From 4248b0da460839e30eaaad78992b9a1dd3e63e21 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 6 Aug 2015 15:46:20 -0700 Subject: fs, file table: reinit files_stat.max_files after deferred memory initialisation Dave Hansen reported the following; My laptop has been behaving strangely with 4.2-rc2. Once I log in to my X session, I start getting all kinds of strange errors from applications and see this in my dmesg: VFS: file-max limit 8192 reached The problem is that the file-max is calculated before memory is fully initialised and miscalculates how much memory the kernel is using. This patch recalculates file-max after deferred memory initialisation. Note that using memory hotplug infrastructure would not have avoided this problem as the value is not recalculated after memory hot-add. 4.1: files_stat.max_files = 6582781 4.2-rc2: files_stat.max_files = 8192 4.2-rc2 patched: files_stat.max_files = 6562467 Small differences with the patch applied and 4.1 but not enough to matter. Signed-off-by: Mel Gorman Reported-by: Dave Hansen Cc: Nicolai Stange Cc: Dave Hansen Cc: Alex Ng Cc: Fengguang Wu Cc: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cc008c338f5a..84b783f277f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -55,7 +55,8 @@ struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); -extern void __init files_init(unsigned long); +extern void __init files_init(void); +extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); @@ -2245,7 +2246,7 @@ extern int ioctl_preallocate(struct file *filp, void __user *argp); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); -extern void __init vfs_caches_init(unsigned long); +extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; -- cgit v1.3-18-gd494 From f4c18e6f7b5bbb5b528b3334115806b0d76f50f9 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:08 -0700 Subject: mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_* The race condition addressed in commit add05cecef80 ("mm: soft-offline: don't free target page in successful page migration") was not closed completely, because that can happen not only for soft-offline, but also for hard-offline. Consider that a slab page is about to be freed into buddy pool, and then an uncorrected memory error hits the page just after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not necessary because the data on the affected page is not consumed. To solve it, this patch drops __PG_HWPOISON from page flag checks at allocation/free time. I think it's justified because __PG_HWPOISON flags is defined to prevent the page from being reused, and setting it outside the page's alloc-free cycle is a designed behavior (not a bug.) For recent months, I was annoyed about BUG_ON when soft-offlined page remains on lru cache list for a while, which is avoided by calling put_page() instead of putback_lru_page() in page migration's success path. This means that this patch reverts a major change from commit add05cecef80 about the new refcounting rule of soft-offlined pages, so "reuse window" revives. This will be closed by a subsequent patch. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 10 +++++++--- mm/huge_memory.c | 7 +------ mm/migrate.c | 5 ++++- mm/page_alloc.c | 4 ++++ 4 files changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f34e040b34e9..41c93844fb1d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -631,15 +631,19 @@ static inline void ClearPageSlabPfmemalloc(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ + 1 << PG_unevictable | __PG_MLOCKED | \ __PG_COMPOUND_LOCK) /* * Flags checked when a page is prepped for return by the page allocator. - * Pages being prepped should not have any flags set. It they are set, + * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. + * + * __PG_HWPOISON is exceptional because it needs to be kept beyond page's + * alloc-free cycle to prevent from reusing the page. */ -#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1) +#define PAGE_FLAGS_CHECK_AT_PREP \ + (((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1 << PG_private | 1 << PG_private_2) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c107094f79ba..097c7a4bfbd9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1676,12 +1676,7 @@ static void __split_huge_page_refcount(struct page *page, /* after clearing PageTail the gup refcount can be released */ smp_mb__after_atomic(); - /* - * retain hwpoison flag of the poisoned tail page: - * fix for the unsuitable process killed on Guest Machine(KVM) - * by the memory-failure. - */ - page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON; + page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (page->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | diff --git a/mm/migrate.c b/mm/migrate.c index ee401e4e5ef1..f2415be7d93b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -950,7 +950,10 @@ out: list_del(&page->lru); dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); - if (reason != MR_MEMORY_FAILURE) + /* Soft-offlined page shouldn't go through lru cache list */ + if (reason == MR_MEMORY_FAILURE) + put_page(page); + else putback_lru_page(page); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cb61f44eb3fc..beda41710802 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1296,6 +1296,10 @@ static inline int check_new_page(struct page *page) bad_reason = "non-NULL mapping"; if (unlikely(atomic_read(&page->_count) != 0)) bad_reason = "nonzero _count"; + if (unlikely(page->flags & __PG_HWPOISON)) { + bad_reason = "HWPoisoned (hardware-corrupted)"; + bad_flags = __PG_HWPOISON; + } if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) { bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set"; bad_flags = PAGE_FLAGS_CHECK_AT_PREP; -- cgit v1.3-18-gd494 From ffe8690c85b8426db7783064724d106702f1b1e8 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 6 Aug 2015 07:02:32 +0000 Subject: perf: add the necessary core perf APIs when accessing events counters in eBPF programs This patch add three core perf APIs: - perf_event_attrs(): export the struct perf_event_attr from struct perf_event; - perf_event_get(): get the struct perf_event from the given fd; - perf_event_read_local(): read the events counters active on the current CPU; These APIs are needed when accessing events counters in eBPF programs. The API perf_event_read_local() comes from Peter and I add the corresponding SOB. Signed-off-by: Kaixu Xia Signed-off-by: Peter Zijlstra Signed-off-by: David S. Miller --- include/linux/perf_event.h | 10 ++++++ kernel/events/core.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2027809433b3..092a0e8a479a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -641,6 +641,8 @@ extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); +extern struct perf_event *perf_event_get(unsigned int fd); +extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); @@ -659,6 +661,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); +extern u64 perf_event_read_local(struct perf_event *event); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); @@ -979,6 +982,12 @@ static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } +static inline struct perf_event *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } +static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) +{ + return ERR_PTR(-EINVAL); +} +static inline u64 perf_event_read_local(struct perf_event *event) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } @@ -1011,6 +1020,7 @@ static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } +static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_NO_HZ_FULL) diff --git a/kernel/events/core.c b/kernel/events/core.c index d3dae3419b99..e2c6a8886d4d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3212,6 +3212,59 @@ static inline u64 perf_event_count(struct perf_event *event) return __perf_event_count(event); } +/* + * NMI-safe method to read a local event, that is an event that + * is: + * - either for the current task, or for this CPU + * - does not have inherit set, for inherited task events + * will not be local and we cannot read them atomically + * - must not have a pmu::count method + */ +u64 perf_event_read_local(struct perf_event *event) +{ + unsigned long flags; + u64 val; + + /* + * Disabling interrupts avoids all counter scheduling (context + * switches, timer based rotation and IPIs). + */ + local_irq_save(flags); + + /* If this is a per-task event, it must be for current */ + WARN_ON_ONCE((event->attach_state & PERF_ATTACH_TASK) && + event->hw.target != current); + + /* If this is a per-CPU event, it must be for this CPU */ + WARN_ON_ONCE(!