diff --git a/Documentation/trace/index.rst b/Documentation/trace/index.rst index 5092d6c13af5..0b300901fd75 100644 --- a/Documentation/trace/index.rst +++ b/Documentation/trace/index.rst @@ -29,6 +29,7 @@ Linux Tracing Technologies timerlat-tracer intel_th ring-buffer-design + ring-buffer-map stm sys-t coresight/index diff --git a/Documentation/trace/ring-buffer-map.rst b/Documentation/trace/ring-buffer-map.rst new file mode 100644 index 000000000000..8e296bcc0d7f --- /dev/null +++ b/Documentation/trace/ring-buffer-map.rst @@ -0,0 +1,106 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== +Tracefs ring-buffer memory mapping +================================== + +:Author: Vincent Donnefort + +Overview +======== +Tracefs ring-buffer memory map provides an efficient method to stream data +as no memory copy is necessary. The application mapping the ring-buffer becomes +then a consumer for that ring-buffer, in a similar fashion to trace_pipe. + +Memory mapping setup +==================== +The mapping works with a mmap() of the trace_pipe_raw interface. + +The first system page of the mapping contains ring-buffer statistics and +description. It is referred to as the meta-page. One of the most important +fields of the meta-page is the reader. It contains the sub-buffer ID which can +be safely read by the mapper (see ring-buffer-design.rst). + +The meta-page is followed by all the sub-buffers, ordered by ascending ID. It is +therefore effortless to know where the reader starts in the mapping: + +.. code-block:: c + + reader_id = meta->reader->id; + reader_offset = meta->meta_page_size + reader_id * meta->subbuf_size; + +When the application is done with the current reader, it can get a new one using +the trace_pipe_raw ioctl() TRACE_MMAP_IOCTL_GET_READER. This ioctl also updates +the meta-page fields. + +Limitations +=========== +When a mapping is in place on a Tracefs ring-buffer, it is not possible to +either resize it (either by increasing the entire size of the ring-buffer or +each subbuf). It is also not possible to use snapshot and causes splice to copy +the ring buffer data instead of using the copyless swap from the ring buffer. + +Concurrent readers (either another application mapping that ring-buffer or the +kernel with trace_pipe) are allowed but not recommended. They will compete for +the ring-buffer and the output is unpredictable, just like concurrent readers on +trace_pipe would be. + +Example +======= + +.. code-block:: c + + #include + #include + #include + #include + + #include + + #include + #include + + #define TRACE_PIPE_RAW "/sys/kernel/tracing/per_cpu/cpu0/trace_pipe_raw" + + int main(void) + { + int page_size = getpagesize(), fd, reader_id; + unsigned long meta_len, data_len; + struct trace_buffer_meta *meta; + void *map, *reader, *data; + + fd = open(TRACE_PIPE_RAW, O_RDONLY | O_NONBLOCK); + if (fd < 0) + exit(EXIT_FAILURE); + + map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); + if (map == MAP_FAILED) + exit(EXIT_FAILURE); + + meta = (struct trace_buffer_meta *)map; + meta_len = meta->meta_page_size; + + printf("entries: %llu\n", meta->entries); + printf("overrun: %llu\n", meta->overrun); + printf("read: %llu\n", meta->read); + printf("nr_subbufs: %u\n", meta->nr_subbufs); + + data_len = meta->subbuf_size * meta->nr_subbufs; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, fd, meta_len); + if (data == MAP_FAILED) + exit(EXIT_FAILURE); + + if (ioctl(fd, TRACE_MMAP_IOCTL_GET_READER) < 0) + exit(EXIT_FAILURE); + + reader_id = meta->reader.id; + reader = data + meta->subbuf_size * reader_id; + + printf("Current reader address: %p\n", reader); + + munmap(data, data_len); + munmap(meta, meta_len); + close (fd); + + return 0; + } diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dc5ae4e96aee..96d2140b471e 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -6,6 +6,8 @@ #include #include +#include + struct trace_buffer; struct ring_buffer_iter; @@ -223,4 +225,8 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); #define trace_rb_cpu_prepare NULL #endif +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma); +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/uapi/linux/trace_mmap.h b/include/uapi/linux/trace_mmap.h new file mode 100644 index 000000000000..bd1066754220 --- /dev/null +++ b/include/uapi/linux/trace_mmap.