From e692b4021a2e48745d4bdac2b2775bdc8f03b433 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 4 Nov 2019 18:37:19 +0100 Subject: lockdep: add might_lock_nested() Necessary to annotate functions where we might acquire a mutex_lock_nested() or similar. Needed by i915. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Daniel Vetter Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: linux-kernel@vger.kernel.org Signed-off-by: Daniel Vetter Signed-off-by: Maarten Lankhorst Link: https://patchwork.freedesktop.org/patch/msgid/20191104173720.2696-2-daniel.vetter@ffwll.ch --- include/linux/lockdep.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b8a835fd611b..827722c21797 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -628,6 +628,13 @@ do { \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ } while (0) +# define might_lock_nested(lock, subclass) \ +do { \ + typecheck(struct lockdep_map *, &(lock)->dep_map); \ + lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL, \ + _THIS_IP_); \ + lock_release(&(lock)->dep_map, 0, _THIS_IP_); \ +} while (0) #define lockdep_assert_irqs_enabled() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ @@ -650,6 +657,7 @@ do { \ #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) +# define might_lock_nested(lock, subclass) do { } while (0) # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) -- cgit v1.2.3 From f597c2089da4dd55133546b1255493579a295bff Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 14 Nov 2019 13:51:06 +0100 Subject: fbdev: Unexport unlink_framebuffer() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no external callers of unlink_framebuffer() left. Make the function an internal interface. Signed-off-by: Thomas Zimmermann Reviewed-by: Noralf Trønnes Link: https://patchwork.freedesktop.org/patch/msgid/20191114125106.28347-4-tzimmermann@suse.de --- include/linux/fb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 41e0069eca0a..a6ad528990de 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -606,7 +606,6 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, /* drivers/video/fbmem.c */ extern int register_framebuffer(struct fb_info *fb_info); extern void unregister_framebuffer(struct fb_info *fb_info); -extern void unlink_framebuffer(struct fb_info *fb_info); extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, -- cgit v1.2.3 From 6a9afcb198b4de323485c0ee94ff09f653012d4b Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:11 +0200 Subject: iio: imu: adis: rename txrx_lock -> state_lock The lock can be extended a bit to protect other elements that are not particular to just TX/RX. Another idea would have been to just add a new `state_lock`, but that would mean 2 locks which would be redundant, and probably cause more potential for dead-locks. What will be done in the next patches, will be to add some unlocked versions for read/write_reg functions. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 92aae14593bf..100b5d1cebf1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -61,7 +61,7 @@ struct adis { const struct adis_data *data; struct adis_burst *burst; - struct mutex txrx_lock; + struct mutex state_lock; struct spi_message msg; struct spi_transfer *xfer; unsigned int current_page; -- cgit v1.2.3 From 770d465619423a946248018ea39ed9a74c8f2ff4 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:12 +0200 Subject: iio: imu: adis: add unlocked read/write function versions This will allow more flexible control to group reads & writes into a single lock (particularly the state_lock). The end-goal is to remove the indio_dev->mlock usage, and the simplest fix would have been to just add another lock, which would not be a good idea on the long-run. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 116 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 114 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 100b5d1cebf1..38ebe41092e1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -75,11 +75,123 @@ int adis_init(struct adis *adis, struct iio_dev *indio_dev, struct spi_device *spi, const struct adis_data *data); int adis_reset(struct adis *adis); -int adis_write_reg(struct adis *adis, unsigned int reg, +int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size); -int adis_read_reg(struct adis *adis, unsigned int reg, +int __adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, unsigned int size); +/** + * __adis_write_reg_8() - Write single byte to a register (unlocked) + * @adis: The adis device + * @reg: The address of the register to be written + * @value: The value to write + */ +static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg, + uint8_t val) +{ + return __adis_write_reg(adis, reg, val, 1); +} + +/** + * __adis_write_reg_16() - Write 2 bytes to a pair of registers (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @value: Value to be written + */ +static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg, + uint16_t val) +{ + return __adis_write_reg(adis, reg, val, 2); +} + +/** + * __adis_write_reg_32() - write 4 bytes to four registers (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the four register + * @value: Value to be written + */ +static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg, + uint32_t val) +{ + return __adis_write_reg(adis, reg, val, 4); +} + +/** + * __adis_read_reg_16() - read 2 bytes from a 16-bit register (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @val: The value read back from the device + */ +static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg, + uint16_t *val) +{ + unsigned int tmp; + int ret; + + ret = __adis_read_reg(adis, reg, &tmp, 2); + if (ret == 0) + *val = tmp; + + return ret; +} + +/** + * __adis_read_reg_32() - read 4 bytes from a 32-bit register (unlocked) + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @val: The value read back from the device + */ +static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, + uint32_t *val) +{ + unsigned int tmp; + int ret; + + ret = __adis_read_reg(adis, reg, &tmp, 4); + if (ret == 0) + *val = tmp; + + return ret; +} + +/** + * adis_write_reg() - write N bytes to register + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @value: The value to write to device (up to 4 bytes) + * @size: The size of the @value (in bytes) + */ +static inline int adis_write_reg(struct adis *adis, unsigned int reg, + unsigned int