From db1bb44c4c7e8d49ed674dc59e5222d99c698088 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:44 -0400 Subject: SUNRPC: Don't allocate a full sockaddr_storage for tracing We're always tracing IPv4 or IPv6 addresses, so we can save a lot of space on the ringbuffer by allocating the correct sockaddr size. Signed-off-by: Trond Myklebust Cc: stable@vger.kernel.org Fixes: 83a712e0afef "sunrpc: add some tracepoints around ..." Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 47 +++++++++++++++++++++++++++++++------------ 1 file changed, 34 insertions(+), 13 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 003dca933803..5664ca07c9c7 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -529,20 +529,27 @@ TRACE_EVENT(svc_xprt_do_enqueue, TP_STRUCT__entry( __field(struct svc_xprt *, xprt) - __field_struct(struct sockaddr_storage, ss) __field(int, pid) __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, xprt != NULL ? + xprt->xpt_remotelen : 0) ), TP_fast_assign( __entry->xprt = xprt; - xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss)); __entry->pid = rqst? rqst->rq_task->pid : 0; - __entry->flags = xprt ? xprt->xpt_flags : 0; + if (xprt) { + memcpy(__get_dynamic_array(addr), + &xprt->xpt_remote, + xprt->xpt_remotelen); + __entry->flags = xprt->xpt_flags; + } else + __entry->flags = 0; ), TP_printk("xprt=0x%p addr=%pIScp pid=%d flags=%s", __entry->xprt, - (struct sockaddr *)&__entry->ss, + __get_dynamic_array_len(addr) != 0 ? + (struct sockaddr *)__get_dynamic_array(addr) : NULL, __entry->pid, show_svc_xprt_flags(__entry->flags)) ); @@ -553,18 +560,25 @@ TRACE_EVENT(svc_xprt_dequeue, TP_STRUCT__entry( __field(struct svc_xprt *, xprt) - __field_struct(struct sockaddr_storage, ss) __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, xprt != NULL ? + xprt->xpt_remotelen : 0) ), TP_fast_assign( - __entry->xprt = xprt, - xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss)); - __entry->flags = xprt ? xprt->xpt_flags : 0; + __entry->xprt = xprt; + if (xprt) { + memcpy(__get_dynamic_array(addr), + &xprt->xpt_remote, + xprt->xpt_remotelen); + __entry->flags = xprt->xpt_flags; + } else + __entry->flags = 0; ), TP_printk("xprt=0x%p addr=%pIScp flags=%s", __entry->xprt, - (struct sockaddr *)&__entry->ss, + __get_dynamic_array_len(addr) != 0 ? + (struct sockaddr *)__get_dynamic_array(addr) : NULL, show_svc_xprt_flags(__entry->flags)) ); @@ -592,19 +606,26 @@ TRACE_EVENT(svc_handle_xprt, TP_STRUCT__entry( __field(struct svc_xprt *, xprt) __field(int, len) - __field_struct(struct sockaddr_storage, ss) __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, xprt != NULL ? + xprt->xpt_remotelen : 0) ), TP_fast_assign( __entry->xprt = xprt; - xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss)); __entry->len = len; - __entry->flags = xprt ? xprt->xpt_flags : 0; + if (xprt) { + memcpy(__get_dynamic_array(addr), + &xprt->xpt_remote, + xprt->xpt_remotelen); + __entry->flags = xprt->xpt_flags; + } else + __entry->flags = 0; ), TP_printk("xprt=0x%p addr=%pIScp len=%d flags=%s", __entry->xprt, - (struct sockaddr *)&__entry->ss, + __get_dynamic_array_len(addr) != 0 ? + (struct sockaddr *)__get_dynamic_array(addr) : NULL, __entry->len, show_svc_xprt_flags(__entry->flags)) ); #endif /* _TRACE_SUNRPC_H */ -- cgit v1.2.3 From c83f8effefa46c15f2fd43de598d9839d0056096 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 25 Mar 2016 13:25:52 -0400 Subject: Btrfs: add tracepoint for adding block groups I'm writing a tool to visualize the enospc system inside btrfs, I need this tracepoint in order to keep track of the block groups in the system. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 2 ++ include/trace/events/btrfs.h | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) (limited to 'include/trace') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a1355a33e7e9..aae7b04afa9f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -9994,6 +9994,7 @@ int btrfs_read_block_groups(struct btrfs_root *root) goto error; } + trace_btrfs_add_block_group(root->fs_info, cache, 0); ret = update_space_info(info, cache->flags, found_key.offset, btrfs_block_group_used(&cache->item), cache->bytes_super, &space_info); @@ -10164,6 +10165,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, * Now that our block group has its ->space_info set and is inserted in * the rbtree, update the space info's counters. */ + trace_btrfs_add_block_group(root->fs_info, cache, 1); ret = update_space_info(root->fs_info, cache->flags, size, bytes_used, cache->bytes_super, &cache->space_info); if (ret) { diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index e90e82ad6875..985e01b6c849 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -440,6 +440,46 @@ TRACE_EVENT(btrfs_sync_fs, TP_printk("wait = %d", __entry->wait) ); +TRACE_EVENT(btrfs_add_block_group, + + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_block_group_cache *block_group, int create), + + TP_ARGS(fs_info, block_group, create), + + TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, offset ) + __field( u64, size ) + __field( u64, flags ) + __field( u64, bytes_used ) + __field( u64, bytes_super ) + __field( int, create ) + ), + + TP_fast_assign( + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + __entry->offset = block_group->key.objectid; + __entry->size = block_group->key.offset; + __entry->flags = block_group->flags; + __entry->bytes_used = + btrfs_block_group_used(&block_group->item); + __entry->bytes_super = block_group->bytes_super; + __entry->create = create; + ), + + TP_printk("%pU: block_group offset = %llu, size = %llu, " + "flags = %llu(%s), bytes_used = %llu, bytes_super = %llu, " + "create = %d", __entry->fsid, + (unsigned long long)__entry->offset, + (unsigned long long)__entry->size, + (unsigned long long)__entry->flags, + __print_flags((unsigned long)__entry->flags, "|", + BTRFS_GROUP_FLAGS), + (unsigned long long)__entry->bytes_used, + (unsigned long long)__entry->bytes_super, __entry->create) +); + #define show_ref_action(action) \ __print_symbolic(action, \ { BTRFS_ADD_DELAYED_REF, "ADD_DELAYED_REF" }, \ -- cgit v1.2.3 From f376df2b7da3a40f62f861a65efdd8c29fa1b877 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 25 Mar 2016 13:25:56 -0400 Subject: Btrfs: add tracepoints for flush events We want to track when we're triggering flushing from our reservation code and what flushing is being done when we start flushing. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 9 +++++ fs/btrfs/extent-tree.c | 22 ++++++------ include/trace/events/btrfs.h | 82 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 103 insertions(+), 10 deletions(-) (limited to 'include/trace') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2e04c9d6f21d..83a6a931af09 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2626,6 +2626,15 @@ enum btrfs_reserve_flush_enum { BTRFS_RESERVE_FLUSH_ALL, }; +enum btrfs_flush_state { + FLUSH_DELAYED_ITEMS_NR = 1, + FLUSH_DELAYED_ITEMS = 2, + FLUSH_DELALLOC = 3, + FLUSH_DELALLOC_WAIT = 4, + ALLOC_CHUNK = 5, + COMMIT_TRANS = 6, +}; + int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes); void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5d24ec44d99b..31ded6aae1f0 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4835,15 +4835,6 @@ commit: return btrfs_commit_transaction(trans, root); } -enum flush_state { - FLUSH_DELAYED_ITEMS_NR = 1, - FLUSH_DELAYED_ITEMS = 2, - FLUSH_DELALLOC = 3, - FLUSH_DELALLOC_WAIT = 4, - ALLOC_CHUNK = 5, - COMMIT_TRANS = 6, -}; - struct reserve_ticket { u64 bytes; int error; @@ -4901,6 +4892,8 @@ static int flush_space(struct btrfs_root *root, break; } + trace_btrfs_flush_space(root->fs_info, space_info->flags, num_bytes, + orig_bytes, state, ret); return ret; } @@ -5178,6 +5171,10 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, list_add_tail(&ticket.list, &space_info->tickets); if (!space_info->flush) { space_info->flush = 1; + trace_btrfs_trigger_flush(root->fs_info, + space_info->flags, + orig_bytes, flush, + "enospc"); queue_work(system_unbound_wq, &root->fs_info->async_reclaim_work); } @@ -5194,9 +5191,14 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, */ if (!root->fs_info->log_root_recovering && need_do_async_reclaim(space_info, root->fs_info, used) && - !work_busy(&root->fs_info->async_reclaim_work)) + !work_busy(&root->fs_info->async_reclaim_work)) { + trace_btrfs_trigger_flush(root->fs_info, + space_info->flags, + orig_bytes, flush, + "preempt"); queue_work(system_unbound_wq, &root->fs_info->async_reclaim_work); + } } spin_unlock(&space_info->lock); if (!ret || flush == BTRFS_RESERVE_NO_FLUSH) diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 985e01b6c849..226c7f283247 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -784,6 +784,88 @@ TRACE_EVENT(btrfs_space_reservation, __entry->bytes) ); +#define show_flush_action(action) \ + __print_symbolic(action, \ + { BTRFS_RESERVE_NO_FLUSH, "BTRFS_RESERVE_NO_FLUSH"}, \ + { BTRFS_RESERVE_FLUSH_LIMIT, "BTRFS_RESERVE_FLUSH_LIMIT"}, \ + { BTRFS_RESERVE_FLUSH_ALL, "BTRFS_RESERVE_FLUSH_ALL"}) + +TRACE_EVENT(btrfs_trigger_flush, + + TP_PROTO(struct btrfs_fs_info *fs_info, u64 flags, u64 bytes, + int flush, char *reason), + + TP_ARGS(fs_info, flags, bytes, flush, reason), + + TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, flags ) + __field( u64, bytes ) + __field( int, flush ) + __string( reason, reason ) + ), + + TP_fast_assign( + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + __entry->flags = flags; + __entry->bytes = bytes; + __entry->flush = flush; + __assign_str(reason, reason) + ), + + TP_printk("%pU: %s: flush = %d(%s), flags = %llu(%s), bytes = %llu", + __entry->fsid, __get_str(reason), __entry->flush, + show_flush_action(__entry->flush), + (unsigned long long)__entry->flags, + __print_flags((unsigned long)__entry->flags, "|", + BTRFS_GROUP_FLAGS), + (unsigned long long)__entry->bytes) +); + +#define show_flush_state(state) \ + __print_symbolic(state, \ + { FLUSH_DELAYED_ITEMS_NR, "FLUSH_DELAYED_ITEMS_NR"}, \ + { FLUSH_DELAYED_ITEMS, "FLUSH_DELAYED_ITEMS"}, \ + { FLUSH_DELALLOC, "FLUSH_DELALLOC"}, \ + { FLUSH_DELALLOC_WAIT, "FLUSH_DELALLOC_WAIT"}, \ + { ALLOC_CHUNK, "ALLOC_CHUNK"}, \ + { COMMIT_TRANS, "COMMIT_TRANS"}) + +TRACE_EVENT(btrfs_flush_space, + + TP_PROTO(struct btrfs_fs_info *fs_info, u64 flags, u64 num_bytes, + u64 orig_bytes, int state, int ret), + + TP_ARGS(fs_info, flags, num_bytes, orig_bytes, state, ret), + + TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, flags ) + __field( u64, num_bytes ) + __field( u64, orig_bytes ) + __field( int, state ) + __field( int, ret ) + ), + + TP_fast_assign( + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + __entry->flags = flags; + __entry->num_bytes = num_bytes; + __entry->orig_bytes = orig_bytes; + __entry->state = state; + __entry->ret = ret; + ), + + TP_printk("%pU: state = %d(%s), flags = %llu(%s), num_bytes = %llu, " + "orig_bytes = %llu, ret = %d", __entry->fsid, __entry->state, + show_flush_state(__entry->state), + (unsigned long long)__entry->flags, + __print_flags((unsigned long)__entry->flags, "|", + BTRFS_GROUP_FLAGS), + (unsigned long long)__entry->num_bytes, + (unsigned long long)__entry->orig_bytes, __entry->ret) +); + DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_PROTO(struct btrfs_root *root, u64 start, u64 len), -- cgit v1.2.3 From dce3afa5932776f7b925249fbef435c265014f91 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 25 Mar 2016 13:25:57 -0400 Subject: Btrfs: add fsid to some tracepoints When tracing enospc problems on a box with multiple file systems mounted I need to be able to differentiate between the two file systems. Most of the important trace points I'm looking at already have an fsid, but the reserved extent trace points do not, so add that to make it possible to figure out which trace point belongs to which file system. Thanks, Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- include/trace/events/btrfs.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 226c7f283247..5b81ef304388 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -873,18 +873,21 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_ARGS(root, start, len), TP_STRUCT__entry( - __field( u64, root_objectid ) - __field( u64, start ) - __field( u64, len ) + __array( u8, fsid, BTRFS_UUID_SIZE ) + __field( u64, root_objectid ) + __field( u64, start ) + __field( u64, len ) ), TP_fast_assign( + memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); __entry->root_objectid = root->root_key.objectid; __entry->start = start; __entry->len = len; ), - TP_printk("root = %llu(%s), start = %llu, len = %llu", + TP_printk("%pU: root = %llu(%s), start = %llu, len = %llu", + __entry->fsid, show_root_type(__entry->root_objectid), (unsigned long long)__entry->start, (unsigned long long)__entry->len) @@ -941,6 +944,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, TP_ARGS(root, block_group, start, len), TP_STRUCT__entry( + __array( u8, fsid, BTRFS_UUID_SIZE ) __field( u64, root_objectid ) __field( u64, bg_objectid ) __field( u64, flags ) @@ -949,6 +953,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, ), TP_fast_assign( + memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); __entry->root_objectid = root->root_key.objectid; __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; @@ -956,8 +961,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __entry->len = len; ), - TP_printk("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " - "start = %Lu, len = %Lu", + TP_printk("%pU: root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " + "start = %Lu, len = %Lu", __entry->fsid, show_root_type(__entry->root_objectid), __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), -- cgit v1.2.3 From 82ea2d7615309d755579d609ad9c11daea25d0cc Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:45 -0400 Subject: SUNRPC: Add a tracepoint for server socket out-of-space conditions Add a tracepoint to track when the processing of incoming RPC data gets deferred due to out-of-space issues on the outgoing transport. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 10 +++++++++- net/sunrpc/svc_xprt.c | 8 ++++++-- 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 5664ca07c9c7..b014207a95a8 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -553,7 +553,7 @@ TRACE_EVENT(svc_xprt_do_enqueue, __entry->pid, show_svc_xprt_flags(__entry->flags)) ); -TRACE_EVENT(svc_xprt_dequeue, +DECLARE_EVENT_CLASS(svc_xprt_event, TP_PROTO(struct svc_xprt *xprt), TP_ARGS(xprt), @@ -582,6 +582,14 @@ TRACE_EVENT(svc_xprt_dequeue, show_svc_xprt_flags(__entry->flags)) ); +DEFINE_EVENT(svc_xprt_event, svc_xprt_dequeue, + TP_PROTO(struct svc_xprt *xprt), + TP_ARGS(xprt)); + +DEFINE_EVENT(svc_xprt_event, svc_xprt_no_write_space, + TP_PROTO(struct svc_xprt *xprt), + TP_ARGS(xprt)); + TRACE_EVENT(svc_wake_up, TP_PROTO(int pid), diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 4f01f63102ee..4d2189a562af 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -333,8 +333,12 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) { if (xprt->xpt_flags & ((1<xpt_flags & ((1<xpt_ops->xpo_has_wspace(xprt); + if (xprt->xpt_flags & ((1<xpt_ops->xpo_has_wspace(xprt)) + return true; + trace_svc_xprt_no_write_space(xprt); + return false; + } return false; } -- cgit v1.2.3 From 104f6351f7dc0036575b4e47765d6d39c757c066 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 24 Jun 2016 10:55:46 -0400 Subject: SUNRPC: Add tracepoints for dropped and deferred requests Dropping and/or deferring requests has an impact on performance. Let's make sure we can trace those events. Signed-off-by: Trond Myklebust Signed-off-by: J. Bruce Fields --- include/trace/events/sunrpc.h | 61 +++++++++++++++++++++++++++++++++++++++++++ net/sunrpc/svc_xprt.c | 4 +++ 2 files changed, 65 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index b014207a95a8..8a707f8a41c3 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -473,6 +473,39 @@ TRACE_EVENT(svc_recv, show_rqstp_flags(__entry->flags)) ); +DECLARE_EVENT_CLASS(svc_rqst_event, + + TP_PROTO(struct svc_rqst *rqst), + + TP_ARGS(rqst), + + TP_STRUCT__entry( + __field(__be32, xid) + __field(unsigned long, flags) + __dynamic_array(unsigned char, addr, rqst->rq_addrlen) + ), + + TP_fast_assign( + __entry->xid = rqst->rq_xid; + __entry->flags = rqst->rq_flags; + memcpy(__get_dynamic_array(addr), + &rqst->rq_addr, rqst->rq_addrlen); + ), + + TP_printk("addr=%pIScp rq_xid=0x%x flags=%s", + (struct sockaddr *)__get_dynamic_array(addr), + be32_to_cpu(__entry->xid), + show_rqstp_flags(__entry->flags)) +); + +DEFINE_EVENT(svc_rqst_event, svc_defer, + TP_PROTO(struct svc_rqst *rqst), + TP_ARGS(rqst)); + +DEFINE_EVENT(svc_rqst_event, svc_drop, + TP_PROTO(struct svc_rqst *rqst), + TP_ARGS(rqst)); + DECLARE_EVENT_CLASS(svc_rqst_status, TP_PROTO(struct svc_rqst *rqst, int status), @@ -636,6 +669,34 @@ TRACE_EVENT(svc_handle_xprt, (struct sockaddr *)__get_dynamic_array(addr) : NULL, __entry->len, show_svc_xprt_flags(__entry->flags)) ); + + +DECLARE_EVENT_CLASS(svc_deferred_event, + TP_PROTO(struct svc_deferred_req *dr), + + TP_ARGS(dr), + + TP_STRUCT__entry( + __field(__be32, xid) + __dynamic_array(unsigned char, addr, dr->addrlen) + ), + + TP_fast_assign( + __entry->xid = *(__be32 *)(dr->args + (dr->xprt_hlen>>2)); + memcpy(__get_dynamic_array(addr), &dr->addr, dr->addrlen); + ), + + TP_printk("addr=%pIScp xid=0x%x", + (struct sockaddr *)__get_dynamic_array(addr), + be32_to_cpu(__entry->xid)) +); + +DEFINE_EVENT(svc_deferred_event, svc_drop_deferred, + TP_PROTO(struct svc_deferred_req *dr), + TP_ARGS(dr)); +DEFINE_EVENT(svc_deferred_event, svc_revisit_deferred, + TP_PROTO(struct svc_deferred_req *dr), + TP_ARGS(dr)); #endif /* _TRACE_SUNRPC_H */ #include diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 4d2189a562af..e7082a4aeb56 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -875,6 +875,7 @@ EXPORT_SYMBOL_GPL(svc_recv); */ void svc_drop(struct svc_rqst *rqstp) { + trace_svc_drop(rqstp); dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt); svc_xprt_release(rqstp); } @@ -1152,6 +1153,7 