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _TRACE_MMAP_H_ +#define _TRACE_MMAP_H_ + +#include + +/** + * struct trace_buffer_meta - Ring-buffer Meta-page description + * @meta_page_size: Size of this meta-page. + * @meta_struct_len: Size of this structure. + * @subbuf_size: Size of each sub-buffer. + * @nr_subbufs: Number of subbfs in the ring-buffer, including the reader. + * @reader.lost_events: Number of events lost at the time of the reader swap. + * @reader.id: subbuf ID of the current reader. ID range [0 : @nr_subbufs - 1] + * @reader.read: Number of bytes read on the reader subbuf. + * @flags: Placeholder for now, 0 until new features are supported. + * @entries: Number of entries in the ring-buffer. + * @overrun: Number of entries lost in the ring-buffer. + * @read: Number of entries that have been read. + * @Reserved1: Internal use only. + * @Reserved2: Internal use only. + */ +struct trace_buffer_meta { + __u32 meta_page_size; + __u32 meta_struct_len; + + __u32 subbuf_size; + __u32 nr_subbufs; + + struct { + __u64 lost_events; + __u32 id; + __u32 read; + } reader; + + __u64 flags; + + __u64 entries; + __u64 overrun; + __u64 read; + + __u64 Reserved1; + __u64 Reserved2; +}; + +#define TRACE_MMAP_IOCTL_GET_READER _IO('T', 0x1) + +#endif /* _TRACE_MMAP_H_ */ diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6511dc3a00da..7345a8b625fb 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -26,6 +27,7 @@ #include #include #include +#include #include #include @@ -312,6 +314,8 @@ static u64 rb_event_time_stamp(struct ring_buffer_event *event) /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) +#define RB_MISSED_MASK (3 << 30) + struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ @@ -338,6 +342,7 @@ struct buffer_page { local_t entries; /* entries on this page */ unsigned long real_end; /* real end of data */ unsigned order; /* order of the page */ + u32 id; /* ID for external mapping */ struct buffer_data_page *page; /* Actual data page */ }; @@ -484,6 +489,12 @@ struct ring_buffer_per_cpu { u64 read_stamp; /* pages removed since last reset */ unsigned long pages_removed; + + unsigned int mapped; + struct mutex mapping_lock; + unsigned long *subbuf_ids; /* ID to subbuf VA */ + struct trace_buffer_meta *meta_page; + /* ring buffer pages to update, > 0 to add, < 0 to remove */ long nr_pages_to_update; struct list_head new_pages; /* new pages to add */ @@ -1524,7 +1535,7 @@ static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, list_add(&bpage->list, pages); page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), - mflags | __GFP_ZERO, + mflags | __GFP_COMP | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) goto free_pages; @@ -1599,6 +1610,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters); init_waitqueue_head(&cpu_buffer->irq_work.waiters); init_waitqueue_head(&cpu_buffer->irq_work.full_waiters); + mutex_init(&cpu_buffer->mapping_lock); bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), GFP_KERNEL, cpu_to_node(cpu)); @@ -1609,7 +1621,7 @@ rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) cpu_buffer->reader_page = bpage; - page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO, + page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_COMP | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) goto fail_free_reader; @@ -1789,8 +1801,6 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer) return buffer->time_stamp_abs; } -static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer); - static inline unsigned long rb_page_entries(struct buffer_page *bpage) { return local_read(&bpage->entries) & RB_WRITE_MASK; @@ -2318,7 +2328,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) /* Size is determined by what has been committed */ static __always_inline unsigned rb_page_size(struct buffer_page *bpage) { - return rb_page_commit(bpage); + return rb_page_commit(bpage) & ~RB_MISSED_MASK; } static __always_inline unsigned @@ -3945,7 +3955,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) return true; /* Reader should exhaust content in reader page */ - if (reader->read != rb_page_commit(reader)) + if (reader->read != rb_page_size(reader)) return false; /* @@ -4416,7 +4426,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) return ((iter->head_page == commit_page && iter->head >= commit) || (iter->head_page == reader && commit_page == head_page && head_page->read == commit && - iter->head == rb_page_commit(cpu_buffer->reader_page))); + iter->head == rb_page_size(cpu_buffer->reader_page))); } EXPORT_SYMBOL_GPL(ring_buffer_iter_empty); @@ -5211,6 +5221,22 @@ static void rb_clear_buffer_page(struct buffer_page *page) page->read = 0; } +static void rb_update_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct trace_buffer_meta *meta = cpu_buffer->meta_page; + + meta->reader.read = cpu_buffer->reader_page->read; + meta->reader.id = cpu_buffer->reader_page->id; + meta->reader.lost_events = cpu_buffer->lost_events; + + meta->entries = local_read(&cpu_buffer->entries); + meta->overrun = local_read(&cpu_buffer->overrun); + meta->read = cpu_buffer->read; + + /* Some archs do not have data cache coherency between kernel and user-space */ + flush_dcache_folio(virt_to_folio(cpu_buffer->meta_page)); +} + static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) { @@ -5255,6 +5281,9 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->lost_events = 0; cpu_buffer->last_overrun = 0; + if (cpu_buffer->mapped) + rb_update_meta_page(cpu_buffer); + rb_head_page_activate(cpu_buffer); cpu_buffer->pages_removed = 0; } @@ -5469,6 +5498,12 @@ int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, cpu_buffer_a = buffer_a->buffers[cpu]; cpu_buffer_b = buffer_b->buffers[cpu]; + /* It's up to the callers to not try to swap mapped buffers */ + if (WARN_ON_ONCE(cpu_buffer_a->mapped || cpu_buffer_b->mapped)) { + ret = -EBUSY; + goto out; + } + /* At least make sure the two buffers are somewhat the same */ if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out; @@ -5579,7 +5614,7 @@ ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) goto out; page = alloc_pages_node(cpu_to_node(cpu), - GFP_KERNEL | __GFP_NORETRY | __GFP_ZERO, + GFP_KERNEL | __GFP_NORETRY | __GFP_COMP | __GFP_ZERO, cpu_buffer->buffer->subbuf_order); if (!page) { kfree(bpage); @@ -5720,7 +5755,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, event = rb_reader_event(cpu_buffer); read = reader->read; - commit = rb_page_commit(reader); + commit = rb_page_size(reader); /* Check if any events were dropped */ missed_events = cpu_buffer->lost_events; @@ -5733,7 +5768,8 @@ int ring_buffer_read_page(struct trace_buffer *buffer, * Otherwise, we can simply swap the page with the one passed in. */ if (read || (len < (commit - read)) || - cpu_buffer->reader_page == cpu_buffer->commit_page) { + cpu_buffer->reader_page == cpu_buffer->commit_page || + cpu_buffer->mapped) { struct buffer_data_page *rpage = cpu_buffer->reader_page->page; unsigned int rpos = read; unsigned int pos = 0; @@ -5796,7 +5832,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, } else { /* update the entry counter */ cpu_buffer->read += rb_page_entries(reader); - cpu_buffer->read_bytes += rb_page_commit(reader); + cpu_buffer->read_bytes += rb_page_size(reader); /* swap the pages */ rb_init_page(bpage); @@ -5956,6 +5992,11 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) cpu_buffer = buffer->buffers[cpu]; + if (cpu_buffer->mapped) { + err = -EBUSY; + goto error; + } + /* Update the number of pages to match the new size */ nr_pages = old_size * buffer->buffers[cpu]->nr_pages; nr_pages = DIV_ROUND_UP(nr_pages, buffer->subbuf_size); @@ -6057,6 +6098,414 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) } EXPORT_SYMBOL_GPL(ring_buffer_subbuf_order_set); +static int rb_alloc_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + struct page *page; + + if (cpu_buffer->meta_page) + return 