val, unsigned int size) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_write_reg(adis, reg, val, size); + mutex_unlock(&adis->state_lock); + + return ret; +} + +/** + * adis_read_reg() - read N bytes from register + * @adis: The adis device + * @reg: The address of the lower of the two registers + * @val: The value read back from the device + * @size: The size of the @val buffer + */ +static int adis_read_reg(struct adis *adis, unsigned int reg, + unsigned int *val, unsigned int size) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_read_reg(adis, reg, val, size); + mutex_unlock(&adis->state_lock); + + return ret; +} + /** * adis_write_reg_8() - Write single byte to a register * @adis: The adis device -- cgit v1.2.3 From 6a4d6a7d6588d8c15501542da786ebff6602475c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:14 +0200 Subject: iio: imu: adis: create an unlocked version of adis_check_status() This one also gets re-used in certain operations, so it makes sense to have an unlocked version of this to group it with other reads/writes/operations to have a single lock for the whole state change. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 38ebe41092e1..db759957e1c1 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -267,7 +267,18 @@ static inline int adis_read_reg_32(struct adis *adis, unsigned int reg, } int adis_enable_irq(struct adis *adis, bool enable); -int adis_check_status(struct adis *adis); +int __adis_check_status(struct adis *adis); + +static inline int adis_check_status(struct adis *adis) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_check_status(adis); + mutex_unlock(&adis->state_lock); + + return ret; +} int adis_initial_startup(struct adis *adis); -- cgit v1.2.3 From 762ab093cbe26451175a5a63ea06c971bf973525 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 22 Nov 2019 15:24:15 +0200 Subject: iio: imu: adis: create an unlocked version of adis_reset() The reset routine may also be important to be protected by the state-lock and grouped with other operations, so create an unlocked version, so that this can be done. Signed-off-by: Alexandru Ardelean Signed-off-by: Jonathan Cameron --- include/linux/iio/imu/adis.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index db759957e1c1..4b5bc0e06e69 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -73,7 +73,24 @@ struct adis { int adis_init(struct adis *adis, struct iio_dev *indio_dev, struct spi_device *spi, const struct adis_data *data); -int adis_reset(struct adis *adis); +int __adis_reset(struct adis *adis); + +/** + * adis_reset() - Reset the device + * @adis: The adis device + * + * Returns 0 on success, a negative error code otherwise + */ +static inline int adis_reset(struct adis *adis) +{ + int ret; + + mutex_lock(&adis->state_lock); + ret = __adis_reset(adis); + mutex_unlock(&adis->state_lock); + + return ret; +} int __adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size); -- cgit v1.2.3 From 8cb3403633146afe1ba81f79224679f5df2940d4 Mon Sep 17 00:00:00 2001 From: Andrea Merello Date: Wed, 20 Nov 2019 15:47:51 +0100 Subject: iio: core: add char type for sysfs attributes This patch introduces IIO_VAL_CHAR type for standard IIO attributes to allow for attributes that needs to be represented by character rather than a number. This is preparatory for introducing a new attribute whose purpose is to describe thermocouple type, that can be i.e. "J", "K", etc.. The char-type value is stored in the first "value" integer that is passed to the .[read/write]_raw() callbacks. Note that in order to make it possible for the IIO core to correctly parse this type (actually, to avoid integer parsing), it became mandatory for any driver that wish to use IIO_VAL_CHAR on a writable attribute to implement .write_raw_get_fmt(). Cc: Hartmut Knaack Cc: Lars-Peter Clausen Cc: Peter Meerwald-Stadler Cc: Colin Ian King Cc: Patrick Havelange Cc: Matt Weber Cc: Matt Ranostay Cc: Chuhong Yuan Cc: Daniel Gomez Cc: linux-iio@vger.kernel.org Signed-off-by: Andrea Merello Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index fa824e160f35..8e0026da38c9 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -25,6 +25,7 @@ enum iio_event_info { #define IIO_VAL_INT_MULTIPLE 5 #define IIO_VAL_FRACTIONAL 10 #define IIO_VAL_FRACTIONAL_LOG2 11 +#define IIO_VAL_CHAR 12 enum iio_available_type { IIO_AVAIL_LIST, -- cgit v1.2.3 From ddfb97d8f06c98fa5d80bbb6a997155a838161e9 Mon Sep 17 00:00:00 2001 From: Andrea Merello Date: Wed, 20 Nov 2019 15:47:52 +0100 Subject: iio: core: add thermocouple_type standard attribute We have a couple of thermocouple IIO drivers, supporting several chips. Some of them support only one specific thermocouple type (e.g. "K", "J"), one of them can be configured to work with several different thermocouple types. In certain applications thermocouples could be externally connected to the chip by the user. This patch introduces a new IIO standard attribute to report the supported thermocouple type and, where applicable, to allow it to be dynamically set using sysfs. Cc: Hartmut Knaack Cc: Lars-Peter Clausen Cc: Peter Meerwald-Stadler Cc: Colin Ian King Cc: Patrick Havelange Cc: Matt Weber Cc: Matt Ranostay Cc: Chuhong Yuan Cc: Daniel Gomez Cc: linux-iio@vger.kernel.org Signed-off-by: Andrea Merello Signed-off-by: Jonathan Cameron --- include/linux/iio/types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 8e0026da38c9..e6fd3645963c 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -58,6 +58,7 @@ enum iio_chan_info_enum { IIO_CHAN_INFO_DEBOUNCE_TIME, IIO_CHAN_INFO_CALIBEMISSIVITY, IIO_CHAN_INFO_OVERSAMPLING_RATIO, + IIO_CHAN_INFO_THERMOCOUPLE_TYPE, }; #endif /* _IIO_TYPES_H_ */ -- cgit v1.2.3 From 35bd71dd1c161e6e89b21138e01e8c04c6347716 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 18 Nov 2019 11:35:23 +0100 Subject: drm/tegra: Delete host1x_bo_ops->k(un)map It doesn't have any callers anymore. Aside: The ->mmap/munmap hooks have a bit a confusing name, they don't do userspace mmaps, but a kernel vmap. I think most places use vmap for this, except ttm, which uses kmap for vmap for added confusion. mmap seems entirely for userspace mappings set up through mmap(2) syscall. Reviewed-by: Thierry Reding Tested-by: Thierry Reding Acked-by: Sumit Semwal Signed-off-by: Daniel Vetter Cc: Thierry Reding Cc: Jonathan Hunter Cc: linux-tegra@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20191118103536.17675-3-daniel.vetter@ffwll.ch --- include/linux/host1x.