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) spin_unlock(&xprt->xpt_lock); dprintk("revisit canceled\n"); svc_xprt_put(xprt); + trace_svc_drop_deferred(dr); kfree(dr); return; } @@ -1209,6 +1211,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; + trace_svc_defer(rqstp); return &dr->handle; } @@ -1249,6 +1252,7 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) struct svc_deferred_req, handle.recent); list_del_init(&dr->handle.recent); + trace_svc_revisit_deferred(dr); } else clear_bit(XPT_DEFERRED, &xprt->xpt_flags); spin_unlock(&xprt->xpt_lock); -- cgit v1.2.3 From 3713131345fbea291cbd859d248e06ed77815962 Mon Sep 17 00:00:00 2001 From: Radim Krčmář Date: Tue, 12 Jul 2016 22:09:27 +0200 Subject: KVM: x86: add KVM_CAP_X2APIC_API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM_CAP_X2APIC_API is a capability for features related to x2APIC enablement. KVM_X2APIC_API_32BIT_FORMAT feature can be enabled to extend APIC ID in get/set ioctl and MSI addresses to 32 bits. Both are needed to support x2APIC. The feature has to be enableable and disabled by default, because get/set ioctl shifted and truncated APIC ID to 8 bits by using a non-standard protocol inspired by xAPIC and the change is not backward-compatible. Changes to MSI addresses follow the format used by interrupt remapping unit. The upper address word, that used to be 0, contains upper 24 bits of the LAPIC address in its upper 24 bits. Lower 8 bits are reserved as 0. Using the upper address word is not backward-compatible either as we didn't check that userspace zeroed the word. Reserved bits are still not explicitly checked, but non-zero data will affect LAPIC addresses, which will cause a bug. Signed-off-by: Radim Krčmář Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 41 +++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/kvm_host.h | 4 +++- arch/x86/kvm/irq_comm.c | 29 ++++++++++++++++++++++----- arch/x86/kvm/lapic.c | 13 +++++++++---- arch/x86/kvm/vmx.c | 2 +- arch/x86/kvm/x86.c | 15 ++++++++++++++ include/trace/events/kvm.h | 5 +++-- include/uapi/linux/kvm.h | 3 +++ 8 files changed, 99 insertions(+), 13 deletions(-) (limited to 'include/trace') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 09efa9eb3926..e34e51fa28b0 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1482,6 +1482,11 @@ struct kvm_irq_routing_msi { __u32 pad; }; +On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS +feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled, +address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of +address_hi must be zero. + struct kvm_irq_routing_s390_adapter { __u64 ind_addr; __u64 summary_addr; @@ -1583,6 +1588,17 @@ struct kvm_lapic_state { Reads the Local APIC registers and copies them into the input argument. The data format and layout are the same as documented in the architecture manual. +If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is +enabled, then the format of APIC_ID register depends on the APIC mode +(reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in +the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID +which is stored in bits 31-24 of the APIC register, or equivalently in +byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then +be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR. + +If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state +always uses xAPIC format. + 4.58 KVM_SET_LAPIC @@ -1600,6 +1616,10 @@ struct kvm_lapic_state { Copies the input argument into the Local APIC registers. The data format and layout are the same as documented in the architecture manual. +The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's +regs field) depends on the state of the KVM_CAP_X2APIC_API capability. +See the note in KVM_GET_LAPIC. + 4.59 KVM_IOEVENTFD @@ -2180,6 +2200,10 @@ struct kvm_msi { No flags are defined so far. The corresponding field must be 0. +On x86, address_hi is ignored unless the KVM_CAP_X2APIC_API capability is +enabled. If it is enabled, address_hi bits 31-8 provide bits 31-8 of the +destination id. Bits 7-0 of address_hi must be zero. + 4.71 KVM_CREATE_PIT2 @@ -3811,6 +3835,23 @@ Allows use of runtime-instrumentation introduced with zEC12 processor. Will return -EINVAL if the machine does not support runtime-instrumentation. Will return -EBUSY if a VCPU has already been created. +7.7 KVM_CAP_X2APIC_API + +Architectures: x86 +Parameters: args[0] - features that should be enabled +Returns: 0 on success, -EINVAL when args[0] contains invalid features + +Valid feature flags in args[0] are + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) + +Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of +KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC, +allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their +respective sections. + + + 8. Other capabilities. ---------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a2832cc3cb81..7c00ba3242d7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -782,6 +782,8 @@ struct kvm_arch { u32 ldr_mode; struct page *avic_logical_id_table_page; struct page *avic_physical_id_table_page; + + bool x2apic_format; }; struct kvm_vm_stat { @@ -1364,7 +1366,7 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu); -void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, +void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq); static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 889563d50c55..25810b144b58 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -110,13 +110,17 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, return r; } -void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, +void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, struct kvm_lapic_irq *irq) { - trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); + trace_kvm_msi_set_irq(e->msi.address_lo | (kvm->arch.x2apic_format ? + (u64)e->msi.address_hi << 32 : 0), + e->msi.data); irq->dest_id = (e->msi.address_lo & MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT; + if (kvm->arch.x2apic_format) + irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi); irq->vector = (e->msi.data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT; irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; @@ -129,15 +133,24 @@ void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, } EXPORT_SYMBOL_GPL(kvm_set_msi_irq); +static inline bool kvm_msi_route_invalid(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e) +{ + return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff); +} + int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_lapic_irq irq; + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + if (!level) return -1; - kvm_set_msi_irq(e, &irq); + kvm_set_msi_irq(kvm, e, &irq); return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } @@ -153,7 +166,10 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, if (unlikely(e->type != KVM_IRQ_ROUTING_MSI)) return -EWOULDBLOCK; - kvm_set_msi_irq(e, &irq); + if (kvm_msi_route_invalid(kvm, e)) + return -EINVAL; + + kvm_set_msi_irq(kvm, e, &irq); if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) return r; @@ -286,6 +302,9 @@ int kvm_set_routing_entry(struct kvm *kvm, e->msi.address_lo = ue->u.msi.address_lo; e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; + + if (kvm_msi_route_invalid(kvm, e)) + goto out; break; case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; @@ -394,7 +413,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, if (entry->type != KVM_IRQ_ROUTING_MSI) continue; - kvm_set_msi_irq(entry, &irq); + kvm_set_msi_irq(vcpu->kvm, entry, &irq); if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0, irq.dest_id, irq.dest_mode)) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3c2a8c113054..d27a7829a4ce 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1991,10 +1991,15 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, if (apic_x2apic_mode(vcpu->arch.apic)) { u32 *id = (u32 *)(s->regs + APIC_ID); - if (set) - *id >>= 24; - else - *id <<= 24; + if (vcpu->kvm->arch.x2apic_format) { + if (*id != vcpu->vcpu_id) + return -EINVAL; + } else { + if (set) + *id >>= 24; + else + *id <<= 24; + } } return 0; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7bdd6b1a2373..b61cdadf8623 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11104,7 +11104,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * We will support full lowest-priority interrupt later. */ - kvm_set_msi_irq(e, &irq); + kvm_set_msi_irq(kvm, e, &irq); if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) { /* * Make sure the IRTE is in remapped mode if diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b6e402d16e0c..d86f563a6896 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,6 +90,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU +#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS) + static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); static void enter_smm(struct kvm_vcpu *vcpu); @@ -2625,6 +2627,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_TSC_CONTROL: r = kvm_has_tsc_control; break; + case KVM_CAP_X2APIC_API: + r = KVM_X2APIC_API_VALID_FLAGS; + break; default: r = 0; break; @@ -3799,6 +3804,16 @@ split_irqchip_unlock: mutex_unlock(&kvm->lock); break; } + case KVM_CAP_X2APIC_API: + r = -EINVAL; + if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS) + break; + + if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS) + kvm->arch.x2apic_format = true; + + r = 0; + break; default: r = -EINVAL; break; diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index f28292d73ddb..8ade3eb6c640 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -151,8 +151,9 @@ TRACE_EVENT(kvm_msi_set_irq, __entry->data = data; ), - TP_printk("dst %u vec %u (%s|%s|%s%s)", - (u8)(__entry->address >> 12), (u8)__entry->data, + TP_printk("dst %llx vec %u (%s|%s|%s%s)", + (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00), + (u8)__entry->data, __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode), (__entry->address & (1<<2)) ? "logical" : "physical", (__entry->data & (1<<15)) ? "level" : "edge", diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 05ebf475104c..f704403e19a0 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -866,6 +866,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_ARM_PMU_V3 126 #define KVM_CAP_VCPU_ATTRIBUTES 127 #define KVM_CAP_MAX_VCPU_ID 128 +#define KVM_CAP_X2APIC_API 129 #ifdef KVM_CAP_IRQ_ROUTING @@ -1313,4 +1314,6 @@ struct kvm_assigned_msix_entry { __u16 padding[3]; }; +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From bc074524e123ded281cde25ebc5661910f9679e3 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 9 Jun 2016 17:27:55 -0400 Subject: btrfs: prefix fsid to all trace events When using trace events to debug a problem, it's impossible to determine which file system generated a particular event. This patch adds a macro to prefix standard information to the head of a trace event. The extent_state alloc/free events are all that's left without an fs_info available. Signed-off-by: Jeff Mahoney Signed-off-by: David Sterba --- fs/btrfs/delayed-ref.c | 9 +- fs/btrfs/extent-tree.c | 10 +- fs/btrfs/qgroup.c | 19 +-- fs/btrfs/qgroup.h | 9 +- fs/btrfs/super.c | 2 +- include/trace/events/btrfs.h | 295 +++++++++++++++++++++++-------------------- 6 files changed, 186 insertions(+), 158 deletions(-) (limited to 'include/trace') diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 08e452599249..b6d210e7a993 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -606,7 +606,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, qrecord->num_bytes = num_bytes; qrecord->old_roots = NULL; - qexisting = btrfs_qgroup_insert_dirty_extent(delayed_refs, + qexisting = btrfs_qgroup_insert_dirty_extent(fs_info, + delayed_refs, qrecord); if (qexisting) kfree(qrecord); @@ -615,7 +616,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, spin_lock_init(&head_ref->lock); mutex_init(&head_ref->mutex); - trace_add_delayed_ref_head(ref, head_ref, action); + trace_add_delayed_ref_head(fs_info, ref, head_ref, action); existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); @@ -682,7 +683,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info, ref->type = BTRFS_TREE_BLOCK_REF_KEY; full_ref->level = level; - trace_add_delayed_tree_ref(ref, full_ref, action); + trace_add_delayed_tree_ref(fs_info, ref, full_ref, action); ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref); @@ -739,7 +740,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info, full_ref->objectid = owner; full_ref->offset = offset; - trace_add_delayed_data_ref(ref, full_ref, action); + trace_add_delayed_data_ref(fs_info, ref, full_ref, action); ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 81d83300c99b..73f6dd2cf3cb 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2204,7 +2204,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; ref = btrfs_delayed_node_to_data_ref(node); - trace_run_delayed_data_ref(node, ref, node->action); + trace_run_delayed_data_ref(root->fs_info, node, ref, node->action); if (node->type == BTRFS_SHARED_DATA_REF_KEY) parent = ref->parent; @@ -2359,7 +2359,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans, SKINNY_METADATA); ref = btrfs_delayed_node_to_tree_ref(node); - trace_run_delayed_tree_ref(node, ref, node->action); + trace_run_delayed_tree_ref(root->fs_info, node, ref, node->action); if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) parent = ref->parent; @@ -2423,7 +2423,8 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, */ BUG_ON(extent_op); head = btrfs_delayed_node_to_head(node); - trace_run_delayed_ref_head(node, head, node->action); + trace_run_delayed_ref_head(root->fs_info, node, head, + node->action); if (insert_reserved) { btrfs_pin_extent(root, node->bytenr, @@ -8542,7 +8543,8 @@ static int record_one_subtree_extent(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); - if (btrfs_qgroup_insert_dirty_extent(delayed_refs, qrecord)) + if (btrfs_qgroup_insert_dirty_extent(trans->root->fs_info, + delayed_refs, qrecord)) kfree(qrecord); spin_unlock(&delayed_refs->lock); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 9d4c05b14f6e..13e28d8a7d42 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1453,9 +1453,10 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, return ret; } -struct btrfs_qgroup_extent_record -*btrfs_qgroup_insert_dirty_extent(struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record) +struct btrfs_qgroup_extent_record * +btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record) { struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node; struct rb_node *parent_node = NULL; @@ -1463,7 +1464,7 @@ struct btrfs_qgroup_extent_record u64 bytenr = record->bytenr; assert_spin_locked(&delayed_refs->lock); - trace_btrfs_qgroup_insert_dirty_extent(record); + trace_btrfs_qgroup_insert_dirty_extent(fs_info, record); while (*p) { parent_node = *p; @@ -1595,8 +1596,8 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq); cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq); - trace_qgroup_update_counters(qg->qgroupid, cur_old_count, - cur_new_count); + trace_qgroup_update_counters(fs_info, qg->qgroupid, + cur_old_count, cur_new_count); /* Rfer update part */ if (cur_old_count == 0 && cur_new_count > 0) { @@ -1687,8 +1688,8 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, goto out_free; BUG_ON(!fs_info->quota_root); - trace_btrfs_qgroup_account_extent(bytenr, num_bytes, nr_old_roots, - nr_new_roots); + trace_btrfs_qgroup_account_extent(fs_info, bytenr, num_bytes, + nr_old_roots, nr_new_roots); qgroups = ulist_alloc(GFP_NOFS); if (!qgroups) { @@ -1759,7 +1760,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans, record = rb_entry(node, struct btrfs_qgroup_extent_record, node); - trace_btrfs_qgroup_account_extents(record); + trace_btrfs_qgroup_account_extents(fs_info, record); if (!ret) { /* diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index ecb2c143ef75..710887c06aaf 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -63,9 +63,10 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -struct btrfs_qgroup_extent_record -*btrfs_qgroup_insert_dirty_extent(struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record); +struct btrfs_qgroup_extent_record * +btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record); int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, @@ -88,7 +89,7 @@ static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info, u64 ref_root, u64 num_bytes) { btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes); - trace_btrfs_qgroup_free_delayed_ref(ref_root, num_bytes); + trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes); } void assert_qgroups_uptodate(struct btrfs_trans_handle *trans); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 208b15e7a171..d965abbcac8e 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1171,7 +1171,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root = fs_info->tree_root; - trace_btrfs_sync_fs(wait); + trace_btrfs_sync_fs(fs_info, wait); if (!wait) { filemap_flush(fs_info->btree_inode->i_mapping); diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 5b81ef304388..e030d6f6c19a 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -66,6 +66,21 @@ struct btrfs_qgroup_extent_record; { BTRFS_BLOCK_GROUP_RAID6, "RAID6"} #define BTRFS_UUID_SIZE 16 +#define TP_STRUCT__entry_fsid __array(u8, fsid, BTRFS_UUID_SIZE) + +#define TP_fast_assign_fsid(fs_info) \ + memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE) + +#define TP_STRUCT__entry_btrfs(args...) \ + TP_STRUCT__entry( \ + TP_STRUCT__entry_fsid \ + args) +#define TP_fast_assign_btrfs(fs_info, args...) \ + TP_fast_assign( \ + TP_fast_assign_fsid(fs_info); \ + args) +#define TP_printk_btrfs(fmt, args...) \ + TP_printk("%pU: " fmt, __entry->fsid, args) TRACE_EVENT(btrfs_transaction_commit, @@ -73,17 +88,17 @@ TRACE_EVENT(btrfs_transaction_commit, TP_ARGS(root), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, generation ) __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->generation = root->fs_info->generation; __entry->root_objectid = root->root_key.objectid; ), - TP_printk("root = %llu(%s), gen = %llu", + TP_printk_btrfs("root = %llu(%s), gen = %llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->generation) ); @@ -94,7 +109,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, TP_ARGS(inode), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( blkcnt_t, blocks ) __field( u64, disk_i_size ) @@ -104,7 +119,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = inode->i_ino; __entry->blocks = inode->i_blocks; __entry->disk_i_size = BTRFS_I(inode)->disk_i_size; @@ -115,7 +130,7 @@ DECLARE_EVENT_CLASS(btrfs__inode, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), gen = %llu, ino = %lu, blocks = %llu, " + TP_printk_btrfs("root = %llu(%s), gen = %llu, ino = %lu, blocks = %llu, " "disk_i_size = %llu, last_trans = %llu, logged_trans = %llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->generation, @@ -175,7 +190,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, TP_CONDITION(map), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, start ) __field( u64, len ) @@ -187,7 +202,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, __field( unsigned int, compress_type ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->start = map->start; __entry->len = map->len; @@ -199,7 +214,7 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, __entry->compress_type = map->compress_type; ), - TP_printk("root = %llu(%s), start = %llu, len = %llu, " + TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu, " "orig_start = %llu, block_start = %llu(%s), " "block_len = %llu, flags = %s, refs = %u, " "compress_type = %u", @@ -233,7 +248,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, TP_ARGS(inode, ordered), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( u64, file_offset ) __field( u64, start ) @@ -246,7 +261,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = inode->i_ino; __entry->file_offset = ordered->file_offset; __entry->start = ordered->start; @@ -260,7 +275,7 @@ DECLARE_EVENT_CLASS(btrfs__ordered_extent, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %llu, file_offset = %llu, " + TP_printk_btrfs("root = %llu(%s), ino = %llu, file_offset = %llu, " "start = %llu, len = %llu, disk_len = %llu, " "bytes_left = %llu, flags = %s, compress_type = %d, " "refs = %d", @@ -310,7 +325,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, TP_ARGS(page, inode, wbc), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( pgoff_t, index ) __field( long, nr_to_write ) @@ -324,7 +339,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->ino = inode->i_ino; __entry->index = page->index; __entry->nr_to_write = wbc->nr_to_write; @@ -339,7 +354,7 @@ DECLARE_EVENT_CLASS(btrfs__writepage, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %lu, page_index = %lu, " + TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, " "nr_to_write = %ld, pages_skipped = %ld, range_start = %llu, " "range_end = %llu, for_kupdate = %d, " "for_reclaim = %d, range_cyclic = %d, writeback_index = %lu", @@ -366,7 +381,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, TP_ARGS(page, start, end, uptodate), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( pgoff_t, index ) __field( u64, start ) @@ -375,7 +390,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(page->mapping->host->i_sb), __entry->ino = page->mapping->host->i_ino; __entry->index = page->index; __entry->start = start; @@ -385,7 +400,7 @@ TRACE_EVENT(btrfs_writepage_end_io_hook, BTRFS_I(page->mapping->host)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %lu, page_index = %lu, start = %llu, " + TP_printk_btrfs("root = %llu(%s), ino = %lu, page_index = %lu, start = %llu, " "end = %llu, uptodate = %d", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, (unsigned long)__entry->index, @@ -399,7 +414,7 @@ TRACE_EVENT(btrfs_sync_file, TP_ARGS(file, datasync), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( ino_t, ino ) __field( ino_t, parent ) __field( int, datasync ) @@ -410,6 +425,7 @@ TRACE_EVENT(btrfs_sync_file, struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); + TP_fast_assign_fsid(btrfs_sb(file->f_path.dentry->d_sb)); __entry->ino = inode->i_ino; __entry->parent = d_inode(dentry->d_parent)->i_ino; __entry->datasync = datasync; @@ -417,7 +433,7 @@ TRACE_EVENT(btrfs_sync_file, BTRFS_I(inode)->root->root_key.objectid; ), - TP_printk("root = %llu(%s), ino = %ld, parent = %ld, datasync = %d", + TP_printk_btrfs("root = %llu(%s), ino = %ld, parent = %ld, datasync = %d", show_root_type(__entry->root_objectid), (unsigned long)__entry->ino, (unsigned long)__entry->parent, __entry->datasync) @@ -425,19 +441,19 @@ TRACE_EVENT(btrfs_sync_file, TRACE_EVENT(btrfs_sync_fs, - TP_PROTO(int wait), + TP_PROTO(struct btrfs_fs_info *fs_info, int wait), - TP_ARGS(wait), + TP_ARGS(fs_info, wait), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( int, wait ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->wait = wait; ), - TP_printk("wait = %d", __entry->wait) + TP_printk_btrfs("wait = %d", __entry->wait) ); TRACE_EVENT(btrfs_add_block_group, @@ -490,13 +506,14 @@ TRACE_EVENT(btrfs_add_block_group, DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_tree_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action), + TP_ARGS(fs_info, ref, full_ref, action), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) @@ -507,7 +524,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, __field( u64, seq ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = action; @@ -518,7 +535,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, __entry->seq = ref->seq; ), - TP_printk("bytenr = %llu, num_bytes = %llu, action = %s, " + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, " "parent = %llu(%s), ref_root = %llu(%s), level = %d, " "type = %s, seq = %llu", (unsigned long long)__entry->bytenr, @@ -532,31 +549,34 @@ DECLARE_EVENT_CLASS(btrfs_delayed_tree_ref, DEFINE_EVENT(btrfs_delayed_tree_ref, add_delayed_tree_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_tree_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DEFINE_EVENT(btrfs_delayed_tree_ref, run_delayed_tree_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_tree_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_data_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action), + TP_ARGS(fs_info, ref, full_ref, action), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) @@ -568,7 +588,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, __field( u64, seq ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = action; @@ -580,7 +600,7 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, __entry->seq = ref->seq; ), - TP_printk("bytenr = %llu, num_bytes = %llu, action = %s, " + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, " "parent = %llu(%s), ref_root = %llu(%s), owner = %llu, " "offset = %llu, type = %s, seq = %llu", (unsigned long long)__entry->bytenr, @@ -596,45 +616,48 @@ DECLARE_EVENT_CLASS(btrfs_delayed_data_ref, DEFINE_EVENT(btrfs_delayed_data_ref, add_delayed_data_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_data_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DEFINE_EVENT(btrfs_delayed_data_ref, run_delayed_data_ref, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_data_ref *full_ref, int action), - TP_ARGS(ref, full_ref, action) + TP_ARGS(fs_info, ref, full_ref, action) ); DECLARE_EVENT_CLASS(btrfs_delayed_ref_head, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_ref_head *head_ref, int action), - TP_ARGS(ref, head_ref, action), + TP_ARGS(fs_info, ref, head_ref, action), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( int, action ) __field( int, is_data ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = ref->bytenr; __entry->num_bytes = ref->num_bytes; __entry->action = action; __entry->is_data = head_ref->is_data; ), - TP_printk("bytenr = %llu, num_bytes = %llu, action = %s, is_data = %d", + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, action = %s, is_data = %d", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes, show_ref_action(__entry->action), @@ -643,20 +666,22 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head, DEFINE_EVENT(btrfs_delayed_ref_head, add_delayed_ref_head, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_ref_head *head_ref, int action), - TP_ARGS(ref, head_ref, action) + TP_ARGS(fs_info, ref, head_ref, action) ); DEFINE_EVENT(btrfs_delayed_ref_head, run_delayed_ref_head, - TP_PROTO(struct btrfs_delayed_ref_node *ref, + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_node *ref, struct btrfs_delayed_ref_head *head_ref, int action), - TP_ARGS(ref, head_ref, action) + TP_ARGS(fs_info, ref, head_ref, action) ); #define show_chunk_type(type) \ @@ -678,7 +703,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk, TP_ARGS(root, map, offset, size), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( int, num_stripes ) __field( u64, type ) __field( int, sub_stripes ) @@ -687,7 +712,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk, __field( u64, root_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->num_stripes = map->num_stripes; __entry->type = map->type; __entry->sub_stripes = map->sub_stripes; @@ -696,7 +721,7 @@ DECLARE_EVENT_CLASS(btrfs__chunk, __entry->root_objectid = root->root_key.objectid; ), - TP_printk("root = %llu(%s), offset = %llu, size = %llu, " + TP_printk_btrfs("root = %llu(%s), offset = %llu, size = %llu, " "num_stripes = %d, sub_stripes = %d, type = %s", show_root_type(__entry->root_objectid), (unsigned long long)__entry->offset, @@ -728,7 +753,7 @@ TRACE_EVENT(btrfs_cow_block, TP_ARGS(root, buf, cow), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, buf_start ) __field( int, refs ) @@ -737,7 +762,7 @@ TRACE_EVENT(btrfs_cow_block, __field( int, cow_level ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->buf_start = buf->start; __entry->refs = atomic_read(&buf->refs); @@ -746,7 +771,7 @@ TRACE_EVENT(btrfs_cow_block, __entry->cow_level = btrfs_header_level(cow); ), - TP_printk("root = %llu(%s), refs = %d, orig_buf = %llu " + TP_printk_btrfs("root = %llu(%s), refs = %d, orig_buf = %llu " "(orig_level = %d), cow_buf = %llu (cow_level = %d)", show_root_type(__entry->root_objectid), __entry->refs, @@ -763,25 +788,23 @@ TRACE_EVENT(btrfs_space_reservation, TP_ARGS(fs_info, type, val, bytes, reserve), - TP_STRUCT__entry( - __array( u8, fsid, BTRFS_UUID_SIZE ) + TP_STRUCT__entry_btrfs( __string( type, type ) __field( u64, val ) __field( u64, bytes ) __field( int, reserve ) ), - TP_fast_assign( - memcpy(__entry->fsid, fs_info->fsid, BTRFS_UUID_SIZE); + TP_fast_assign_btrfs(fs_info, __assign_str(type, type); __entry->val = val; __entry->bytes = bytes; __entry->reserve = reserve; ), - TP_printk("%pU: %s: %Lu %s %Lu", __entry->fsid, __get_str(type), - __entry->val, __entry->reserve ? "reserve" : "release", - __entry->bytes) + TP_printk_btrfs("%s: %Lu %s %Lu", __get_str(type), __entry->val, + __entry->reserve ? "reserve" : "release", + __entry->bytes) ); #define show_flush_action(action) \ @@ -872,22 +895,19 @@ DECLARE_EVENT_CLASS(btrfs__reserved_extent, TP_ARGS(root, start, len), - TP_STRUCT__entry( - __array( u8, fsid, BTRFS_UUID_SIZE ) - __field( u64, root_objectid ) - __field( u64, start ) - __field( u64, len ) + TP_STRUCT__entry_btrfs( + __field( u64, root_objectid ) + __field( u64, start ) + __field( u64, len ) ), - TP_fast_assign( - memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->start = start; __entry->len = len; ), - TP_printk("%pU: root = %llu(%s), start = %llu, len = %llu", - __entry->fsid, + TP_printk_btrfs("root = %llu(%s), start = %llu, len = %llu", show_root_type(__entry->root_objectid), (unsigned long long)__entry->start, (unsigned long long)__entry->len) @@ -914,21 +934,21 @@ TRACE_EVENT(find_free_extent, TP_ARGS(root, num_bytes, empty_size, data), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, num_bytes ) __field( u64, empty_size ) __field( u64, data ) ), - TP_fast_assign( + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->num_bytes = num_bytes; __entry->empty_size = empty_size; __entry->data = data; ), - TP_printk("root = %Lu(%s), len = %Lu, empty_size = %Lu, " + TP_printk_btrfs("root = %Lu(%s), len = %Lu, empty_size = %Lu, " "flags = %Lu(%s)", show_root_type(__entry->root_objectid), __entry->num_bytes, __entry->empty_size, __entry->data, __print_flags((unsigned long)__entry->data, "|", @@ -943,8 +963,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, TP_ARGS(root, block_group, start, len), - TP_STRUCT__entry( - __array( u8, fsid, BTRFS_UUID_SIZE ) + TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, bg_objectid ) __field( u64, flags ) @@ -952,8 +971,7 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __field( u64, len ) ), - TP_fast_assign( - memcpy(__entry->fsid, root->fs_info->fsid, BTRFS_UUID_SIZE); + TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; @@ -961,8 +979,8 @@ DECLARE_EVENT_CLASS(btrfs__reserve_extent, __entry->len = len; ), - TP_printk("%pU: root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " - "start = %Lu, len = %Lu", __entry->fsid, + TP_printk_btrfs("root = %Lu(%s), block_group = %Lu, flags = %Lu(%s), " + "start = %Lu, len = %Lu", show_root_type(__entry->root_objectid), __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", BTRFS_GROUP_FLAGS), @@ -994,7 +1012,7 @@ TRACE_EVENT(btrfs_find_cluster, TP_ARGS(block_group, start, bytes, empty_size, min_bytes), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( u64, start ) @@ -1003,7 +1021,7 @@ TRACE_EVENT(btrfs_find_cluster, __field( u64, min_bytes ) ), - TP_fast_assign( + TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; __entry->start = start; @@ -1012,7 +1030,7 @@ TRACE_EVENT(btrfs_find_cluster, __entry->min_bytes = min_bytes; ), - TP_printk("block_group = %Lu, flags = %Lu(%s), start = %Lu, len = %Lu," + TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), start = %Lu, len = %Lu," " empty_size = %Lu, min_bytes = %Lu", __entry->bg_objectid, __entry->flags, __print_flags((unsigned long)__entry->flags, "|", @@ -1026,15 +1044,15 @@ TRACE_EVENT(btrfs_failed_cluster_setup, TP_ARGS(block_group), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) ), - TP_fast_assign( + TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->key.objectid; ), - TP_printk("block_group = %Lu", __entry->bg_objectid) + TP_printk_btrfs("block_group = %Lu", __entry->bg_objectid) ); TRACE_EVENT(btrfs_setup_cluster, @@ -1044,7 +1062,7 @@ TRACE_EVENT(btrfs_setup_cluster, TP_ARGS(block_group, cluster, size, bitmap), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bg_objectid ) __field( u64, flags ) __field( u64, start ) @@ -1053,7 +1071,7 @@ TRACE_EVENT(btrfs_setup_cluster, __field( int, bitmap ) ), - TP_fast_assign( + TP_fast_assign_btrfs(block_group->fs_info, __entry->bg_objectid = block_group->key.objectid; __entry->flags = block_group->flags; __entry->start = cluster->window_start; @@ -1062,7 +1080,7 @@ TRACE_EVENT(btrfs_setup_cluster, __entry->bitmap = bitmap; ), - TP_printk("block_group = %Lu, flags = %Lu(%s), window_start = %Lu, " + TP_printk_btrfs("block_group = %Lu, flags = %Lu(%s), window_start = %Lu, " "size = %Lu, max_size = %Lu, bitmap = %d", __entry->bg_objectid, __entry->flags, @@ -1120,7 +1138,7 @@ DECLARE_EVENT_CLASS(btrfs__work, TP_ARGS(work), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, work ) __field( void *, wq ) __field( void *, func ) @@ -1129,7 +1147,7 @@ DECLARE_EVENT_CLASS(btrfs__work, __field( void *, normal_work ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_work_owner(work), __entry->work = work; __entry->wq = work->wq; __entry->func = work->func; @@ -1138,7 +1156,7 @@ DECLARE_EVENT_CLASS(btrfs__work, __entry->normal_work = &work->normal_work; ), - TP_printk("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p," + TP_printk_btrfs("work=%p (normal_work=%p), wq=%p, func=%pf, ordered_func=%p," " ordered_free=%p", __entry->work, __entry->normal_work, __entry->wq, __entry->func, __entry->ordered_func, __entry->ordered_free) @@ -1151,15 +1169,15 @@ DECLARE_EVENT_CLASS(btrfs__work__done, TP_ARGS(work), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, work ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_work_owner(work), __entry->work = work; ), - TP_printk("work->%p", __entry->work) + TP_printk_btrfs("work->%p", __entry->work) ); DEFINE_EVENT(btrfs__work, btrfs_work_queued, @@ -1196,19 +1214,19 @@ DECLARE_EVENT_CLASS(btrfs__workqueue, TP_ARGS(wq, name, high), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, wq ) __string( name, name ) __field( int , high ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; __assign_str(name, name); __entry->high = high; ), - TP_printk("name=%s%s, wq=%p", __get_str(name), + TP_printk_btrfs("name=%s%s, wq=%p", __get_str(name), __print_flags(__entry->high, "", {(WQ_HIGHPRI), "-high"}), __entry->wq) @@ -1227,15 +1245,15 @@ DECLARE_EVENT_CLASS(btrfs__workqueue_done, TP_ARGS(wq), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( void *, wq ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_workqueue_owner(wq), __entry->wq = wq; ), - TP_printk("wq=%p", __entry->wq) + TP_printk_btrfs("wq=%p", __entry->wq) ); DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy, @@ -1251,19 +1269,19 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_data_map, TP_ARGS(inode, free_reserved), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, rootid ) __field( unsigned long, ino ) __field( u64, free_reserved ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->rootid = BTRFS_I(inode)->root->objectid; __entry->ino = inode->i_ino; __entry->free_reserved = free_reserved; ), - TP_printk("rootid=%llu, ino=%lu, free_reserved=%llu", + TP_printk_btrfs("rootid=%llu, ino=%lu, free_reserved=%llu", __entry->rootid, __entry->ino, __entry->free_reserved) ); @@ -1292,7 +1310,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, TP_ARGS(inode, start, len, reserved, op), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, rootid ) __field( unsigned long, ino ) __field( u64, start ) @@ -1301,7 +1319,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, __field( int, op ) ), - TP_fast_assign( + TP_fast_assign_btrfs(btrfs_sb(inode->i_sb), __entry->rootid = BTRFS_I(inode)->root->objectid; __entry->ino = inode->i_ino; __entry->start = start; @@ -1310,7 +1328,7 @@ DECLARE_EVENT_CLASS(btrfs__qgroup_rsv_data, __entry->op = op; ), - TP_printk("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s", + TP_printk_btrfs("root=%llu, ino=%lu, start=%llu, len=%llu, reserved=%llu, op=%s", __entry->rootid, __entry->ino, __entry->start, __entry->len, __entry->reserved, __print_flags((unsigned long)__entry->op, "", @@ -1334,86 +1352,90 @@ DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data, DECLARE_EVENT_CLASS(btrfs__qgroup_delayed_ref, - TP_PROTO(u64 ref_root, u64 reserved), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 ref_root, u64 reserved), - TP_ARGS(ref_root, reserved), + TP_ARGS(fs_info, ref_root, reserved), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, ref_root ) __field( u64, reserved ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->ref_root = ref_root; __entry->reserved = reserved; ), - TP_printk("root=%llu, reserved=%llu, op=free", + TP_printk_btrfs("root=%llu, reserved=%llu, op=free", __entry->ref_root, __entry->reserved) ); DEFINE_EVENT(btrfs__qgroup_delayed_ref, btrfs_qgroup_free_delayed_ref, - TP_PROTO(u64 ref_root, u64 reserved), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 ref_root, u64 reserved), - TP_ARGS(ref_root, reserved) + TP_ARGS(fs_info, ref_root, reserved) ); DECLARE_EVENT_CLASS(btrfs_qgroup_extent, - TP_PROTO(struct btrfs_qgroup_extent_record *rec), + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *rec), - TP_ARGS(rec), + TP_ARGS(fs_info, rec), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = rec->bytenr, __entry->num_bytes = rec->num_bytes; ), - TP_printk("bytenr = %llu, num_bytes = %llu", + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu", (unsigned long long)__entry->bytenr, (unsigned long long)__entry->num_bytes) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents, - TP_PROTO(struct btrfs_qgroup_extent_record *rec), + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *rec), - TP_ARGS(rec) + TP_ARGS(fs_info, rec) ); DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_insert_dirty_extent, - TP_PROTO(struct btrfs_qgroup_extent_record *rec), + TP_PROTO(struct btrfs_fs_info *fs_info, + struct btrfs_qgroup_extent_record *rec), - TP_ARGS(rec) + TP_ARGS(fs_info, rec) ); TRACE_EVENT(btrfs_qgroup_account_extent, - TP_PROTO(u64 bytenr, u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 bytenr, + u64 num_bytes, u64 nr_old_roots, u64 nr_new_roots), - TP_ARGS(bytenr, num_bytes, nr_old_roots, nr_new_roots), + TP_ARGS(fs_info, bytenr, num_bytes, nr_old_roots, nr_new_roots), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, bytenr ) __field( u64, num_bytes ) __field( u64, nr_old_roots ) __field( u64, nr_new_roots ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->bytenr = bytenr; __entry->num_bytes = num_bytes; __entry->nr_old_roots = nr_old_roots; __entry->nr_new_roots = nr_new_roots; ), - TP_printk("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, " + TP_printk_btrfs("bytenr = %llu, num_bytes = %llu, nr_old_roots = %llu, " "nr_new_roots = %llu", __entry->bytenr, __entry->num_bytes, @@ -1423,23 +1445,24 @@ TRACE_EVENT(btrfs_qgroup_account_extent, TRACE_EVENT(qgroup_update_counters, - TP_PROTO(u64 qgid, u64 cur_old_count, u64 cur_new_count), + TP_PROTO(struct btrfs_fs_info *fs_info, u64 qgid, + u64 cur_old_count, u64 cur_new_count), - TP_ARGS(qgid, cur_old_count, cur_new_count), + TP_ARGS(fs_info, qgid, cur_old_count, cur_new_count), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, qgid ) __field( u64, cur_old_count ) __field( u64, cur_new_count ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->qgid = qgid; __entry->cur_old_count = cur_old_count; __entry->cur_new_count = cur_new_count; ), - TP_printk("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu", + TP_printk_btrfs("qgid = %llu, cur_old_count = %llu, cur_new_count = %llu", __entry->qgid, __entry->cur_old_count, __entry->cur_new_count) -- cgit v1.2.3 From 06a8fc78367d070720af960dcecec917d3ae5f3b Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 28 Jul 2016 15:36:32 +0100 Subject: VSOCK: Introduce virtio_vsock_common.ko This module contains the common code and header files for the following virtio_transporto and vhost_vsock kernel modules. Signed-off-by: Asias He Signed-off-by: Claudio Imbrenda Signed-off-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- MAINTAINERS | 10 + include/linux/virtio_vsock.h | 154 ++++ include/net/af_vsock.h | 2 + .../trace/events/vsock_virtio_transport_common.h | 144 +++ include/uapi/linux/Kbuild | 1 + include/uapi/linux/virtio_ids.h | 1 + include/uapi/linux/virtio_vsock.h | 94 ++ net/vmw_vsock/virtio_transport_common.c | 992 +++++++++++++++++++++ 8 files changed, 1398 insertions(+) create mode 100644 include/linux/virtio_vsock.h create mode 100644 include/trace/events/vsock_virtio_transport_common.h create mode 100644 include/uapi/linux/virtio_vsock.h create mode 100644 net/vmw_vsock/virtio_transport_common.c (limited to 'include/trace') diff --git a/MAINTAINERS b/MAINTAINERS index 8c20323d1277..b49ffb86ebf0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12138,6 +12138,16 @@ S: Maintained F: drivers/media/v4l2-core/videobuf2-* F: include/media/videobuf2-* +VIRTIO AND VHOST VSOCK DRIVER +M: Stefan Hajnoczi +L: kvm@vger.kernel.org +L: virtualization@lists.linux-foundation.org +L: netdev@vger.kernel.org +S: Maintained +F: include/linux/virtio_vsock.h +F: include/uapi/linux/virtio_vsock.h +F: net/vmw_vsock/virtio_transport_common.c + VIRTUAL SERIO DEVICE DRIVER M: Stephen Chandler Paul S: Maintained diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h new file mode 100644 index 000000000000..9638bfeb0d1f --- /dev/null +++ b/include/linux/virtio_vsock.h @@ -0,0 +1,154 @@ +#ifndef _LINUX_VIRTIO_VSOCK_H +#define _LINUX_VIRTIO_VSOCK_H + +#include +#include +#include +#include + +#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 +#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) +#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) +#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) +#define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL +#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) + +enum { + VSOCK_VQ_RX = 0, /* for host to guest data */ + VSOCK_VQ_TX = 1, /* for guest to host data */ + VSOCK_VQ_EVENT = 2, + VSOCK_VQ_MAX = 3, +}; + +/* Per-socket state (accessed via vsk->trans) */ +struct virtio_vsock_sock { + struct vsock_sock *vsk; + + /* Protected by lock_sock(sk_vsock(trans->vsk)) */ + u32 buf_size; + u32 buf_size_min; + u32 buf_size_max; + + spinlock_t tx_lock; + spinlock_t rx_lock; + + /* Protected by tx_lock */ + u32 tx_cnt; + u32 buf_alloc; + u32 peer_fwd_cnt; + u32 peer_buf_alloc; + + /* Protected by rx_lock */ + u32 fwd_cnt; + u32 rx_bytes; + struct list_head rx_queue; +}; + +struct virtio_vsock_pkt { + struct virtio_vsock_hdr hdr; + struct work_struct work; + struct list_head list; + void *buf; + u32 len; + u32 off; + bool reply; +}; + +struct virtio_vsock_pkt_info { + u32 remote_cid, remote_port; + struct msghdr *msg; + u32 pkt_len; + u16 type; + u16 op; + u32 flags; + bool reply; +}; + +struct virtio_transport { + /* This must be the first field */ + struct vsock_transport transport; + + /* Takes ownership of the packet */ + int (*send_pkt)(struct virtio_vsock_pkt *pkt); +}; + +ssize_t +virtio_transport_stream_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, + int type); +int +virtio_transport_dgram_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags); + +s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); +s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); + +int virtio_transport_do_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk); +u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); +u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); +u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); +void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); +void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); +void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); +int +virtio_transport_notify_poll_in(struct vsock_sock *vsk, + size_t target, + bool *data_ready_now); +int +virtio_transport_notify_poll_out(struct vsock_sock *vsk, + size_t target, + bool *space_available_now); + +int virtio_transport_notify_recv_init(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, + size_t target, ssize_t copied, bool data_read, + struct vsock_transport_recv_notify_data *data); +int virtio_transport_notify_send_init(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data); +int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, + ssize_t written, struct vsock_transport_send_notify_data *data); + +u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); +bool virtio_transport_stream_is_active(struct vsock_sock *vsk); +bool virtio_transport_stream_allow(u32 cid, u32 port); +int virtio_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr); +bool virtio_transport_dgram_allow(u32 cid, u32 port); + +int virtio_transport_connect(struct vsock_sock *vsk); + +int virtio_transport_shutdown(struct vsock_sock *vsk, int mode); + +void virtio_transport_release(struct vsock_sock *vsk); + +ssize_t +virtio_transport_stream_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); +int +virtio_transport_dgram_enqueue(struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct msghdr *msg, + size_t len); + +void virtio_transport_destruct(struct vsock_sock *vsk); + +void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); +u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); +void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit); + +#endif /* _LINUX_VIRTIO_VSOCK_H */ diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 3af0b224f754..f2758964ce6f 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -63,6 +63,8 @@ struct vsock_sock { struct list_head accept_queue; bool rejected; struct delayed_work dwork; + struct delayed_work close_work; + bool close_work_scheduled; u32 peer_shutdown; bool sent_request; bool ignore_connecting_rst; diff --git a/include/trace/events/vsock_virtio_transport_common.h b/include/trace/events/vsock_virtio_transport_common.h new file mode 100644 index 000000000000..b7f1d6278280 --- /dev/null +++ b/include/trace/events/vsock_virtio_transport_common.h @@ -0,0 +1,144 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vsock + +#if !defined(_TRACE_VSOCK_VIRTIO_TRANSPORT_COMMON_H) || \ + defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VSOCK_VIRTIO_TRANSPORT_COMMON_H + +#include + +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_STREAM); + +#define show_type(val) \ + __print_symbolic(val, { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }) + +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_INVALID); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_REQUEST); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_RESPONSE); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_RST); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_SHUTDOWN); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_RW); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_CREDIT_UPDATE); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_CREDIT_REQUEST); + +#define show_op(val) \ + __print_symbolic(val, \ + { VIRTIO_VSOCK_OP_INVALID, "INVALID" }, \ + { VIRTIO_VSOCK_OP_REQUEST, "REQUEST" }, \ + { VIRTIO_VSOCK_OP_RESPONSE, "RESPONSE" }, \ + { VIRTIO_VSOCK_OP_RST, "RST" }, \ + { VIRTIO_VSOCK_OP_SHUTDOWN, "SHUTDOWN" }, \ + { VIRTIO_VSOCK_OP_RW, "RW" }, \ + { VIRTIO_VSOCK_OP_CREDIT_UPDATE, "CREDIT_UPDATE" }, \ + { VIRTIO_VSOCK_OP_CREDIT_REQUEST, "CREDIT_REQUEST" }) + +TRACE_EVENT(virtio_transport_alloc_pkt, + TP_PROTO( + __u32 src_cid, __u32 src_port, + __u32 dst_cid, __u32 dst_port, + __u32 len, + __u16 type, + __u16 op, + __u32 flags + ), + TP_ARGS( + src_cid, src_port, + dst_cid, dst_port, + len, + type, + op, + flags + ), + TP_STRUCT__entry( + __field(__u32, src_cid) + __field(__u32, src_port) + __field(__u32, dst_cid) + __field(__u32, dst_port) + __field(__u32, len) + __field(__u16, type) + __field(__u16, op) + __field(__u32, flags) + ), + TP_fast_assign( + __entry->src_cid = src_cid; + __entry->src_port = src_port; + __entry->dst_cid = dst_cid; + __entry->dst_port = dst_port; + __entry->len = len; + __entry->type = type; + __entry->op = op; + __entry->flags = flags; + ), + TP_printk("%u:%u -> %u:%u len=%u type=%s op=%s flags=%#x", + __entry->src_cid, __entry->src_port, + __entry->dst_cid, __entry->dst_port, + __entry->len, + show_type(__entry->type), + show_op(__entry->op), + __entry->flags) +); + +TRACE_EVENT(virtio_transport_recv_pkt, + TP_PROTO( + __u32 src_cid, __u32 src_port, + __u32 dst_cid, __u32 dst_port, + __u32 len, + __u16 type, + __u16 op, + __u32 flags, + __u32 buf_alloc, + __u32 fwd_cnt + ), + TP_ARGS( + src_cid, src_port, + dst_cid, dst_port, + len, + type, + op, + flags, + buf_alloc, + fwd_cnt + ), + TP_STRUCT__entry( + __field(__u32, src_cid) + __field(__u32, src_port) + __field(__u32, dst_cid) + __field(__u32, dst_port) + __field(__u32, len) + __field(__u16, type) + __field(__u16, op) + __field(__u32, flags) + __field(__u32, buf_alloc) + __field(__u32, fwd_cnt) + ), + TP_fast_assign( + __entry->src_cid = src_cid; + __entry->src_port = src_port; + __entry->dst_cid = dst_cid; + __entry->dst_port = dst_port; + __entry->len = len; + __entry->type = type; + __entry->op = op; + __entry->flags = flags; + __entry->buf_alloc = buf_alloc; + __entry->fwd_cnt = fwd_cnt; + ), + TP_printk("%u:%u -> %u:%u len=%u type=%s op=%s flags=%#x " + "buf_alloc=%u fwd_cnt=%u", + __entry->src_cid, __entry->src_port, + __entry->dst_cid, __entry->dst_port, + __entry->len, + show_type(__entry->type), + show_op(__entry->op), + __entry->flags, + __entry->buf_alloc, + __entry->fwd_cnt) +); + +#endif /* _TRACE_VSOCK_VIRTIO_TRANSPORT_COMMON_H */ + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE vsock_virtio_transport_common + +/* This part must be outside protection */ +#include diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index ec10cfef166a..3cf0116d9c2b 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -453,6 +453,7 @@ header-y += virtio_ring.h header-y += virtio_rng.h header-y += virtio_scsi.h header-y += virtio_types.h +header-y += virtio_vsock.h header-y += vm_sockets.h header-y += vt.h header-y += wait.h diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 77925f587b15..3228d582234a 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -41,5 +41,6 @@ #define VIRTIO_ID_CAIF 12 /* Virtio caif */ #define VIRTIO_ID_GPU 16 /* virtio GPU */ #define VIRTIO_ID_INPUT 18 /* virtio input */ +#define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h new file mode 100644 index 000000000000..6b011c19b50f --- /dev/null +++ b/include/uapi/linux/virtio_vsock.h @@ -0,0 +1,94 @@ +/* + * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so + * anyone can use the definitions to implement compatible drivers/servers: + * + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * Copyright (C) Red Hat, Inc., 2013-2015 + * Copyright (C) Asias He , 2013 + * Copyright (C) Stefan Hajnoczi , 2015 + */ + +#ifndef _UAPI_LINUX_VIRTIO_VSOCK_H +#define _UAPI_LINUX_VIRTIO_VOSCK_H + +#include +#include +#include + +struct virtio_vsock_config { + __le64 guest_cid; +} __attribute__((packed)); + +enum virtio_vsock_event_id { + VIRTIO_VSOCK_EVENT_TRANSPORT_RESET = 0, +}; + +struct virtio_vsock_event { + __le32 id; +} __attribute__((packed)); + +struct virtio_vsock_hdr { + __le64 src_cid; + __le64 dst_cid; + __le32 src_port; + __le32 dst_port; + __le32 len; + __le16 type; /* enum virtio_vsock_type */ + __le16 op; /* enum virtio_vsock_op */ + __le32 flags; + __le32 buf_alloc; + __le32 fwd_cnt; +} __attribute__((packed)); + +enum virtio_vsock_type { + VIRTIO_VSOCK_TYPE_STREAM = 1, +}; + +enum virtio_vsock_op { + VIRTIO_VSOCK_OP_INVALID = 0, + + /* Connect operations */ + VIRTIO_VSOCK_OP_REQUEST = 1, + VIRTIO_VSOCK_OP_RESPONSE = 2, + VIRTIO_VSOCK_OP_RST = 3, + VIRTIO_VSOCK_OP_SHUTDOWN = 4, + + /* To send payload */ + VIRTIO_VSOCK_OP_RW = 5, + + /* Tell the peer our credit info */ + VIRTIO_VSOCK_OP_CREDIT_UPDATE = 6, + /* Request the peer to send the credit info to us */ + VIRTIO_VSOCK_OP_CREDIT_REQUEST = 7, +}; + +/* VIRTIO_VSOCK_OP_SHUTDOWN flags values */ +enum virtio_vsock_shutdown { + VIRTIO_VSOCK_SHUTDOWN_RCV = 1, + VIRTIO_VSOCK_SHUTDOWN_SEND = 2, +}; + +#endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */ diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c new file mode 100644 index 000000000000..a53b3a16b4f1 --- /dev/null +++ b/net/vmw_vsock/virtio_transport_common.c @@ -0,0 +1,992 @@ +/* + * common code for virtio vsock + * + * Copyright (C) 2013-2015 Red Hat, Inc. + * Author: Asias He + * Stefan Hajnoczi + * + * This work is licensed under the terms of the GNU GPL, version 2. + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define CREATE_TRACE_POINTS +#include + +/* How long to wait for graceful shutdown of a connection */ +#define VSOCK_CLOSE_TIMEOUT (8 * HZ) + +static const struct virtio_transport *virtio_transport_get_ops(void) +{ + const struct vsock_transport *t = vsock_core_get_transport(); + + return container_of(t, struct virtio_transport, transport); +} + +struct virtio_vsock_pkt * +virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, + size_t len, + u32 src_cid, + u32 src_port, + u32 dst_cid, + u32 dst_port) +{ + struct virtio_vsock_pkt *pkt; + int err; + + pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return NULL; + + pkt->hdr.type = cpu_to_le16(info->type); + pkt->hdr.op = cpu_to_le16(info->op); + pkt->hdr.src_cid = cpu_to_le64(src_cid); + pkt->hdr.dst_cid = cpu_to_le64(dst_cid); + pkt->hdr.src_port = cpu_to_le32(src_port); + pkt->hdr.dst_port = cpu_to_le32(dst_port); + pkt->hdr.flags = cpu_to_le32(info->flags); + pkt->len = len; + pkt->hdr.len = cpu_to_le32(len); + pkt->reply = info->reply; + + if (info->msg && len > 0) { + pkt->buf = kmalloc(len, GFP_KERNEL); + if (!pkt->buf) + goto out_pkt; + err = memcpy_from_msg(pkt->buf, info->msg, len); + if (err) + goto out; + } + + trace_virtio_transport_alloc_pkt(src_cid, src_port, + dst_cid, dst_port, + len, + info->type, + info->op, + info->flags); + + return pkt; + +out: + kfree(pkt->buf); +out_pkt: + kfree(pkt); + return NULL; +} +EXPORT_SYMBOL_GPL(virtio_transport_alloc_pkt); + +static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, + struct virtio_vsock_pkt_info *info) +{ + u32 src_cid, src_port, dst_cid, dst_port; + struct virtio_vsock_sock *vvs; + struct virtio_vsock_pkt *pkt; + u32 pkt_len = info->pkt_len; + + src_cid = vm_sockets_get_local_cid(); + src_port = vsk->local_addr.svm_port; + if (!info->remote_cid) { + dst_cid = vsk->remote_addr.svm_cid; + dst_port = vsk->remote_addr.svm_port; + } else { + dst_cid = info->remote_cid; + dst_port = info->remote_port; + } + + vvs = vsk->trans; + + /* we can send less than pkt_len bytes */ + if (pkt_len > VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE) + pkt_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE; + + /* virtio_transport_get_credit might return less than pkt_len credit */ + pkt_len = virtio_transport_get_credit(vvs, pkt_len); + + /* Do not send zero length OP_RW pkt */ + if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) + return pkt_len; + + pkt = virtio_transport_alloc_pkt(info, pkt_len, + src_cid, src_port, + dst_cid, dst_port); + if (!pkt) { + virtio_transport_put_credit(vvs, pkt_len); + return -ENOMEM; + } + + virtio_transport_inc_tx_pkt(vvs, pkt); + + return virtio_transport_get_ops()->send_pkt(pkt); +} + +static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, + struct virtio_vsock_pkt *pkt) +{ + vvs->rx_bytes += pkt->len; +} + +static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, + struct virtio_vsock_pkt *pkt) +{ + vvs->rx_bytes -= pkt->len; + vvs->fwd_cnt += pkt->len; +} + +void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) +{ + spin_lock_bh(&vvs->tx_lock); + pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt); + pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc); + spin_unlock_bh(&vvs->tx_lock); +} +EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); + +u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) +{ + u32 ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + if (ret > credit) + ret = credit; + vvs->tx_cnt += ret; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_credit); + +void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) +{ + spin_lock_bh(&vvs->tx_lock); + vvs->tx_cnt -= credit; + spin_unlock_bh(&vvs->tx_lock); +} +EXPORT_SYMBOL_GPL(virtio_transport_put_credit); + +static int virtio_transport_send_credit_update(struct vsock_sock *vsk, + int type, + struct virtio_vsock_hdr *hdr) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, + .type = type, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +static ssize_t +virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + size_t bytes, total = 0; + int err = -EFAULT; + + spin_lock_bh(&vvs->rx_lock); + while (total < len && !list_empty(&vvs->rx_queue)) { + pkt = list_first_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + bytes = len - total; + if (bytes > pkt->len - pkt->off) + bytes = pkt->len - pkt->off; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes); + if (err) + goto out; + + spin_lock_bh(&vvs->rx_lock); + + total += bytes; + pkt->off += bytes; + if (pkt->off == pkt->len) { + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + } + spin_unlock_bh(&vvs->rx_lock); + + /* Send a credit pkt to peer */ + virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, + NULL); + + return total; + +out: + if (total) + err = total; + return err; +} + +ssize_t +virtio_transport_stream_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_stream_do_dequeue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); + +int +virtio_transport_dgram_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len, int flags) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue); + +s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + spin_lock_bh(&vvs->rx_lock); + bytes = vvs->rx_bytes; + spin_unlock_bh(&vvs->rx_lock); + + return bytes; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); + +static s64 virtio_transport_has_space(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + if (bytes < 0) + bytes = 0; + + return bytes; +} + +s64 virtio_transport_stream_has_space(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + s64 bytes; + + spin_lock_bh(&vvs->tx_lock); + bytes = virtio_transport_has_space(vsk); + spin_unlock_bh(&vvs->tx_lock); + + return bytes; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space); + +int virtio_transport_do_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk) +{ + struct virtio_vsock_sock *vvs; + + vvs = kzalloc(sizeof(*vvs), GFP_KERNEL); + if (!vvs) + return -ENOMEM; + + vsk->trans = vvs; + vvs->vsk = vsk; + if (psk) { + struct virtio_vsock_sock *ptrans = psk->trans; + + vvs->buf_size = ptrans->buf_size; + vvs->buf_size_min = ptrans->buf_size_min; + vvs->buf_size_max = ptrans->buf_size_max; + vvs->peer_buf_alloc = ptrans->peer_buf_alloc; + } else { + vvs->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE; + vvs->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE; + vvs->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE; + } + + vvs->buf_alloc = vvs->buf_size; + + spin_lock_init(&vvs->rx_lock); + spin_lock_init(&vvs->tx_lock); + INIT_LIST_HEAD(&vvs->rx_queue); + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init); + +u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size); + +u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size_min; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_min_buffer_size); + +u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size_max; +} +EXPORT_SYMBOL_GPL(virtio_transport_get_max_buffer_size); + +void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val < vvs->buf_size_min) + vvs->buf_size_min = val; + if (val > vvs->buf_size_max) + vvs->buf_size_max = val; + vvs->buf_size = val; + vvs->buf_alloc = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size); + +void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val > vvs->buf_size) + vvs->buf_size = val; + vvs->buf_size_min = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_min_buffer_size); + +void virtio_transport_set_max_buffer_size(struct vsock_sock *vsk, u64 val) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + if (val > VIRTIO_VSOCK_MAX_BUF_SIZE) + val = VIRTIO_VSOCK_MAX_BUF_SIZE; + if (val < vvs->buf_size) + vvs->buf_size = val; + vvs->buf_size_max = val; +} +EXPORT_SYMBOL_GPL(virtio_transport_set_max_buffer_size); + +int +virtio_transport_notify_poll_in(struct vsock_sock *vsk, + size_t target, + bool *data_ready_now) +{ + if (vsock_stream_has_data(vsk)) + *data_ready_now = true; + else + *data_ready_now = false; + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in); + +int +virtio_transport_notify_poll_out(struct vsock_sock *vsk, + size_t target, + bool *space_avail_now) +{ + s64 free_space; + + free_space = vsock_stream_has_space(vsk); + if (free_space > 0) + *space_avail_now = true; + else if (free_space == 0) + *space_avail_now = false; + + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out); + +int virtio_transport_notify_recv_init(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init); + +int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block); + +int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk, + size_t target, struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue); + +int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk, + size_t target, ssize_t copied, bool data_read, + struct vsock_transport_recv_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue); + +int virtio_transport_notify_send_init(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init); + +int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block); + +int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue); + +int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, + ssize_t written, struct vsock_transport_send_notify_data *data) +{ + return 0; +} +EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue); + +u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + return vvs->buf_size; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat); + +bool virtio_transport_stream_is_active(struct vsock_sock *vsk) +{ + return true; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active); + +bool virtio_transport_stream_allow(u32 cid, u32 port) +{ + return true; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_allow); + +int virtio_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind); + +bool virtio_transport_dgram_allow(u32 cid, u32 port) +{ + return false; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow); + +int virtio_transport_connect(struct vsock_sock *vsk) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_REQUEST, + .type = VIRTIO_VSOCK_TYPE_STREAM, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_connect); + +int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_SHUTDOWN, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .flags = (mode & RCV_SHUTDOWN ? + VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | + (mode & SEND_SHUTDOWN ? + VIRTIO_VSOCK_SHUTDOWN_SEND : 0), + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_shutdown); + +int +virtio_transport_dgram_enqueue(struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct msghdr *msg, + size_t dgram_len) +{ + return -EOPNOTSUPP; +} +EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue); + +ssize_t +virtio_transport_stream_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RW, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .msg = msg, + .pkt_len = len, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue); + +void virtio_transport_destruct(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + kfree(vvs); +} +EXPORT_SYMBOL_GPL(virtio_transport_destruct); + +static int virtio_transport_reset(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RST, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .reply = !!pkt, + }; + + /* Send RST only if the original pkt is not a RST pkt */ + if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + return 0; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +/* Normally packets are associated with a socket. There may be no socket if an + * attempt was made to connect to a socket that does not exist. + */ +static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RST, + .type = le16_to_cpu(pkt->hdr.type), + .reply = true, + }; + + /* Send RST only if the original pkt is not a RST pkt */ + if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + return 0; + + pkt = virtio_transport_alloc_pkt(&info, 0, + le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port), + le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + if (!pkt) + return -ENOMEM; + + return virtio_transport_get_ops()->send_pkt(pkt); +} + +static void virtio_transport_wait_close(struct sock *sk, long timeout) +{ + if (timeout) { + DEFINE_WAIT(wait); + + do { + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); + if (sk_wait_event(sk, &timeout, + sock_flag(sk, SOCK_DONE))) + break; + } while (!signal_pending(current) && timeout); + + finish_wait(sk_sleep(sk), &wait); + } +} + +static void virtio_transport_do_close(struct vsock_sock *vsk, + bool cancel_timeout) +{ + struct sock *sk = sk_vsock(vsk); + + sock_set_flag(sk, SOCK_DONE); + vsk->peer_shutdown = SHUTDOWN_MASK; + if (vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + sk->sk_state_change(sk); + + if (vsk->close_work_scheduled && + (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { + vsk->close_work_scheduled = false; + + vsock_remove_sock(vsk); + + /* Release refcnt obtained when we scheduled the timeout */ + sock_put(sk); + } +} + +static void virtio_transport_close_timeout(struct work_struct *work) +{ + struct vsock_sock *vsk = + container_of(work, struct vsock_sock, close_work.work); + struct sock *sk = sk_vsock(vsk); + + sock_hold(sk); + lock_sock(sk); + + if (!sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, false); + } + + vsk->close_work_scheduled = false; + + release_sock(sk); + sock_put(sk); +} + +/* User context, vsk->sk is locked */ +static bool virtio_transport_close(struct vsock_sock *vsk) +{ + struct sock *sk = &vsk->sk; + + if (!(sk->sk_state == SS_CONNECTED || + sk->sk_state == SS_DISCONNECTING)) + return true; + + /* Already received SHUTDOWN from peer, reply with RST */ + if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) { + (void)virtio_transport_reset(vsk, NULL); + return true; + } + + if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK) + (void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK); + + if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING)) + virtio_transport_wait_close(sk, sk->sk_lingertime); + + if (sock_flag(sk, SOCK_DONE)) { + return true; + } + + sock_hold(sk); + INIT_DELAYED_WORK(&vsk->close_work, + virtio_transport_close_timeout); + vsk->close_work_scheduled = true; + schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT); + return false; +} + +void virtio_transport_release(struct vsock_sock *vsk) +{ + struct sock *sk = &vsk->sk; + bool remove_sock = true; + + lock_sock(sk); + if (sk->sk_type == SOCK_STREAM) + remove_sock = virtio_transport_close(vsk); + release_sock(sk); + + if (remove_sock) + vsock_remove_sock(vsk); +} +EXPORT_SYMBOL_GPL(virtio_transport_release); + +static int +virtio_transport_recv_connecting(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + int err; + int skerr; + + switch (le16_to_cpu(pkt->hdr.op)) { + case VIRTIO_VSOCK_OP_RESPONSE: + sk->sk_state = SS_CONNECTED; + sk->sk_socket->state = SS_CONNECTED; + vsock_insert_connected(vsk); + sk->sk_state_change(sk); + break; + case VIRTIO_VSOCK_OP_INVALID: + break; + case VIRTIO_VSOCK_OP_RST: + skerr = ECONNRESET; + err = 0; + goto destroy; + default: + skerr = EPROTO; + err = -EINVAL; + goto destroy; + } + return 0; + +destroy: + virtio_transport_reset(vsk, pkt); + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = skerr; + sk->sk_error_report(sk); + return err; +} + +static int +virtio_transport_recv_connected(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct virtio_vsock_sock *vvs = vsk->trans; + int err = 0; + + switch (le16_to_cpu(pkt->hdr.op)) { + case VIRTIO_VSOCK_OP_RW: + pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->off = 0; + + spin_lock_bh(&vvs->rx_lock); + virtio_transport_inc_rx_pkt(vvs, pkt); + list_add_tail(&pkt->list, &vvs->rx_queue); + spin_unlock_bh(&vvs->rx_lock); + + sk->sk_data_ready(sk); + return err; + case VIRTIO_VSOCK_OP_CREDIT_UPDATE: + sk->sk_write_space(sk); + break; + case VIRTIO_VSOCK_OP_SHUTDOWN: + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV) + vsk->peer_shutdown |= RCV_SHUTDOWN; + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) + vsk->peer_shutdown |= SEND_SHUTDOWN; + if (vsk->peer_shutdown == SHUTDOWN_MASK && + vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + if (le32_to_cpu(pkt->hdr.flags)) + sk->sk_state_change(sk); + break; + case VIRTIO_VSOCK_OP_RST: + virtio_transport_do_close(vsk, true); + break; + default: + err = -EINVAL; + break; + } + + virtio_transport_free_pkt(pkt); + return err; +} + +static void +virtio_transport_recv_disconnecting(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST) + virtio_transport_do_close(vsk, true); +} + +static int +virtio_transport_send_response(struct vsock_sock *vsk, + struct virtio_vsock_pkt *pkt) +{ + struct virtio_vsock_pkt_info info = { + .op = VIRTIO_VSOCK_OP_RESPONSE, + .type = VIRTIO_VSOCK_TYPE_STREAM, + .remote_cid = le32_to_cpu(pkt->hdr.src_cid), + .remote_port = le32_to_cpu(pkt->hdr.src_port), + .reply = true, + }; + + return virtio_transport_send_pkt_info(vsk, &info); +} + +/* Handle server socket */ +static int +virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct vsock_sock *vchild; + struct sock *child; + + if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { + virtio_transport_reset(vsk, pkt); + return -EINVAL; + } + + if (sk_acceptq_is_full(sk)) { + virtio_transport_reset(vsk, pkt); + return -ENOMEM; + } + + child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL, + sk->sk_type, 0); + if (!child) { + virtio_transport_reset(vsk, pkt); + return -ENOMEM; + } + + sk->sk_ack_backlog++; + + lock_sock_nested(child, SINGLE_DEPTH_NESTING); + + child->sk_state = SS_CONNECTED; + + vchild = vsock_sk(child); + vsock_addr_init(&vchild->local_addr, le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port)); + vsock_addr_init(&vchild->remote_addr, le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + + vsock_insert_connected(vchild); + vsock_enqueue_accept(sk, child); + virtio_transport_send_response(vchild, pkt); + + release_sock(child); + + sk->sk_data_ready(sk); + return 0; +} + +static bool virtio_transport_space_update(struct sock *sk, + struct virtio_vsock_pkt *pkt) +{ + struct vsock_sock *vsk = vsock_sk(sk); + struct virtio_vsock_sock *vvs = vsk->trans; + bool space_available; + + /* buf_alloc and fwd_cnt is always included in the hdr */ + spin_lock_bh(&vvs->tx_lock); + vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc); + vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt); + space_available = virtio_transport_has_space(vsk); + spin_unlock_bh(&vvs->tx_lock); + return space_available; +} + +/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex + * lock. + */ +void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt) +{ + struct sockaddr_vm src, dst; + struct vsock_sock *vsk; + struct sock *sk; + bool space_available; + + vsock_addr_init(&src, le32_to_cpu(pkt->hdr.src_cid), + le32_to_cpu(pkt->hdr.src_port)); + vsock_addr_init(&dst, le32_to_cpu(pkt->hdr.dst_cid), + le32_to_cpu(pkt->hdr.dst_port)); + + trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port, + dst.svm_cid, dst.svm_port, + le32_to_cpu(pkt->hdr.len), + le16_to_cpu(pkt->hdr.type), + le16_to_cpu(pkt->hdr.op), + le32_to_cpu(pkt->hdr.flags), + le32_to_cpu(pkt->hdr.buf_alloc), + le32_to_cpu(pkt->hdr.fwd_cnt)); + + if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + (void)virtio_transport_reset_no_sock(pkt); + goto free_pkt; + } + + /* The socket must be in connected or bound table + * otherwise send reset back + */ + sk = vsock_find_connected_socket(&src, &dst); + if (!sk) { + sk = vsock_find_bound_socket(&dst); + if (!sk) { + (void)virtio_transport_reset_no_sock(pkt); + goto free_pkt; + } + } + + vsk = vsock_sk(sk); + + space_available = virtio_transport_space_update(sk, pkt); + + lock_sock(sk); + + /* Update CID in case it has changed after a transport reset event */ + vsk->local_addr.svm_cid = dst.svm_cid; + + if (space_available) + sk->sk_write_space(sk); + + switch (sk->sk_state) { + case VSOCK_SS_LISTEN: + virtio_transport_recv_listen(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + case SS_CONNECTING: + virtio_transport_recv_connecting(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + case SS_CONNECTED: + virtio_transport_recv_connected(sk, pkt); + break; + case SS_DISCONNECTING: + virtio_transport_recv_disconnecting(sk, pkt); + virtio_transport_free_pkt(pkt); + break; + default: + virtio_transport_free_pkt(pkt); + break; + } + release_sock(sk); + + /* Release refcnt obtained when we fetched this socket out of the + * bound or connected list. + */ + sock_put(sk); + return; + +free_pkt: + virtio_transport_free_pkt(pkt); +} +EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt); + +void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt) +{ + kfree(pkt->buf); + kfree(pkt); +} +EXPORT_SYMBOL_GPL(virtio_transport_free_pkt); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Asias He"); +MODULE_DESCRIPTION("common code for virtio vsock"); -- cgit v1.2.3 From 1eff9d322a444245c67515edb52bc0eb68374aa8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 5 Aug 2016 15:35:16 -0600 Subject: block: rename bio bi_rw to bi_opf Since commit 63a4cc24867d, bio->bi_rw contains flags in the lower portion and the op code in the higher portions. This means that old code that relies on manually setting bi_rw is most likely going to be broken. Instead of letting that brokeness linger, rename the member, to force old and out-of-tree code to break at compile time instead of at runtime. No intended functional changes in this commit. Signed-off-by: Jens Axboe --- Documentation/block/biodoc.txt | 4 ++-- Documentation/device-mapper/dm-flakey.txt | 2 +- block/bio-integrity.c | 2 +- block/bio.c | 6 +++--- block/blk-core.c | 26 +++++++++++++------------- block/blk-merge.c | 8 ++++---- block/blk-mq.c | 10 +++++----- block/blk-throttle.c | 8 ++++---- block/cfq-iosched.c | 4 ++-- drivers/block/drbd/drbd_main.c | 8 ++++---- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/drbd/drbd_req.c | 6 +++--- drivers/block/drbd/drbd_worker.c | 2 +- drivers/block/pktcdvd.c | 2 +- drivers/block/umem.c | 2 +- drivers/md/bcache/request.c | 12 ++++++------ drivers/md/bcache/super.c | 2 +- drivers/md/bcache/writeback.h | 2 +- drivers/md/dm-cache-target.c | 8 ++++---- drivers/md/dm-crypt.c | 4 ++-- drivers/md/dm-era-target.c | 2 +- drivers/md/dm-flakey.c | 6 +++--- drivers/md/dm-io.c | 6 +++--- drivers/md/dm-log-writes.c | 4 ++-- drivers/md/dm-mpath.c | 2 +- drivers/md/dm-raid1.c | 10 +++++----- drivers/md/dm-region-hash.c | 4 ++-- drivers/md/dm-snap.c | 6 +++--- drivers/md/dm-stripe.c | 4 ++-- drivers/md/dm-thin.c | 8 ++++---- drivers/md/dm-zero.c | 2 +- drivers/md/dm.c | 10 +++++----- drivers/md/linear.c | 2 +- drivers/md/md.c | 4 ++-- drivers/md/multipath.c | 8 ++++---- drivers/md/raid0.c | 2 +- drivers/md/raid1.c | 6 +++--- drivers/md/raid10.c | 8 ++++---- drivers/md/raid5-cache.c | 2 +- drivers/md/raid5.c | 20 ++++++++++---------- drivers/nvdimm/pmem.c | 4 ++-- fs/btrfs/check-integrity.c | 10 +++++----- fs/btrfs/disk-io.c | 2 +- fs/btrfs/inode.c | 6 +++--- fs/btrfs/volumes.c | 6 +++--- include/linux/bio.h | 4 ++-- include/linux/blk-cgroup.h | 4 ++-- include/linux/blk_types.h | 15 ++++++++------- include/trace/events/bcache.h | 8 ++++---- include/trace/events/block.h | 14 +++++++------- kernel/trace/blktrace.c | 6 +++--- 51 files changed, 158 insertions(+), 157 deletions(-) (limited to 'include/trace') diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 026d13362aca..bcdb2b4c1f12 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -269,7 +269,7 @@ Arjan's proposed request priority scheme allows higher levels some broad requests which haven't aged too much on the queue. Potentially this priority could even be exposed to applications in some manner, providing higher level tunability. Time based aging avoids starvation of lower priority - requests. Some bits in the bi_rw flags field in the bio structure are + requests. Some bits in the bi_opf flags field in the bio structure are intended to be used for this priority information. @@ -432,7 +432,7 @@ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; /* target device */ unsigned long bi_flags; /* status, command, etc */ - unsigned long bi_rw; /* low bits: r/w, high: priority */ + unsigned long bi_opf; /* low bits: r/w, high: priority */ unsigned int bi_vcnt; /* how may bio_vec's */ struct bvec_iter bi_iter; /* current index into bio_vec array */ diff --git a/Documentation/device-mapper/dm-flakey.txt b/Documentation/device-mapper/dm-flakey.txt index 6ff5c2327227..c43030718cef 100644 --- a/Documentation/device-mapper/dm-flakey.txt +++ b/Documentation/device-mapper/dm-flakey.txt @@ -42,7 +42,7 @@ Optional feature parameters: : Either 'r' to corrupt reads or 'w' to corrupt writes. 'w' is incompatible with drop_writes. : The value (from 0-255) to write. - : Perform the replacement only if bio->bi_rw has all the + : Perform the replacement only if bio->bi_opf has all the selected flags set. Examples: diff --git a/block/bio-integrity.c b/block/bio-integrity.c index f70cc3bdfd01..63f72f00c72e 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -86,7 +86,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, bip->bip_bio = bio; bio->bi_integrity = bip; - bio->bi_rw |= REQ_INTEGRITY; + bio->bi_opf |= REQ_INTEGRITY; return bip; err: diff --git a/block/bio.c b/block/bio.c index 3f76a38a5e2d..f39477538fef 100644 --- a/block/bio.c +++ b/block/bio.c @@ -580,7 +580,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) */ bio->bi_bdev = bio_src->bi_bdev; bio_set_flag(bio, BIO_CLONED); - bio->bi_rw = bio_src->bi_rw; + bio->bi_opf = bio_src->bi_opf; bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; @@ -663,7 +663,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, if (!bio) return NULL; bio->bi_bdev = bio_src->bi_bdev; - bio->bi_rw = bio_src->bi_rw; + bio->bi_opf = bio_src->bi_opf; bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; @@ -873,7 +873,7 @@ int submit_bio_wait(struct bio *bio) init_completion(&ret.event); bio->bi_private = &ret; bio->bi_end_io = submit_bio_wait_endio; - bio->bi_rw |= REQ_SYNC; + bio->bi_opf |= REQ_SYNC; submit_bio(bio); wait_for_completion_io(&ret.event); diff --git a/block/blk-core.c b/block/blk-core.c index a687e9cc16c2..999442ec4601 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1029,7 +1029,7 @@ static bool blk_rq_should_init_elevator(struct bio *bio) * Flush requests do not use the elevator so skip initialization. * This allows a request to share the flush and elevator data. */ - if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) + if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) return false; return true; @@ -1504,7 +1504,7 @@ EXPORT_SYMBOL_GPL(blk_add_request_payload); bool bio_attempt_back_merge(struct request_queue *q, struct request *req, struct bio *bio) { - const int ff = bio->bi_rw & REQ_FAILFAST_MASK; + const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_back_merge_fn(q, req, bio)) return false; @@ -1526,7 +1526,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req, bool bio_attempt_front_merge(struct request_queue *q, struct request *req, struct bio *bio) { - const int ff = bio->bi_rw & REQ_FAILFAST_MASK; + const int ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_front_merge_fn(q, req, bio)) return false; @@ -1648,8 +1648,8 @@ void init_request_from_bio(struct request *req, struct bio *bio) { req->cmd_type = REQ_TYPE_FS; - req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK; - if (bio->bi_rw & REQ_RAHEAD) + req->cmd_flags |= bio->bi_opf & REQ_COMMON_MASK; + if (bio->bi_opf & REQ_RAHEAD) req->cmd_flags |= REQ_FAILFAST_MASK; req->errors = 0; @@ -1660,7 +1660,7 @@ void init_request_from_bio(struct request *req, struct bio *bio) static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) { - const bool sync = !!(bio->bi_rw & REQ_SYNC); + const bool sync = !!(bio->bi_opf & REQ_SYNC); struct blk_plug *plug; int el_ret, rw_flags = 0, where = ELEVATOR_INSERT_SORT; struct request *req; @@ -1681,7 +1681,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; } - if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) { + if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) { spin_lock_irq(q->queue_lock); where = ELEVATOR_INSERT_FLUSH; goto get_rq; @@ -1728,7 +1728,7 @@ get_rq: /* * Add in META/PRIO flags, if set, before we get to the IO scheduler */ - rw_flags |= (bio->bi_rw & (REQ_META | REQ_PRIO)); + rw_flags |= (bio->bi_opf & (REQ_META | REQ_PRIO)); /* * Grab a free request. This is might sleep but can not fail. @@ -1805,7 +1805,7 @@ static void handle_bad_sector(struct bio *bio) printk(KERN_INFO "attempt to access beyond end of device\n"); printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n", bdevname(bio->bi_bdev, b), - bio->bi_rw, + bio->bi_opf, (unsigned long long)bio_end_sector(bio), (long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9)); } @@ -1918,9 +1918,9 @@ generic_make_request_checks(struct bio *bio) * drivers without flush support don't have to worry * about them. */ - if ((bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) && + if ((bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) && !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { - bio->bi_rw &= ~(REQ_PREFLUSH | REQ_FUA); + bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!nr_sectors) { err = 0; goto end_io; @@ -2219,7 +2219,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq) * one. */ for (bio = rq->bio; bio; bio = bio->bi_next) { - if ((bio->bi_rw & ff) != ff) + if ((bio->bi_opf & ff) != ff) break; bytes += bio->bi_iter.bi_size; } @@ -2630,7 +2630,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) /* mixed attributes always follow the first bio */ if (req->cmd_flags & REQ_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; - req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK; + req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } /* diff --git a/block/blk-merge.c b/block/blk-merge.c index 41cbd4878958..3eec75a9e91d 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -186,7 +186,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, if (split) { /* there isn't chance to merge the splitted bio */ - split->bi_rw |= REQ_NOMERGE; + split->bi_opf |= REQ_NOMERGE; bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); @@ -616,9 +616,9 @@ void blk_rq_set_mixed_merge(struct request *rq) * Distributes the attributs to each bio. */ for (bio = rq->bio; bio; bio = bio->bi_next) { - WARN_ON_ONCE((bio->bi_rw & REQ_FAILFAST_MASK) && - (bio->bi_rw & REQ_FAILFAST_MASK) != ff); - bio->bi_rw |= ff; + WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) && + (bio->bi_opf & REQ_FAILFAST_MASK) != ff); + bio->bi_opf |= ff; } rq->cmd_flags |= REQ_MIXED_MERGE; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 6a63da101bc4..e931a0e8e73d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1234,7 +1234,7 @@ static struct request *blk_mq_map_request(struct request_queue *q, ctx = blk_mq_get_ctx(q); hctx = q->mq_ops->map_queue(q, ctx->cpu); - if (rw_is_sync(bio_op(bio), bio->bi_rw)) + if (rw_is_sync(bio_op(bio), bio->bi_opf)) op_flags |= REQ_SYNC; trace_block_getrq(q, bio, op); @@ -1302,8 +1302,8 @@ static int blk_mq_direct_issue_request(struct request *rq, blk_qc_t *cookie) */ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { - const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw); - const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA); + const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf); + const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); struct blk_map_ctx data; struct request *rq; unsigned int request_count = 0; @@ -1396,8 +1396,8 @@ done: */ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) { - const int is_sync = rw_is_sync(bio_op(bio), bio->bi_rw); - const int is_flush_fua = bio->bi_rw & (REQ_PREFLUSH | REQ_FUA); + const int is_sync = rw_is_sync(bio_op(bio), bio->bi_opf); + const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); struct blk_plug *plug; unsigned int request_count = 0; struct blk_map_ctx data; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index c5494e403239..f1aba26f4719 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -821,8 +821,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) * second time when it eventually gets issued. Set it when a bio * is being charged to a tg. */ - if (!(bio->bi_rw & REQ_THROTTLED)) - bio->bi_rw |= REQ_THROTTLED; + if (!(bio->bi_opf & REQ_THROTTLED)) + bio->bi_opf |= REQ_THROTTLED; } /** @@ -1399,7 +1399,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, WARN_ON_ONCE(!rcu_read_lock_held()); /* see throtl_charge_bio() */ - if ((bio->bi_rw & REQ_THROTTLED) || !tg->has_rules[rw]) + if ((bio->bi_opf & REQ_THROTTLED) || !tg->has_rules[rw]) goto out; spin_lock_irq(q->queue_lock); @@ -1478,7 +1478,7 @@ out: * being issued. */ if (!throttled) - bio->bi_rw &= ~REQ_THROTTLED; + bio->bi_opf &= ~REQ_THROTTLED; return throttled; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index acabba198de9..cc2f6dbd4303 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -918,7 +918,7 @@ static inline struct cfq_data *cic_to_cfqd(struct cfq_io_cq *cic) */ static inline bool cfq_bio_sync(struct bio *bio) { - return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC); + return bio_data_dir(bio) == READ || (bio->bi_opf & REQ_SYNC); } /* @@ -2565,7 +2565,7 @@ static void cfq_merged_request(struct request_queue *q, struct request *req, static void cfq_bio_merged(struct request_queue *q, struct request *req, struct bio *bio) { - cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_rw); + cfqg_stats_update_io_merged(RQ_CFQG(req), bio_op(bio), bio->bi_opf); } static void diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 0501ae0c517b..100be556e613 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1663,13 +1663,13 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection, struct bio *bio) { if (connection->agreed_pro_version >= 95) - return (bio->bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) | - (bio->bi_rw & REQ_FUA ? DP_FUA : 0) | - (bio->bi_rw & REQ_PREFLUSH ? DP_FLUSH : 0) | + return (bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0) | + (bio->bi_opf & REQ_FUA ? DP_FUA : 0) | + (bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) | (bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) | (bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0); else - return bio->bi_rw & REQ_SYNC ? DP_RW_SYNC : 0; + return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0; } /* Used to send write or TRIM aka REQ_DISCARD requests diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index df45713dfbe8..942384f34e22 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1564,7 +1564,7 @@ static void drbd_issue_peer_wsame(struct drbd_device *device, * drbd_submit_peer_request() * @device: DRBD device. * @peer_req: peer request - * @rw: flag field, see bio->bi_rw + * @rw: flag field, see bio->bi_opf * * May spread the pages to multiple bios, * depending on bio_add_page restrictions. diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 66b8e4bb74d8..de279fe4e4fd 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -288,7 +288,7 @@ void drbd_req_complete(struct drbd_request *req, struct bio_and_error *m) */ if (!ok && bio_op(req->master_bio) == REQ_OP_READ && - !(req->master_bio->bi_rw & REQ_RAHEAD) && + !(req->master_bio->bi_opf & REQ_RAHEAD) && !list_empty(&req->tl_requests)) req->rq_state |= RQ_POSTPONED; @@ -1137,7 +1137,7 @@ static int drbd_process_write_request(struct drbd_request *req) * replicating, in which case there is no point. */ if (unlikely(req->i.size == 0)) { /* The only size==0 bios we expect are empty flushes. */ - D_ASSERT(device, req->master_bio->bi_rw & REQ_PREFLUSH); + D_ASSERT(device, req->master_bio->bi_opf & REQ_PREFLUSH); if (remote) _req_mod(req, QUEUE_AS_DRBD_BARRIER); return remote; @@ -1176,7 +1176,7 @@ drbd_submit_req_private_bio(struct drbd_request *req) if (bio_op(bio) != REQ_OP_READ) type = DRBD_FAULT_DT_WR; - else if (bio->bi_rw & REQ_RAHEAD) + else if (bio->bi_opf & REQ_RAHEAD) type = DRBD_FAULT_DT_RA; else type = DRBD_FAULT_DT_RD; diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 35dbb3dca47e..c6755c9a0aea 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -256,7 +256,7 @@ void drbd_request_endio(struct bio *bio) what = DISCARD_COMPLETED_WITH_ERROR; break; case REQ_OP_READ: - if (bio->bi_rw & REQ_RAHEAD) + if (bio->bi_opf & REQ_RAHEAD) what = READ_AHEAD_COMPLETED_WITH_ERROR; else what = READ_COMPLETED_WITH_ERROR; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 9393bc730acf..90fa4ac149db 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1157,7 +1157,7 @@ static int pkt_start_recovery(struct packet_data *pkt) bio_reset(pkt->bio); pkt->bio->bi_bdev = pd->bdev; - pkt->bio->bi_rw = REQ_WRITE; + bio_set_op_attrs(pkt->bio, REQ_OP_WRITE, 0); pkt->bio->bi_iter.bi_sector = new_sector; pkt->bio->bi_iter.bi_size = pkt->frames * CD_FRAMESIZE; pkt->bio->bi_vcnt = pkt->frames; diff --git a/drivers/block/umem.c b/drivers/block/umem.c index d0a3e6d4515f..be90e15854ed 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -535,7 +535,7 @@ static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio) *card->biotail = bio; bio->bi_next = NULL; card->biotail = &bio->bi_next; - if (bio->bi_rw & REQ_SYNC || !mm_check_plugged(card)) + if (bio->bi_opf & REQ_SYNC || !mm_check_plugged(card)) activate(card); spin_unlock_irq(&card->lock); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 69f16f43f8ab..4b177fe11ebb 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -208,7 +208,7 @@ static void bch_data_insert_start(struct closure *cl) * Journal writes are marked REQ_PREFLUSH; if the original write was a * flush, it'll wait on the journal write. */ - bio->bi_rw &= ~(REQ_PREFLUSH|REQ_FUA); + bio->bi_opf &= ~(REQ_PREFLUSH|REQ_FUA); do { unsigned i; @@ -405,7 +405,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) if (!congested && mode == CACHE_MODE_WRITEBACK && op_is_write(bio_op(bio)) && - (bio->bi_rw & REQ_SYNC)) + (bio->bi_opf & REQ_SYNC)) goto rescale; spin_lock(&dc->io_lock); @@ -668,7 +668,7 @@ static inline struct search *search_alloc(struct bio *bio, s->iop.write_prio = 0; s->iop.error = 0; s->iop.flags = 0; - s->iop.flush_journal = (bio->bi_rw & (REQ_PREFLUSH|REQ_FUA)) != 0; + s->iop.flush_journal = (bio->bi_opf & (REQ_PREFLUSH|REQ_FUA)) != 0; s->iop.wq = bcache_wq; return s; @@ -796,8 +796,8 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, goto out_submit; } - if (!