From f2cc020d7876de7583feb52ec939a32419cf9468 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 23 Mar 2021 18:49:35 +0100 Subject: tracing: Fix various typos in comments Fix ~59 single-word typos in the tracing code comments, and fix the grammar in a handful of places. Link: https://lore.kernel.org/r/20210322224546.GA1981273@gmail.com Link: https://lkml.kernel.org/r/20210323174935.GA4176821@gmail.com Reviewed-by: Randy Dunlap Signed-off-by: Ingo Molnar Signed-off-by: Steven Rostedt (VMware) --- include/trace/events/io_uring.h | 2 +- include/trace/events/rcu.h | 2 +- include/trace/events/sched.h | 2 +- include/trace/events/timer.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 9f0d3b7d56b0..ba78a5602cd1 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -49,7 +49,7 @@ TRACE_EVENT(io_uring_create, ); /** - * io_uring_register - called after a buffer/file/eventfd was succesfully + * io_uring_register - called after a buffer/file/eventfd was successfully * registered for a ring * * @ctx: pointer to a ring context structure diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5fc29400e1a2..97177c10bf64 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -48,7 +48,7 @@ TRACE_EVENT(rcu_utilization, * RCU flavor, the grace-period number, and a string identifying the * grace-period-related event as follows: * - * "AccReadyCB": CPU acclerates new callbacks to RCU_NEXT_READY_TAIL. + * "AccReadyCB": CPU accelerates new callbacks to RCU_NEXT_READY_TAIL. * "AccWaitCB": CPU accelerates new callbacks to RCU_WAIT_TAIL. * "newreq": Request a new grace period. * "start": Start a grace period. diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index cbe3e152d24c..1eca2305ca42 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -174,7 +174,7 @@ DEFINE_EVENT(sched_wakeup_template, sched_waking, TP_ARGS(p)); /* - * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG. + * Tracepoint called when the task is actually woken; p->state == TASK_RUNNING. * It is not always called from the waking context. */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup, diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 19abb6c3eb73..6ad031c71be7 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -119,7 +119,7 @@ TRACE_EVENT(timer_expire_entry, * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * - * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might + * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, -- cgit v1.2.3 From e936a5970ef596ff48fca72aa8200955753c543f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 31 Mar 2021 13:22:27 -0400 Subject: SUNRPC: Add tracepoint that fires when an RPC is retransmitted A separate tracepoint can be left enabled all the time to capture rare but important retransmission events. So for example: kworker/u26:3-568 [009] 156.967933: xprt_retransmit: task:44093@5 xid=0xa25dbc79 nfsv3 WRITE ntrans=2 Or, for example, enable all nfs and nfs4 tracepoints, and set up a trigger to disable tracing when xprt_retransmit fires to capture everything that leads up to it. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/sunrpc.h | 40 ++++++++++++++++++++++++++++++++++++++++ net/sunrpc/xprt.c | 4 +++- 2 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 036eb1f5c133..430b42f2351f 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1079,6 +1079,46 @@ TRACE_EVENT(xprt_transmit, __entry->seqno, __entry->status) ); +TRACE_EVENT(xprt_retransmit, + TP_PROTO( + const struct rpc_rqst *rqst + ), + + TP_ARGS(rqst), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, xid) + __field(int, ntrans) + __field(int, version) + __string(progname, + rqst->rq_task->tk_client->cl_program->name) + __string(procedure, + rqst->rq_task->tk_msg.rpc_proc->p_name) + ), + + TP_fast_assign( + struct rpc_task *task = rqst->rq_task; + + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client ? + task->tk_client->cl_clid : -1; + __entry->xid = be32_to_cpu(rqst->rq_xid); + __entry->ntrans = rqst->rq_ntrans; + __assign_str(progname, + task->tk_client->cl_program->name) + __entry->version = task->tk_client->cl_vers; + __assign_str(procedure, task->tk_msg.rpc_proc->p_name) + ), + + TP_printk( + "task:%u@%u xid=0x%08x %sv%d %s ntrans=%d", + __entry->task_id, __entry->client_id, __entry->xid, + __get_str(progname), __entry->version, __get_str(procedure), + __entry->ntrans) +); + TRACE_EVENT(xprt_ping, TP_PROTO(const struct rpc_xprt *xprt, int status), diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 80c94ead4aa0..67039ee443eb 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1542,8 +1542,10 @@ xprt_request_transmit(struct rpc_rqst *req, struct rpc_task *snd_task) return status; } - if (is_retrans) + if (is_retrans) { task->tk_client->cl_stats->rpcretrans++; + trace_xprt_retransmit(req); + } xprt_inject_disconnect(xprt); -- cgit v1.2.3 From 6cf23783f750634e10daeede48b0f5f5d64ebf3a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 31 Mar 2021 16:03:08 -0400 Subject: SUNRPC: Remove trace_xprt_transmit_queued This tracepoint can crash when dereferencing snd_task because when some transports connect, they put a cookie in that field instead of a pointer to an rpc_task. BUG: KASAN: use-after-free in trace_event_raw_event_xprt_writelock_event+0x141/0x18e [sunrpc] Read of size 2 at addr ffff8881a83bd3a0 by task git/331872 CPU: 11 PID: 331872 Comm: git Tainted: G S 5.12.0-rc2-00007-g3ab6e585a7f9 #1453 Hardware name: Supermicro SYS-6028R-T/X10DRi, BIOS 1.1a 10/16/2015 Call Trace: dump_stack+0x9c/0xcf print_address_description.constprop.0+0x18/0x239 kasan_report+0x174/0x1b0 trace_event_raw_event_xprt_writelock_event+0x141/0x18e [sunrpc] xprt_prepare_transmit+0x8e/0xc1 [sunrpc] call_transmit+0x4d/0xc6 [sunrpc] Fixes: 9ce07ae5eb1d ("SUNRPC: Replace dprintk() call site in xprt_prepare_transmit") Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/sunrpc.h | 1 - net/sunrpc/xprt.c | 2 -- 2 files changed, 3 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 430b42f2351f..3c3c4c843c62 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1181,7 +1181,6 @@ DECLARE_EVENT_CLASS(xprt_writelock_event, DEFINE_WRITELOCK_EVENT(reserve_xprt); DEFINE_WRITELOCK_EVENT(release_xprt); -DEFINE_WRITELOCK_EVENT(transmit_queued); DECLARE_EVENT_CLASS(xprt_cong_event, TP_PROTO( diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 67039ee443eb..baba7d14825a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1471,8 +1471,6 @@ bool xprt_prepare_transmit(struct rpc_task *task) struct rpc_xprt *xprt = req->rq_xprt; if (!xprt_lock_write(xprt, task)) { - trace_xprt_transmit_queued(xprt, task); - /* Race breaker: someone may have transmitted us */ if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate)) rpc_wake_up_queued_task_set_status(&xprt->sending, -- cgit v1.2.3 From e4b52ca01315ad53df41877708428c1c41c1444d Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:03:12 -0400 Subject: xprtrdma: Do not recycle MR after FastReg/LocalInv flushes Better not to touch MRs involved in a flush or post error until the Send and Receive Queues are drained and the transport is fully quiescent. Simply don't insert such MRs back onto the free list. They remain on mr_all and will be released when the connection is torn down. I had thought that recycling would prevent hardware resources from being tied up for a long time. However, since v5.7, a transport disconnect destroys the QP and other hardware-owned resources. The MRs get cleaned up nicely at that point. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/rpcrdma.h | 1 - net/sunrpc/xprtrdma/frwr_ops.c | 69 +++++++++++------------------------------- 2 files changed, 17 insertions(+), 53 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index c838e7ac1c2d..e38e745d13b0 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1014,7 +1014,6 @@ DEFINE_MR_EVENT(localinv); DEFINE_MR_EVENT(map); DEFINE_ANON_MR_EVENT(unmap); -DEFINE_ANON_MR_EVENT(recycle); TRACE_EVENT(xprtrdma_dma_maperr, TP_PROTO( diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index af85cec0ce31..27087dc8ba3c 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -49,6 +49,16 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif +static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) +{ + if (mr->mr_device) { + trace_xprtrdma_mr_unmap(mr); + ib_dma_unmap_sg(mr->mr_device, mr->mr_sg, mr->mr_nents, + mr->mr_dir); + mr->mr_device = NULL; + } +} + /** * frwr_mr_release - Destroy one MR * @mr: MR allocated by frwr_mr_init @@ -58,6 +68,8 @@ void frwr_mr_release(struct rpcrdma_mr *mr) { int rc; + frwr_mr_unmap(mr->mr_xprt, mr); + rc = ib_dereg_mr(mr->frwr.fr_mr); if (rc) trace_xprtrdma_frwr_dereg(mr, rc); @@ -65,32 +77,6 @@ void frwr_mr_release(struct rpcrdma_mr *mr) kfree(mr); } -static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) -{ - if (mr->mr_device) { - trace_xprtrdma_mr_unmap(mr); - ib_dma_unmap_sg(mr->mr_device, mr->mr_sg, mr->mr_nents, - mr->mr_dir); - mr->mr_device = NULL; - } -} - -static void frwr_mr_recycle(struct rpcrdma_mr *mr) -{ - struct rpcrdma_xprt *r_xprt = mr->mr_xprt; - - trace_xprtrdma_mr_recycle(mr); - - frwr_mr_unmap(r_xprt, mr); - - spin_lock(&r_xprt->rx_buf.rb_lock); - list_del(&mr->mr_all); - r_xprt->rx_stats.mrs_recycled++; - spin_unlock(&r_xprt->rx_buf.rb_lock); - - frwr_mr_release(mr); -} - static void frwr_mr_put(struct rpcrdma_mr *mr) { frwr_mr_unmap(mr->mr_xprt, mr); @@ -365,6 +351,7 @@ out_mapmr_err: * @cq: completion queue * @wc: WCE for a completed FastReg WR * + * Each flushed MR gets destroyed after the QP has drained. */ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) { @@ -374,7 +361,6 @@ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc) /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_fastreg(wc, &frwr->fr_cid); - /* The MR will get recycled when the associated req is retransmitted */ rpcrdma_flush_disconnect(cq->cq_context, wc); } @@ -448,9 +434,7 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) static void frwr_mr_done(struct ib_wc *wc, struct rpcrdma_mr *mr) { - if (wc->status != IB_WC_SUCCESS) - frwr_mr_recycle(mr); - else + if (likely(wc->status == IB_WC_SUCCESS)) frwr_mr_put(mr); } @@ -567,17 +551,8 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) if (!rc) return; - /* Recycle MRs in the LOCAL_INV chain that did not get posted. - */ + /* On error, the MRs get destroyed once the QP has drained. */ trace_xprtrdma_post_linv_err(req, rc); - while (bad_wr) { - frwr = container_of(bad_wr, struct rpcrdma_frwr, - fr_invwr); - mr = container_of(frwr, struct rpcrdma_mr, frwr); - bad_wr = bad_wr->next; - - frwr_mr_recycle(mr); - } } /** @@ -621,7 +596,6 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) { struct ib_send_wr *first, *last, **prev; struct rpcrdma_ep *ep = r_xprt->rx_ep; - const struct ib_send_wr *bad_wr; struct rpcrdma_frwr *frwr; struct rpcrdma_mr *mr; int rc; @@ -663,21 +637,12 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * replaces the QP. The RPC reply handler won't call us * unless re_id->qp is a valid pointer. */ - bad_wr = NULL; - rc = ib_post_send(ep->re_id->qp, first, &bad_wr); + rc = ib_post_send(ep->re_id->qp, first, NULL); if (!rc) return; - /* Recycle MRs in the LOCAL_INV chain that did not get posted. - */ + /* On error, the MRs get destroyed once the QP has drained. */ trace_xprtrdma_post_linv_err(req, rc); - while (bad_wr) { - frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr); - mr = container_of(frwr, struct rpcrdma_mr, frwr); - bad_wr = bad_wr->next; - - frwr_mr_recycle(mr); - } /* The final LOCAL_INV WR in the chain is supposed to * do the wake. If it was never posted, the wake will -- cgit v1.2.3 From 4ddd0fc32c94fbb77a8c0728dc507b2bdcc67edc Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:03:31 -0400 Subject: xprtrdma: Add tracepoints showing FastReg WRs and remote invalidation The Send signaling logic is a little subtle, so add some observability around it. For every xprtrdma_mr_fastreg event, there should be an xprtrdma_mr_localinv or xprtrdma_mr_reminv event. When these tracepoints are enabled, we can see exactly when an MR is DMA-mapped, registered, invalidated (either locally or remotely) and then DMA-unmapped. kworker/u25:2-190 [000] 787.979512: xprtrdma_mr_map: task:351@5 mr.id=4 nents=2 5608@0x8679e0c8f6f56000:0x00000503 (TO_DEVICE) kworker/u25:2-190 [000] 787.979515: xprtrdma_chunk_read: task:351@5 pos=148 5608@0x8679e0c8f6f56000:0x00000503 (last) kworker/u25:2-190 [000] 787.979519: xprtrdma_marshal: task:351@5 xid=0x8679e0c8: hdr=52 xdr=148/5608/0 read list/inline kworker/u25:2-190 [000] 787.979525: xprtrdma_mr_fastreg: task:351@5 mr.id=4 nents=2 5608@0x8679e0c8f6f56000:0x00000503 (TO_DEVICE) kworker/u25:2-190 [000] 787.979526: xprtrdma_post_send: task:351@5 cq.id=0 cid=73 (2 SGEs) ... kworker/5:1H-219 [005] 787.980567: xprtrdma_wc_receive: cq.id=1 cid=161 status=SUCCESS (0/0x0) received=164 kworker/5:1H-219 [005] 787.980571: xprtrdma_post_recvs: peer=[192.168.100.55]:20049 r_xprt=0xffff8884974d4000: 0 new recvs, 70 active (rc 0) kworker/5:1H-219 [005] 787.980573: xprtrdma_reply: task:351@5 xid=0x8679e0c8 credits=64 kworker/5:1H-219 [005] 787.980576: xprtrdma_mr_reminv: task:351@5 mr.id=4 nents=2 5608@0x8679e0c8f6f56000:0x00000503 (TO_DEVICE) kworker/5:1H-219 [005] 787.980577: xprtrdma_mr_unmap: mr.id=4 nents=2 5608@0x8679e0c8f6f56000:0x00000503 (TO_DEVICE) Note that I've moved the xprtrdma_post_send tracepoint so that event always appears after the xprtrdma_mr_fastreg tracepoint. Otherwise the event log looks counterintuitive (FastReg is always supposed to happen before Send). Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/rpcrdma.h | 2 ++ net/sunrpc/xprtrdma/frwr_ops.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index e38e745d13b0..9462326b3535 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1010,7 +1010,9 @@ TRACE_EVENT(xprtrdma_frwr_maperr, ) ); +DEFINE_MR_EVENT(fastreg); DEFINE_MR_EVENT(localinv); +DEFINE_MR_EVENT(reminv); DEFINE_MR_EVENT(map); DEFINE_ANON_MR_EVENT(unmap); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 43a412ea337a..0f47c1e24037 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -400,6 +400,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) list_for_each_entry(mr, &req->rl_registered, mr_list) { struct rpcrdma_frwr *frwr; + trace_xprtrdma_mr_fastreg(mr); frwr = &mr->frwr; frwr->fr_cqe.done = frwr_wc_fastreg; @@ -440,6 +441,7 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) list_for_each_entry(mr, mrs, mr_list) if (mr->mr_handle == rep->rr_inv_rkey) { list_del_init(&mr->mr_list); + trace_xprtrdma_mr_reminv(mr); frwr_mr_put(mr); break; /* only one invalidated MR per RPC */ } -- cgit v1.2.3 From 6b147ea7f442e1fb31dfa25e25b7a8ca3fb817f0 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:03:38 -0400 Subject: xprtrdma: Add an rpcrdma_mr_completion_class I found it confusing that the MR_EVENT class displays the mr.id but the associated COMPLETION_EVENT class displays a cid (that happens to contain the mr.id!). To make it a little easier on humans who have to read and interpret these events, create an MR_COMPLETION class that displays the mr.id in the same way as the MR_EVENT class. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/rpcrdma.h | 48 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 44 insertions(+), 4 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 9462326b3535..3e6e4c69b533 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -60,6 +60,46 @@ DECLARE_EVENT_CLASS(rpcrdma_completion_class, ), \ TP_ARGS(wc, cid)) +DECLARE_EVENT_CLASS(rpcrdma_mr_completion_class, + TP_PROTO( + const struct ib_wc *wc, + const struct rpc_rdma_cid *cid + ), + + TP_ARGS(wc, cid), + + TP_STRUCT__entry( + __field(u32, cq_id) + __field(int, completion_id) + __field(unsigned long, status) + __field(unsigned int, vendor_err) + ), + + TP_fast_assign( + __entry->cq_id = cid->ci_queue_id; + __entry->completion_id = cid->ci_completion_id; + __entry->status = wc->status; + if (wc->status) + __entry->vendor_err = wc->vendor_err; + else + __entry->vendor_err = 0; + ), + + TP_printk("cq.id=%u mr.id=%d status=%s (%lu/0x%x)", + __entry->cq_id, __entry->completion_id, + rdma_show_wc_status(__entry->status), + __entry->status, __entry->vendor_err + ) +); + +#define DEFINE_MR_COMPLETION_EVENT(name) \ + DEFINE_EVENT(rpcrdma_mr_completion_class, name, \ + TP_PROTO( \ + const struct ib_wc *wc, \ + const struct rpc_rdma_cid *cid \ + ), \ + TP_ARGS(wc, cid)) + DECLARE_EVENT_CLASS(rpcrdma_receive_completion_class, TP_PROTO( const struct ib_wc *wc, @@ -886,10 +926,10 @@ TRACE_EVENT(xprtrdma_post_linv_err, DEFINE_RECEIVE_COMPLETION_EVENT(xprtrdma_wc_receive); DEFINE_COMPLETION_EVENT(xprtrdma_wc_send); -DEFINE_COMPLETION_EVENT(xprtrdma_wc_fastreg); -DEFINE_COMPLETION_EVENT(xprtrdma_wc_li); -DEFINE_COMPLETION_EVENT(xprtrdma_wc_li_wake); -DEFINE_COMPLETION_EVENT(xprtrdma_wc_li_done); +DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_fastreg); +DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_li); +DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_li_wake); +DEFINE_MR_COMPLETION_EVENT(xprtrdma_wc_li_done); TRACE_EVENT(xprtrdma_frwr_alloc, TP_PROTO( -- cgit v1.2.3 From 83189d15115467061295c0b75334b39fc64c6142 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:03:44 -0400 Subject: xprtrdma: Don't display r_xprt memory addresses in tracepoints The remote peer's IP address is sufficient, and does not expose details of the kernel's memory layout. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/rpcrdma.h | 51 ++++++++++++++++-------------------------- 1 file changed, 19 insertions(+), 32 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 3e6e4c69b533..e38b8e33be2d 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -190,19 +190,17 @@ DECLARE_EVENT_CLASS(xprtrdma_rxprt, TP_ARGS(r_xprt), TP_STRUCT__entry( - __field(const void *, r_xprt) __string(addr, rpcrdma_addrstr(r_xprt)) __string(port, rpcrdma_portstr(r_xprt)) ), TP_fast_assign( - __entry->r_xprt = r_xprt; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p", - __get_str(addr), __get_str(port), __entry->r_xprt + TP_printk("peer=[%s]:%s", + __get_str(addr), __get_str(port) ) ); @@ -222,7 +220,6 @@ DECLARE_EVENT_CLASS(xprtrdma_connect_class, TP_ARGS(r_xprt, rc), TP_STRUCT__entry( - __field(const void *, r_xprt) __field(int, rc) __field(int, connect_status) __string(addr, rpcrdma_addrstr(r_xprt)) @@ -230,15 +227,14 @@ DECLARE_EVENT_CLASS(xprtrdma_connect_class, ), TP_fast_assign( - __entry->r_xprt = r_xprt; __entry->rc = rc; __entry->connect_status = r_xprt->rx_ep->re_connect_status; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p: rc=%d connection status=%d", - __get_str(addr), __get_str(port), __entry->r_xprt, + TP_printk("peer=[%s]:%s rc=%d connection status=%d", + __get_str(addr), __get_str(port), __entry->rc, __entry->connect_status ) ); @@ -535,22 +531,19 @@ TRACE_EVENT(xprtrdma_op_connect, TP_ARGS(r_xprt, delay), TP_STRUCT__entry( - __field(const void *, r_xprt) __field(unsigned long, delay) __string(addr, rpcrdma_addrstr(r_xprt)) __string(port, rpcrdma_portstr(r_xprt)) ), TP_fast_assign( - __entry->r_xprt = r_xprt; __entry->delay = delay; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p delay=%lu", - __get_str(addr), __get_str(port), __entry->r_xprt, - __entry->delay + TP_printk("peer=[%s]:%s delay=%lu", + __get_str(addr), __get_str(port), __entry->delay ) ); @@ -565,7 +558,6 @@ TRACE_EVENT(xprtrdma_op_set_cto, TP_ARGS(r_xprt, connect, reconnect), TP_STRUCT__entry( - __field(const void *, r_xprt) __field(unsigned long, connect) __field(unsigned long, reconnect) __string(addr, rpcrdma_addrstr(r_xprt)) @@ -573,15 +565,14 @@ TRACE_EVENT(xprtrdma_op_set_cto, ), TP_fast_assign( - __entry->r_xprt = r_xprt; __entry->connect = connect; __entry->reconnect = reconnect; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p: connect=%lu reconnect=%lu", - __get_str(addr), __get_str(port), __entry->r_xprt, + TP_printk("peer=[%s]:%s connect=%lu reconnect=%lu", + __get_str(addr), __get_str(port), __entry->connect / HZ, __entry->reconnect / HZ ) ); @@ -631,22 +622,19 @@ TRACE_EVENT(xprtrdma_createmrs, TP_ARGS(r_xprt, count), TP_STRUCT__entry( - __field(const void *, r_xprt) __string(addr, rpcrdma_addrstr(r_xprt)) __string(port, rpcrdma_portstr(r_xprt)) __field(unsigned int, count) ), TP_fast_assign( - __entry->r_xprt = r_xprt; __entry->count = count; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p: created %u MRs", - __get_str(addr), __get_str(port), __entry->r_xprt, - __entry->count + TP_printk("peer=[%s]:%s created %u MRs", + __get_str(addr), __get_str(port), __entry->count ) ); @@ -869,7 +857,7 @@ TRACE_EVENT(xprtrdma_post_recvs, TP_ARGS(r_xprt, count, status), TP_STRUCT__entry( - __field(const void *, r_xprt) + __field(u32, cq_id) __field(unsigned int, count) __field(int, status) __field(int, posted) @@ -878,16 +866,18 @@ TRACE_EVENT(xprtrdma_post_recvs, ), TP_fast_assign( - __entry->r_xprt = r_xprt; + const struct rpcrdma_ep *ep = r_xprt->rx_ep; + + __entry->cq_id = ep->re_attr.recv_cq->res.id; __entry->count = count; __entry->status = status; - __entry->posted = r_xprt->rx_ep->re_receive_count; + __entry->posted = ep->re_receive_count; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p: %u new recvs, %d active (rc %d)", - __get_str(addr), __get_str(port), __entry->r_xprt, + TP_printk("peer=[%s]:%s cq.id=%d %u new recvs, %d active (rc %d)", + __get_str(addr), __get_str(port), __entry->cq_id, __entry->count, __entry->posted, __entry->status ) ); @@ -1289,22 +1279,19 @@ TRACE_EVENT(xprtrdma_cb_setup, TP_ARGS(r_xprt, reqs), TP_STRUCT__entry( - __field(const void *, r_xprt) __field(unsigned int, reqs) __string(addr, rpcrdma_addrstr(r_xprt)) __string(port, rpcrdma_portstr(r_xprt)) ), TP_fast_assign( - __entry->r_xprt = r_xprt; __entry->reqs = reqs; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), - TP_printk("peer=[%s]:%s r_xprt=%p: %u reqs", - __get_str(addr), __get_str(port), - __entry->r_xprt, __entry->reqs + TP_printk("peer=[%s]:%s %u reqs", + __get_str(addr), __get_str(port), __entry->reqs ) ); -- cgit v1.2.3 From e1648eb23d839bd4b9f2999296d5e81dcd93311f Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:03:50 -0400 Subject: xprtrdma: Remove the RPC/RDMA QP event handler Clean up: The handler only recorded a trace event. If indeed no action is needed by the RPC/RDMA consumer, then the event can be ignored. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/rpcrdma.h | 32 -------------------------------- net/sunrpc/xprtrdma/verbs.c | 18 ------------------ 2 files changed, 50 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index e38b8e33be2d..ef6166b840e7 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -577,38 +577,6 @@ TRACE_EVENT(xprtrdma_op_set_cto, ) ); -TRACE_EVENT(xprtrdma_qp_event, - TP_PROTO( - const struct rpcrdma_ep *ep, - const struct ib_event *event - ), - - TP_ARGS(ep, event), - - TP_STRUCT__entry( - __field(unsigned long, event) - __string(name, event->device->name) - __array(unsigned char, srcaddr, sizeof(struct sockaddr_in6)) - __array(unsigned char, dstaddr, sizeof(struct sockaddr_in6)) - ), - - TP_fast_assign( - const struct rdma_cm_id *id = ep->re_id; - - __entry->event = event->event; - __assign_str(name, event->device->name); - memcpy(__entry->srcaddr, &id->route.addr.src_addr, - sizeof(struct sockaddr_in6)); - memcpy(__entry->dstaddr, &id->route.addr.dst_addr, - sizeof(struct sockaddr_in6)); - ), - - TP_printk("%pISpc -> %pISpc device=%s %s (%lu)", - __entry->srcaddr, __entry->dstaddr, __get_str(name), - rdma_show_ib_event(__entry->event), __entry->event - ) -); - /** ** Call events **/ diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 72b24dca96c1..1e965a380896 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -120,22 +120,6 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) rpcrdma_ep_put(ep); } -/** - * rpcrdma_qp_event_handler - Handle one QP event (error notification) - * @event: details of the event - * @context: ep that owns QP where event occurred - * - * Called from the RDMA provider (device driver) possibly in an interrupt - * context. The QP is always destroyed before the ID, so the ID will be - * reliably available when this handler is invoked. - */ -static void rpcrdma_qp_event_handler(struct ib_event *event, void *context) -{ - struct rpcrdma_ep *ep = context; - - trace_xprtrdma_qp_event(ep, event); -} - /* Ensure xprt_force_disconnect() is invoked exactly once when a * connection is closed or lost. (The important thing is it needs * to be invoked "at least" once). @@ -431,8 +415,6 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) r_xprt->rx_buf.rb_max_requests = cpu_to_be32(ep->re_max_requests); - ep->re_attr.event_handler = rpcrdma_qp_event_handler; - ep->re_attr.qp_context = ep; ep->re_attr.srq = NULL; ep->re_attr.cap.max_inline_data = 0; ep->re_attr.sq_sig_type = IB_SIGNAL_REQ_WR; -- cgit v1.2.3 From 13bcf7e32a0181095cd62010579869e87aacb332 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 19 Apr 2021 14:04:21 -0400 Subject: xprtrdma: Move fr_mr field to struct rpcrdma_mr Clean up: The last remaining field in struct rpcrdma_frwr has been removed, so the struct can be eliminated. