Skip to content

Commit

Permalink
ice: move netif_queue_set_napi to rtnl-protected sections
Browse files Browse the repository at this point in the history 
Currently, netif_queue_set_napi() is called from ice_vsi_rebuild() that is
not rtnl-locked when called from the reset. This creates the need to take
the rtnl_lock just for a single function and complicates the
synchronization with .ndo_bpf. At the same time, there no actual need to
fill napi-to-queue information at this exact point.

Fill napi-to-queue information when opening the VSI and clear it when the
VSI is being closed. Those routines are already rtnl-locked.

Also, rewrite napi-to-queue assignment in a way that prevents inclusion of
XDP queues, as this leads to out-of-bounds writes, such as one below.

[  +0.000004] BUG: KASAN: slab-out-of-bounds in netif_queue_set_napi+0x1c2/0x1e0
[  +0.000012] Write of size 8 at addr ffff889881727c80 by task bash/7047
[  +0.000006] CPU: 24 PID: 7047 Comm: bash Not tainted 6.10.0-rc2+ #2
[  +0.000004] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0014.082620210524 08/26/2021
[  +0.000003] Call Trace:
[  +0.000003]  <TASK>
[  +0.000002]  dump_stack_lvl+0x60/0x80
[  +0.000007]  print_report+0xce/0x630
[  +0.000007]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[  +0.000007]  ? __virt_addr_valid+0x1c9/0x2c0
[  +0.000005]  ? netif_queue_set_napi+0x1c2/0x1e0
[  +0.000003]  kasan_report+0xe9/0x120
[  +0.000004]  ? netif_queue_set_napi+0x1c2/0x1e0
[  +0.000004]  netif_queue_set_napi+0x1c2/0x1e0
[  +0.000005]  ice_vsi_close+0x161/0x670 [ice]
[  +0.000114]  ice_dis_vsi+0x22f/0x270 [ice]
[  +0.000095]  ice_pf_dis_all_vsi.constprop.0+0xae/0x1c0 [ice]
[  +0.000086]  ice_prepare_for_reset+0x299/0x750 [ice]
[  +0.000087]  pci_dev_save_and_disable+0x82/0xd0
[  +0.000006]  pci_reset_function+0x12d/0x230
[  +0.000004]  reset_store+0xa0/0x100
[  +0.000006]  ? __pfx_reset_store+0x10/0x10
[  +0.000002]  ? __pfx_mutex_lock+0x10/0x10
[  +0.000004]  ? __check_object_size+0x4c1/0x640
[  +0.000007]  kernfs_fop_write_iter+0x30b/0x4a0
[  +0.000006]  vfs_write+0x5d6/0xdf0
[  +0.000005]  ? fd_install+0x180/0x350
[  +0.000005]  ? __pfx_vfs_write+0x10/0xA10
[  +0.000004]  ? do_fcntl+0x52c/0xcd0
[  +0.000004]  ? kasan_save_track+0x13/0x60
[  +0.000003]  ? kasan_save_free_info+0x37/0x60
[  +0.000006]  ksys_write+0xfa/0x1d0
[  +0.000003]  ? __pfx_ksys_write+0x10/0x10
[  +0.000002]  ? __x64_sys_fcntl+0x121/0x180
[  +0.000004]  ? _raw_spin_lock+0x87/0xe0
[  +0.000005]  do_syscall_64+0x80/0x170
[  +0.000007]  ? _raw_spin_lock+0x87/0xe0
[  +0.000004]  ? __pfx__raw_spin_lock+0x10/0x10
[  +0.000003]  ? file_close_fd_locked+0x167/0x230
[  +0.000005]  ? syscall_exit_to_user_mode+0x7d/0x220
[  +0.000005]  ? do_syscall_64+0x8c/0x170
[  +0.000004]  ? do_syscall_64+0x8c/0x170
[  +0.000003]  ? do_syscall_64+0x8c/0x170
[  +0.000003]  ? fput+0x1a/0x2c0
[  +0.000004]  ? filp_close+0x19/0x30
[  +0.000004]  ? do_dup2+0x25a/0x4c0
[  +0.000004]  ? __x64_sys_dup2+0x6e/0x2e0
[  +0.000002]  ? syscall_exit_to_user_mode+0x7d/0x220
[  +0.000004]  ? do_syscall_64+0x8c/0x170
[  +0.000003]  ? __count_memcg_events+0x113/0x380
[  +0.000005]  ? handle_mm_fault+0x136/0x820
[  +0.000005]  ? do_user_addr_fault+0x444/0xa80
[  +0.000004]  ? clear_bhb_loop+0x25/0x80
[  +0.000004]  ? clear_bhb_loop+0x25/0x80
[  +0.000002]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000005] RIP: 0033:0x7f2033593154

