From 203a6763ab699da0568fd2b76303d03bb121abd4 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 13 Mar 2024 16:32:27 -0700 Subject: Revert "crypto: pkcs7 - remove sha1 support" This reverts commit 16ab7cb5825fc3425c16ad2c6e53d827f382d7c6 because it broke iwd. iwd uses the KEYCTL_PKEY_* UAPIs via its dependency libell, and apparently it is relying on SHA-1 signature support. These UAPIs are fairly obscure, and their documentation does not mention which algorithms they support. iwd really should be using a properly supported userspace crypto library instead. Regardless, since something broke we have to revert the change. It may be possible that some parts of this commit can be reinstated without breaking iwd (e.g. probably the removal of MODULE_SIG_SHA1), but for now this just does a full revert to get things working again. Reported-by: Karel Balej Closes: https://lore.kernel.org/r/CZSHRUIJ4RKL.34T4EASV5DNJM@matfyz.cz Cc: Dimitri John Ledkov Signed-off-by: Eric Biggers Tested-by: Karel Balej Signed-off-by: Herbert Xu --- include/linux/oid_registry.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 3921fbed0b28..51421fdbb0ba 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -17,10 +17,12 @@ * build_OID_registry.pl to generate the data for look_up_OID(). */ enum OID { + OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */ OID_id_dsa, /* 1.2.840.10040.4.1 */ OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */ OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */ OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */ + OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */ OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */ OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */ @@ -28,6 +30,7 @@ enum OID { /* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */ OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */ + OID_sha1WithRSAEncryption, /* 1.2.840.113549.1.1.5 */ OID_sha256WithRSAEncryption, /* 1.2.840.113549.1.1.11 */ OID_sha384WithRSAEncryption, /* 1.2.840.113549.1.1.12 */ OID_sha512WithRSAEncryption, /* 1.2.840.113549.1.1.13 */ @@ -64,6 +67,7 @@ enum OID { OID_PKU2U, /* 1.3.5.1.5.2.7 */ OID_Scram, /* 1.3.6.1.5.5.14 */ OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ + OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ -- cgit v1.2.3 From 0c76106cb97548810214def8ee22700bbbb90543 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 19 Mar 2024 16:12:09 +0900 Subject: scsi: sd: Fix TCG OPAL unlock on system resume Commit 3cc2ffe5c16d ("scsi: sd: Differentiate system and runtime start/stop management") introduced the manage_system_start_stop scsi_device flag to allow libata to indicate to the SCSI disk driver that nothing should be done when resuming a disk on system resume. This change turned the execution of sd_resume() into a no-op for ATA devices on system resume. While this solved deadlock issues during device resume, this change also wrongly removed the execution of opal_unlock_from_suspend(). As a result, devices with TCG OPAL locking enabled remain locked and inaccessible after a system resume from sleep. To fix this issue, introduce the SCSI driver resume method and implement it with the sd_resume() function calling opal_unlock_from_suspend(). The former sd_resume() function is renamed to sd_resume_common() and modified to call the new sd_resume() function. For non-ATA devices, this result in no functional changes. In order for libata to explicitly execute sd_resume() when a device is resumed during system restart, the function scsi_resume_device() is introduced. libata calls this function from the revalidation work executed on devie resume, a state that is indicated with the new device flag ATA_DFLAG_RESUMING. Doing so, locked TCG OPAL enabled devices are unlocked on resume, allowing normal operation. Fixes: 3cc2ffe5c16d ("scsi: sd: Differentiate system and runtime start/stop management") Link: https://bugzilla.kernel.org/show_bug.cgi?id=218538 Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal Link: https://lore.kernel.org/r/20240319071209.1179257-1-dlemoal@kernel.org Signed-off-by: Martin K. Petersen --- drivers/ata/libata-eh.c | 5 ++++- drivers/ata/libata-scsi.c | 9 +++++++++ drivers/scsi/scsi_scan.c | 34 ++++++++++++++++++++++++++++++++++ drivers/scsi/sd.c | 23 +++++++++++++++++++---- include/linux/libata.h | 1 + include/scsi/scsi_driver.h | 1 + include/scsi/scsi_host.h | 1 + 7 files changed, 69 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index b0d6e69c4a5b..214b935c2ced 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -712,8 +712,10 @@ void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap) ehc->saved_ncq_enabled |= 1 << devno; /* If we are resuming, wake up the device */ - if (ap->pflags & ATA_PFLAG_RESUMING) + if (ap->pflags & ATA_PFLAG_RESUMING) { + dev->flags |= ATA_DFLAG_RESUMING; ehc->i.dev_action[devno] |= ATA_EH_SET_ACTIVE; + } } } @@ -3169,6 +3171,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link, return 0; err: + dev->flags &= ~ATA_DFLAG_RESUMING; *r_failed_dev = dev; return rc; } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 0a0f483124c3..2f4c58837641 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -4730,6 +4730,7 @@ void ata_scsi_dev_rescan(struct work_struct *work) struct ata_link *link; struct ata_device *dev; unsigned long flags; + bool do_resume; int ret = 0; mutex_lock(&ap->scsi_scan_mutex); @@ -4751,7 +4752,15 @@ void ata_scsi_dev_rescan(struct work_struct *work) if (scsi_device_get(sdev)) continue; + do_resume = dev->flags & ATA_DFLAG_RESUMING; + spin_unlock_irqrestore(ap->lock, flags); + if (do_resume) { + ret = scsi_resume_device(sdev); + if (ret == -EWOULDBLOCK) + goto unlock; + dev->flags &= ~ATA_DFLAG_RESUMING; + } ret = scsi_rescan_device(sdev); scsi_device_put(sdev); spin_lock_irqsave(ap->lock, flags); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 8d06475de17a..ffd7e7e72933 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1642,6 +1642,40 @@ int scsi_add_device(struct Scsi_Host *host, uint channel, } EXPORT_SYMBOL(scsi_add_device); +int scsi_resume_device(struct scsi_device *sdev) +{ + struct device *dev = &sdev->sdev_gendev; + int ret = 0; + + device_lock(dev); + + /* + * Bail out if the device or its queue are not running. Otherwise, + * the rescan may block waiting for commands to be executed, with us + * holding the device lock. This can result in a potential deadlock + * in the power management core code when system resume is on-going. + */ + if (sdev->sdev_state != SDEV_RUNNING || + blk_queue_pm_only(sdev->request_queue)) { + ret = -EWOULDBLOCK; + goto unlock; + } + + if (dev->driver && try_module_get(dev->driver->owner)) { + struct scsi_driver *drv = to_scsi_driver(dev->driver); + + if (drv->resume) + ret = drv->resume(dev); + module_put(dev->driver->owner); + } + +unlock: + device_unlock(dev); + + return ret; +} +EXPORT_SYMBOL(scsi_resume_device); + int scsi_rescan_device(struct scsi_device *sdev) { struct device *dev = &sdev->sdev_gendev; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index ccff8f2e2e75..3cf898670290 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -4108,7 +4108,21 @@ static int sd_suspend_runtime(struct device *dev) return sd_suspend_common(dev, true); } -static int sd_resume(struct device *dev, bool runtime) +static int sd_resume(struct device *dev) +{ + struct scsi_disk *sdkp = dev_get_drvdata(dev); + + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + + if (opal_unlock_from_suspend(sdkp->opal_dev)) { + sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n"); + return -EIO; + } + + return 0; +} + +static int sd_resume_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret; @@ -4124,7 +4138,7 @@ static int sd_resume(struct device *dev, bool runtime) sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); if (!ret) { - opal_unlock_from_suspend(sdkp->opal_dev); + sd_resume(dev); sdkp->suspended = false; } @@ -4143,7 +4157,7 @@ static int sd_resume_system(struct device *dev) return 0; } - return sd_resume(dev, false); + return sd_resume_common(dev, false); } static int sd_resume_runtime(struct device *dev) @@ -4170,7 +4184,7 @@ static int sd_resume_runtime(struct device *dev) "Failed to clear sense data\n"); } - return sd_resume(dev, true); + return sd_resume_common(dev, true); } static const struct dev_pm_ops sd_pm_ops = { @@ -4193,6 +4207,7 @@ static struct scsi_driver sd_template = { .pm = &sd_pm_ops, }, .rescan = sd_rescan, + .resume = sd_resume, .init_command = sd_init_command, .uninit_command = sd_uninit_command, .done = sd_done, diff --git a/include/linux/libata.h b/include/linux/libata.h index 26d68115afb8..324d792e7c78 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -107,6 +107,7 @@ enum { ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */ ATA_DFLAG_CDL_ENABLED = (1 << 21), /* cmd duration limits is enabled */ + ATA_DFLAG_RESUMING = (1 << 22), /* Device is resuming */ ATA_DFLAG_DETACH = (1 << 24), ATA_DFLAG_DETACHED = (1 << 25), ATA_DFLAG_DA = (1 << 26), /* device supports Device Attention */ diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h index 4ce1988b2ba0..f40915d2ecee 100644 --- a/include/scsi/scsi_driver.h +++ b/include/scsi/scsi_driver.h @@ -12,6 +12,7 @@ struct request; struct scsi_driver { struct device_driver gendrv; + int (*resume)(struct device *); void (*rescan)(struct device *); blk_status_t (*init_command)(struct scsi_cmnd *); void (*uninit_command)(struct scsi_cmnd *); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index b259d42a1e1a..129001f600fc 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -767,6 +767,7 @@ scsi_template_proc_dir(const struct scsi_host_template *sht); #define scsi_template_proc_dir(sht) NULL #endif extern void scsi_scan_host(struct Scsi_Host *); +extern int scsi_resume_device(struct scsi_device *sdev); extern int scsi_rescan_device(struct scsi_device *sdev); extern void scsi_remove_host(struct Scsi_Host *); extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *); -- cgit v1.2.3 From c2ddeb29612f7ca84ed10c6d4f3ac99705135447 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 25 Mar 2024 13:58:08 +0100 Subject: genirq: Introduce IRQF_COND_ONESHOT and use it in pinctrl-amd There is a problem when a driver requests a shared interrupt line to run a threaded handler on it without IRQF_ONESHOT set