ice: arfs: fix use-after-free when freeing @rx_cpu_rmap
Subsystems (3)
From: Alexander Lobakin <[email protected]>
[ Upstream commit d7442f512b71fc63a99c8a801422dde4fbbf9f93 ]
The CI testing bots triggered the following splat:
[ 718.203054] BUG: KASAN: use-after-free in free_irq_cpu_rmap+0x53/0x80
[ 718.206349] Read of size 4 at addr ffff8881bd127e00 by task sh/20834
[ 718.212852] CPU: 28 PID: 20834 Comm: sh Kdump: loaded Tainted: G S W IOE 5.17.0-rc8_nextqueue-devqueue-02643-g23f3121aca93 #1
[ 718.219695] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0012.070720200218 07/07/2020
[ 718.223418] Call Trace:
[ 718.227139]
[ 718.230783] dump_stack_lvl+0x33/0x42
[ 718.234431] print_address_description.constprop.9+0x21/0x170
[ 718.238177] ? free_irq_cpu_rmap+0x53/0x80
[ 718.241885] ? free_irq_cpu_rmap+0x53/0x80
[ 718.245539] kasan_report.cold.18+0x7f/0x11b
[ 718.249197] ? free_irq_cpu_rmap+0x53/0x80
[ 718.252852] free_irq_cpu_rmap+0x53/0x80
[ 718.256471] ice_free_cpu_rx_rmap.part.11+0x37/0x50 [ice]
[ 718.260174] ice_remove_arfs+0x5f/0x70 [ice]
[ 718.263810] ice_rebuild_arfs+0x3b/0x70 [ice]
[ 718.267419] ice_rebuild+0x39c/0xb60 [ice]
[ 718.270974] ? asm_sysvec_apic_timer_interrupt+0x12/0x20
[ 718.274472] ? ice_init_phy_user_cfg+0x360/0x360 [ice]
[ 718.278033] ? delay_tsc+0x4a/0xb0
[ 718.281513] ? preempt_count_sub+0x14/0xc0
[ 718.284984] ? delay_tsc+0x8f/0xb0
[ 718.288463] ice_do_reset+0x92/0xf0 [ice]
[ 718.292014] ice_pci_err_resume+0x91/0xf0 [ice]
[ 718.295561] pci_reset_function+0x53/0x80
<...>
[ 718.393035] Allocated by task 690:
[ 718.433497] Freed by task 20834:
[ 718.495688] Last potentially related work creation:
[ 718.568966] The buggy address belongs to the object at ffff8881bd127e00
which belongs to the cache kmalloc-96 of size 96
[ 718.574085] The buggy address is located 0 bytes inside of
96-byte region [ffff8881bd127e00, ffff8881bd127e60)
[ 718.579265] The buggy address belongs to the page:
[ 718.598905] Memory state around the buggy address:
[ 718.601809] ffff8881bd127d00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
[ 718.604796] ffff8881bd127d80: 00 00 00 00 00 00 00 00 00 00 fc fc fc fc fc fc
[ 718.607794] >ffff8881bd127e00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
[ 718.610811] ^
[ 718.613819] ffff8881bd127e80: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc
[ 718.617107] ffff8881bd127f00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fcThis is due to that free_irq_cpu_rmap() is always being called *after* (devm_)free_irq() and thus it tries to work with IRQ descs already freed. For example, on device reset the driver frees the rmap right before allocating a new one (the splat above). Make rmap creation and freeing function symmetrical with {request,free}_irq() calls i.e. do that on ifup/ifdown instead of device probe/remove/resume. These operations can be performed independently from the actual device aRFS configuration. Also, make sure ice_vsi_free_irq() clears IRQ affinity notifiers only when aRFS is disabled -- otherwise, CPU rmap sets and clears its own and they must not be touched manually.
--- drivers/net/ethernet/intel/ice/ice_arfs.c | 9 ++------- drivers/net/ethernet/intel/ice/ice_lib.c | 5 ++++- drivers/net/ethernet/intel/ice/ice_main.c | 20 ++++++++------------ 3 files changed, 14 insertions(+), 20 deletions(-)
drivers/net/ethernet/intel/ice/ice_arfs.c +2 -7
@@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) {struct net_device *netdev; -if (!vsi || vsi->type !=ICE_VSI_PF || !vsi->arfs_fltr_list) +if (!vsi || vsi->type !=ICE_VSI_PF )return ; netdev = vsi->netdev;
@@ -600,7 +600,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)int base_idx, i;if (!vsi || vsi->type !=ICE_VSI_PF ) -return -EINVAL ; +return 0 ; pf = vsi->back; netdev = vsi->netdev;
@@ -638,7 +638,6 @@ void ice_remove_arfs(struct ice_pf *pf)if (!pf_vsi)return ; -ice_free_cpu_rx_rmap (pf_vsi);ice_clear_arfs (pf_vsi); }
@@ -655,9 +654,5 @@ void ice_rebuild_arfs(struct ice_pf *pf)return ;ice_remove_arfs (pf); -if (ice_set_cpu_rx_rmap (pf_vsi)) { -dev_err (ice_pf_to_dev (pf),"Failed to rebuild aRFS\n" ); -return ; - }ice_init_arfs (pf_vsi); }
drivers/net/ethernet/intel/ice/ice_lib.c +4 -1
@@ -2411,6 +2411,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)return ; vsi->irqs_ready = false; +ice_free_cpu_rx_rmap (vsi); +ice_for_each_q_vector (vsi, i) {u16 vector = i + base;int irq_num;
@@ -2424,7 +2426,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)continue ;/* clear the affinity notifier in the IRQ descriptor */ -irq_set_affinity_notifier (irq_num,NULL ); +if (!IS_ENABLED (CONFIG_RFS_ACCEL )) +irq_set_affinity_notifier (irq_num,NULL );/* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint (irq_num,NULL );
drivers/net/ethernet/intel/ice/ice_main.c +8 -12
@@ -2247,6 +2247,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)irq_set_affinity_hint (irq_num, &q_vector->affinity_mask); } + err =ice_set_cpu_rx_rmap (vsi); +if (err) { +netdev_err (vsi->netdev,"Failed to setup CPU RMAP on VSI %u: %pe\n" , + vsi->vsi_num,ERR_PTR (err)); + goto free_q_irqs; + } + vsi->irqs_ready = true;return 0 ;
@@ -3242,22 +3249,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf)*/ ice_napi_add (vsi); - status =ice_set_cpu_rx_rmap (vsi); -if (status) { -dev_err (ice_pf_to_dev (pf),"Failed to set CPU Rx map VSI %d error %d\n" , - vsi->vsi_num, status); - status = -EINVAL ; - goto unroll_napi_add; - } status =ice_init_mac_fltr (pf);if (status) - goto free_cpu_rx_map; + goto unroll_napi_add;return status; -free_cpu_rx_map: -ice_free_cpu_rx_rmap (vsi); - unroll_napi_add:if (vsi) {ice_napi_del (vsi);
@@ -4598,7 +4595,6 @@ static int __maybe_unused ice_suspend(struct device *dev)continue ;ice_vsi_free_q_vectors (pf->vsi[v]); } -ice_free_cpu_rx_rmap (ice_get_main_vsi (pf));ice_clear_interrupt_scheme (pf);pci_save_state (pdev);
Signature · 1 line
2.47.1