Fixes: 080b0c8 ("ice: Fix ASSERT_RTNL() warning during certain scenarios")
Fixes: 91fdbce ("ice: Add support in the driver for associating queue with napi")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
  • Loading branch information
@walking-machine @anguy11
walking-machine authored and anguy11 committed Sep 3, 2024
1 parent cfd433c commit 2a5dc09
Show file tree
Hide file tree
Showing 4 changed files with 49 additions and 118 deletions.
11 changes: 3 additions & 8 deletions drivers/net/ethernet/intel/ice/ice_base.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -190,16 +190,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
}
q_vector = vsi->q_vectors[v_idx];

ice_for_each_tx_ring(tx_ring, q_vector->tx) {
ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX,
NULL);
ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx)
tx_ring->q_vector = NULL;
}
ice_for_each_rx_ring(rx_ring, q_vector->rx) {
ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX,
NULL);

ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx)
rx_ring->q_vector = NULL;
}

/* only VSI with an associated netdev is set up with NAPI */
if (vsi->netdev)
Expand Down
129 changes: 31 additions & 98 deletions drivers/net/ethernet/intel/ice/ice_lib.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2286,9 +2286,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)

ice_vsi_map_rings_to_vectors(vsi);

/* Associate q_vector rings to napi */
ice_vsi_set_napi_queues(vsi);

vsi->stat_offsets_loaded = false;

/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
Expand Down Expand Up @@ -2628,6 +2625,7 @@ void ice_vsi_close(struct ice_vsi *vsi)
if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state))
ice_down(vsi);

ice_vsi_clear_napi_queues(vsi);
ice_vsi_free_irq(vsi);
ice_vsi_free_tx_rings(vsi);
ice_vsi_free_rx_rings(vsi);
Expand Down Expand Up @@ -2694,120 +2692,55 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
}

/**
* __ice_queue_set_napi - Set the napi instance for the queue
* @dev: device to which NAPI and queue belong
* @queue_index: Index of queue
* @type: queue type as RX or TX
* @napi: NAPI context
* @locked: is the rtnl_lock already held
*
* Set the napi instance for the queue. Caller indicates the lock status.
*/
static void
__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
enum netdev_queue_type type, struct napi_struct *napi,
bool locked)
{
if (!locked)
rtnl_lock();
netif_queue_set_napi(dev, queue_index, type, napi);
if (!locked)
rtnl_unlock();
}

/**
* ice_queue_set_napi - Set the napi instance for the queue
* @vsi: VSI being configured
* @queue_index: Index of queue
* @type: queue type as RX or TX
* @napi: NAPI context
* ice_vsi_set_napi_queues - associate netdev queues with napi
* @vsi: VSI pointer
*
* Set the napi instance for the queue. The rtnl lock state is derived from the
* execution path.
* Associate queue[s] with napi for all vectors.
* The caller must hold rtnl_lock.
*/
void
ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
enum netdev_queue_type type, struct napi_struct *napi)
void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
{
struct ice_pf *pf = vsi->back;
struct net_device *netdev = vsi->netdev;
int q_idx, v_idx;

if (!vsi->netdev)
if (!netdev)
return;

if (current_work() == &pf->serv_task ||
test_bit(ICE_PREPARED_FOR_RESET, pf->state) ||
test_bit(ICE_DOWN, pf->state) ||
test_bit(ICE_SUSPENDED, pf->state))
__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
false);
else
__ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
true);
}
ice_for_each_rxq(vsi, q_idx)
netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX,
&vsi->rx_rings[q_idx]->q_vector->napi);

