lttng lib: ring buffer

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

drivers/staging/lttng/lib/ringbuffer/api.h

+#ifndef _LINUX_RING_BUFFER_API_H
+#define _LINUX_RING_BUFFER_API_H
+
+/*
+ * linux/ringbuffer/api.h
+ *
+ * Copyright (C) 2010 - Mathieu Desnoyers "mathieu.desnoyers@efficios.com"
+ *
+ * Ring Buffer API.
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#include "../../wrapper/ringbuffer/backend.h"
+#include "../../wrapper/ringbuffer/frontend.h"
+#include "../../wrapper/ringbuffer/vfs.h"
+
+/*
+ * ring_buffer_frontend_api.h contains static inline functions that depend on
+ * client static inlines. Hence the inclusion of this "api" header only
+ * within the client.
+ */
+#include "../../wrapper/ringbuffer/frontend_api.h"
+
+#endif /* _LINUX_RING_BUFFER_API_H */

drivers/staging/lttng/lib/ringbuffer/backend.h

+#ifndef _LINUX_RING_BUFFER_BACKEND_H
+#define _LINUX_RING_BUFFER_BACKEND_H
+
+/*
+ * linux/ringbuffer/backend.h
+ *
+ * Copyright (C) 2008-2010 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Ring buffer backend (API).
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ *
+ * Credits to Steven Rostedt for proposing to use an extra-subbuffer owned by
+ * the reader in flight recorder mode.
+ */
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/poll.h>
+#include <linux/list.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+/* Internal helpers */
+#include "../../wrapper/ringbuffer/backend_internal.h"
+#include "../../wrapper/ringbuffer/frontend_internal.h"
+
+/* Ring buffer backend API */
+
+/* Ring buffer backend access (read/write) */
+
+extern size_t lib_ring_buffer_read(struct lib_ring_buffer_backend *bufb,
+				   size_t offset, void *dest, size_t len);
+
+extern int __lib_ring_buffer_copy_to_user(struct lib_ring_buffer_backend *bufb,
+					  size_t offset, void __user *dest,
+					  size_t len);
+
+extern int lib_ring_buffer_read_cstr(struct lib_ring_buffer_backend *bufb,
+				     size_t offset, void *dest, size_t len);
+
+extern struct page **
+lib_ring_buffer_read_get_page(struct lib_ring_buffer_backend *bufb, size_t offset,
+			      void ***virt);
+
+/*
+ * Return the address where a given offset is located.
+ * Should be used to get the current subbuffer header pointer. Given we know
+ * it's never on a page boundary, it's safe to write directly to this address,
+ * as long as the write is never bigger than a page size.
+ */
+extern void *
+lib_ring_buffer_offset_address(struct lib_ring_buffer_backend *bufb,
+			       size_t offset);
+extern void *
+lib_ring_buffer_read_offset_address(struct lib_ring_buffer_backend *bufb,
+				    size_t offset);
+
+/**
+ * lib_ring_buffer_write - write data to a buffer backend
+ * @config : ring buffer instance configuration
+ * @ctx: ring buffer context. (input arguments only)
+ * @src : source pointer to copy from
+ * @len : length of data to copy
+ *
+ * This function copies "len" bytes of data from a source pointer to a buffer
+ * backend, at the current context offset. This is more or less a buffer
+ * backend-specific memcpy() operation. Calls the slow path (_ring_buffer_write)
+ * if copy is crossing a page boundary.
+ */
+static inline
+void lib_ring_buffer_write(const struct lib_ring_buffer_config *config,
+			   struct lib_ring_buffer_ctx *ctx,
+			   const void *src, size_t len)
+{
+	struct lib_ring_buffer_backend *bufb = &ctx->buf->backend;
+	struct channel_backend *chanb = &ctx->chan->backend;
+	size_t sbidx, index;
+	size_t offset = ctx->buf_offset;
+	ssize_t pagecpy;
+	struct lib_ring_buffer_backend_pages *rpages;
+	unsigned long sb_bindex, id;
+
+	offset &= chanb->buf_size - 1;
+	sbidx = offset >> chanb->subbuf_size_order;
+	index = (offset & (chanb->subbuf_size - 1)) >> PAGE_SHIFT;
+	pagecpy = min_t(size_t, len, (-offset) & ~PAGE_MASK);
+	id = bufb->buf_wsb[sbidx].id;
+	sb_bindex = subbuffer_id_get_index(config, id);
+	rpages = bufb->array[sb_bindex];
+	CHAN_WARN_ON(ctx->chan,
+		     config->mode == RING_BUFFER_OVERWRITE
+		     && subbuffer_id_is_noref(config, id));
+	if (likely(pagecpy == len))
+		lib_ring_buffer_do_copy(config,
+					rpages->p[index].virt
+					    + (offset & ~PAGE_MASK),
+					src, len);
+	else
+		_lib_ring_buffer_write(bufb, offset, src, len, 0);
+	ctx->buf_offset += len;
+}
+
+/**
+ * lib_ring_buffer_memset - write len bytes of c to a buffer backend
+ * @config : ring buffer instance configuration
+ * @bufb : ring buffer backend
+ * @offset : offset within the buffer
+ * @c : the byte to copy
+ * @len : number of bytes to copy
+ *
+ * This function writes "len" bytes of "c" to a buffer backend, at a specific