(event->attach_state & PERF_ATTACH_TASK) && + event->cpu != smp_processor_id()); + + /* + * It must not be an event with inherit set, we cannot read + * all child counters from atomic context. + */ + WARN_ON_ONCE(event->attr.inherit); + + /* + * It must not have a pmu::count method, those are not + * NMI safe. + */ + WARN_ON_ONCE(event->pmu->count); + + /* + * If the event is currently on this CPU, its either a per-task event, + * or local to this CPU. Furthermore it means its ACTIVE (otherwise + * oncpu == -1). + */ + if (event->oncpu == smp_processor_id()) + event->pmu->read(event); + + val = local64_read(&event->count); + local_irq_restore(flags); + + return val; +} + static u64 perf_event_read(struct perf_event *event) { /* @@ -8574,6 +8627,31 @@ void perf_event_delayed_put(struct task_struct *task) WARN_ON_ONCE(task->perf_event_ctxp[ctxn]); } +struct perf_event *perf_event_get(unsigned int fd) +{ + int err; + struct fd f; + struct perf_event *event; + + err = perf_fget_light(fd, &f); + if (err) + return ERR_PTR(err); + + event = f.file->private_data; + atomic_long_inc(&event->refcount); + fdput(f); + + return event; +} + +const struct perf_event_attr *perf_event_attrs(struct perf_event *event) +{ + if (!event) + return ERR_PTR(-EINVAL); + + return &event->attr; +} + /* * inherit a event from parent task to child task: */ -- cgit v1.3-18-gd494 From 2a36f0b92eb638dd023870574eb471b1c56be9ad Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Thu, 6 Aug 2015 07:02:33 +0000 Subject: bpf: Make the bpf_prog_array_map more generic All the map backends are of generic nature. In order to avoid adding much special code into the eBPF core, rewrite part of the bpf_prog_array map code and make it more generic. So the new perf_event_array map type can reuse most of code with bpf_prog_array map and add fewer lines of special code. Signed-off-by: Wang Nan Signed-off-by: Kaixu Xia Signed-off-by: David S. Miller --- arch/x86/net/bpf_jit_comp.c | 6 ++-- include/linux/bpf.h | 8 +++-- kernel/bpf/arraymap.c | 80 +++++++++++++++++++++++++++------------------ kernel/bpf/core.c | 2 +- kernel/bpf/syscall.c | 2 +- 5 files changed, 60 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index ec5214f39aa8..70efcd0940f9 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -246,7 +246,7 @@ static void emit_prologue(u8 **pprog) * goto out; * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; - * prog = array->prog[index]; + * prog = array->ptrs[index]; * if (prog == NULL) * goto out; * goto *(prog->bpf_func + prologue_size); @@ -284,9 +284,9 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ - /* prog = array->prog[index]; */ + /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ - offsetof(struct bpf_array, prog)); + offsetof(struct bpf_array, ptrs)); EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ /* if (prog == NULL) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 139d6d2e123f..d495211d63d1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -24,6 +24,10 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + + /* funcs called by prog_array and perf_event_array map */ + void *(*map_fd_get_ptr) (struct bpf_map *map, int fd); + void (*map_fd_put_ptr) (void *ptr); }; struct bpf_map { @@ -142,13 +146,13 @@ struct bpf_array { bool owner_jited; union { char value[0] __aligned(8); - struct bpf_prog *prog[0] __aligned(8); + void *ptrs[0] __aligned(8); }; }; #define MAX_TAIL_CALL_CNT 32 u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5); -void bpf_prog_array_map_clear(struct bpf_map *map); +void bpf_fd_array_map_clear(struct bpf_map *map); bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index cb31229a6fa4..45df6572ecfd 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -150,15 +150,15 @@ static int __init register_array_map(void) } late_initcall(register_array_map); -static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) +static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr) { - /* only bpf_prog file descriptors can be stored in prog_array map */ + /* only file descriptors can be stored in this type of map */ if (attr->value_size != sizeof(u32)) return ERR_PTR(-EINVAL); return array_map_alloc(attr); } -static void prog_array_map_free(struct bpf_map *map) +static void fd_array_map_free(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; @@ -167,21 +167,21 @@ static void prog_array_map_free(struct bpf_map *map) /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) - BUG_ON(array->prog[i] != NULL); + BUG_ON(array->ptrs[i] != NULL); kvfree(array); } -static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key) +static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) { return NULL; } /* only called from syscall */ -static int prog_array_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 map_flags) +static int fd_array_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); - struct bpf_prog *prog, *old_prog; + void *new_ptr, *old_ptr; u32 index = *(u32 *)key, ufd; if (map_flags != BPF_ANY) @@ -191,57 +191,75 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key, return -E2BIG; ufd = *(u32 *)value; - prog = bpf_prog_get(ufd); - if (IS_ERR(prog)) - return PTR_ERR(prog); - - if (!bpf_prog_array_compatible(array, prog)) { - bpf_prog_put(prog); - return -EINVAL; - } + new_ptr = map->ops->map_fd_get_ptr(map, ufd); + if (IS_ERR(new_ptr)) + return PTR_ERR(new_ptr); - old_prog = xchg(array->prog + index, prog); - if (old_prog) - bpf_prog_put_rcu(old_prog); + old_ptr = xchg(array->ptrs + index, new_ptr); + if (old_ptr) + map->ops->map_fd_put_ptr(old_ptr); return 0; } -static int prog_array_map_delete_elem(struct bpf_map *map, void *key) +static int fd_array_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_array *array = container_of(map, struct bpf_array, map); - struct bpf_prog *old_prog; + void *old_ptr; u32 index = *(u32 *)key; if (index >= array->map.max_entries) return -E2BIG; - old_prog = xchg(array->prog + index, NULL); - if (old_prog) { - bpf_prog_put_rcu(old_prog); + old_ptr = xchg(array->ptrs + index, NULL); + if (old_ptr) { + map->ops->map_fd_put_ptr(old_ptr); return 0; } else { return -ENOENT; } } +static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct bpf_prog *prog = bpf_prog_get(fd); + if (IS_ERR(prog)) + return prog; + + if (!bpf_prog_array_compatible(array, prog)) { + bpf_prog_put(prog); + return ERR_PTR(-EINVAL); + } + return prog; +} + +static void prog_fd_array_put_ptr(void *ptr) +{ + struct bpf_prog *prog = ptr; + + bpf_prog_put_rcu(prog); +} + /* decrement refcnt of all bpf_progs that are stored in this map */ -void bpf_prog_array_map_clear(struct bpf_map *map) +void bpf_fd_array_map_clear(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; for (i = 0; i < array->map.max_entries; i++) - prog_array_map_delete_elem(map, &i); + fd_array_map_delete_elem(map, &i); } static const struct bpf_map_ops prog_array_ops = { - .map_alloc = prog_array_map_alloc, - .map_free = prog_array_map_free, + .map_alloc = fd_array_map_alloc, + .map_free = fd_array_map_free, .map_get_next_key = array_map_get_next_key, - .map_lookup_elem = prog_array_map_lookup_elem, - .map_update_elem = prog_array_map_update_elem, - .map_delete_elem = prog_array_map_delete_elem, + .map_lookup_elem = fd_array_map_lookup_elem, + .map_update_elem = fd_array_map_update_elem, + .map_delete_elem = fd_array_map_delete_elem, + .map_fd_get_ptr = prog_fd_array_get_ptr, + .map_fd_put_ptr = prog_fd_array_put_ptr, }; static struct bpf_map_type_list prog_array_type __read_mostly = { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index fafa74161445..67c380cfa9ca 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -450,7 +450,7 @@ select_insn: tail_call_cnt++; - prog = READ_ONCE(array->prog[index]); + prog = READ_ONCE(array->ptrs[index]); if (unlikely(!prog)) goto out; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a1b14d197a4f..dc9b464fefa9 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -72,7 +72,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp) /* prog_array stores refcnt-ed bpf_prog pointers * release them all when user space closes prog_array_fd */ - bpf_prog_array_map_clear(map); + bpf_fd_array_map_clear(map); bpf_map_put(map); return 0; -- cgit v1.3-18-gd494 From ea317b267e9d03a8241893aa176fba7661d07579 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 6 Aug 2015 07:02:34 +0000 Subject: bpf: Add new bpf map type to store the pointer to struct perf_event Introduce a new bpf map type 'BPF_MAP_TYPE_PERF_EVENT_ARRAY'. This map only stores the pointer to struct perf_event. The user space event FDs from perf_event_open() syscall are converted to the pointer to struct perf_event and stored in map. Signed-off-by: Kaixu Xia Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/arraymap.