/**
* __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
* @q_vector: q_vector pointer
* @locked: is the rtnl_lock already held
*
* Associate the q_vector napi with all the queue[s] on the vector.
* Caller indicates the lock status.
*/
void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
{
struct ice_rx_ring *rx_ring;
struct ice_tx_ring *tx_ring;

ice_for_each_rx_ring(rx_ring, q_vector->rx)
__ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
locked);

ice_for_each_tx_ring(tx_ring, q_vector->tx)
__ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
locked);
ice_for_each_txq(vsi, q_idx)
netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX,
&vsi->tx_rings[q_idx]->q_vector->napi);
/* Also set the interrupt number for the NAPI */
netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
}
ice_for_each_q_vector(vsi, v_idx) {
struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];

/**
* ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
* @q_vector: q_vector pointer
*
* Associate the q_vector napi with all the queue[s] on the vector
*/
void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector)
{
struct ice_rx_ring *rx_ring;
struct ice_tx_ring *tx_ring;

ice_for_each_rx_ring(rx_ring, q_vector->rx)
ice_queue_set_napi(q_vector->vsi, rx_ring->q_index,
NETDEV_QUEUE_TYPE_RX, &q_vector->napi);

ice_for_each_tx_ring(tx_ring, q_vector->tx)
ice_queue_set_napi(q_vector->vsi, tx_ring->q_index,
NETDEV_QUEUE_TYPE_TX, &q_vector->napi);
/* Also set the interrupt number for the NAPI */
netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
}
}

/**
* ice_vsi_set_napi_queues
* ice_vsi_clear_napi_queues - dissociate netdev queues from napi
* @vsi: VSI pointer
*
* Associate queue[s] with napi for all vectors
* Clear the association between all VSI queues queue[s] and napi.
* The caller must hold rtnl_lock.
*/
void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
{
int i;
struct net_device *netdev = vsi->netdev;
int q_idx;

if (!vsi->netdev)
if (!netdev)
return;

ice_for_each_q_vector(vsi, i)
ice_q_vector_set_napi_queues(vsi->q_vectors[i]);
ice_for_each_txq(vsi, q_idx)
netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);

ice_for_each_rxq(vsi, q_idx)
netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL);
}

/**
Expand Down
10 changes: 2 additions & 8 deletions drivers/net/ethernet/intel/ice/ice_lib.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -44,16 +44,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
struct ice_vsi *
ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);

void
ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
enum netdev_queue_type type, struct napi_struct *napi);

void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);

void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector);

void ice_vsi_set_napi_queues(struct ice_vsi *vsi);

void ice_vsi_clear_napi_queues(struct ice_vsi *vsi);

int ice_vsi_release(struct ice_vsi *vsi);

void ice_vsi_close(struct ice_vsi *vsi);
Expand Down
17 changes: 13 additions & 4 deletions drivers/net/ethernet/intel/ice/ice_main.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3558,11 +3558,9 @@ static void ice_napi_add(struct ice_vsi *vsi)
if (!vsi->netdev)
return;

ice_for_each_q_vector(vsi, v_idx) {
ice_for_each_q_vector(vsi, v_idx)
netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
ice_napi_poll);
__ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
}
}

/**
Expand Down Expand Up @@ -5540,7 +5538,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
if (ret)
goto err_reinit;
ice_vsi_map_rings_to_vectors(pf->vsi[v]);
rtnl_lock();
ice_vsi_set_napi_queues(pf->vsi[v]);
rtnl_unlock();
}

ret = ice_req_irq_msix_misc(pf);
Expand All @@ -5554,8 +5554,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)

err_reinit:
while (v--)
if (pf->vsi[v])
if (pf->vsi[v]) {
rtnl_lock();
ice_vsi_clear_napi_queues(pf->vsi[v]);
rtnl_unlock();
ice_vsi_free_q_vectors(pf->vsi[v]);
}

return ret;
}
Expand Down Expand Up @@ -5620,6 +5624,9 @@ static int ice_suspend(struct device *dev)
ice_for_each_vsi(pf, v) {
if (!pf->vsi[v])
continue;
rtnl_lock();
ice_vsi_clear_napi_queues(pf->vsi[v]);
rtnl_unlock();
ice_vsi_free_q_vectors(pf->vsi[v]);
}
ice_clear_interrupt_scheme(pf);
Expand Down Expand Up @@ -7455,6 +7462,8 @@ int ice_vsi_open(struct ice_vsi *vsi)
err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq);
if (err)
goto err_set_qs;

ice_vsi_set_napi_queues(vsi);
}

err = ice_up_complete(vsi);
Expand Down

0 comments on commit 2a5dc09

Please sign in to comment.