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/trace/events/rpcrdma.h | 12 ++++++------ net/sunrpc/xprtrdma/frwr_ops.c | 8 ++++---- net/sunrpc/xprtrdma/xprt_rdma.h | 7 ++----- 3 files changed, 12 insertions(+), 15 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index ef6166b840e7..bd55908c1bef 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -379,7 +379,7 @@ DECLARE_EVENT_CLASS(xprtrdma_mr_class, __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; - __entry->mr_id = mr->frwr.fr_mr->res.id; + __entry->mr_id = mr->mr_ibmr->res.id; __entry->nents = mr->mr_nents; __entry->handle = mr->mr_handle; __entry->length = mr->mr_length; @@ -420,7 +420,7 @@ DECLARE_EVENT_CLASS(xprtrdma_anonymous_mr_class, ), TP_fast_assign( - __entry->mr_id = mr->frwr.fr_mr->res.id; + __entry->mr_id = mr->mr_ibmr->res.id; __entry->nents = mr->mr_nents; __entry->handle = mr->mr_handle; __entry->length = mr->mr_length; @@ -903,7 +903,7 @@ TRACE_EVENT(xprtrdma_frwr_alloc, ), TP_fast_assign( - __entry->mr_id = mr->frwr.fr_mr->res.id; + __entry->mr_id = mr->mr_ibmr->res.id; __entry->rc = rc; ), @@ -931,7 +931,7 @@ TRACE_EVENT(xprtrdma_frwr_dereg, ), TP_fast_assign( - __entry->mr_id = mr->frwr.fr_mr->res.id; + __entry->mr_id = mr->mr_ibmr->res.id; __entry->nents = mr->mr_nents; __entry->handle = mr->mr_handle; __entry->length = mr->mr_length; @@ -964,7 +964,7 @@ TRACE_EVENT(xprtrdma_frwr_sgerr, ), TP_fast_assign( - __entry->mr_id = mr->frwr.fr_mr->res.id; + __entry->mr_id = mr->mr_ibmr->res.id; __entry->addr = mr->mr_sg->dma_address; __entry->dir = mr->mr_dir; __entry->nents = sg_nents; @@ -994,7 +994,7 @@ TRACE_EVENT(xprtrdma_frwr_maperr, ), TP_fast_assign( - __entry->mr_id = mr->frwr.fr_mr->res.id; + __entry->mr_id = mr->mr_ibmr->res.id; __entry->addr = mr->mr_sg->dma_address; __entry->dir = mr->mr_dir; __entry->num_mapped = num_mapped; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index bb2b9c607c71..285d73246fc2 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -55,7 +55,7 @@ static void frwr_cid_init(struct rpcrdma_ep *ep, struct rpc_rdma_cid *cid = &mr->mr_cid; cid->ci_queue_id = ep->re_attr.send_cq->res.id; - cid->ci_completion_id = mr->frwr.fr_mr->res.id; + cid->ci_completion_id = mr->mr_ibmr->res.id; } static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) @@ -79,7 +79,7 @@ void frwr_mr_release(struct rpcrdma_mr *mr) frwr_mr_unmap(mr->mr_xprt, mr); - rc = ib_dereg_mr(mr->frwr.fr_mr); + rc = ib_dereg_mr(mr->mr_ibmr); if (rc) trace_xprtrdma_frwr_dereg(mr, rc); kfree(mr->mr_sg); @@ -139,7 +139,7 @@ int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) goto out_list_err; mr->mr_xprt = r_xprt; - mr->frwr.fr_mr = frmr; + mr->mr_ibmr = frmr; mr->mr_device = NULL; INIT_LIST_HEAD(&mr->mr_list); init_completion(&mr->mr_linv_done); @@ -323,7 +323,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, goto out_dmamap_err; mr->mr_device = ep->re_id->device; - ibmr = mr->frwr.fr_mr; + ibmr = mr->mr_ibmr; n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE); if (n != dma_nents) goto out_mapmr_err; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 99ef83d673d6..436ad7312614 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -229,14 +229,12 @@ struct rpcrdma_sendctx { * An external memory region is any buffer or page that is registered * on the fly (ie, not pre-registered). */ -struct rpcrdma_frwr { - struct ib_mr *fr_mr; -}; - struct rpcrdma_req; struct rpcrdma_mr { struct list_head mr_list; struct rpcrdma_req *mr_req; + + struct ib_mr *mr_ibmr; struct ib_device *mr_device; struct scatterlist *mr_sg; int mr_nents; @@ -247,7 +245,6 @@ struct rpcrdma_mr { struct ib_reg_wr mr_regwr; struct ib_send_wr mr_invwr; }; - struct rpcrdma_frwr frwr; struct rpcrdma_xprt *mr_xprt; u32 mr_handle; u32 mr_length; -- cgit v1.2.3 From 7677f7fd8be76659cd2d0db8ff4093bbb51c20e5 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 4 May 2021 18:35:36 -0700 Subject: userfaultfd: add minor fault registration mode Patch series "userfaultfd: add minor fault handling", v9. Overview ======== This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS. When enabled (via the UFFDIO_API ioctl), this feature means that any hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also* get events for "minor" faults. By "minor" fault, I mean the following situation: Let there exist two mappings (i.e., VMAs) to the same page(s) (shared memory). One of the mappings is registered with userfaultfd (in minor mode), and the other is not. Via the non-UFFD mapping, the underlying pages have already been allocated & filled with some contents. The UFFD mapping has not yet been faulted in; when it is touched for the first time, this results in what I'm calling a "minor" fault. As a concrete example, when working with hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing page. We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea is, userspace resolves the fault by either a) doing nothing if the contents are already correct, or b) updating the underlying contents using the second, non-UFFD mapping (via memcpy/memset or similar, or something fancier like RDMA, or etc...). In either case, userspace issues UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are correct, carry on setting up the mapping". Use Case ======== Consider the use case of VM live migration (e.g. under QEMU/KVM): 1. While a VM is still running, we copy the contents of its memory to a target machine. The pages are populated on the target by writing to the non-UFFD mapping, using the setup described above. The VM is still running (and therefore its memory is likely changing), so this may be repeated several times, until we decide the target is "up to date enough". 2. We pause the VM on the source, and start executing on the target machine. During this gap, the VM's user(s) will *see* a pause, so it is desirable to minimize this window. 3. Between the last time any page was copied from the source to the target, and when the VM was paused, the contents of that page may have changed - and therefore the copy we have on the target machine is out of date. Although we can keep track of which pages are out of date, for VMs with large amounts of memory, it is "slow" to transfer this information to the target machine. We want to resume execution before such a transfer would complete. 4. So, the guest begins executing on the target machine. The first time it touches its memory (via the UFFD-registered mapping), userspace wants to intercept this fault. Userspace checks whether or not the page is up to date, and if not, copies the updated page from the source machine, via the non-UFFD mapping. Finally, whether a copy was performed or not, userspace issues a UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents are correct, carry on setting up the mapping". We don't have to do all of the final updates on-demand. The userfaultfd manager can, in the background, also copy over updated pages once it receives the map of which pages are up-to-date or not. Interaction with Existing APIs ============================== Because this is a feature, a registered VMA could potentially receive both missing and minor faults. I spent some time thinking through how the existing API interacts with the new feature: UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault: - For non-shared memory or shmem, -EINVAL is returned. - For hugetlb, -EFAULT is returned. UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults. Without modifications, the existing codepath assumes a new page needs to be allocated. This is okay, since userspace must have a second non-UFFD-registered mapping anyway, thus there isn't much reason to want to use these in any case (just memcpy or memset or similar). - If UFFDIO_COPY is used on a minor fault, -EEXIST is returned. - If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case). - UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns -ENOENT in that case (regardless of the kind of fault). Future Work =========== This series only supports hugetlbfs. I have a second series in flight to support shmem as well, extending the functionality. This series is more mature than the shmem support at this point, and the functionality works fully on hugetlbfs, so this series can be merged first and then shmem support will follow. This patch (of 6): This feature allows userspace to intercept "minor" faults. By "minor" faults, I mean the following situation: Let there exist two mappings (i.e., VMAs) to the same page(s). One of the mappings is registered with userfaultfd (in minor mode), and the other is not. Via the non-UFFD mapping, the underlying pages have already been allocated & filled with some contents. The UFFD mapping has not yet been faulted in; when it is touched for the first time, this results in what I'm calling a "minor" fault. As a concrete example, when working with hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing page. This commit adds the new registration mode, and sets the relevant flag on the VMAs being registered. In the hugetlb fault path, if we find that we have huge_pte_none(), but find_lock_page() does indeed find an existing page, then we have a "minor" fault, and if the VMA has the userfaultfd registration flag, we call into userfaultfd to handle it. This is implemented as a new registration mode, instead of an API feature. This is because the alternative implementation has significant drawbacks [1]. However, doing it this was requires we allocate a VM_* flag for the new registration mode. On 32-bit systems, there are no unused bits, so this feature is only supported on architectures with CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in MINOR mode on 32-bit architectures, we return -EINVAL. [1] https://lore.kernel.org/patchwork/patch/1380226/ [peterx@redhat.com: fix minor fault page leak] Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alexander