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d495211d63d1..4fc1f4070789 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -10,6 +10,7 @@ #include #include #include +#include struct bpf_map; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2ce13c109b00..a1814e8e53a7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -114,6 +114,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, }; enum bpf_prog_type { diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 45df6572ecfd..29ace107f236 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -273,3 +273,60 @@ static int __init register_prog_array_map(void) return 0; } late_initcall(register_prog_array_map); + +static void perf_event_array_map_free(struct bpf_map *map) +{ + bpf_fd_array_map_clear(map); + fd_array_map_free(map); +} + +static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) +{ + struct perf_event *event; + const struct perf_event_attr *attr; + + event = perf_event_get(fd); + if (IS_ERR(event)) + return event; + + attr = perf_event_attrs(event); + if (IS_ERR(attr)) + return (void *)attr; + + if (attr->type != PERF_TYPE_RAW && + attr->type != PERF_TYPE_HARDWARE) { + perf_event_release_kernel(event); + return ERR_PTR(-EINVAL); + } + return event; +} + +static void perf_event_fd_array_put_ptr(void *ptr) +{ + struct perf_event *event = ptr; + + perf_event_release_kernel(event); +} + +static const struct bpf_map_ops perf_event_array_ops = { + .map_alloc = fd_array_map_alloc, + .map_free = perf_event_array_map_free, + .map_get_next_key = array_map_get_next_key, + .map_lookup_elem = fd_array_map_lookup_elem, + .map_update_elem = fd_array_map_update_elem, + .map_delete_elem = fd_array_map_delete_elem, + .map_fd_get_ptr = perf_event_fd_array_get_ptr, + .map_fd_put_ptr = perf_event_fd_array_put_ptr, +}; + +static struct bpf_map_type_list perf_event_array_type __read_mostly = { + .ops = &perf_event_array_ops, + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, +}; + +static int __init register_perf_event_array_map(void) +{ + bpf_register_map_type(&perf_event_array_type); + return 0; +} +late_initcall(register_perf_event_array_map); -- cgit v1.3-18-gd494 From 35578d7984003097af2b1e34502bc943d40c1804 Mon Sep 17 00:00:00 2001 From: Kaixu Xia Date: Thu, 6 Aug 2015 07:02:35 +0000 Subject: bpf: Implement function bpf_perf_event_read() that get the selected hardware PMU conuter According to the perf_event_map_fd and index, the function bpf_perf_event_read() can convert the corresponding map value to the pointer to struct perf_event and return the Hardware PMU counter value. Signed-off-by: Kaixu Xia Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/verifier.c | 48 +++++++++++++++++++++++++++++++++--------------- kernel/trace/bpf_trace.c | 31 +++++++++++++++++++++++++++++++ 4 files changed, 66 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4fc1f4070789..f57d7fed9ec3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -190,6 +190,7 @@ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_perf_event_read_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a1814e8e53a7..92a48e2d5461 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -271,6 +271,7 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_key, BPF_FUNC_skb_set_tunnel_key, + BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ __BPF_FUNC_MAX_ID, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index cd307df98cb3..48e1c7192560 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -238,6 +238,14 @@ static const char * const reg_type_str[] = { [CONST_IMM] = "imm", }; +static const struct { + int map_type; + int func_id; +} func_limit[] = { + {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, + {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, +}; + static void print_verifier_state(struct verifier_env *env) { enum bpf_reg_type t; @@ -837,6 +845,28 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return err; } +static int check_map_func_compatibility(struct bpf_map *map, int func_id) +{ + bool bool_map, bool_func; + int i; + + if (!map) + return 0; + + for (i = 0; i <= ARRAY_SIZE(func_limit); i++) { + bool_map = (map->map_type == func_limit[i].map_type); + bool_func = (func_id == func_limit[i].func_id); + /* only when map & func pair match it can continue. + * don't allow any other map type to be passed into + * the special func; + */ + if (bool_map != bool_func) + return -EINVAL; + } + + return 0; +} + static int check_call(struct verifier_env *env, int func_id) { struct verifier_state *state = &env->cur_state; @@ -912,21 +942,9 @@ static int check_call(struct verifier_env *env, int func_id) return -EINVAL; } - if (map && map->map_type == BPF_MAP_TYPE_PROG_ARRAY && - func_id != BPF_FUNC_tail_call) - /* prog_array map type needs extra care: - * only allow to pass it into bpf_tail_call() for now. - * bpf_map_delete_elem() can be allowed in the future, - * while bpf_map_update_elem() must only be done via syscall - */ - return -EINVAL; - - if (func_id == BPF_FUNC_tail_call && - map->map_type != BPF_MAP_TYPE_PROG_ARRAY) - /* don't allow any other map type to be passed into - * bpf_tail_call() - */ - return -EINVAL; + err = check_map_func_compatibility(map, func_id); + if (err) + return err; return 0; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 88a041adee90..ef9936df1b04 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -158,6 +158,35 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } +static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) +{ + struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; + struct bpf_array *array = container_of(map, struct bpf_array, map); + struct perf_event *event; + + if (unlikely(index >= array->map.max_entries)) + return -E2BIG; + + event = (struct perf_event *)array->ptrs[index]; + if (!event) + return -ENOENT; + + /* + * we don't know if the function is run successfully by the + * return value. It can be judged in other places, such as + * eBPF programs. + */ + return perf_event_read_local(event); +} + +const struct bpf_func_proto bpf_perf_event_read_proto = { + .func = bpf_perf_event_read, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -183,6 +212,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_perf_event_read: + return &bpf_perf_event_read_proto; default: return NULL; } -- cgit v1.3-18-gd494 From 7a76a021cd5a292be875fbc616daf03eab1e6996 Mon Sep 17 00:00:00 2001 From: Benjamin Poirier Date: Fri, 7 Aug 2015 09:32:21 -0700 Subject: net-timestamp: Update skb_complete_tx_timestamp comment After "62bccb8 net-timestamp: Make the clone operation stand-alone from phy timestamping" the hwtstamps parameter of skb_complete_tx_timestamp() may no longer be NULL. Signed-off-by: Benjamin Poirier Cc: Alexander Duyck Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d6cdd6e87d53..22b6d9ca1654 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2884,11 +2884,11 @@ static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers - * must call this function to return the skb back to the stack, with - * or without a timestamp. + * must call this function to return the skb back to the stack with a + * timestamp. * * @skb: clone of the the original outgoing packet - * @hwtstamps: hardware time stamps, may be NULL if not available + * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, -- cgit v1.3-18-gd494 From 4c96b7dc0d393f12c17e0d81db15aa4a820a6ab3 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Wed, 12 Aug 2015 17:06:26 -0500 Subject: Add a matching set of device_ functions for determining mac/phy OF has some helper functions for parsing MAC and PHY settings. In cases where the platform is providing this information rather than the device itself, there needs to be similar functions for ACPI. These functions are slightly modified versions of the ones in of_net which can use information provided via DT or ACPI. Signed-off-by: Jeremy Linton Signed-off-by: David S. Miller --- drivers/base/property.