From 02669b17a433c242a40f01f14b691c9c9d1f8a13 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 5 Dec 2018 16:37:03 -0500 Subject: XArray: Turn xa_init_flags into a static inline A regular xa_init_flags() put all dynamically-initialised XArrays into the same locking class. That leads to lockdep believing that taking one XArray lock while holding another is a deadlock. It's possible to work around some of these situations with separate locking classes for irq/bh/regular XArrays, and SINGLE_DEPTH_NESTING, but that's ugly, and it doesn't work for all situations (where we have completely unrelated XArrays). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index f492e21c4aa2..4cf3cd128689 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -286,7 +286,6 @@ struct xarray { */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) -void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); @@ -303,6 +302,24 @@ unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); +/** + * xa_init_flags() - Initialise an empty XArray with flags. + * @xa: XArray. + * @flags: XA_FLAG values. + * + * If you need to initialise an XArray with special flags (eg you need + * to take the lock from interrupt context), use this function instead + * of xa_init(). + * + * Context: Any context. + */ +static inline void xa_init_flags(struct xarray *xa, gfp_t flags) +{ + spin_lock_init(&xa->xa_lock); + xa->xa_flags = flags; + xa->xa_head = NULL; +} + /** * xa_init() - Initialise an empty XArray. * @xa: XArray. -- cgit v1.2.3 From 4a31896c5b5a2715ecf4033426aa0a35066d92d6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 17 Dec 2018 14:45:36 -0500 Subject: XArray: Change xa_for_each iterator There were three problems with this API: 1. It took too many arguments; almost all users wanted to iterate over every element in the array rather than a subset. 2. It required that 'index' be initialised before use, and there's no realistic way to make GCC catch that. 3. 'index' and 'entry' were the opposite way round from every other member of the XArray APIs. So split it into three different APIs: xa_for_each(xa, index, entry) xa_for_each_start(xa, index, entry, start) xa_for_each_marked(xa, index, entry, filter) Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 78 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 65 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4cf3cd128689..3d0ce8b267e3 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -359,20 +359,45 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) } /** - * xa_for_each() - Iterate over a portion of an XArray. + * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. + * @index: Index of @entry. * @entry: Entry retrieved from array. + * @start: First index to retrieve from array. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you + * want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set + * to NULL and @index will have a value less than or equal to max. + * + * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_start() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each() iterator instead. + * The xas_for_each() iterator will expand into more inline code than + * xa_for_each_start(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_start(xa, index, entry, start) \ + for (index = start, \ + entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \ + entry; \ + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)) + +/** + * xa_for_each() - Iterate over present entries in an XArray. + * @xa: XArray. * @index: Index of @entry. - * @max: Maximum index to retrieve from array. - * @filter: Selection criterion. + * @entry: Entry retrieved from array. * - * Initialise @index to the lowest index you want to retrieve from the - * array. During the iteration, @entry will have the value of the entry - * stored in @xa at @index. The iteration will skip all entries in the - * array which do not match @filter. You may modify @index during the - * iteration if you want to skip or reprocess indices. It is safe to modify - * the array during the iteration. At the end of the iteration, @entry will - * be set to NULL and @index will have a value less than or equal to max. + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you want + * to skip or reprocess indices. It is safe to modify the array during the + * iteration. At the end of the iteration, @entry will be set to NULL and + * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock @@ -383,9 +408,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) * * Context: Any context. Takes and releases the RCU lock. */ -#define xa_for_each(xa, entry, index, max, filter) \ - for (entry = xa_find(xa, &index, max, filter); entry; \ - entry = xa_find_after(xa, &index, max, filter)) +#define xa_for_each(xa, index, entry) \ + xa_for_each_start(xa, index, entry, 0) + +/** + * xa_for_each_marked() - Iterate over marked entries in an XArray. + * @xa: XArray. + * @index: Index of @entry. + * @entry: Entry retrieved from array. + * @filter: Selection criterion. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. The iteration will skip all entries in the array + * which do not match @filter. You may modify @index during the iteration + * if you want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set to + * NULL and @index will have a value less than or equal to max. + * + * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). + * You have to handle your own locking with xas_for_each(), and if you have + * to unlock after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_marked() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each_marked() iterator + * instead. The xas_for_each_marked() iterator will expand into more inline + * code than xa_for_each_marked(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_marked(xa, index, entry, filter) \ + for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ + entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) -- cgit v1.2.3 From 76b4e52995654af260f14558e0e07b5b039ae202 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 28 Dec 2018 23:20:44 -0500 Subject: XArray: Permit storing 2-byte-aligned pointers On m68k, statically allocated pointers may only be two-byte aligned. This clashes with the XArray's method for tagging internal pointers. Permit storing these pointers in single slots (ie not in multislots). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 3d0ce8b267e3..435c25b29079 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -176,7 +176,8 @@ static inline bool xa_is_internal(const void *entry) */ static inline bool xa_is_err(const void *entry) { - return unlikely(xa_is_internal(entry)); + return unlikely(xa_is_internal(entry) && + (unsigned long)entry >= -((MAX_ERRNO << 2) + 2)); } /** @@ -1039,8 +1040,8 @@ static inline bool xa_is_sibling(const void *entry) (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } -#define XA_ZERO_ENTRY xa_mk_internal(256) -#define XA_RETRY_ENTRY xa_mk_internal(257) +#define XA_RETRY_ENTRY xa_mk_internal(256) +#define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? @@ -1064,6 +1065,17 @@ static inline bool xa_is_retry(const void *entry) return unlikely(entry == XA_RETRY_ENTRY); } +/** + * xa_is_advanced() - Is the entry only permitted for the advanced API? + * @entry: Entry to be stored in the XArray. + * + * Return: %true if the entry cannot be stored by the normal API. + */ +static inline bool xa_is_advanced(const void *entry) +{ + return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); +} + /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed -- cgit v1.2.3 From b0606fed6eece16a421034eca0bbea9a08b90e91 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 2 Jan 2019 13:57:03 -0500 Subject: XArray: Honour reserved entries in xa_insert xa_insert() should treat reserved entries as occupied, not as available. Also, it should treat requests to insert a NULL pointer as a request to reserve the slot. Add xa_insert_bh() and xa_insert_irq() for completeness. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 110 +++++++++++++++++++++++++++++++------------------ 1 file changed, 71 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 435c25b29079..12244aa98a69 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -463,39 +463,12 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); -/** - * __xa_insert() - Store this entry in the XArray unless another entry is - * already present. - * @xa: XArray. - * @index: Index into array. - * @entry: New entry. - * @gfp: Memory allocation flags. - * - * If you would rather see the existing entry in the array, use __xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. - * - * Context: Any context. Expects xa_lock to be held on entry. May - * release and reacquire xa_lock if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. - * -ENOMEM if memory could not be allocated. - */ -static inline int __xa_insert(struct xarray *xa, unsigned long index, - void *entry, gfp_t gfp) -{ - void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; -} - /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. @@ -685,24 +658,83 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, * @entry: New entry. * @gfp: Memory allocation flags. * - * If you would rather see the existing entry in the array, use xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. * - * Context: Process context. Takes and releases the xa_lock. - * May sleep if the @gfp flags permit. + * Context: Any context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. * Return: 0 if the store succeeded. -EEXIST if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { - void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; + int err; + + xa_lock(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_insert_bh() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert_bh(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_insert_irq() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert_irq(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock_irq(xa); + + return err; } /** -- cgit v1.2.3 From 1cb95e072ede5e3d6a54eefd520db21b45985896 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 8 Jan 2019 15:34:52 -0800 Subject: libnvdimm/dimm: Fix security capability detection for non-Intel NVDIMMs Kees reports a crash with the following signature... RIP: 0010:nvdimm_visible+0x79/0x80 [..] Call Trace: internal_create_group+0xf4/0x380 sysfs_create_groups+0x46/0xb0 device_add+0x331/0x680 nd_async_device_register+0x15/0x60 async_run_entry_fn+0x38/0x100 ...when starting a QEMU environment with "label-less" DIMM. Without labels QEMU does not publish any DSM methods. Without defined methods the NVDIMM_FAMILY type is not established and the nfit driver will skip registering security operations. In that case the security state should be initialized to a negative value in __nvdimm_create() and nvdimm_visible() should skip interrogating the specific ops. However, since 'enum nvdimm_security_state' was only defined to contain positive values the "if (nvdimm->sec.state < 0)" check always fails. Define a negative error state to allow negative state values to be handled as expected. Fixes: f2989396553a ("acpi/nfit, libnvdimm: Introduce nvdimm_security_ops") Reviewed-by: Dave Jiang Reported-by: Kees Cook Tested-by: Kees Cook Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 5440f11b0907..7315977b64da 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -160,6 +160,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc( } enum nvdimm_security_state { + NVDIMM_SECURITY_ERROR = -1, NVDIMM_SECURITY_DISABLED, NVDIMM_SECURITY_UNLOCKED, NVDIMM_SECURITY_LOCKED, -- cgit v1.2.3 From 3e2ffd655cc6a694608d997738989ff5572a8266 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 2 Jan 2019 15:57:49 -0500 Subject: include/linux/compiler*.h: fix OPTIMIZER_HIDE_VAR Since commit 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") clang no longer reuses the OPTIMIZER_HIDE_VAR macro from compiler-gcc - instead it gets the version in include/linux/compiler.h. Unfortunately that version doesn't actually prevent compiler from optimizing out the variable. Fix up by moving the macro out from compiler-gcc.h to compiler.h. Compilers without incline asm support will keep working since it's protected by an ifdef. Also fix up comments to match reality since we are no longer overriding any macros. Build-tested with gcc and clang. Fixes: 815f0ddb346c ("include/linux/compiler*.h: make compiler-*.h mutually exclusive") Cc: Eli Friedman Cc: Joe Perches Cc: Linus Torvalds Reviewed-by: Nick Desaulniers Signed-off-by: Michael S. Tsirkin Signed-off-by: Miguel Ojeda --- include/linux/compiler-clang.h | 5 ++--- include/linux/compiler-gcc.h | 4 ---- include/linux/compiler-intel.h | 4 +--- include/linux/compiler.h | 4 +++- 4 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 39f668d5066b..333a6695a918 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -3,9 +3,8 @@ #error "Please don't include directly, include instead." #endif -/* Some compiler specific definitions are overwritten here - * for Clang compiler - */ +/* Compiler specific definitions for Clang compiler */ + #define uninitialized_var(x) x = *(&(x)) /* same as gcc, this was present in clang-2.6 so we can assume it works diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5776da43da97..7b834e37d0c0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -58,10 +58,6 @@ (typeof(ptr)) (__ptr + (off)); \ }) -/* Make the optimizer believe the variable can be manipulated arbitrarily. */ -#define OPTIMIZER_HIDE_VAR(var) \ - __asm__ ("" : "=r" (var) : "0" (var)) - /* * A trick to suppress uninitialized variable warning without generating any * code diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 517bd14e1222..b17f3cd18334 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -5,9 +5,7 @@ #ifdef __ECC -/* Some compiler specific definitions are overwritten here - * for Intel ECC compiler - */ +/* Compiler specific definitions for Intel ECC compiler */ #include diff --git a/include/linux/compiler.h b/include/linux/compiler.h index fc5004a4b07d..445348facea9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -161,7 +161,9 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif #ifndef OPTIMIZER_HIDE_VAR -#define OPTIMIZER_HIDE_VAR(var) barrier() +/* Make the optimizer believe the variable can be manipulated arbitrarily. */ +#define OPTIMIZER_HIDE_VAR(var) \ + __asm__ ("" : "=r" (var) : "0" (var)) #endif /* Not-quite-unique ID. */ -- cgit v1.2.3 From ba50bf1ce9a51fc97db58b96d01306aa70bc3979 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 17 Dec 2018 20:16:09 +0000 Subject: Drivers: hv: vmbus: Check for ring when getting debug info fc96df16a1ce is good and can already fix the "return stack garbage" issue, but let's also improve hv_ringbuffer_get_debuginfo(), which would silently return stack garbage, if people forget to check channel->state or ring_info->ring_buffer, when using the function in the future. Having an error check in the function would eliminate the potential risk. Add a Fixes tag to indicate the patch depdendency. Fixes: fc96df16a1ce ("Drivers: hv: vmbus: Return -EINVAL for the sys files for unopened channels") Cc: stable@vger.kernel.org Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Stephen Hemminger Signed-off-by: Dexuan Cui Signed-off-by: Sasha Levin --- include/linux/hyperv.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f0885cc01db6..dcb6977afce9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1159,8 +1159,9 @@ struct hv_ring_buffer_debug_info { u32 bytes_avail_towrite; }; -void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, - struct hv_ring_buffer_debug_info *debug_info); + +int hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, + struct hv_ring_buffer_debug_info *debug_info); /* Vmbus interface */ #define vmbus_driver_register(driver) \ -- cgit v1.2.3 From 321c46b91550adc03054125fa7a1639390608e1a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 3 Jan 2019 08:34:17 +0100 Subject: MIPS: BCM47XX: Setup struct device for the SoC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So far we never had any device registered for the SoC. This resulted in some small issues that we kept ignoring like: 1) Not working GPIOLIB_IRQCHIP (gpiochip_irqchip_add_key() failing) 2) Lack of proper tree in the /sys/devices/ 3) mips_dma_alloc_coherent() silently handling empty coherent_dma_mask Kernel 4.19 came with a lot of DMA changes and caused a regression on bcm47xx. Starting with the commit f8c55dc6e828 ("MIPS: use generic dma noncoherent ops for simple noncoherent platforms") DMA coherent allocations just fail. Example: [ 1.114914] bgmac_bcma bcma0:2: Allocation of TX ring 0x200 failed [ 1.121215] bgmac_bcma bcma0:2: Unable to alloc memory for DMA [ 1.127626] bgmac_bcma: probe of bcma0:2 failed with error -12 [ 1.133838] bgmac_bcma: Broadcom 47xx GBit MAC driver loaded The bgmac driver also triggers a WARNING: [ 0.959486] ------------[ cut here ]------------ [ 0.964387] WARNING: CPU: 0 PID: 1 at ./include/linux/dma-mapping.h:516 bgmac_enet_probe+0x1b4/0x5c4 [ 0.973751] Modules linked in: [ 0.976913] CPU: 0 PID: 1 Comm: swapper Not tainted 4.19.9 #0 [ 0.982750] Stack : 804a0000 804597c4 00000000 00000000 80458fd8 8381bc2c 838282d4 80481a47 [ 0.991367] 8042e3ec 00000001 804d38f0 00000204 83980000 00000065 8381bbe0 6f55b24f [ 0.999975] 00000000 00000000 80520000 00002018 00000000 00000075 00000007 00000000 [ 1.008583] 00000000 80480000 000ee811 00000000 00000000 00000000 80432c00 80248db8 [ 1.017196] 00000009 00000204 83980000 803ad7b0 00000000 801feeec 00000000 804d0000 [ 1.025804] ... [ 1.028325] Call Trace: [ 1.030875] [<8000aef8>] show_stack+0x58/0x100 [ 1.035513] [<8001f8b4>] __warn+0xe4/0x118 [ 1.039708] [<8001f9a4>] warn_slowpath_null+0x48/0x64 [ 1.044935] [<80248db8>] bgmac_enet_probe+0x1b4/0x5c4 [ 1.050101] [<802498e0>] bgmac_probe+0x558/0x590 [ 1.054906] [<80252fd0>] bcma_device_probe+0x38/0x70 [ 1.060017] [<8020e1e8>] really_probe+0x170/0x2e8 [ 1.064891] [<8020e714>] __driver_attach+0xa4/0xec [ 1.069784] [<8020c1e0>] bus_for_each_dev+0x58/0xb0 [ 1.074833] [<8020d590>] bus_add_driver+0xf8/0x218 [ 1.079731] [<8020ef24>] driver_register+0xcc/0x11c [ 1.084804] [<804b54cc>] bgmac_init+0x1c/0x44 [ 1.089258] [<8000121c>] do_one_initcall+0x7c/0x1a0 [ 1.094343] [<804a1d34>] kernel_init_freeable+0x150/0x218 [ 1.099886] [<803a082c>] kernel_init+0x10/0x104 [ 1.104583] [<80005878>] ret_from_kernel_thread+0x14/0x1c [ 1.110107] ---[ end trace f441c0d873d1fb5b ]--- This patch setups a "struct device" (and passes it to the bcma) which allows fixing all the mentioned problems. It'll also require a tiny bcma patch which will follow through the wireless tree & its maintainer. Fixes: f8c55dc6e828 ("MIPS: use generic dma noncoherent ops for simple noncoherent platforms") Signed-off-by: Rafał Miłecki Signed-off-by: Paul Burton Acked-by: Hauke Mehrtens Cc: Christoph Hellwig Cc: Linus Walleij Cc: linux-wireless@vger.kernel.org Cc: Ralf Baechle Cc: James Hogan Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v4.19+ --- include/linux/bcma/bcma_soc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bcma/bcma_soc.h b/include/linux/bcma/bcma_soc.h index 7cca5f859a90..f3c43519baa7 100644 --- a/include/linux/bcma/bcma_soc.h +++ b/include/linux/bcma/bcma_soc.h @@ -6,6 +6,7 @@ struct bcma_soc { struct bcma_bus bus; + struct device *dev; }; int __init bcma_host_soc_register(struct bcma_soc *soc); -- cgit v1.2.3 From ee46967fc6e74d412fe1ec15f77fdb8624bde2b0 Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Wed, 9 Jan 2019 13:50:18 +1000 Subject: HID: core: replace the collection tree pointers with indices Previously, the pointer to the parent collection was stored. If a device exceeds 16 collections (HID_DEFAULT_NUM_COLLECTIONS), the array to store the collections is reallocated, the pointer to the parent collection becomes invalid. Replace the pointers with an index-based lookup into the collections array. Fixes: c53431eb696f3c ("HID: core: store the collections as a basic tree") Reported-by: Pandruvada, Srinivas Signed-off-by: Peter Hutterer Tested-by: Kyle Pelton Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index d99287327ef2..992bbb7196df 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -430,7 +430,7 @@ struct hid_local { */ struct hid_collection { - struct hid_collection *parent; + int parent_idx; /* device->collection */ unsigned type; unsigned usage; unsigned level; @@ -658,7 +658,7 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; - struct hid_collection *active_collection; + int active_collection_idx; /* device->collection */ struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From 8ce5f84157530ffa64b3e0acf00b9261f41c8da8 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Tue, 11 Dec 2018 14:31:05 -0600 Subject: of: Remove struct device_node.type pointer Now that all users of device_node.type pointer have been removed in favor of accessor functions, we can remove it. Cc: Frank Rowand Cc: devicetree@vger.kernel.org Signed-off-by: Rob Herring --- include/linux/of.