From 408cc4e97a3ccd172d2d676e4b585badf439271b Mon Sep 17 00:00:00 2001 From: Mark Tinguely Date: Thu, 20 Sep 2012 13:16:45 -0500 Subject: xfs: zero allocation_args on the kernel stack Zero the kernel stack space that makes up the xfs_alloc_arg structures. Signed-off-by: Mark Tinguely Reviewed-by: Ben Myers Signed-off-by: Ben Myers --- fs/xfs/xfs_alloc.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/xfs/xfs_alloc.c') diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 4f33c32affe3..0287f3b1b503 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1866,6 +1866,7 @@ xfs_alloc_fix_freelist( /* * Initialize the args structure. */ + memset(&targs, 0, sizeof(targs)); targs.tp = tp; targs.mp = mp; targs.agbp = agbp; -- cgit v1.2.3 From 326c03555b914ff153ba5b40df87fd6e28e7e367 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 5 Oct 2012 11:06:58 +1000 Subject: xfs: introduce XFS_BMAPI_STACK_SWITCH Certain allocation paths through xfs_bmapi_write() are in situations where we have limited stack available. These are almost always in the buffered IO writeback path when convertion delayed allocation extents to real extents. The current stack switch occurs for userdata allocations, which means we also do stack switches for preallocation, direct IO and unwritten extent conversion, even those these call chains have never been implicated in a stack overrun. Hence, let's target just the single stack overun offended for stack switches. To do that, introduce a XFS_BMAPI_STACK_SWITCH flag that the caller can pass xfs_bmapi_write() to indicate it should switch stacks if it needs to do allocation. Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers --- fs/xfs/xfs_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/xfs/xfs_alloc.c') diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 0287f3b1b503..43f791bcd8b1 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -2447,7 +2447,7 @@ xfs_alloc_vextent( { DECLARE_COMPLETION_ONSTACK(done); - if (!args->userdata) + if (!args->stack_switch) return __xfs_alloc_vextent(args); -- cgit v1.2.3 From 1f3c785c3adb7d2b109ec7c8f10081d1294b03d3 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 5 Oct 2012 11:06:59 +1000 Subject: xfs: move allocation stack switch up to xfs_bmapi_allocate Switching stacks are xfs_alloc_vextent can cause deadlocks when we run out of worker threads on the allocation workqueue. This can occur because xfs_bmap_btalloc can make multiple calls to xfs_alloc_vextent() and even if xfs_alloc_vextent() fails it can return with the AGF locked in the current allocation transaction. If we then need to make another allocation, and all the allocation worker contexts are exhausted because the are blocked waiting for the AGF lock, holder of the AGF cannot get it's xfs-alloc_vextent work completed to release the AGF. Hence allocation effectively deadlocks. To avoid this, move the stack switch one layer up to xfs_bmapi_allocate() so that all of the allocation attempts in a single switched stack transaction occur in a single worker context. This avoids the problem of an allocation being blocked waiting for a worker thread whilst holding the AGF. Signed-off-by: Dave Chinner Reviewed-by: Mark Tinguely Signed-off-by: Ben Myers --- fs/xfs/xfs_alloc.c | 42 +----------------------------------------- 1 file changed, 1 insertion(+), 41 deletions(-) (limited to 'fs/xfs/xfs_alloc.c') diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 43f791bcd8b1..335206a9c698 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -2208,7 +2208,7 @@ xfs_alloc_read_agf( * group or loop over the allocation groups to find the result. */ int /* error */ -__xfs_alloc_vextent( +xfs_alloc_vextent( xfs_alloc_arg_t *args) /* allocation argument structure */ { xfs_agblock_t agsize; /* allocation group size */ @@ -2418,46 +2418,6 @@ error0: return error; } -static void -xfs_alloc_vextent_worker( - struct work_struct *work) -{ - struct xfs_alloc_arg *args = container_of(work, - struct xfs_alloc_arg, work); - unsigned long pflags; - - /* we are in a transaction context here */ - current_set_flags_nested(&pflags, PF_FSTRANS); - - args->result = __xfs_alloc_vextent(args); - complete(args->done); - - current_restore_flags_nested(&pflags, PF_FSTRANS); -} - -/* - * Data allocation requests often come in with little stack to work on. Push - * them off to a worker thread so there is lots of stack to use. Metadata - * requests, OTOH, are generally from low stack usage paths, so avoid the - * context switch overhead here. - */ -int -xfs_alloc_vextent( - struct xfs_alloc_arg *args) -{ - DECLARE_COMPLETION_ONSTACK(done); - - if (!args->stack_switch) - return __xfs_alloc_vextent(args); - - - args->done = &done; - INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); - queue_work(xfs_alloc_wq, &args->work); - wait_for_completion(&done); - return args->result; -} - /* * Free an extent. * Just break up the extent address and hand off to xfs_free_ag_extent -- cgit v1.2.3