+ * offset. This is more or less a buffer backend-specific memset() operation.
+ * Calls the slow path (_ring_buffer_memset) if write is crossing a page
+ * boundary.
+ */
+static inline
+void lib_ring_buffer_memset(const struct lib_ring_buffer_config *config,
+			    struct lib_ring_buffer_ctx *ctx, int c, size_t len)
+{
+
+	struct lib_ring_buffer_backend *bufb = &ctx->buf->backend;
+	struct channel_backend *chanb = &ctx->chan->backend;
+	size_t sbidx, index;
+	size_t offset = ctx->buf_offset;
+	ssize_t pagecpy;
+	struct lib_ring_buffer_backend_pages *rpages;
+	unsigned long sb_bindex, id;
+
+	offset &= chanb->buf_size - 1;
+	sbidx = offset >> chanb->subbuf_size_order;
+	index = (offset & (chanb->subbuf_size - 1)) >> PAGE_SHIFT;
+	pagecpy = min_t(size_t, len, (-offset) & ~PAGE_MASK);
+	id = bufb->buf_wsb[sbidx].id;
+	sb_bindex = subbuffer_id_get_index(config, id);
+	rpages = bufb->array[sb_bindex];
+	CHAN_WARN_ON(ctx->chan,
+		     config->mode == RING_BUFFER_OVERWRITE
+		     && subbuffer_id_is_noref(config, id));
+	if (likely(pagecpy == len))
+		lib_ring_buffer_do_memset(rpages->p[index].virt
+					  + (offset & ~PAGE_MASK),
+					  c, len);
+	else
+		_lib_ring_buffer_memset(bufb, offset, c, len, 0);
+	ctx->buf_offset += len;
+}
+
+/**
+ * lib_ring_buffer_copy_from_user - write userspace data to a buffer backend
+ * @config : ring buffer instance configuration
+ * @ctx: ring buffer context. (input arguments only)
+ * @src : userspace source pointer to copy from
+ * @len : length of data to copy
+ *
+ * This function copies "len" bytes of data from a userspace pointer to a
+ * buffer backend, at the current context offset. This is more or less a buffer
+ * backend-specific memcpy() operation. Calls the slow path
+ * (_ring_buffer_write_from_user) if copy is crossing a page boundary.
+ */
+static inline
+void lib_ring_buffer_copy_from_user(const struct lib_ring_buffer_config *config,
+				    struct lib_ring_buffer_ctx *ctx,
+				    const void __user *src, size_t len)
+{
+	struct lib_ring_buffer_backend *bufb = &ctx->buf->backend;
+	struct channel_backend *chanb = &ctx->chan->backend;
+	size_t sbidx, index;
+	size_t offset = ctx->buf_offset;
+	ssize_t pagecpy;
+	struct lib_ring_buffer_backend_pages *rpages;
+	unsigned long sb_bindex, id;
+	unsigned long ret;
+
+	offset &= chanb->buf_size - 1;
+	sbidx = offset >> chanb->subbuf_size_order;
+	index = (offset & (chanb->subbuf_size - 1)) >> PAGE_SHIFT;
+	pagecpy = min_t(size_t, len, (-offset) & ~PAGE_MASK);
+	id = bufb->buf_wsb[sbidx].id;
+	sb_bindex = subbuffer_id_get_index(config, id);
+	rpages = bufb->array[sb_bindex];
+	CHAN_WARN_ON(ctx->chan,
+		     config->mode == RING_BUFFER_OVERWRITE
+		     && subbuffer_id_is_noref(config, id));
+
+	if (unlikely(!access_ok(VERIFY_READ, src, len)))
+		goto fill_buffer;
+
+	if (likely(pagecpy == len)) {
+		ret = lib_ring_buffer_do_copy_from_user(
+			rpages->p[index].virt + (offset & ~PAGE_MASK),
+			src, len);
+		if (unlikely(ret > 0)) {
+			len -= (pagecpy - ret);
+			offset += (pagecpy - ret);
+			goto fill_buffer;
+		}
+	} else {
+		_lib_ring_buffer_copy_from_user(bufb, offset, src, len, 0);
+	}
+	ctx->buf_offset += len;
+
+	return;
+
+fill_buffer:
+	/*
+	 * In the error path we call the slow path version to avoid
+	 * the pollution of static inline code.
+	 */
+	_lib_ring_buffer_memset(bufb, offset, 0, len, 0);
+}
+
+/*
+ * This accessor counts the number of unread records in a buffer.
+ * It only provides a consistent value if no reads not writes are performed
+ * concurrently.
+ */
+static inline
+unsigned long lib_ring_buffer_get_records_unread(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	struct lib_ring_buffer_backend *bufb = &buf->backend;
+	struct lib_ring_buffer_backend_pages *pages;
+	unsigned long records_unread = 0, sb_bindex, id;
+	unsigned int i;
+
+	for (i = 0; i < bufb->chan->backend.num_subbuf; i++) {
+		id = bufb->buf_wsb[i].id;
+		sb_bindex = subbuffer_id_get_index(config, id);
+		pages = bufb->array[sb_bindex];
+		records_unread += v_read(config, &pages->records_unread);
+	}
+	if (config->mode == RING_BUFFER_OVERWRITE) {
+		id = bufb->buf_rsb.id;
+		sb_bindex = subbuffer_id_get_index(config, id);
+		pages = bufb->array[sb_bindex];
+		records_unread += v_read(config, &pages->records_unread);
+	}
+	return records_unread;
+}
+
+ssize_t lib_ring_buffer_file_splice_read(struct file *in, loff_t *ppos,
+					 struct pipe_inode_info *pipe,
+					 size_t len, unsigned int flags);
+loff_t lib_ring_buffer_no_llseek(struct file *file, loff_t offset, int origin);
+
+#endif /* _LINUX_RING_BUFFER_BACKEND_H */

