown at the bottom is an example use case where plaintext traffic sent to a physical port of a NIC configured for MACsec offload is unable to be handled correctly by the software stack when the NIC provides awareness to the kernel about whether the received packet is MACsec traffic or not. In this specific example, plaintext ARP requests are being responded with MACsec encrypted ARP replies (which leads to routing information being unable to be built for the requester). Side 1 ip link del macsec0 ip address flush mlx5_1 ip address add 1.1.1.1/24 dev mlx5_1 ip link set dev mlx5_1 up ip link add link mlx5_1 macsec0 type macsec sci 1 encrypt on ip link set dev macsec0 address 00:11:22:33:44:66 ip macsec offload macsec0 mac ip macsec add macsec0 tx sa 0 pn 1 on key 00 dffafc8d7b9a43d5b9a3dfbbf6a30c16 ip macsec add macsec0 rx sci 2 on ip macsec add macsec0 rx sci 2 sa 0 pn 1 on key 00 ead3664f508eb06c40ac7104cdae4ce5 ip address flush macsec0 ip address add 2.2.2.1/24 dev macsec0 ip link set dev macsec0 up # macsec0 enters promiscuous mode. # This enables all traffic received on macsec_vlan to be processed by # the macsec offload rx datapath. This however means that traffic # meant to be received by mlx5_1 will be incorrectly steered to # macsec0 as well. ip link add link macsec0 name macsec_vlan type vlan id 1 ip link set dev macsec_vlan address 00:11:22:33:44:88 ip address flush macsec_vlan ip address add 3.3.3.1/24 dev macsec_vlan ip link set dev macsec_vlan up Side 2 ip link del macsec0 ip address flush mlx5_1 ip address add 1.1.1.2/24 dev mlx5_1 ip link set dev mlx5_1 up ip link add link mlx5_1 macsec0 type macsec sci 2 encrypt on ip link set dev macsec0 address 00:11:22:33:44:77 ip macsec offload macsec0 mac ip macsec add macsec0 tx sa 0 pn 1 on key 00 ead3664f508eb06c40ac7104cdae4ce5 ip macsec add macsec0 rx sci 1 on ip macsec add macsec0 rx sci 1 sa 0 pn 1 on key 00 dffafc8d7b9a43d5b9a3dfbbf6a30c16 ip address flush macsec0 ip address add 2.2.2.2/24 dev macsec0 ip link set dev macsec0 up # macsec0 enters promiscuous mode. # This enables all traffic received on macsec_vlan to be processed by # the macsec offload rx datapath. This however means that traffic # meant to be received by mlx5_1 will be incorrectly steered to # macsec0 as well. ip link add link macsec0 name macsec_vlan type vlan id 1 ip link set dev macsec_vlan address 00:11:22:33:44:99 ip address flush macsec_vlan ip address add 3.3.3.2/24 dev macsec_vlan ip link set dev macsec_vlan up Side 1 ping -I mlx5_1 1.1.1.2 PING 1.1.1.2 (1.1.1.2) from 1.1.1.1 mlx5_1: 56(84) bytes of data. From 1.1.1.1 icmp_seq=1 Destination Host Unreachable ping: sendmsg: No route to host From 1.1.1.1 icmp_seq=2 Destination Host Unreachable From 1.1.1.1 icmp_seq=3 Destination Host Unreachable Changes: v1->v2: * Fixed series subject to detail the issue being fixed * Removed strange characters from cover letter * Added comment in example that illustrates the impact involving promiscuous mode * Added patch for generalizing packet type detection * Added Fixes: tags and targeting net * Removed pointless warning in the heuristic Rx path for macsec offload * Applied small refactor in Rx path offload to minimize scope of rx_sc local variable Link: https://github.com/Binary-Eater/macsec-rx-offload/blob/trunk/MACsec_violati… Link: https://lore.kernel.org/netdev/20240419011740.333714-1-rrameshbabu@nvidia.c… Link: https://lore.kernel.org/netdev/87r0l25y1c.fsf@nvidia.com/ Link: https://lore.kernel.org/netdev/20231116182900.46052-1-rrameshbabu@nvidia.co… Cc: Sabrina Dubroca <sd(a)queasysnail.net> Cc: stable(a)vger.kernel.org Signed-off-by: Rahul Rameshbabu <rrameshbabu(a)nvidia.com> --- Rahul Rameshbabu (4): macsec: Enable devices to advertise whether they update sk_buff md_dst during offloads ethernet: Add helper for assigning packet type when dest address does not match device address macsec: Detect if Rx skb is macsec-related for offloading devices that update md_dst net/mlx5e: Advertise mlx5 ethernet driver updates sk_buff md_dst for MACsec .../mellanox/mlx5/core/en_accel/macsec.c | 1 + drivers/net/macsec.c | 46 +++++++++++++++---- include/linux/etherdevice.h | 24 ++++++++++ include/net/macsec.h | 2 + net/ethernet/eth.c | 12 +---- 5 files changed, 64 insertions(+), 21 deletions(-) -- 2.42.0