Viro Cc: Alexey Dobriyan Cc: Andrea Arcangeli Cc: Anshuman Khandual Cc: Catalin Marinas Cc: Chinwen Chang Cc: Huang Ying Cc: Ingo Molnar Cc: Jann Horn Cc: Jerome Glisse Cc: Lokesh Gidra Cc: "Matthew Wilcox (Oracle)" Cc: Michael Ellerman Cc: "Michal Koutn" Cc: Michel Lespinasse Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Peter Xu Cc: Shaohua Li Cc: Shawn Anastasio Cc: Steven Rostedt Cc: Steven Price Cc: Vlastimil Babka Cc: Adam Ruprecht Cc: Axel Rasmussen Cc: Cannon Matthews Cc: "Dr . David Alan Gilbert" Cc: David Rientjes Cc: Mina Almasry Cc: Oliver Upton Cc: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/Kconfig | 1 + arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 3 ++ fs/userfaultfd.c | 78 +++++++++++++++++++++++---------------- include/linux/mm.h | 7 ++++ include/linux/userfaultfd_k.h | 15 +++++++- include/trace/events/mmflags.h | 7 ++++ include/uapi/linux/userfaultfd.h | 15 +++++++- init/Kconfig | 5 +++ mm/hugetlb.c | 80 ++++++++++++++++++++++++++-------------- 10 files changed, 150 insertions(+), 62 deletions(-) (limited to 'include/trace') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7f2a80091337..04c69f606537 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -213,6 +213,7 @@ config ARM64 select SWIOTLB select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK + select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD help ARM 64-bit (AArch64) Linux support. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dac15f646f79..1c350e8782ed 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -165,6 +165,7 @@ config X86 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 select HAVE_ARCH_USERFAULTFD_WP if X86_64 && USERFAULTFD + select HAVE_ARCH_USERFAULTFD_MINOR if X86_64 && USERFAULTFD select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_WITHIN_STACK_FRAMES diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e862cab69583..fc9784544b24 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -661,6 +661,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_PKEY_BIT4)] = "", #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR + [ilog2(VM_UFFD_MINOR)] = "ui", +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ }; size_t i; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e5ce3b4e6c3d..ba35cafa8b0d 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -197,24 +197,21 @@ static inline struct uffd_msg userfault_msg(unsigned long address, msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = address; + /* + * These flags indicate why the userfault occurred: + * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. + * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. + * - Neither of these flags being set indicates a MISSING fault. + * + * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write + * fault. Otherwise, it was a read fault. + */ if (flags & FAULT_FLAG_WRITE) - /* - * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the - * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE - * was not set in a UFFD_EVENT_PAGEFAULT, it means it - * was a read fault, otherwise if set it means it's - * a write fault. - */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) - /* - * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the - * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was - * not set in a UFFD_EVENT_PAGEFAULT, it means it was - * a missing fault, otherwise if set it means it's a - * write protect fault. - */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; + if (reason & VM_UFFD_MINOR) + msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; @@ -401,8 +398,10 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) BUG_ON(ctx->mm != mm); - VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); - VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); + /* Any unrecognized flag is a bug. */ + VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); + /* 0 or > 1 flags set is a bug; we expect exactly 1. */ + VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; @@ -612,7 +611,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + vma->vm_flags &= ~__VM_UFFD_FLAGS; } mmap_write_unlock(mm); @@ -644,7 +643,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + vma->vm_flags &= ~__VM_UFFD_FLAGS; return 0; } @@ -726,7 +725,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, } else { /* Drop uffd context if remap feature not enabled */ vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + vma->vm_flags &= ~__VM_UFFD_FLAGS; } } @@ -867,12 +866,12 @@ static int userfaultfd_release(struct inode *inode, struct file *file) for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^ - !!(vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP))); + !!(vma->vm_flags & __VM_UFFD_FLAGS)); if (vma->vm_userfaultfd_ctx.ctx != ctx) { prev = vma; continue; } - new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, @@ -1262,9 +1261,19 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, unsigned long vm_flags) { /* FIXME: add WP support to hugetlbfs and shmem */ - return vma_is_anonymous(vma) || - ((is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) && - !(vm_flags & VM_UFFD_WP)); + if (vm_flags & VM_UFFD_WP) { + if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma)) + return false; + } + + if (vm_flags & VM_UFFD_MINOR) { + /* FIXME: Add minor fault interception for shmem. */ + if (!is_vm_hugetlb_page(vma)) + return false; + } + + return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) || + vma_is_shmem(vma); } static int userfaultfd_register(struct userfaultfd_ctx *ctx, @@ -1290,14 +1299,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, ret = -EINVAL; if (!uffdio_register.mode) goto out; - if (uffdio_register.mode & ~(UFFDIO_REGISTER_MODE_MISSING| - UFFDIO_REGISTER_MODE_WP)) + if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) vm_flags |= VM_UFFD_WP; + if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR + goto out; +#endif + vm_flags |= VM_UFFD_MINOR; + } ret = validate_range(mm, &uffdio_register.range.start, uffdio_register.range.len); @@ -1341,7 +1355,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ - !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP))); + !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; @@ -1421,8 +1435,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, start = vma->vm_start; vma_end = min(end, vma->vm_end); - new_flags = (vma->vm_flags & - ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags; + new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), @@ -1544,7 +1557,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ - !!(cur->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP))); + !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required @@ -1595,7 +1608,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } - new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP); + new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), @@ -1863,6 +1876,9 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, goto err_out; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR + uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS; +#endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) diff --git a/include/linux/mm.h b/include/linux/mm.h index 011f43605807..1dbb53c44243 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -372,6 +372,13 @@ extern unsigned int kobjsize(const void *objp); # define VM_GROWSUP VM_NONE #endif +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +# define VM_UFFD_MINOR_BIT 37 +# define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ +#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +# define VM_UFFD_MINOR VM_NONE +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index c63ccdae3eab..0390e5ac63b3 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -17,6 +17,9 @@ #include #include +/* The set of all possible UFFD-related VM flags. */ +#define __VM_UFFD_FLAGS (VM_UFFD_MISSING | VM_UFFD_WP | VM_UFFD_MINOR) + /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining * new flags, since they might collide with O_* ones. We want @@ -71,6 +74,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma) return vma->vm_flags & VM_UFFD_WP; } +static inline bool userfaultfd_minor(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_UFFD_MINOR; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { @@ -85,7 +93,7 @@ static inline bool userfaultfd_huge_pmd_wp(struct vm_area_struct *vma, static inline bool userfaultfd_armed(struct vm_area_struct *vma) { - return vma->vm_flags & (VM_UFFD_MISSING | VM_UFFD_WP); + return vma->vm_flags & __VM_UFFD_FLAGS; } extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); @@ -132,6 +140,11 @@ static inline bool