[PATCH net-next 20/24] net: intel: Use nested-BH locking for XDP redirect.

From: Sebastian Andrzej Siewior
Date: Fri Dec 15 2023 - 12:17:13 EST

The per-CPU variables used during bpf_prog_run_xdp() invocation and
later during xdp_do_redirect() rely on disabled BH for their protection.
Without locking in local_bh_disable() on PREEMPT_RT these data structure
require explicit locking.

This is a follow-up on the previous change which introduced
bpf_run_lock.redirect_lock and uses it now within drivers.

The simple way is to acquire the lock before bpf_prog_run_xdp() is
invoked and hold it until the end of function.
This does not always work because some drivers (cpsw, atlantic) invoke
xdp_do_flush() in the same context.
Acquiring the lock in bpf_prog_run_xdp() and dropping in
xdp_do_redirect() (without touching drivers) does not work because not
all driver, which use bpf_prog_run_xdp(), do support XDP_REDIRECT (and
invoke xdp_do_redirect()).

Ideally the minimal locking scope would be bpf_prog_run_xdp() +
xdp_do_redirect() and everything else (error recovery, DMA unmapping,
free/ alloc of memory, …) would happen outside of the locked section.

Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Jesper Dangaard Brouer <hawk@xxxxxxxxxx>
Cc: Jesse Brandeburg <jesse.brandeburg@xxxxxxxxx>
Cc: John Fastabend <john.fastabend@xxxxxxxxx>
Cc: Tony Nguyen <anthony.l.nguyen@xxxxxxxxx>
Cc: bpf@xxxxxxxxxxxxxxx (open list:XDP
Cc: intel-wired-lan@xxxxxxxxxxxxxxxx
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
drivers/net/ethernet/intel/i40e/i40e_txrx.c | 1 +
drivers/net/ethernet/intel/i40e/i40e_xsk.c | 22 +++++++++--------
drivers/net/ethernet/intel/ice/ice_txrx.c | 1 +
drivers/net/ethernet/intel/ice/ice_xsk.c | 21 ++++++++--------
drivers/net/ethernet/intel/igb/igb_main.c | 1 +
drivers/net/ethernet/intel/igc/igc_main.c | 5 +++-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 1 +
drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 24 ++++++++++---------
.../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 3 ++-
9 files changed, 46 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index dd410b15000f7..76e069ae2183a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2326,6 +2326,7 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp, struct

prefetchw(xdp->data_hard_start); /* xdp_frame write */

+ guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock);
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index e99fa854d17f1..2b0c0c1f3ddc8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -201,17 +201,19 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp,
struct i40e_ring *xdp_ring;
u32 act;

- act = bpf_prog_run_xdp(xdp_prog, xdp);
+ scoped_guard(local_lock_nested_bh, &bpf_run_lock.redirect_lock) {
+ act = bpf_prog_run_xdp(xdp_prog, xdp);

- if (likely(act == XDP_REDIRECT)) {
- err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- if (!err)
- return I40E_XDP_REDIR;
- if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
- result = I40E_XDP_EXIT;
- else
- result = I40E_XDP_CONSUMED;
- goto out_failure;
+ if (likely(act == XDP_REDIRECT)) {
+ err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+ if (!err)
+ return I40E_XDP_REDIR;
+ if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+ result = I40E_XDP_EXIT;
+ else
+ result = I40E_XDP_CONSUMED;
+ goto out_failure;
+ }
}

switch (act) {
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 9e97ea8630686..5d4cfa3455b37 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -571,6 +571,7 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
if (!xdp_prog)
goto exit;

+ guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock);
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 99954508184f9..02f89c22d19e3 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -762,17 +762,18 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
int err, result = ICE_XDP_PASS;
u32 act;

+ scoped_guard(local_lock_nested_bh, &bpf_run_lock.redirect_lock) {
act = bpf_prog_run_xdp(xdp_prog, xdp);
-
- if (likely(act == XDP_REDIRECT)) {
- err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- if (!err)
- return ICE_XDP_REDIR;
- if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
- result = ICE_XDP_EXIT;
- else
- result = ICE_XDP_CONSUMED;
- goto out_failure;
+ if (likely(act == XDP_REDIRECT)) {
+ err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+ if (!err)
+ return ICE_XDP_REDIR;
+ if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+ result = ICE_XDP_EXIT;
+ else
+ result = ICE_XDP_CONSUMED;
+ goto out_failure;
+ }
}

switch (act) {
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b2295caa2f0ab..e01be809d030e 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8621,6 +8621,7 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,

prefetchw(xdp->data_hard_start); /* xdp_frame write */

+ guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock);
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e9bb403bbacf9..8321419b3a307 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2485,7 +2485,10 @@ static int __igc_xdp_run_prog(struct igc_adapter *adapter,
struct bpf_prog *prog,
struct xdp_buff *xdp)
{
- u32 act = bpf_prog_run_xdp(prog, xdp);
+ u32 act;
+
+ guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock);
+ act = bpf_prog_run_xdp(prog, xdp);

switch (act) {
case XDP_PASS:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 94bde2cad0f47..de564e8b83be2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2203,6 +2203,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,

prefetchw(xdp->data_hard_start); /* xdp_frame write */

+ guard(local_lock_nested_bh)(&bpf_run_lock.redirect_lock);
act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 59798bc33298f..b988f758aad49 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -104,18 +104,20 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
struct xdp_frame *xdpf;
u32 act;

- xdp_prog = READ_ONCE(rx_ring->xdp_prog);
- act = bpf_prog_run_xdp(xdp_prog, xdp);
+ scoped_guard(local_lock_nested_bh, &bpf_run_lock.redirect_lock) {
+ xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+ act = bpf_prog_run_xdp(xdp_prog, xdp);

- if (likely(act == XDP_REDIRECT)) {
- err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- if (!err)
- return IXGBE_XDP_REDIR;
- if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
- result = IXGBE_XDP_EXIT;
- else
- result = IXGBE_XDP_CONSUMED;
- goto out_failure;
+ if (likely(act == XDP_REDIRECT)) {
+ err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+ if (!err)
+ return IXGBE_XDP_REDIR;
+ if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
+ result = IXGBE_XDP_EXIT;
+ else
+ result = IXGBE_XDP_CONSUMED;
+ goto out_failure;
+ }
}

switch (act) {
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index a44e4bd561421..1c58c08aa15ff 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1059,7 +1059,8 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
if (!xdp_prog)
goto xdp_out;

- act = bpf_prog_run_xdp(xdp_prog, xdp);
+ scoped_guard(local_lock_nested_bh, &bpf_run_lock.redirect_lock)
+ act = bpf_prog_run_xdp(xdp_prog, xdp);
switch (act) {
case XDP_PASS:
break;
--
2.43.0