if that flag has been set already for the IRQ in question by somebody else. Namely, the request fails which usually leads to a probe failure even though the driver might have worked just fine with IRQF_ONESHOT, but it does not want to use it by default. Currently, the only way to handle this is to try to request the IRQ without IRQF_ONESHOT, but with IRQF_PROBE_SHARED set and if this fails, try again with IRQF_ONESHOT set. However, this is a bit cumbersome and not very clean. When commit 7a36b901a6eb ("ACPI: OSL: Use a threaded interrupt handler for SCI") switched the ACPI subsystem over to using a threaded interrupt handler for the SCI, it had to use IRQF_ONESHOT for it because that's required due to the way the SCI handler works (it needs to walk all of the enabled GPEs before the interrupt line can be unmasked). The SCI interrupt line is not shared with other users very often due to the SCI handling overhead, but on sone systems it is shared and when the other user of it attempts to install a threaded handler, a flags mismatch related to IRQF_ONESHOT may occur. As it turned out, that happened to the pinctrl-amd driver and so commit 4451e8e8415e ("pinctrl: amd: Add IRQF_ONESHOT to the interrupt request") attempted to address the issue by adding IRQF_ONESHOT to the interrupt flags in that driver, but this is now causing an IRQF_ONESHOT-related mismatch to occur on another system which cannot boot as a result of it. Clearly, pinctrl-amd can work with IRQF_ONESHOT if need be, but it should not set that flag by default, so it needs a way to indicate that to the interrupt subsystem. To that end, introdcuce a new interrupt flag, IRQF_COND_ONESHOT, which will only have effect when the IRQ line is shared and IRQF_ONESHOT has been set for it already, in which case it will be promoted to the latter. This is sufficient for drivers sharing the interrupt line with the SCI as it is requested by the ACPI subsystem before any drivers are probed, so they will always see IRQF_ONESHOT set for the interrupt in question. Fixes: 4451e8e8415e ("pinctrl: amd: Add IRQF_ONESHOT to the interrupt request") Reported-by: Francisco Ayala Le Brun Signed-off-by: Rafael J. Wysocki Signed-off-by: Thomas Gleixner Reviewed-by: Linus Walleij Cc: 6.8+ # 6.8+ Closes: https://lore.kernel.org/lkml/CAN-StX1HqWqi+YW=t+V52-38Mfp5fAz7YHx4aH-CQjgyNiKx3g@mail.gmail.com/ Link: https://lore.kernel.org/r/12417336.O9o76ZdvQC@kreacher --- drivers/pinctrl/pinctrl-amd.c | 2 +- include/linux/interrupt.h | 3 +++ kernel/irq/manage.c | 9 +++++++-- 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 49f89b70dcec..7f66ec73199a 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -1159,7 +1159,7 @@ static int amd_gpio_probe(struct platform_device *pdev) } ret = devm_request_irq(&pdev->dev, gpio_dev->irq, amd_gpio_irq_handler, - IRQF_SHARED | IRQF_ONESHOT, KBUILD_MODNAME, gpio_dev); + IRQF_SHARED | IRQF_COND_ONESHOT, KBUILD_MODNAME, gpio_dev); if (ret) goto out2; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 76121c2bb4f8..5c9bdd3ffccc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -67,6 +67,8 @@ * later. * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, * depends on IRQF_PERCPU. + * IRQF_COND_ONESHOT - Agree to do IRQF_ONESHOT if already set for a shared + * interrupt. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -82,6 +84,7 @@ #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 #define IRQF_NO_DEBUG 0x00100000 +#define IRQF_COND_ONESHOT 0x00200000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index ad3eaf2ab959..bf9ae8a8686f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,8 +1643,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!((old->flags & new->flags) & IRQF_SHARED) || - (oldtype != (new->flags & IRQF_TRIGGER_MASK)) || - ((old->flags ^ new->flags) & IRQF_ONESHOT)) + (oldtype != (new->flags & IRQF_TRIGGER_MASK))) + goto mismatch; + + if ((old->flags & IRQF_ONESHOT) && + (new->flags & IRQF_COND_ONESHOT)) + new->flags |= IRQF_ONESHOT; + else if ((old->flags ^ new->flags) & IRQF_ONESHOT) goto mismatch; /* All handlers must agree on per-cpuness */ -- cgit v1.2.3 From 52464f59a361a3ba49d6eabc4f65d5c0b9d1de39 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 25 Mar 2024 17:00:57 +0000 Subject: gpiolib: Add stubs for GPIO lookup functions The gpio_device_find_by_() functions do not have stubs which means that if they are referenced from code with an optiona dependency on gpiolib then the code will fail to link. Add stubs for lookups via fwnode and label. I have not added a stub for plain gpio_device_find() since it seems harder to see a use case for that which does not depend on gpiolib. With the addition of the GPIO reset controller (which lacks a gpiolib dependency) to the arm64 defconfig this is causing build breaks for arm64 virtconfig in -next: aarch64-linux-gnu-ld: drivers/reset/core.o: in function `__reset_add_reset_gpio_lookup': /build/stage/linux/drivers/reset/core.c:861:(.text+0xccc): undefined reference to `gpio_device_find_by_fwnode' Signed-off-by: Mark Brown Reviewed-by: Krzysztof Kozlowski Signed-off-by: Bartosz Golaszewski --- include/linux/gpio/driver.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index dc75f802e284..f8617eaf08ba 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -646,8 +646,6 @@ int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, struct gpio_device *gpio_device_find(const void *data, int (*match)(struct gpio_chip *gc, const void *data)); -struct gpio_device *gpio_device_find_by_label(const char *label); -struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode); struct gpio_device *gpio_device_get(struct gpio_device *gdev); void gpio_device_put(struct gpio_device *gdev); @@ -814,6 +812,9 @@ struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc); int gpio_device_get_base(struct gpio_device *gdev); const char *gpio_device_get_label(struct gpio_device *gdev); +struct gpio_device *gpio_device_find_by_label(const char *label); +struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode); + #else /* CONFIG_GPIOLIB */ #include @@ -843,6 +844,18 @@ static inline const char *gpio_device_get_label(struct gpio_device *gdev) return NULL; } +static inline struct gpio_device *gpio_device_find_by_label(const char *label) +{ + WARN_ON(1); + return NULL; +} + +static inline struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + WARN_ON(1); + return NULL; +} + static inline int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset) { -- cgit v1.2.3 From 9cecde80aae0fb0aa44425575d5aca71bc646d89 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 15 Mar 2024 14:08:21 +0000 Subject: mm: increase folio batch size On a 104 thread, 2 socket Skylake system, Intel report a 4.7% performance reduction with will-it-scale page_fault2. This was due to reducing the size of the batch from 32 to 15. Increasing the folio batch size from 15 to 31 gives a performance increase of 12.5% relative to the original, or 17.2% relative to the reduced performance commit. The penalty of this commit is an additional 128 bytes of stack usage. Six folio_batches are also allocated from percpu memory in cpu_fbatches so that will be an additional 768 bytes of percpu memory (per CPU). Tim Chen originally submitted a patch like this in 2020: https://lore.kernel.org/linux-mm/d1cc9f12a8ad6c2a52cb600d93b06b064f2bbc57.1593205965.git.tim.c.chen@linux.intel.com/ Link: https://lkml.kernel.org/r/20240315140823.2478146-1-willy@infradead.org Fixes: 99fbb6bfc16f ("mm: make folios_put() the basis of release_pages()") Signed-off-by: Matthew Wilcox (Oracle) Tested-by: Yujie Liu Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202403151058.7048f6a8-oliver.sang@intel.com Signed-off-by: Andrew Morton --- include/linux/pagevec.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index fcc06c300a72..5d3a0cccc6bf 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -11,8 +11,8 @@ #include -/* 15 pointers + header align the folio_batch structure to a power of two */ -#define PAGEVEC_SIZE 15 +/* 31 pointers + header align the folio_batch structure to a power of two */ +#define PAGEVEC_SIZE 31 struct folio; -- cgit v1.2.3 From d5aad4c2ca057e760a92a9a7d65bd38d72963f27 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Mon, 26 Feb 2024 17:35:41 -0800 Subject: prctl: generalize PR_SET_MDWE support check to be per-arch Patch series "ARM: prctl: Reject PR_SET_MDWE where not supported". I noticed after a recent kernel update that my ARM926 system started segfaulting on any execve() after calling prctl(PR_SET_MDWE). After some investigation it appears that ARMv5 is incapable of providing the appropriate protections for MDWE, since any readable memory is also implicitly executable. The prctl_set_mdwe() function already had some special-case logic added disabling it on PARISC (commit 793838138c15, "prctl: Disable prctl(PR_SET_MDWE) on parisc"); this patch series (1) generalizes that check to use an arch_*() function, and (2) adds a corresponding override for ARM to disable MDWE on pre-ARMv6 CPUs. With the series applied, prctl(PR_SET_MDWE) is rejected on ARMv5 and subsequent execve() calls (as well as mmap(PROT_READ|PROT_WRITE)) can succeed instead of unconditionally failing; on ARMv6 the prctl works as it did previously. [0] https://lore.kernel.org/all/2023112456-linked-nape-bf19@gregkh/ This patch (of 2): There exist systems other than PARISC where MDWE may not be feasible to support; rather than cluttering up the generic code with additional arch-specific logic let's add a generic function for checking MDWE support and allow each arch to override it as needed. Link: https://lkml.kernel.org/r/20240227013546.15769-4-zev@bewilderbeest.net Link: https://lkml.kernel.org/r/20240227013546.15769-5-zev@bewilderbeest.net Signed-off-by: Zev Weiss Acked-by: Helge Deller [parisc] Cc: Borislav Petkov Cc: David Hildenbrand Cc: Florent Revest Cc: "James E.J. Bottomley" Cc: Josh Triplett Cc: Kees Cook Cc: Miguel Ojeda Cc: Mike Rapoport (IBM) Cc: Oleg Nesterov Cc: Ondrej Mosnacek Cc: Rick Edgecombe Cc: Russell King (Oracle) Cc: Sam James Cc: Stefan Roesch Cc: Yang Shi Cc: Yin Fengwei Cc: [6.3+] Signed-off-by: Andrew Morton --- arch/parisc/include/asm/mman.h | 14 ++++++++++++++ include/linux/mman.h | 8 ++++++++ kernel/sys.c | 7 +++++-- 3 files changed, 27 insertions(+), 2 deletions(-) create mode 100644 arch/parisc/include/asm/mman.h (limited to 'include/linux') diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h new file mode 100644 index 000000000000..47c5a1991d10 --- /dev/null +++ b/arch/parisc/include/asm/mman.