drivers/staging/lttng/lib/ringbuffer/backend_types.h

+#ifndef _LINUX_RING_BUFFER_BACKEND_TYPES_H
+#define _LINUX_RING_BUFFER_BACKEND_TYPES_H
+
+/*
+ * linux/ringbuffer/backend_types.h
+ *
+ * Copyright (C) 2008-2010 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Ring buffer backend (types).
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#include <linux/cpumask.h>
+#include <linux/types.h>
+
+struct lib_ring_buffer_backend_page {
+	void *virt;			/* page virtual address (cached) */
+	struct page *page;		/* pointer to page structure */
+};
+
+struct lib_ring_buffer_backend_pages {
+	unsigned long mmap_offset;	/* offset of the subbuffer in mmap */
+	union v_atomic records_commit;	/* current records committed count */
+	union v_atomic records_unread;	/* records to read */
+	unsigned long data_size;	/* Amount of data to read from subbuf */
+	struct lib_ring_buffer_backend_page p[];
+};
+
+struct lib_ring_buffer_backend_subbuffer {
+	/* Identifier for subbuf backend pages. Exchanged atomically. */
+	unsigned long id;		/* backend subbuffer identifier */
+};
+
+/*
+ * Forward declaration of frontend-specific channel and ring_buffer.
+ */
+struct channel;
+struct lib_ring_buffer;
+
+struct lib_ring_buffer_backend {
+	/* Array of ring_buffer_backend_subbuffer for writer */
+	struct lib_ring_buffer_backend_subbuffer *buf_wsb;
+	/* ring_buffer_backend_subbuffer for reader */
+	struct lib_ring_buffer_backend_subbuffer buf_rsb;
+	/*
+	 * Pointer array of backend pages, for whole buffer.
+	 * Indexed by ring_buffer_backend_subbuffer identifier (id) index.
+	 */
+	struct lib_ring_buffer_backend_pages **array;
+	unsigned int num_pages_per_subbuf;
+
+	struct channel *chan;		/* Associated channel */
+	int cpu;			/* This buffer's cpu. -1 if global. */
+	union v_atomic records_read;	/* Number of records read */
+	unsigned int allocated:1;	/* Bool: is buffer allocated ? */
+};
+
+struct channel_backend {
+	unsigned long buf_size;		/* Size of the buffer */
+	unsigned long subbuf_size;	/* Sub-buffer size */
+	unsigned int subbuf_size_order;	/* Order of sub-buffer size */
+	unsigned int num_subbuf_order;	/*
+					 * Order of number of sub-buffers/buffer
+					 * for writer.
+					 */
+	unsigned int buf_size_order;	/* Order of buffer size */
+	int extra_reader_sb:1;		/* Bool: has extra reader subbuffer */
+	struct lib_ring_buffer *buf;	/* Channel per-cpu buffers */
+
+	unsigned long num_subbuf;	/* Number of sub-buffers for writer */
+	u64 start_tsc;			/* Channel creation TSC value */
+	void *priv;			/* Client-specific information */
+	struct notifier_block cpu_hp_notifier;	 /* CPU hotplug notifier */
+	const struct lib_ring_buffer_config *config; /* Ring buffer configuration */
+	cpumask_var_t cpumask;		/* Allocated per-cpu buffers cpumask */
+	char name[NAME_MAX];		/* Channel name */
+};
+
+#endif /* _LINUX_RING_BUFFER_BACKEND_TYPES_H */

