From: Yacan Liu <liuyacan@corp.netease.com>
Date: Tue, 6 Sep 2022 21:01:39 +0800
Subject: net/smc: Fix possible access to freed memory in link clear
Git-commit: e9b1a4f867ae9c1dbd1d71cd09cbdb3239fb4968
Patch-mainline: v6.0-rc5
References: git-fixes

After modifying the QP to the Error state, all RX WR would be completed
with WC in IB_WC_WR_FLUSH_ERR status. Current implementation does not
wait for it is done, but destroy the QP and free the link group directly.
So there is a risk that accessing the freed memory in tasklet context.

Here is a crash example:

 BUG: unable to handle page fault for address: ffffffff8f220860
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0002) - not-present page
 PGD f7300e067 P4D f7300e067 PUD f7300f063 PMD 8c4e45063 PTE 800ffff08c9df060
 Oops: 0002 [#1] SMP PTI
 CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: G S         OE     5.10.0-0607+ #23
 Hardware name: Inspur NF5280M4/YZMB-00689-101, BIOS 4.1.20 07/09/2018
 RIP: 0010:native_queued_spin_lock_slowpath+0x176/0x1b0
 Code: f3 90 48 8b 32 48 85 f6 74 f6 eb d5 c1 ee 12 83 e0 03 83 ee 01 48 c1 e0 05 48 63 f6 48 05 00 c8 02 00 48 03 04 f5 00 09 98 8e <48> 89 10 8b 42 08 85 c0 75 09 f3 90 8b 42 08 85 c0 74 f7 48 8b 32
 RSP: 0018:ffffb3b6c001ebd8 EFLAGS: 00010086
 RAX: ffffffff8f220860 RBX: 0000000000000246 RCX: 0000000000080000
 RDX: ffff91db1f86c800 RSI: 000000000000173c RDI: ffff91db62bace00
 RBP: ffff91db62bacc00 R08: 0000000000000000 R09: c00000010000028b
 R10: 0000000000055198 R11: ffffb3b6c001ea58 R12: ffff91db80e05010
 R13: 000000000000000a R14: 0000000000000006 R15: 0000000000000040
 FS:  0000000000000000(0000) GS:ffff91db1f840000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: ffffffff8f220860 CR3: 00000001f9580004 CR4: 00000000003706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 Call Trace:
  <IRQ>
  _raw_spin_lock_irqsave+0x30/0x40
  mlx5_ib_poll_cq+0x4c/0xc50 [mlx5_ib]
  smc_wr_rx_tasklet_fn+0x56/0xa0 [smc]
  tasklet_action_common.isra.21+0x66/0x100
  __do_softirq+0xd5/0x29c
  asm_call_irq_on_stack+0x12/0x20
  </IRQ>
  do_softirq_own_stack+0x37/0x40
  irq_exit_rcu+0x9d/0xa0
  sysvec_call_function_single+0x34/0x80
  asm_sysvec_call_function_single+0x12/0x20

Fixes: bd4ad57718cc ("smc: initialize IB transport incl. PD, MR, QP, CQ, event, WR")
Signed-off-by: Yacan Liu <liuyacan@corp.netease.com>
Reviewed-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 net/smc/smc_core.c |    1 +
 net/smc/smc_core.h |    2 ++
 net/smc/smc_wr.c   |    5 +++++
 net/smc/smc_wr.h   |    5 +++++
 4 files changed, 13 insertions(+)

--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -750,6 +750,7 @@ int smcr_link_init(struct smc_link_group
 	lnk->link_id = smcr_next_link_id(lgr);
 	lnk->lgr = lgr;
 	lnk->link_idx = link_idx;
+	lnk->wr_rx_id_compl = 0;
 	smc_ibdev_cnt_inc(lnk);
 	smcr_copy_dev_info_to_link(lnk);
 	atomic_set(&lnk->conn_cnt, 0);
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -115,8 +115,10 @@ struct smc_link {
 	dma_addr_t		wr_rx_dma_addr;	/* DMA address of wr_rx_bufs */
 	dma_addr_t		wr_rx_v2_dma_addr; /* DMA address of v2 rx buf*/
 	u64			wr_rx_id;	/* seq # of last recv WR */
+	u64			wr_rx_id_compl; /* seq # of last completed WR */
 	u32			wr_rx_cnt;	/* number of WR recv buffers */
 	unsigned long		wr_rx_tstamp;	/* jiffies when last buf rx */
+	wait_queue_head_t       wr_rx_empty_wait; /* wait for RQ empty */
 
 	struct ib_reg_wr	wr_reg;		/* WR register memory region */
 	wait_queue_head_t	wr_reg_wait;	/* wait for wr_reg result */
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -458,6 +458,7 @@ static inline void smc_wr_rx_process_cqe
 
 	for (i = 0; i < num; i++) {
 		link = wc[i].qp->qp_context;
+		link->wr_rx_id_compl = wc[i].wr_id;
 		if (wc[i].status == IB_WC_SUCCESS) {
 			link->wr_rx_tstamp = jiffies;
 			smc_wr_rx_demultiplex(&wc[i]);
@@ -469,6 +470,8 @@ static inline void smc_wr_rx_process_cqe
 			case IB_WC_RNR_RETRY_EXC_ERR:
 			case IB_WC_WR_FLUSH_ERR:
 				smcr_link_down_cond_sched(link);
+				if (link->wr_rx_id_compl == link->wr_rx_id)
+					wake_up(&link->wr_rx_empty_wait);
 				break;
 			default:
 				smc_wr_rx_post(link); /* refill WR RX */
@@ -640,6 +643,7 @@ void smc_wr_free_link(struct smc_link *l
 		return;
 	ibdev = lnk->smcibdev->ibdev;
 
+	smc_wr_drain_cq(lnk);
 	smc_wr_wakeup_reg_wait(lnk);
 	smc_wr_wakeup_tx_wait(lnk);
 
@@ -893,6 +897,7 @@ int smc_wr_create_link(struct smc_link *
 	atomic_set(&lnk->wr_tx_refcnt, 0);
 	init_waitqueue_head(&lnk->wr_reg_wait);
 	atomic_set(&lnk->wr_reg_refcnt, 0);
+	init_waitqueue_head(&lnk->wr_rx_empty_wait);
 	return rc;
 
 dma_unmap:
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -73,6 +73,11 @@ static inline void smc_wr_tx_link_put(st
 		wake_up_all(&link->wr_tx_wait);
 }
 
+static inline void smc_wr_drain_cq(struct smc_link *lnk)
+{
+	wait_event(lnk->wr_rx_empty_wait, lnk->wr_rx_id_compl == lnk->wr_rx_id);
+}
+
 static inline void smc_wr_wakeup_tx_wait(struct smc_link *lnk)
 {
 	wake_up_all(&lnk->wr_tx_wait);