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index e6eea45e1154..d11e89db7d7f 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -68,8 +68,6 @@ struct host1x_bo_ops { void (*unpin)(struct host1x_bo *bo, struct sg_table *sgt); void *(*mmap)(struct host1x_bo *bo); void (*munmap)(struct host1x_bo *bo, void *addr); - void *(*kmap)(struct host1x_bo *bo, unsigned int pagenum); - void (*kunmap)(struct host1x_bo *bo, unsigned int pagenum, void *addr); }; struct host1x_bo { @@ -113,17 +111,6 @@ static inline void host1x_bo_munmap(struct host1x_bo *bo, void *addr) bo->ops->munmap(bo, addr); } -static inline void *host1x_bo_kmap(struct host1x_bo *bo, unsigned int pagenum) -{ - return bo->ops->kmap(bo, pagenum); -} - -static inline void host1x_bo_kunmap(struct host1x_bo *bo, - unsigned int pagenum, void *addr) -{ - bo->ops->kunmap(bo, pagenum, addr); -} - /* * host1x syncpoints */ -- cgit v1.2.3 From 7f0de8d80816d9620e995cf98acf4b6cd2d7c230 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 18 Nov 2019 11:35:30 +0100 Subject: dma-buf: Drop dma_buf_k(un)map It's unused. 10 years ago, back when 32bit was still fairly common and trying to not exhaust vmalloc space sounded like a worthwhile goal, adding these to dma_buf made sense. Reality is that they simply never caught on, and nowadays everyone who needs plenty of buffers will run in 64bit mode anyway. Also update the docs in this area to adjust them to reality. The actual hooks in dma_buf_ops will be removed once all the implementations are gone. Acked-by: Sumit Semwal Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20191118103536.17675-10-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index af73f835c51c..7feb9c3805ae 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -464,8 +464,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); int dma_buf_end_cpu_access(struct dma_buf *dma_buf, enum dma_data_direction dir); -void *dma_buf_kmap(struct dma_buf *, unsigned long); -void dma_buf_kunmap(struct dma_buf *, unsigned long, void *); int dma_buf_mmap(struct dma_buf *, struct vm_area_struct *, unsigned long); -- cgit v1.2.3 From 4337ebbbbda3fb82e4fd928188a86e0bff0e9042 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Mon, 18 Nov 2019 11:35:36 +0100 Subject: dma-buf: Remove kernel map/unmap hooks All implementations are gone now. Acked-by: Sumit Semwal Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20191118103536.17675-16-daniel.vetter@ffwll.ch --- include/linux/dma-buf.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 7feb9c3805ae..abf5459a5b9d 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -249,31 +249,6 @@ struct dma_buf_ops { */ int (*mmap)(struct dma_buf *, struct vm_area_struct *vma); - /** - * @map: - * - * Maps a page from the buffer into kernel address space. The page is - * specified by offset into the buffer in PAGE_SIZE units. - * - * This callback is optional. - * - * Returns: - * - * Virtual address pointer where requested page can be accessed. NULL - * on error or when this function is unimplemented by the exporter. - */ - void *(*map)(struct dma_buf *, unsigned long); - - /** - * @unmap: - * - * Unmaps a page from the buffer. Page offset and address pointer should - * be the same as the one passed to and returned by matching call to map. - * - * This callback is optional. - */ - void (*unmap)(struct dma_buf *, unsigned long, void *); - void *(*vmap)(struct dma_buf *); void (*vunmap)(struct dma_buf *, void *vaddr); }; -- cgit v1.2.3 From 958de668197651bbf2b4b9528f204ab5a0f1af65 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Oct 2019 21:07:31 +0200 Subject: module: Remove set_all_modules_text_*() Now that there are no users of set_all_modules_text_*() left, remove it. While it appears nds32 uses it, it does not have STRICT_MODULE_RWX and therefore ends up with the NOP stubs. Tested-by: Alexei Starovoitov Tested-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Acked-by: Alexei Starovoitov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Greentime Hu Cc: H. Peter Anvin Cc: Jessica Yu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vincent Chen Link: https://lkml.kernel.org/r/20191111132458.284298307@infradead.org Signed-off-by: Ingo Molnar --- include/linux/module.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 6d20895e7739..daae84705040 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -846,13 +846,9 @@ extern int module_sysfs_initialized; #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_STRICT_MODULE_RWX -extern void set_all_modules_text_rw(void); -extern void set_all_modules_text_ro(void); extern void module_enable_ro(const struct module *mod, bool after_init); extern void module_disable_ro(const struct module *mod); #else -static inline void set_all_modules_text_rw(void) { } -static inline void set_all_modules_text_ro(void) { } static inline void module_enable_ro(const struct module *mod, bool after_init) { } static inline void module_disable_ro(const struct module *mod) { } #endif -- cgit v1.2.3 From 04ae87a52074e2d448fc66143f1bd2c7d694d2b9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 24 Oct 2019 22:26:59 +0200 Subject: ftrace: Rework event_create_dir() Rework event_create_dir() to use an array of static data instead of function pointers where possible. The problem is that it would call the function pointer on module load before parse_args(), possibly even before jump_labels were initialized. Luckily the generated functions don't use jump_labels but it still seems fragile. It also gets in the way of changing when we make the module map executable. The generated function are basically calling trace_define_field() with a bunch of static arguments. So instead of a function, capture these arguments in a static array, avoiding the function call. Now there are a number of cases where the fields are dynamic (syscall arguments, kprobes and uprobes), in which case a static array does not work, for these we preserve the function call. Luckily all these cases are not related to modules and so we can retain the function call for them. Also fix up all broken tracepoint definitions that now generate a compile error. Tested-by: Alexei Starovoitov Tested-by: Steven Rostedt (VMware) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (VMware) Acked-by: Alexei Starovoitov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191111132458.342979914@infradead.org Signed-off-by: Ingo Molnar --- include/linux/trace_events.