[PATCH iwl-net 1/3] ice: synchronize XDP setup with reset

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



XDP setup and PF reset code access the same resources in the following
sections:
* ice_vsi_close() in ice_prepare_for_reset() - already rtnl-locked
* ice_vsi_rebuild() for the PF VSI - not protected

With an unfortunate timing, such accesses can result in a crash such as the
one below:

[ +1.999878] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 14
[ +2.002992] ice 0000:b1:00.0: Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring 18
[Mar15 18:17] ice 0000:b1:00.0 ens801f0np0: NETDEV WATCHDOG: CPU: 38: transmit queue 14 timed out 80692736 ms
[ +0.000093] ice 0000:b1:00.0 ens801f0np0: tx_timeout: VSI_num: 6, Q 14, NTC: 0x0, HW_HEAD: 0x0, NTU: 0x0, INT: 0x4000001
[ +0.000012] ice 0000:b1:00.0 ens801f0np0: tx_timeout recovery level 1, txqueue 14
[ +0.394718] ice 0000:b1:00.0: PTP reset successful
[ +0.006184] BUG: kernel NULL pointer dereference, address: 0000000000000098
[ +0.000045] #PF: supervisor read access in kernel mode
[ +0.000023] #PF: error_code(0x0000) - not-present page
[ +0.000023] PGD 0 P4D 0
[ +0.000018] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ +0.000023] CPU: 38 PID: 7540 Comm: kworker/38:1 Not tainted 6.8.0-rc7 #1
[ +0.000031] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021
[ +0.000036] Workqueue: ice ice_service_task [ice]
[ +0.000183] RIP: 0010:ice_clean_tx_ring+0xa/0xd0 [ice]
[...]
[ +0.000013] Call Trace:
[ +0.000016] <TASK>
[ +0.000014] ? __die+0x1f/0x70
[ +0.000029] ? page_fault_oops+0x171/0x4f0
[ +0.000029] ? schedule+0x3b/0xd0
[ +0.000027] ? exc_page_fault+0x7b/0x180
[ +0.000022] ? asm_exc_page_fault+0x22/0x30
[ +0.000031] ? ice_clean_tx_ring+0xa/0xd0 [ice]
[ +0.000194] ice_free_tx_ring+0xe/0x60 [ice]
[ +0.000186] ice_destroy_xdp_rings+0x157/0x310 [ice]
[ +0.000151] ice_vsi_decfg+0x53/0xe0 [ice]
[ +0.000180] ice_vsi_rebuild+0x239/0x540 [ice]
[ +0.000186] ice_vsi_rebuild_by_type+0x76/0x180 [ice]
[ +0.000145] ice_rebuild+0x18c/0x840 [ice]
[ +0.000145] ? delay_tsc+0x4a/0xc0
[ +0.000022] ? delay_tsc+0x92/0xc0
[ +0.000020] ice_do_reset+0x140/0x180 [ice]
[ +0.000886] ice_service_task+0x404/0x1030 [ice]
[ +0.000824] process_one_work+0x171/0x340
[ +0.000685] worker_thread+0x277/0x3a0
[ +0.000675] ? preempt_count_add+0x6a/0xa0
[ +0.000677] ? _raw_spin_lock_irqsave+0x23/0x50
[ +0.000679] ? __pfx_worker_thread+0x10/0x10
[ +0.000653] kthread+0xf0/0x120
[ +0.000635] ? __pfx_kthread+0x10/0x10
[ +0.000616] ret_from_fork+0x2d/0x50
[ +0.000612] ? __pfx_kthread+0x10/0x10
[ +0.000604] ret_from_fork_asm+0x1b/0x30
[ +0.000604] </TASK>

The previous way of handling this through returning -EBUSY is not viable,
particularly when destroying AF_XDP socket, because the kernel proceeds
with removal anyway.

There is plenty of code between those calls and there is no need to create
a large critical section that covers them both, same as there is no need to
protect ice_vsi_rebuild() with rtnl_lock().