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/of.h b/include/linux/of.h index fe472e5195a9..e240992e5cb6 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -50,7 +50,6 @@ struct of_irq_controller; struct device_node { const char *name; - const char *type; phandle phandle; const char *full_name; struct fwnode_handle fwnode; -- cgit v1.2.3 From 10f4e765879e514e1ce7f52ed26603047af196e2 Mon Sep 17 00:00:00 2001 From: wenxu Date: Thu, 10 Jan 2019 14:51:35 +0800 Subject: netfilter: nft_flow_offload: fix interaction with vrf slave device In the forward chain, the iif is changed from slave device to master vrf device. Thus, flow offload does not find a match on the lower slave device. This patch uses the cached route, ie. dst->dev, to update the iif and oif fields in the flow entry. After this patch, the following example works fine: # ip addr add dev eth0 1.1.1.1/24 # ip addr add dev eth1 10.0.0.1/24 # ip link add user1 type vrf table 1 # ip l set user1 up # ip l set dev eth0 master user1 # ip l set dev eth1 master user1 # nft add table firewall # nft add flowtable f fb1 { hook ingress priority 0 \; devices = { eth0, eth1 } \; } # nft add chain f ftb-all {type filter hook forward priority 0 \; policy accept \; } # nft add rule f ftb-all ct zone 1 ip protocol tcp flow offload @fb1 # nft add rule f ftb-all ct zone 1 ip protocol udp flow offload @fb1 Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 7d5cda7ce32a..3e370cb36263 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -84,7 +84,6 @@ struct flow_offload { struct nf_flow_route { struct { struct dst_entry *dst; - int ifindex; } tuple[FLOW_OFFLOAD_DIR_MAX]; }; -- cgit v1.2.3 From 6325e01b6cdf4636b721cf7259c1616e3cf28ce2 Mon Sep 17 00:00:00 2001 From: Adit Ranadive Date: Wed, 9 Jan 2019 23:08:49 +0000 Subject: RDMA/vmw_pvrdma: Return the correct opcode when creating WR Since the IB_WR_REG_MR opcode value changed, let's set the PVRDMA device opcodes explicitly. Reported-by: Ruishuang Wang Fixes: 9a59739bd01f ("IB/rxe: Revise the ib_wr_opcode enum") Cc: stable@vger.kernel.org Reviewed-by: Bryan Tan Reviewed-by: Ruishuang Wang Reviewed-by: Vishnu Dasa Signed-off-by: Adit Ranadive Signed-off-by: Jason Gunthorpe --- include/uapi/rdma/vmw_pvrdma-abi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/rdma/vmw_pvrdma-abi.h b/include/uapi/rdma/vmw_pvrdma-abi.h index d13fd490b66d..6e73f0274e41 100644 --- a/include/uapi/rdma/vmw_pvrdma-abi.h +++ b/include/uapi/rdma/vmw_pvrdma-abi.h @@ -78,6 +78,7 @@ enum pvrdma_wr_opcode { PVRDMA_WR_MASKED_ATOMIC_FETCH_AND_ADD, PVRDMA_WR_BIND_MW, PVRDMA_WR_REG_SIG_MR, + PVRDMA_WR_ERROR, }; enum pvrdma_wc_status { -- cgit v1.2.3 From c13295ad219d8bb0e47942d4cfc8251de449a67e Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 11 Jan 2019 00:25:41 +0100 Subject: binderfs: rename header to binderfs.h It doesn't make sense to call the header binder_ctl.h when its sole existence is tied to binderfs. So give it a sensible name. Users will far more easily remember binderfs.h than binder_ctl.h. Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder_ctl.h | 35 --------------------------------- include/uapi/linux/android/binderfs.h | 35 +++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+), 35 deletions(-) delete mode 100644 include/uapi/linux/android/binder_ctl.h create mode 100644 include/uapi/linux/android/binderfs.h (limited to 'include') diff --git a/include/uapi/linux/android/binder_ctl.h b/include/uapi/linux/android/binder_ctl.h deleted file mode 100644 index 65b2efd1a0a5..000000000000 --- a/include/uapi/linux/android/binder_ctl.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (C) 2018 Canonical Ltd. - * - */ - -#ifndef _UAPI_LINUX_BINDER_CTL_H -#define _UAPI_LINUX_BINDER_CTL_H - -#include -#include -#include - -#define BINDERFS_MAX_NAME 255 - -/** - * struct binderfs_device - retrieve information about a new binder device - * @name: the name to use for the new binderfs binder device - * @major: major number allocated for binderfs binder devices - * @minor: minor number allocated for the new binderfs binder device - * - */ -struct binderfs_device { - char name[BINDERFS_MAX_NAME + 1]; - __u8 major; - __u8 minor; -}; - -/** - * Allocate a new binder device. - */ -#define BINDER_CTL_ADD _IOWR('b', 1, struct binderfs_device) - -#endif /* _UAPI_LINUX_BINDER_CTL_H */ - diff --git a/include/uapi/linux/android/binderfs.h b/include/uapi/linux/android/binderfs.h new file mode 100644 index 000000000000..65b2efd1a0a5 --- /dev/null +++ b/include/uapi/linux/android/binderfs.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2018 Canonical Ltd. + * + */ + +#ifndef _UAPI_LINUX_BINDER_CTL_H +#define _UAPI_LINUX_BINDER_CTL_H + +#include +#include +#include + +#define BINDERFS_MAX_NAME 255 + +/** + * struct binderfs_device - retrieve information about a new binder device + * @name: the name to use for the new binderfs binder device + * @major: major number allocated for binderfs binder devices + * @minor: minor number allocated for the new binderfs binder device + * + */ +struct binderfs_device { + char name[BINDERFS_MAX_NAME + 1]; + __u8 major; + __u8 minor; +}; + +/** + * Allocate a new binder device. + */ +#define BINDER_CTL_ADD _IOWR('b', 1, struct binderfs_device) + +#endif /* _UAPI_LINUX_BINDER_CTL_H */ + -- cgit v1.2.3 From 2e746942ebacf1565caa72cf980745e5ce297c48 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Sun, 13 Jan 2019 22:28:05 -0800 Subject: Input: input_event - provide override for sparc64 The usec part of the timeval is defined as __kernel_suseconds_t tv_usec; /* microseconds */ Arnd noticed that sparc64 is the only architecture that defines __kernel_suseconds_t as int rather than long. This breaks the current y2038 fix for kernel as we only access and define the timeval struct for non-kernel use cases. But, this was hidden by an another typo in the use of __KERNEL__ qualifier. Fix the typo, and provide an override for sparc64. Fixes: 152194fe9c3f ("Input: extend usable life of event timestamps to 2106 on 32 bit systems") Reported-by: Arnd Bergmann Signed-off-by: Deepa Dinamani Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 7288a7c573cc..551866a4f658 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -26,13 +26,17 @@ */ struct input_event { -#if (__BITS_PER_LONG != 32 || !defined(__USE_TIME_BITS64)) && !defined(__KERNEL) +#if (__BITS_PER_LONG != 32 || !defined(__USE_TIME_BITS64)) && !defined(__KERNEL__) struct timeval time; #define input_event_sec time.tv_sec #define input_event_usec time.tv_usec #else __kernel_ulong_t __sec; +#ifdef CONFIG_SPARC64 + unsigned int __usec; +#else __kernel_ulong_t __usec; +#endif #define input_event_sec __sec #define input_event_usec __usec #endif -- cgit v1.2.3 From 19ba9ecf24189bd74d070aa1b1c4bcb9fe4ae849 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 14 Jan 2019 11:40:47 +0300 Subject: XArray: Fix typo in comment Seems copy and paste typo, not a big deal but still for consistency sake better to fix. Signed-off-by: Cyrill Gorcunov Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 12244aa98a69..7da665f5cb20 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -496,7 +496,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, } /** - * xa_store_irq() - Erase this entry from the XArray. + * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. -- cgit v1.2.3 From 09ac6a817bd687e7f5dac00470262efdd72f9319 Mon Sep 17 00:00:00 2001 From: Curtis Malainey Date: Thu, 10 Jan 2019 16:21:04 -0800 Subject: ASoC: soc-core: fix init platform memory handling snd_soc_init_platform initializes pointers to snd_soc_dai_link which is statically allocated and it does this by devm_kzalloc. In the event of an EPROBE_DEFER the memory will be freed and the pointers are left dangling. snd_soc_init_platform sees the dangling pointers and assumes they are pointing to initialized memory and does not reallocate them on the second probe attempt which results in a use after free bug since devm has freed the memory from the first probe attempt. Since the intention for snd_soc_dai_link->platform is that it can be set statically by the machine driver we need to respect the pointer in the event we did not set it but still catch dangling pointers. The solution is to add a flag to track whether the pointer was dynamically allocated or not. Signed-off-by: Curtis Malainey Signed-off-by: Mark Brown --- include/sound/soc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/sound/soc.h b/include/sound/soc.h index 8ec1de856ee7..e665f111b0d2 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -985,6 +985,12 @@ struct snd_soc_dai_link { /* Do not create a PCM for this DAI link (Backend link) */ unsigned int ignore:1; + /* + * This driver uses legacy platform naming. Set by the core, machine + * drivers should not modify this value. + */ + unsigned int legacy_platform:1; + struct list_head list; /* DAI link list of the soc card */ struct snd_soc_dobj dobj; /* For topology */ }; -- cgit v1.2.3 From b89a07c4373b27321b1f6d4b4fdc369fd45ef79d Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 3 Jan 2019 17:08:03 +0100 Subject: virtio: fix virtio_config_ops description - get_features has returned 64 bits since commit d025477368792 ("virtio: add support for 64 bit features.") - properly mark all optional callbacks Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin Reviewed-by: Halil Pasic --- include/linux/virtio_config.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 32baf8e26735..7087ef946ba7 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -22,7 +22,7 @@ struct irq_affinity; * offset: the offset of the configuration field * buf: the buffer to read the field value from. * len: the length of the buffer - * @generation: config generation counter + * @generation: config generation counter (optional) * vdev: the virtio_device * Returns the config generation counter * @get_status: read the status byte @@ -48,17 +48,17 @@ struct irq_affinity; * @del_vqs: free virtqueues found by find_vqs(). * @get_features: get the array of feature bits for this device. * vdev: the virtio_device - * Returns the first 32 feature bits (all we currently need). + * Returns the first 64 feature bits (all we currently need). * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device * This gives the final feature bits for the device: it can change * the dev->feature bits if it wants. * Returns 0 on success or error status - * @bus_name: return the bus name associated with the device + * @bus_name: return the bus name associated with the device (optional) * vdev: the virtio_device * This returns a pointer to the bus name a la pci_name from which * the caller can then copy. - * @set_vq_affinity: set the affinity for a virtqueue. + * @set_vq_affinity: set the affinity for a virtqueue (optional). * @get_vq_affinity: get the affinity for a virtqueue (optional). */ typedef void vq_callback_t(struct virtqueue *); -- cgit v1.2.3 From d1c1dad89e7a8be2cfdc7b92deca2c8048f0d263 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Thu, 3 Jan 2019 17:08:04 +0100 Subject: virtio: document virtio_config_ops restrictions Some transports (e.g. virtio-ccw) implement virtio operations that seem to be a simple read/write as something more involved that cannot be done from an atomic context. Give at least a hint about that. Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 7087ef946ba7..987b6491b946 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -12,6 +12,11 @@ struct irq_affinity; /** * virtio_config_ops - operations for configuring a virtio device + * Note: Do not assume that a transport implements all of the operations + * getting/setting a value as a simple read/write! Generally speaking, + * any of @get/@set, @get_status/@set_status, or @get_features/ + * @finalize_features are NOT safe to be called from an atomic + * context. * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field -- cgit v1.2.3 From f97f4dd8b3bb9d0993d2491e0f22024c68109184 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 9 Jan 2019 09:57:39 +0000 Subject: net: ipv4: Fix memory leak in network namespace dismantle IPv4 routing tables are flushed in two cases: 1. In response to events in the netdev and inetaddr notification chains 2. When a network namespace is being dismantled In both cases only routes associated with a dead nexthop group are flushed. However, a nexthop group will only be marked as dead in case it is populated with actual nexthops using a nexthop device. This is not the case when the route in question is an error route (e.g., 'blackhole', 'unreachable'). Therefore, when a network namespace is being dismantled such routes are not flushed and leaked [1]. To reproduce: # ip netns add blue # ip -n blue route add unreachable 192.0.2.0/24 # ip netns del blue Fix this by not skipping error routes that are not marked with RTNH_F_DEAD when flushing the routing tables. To prevent the flushing of such routes in case #1, add a parameter to fib_table_flush() that indicates if the table is flushed as part of namespace dismantle or not. Note that this problem does not exist in IPv6 since error routes are associated with the loopback device. [1] unreferenced object 0xffff888066650338 (size 56): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 b0 1c 62 61 80 88 ff ff ..........ba.... e8 8b a1 64 80 88 ff ff 00 07 00 08 fe 00 00 00 ...d............ backtrace: [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff unreferenced object 0xffff888061621c88 (size 48): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b d8 8e 26 5f 80 88 ff ff kkkkkkkk..&_.... backtrace: [<00000000733609e3>] fib_table_insert+0x978/0x1500 [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff Fixes: 8cced9eff1d4 ("[NETNS]: Enable routing configuration in non-initial namespace.") Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c5969762a8f4..9c8214d2116d 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -241,7 +241,7 @@ int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); -int fib_table_flush(struct net *net, struct fib_table *table); +int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); -- cgit v1.2.3 From e122d845a01ece2ddd28b2f125ef2db66b8b627a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 10 Jan 2019 16:59:13 +0000 Subject: Revert "rxrpc: Allow failed client calls to be retried" The changes introduced to allow rxrpc calls to be retried creates an issue when it comes to refcounting afs_call structs. The problem is that when rxrpc_send_data() queues the last packet for an asynchronous call, the following sequence can occur: (1) The notify_end_tx callback is invoked which causes the state in the afs_call to be changed from AFS_CALL_CL_REQUESTING or AFS_CALL_SV_REPLYING. (2) afs_deliver_to_call() can then process event notifications from rxrpc on the async_work queue. (3) Delivery of events, such as an abort from the server, can cause the afs_call state to be changed to AFS_CALL_COMPLETE on async_work. (4) For an asynchronous call, afs_process_async_call() notes that the call is complete and tried to clean up all the refs on async_work. (5) rxrpc_send_data() might return the amount of data transferred (success) or an error - which could in turn reflect a local error or a received error. Synchronising the clean up after rxrpc_kernel_send_data() returns an error with the asynchronous cleanup is then tricky to get right. Mostly revert commit c038a58ccfd6704d4d7d60ed3d6a0fca13cf13a4. The two API functions the original commit added aren't currently used. This makes rxrpc_kernel_send_data() always return successfully if it queued the data it was given. Note that this doesn't affect synchronous calls since their Rx notification function merely pokes a wait queue and does not refcounting. The asynchronous call notification function *has* to do refcounting and pass a ref over the work item to avoid the need to sync the workqueue in call cleanup. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/net/af_rxrpc.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include') diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 1adefe42c0a6..2bfb87eb98ce 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -20,18 +20,6 @@ struct sock; struct socket; struct rxrpc_call; -/* - * Call completion condition (state == RXRPC_CALL_COMPLETE). - */ -enum rxrpc_call_completion { - RXRPC_CALL_SUCCEEDED, /* - Normal termination */ - RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ - RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ - RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ - RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ - NR__RXRPC_CALL_COMPLETIONS -}; - /* * Debug ID counter for tracing. */ @@ -73,10 +61,6 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); -int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *, - struct sockaddr_rxrpc *, struct key *); -int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *, - enum rxrpc_call_completion *, u32 *); u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *); u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); -- cgit v1.2.3 From f275ee0fa3a06eb87edc229749cf1eb18f0663fa Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 10 Jan 2019 21:24:13 +0100 Subject: IN_BADCLASS: fix macro to actually work Commit 65cab850f0ee ("net: Allow class-e address assignment via ifconfig ioctl") modified the IN_BADCLASS macro a bit, but unfortunatly one too many '(' characters were added to the line, making any code that used it, not build properly. Also, the macro now compares an unsigned with a signed value, which isn't ok, so fix that up by making both types match properly. Reported-by: Christopher Ferris Fixes: 65cab850f0ee ("net: Allow class-e address assignment via ifconfig ioctl") Cc: Dave Taht Signed-off-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index f6052e70bf40..a55cb8b10165 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -268,7 +268,7 @@ struct sockaddr_in { #define IN_MULTICAST(a) IN_CLASSD(a) #define IN_MULTICAST_NET 0xe0000000 -#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) #define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) #define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) -- cgit v1.2.3 From 1950f462916edc9581168ca8d5882a8101e8bbcf Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 14 Jan 2019 08:19:22 +0100 Subject: HID: core: simplify active collection tracking Manually tracking an active collection to set collection parents is not necessary, we just have to look one step back into the collection stack to find the correct parent. Signed-off-by: Philipp Zabel Reviewed-by: Peter Hutterer Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/hid.h b/include/linux/hid.h index 992bbb7196df..f9707d1dcb58 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -658,7 +658,6 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; - int active_collection_idx; /* device->collection */ struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From 890d14d2d4b57ff5a149309da3ed36c8a529987f Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Wed, 16 Jan 2019 17:42:35 +0100 Subject: fbdev: fbmem: convert CONFIG_FB_LOGO_CENTER into a cmd line option A command line option is much more flexible than a config option and the supporting code is small. Gets rid of #ifdefs in the code too... Suggested-by: Geert Uytterhoeven Cc: Jonathan Corbet Signed-off-by: Peter Rosin Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/fb.h b/include/linux/fb.h index 7cdd31a69719..f52ef0ad6781 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -653,6 +653,7 @@ extern int fb_new_modelist(struct fb_info *info); extern struct fb_info *registered_fb[FB_MAX]; extern int num_registered_fb; +extern bool fb_center_logo; extern struct class *fb_class; #define for_each_registered_fb(i) \ -- cgit v1.2.3 From 3705add0b783e0deeb6646ba0311bf214fe52b0a Mon Sep 17 00:00:00 2001 From: Jerome Brunet Date: Wed, 16 Jan 2019 11:36:32 +0100 Subject: dt-bindings: reset: meson-axg: fix SPDX license id As reported, the SPDX license id is not placed correctly and the variant of the BSD License used should be specified. Fixes: c16292578ffa ("dt-bindings: reset: Add bindings for the Meson-AXG SoC Reset Controller") Reported-by: Thomas Gleixner Signed-off-by: Jerome Brunet Reviewed-by: Thomas Gleixner Signed-off-by: Rob Herring --- include/dt-bindings/reset/amlogic,meson-axg-reset.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/dt-bindings/reset/amlogic,meson-axg-reset.h b/include/dt-bindings/reset/amlogic,meson-axg-reset.h index ad6f55dabd6d..0f2e0fe45ca4 100644 --- a/include/dt-bindings/reset/amlogic,meson-axg-reset.h +++ b/include/dt-bindings/reset/amlogic,meson-axg-reset.h @@ -1,12 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* - * * Copyright (c) 2016 BayLibre, SAS. * Author: Neil Armstrong * * Copyright (c) 2017 Amlogic, inc. * Author: Yixun Lan * - * SPDX-License-Identifier: (GPL-2.0+ OR BSD) */ #ifndef _DT_BINDINGS_AMLOGIC_MESON_AXG_RESET_H -- cgit v1.2.3 From 9e857a40dc4eba15a739b4194d7db873d82c28a0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 15 Jan 2019 16:55:30 +0100 Subject: net: phy: Add missing features to PHY drivers The bcm87xx and micrel driver has PHYs which are missing the .features value. Add them. The bcm87xx is a 10G FEC only PHY. Add the needed features definition of this PHY. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Reported-by: Scott Wood Reported-by: Camelia Groza Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b051f761450..55114657a577 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -48,6 +48,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) @@ -56,6 +57,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) +#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) extern const int phy_10_100_features_array[4]; -- cgit v1.2.3 From edcddd4c879af48ec922d680b2d56834c085683b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 17 Jan 2019 07:15:35 -0500 Subject: XArray: Fix an arithmetic error in xa_is_err There is a math problem here which leads to a lot of static checker warnings for me: net/sunrpc/clnt.c:451 rpc_new_client() error: (-4096) too low for ERR_PTR Error values are from -1 to -4095 or from 0xffffffff to 0xfffff001 in hexadecimal. (I am assuming a 32 bit system for simplicity). We are using the lowest two bits to hold some internal XArray data so the error is shifted two spaces to the left. 0xfffff001 << 2 is 0xffffc004. And finally we want to check that BIT(1) is set so we add 2 which gives us 0xffffc006. In other words, we should be checking that "entry >= 0xffffc006", but the check is actually testing if "entry >= 0xffffc002". Fixes: 76b4e5299565 ("XArray: Permit storing 2-byte-aligned pointers") Signed-off-by: Dan Carpenter [Use xa_mk_internal() instead of changing the bracketing] Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 7da665f5cb20..5d9d318bcf7a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -177,7 +177,7 @@ static inline bool xa_is_internal(const void *entry) static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && - (unsigned long)entry >= -((MAX_ERRNO << 2) + 2)); + entry >= xa_mk_internal(-MAX_ERRNO)); } /** -- cgit v1.2.3 From 34fa47612bfe5d7de7fcaf658a6952b6aeec3b13 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 10 Jan 2019 15:40:50 +0000 Subject: afs: Fix race in async call refcounting There's a race between afs_make_call() and afs_wake_up_async_call() in the case that an error is returned from rxrpc_kernel_send_data() after it has queued the final packet. afs_make_call() will try and clean up the mess, but the call state may have been moved on thereby causing afs_process_async_call() to also try and to delete the call. Fix this by: (1) Getting an extra ref for an asynchronous call for the call itself to hold. This makes sure the call doesn't evaporate on us accidentally and will allow the call to be retained by the caller in a future patch. The ref is released on leaving afs_make_call() or afs_wait_for_call_to_complete(). (2) In the event of an error from rxrpc_kernel_send_data(): (a) Don't set the call state to AFS_CALL_COMPLETE until *after* the call has been aborted and ended. This prevents afs_deliver_to_call() from doing anything with any notifications it gets. (b) Explicitly end the call immediately to prevent further callbacks. (c) Cancel any queued async_work and wait for the work if it's executing. This allows us to be sure the race won't recur when we change the state. We put the work queue's ref on the call if we managed to cancel it. (d) Put the call's ref that we got in (1). This belongs to us as long as the call is in state AFS_CALL_CL_REQUESTING. Fixes: 341f741f04be ("afs: Refcount the afs_call struct") Signed-off-by: David Howells --- include/trace/events/afs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 33d291888ba9..e3f005eae1f7 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -25,6 +25,7 @@ enum afs_call_trace { afs_call_trace_alloc, afs_call_trace_free, + afs_call_trace_get, afs_call_trace_put, afs_call_trace_wake, afs_call_trace_work, @@ -159,6 +160,7 @@ enum afs_file_error { #define afs_call_traces \ EM(afs_call_trace_alloc, "ALLOC") \ EM(afs_call_trace_free, "FREE ") \ + EM(afs_call_trace_get, "GET ") \ EM(afs_call_trace_put, "PUT ") \ EM(afs_call_trace_wake, "WAKE ") \ E_(afs_call_trace_work, "WORK ") -- cgit v1.2.3 From 70921ae25f944423f0abf096f73455c586da0652 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 8 Jan 2019 17:04:32 -0700 Subject: genirq: Fix the kerneldoc comment for struct irq_affinity_desc A recent commit added a new field but did not update the kerneldoc comment, leading to this build warning: ./include/linux/interrupt.h:268: warning: Function parameter or member 'is_managed' not described in 'irq_affinity_desc' Add the missing information, making the docs build 0.001% quieter. Fixes: c410abbbacb9 ("genirq/affinity: Add is_managed to struct irq_affinity_desc") Signed-off-by: Jonathan Corbet Signed-off-by: Thomas Gleixner Cc: Dou Liyang Link: https://lkml.kernel.org/r/20190108170432.59bae8a6@lwn.net --- include/linux/interrupt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c672f34235e7..4a728dba02e2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -260,6 +260,7 @@ struct irq_affinity { /** * struct irq_affinity_desc - Interrupt affinity descriptor * @mask: cpumask to hold the affinity assignment + * @is_managed: 1 if the interrupt is managed internally */ struct irq_affinity_desc { struct cpumask mask; -- cgit v1.2.3 From d152159b89118841ebc0f7be2aadf79a22c6c501 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jan 2019 15:45:58 +0100 Subject: netfilter: nf_tables: prepare nft_object for lookups via hashtable Add a 'key' structure for object, so we can look them up by name + table combination (the name can be the same in each table). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 841835a387e1..325d0a6b808b 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1011,12 +1011,22 @@ void nft_unregister_expr(struct nft_expr_type *); int nft_verdict_dump(struct sk_buff *skb, int type, const struct nft_verdict *v); +/** + * struct nft_object_hash_key - key to lookup nft_object + * + * @name: name of the stateful object to look up + * @table: table the object belongs to + */ +struct nft_object_hash_key { + const char *name; + const struct nft_table *table; +}; + /** * struct nft_object - nf_tables stateful object * * @list: table stateful object list node - * @table: table this object belongs to - * @name: name of this stateful object + * @key: keys that identify this object * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle @@ -1025,8 +1035,7 @@ int nft_verdict_dump(struct sk_buff *skb, int type, */ struct nft_object { struct list_head list; - char *name; - struct nft_table *table; + struct nft_object_hash_key key; u32 genmask:2, use:30; u64 handle; @@ -1047,7 +1056,7 @@ struct nft_object *nft_obj_lookup(const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); -void nft_obj_notify(struct net *net, struct nft_table *table, +void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp); -- cgit v1.2.3 From 4d44175aa5bb5f68772b1eb0306554812294ca52 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jan 2019 15:45:59 +0100 Subject: netfilter: nf_tables: handle nft_object lookups via rhltable Instead of linear search, use rhlist interface to look up the objects. This fixes rulesets with thousands of named objects (quota, counters and the like). We only use a single table for this and consider the address of the table we're doing the lookup in as a part of the key. This reduces restore time of a sample ruleset with ~20k named counters from 37 seconds to 0.8 seconds. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 325d0a6b808b..45eba7d7ab38 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1027,14 +1027,16 @@ struct nft_object_hash_key { * * @list: table stateful object list node * @key: keys that identify this object + * @rhlhead: nft_objname_ht node * @genmask: generation mask * @use: number of references to this stateful object * @handle: unique object handle * @ops: object operations - * @data: object data, layout depends on type + * @data: object data, layout depends on type */ struct nft_object { struct list_head list; + struct rhlist_head rhlhead; struct nft_object_hash_key key; u32 genmask:2, use:30; @@ -1052,7 +1054,8 @@ static inline void *nft_obj_data(const struct nft_object *obj) #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) -struct nft_object *nft_obj_lookup(const struct nft_table *table, +struct nft_object *nft_obj_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask); -- cgit v1.2.3 From 10870dd89e956d911d1a39474c0bf4a18c72cffc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jan 2019 17:35:34 +0100 Subject: netfilter: nf_tables: add direct calls for all builtin expressions With CONFIG_RETPOLINE its faster to add an if (ptr == &foo_func) check and and use direct calls for all the built-in expressions. ~15% improvement in pathological cases. checkpatch doesn't like the X macro due to the embedded return statement, but the macro has a very limited scope so I don't think its a problem. I would like to avoid bugs of the form If (e->ops->eval == (unsigned long)nft_foo_eval) nft_bar_eval(); and open-coded if ()/else if()/else cascade, thus the macro. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 2046d104f323..7281895fa6d9 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -80,6 +80,22 @@ struct nft_regs; struct nft_pktinfo; void nft_meta_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_cmp_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_payload_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_immediate_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_bitwise_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_range_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_byteorder_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_dynset_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt); #endif /* _NET_NF_TABLES_CORE_H */ -- cgit v1.2.3 From 8e2f311a68494a6677c1724bdcb10bada21af37c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 11 Jan 2019 14:46:15 +0100 Subject: netfilter: physdev: relax br_netfilter dependency Following command: iptables -D FORWARD -m physdev ... causes connectivity loss in some setups. Reason is that iptables userspace will probe kernel for the module revision of the physdev patch, and physdev has an artificial dependency on br_netfilter (xt_physdev use makes no sense unless a br_netfilter module is loaded). This causes the "phydev" module to be loaded, which in turn enables the "call-iptables" infrastructure. bridged packets might then get dropped by the iptables ruleset. The better fix would be to change the "call-iptables" defaults to 0 and enforce explicit setting to 1, but that breaks backwards compatibility. This does the next best thing: add a request_module call to checkentry. This was a stray '-D ... -m physdev' won't activate br_netfilter anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/br_netfilter.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 4cd56808ac4e..89808ce293c4 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -43,7 +43,6 @@ static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) } struct net_device *setup_pre_routing(struct sk_buff *skb); -void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) int br_validate_ipv6(struct net *net, struct sk_buff *skb); -- cgit v1.2.3 From 75dd48e2e420a3cbbe56dd7adfcc6f142c948272 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Mon, 14 Jan 2019 18:41:35 +0100 Subject: netfilter: nf_tables: Support RULE_ID reference in new rule To allow for a batch to contain rules in arbitrary ordering, introduce NFTA_RULE_POSITION_ID attribute which works just like NFTA_RULE_POSITION but contains the ID of another rule within the same batch. This helps iptables-nft-restore handling dumps with mixed insert/append commands correctly. Note that NFTA_RULE_POSITION takes precedence over NFTA_RULE_POSITION_ID, so if the former is present, the latter is ignored. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 7de4f1bdaf06..99ca95b830b6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -219,6 +219,7 @@ enum nft_chain_attributes { * @NFTA_RULE_POSITION: numeric handle of the previous rule (NLA_U64) * @NFTA_RULE_USERDATA: user data (NLA_BINARY, NFT_USERDATA_MAXLEN) * @NFTA_RULE_ID: uniquely identifies a rule in a transaction (NLA_U32) + * @NFTA_RULE_POSITION_ID: transaction unique identifier of the previous rule (NLA_U32) */ enum nft_rule_attributes { NFTA_RULE_UNSPEC, @@ -231,6 +232,7 @@ enum nft_rule_attributes { NFTA_RULE_USERDATA, NFTA_RULE_PAD, NFTA_RULE_ID, + NFTA_RULE_POSITION_ID, __NFTA_RULE_MAX }; #define NFTA_RULE_MAX (__NFTA_RULE_MAX - 1) -- cgit v1.2.3 From a47c5404816254d6cc4787f335c4720066a538e6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:32 +0100 Subject: netfilter: conntrack: handle builtin l4proto packet functions via direct calls The l4 protocol trackers are invoked via indirect call: l4proto->packet(). With one exception (gre), all l4trackers are builtin, so we can make .packet optional and use a direct call for most protocols. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 37 ++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index ae7b86f587f2..6ca4355ae3dc 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -99,6 +99,43 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state); + +int nf_conntrack_icmp_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); + +int nf_conntrack_icmpv6_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); + +int nf_conntrack_udp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_udplite_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_tcp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_dccp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); +int nf_conntrack_sctp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); + /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; -- cgit v1.2.3 From e2e48b471634faa6958718c27208d366b13fe878 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:33 +0100 Subject: netfilter: conntrack: handle icmp pkt_to_tuple helper via direct calls rather than handling them via indirect call, use a direct one instead. This leaves GRE as the last user of this indirect call facility. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6ca4355ae3dc..46d554806eb3 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -90,6 +90,16 @@ struct nf_conntrack_l4proto { struct module *me; }; +bool icmp_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple); + +bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, -- cgit v1.2.3 From 202e651cd43c69a43f75b445e90f55b59f9af0ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:34 +0100 Subject: netfilter: conntrack: gre: convert rwlock to rcu We can use gre. Lock is only needed when a new expectation is added. In case a single spinlock proves to be problematic we can either add one per netns or use an array of locks combined with net_hash_mix() or similar to pick the 'correct' one. But given this is only needed for an expectation rather than per packet a single one should be ok. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 6989e2e4eabf..222c9d3d453f 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -19,6 +19,7 @@ struct nf_conn; struct nf_ct_gre_keymap { struct list_head list; struct nf_conntrack_tuple tuple; + struct rcu_head rcu; }; enum grep_conntrack { -- cgit v1.2.3 From 22fc4c4c9fd60427bcda00878cee94e7622cfa7a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:35 +0100 Subject: netfilter: conntrack: gre: switch module to be built-in This makes the last of the modular l4 trackers 'bool'. After this, all infrastructure to handle dynamic l4 protocol registration becomes obsolete and can be removed in followup patches. Old: 302824 net/netfilter/nf_conntrack.ko 21504 net/netfilter/nf_conntrack_proto_gre.ko New: 313728 net/netfilter/nf_conntrack.ko Old: text data bss dec hex filename 6281 1732 4 8017 1f51 nf_conntrack_proto_gre.ko 108356 20613 236 129205 1f8b5 nf_conntrack.ko New: 112095 21381 240 133716 20a54 nf_conntrack.ko The size increase is only temporary. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 14 +------------- include/net/netfilter/ipv4/nf_conntrack_ipv4.h | 3 +++ include/net/netfilter/nf_conntrack_l4proto.h | 7 +++++++ include/net/netns/conntrack.h | 17 +++++++++++++++++ 4 files changed, 28 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 222c9d3d453f..59714e9ee4ef 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -22,23 +22,11 @@ struct nf_ct_gre_keymap { struct rcu_head rcu; }; -enum grep_conntrack { - GRE_CT_UNREPLIED, - GRE_CT_REPLIED, - GRE_CT_MAX -}; - -struct netns_proto_gre { - struct nf_proto_net nf; - rwlock_t keymap_lock; - struct list_head keymap_list; - unsigned int gre_timeouts[GRE_CT_MAX]; -}; - /* add new tuple->key_reply pair to keymap */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); +void nf_ct_gre_keymap_flush(struct net *net); /* delete keymap entries */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 135ee702c7b0..2c8c2b023848 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -22,5 +22,8 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp; #ifdef CONFIG_NF_CT_PROTO_UDPLITE extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite; #endif +#ifdef CONFIG_NF_CT_PROTO_GRE +extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre; +#endif #endif /*_NF_CONNTRACK_IPV4_H*/ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 46d554806eb3..fded3f164dcc 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -239,4 +239,11 @@ static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) } #endif +#ifdef CONFIG_NF_CT_PROTO_GRE +static inline struct nf_gre_net *nf_gre_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.gre; +} +#endif + #endif /*_NF_CONNTRACK_PROTOCOL_H*/ diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 51cba0b8adf5..c72f413a2d4d 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -70,6 +70,20 @@ struct nf_sctp_net { }; #endif +#ifdef CONFIG_NF_CT_PROTO_GRE +enum gre_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +struct nf_gre_net { + struct nf_proto_net nf; + struct list_head keymap_list; + unsigned int timeouts[GRE_CT_MAX]; +}; +#endif + struct nf_ip_net { struct nf_generic_net generic; struct nf_tcp_net tcp; @@ -82,6 +96,9 @@ struct nf_ip_net { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net sctp; #endif +#ifdef CONFIG_NF_CT_PROTO_GRE + struct nf_gre_net gre; +#endif }; struct ct_pcpu { -- cgit v1.2.3 From 751fc301ecbd0fc08d4d6c388f170e2081df26e6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:36 +0100 Subject: netfilter: conntrack: remove net_id No users anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index fded3f164dcc..3585f8666fc0 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -79,7 +79,7 @@ struct nf_conntrack_l4proto { /* Print out the private part of the conntrack. */ void (*print_conntrack)(struct seq_file *s, struct nf_conn *); #endif - unsigned int *net_id; + /* Init l4proto pernet data */ int (*init_net)(struct net *net); -- cgit v1.2.3 From df5e1629087a45ca915fa0f69ea662175261855e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:37 +0100 Subject: netfilter: conntrack: remove pkt_to_tuple callback GRE is now builtin, so we can handle it via direct call and remove the callback. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_proto_gre.h | 2 ++ include/net/netfilter/nf_conntrack_l4proto.h | 5 ----- 2 files changed, 2 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index 59714e9ee4ef..25f9a770fb84 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -30,5 +30,7 @@ void nf_ct_gre_keymap_flush(struct net *net); /* delete keymap entries */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct); +bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple); #endif /* __KERNEL__ */ #endif /* _CONNTRACK_PROTO_GRE_H */ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 3585f8666fc0..0d4b0398aeb9 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,11 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Try to fill in the third arg: dataoff is offset past network protocol - hdr. Return true if possible. */ - bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple); - /* Invert the per-proto part of the tuple: ie. turn xmit into reply. * Only used by icmp, most protocols use a generic version. */ -- cgit v1.2.3 From 197c4300aec09b7cd2df124cea92f9f5a82efe42 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:38 +0100 Subject: netfilter: conntrack: remove invert_tuple callback Only used by icmp(v6). Prefer a direct call and remove this function from the l4proto struct. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 0d4b0398aeb9..6cec8337e684 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,12 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Invert the per-proto part of the tuple: ie. turn xmit into reply. - * Only used by icmp, most protocols use a generic version. - */ - bool (*invert_tuple)(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig); - /* Returns verdict for packet, or -1 for invalid. */ int (*packet)(struct nf_conn *ct, struct sk_buff *skb, @@ -95,6 +89,11 @@ bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, struct net *net, struct nf_conntrack_tuple *tuple); +bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig); +bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig); + int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, -- cgit v1.2.3 From b184356d0a003ac5e82b4adf37f2d334df1d213c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:39 +0100 Subject: netfilter: conntrack: remove module owner field No need to get/put module owner reference, none of these can be removed anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6cec8337e684..fd8954429e87 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -74,9 +74,6 @@ struct nf_conntrack_l4proto { /* Return the per-net protocol part. */ struct nf_proto_net *(*get_net_proto)(struct net *net); - - /* Module (if any) which this is connected to. */ - struct module *me; }; bool icmp_pkt_to_tuple(const struct sk_buff *skb, @@ -148,7 +145,6 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); -void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p); /* Protocol pernet registration. */ int nf_ct_l4proto_pernet_register_one(struct net *net, -- cgit v1.2.3 From 44fb87f6351d04fafae2b17df5f46f1ce22c6f93 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:40 +0100 Subject: netfilter: conntrack: remove remaining l4proto indirect packet calls Now that all l4trackers are builtin, no need to use a mix of direct and indirect calls. This removes the last two users: gre and the generic l4 protocol tracker. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index fd8954429e87..dda028996559 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,13 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Returns verdict for packet, or -1 for invalid. */ - int (*packet)(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state); - /* Called when a conntrack entry is destroyed */ void (*destroy)(struct nf_conn *ct); @@ -136,6 +129,11 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); +int nf_conntrack_gre_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state); /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; -- cgit v1.2.3 From edf0338dabf0f330873f7a9f84ea9f9ac431c0a8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:41 +0100 Subject: netfilter: conntrack: remove pernet l4 proto register interface No used anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index dda028996559..87d9c198c05e 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -144,18 +144,6 @@ const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); -/* Protocol pernet registration. */ -int nf_ct_l4proto_pernet_register_one(struct net *net, - const struct nf_conntrack_l4proto *proto); -void nf_ct_l4proto_pernet_unregister_one(struct net *net, - const struct nf_conntrack_l4proto *proto); -int nf_ct_l4proto_pernet_register(struct net *net, - const struct nf_conntrack_l4proto *const proto[], - unsigned int num_proto); -void nf_ct_l4proto_pernet_unregister(struct net *net, - const struct nf_conntrack_l4proto *const proto[], - unsigned int num_proto); - /* Protocol global registration. */ int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto); void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto); -- cgit v1.2.3 From 303e0c5589592e4f623bfcaf4292a1ed816328ad Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:42 +0100 Subject: netfilter: conntrack: avoid unneeded nf_conntrack_l4proto lookups after removal of the packet and invert function pointers, several places do not need to lookup the l4proto structure anymore. Remove those lookups. The function nf_ct_invert_tuplepr becomes redundant, replace it with nf_ct_invert_tuple everywhere. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 -- include/net/netfilter/nf_conntrack_core.h | 3 +-- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 249d0a5b12b8..b5aac5ae5129 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -187,8 +187,6 @@ bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, struct net *net, struct nf_conntrack_tuple *tuple); -bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig); void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct sk_buff *skb, diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index afc9b3620473..235c182022b2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -39,8 +39,7 @@ void nf_conntrack_init_end(void); void nf_conntrack_cleanup_end(void); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_l4proto *l4proto); + const struct nf_conntrack_tuple *orig); /* Find a connection corresponding to a tuple. */ struct nf_conntrack_tuple_hash * -- cgit v1.2.3 From 70aed4647cbd63e3371386ddfaeb195413f38d99 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:44 +0100 Subject: netfilter: conntrack: remove sysctl registration helpers After previous patch these are not used anymore. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netns/conntrack.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index c72f413a2d4d..b8faa72e0f5b 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -19,10 +19,6 @@ struct ctl_table_header; struct nf_conntrack_ecache; struct nf_proto_net { -#ifdef CONFIG_SYSCTL - struct ctl_table_header *ctl_table_header; - struct ctl_table *ctl_table; -#endif unsigned int users; }; -- cgit v1.2.3 From 2a389de86e4a5d0bd3abed9e6fee27050652d339 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:45 +0100 Subject: netfilter: conntrack: remove l4proto init and get_net callbacks Those were needed we still had modular trackers. As we don't have those anymore, prefer direct calls and remove all the (un)register infrastructure associated with this. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 15 +++++++++------ include/net/netns/conntrack.h | 11 ----------- 2 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 87d9c198c05e..d5909e51ca92 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -61,12 +61,6 @@ struct nf_conntrack_l4proto { /* Print out the private part of the conntrack. */ void (*print_conntrack)(struct seq_file *s, struct nf_conn *); #endif - - /* Init l4proto pernet data */ - int (*init_net)(struct net *net); - - /* Return the per-net protocol part. */ - struct nf_proto_net *(*get_net_proto)(struct net *net); }; bool icmp_pkt_to_tuple(const struct sk_buff *skb, @@ -135,6 +129,15 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state); +void nf_conntrack_generic_init_net(struct net *net); +void nf_conntrack_tcp_init_net(struct net *net); +void nf_conntrack_udp_init_net(struct net *net); +void nf_conntrack_gre_init_net(struct net *net); +void nf_conntrack_dccp_init_net(struct net *net); +void nf_conntrack_sctp_init_net(struct net *net); +void nf_conntrack_icmp_init_net(struct net *net); +void nf_conntrack_icmpv6_init_net(struct net *net); + /* Existing built-in generic protocol */ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index b8faa72e0f5b..f19b53130bf7 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -18,17 +18,11 @@ struct ctl_table_header; struct nf_conntrack_ecache; -struct nf_proto_net { - unsigned int users; -}; - struct nf_generic_net { - struct nf_proto_net pn; unsigned int timeout; }; struct nf_tcp_net { - struct nf_proto_net pn; unsigned int timeouts[TCP_CONNTRACK_TIMEOUT_MAX]; unsigned int tcp_loose; unsigned int tcp_be_liberal; @@ -42,18 +36,15 @@ enum udp_conntrack { }; struct nf_udp_net { - struct nf_proto_net pn; unsigned int timeouts[UDP_CT_MAX]; }; struct nf_icmp_net { - struct nf_proto_net pn; unsigned int timeout; }; #ifdef CONFIG_NF_CT_PROTO_DCCP struct nf_dccp_net { - struct nf_proto_net pn; int dccp_loose; unsigned int dccp_timeout[CT_DCCP_MAX + 1]; }; @@ -61,7 +52,6 @@ struct nf_dccp_net { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net { - struct nf_proto_net pn; unsigned int timeouts[SCTP_CONNTRACK_MAX]; }; #endif @@ -74,7 +64,6 @@ enum gre_conntrack { }; struct nf_gre_net { - struct nf_proto_net nf; struct list_head keymap_list; unsigned int timeouts[GRE_CT_MAX]; }; -- cgit v1.2.3 From e56894356f60f9d11bdf53ee5a050a235f6d2b48 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:46 +0100 Subject: netfilter: conntrack: remove l4proto destroy hook Only one user (gre), add a direct call and remove this facility. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_l4proto.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index d5909e51ca92..5d1419ac6a38 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -27,9 +27,6 @@ struct nf_conntrack_l4proto { /* protoinfo nlattr size, closes a hole */ u16 nlattr_size; - /* Called when a conntrack entry is destroyed */ - void (*destroy)(struct nf_conn *ct); - /* called by gc worker if table is full */ bool (*can_early_drop)(const struct nf_conn *ct); -- cgit v1.2.3 From 4a60dc748d121b52533a2956567df4f87a3835b1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 15 Jan 2019 22:03:47 +0100 Subject: netfilter: conntrack: remove nf_ct_l4proto_find_get Its now same as __nf_ct_l4proto_find(), so rename that to nf_ct_l4proto_find and use it everywhere. It never returns NULL and doesn't need locks or reference counts. Before this series: 302824 net/netfilter/nf_conntrack.ko 21504 net/netfilter/nf_conntrack_proto_gre.ko text data bss dec hex filename 6281 1732 4 8017 1f51 nf_conntrack_proto_gre.ko 108356 20613 236 129205 1f8b5 nf_conntrack.ko After: 294864 net/netfilter/nf_conntrack.ko text data bss dec hex filename 106979 19557 240 126776 1ef38 nf_conntrack.ko so, even with builtin gre, total size got reduced. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 2 +- include/net/netfilter/nf_conntrack_l4proto.h | 8 +------- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 235c182022b2..ae41e92251dd 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -26,7 +26,7 @@ int nf_conntrack_init_net(struct net *net); void nf_conntrack_cleanup_net(struct net *net); void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list); -int nf_conntrack_proto_pernet_init(struct net *net); +void nf_conntrack_proto_pernet_init(struct net *net); void nf_conntrack_proto_pernet_fini(struct net *net); int nf_conntrack_proto_init(void); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 5d1419ac6a38..778087591983 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -140,13 +140,7 @@ extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic; #define MAX_NF_CT_PROTO IPPROTO_UDPLITE -const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto); - -const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4proto); - -/* Protocol global registration. */ -int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto); -void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto); +const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto); /* Generic netlink helpers */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, -- cgit v1.2.3 From 0fb4d21956f4a9af225594a46857ccf29bd747bc Mon Sep 17 00:00:00 2001 From: wenxu Date: Wed, 16 Jan 2019 07:53:51 +0800 Subject: netfilter: nft_meta: Add NFT_META_I/OIFKIND meta type In the ip_rcv the skb goes through the PREROUTING hook first, then kicks in vrf device and go through the same hook again. When conntrack dnat works with vrf, there will be some conflict with rules because the packet goes through the hook twice with different nf status. ip link add user1 type vrf table 1 ip link add user2 type vrf table 2 ip l set dev tun1 master user1 ip l set dev tun2 master user2 nft add table firewall nft add chain firewall zones { type filter hook prerouting priority - 300 \; } nft add rule firewall zones counter ct zone set iif map { "tun1" : 1, "tun2" : 2 } nft add chain firewall rule-1000-ingress nft add rule firewall rule-1000-ingress ct zone 1 tcp dport 22 ct state new counter accept nft add rule firewall rule-1000-ingress counter drop nft add chain firewall rule-1000-egress nft add rule firewall rule-1000-egress tcp dport 22 ct state new counter drop nft add rule firewall rule-1000-egress counter accept nft add chain firewall rules-all { type filter hook prerouting priority - 150 \; } nft add rule firewall rules-all ip daddr vmap { "2.2.2.11" : jump rule-1000-ingress } nft add rule firewall rules-all ct zone vmap { 1 : jump rule-1000-egress } nft add rule firewall dnat-all ct zone vmap { 1 : jump dnat-1000 } nft add rule firewall dnat-1000 ip daddr 2.2.2.11 counter dnat to 10.0.0.7 For a package with ip daddr 2.2.2.11 and tcp dport 22, first time accept in the rule-1000-ingress and dnat to 10.0.0.7. Then second time the packet goto the wrong chain rule-1000-egress which leads the packet drop With this patch, userspace can add the 'don't re-do entire ruleset for vrf' policy itself via: nft add rule firewall rules-all meta iifkind "vrf" counter accept Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 99ca95b830b6..0ba8f48bdf0b 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -791,6 +791,8 @@ enum nft_exthdr_attributes { * @NFT_META_CGROUP: socket control group (skb->sk->sk_classid) * @NFT_META_PRANDOM: a 32bit pseudo-random number * @NFT_META_SECPATH: boolean, secpath_exists (!!skb->sp) + * @NFT_META_IIFKIND: packet input interface kind name (dev->rtnl_link_ops->kind) + * @NFT_META_OIFKIND: packet output interface kind name (dev->rtnl_link_ops->kind) */ enum nft_meta_keys { NFT_META_LEN, @@ -819,6 +821,8 @@ enum nft_meta_keys { NFT_META_CGROUP, NFT_META_PRANDOM, NFT_META_SECPATH, + NFT_META_IIFKIND, + NFT_META_OIFKIND, }; /** -- cgit v1.2.3 From 472caa69183f7eaf30ecb34451826dd5b98d7b3a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 17 Jan 2019 00:11:43 +0100 Subject: netfilter: nat: un-export nf_nat_used_tuple Not used since 203f2e78200c27e ("netfilter: nat: remove l4proto->unique_tuple") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_nat.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index a17eb2f8d40e..8aff77cafb8b 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -47,10 +47,6 @@ extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct, struct nf_conn_nat *nf_ct_nat_ext_add(struct nf_conn *ct); -/* Is this tuple already taken? (not by us)*/ -int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, - const struct nf_conn *ignored_conntrack); - static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { #if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) -- cgit v1.2.3 From 0123a75e1d57c3df31e536868339c98c02c14917 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Fri, 18 Jan 2019 14:36:29 +0100 Subject: Revert "netfilter: nft_hash: add map lookups for hashing operations" A better way to implement this from userspace has been found without specific code in the kernel side, revert this. Fixes: b9ccc07e3f31 ("netfilter: nft_hash: add map lookups for hashing operations") Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 0ba8f48bdf0b..030302893d96 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -877,8 +877,8 @@ enum nft_hash_attributes { NFTA_HASH_SEED, NFTA_HASH_OFFSET, NFTA_HASH_TYPE, - NFTA_HASH_SET_NAME, - NFTA_HASH_SET_ID, + NFTA_HASH_SET_NAME, /* deprecated */ + NFTA_HASH_SET_ID, /* deprecated */ __NFTA_HASH_MAX, }; #define NFTA_HASH_MAX (__NFTA_HASH_MAX - 1) -- cgit v1.2.3 From 6c57f0458022298e4da1729c67bd33ce41c14e7a Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Thu, 17 Jan 2019 15:34:38 +0000 Subject: net: Fix usage of pskb_trim_rcsum In certain cases, pskb_trim_rcsum() may change skb pointers. Reinitialize header pointers afterwards to avoid potential use-after-frees. Add a note in the documentation of pskb_trim_rcsum(). Found by KASAN. Signed-off-by: Ross Lagerwall Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..95d25b010a25 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3218,6 +3218,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. + * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) -- cgit v1.2.3 From 5f2939d933e9616b8b779fa46963689000f1a8f4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Wed, 9 Jan 2019 17:10:57 +0100 Subject: sch_api: Change signature of qdisc_tree_reduce_backlog() to use ints MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are now several places where qdisc_tree_reduce_backlog() is called with a negative number of packets (to signal an increase in number of packets in the queue). Rather than rely on overflow behaviour, change the function signature to use signed integers to communicate this usage to people reading the code. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/net/sch_generic.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 9481f2c142e2..7a4957599874 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -580,8 +580,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, void qdisc_reset(struct Qdisc *qdisc); void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); -void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, - unsigned int len); +void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, int n, int len); #ifdef CONFIG_NET_SCHED int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, void *type_data); -- cgit v1.2.3 From 3e64cf7a435ed0500e3adaa8aada2272d3ae8abc Mon Sep 17 00:00:00 2001 From: Camelia Groza Date: Thu, 17 Jan 2019 14:22:36 +0200 Subject: net: phy: phy driver features are mandatory Since phy driver features became a link_mode bitmap, phy drivers that don't have a list of features configured will cause the kernel to crash when probed. Prevent the phy driver from registering if the features field is missing. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Reported-by: Scott Wood Signed-off-by: Camelia Groza Signed-off-by: David S. Miller --- include/linux/phy.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 55114657a577..ef20aeea10cc 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -469,8 +469,8 @@ struct phy_device { * only works for PHYs with IDs which match this field * name: The friendly name of this PHY type * phy_id_mask: Defines the important bits of the phy_id - * features: A list of features (speed, duplex, etc) supported - * by this PHY + * features: A mandatory list of features (speed, duplex, etc) + * supported by this PHY * flags: A bitfield defining certain other features this PHY * supports (like interrupts) * -- cgit v1.2.3 From 59c28058fa7bb1cc7ab8b2c5607093cbbefafeb4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 18 Jan 2019 10:46:13 -0800 Subject: net: netlink: add helper to retrieve NETLINK_F_STRICT_CHK Dumps can read state of the NETLINK_F_STRICT_CHK flag from a field in the callback structure. For non-dump GET requests we need a way to access the state of that flag from a socket. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 4e8add270200..593d1b9c33a8 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -126,6 +126,7 @@ void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack); int netlink_has_listeners(struct sock *sk, unsigned int group); +bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, -- cgit v1.2.3 From 5954894ba3723995fbeab77bef62bb4878a654bb Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Jan 2019 17:14:01 -0800 Subject: net_sched: add performance counters for basic filter Similar to u32 filter, it is useful to know how many times we reach each basic filter and how many times we pass the ematch attached to it. Sample output: filter protocol arp pref 49152 basic chain 0 filter protocol arp pref 49152 basic chain 0 handle 0x1 (rule hit 3 success 3) action order 1: gact action pass random type none pass val 0 index 1 ref 1 bind 1 installed 81 sec used 4 sec Action statistics: Sent 126 bytes 3 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 Cc: Jamal Hadi Salim Cc: Jiri Pirko Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 32a3416b51c3..02ac251be8c4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -333,12 +333,19 @@ enum { /* Basic filter */ +struct tc_basic_pcnt { + __u64 rcnt; + __u64 rhit; +}; + enum { TCA_BASIC_UNSPEC, TCA_BASIC_CLASSID, TCA_BASIC_EMATCHES, TCA_BASIC_ACT, TCA_BASIC_POLICE, + TCA_BASIC_PCNT, + TCA_BASIC_PAD, __TCA_BASIC_MAX }; -- cgit v1.2.3 From e6018c0f5c996e61639adce6a0697391a2861916 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Dec 2018 10:14:53 +0100 Subject: sched/wake_q: Document wake_q_add() The only guarantee provided by wake_q_add() is that a wakeup will happen after it, it does _NOT_ guarantee the wakeup will be delayed until the matching wake_up_q(). If wake_q_add() fails the cmpxchg() a concurrent wakeup is pending and that can happen at any time after the cmpxchg(). This means we should not rely on the wakeup happening at wake_q_up(), but should be ready for wake_q_add() to issue the wakeup. The delay; if provided (most likely); should only result in more efficient behaviour. Reported-by: Yongji Xie Signed-off-by: Peter Zijlstra (Intel) Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Signed-off-by: Ingo Molnar --- include/linux/sched/wake_q.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 10b19a192b2d..545f37138057 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -24,9 +24,13 @@ * called near the end of a function. Otherwise, the list can be * re-initialized for later re-use by wake_q_init(). * - * Note that this can cause spurious wakeups. schedule() callers + * NOTE that this can cause spurious wakeups. schedule() callers * must ensure the call is done inside a loop, confirming that the * wakeup condition has in fact occurred. + * + * NOTE that there is no guarantee the wakeup will happen any later than the + * wake_q_add() location. Therefore task must be ready to be woken at the + * location of the wake_q_add(). */ #include -- cgit v1.2.3 From 1cd7386549f9b6f2f230da54aa9e7fe2d6c216d2 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 19 Jan 2019 08:45:56 -0800 Subject: libnvdimm/security: Require nvdimm_security_setup_events() to succeed The following warning: ACPI0012:00: security event setup failed: -19 ...is meant to capture exceptional failures of sysfs_get_dirent(), however it will also fail in the common case when security support is disabled. A few issues: 1/ A dev_warn() report for a common case is too chatty 2/ The setup of this notifier is generic, no need for it to be driven from the nfit driver, it can exist completely in the core. 3/ If it fails for any reason besides security support being disabled, that's fatal and should abort DIMM activation. Userspace may hang if it never gets overwrite notifications. 4/ The dirent needs to be released. Move the call to the core 'dimm' driver, make it conditional on security support being active, make it fatal for the exceptional case, add the missing sysfs_put() at device disable time. Fixes: 7d988097c546 ("...Add security DSM overwrite support") Reviewed-by: Dave Jiang Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7315977b64da..ad609617aeb8 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -235,7 +235,6 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, cmd_mask, num_flush, flush_wpq, NULL, NULL); } -int nvdimm_security_setup_events(struct nvdimm *nvdimm); const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, -- cgit v1.2.3 From 6fc23b6ed8fa0ba6cc47b2f8756df1199abc3a5c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 21 Jan 2019 12:01:19 +0100 Subject: binderfs: use correct include guards in header When we switched over from binder_ctl.h to binderfs.h we forgot to change the include guards. It's minor but it's obviously correct. Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binderfs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/android/binderfs.h b/include/uapi/linux/android/binderfs.h index 65b2efd1a0a5..b41628b77120 100644 --- a/include/uapi/linux/android/binderfs.h +++ b/include/uapi/linux/android/binderfs.h @@ -4,8 +4,8 @@ * */ -#ifndef _UAPI_LINUX_BINDER_CTL_H -#define _UAPI_LINUX_BINDER_CTL_H +#ifndef _UAPI_LINUX_BINDERFS_H +#define _UAPI_LINUX_BINDERFS_H #include #include @@ -31,5 +31,5 @@ struct binderfs_device { */ #define BINDER_CTL_ADD _IOWR('b', 1, struct binderfs_device) -#endif /* _UAPI_LINUX_BINDER_CTL_H */ +#endif /* _UAPI_LINUX_BINDERFS_H */ -- cgit v1.2.3 From 7d0174065f4903fb0ce0bab3d5047284faa7226d Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 21 Jan 2019 12:01:20 +0100 Subject: binderfs: use __u32 for device numbers We allow more then 255 binderfs binder devices to be created since there are workloads that require more than that. If we use __u8 we'll overflow after 255. So let's use a __u32. Note that there's no released kernel with binderfs out there so this is not a regression. Signed-off-by: Christian Brauner Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binderfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/android/binderfs.h b/include/uapi/linux/android/binderfs.h index b41628b77120..87410477aea9 100644 --- a/include/uapi/linux/android/binderfs.h +++ b/include/uapi/linux/android/binderfs.h @@ -22,8 +22,8 @@ */ struct binderfs_device { char name[BINDERFS_MAX_NAME + 1]; - __u8 major; - __u8 minor; + __u32 major; + __u32 minor; }; /** -- cgit v1.2.3 From 856c395cfa63b94a1d8215182f0243c222f6f927 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 17 Jan 2019 23:27:11 -0800 Subject: net: introduce a knob to control whether to inherit devconf config There have been many people complaining about the inconsistent behaviors of IPv4 and IPv6 devconf when creating new network namespaces. Currently, for IPv4, we inherit all current settings from init_net, but for IPv6 we reset all setting to default. This patch introduces a new /proc file /proc/sys/net/core/devconf_inherit_init_net to control the behavior of whether to inhert sysctl current settings from init_net. This file itself is only available in init_net. As demonstrated below: Initial setup in init_net: # cat /proc/sys/net/ipv4/conf/all/rp_filter 2 # cat /proc/sys/net/ipv6/conf/all/accept_dad 1 Default value 0 (current behavior): # ip netns del test # ip netns add test # ip netns exec test cat /proc/sys/net/ipv4/conf/all/rp_filter 2 # ip netns exec test cat /proc/sys/net/ipv6/conf/all/accept_dad 0 Set to 1 (inherit from init_net): # echo 1 > /proc/sys/net/core/devconf_inherit_init_net # ip netns del test # ip netns add test # ip netns exec test cat /proc/sys/net/ipv4/conf/all/rp_filter 2 # ip netns exec test cat /proc/sys/net/ipv6/conf/all/accept_dad 1 Set to 2 (reset to default): # echo 2 > /proc/sys/net/core/devconf_inherit_init_net # ip netns del test # ip netns add test # ip netns exec test cat /proc/sys/net/ipv4/conf/all/rp_filter 0 # ip netns exec test cat /proc/sys/net/ipv6/conf/all/accept_dad 0 Set to a value out of range (invalid): # echo 3 > /proc/sys/net/core/devconf_inherit_init_net -bash: echo: write error: Invalid argument # echo -1 > /proc/sys/net/core/devconf_inherit_init_net -bash: echo: write error: Invalid argument Reported-by: Zhu Yanjun Reported-by: Tonghao Zhang Cc: Nicolas Dichtel Signed-off-by: Cong Wang Acked-by: Nicolas Dichtel Acked-by: Tonghao Zhang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a57b9a853aab..e675ef97a426 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -630,6 +630,7 @@ struct netdev_queue { } ____cacheline_aligned_in_smp; extern int sysctl_fb_tunnels_only_for_init_net; +extern int sysctl_devconf_inherit_init_net; static inline bool net_has_fallback_tunnels(const struct net *net) { -- cgit v1.2.3 From 267c095aa2d9126059c1f5a65c660d5a71833e3f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 18 Jan 2019 14:30:22 +0200 Subject: bonding: add 3ad stats Count the following types of 3ad packets per slave: - rx/tx lacpdu - rx/tx marker - rx/tx marker response - rx illegal lacpdus (right now counted on wrong length) - rx unknown lacpdu type - rx unknown marker type The counters are using atomic64 since this is not fast path. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index fc3111515f5c..30e60dba1b2d 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -180,6 +180,19 @@ struct port; #pragma pack(8) #endif +struct bond_3ad_stats { + atomic64_t lacpdu_rx; + atomic64_t lacpdu_tx; + atomic64_t lacpdu_unknown_rx; + atomic64_t lacpdu_illegal_rx; + + atomic64_t marker_rx; + atomic64_t marker_tx; + atomic64_t marker_resp_rx; + atomic64_t marker_resp_tx; + atomic64_t marker_unknown_rx; +}; + /* aggregator structure(43.4.5 in the 802.3ad standard) */ typedef struct aggregator { struct mac_addr aggregator_mac_address; @@ -272,6 +285,7 @@ struct ad_bond_info { struct ad_slave_info { struct aggregator aggregator; /* 802.3ad aggregator structure */ struct port port; /* 802.3ad port structure */ + struct bond_3ad_stats stats; u16 id; }; -- cgit v1.2.3 From a258aeacd7f0dc10bb45caa7e92a3ea3ca1a76e9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 18 Jan 2019 14:30:23 +0200 Subject: bonding: add support for xstats and export 3ad stats This patch adds support for extended statistics (xstats) call to the bonding. The first user would be the 3ad code which counts the following events: - LACPDU Rx/Tx - LACPDU unknown type Rx - LACPDU illegal Rx - Marker Rx/Tx - Marker response Rx/Tx - Marker unknown type Rx All of these are exported via netlink as separate attributes to be easily extensible as we plan to add more in the future. Similar to how the bridge and other xstats exports, the structure inside is: [ IFLA_STATS_LINK_XSTATS ] -> [ LINK_XSTATS_TYPE_BOND ] -> [ BOND_XSTATS_3AD ] -> [ 3ad stats attributes ] With this structure it's easy to add more stat types later. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 3 +++ include/uapi/linux/if_bonding.h | 24 ++++++++++++++++++++++++ include/uapi/linux/if_link.h | 1 + 3 files changed, 28 insertions(+) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 30e60dba1b2d..25aaf49d19be 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -321,5 +321,8 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); +void bond_3ad_stats_add(struct slave *slave, struct bond_3ad_stats *stats); +int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); +size_t bond_3ad_stats_size(void); #endif /* _NET_BOND_3AD_H */ diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 61a1bf6e865e..790585f0e61b 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -117,6 +117,30 @@ struct ad_info { __u8 partner_system[ETH_ALEN]; }; +/* Embedded inside LINK_XSTATS_TYPE_BOND */ +enum { + BOND_XSTATS_UNSPEC, + BOND_XSTATS_3AD, + __BOND_XSTATS_MAX +}; +#define BOND_XSTATS_MAX (__BOND_XSTATS_MAX - 1) + +/* Embedded inside BOND_XSTATS_3AD */ +enum { + BOND_3AD_STAT_LACPDU_RX, + BOND_3AD_STAT_LACPDU_TX, + BOND_3AD_STAT_LACPDU_UNKNOWN_RX, + BOND_3AD_STAT_LACPDU_ILLEGAL_RX, + BOND_3AD_STAT_MARKER_RX, + BOND_3AD_STAT_MARKER_TX, + BOND_3AD_STAT_MARKER_RESP_RX, + BOND_3AD_STAT_MARKER_RESP_TX, + BOND_3AD_STAT_MARKER_UNKNOWN_RX, + BOND_3AD_STAT_PAD, + __BOND_3AD_STAT_MAX +}; +#define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1) + #endif /* _LINUX_IF_BONDING_H */ /* diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d6533828123a..5b225ff63b48 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -925,6 +925,7 @@ enum { enum { LINK_XSTATS_TYPE_UNSPEC, LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, __LINK_XSTATS_TYPE_MAX }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) -- cgit v1.2.3 From 7fc5854f8c6efae9e7624970ab49a1eac2faefb1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Dec 2017 08:38:30 -0800 Subject: writeback: synchronize sync(2) against cgroup writeback membership switches sync_inodes_sb() can race against cgwb (cgroup writeback) membership switches and fail to writeback some inodes. For example, if an inode switches to another wb while sync_inodes_sb() is in progress, the new wb might not be visible to bdi_split_work_to_wbs() at all or the inode might jump from a wb which hasn't issued writebacks yet to one which already has. This patch adds backing_dev_info->wb_switch_rwsem to synchronize cgwb switch path against sync_inodes_sb() so that sync_inodes_sb() is guaranteed to see all the target wbs and inodes can't jump wbs to escape syncing. v2: Fixed misplaced rwsem init. Spotted by Jiufei. Signed-off-by: Tejun Heo Reported-by: Jiufei Xue Link: http://lkml.kernel.org/r/dc694ae2-f07f-61e1-7097-7c8411cee12d@gmail.com Acked-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c31157135598..07e02d6df5ad 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -190,6 +190,7 @@ struct backing_dev_info { struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ + struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #else struct bdi_writeback_congested *wb_congested; #endif -- cgit v1.2.3 From ba5ea614622dca6d675b4cc8a97270569ae13a23 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Mon, 21 Jan 2019 07:26:25 +0100 Subject: bridge: simplify ip_mc_check_igmp() and ipv6_mc_check_mld() calls MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch refactors ip_mc_check_igmp(), ipv6_mc_check_mld() and their callers (more precisely, the Linux bridge) to not rely on the skb_trimmed parameter anymore. An skb with its tail trimmed to the IP packet length was initially introduced for the following three reasons: 1) To be able to verify the ICMPv6 checksum. 2) To be able to distinguish the version of an IGMP or MLD query. They are distinguishable only by their size. 3) To avoid parsing data for an IGMPv3 or MLDv2 report that is beyond the IP packet but still within the skb. The first case still uses a cloned and potentially trimmed skb to verfiy. However, there is no need to propagate it to the caller. For the second and third case explicit IP packet length checks were added. This hopefully makes ip_mc_check_igmp() and ipv6_mc_check_mld() easier to read and verfiy, as well as easier to use. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/igmp.h | 11 ++++++++++- include/linux/ip.h | 5 +++++ include/linux/ipv6.h | 6 ++++++ include/net/addrconf.h | 12 +++++++++++- 4 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 119f53941c12..8b4348f69bc5 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -106,6 +107,14 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) +static inline int ip_mc_may_pull(struct sk_buff *skb, unsigned int len) +{ + if (skb_transport_offset(skb) + ip_transport_len(skb) < len) + return -EINVAL; + + return pskb_may_pull(skb, len); +} + extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); @@ -130,6 +139,6 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); -int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed); +int ip_mc_check_igmp(struct sk_buff *skb); #endif diff --git a/include/linux/ip.h b/include/linux/ip.h index 492bc6513533..482b7b7c9f30 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -34,4 +34,9 @@ static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); } + +static inline unsigned int ip_transport_len(const struct sk_buff *skb) +{ + return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); +} #endif /* _LINUX_IP_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 495e834c1367..6d45ce784bea 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -104,6 +104,12 @@ static inline struct ipv6hdr *ipipv6_hdr(const struct sk_buff *skb) return (struct ipv6hdr *)skb_transport_header(skb); } +static inline unsigned int ipv6_transport_len(const struct sk_buff *skb) +{ + return ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr) - + skb_network_header_len(skb); +} + /* This structure contains results of exthdrs parsing as offsets from skb->nh. diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 1656c5978498..daf11dcb0f70 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -49,6 +49,7 @@ struct prefix_info { struct in6_addr prefix; }; +#include #include #include #include @@ -201,6 +202,15 @@ u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, /* * multicast prototypes (mcast.c) */ +static inline int ipv6_mc_may_pull(struct sk_buff *skb, + unsigned int len) +{ + if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len) + return -EINVAL; + + return pskb_may_pull(skb, len); +} + int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, @@ -219,7 +229,7 @@ void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); -int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed); +int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, -- cgit v1.2.3 From 4effd28c1245303dce7fd290c501ac2c11052114 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Mon, 21 Jan 2019 07:26:27 +0100 Subject: bridge: join all-snoopers multicast address MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Next to snooping IGMP/MLD queries RFC4541, section 2.1.1.a) recommends to snoop multicast router advertisements to detect multicast routers. Multicast router advertisements are sent to an "all-snoopers" multicast address. To be able to receive them reliably, we need to join this group. Otherwise other snooping switches might refrain from forwarding these advertisements to us. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index a55cb8b10165..e7ad9d350a28 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -292,10 +292,11 @@ struct sockaddr_in { #define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) /* Defines for Multicast INADDR */ -#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ -#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ -#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ -#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ #endif /* contains the htonl type stuff.. */ -- cgit v1.2.3 From 4b3087c7e37f9e499127201849e33960dc81da11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Linus=20L=C3=BCssing?= Date: Mon, 21 Jan 2019 07:26:28 +0100 Subject: bridge: Snoop Multicast Router Advertisements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When multiple multicast routers are present in a broadcast domain then only one of them will be detectable via IGMP/MLD query snooping. The multicast router with the lowest IP address will become the selected and active querier while all other multicast routers will then refrain from sending queries. To detect such rather silent multicast routers, too, RFC4286 ("Multicast Router Discovery") provides a standardized protocol to detect multicast routers for multicast snooping switches. This patch implements the necessary MRD Advertisement message parsing and after successful processing adds such routers to the internal multicast router list. Signed-off-by: Linus Lüssing Signed-off-by: David S. Miller --- include/linux/in.h | 5 +++++ include/net/addrconf.h | 15 +++++++++++++++ include/uapi/linux/icmpv6.h | 2 ++ include/uapi/linux/igmp.h | 1 + 4 files changed, 23 insertions(+) (limited to 'include') diff --git a/include/linux/in.h b/include/linux/in.h index 31b493734763..435e7f2a513a 100644 --- a/include/linux/in.h +++ b/include/linux/in.h @@ -60,6 +60,11 @@ static inline bool ipv4_is_lbcast(__be32 addr) return addr == htonl(INADDR_BROADCAST); } +static inline bool ipv4_is_all_snoopers(__be32 addr) +{ + return addr == htonl(INADDR_ALLSNOOPERS_GROUP); +} + static inline bool ipv4_is_zeronet(__be32 addr) { return (addr & htonl(0xff000000)) == htonl(0x00000000); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index daf11dcb0f70..20d523ee2fec 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -229,6 +229,7 @@ void ipv6_mc_unmap(struct inet6_dev *idev); void ipv6_mc_remap(struct inet6_dev *idev); void ipv6_mc_init_dev(struct inet6_dev *idev); void ipv6_mc_destroy_dev(struct inet6_dev *idev); +int ipv6_mc_check_icmpv6(struct sk_buff *skb); int ipv6_mc_check_mld(struct sk_buff *skb); void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp); @@ -499,6 +500,20 @@ static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) #endif } +static inline bool ipv6_addr_is_all_snoopers(const struct in6_addr *addr) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 + __be64 *p = (__be64 *)addr; + + return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | + (p[1] ^ cpu_to_be64(0x6a))) == 0UL; +#else + return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | + addr->s6_addr32[1] | addr->s6_addr32[2] | + (addr->s6_addr32[3] ^ htonl(0x0000006a))) == 0; +#endif +} + #ifdef CONFIG_PROC_FS int if6_proc_init(void); void if6_proc_exit(void); diff --git a/include/uapi/linux/icmpv6.h b/include/uapi/linux/icmpv6.h index caf8dc019250..325395f56bfa 100644 --- a/include/uapi/linux/icmpv6.h +++ b/include/uapi/linux/icmpv6.h @@ -108,6 +108,8 @@ struct icmp6hdr { #define ICMPV6_MOBILE_PREFIX_SOL 146 #define ICMPV6_MOBILE_PREFIX_ADV 147 +#define ICMPV6_MRDISC_ADV 151 + /* * Codes for Destination Unreachable */ diff --git a/include/uapi/linux/igmp.h b/include/uapi/linux/igmp.h index 7e44ac02ca18..90c28bc466c6 100644 --- a/include/uapi/linux/igmp.h +++ b/include/uapi/linux/igmp.h @@ -93,6 +93,7 @@ struct igmpv3_query { #define IGMP_MTRACE_RESP 0x1e #define IGMP_MTRACE 0x1f +#define IGMP_MRDISC_ADV 0x30 /* From RFC4286 */ /* * Use the BSD names for these for compatibility -- cgit v1.2.3 From c75860e48a7634ff8dc050842211f79a0e4e6c46 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 20 Jan 2019 11:36:38 +0200 Subject: qed: Add infrastructure for error detection and recovery This patch adds the detection and handling of a parity error ("process kill event"), including the update of the protocol drivers, and the prevention of any HW access that will lead to device access towards the host while recovery is in progress. It also provides the means for the protocol drivers to trigger a recovery process on their decision. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 91c536a01b56..c2a1b7dbe4eb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -764,6 +764,7 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; + bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -810,6 +811,7 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); + void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1057,6 +1059,24 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); +/** + * @brief recovery_process - Trigger a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_process)(struct qed_dev *cdev); + +/** + * @brief recovery_prolog - Execute the prolog operations of a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_prolog)(struct qed_dev *cdev); + /** * @brief update_drv_state - API to inform the change in the driver state. * -- cgit v1.2.3 From 278396de78a9b59a692bc140233bde3a9d8a8a31 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 20 Jan 2019 11:36:39 +0200 Subject: qede: Error recovery process This patch adds the error recovery process in the qede driver. The process includes a partial/customized driver unload and load, which allows it to look like a short suspend period to the kernel while preserving the net devices' state. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qede_rdma.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 9904617a9730..e29d7199c10e 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -55,6 +55,16 @@ struct qede_rdma_event_work { enum qede_rdma_event event; }; +enum qede_rdma_probe_mode { + QEDE_RDMA_PROBE_NORMAL, + QEDE_RDMA_PROBE_RECOVERY, +}; + +enum qede_rdma_remove_mode { + QEDE_RDMA_REMOVE_NORMAL, + QEDE_RDMA_REMOVE_RECOVERY, +}; + struct qedr_driver { unsigned char name[32]; @@ -74,21 +84,24 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev); +int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev, + enum qede_rdma_remove_mode mode); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev, + enum qede_rdma_probe_mode mode) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev, + enum qede_rdma_remove_mode mode) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From 6815d8b09282c1df8e016bd2fabf25ada6d4462b Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 21 Jan 2019 18:41:39 +0800 Subject: ptp_qoriq: support external trigger stamp FIFO The external trigger stamp FIFO was introduced as a new feature for QorIQ 1588 timer IP block. This patch is to support it by adding a new dts property "fsl,extts-fifo". Any QorIQ 1588 timer supporting this feature is required to add this property in its dts node. In addition, the FIFO should be cleaned up before enabling external trigger interrupts. Otherwise, there will be interrupts immediately just after enabling external trigger interrupts. Signed-off-by: Yangbo Lu Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index c1f003aadcce..43b4b442f6a4 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -120,6 +120,8 @@ struct qoriq_ptp_registers { /* Bit definitions for the TMR_STAT register */ #define STAT_VEC_SHIFT (0) /* Timer general purpose status vector */ #define STAT_VEC_MASK (0x3f) +#define ETS1_VLD (1<<24) +#define ETS2_VLD (1<<25) /* Bit definitions for the TMR_PRSC register */ #define PRSC_OCK_SHIFT (0) /* Output clock division/prescale factor. */ @@ -141,6 +143,7 @@ struct qoriq_ptp { struct ptp_clock *clock; struct ptp_clock_info caps; struct resource *rsrc; + bool extts_fifo_support; int irq; int phc_index; u64 alarm_interval; /* for periodic alarm */ -- cgit v1.2.3 From 19df7510d5cf077c2e88a7690fb7617e6d341beb Mon Sep 17 00:00:00 2001 From: Yangbo Lu Date: Mon, 21 Jan 2019 18:41:42 +0800 Subject: ptp: add debugfs support for ptp_qoriq This patch is to add debugfs support for ptp_qoriq. Current debugfs supports to control fiper1/fiper2 loopback mode. If the loopback mode is enabled, the fiper1/fiper2 pulse is looped back into trigger1/ trigger2 input. This is very useful for validating hardware and driver without external hardware. Below is an example to enable fiper1 loopback. echo 1 > /sys/kernel/debug/2d10e00.ptp_clock/fiper1-loopback Signed-off-by: Yangbo Lu Signed-off-by: David S. Miller --- include/linux/fsl/ptp_qoriq.