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 30a8cdcfd4a4..a379255c14a9 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -187,6 +187,22 @@ enum trace_reg { struct trace_event_call; +#define TRACE_FUNCTION_TYPE ((const char *)~0UL) + +struct trace_event_fields { + const char *type; + union { + struct { + const char *name; + const int size; + const int align; + const int is_signed; + const int filter_type; + }; + int (*define_fields)(struct trace_event_call *); + }; +}; + struct trace_event_class { const char *system; void *probe; @@ -195,7 +211,7 @@ struct trace_event_class { #endif int (*reg)(struct trace_event_call *event, enum trace_reg type, void *data); - int (*define_fields)(struct trace_event_call *); + struct trace_event_fields *fields_array; struct list_head *(*get_fields)(struct trace_event_call *); struct list_head fields; int (*raw_init)(struct trace_event_call *); -- cgit v1.2.3 From e6bff4665c595b5a4aff173848851ed49ac3bfad Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:20 -0800 Subject: software node: replace is_array with is_inline We do not need a special flag to know if we are dealing with an array, as we can get that data from ratio between element length and the data size, but we do need a flag to know whether or not the data is stored directly inside property_entry. Signed-off-by: Dmitry Torokhov [ rjw: Subject & changelog, struct property_entry kerneldoc ] Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 48335288c2a9..6c1ca870a9a9 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -227,15 +227,15 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode, * struct property_entry - "Built-in" device property representation. * @name: Name of the property. * @length: Length of data making up the value. - * @is_array: True when the property is an array. + * @is_inline: True when the property value is stored inline. * @type: Type of the data in unions. - * @pointer: Pointer to the property (an array of items of the given type). - * @value: Value of the property (when it is a single item of the given type). + * @pointer: Pointer to the property when it is not stored inline. + * @value: Value of the property when it is stored inline. */ struct property_entry { const char *name; size_t length; - bool is_array; + bool is_inline; enum dev_prop_type type; union { const void *pointer; @@ -262,7 +262,6 @@ struct property_entry { (struct property_entry) { \ .name = _name_, \ .length = (_len_) * __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ - .is_array = true, \ .type = DEV_PROP_##_Type_, \ { .pointer = _val_ }, \ } @@ -293,6 +292,7 @@ struct property_entry { (struct property_entry) { \ .name = _name_, \ .length = __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + .is_inline = true, \ .type = DEV_PROP_##_Type_, \ { .value = { ._elem_ = _val_ } }, \ } @@ -311,6 +311,7 @@ struct property_entry { #define PROPERTY_ENTRY_BOOL(_name_) \ (struct property_entry) { \ .name = _name_, \ + .is_inline = true, \ } struct property_entry * -- cgit v1.2.3 From 996b0830f95d132e50891a5568fef9e2965e4af2 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:21 -0800 Subject: software node: allow embedding of small arrays into property_entry We should not conflate whether a property data is an array or a single value with where it is stored (embedded into property_entry structure or out-of-line). All single-value properties are in effect 1-element arrays, and we can figure the amount of data stored in a property by examining its length and the data type. And arrays can be as easily stored in property entry instances as single values are, provided that we have enough space (we have up to 8 bytes). We can embed: - up to 8 bytes from U8 arrays - up to 4 words - up to 2 double words - one U64 value - one (on 64 bit architectures) or 2 (on 32 bit) strings. This change also has an effect of switching properties with small amount of data to embed it instead of keeping it separate when copying such properties. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 6c1ca870a9a9..fc819c6ebf33 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -240,11 +240,11 @@ struct property_entry { union { const void *pointer; union { - u8 u8_data; - u16 u16_data; - u32 u32_data; - u64 u64_data; - const char *str; + u8 u8_data[sizeof(u64) / sizeof(u8)]; + u16 u16_data[sizeof(u64) / sizeof(u16)]; + u32 u32_data[sizeof(u64) / sizeof(u32)]; + u64 u64_data[sizeof(u64) / sizeof(u64)]; + const char *str[sizeof(u64) / sizeof(char *)]; } value; }; }; @@ -256,7 +256,7 @@ struct property_entry { */ #define __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_) \ - sizeof(((struct property_entry *)NULL)->value._elem_) + sizeof(((struct property_entry *)NULL)->value._elem_[0]) #define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ (struct property_entry) { \ @@ -294,7 +294,7 @@ struct property_entry { .length = __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ .is_inline = true, \ .type = DEV_PROP_##_Type_, \ - { .value = { ._elem_ = _val_ } }, \ + { .value = { ._elem_[0] = _val_ } }, \ } #define PROPERTY_ENTRY_U8(_name_, _val_) \ -- cgit v1.2.3 From e64b674bc9d76edb4cf1b8c98446b1d29a16b9df Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:22 -0800 Subject: software node: implement reference properties It is possible to store references to software nodes in the same fashion as other static properties, so that users do not need to define separate structures: static const struct software_node gpio_bank_b_node = { .name = "B", }; static const struct property_entry simone_key_enter_props[] = { PROPERTY_ENTRY_U32("linux,code", KEY_ENTER), PROPERTY_ENTRY_STRING("label", "enter"), PROPERTY_ENTRY_REF("gpios", &gpio_bank_b_node, 123, GPIO_ACTIVE_LOW), { } }; Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 57 ++++++++++++++++++++++++++++++++++-------------- 1 file changed, 41 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index fc819c6ebf33..3df7089f0dbd 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -22,6 +22,7 @@ enum dev_prop_type { DEV_PROP_U32, DEV_PROP_U64, DEV_PROP_STRING, + DEV_PROP_REF, }; enum dev_dma_attr { @@ -223,6 +224,20 @@ static inline