0; + + page = alloc_page(GFP_USER | __GFP_ZERO); + if (!page) + return -ENOMEM; + + cpu_buffer->meta_page = page_to_virt(page); + + return 0; +} + +static void rb_free_meta_page(struct ring_buffer_per_cpu *cpu_buffer) +{ + unsigned long addr = (unsigned long)cpu_buffer->meta_page; + + free_page(addr); + cpu_buffer->meta_page = NULL; +} + +static void rb_setup_ids_meta_page(struct ring_buffer_per_cpu *cpu_buffer, + unsigned long *subbuf_ids) +{ + struct trace_buffer_meta *meta = cpu_buffer->meta_page; + unsigned int nr_subbufs = cpu_buffer->nr_pages + 1; + struct buffer_page *first_subbuf, *subbuf; + int id = 0; + + subbuf_ids[id] = (unsigned long)cpu_buffer->reader_page->page; + cpu_buffer->reader_page->id = id++; + + first_subbuf = subbuf = rb_set_head_page(cpu_buffer); + do { + if (WARN_ON(id >= nr_subbufs)) + break; + + subbuf_ids[id] = (unsigned long)subbuf->page; + subbuf->id = id; + + rb_inc_page(&subbuf); + id++; + } while (subbuf != first_subbuf); + + /* install subbuf ID to kern VA translation */ + cpu_buffer->subbuf_ids = subbuf_ids; + + meta->meta_page_size = PAGE_SIZE; + meta->meta_struct_len = sizeof(*meta); + meta->nr_subbufs = nr_subbufs; + meta->subbuf_size = cpu_buffer->buffer->subbuf_size + BUF_PAGE_HDR_SIZE; + + rb_update_meta_page(cpu_buffer); +} + +static struct ring_buffer_per_cpu * +rb_get_mapped_buffer(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return ERR_PTR(-EINVAL); + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + mutex_unlock(&cpu_buffer->mapping_lock); + return ERR_PTR(-ENODEV); + } + + return cpu_buffer; +} + +static void rb_put_mapped_buffer(struct ring_buffer_per_cpu *cpu_buffer) +{ + mutex_unlock(&cpu_buffer->mapping_lock); +} + +/* + * Fast-path for rb_buffer_(un)map(). Called whenever the meta-page doesn't need + * to be set-up or torn-down. + */ +static int __rb_inc_dec_mapped(struct ring_buffer_per_cpu *cpu_buffer, + bool inc) +{ + unsigned long flags; + + lockdep_assert_held(&cpu_buffer->mapping_lock); + + if (inc && cpu_buffer->mapped == UINT_MAX) + return -EBUSY; + + if (WARN_ON(!inc && cpu_buffer->mapped == 0)) + return -EINVAL; + + mutex_lock(&cpu_buffer->buffer->mutex); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + if (inc) + cpu_buffer->mapped++; + else + cpu_buffer->mapped--; + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + mutex_unlock(&cpu_buffer->buffer->mutex); + + return 0; +} + +/* + * +--------------+ pgoff == 0 + * | meta page | + * +--------------+ pgoff == 1 + * | subbuffer 0 | + * | | + * +--------------+ pgoff == (1 + (1 << subbuf_order)) + * | subbuffer 1 | + * | | + * ... + */ +#ifdef CONFIG_MMU +static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, + struct vm_area_struct *vma) +{ + unsigned long nr_subbufs, nr_pages, vma_pages, pgoff = vma->vm_pgoff; + unsigned int subbuf_pages, subbuf_order; + struct page **pages; + int p = 0, s = 0; + int err; + + /* Refuse MP_PRIVATE or writable mappings */ + if (vma->vm_flags & VM_WRITE || vma->vm_flags & VM_EXEC || + !(vma->vm_flags & VM_MAYSHARE)) + return -EPERM; + + /* + * Make sure the mapping cannot become writable later. Also tell the VM + * to not touch these pages (VM_DONTCOPY | VM_DONTEXPAND). + */ + vm_flags_mod(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP, + VM_MAYWRITE); + + lockdep_assert_held(&cpu_buffer->mapping_lock); + + subbuf_order = cpu_buffer->buffer->subbuf_order; + subbuf_pages = 1 << subbuf_order; + + nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ + nr_pages = ((nr_subbufs) << subbuf_order) - pgoff + 1; /* + meta-page */ + + vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + if (!vma_pages || vma_pages > nr_pages) + return -EINVAL; + + nr_pages = vma_pages; + + pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + if (!pgoff) { + pages[p++] = virt_to_page(cpu_buffer->meta_page); + + /* + * TODO: Align sub-buffers on their size, once + * vm_insert_pages() supports the zero-page. + */ + } else { + /* Skip the meta-page */ + pgoff--; + + if (pgoff % subbuf_pages) { + err = -EINVAL; + goto out; + } + + s += pgoff / subbuf_pages; + } + + while (p < nr_pages) { + struct page *page = virt_to_page((void *)cpu_buffer->subbuf_ids[s]); + int off = 0; + + if (WARN_ON_ONCE(s >= nr_subbufs)) { + err = -EINVAL; + goto out; + } + + for (; off < (1 << (subbuf_order)); off++, page++) { + if (p >= nr_pages) + break; + + pages[p++] = page; + } + s++; + } + + err = vm_insert_pages(vma, vma->vm_start, pages, &nr_pages); + +out: + kfree(pages); + + return err; +} +#else +static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, + struct vm_area_struct *vma) +{ + return -EOPNOTSUPP; +} +#endif + +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags, *subbuf_ids; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (cpu_buffer->mapped) { + err = __rb_map_vma(cpu_buffer, vma); + if (!err) + err = __rb_inc_dec_mapped(cpu_buffer, true); + mutex_unlock(&cpu_buffer->mapping_lock); + return err; + } + + /* prevent another thread from changing buffer/sub-buffer sizes */ + mutex_lock(&buffer->mutex); + + err = rb_alloc_meta_page(cpu_buffer); + if (err) + goto unlock; + + /* subbuf_ids include the reader while nr_pages does not */ + subbuf_ids = kcalloc(cpu_buffer->nr_pages + 1, sizeof(*subbuf_ids), GFP_KERNEL); + if (!subbuf_ids) { + rb_free_meta_page(cpu_buffer); + err = -ENOMEM; + goto unlock; + } + + atomic_inc(&cpu_buffer->resize_disabled); + + /* + * Lock all readers to block any subbuf swap until the subbuf IDs are + * assigned. + */ + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + rb_setup_ids_meta_page(cpu_buffer, subbuf_ids); + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + err = __rb_map_vma(cpu_buffer, vma); + if (!err) { + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + cpu_buffer->mapped = 1; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } else { + kfree(cpu_buffer->subbuf_ids); + cpu_buffer->subbuf_ids = NULL; + rb_free_meta_page(cpu_buffer); + } + +unlock: + mutex_unlock(&buffer->mutex); + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + unsigned long flags; + int err = 0; + + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + + cpu_buffer = buffer->buffers[cpu]; + + mutex_lock(&cpu_buffer->mapping_lock); + + if (!cpu_buffer->mapped) { + err = -ENODEV; + goto out; + } else if (cpu_buffer->mapped > 1) { + __rb_inc_dec_mapped(cpu_buffer, false); + goto out; + } + + mutex_lock(&buffer->mutex); + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + + cpu_buffer->mapped = 0; + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + + kfree(cpu_buffer->subbuf_ids); + cpu_buffer->subbuf_ids = NULL; + rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); + + mutex_unlock(&buffer->mutex); + +out: + mutex_unlock(&cpu_buffer->mapping_lock); + + return err; +} + +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + struct buffer_page *reader; + unsigned long missed_events; + unsigned long reader_size; + unsigned long flags; + + cpu_buffer = rb_get_mapped_buffer(buffer, cpu); + if (IS_ERR(cpu_buffer)) + return (int)PTR_ERR(cpu_buffer); + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + +consume: + if (rb_per_cpu_empty(cpu_buffer)) + goto out; + + reader_size = rb_page_size(cpu_buffer->reader_page); + + /* + * There are data to be read on the current reader page, we can + * return to the caller. But before that, we assume the latter will read + * everything. Let's update the kernel reader accordingly. + */ + if (cpu_buffer->reader_page->read < reader_size) { + while (cpu_buffer->reader_page->read < reader_size) + rb_advance_reader(cpu_buffer); + goto out; + } + + reader = rb_get_reader_page(cpu_buffer); + if (WARN_ON(!reader)) + goto out; + + /* Check if any events were dropped */ + missed_events = cpu_buffer->lost_events; + + if (cpu_buffer->reader_page != cpu_buffer->commit_page) { + if (missed_events) { + struct buffer_data_page *bpage = reader->page; + unsigned int commit; + /* + * Use the real_end for the data size, + * This gives us a chance to store the lost events + * on the page. + */ + if (reader->real_end) + local_set(&bpage->commit, reader->real_end); + /* + * If there is room at the end of the page