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 43b4b442f6a4..94e9797e434c 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -143,6 +143,8 @@ struct qoriq_ptp { struct ptp_clock *clock; struct ptp_clock_info caps; struct resource *rsrc; + struct dentry *debugfs_root; + struct device *dev; bool extts_fifo_support; int irq; int phc_index; @@ -169,4 +171,14 @@ static inline void qoriq_write(unsigned __iomem *addr, u32 val) iowrite32be(val, addr); } +#ifdef CONFIG_DEBUG_FS +void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp); +void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp); +#else +static inline void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp) +{ } +static inline void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp) +{ } +#endif + #endif -- cgit v1.2.3 From 63530aba7826a0f8e129874df9c4d264f9db3f9e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 22 Jan 2019 10:40:59 -0800 Subject: ax25: fix possible use-after-free syzbot found that ax25 routes where not properly protected against concurrent use [1]. In this particular report the bug happened while copying ax25->digipeat. Fix this problem by making sure we call ax25_get_route() while ax25_route_lock is held, so that no modification could happen while using the route. The current two ax25_get_route() callers do not sleep, so this change should be fine. Once we do that, ax25_get_route() no longer needs to grab a reference on the found route. [1] ax25_connect(): syz-executor0 uses autobind, please contact jreuter@yaina.de BUG: KASAN: use-after-free in memcpy include/linux/string.h:352 [inline] BUG: KASAN: use-after-free in kmemdup+0x42/0x60 mm/util.c:113 Read of size 66 at addr ffff888066641a80 by task syz-executor2/531 ax25_connect(): syz-executor0 uses autobind, please contact jreuter@yaina.de CPU: 1 PID: 531 Comm: syz-executor2 Not tainted 5.0.0-rc2+ #10 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1db/0x2d0 lib/dump_stack.c:113 print_address_description.cold+0x7c/0x20d mm/kasan/report.c:187 kasan_report.cold+0x1b/0x40 mm/kasan/report.c:317 check_memory_region_inline mm/kasan/generic.c:185 [inline] check_memory_region+0x123/0x190 mm/kasan/generic.c:191 memcpy+0x24/0x50 mm/kasan/common.c:130 memcpy include/linux/string.h:352 [inline] kmemdup+0x42/0x60 mm/util.c:113 kmemdup include/linux/string.h:425 [inline] ax25_rt_autobind+0x25d/0x750 net/ax25/ax25_route.c:424 ax25_connect.cold+0x30/0xa4 net/ax25/af_ax25.c:1224 __sys_connect+0x357/0x490 net/socket.c:1664 __do_sys_connect net/socket.c:1675 [inline] __se_sys_connect net/socket.c:1672 [inline] __x64_sys_connect+0x73/0xb0 net/socket.c:1672 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x458099 Code: 6d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 3b b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f870ee22c78 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000458099 RDX: 0000000000000048 RSI: 0000000020000080 RDI: 0000000000000005 RBP: 000000000073bf00 R08: 0000000000000000 R09: 0000000000000000 ax25_connect(): syz-executor4 uses autobind, please contact jreuter@yaina.de R10: 0000000000000000 R11: 0000000000000246 R12: 00007f870ee236d4 R13: 00000000004be48e R14: 00000000004ce9a8 R15: 00000000ffffffff Allocated by task 526: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_kmalloc mm/kasan/common.c:496 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:469 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:504 ax25_connect(): syz-executor5 uses autobind, please contact jreuter@yaina.de kmem_cache_alloc_trace+0x151/0x760 mm/slab.c:3609 kmalloc include/linux/slab.h:545 [inline] ax25_rt_add net/ax25/ax25_route.c:95 [inline] ax25_rt_ioctl+0x3b9/0x1270 net/ax25/ax25_route.c:233 ax25_ioctl+0x322/0x10b0 net/ax25/af_ax25.c:1763 sock_do_ioctl+0xe2/0x400 net/socket.c:950 sock_ioctl+0x32f/0x6c0 net/socket.c:1074 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0x107b/0x17d0 fs/ioctl.c:696 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe ax25_connect(): syz-executor5 uses autobind, please contact jreuter@yaina.de Freed by task 550: save_stack+0x45/0xd0 mm/kasan/common.c:73 set_track mm/kasan/common.c:85 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:458 kasan_slab_free+0xe/0x10 mm/kasan/common.c:466 __cache_free mm/slab.c:3487 [inline] kfree+0xcf/0x230 mm/slab.c:3806 ax25_rt_add net/ax25/ax25_route.c:92 [inline] ax25_rt_ioctl+0x304/0x1270 net/ax25/ax25_route.c:233 ax25_ioctl+0x322/0x10b0 net/ax25/af_ax25.c:1763 sock_do_ioctl+0xe2/0x400 net/socket.c:950 sock_ioctl+0x32f/0x6c0 net/socket.c:1074 vfs_ioctl fs/ioctl.c:46 [inline] file_ioctl fs/ioctl.c:509 [inline] do_vfs_ioctl+0x107b/0x17d0 fs/ioctl.c:696 ksys_ioctl+0xab/0xd0 fs/ioctl.c:713 __do_sys_ioctl fs/ioctl.c:720 [inline] __se_sys_ioctl fs/ioctl.c:718 [inline] __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:718 do_syscall_64+0x1a3/0x800 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff888066641a80 which belongs to the cache kmalloc-96 of size 96 The buggy address is located 0 bytes inside of 96-byte region [ffff888066641a80, ffff888066641ae0) The buggy address belongs to the page: page:ffffea0001999040 count:1 mapcount:0 mapping:ffff88812c3f04c0 index:0x0 flags: 0x1fffc0000000200(slab) ax25_connect(): syz-executor4 uses autobind, please contact jreuter@yaina.de raw: 01fffc0000000200 ffffea0001817948 ffffea0002341dc8 ffff88812c3f04c0 raw: 0000000000000000 ffff888066641000 0000000100000020 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888066641980: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888066641a00: 00 00 00 00 00 00 00 00 02 fc fc fc fc fc fc fc >ffff888066641a80: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888066641b00: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888066641b80: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc Signed-off-by: Eric Dumazet Cc: Ralf Baechle Reported-by: syzbot Signed-off-by: David S. Miller --- include/net/ax25.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/ax25.h b/include/net/ax25.h index 3f9aea8087e3..8b7eb46ad72d 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -201,6 +201,18 @@ static inline void ax25_hold_route(ax25_route *ax25_rt) void __ax25_put_route(ax25_route *ax25_rt); +extern rwlock_t ax25_route_lock; + +static inline void ax25_route_lock_use(void) +{ + read_lock(&ax25_route_lock); +} + +static inline void ax25_route_lock_unuse(void) +{ + read_unlock(&ax25_route_lock); +} + static inline void ax25_put_route(ax25_route *ax25_rt) { if (refcount_dec_and_test(&ax25_rt->refcount)) -- cgit v1.2.3 From 60d8cd572f655aac6107a2330dced004ad1fe3d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 16 Jan 2019 19:01:48 +0100 Subject: arm64/xen: fix xen-swiotlb cache flushing Xen-swiotlb hooks into the arm/arm64 arch code through a copy of the DMA DMA mapping operations stored in the struct device arch data. Switching arm64 to use the direct calls for the merged DMA direct / swiotlb code broke this scheme. Replace the indirect calls with direct-calls in xen-swiotlb as well to fix this problem. Fixes: 356da6d0cde3 ("dma-mapping: bypass indirect calls for dma-direct") Reported-by: Julien Grall Signed-off-by: Christoph Hellwig Reviewed-by: Stefano Stabellini --- include/xen/arm/page-coherent.h | 97 ++--------------------------------------- 1 file changed, 3 insertions(+), 94 deletions(-) (limited to 'include') diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h index 59a260712a56..2ca9164a79bf 100644 --- a/include/xen/arm/page-coherent.h +++ b/include/xen/arm/page-coherent.h @@ -1,17 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H -#define _ASM_ARM_XEN_PAGE_COHERENT_H - -#include -#include -#include - -static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev) -{ - if (dev && dev->archdata.dev_dma_ops) - return dev->archdata.dev_dma_ops; - return get_arch_dma_ops(NULL); -} +#ifndef _XEN_ARM_PAGE_COHERENT_H +#define _XEN_ARM_PAGE_COHERENT_H void __xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, @@ -21,87 +10,7 @@ void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, unsigned long attrs); void __xen_dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir); - void __xen_dma_sync_single_for_device(struct device *hwdev, dma_addr_t handle, size_t size, enum dma_data_direction dir); -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) -{ - return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); -} - -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) -{ - xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); -} - -static inline void xen_dma_map_page(struct device *hwdev, struct page *page, - dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long page_pfn = page_to_xen_pfn(page); - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); - unsigned long compound_pages = - (1<map_page(hwdev, page, offset, size, dir, attrs); - else - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs); -} - -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long pfn = PFN_DOWN(handle); - /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a - * foreign mfn will always return false. If the page is local we can - * safely call the native dma_ops function, otherwise we call the xen - * specific function. - */ - if (pfn_valid(pfn)) { - if (xen_get_dma_ops(hwdev)->unmap_page) - xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); - } else - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs); -} - -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - if (pfn_valid(pfn)) { - if (xen_get_dma_ops(hwdev)->sync_single_for_cpu) - xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); - } else - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir); -} - -static inline void xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - if (pfn_valid(pfn)) { - if (xen_get_dma_ops(hwdev)->sync_single_for_device) - xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); - } else - __xen_dma_sync_single_for_device(hwdev, handle, size, dir); -} - -#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */ +#endif /* _XEN_ARM_PAGE_COHERENT_H */ -- cgit v1.2.3 From 52875a04f4b26e7ef30a288ea096f7cfec0e93cd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 22 Jan 2019 22:45:20 -0800 Subject: bpf: verifier: remove dead code Instead of overwriting dead code with jmp -1 instructions remove it completely for root. Adjust verifier state and line info appropriately. v2: - adjust func_info (Alexei); - make sure first instruction retains line info (Alexei). v4: (Yonghong) - remove unnecessary if (!insn to remove) checks; - always keep last line info if first live instruction lacks one. v5: (Martin Lau) - improve and clarify comments. Signed-off-by: Jakub Kicinski Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..be9af6b4a9e4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -778,6 +778,7 @@ static inline bool bpf_dump_raw_ok(void) struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); void bpf_clear_redirect_map(struct bpf_map *map); -- cgit v1.2.3 From 9e4c24e7ee7dfd3898269519103e823892b730d8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 22 Jan 2019 22:45:23 -0800 Subject: bpf: verifier: record original instruction index The communication between the verifier and advanced JITs is based on instruction indexes. We have to keep them stable throughout the optimizations otherwise referring to a particular instruction gets messy quickly. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 573cca00a0e6..f3ae00ee5516 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -187,6 +187,7 @@ struct bpf_insn_aux_data { int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ u8 alu_state; /* used in combination with alu_limit */ + unsigned int orig_idx; /* original instruction index */ }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ -- cgit v1.2.3 From 08ca90afba255d05dc3253caa44056e7aecbe8c5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 22 Jan 2019 22:45:24 -0800 Subject: bpf: notify offload JITs about optimizations Let offload JITs know when instructions are replaced and optimized out, so they can update their state appropriately. The optimizations are best effort, if JIT returns an error from any callback verifier will stop notifying it as state may now be out of sync, but the verifier continues making progress. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 +++++++ include/linux/bpf_verifier.h | 5 +++++ 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e734f163bd0b..3851529062ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -268,9 +268,15 @@ struct bpf_verifier_ops { }; struct bpf_prog_offload_ops { + /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); + /* verifier optimization callbacks (called after .finalize) */ + int (*replace_insn)(struct bpf_verifier_env *env, u32 off, + struct bpf_insn *insn); + int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); + /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); @@ -283,6 +289,7 @@ struct bpf_prog_offload { void *dev_priv; struct list_head offloads; bool dev_state; + bool opt_failed; void *jited_image; u32 jited_len; }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f3ae00ee5516..0620e418dde5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -266,5 +266,10 @@ int bpf_prog_offload_verifier_prep(struct bpf_prog *prog); int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int bpf_prog_offload_finalize(struct bpf_verifier_env *env); +void +bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, + struct bpf_insn *insn); +void +bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 141e5dcaa7356077028b4cd48ec351a38c70e5e5 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Thu, 24 Jan 2019 00:29:20 -0800 Subject: Input: input_event - fix the CONFIG_SPARC64 mixup Arnd Bergmann pointed out that CONFIG_* cannot be used in a uapi header. Override with an equivalent conditional. Fixes: 2e746942ebac ("Input: input_event - provide override for sparc64") Fixes: 152194fe9c3f ("Input: extend usable life of event timestamps to 2106 on 32 bit systems") Signed-off-by: Deepa Dinamani Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index ffab958bc512..f056b2a00d5c 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -32,7 +32,7 @@ struct input_event { #define input_event_usec time.tv_usec #else __kernel_ulong_t __sec; -#ifdef CONFIG_SPARC64 +#if defined(__sparc__) && defined(__arch64__) unsigned int __usec; #else __kernel_ulong_t __usec; -- cgit v1.2.3 From d9ff286a0f59fa7843549e49bd240393dd7d8b87 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 23 Jan 2019 09:22:27 -0800 Subject: bpf: allow BPF programs access skb_shared_info->gso_segs field This adds the ability to read gso_segs from a BPF program. v3: Use BPF_REG_AX instead of BPF_REG_TMP for the temporary register, as suggested by Martin. v2: refined Eddie Hao patch to address Alexei feedback. Signed-off-by: Eric Dumazet Cc: Eddie Hao Cc: Martin KaFai Lau Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 91c43884f295..2940a9854f6d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2540,6 +2540,7 @@ struct __sk_buff { __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); __u64 tstamp; __u32 wire_len; + __u32 gso_segs; }; struct bpf_tunnel_key { -- cgit v1.2.3 From 745815f955f65f22d378d69822da11043d00aaff Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Jan 2019 18:20:13 +0900 Subject: uapi: fix ioctl documentation The description of the BLKGETNRZONES zoned block device ioctl was not added as a comment together with this ioctl definition in commit 65e4e3eee83d7 ("block: Introduce BLKGETNRZONES ioctl"). Add its description here. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 6fa38d001d84..498eec813494 100644 --- a/include/uapi/linux/blkzoned.h +++ b/include/uapi/linux/blkzoned.h @@ -138,6 +138,7 @@ struct blk_zone_range { * @BLKRESETZONE: Reset the write pointer of the zones in the specified * sector range. The sector range must be zone aligned. * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors. + * @BLKGETNRZONES: Get the total number of zones of the device. */ #define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) #define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) -- cgit v1.2.3 From 8367de2c99a13d35960a51d6084631c883e93a4d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Jan 2019 18:20:14 +0900 Subject: block: Fix comment typo Fix typo in REQ_OP_ZONE_RESET description. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5c7e7f859a24..d66bf5f32610 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -287,7 +287,7 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* seset a zone write pointer */ + /* reset a zone write pointer */ REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, -- cgit v1.2.3 From 1d0dc06930a917eaca4156193c6c49f798b95ce7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Thu, 24 Jan 2019 19:59:37 +0100 Subject: net: xsk: track AF_XDP sockets on a per-netns list MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Track each AF_XDP socket in a per-netns list. This will be used later by the sock_diag interface for querying sockets from userspace. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/net/net_namespace.h | 4 ++++ include/net/netns/xdp.h | 13 +++++++++++++ 2 files changed, 17 insertions(+) create mode 100644 include/net/netns/xdp.h (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 99d4148e0f90..a68ced28d8f4 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -160,6 +161,9 @@ struct net { #endif #if IS_ENABLED(CONFIG_CAN) struct netns_can can; +#endif +#ifdef CONFIG_XDP_SOCKETS + struct netns_xdp xdp; #endif struct sock *diag_nlsk; atomic_t fnhe_genid; diff --git a/include/net/netns/xdp.h b/include/net/netns/xdp.h new file mode 100644 index 000000000000..e5734261ba0a --- /dev/null +++ b/include/net/netns/xdp.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NETNS_XDP_H__ +#define __NETNS_XDP_H__ + +#include +#include + +struct netns_xdp { + struct mutex lock; + struct hlist_head list; +}; + +#endif /* __NETNS_XDP_H__ */ -- cgit v1.2.3 From 50e74c0131a5b3a3e387798a5705158c04fb3bd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Thu, 24 Jan 2019 19:59:38 +0100 Subject: xsk: add id to umem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This commit adds an id to the umem structure. The id uniquely identifies a umem instance, and will be exposed to user-space via the socket monitoring interface. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/net/xdp_sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 13acb9803a6d..61cf7dbb6782 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -42,6 +42,7 @@ struct xdp_umem { struct work_struct work; struct page **pgs; u32 npgs; + int id; struct net_device *dev; struct xdp_umem_fq_reuse *fq_reuse; u16 queue_id; -- cgit v1.2.3 From a36b38aa2af61146ea80980a01cf6e952ab021c1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= Date: Thu, 24 Jan 2019 19:59:39 +0100 Subject: xsk: add sock_diag interface for AF_XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch adds the sock_diag interface for querying sockets from user space. Tools like iproute2 ss(8) can use this interface to list open AF_XDP sockets. The user-space ABI is defined in linux/xdp_diag.h and includes netlink request and response structs. The request can query sockets and the response contains socket information about the rings, umems, inode and more. Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann --- include/uapi/linux/xdp_diag.h | 72 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100644 include/uapi/linux/xdp_diag.h (limited to 'include') diff --git a/include/uapi/linux/xdp_diag.h b/include/uapi/linux/xdp_diag.h new file mode 100644 index 000000000000..78b2591a7782 --- /dev/null +++ b/include/uapi/linux/xdp_diag.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * xdp_diag: interface for query/monitor XDP sockets + * Copyright(c) 2019 Intel Corporation. + */ + +#ifndef _LINUX_XDP_DIAG_H +#define _LINUX_XDP_DIAG_H + +#include + +struct xdp_diag_req { + __u8 sdiag_family; + __u8 sdiag_protocol; + __u16 pad; + __u32 xdiag_ino; + __u32 xdiag_show; + __u32 xdiag_cookie[2]; +}; + +struct xdp_diag_msg { + __u8 xdiag_family; + __u8 xdiag_type; + __u16 pad; + __u32 xdiag_ino; + __u32 xdiag_cookie[2]; +}; + +#define XDP_SHOW_INFO (1 << 0) /* Basic information */ +#define XDP_SHOW_RING_CFG (1 << 1) +#define XDP_SHOW_UMEM (1 << 2) +#define XDP_SHOW_MEMINFO (1 << 3) + +enum { + XDP_DIAG_NONE, + XDP_DIAG_INFO, + XDP_DIAG_UID, + XDP_DIAG_RX_RING, + XDP_DIAG_TX_RING, + XDP_DIAG_UMEM, + XDP_DIAG_UMEM_FILL_RING, + XDP_DIAG_UMEM_COMPLETION_RING, + XDP_DIAG_MEMINFO, + __XDP_DIAG_MAX, +}; + +#define XDP_DIAG_MAX (__XDP_DIAG_MAX - 1) + +struct xdp_diag_info { + __u32 ifindex; + __u32 queue_id; +}; + +struct xdp_diag_ring { + __u32 entries; /*num descs */ +}; + +#define XDP_DU_F_ZEROCOPY (1 << 0) + +struct xdp_diag_umem { + __u64 size; + __u32 id; + __u32 num_pages; + __u32 chunk_size; + __u32 headroom; + __u32 ifindex; + __u32 queue_id; + __u32 flags; + __u32 refs; +}; + +#endif /* _LINUX_XDP_DIAG_H */ -- cgit v1.2.3 From 434a4315b9617bf1742bc64712bf44a208502f7f Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 23 Jan 2019 07:31:58 +0100 Subject: net: phy: change phy_start_interrupts to phy_request_interrupt Now that we enable the interrupts in phy_start() we don't have to do it before. Therefore remove enabling interrupts from phy_start_interrupts() and rename this function to reflect the changed functionality. v2: - improve warning to clearly state that we fall back to polling Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1f3873a2ff29..70f83d0d7469 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1047,7 +1047,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); -int phy_start_interrupts(struct phy_device *phydev); +void phy_request_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); -- cgit v1.2.3 From 949e7cea0cbccd7e2afc4b374e2be998b8fcef78 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 23 Jan 2019 19:14:50 +0200 Subject: bonding: count master 3ad stats separately I made a dumb mistake when I summed up the slave stats, obviously slaves can come and go which would make the master stats unreliable. Count and export the master stats separately. Fixes: a258aeacd7f0 ("bonding: add support for xstats and export 3ad stats") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/bond_3ad.