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/property.h | 4 +++ 2 files changed, 77 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index f3f6d167f3f1..2e8cd147f02d 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -16,6 +16,8 @@ #include #include #include +#include +#include /** * device_add_property_set - Add a collection of properties to a device object. @@ -533,3 +535,74 @@ bool device_dma_is_coherent(struct device *dev) return coherent; } EXPORT_SYMBOL_GPL(device_dma_is_coherent); + +/** + * device_get_phy_mode - Get phy mode for given device_node + * @dev: Pointer to the given device + * + * The function gets phy interface string from property 'phy-mode' or + * 'phy-connection-type', and return its index in phy_modes table, or errno in + * error case. + */ +int device_get_phy_mode(struct device *dev) +{ + const char *pm; + int err, i; + + err = device_property_read_string(dev, "phy-mode", &pm); + if (err < 0) + err = device_property_read_string(dev, + "phy-connection-type", &pm); + if (err < 0) + return err; + + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) + if (!strcasecmp(pm, phy_modes(i))) + return i; + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(device_get_phy_mode); + +static void *device_get_mac_addr(struct device *dev, + const char *name, char *addr, + int alen) +{ + int ret = device_property_read_u8_array(dev, name, addr, alen); + + if (ret == 0 && is_valid_ether_addr(addr)) + return addr; + return NULL; +} + +/** + * Search the device tree for the best MAC address to use. 'mac-address' is + * checked first, because that is supposed to contain to "most recent" MAC + * address. If that isn't set, then 'local-mac-address' is checked next, + * because that is the default address. If that isn't set, then the obsolete + * 'address' is checked, just in case we're using an old device tree. + * + * Note that the 'address' property is supposed to contain a virtual address of + * the register set, but some DTS files have redefined that property to be the + * MAC address. + * + * All-zero MAC addresses are rejected, because those could be properties that + * exist in the device tree, but were not set by U-Boot. For example, the + * DTS could define 'mac-address' and 'local-mac-address', with zero MAC + * addresses. Some older U-Boots only initialized 'local-mac-address'. In + * this case, the real MAC is in 'local-mac-address', and 'mac-address' exists + * but is all zeros. +*/ +void *device_get_mac_address(struct device *dev, char *addr, int alen) +{ + addr = device_get_mac_addr(dev, "mac-address", addr, alen); + if (addr) + return addr; + + addr = device_get_mac_addr(dev, "local-mac-address", addr, alen); + if (addr) + return addr; + + return device_get_mac_addr(dev, "address", addr, alen); +} +EXPORT_SYMBOL(device_get_mac_address); diff --git a/include/linux/property.h b/include/linux/property.h index 76ebde9c11d4..a59c6ee566c2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -166,4 +166,8 @@ void device_add_property_set(struct device *dev, struct property_set *pset); bool device_dma_is_coherent(struct device *dev); +int device_get_phy_mode(struct device *dev); + +void *device_get_mac_address(struct device *dev, char *addr, int alen); + #endif /* _LINUX_PROPERTY_H_ */ -- cgit v1.3-18-gd494 From 35103d11173b8fea874183f8aa508ae71234d299 Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Thu, 13 Aug 2015 10:39:01 -0400 Subject: net: ipv6 sysctl option to ignore routes when nexthop link is down Like the ipv4 patch with a similar title, this adds a sysctl to allow the user to change routing behavior based on whether or not the interface associated with the nexthop was an up or down link. The default setting preserves the current behavior, but anyone that enables it will notice that nexthops on down interfaces will no longer be selected: net.ipv6.conf.all.ignore_routes_with_linkdown = 0 net.ipv6.conf.default.ignore_routes_with_linkdown = 0 net.ipv6.conf.lo.ignore_routes_with_linkdown = 0 ... When the above sysctls are set, not only will link status be reported to userspace, but an indication that a nexthop is dead and will not be used is also reported. 1000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium 1000::/8 via 8000::2 dev p8p1 metric 1024 pref medium 7000::/8 dev p7p1 proto kernel metric 256 dead linkdown pref medium 8000::/8 dev p8p1 proto kernel metric 256 pref medium 9000::/8 via 8000::2 dev p8p1 metric 2048 pref medium 9000::/8 via 7000::2 dev p7p1 metric 1024 dead linkdown pref medium fe80::/64 dev p7p1 proto kernel metric 256 dead linkdown pref medium fe80::/64 dev p8p1 proto kernel metric 256 pref medium This also adds devconf support and notification when sysctl values change. v2: drop use of rt6i_nhflags since it is not needed right now Signed-off-by: Andy Gospodarek Signed-off-by: Dinesh Dutt Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 105 +++++++++++++++++++++++++++++++++++++++++++++- net/ipv6/route.c | 11 ++++- 4 files changed, 116 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index cb9dcad72372..f1f32af6d9b9 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -31,6 +31,7 @@ struct ipv6_devconf { __s32 accept_ra_defrtr; __s32 accept_ra_min_hop_limit; __s32 accept_ra_pinfo; + __s32 ignore_routes_with_linkdown; #ifdef CONFIG_IPV6_ROUTER_PREF __s32 accept_ra_rtr_pref; __s32 rtr_probe_interval; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 80f3b74446a1..38b4fef20219 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -173,6 +173,7 @@ enum { DEVCONF_STABLE_SECRET, DEVCONF_USE_OIF_ADDRS_ONLY, DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT, + DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 53e3a9d756b0..5dfbac72f1ab 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -214,6 +214,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .initialized = false, }, .use_oif_addrs_only = 0, + .ignore_routes_with_linkdown = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -257,6 +258,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .initialized = false, }, .use_oif_addrs_only = 0, + .ignore_routes_with_linkdown = 0, }; /* Check if a valid qdisc is available */ @@ -472,6 +474,9 @@ static int inet6_netconf_msgsize_devconf(int type) if (type == -1 || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); + if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) + size += nla_total_size(4); + return size; } @@ -508,6 +513,11 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) goto nla_put_failure; + if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && + nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + devconf->ignore_routes_with_linkdown) < 0) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -544,6 +554,7 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, + [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet6_netconf_get_devconf(struct sk_buff *in_skb, @@ -766,6 +777,63 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) rt6_purge_dflt_routers(net); return 1; } + +static void addrconf_linkdown_change(struct net *net, __s32 newf) +{ + struct net_device *dev; + struct inet6_dev *idev; + + for_each_netdev(net, dev) { + idev = __in6_dev_get(dev); + if (idev) { + int changed = (!idev->cnf.ignore_routes_with_linkdown) ^ (!newf); + + idev->cnf.ignore_routes_with_linkdown = newf; + if (changed) + inet6_netconf_notify_devconf(dev_net(dev), + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + dev->ifindex, + &idev->cnf); + } + } +} + +static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) +{ + struct net *net; + int old; + + if (!rtnl_trylock()) + return restart_syscall(); + + net = (struct net *)table->extra2; + old = *p; + *p = newf; + + if (p == &net->ipv6.devconf_dflt->ignore_routes_with_linkdown) { + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + rtnl_unlock(); + return 0; + } + + if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { + net->ipv6.devconf_dflt->ignore_routes_with_linkdown = newf; + addrconf_linkdown_change(net, newf); + if ((!newf) ^ (!old)) + inet6_netconf_notify_devconf(net, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + } + rtnl_unlock(); + + return 1; +} + #endif /* Nobody refers to this ifaddr, destroy it */ @@ -4616,6 +4684,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc; array[DEVCONF_ACCEPT_RA_FROM_LOCAL] = cnf->accept_ra_from_local; array[DEVCONF_ACCEPT_RA_MTU] = cnf->accept_ra_mtu; + array[DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN] = cnf->ignore_routes_with_linkdown; /* we omit DEVCONF_STABLE_SECRET for now */ array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; } @@ -5338,6 +5407,34 @@ out: return err; } +static +int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, + int write, + void __user *buffer, + size_t *lenp, + loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + struct ctl_table lctl; + int ret; + + /* ctl->data points to idev->cnf.ignore_routes_when_linkdown + * we should not modify it until we get the rtnl lock. + */ + lctl = *ctl; + lctl.data = &val; + + ret = proc_dointvec(&lctl, write, buffer, lenp, ppos); + + if (write) + ret = addrconf_fixup_linkdown(ctl, valp, val); + if (ret) + *ppos = pos; + return ret; +} + static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; @@ -5629,7 +5726,13 @@ static struct addrconf_sysctl_table .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, - + }, + { + .procname = "ignore_routes_with_linkdown", + .data = &ipv6_devconf.ignore_routes_with_linkdown, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_ignore_routes_with_linkdown, }, { /* sentinel */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 370f72785385..1c0217e61357 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -665,6 +665,12 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, { int m; bool match_do_rr = false; + struct inet6_dev *idev = rt->rt6i_idev; + struct net_device *dev = rt->dst.dev; + + if (dev && !netif_carrier_ok(dev) && + idev->cnf.ignore_routes_with_linkdown) + goto out; if (rt6_check_expired(rt)) goto out; @@ -2887,8 +2893,11 @@ static int rt6_fill_node(struct net *net, else rtm->rtm_type = RTN_UNICAST; rtm->rtm_flags = 0; - if (!netif_carrier_ok(rt->dst.dev)) + if (!netif_carrier_ok(rt->dst.dev)) { rtm->rtm_flags |= RTNH_F_LINKDOWN; + if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown) + rtm->rtm_flags |= RTNH_F_DEAD; + } rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->rt6i_protocol; if (rt->rt6i_flags & RTF_DYNAMIC) -- cgit v1.3-18-gd494 From 4e3c89920cd3a6cfce22c6f537690747c26128dd Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 13 Aug 2015 14:59:00 -0600 Subject: net: Introduce VRF related flags and helpers Add a VRF_MASTER flag for interfaces and helper functions for determining if a device is a VRF_MASTER. Add link attribute for passing VRF_TABLE id. Add vrf_ptr to netdevice. Add various macros for determining if a device is a VRF device, the index of the master VRF device and table associated with VRF device. Signed-off-by: Shrijeet Mukherjee Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 +++++++ include/net/vrf.h | 139 +++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/if_link.h | 9 +++ 3 files changed, 168 insertions(+) create mode 100644 include/net/vrf.h (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 607b5f41f46f..f7a6ef2fae3a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1289,6 +1289,7 @@ enum netdev_priv_flags { IFF_XMIT_DST_RELEASE_PERM = 1<<22, IFF_IPVLAN_MASTER = 1<<23, IFF_IPVLAN_SLAVE = 1<<24, + IFF_VRF_MASTER = 1<<25, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1316,6 +1317,7 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE +#define IFF_VRF_MASTER IFF_VRF_MASTER /** * struct net_device - The DEVICE structure. @@ -1432,6 +1434,7 @@ enum netdev_priv_flags { * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data + * @vrf_ptr: VRF specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * * @last_rx: Time of last Rx @@ -1650,6 +1653,7 @@ struct net_device { struct dn_dev __rcu *dn_ptr; struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; + struct net_vrf_dev __rcu *vrf_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) @@ -3808,6 +3812,22 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_is_vrf(const struct net_device *dev) +{ + return dev->priv_flags & IFF_VRF_MASTER; +} + +static inline bool netif_index_is_vrf(struct net *net, int ifindex) +{ + struct net_device *dev = dev_get_by_index_rcu(net, ifindex); + bool rc = false; + + if (dev) + rc = netif_is_vrf(dev); + + return rc; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/include/net/vrf.h b/include/net/vrf.h new file mode 100644 index 000000000000..0484d29d4589 --- /dev/null +++ b/include/net/vrf.h @@ -0,0 +1,139 @@ +/* + * include/net/net_vrf.h - adds vrf dev structure definitions + * Copyright (c) 2015 Cumulus Networks + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_NET_VRF_H +#define __LINUX_NET_VRF_H + +struct net_vrf_dev { + struct rcu_head rcu; + int ifindex; /* ifindex of master dev */ + u32 tb_id; /* table id for VRF */ +}; + +struct slave { + struct list_head list; + struct net_device *dev; +}; + +struct slave_queue { + struct list_head all_slaves; + int num_slaves; +}; + +struct net_vrf { + struct slave_queue queue; + struct rtable *rth; + u32 tb_id; +}; + + +#if IS_ENABLED(CONFIG_NET_VRF) +/* called with rcu_read_lock() */ +static inline int vrf_master_ifindex_rcu(const struct net_device *dev) +{ + struct net_vrf_dev *vrf_ptr; + int ifindex = 0; + + if (!dev) + return 0; + + if (netif_is_vrf(dev)) + ifindex = dev->ifindex; + else { + vrf_ptr = rcu_dereference(dev->vrf_ptr); + if (vrf_ptr) + ifindex = vrf_ptr->ifindex; + } + + return ifindex; +} + +/* called with rcu_read_lock */ +static inline int vrf_dev_table_rcu(const struct net_device *dev) +{ + int tb_id = 0; + + if (dev) { + struct net_vrf_dev *vrf_ptr; + + vrf_ptr = rcu_dereference(dev->vrf_ptr); + if (vrf_ptr) + tb_id = vrf_ptr->tb_id; + } + return tb_id; +} + +static inline int vrf_dev_table(const struct net_device *dev) +{ + int tb_id; + + rcu_read_lock(); + tb_id = vrf_dev_table_rcu(dev); + rcu_read_unlock(); + + return tb_id; +} + +/* called with rtnl */ +static inline int vrf_dev_table_rtnl(const struct net_device *dev) +{ + int tb_id = 0; + + if (dev) { + struct net_vrf_dev *vrf_ptr; + + vrf_ptr = rtnl_dereference(dev->vrf_ptr); + if (vrf_ptr) + tb_id = vrf_ptr->tb_id; + } + return tb_id; +} + +/* caller has already checked netif_is_vrf(dev) */ +static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) +{ + struct rtable *rth = ERR_PTR(-ENETUNREACH); + struct net_vrf *vrf = netdev_priv(dev); + + if (vrf) { + rth = vrf->rth; + atomic_inc(&rth->dst.__refcnt); + } + return rth; +} + +#else +static inline int vrf_master_ifindex_rcu(const struct net_device *dev) +{ + return 0; +} + +static inline int vrf_dev_table_rcu(const struct net_device *dev) +{ + return 0; +} + +static inline int vrf_dev_table(const struct net_device *dev) +{ + return 0; +} + +static inline int vrf_dev_table_rtnl(const struct net_device *dev) +{ + return 0; +} + +static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) +{ + return ERR_PTR(-ENETUNREACH); +} +#endif + +#endif /* __LINUX_NET_VRF_H */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d450be36add2..313c305fd1ad 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -341,6 +341,15 @@ enum macvlan_macaddr_mode { #define MACVLAN_FLAG_NOPROMISC 1 +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + /* IPVLAN section */ enum { IFLA_IPVLAN_UNSPEC, -- cgit v1.3-18-gd494 From 2377799c084d86d22074cd4acd20edc32024d669 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 13 Jul 2015 12:17:25 +0200 Subject: average: provide macro to create static EWMA Having the EWMA parameters stored in the runtime struct imposes memory requirements for the constant values that could just be inlined in the code. This particularly makes sense if there are a lot of such structs, for example in mac80211 in the station table where each station has a number of these in an array, and there can be many stations. Provide a macro DECLARE_EWMA() that declares the necessary struct and inline functions to access it with the parameters hard-coded; using this also means the user no longer needs to 