to save the + * missed events, then record it there. + */ + commit = rb_page_size(reader); + if (buffer->subbuf_size - commit >= sizeof(missed_events)) { + memcpy(&bpage->data[commit], &missed_events, + sizeof(missed_events)); + local_add(RB_MISSED_STORED, &bpage->commit); + } + local_add(RB_MISSED_EVENTS, &bpage->commit); + } + } else { + /* + * There really shouldn't be any missed events if the commit + * is on the reader page. + */ + WARN_ON_ONCE(missed_events); + } + + cpu_buffer->lost_events = 0; + + goto consume; + +out: + /* Some archs do not have data cache coherency between kernel and user-space */ + flush_dcache_folio(virt_to_folio(cpu_buffer->reader_page->page)); + + rb_update_meta_page(cpu_buffer); + + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + rb_put_mapped_buffer(cpu_buffer); + + return 0; +} + /* * We only allocate new buffers, never free them if the CPU goes down. * If we were to free the buffer, then the user would lose any trace that was in diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7fe4b539a423..578a49ff5c32 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1191,6 +1191,12 @@ static void tracing_snapshot_instance_cond(struct trace_array *tr, return; } + if (tr->mapped) { + trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); + trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); + return; + } + local_irq_save(flags); update_max_tr(tr, current, smp_processor_id(), cond_data); local_irq_restore(flags); @@ -1323,7 +1329,7 @@ static int tracing_arm_snapshot_locked(struct trace_array *tr) lockdep_assert_held(&trace_types_lock); spin_lock(&tr->snapshot_trigger_lock); - if (tr->snapshot == UINT_MAX) { + if (tr->snapshot == UINT_MAX || tr->mapped) { spin_unlock(&tr->snapshot_trigger_lock); return -EBUSY; } @@ -6068,7 +6074,7 @@ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; - + tr->current_trace->enabled--; if (tr->current_trace->reset) @@ -8194,15 +8200,32 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return ret; } -/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; + int err; - if (cmd) - return -ENOIOCTLCMD; + if (cmd == TRACE_MMAP_IOCTL_GET_READER) { + if (!(file->f_flags & O_NONBLOCK)) { + err = ring_buffer_wait(iter->array_buffer->buffer, + iter->cpu_file, + iter->tr->buffer_percent, + NULL, NULL); + if (err) + return err; + } + return ring_buffer_map_get_reader(iter->array_buffer->buffer, + iter->cpu_file); + } else if (cmd) { + return -ENOTTY; + } + + /* + * An ioctl call with cmd 0 to the ring buffer file will wake up all + * waiters + */ mutex_lock(&trace_types_lock); /* Make sure the waiters see the new wait_index */ @@ -8214,6 +8237,76 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned return 0; } +#ifdef CONFIG_TRACER_MAX_TRACE +static int get_snapshot_map(struct trace_array *tr) +{ + int err = 0; + + /* + * Called with mmap_lock held. lockdep would be unhappy if we would now + * take trace_types_lock. Instead use the specific + * snapshot_trigger_lock. + */ + spin_lock(&tr->snapshot_trigger_lock); + + if (tr->snapshot || tr->mapped == UINT_MAX) + err = -EBUSY; + else + tr->mapped++; + + spin_unlock(&tr->snapshot_trigger_lock); + + /* Wait for update_max_tr() to observe iter->tr->mapped */ + if (tr->mapped == 1) + synchronize_rcu(); + + return err; + +} +static void put_snapshot_map(struct trace_array *tr) +{ + spin_lock(&tr->snapshot_trigger_lock); + if (!WARN_ON(!tr->mapped)) + tr->mapped--; + spin_unlock(&tr->snapshot_trigger_lock); +} +#else +static inline int get_snapshot_map(struct trace_array *tr) { return 0; } +static inline void put_snapshot_map(struct trace_array *tr) { } +#endif + +static void tracing_buffers_mmap_close(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file)); + put_snapshot_map(iter->tr); +} + +static const struct vm_operations_struct tracing_buffers_vmops = { + .close = tracing_buffers_mmap_close, +}; + +static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = filp->private_data; + struct trace_iterator *iter = &info->iter; + int ret = 0; + + ret = get_snapshot_map(iter->tr); + if (ret) + return ret; + + ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma); + if (ret) + put_snapshot_map(iter->tr); + + vma->vm_ops = &tracing_buffers_vmops; + + return ret; +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, @@ -8223,6 +8316,7 @@ static const struct file_operations tracing_buffers_fops = { .