int fwnode_property_count_u64(const struct fwnode_handle *fwnode, return fwnode_property_read_u64_array(fwnode, propname, NULL, 0); } +struct software_node; + +/** + * struct software_node_ref_args - Reference property with additional arguments + * @node: Reference to a software node + * @nargs: Number of elements in @args array + * @args: Integer arguments + */ +struct software_node_ref_args { + const struct software_node *node; + unsigned int nargs; + u64 args[NR_FWNODE_REFERENCE_ARGS]; +}; + /** * struct property_entry - "Built-in" device property representation. * @name: Name of the property. @@ -258,14 +273,20 @@ struct property_entry { #define __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_) \ sizeof(((struct property_entry *)NULL)->value._elem_[0]) -#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ +#define __PROPERTY_ENTRY_ARRAY_ELSIZE_LEN(_name_, _elsize_, _Type_, \ + _val_, _len_) \ (struct property_entry) { \ .name = _name_, \ - .length = (_len_) * __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + .length = (_len_) * (_elsize_), \ .type = DEV_PROP_##_Type_, \ { .pointer = _val_ }, \ } +#define __PROPERTY_ENTRY_ARRAY_LEN(_name_, _elem_, _Type_, _val_, _len_)\ + __PROPERTY_ENTRY_ARRAY_ELSIZE_LEN(_name_, \ + __PROPERTY_ENTRY_ELEMENT_SIZE(_elem_), \ + _Type_, _val_, _len_) + #define PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, u8_data, U8, _val_, _len_) #define PROPERTY_ENTRY_U16_ARRAY_LEN(_name_, _val_, _len_) \ @@ -276,6 +297,10 @@ struct property_entry { __PROPERTY_ENTRY_ARRAY_LEN(_name_, u64_data, U64, _val_, _len_) #define PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, _len_) \ __PROPERTY_ENTRY_ARRAY_LEN(_name_, str, STRING, _val_, _len_) +#define PROPERTY_ENTRY_REF_ARRAY_LEN(_name_, _val_, _len_) \ + __PROPERTY_ENTRY_ARRAY_ELSIZE_LEN(_name_, \ + sizeof(struct software_node_ref_args), \ + REF, _val_, _len_) #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_U8_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) @@ -287,6 +312,8 @@ struct property_entry { PROPERTY_ENTRY_U64_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define PROPERTY_ENTRY_STRING_ARRAY(_name_, _val_) \ PROPERTY_ENTRY_STRING_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) +#define PROPERTY_ENTRY_REF_ARRAY(_name_, _val_) \ + PROPERTY_ENTRY_REF_ARRAY_LEN(_name_, _val_, ARRAY_SIZE(_val_)) #define __PROPERTY_ENTRY_ELEMENT(_name_, _elem_, _Type_, _val_) \ (struct property_entry) { \ @@ -314,6 +341,18 @@ struct property_entry { .is_inline = true, \ } +#define PROPERTY_ENTRY_REF(_name_, _ref_, ...) \ +(struct property_entry) { \ + .name = _name_, \ + .length = sizeof(struct software_node_ref_args), \ + .type = DEV_PROP_REF, \ + { .pointer = &(const struct software_node_ref_args) { \ + .node = _ref_, \ + .nargs = ARRAY_SIZE(((u64[]){ 0, ##__VA_ARGS__ })) - 1, \ + .args = { __VA_ARGS__ }, \ + } }, \ +} + struct property_entry * property_entries_dup(const struct property_entry *properties); @@ -377,20 +416,6 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -struct software_node; - -/** - * struct software_node_ref_args - Reference with additional arguments - * @node: Reference to a software node - * @nargs: Number of elements in @args array - * @args: Integer arguments - */ -struct software_node_ref_args { - const struct software_node *node; - unsigned int nargs; - u64 args[NR_FWNODE_REFERENCE_ARGS]; -}; - /** * struct software_node_reference - Named software node reference property * @name: Name of the property -- cgit v1.2.3 From e933bedd45099dce1165104138bb703a6e31df82 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Thu, 7 Nov 2019 20:22:24 -0800 Subject: software node: remove separate handling of references Now that all users of references have moved to reference properties, we can remove separate handling of references. Signed-off-by: Dmitry Torokhov Signed-off-by: Rafael J. Wysocki --- include/linux/property.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/property.h b/include/linux/property.h index 3df7089f0dbd..d86de017c689 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -416,30 +416,16 @@ int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, /* -------------------------------------------------------------------------- */ /* Software fwnode support - when HW description is incomplete or missing */ -/** - * struct software_node_reference - Named software node reference property - * @name: Name of the property - * @nrefs: Number of elements in @refs array - * @refs: Array of references with optional arguments - */ -struct software_node_reference { - const char *name; - unsigned int nrefs; - const struct software_node_ref_args *refs; -}; - /** * struct software_node - Software node description * @name: Name of the software node * @parent: Parent of the software node * @properties: Array of device properties - * @references: Array of software node reference properties */ struct software_node { const char *name; const struct software_node *parent; const struct property_entry *properties; - const struct software_node_reference *references; }; bool is_software_node(const struct fwnode_handle *fwnode); -- cgit v1.2.3 From bf9e25ec12877a622857460c2f542a6c31393250 Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Tue, 3 Dec 2019 18:38:47 +0200 Subject: video: fbdev: make fbops member of struct fb_info a const pointer Now that we no longer modify the fbops, or hold non-const pointers to it, we can make it const. After this, we can start making the fbops const all over the place. Cc: linux-fbdev@vger.kernel.org Reviewed-by: Daniel Vetter Signed-off-by: Jani Nikula Link: https://patchwork.freedesktop.org/patch/msgid/700c6b52c39c6e7babaa921f583eac354714d9fc.1575390740.git.jani.nikula@intel.com --- include/linux/fb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index a6ad528990de..6557fabdea62 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -472,7 +472,7 @@ struct fb_info { struct fb_deferred_io *fbdefio; #endif - struct fb_ops *fbops; + const struct fb_ops *fbops; struct device *device; /* This is the parent */ struct device *dev; /* This is this fb device */ int class_flag; /* private sysfs flags */ -- cgit v1.2.3 From 2496396fcb44404ead24b578c583d5286886e857 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Oct 2019 21:18:10 +0200 Subject: sched/rt, fs: Use CONFIG_PREEMPTION MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit CONFIG_PREEMPTION is selected by CONFIG_PREEMPT and by CONFIG_PREEMPT_RT. Both PREEMPT and PREEMPT_RT require the same functionality which today depends on CONFIG_PREEMPT. Switch the i_size() and part_nr_sects_…() code over to use CONFIG_PREEMPTION. Update the comment for fsstack_copy_inode_size() also to refer to CONFIG_PREEMPTION. [bigeasy: +PREEMPT comments] Signed-off-by: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Cc: Alexander Viro Cc: Linus Torvalds Cc: Peter Zijlstra Cc: linux-fsdevel@vger.kernel.org Link: https://lore.kernel.org/r/20191015191821.11479-24-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/fs.h | 4 ++-- include/linux/genhd.