From 0c2cae09a765b1c1d842eb9328982976ec735926 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 17 Mar 2022 11:33:11 +0200 Subject: gpiolib: acpi: Convert type for pin to be unsigned A pin that comes from ACPI tables is of unsigned type. This also applies to the internal APIs which use unsigned int to store the pin. Convert type for pin to be unsigned in the places where it's not yet true. While at it, add a stub for acpi_get_and_request_gpiod() for the sake of consistency in the APIs. Signed-off-by: Andy Shevchenko --- include/linux/gpio/consumer.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c3aa8b330e1c..e71f6e1bfafe 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -688,7 +688,7 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label); #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ @@ -705,6 +705,12 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, return -ENXIO; } +static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, + char *label) +{ + return ERR_PTR(-ENOSYS); +} + #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ -- cgit v1.2.3 From 868e6139c5212e7d9de8332806aacfeafb349320 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Sun, 27 Mar 2022 11:33:16 -0600 Subject: block: move lower_48_bits() to block The function is not generally applicable enough to be included in the core kernel header. Move it to block since it's the only subsystem using it. Suggested-by: Linus Torvalds Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220327173316.315-1-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/kernel.h | 9 --------- include/linux/t10-pi.h | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 08ba5995aa8b..a890428bcc1a 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -63,15 +63,6 @@ } \ ) -/** - * lower_48_bits() - return bits 0-47 of a number - * @n: the number we're accessing - */ -static inline u64 lower_48_bits(u64 n) -{ - return n & ((1ull << 48) - 1); -} - /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index a4b1af581f69..248f4ac95642 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -59,6 +59,15 @@ struct crc64_pi_tuple { __u8 ref_tag[6]; }; +/** + * lower_48_bits() - return bits 0-47 of a number + * @n: the number we're accessing + */ +static inline u64 lower_48_bits(u64 n) +{ + return n & ((1ull << 48) - 1); +} + static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -- cgit v1.2.3 From b0c3e796f24b588b862b61ce235d3c9417dc8983 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" Date: Fri, 8 Apr 2022 18:14:57 +0200 Subject: random: make random_get_entropy() return an unsigned long Some implementations were returning type `unsigned long`, while others that fell back to get_cycles() were implicitly returning a `cycles_t` or an untyped constant int literal. That makes for weird and confusing code, and basically all code in the kernel already handled it like it was an `unsigned long`. I recently tried to handle it as the largest type it could be, a `cycles_t`, but doing so doesn't really help with much. Instead let's just make random_get_entropy() return an unsigned long all the time. This also matches the commonly used `arch_get_random_long()` function, so now RDRAND and RDTSC return the same sized integer, which means one can fallback to the other more gracefully. Cc: Dominik Brodowski Cc: Theodore Ts'o Acked-by: Thomas Gleixner Signed-off-by: Jason A. Donenfeld --- include/linux/timex.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index 059b18eb1f1f..5745c90c8800 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -75,7 +75,7 @@ * By default we use get_cycles() for this purpose, but individual * architectures may override this in their asm/timex.h header file. */ -#define random_get_entropy() get_cycles() +#define random_get_entropy() ((unsigned long)get_cycles()) #endif /* -- cgit v1.2.3 From 1ef3342a934e235aca72b4bcc0d6854d80a65077 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Wed, 13 Apr 2022 10:10:36 -0300 Subject: vfio/pci: Fix vf_token mechanism when device-specific VF drivers are used get_pf_vdev() tries to check if a PF is a VFIO PF by looking at the driver: if (pci_dev_driver(physfn) != pci_dev_driver(vdev->pdev)) { However now that we have multiple VF and PF drivers this is no longer reliable. This means that security tests realted to vf_token can be skipped by mixing and matching different VFIO PCI drivers. Instead of trying to use the driver core to find the PF devices maintain a linked list of all PF vfio_pci_core_device's that we have called pci_enable_sriov() on. When registering a VF just search the list to see if the PF is present and record the match permanently in the struct. PCI core locking prevents a PF from passing pci_disable_sriov() while VF drivers are attached so the VFIO owned PF becomes a static property of the VF. In common cases where vfio does not own the PF the global list remains empty and the VF's pointer is statically NULL. This also fixes a lockdep splat from recursive locking of the vfio_group::device_lock between vfio_device_get_from_name() and vfio_device_get_from_dev(). If the VF and PF share the same group this would deadlock. Fixes: ff53edf6d6ab ("vfio/pci: Split the pci_driver code out of vfio_pci_core.c") Signed-off-by: Jason Gunthorpe Link: https://lore.kernel.org/r/0-v3-876570980634+f2e8-vfio_vf_token_jgg@nvidia.com Signed-off-by: Alex Williamson --- include/linux/vfio_pci_core.