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, + .mmap = tracing_buffers_mmap, }; static ssize_t diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 64450615ca0c..749a182dab48 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -336,6 +336,7 @@ struct trace_array { bool allocated_snapshot; spinlock_t snapshot_trigger_lock; unsigned int snapshot; + unsigned int mapped; unsigned long max_latency; #ifdef CONFIG_FSNOTIFY struct dentry *d_max_latency; diff --git a/tools/testing/selftests/ring-buffer/.gitignore b/tools/testing/selftests/ring-buffer/.gitignore new file mode 100644 index 000000000000..3aed1a2a6c67 --- /dev/null +++ b/tools/testing/selftests/ring-buffer/.gitignore @@ -0,0 +1 @@ +map_test diff --git a/tools/testing/selftests/ring-buffer/Makefile b/tools/testing/selftests/ring-buffer/Makefile new file mode 100644 index 000000000000..627c5fa6d1ab --- /dev/null +++ b/tools/testing/selftests/ring-buffer/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -Wl,-no-as-needed -Wall +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -D_GNU_SOURCE + +TEST_GEN_PROGS = map_test + +include ../lib.mk diff --git a/tools/testing/selftests/ring-buffer/config b/tools/testing/selftests/ring-buffer/config new file mode 100644 index 000000000000..d936f8f00e78 --- /dev/null +++ b/tools/testing/selftests/ring-buffer/config @@ -0,0 +1,2 @@ +CONFIG_FTRACE=y +CONFIG_TRACER_SNAPSHOT=y diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c new file mode 100644 index 000000000000..a9006fa7097e --- /dev/null +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -0,0 +1,294 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Ring-buffer memory mapping tests + * + * Copyright (c) 2024 Vincent Donnefort + */ +#include +#include +#include +#include +#include +#include + +#include + +#include +#include + +#include "../user_events/user_events_selftests.h" /* share tracefs setup */ +#include "../kselftest_harness.h" + +#define TRACEFS_ROOT "/sys/kernel/tracing" + +static int __tracefs_write(const char *path, const char *value) +{ + int fd, ret; + + fd = open(path, O_WRONLY | O_TRUNC); + if (fd < 0) + return fd; + + ret = write(fd, value, strlen(value)); + + close(fd); + + return ret == -1 ? -errno : 0; +} + +static int __tracefs_write_int(const char *path, int value) +{ + char *str; + int ret; + + if (asprintf(&str, "%d", value) < 0) + return -1; + + ret = __tracefs_write(path, str); + + free(str); + + return ret; +} + +#define tracefs_write_int(path, value) \ + ASSERT_EQ(__tracefs_write_int((path), (value)), 0) + +#define tracefs_write(path, value) \ + ASSERT_EQ(__tracefs_write((path), (value)), 0) + +static int tracefs_reset(void) +{ + if (__tracefs_write_int(TRACEFS_ROOT"/tracing_on", 0)) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/trace", "")) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/set_event", "")) + return -1; + if (__tracefs_write(TRACEFS_ROOT"/current_tracer", "nop")) + return -1; + + return 0; +} + +struct tracefs_cpu_map_desc { + struct trace_buffer_meta *meta; + int cpu_fd; +}; + +int tracefs_cpu_map(struct tracefs_cpu_map_desc *desc, int cpu) +{ + int page_size = getpagesize(); + char *cpu_path; + void *map; + + if (asprintf(&cpu_path, + TRACEFS_ROOT"/per_cpu/cpu%d/trace_pipe_raw", + cpu) < 0) + return -ENOMEM; + + desc->cpu_fd = open(cpu_path, O_RDONLY | O_NONBLOCK); + free(cpu_path); + if (desc->cpu_fd < 0) + return -ENODEV; + + map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, desc->cpu_fd, 0); + if (map == MAP_FAILED) + return -errno; + + desc->meta = (struct trace_buffer_meta *)map; + + return 0; +} + +void tracefs_cpu_unmap(struct tracefs_cpu_map_desc *desc) +{ + munmap(desc->meta, desc->meta->meta_page_size); + close(desc->cpu_fd); +} + +FIXTURE(map) { + struct tracefs_cpu_map_desc