Leaving an unprotexted section in between would result in a state, when the
VSI is closed, but not yet rebuild, such situation can be handled pretty
easily.

Lock ice_vsi_rebuild() with ICE_CFG_BUSY flag. Particularly, to prevent
system crash, when tx_timeout and .ndo_bpf() happen at the same time.
Also, handle the state between critical sections by skipping XDP ring
configuration.

Fixes: efc2214b6047 ("ice: Add support for XDP")
Reviewed-by: Igor Bagnucki <igor.bagnucki@xxxxxxxxx>
Signed-off-by: Larysa Zaremba <larysa.zaremba@xxxxxxxxx>
---
 drivers/net/ethernet/intel/ice/ice_lib.c  |  5 +++-
 drivers/net/ethernet/intel/ice/ice_main.c | 36 +++++++++++++++++++----
 2 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 7629b0190578..4774bcc4d5a8 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2426,7 +2426,10 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 		dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
 			vsi->vsi_num, err);
 
-	if (ice_is_xdp_ena_vsi(vsi))
+	/* xdp_rings can be absent, if program was attached amid reset,
+	 * VSI rebuild is supposed to create them later
+	 */
+	if (ice_is_xdp_ena_vsi(vsi) && vsi->xdp_rings)
 		/* return value check can be skipped here, it always returns
 		 * 0 if reset is in progress
 		 */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 15a6805ac2a1..dc60d816a345 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2986,6 +2986,20 @@ static int ice_max_xdp_frame_size(struct ice_vsi *vsi)
 		return ICE_RXBUF_3072;
 }
 
+/**
+ * ice_rebuild_pending - ice_vsi_rebuild will be performed, when locks are released
+ * @vsi: VSI to setup XDP for
+ *
+ * ice_vsi_close() in the reset path is called under rtnl_lock(),
+ * so it happens strictly before or after .ndo_bpf().
+ * In case it has happened before, we do not have anything attached to rings
+ */
+static bool ice_rebuild_pending(struct ice_vsi *vsi)
+{
+	return ice_is_reset_in_progress(vsi->back->state) &&
+	       !vsi->rx_rings[0]->desc;
+}
+
 /**
  * ice_xdp_setup_prog - Add or remove XDP eBPF program
  * @vsi: VSI to setup XDP for
@@ -3009,7 +3023,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
 	}
 
 	/* hot swap progs and avoid toggling link */
-	if (ice_is_xdp_ena_vsi(vsi) == !!prog) {
+	if (ice_is_xdp_ena_vsi(vsi) == !!prog || ice_rebuild_pending(vsi)) {
 		ice_vsi_assign_bpf_prog(vsi, prog);
 		return 0;
 	}
@@ -3081,21 +3095,30 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	int ret;
 
 	if (vsi->type != ICE_VSI_PF) {
 		NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI");
 		return -EINVAL;
 	}
 
+	while (test_and_set_bit(ICE_CFG_BUSY, pf->state))
+		usleep_range(1000, 2000);
+
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
-		return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+		ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+		break;
 	case XDP_SETUP_XSK_POOL:
-		return ice_xsk_pool_setup(vsi, xdp->xsk.pool,
-					  xdp->xsk.queue_id);
+		ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id);
+		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
 	}
+
+	clear_bit(ICE_CFG_BUSY, pf->state);
+	return ret;
 }
 
 /**
@@ -7672,7 +7695,10 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 		ice_gnss_init(pf);
 
 	/* rebuild PF VSI */
+	while (test_and_set_bit(ICE_CFG_BUSY, pf->state))
+		usleep_range(1000, 2000);
 	err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF);
+	clear_bit(ICE_CFG_BUSY, pf->state);
 	if (err) {
 		dev_err(dev, "PF VSI rebuild failed: %d\n", err);
 		goto err_vsi_rebuild;
-- 
2.43.0





[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]


  Powered by Linux