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include + +/* PARISC cannot allow mdwe as it needs writable stacks */ +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return false; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported + +#endif /* __ASM_MMAN_H__ */ diff --git a/include/linux/mman.h b/include/linux/mman.h index dc7048824be8..bcb201ab7a41 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -162,6 +162,14 @@ calc_vm_flag_bits(unsigned long flags) unsigned long vm_commit_limit(void); +#ifndef arch_memory_deny_write_exec_supported +static inline bool arch_memory_deny_write_exec_supported(void) +{ + return true; +} +#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported +#endif + /* * Denies creating a writable executable mapping or gaining executable permissions. * diff --git a/kernel/sys.c b/kernel/sys.c index f8e543f1e38a..8bb106a56b3a 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2408,8 +2408,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; - /* PARISC cannot allow mdwe as it needs writable stacks */ - if (IS_ENABLED(CONFIG_PARISC)) + /* + * EOPNOTSUPP might be more appropriate here in principle, but + * existing userspace depends on EINVAL specifically. + */ + if (!arch_memory_deny_write_exec_supported()) return -EINVAL; current_bits = get_current_mdwe(); -- cgit v1.2.3 From 0462c56c290a99a7f03e817ae5b843116dfb575c Mon Sep 17 00:00:00 2001 From: Herve Codina Date: Mon, 25 Mar 2024 16:21:25 +0100 Subject: driver core: Introduce device_link_wait_removal() The commit 80dd33cf72d1 ("drivers: base: Fix device link removal") introduces a workqueue to release the consumer and supplier devices used in the devlink. In the job queued, devices are release and in turn, when all the references to these devices are dropped, the release function of the device itself is called. Nothing is present to provide some synchronisation with this workqueue in order to ensure that all ongoing releasing operations are done and so, some other operations can be started safely. For instance, in the following sequence: 1) of_platform_depopulate() 2) of_overlay_remove() During the step 1, devices are released and related devlinks are removed (jobs pushed in the workqueue). During the step 2, OF nodes are destroyed but, without any synchronisation with devlink removal jobs, of_overlay_remove() can raise warnings related to missing of_node_put(): ERROR: memory leak, expected refcount 1 instead of 2 Indeed, the missing of_node_put() call is going to be done, too late, from the workqueue job execution. Introduce device_link_wait_removal() to offer a way to synchronize operations waiting for the end of devlink removals (i.e. end of workqueue jobs). Also, as a flushing operation is done on the workqueue, the workqueue used is moved from a system-wide workqueue to a local one. Cc: stable@vger.kernel.org Signed-off-by: Herve Codina Tested-by: Luca Ceresoli Reviewed-by: Nuno Sa Reviewed-by: Saravana Kannan Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20240325152140.198219-2-herve.codina@bootlin.com Signed-off-by: Rob Herring --- drivers/base/core.c | 26 +++++++++++++++++++++++--- include/linux/device.h | 1 + 2 files changed, 24 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index b93f3c5716ae..5f4e03336e68 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -44,6 +44,7 @@ static bool fw_devlink_is_permissive(void); static void __fw_devlink_link_to_consumers(struct device *dev); static bool fw_devlink_drv_reg_done; static bool fw_devlink_best_effort; +static struct workqueue_struct *device_link_wq; /** * __fwnode_link_add - Create a link between two fwnode_handles. @@ -533,12 +534,26 @@ static void devlink_dev_release(struct device *dev) /* * It may take a while to complete this work because of the SRCU * synchronization in device_link_release_fn() and if the consumer or - * supplier devices get deleted when it runs, so put it into the "long" - * workqueue. + * supplier devices get deleted when it runs, so put it into the + * dedicated workqueue. */ - queue_work(system_long_wq, &link->rm_work); + queue_work(device_link_wq, &link->rm_work); } +/** + * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate + */ +void device_link_wait_removal(void) +{ + /* + * devlink removal jobs are queued in the dedicated work queue. + * To be sure that all removal jobs are terminated, ensure that any + * scheduled work has run to completion. + */ + flush_workqueue(device_link_wq); +} +EXPORT_SYMBOL_GPL(device_link_wait_removal); + static struct class devlink_class = { .name = "devlink", .dev_groups = devlink_groups, @@ -4164,9 +4179,14 @@ int __init devices_init(void) sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj); if (!sysfs_dev_char_kobj) goto char_kobj_err; + device_link_wq = alloc_workqueue("device_link_wq", 0, 0); + if (!device_link_wq) + goto wq_err; return 0; + wq_err: + kobject_put(sysfs_dev_char_kobj); char_kobj_err: kobject_put(sysfs_dev_block_kobj); block_kobj_err: diff --git a/include/linux/device.h b/include/linux/device.h index 97c4b046c09d..b9f5464f44ed 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1247,6 +1247,7 @@ void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); +void device_link_wait_removal(void); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ -- cgit v1.2.3 From ddd65e19c60140673ea9f7249af0a672f1820623 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Sat, 23 Mar 2024 17:11:19 +0100 Subject: block: handle BLK_OPEN_RESTRICT_WRITES correctly Last kernel release we introduce CONFIG_BLK_DEV_WRITE_MOUNTED. By default this option is set. When it is set the long-standing behavior of being able to write to mounted block devices is enabled. But in order to guard against unintended corruption by writing to the block device buffer cache CONFIG_BLK_DEV_WRITE_MOUNTED can be turned off. In that case it isn't possible to write to mounted block devices anymore. A filesystem may open its block devices with BLK_OPEN_RESTRICT_WRITES which disallows concurrent BLK_OPEN_WRITE access. When we still had the bdev handle around we could recognize BLK_OPEN_RESTRICT_WRITES because the mode was passed around. Since we managed to get rid of the bdev handle we changed that logic to recognize BLK_OPEN_RESTRICT_WRITES based on whether the file was opened writable and writes to that block device are blocked. That logic doesn't work because we do allow BLK_OPEN_RESTRICT_WRITES to be specified without BLK_OPEN_WRITE. Fix the detection logic and use an FMODE_* bit. We could've also abused O_EXCL as an indicator that BLK_OPEN_RESTRICT_WRITES has been requested. For userspace open paths O_EXCL will never be retained but for internal opens where we open files that are never installed into a file descriptor table this is fine. But it would be a gamble that this doesn't cause bugs. Note that BLK_OPEN_RESTRICT_WRITES is an internal only flag that cannot directly be raised by userspace. It is implicitly raised during mounting. Passes xftests and blktests with CONFIG_BLK_DEV_WRITE_MOUNTED set and unset. Link: https://lore.kernel.org/r/ZfyyEwu9Uq5Pgb94@casper.infradead.org Link: https://lore.kernel.org/r/20240323-zielbereich-mittragen-6fdf14876c3e@brauner Fixes: 321de651fa56 ("block: don't rely on BLK_OPEN_RESTRICT_WRITES when yielding write access") Reviewed-by: Yu Kuai Reviewed-by: Jan Kara Reported-by: Matthew Wilcox Signed-off-by: Christian Brauner --- block/bdev.c | 14 +++++++------- include/linux/fs.h | 2 ++ 2 files changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index 7a5f611c3d2e..ab9cae0e05f1 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -821,13 +821,11 @@ static void bdev_yield_write_access(struct file *bdev_file) return; bdev = file_bdev(bdev_file); - /* Yield exclusive or shared write access. */ - if (bdev_file->f_mode & FMODE_WRITE) { - if (bdev_writes_blocked(bdev)) - bdev_unblock_writes(bdev); - else - bdev->bd_writers--; - } + + if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED) + bdev_unblock_writes(bdev); + else if (bdev_file->f_mode & FMODE_WRITE) + bdev->bd_writers--; } /** @@ -907,6 +905,8 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT; if (bdev_nowait(bdev)) bdev_file->f_mode |= FMODE_NOWAIT; + if (mode & BLK_OPEN_RESTRICT_WRITES) + bdev_file->f_mode |= FMODE_WRITE_RESTRICTED; bdev_file->f_mapping = bdev->bd_inode->i_mapping; bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping); bdev_file->private_data = holder; diff --git a/include/linux/fs.h b/include/linux/fs.h index 00fc429b0af0..8dfd53b52744 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -121,6 +121,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) +/* File writes are restricted (block device specific) */ +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ -- cgit v1.2.3 From ea2c09283b44d1a3732a195a9b257d56779c8863 Mon Sep 17 00:00:00 2001 From: Herve Codina Date: Mon, 25 Mar 2024 09:25:05 +0100 Subject: net: wan: framer: Add missing static inline qualifiers Compilation with CONFIG_GENERIC_FRAMER disabled lead to the following warnings: framer.h:184:16: warning: no previous prototype for function 'framer_get' [-Wmissing-prototypes] 184 | struct framer *framer_get(struct device *dev, const char *con_id) framer.h:184:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 184 | struct framer *framer_get(struct device *dev, const char *con_id) framer.h:189:6: warning: no previous prototype for function 'framer_put' [-Wmissing-prototypes] 189 | void framer_put(struct device *dev, struct framer *framer) framer.h:189:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 189 | void framer_put(struct device *dev, struct framer *framer) Add missing 'static inline' qualifiers for these functions. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202403241110.hfJqeJRu-lkp@intel.com/ Fixes: 82c944d05b1a ("net: wan: Add framer framework support") Cc: stable@vger.kernel.org Signed-off-by: Herve Codina Reviewed-by: Andy Shevchenko Signed-off-by: David S. Miller --- include/linux/framer/framer.