map_desc; + bool umount; +}; + +FIXTURE_VARIANT(map) { + int subbuf_size; +}; + +FIXTURE_VARIANT_ADD(map, subbuf_size_4k) { + .subbuf_size = 4, +}; + +FIXTURE_VARIANT_ADD(map, subbuf_size_8k) { + .subbuf_size = 8, +}; + +FIXTURE_SETUP(map) +{ + int cpu = sched_getcpu(); + cpu_set_t cpu_mask; + bool fail, umount; + char *message; + + if (getuid() != 0) + SKIP(return, "Skipping: %s", "Please run the test as root"); + + if (!tracefs_enabled(&message, &fail, &umount)) { + if (fail) { + TH_LOG("Tracefs setup failed: %s", message); + ASSERT_FALSE(fail); + } + SKIP(return, "Skipping: %s", message); + } + + self->umount = umount; + + ASSERT_GE(cpu, 0); + + ASSERT_EQ(tracefs_reset(), 0); + + tracefs_write_int(TRACEFS_ROOT"/buffer_subbuf_size_kb", variant->subbuf_size); + + ASSERT_EQ(tracefs_cpu_map(&self->map_desc, cpu), 0); + + /* + * Ensure generated events will be found on this very same ring-buffer. + */ + CPU_ZERO(&cpu_mask); + CPU_SET(cpu, &cpu_mask); + ASSERT_EQ(sched_setaffinity(0, sizeof(cpu_mask), &cpu_mask), 0); +} + +FIXTURE_TEARDOWN(map) +{ + tracefs_reset(); + + if (self->umount) + tracefs_unmount(); + + tracefs_cpu_unmap(&self->map_desc); +} + +TEST_F(map, meta_page_check) +{ + struct tracefs_cpu_map_desc *desc = &self->map_desc; + int cnt = 0; + + ASSERT_EQ(desc->meta->entries, 0); + ASSERT_EQ(desc->meta->overrun, 0); + ASSERT_EQ(desc->meta->read, 0); + + ASSERT_EQ(desc->meta->reader.id, 0); + ASSERT_EQ(desc->meta->reader.read, 0); + + ASSERT_EQ(ioctl(desc->cpu_fd, TRACE_MMAP_IOCTL_GET_READER), 0); + ASSERT_EQ(desc->meta->reader.id, 0); + + tracefs_write_int(TRACEFS_ROOT"/tracing_on", 1); + for (int i = 0; i < 16; i++) + tracefs_write_int(TRACEFS_ROOT"/trace_marker", i); +again: + ASSERT_EQ(ioctl(desc->cpu_fd, TRACE_MMAP_IOCTL_GET_READER), 0); + + ASSERT_EQ(desc->meta->entries, 16); + ASSERT_EQ(desc->meta->overrun, 0); + ASSERT_EQ(desc->meta->read, 16); + + ASSERT_EQ(desc->meta->reader.id, 1); + + if (!(cnt++)) + goto again; +} + +TEST_F(map, data_mmap) +{ + struct tracefs_cpu_map_desc *desc = &self->map_desc; + unsigned long meta_len, data_len; + void *data; + + meta_len = desc->meta->meta_page_size; + data_len = desc->meta->subbuf_size * desc->meta->nr_subbufs; + + /* Map all the available subbufs */ + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, meta_len); + ASSERT_NE(data, MAP_FAILED); + munmap(data, data_len); + + /* Map all the available subbufs - 1 */ + data_len -= desc->meta->subbuf_size; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, meta_len); + ASSERT_NE(data, MAP_FAILED); + munmap(data, data_len); + + /* Overflow the available subbufs by 1 */ + meta_len += desc->meta->subbuf_size * 2; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, meta_len); + ASSERT_EQ(data, MAP_FAILED); +} + +FIXTURE(snapshot) { + bool umount; +}; + +FIXTURE_SETUP(snapshot) +{ + bool fail, umount; + struct stat sb; + char *message; + + if (getuid() != 0) + SKIP(return, "Skipping: %s", "Please run the test as root"); + + if (stat(TRACEFS_ROOT"/snapshot", &sb)) + SKIP(return, "Skipping: %s", "snapshot not available"); + + if (!tracefs_enabled(&message, &fail, &umount)) { + if (fail) { + TH_LOG("Tracefs setup failed: %s", message); + ASSERT_FALSE(fail); + } + SKIP(return, "Skipping: %s", message); + } + + self->umount = umount; +} + +FIXTURE_TEARDOWN(snapshot) +{ + __tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "!snapshot"); + tracefs_reset(); + + if (self->umount) + tracefs_unmount(); +} + +TEST_F(snapshot, excludes_map) +{ + struct tracefs_cpu_map_desc map_desc; + int cpu = sched_getcpu(); + + ASSERT_GE(cpu, 0); + tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "snapshot"); + ASSERT_EQ(tracefs_cpu_map(&map_desc, cpu), -EBUSY); +} + +TEST_F(snapshot, excluded_by_map) +{ + struct tracefs_cpu_map_desc map_desc; + int cpu = sched_getcpu(); + + ASSERT_EQ(tracefs_cpu_map(&map_desc, cpu), 0); + + ASSERT_EQ(__tracefs_write(TRACEFS_ROOT"/events/sched/sched_switch/trigger", + "snapshot"), -EBUSY); + ASSERT_EQ(__tracefs_write(TRACEFS_ROOT"/snapshot", + "1"), -EBUSY); +} + +TEST_HARNESS_MAIN