(bio->bi_rw & REQ_RAHEAD) && - !(bio->bi_rw & REQ_META) && + if (!(bio->bi_opf & REQ_RAHEAD) && + !(bio->bi_opf & REQ_META) && s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA) reada = min_t(sector_t, dc->readahead >> 9, bdev_sectors(bio->bi_bdev) - bio_end_sector(bio)); @@ -920,7 +920,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s) bch_writeback_add(dc); s->iop.bio = bio; - if (bio->bi_rw & REQ_PREFLUSH) { + if (bio->bi_opf & REQ_PREFLUSH) { /* Also need to send a flush to the backing device */ struct bio *flush = bio_alloc_bioset(GFP_NOIO, 0, dc->disk.bio_split); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 88ef6d14cce3..95a4ca6ce6ff 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -347,7 +347,7 @@ static void uuid_io(struct cache_set *c, int op, unsigned long op_flags, for (i = 0; i < KEY_PTRS(k); i++) { struct bio *bio = bch_bbio_alloc(c); - bio->bi_rw = REQ_SYNC|REQ_META|op_flags; + bio->bi_opf = REQ_SYNC | REQ_META | op_flags; bio->bi_iter.bi_size = KEY_SIZE(k) << 9; bio->bi_end_io = uuid_endio; diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 073a042aed24..301eaf565167 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -57,7 +57,7 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, if (would_skip) return false; - return bio->bi_rw & REQ_SYNC || + return bio->bi_opf & REQ_SYNC || in_use <= CUTOFF_WRITEBACK; } diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 718744db62df..59b2c50562e4 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -788,7 +788,7 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) spin_lock_irqsave(&cache->lock, flags); if (cache->need_tick_bio && - !(bio->bi_rw & (REQ_FUA | REQ_PREFLUSH)) && + !(bio->bi_opf & (REQ_FUA | REQ_PREFLUSH)) && bio_op(bio) != REQ_OP_DISCARD) { pb->tick = true; cache->need_tick_bio = false; @@ -830,7 +830,7 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio) static int bio_triggers_commit(struct cache *cache, struct bio *bio) { - return bio->bi_rw & (REQ_PREFLUSH | REQ_FUA); + return bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); } /* @@ -1069,7 +1069,7 @@ static void dec_io_migrations(struct cache *cache) static bool discard_or_flush(struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || - bio->bi_rw & (REQ_PREFLUSH | REQ_FUA); + bio->bi_opf & (REQ_PREFLUSH | REQ_FUA); } static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell) @@ -1980,7 +1980,7 @@ static void process_deferred_bios(struct cache *cache) bio = bio_list_pop(&bios); - if (bio->bi_rw & REQ_PREFLUSH) + if (bio->bi_opf & REQ_PREFLUSH) process_flush_bio(cache, bio); else if (bio_op(bio) == REQ_OP_DISCARD) process_discard_bio(cache, &structs, bio); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 8f2e3e2ffd26..4e9784b4e0ac 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1136,7 +1136,7 @@ static void clone_init(struct dm_crypt_io *io, struct bio *clone) clone->bi_private = io; clone->bi_end_io = crypt_endio; clone->bi_bdev = cc->dev->bdev; - bio_set_op_attrs(clone, bio_op(io->base_bio), io->base_bio->bi_rw); + bio_set_op_attrs(clone, bio_op(io->base_bio), io->base_bio->bi_opf); } static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp) @@ -1915,7 +1915,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) * - for REQ_PREFLUSH device-mapper core ensures that no IO is in-flight * - for REQ_OP_DISCARD caller must use flush if IO ordering matters */ - if (unlikely(bio->bi_rw & REQ_PREFLUSH || + if (unlikely(bio->bi_opf & REQ_PREFLUSH || bio_op(bio) == REQ_OP_DISCARD)) { bio->bi_bdev = cc->dev->bdev; if (bio_sectors(bio)) diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 2faf49d8f4d7..bf2b2676cb8a 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1542,7 +1542,7 @@ static int era_map(struct dm_target *ti, struct bio *bio) /* * REQ_PREFLUSH bios carry no data, so we're not interested in them. */ - if (!(bio->bi_rw & REQ_PREFLUSH) && + if (!(bio->bi_opf & REQ_PREFLUSH) && (bio_data_dir(bio) == WRITE) && !metadata_current_marked(era->md, block)) { defer_bio(era, bio); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 19db13e99466..97e446d54a15 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -16,7 +16,7 @@ #define DM_MSG_PREFIX "flakey" #define all_corrupt_bio_flags_match(bio, fc) \ - (((bio)->bi_rw & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags) + (((bio)->bi_opf & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags) /* * Flakey: Used for testing only, simulates intermittent, @@ -266,9 +266,9 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc) data[fc->corrupt_bio_byte - 1] = fc->corrupt_bio_value; DMDEBUG("Corrupting data bio=%p by writing %u to byte %u " - "(rw=%c bi_rw=%u bi_sector=%llu cur_bytes=%u)\n", + "(rw=%c bi_opf=%u bi_sector=%llu cur_bytes=%u)\n", bio, fc->corrupt_bio_value, fc->corrupt_bio_byte, - (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_rw, + (bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf, (unsigned long long)bio->bi_iter.bi_sector, bio_bytes); } } diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index daa03e41654a..0bf1a12e35fe 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -505,9 +505,9 @@ static int dp_init(struct dm_io_request *io_req, struct dpages *dp, * New collapsed (a)synchronous interface. * * If the IO is asynchronous (i.e. it has notify.fn), you must either unplug - * the queue with blk_unplug() some time later or set REQ_SYNC in io_req->bi_rw. - * If you fail to do one of these, the IO will be submitted to the disk after - * q->unplug_delay, which defaults to 3ms in blk-settings.c. + * the queue with blk_unplug() some time later or set REQ_SYNC in + * io_req->bi_opf. If you fail to do one of these, the IO will be submitted to + * the disk after q->unplug_delay, which defaults to 3ms in blk-settings.c. */ int dm_io(struct dm_io_request *io_req, unsigned num_regions, struct dm_io_region *where, unsigned long *sync_error_bits) diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index b5dbf7a0515e..4ab68033f9d1 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -555,8 +555,8 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio) struct bio_vec bv; size_t alloc_size; int i = 0; - bool flush_bio = (bio->bi_rw & REQ_PREFLUSH); - bool fua_bio = (bio->bi_rw & REQ_FUA); + bool flush_bio = (bio->bi_opf & REQ_PREFLUSH); + bool fua_bio = (bio->bi_opf & REQ_FUA); bool discard_bio = (bio_op(bio) == REQ_OP_DISCARD); pb->block = NULL; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index d7107d23b897..ac734e5bbe48 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -661,7 +661,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m bio->bi_error = 0; bio->bi_bdev = pgpath->path.dev->bdev; - bio->bi_rw |= REQ_FAILFAST_TRANSPORT; + bio->bi_opf |= REQ_FAILFAST_TRANSPORT; if (pgpath->pg->ps.type->start_io) pgpath->pg->ps.type->start_io(&pgpath->pg->ps, diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index dac55b254a09..bdf1606f67bc 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -657,7 +657,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio) struct mirror *m; struct dm_io_request io_req = { .bi_op = REQ_OP_WRITE, - .bi_op_flags = bio->bi_rw & WRITE_FLUSH_FUA, + .bi_op_flags = bio->bi_opf & WRITE_FLUSH_FUA, .mem.type = DM_IO_BIO, .mem.ptr.bio = bio, .notify.fn = write_callback, @@ -704,7 +704,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes) bio_list_init(&requeue); while ((bio = bio_list_pop(writes))) { - if ((bio->bi_rw & REQ_PREFLUSH) || + if ((bio->bi_opf & REQ_PREFLUSH) || (bio_op(bio) == REQ_OP_DISCARD)) { bio_list_add(&sync, bio); continue; @@ -1217,7 +1217,7 @@ static int mirror_map(struct dm_target *ti, struct bio *bio) * If region is not in-sync queue the bio. */ if (!r || (r == -EWOULDBLOCK)) { - if (bio->bi_rw & REQ_RAHEAD) + if (bio->bi_opf & REQ_RAHEAD) return -EWOULDBLOCK; queue_bio(ms, bio, rw); @@ -1253,7 +1253,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) * We need to dec pending if this was a write. */ if (rw == WRITE) { - if (!(bio->bi_rw & REQ_PREFLUSH) && + if (!(bio->bi_opf & REQ_PREFLUSH) && bio_op(bio) != REQ_OP_DISCARD) dm_rh_dec(ms->rh, bio_record->write_region); return error; @@ -1262,7 +1262,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) if (error == -EOPNOTSUPP) goto out; - if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD)) + if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD)) goto out; if (unlikely(error)) { diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c index b11813431f31..85c32b22a420 100644 --- a/drivers/md/dm-region-hash.c +++ b/drivers/md/dm-region-hash.c @@ -398,7 +398,7 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio) region_t region = dm_rh_bio_to_region(rh, bio); int recovering = 0; - if (bio->bi_rw & REQ_PREFLUSH) { + if (bio->bi_opf & REQ_PREFLUSH) { rh->flush_failure = 1; return; } @@ -526,7 +526,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios) struct bio *bio; for (bio = bios->head; bio; bio = bio->bi_next) { - if (bio->bi_rw & REQ_PREFLUSH || bio_op(bio) == REQ_OP_DISCARD) + if (bio->bi_opf & REQ_PREFLUSH || bio_op(bio) == REQ_OP_DISCARD) continue; rh_inc(rh, dm_rh_bio_to_region(rh, bio)); } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index ce2a910709f7..c65feeada864 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -1680,7 +1680,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio) init_tracked_chunk(bio); - if (bio->bi_rw & REQ_PREFLUSH) { + if (bio->bi_opf & REQ_PREFLUSH) { bio->bi_bdev = s->cow->bdev; return DM_MAPIO_REMAPPED; } @@ -1800,7 +1800,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio) init_tracked_chunk(bio); - if (bio->bi_rw & REQ_PREFLUSH) { + if (bio->bi_opf & REQ_PREFLUSH) { if (!dm_bio_get_target_bio_nr(bio)) bio->bi_bdev = s->origin->bdev; else @@ -2286,7 +2286,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio) bio->bi_bdev = o->dev->bdev; - if (unlikely(bio->bi_rw & REQ_PREFLUSH)) + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) return DM_MAPIO_REMAPPED; if (bio_data_dir(bio) != WRITE) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 83f1d4667195..28193a57bf47 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -286,7 +286,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) uint32_t stripe; unsigned target_bio_nr; - if (bio->bi_rw & REQ_PREFLUSH) { + if (bio->bi_opf & REQ_PREFLUSH) { target_bio_nr = dm_bio_get_target_bio_nr(bio); BUG_ON(target_bio_nr >= sc->stripes); bio->bi_bdev = sc->stripe[target_bio_nr].dev->bdev; @@ -383,7 +383,7 @@ static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error) if (!error) return 0; /* I/O complete */ - if ((error == -EWOULDBLOCK) && (bio->bi_rw & REQ_RAHEAD)) + if ((error == -EWOULDBLOCK) && (bio->bi_opf & REQ_RAHEAD)) return error; if (error == -EOPNOTSUPP) diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 197ea2003400..d1c05c12a9db 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -699,7 +699,7 @@ static void remap_to_origin(struct thin_c *tc, struct bio *bio) static int bio_triggers_commit(struct thin_c *tc, struct bio *bio) { - return (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA)) && + return (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) && dm_thin_changed_this_transaction(tc->td); } @@ -870,7 +870,7 @@ static void __inc_remap_and_issue_cell(void *context, struct bio *bio; while ((bio = bio_list_pop(&cell->bios))) { - if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA) || + if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) || bio_op(bio) == REQ_OP_DISCARD) bio_list_add(&info->defer_bios, bio); else { @@ -1717,7 +1717,7 @@ static void __remap_and_issue_shared_cell(void *context, while ((bio = bio_list_pop(&cell->bios))) { if ((bio_data_dir(bio) == WRITE) || - (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA) || + (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) || bio_op(bio) == REQ_OP_DISCARD)) bio_list_add(&info->defer_bios, bio); else { @@ -2635,7 +2635,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } - if (bio->bi_rw & (REQ_PREFLUSH | REQ_FUA) || + if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) || bio_op(bio) == REQ_OP_DISCARD) { thin_defer_bio_with_throttle(tc, bio); return DM_MAPIO_SUBMITTED; diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index 618b8752dcf1..b616f11d8473 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -37,7 +37,7 @@ static int zero_map(struct dm_target *ti, struct bio *bio) { switch (bio_op(bio)) { case REQ_OP_READ: - if (bio->bi_rw & REQ_RAHEAD) { + if (bio->bi_opf & REQ_RAHEAD) { /* readahead of null bytes only wastes buffer cache */ return -EIO; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index dfa09e14e847..fa9b1cb4438a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -798,12 +798,12 @@ static void dec_pending(struct dm_io *io, int error) if (io_error == DM_ENDIO_REQUEUE) return; - if ((bio->bi_rw & REQ_PREFLUSH) && bio->bi_iter.bi_size) { + if ((bio->bi_opf & REQ_PREFLUSH) && bio->bi_iter.bi_size) { /* * Preflush done for flush with data, reissue * without REQ_PREFLUSH. */ - bio->bi_rw &= ~REQ_PREFLUSH; + bio->bi_opf &= ~REQ_PREFLUSH; queue_io(md, bio); } else { /* done with normal IO or empty flush */ @@ -964,7 +964,7 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) { struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT; - BUG_ON(bio->bi_rw & REQ_PREFLUSH); + BUG_ON(bio->bi_opf & REQ_PREFLUSH); BUG_ON(bi_size > *tio->len_ptr); BUG_ON(n_sectors > bi_size); *tio->len_ptr -= bi_size - n_sectors; @@ -1252,7 +1252,7 @@ static void __split_and_process_bio(struct mapped_device *md, start_io_acct(ci.io); - if (bio->bi_rw & REQ_PREFLUSH) { + if (bio->bi_opf & REQ_PREFLUSH) { ci.bio = &ci.md->flush_bio; ci.sector_count = 0; error = __send_empty_flush(&ci); @@ -1290,7 +1290,7 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio) if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) { dm_put_live_table(md, srcu_idx); - if (!(bio->bi_rw & REQ_RAHEAD)) + if (!(bio->bi_opf & REQ_RAHEAD)) queue_io(md, bio); else bio_io_error(bio); diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 70ff888d25d0..86f5d435901d 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -221,7 +221,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio) struct bio *split; sector_t start_sector, end_sector, data_offset; - if (unlikely(bio->bi_rw & REQ_PREFLUSH)) { + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { md_flush_request(mddev, bio); return; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 2c3ab6f5e6be..d646f6e444f0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -285,7 +285,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) */ sectors = bio_sectors(bio); /* bio could be mergeable after passing to underlayer */ - bio->bi_rw &= ~REQ_NOMERGE; + bio->bi_opf &= ~REQ_NOMERGE; mddev->pers->make_request(mddev, bio); cpu = part_stat_lock(); @@ -414,7 +414,7 @@ static void md_submit_flush_data(struct work_struct *ws) /* an empty barrier - all done */ bio_endio(bio); else { - bio->bi_rw &= ~REQ_PREFLUSH; + bio->bi_opf &= ~REQ_PREFLUSH; mddev->pers->make_request(mddev, bio); } diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 4974682842ae..673efbd6fc47 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -91,7 +91,7 @@ static void multipath_end_request(struct bio *bio) if (!bio->bi_error) multipath_end_bh_io(mp_bh, 0); - else if (!(bio->bi_rw & REQ_RAHEAD)) { + else if (!