drivers/staging/lttng/lib/ringbuffer/config.h

+#ifndef _LINUX_RING_BUFFER_CONFIG_H
+#define _LINUX_RING_BUFFER_CONFIG_H
+
+/*
+ * linux/ringbuffer/config.h
+ *
+ * Copyright (C) 2010 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Ring buffer configuration header. Note: after declaring the standard inline
+ * functions, clients should also include linux/ringbuffer/api.h.
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+#include "../align.h"
+
+struct lib_ring_buffer;
+struct channel;
+struct lib_ring_buffer_config;
+struct lib_ring_buffer_ctx;
+
+/*
+ * Ring buffer client callbacks. Only used by slow path, never on fast path.
+ * For the fast path, record_header_size(), ring_buffer_clock_read() should be
+ * provided as inline functions too.  These may simply return 0 if not used by
+ * the client.
+ */
+struct lib_ring_buffer_client_cb {
+	/* Mandatory callbacks */
+
+	/* A static inline version is also required for fast path */
+	u64 (*ring_buffer_clock_read) (struct channel *chan);
+	size_t (*record_header_size) (const struct lib_ring_buffer_config *config,
+				      struct channel *chan, size_t offset,
+				      size_t *pre_header_padding,
+				      struct lib_ring_buffer_ctx *ctx);
+
+	/* Slow path only, at subbuffer switch */
+	size_t (*subbuffer_header_size) (void);
+	void (*buffer_begin) (struct lib_ring_buffer *buf, u64 tsc,
+			      unsigned int subbuf_idx);
+	void (*buffer_end) (struct lib_ring_buffer *buf, u64 tsc,
+			    unsigned int subbuf_idx, unsigned long data_size);
+
+	/* Optional callbacks (can be set to NULL) */
+
+	/* Called at buffer creation/finalize */
+	int (*buffer_create) (struct lib_ring_buffer *buf, void *priv,
+			      int cpu, const char *name);
+	/*
+	 * Clients should guarantee that no new reader handle can be opened
+	 * after finalize.
+	 */
+	void (*buffer_finalize) (struct lib_ring_buffer *buf, void *priv, int cpu);
+
+	/*
+	 * Extract header length, payload length and timestamp from event
+	 * record. Used by buffer iterators. Timestamp is only used by channel
+	 * iterator.
+	 */
+	void (*record_get) (const struct lib_ring_buffer_config *config,
+			    struct channel *chan, struct lib_ring_buffer *buf,
+			    size_t offset, size_t *header_len,
+			    size_t *payload_len, u64 *timestamp);
+};
+
+/*
+ * Ring buffer instance configuration.
+ *
+ * Declare as "static const" within the client object to ensure the inline fast
+ * paths can be optimized.
+ *
+ * alloc/sync pairs:
+ *
+ * RING_BUFFER_ALLOC_PER_CPU and RING_BUFFER_SYNC_PER_CPU :
+ *   Per-cpu buffers with per-cpu synchronization. Tracing must be performed
+ *   with preemption disabled (lib_ring_buffer_get_cpu() and
+ *   lib_ring_buffer_put_cpu()).
+ *
+ * RING_BUFFER_ALLOC_PER_CPU and RING_BUFFER_SYNC_GLOBAL :
+ *   Per-cpu buffer with global synchronization. Tracing can be performed with
+ *   preemption enabled, statistically stays on the local buffers.
+ *
+ * RING_BUFFER_ALLOC_GLOBAL and RING_BUFFER_SYNC_PER_CPU :
+ *   Should only be used for buffers belonging to a single thread or protected
+ *   by mutual exclusion by the client. Note that periodical sub-buffer switch
+ *   should be disabled in this kind of configuration.
+ *
+ * RING_BUFFER_ALLOC_GLOBAL and RING_BUFFER_SYNC_GLOBAL :
+ *   Global shared buffer with global synchronization.
+ *
+ * wakeup:
+ *
+ * RING_BUFFER_WAKEUP_BY_TIMER uses per-cpu deferrable timers to poll the
+ * buffers and wake up readers if data is ready. Mainly useful for tracers which
+ * don't want to call into the wakeup code on the tracing path. Use in
+ * combination with "read_timer_interval" channel_create() argument.
+ *
+ * RING_BUFFER_WAKEUP_BY_WRITER directly wakes up readers when a subbuffer is
+ * ready to read. Lower latencies before the reader is woken up. Mainly suitable
+ * for drivers.
+ *
+ * RING_BUFFER_WAKEUP_NONE does not perform any wakeup whatsoever. The client
+ * has the responsibility to perform wakeups.
+ */
+struct lib_ring_buffer_config {
+	enum {
+		RING_BUFFER_ALLOC_PER_CPU,
+		RING_BUFFER_ALLOC_GLOBAL,
+	} alloc;
+	enum {
+		RING_BUFFER_SYNC_PER_CPU,	/* Wait-free */
+		RING_BUFFER_SYNC_GLOBAL,	/* Lock-free */
+	} sync;
+	enum {
+		RING_BUFFER_OVERWRITE,		/* Overwrite when buffer full */
+		RING_BUFFER_DISCARD,		/* Discard when buffer full */
+	} mode;
+	enum {
+		RING_BUFFER_SPLICE,
+		RING_BUFFER_MMAP,
+		RING_BUFFER_READ,		/* TODO */
+		RING_BUFFER_ITERATOR,
+		RING_BUFFER_NONE,
+	} output;
+	enum {
+		RING_BUFFER_PAGE,
+		RING_BUFFER_VMAP,		/* TODO */
+		RING_BUFFER_STATIC,		/* TODO */
+	} backend;
+	enum {
+		RING_BUFFER_NO_OOPS_CONSISTENCY,
+		RING_BUFFER_OOPS_CONSISTENCY,
+	} oops;
+	enum {
+		RING_BUFFER_IPI_BARRIER,