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h index 9a9b88962c29..2b85fe9e7f9a 100644 --- a/include/linux/framer/framer.h +++ b/include/linux/framer/framer.h @@ -181,12 +181,12 @@ static inline int framer_notifier_unregister(struct framer *framer, return -ENOSYS; } -struct framer *framer_get(struct device *dev, const char *con_id) +static inline struct framer *framer_get(struct device *dev, const char *con_id) { return ERR_PTR(-ENOSYS); } -void framer_put(struct device *dev, struct framer *framer) +static inline void framer_put(struct device *dev, struct framer *framer) { } -- cgit v1.2.3 From 22650a99821dda3d05f1c334ea90330b4982de56 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 26 Mar 2024 13:47:22 +0100 Subject: fs,block: yield devices early Currently a device is only really released once the umount returns to userspace due to how file closing works. That ultimately could cause an old umount assumption to be violated that concurrent umount and mount don't fail. So an exclusively held device with a temporary holder should be yielded before the filesystem is gone. Add a helper that allows callers to do that. This also allows us to remove the two holder ops that Linus wasn't excited about. Link: https://lore.kernel.org/r/20240326-vfs-bdev-end_holder-v1-1-20af85202918@kernel.org Fixes: f3a608827d1f ("bdev: open block device as files") # mainline only Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Suggested-by: Linus Torvalds Signed-off-by: Christian Brauner --- block/bdev.c | 64 +++++++++++++++++++++++++++++++++++------ drivers/mtd/devices/block2mtd.c | 2 +- fs/bcachefs/super-io.c | 2 +- fs/cramfs/inode.c | 2 +- fs/ext4/super.c | 8 +++--- fs/f2fs/super.c | 2 +- fs/jfs/jfs_logmgr.c | 4 +-- fs/reiserfs/journal.c | 2 +- fs/romfs/super.c | 2 +- fs/super.c | 24 ++-------------- fs/xfs/xfs_buf.c | 2 +- fs/xfs/xfs_super.c | 6 ++-- include/linux/blkdev.h | 11 +------ 13 files changed, 76 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index a1946a902df3..b8e32d933a63 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -583,9 +583,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder, mutex_unlock(&bdev->bd_holder_lock); bd_clear_claiming(whole, holder); mutex_unlock(&bdev_lock); - - if (hops && hops->get_holder) - hops->get_holder(holder); } /** @@ -608,7 +605,6 @@ EXPORT_SYMBOL(bd_abort_claiming); static void bd_end_claim(struct block_device *bdev, void *holder) { struct block_device *whole = bdev_whole(bdev); - const struct blk_holder_ops *hops = bdev->bd_holder_ops; bool unblock = false; /* @@ -631,9 +627,6 @@ static void bd_end_claim(struct block_device *bdev, void *holder) whole->bd_holder = NULL; mutex_unlock(&bdev_lock); - if (hops && hops->put_holder) - hops->put_holder(holder); - /* * If this was the last claim, remove holder link and unblock evpoll if * it was a write holder. @@ -813,6 +806,11 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode) bdev->bd_writers++; } +static inline bool bdev_unclaimed(const struct file *bdev_file) +{ + return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host); +} + static void bdev_yield_write_access(struct file *bdev_file) { struct block_device *bdev; @@ -820,6 +818,9 @@ static void bdev_yield_write_access(struct file *bdev_file) if (bdev_allow_write_mounted) return; + if (bdev_unclaimed(bdev_file)) + return; + bdev = file_bdev(bdev_file); if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED) @@ -1012,6 +1013,20 @@ struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, } EXPORT_SYMBOL(bdev_file_open_by_path); +static inline void bd_yield_claim(struct file *bdev_file) +{ + struct block_device *bdev = file_bdev(bdev_file); + void *holder = bdev_file->private_data; + + lockdep_assert_held(&bdev->bd_disk->open_mutex); + + if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder))) + return; + + if (!bdev_unclaimed(bdev_file)) + bd_end_claim(bdev, holder); +} + void bdev_release(struct file *bdev_file) { struct block_device *bdev = file_bdev(bdev_file); @@ -1036,7 +1051,7 @@ void bdev_release(struct file *bdev_file) bdev_yield_write_access(bdev_file); if (holder) - bd_end_claim(bdev, holder); + bd_yield_claim(bdev_file); /* * Trigger event checking and tell drivers to flush MEDIA_CHANGE @@ -1056,6 +1071,39 @@ put_no_open: blkdev_put_no_open(bdev); } +/** + * bdev_fput - yield claim to the block device and put the file + * @bdev_file: open block device + * + * Yield claim on the block device and put the file. Ensure that the + * block device can be reclaimed before the file is closed which is a + * deferred operation. + */ +void bdev_fput(struct file *bdev_file) +{ + if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops)) + return; + + if (bdev_file->private_data) { + struct block_device *bdev = file_bdev(bdev_file); + struct gendisk *disk = bdev->bd_disk; + + mutex_lock(&disk->open_mutex); + bdev_yield_write_access(bdev_file); + bd_yield_claim(bdev_file); + /* + * Tell release we already gave up our hold on the + * device and if write restrictions are available that + * we already gave up write access to the device. + */ + bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host); + mutex_unlock(&disk->open_mutex); + } + + fput(bdev_file); +} +EXPORT_SYMBOL(bdev_fput); + /** * lookup_bdev() - Look up a struct block_device by name. * @pathname: Name of the block device in the filesystem. diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 97a00ec9a4d4..caacdc0a3819 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -209,7 +209,7 @@ static void block2mtd_free_device(struct block2mtd_dev *dev) if (dev->bdev_file) { invalidate_mapping_pages(dev->bdev_file->f_mapping, 0, -1); - fput(dev->bdev_file); + bdev_fput(dev->bdev_file); } kfree(dev); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index ad28e370b640..cb7b4de11a49 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -143,7 +143,7 @@ void bch2_free_super(struct bch_sb_handle *sb) { kfree(sb->bio); if (!IS_ERR_OR_NULL(sb->s_bdev_file)) - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); kfree(sb->holder); kfree(sb->sb_name); diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 39e75131fd5a..9901057a15ba 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb) sb->s_mtd = NULL; } else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) { sync_blockdev(sb->s_bdev); - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); } kfree(sbi); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cfb8449c731f..044135796f2b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5668,7 +5668,7 @@ failed_mount: brelse(sbi->s_sbh); if (sbi->s_journal_bdev_file) { invalidate_bdev(file_bdev(sbi->s_journal_bdev_file)); - fput(sbi->s_journal_bdev_file); + bdev_fput(sbi->s_journal_bdev_file); } out_fail: invalidate_bdev(sb->s_bdev); @@ -5913,7 +5913,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb, out_bh: brelse(bh); out_bdev: - fput(bdev_file); + bdev_fput(bdev_file); return ERR_PTR(errno); } @@ -5952,7 +5952,7 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, out_journal: jbd2_journal_destroy(journal); out_bdev: - fput(bdev_file); + bdev_fput(bdev_file); return ERR_PTR(errno); } @@ -7327,7 +7327,7 @@ static void ext4_kill_sb(struct super_block *sb) kill_block_super(sb); if (bdev_file) - fput(bdev_file); + bdev_fput(bdev_file); } static struct file_system_type ext4_fs_type = { diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index a6867f26f141..a4bc26dfdb1a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1558,7 +1558,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { if (i > 0) - fput(FDEV(i).bdev_file); + bdev_fput(FDEV(i).bdev_file); #ifdef CONFIG_BLK_DEV_ZONED kvfree(FDEV(i).blkz_seq); #endif diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 73389c68e251..9609349e92e5 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1141,7 +1141,7 @@ journal_found: lbmLogShutdown(log); close: /* close external log device */ - fput(bdev_file); + bdev_fput(bdev_file); free: /* free log descriptor */ mutex_unlock(&jfs_log_mutex); @@ -1485,7 +1485,7 @@ int lmLogClose(struct super_block *sb) bdev_file = log->bdev_file; rc = lmLogShutdown(log); - fput(bdev_file); + bdev_fput(bdev_file); kfree(log); diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 6474529c4253..e539ccd39e1e 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2589,7 +2589,7 @@ static void journal_list_init(struct super_block *sb) static void release_journal_dev(struct reiserfs_journal *journal) { if (journal->j_bdev_file) { - fput(journal->j_bdev_file); + bdev_fput(journal->j_bdev_file); journal->j_bdev_file = NULL; } } diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 2be227532f39..2cbb92462074 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -594,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb) #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); } #endif } diff --git a/fs/super.c b/fs/super.c index 71d9779c42b1..69ce6c600968 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1515,29 +1515,11 @@ static int fs_bdev_thaw(struct block_device *bdev) return error; } -static void fs_bdev_super_get(void *data) -{ - struct super_block *sb = data; - - spin_lock(&sb_lock); - sb->s_count++; - spin_unlock(&sb_lock); -} - -static void fs_bdev_super_put(void *data) -{ - struct super_block *sb = data; - - put_super(sb); -} - const struct blk_holder_ops fs_holder_ops = { .mark_dead = fs_bdev_mark_dead, .sync = fs_bdev_sync, .freeze = fs_bdev_freeze, .thaw = fs_bdev_thaw, - .get_holder = fs_bdev_super_get, - .put_holder = fs_bdev_super_put, }; EXPORT_SYMBOL_GPL(fs_holder_ops); @@ -1562,7 +1544,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, * writable from userspace even for a read-only block device. */ if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { - fput(bdev_file); + bdev_fput(bdev_file); return -EACCES; } @@ -1573,7 +1555,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, if (atomic_read(&bdev->bd_fsfreeze_count) > 0) { if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); - fput(bdev_file); + bdev_fput(bdev_file); return -EBUSY; } spin_lock(&sb_lock); @@ -1693,7 +1675,7 @@ void kill_block_super(struct super_block *sb) generic_shutdown_super(sb); if (bdev) { sync_blockdev(bdev); - fput(sb->s_bdev_file); + bdev_fput(sb->s_bdev_file); } } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 1a18c381127e..f0fa02264eda 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -2030,7 +2030,7 @@ xfs_free_buftarg( fs_put_dax(btp->bt_daxdev, btp->bt_mount); /* the main block device is closed by kill_block_super */ if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev) - fput(btp->bt_bdev_file); + bdev_fput(btp->bt_bdev_file); kfree(btp); } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index c21f10ab0f5d..bce020374c5e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -485,7 +485,7 @@ xfs_open_devices( mp->m_logdev_targp = mp->m_ddev_targp; /* Handle won't be used, drop it */ if (logdev_file) - fput(logdev_file); + bdev_fput(logdev_file); } return 0; @@ -497,10 +497,10 @@ xfs_open_devices( xfs_free_buftarg(mp->m_ddev_targp); out_close_rtdev: if (rtdev_file) - fput(rtdev_file); + bdev_fput(rtdev_file); out_close_logdev: if (logdev_file) - fput(logdev_file); + bdev_fput(logdev_file); return error; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c3e8f7cf96be..172c91879999 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1505,16 +1505,6 @@ struct blk_holder_ops { * Thaw the file system mounted on the block device. */ int (*thaw)(struct block_device *bdev); - - /* - * If needed, get a reference to the holder. - */ - void (*get_holder)(void *holder); - - /* - * Release the holder. - */ - void (*put_holder)(void *holder); }; /* @@ -1585,6 +1575,7 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) int bdev_freeze(struct block_device *bdev); int bdev_thaw(struct block_device *bdev); +void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct request *req_list; -- cgit v1.2.3 From 18685451fc4e546fc0e718580d32df3c0e5c8272 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 26 Mar 2024 11:18:41 +0100 Subject: inet: inet_defrag: prevent sk release while still in use 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 Reported-by: xingwei lee Reported-by: yue sun Reported-by: syzbot+e5167d7144a62715044c@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240326101845.30836-1-fw@strlen.de Signed-off-by: Paolo Abeni --- include/linux/skbuff.h | 7 +--- net/ipv4/inet_fragment.c | 70 +++++++++++++++++++++++++++------ net/ipv4/ip_fragment.c | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +- 4 files changed, 60 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0c7c67b3a87b..9d24aec064e8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -753,8 +753,6 @@ typedef unsigned char *sk_buff_data_t; * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by - * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in - * fragmentation management * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -875,10 +873,7 @@ struct sk_buff { struct llist_node ll_node; }; - union { - struct sock *sk; - int ip_defrag_offset; - }; + struct sock *sk; union { ktime_t tstamp; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 7072fc0783ef..c88c9034d630 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -24,6 +24,8 @@ #include #include +#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. @@ -39,6 +41,7 @@ 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)) @@ -396,12 +399,12 @@ 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); @@ -418,13 +421,13 @@ 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 @@ -438,7 +441,7 @@ 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; } @@ -448,13 +451,28 @@ 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; @@ -463,6 +481,12 @@ 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, @@ -470,13 +494,13 @@ 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) @@ -492,7 +516,7 @@ 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++) @@ -509,6 +533,21 @@ 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); @@ -516,6 +555,8 @@ EXPORT_SYMBOL(inet_frag_reasm_prepare); void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, void *reasm_data, bool try_coalesce) { + struct sock *sk = is_skb_wmem(head) ? head->sk : NULL; + const unsigned int head_truesize = head->truesize; struct sk_buff **nextp = reasm_data; struct rb_node *rbn; struct sk_buff *fp; @@ -579,6 +620,9 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, head->prev = NULL; head->tstamp = q->stamp; head->mono_delivery_time = q->mono_delivery_time; + + 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 a4941f53b523..fb947d1613fe 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -384,6 +384,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) } skb_dst_drop(skb); + skb_orphan(skb); return -EINPROGRESS; insert_error: @@ -487,7 +488,6 @@ 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 1a51a44571c3..d0dcbaca1994 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -294,6 +294,7 @@ 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: @@ -469,7 +470,6 @@ 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) { -- cgit v1.2.3 From 1a80dbcb2dbaf6e4c216e62e30fa7d3daa8001ce Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 27 Mar 2024 22:24:26 -0700 Subject: bpf: support deferring bpf_link dealloc to after RCU grace period BPF link for some program types is passed as a "context" which can be used by those BPF programs to look up additional information. E.g., for multi-kprobes and multi-uprobes, link is used to fetch BPF cookie values. Because of this runtime dependency, when bpf_link refcnt drops to zero there could still be active BPF programs running accessing link data. This patch adds generic support to defer bpf_link dealloc callback to after RCU GP, if requested. This is done by exposing two different deallocation callbacks, one synchronous and one deferred. If deferred one is provided, bpf_link_free() will schedule dealloc_deferred() callback to happen after RCU GP. BPF is using two flavors of RCU: "classic" non-sleepable one and RCU tasks trace one. The latter is used when sleepable BPF programs are used. bpf_link_free() accommodates that by checking underlying BPF program's sleepable flag, and goes either through normal RCU GP only for non-sleepable, or through RCU tasks trace GP *and* then normal RCU GP (taking into account rcu_trace_implies_rcu_gp() optimization), if BPF program is sleepable. We use this for multi-kprobe and multi-uprobe links, which dereference link during program run. We also preventively switch raw_tp link to use deferred dealloc callback, as upcoming changes in bpf-next tree expose raw_tp link data (specifically, cookie value) to BPF program at runtime as well. Fixes: 0dcac2725406 ("bpf: Add multi kprobe link") Fixes: 89ae89f53d20 ("bpf: Add multi uprobe link") Reported-by: syzbot+981935d9485a560bfbcb@syzkaller.appspotmail.com Reported-by: syzbot+2cb5a6c573e98db598cc@syzkaller.appspotmail.com Reported-by: syzbot+62d8b26793e8a2bd0516@syzkaller.appspotmail.com Signed-off-by: Andrii Nakryiko Acked-by: Jiri Olsa Link: https://lore.kernel.org/r/20240328052426.3042617-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 16 +++++++++++++++- kernel/bpf/syscall.c | 35 ++++++++++++++++++++++++++++++++--- kernel/trace/bpf_trace.c | 4 ++-- 3 files changed, 49 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4f20f62f9d63..890e152d553e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1574,12 +1574,26 @@ struct bpf_link { enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; - struct work_struct work; + /* rcu is used before freeing, work can be used to schedule that + * RCU-based freeing before that, so they never overlap + */ + union { + struct rcu_head rcu; + struct work_struct work; + }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); + /* deallocate link resources callback, called without RCU grace period + * waiting + */ void (*dealloc)(struct bpf_link *link); + /* deallocate link resources callback, called after RCU grace period; + * if underlying BPF program is sleepable we go through tasks trace + * RCU GP and then "classic" RCU GP + */ + void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ae2ff73bde7e..c287925471f6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3024,17 +3024,46 @@ void bpf_link_inc(struct bpf_link *link) atomic64_inc(&link->refcnt); } +static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) +{ + struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); + + /* free bpf_link and its containing memory */ + link->ops->dealloc_deferred(link); +} + +static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_link_defer_dealloc_rcu_gp(rcu); + else + call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); +} + /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { + bool sleepable = false; + bpf_link_free_id(link->id); if (link->prog) { + sleepable = link->prog->sleepable; /* detach BPF program, clean up used resources */ link->ops->release(link); bpf_prog_put(link->prog); } - /* free bpf_link and its containing memory */ - link->ops->dealloc(link); + if (link->ops->dealloc_deferred) { + /* schedule BPF link deallocation; if underlying BPF program + * is sleepable, we need to first wait for RCU tasks trace + * sync, then go through "classic" RCU grace period + */ + if (sleepable) + call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); + else + call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); + } + if (link->ops->dealloc) + link->ops->dealloc(link); } static void bpf_link_put_deferred(struct work_struct *work) @@ -3544,7 +3573,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, - .dealloc = bpf_raw_tp_link_dealloc, + .