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..dddfcbb140a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -855,7 +855,7 @@ static inline loff_t i_size_read(const struct inode *inode) i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); @@ -880,7 +880,7 @@ static inline void i_size_write(struct inode *inode, loff_t i_size) inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8bb63027e4d6..a927829bb73a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -718,7 +718,7 @@ static inline void hd_free_part(struct hd_struct *part) * accessor function. * * Code written along the lines of i_size_read() and i_size_write(). - * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption + * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption * on. */ static inline sector_t part_nr_sects_read(struct hd_struct *part) @@ -731,7 +731,7 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part) nr_sects = part->nr_sects; } while (read_seqcount_retry(&part->nr_sects_seq, seq)); return nr_sects; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) sector_t nr_sects; preempt_disable(); @@ -754,7 +754,7 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) write_seqcount_begin(&part->nr_sects_seq); part->nr_sects = size; write_seqcount_end(&part->nr_sects_seq); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); part->nr_sects = size; preempt_enable(); -- cgit v1.2.3 From ce623f89872df4253719be71531116751eeab85f Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:27 +1100 Subject: nsfs: clean-up ns_get_path() signature to return int ns_get_path() and ns_get_path_cb() only ever return either NULL or an ERR_PTR. It is far more idiomatic to simply return an integer, and it makes all of the callers of ns_get_path() more straightforward to read. Fixes: e149ed2b805f ("take the targets of /proc/*/ns/* symlinks to separate fs") Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/proc_ns.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index d31cb6215905..aed366b4795c 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -76,10 +76,10 @@ static inline int ns_alloc_inum(struct ns_common *ns) extern struct file *proc_ns_fget(int fd); #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) -extern void *ns_get_path(struct path *path, struct task_struct *task, +extern int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); typedef struct ns_common *ns_get_path_helper_t(void *); -extern void *ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, +extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, void *private_data); extern int ns_get_name(char *buf, size_t size, struct task_struct *task, -- cgit v1.2.3 From 1bc82070fa2763bdca626fa8bde72b35f11e8960 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:28 +1100 Subject: namei: allow nd_jump_link() to produce errors In preparation for LOOKUP_NO_MAGICLINKS, it's necessary to add the ability for nd_jump_link() to return an error which the corresponding get_link() caller must propogate back up to the VFS. Suggested-by: Al Viro Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 7fe7b87a3ded..b2479cc119c6 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -69,7 +69,7 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); -extern void nd_jump_link(struct path *path); +extern int __must_check nd_jump_link(struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { -- cgit v1.2.3 From 278121417a72d87fb29dd8c48801f80821e8f75a Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:30 +1100 Subject: namei: LOOKUP_NO_SYMLINKS: block symlink resolution /* Background. */ Userspace cannot easily resolve a path without resolving symlinks, and would have to manually resolve each path component with O_PATH and O_NOFOLLOW. This is clearly inefficient, and can be fairly easy to screw up (resulting in possible security bugs). Linus has mentioned that Git has a particular need for this kind of flag[1]. It also resolves a fairly long-standing perceived deficiency in O_NOFOLLOw -- that it only blocks the opening of trailing symlinks. This is part of a refresh of Al's AT_NO_JUMPS patchset[2] (which was a variation on David Drysdale's O_BENEATH patchset[3], which in turn was based on the Capsicum project[4]). /* Userspace API. */ LOOKUP_NO_SYMLINKS will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_NO_SYMLINKS applies to all components of the path. With LOOKUP_NO_SYMLINKS, any symlink path component encountered during path resolution will yield -ELOOP. If the trailing component is a symlink (and no other components were symlinks), then O_PATH|O_NOFOLLOW will not error out and will instead provide a handle to the trailing symlink -- without resolving it. /* Testing. */ LOOKUP_NO_SYMLINKS is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/CA+55aFyOKM7DW7+0sdDFKdZFXgptb5r1id9=Wvhd8AgSP7qjwQ@mail.gmail.com/ [2]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [3]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [4]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ Cc: Christian Brauner Suggested-by: Al Viro Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index b2479cc119c6..c42a1924ad67 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -39,6 +39,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_ROOT 0x2000 #define LOOKUP_ROOT_GRABBED 0x0008 +/* Scoping flags for lookup. */ +#define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ + extern int path_pts(struct path *path); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); -- cgit v1.2.3 From 4b99d4996979d582859c5a49072e92de124bf691 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:31 +1100 Subject: namei: LOOKUP_NO_MAGICLINKS: block