8 months, 2 weeks

3
7
0 0

Re:

by Greg KH

On Fri, Apr 19, 2024 at 11:46:56PM +0800, George Guo wrote: > Subject: [PATCH 4.19.y v6 0/2] Double-free bug discovery on testing trigger-field-variable-support.tc > > 1) About v4-0001-tracing-Remove-hist-trigger-synth_var_refs.patch: > > The reason I am backporting this patch is that no one found the double-free bug > at that time, then later the code was removed on upstream, but > 4.19-stable has the bug. Both now queued up, thanks greg k-h

8 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] NFSD: fix endianness issue in nfsd4_encode_fattr4" failed to apply to 6.8-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.8-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-6.8.y git checkout FETCH_HEAD git cherry-pick -x f488138b526715c6d2568d7329c4477911be4210 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024041908-sandblast-sullen-2eed@gregkh' --subject-prefix 'PATCH 6.8.y' HEAD^.. Possible dependencies: f488138b5267 ("NFSD: fix endianness issue in nfsd4_encode_fattr4") c5967721e106 ("NFSD: handle GETATTR conflict with write delegation") 6487a13b5c6b ("NFSD: add support for CB_GETATTR callback") 4b14885411f7 ("nfsd: make all of the nfsd stats per-network namespace") 93483ac5fec6 ("nfsd: expose /proc/net/sunrpc/nfsd in net namespaces") d98416cc2154 ("nfsd: rename NFSD_NET_* to NFSD_STATS_*") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f488138b526715c6d2568d7329c4477911be4210 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik <gor(a)linux.ibm.com> Date: Thu, 11 Apr 2024 11:45:57 +0200 Subject: [PATCH] NFSD: fix endianness issue in nfsd4_encode_fattr4 The nfs4 mount fails with EIO on 64-bit big endian architectures since v6.7. The issue arises from employing a union in the nfsd4_encode_fattr4() function to overlay a 32-bit array with a 64-bit values based bitmap, which does not function as intended. Address the endianness issue by utilizing bitmap_from_arr32() to copy 32-bit attribute masks into a bitmap in an endianness-agnostic manner. Cc: stable(a)vger.kernel.org Fixes: fce7913b13d0 ("NFSD: Use a bitmask loop to encode FATTR4 results") Link: https://bugs.launchpad.net/ubuntu/+source/nfs-utils/+bug/2060217 Signed-off-by: Vasily Gorbik <gor(a)linux.ibm.com> Reviewed-by: Jeff Layton <jlayton(a)kernel.org> Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fac938f563ad..1955481832e0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3490,11 +3490,13 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct dentry *dentry, const u32 *bmval, int ignore_crossmnt) { + DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); struct nfsd4_fattr_args args; struct svc_fh *tempfh = NULL; int starting_len = xdr->buf->len; __be32 *attrlen_p, status; int attrlen_offset; + u32 attrmask[3]; int err; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; @@ -3502,10 +3504,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, .mnt = exp->ex_path.mnt, .dentry = dentry, }; - union { - u32 attrmask[3]; - unsigned long mask[2]; - } u; unsigned long bit; bool file_modified = false; u64 size = 0; @@ -3521,20 +3519,19 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, /* * Make a local copy of the attribute bitmap that can be modified. */ - memset(&u, 0, sizeof(u)); - u.attrmask[0] = bmval[0]; - u.attrmask[1] = bmval[1]; - u.attrmask[2] = bmval[2]; + attrmask[0] = bmval[0]; + attrmask[1] = bmval[1]; + attrmask[2] = bmval[2]; args.rdattr_err = 0; if (exp->ex_fslocs.migrated) { - status = fattr_handle_absent_fs(&u.attrmask[0], &u.attrmask[1], - &u.attrmask[2], &args.rdattr_err); + status = fattr_handle_absent_fs(&attrmask[0], &attrmask[1], + &attrmask[2], &args.rdattr_err); if (status) goto out; } args.size = 0; - if (u.attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { + if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) { status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry), &file_modified, &size); if (status) @@ -3553,16 +3550,16 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (!(args.stat.result_mask & STATX_BTIME)) /* underlying FS does not offer btime so we can't share it */ - u.attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; - if ((u.attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | + attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE; + if ((attrmask[0] & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_MAXNAME)) || - (u.attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | + (attrmask[1] & (FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL))) { err = vfs_statfs(&path, &args.statfs); if (err) goto out_nfserr; } - if ((u.attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && + if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) { tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL); status = nfserr_jukebox; @@ -3577,10 +3574,10 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, args.fhp = fhp; args.acl = NULL; - if (u.attrmask[0] & FATTR4_WORD0_ACL) { + if (attrmask[0] & FATTR4_WORD0_ACL) { err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl); if (err == -EOPNOTSUPP) - u.attrmask[0] &= ~FATTR4_WORD0_ACL; + attrmask[0] &= ~FATTR4_WORD0_ACL; else if (err == -EINVAL) { status = nfserr_attrnotsupp; goto out; @@ -3592,17 +3589,17 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #ifdef CONFIG_NFSD_V4_SECURITY_LABEL args.context = NULL; - if ((u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || - u.attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) || + attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { if (exp->ex_flags & NFSEXP_SECURITY_LABEL) err = security_inode_getsecctx(d_inode(dentry), &args.context, &args.contextlen); else err = -EOPNOTSUPP; args.contextsupport = (err == 0); - if (u.attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { + if (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) { if (err == -EOPNOTSUPP) - u.attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + attrmask[2] &= ~FATTR4_WORD2_SECURITY_LABEL; else if (err) goto out_nfserr; } @@ -3610,8 +3607,8 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */ /* attrmask */ - status = nfsd4_encode_bitmap4(xdr, u.attrmask[0], - u.attrmask[1], u.attrmask[2]); + status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], + attrmask[2]); if (status) goto out; @@ -3620,7 +3617,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr, attrlen_p = xdr_reserve_space(xdr, XDR_UNIT); if (!attrlen_p) goto out_resource; - for_each_set_bit(bit, (const unsigned long *)&u.mask, + bitmap_from_arr32(attr_bitmap, attrmask, + ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)); + for_each_set_bit(bit, attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) { status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args); if (status != nfs_ok)