userfaultfd_wp(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_minor(struct vm_area_struct *vma) +{ + return false; +} + static inline bool userfaultfd_pte_wp(struct vm_area_struct *vma, pte_t pte) { diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 67018d367b9f..629c7a0eaff2 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -137,6 +137,12 @@ IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) #define IF_HAVE_VM_SOFTDIRTY(flag,name) #endif +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR +# define IF_HAVE_UFFD_MINOR(flag, name) {flag, name}, +#else +# define IF_HAVE_UFFD_MINOR(flag, name) +#endif + #define __def_vmaflag_names \ {VM_READ, "read" }, \ {VM_WRITE, "write" }, \ @@ -148,6 +154,7 @@ IF_HAVE_PG_ARCH_2(PG_arch_2, "arch_2" ) {VM_MAYSHARE, "mayshare" }, \ {VM_GROWSDOWN, "growsdown" }, \ {VM_UFFD_MISSING, "uffd_missing" }, \ +IF_HAVE_UFFD_MINOR(VM_UFFD_MINOR, "uffd_minor" ) \ {VM_PFNMAP, "pfnmap" }, \ {VM_DENYWRITE, "denywrite" }, \ {VM_UFFD_WP, "uffd_wp" }, \ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 5f2d88212f7c..f24dd4fcbad9 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -19,15 +19,19 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR) #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ - UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ - UFFD_FEATURE_THREAD_ID) + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -127,6 +131,7 @@ struct uffd_msg { /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ #define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ struct uffdio_api { /* userland asks for an API number and the features to enable */ @@ -171,6 +176,10 @@ struct uffdio_api { * * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -181,6 +190,7 @@ struct uffdio_api { #define UFFD_FEATURE_EVENT_UNMAP (1<<6) #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) __u64 features; __u64 ioctls; @@ -195,6 +205,7 @@ struct uffdio_register { struct uffdio_range range; #define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) #define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) __u64 mode; /* diff --git a/init/Kconfig b/init/Kconfig index 9acb7762e971..1413413fcb9f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1644,6 +1644,11 @@ config HAVE_ARCH_USERFAULTFD_WP help Arch has userfaultfd write protection support +config HAVE_ARCH_USERFAULTFD_MINOR + bool + help + Arch has userfaultfd minor fault support + config MEMBARRIER bool "Enable membarrier() system call" if EXPERT default y diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b5977d9709ad..84530876b2ae 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4469,6 +4469,44 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, return 0; } +static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, + unsigned int flags, + unsigned long haddr, + unsigned long reason) +{ + vm_fault_t ret; + u32 hash; + struct vm_fault vmf = { + .vma = vma, + .address = haddr, + .flags = flags, + + /* + * Hard to debug if it ends up being + * used by a callee that assumes + * something about the other + * uninitialized fields... same as in + * memory.c + */ + }; + + /* + * hugetlb_fault_mutex and i_mmap_rwsem must be + * dropped before handling userfault. Reacquire + * after handling fault to make calling code simpler. + */ + hash = hugetlb_fault_mutex_hash(mapping, idx); + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); + ret = handle_userfault(&vmf, reason); + i_mmap_lock_read(mapping); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + + return ret; +} + static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, @@ -4507,35 +4545,11 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, retry: page = find_lock_page(mapping, idx); if (!page) { - /* - * Check for page in userfault range - */ + /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { - u32 hash; - struct vm_fault vmf = { - .vma = vma, - .address = haddr, - .flags = flags, - /* - * Hard to debug if it ends up being - * used by a callee that assumes - * something about the other - * uninitialized fields... same as in - * memory.c - */ - }; - - /* - * hugetlb_fault_mutex and i_mmap_rwsem must be - * dropped before handling userfault. Reacquire - * after handling fault to make calling code simpler. - */ - hash = hugetlb_fault_mutex_hash(mapping, idx); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); - ret = handle_userfault(&vmf, VM_UFFD_MISSING); - i_mmap_lock_read(mapping); - mutex_lock(&hugetlb_fault_mutex_table[hash]); + ret = hugetlb_handle_userfault(vma, mapping, idx, + flags, haddr, + VM_UFFD_MISSING); goto out; } @@ -4591,6 +4605,16 @@ retry: VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } + + /* Check for page in userfault range. */ + if (userfaultfd_minor(vma)) { + unlock_page(page); + put_page(page); + ret = hugetlb_handle_userfault(vma, mapping, idx, + flags, haddr, + VM_UFFD_MINOR); + goto out; + } } /* -- cgit v1.2.3 From 7bc1aec5e28765ad18742824b3b972471807a632 Mon Sep 17 00:00:00 2001 From: Liam Mark Date: Tue, 4 May 2021 18:37:25 -0700 Subject: mm: cma: add trace events for CMA alloc perf testing Add cma and migrate trace events to enable CMA allocation performance to be measured via ftrace. [georgi.djakov@linaro.org: add the CMA instance name to the cma_alloc_start trace event] Link: https://lkml.kernel.org/r/20210326155414.25006-1-georgi.djakov@linaro.org Link: https://lkml.kernel.org/r/20210324160740.15901-1-georgi.djakov@linaro.org Signed-off-by: Liam Mark Signed-off-by: Georgi Djakov Acked-by: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/cma.h | 42 +++++++++++++++++++++++++++++++++++++++++- include/trace/events/migrate.h | 22 ++++++++++++++++++++++ mm/cma.c | 4 ++++ mm/migrate.c | 2 ++ 4 files changed, 69 insertions(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h index 5017a8829270..be1525a10457 100644 --- a/include/trace/events/cma.h +++ b/include/trace/events/cma.h @@ -8,7 +8,7 @@ #include #include -TRACE_EVENT(cma_alloc, +DECLARE_EVENT_CLASS(cma_alloc_class, TP_PROTO(unsigned long pfn, const struct page *page, unsigned int count, unsigned int align), @@ -61,6 +61,46 @@ TRACE_EVENT(cma_release, __entry->count) ); +TRACE_EVENT(cma_alloc_start, + + TP_PROTO(const char *name, unsigned int count, unsigned int align), + + TP_ARGS(name, count, align), + + TP_STRUCT__entry( + __string(name, name) + __field(unsigned int, count) + __field(unsigned int, align) + ), + + TP_fast_assign( + __assign_str(name, name); + __entry->count = count; + __entry->align = align; + ), + + TP_printk("name=%s count=%u align=%u", + __get_str(name), + __entry->count, + __entry->align) +); + +DEFINE_EVENT(cma_alloc_class, cma_alloc, + + TP_PROTO(unsigned long pfn, const struct page *page, + unsigned int count, unsigned int align), + + TP_ARGS(pfn, page, count, align) +); + +DEFINE_EVENT(cma_alloc_class, cma_alloc_busy_retry, + + TP_PROTO(unsigned long pfn, const struct page *page, + unsigned int count, unsigned int align), + + TP_ARGS(pfn, page, count, align) +); + #endif /* _TRACE_CMA_H */ /* This part must be outside protection */ diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 4d434398d64d..f2c990603888 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -81,6 +81,28 @@ TRACE_EVENT(mm_migrate_pages, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); + +TRACE_EVENT(mm_migrate_pages_start, + + TP_PROTO(enum migrate_mode mode, int reason), + + TP_ARGS(mode, reason), + + TP_STRUCT__entry( + __field(enum migrate_mode, mode) + __field(int, reason) + ), + + TP_fast_assign( + __entry->mode = mode; + __entry->reason = reason; + ), + + TP_printk("mode=%s reason=%s", + __print_symbolic(__entry->mode, MIGRATE_MODE), + __print_symbolic(__entry->reason, MIGRATE_REASON)) +); + #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ diff --git a/mm/cma.c b/mm/cma.c index a862ff8c23ce..d1a4c06b5039 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -443,6 +443,8 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, if (!count) goto out; + trace_cma_alloc_start(cma->name, count, align); + mask = cma_bitmap_aligned_mask(cma, align); offset = cma_bitmap_aligned_offset(cma, align); bitmap_maxno = cma_bitmap_maxno(cma); @@ -483,6 +485,8 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, pr_debug("%s(): memory range at %p is busy, retrying\n", __func__, pfn_to_page(pfn)); + + trace_cma_alloc_busy_retry(pfn, pfn_to_page(pfn), count, align); /* try again with a bit different memory target */ start = bitmap_no + mask + 1; } diff --git a/mm/migrate.c b/mm/migrate.c index 30c65c2be30b..6b37d00890ca 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1418,6 +1418,8 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, int rc, nr_subpages; LIST_HEAD(ret_pages); + trace_mm_migrate_pages_start(mode, reason); + if (!swapwrite) current->flags |= PF_SWAPWRITE; -- cgit v1.2.3 From 3aab8ae7aace3388da319a233edf48f0f5d26a44 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 4 May 2021 18:37:31 -0700 Subject: mm: cma: add the CMA instance name to cma trace events There were missing places to add cma instance name. To identify each CMA instance, let's add the name for every cma trace. This patch also changes the existing cma_trace_alloc to cma_trace_finish since we have cma_alloc_start[1]. [1] https://lore.kernel.org/linux-mm/20210324160740.15901-1-georgi.djakov@linaro.org Link: https://lkml.kernel.org/r/20210330220237.748899-1-minchan@kernel.org Signed-off-by: Minchan Kim Cc: Liam Mark Cc: Georgi Djakov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/cma.h | 28 +++++++++++++++++----------- mm/cma.c | 7 ++++--- 2 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h index be1525a10457..5cf385ae7c08 100644 --- a/include/trace/events/cma.h +++ b/include/trace/events/cma.h @@ -10,12 +10,13 @@ DECLARE_EVENT_CLASS(cma_alloc_class, - TP_PROTO(unsigned long pfn, const struct page *page, + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, unsigned int count, unsigned int align), - TP_ARGS(pfn, page, count, align), + TP_ARGS(name, pfn, page, count, align), TP_STRUCT__entry( + __string(name, name) __field(unsigned long, pfn) __field(const struct page *, page) __field(unsigned int, count) @@ -23,13 +24,15 @@ DECLARE_EVENT_CLASS(cma_alloc_class, ), TP_fast_assign( + __assign_str(name, name); __entry->pfn = pfn; __entry->page = page; __entry->count = count; __entry->align = align; ), - TP_printk("pfn=%lx page=%p count=%u align=%u", + TP_printk("name=%s pfn=%lx page=%p count=%u align=%u", + __get_str(name), __entry->pfn, __entry->page, __entry->count, @@ -38,24 +41,27 @@ DECLARE_EVENT_CLASS(cma_alloc_class, TRACE_EVENT(cma_release, - TP_PROTO(unsigned long pfn, const struct page *page, + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, unsigned int count), - TP_ARGS(pfn, page, count), + TP_ARGS(name, pfn, page, count), TP_STRUCT__entry( + __string(name, name) __field(unsigned long, pfn) __field(const struct page *, page) __field(unsigned int, count) ), TP_fast_assign( + __assign_str(name, name); __entry->pfn = pfn; __entry->page = page; __entry->count = count; ), - TP_printk("pfn=%lx page=%p count=%u", + TP_printk("name=%s pfn=%lx page=%p count=%u", + __get_str(name), __entry->pfn, __entry->page, __entry->count) @@ -85,20 +91,20 @@ TRACE_EVENT(cma_alloc_start, __entry->align) ); -DEFINE_EVENT(cma_alloc_class, cma_alloc, +DEFINE_EVENT(cma_alloc_class, cma_alloc_finish, - TP_PROTO(unsigned long pfn, const struct page *page, + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, unsigned int count, unsigned int align), - TP_ARGS(pfn, page, count, align) + TP_ARGS(name, pfn, page, count, align) ); DEFINE_EVENT(cma_alloc_class, cma_alloc_busy_retry, - TP_PROTO(unsigned long pfn, const struct page *page, + TP_PROTO(const char *name, unsigned long pfn, const struct page *page, unsigned int count, unsigned int align), - TP_ARGS(pfn, page, count, align) + TP_ARGS(name, pfn, page, count, align) ); #endif /* _TRACE_CMA_H */ diff --git a/mm/cma.c b/mm/cma.c index 2380f2571eb5..cdad8c4de921 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -486,12 +486,13 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, pr_debug("%s(): memory range at %p is busy, retrying\n", __func__, pfn_to_page(pfn)); - trace_cma_alloc_busy_retry(pfn, pfn_to_page(pfn), count, align); + trace_cma_alloc_busy_retry(cma->name, pfn, pfn_to_page(pfn), + count, align); /* try again with a bit different memory target */ start = bitmap_no + mask + 1; } - trace_cma_alloc(pfn, page, count, align); + trace_cma_alloc_finish(cma->name, pfn, page, count, align); /* * CMA can allocate multiple page blocks, which results in different @@ -551,7 +552,7 @@ bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) free_contig_range(pfn, count); cma_clear_bitmap(cma, pfn, count); - trace_cma_release(pfn, pages, count); + trace_cma_release(cma->name, pfn, pages, count); return true; } -- cgit v1.2.3 From 78fa51503fdbe463c96eef4c3cf69ca54032647a Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 4 May 2021 18:37:34 -0700 Subject: mm: use proper type for cma_[alloc|release] size_t in cma_alloc is confusing since it makes people think it's byte count, not pages. Change it to unsigned long[1]. The unsigned int in cma_release is also not right so change it. Since we have unsigned long in cma_release, free_contig_range should also respect it. [1] 67a2e213e7e9, mm: cma: fix incorrect type conversion for size during dma allocation Link: https://lore.kernel.org/linux-mm/20210324043434.GP1719932@casper.infradead.org/ Link: https://lkml.kernel.org/r/20210331164018.710560-1-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: David Hildenbrand Cc: Matthew Wilcox Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 4 ++-- include/linux/gfp.h | 2 +- include/trace/events/cma.h | 22 +++++++++++----------- mm/cma.c | 17 +++++++++-------- mm/page_alloc.c | 6 +++--- 5 files changed, 26 insertions(+), 25 deletions(-) (limited to 'include/trace') diff --git a/include/linux/cma.h b/include/linux/cma.h index 217999c8a762..53fd8c3cdbd0 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -44,9 +44,9 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, unsigned int order_per_bit, const char *name, struct cma **res_cma); -extern struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, +extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); -extern bool cma_release(struct cma *cma, const struct page *pages, unsigned int count); +extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); #endif diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 26f4d907254a..8a5f6c3d7dba 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -657,7 +657,7 @@ extern int alloc_contig_range(unsigned long start, unsigned long end, extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif -void free_contig_range(unsigned long pfn, unsigned int nr_pages); +void free_contig_range(unsigned long pfn, unsigned long nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h index 5cf385ae7c08..c3d354702cb0 100644 --- a/include/trace/events/cma.h +++ b/include/trace/events/cma.h @@ -11,7 +11,7 @@ DECLARE_EVENT_CLASS(cma_alloc_class, TP_PROTO(const char *name, unsigned long pfn, const struct page *page, - unsigned int count, unsigned int align), + unsigned long count, unsigned int align), TP_ARGS(name, pfn, page, count, align), @@ -19,7 +19,7 @@ DECLARE_EVENT_CLASS(cma_alloc_class, __string(name, name) __field(unsigned long, pfn) __field(const struct page *, page) - __field(unsigned int, count) + __field(unsigned long, count) __field(unsigned int, align) ), @@ -31,7 +31,7 @@ DECLARE_EVENT_CLASS(cma_alloc_class, __entry->align = align; ), - TP_printk("name=%s pfn=%lx page=%p count=%u align=%u", + TP_printk("name=%s pfn=%lx page=%p count=%lu align=%u", __get_str(name), __entry->pfn, __entry->page, @@ -42,7 +42,7 @@ DECLARE_EVENT_CLASS(cma_alloc_class, TRACE_EVENT(cma_release, TP_PROTO(const char *name, unsigned long pfn, const struct page *page, - unsigned int count), + unsigned long count), TP_ARGS(name, pfn, page, count), @@ -50,7 +50,7 @@ TRACE_EVENT(cma_release, __string(name, name) __field(unsigned long, pfn) __field(const struct page *, page) - __field(unsigned int, count) + __field(unsigned long, count) ), TP_fast_assign( @@ -60,7 +60,7 @@ TRACE_EVENT(cma_release, __entry->count = count; ), - TP_printk("name=%s pfn=%lx page=%p count=%u", + TP_printk("name=%s pfn=%lx page=%p count=%lu", __get_str(name), __entry->pfn, __entry->page, @@ -69,13 +69,13 @@ TRACE_EVENT(cma_release, TRACE_EVENT(cma_alloc_start, - TP_PROTO(const char *name, unsigned int count, unsigned int align), + TP_PROTO(const char *name, unsigned long count, unsigned int align), TP_ARGS(name, count, align), TP_STRUCT__entry( __string(name, name) - __field(unsigned int, count) + __field(unsigned long, count) __field(unsigned int, align) ), @@ -85,7 +85,7 @@ TRACE_EVENT(cma_alloc_start, __entry->align = align; ), - TP_printk("name=%s count=%u align=%u", + TP_printk("name=%s count=%lu align=%u", __get_str(name), __entry->count, __entry->align) @@ -94,7 +94,7 @@ TRACE_EVENT(cma_alloc_start, DEFINE_EVENT(cma_alloc_class, cma_alloc_finish, TP_PROTO(const char *name, unsigned long pfn, const struct page *page, - unsigned int count, unsigned int align), + unsigned long count, unsigned int align), TP_ARGS(name, pfn, page, count, align) ); @@ -102,7 +102,7 @@ DEFINE_EVENT(cma_alloc_class, cma_alloc_finish, DEFINE_EVENT(cma_alloc_class, cma_alloc_busy_retry, TP_PROTO(const char *name, unsigned long pfn, const struct page *page, - unsigned int count, unsigned int align), + unsigned