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 25aaf49d19be..c781e1afd683 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -278,6 +278,7 @@ struct ad_system { struct ad_bond_info { struct ad_system system; /* 802.3ad system structure */ + struct bond_3ad_stats stats; u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ u16 aggregator_identifier; }; @@ -321,7 +322,6 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); -void bond_3ad_stats_add(struct slave *slave, struct bond_3ad_stats *stats); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); size_t bond_3ad_stats_size(void); #endif /* _NET_BOND_3AD_H */ -- cgit v1.2.3 From 78dc70ebaa38aa303274e333be6c98eef87619e2 Mon Sep 17 00:00:00 2001 From: Priyaranjan Jha Date: Wed, 23 Jan 2019 12:04:54 -0800 Subject: tcp_bbr: adapt cwnd based on ack aggregation estimation Aggregation effects are extremely common with wifi, cellular, and cable modem link technologies, ACK decimation in middleboxes, and LRO and GRO in receiving hosts. The aggregation can happen in either direction, data or ACKs, but in either case the aggregation effect is visible to the sender in the ACK stream. Previously BBR's sending was often limited by cwnd under severe ACK aggregation/decimation because BBR sized the cwnd at 2*BDP. If packets were acked in bursts after long delays (e.g. one ACK acking 5*BDP after 5*RTT), BBR's sending was halted after sending 2*BDP over 2*RTT, leaving the bottleneck idle for potentially long periods. Note that loss-based congestion control does not have this issue because when facing aggregation it continues increasing cwnd after bursts of ACKs, growing cwnd until the buffer is full. To achieve good throughput in the presence of aggregation effects, this algorithm allows the BBR sender to put extra data in flight to keep the bottleneck utilized during silences in the ACK stream that it has evidence to suggest were caused by aggregation. A summary of the algorithm: when a burst of packets are acked by a stretched ACK or a burst of ACKs or both, BBR first estimates the expected amount of data that should have been acked, based on its estimated bandwidth. Then the surplus ("extra_acked") is recorded in a windowed-max filter to estimate the recent level of observed ACK aggregation. Then cwnd is increased by the ACK aggregation estimate. The larger cwnd avoids BBR being cwnd-limited in the face of ACK silences that recent history suggests were caused by aggregation. As a sanity check, the ACK aggregation degree is upper-bounded by the cwnd (at the time of measurement) and a global max of BW * 100ms. The algorithm is further described by the following presentation: https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-00 In our internal testing, we observed a significant increase in BBR throughput (measured using netperf), in a basic wifi setup. - Host1 (sender on ethernet) -> AP -> Host2 (receiver on wifi) - 2.4 GHz -> BBR before: ~73 Mbps; BBR after: ~102 Mbps; CUBIC: ~100 Mbps - 5.0 GHz -> BBR before: ~362 Mbps; BBR after: ~593 Mbps; CUBIC: ~601 Mbps Also, this code is running globally on YouTube TCP connections and produced significant bandwidth increases for YouTube traffic. This is based on Ian Swett's max_ack_height_ algorithm from the QUIC BBR implementation. Signed-off-by: Priyaranjan Jha Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 371b3b45fd5c..fe0d9b44d6fc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -139,8 +139,8 @@ struct inet_connection_sock { } icsk_mtup; u32 icsk_user_timeout; - u64 icsk_ca_priv[88 / sizeof(u64)]; -#define ICSK_CA_PRIV_SIZE (11 * sizeof(u64)) + u64 icsk_ca_priv[104 / sizeof(u64)]; +#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64)) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ -- cgit v1.2.3 From 3b707c3008cad04604c1f50e39f456621821c414 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Thu, 24 Jan 2019 03:07:02 -0800 Subject: net: dev_is_mac_header_xmit() true for ARPHRD_RAWIP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __bpf_redirect() and act_mirred checks this boolean to determine whether to prefix an ethernet header. Signed-off-by: Maciej Żenczykowski Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 6756fea18b69..e44746de95cd 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -54,6 +54,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_IPGRE: case ARPHRD_VOID: case ARPHRD_NONE: + case ARPHRD_RAWIP: return false; default: return true; -- cgit v1.2.3 From 30e5c2c6bf285d93dee4c45f23da95d7d50b125a Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 25 Jan 2019 10:53:23 -0800 Subject: net: Revert devlink health changes. This reverts the devlink health changes from 9/17/2019, Jiri wants things to be designed differently and it was agreed that the easiest way to do this is start from the beginning again. Commits reverted: cb5ccfbe73b389470e1dc11061bb185ef4bc9aec 880ee82f0313453ec5a6cb122866ac057263066b c7af343b4e33578b7de91786a3f639c8cfa0d97b ff253fedab961b22117a73ab808fcfa9e6852b50 6f9d56132eb6d2603d4273cfc65bed914ec47acb fcd852c69d776c0f46c8f79e8e431e5cc6ddc7b7 8a66704a13d9713593342e29b4f0c19762f5746b 12bd0dcefe88782ac1c9fff632958dd1b71d27e5 aba25279c10094c5c97d09c3491ca86d00b4ad5e ce019faa70f81555fa17ebc1d5a03651f2e7e15a b8c45a033acc607201588f7665ba84207e5149e0 And the follow-on build fix: o33a0efa4baecd689da9474ce0e8b673eb6931c60 Signed-off-by: David S. Miller --- include/net/devlink.h | 144 ----------------------------------------- include/trace/events/devlink.h | 62 ------------------ include/uapi/linux/devlink.h | 25 ------- 3 files changed, 231 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index a81a1b7a67d7..67f4293bc970 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -30,7 +30,6 @@ struct devlink { struct list_head param_list; struct list_head region_list; u32 snapshot_id; - struct list_head reporter_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -424,36 +423,6 @@ struct devlink_region; typedef void devlink_snapshot_data_dest_t(const void *data); -struct devlink_health_buffer; -struct devlink_health_reporter; - -/** - * struct devlink_health_reporter_ops - Reporter operations - * @name: reporter name - * dump_size: dump buffer size allocated by the devlink - * diagnose_size: diagnose buffer size allocated by the devlink - * recover: callback to recover from reported error - * if priv_ctx is NULL, run a full recover - * dump: callback to dump an object - * if priv_ctx is NULL, run a full dump - * diagnose: callback to diagnose the current status - */ - -struct devlink_health_reporter_ops { - char *name; - unsigned int dump_size; - unsigned int diagnose_size; - int (*recover)(struct devlink_health_reporter *reporter, - void *priv_ctx); - int (*dump)(struct devlink_health_reporter *reporter, - struct devlink_health_buffer **buffers_array, - unsigned int buffer_size, unsigned int num_buffers, - void *priv_ctx); - int (*diagnose)(struct devlink_health_reporter *reporter, - struct devlink_health_buffer **buffers_array, - unsigned int buffer_size, unsigned int num_buffers); -}; - struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -615,34 +584,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); -int devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, - int attrtype); -void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer); -void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer); -int devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, - char *name); -int devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, - u8 value); -int devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, - u32 value); -int devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, - u64 value); -int devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, - char *name); -int devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, - void *data, int len); -struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, bool auto_recover, - void *priv); -void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); - -void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter); -int devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx); #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -903,91 +844,6 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, return 0; } -static inline int -devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, - int attrtype) -{ - return 0; -} - -static inline void -devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) -{ -} - -static inline void -devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) -{ -} - -static inline int -devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, - char *name) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, - u8 value) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, - u32 value) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, - u64 value) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, - char *name) -{ - return 0; -} - -static inline int -devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, - void *data, int len) -{ - return 0; -} - -static inline struct devlink_health_reporter * -devlink_health_reporter_create(struct devlink *devlink, - const struct devlink_health_reporter_ops *ops, - u64 graceful_period, bool auto_recover, - void *priv) -{ - return NULL; -} - -static inline void -devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) -{ -} - -static inline void * -devlink_health_reporter_priv(struct devlink_health_reporter *reporter) -{ - return NULL; -} - -static inline int -devlink_health_report(struct devlink_health_reporter *reporter, - const char *msg, void *priv_ctx) -{ - return 0; -} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 7e39d2fc7c75..44acfbca1266 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -46,65 +46,6 @@ TRACE_EVENT(devlink_hwmsg, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); -TRACE_EVENT(devlink_health_report, - TP_PROTO(const struct devlink *devlink, const char *reporter_name, - const char *msg), - - TP_ARGS(devlink, reporter_name, msg), - - TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) - __string(reporter_name, msg) - __string(msg, msg) - ), - - TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); - __assign_str(reporter_name, reporter_name); - __assign_str(msg, msg); - ), - - TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s", - __get_str(bus_name), __get_str(dev_name), - __get_str(driver_name), __get_str(reporter_name), - __get_str(msg)) -); - -TRACE_EVENT(devlink_health_recover_aborted, - TP_PROTO(const struct devlink *devlink, const char *reporter_name, - bool health_state, u64 time_since_last_recover), - - TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), - - TP_STRUCT__entry( - __string(bus_name, devlink->dev->bus->name) - __string(dev_name, dev_name(devlink->dev)) - __string(driver_name, devlink->dev->driver->name) - __string(reporter_name, reporter_name) - __field(bool, health_state) - __field(u64, time_since_last_recover) - ), - - TP_fast_assign( - __assign_str(bus_name, devlink->dev->bus->name); - __assign_str(dev_name, dev_name(devlink->dev)); - __assign_str(driver_name, devlink->dev->driver->name); - __assign_str(reporter_name, reporter_name); - __entry->health_state = health_state; - __entry->time_since_last_recover = time_since_last_recover; - ), - - TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover = %llu recover aborted", - __get_str(bus_name), __get_str(dev_name), - __get_str(driver_name), __get_str(reporter_name), - __entry->health_state, - __entry->time_since_last_recover) -); - #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ @@ -123,9 +64,6 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink, { } -static inline void trace_devlink_health(const char *msg) -{ -} #endif /* _TRACE_DEVLINK_H */ #endif diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6b26bb2ce4dc..6e52d3660654 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,13 +89,6 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, - DEVLINK_CMD_HEALTH_REPORTER_GET, - DEVLINK_CMD_HEALTH_REPORTER_SET, - DEVLINK_CMD_HEALTH_REPORTER_RECOVER, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, - /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -292,24 +285,6 @@ enum devlink_attr { DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME, /* string */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY, /* nested */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, /* u8 */ - DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, /* dynamic */ - - DEVLINK_ATTR_HEALTH_REPORTER, /* nested */ - DEVLINK_ATTR_HEALTH_REPORTER_NAME, /* string */ - DEVLINK_ATTR_HEALTH_REPORTER_STATE, /* u8 */ - DEVLINK_ATTR_HEALTH_REPORTER_ERR, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, /* u8 */ - DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, /* u64 */ - DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, /* u8 */ - /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From abfd04f738c2625f63e04c8fc7cadb3b7a70d580 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 25 Jan 2019 15:32:28 -0800 Subject: qed: Revert error handling changes. This is new code and not bug fixes. This reverts all changes added by merge commit 8fb18be93efd7292d6ee403b9f61af1008239639 Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 -------------------- include/linux/qed/qede_rdma.h | 21 ++++----------------- 2 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index c2a1b7dbe4eb..91c536a01b56 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -764,7 +764,6 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; - bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -811,7 +810,6 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); - void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1059,24 +1057,6 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); -/** - * @brief recovery_process - Trigger a recovery process - * - * @param cdev - * - * @return 0 on success, error otherwise. - */ - int (*recovery_process)(struct qed_dev *cdev); - -/** - * @brief recovery_prolog - Execute the prolog operations of a recovery process - * - * @param cdev - * - * @return 0 on success, error otherwise. - */ - int (*recovery_prolog)(struct qed_dev *cdev); - /** * @brief update_drv_state - API to inform the change in the driver state. * diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index e29d7199c10e..9904617a9730 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -55,16 +55,6 @@ struct qede_rdma_event_work { enum qede_rdma_event event; }; -enum qede_rdma_probe_mode { - QEDE_RDMA_PROBE_NORMAL, - QEDE_RDMA_PROBE_RECOVERY, -}; - -enum qede_rdma_remove_mode { - QEDE_RDMA_REMOVE_NORMAL, - QEDE_RDMA_REMOVE_RECOVERY, -}; - struct qedr_driver { unsigned char name[32]; @@ -84,24 +74,21 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode); +int qede_rdma_dev_add(struct qede_dev *dev); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev, - enum qede_rdma_remove_mode mode); +void qede_rdma_dev_remove(struct qede_dev *dev); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev, - enum qede_rdma_probe_mode mode) +static inline int qede_rdma_dev_add(struct qede_dev *dev) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev, - enum qede_rdma_remove_mode mode) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From c23f35d19db3b36ffb9e04b08f1d91565d15f84f Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Tue, 22 Jan 2019 10:02:50 -0800 Subject: net: IP defrag: encapsulate rbtree defrag code into callable functions This is a refactoring patch: without changing runtime behavior, it moves rbtree-related code from IPv4-specific files/functions into .h/.c defrag files shared with IPv6 defragmentation code. Signed-off-by: Peter Oskolkov Cc: Eric Dumazet Cc: Florian Westphal Cc: Tom Herbert Signed-off-by: David S. Miller --- include/net/inet_frag.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 1662cbc0b46b..b02bf737d019 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -77,8 +77,8 @@ struct inet_frag_queue { struct timer_list timer; spinlock_t lock; refcount_t refcnt; - struct sk_buff *fragments; /* Used in IPv6. */ - struct rb_root rb_fragments; /* Used in IPv4. */ + struct sk_buff *fragments; /* used in 6lopwpan IPv6. */ + struct rb_root rb_fragments; /* Used in IPv4/IPv6. */ struct sk_buff *fragments_tail; struct sk_buff *last_run_head; ktime_t stamp; @@ -153,4 +153,16 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, long val) extern const u8 ip_frag_ecn_table[16]; +/* Return values of inet_frag_queue_insert() */ +#define IPFRAG_OK 0 +#define IPFRAG_DUP 1 +#define IPFRAG_OVERLAP 2 +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end); +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent); +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data); +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q); + #endif -- cgit v1.2.3 From d4289fcc9b16b89619ee1c54f829e05e56de8b9a Mon Sep 17 00:00:00 2001 From: Peter Oskolkov Date: Tue, 22 Jan 2019 10:02:51 -0800 Subject: net: IP6 defrag: use rbtrees for IPv6 defrag Currently, IPv6 defragmentation code drops non-last fragments that are smaller than 1280 bytes: see commit 0ed4229b08c1 ("ipv6: defrag: drop non-last frags smaller than min mtu") This behavior is not specified in IPv6 RFCs and appears to break compatibility with some IPv6 implemenations, as reported here: https://www.spinics.net/lists/netdev/msg543846.html This patch re-uses common IP defragmentation queueing and reassembly code in IPv6, removing the 1280 byte restriction. Signed-off-by: Peter Oskolkov Reported-by: Tom Herbert Cc: Eric Dumazet Cc: Florian Westphal Signed-off-by: David S. Miller --- include/net/ipv6_frag.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 6ced1e6899b6..28aa9b30aece 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -82,8 +82,15 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); /* Don't send error if the first segment did not arrive. */ - head = fq->q.fragments; - if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) + if (!(fq->q.flags & INET_FRAG_FIRST_IN)) + goto out; + + /* sk_buff::dev and sk_buff::rbnode are unionized. So we + * pull the head out of the tree in order to be able to + * deal with head->dev. + */ + head = inet_frag_pull_head(&fq->q); + if (!head) goto out; head->dev = dev; -- cgit v1.2.3 From f859a448470304135f7a1af0083b99e188873bb4 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 25 Jan 2019 11:17:23 -0500 Subject: tcp: allow zerocopy with fastopen Accept MSG_ZEROCOPY in all the TCP states that allow sendmsg. Remove the explicit check for ESTABLISHED and CLOSE_WAIT states. This requires correctly handling zerocopy state (uarg, sk_zckey) in all paths reachable from other TCP states. Such as the EPIPE case in sk_stream_wait_connect, which a sendmsg() in incorrect state will now hit. Most paths are already safe. Only extension needed is for TCP Fastopen active open. This can build an skb with data in tcp_send_syn_data. Pass the uarg along with other fastopen state, so that this skb also generates a zerocopy notification on release. Tested with active and passive tcp fastopen packetdrill scripts at https://github.com/wdebruij/packetdrill/commit/1747eef03d25a2404e8132817d0f1244fd6f129d Signed-off-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 5c950180d61b..a6e0355921e1 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1608,6 +1608,7 @@ struct tcp_fastopen_request { struct msghdr *data; /* data in MSG_FASTOPEN */ size_t size; int copied; /* queued in tcp_connect() */ + struct ubuf_info *uarg; }; void tcp_free_fastopen_req(struct tcp_sock *tp); void tcp_fastopen_destroy_cipher(struct sock *sk); -- cgit v1.2.3 From c8b34e680a090ab8dc42f8331020e31052b49a70 Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 22 Jan 2019 18:39:50 +0800 Subject: ip_tunnel: Add tnl_update_pmtu in ip_md_tunnel_xmit Add tnl_update_pmtu in ip_md_tunnel_xmit to dynamic modify the pmtu which packet send through collect_metadata mode ip tunnel Signed-off-by: wenxu Signed-off-by: David S. Miller --- include/net/ip_tunnels.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 34f019650941..f069f64ebf29 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -267,7 +267,7 @@ void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id, void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, const u8 protocol); void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, - const u8 proto); + const u8 proto, int tunnel_hlen); int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); -- cgit v1.2.3 From d405c7407a5468d4fc11724d76063e0647d80106 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Sat, 26 Jan 2019 12:25:59 -0500 Subject: bpf: allocate 0x06 to new eBPF instruction class JMP32 The new eBPF instruction class JMP32 uses the reserved class number 0x6. Kernel BPF ISA documentation updated accordingly. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2940a9854f6d..60b99b730a41 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -14,6 +14,7 @@ /* Extended instruction set based on top of classic BPF */ /* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ #define BPF_ALU64 0x07 /* alu mode in double word width */ /* ld/ldx fields */ -- cgit v1.2.3 From a7b76c8857692b0fce063b94ed83da11c396d341 Mon Sep 17 00:00:00 2001 From: Jiong Wang Date: Sat, 26 Jan 2019 12:26:05 -0500 Subject: bpf: JIT blinds support JMP32 This patch adds JIT blinds support for JMP32. Like BPF_JMP_REG/IMM, JMP32 version are needed for building raw bpf insn. They are added to both include/linux/filter.h and tools/include/linux/filter.h. Reviewed-by: Jakub Kicinski Signed-off-by: Jiong Wang Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/filter.h b/include/linux/filter.h index be9af6b4a9e4..e4b473f85b46 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -277,6 +277,26 @@ struct sock_reuseport; .off = OFF, \ .imm = IMM }) +/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ + +#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = OFF, \ + .imm = IMM }) + /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ -- cgit v1.2.3 From 31954cd8bb667030b1c0d3d77f28fe71f06999f9 Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 25 Jan 2019 10:53:19 -0800 Subject: tcp: Refactor pingpong code Instead of using pingpong as a single bit information, we refactor the code to treat it as a counter. When interactive session is detected, we set pingpong count to TCP_PINGPONG_THRESH. And when pingpong count is >= TCP_PINGPONG_THRESH, we consider the session in pingpong mode. This patch is a pure refactor and sets foundation for the next patch. This patch itself does not change any pingpong logic. Signed-off-by: Wei Wang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fe0d9b44d6fc..179609d1d1ea 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -314,4 +314,21 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); + +#define TCP_PINGPONG_THRESH 1 + +static inline void inet_csk_enter_pingpong_mode(struct sock *sk) +{ + inet_csk(sk)->icsk_ack.pingpong = TCP_PINGPONG_THRESH; +} + +static inline void inet_csk_exit_pingpong_mode(struct sock *sk) +{ + inet_csk(sk)->icsk_ack.pingpong = 0; +} + +static inline bool inet_csk_in_pingpong_mode(struct sock *sk) +{ + return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; +} #endif /* _INET_CONNECTION_SOCK_H */ -- cgit v1.2.3 From 4a41f453bedfd5e9cd040bad509d9da49feb3e2c Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Fri, 25 Jan 2019 10:53:20 -0800 Subject: tcp: change pingpong threshold to 3 In order to be more confident about an on-going interactive session, we increment pingpong count by 1 for every interactive transaction and we adjust TCP_PINGPONG_THRESH to 3. This means, we only consider a session in pingpong mode after we see 3 interactive transactions, and start to activate delayed acks in quick ack mode. And in order to not over-count the credits, we only increase pingpong count for the first packet sent in response for the previous received packet. This is mainly to prevent delaying the ack immediately after some handshake protocol but no real interactive traffic pattern afterwards. Signed-off-by: Wei Wang Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 179609d1d1ea..ff40e1d08157 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -315,7 +315,7 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); -#define TCP_PINGPONG_THRESH 1 +#define TCP_PINGPONG_THRESH 3 static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { @@ -331,4 +331,12 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk) { return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; } + +static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ack.pingpong < U8_MAX) + icsk->icsk_ack.pingpong++; +} #endif /* _INET_CONNECTION_SOCK_H */ -- cgit v1.2.3 From fe19a8fea7cb59f202ddd30ec2fa9f5bd907b3d2 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Sat, 19 Jan 2019 15:22:38 +0100 Subject: ipvs: avoid indirect calls when calculating checksums The function pointer ip_vs_protocol->csum_check is only used in protocol specific code, and never in the generic one. Remove the function pointer from struct ip_vs_protocol and call the checksum functions directly. This reduces the performance impact of the Spectre mitigation, and should give a small improvement even with RETPOLINES disabled. Signed-off-by: Matteo Croce Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a0d2e0bb9a94..047f9a5ccaad 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -453,9 +453,6 @@ struct ip_vs_protocol { int (*dnat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph); - int (*csum_check)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp); - const char *(*state_name)(int state); void (*state_transition)(struct ip_vs_conn *cp, int direction, -- cgit v1.2.3 From 83f529281d7aa42b10c2c5cb64fcbd2c7cab4409 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 27 Jan 2019 19:18:57 +0100 Subject: netfilter: ipv4: remove useless export_symbol Only one caller; place it where needed and get rid of the EXPORT_SYMBOL. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 95ab5cc64422..082e2c41b7ff 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -25,7 +25,6 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict); -int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry); #else static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol) @@ -37,11 +36,6 @@ static inline int nf_ip_route(struct net *net, struct dst_entry **dst, { return -EOPNOTSUPP; } -static inline int nf_ip_reroute(struct sk_buff *skb, - const struct nf_queue_entry *entry) -{ - return -EOPNOTSUPP; -} #endif /* CONFIG_INET */ #endif /*__LINUX_IP_NETFILTER_H*/ -- cgit v1.2.3 From 64515dc899df898991b2b7e56f69f56f014ea888 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 28 Jan 2019 19:27:55 +0200 Subject: qed: Add infrastructure for error detection and recovery This patch adds the detection and handling of a parity error ("process kill event"), including the update of the protocol drivers, and the prevention of any HW access that will lead to device access towards the host while recovery is in progress. It also provides the means for the protocol drivers to trigger a recovery process on their decision. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 5f818fda96bd..35170f74ed80 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -763,6 +763,7 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; + bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -809,6 +810,7 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); + void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1056,6 +1058,24 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); +/** + * @brief recovery_process - Trigger a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_process)(struct qed_dev *cdev); + +/** + * @brief recovery_prolog - Execute the prolog operations of a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_prolog)(struct qed_dev *cdev); + /** * @brief update_drv_state - API to inform the change in the driver state. * -- cgit v1.2.3 From ccc67ef50b9085b895738d7720840eb6fe98745e Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 28 Jan 2019 19:27:56 +0200 Subject: qede: Error recovery process This patch adds the error recovery process in the qede driver. The process includes a partial/customized driver unload and load, which allows it to look like a short suspend period to the kernel while preserving the net devices' state. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qede_rdma.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 9904617a9730..5a00c7a473bf 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -74,21 +74,23 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev); +int qede_rdma_dev_add(struct qede_dev *dev, bool recovery); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev, bool recovery); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev, + bool recovery) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev, + bool recovery) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From c8aa703822bf811269975cf7251b5eaad4c38e9c Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 28 Jan 2019 08:53:53 -0800 Subject: net/flow_dissector: move bpf case into __skb_flow_bpf_dissect This way, we can reuse it for flow dissector in BPF_PROG_TEST_RUN. No functional changes. Signed-off-by: Stanislav Fomichev Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..be762fc34ff3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1221,6 +1221,11 @@ static inline int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) } #endif +struct bpf_flow_keys; +bool __skb_flow_bpf_dissect(struct bpf_prog *prog, + const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + struct bpf_flow_keys *flow_keys); bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, -- cgit v1.2.3 From b7a1848e8398b8396c990279e6a10272d818577e Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 28 Jan 2019 08:53:54 -0800 Subject: bpf: add BPF_PROG_TEST_RUN support for flow dissector The input is packet data, the output is struct bpf_flow_key. This should make it easy to test flow dissector programs without elaborate setup. Signed-off-by: Stanislav Fomichev Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3851529062ec..0394f1f9213b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -404,6 +404,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); /* an array of programs to be executed under rcu_lock. * -- cgit v1.2.3 From 32eb67b93c9e3cd62cb423e30b090cdd4aa8d275 Mon Sep 17 00:00:00 2001 From: Dave Watson Date: Sun, 27 Jan 2019 00:57:38 +0000 Subject: net: tls: Save iv in tls_rec for async crypto requests aead_request_set_crypt takes an iv pointer, and we change the iv soon after setting it. Some async crypto algorithms don't save the iv, so we need to save it in the tls_rec for async requests. Found by hardcoding x64 aesni to use async crypto manager (to test the async codepath), however I don't think this combination can happen in the wild. Presumably other hardware offloads will need this fix, but there have been no user reports. Fixes: a42055e8d2c30 ("Add support for async encryption of records...") Signed-off-by: Dave Watson Signed-off-by: David S. Miller --- include/net/tls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/tls.h b/include/net/tls.h index 2a6ac8d642af..1486b60c4de8 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -120,6 +120,8 @@ struct tls_rec { struct scatterlist sg_aead_out[2]; char aad_space[TLS_AAD_SPACE_SIZE]; + u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE + + TLS_CIPHER_AES_GCM_128_SALT_SIZE]; struct aead_request aead_req; u8 aead_req_ctx[]; }; -- cgit v1.2.3 From 39e6160e14bd011988e4f88fd3d3f1205c3b9776 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:20 +0530 Subject: devlink: Add devlink_param for port register and unregister Add functions to register and unregister for the driver supported configuration parameters table per port. v7->v8: - Order the definitions following way as suggested by Jiri. __devlink_params_register __devlink_params_unregister devlink_params_register devlink_params_unregister devlink_port_params_register devlink_port_params_unregister - Append with Acked-by: Jiri Pirko . v2->v3: - Add a helper __devlink_params_register() with common code used by both devlink_params_register() and devlink_port_params_register(). Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 67f4293bc970..7fc0748c58e3 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -48,6 +48,7 @@ struct devlink_port_attrs { struct devlink_port { struct list_head list; + struct list_head param_list; struct devlink *devlink; unsigned index; bool registered; @@ -567,6 +568,12 @@ int devlink_params_register(struct devlink *devlink, void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count); +int devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count); +void devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count); int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, @@ -791,6 +798,21 @@ devlink_params_unregister(struct devlink *devlink, } +static inline int +devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return 0; +} + +static inline void +devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ +} + static inline int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val) -- cgit v1.2.3 From f4601dee25d5fe8010023552b10879f3d62e45ce Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:21 +0530 Subject: devlink: Add port param get command Add port param get command which gets data per parameter. It also has option to dump the parameters data per port. v7->v8: Append "Acked-by: Jiri Pirko " Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6e52d3660654..448973beac9d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,6 +89,8 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, + DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 -- cgit v1.2.3 From 9c54873b4e2ee22507627b1adac9e3a8407741bd Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:22 +0530 Subject: devlink: Add port param set command Add port param set command to set the value for a parameter. Value can be set to any of the supported configuration modes. v7->v8: Append "Acked-by: Jiri Pirko " Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/devlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 448973beac9d..3658fb20b190 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -90,6 +90,7 @@ enum devlink_command { DEVLINK_CMD_REGION_READ, DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ + DEVLINK_CMD_PORT_PARAM_SET, /* add new commands above here */ __DEVLINK_CMD_MAX, -- cgit v1.2.3 From ffd19b9a490a6b022b58bada054ee130fff06a1c Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:23 +0530 Subject: devlink: Add support for driverinit get value for devlink_port Add support for "driverinit" configuration mode value for devlink_port configuration parameters. Add devlink_port_param_driverinit_value_get() function to help the driver get the value from devlink_port. Also, move the common code to __devlink_param_driverinit_value_get() to be used by both device and port params. v7->v8: -Add the missing devlink_port_param_driverinit_value_get() declaration. -Also, order devlink_port_param_driverinit_value_get() after devlink_param_driverinit_value_get/set() calls Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7fc0748c58e3..3943072d3552 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -578,6 +578,10 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); +int +devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); @@ -827,6 +831,14 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, return -EOPNOTSUPP; } +static inline int +devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val) +{ + return -EOPNOTSUPP; +} + static inline void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { -- cgit v1.2.3 From 5473a7bdad78f2efe8ee508e8c7bbb762896e78f Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:24 +0530 Subject: devlink: Add support for driverinit set value for devlink_port Add support for "driverinit" configuration mode value for devlink_port configuration parameters. Add devlink_port_param_driverinit_value_set() function to help the driver set the value to devlink_port. Also, move the common code to __devlink_param_driverinit_value_set() to be used by both device and port params. v7->v8: Re-order the definitions as follows: __devlink_param_driverinit_value_get __devlink_param_driverinit_value_set devlink_param_driverinit_value_get devlink_param_driverinit_value_set devlink_port_param_driverinit_value_get devlink_port_param_driverinit_value_set Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3943072d3552..ae2ccf297946 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -582,6 +582,9 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, u32 param_id, union devlink_param_value *init_val); +int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); @@ -839,6 +842,14 @@ devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, return -EOPNOTSUPP; } +static inline int +devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val) +{ + return -EOPNOTSUPP; +} + static inline void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { -- cgit v1.2.3 From c1e5786d6771c67fe044c3bcaa23e631e0503261 Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:25 +0530 Subject: devlink: Add devlink notifications support for port params Add notification call for devlink port param set, register and unregister functions. Add devlink_port_param_value_changed() function to enable the driver notify devlink on value change. Driver should use this function after value was changed on any configuration mode part to driverinit. v7->v8: Order devlink_port_param_value_changed() definitions followed by devlink_param_value_changed() Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++++ include/uapi/linux/devlink.h | 2 ++ 2 files changed, 10 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index ae2ccf297946..ceb5e89d74d6 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -586,6 +586,8 @@ int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, u32 param_id, union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); +void devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); struct devlink_region *devlink_region_create(struct devlink *devlink, @@ -855,6 +857,12 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id) { } +static inline void +devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id) +{ +} + static inline void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src) diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 3658fb20b190..61b4447a6c5b 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -91,6 +91,8 @@ enum devlink_command { DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ DEVLINK_CMD_PORT_PARAM_SET, + DEVLINK_CMD_PORT_PARAM_NEW, + DEVLINK_CMD_PORT_PARAM_DEL, /* add new commands above here */ __DEVLINK_CMD_MAX, -- cgit v1.2.3 From b639583f9e36d044ac1b13090ae812266992cbac Mon Sep 17 00:00:00 2001 From: Vasundhara Volam Date: Mon, 28 Jan 2019 18:00:26 +0530 Subject: devlink: Add a generic wake_on_lan port parameter wake_on_lan - Enables Wake on Lan for this port. If enabled, the controller asserts a wake pin based on the WOL type. v2->v3: - Define only WOL types used now and define them as bitfield, so that mutliple WOL types can be enabled upon power on. - Modify "wake-on-lan" name to "wake_on_lan" to be symmetric with previous definitions. - Rename DEVLINK_PARAM_WOL_XXX to DEVLINK_PARAM_WAKE_XXX to be symmetrical with ethtool WOL definitions. Cc: Jiri Pirko Signed-off-by: Vasundhara Volam Signed-off-by: David S. Miller --- include/net/devlink.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index ceb5e89d74d6..85c9eabaf056 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -367,12 +367,17 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, + DEVLINK_PARAM_GENERIC_ID_WOL, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1, }; +enum devlink_param_wol_types { + DEVLINK_PARAM_WAKE_MAGIC = (1 << 0), +}; + #define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME "internal_error_reset" #define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL @@ -397,6 +402,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME "fw_load_policy" #define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE DEVLINK_PARAM_TYPE_U8 +#define DEVLINK_PARAM_GENERIC_WOL_NAME "wake_on_lan" +#define DEVLINK_PARAM_GENERIC_WOL_TYPE DEVLINK_PARAM_TYPE_U8 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ -- cgit v1.2.3 From 80df2704a375bb4b3c9c5cce9c00052361b16d61 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 28 Jan 2019 15:08:23 +0800 Subject: sctp: introduce SCTP_FUTURE/CURRENT/ALL_ASSOC This patch is to add 3 constants SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and SCTP_ALL_ASSOC for reserved assoc_ids, as defined in rfc6458#section-7.2. And add the process for them when doing lookup and inserting in sctp_id2assoc and sctp_assoc_set_id. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d584073532b8..b8f2c4d56532 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -59,6 +59,10 @@ typedef __s32 sctp_assoc_t; +#define SCTP_FUTURE_ASSOC 0 +#define SCTP_CURRENT_ASSOC 1 +#define SCTP_ALL_ASSOC 2 + /* The following symbols come from the Sockets API Extensions for * SCTP . */ -- cgit v1.2.3 From 8add543e369d67ccd42f7e67d68866b4d606f632 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 28 Jan 2019 15:08:29 +0800 Subject: sctp: add SCTP_FUTURE_ASSOC for SCTP_PEER_ADDR_THLDS sockopt Check with SCTP_FUTURE_ASSOC instead in sctp_set/getsockopt_paddr_thresholds, it's compatible with 0. It also adds pf_retrans in sctp_sock to support SCTP_FUTURE_ASSOC. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 003020eb6e66..a5a46b1c9261 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -199,6 +199,8 @@ struct sctp_sock { __u32 flowlabel; __u8 dscp; + int pf_retrans; + /* The initial Path MTU to use for new associations. */ __u32 pathmtu; -- cgit v1.2.3 From 7efba10d6bd22030fb5931e50bf97496f932f00e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 28 Jan 2019 15:08:46 +0800 Subject: sctp: add SCTP_FUTURE_ASOC and SCTP_CURRENT_ASSOC for SCTP_STREAM_SCHEDULER sockopt Check with SCTP_ALL_ASSOC instead in sctp_setsockopt_scheduler and check with SCTP_FUTURE_ASSOC instead in sctp_getsockopt_scheduler, it's compatible with 0. SCTP_CURRENT_ASSOC is supported for SCTP_STREAM_SCHEDULER in this patch. It also adds default_ss in sctp_sock to support SCTP_FUTURE_ASSOC. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a5a46b1c9261..58e4b23cecf4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -211,6 +211,8 @@ struct sctp_sock { /* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */ __u32 param_flags; + __u32 default_ss; + struct sctp_rtoinfo rtoinfo; struct sctp_paddrparams paddrparam; struct sctp_assocparams assocparams; -- cgit v1.2.3 From a97cfe4de1bee89db3286ad0a4201dc6d2b72456 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 30 Jan 2019 08:58:34 +0000 Subject: mlxsw: spectrum_acl: Add C-TCAM spill tracepoint Add some visibility to the rule addition process and trace whenever rule spilled into C-TCAM. Signed-off-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/trace/events/mlxsw.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 include/trace/events/mlxsw.h (limited to 'include') diff --git a/include/trace/events/mlxsw.h b/include/trace/events/mlxsw.h new file mode 100644 index 000000000000..6c2bafcade18 --- /dev/null +++ b/include/trace/events/mlxsw.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlxsw + +#if !defined(_MLXSW_TRACEPOINT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _MLXSW_TRACEPOINT_H + +#include + +struct mlxsw_sp; +struct mlxsw_sp_acl_atcam_region; + +TRACE_EVENT(mlxsw_sp_acl_atcam_entry_add_ctcam_spill, + TP_PROTO(const struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_acl_atcam_region *aregion), + + TP_ARGS(mlxsw_sp, aregion), + + TP_STRUCT__entry( + __field(const void *, mlxsw_sp) + __field(const void *, aregion) + ), + + TP_fast_assign( + __entry->mlxsw_sp = mlxsw_sp; + __entry->aregion = aregion; + ), + + TP_printk("mlxsw_sp %p, aregion %p", + __entry->mlxsw_sp, __entry->aregion) +); + +#endif /* _MLXSW_TRACEPOINT_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3