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0b73fe5f7206..9dc605f08a23 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2728,7 +2728,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_kprobe_multi_link_lops = { .release = bpf_kprobe_multi_link_release, - .dealloc = bpf_kprobe_multi_link_dealloc, + .dealloc_deferred = bpf_kprobe_multi_link_dealloc, .fill_link_info = bpf_kprobe_multi_link_fill_link_info, }; @@ -3242,7 +3242,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, static const struct bpf_link_ops bpf_uprobe_multi_link_lops = { .release = bpf_uprobe_multi_link_release, - .dealloc = bpf_uprobe_multi_link_dealloc, + .dealloc_deferred = bpf_uprobe_multi_link_dealloc, .fill_link_info = bpf_uprobe_multi_link_fill_link_info, }; -- cgit v1.2.3 From 3d010c8031e39f5fa1e8b13ada77e0321091011f Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Tue, 26 Mar 2024 12:33:58 +0100 Subject: udp: do not accept non-tunnel GSO skbs landing in a tunnel When rx-udp-gro-forwarding is enabled UDP packets might be GROed when being forwarded. If such packets might land in a tunnel this can cause various issues and udp_gro_receive makes sure this isn't the case by looking for a matching socket. This is performed in udp4/6_gro_lookup_skb but only in the current netns. This is an issue with tunneled packets when the endpoint is in another netns. In such cases the packets will be GROed at the UDP level, which leads to various issues later on. The same thing can happen with rx-gro-list. We saw this with geneve packets being GROed at the UDP level. In such case gso_size is set; later the packet goes through the geneve rx path, the geneve header is pulled, the offset are adjusted and frag_list skbs are not adjusted with regard to geneve. When those skbs hit skb_fragment, it will misbehave. Different outcomes are possible depending on what the GROed skbs look like; from corrupted packets to kernel crashes. One example is a BUG_ON[1] triggered in skb_segment while processing the frag_list. Because gso_size is wrong (geneve header was pulled) skb_segment thinks there is "geneve header size" of data in frag_list, although it's in fact the next packet. The BUG_ON itself has nothing to do with the issue. This is only one of the potential issues. Looking up for a matching socket in udp_gro_receive is fragile: the lookup could be extended to all netns (not speaking about performances) but nothing prevents those packets from being modified in between and we could still not find a matching socket. It's OK to keep the current logic there as it should cover most cases but we also need to make sure we handle tunnel packets being GROed too early. This is done by extending the checks in udp_unexpected_gso: GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits and landing in a tunnel must be segmented. [1] kernel BUG at net/core/skbuff.c:4408! RIP: 0010:skb_segment+0xd2a/0xf70 __udp_gso_segment+0xaa/0x560 Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.") Fixes: 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets") Signed-off-by: Antoine Tenart Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/udp.h | 28 ++++++++++++++++++++++++++++ net/ipv4/udp.c | 7 +++++++ net/ipv4/udp_offload.c | 6 ++++-- net/ipv6/udp.c | 2 +- 4 files changed, 40 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 3748e82b627b..17539d089666 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -150,6 +150,24 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, } } +DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key); +#if IS_ENABLED(CONFIG_IPV6) +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +#endif + +static inline bool udp_encap_needed(void) +{ + if (static_branch_unlikely(&udp_encap_needed_key)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (static_branch_unlikely(&udpv6_encap_needed_key)) + return true; +#endif + + return false; +} + static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) { if (!skb_is_gso(skb)) @@ -163,6 +181,16 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; + /* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still + * land in a tunnel as the socket check in udp_gro_receive cannot be + * foolproof. + */ + if (udp_encap_needed() && + READ_ONCE(udp_sk(sk)->encap_rcv) && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM))) + return true; + return false; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 661d0e0d273f..c02bf011d4a6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -582,6 +582,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index b9880743765c..e9719afe91cf 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -551,8 +551,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; - /* we can do L4 aggregation only if the packet can't land in a tunnel - * otherwise we could corrupt the inner stream + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7c1e6469d091..8b1dd7f51249 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -447,7 +447,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); -- cgit v1.2.3 From aa7cbefe65e455178c33eca308349e687d262ea7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 31 Mar 2024 10:26:47 -0700 Subject: time/timecounter: Fix inline documentation Fix kernel-doc warnings, text punctuation, and a kernel-doc marker (change '%' to '&' to indicate a struct): timecounter.h:72: warning: No description found for return value of 'cyclecounter_cyc2ns' timecounter.h:85: warning: Function parameter or member 'tc' not described in 'timecounter_adjtime' timecounter.h:111: warning: No description found for return value of 'timecounter_read' timecounter.h:128: warning: No description found for return value of 'timecounter_cyc2time' Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240331172652.14086-2-rdunlap@infradead.org --- include/linux/timecounter.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h index c6540ceea143..0982d1d52b24 100644 --- a/include/linux/timecounter.h +++ b/include/linux/timecounter.h @@ -22,7 +22,7 @@ * * @read: returns the current cycle value * @mask: bitmask for two's complement - * subtraction of non 64 bit counters, + * subtraction of non-64-bit counters, * see CYCLECOUNTER_MASK() helper macro * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) @@ -35,7 +35,7 @@ struct cyclecounter { }; /** - * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds + * struct timecounter - layer above a &struct cyclecounter which counts nanoseconds * Contains the state needed by timecounter_read() to detect * cycle counter wrap around. Initialize with * timecounter_init(). Also used to convert cycle counts into the @@ -66,6 +66,8 @@ struct timecounter { * @cycles: Cycles * @mask: bit mask for maintaining the 'frac' field * @frac: pointer to storage for the fractional nanoseconds. + * + * Returns: cycle counter cycles converted to nanoseconds */ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, u64 cycles, u64 mask, u64 *frac) @@ -79,6 +81,7 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc, /** * timecounter_adjtime - Shifts the time of the clock. + * @tc: The &struct timecounter to adjust * @delta: Desired change in nanoseconds. */ static inline void timecounter_adjtime(struct timecounter *tc, s64 delta) @@ -107,6 +110,8 @@ extern void timecounter_init(struct timecounter *tc, * * In other words, keeps track of time since the same epoch as * the function which generated the initial time stamp. + * + * Returns: nanoseconds since the initial time stamp */ extern u64 timecounter_read(struct timecounter *tc); @@ -123,6 +128,8 @@ extern u64 timecounter_read(struct timecounter *tc); * * This allows conversion of cycle counter values which were generated * in the past. + * + * Returns: cycle counter converted to nanoseconds since the initial time stamp */ extern u64 timecounter_cyc2time(const struct timecounter *tc, u64 cycle_tstamp); -- cgit v1.2.3 From 76f788ee4a7d9f826738a034f9d2ee0bc4cd291b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 31 Mar 2024 10:26:48 -0700 Subject: time/timekeeping: Fix kernel-doc warnings and typos Fix punctuation, spellos, and kernel-doc warnings: timekeeping.h:79: warning: No description found for return value of 'ktime_get_real' timekeeping.h:95: warning: No description found for return value of 'ktime_get_boottime' timekeeping.h:108: warning: No description found for return value of 'ktime_get_clocktai' timekeeping.h:149: warning: Function parameter or struct member 'mono' not described in 'ktime_mono_to_real' timekeeping.h:149: warning: No description found for return value of 'ktime_mono_to_real' timekeeping.h:255: warning: Function parameter or struct member 'cs_id' not described in 'system_time_snapshot' Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240331172652.14086-3-rdunlap@infradead.org --- include/linux/timekeeping.h | 49 ++++++++++++++++++++++++++++++++++++++------- 1 file changed, 42 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7e50cbd97f86..0ea7823b7f31 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -22,14 +22,14 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* - * ktime_get() family: read the current time in a multitude of ways, + * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * - * To get the time in a different format, use the ones wit + * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. @@ -74,6 +74,8 @@ extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format + * + * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { @@ -86,10 +88,12 @@ static inline ktime_t ktime_get_coarse_real(void) } /** - * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. + * + * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { @@ -102,7 +106,9 @@ static inline ktime_t ktime_get_coarse_boottime(void) } /** - * ktime_get_clocktai - Returns the TAI time of day in ktime_t format + * ktime_get_clocktai - Get the TAI time of day in ktime_t format + * + * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { @@ -144,32 +150,60 @@ static inline u64 ktime_get_coarse_clocktai_ns(void) /** * ktime_mono_to_real - Convert monotonic time to clock realtime + * @mono: monotonic time to convert + * + * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } +/** + * ktime_get_ns - Get the current time in nanoseconds + * + * Returns: current time converted to nanoseconds + */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } +/** + * ktime_get_real_ns - Get the current real/wall time in nanoseconds + * + * Returns: current real time converted to nanoseconds + */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } +/** + * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds + * + * Returns: current boottime converted to nanoseconds + */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } +/** + * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds + * + * Returns: current TAI time converted to nanoseconds + */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } +/** + * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds + * + * Returns: current raw monotonic time converted to nanoseconds + */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); @@ -224,8 +258,8 @@ extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); -/* - * struct ktime_timestanps - Simultaneous mono/boot/real timestamps +/** + * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp @@ -242,7 +276,8 @@ struct ktime_timestamps { * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @raw: Monotonic raw system time - * @clock_was_set_seq: The sequence number of clock was set events + * @cs_id: Clocksource ID + * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { -- cgit v1.2.3 From b87752ef5cc15b0bae04583d599e873d92dc0618 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 31 Mar 2024 10:26:49 -0700 Subject: timers: Fix kernel-doc format and add Return values Fix kernel-doc format and warnings: timer.h:26: warning: Cannot understand * @TIMER_DEFERRABLE: A deferrable timer will work normally when the on line 26 - I thought it was a doc line timer.h:146: warning: No description found for return value of 'timer_pending' timer.h:180: warning: No description found for return value of 'del_timer_sync' timer.h:193: warning: No description found for return value of 'del_timer' Signed-off-by: Randy Dunlap Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20240331172652.14086-4-rdunlap@infradead.org --- include/linux/timer.