(bio->bi_opf & REQ_RAHEAD)) { /* * oops, IO error: */ @@ -112,7 +112,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio) struct multipath_bh * mp_bh; struct multipath_info *multipath; - if (unlikely(bio->bi_rw & REQ_PREFLUSH)) { + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { md_flush_request(mddev, bio); return; } @@ -135,7 +135,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio) mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset; mp_bh->bio.bi_bdev = multipath->rdev->bdev; - mp_bh->bio.bi_rw |= REQ_FAILFAST_TRANSPORT; + mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT; mp_bh->bio.bi_end_io = multipath_end_request; mp_bh->bio.bi_private = mp_bh; generic_make_request(&mp_bh->bio); @@ -360,7 +360,7 @@ static void multipathd(struct md_thread *thread) bio->bi_iter.bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset; bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev; - bio->bi_rw |= REQ_FAILFAST_TRANSPORT; + bio->bi_opf |= REQ_FAILFAST_TRANSPORT; bio->bi_end_io = multipath_end_request; bio->bi_private = mp_bh; generic_make_request(bio); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index c3d439083212..258986a2699d 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -458,7 +458,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio) struct md_rdev *tmp_dev; struct bio *split; - if (unlikely(bio->bi_rw & REQ_PREFLUSH)) { + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { md_flush_request(mddev, bio); return; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 46168ef2e279..21dc00eb1989 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1043,8 +1043,8 @@ static void raid1_make_request(struct mddev *mddev, struct bio * bio) unsigned long flags; const int op = bio_op(bio); const int rw = bio_data_dir(bio); - const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); - const unsigned long do_flush_fua = (bio->bi_rw & + const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); + const unsigned long do_flush_fua = (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)); struct md_rdev *blocked_rdev; struct blk_plug_cb *cb; @@ -2318,7 +2318,7 @@ read_more: raid_end_bio_io(r1_bio); } else { const unsigned long do_sync - = r1_bio->master_bio->bi_rw & REQ_SYNC; + = r1_bio->master_bio->bi_opf & REQ_SYNC; if (bio) { r1_bio->bios[r1_bio->read_disk] = mddev->ro ? IO_BLOCKED : NULL; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index ed29fc899f06..0e4efcd10795 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1054,8 +1054,8 @@ static void __make_request(struct mddev *mddev, struct bio *bio) int i; const int op = bio_op(bio); const int rw = bio_data_dir(bio); - const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); - const unsigned long do_fua = (bio->bi_rw & REQ_FUA); + const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); + const unsigned long do_fua = (bio->bi_opf & REQ_FUA); unsigned long flags; struct md_rdev *blocked_rdev; struct blk_plug_cb *cb; @@ -1440,7 +1440,7 @@ static void raid10_make_request(struct mddev *mddev, struct bio *bio) struct bio *split; - if (unlikely(bio->bi_rw & REQ_PREFLUSH)) { + if (unlikely(bio->bi_opf & REQ_PREFLUSH)) { md_flush_request(mddev, bio); return; } @@ -2533,7 +2533,7 @@ read_more: return; } - do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC); + do_sync = (r10_bio->master_bio->bi_opf & REQ_SYNC); slot = r10_bio->read_slot; printk_ratelimited( KERN_ERR diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 5504ce2bac06..51f76ddbe265 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -536,7 +536,7 @@ int r5l_handle_flush_request(struct r5l_log *log, struct bio *bio) bio_endio(bio); return 0; } - bio->bi_rw &= ~REQ_PREFLUSH; + bio->bi_opf &= ~REQ_PREFLUSH; return -EAGAIN; } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index d189e894b921..8912407a4dd0 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -806,7 +806,7 @@ static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh dd_idx = 0; while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx) dd_idx++; - if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw || + if (head->dev[dd_idx].towrite->bi_opf != sh->dev[dd_idx].towrite->bi_opf || bio_op(head->dev[dd_idx].towrite) != bio_op(sh->dev[dd_idx].towrite)) goto unlock_out; @@ -1003,7 +1003,7 @@ again: pr_debug("%s: for %llu schedule op %d on disc %d\n", __func__, (unsigned long long)sh->sector, - bi->bi_rw, i); + bi->bi_opf, i); atomic_inc(&sh->count); if (sh != head_sh) atomic_inc(&head_sh->count); @@ -1014,7 +1014,7 @@ again: bi->bi_iter.bi_sector = (sh->sector + rdev->data_offset); if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags)) - bi->bi_rw |= REQ_NOMERGE; + bi->bi_opf |= REQ_NOMERGE; if (test_bit(R5_SkipCopy, &sh->dev[i].flags)) WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags)); @@ -1055,7 +1055,7 @@ again: pr_debug("%s: for %llu schedule op %d on " "replacement disc %d\n", __func__, (unsigned long long)sh->sector, - rbi->bi_rw, i); + rbi->bi_opf, i); atomic_inc(&sh->count); if (sh != head_sh) atomic_inc(&head_sh->count); @@ -1088,7 +1088,7 @@ again: if (op_is_write(op)) set_bit(STRIPE_DEGRADED, &sh->state); pr_debug("skip op %d on disc %d for sector %llu\n", - bi->bi_rw, i, (unsigned long long)sh->sector); + bi->bi_opf, i, (unsigned long long)sh->sector); clear_bit(R5_LOCKED, &sh->dev[i].flags); set_bit(STRIPE_HANDLE, &sh->state); } @@ -1619,9 +1619,9 @@ again: while (wbi && wbi->bi_iter.bi_sector < dev->sector + STRIPE_SECTORS) { - if (wbi->bi_rw & REQ_FUA) + if (wbi->bi_opf & REQ_FUA) set_bit(R5_WantFUA, &dev->flags); - if (wbi->bi_rw & REQ_SYNC) + if (wbi->bi_opf & REQ_SYNC) set_bit(R5_SyncIO, &dev->flags); if (bio_op(wbi) == REQ_OP_DISCARD) set_bit(R5_Discard, &dev->flags); @@ -5154,7 +5154,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi) DEFINE_WAIT(w); bool do_prepare; - if (unlikely(bi->bi_rw & REQ_PREFLUSH)) { + if (unlikely(bi->bi_opf & REQ_PREFLUSH)) { int ret = r5l_handle_flush_request(conf->log, bi); if (ret == 0) @@ -5237,7 +5237,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi) (unsigned long long)logical_sector); sh = raid5_get_active_stripe(conf, new_sector, previous, - (bi->bi_rw & REQ_RAHEAD), 0); + (bi->bi_opf & REQ_RAHEAD), 0); if (sh) { if (unlikely(previous)) { /* expansion might have moved on while waiting for a @@ -5305,7 +5305,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi) set_bit(STRIPE_HANDLE, &sh->state); clear_bit(STRIPE_DELAYED, &sh->state); if ((!sh->batch_head || sh == sh->batch_head) && - (bi->bi_rw & REQ_SYNC) && + (bi->bi_opf & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); release_stripe_plug(mddev, sh); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 20bae50c231d..571a6c7ee2fc 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -128,7 +128,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) struct pmem_device *pmem = q->queuedata; struct nd_region *nd_region = to_region(pmem); - if (bio->bi_rw & REQ_FLUSH) + if (bio->bi_opf & REQ_FLUSH) nvdimm_flush(nd_region); do_acct = nd_iostat_start(bio, &start); @@ -144,7 +144,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio) if (do_acct) nd_iostat_end(bio, start); - if (bio->bi_rw & REQ_FUA) + if (bio->bi_opf & REQ_FUA) nvdimm_flush(nd_region); bio_endio(bio); diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index 5d5cae05818d..66789471b49d 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -2945,7 +2945,7 @@ static void __btrfsic_submit_bio(struct bio *bio) printk(KERN_INFO "submit_bio(rw=%d,0x%x, bi_vcnt=%u," " bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", - bio_op(bio), bio->bi_rw, bio->bi_vcnt, + bio_op(bio), bio->bi_opf, bio->bi_vcnt, (unsigned long long)bio->bi_iter.bi_sector, dev_bytenr, bio->bi_bdev); @@ -2976,18 +2976,18 @@ static void __btrfsic_submit_bio(struct bio *bio) btrfsic_process_written_block(dev_state, dev_bytenr, mapped_datav, bio->bi_vcnt, bio, &bio_is_patched, - NULL, bio->bi_rw); + NULL, bio->bi_opf); while (i > 0) { i--; kunmap(bio->bi_io_vec[i].bv_page); } kfree(mapped_datav); - } else if (NULL != dev_state && (bio->bi_rw & REQ_PREFLUSH)) { + } else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) { if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) printk(KERN_INFO "submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n", - bio_op(bio), bio->bi_rw, bio->bi_bdev); + bio_op(bio), bio->bi_opf, bio->bi_bdev); if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { if ((dev_state->state->print_mask & (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | @@ -3005,7 +3005,7 @@ static void __btrfsic_submit_bio(struct bio *bio) block->never_written = 0; block->iodone_w_error = 0; block->flush_gen = dev_state->last_flush_gen + 1; - block->submit_bio_bh_rw = bio->bi_rw; + block->submit_bio_bh_rw = bio->bi_opf; block->orig_bio_bh_private = bio->bi_private; block->orig_bio_bh_end_io.bio = bio->bi_end_io; block->next_in_same_bio = NULL; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 87dad552e39a..59febfb8d04a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -870,7 +870,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, atomic_inc(&fs_info->nr_async_submits); - if (bio->bi_rw & REQ_SYNC) + if (bio->bi_opf & REQ_SYNC) btrfs_set_work_high_priority(&async->work); btrfs_queue_work(fs_info->workers, &async->work); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b0f421f332ae..2f5975954ccf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8209,7 +8209,7 @@ static void btrfs_end_dio_bio(struct bio *bio) if (err) btrfs_warn(BTRFS_I(dip->inode)->root->fs_info, "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d", - btrfs_ino(dip->inode), bio_op(bio), bio->bi_rw, + btrfs_ino(dip->inode), bio_op(bio), bio->bi_opf, (unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size, err); @@ -8373,7 +8373,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, if (!bio) return -ENOMEM; - bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw); + bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_opf); bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; @@ -8411,7 +8411,7 @@ next_block: start_sector, GFP_NOFS); if (!bio) goto out_err; - bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw); + bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_opf); bio->bi_private = dip; bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bb0addce7558..51f125508771 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6012,7 +6012,7 @@ static void btrfs_end_bio(struct bio *bio) else btrfs_dev_stat_inc(dev, BTRFS_DEV_STAT_READ_ERRS); - if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) + if ((bio->bi_opf & WRITE_FLUSH) == WRITE_FLUSH) btrfs_dev_stat_inc(dev, BTRFS_DEV_STAT_FLUSH_ERRS); btrfs_dev_stat_print_on_error(dev); @@ -6089,7 +6089,7 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root, bio->bi_next = NULL; spin_lock(&device->io_lock); - if (bio->bi_rw & REQ_SYNC) + if (bio->bi_opf & REQ_SYNC) pending_bios = &device->pending_sync_bios; else pending_bios = &device->pending_bios; @@ -6127,7 +6127,7 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio, rcu_read_lock(); name = rcu_dereference(dev->name); pr_debug("btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu " - "(%s id %llu), size=%u\n", bio_op(bio), bio->bi_rw, + "(%s id %llu), size=%u\n", bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector, (u_long)dev->bdev->bd_dev, name->str, dev->devid, bio->bi_iter.bi_size); rcu_read_unlock(); diff --git a/include/linux/bio.h b/include/linux/bio.h index e09a8895fc31..59ffaa68b11b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -95,7 +95,7 @@ static inline bool bio_is_rw(struct bio *bio) static inline bool bio_mergeable(struct bio *bio) { - if (bio->bi_rw & REQ_NOMERGE_FLAGS) + if (bio->bi_opf & REQ_NOMERGE_FLAGS) return false; return true; @@ -318,7 +318,7 @@ struct bio_integrity_payload { static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { - if (bio->bi_rw & REQ_INTEGRITY) + if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f77150a4a96a..10648e300c93 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -714,9 +714,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, if (!throtl) { blkg = blkg ?: q->root_blkg; - blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_rw, + blkg_rwstat_add(&blkg->stat_bytes, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_rw, 1); + blkg_rwstat_add(&blkg->stat_ios, bio_op(bio), bio->bi_opf, 1); } rcu_read_unlock(); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f254eb264924..436f43f87da9 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -27,8 +27,9 @@ struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; int bi_error; - unsigned int bi_rw; /* bottom bits req flags, - * top bits REQ_OP + unsigned int bi_opf; /* bottom bits req flags, + * top bits REQ_OP. Use + * accessors. */ unsigned short bi_flags; /* status, command, etc */ unsigned short bi_ioprio; @@ -89,13 +90,13 @@ struct bio { }; #define BIO_OP_SHIFT (8 * sizeof(unsigned int) - REQ_OP_BITS) -#define bio_op(bio) ((bio)->bi_rw >> BIO_OP_SHIFT) +#define bio_op(bio) ((bio)->bi_opf >> BIO_OP_SHIFT) #define bio_set_op_attrs(bio, op, op_flags) do { \ WARN_ON(op >= (1 << REQ_OP_BITS)); \ - (bio)->bi_rw &= ((1 << BIO_OP_SHIFT) - 1); \ - (bio)->bi_rw |= ((unsigned int) (op) << BIO_OP_SHIFT); \ - (bio)->bi_rw |= op_flags; \ + (bio)->bi_opf &= ((1 << BIO_OP_SHIFT) - 1); \ + (bio)->bi_opf |= ((unsigned int) (op) << BIO_OP_SHIFT); \ + (bio)->bi_opf |= op_flags; \ } while (0) #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) @@ -138,7 +139,7 @@ struct bio { /* * Request flags. For use in the cmd_flags field of struct request, and in - * bi_rw of struct bio. Note that some flags are only valid in either one. + * bi_opf of struct bio. Note that some flags are only valid in either one. */ enum rq_flag_bits { /* common flags */ diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h index 65673d8b81ac..d336b890e31f 100644 --- a/include/trace/events/bcache.h +++ b/include/trace/events/bcache.h @@ -27,7 +27,7 @@ DECLARE_EVENT_CLASS(bcache_request, __entry->sector = bio->bi_iter.bi_sector; __entry->orig_sector = bio->bi_iter.bi_sector - 16; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), @@ -102,7 +102,7 @@ DECLARE_EVENT_CLASS(bcache_bio, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), @@ -138,7 +138,7 @@ TRACE_EVENT(bcache_read, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); __entry->cache_hit = hit; __entry->bypass = bypass; @@ -170,7 +170,7 @@ TRACE_EVENT(bcache_write, __entry->inode = inode; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio->bi_iter.bi_size >> 9; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); __entry->writeback = writeback; __entry->bypass = bypass; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 5a2a7592068f..8f3a163b8166 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -274,7 +274,7 @@ TRACE_EVENT(block_bio_bounce, bio->bi_bdev->bd_dev : 0; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -313,7 +313,7 @@ TRACE_EVENT(block_bio_complete, __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); __entry->error = error; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), @@ -341,7 +341,7 @@ DECLARE_EVENT_CLASS(block_bio_merge, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -409,7 +409,7 @@ TRACE_EVENT(block_bio_queue, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->nr_sector = bio_sectors(bio); - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -439,7 +439,7 @@ DECLARE_EVENT_CLASS(block_get_rq, __entry->sector = bio ? bio->bi_iter.bi_sector : 0; __entry->nr_sector = bio ? bio_sectors(bio) : 0; blk_fill_rwbs(__entry->rwbs, bio ? bio_op(bio) : 0, - bio ? bio->bi_rw : 0, __entry->nr_sector); + bio ? bio->bi_opf : 0, __entry->nr_sector); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -573,7 +573,7 @@ TRACE_EVENT(block_split, __entry->dev = bio->bi_bdev->bd_dev; __entry->sector = bio->bi_iter.bi_sector; __entry->new_sector = new_sector; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); memcpy(__entry->comm, current->comm, TASK_COMM_LEN); ), @@ -617,7 +617,7 @@ TRACE_EVENT(block_bio_remap, __entry->nr_sector = bio_sectors(bio); __entry->old_dev = dev; __entry->old_sector = from; - blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_rw, + blk_fill_rwbs(__entry->rwbs, bio_op(bio), bio->bi_opf, bio->bi_iter.bi_size); ), diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fb345cd11883..7598e6ca817a 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -776,7 +776,7 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, return; __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_rw, what, error, 0, NULL); + bio_op(bio), bio->bi_opf, what, error, 0, NULL); } static void blk_add_trace_bio_bounce(void *ignore, @@ -881,7 +881,7 @@ static void blk_add_trace_split(void *ignore, __be64 rpdu = cpu_to_be64(pdu); __blk_add_trace(bt, bio->bi_iter.bi_sector, - bio->bi_iter.bi_size, bio_op(bio), bio->bi_rw, + bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_SPLIT, bio->bi_error, sizeof(rpdu), &rpdu); } @@ -915,7 +915,7 @@ static void blk_add_trace_bio_remap(void *ignore, r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, - bio_op(bio), bio->bi_rw, BLK_TA_REMAP, bio->bi_error, + bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_error, sizeof(r), &r); } -- cgit v1.2.3 From c87edb36118664f1fa275107c1138b6f47793240 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 5 Aug 2016 12:41:52 -0400 Subject: tracing: Fix tick_stop tracepoint symbols for user export The symbols used in the tick_stop tracepoint were not being converted properly into integers in the trace_stop format file. Instead we had this: print fmt: "success=%d dependency=%s", REC->success, __print_symbolic(REC->dependency, { 0, "NONE" }, { (1 << TICK_DEP_BIT_POSIX_TIMER), "POSIX_TIMER" }, { (1 << TICK_DEP_BIT_PERF_EVENTS), "PERF_EVENTS" }, { (1 << TICK_DEP_BIT_SCHED), "SCHED" }, { (1 << TICK_DEP_BIT_CLOCK_UNSTABLE), "CLOCK_UNSTABLE" }) User space tools have no idea how to parse "TICK_DEP_BIT_SCHED" or the other symbols used to do the bit shifting. The reason is that the conversion was done with using the TICK_DEP_MASK_* symbols which are just macros that convert to the BIT shift itself (with the exception of NONE, which was converted properly, because it doesn't use bits, and is defined as zero). The TICK_DEP_BIT_* needs to be denoted by TRACE_DEFINE_ENUM() in order to have this properly converted for user space tools to parse this event. Cc: stable@vger.kernel.org Cc: Frederic Weisbecker Fixes: e6e6cc22e067 ("nohz: Use enum code for tick stop failure tracing message") Reported-by: Luiz Capitulino Tested-by: Luiz Capitulino Signed-off-by: Steven Rostedt --- include/trace/events/timer.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 51440131d337..28c5da6fdfac 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -330,24 +330,32 @@ TRACE_EVENT(itimer_expire, #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ - tick_dep_name(NONE) \ + tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name_end(CLOCK_UNSTABLE) #undef tick_dep_name +#undef tick_dep_mask_name #undef tick_dep_name_end -#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); -#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +/* The MASK will convert to their bits and they need to be processed too */ +#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ + TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ + TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +/* NONE only has a mask defined for it */ +#define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name +#undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, +#define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ -- cgit v1.2.3