long count, unsigned int align), TP_ARGS(name, pfn, page, count, align) ); diff --git a/mm/cma.c b/mm/cma.c index cdad8c4de921..995e15480937 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -79,7 +79,7 @@ static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma, } static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, - unsigned int count) + unsigned long count) { unsigned long bitmap_no, bitmap_count; unsigned long flags; @@ -423,21 +423,21 @@ static inline void cma_debug_show_areas(struct cma *cma) { } * This function allocates part of contiguous memory on specific * contiguous memory area. */ -struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, - bool no_warn) +struct page *cma_alloc(struct cma *cma, unsigned long count, + unsigned int align, bool no_warn) { unsigned long mask, offset; unsigned long pfn = -1; unsigned long start = 0; unsigned long bitmap_maxno, bitmap_no, bitmap_count; - size_t i; + unsigned long i; struct page *page = NULL; int ret = -ENOMEM; if (!cma || !cma->count || !cma->bitmap) goto out; - pr_debug("%s(cma %p, count %zu, align %d)\n", __func__, (void *)cma, + pr_debug("%s(cma %p, count %lu, align %d)\n", __func__, (void *)cma, count, align); if (!count) @@ -505,7 +505,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align, } if (ret && !no_warn) { - pr_err_ratelimited("%s: %s: alloc failed, req-size: %zu pages, ret: %d\n", + pr_err_ratelimited("%s: %s: alloc failed, req-size: %lu pages, ret: %d\n", __func__, cma->name, count, ret); cma_debug_show_areas(cma); } @@ -534,14 +534,15 @@ out: * It returns false when provided pages do not belong to contiguous area and * true otherwise. */ -bool cma_release(struct cma *cma, const struct page *pages, unsigned int count) +bool cma_release(struct cma *cma, const struct page *pages, + unsigned long count) { unsigned long pfn; if (!cma || !pages) return false; - pr_debug("%s(page %p, count %u)\n", __func__, (void *)pages, count); + pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); pfn = page_to_pfn(pages); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 80754fc1f1ff..d12299c08b95 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8973,9 +8973,9 @@ struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, } #endif /* CONFIG_CONTIG_ALLOC */ -void free_contig_range(unsigned long pfn, unsigned int nr_pages) +void free_contig_range(unsigned long pfn, unsigned long nr_pages) { - unsigned int count = 0; + unsigned long count = 0; for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); @@ -8983,7 +8983,7 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) count += page_count(page) != 1; __free_page(page); } - WARN(count != 0, "%d pages are still in use!\n", count); + WARN(count != 0, "%lu pages are still in use!\n", count); } EXPORT_SYMBOL(free_contig_range); -- cgit v1.2.3 From d1e153fea2a8940273174fc17733c44323d35cd5 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Tue, 4 May 2021 18:39:08 -0700 Subject: mm/gup: migrate pinned pages out of movable zone We should not pin pages in ZONE_MOVABLE. Currently, we do not pin only movable CMA pages. Generalize the function that migrates CMA pages to migrate all movable pages. Use is_pinnable_page() to check which pages need to be migrated Link: https://lkml.kernel.org/r/20210215161349.246722-10-pasha.tatashin@soleen.com Signed-off-by: Pavel Tatashin Reviewed-by: John Hubbard Cc: Dan Williams Cc: David Hildenbrand Cc: David Rientjes Cc: Ingo Molnar Cc: Ira Weiny Cc: James Morris Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Peter Zijlstra Cc: Sasha Levin Cc: Steven Rostedt (VMware) Cc: Tyler Hicks Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 1 + include/linux/mmzone.h | 9 ++++-- include/trace/events/migrate.h | 3 +- mm/gup.c | 67 +++++++++++++++++++++--------------------- 4 files changed, 44 insertions(+), 36 deletions(-) (limited to 'include/trace') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 175ef15ae9e8..4bb4e519e3f5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -27,6 +27,7 @@ enum migrate_reason { MR_MEMPOLICY_MBIND, MR_NUMA_MISPLACED, MR_CONTIG_RANGE, + MR_LONGTERM_PIN, MR_TYPES }; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 92b44149d5b9..e8922a67d1a4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -407,8 +407,13 @@ enum zone_type { * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might - * essentially turn such pages unmovable. Memory offlining might - * retry a long time. + * essentially turn such pages unmovable. Therefore, we do not allow + * pinning long-term pages in ZONE_MOVABLE. When pages are pinned and + * faulted, they come from the right zone right away. However, it is + * still possible that address space already has pages in + * ZONE_MOVABLE at the time when pages are pinned (i.e. user has + * touches that memory before pinning). In such case we migrate them + * to a different zone. When migration fails - pinning fails. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index f2c990603888..9fb2a3bbcdfb 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -20,7 +20,8 @@ EM( MR_SYSCALL, "syscall_or_cpuset") \ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ - EMe(MR_CONTIG_RANGE, "contig_range") + EM( MR_CONTIG_RANGE, "contig_range") \ + EMe(MR_LONGTERM_PIN, "longterm_pin") /* * First define the enums in the above macros to be exported to userspace diff --git a/mm/gup.c b/mm/gup.c index a1eff7ad31da..4bc57420f535 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -87,11 +87,12 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, int orig_refs = refs; /* - * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast - * path, so fail and let the caller fall back to the slow path. + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. */ - if (unlikely(flags & FOLL_LONGTERM) && - is_migrate_cma_page(page)) + if (unlikely((flags & FOLL_LONGTERM) && + !is_pinnable_page(page))) return NULL; /* @@ -1600,17 +1601,17 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ -#ifdef CONFIG_CMA -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +#ifdef CONFIG_MIGRATION +static long check_and_migrate_movable_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) { unsigned long i, isolation_error_count; bool drain_allow; - LIST_HEAD(cma_page_list); + LIST_HEAD(movable_page_list); long ret = nr_pages; struct page *prev_head, *head; struct migration_target_control mtc = { @@ -1628,13 +1629,12 @@ check_again: continue; prev_head = head; /* - * If we get a page from the CMA zone, since we are going to - * be pinning these entries, we might as well move them out - * of the CMA zone if possible. + * If we get a movable page, since we are going to be pinning + * these entries, try to move them out if possible. */ - if (is_migrate_cma_page(head)) { + if (!is_pinnable_page(head)) { if (PageHuge(head)) { - if (!isolate_huge_page(head, &cma_page_list)) + if (!isolate_huge_page(head, &movable_page_list)) isolation_error_count++; } else { if (!PageLRU(head) && drain_allow) { @@ -1646,7 +1646,7 @@ check_again: isolation_error_count++; continue; } - list_add_tail(&head->lru, &cma_page_list); + list_add_tail(&head->lru, &movable_page_list); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_lru(head), @@ -1659,10 +1659,10 @@ check_again: * If list is empty, and no isolation errors, means that all pages are * in the correct zone. */ - if (list_empty(&cma_page_list) && !isolation_error_count) + if (list_empty(&movable_page_list) && !isolation_error_count) return ret; - if (!list_empty(&cma_page_list)) { + if (!list_empty(&movable_page_list)) { /* * drop the above get_user_pages reference. */ @@ -1672,12 +1672,12 @@ check_again: for (i = 0; i < nr_pages; i++) put_page(pages[i]); - ret = migrate_pages(&cma_page_list, alloc_migration_target, + ret = migrate_pages(&movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, - MR_CONTIG_RANGE); + MR_LONGTERM_PIN); if (ret) { - if (!list_empty(&cma_page_list)) - putback_movable_pages(&cma_page_list); + if (!list_empty(&movable_page_list)) + putback_movable_pages(&movable_page_list); return ret > 0 ? -ENOMEM : ret; } @@ -1696,16 +1696,16 @@ check_again: goto check_again; } #else -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +static long check_and_migrate_movable_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) { return nr_pages; } -#endif /* CONFIG_CMA */ +#endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which @@ -1729,8 +1729,9 @@ static long __gup_longterm_locked(struct mm_struct *mm, if (gup_flags & FOLL_LONGTERM) { if (rc > 0) - rc = check_and_migrate_cma_pages(mm, start, rc, pages, - vmas, gup_flags); + rc = check_and_migrate_movable_pages(mm, start, rc, + pages, vmas, + gup_flags); memalloc_pin_restore(flags); } return rc; -- cgit v1.2.3