+		RING_BUFFER_NO_IPI_BARRIER,
+	} ipi;
+	enum {
+		RING_BUFFER_WAKEUP_BY_TIMER,	/* wake up performed by timer */
+		RING_BUFFER_WAKEUP_BY_WRITER,	/*
+						 * writer wakes up reader,
+						 * not lock-free
+						 * (takes spinlock).
+						 */
+	} wakeup;
+	/*
+	 * tsc_bits: timestamp bits saved at each record.
+	 *   0 and 64 disable the timestamp compression scheme.
+	 */
+	unsigned int tsc_bits;
+	struct lib_ring_buffer_client_cb cb;
+};
+
+/*
+ * ring buffer context
+ *
+ * Context passed to lib_ring_buffer_reserve(), lib_ring_buffer_commit(),
+ * lib_ring_buffer_try_discard_reserve(), lib_ring_buffer_align_ctx() and
+ * lib_ring_buffer_write().
+ */
+struct lib_ring_buffer_ctx {
+	/* input received by lib_ring_buffer_reserve(), saved here. */
+	struct channel *chan;		/* channel */
+	void *priv;			/* client private data */
+	size_t data_size;		/* size of payload */
+	int largest_align;		/*
+					 * alignment of the largest element
+					 * in the payload
+					 */
+	int cpu;			/* processor id */
+
+	/* output from lib_ring_buffer_reserve() */
+	struct lib_ring_buffer *buf;	/*
+					 * buffer corresponding to processor id
+					 * for this channel
+					 */
+	size_t slot_size;		/* size of the reserved slot */
+	unsigned long buf_offset;	/* offset following the record header */
+	unsigned long pre_offset;	/*
+					 * Initial offset position _before_
+					 * the record is written. Positioned
+					 * prior to record header alignment
+					 * padding.
+					 */
+	u64 tsc;			/* time-stamp counter value */
+	unsigned int rflags;		/* reservation flags */
+};
+
+/**
+ * lib_ring_buffer_ctx_init - initialize ring buffer context
+ * @ctx: ring buffer context to initialize
+ * @chan: channel
+ * @priv: client private data
+ * @data_size: size of record data payload
+ * @largest_align: largest alignment within data payload types
+ * @cpu: processor id
+ */
+static inline
+void lib_ring_buffer_ctx_init(struct lib_ring_buffer_ctx *ctx,
+			      struct channel *chan, void *priv,
+			      size_t data_size, int largest_align,
+			      int cpu)
+{
+	ctx->chan = chan;
+	ctx->priv = priv;
+	ctx->data_size = data_size;
+	ctx->largest_align = largest_align;
+	ctx->cpu = cpu;
+	ctx->rflags = 0;
+}
+
+/*
+ * Reservation flags.
+ *
+ * RING_BUFFER_RFLAG_FULL_TSC
+ *
+ * This flag is passed to record_header_size() and to the primitive used to
+ * write the record header. It indicates that the full 64-bit time value is
+ * needed in the record header. If this flag is not set, the record header needs
+ * only to contain "tsc_bits" bit of time value.
+ *
+ * Reservation flags can be added by the client, starting from
+ * "(RING_BUFFER_FLAGS_END << 0)". It can be used to pass information from
+ * record_header_size() to lib_ring_buffer_write_record_header().
+ */
+#define	RING_BUFFER_RFLAG_FULL_TSC		(1U << 0)
+#define RING_BUFFER_RFLAG_END			(1U << 1)
+
+/*
+ * We need to define RING_BUFFER_ALIGN_ATTR so it is known early at
+ * compile-time. We have to duplicate the "config->align" information and the
+ * definition here because config->align is used both in the slow and fast
+ * paths, but RING_BUFFER_ALIGN_ATTR is only available for the client code.
+ */
+#ifdef RING_BUFFER_ALIGN
+
+# define RING_BUFFER_ALIGN_ATTR		/* Default arch alignment */
+
+/*
+ * Calculate the offset needed to align the type.
+ * size_of_type must be non-zero.
+ */
+static inline
+unsigned int lib_ring_buffer_align(size_t align_drift, size_t size_of_type)
+{
+	return offset_align(align_drift, size_of_type);
+}
+
+#else
+
+# define RING_BUFFER_ALIGN_ATTR __attribute__((packed))
+
+/*
+ * Calculate the offset needed to align the type.
+ * size_of_type must be non-zero.
+ */
+static inline
+unsigned int lib_ring_buffer_align(size_t align_drift, size_t size_of_type)
+{
+	return 0;
+}
+
+#endif
+
+/**
+ * lib_ring_buffer_align_ctx - Align context offset on "alignment"
+ * @ctx: ring buffer context.
+ */
+static inline
+void lib_ring_buffer_align_ctx(struct lib_ring_buffer_ctx *ctx,
+			   size_t alignment)
+{
+	ctx->buf_offset += lib_ring_buffer_align(ctx->buf_offset,
+						 alignment);
+}
+
+/*
+ * lib_ring_buffer_check_config() returns 0 on success.
+ * Used internally to check for valid configurations at channel creation.
+ */
+static inline
+int lib_ring_buffer_check_config(const struct lib_ring_buffer_config *config,
+			     unsigned int switch_timer_interval,
+			     unsigned int read_timer_interval)
+{
+	if (config->alloc == RING_BUFFER_ALLOC_GLOBAL
+	    && config->sync == RING_BUFFER_SYNC_PER_CPU
+	    && switch_timer_interval)
+		return -EINVAL;
+	return 0;
+}
+
+#include "../../wrapper/ringbuffer/vatomic.h"
+
+#endif /* _LINUX_RING_BUFFER_CONFIG_H */