8 months, 2 weeks

5
6
0 0

FAILED: patch "[PATCH] powerpc/ftrace: Ignore ftrace locations in exit text sections" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-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-6.6.y git checkout FETCH_HEAD git cherry-pick -x ea73179e64131bcd29ba6defd33732abdf8ca14b # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024021902-authentic-handpick-da09@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: ea73179e6413 ("powerpc/ftrace: Ignore ftrace locations in exit text sections") 2ec36570c358 ("powerpc/ftrace: Fix indentation in ftrace.h") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ea73179e64131bcd29ba6defd33732abdf8ca14b Mon Sep 17 00:00:00 2001 From: Naveen N Rao <naveen(a)kernel.org> Date: Tue, 13 Feb 2024 23:24:10 +0530 Subject: [PATCH] powerpc/ftrace: Ignore ftrace locations in exit text sections Michael reported that we are seeing an ftrace bug on bootup when KASAN is enabled and we are using -fpatchable-function-entry: ftrace: allocating 47780 entries in 18 pages ftrace-powerpc: 0xc0000000020b3d5c: No module provided for non-kernel address ------------[ ftrace bug ]------------ ftrace faulted on modifying [<c0000000020b3d5c>] 0xc0000000020b3d5c Initializing ftrace call sites ftrace record flags: 0 (0) expected tramp: c00000000008cef4 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/trace/ftrace.c:2180 ftrace_bug+0x3c0/0x424 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 6.5.0-rc3-00120-g0f71dcfb4aef #860 Hardware name: IBM pSeries (emulated by qemu) POWER9 (raw) 0x4e1202 0xf000005 of:SLOF,HEAD hv:linux,kvm pSeries NIP: c0000000003aa81c LR: c0000000003aa818 CTR: 0000000000000000 REGS: c0000000033cfab0 TRAP: 0700 Not tainted (6.5.0-rc3-00120-g0f71dcfb4aef) MSR: 8000000002021033 <SF,VEC,ME,IR,DR,RI,LE> CR: 28028240 XER: 00000000 CFAR: c0000000002781a8 IRQMASK: 3 ... NIP [c0000000003aa81c] ftrace_bug+0x3c0/0x424 LR [c0000000003aa818] ftrace_bug+0x3bc/0x424 Call Trace: ftrace_bug+0x3bc/0x424 (unreliable) ftrace_process_locs+0x5f4/0x8a0 ftrace_init+0xc0/0x1d0 start_kernel+0x1d8/0x484 With CONFIG_FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY=y and CONFIG_KASAN=y, compiler emits nops in functions that it generates for registering and unregistering global variables (unlike with -pg and -mprofile-kernel where calls to _mcount() are not generated in those functions). Those functions then end up in INIT_TEXT and EXIT_TEXT respectively. We don't expect to see any profiled functions in EXIT_TEXT, so ftrace_init_nop() assumes that all addresses that aren't in the core kernel text belongs to a module. Since these functions do not match that criteria, we see the above bug. Address this by having ftrace ignore all locations in the text exit sections of vmlinux. Fixes: 0f71dcfb4aef ("powerpc/ftrace: Add support for -fpatchable-function-entry") Cc: stable(a)vger.kernel.org # v6.6+ Reported-by: Michael Ellerman <mpe(a)ellerman.id.au> Signed-off-by: Naveen N Rao <naveen(a)kernel.org> Reviewed-by: Benjamin Gray <bgray(a)linux.ibm.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://msgid.link/20240213175410.1091313-1-naveen@kernel.org diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 1ebd2ca97f12..107fc5a48456 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -20,14 +20,6 @@ #ifndef __ASSEMBLY__ extern void _mcount(void); -static inline unsigned long ftrace_call_adjust(unsigned long addr) -{ - if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) - addr += MCOUNT_INSN_SIZE; - - return addr; -} - unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp); @@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; } #ifdef CONFIG_FUNCTION_TRACER extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[]; void ftrace_free_init_tramp(void); +unsigned long ftrace_call_adjust(unsigned long addr); #else static inline void ftrace_free_init_tramp(void) { } +static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; } #endif #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index ea26665f82cf..f43f3a6b0051 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t; extern char __head_end[]; extern char __srwx_boundary[]; +extern char __exittext_begin[], __exittext_end[]; /* Patch sites */ extern s32 patch__call_flush_branch_caches1; diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 82010629cf88..d8d6b4fd9a14 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -27,10 +27,22 @@ #include <asm/ftrace.h> #include <asm/syscall.h> #include <asm/inst.h> +#include <asm/sections.h> #define NUM_FTRACE_TRAMPS 2 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; +unsigned long ftrace_call_adjust(unsigned long addr) +{ + if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end) + return 0; + + if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY)) + addr += MCOUNT_INSN_SIZE; + + return addr; +} + static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link) { ppc_inst_t op; diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 7b85c3b460a3..12fab1803bcf 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -37,6 +37,11 @@ #define NUM_FTRACE_TRAMPS 8 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS]; +unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} + static ppc_inst_t ftrace_call_replace(unsigned long ip, unsigned long addr, int link) { diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 1c5970df3233..f420df7888a7 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -281,7 +281,9 @@ SECTIONS * to deal with references from __bug_table */ .exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) { + __exittext_begin = .; EXIT_TEXT + __exittext_end = .; } . = ALIGN(PAGE_SIZE);

8 months, 2 weeks

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2024