magic-link resolution /* Background. */ There has always been a special class of symlink-like objects in procfs (and a few other pseudo-filesystems) which allow for non-lexical resolution of paths using nd_jump_link(). These "magic-links" do not follow traditional mount namespace boundaries, and have been used consistently in container escape attacks because they can be used to trick unsuspecting privileged processes into resolving unexpected paths. It is also non-trivial for userspace to unambiguously avoid resolving magic-links, because they do not have a reliable indication that they are a magic-link (in order to verify them you'd have to manually open the path given by readlink(2) and then verify that the two file descriptors reference the same underlying file, which is plagued with possible race conditions or supplementary attack scenarios). It would therefore be very helpful for userspace to be able to avoid these symlinks easily, thus hopefully removing a tool from attackers' toolboxes. This is part of a refresh of Al's AT_NO_JUMPS patchset[1] (which was a variation on David Drysdale's O_BENEATH patchset[2], which in turn was based on the Capsicum project[3]). /* Userspace API. */ LOOKUP_NO_MAGICLINKS will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_NO_MAGICLINKS applies to all components of the path. With LOOKUP_NO_MAGICLINKS, any magic-link path component encountered during path resolution will yield -ELOOP. The handling of ~LOOKUP_FOLLOW for a trailing magic-link is identical to LOOKUP_NO_SYMLINKS. LOOKUP_NO_SYMLINKS implies LOOKUP_NO_MAGICLINKS. /* Testing. */ LOOKUP_NO_MAGICLINKS is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [2]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [3]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ Cc: Christian Brauner Suggested-by: David Drysdale Suggested-by: Al Viro Suggested-by: Andy Lutomirski Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index c42a1924ad67..f8acec81cf03 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -41,6 +41,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ +#define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ extern int path_pts(struct path *path); -- cgit v1.2.3 From 72ba29297e1439efaa54d9125b866ae9d15df339 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:32 +1100 Subject: namei: LOOKUP_NO_XDEV: block mountpoint crossing /* Background. */ The need to contain path operations within a mountpoint has been a long-standing usecase that userspace has historically implemented manually with liberal usage of stat(). find, rsync, tar and many other programs implement these semantics -- but it'd be much simpler to have a fool-proof way of refusing to open a path if it crosses a mountpoint. This is part of a refresh of Al's AT_NO_JUMPS patchset[1] (which was a variation on David Drysdale's O_BENEATH patchset[2], which in turn was based on the Capsicum project[3]). /* Userspace API. */ LOOKUP_NO_XDEV will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_NO_XDEV applies to all components of the path. With LOOKUP_NO_XDEV, any path component which crosses a mount-point during path resolution (including "..") will yield an -EXDEV. Absolute paths, absolute symlinks, and magic-links will only yield an -EXDEV if the jump involved changing mount-points. /* Testing. */ LOOKUP_NO_XDEV is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [2]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [3]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ Cc: Christian Brauner Suggested-by: David Drysdale Suggested-by: Al Viro Suggested-by: Andy Lutomirski Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index f8acec81cf03..edb4562b5c4e 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -42,6 +42,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ +#define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ extern int path_pts(struct path *path); -- cgit v1.2.3 From adb21d2b526f7f196b2f3fdca97d80ba05dd14a0 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:33 +1100 Subject: namei: LOOKUP_BENEATH: O_BENEATH-like scoped resolution /* Background. */ There are many circumstances when userspace wants to resolve a path and ensure that it doesn't go outside of a particular root directory during resolution. Obvious examples include archive extraction tools, as well as other security-conscious userspace programs. FreeBSD spun out O_BENEATH from their Capsicum project[1,2], so it also seems reasonable to implement similar functionality for Linux. This is part of a refresh of Al's AT_NO_JUMPS patchset[3] (which was a variation on David Drysdale's O_BENEATH patchset[4], which in turn was based on the Capsicum project[5]). /* Userspace API. */ LOOKUP_BENEATH will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_BENEATH applies to all components of the path. With LOOKUP_BENEATH, any path component which attempts to "escape" the starting point of the filesystem lookup (the dirfd passed to openat) will yield -EXDEV. Thus, all absolute paths and symlinks are disallowed. Due to a security concern brought up by Jann[6], any ".." path components are also blocked. This restriction will be lifted in a future patch, but requires more work to ensure that permitting ".." is done safely. Magic-link jumps are also blocked, because they can beam the path lookup across the starting point. It would be possible to detect and block only the "bad" crossings with path_is_under() checks, but it's unclear whether it makes sense to permit magic-links at all. However, userspace is recommended to pass LOOKUP_NO_MAGICLINKS if they want to ensure that magic-link crossing is entirely disabled. /* Testing. */ LOOKUP_BENEATH is tested as part of the openat2(2) selftests. [1]: https://reviews.freebsd.org/D2808 [2]: https://reviews.freebsd.org/D17547 [3]: https://lore.kernel.org/lkml/20170429220414.GT29622@ZenIV.linux.org.uk/ [4]: https://lore.kernel.org/lkml/1415094884-18349-1-git-send-email-drysdale@google.com/ [5]: https://lore.kernel.org/lkml/1404124096-21445-1-git-send-email-drysdale@google.com/ [6]: https://lore.kernel.org/lkml/CAG48ez1jzNvxB+bfOBnERFGp=oMM0vHWuLD6EULmne3R6xa53w@mail.gmail.com/ Cc: Christian Brauner Suggested-by: David Drysdale Suggested-by: Al Viro Suggested-by: Andy Lutomirski Suggested-by: Linus Torvalds Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index