drivers/staging/lttng/lib/ringbuffer/frontend.h

+#ifndef _LINUX_RING_BUFFER_FRONTEND_H
+#define _LINUX_RING_BUFFER_FRONTEND_H
+
+/*
+ * linux/ringbuffer/frontend.h
+ *
+ * (C) Copyright 2005-2010 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Ring Buffer Library Synchronization Header (API).
+ *
+ * Author:
+ *	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * See ring_buffer_frontend.c for more information on wait-free algorithms.
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#include <linux/pipe_fs_i.h>
+#include <linux/rcupdate.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/splice.h>
+#include <linux/string.h>
+#include <linux/timer.h>
+#include <linux/sched.h>
+#include <linux/cache.h>
+#include <linux/time.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/stat.h>
+#include <linux/cpu.h>
+#include <linux/fs.h>
+
+#include <asm/atomic.h>
+#include <asm/local.h>
+
+/* Internal helpers */
+#include "../../wrapper/ringbuffer/frontend_internal.h"
+
+/* Buffer creation/removal and setup operations */
+
+/*
+ * switch_timer_interval is the time interval (in us) to fill sub-buffers with
+ * padding to let readers get those sub-buffers.  Used for live streaming.
+ *
+ * read_timer_interval is the time interval (in us) to wake up pending readers.
+ *
+ * buf_addr is a pointer the the beginning of the preallocated buffer contiguous
+ * address mapping. It is used only by RING_BUFFER_STATIC configuration. It can
+ * be set to NULL for other backends.
+ */
+
+extern
+struct channel *channel_create(const struct lib_ring_buffer_config *config,
+			       const char *name, void *priv,
+			       void *buf_addr,
+			       size_t subbuf_size, size_t num_subbuf,
+			       unsigned int switch_timer_interval,
+			       unsigned int read_timer_interval);
+
+/*
+ * channel_destroy returns the private data pointer. It finalizes all channel's
+ * buffers, waits for readers to release all references, and destroys the
+ * channel.
+ */
+extern
+void *channel_destroy(struct channel *chan);
+
+
+/* Buffer read operations */
+
+/*
+ * Iteration on channel cpumask needs to issue a read barrier to match the write
+ * barrier in cpu hotplug. It orders the cpumask read before read of per-cpu
+ * buffer data. The per-cpu buffer is never removed by cpu hotplug; teardown is
+ * only performed at channel destruction.
+ */
+#define for_each_channel_cpu(cpu, chan)					\
+	for ((cpu) = -1;						\
+		({ (cpu) = cpumask_next(cpu, (chan)->backend.cpumask);	\
+		   smp_read_barrier_depends(); (cpu) < nr_cpu_ids; });)
+
+extern struct lib_ring_buffer *channel_get_ring_buffer(
+				const struct lib_ring_buffer_config *config,
+				struct channel *chan, int cpu);
+extern int lib_ring_buffer_open_read(struct lib_ring_buffer *buf);
+extern void lib_ring_buffer_release_read(struct lib_ring_buffer *buf);
+
+/*
+ * Read sequence: snapshot, many get_subbuf/put_subbuf, move_consumer.
+ */
+extern int lib_ring_buffer_snapshot(struct lib_ring_buffer *buf,
+				    unsigned long *consumed,
+				    unsigned long *produced);
+extern void lib_ring_buffer_move_consumer(struct lib_ring_buffer *buf,
+					  unsigned long consumed_new);
+
+extern int lib_ring_buffer_get_subbuf(struct lib_ring_buffer *buf,
+				      unsigned long consumed);
+extern void lib_ring_buffer_put_subbuf(struct lib_ring_buffer *buf);
+
+/*
+ * lib_ring_buffer_get_next_subbuf/lib_ring_buffer_put_next_subbuf are helpers
+ * to read sub-buffers sequentially.
+ */
+static inline int lib_ring_buffer_get_next_subbuf(struct lib_ring_buffer *buf)
+{
+	int ret;
+
+	ret = lib_ring_buffer_snapshot(buf, &buf->cons_snapshot,
+				       &buf->prod_snapshot);
+	if (ret)
+		return ret;
+	ret = lib_ring_buffer_get_subbuf(buf, buf->cons_snapshot);
+	return ret;
+}
+
+static inline void lib_ring_buffer_put_next_subbuf(struct lib_ring_buffer *buf)
+{
+	lib_ring_buffer_put_subbuf(buf);
+	lib_ring_buffer_move_consumer(buf, subbuf_align(buf->cons_snapshot,
+						    buf->backend.chan));
+}
+
+extern void channel_reset(struct channel *chan);
+extern void lib_ring_buffer_reset(struct lib_ring_buffer *buf);
+
+static inline
+unsigned long lib_ring_buffer_get_offset(const struct lib_ring_buffer_config *config,
+					 struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->offset);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_consumed(const struct lib_ring_buffer_config *config,
+					   struct lib_ring_buffer *buf)
+{
+	return atomic_long_read(&buf->consumed);
+}
+
+/*
+ * Must call lib_ring_buffer_is_finalized before reading counters (memory
+ * ordering enforced with respect to trace teardown).
+ */
+static inline
+int lib_ring_buffer_is_finalized(const struct lib_ring_buffer_config *config,
+				 struct lib_ring_buffer *buf)
+{
+	int finalized = ACCESS_ONCE(buf->finalized);
+	/*
+	 * Read finalized before counters.
+	 */
+	smp_rmb();
+	return finalized;
+}
+
+static inline
+int lib_ring_buffer_channel_is_finalized(const struct channel *chan)
+{
+	return chan->finalized;
+}
+
+static inline
+int lib_ring_buffer_channel_is_disabled(const struct channel *chan)
+{
+	return atomic_read(&chan->record_disabled);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_read_data_size(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return subbuffer_get_read_data_size(config, &buf->backend);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_records_count(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->records_count);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_records_overrun(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->records_overrun);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_records_lost_full(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->records_lost_full);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_records_lost_wrap(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->records_lost_wrap);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_records_lost_big(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->records_lost_big);
+}
+
+static inline
+unsigned long lib_ring_buffer_get_records_read(
+				const struct lib_ring_buffer_config *config,
+				struct lib_ring_buffer *buf)
+{
+	return v_read(config, &buf->backend.records_read);
+}
+
+#endif /* _LINUX_RING_BUFFER_FRONTEND_H */