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timer.h b/include/linux/timer.h index 14a633ba61d6..e67ecd1cbc97 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -22,7 +22,7 @@ #define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn) #endif -/** +/* * @TIMER_DEFERRABLE: A deferrable timer will work normally when the * system is busy, but will not cause a CPU to come out of idle just * to service it; instead, the timer will be serviced when the CPU @@ -140,7 +140,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { } * or not. Callers must ensure serialization wrt. other operations done * to this timer, eg. interrupt contexts, or other CPUs on SMP. * - * return value: 1 if the timer is pending, 0 if not. + * Returns: 1 if the timer is pending, 0 if not. */ static inline int timer_pending(const struct timer_list * timer) { @@ -175,6 +175,10 @@ extern int timer_shutdown(struct timer_list *timer); * See timer_delete_sync() for detailed explanation. * * Do not use in new code. Use timer_delete_sync() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer_sync(struct timer_list *timer) { @@ -188,6 +192,10 @@ static inline int del_timer_sync(struct timer_list *timer) * See timer_delete() for detailed explanation. * * Do not use in new code. Use timer_delete() instead. + * + * Returns: + * * %0 - The timer was not pending + * * %1 - The timer was pending and deactivated */ static inline int del_timer(struct timer_list *timer) { -- cgit v1.2.3 From 09ab7eff38202159271534d2f5ad45526168f2a5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 14 Mar 2024 10:45:07 -0600 Subject: io_uring/kbuf: get rid of lower BGID lists Just rely on the xarray for any kind of bgid. This simplifies things, and it really doesn't bring us much, if anything. Cc: stable@vger.kernel.org # v6.4+ Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 - io_uring/io_uring.c | 2 -- io_uring/kbuf.c | 70 +++++------------------------------------- 3 files changed, 8 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index e24893625085..05df0e399d7c 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -294,7 +294,6 @@ struct io_ring_ctx { struct io_submit_state submit_state; - struct io_buffer_list *io_bl; struct xarray io_bl_xa; struct io_hash_table cancel_table_locked; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d1defb99b89e..bc730f59265f 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -351,7 +351,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) err: kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); - kfree(ctx->io_bl); xa_destroy(&ctx->io_bl_xa); kfree(ctx); return NULL; @@ -2932,7 +2931,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_napi_free(ctx); kfree(ctx->cancel_table.hbs); kfree(ctx->cancel_table_locked.hbs); - kfree(ctx->io_bl); xa_destroy(&ctx->io_bl_xa); kfree(ctx); } diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 693c26da4ee1..8bf0121f00af 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -17,8 +17,6 @@ #define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf)) -#define BGID_ARRAY 64 - /* BIDs are addressed by a 16-bit field in a CQE */ #define MAX_BIDS_PER_BGID (1 << 16) @@ -40,13 +38,9 @@ struct io_buf_free { int inuse; }; -static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, - struct io_buffer_list *bl, - unsigned int bgid) +static inline struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, + unsigned int bgid) { - if (bl && bgid < BGID_ARRAY) - return &bl[bgid]; - return xa_load(&ctx->io_bl_xa, bgid); } @@ -55,7 +49,7 @@ static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, { lockdep_assert_held(&ctx->uring_lock); - return __io_buffer_get_list(ctx, ctx->io_bl, bgid); + return __io_buffer_get_list(ctx, bgid); } static int io_buffer_add_list(struct io_ring_ctx *ctx, @@ -68,10 +62,6 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx, */ bl->bgid = bgid; smp_store_release(&bl->is_ready, 1); - - if (bgid < BGID_ARRAY) - return 0; - return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL)); } @@ -208,24 +198,6 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len, return ret; } -static __cold int io_init_bl_list(struct io_ring_ctx *ctx) -{ - struct io_buffer_list *bl; - int i; - - bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL); - if (!bl) - return -ENOMEM; - - for (i = 0; i < BGID_ARRAY; i++) { - INIT_LIST_HEAD(&bl[i].buf_list); - bl[i].bgid = i; - } - - smp_store_release(&ctx->io_bl, bl); - return 0; -} - /* * Mark the given mapped range as free for reuse */ @@ -300,13 +272,6 @@ void io_destroy_buffers(struct io_ring_ctx *ctx) struct list_head *item, *tmp; struct io_buffer *buf; unsigned long index; - int i; - - for (i = 0; i < BGID_ARRAY; i++) { - if (!ctx->io_bl) - break; - __io_remove_buffers(ctx, &ctx->io_bl[i], -1U); - } xa_for_each(&ctx->io_bl_xa, index, bl) { xa_erase(&ctx->io_bl_xa, bl->bgid); @@ -489,12 +454,6 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) io_ring_submit_lock(ctx, issue_flags); - if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) { - ret = io_init_bl_list(ctx); - if (ret) - goto err; - } - bl = io_buffer_get_list(ctx, p->bgid); if (unlikely(!bl)) { bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT); @@ -507,14 +466,9 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) if (ret) { /* * Doesn't need rcu free as it was never visible, but - * let's keep it consistent throughout. Also can't - * be a lower indexed array group, as adding one - * where lookup failed cannot happen. + * let's keep it consistent throughout. */ - if (p->bgid >= BGID_ARRAY) - kfree_rcu(bl, rcu); - else - WARN_ON_ONCE(1); + kfree_rcu(bl, rcu); goto err; } } @@ -679,12 +633,6 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (reg.ring_entries >= 65536) return -EINVAL; - if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) { - int ret = io_init_bl_list(ctx); - if (ret) - return ret; - } - bl = io_buffer_get_list(ctx, reg.bgid); if (bl) { /* if mapped buffer ring OR classic exists, don't allow */ @@ -734,10 +682,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) return -EINVAL; __io_remove_buffers(ctx, bl, -1U); - if (bl->bgid >= BGID_ARRAY) { - xa_erase(&ctx->io_bl_xa, bl->bgid); - kfree_rcu(bl, rcu); - } + xa_erase(&ctx->io_bl_xa, bl->bgid); + kfree_rcu(bl, rcu); return 0; } @@ -771,7 +717,7 @@ void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid) { struct io_buffer_list *bl; - bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid); + bl = __io_buffer_get_list(ctx, bgid); if (!bl || !bl->is_mmap) return NULL; -- cgit v1.2.3 From bc6f707fc0feec72acc2f49c312eb31d257363a3 Mon Sep 17 00:00:00 2001 From: "Borislav Petkov (AMD)" Date: Wed, 27 Mar 2024 16:43:16 +0100 Subject: x86/cc: Add cc_platform_set/_clear() helpers Add functionality to set and/or clear different attributes of the machine as a confidential computing platform. Add the first one too: whether the machine is running as a host for SEV-SNP guests. Fixes: 216d106c7ff7 ("x86/sev: Add SEV-SNP host initialization support") Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Tom Lendacky Tested-by: Srikanth Aithal Link: https://lore.kernel.org/r/20240327154317.29909-5-bp@alien8.de --- arch/x86/coco/core.c | 52 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/cc_platform.h | 12 +++++++++++ 2 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index ddd4efdc79d6..b31ef2424d19 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -20,6 +20,11 @@ enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; u64 cc_mask __ro_after_init; +static struct cc_attr_flags { + __u64 host_sev_snp : 1, + __resv : 63; +} cc_flags; + static bool noinstr intel_cc_platform_has(enum cc_attr attr) { switch (attr) { @@ -93,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_HOST_SEV_SNP: + return cc_flags.host_sev_snp; + default: return false; } @@ -153,6 +161,50 @@ u64 cc_mkdec(u64 val) } EXPORT_SYMBOL_GPL(cc_mkdec); +static void amd_cc_platform_clear(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 0; + break; + default: + break; + } +} + +void cc_platform_clear(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_clear(attr); + break; + default: + break; + } +} + +static void amd_cc_platform_set(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 1; + break; + default: + break; + } +} + +void cc_platform_set(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_set(attr); + break; + default: + break; + } +} + __init void cc_random_init(void) { /* diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index cb0d6cd1c12f..60693a145894 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -90,6 +90,14 @@ enum cc_attr { * Examples include TDX Guest. */ CC_ATTR_HOTPLUG_DISABLED, + + /** + * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. + * + * The host kernel is running with the necessary features + * enabled to run SEV-SNP guests. + */ + CC_ATTR_HOST_SEV_SNP, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM @@ -107,10 +115,14 @@ enum cc_attr { * * FALSE - Specified Confidential Computing attribute is not active */ bool cc_platform_has(enum cc_attr attr); +void cc_platform_set(enum cc_attr attr); +void cc_platform_clear(enum cc_attr attr); #else /* !CONFIG_ARCH_HAS_CC_PLATFORM */ static inline bool cc_platform_has(enum cc_attr attr) { return false; } +static inline void cc_platform_set(enum