edb4562b5c4e..d2a98083be77 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -2,6 +2,7 @@ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H +#include #include #include #include @@ -43,6 +44,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ +#define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ +/* LOOKUP_* flags which do scope-related checks based on the dirfd. */ +#define LOOKUP_IS_SCOPED LOOKUP_BENEATH extern int path_pts(struct path *path); -- cgit v1.2.3 From 8db52c7e7ee1bd861b6096fcafc0fe7d0f24a994 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sat, 7 Dec 2019 01:13:34 +1100 Subject: namei: LOOKUP_IN_ROOT: chroot-like scoped resolution /* Background. */ Container runtimes or other administrative management processes will often interact with root filesystems while in the host mount namespace, because the cost of doing a chroot(2) on every operation is too prohibitive (especially in Go, which cannot safely use vfork). However, a malicious program can trick the management process into doing operations on files outside of the root filesystem through careful crafting of symlinks. Most programs that need this feature have attempted to make this process safe, by doing all of the path resolution in userspace (with symlinks being scoped to the root of the malicious root filesystem). Unfortunately, this method is prone to foot-guns and usually such implementations have subtle security bugs. Thus, what userspace needs is a way to resolve a path as though it were in a chroot(2) -- with all absolute symlinks being resolved relative to the dirfd root (and ".." components being stuck under the dirfd root). It is much simpler and more straight-forward to provide this functionality in-kernel (because it can be done far more cheaply and correctly). More classical applications that also have this problem (which have their own potentially buggy userspace path sanitisation code) include web servers, archive extraction tools, network file servers, and so on. /* Userspace API. */ LOOKUP_IN_ROOT will be exposed to userspace through openat2(2). /* Semantics. */ Unlike most other LOOKUP flags (most notably LOOKUP_FOLLOW), LOOKUP_IN_ROOT applies to all components of the path. With LOOKUP_IN_ROOT, any path component which attempts to cross the starting point of the pathname lookup (the dirfd passed to openat) will remain at the starting point. Thus, all absolute paths and symlinks will be scoped within the starting point. There is a slight change in behaviour regarding pathnames -- if the pathname is absolute then the dirfd is still used as the root of resolution of LOOKUP_IN_ROOT is specified (this is to avoid obvious foot-guns, at the cost of a minor API inconsistency). As with LOOKUP_BENEATH, Jann's security concern about ".."[1] applies to LOOKUP_IN_ROOT -- therefore ".." resolution is blocked. This restriction will be lifted in a future patch, but requires more work to ensure that permitting ".." is done safely. Magic-link jumps are also blocked, because they can beam the path lookup across the starting point. It would be possible to detect and block only the "bad" crossings with path_is_under() checks, but it's unclear whether it makes sense to permit magic-links at all. However, userspace is recommended to pass LOOKUP_NO_MAGICLINKS if they want to ensure that magic-link crossing is entirely disabled. /* Testing. */ LOOKUP_IN_ROOT is tested as part of the openat2(2) selftests. [1]: https://lore.kernel.org/lkml/CAG48ez1jzNvxB+bfOBnERFGp=oMM0vHWuLD6EULmne3R6xa53w@mail.gmail.com/ Cc: Christian Brauner Signed-off-by: Aleksa Sarai Signed-off-by: Al Viro --- include/linux/namei.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index d2a98083be77..4e77068f7a1a 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -45,8 +45,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ +#define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ -#define LOOKUP_IS_SCOPED LOOKUP_BENEATH +#define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); -- cgit v1.2.3 From ba70609d5ec664a8f36ba1c857fcd97a478adf79 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Mon, 2 Dec 2019 21:19:44 -0800 Subject: fs: Delete timespec64_trunc() There are no more callers to the function remaining. Signed-off-by: Deepa Dinamani Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 98e0349adb52..46dd7e6f6d73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1575,7 +1575,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } -extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran); extern struct timespec64 current_time(struct inode *inode); /* -- cgit v1.2.3 From b50b0580d27bc45a0637aefc8bac4d31aa85771a Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Mon, 25 Nov 2019 14:48:57 +0100 Subject: net: add queue argument to __skb_wait_for_more_packets and __skb_{,try_}recv_datagram This will be used by ESP over TCP to handle the queue of IKE messages. Signed-off-by: Sabrina Dubroca Acked-by: David S. Miller Signed-off-by: Steffen Klassert --- include/linux/skbuff.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e9133bcf0544..49a10f9cc538 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3459,7 +3459,8 @@ static inline void skb_frag_list_init(struct sk_buff *skb) for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) -int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, +int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, + int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff_head *queue, @@ -3468,12 +3469,16 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, struct sk_buff *skb), int *off, int *err, struct sk_buff **last); -struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *__skb_try_recv_datagram(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err, struct sk_buff **last); -struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, +struct sk_buff *__skb_recv_datagram(struct sock *sk, + struct sk_buff_head *sk_queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err); -- cgit v1.2.3 From b6d0531ec7e2ae923395a1d5a80edb7ee51ac204 Mon Sep 17 00:00:00 2001 From: Fabien Dessenne Date: Mon, 2 Dec 2019 10:01:17 +0100 Subject: moduleparam: fix kerneldoc Document missing @arg in xxx_param_cb(). Describe all parameters of module_param_[named_]unsafe() and all *_param_cb() to make ./scripts/kernel-doc happy. Acked-by: Randy Dunlap