drivers/staging/lttng/lib/ringbuffer/frontend_types.h

+#ifndef _LINUX_RING_BUFFER_FRONTEND_TYPES_H
+#define _LINUX_RING_BUFFER_FRONTEND_TYPES_H
+
+/*
+ * linux/ringbuffer/frontend_types.h
+ *
+ * (C) Copyright 2005-2010 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Ring Buffer Library Synchronization Header (types).
+ *
+ * Author:
+ *	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * See ring_buffer_frontend.c for more information on wait-free algorithms.
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#include <linux/kref.h>
+#include "../../wrapper/ringbuffer/config.h"
+#include "../../wrapper/ringbuffer/backend_types.h"
+#include "../../wrapper/spinlock.h"
+#include "../../lib/prio_heap/lttng_prio_heap.h"	/* For per-CPU read-side iterator */
+
+/*
+ * A switch is done during tracing or as a final flush after tracing (so it
+ * won't write in the new sub-buffer).
+ */
+enum switch_mode { SWITCH_ACTIVE, SWITCH_FLUSH };
+
+/* channel-level read-side iterator */
+struct channel_iter {
+	/* Prio heap of buffers. Lowest timestamps at the top. */
+	struct lttng_ptr_heap heap;	/* Heap of struct lib_ring_buffer ptrs */
+	struct list_head empty_head;	/* Empty buffers linked-list head */
+	int read_open;			/* Opened for reading ? */
+	u64 last_qs;			/* Last quiescent state timestamp */
+	u64 last_timestamp;		/* Last timestamp (for WARN_ON) */
+	int last_cpu;			/* Last timestamp cpu */
+	/*
+	 * read() file operation state.
+	 */
+	unsigned long len_left;
+};
+
+/* channel: collection of per-cpu ring buffers. */
+struct channel {
+	atomic_t record_disabled;
+	unsigned long commit_count_mask;	/*
+						 * Commit count mask, removing
+						 * the MSBs corresponding to
+						 * bits used to represent the
+						 * subbuffer index.
+						 */
+
+	struct channel_backend backend;		/* Associated backend */
+
+	unsigned long switch_timer_interval;	/* Buffer flush (jiffies) */
+	unsigned long read_timer_interval;	/* Reader wakeup (jiffies) */
+	struct notifier_block cpu_hp_notifier;	/* CPU hotplug notifier */
+	struct notifier_block tick_nohz_notifier; /* CPU nohz notifier */
+	struct notifier_block hp_iter_notifier;	/* hotplug iterator notifier */
+	int cpu_hp_enable:1;			/* Enable CPU hotplug notif. */
+	int hp_iter_enable:1;			/* Enable hp iter notif. */
+	wait_queue_head_t read_wait;		/* reader wait queue */
+	wait_queue_head_t hp_wait;		/* CPU hotplug wait queue */
+	int finalized;				/* Has channel been finalized */
+	struct channel_iter iter;		/* Channel read-side iterator */
+	struct kref ref;			/* Reference count */
+};
+
+/* Per-subbuffer commit counters used on the hot path */
+struct commit_counters_hot {
+	union v_atomic cc;		/* Commit counter */
+	union v_atomic seq;		/* Consecutive commits */
+};
+
+/* Per-subbuffer commit counters used only on cold paths */
+struct commit_counters_cold {
+	union v_atomic cc_sb;		/* Incremented _once_ at sb switch */
+};
+
+/* Per-buffer read iterator */
+struct lib_ring_buffer_iter {
+	u64 timestamp;			/* Current record timestamp */
+	size_t header_len;		/* Current record header length */
+	size_t payload_len;		/* Current record payload length */
+
+	struct list_head empty_node;	/* Linked list of empty buffers */
+	unsigned long consumed, read_offset, data_size;
+	enum {
+		ITER_GET_SUBBUF = 0,
+		ITER_TEST_RECORD,
+		ITER_NEXT_RECORD,
+		ITER_PUT_SUBBUF,
+	} state;
+	int allocated:1;
+	int read_open:1;		/* Opened for reading ? */
+};
+
+/* ring buffer state */
+struct lib_ring_buffer {
+	/* First 32 bytes cache-hot cacheline */
+	union v_atomic offset;		/* Current offset in the buffer */
+	struct commit_counters_hot *commit_hot;
+					/* Commit count per sub-buffer */
+	atomic_long_t consumed;		/*
+					 * Current offset in the buffer
+					 * standard atomic access (shared)
+					 */
+	atomic_t record_disabled;
+	/* End of first 32 bytes cacheline */
+	union v_atomic last_tsc;	/*
+					 * Last timestamp written in the buffer.
+					 */
+
+	struct lib_ring_buffer_backend backend;	/* Associated backend */
+
+	struct commit_counters_cold *commit_cold;
+					/* Commit count per sub-buffer */
+	atomic_long_t active_readers;	/*
+					 * Active readers count
+					 * standard atomic access (shared)
+					 */
+					/* Dropped records */
+	union v_atomic records_lost_full;	/* Buffer full */
+	union v_atomic records_lost_wrap;	/* Nested wrap-around */
+	union v_atomic records_lost_big;	/* Events too big */
+	union v_atomic records_count;	/* Number of records written */
+	union v_atomic records_overrun;	/* Number of overwritten records */
+	wait_queue_head_t read_wait;	/* reader buffer-level wait queue */
+	wait_queue_head_t write_wait;	/* writer buffer-level wait queue (for metadata only) */
+	int finalized;			/* buffer has been finalized */
+	struct timer_list switch_timer;	/* timer for periodical switch */
+	struct timer_list read_timer;	/* timer for read poll */
+	raw_spinlock_t raw_tick_nohz_spinlock;	/* nohz entry lock/trylock */
+	struct lib_ring_buffer_iter iter;	/* read-side iterator */
+	unsigned long get_subbuf_consumed;	/* Read-side consumed */
+	unsigned long prod_snapshot;	/* Producer count snapshot */
+	unsigned long cons_snapshot;	/* Consumer count snapshot */
+	int get_subbuf:1;		/* Sub-buffer being held by reader */
+	int switch_timer_enabled:1;	/* Protected by ring_buffer_nohz_lock */
+	int read_timer_enabled:1;	/* Protected by ring_buffer_nohz_lock */
+};
+
+static inline
+void *channel_get_private(struct channel *chan)
+{
+	return chan->backend.priv;
+}
+
+/*
+ * Issue warnings and disable channels upon internal error.
+ * Can receive struct lib_ring_buffer or struct lib_ring_buffer_backend
+ * parameters.
+ */
+#define CHAN_WARN_ON(c, cond)						\
+	({								\
+		struct channel *__chan;					\
+		int _____ret = unlikely(cond);				\
+		if (_____ret) {						\
+			if (__same_type(*(c), struct channel_backend))	\
+				__chan = container_of((void *) (c),	\
+							struct channel, \
+							backend);	\
+			else if (__same_type(*(c), struct channel))	\
+				__chan = (void *) (c);			\
+			else						\
+				BUG_ON(1);				\
+			atomic_inc(&__chan->record_disabled);		\
+			WARN_ON(1);					\
+		}							\
+		_____ret;						\
+	})
+
+#endif /* _LINUX_RING_BUFFER_FRONTEND_TYPES_H */