'select AVERAGE' as it's entirely self-contained. In the mac80211 case, on x86-64, this actually slightly *reduces* code size, while also saving 80 bytes of runtime memory per sta. Signed-off-by: Johannes Berg --- include/linux/average.h | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h index c6028fd742c1..60f8226c5652 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -27,4 +27,43 @@ static inline unsigned long ewma_read(const struct ewma *avg) return avg->internal >> avg->factor; } +#define DECLARE_EWMA(name, _factor, _weight) \ + struct ewma_##name { \ + unsigned long internal; \ + }; \ + static inline void ewma_##name##_init(struct ewma_##name *e) \ + { \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + e->internal = 0; \ + } \ + static inline unsigned long \ + ewma_##name##_read(struct ewma_##name *e) \ + { \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + return e->internal >> ilog2(_factor); \ + } \ + static inline void ewma_##name##_add(struct ewma_##name *e, \ + unsigned long val) \ + { \ + unsigned long internal = ACCESS_ONCE(e->internal); \ + unsigned long weight = ilog2(_weight); \ + unsigned long factor = ilog2(_factor); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_factor)); \ + BUILD_BUG_ON(!__builtin_constant_p(_weight)); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_factor); \ + BUILD_BUG_ON_NOT_POWER_OF_2(_weight); \ + \ + ACCESS_ONCE(e->internal) = internal ? \ + (((internal << weight) - internal) + \ + (val << factor)) >> weight : \ + (val << factor); \ + } + #endif /* _LINUX_AVERAGE_H */ -- cgit v1.3-18-gd494 From 8f9c98df949333f08b74e5df1caacf7e2c5e8552 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 19 Jul 2015 16:09:12 +0300 Subject: mac80211: fix BIT position for TDLS WIDE extended cap The bit was not according to ieee80211 specification. Fix that. Reviewed-by: Arik Nemtsov Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b9c7897dc566..cfa906f28b7a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2074,8 +2074,8 @@ enum ieee80211_tdls_actioncode { #define WLAN_EXT_CAPA5_TDLS_PROHIBITED BIT(6) #define WLAN_EXT_CAPA5_TDLS_CH_SW_PROHIBITED BIT(7) +#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(5) #define WLAN_EXT_CAPA8_OPMODE_NOTIF BIT(6) -#define WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED BIT(7) /* TDLS specific payload type in the LLC/SNAP header */ #define WLAN_TDLS_SNAP_RFTYPE 0x2 -- cgit v1.3-18-gd494 From fa8187c96471c49419c25d4ec3299d17d3f274b2 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 13 Aug 2015 19:01:06 +0200 Subject: net: declare new net_device priv_flag IFF_NO_QUEUE This private net_device flag can be set by drivers to inform that a device runs fine without a qdisc attached. This was formerly done by setting tx_queue_len to zero. Signed-off-by: Phil Sutter Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f7a6ef2fae3a..d131755516ca 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1262,6 +1262,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_NO_QUEUE: device can run without qdisc attached */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1290,6 +1291,7 @@ enum netdev_priv_flags { IFF_IPVLAN_MASTER = 1<<23, IFF_IPVLAN_SLAVE = 1<<24, IFF_VRF_MASTER = 1<<25, + IFF_NO_QUEUE = 1<<26, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1318,6 +1320,7 @@ enum netdev_priv_flags { #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE #define IFF_VRF_MASTER IFF_VRF_MASTER +#define IFF_NO_QUEUE IFF_NO_QUEUE /** * struct net_device - The DEVICE structure. -- cgit v1.3-18-gd494 From fbaff3ef859a86dc3df2128d2de9f8a6e255a967 Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Thu, 13 Aug 2015 18:34:03 -0700 Subject: net: fix endian check warning in etherdevice.h Sparse builds have been warning for a really long time now that etherdevice.h has a conversion that is unsafe. include/linux/etherdevice.h:79:32: warning: restricted __be16 degrades to integer This code change fixes the issue and generates the exact same assembly before/after (checked on x86_64) Fixes: 2c722fe1c821 (etherdevice: Optimize a few is__ether_addr functions) Signed-off-by: Jesse Brandeburg CC: Joe Perches Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 9012f8775208..eb049c622208 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -76,7 +76,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr) #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | - ((a[2] ^ b[2]) & m)) == 0; + (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif -- cgit v1.3-18-gd494 From 6fa1bcab6be6e9bd93f80e345c7e9a4ec7861df9 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Sun, 16 Aug 2015 16:04:50 +0300 Subject: net/mlx5e: Ethtool link speed setting fixes - Port speed settings are applied by the device only upon port admin status transition from DOWN to UP. So we enforce this transition regardless of the port's current operation state (which may be occasionally DOWN if for example the network cable is disconnected). - Fix the PORT_UP/DOWN device interface enum - Set the local_port bit in the device PAOS register - EXPORT the PAOS (Port Administrative and Operational Status) register set/query access functions. Signed-off-by: Achiad Shochat Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 25 ++++++---------------- drivers/net/ethernet/mellanox/mlx5/core/port.c | 14 ++++++++---- include/linux/mlx5/driver.h | 11 +++++----- 3 files changed, 23 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 975828521913..77158b31eb0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -628,7 +628,7 @@ static int mlx5e_set_settings(struct net_device *netdev, u32 link_modes; u32 speed; u32 eth_proto_cap, eth_proto_admin; - u8 port_status; + enum mlx5_port_status ps; int err; speed = ethtool_cmd_speed(cmd); @@ -662,24 +662,13 @@ static int mlx5e_set_settings(struct net_device *netdev, if (link_modes == eth_proto_admin) goto out; - err = mlx5_set_port_proto(mdev, link_modes, MLX5_PTYS_EN); - if (err) { - netdev_err(netdev, "%s: set port eth proto admin failed: %d\n", - __func__, err); - goto out; - } + mlx5_query_port_admin_status(mdev, &ps); + if (ps == MLX5_PORT_UP) + mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + mlx5_set_port_proto(mdev, link_modes, MLX5_PTYS_EN); + if (ps == MLX5_PORT_UP) + mlx5_set_port_admin_status(mdev, MLX5_PORT_UP); - err = mlx5_query_port_status(mdev, &port_status); - if (err) - goto out; - - if (port_status == MLX5_PORT_DOWN) - return 0; - - err = mlx5_set_port_status(mdev, MLX5_PORT_DOWN); - if (err) - goto out; - err = mlx5_set_port_status(mdev, MLX5_PORT_UP); out: return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 70147999f657..f8db52bd8f18 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -216,22 +216,25 @@ int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, } EXPORT_SYMBOL_GPL(mlx5_set_port_proto); -int mlx5_set_port_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status) +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status) { u32 in[MLX5_ST_SZ_DW(paos_reg)]; u32 out[MLX5_ST_SZ_DW(paos_reg)]; memset(in, 0, sizeof(in)); + MLX5_SET(paos_reg, in, local_port, 1); MLX5_SET(paos_reg, in, admin_status, status); MLX5_SET(paos_reg, in, ase, 1); return mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_PAOS, 0, 1); } +EXPORT_SYMBOL_GPL(mlx5_set_port_admin_status); -int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status) +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status) { u32 in[MLX5_ST_SZ_DW(paos_reg)]; u32 out[MLX5_ST_SZ_DW(paos_reg)]; @@ -239,14 +242,17 @@ int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status) memset(in, 0, sizeof(in)); + MLX5_SET(paos_reg, in, local_port, 1); + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_PAOS, 0, 0); if (err) return err; - *status = MLX5_GET(paos_reg, out, oper_status); + *status = MLX5_GET(paos_reg, out, admin_status); return err; } +EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status); static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, int *max_mtu, int *oper_mtu, u8 port) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 2039546b0ec6..4b5d7fc88d0f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -152,8 +152,8 @@ enum mlx5_dev_event { }; enum mlx5_port_status { - MLX5_PORT_UP = 1 << 1, - MLX5_PORT_DOWN = 1 << 2, + MLX5_PORT_UP = 1, + MLX5_PORT_DOWN = 2, }; struct mlx5_uuar_info { @@ -761,9 +761,10 @@ int mlx5_query_port_proto_oper(struct mlx5_core_dev *dev, u8 local_port); int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, int proto_mask); -int mlx5_set_port_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_status(struct mlx5_core_dev *dev, u8 *status); +int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status status); +int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, + enum mlx5_port_status *status); int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -- cgit v1.3-18-gd494 From 3c2d18ef22df1bdccfb11a5b85b29e4e61b9d9c6 Mon Sep 17 00:00:00 2001 From: Achiad Shochat Date: Sun, 16 Aug 2015 16:04:51 +0300 Subject: net/mlx5e: Support ethtool get/set_pauseparam Only rx/tx pause settings. Autoneg setting is currently not supported. Signed-off-by: Achiad Shochat Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 38 ++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/port.c | 42 ++++++++++++++++++++++ include/linux/mlx5/driver.h | 5 +++ 3 files changed, 85 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 77158b31eb0b..bce912688ca8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -820,6 +820,42 @@ static int mlx5e_set_tunable(struct net_device *dev, return err; } +static void mlx5e_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pauseparam) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + int err; + + err = mlx5_query_port_pause(mdev, &pauseparam->rx_pause, + &pauseparam->tx_pause); + if (err) { + netdev_err(netdev, "%s: mlx5_query_port_pause failed:0x%x\n", + __func__, err); + } +} + +static int mlx5e_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pauseparam) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + int err; + + if (pauseparam->autoneg) + return -EINVAL; + + err = mlx5_set_port_pause(mdev, + pauseparam->rx_pause ? 1 : 0, + pauseparam->tx_pause ? 1 : 0); + if (err) { + netdev_err(netdev, "%s: mlx5_set_port_pause failed:0x%x\n", + __func__, err); + } + + return err; +} + const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, .get_link = ethtool_op_get_link, @@ -841,4 +877,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_rxnfc = mlx5e_get_rxnfc, .get_tunable = mlx5e_get_tunable, .set_tunable = mlx5e_set_tunable, + .get_pauseparam = mlx5e_get_pauseparam, + .set_pauseparam = mlx5e_set_pauseparam, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index f8db52bd8f18..821caaab9bfb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -334,3 +334,45 @@ int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_vl_hw_cap); + +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + int err; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + MLX5_SET(pfcc_reg, in, pptx, tx_pause); + MLX5_SET(pfcc_reg, in, pprx, rx_pause); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 1); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_set_port_pause); + +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause) +{ + u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; + u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; + int err; + + memset(in, 0, sizeof(in)); + MLX5_SET(pfcc_reg, in, local_port, 1); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 0); + if (err) + return err; + + if (rx_pause) + *rx_pause = MLX5_GET(pfcc_reg, out, pprx); + + if (tx_pause) + *tx_pause = MLX5_GET(pfcc_reg, out, pptx); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_pause); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 4b5d7fc88d0f..8b6d6f2154a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -103,6 +103,7 @@ enum { MLX5_REG_PMTU = 0x5003, MLX5_REG_PTYS = 0x5004, MLX5_REG_PAOS = 0x5006, + MLX5_REG_PFCC = 0x5007, MLX5_REG_PPCNT = 0x5008, MLX5_REG_PMAOS = 0x5012, MLX5_REG_PUDE = 0x5009, @@ -774,6 +775,10 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, u8 *vl_hw_cap, u8 local_port); +int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); +int mlx5_query_port_pause(struct mlx5_core_dev *dev, + u32 *rx_pause, u32 *tx_pause); + int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, -- cgit v1.3-18-gd494 From 2f52bdcf6ba1bd81597b1505a222430676548b3a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 16 Aug 2015 07:49:20 -0600 Subject: net: Updates to netif_index_is_vrf As Eric noted netif_index_is_vrf is not called with rcu_read_lock held, so wrap the dev_get_by_index_rcu in rcu_read_lock and unlock. If VRF is not enabled or oif is 0 skip the device lookup. In both cases index cannot be the VRF master. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d131755516ca..8a530f930754 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3822,12 +3822,22 @@ static inline bool netif_is_vrf(const struct net_device *dev) static inline bool netif_index_is_vrf(struct net *net, int ifindex) { - struct net_device *dev = dev_get_by_index_rcu(net, ifindex); bool rc = false; +#if IS_ENABLED(CONFIG_NET_VRF) + struct net_device *dev; + + if (ifindex == 0) + return false; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); if (dev) rc = netif_is_vrf(dev); + rcu_read_unlock(); +#endif return rc; } -- cgit v1.3-18-gd494 From 808d28c468a89e8680396d98aea96024b6f5afdc Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sun, 16 Aug 2015 10:26:49 -0600 Subject: net: Fix docbook warning for IFF_VRF_MASTER enum kbuild test robot reported: tree: git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master head: d52736e24fe2e927c26817256f8d1a3c8b5d51a0 commit: 4e3c89920cd3a6cfce22c6f537690747c26128dd [751/762] net: Introduce VRF related flags and helpers reproduce: make htmldocs >> Warning(include/linux/netdevice.h:1293): Enum value 'IFF_VRF_MASTER' not described in enum 'netdev_priv_flags' Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8a530f930754..4bd177faa90c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1262,6 +1262,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device + * @IFF_VRF_MASTER: device is a VRF master * @IFF_NO_QUEUE: device can run without qdisc attached */ enum netdev_priv_flags { -- cgit v1.3-18-gd494 From 74f4e0cc61080f63f28e8d519bdf437957e64217 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 14 Aug 2015 00:21:45 +0200 Subject: bcma: switch GPIO portions to use GPIOLIB_IRQCHIP This switches the BCMA GPIO driver to use GPIOLIB_IRQCHIP to handle its interrupts instead of rolling its own copy of the irqdomain handling etc. Signed-off-by: Linus Walleij Signed-off-by: Hauke Mehrtens Signed-off-by: Kalle Valo --- drivers/bcma/Kconfig | 2 +- drivers/bcma/driver_gpio.c | 92 ++++++++++------------------- include/linux/bcma/bcma_driver_chipcommon.h | 1 - 3 files changed, 31 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig index be5fffb6da24..023d448ed3fa 100644 --- a/drivers/bcma/Kconfig +++ b/drivers/bcma/Kconfig @@ -92,7 +92,7 @@ config BCMA_DRIVER_GMAC_CMN config BCMA_DRIVER_GPIO bool "BCMA GPIO driver" depends on BCMA && GPIOLIB - select IRQ_DOMAIN if BCMA_HOST_SOC + select GPIOLIB_IRQCHIP if BCMA_HOST_SOC help Driver to provide access to the GPIO pins of the bcma bus. diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c index 5f6018e7cd4c..504899a72966 100644 --- a/drivers/bcma/driver_gpio.c +++ b/drivers/bcma/driver_gpio.c @@ -8,10 +8,8 @@ * Licensed under the GNU/GPL. See COPYING for details. */ -#include -#include +#include #include -#include #include #include @@ -79,19 +77,11 @@ static void bcma_gpio_free(struct gpio_chip *chip, unsigned gpio) } #if IS_BUILTIN(CONFIG_BCM47XX) || IS_BUILTIN(CONFIG_ARCH_BCM_5301X) -static int bcma_gpio_to_irq(struct gpio_chip *chip, unsigned gpio) -{ - struct bcma_drv_cc *cc = bcma_gpio_get_cc(chip); - - if (cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC) - return irq_find_mapping(cc->irq_domain, gpio); - else - return -EINVAL; -} static void bcma_gpio_irq_unmask(struct irq_data *d) { - struct bcma_drv_cc *cc = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct bcma_drv_cc *cc = bcma_gpio_get_cc(gc); int gpio = irqd_to_hwirq(d); u32 val = bcma_chipco_gpio_in(cc, BIT(gpio)); @@ -101,7 +91,8 @@ static void bcma_gpio_irq_unmask(struct irq_data *d) static void bcma_gpio_irq_mask(struct irq_data *d) { - struct bcma_drv_cc *cc = irq_data_get_irq_chip_data(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct bcma_drv_cc *cc = bcma_gpio_get_cc(gc); int gpio = irqd_to_hwirq(d); bcma_chipco_gpio_intmask(cc, BIT(gpio), 0); @@ -116,6 +107,7 @@ static struct irq_chip bcma_gpio_irq_chip = { static irqreturn_t bcma_gpio_irq_handler(int irq, void *dev_id) { struct bcma_drv_cc *cc = dev_id; + struct gpio_chip *gc = &cc->gpio; u32 val = bcma_cc_read32(cc, BCMA_CC_GPIOIN); u32 mask = bcma_cc_read32(cc, BCMA_CC_GPIOIRQ); u32 pol = bcma_cc_read32(cc, BCMA_CC_GPIOPOL); @@ -125,81 +117,58 @@ static irqreturn_t bcma_gpio_irq_handler(int irq, void *dev_id) if (!irqs) return IRQ_NONE; - for_each_set_bit(gpio, &irqs, cc->gpio.ngpio) - generic_handle_irq(bcma_gpio_to_irq(&cc->gpio, gpio)); + for_each_set_bit(gpio, &irqs, gc->ngpio) + generic_handle_irq(irq_find_mapping(gc->irqdomain, gpio)); bcma_chipco_gpio_polarity(cc, irqs, val & irqs); return IRQ_HANDLED; } -static int bcma_gpio_irq_domain_init(struct bcma_drv_cc *cc) +static int bcma_gpio_irq_init(struct bcma_drv_cc *cc) { struct gpio_chip *chip = &cc->gpio; - int gpio, hwirq, err; + int hwirq, err; if (cc->core->bus->hosttype != BCMA_HOSTTYPE_SOC) return 0; - cc->irq_domain = irq_domain_add_linear(NULL, chip->ngpio, - &irq_domain_simple_ops, cc); - if (!cc->irq_domain) { - err = -ENODEV; - goto err_irq_domain; - } - for (gpio = 0; gpio < chip->ngpio; gpio++) { - int irq = irq_create_mapping(cc->irq_domain, gpio); - - irq_set_chip_data(irq, cc); - irq_set_chip_and_handler(irq, &bcma_gpio_irq_chip, - handle_simple_irq); - } - hwirq = bcma_core_irq(cc->core, 0); err = request_irq(hwirq, bcma_gpio_irq_handler, IRQF_SHARED, "gpio", cc); if (err) - goto err_req_irq; + return err; bcma_chipco_gpio_intmask(cc, ~0, 0); bcma_cc_set32(cc, BCMA_CC_IRQMASK, BCMA_CC_IRQ_GPIO); - return 0; - -err_req_irq: - for (gpio = 0; gpio < chip->ngpio; gpio++) { - int irq = irq_find_mapping(cc->irq_domain, gpio); - - irq_dispose_mapping(irq); + err = gpiochip_irqchip_add(chip, + &bcma_gpio_irq_chip, + 0, + handle_simple_irq, + IRQ_TYPE_NONE); + if (err) { + free_irq(hwirq, cc); + return err; } - irq_domain_remove(cc->irq_domain); -err_irq_domain: - return err; + + return 0; } -static void bcma_gpio_irq_domain_exit(struct bcma_drv_cc *cc) +static void bcma_gpio_irq_exit(struct bcma_drv_cc *cc) { - struct gpio_chip *chip = &cc->gpio; - int gpio; - if (cc->core->bus->hosttype != BCMA_HOSTTYPE_SOC) return; bcma_cc_mask32(cc, BCMA_CC_IRQMASK, ~BCMA_CC_IRQ_GPIO); free_irq(bcma_core_irq(cc->core, 0), cc); - for (gpio = 0; gpio < chip->ngpio; gpio++) { - int irq = irq_find_mapping(cc->irq_domain, gpio); - - irq_dispose_mapping(irq); - } - irq_domain_remove(cc->irq_domain); } #else -static int bcma_gpio_irq_domain_init(struct bcma_drv_cc *cc) +static int bcma_gpio_irq_init(struct bcma_drv_cc *cc) { return 0; } -static void bcma_gpio_irq_domain_exit(struct bcma_drv_cc *cc) +static void bcma_gpio_irq_exit(struct bcma_drv_cc *cc) { } #endif @@ -218,9 +187,8 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) chip->set = bcma_gpio_set_value; chip->direction_input = bcma_gpio_direction_input; chip->direction_output = bcma_gpio_direction_output; -#if IS_BUILTIN(CONFIG_BCM47XX) || IS_BUILTIN(CONFIG_ARCH_BCM_5301X) - chip->to_irq = bcma_gpio_to_irq; -#endif + chip->owner = THIS_MODULE; + chip->dev = bcma_bus_get_host_dev(bus); #if IS_BUILTIN(CONFIG_OF) if (cc->core->bus->hosttype == BCMA_HOSTTYPE_SOC) chip->of_node = cc->core->dev.of_node; @@ -248,13 +216,13 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) else chip->base = -1; - err = bcma_gpio_irq_domain_init(cc); + err = gpiochip_add(chip); if (err) return err; - err = gpiochip_add(chip); + err = bcma_gpio_irq_init(cc); if (err) { - bcma_gpio_irq_domain_exit(cc); + gpiochip_remove(chip); return err; } @@ -263,7 +231,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) int bcma_gpio_unregister(struct bcma_drv_cc *cc) { - bcma_gpio_irq_domain_exit(cc); + bcma_gpio_irq_exit(cc); gpiochip_remove(&cc->gpio); return 0; } diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 6cceedf65ca2..cf038431a5cc 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -640,7 +640,6 @@ struct bcma_drv_cc { spinlock_t gpio_lock; #ifdef CONFIG_BCMA_DRIVER_GPIO struct gpio_chip gpio; - struct irq_domain *irq_domain; #endif }; -- cgit v1.3-18-gd494 From f4e774f55fe0bb568a0877b2eb9e1b4b5a6f5cbc Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 19 Aug 2015 09:46:22 +0200 Subject: average: remove out-of-line implementation Since all users are now converted to the inline implementation, remove the out-of-line implementation entirely. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/average.h | 24 ------------------- lib/Kconfig | 10 -------- lib/average.c | 64 ------------------------------------------------- 3 files changed, 98 deletions(-) delete mode 100644 lib/average.c (limited to 'include/linux') diff --git a/include/linux/average.h b/include/linux/average.h index 60f8226c5652..d04aa58280de 100644 --- a/include/linux/average.h +++ b/include/linux/average.h @@ -3,30 +3,6 @@ /* Exponentially weighted moving average (EWMA) */ -/* For more documentation see lib/average.c */ - -struct ewma { - unsigned long internal; - unsigned long factor; - unsigned long weight; -}; - -extern void ewma_init(struct ewma *avg, unsigned long factor, - unsigned long weight); - -extern struct ewma *ewma_add(struct ewma *avg, unsigned long val); - -/** - * ewma_read() - Get average value - * @avg: Average structure - * - * Returns the average value held in @avg. - */ -static inline unsigned long ewma_read(const struct ewma *avg) -{ - return avg->internal >> avg->factor; -} - #define DECLARE_EWMA(name, _factor, _weight) \ struct ewma_##name { \ unsigned long internal; \ diff --git a/lib/Kconfig b/lib/Kconfig index 3a2ef67db6c7..278890dd1049 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -460,16 +460,6 @@ config ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE config LRU_CACHE tristate -config AVERAGE - bool "Averaging functions" - help - This option is provided for the case where no in-kernel-tree - modules require averaging functions, but a module built outside - the kernel tree does. Such modules that use library averaging - functions require Y here. - - If unsure, say N. - config CLZ_TAB bool diff --git a/lib/average.c b/lib/average.c deleted file mode 100644 index 114d1beae0c7..000000000000 --- a/lib/average.c +++ /dev/null @@ -1,64 +0,0 @@ -/* - * lib/average.c - * - * This source code is licensed under the GNU General Public License, - * Version 2. See the file COPYING for more details. - */ - -#include -#include -#include -#include -#include - -/** - * DOC: Exponentially Weighted Moving Average (EWMA) - * - * These are generic functions for calculating Exponentially Weighted Moving - * Averages (EWMA). We keep a structure with the EWMA parameters and a scaled - * up internal representation of the average value to prevent rounding errors. - * The factor for scaling up and the exponential weight (or decay rate) have to - * be specified thru the init fuction. The structure should not be accessed - * directly but only thru the helper functions. - */ - -/** - * ewma_init() - Initialize EWMA parameters - * @avg: Average structure - * @factor: Factor to use for the scaled up internal value. The maximum value - * of averages can be ULONG_MAX/(factor*weight). For performance reasons - * factor has to be a power of 2. - * @weight: Exponential weight, or decay rate. This defines how fast the - * influence of older values decreases. For performance reasons weight has - * to be a power of 2. - * - * Initialize the EWMA parameters for a given struct ewma @avg. - */ -void ewma_init(struct ewma *avg, unsigned long factor, unsigned long weight) -{ - WARN_ON(!is_power_of_2(weight) || !is_power_of_2(factor)); - - avg->weight = ilog2(weight); - avg->factor = ilog2(factor); - avg->internal = 0; -} -EXPORT_SYMBOL(ewma_init); - -/** - * ewma_add() - Exponentially weighted moving average (EWMA) - * @avg: Average structure - * @val: Current value - * - * Add a sample to the average. - */ -struct ewma *ewma_add(struct ewma *avg, unsigned long val) -{ - unsigned long internal = ACCESS_ONCE(avg->internal); - - ACCESS_ONCE(avg->internal) = internal ? - (((internal << avg->weight) - internal) + - (val << avg->factor)) >> avg->weight : - (val << avg->factor); - return avg; -} -EXPORT_SYMBOL(ewma_add); -- cgit v1.3-18-gd494