cc_attr attr) { } +static inline void cc_platform_clear(enum cc_attr attr) { } #endif /* CONFIG_ARCH_HAS_CC_PLATFORM */ -- cgit v1.2.3 From 8130b05c559d1aa83d0c8971b422ba0da18ef24a Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Thu, 4 Apr 2024 12:42:00 +0200 Subject: PM: EM: fix wrong utilization estimation in em_cpu_energy() Commit 1b600da51073 ("PM: EM: Optimize em_cpu_energy() and remove division") has added back map_util_perf() in em_cpu_energy() computation which has been removed with the rework of scheduler/cpufreq interface. This is wrong because sugov_effective_cpu_perf() already takes care of mapping the utilization to a performance level. Fixes: 1b600da51073 ("PM: EM: Optimize em_cpu_energy() and remove division") Signed-off-by: Vincent Guittot Reviewed-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 770755df852f..70cd7258cd29 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -245,7 +245,6 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * max utilization to the allowed CPU capacity before calculating * effective performance. */ - max_util = map_util_perf(max_util); max_util = min(max_util, allowed_cpu_cap); /* -- cgit v1.2.3 From 65291dcfcf8936e1b23cfd7718fdfde7cfaf7706 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 26 Mar 2024 15:32:08 +0100 Subject: mm/secretmem: fix GUP-fast succeeding on secretmem folios folio_is_secretmem() currently relies on secretmem folios being LRU folios, to save some cycles. However, folios might reside in a folio batch without the LRU flag set, or temporarily have their LRU flag cleared. Consequently, the LRU flag is unreliable for this purpose. In particular, this is the case when secretmem_fault() allocates a fresh page and calls filemap_add_folio()->folio_add_lru(). The folio might be added to the per-cpu folio batch and won't get the LRU flag set until the batch was drained using e.g., lru_add_drain(). Consequently, folio_is_secretmem() might not detect secretmem folios and GUP-fast can succeed in grabbing a secretmem folio, crashing the kernel when we would later try reading/writing to the folio, because the folio has been unmapped from the directmap. Fix it by removing that unreliable check. Link: https://lkml.kernel.org/r/20240326143210.291116-2-david@redhat.com Fixes: 1507f51255c9 ("mm: introduce memfd_secret system call to create "secret" memory areas") Signed-off-by: David Hildenbrand Reported-by: xingwei lee Reported-by: yue sun Closes: https://lore.kernel.org/lkml/CABOYnLyevJeravW=QrH0JUPYEcDN160aZFb7kwndm-J2rmz0HQ@mail.gmail.com/ Debugged-by: Miklos Szeredi Tested-by: Miklos Szeredi Reviewed-by: Mike Rapoport (IBM) Cc: Lorenzo Stoakes Cc: Signed-off-by: Andrew Morton --- include/linux/secretmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index 35f3a4a8ceb1..acf7e1a3f3de 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio) /* * Using folio_mapping() is quite slow because of the actual call * instruction. - * We know that secretmem pages are not compound and LRU so we can + * We know that secretmem pages are not compound, so we can * save a couple of cycles here. */ - if (folio_test_large(folio) || !folio_test_lru(folio)) + if (folio_test_large(folio)) return false; mapping = (struct address_space *) -- cgit v1.2.3 From a6c1d9cb9a68bfa4512248419c4f4d880d19fe90 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Mon, 1 Apr 2024 17:14:58 -0700 Subject: stackdepot: rename pool_index to pool_index_plus_1 Commit 3ee34eabac2a ("lib/stackdepot: fix first entry having a 0-handle") changed the meaning of the pool_index field to mean "the pool index plus 1". This made the code accessing this field less self-documenting, as well as causing debuggers such as drgn to not be able to easily remain compatible with both old and new kernels, because they typically do that by testing for presence of the new field. Because stackdepot is a debugging tool, we should make sure that it is debugger friendly. Therefore, give the field a different name to improve readability as well as enabling debugger backwards compatibility. This is needed in 6.9, which would otherwise become an odd release with the new semantics and old name so debuggers wouldn't recognize the new semantics there. Fixes: 3ee34eabac2a ("lib/stackdepot: fix first entry having a 0-handle") Link: https://lkml.kernel.org/r/20240402001500.53533-1-pcc@google.com Link: https://linux-review.googlesource.com/id/Ib3e70c36c1d230dd0a118dc22649b33e768b9f88 Signed-off-by: Peter Collingbourne Acked-by: Vlastimil Babka Reviewed-by: Alexander Potapenko Acked-by: Marco Elver Acked-by: Oscar Salvador Cc: Andrey Konovalov Cc: Michal Hocko Cc: Omar Sandoval Signed-off-by: Andrew Morton --- include/linux/stackdepot.h | 7 +++---- lib/stackdepot.c | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 3c6caa5abc7c..e9ec32fb97d4 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -44,10 +44,9 @@ typedef u32 depot_stack_handle_t; union handle_parts { depot_stack_handle_t handle; struct { - /* pool_index is offset by 1 */ - u32 pool_index : DEPOT_POOL_INDEX_BITS; - u32 offset : DEPOT_OFFSET_BITS; - u32 extra : STACK_DEPOT_EXTRA_BITS; + u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS; + u32 offset : DEPOT_OFFSET_BITS; + u32 extra : STACK_DEPOT_EXTRA_BITS; }; }; diff --git a/lib/stackdepot.c b/lib/stackdepot.c index af6cc19a2003..68c97387aa54 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -330,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size) stack = current_pool + pool_offset; /* Pre-initialize handle once. */ - stack->handle.pool_index = pool_index + 1; + stack->handle.pool_index_plus_1 = pool_index + 1; stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN; stack->handle.extra = 0; INIT_LIST_HEAD(&stack->hash_list); @@ -441,7 +441,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle) const int pools_num_cached = READ_ONCE(pools_num); union handle_parts parts = { .handle = handle }; void *pool; - u32 pool_index = parts.pool_index - 1; + u32 pool_index = parts.pool_index_plus_1 - 1; size_t offset = parts.offset << DEPOT_STACK_ALIGN; struct stack_record *stack; -- cgit v1.2.3 From b250c20b64290808aa4b5cc6d68819a7ee28237f Mon Sep 17 00:00:00 2001 From: David Lechner Date: Mon, 29 Apr 2024 18:40:09 -0500 Subject: regulator: devres: add API for reference voltage supplies A common use case for regulators is to supply a reference voltage to an analog input or output device. This adds a new devres API to get, enable, and get the voltage in a single call. This allows eliminating boilerplate code in drivers that use reference supplies in this way. Signed-off-by: David Lechner Link: https://lore.kernel.org/r/20240429-regulator-get-enable-get-votlage-v2-1-b1f11ab766c1@baylibre.com Signed-off-by: Mark Brown --- Documentation/driver-api/driver-model/devres.rst | 1 + drivers/regulator/devres.c | 59 ++++++++++++++++++++++++ include/linux/regulator/consumer.h | 7 +++ 3 files changed, 67 insertions(+) (limited to 'include/linux') diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index 7be8b8dd5f00..18caebad7376 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -433,6 +433,7 @@ REGULATOR devm_regulator_bulk_put() devm_regulator_get() devm_regulator_get_enable() + devm_regulator_get_enable_read_voltage() devm_regulator_get_enable_optional() devm_regulator_get_exclusive() devm_regulator_get_optional() diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c index 90bb0d178885..4f290b9b559b 100644 --- a/drivers/regulator/devres.c +++ b/drivers/regulator/devres.c @@ -145,6 +145,65 @@ struct regulator *devm_regulator_get_optional(struct device *dev, } EXPORT_SYMBOL_GPL(devm_regulator_get_optional); +/** + * devm_regulator_get_enable_read_voltage - Resource managed regulator get and + * enable that returns the voltage + * @dev: device to supply + * @id: supply name or regulator ID. + * + * Get and enable regulator for duration of the device life-time. + * regulator_disable() and regulator_put() are automatically called on driver + * detach. See regulator_get_optional(), regulator_enable(), and + * regulator_get_voltage() for more information. + * + * This is a convenience function for supplies that provide a reference voltage + * where the consumer driver just needs to know the voltage and keep the + * regulator enabled. + * + * In cases where the supply is not strictly required, callers can check for + * -ENODEV error and handle it accordingly. + * + * Returns: voltage in microvolts on success, or an error code on failure. + */ +int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id) +{ + struct regulator *r; + int ret; + + /* + * Since we need a real voltage, we use devm_regulator_get_optional() + * rather than getting a dummy regulator with devm_regulator_get() and + * then letting regulator_get_voltage() fail with -EINVAL. This way, the + * caller can handle the -ENODEV error code if needed instead of the + * ambiguous -EINVAL. + */ + r = devm_regulator_get_optional(dev, id); + if (IS_ERR(r)) + return PTR_ERR(r); + + ret = regulator_enable(r); + if (ret) + goto err_regulator_put; + + ret = devm_add_action_or_reset(dev, regulator_action_disable, r); + if (ret) + goto err_regulator_put; + + ret = regulator_get_voltage(r); + if (ret < 0) + goto err_release_action; + + return 0; + +err_release_action: + devm_release_action(dev, regulator_action_disable, r); +err_regulator_put: + devm_regulator_put(r); + + return ret; +} +EXPORT_SYMBOL_GPL(devm_regulator_get_enable_read_voltage); + static int devm_regulator_match(struct device *dev, void *res, void *data) { struct regulator **r = res; diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a3302..6f41a11c92e7 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -164,6 +164,7 @@ struct regulator *__must_check devm_regulator_get_optional(struct device *dev, const char *id); int devm_regulator_get_enable(struct device *dev, const char *id); int devm_regulator_get_enable_optional(struct device *dev, const char *id); +int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -329,6 +330,12 @@ static inline int devm_regulator_get_enable_optional(struct device *dev, return -ENODEV; } +static inline int devm_regulator_get_enable_read_voltage(struct device *dev, + const char *id) +{ + return -ENODEV; +} + static inline struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id) { -- cgit v1.2.3