drivers/staging/lttng/lib/ringbuffer/iterator.h

+#ifndef _LINUX_RING_BUFFER_ITERATOR_H
+#define _LINUX_RING_BUFFER_ITERATOR_H
+
+/*
+ * linux/ringbuffer/iterator.h
+ *
+ * (C) Copyright 2010 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Ring buffer and channel iterators.
+ *
+ * Author:
+ *	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#include "../../wrapper/ringbuffer/backend.h"
+#include "../../wrapper/ringbuffer/frontend.h"
+
+/*
+ * lib_ring_buffer_get_next_record advances the buffer read position to the next
+ * record. It returns either the size of the next record, -EAGAIN if there is
+ * currently no data available, or -ENODATA if no data is available and buffer
+ * is finalized.
+ */
+extern ssize_t lib_ring_buffer_get_next_record(struct channel *chan,
+					       struct lib_ring_buffer *buf);
+
+/*
+ * channel_get_next_record advances the buffer read position to the next record.
+ * It returns either the size of the next record, -EAGAIN if there is currently
+ * no data available, or -ENODATA if no data is available and buffer is
+ * finalized.
+ * Returns the current buffer in ret_buf.
+ */
+extern ssize_t channel_get_next_record(struct channel *chan,
+				       struct lib_ring_buffer **ret_buf);
+
+/**
+ * read_current_record - copy the buffer current record into dest.
+ * @buf: ring buffer
+ * @dest: destination where the record should be copied
+ *
+ * dest should be large enough to contain the record. Returns the number of
+ * bytes copied.
+ */
+static inline size_t read_current_record(struct lib_ring_buffer *buf, void *dest)
+{
+	return lib_ring_buffer_read(&buf->backend, buf->iter.read_offset,
+				    dest, buf->iter.payload_len);
+}
+
+extern int lib_ring_buffer_iterator_open(struct lib_ring_buffer *buf);
+extern void lib_ring_buffer_iterator_release(struct lib_ring_buffer *buf);
+extern int channel_iterator_open(struct channel *chan);
+extern void channel_iterator_release(struct channel *chan);
+
+extern const struct file_operations channel_payload_file_operations;
+extern const struct file_operations lib_ring_buffer_payload_file_operations;
+
+/*
+ * Used internally.
+ */
+int channel_iterator_init(struct channel *chan);
+void channel_iterator_unregister_notifiers(struct channel *chan);
+void channel_iterator_free(struct channel *chan);
+void channel_iterator_reset(struct channel *chan);
+void lib_ring_buffer_iterator_reset(struct lib_ring_buffer *buf);
+
+#endif /* _LINUX_RING_BUFFER_ITERATOR_H */

drivers/staging/lttng/lib/ringbuffer/nohz.h

+#ifndef _LINUX_RING_BUFFER_NOHZ_H
+#define _LINUX_RING_BUFFER_NOHZ_H
+
+/*
+ * ringbuffer/nohz.h
+ *
+ * Copyright (C) 2011 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * Dual LGPL v2.1/GPL v2 license.
+ */
+
+#ifdef CONFIG_LIB_RING_BUFFER
+void lib_ring_buffer_tick_nohz_flush(void);
+void lib_ring_buffer_tick_nohz_stop(void);
+void lib_ring_buffer_tick_nohz_restart(void);
+#else
+static inline void lib_ring_buffer_tick_nohz_flush(void)
+{
+}
+
+static inline void lib_ring_buffer_tick_nohz_stop(void)
+{
+}
+
+static inline void lib_ring_buffer_tick_nohz_restart(void)
+{
+}
+#endif
+
+#endif /* _LINUX_RING_BUFFER_NOHZ_H */