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 74a4a0f17b28..48f2dd3c568c 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -133,6 +133,8 @@ struct vfio_pci_core_device { struct mutex ioeventfds_lock; struct list_head ioeventfds_list; struct vfio_pci_vf_token *vf_token; + struct list_head sriov_pfs_item; + struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; struct mutex vma_lock; struct list_head vma_list; -- cgit v1.2.3 From 2dfe63e61cc31ee59ce951672b0850b5229cd5b0 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 14 Apr 2022 19:13:40 -0700 Subject: mm, kfence: support kmem_dump_obj() for KFENCE objects Calling kmem_obj_info() via kmem_dump_obj() on KFENCE objects has been producing garbage data due to the object not actually being maintained by SLAB or SLUB. Fix this by implementing __kfence_obj_info() that copies relevant information to struct kmem_obj_info when the object was allocated by KFENCE; this is called by a common kmem_obj_info(), which also calls the slab/slub/slob specific variant now called __kmem_obj_info(). For completeness, kmem_dump_obj() now displays if the object was allocated by KFENCE. Link: https://lore.kernel.org/all/20220323090520.GG16885@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20220406131558.3558585-1-elver@google.com Fixes: b89fb5ef0ce6 ("mm, kfence: insert KFENCE hooks for SLUB") Fixes: d3fb45f370d9 ("mm, kfence: insert KFENCE hooks for SLAB") Signed-off-by: Marco Elver Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Reported-by: kernel test robot Acked-by: Vlastimil Babka [slab] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index f49e64222628..726857a4b680 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -204,6 +204,22 @@ static __always_inline __must_check bool kfence_free(void *addr) */ bool __must_check kfence_handle_page_fault(unsigned long addr, bool is_write, struct pt_regs *regs); +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +/** + * __kfence_obj_info() - fill kmem_obj_info struct + * @kpp: kmem_obj_info to be filled + * @object: the object + * + * Return: + * * false - not a KFENCE object + * * true - a KFENCE object, filled @kpp + * + * Copies information to @kpp for KFENCE objects. + */ +bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); +#endif + #else /* CONFIG_KFENCE */ static inline bool is_kfence_address(const void *addr) { return false; } @@ -221,6 +237,14 @@ static inline bool __must_check kfence_handle_page_fault(unsigned long addr, boo return false; } +#ifdef CONFIG_PRINTK +struct kmem_obj_info; +static inline bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) +{ + return false; +} +#endif + #endif #endif /* _LINUX_KFENCE_H */ -- cgit v1.2.3 From 705191b03d507744c7e097f78d583621c14988ac Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 19 Apr 2022 15:14:23 +0200 Subject: fs: fix acl translation Last cycle we extended the idmapped mounts infrastructure to support idmapped mounts of idmapped filesystems (No such filesystem yet exist.). Since then, the meaning of an idmapped mount is a mount whose idmapping is different from the filesystems idmapping. While doing that work we missed to adapt the acl translation helpers. They still assume that checking for the identity mapping is enough. But they need to use the no_idmapping() helper instead. Note, POSIX ACLs are always translated right at the userspace-kernel boundary using the caller's current idmapping and the initial idmapping. The order depends on whether we're coming from or going to userspace. The filesystem's idmapping doesn't matter at the border. Consequently, if a non-idmapped mount is passed we need to make sure to always pass the initial idmapping as the mount's idmapping and not the filesystem idmapping. Since it's irrelevant here it would yield invalid ids and prevent setting acls for filesystems that are mountable in a userns and support posix acls (tmpfs and fuse). I verified the regression reported in [1] and verified that this patch fixes it. A regression test will be added to xfstests in parallel. Link: https://bugzilla.kernel.org/show_bug.cgi?id=215849 [1] Fixes: bd303368b776 ("fs: support mapped mounts of mapped filesystems") Cc: Seth Forshee Cc: Christoph Hellwig Cc: # 5.17 Cc: Signed-off-by: Christian Brauner (Microsoft) Signed-off-by: Linus Torvalds --- include/linux/posix_acl_xattr.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 060e8d203181..1766e1de6956 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -34,15 +34,19 @@ posix_acl_xattr_count(size_t size) #ifdef CONFIG_FS_POSIX_ACL void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size); #else static inline void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } static inline void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { } -- cgit v1.2.3 From 559089e0a93d44280ec3ab478830af319c56dbe3 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 15 Apr 2022 09:44:10 -0700 Subject: vmalloc: replace VM_NO_HUGE_VMAP with VM_ALLOW_HUGE_VMAP Huge page backed vmalloc memory could benefit performance in many cases. However, some users of vmalloc may not be ready to handle huge pages for various reasons: hardware constraints, potential pages split, etc. VM_NO_HUGE_VMAP was introduced to allow vmalloc users to opt-out huge pages. However, it is not easy to track down all the users that require the opt-out, as the allocation are passed different stacks and may cause issues in different layers. To address this issue, replace VM_NO_HUGE_VMAP with an opt-in flag, VM_ALLOW_HUGE_VMAP, so that users that benefit from huge pages could ask specificially. Also, remove vmalloc_no_huge() and add opt-in helper vmalloc_huge(). Fixes: fac54e2bfb5b ("x86/Kconfig: Select HAVE_ARCH_HUGE_VMALLOC with HAVE_ARCH_HUGE_VMAP") Link: https://lore.kernel.org/netdev/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg.de/" Reviewed-by: Christoph Hellwig Signed-off-by: Song Liu Reviewed-by: Rik van Riel Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3b1df7da402d..b159c2789961 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -26,7 +26,7 @@ struct notifier_block; /* in notifier.h */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ -#define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -153,7 +153,7 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_no_huge(unsigned long size) __alloc_size(1); +void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); -- cgit v1.2.3