diff mbox series

[v2,bpf-next,06/14] i40e: xsk: terminate Rx side of NAPI when XSK Rx queue gets full

Message ID 20220413153015.453864-7-maciej.fijalkowski@intel.com (mailing list archive)
State Accepted
Commit b8aef650e54982728660919a0cf9cdacb079ef86
Delegated to: BPF
Headers show
Series xsk: stop NAPI Rx processing on full XSK RQ | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for bpf-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit fail Errors and warnings before: 0 this patch: 1
netdev/cc_maintainers warning 12 maintainers not CCed: songliubraving@fb.com davem@davemloft.net andrii@kernel.org pabeni@redhat.com kafai@fb.com anthony.l.nguyen@intel.com jesse.brandeburg@intel.com intel-wired-lan@lists.osuosl.org john.fastabend@gmail.com yhs@fb.com hawk@kernel.org kpsingh@kernel.org
netdev/build_clang fail Errors and warnings before: 0 this patch: 9
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn fail Errors and warnings before: 0 this patch: 1
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 86 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-1 success Logs for Kernel LATEST on ubuntu-latest + selftests
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Kernel LATEST on z15 + selftests
bpf/vmtest-bpf-next-PR success PR summary

Commit Message

Maciej Fijalkowski April 13, 2022, 3:30 p.m. UTC
When XSK pool uses need_wakeup feature, correlate -ENOBUFS that was
returned from xdp_do_redirect() with a XSK Rx queue being full. In such
case, terminate the Rx processing that is being done on the current HW
Rx ring and let the user space consume descriptors from XSK Rx queue so
that there is room that driver can use later on.

Introduce new internal return code I40E_XDP_EXIT that will indicate case
described above.

Note that it does not affect Tx processing that is bound to the same
NAPI context, nor the other Rx rings.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
---
 .../ethernet/intel/i40e/i40e_txrx_common.h    |  1 +
 drivers/net/ethernet/intel/i40e/i40e_xsk.c    | 32 +++++++++++++------
 2 files changed, 23 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
index 19da3b22160f..8c5118c8baaf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h
@@ -20,6 +20,7 @@  void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val);
 #define I40E_XDP_CONSUMED	BIT(0)
 #define I40E_XDP_TX		BIT(1)
 #define I40E_XDP_REDIR		BIT(2)
+#define I40E_XDP_EXIT		BIT(3)
 
 /*
  * build_ctob - Builds the Tx descriptor (cmd, offset and type) qword
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index c1d25b0b0ca2..94ea8288859a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -161,9 +161,13 @@  static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 
 	if (likely(act == XDP_REDIRECT)) {
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		if (err)
-			goto out_failure;
-		return I40E_XDP_REDIR;
+		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) {
@@ -175,16 +179,17 @@  static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 		if (result == I40E_XDP_CONSUMED)
 			goto out_failure;
 		break;
+	case XDP_DROP:
+		result = I40E_XDP_CONSUMED;
+		break;
 	default:
 		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
 		fallthrough;
 	case XDP_ABORTED:
+		result = I40E_XDP_CONSUMED;
 out_failure:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
 		fallthrough; /* handle aborts by dropping packet */
-	case XDP_DROP:
-		result = I40E_XDP_CONSUMED;
-		break;
 	}
 	return result;
 }
@@ -271,7 +276,8 @@  static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 				      unsigned int *rx_packets,
 				      unsigned int *rx_bytes,
 				      unsigned int size,
-				      unsigned int xdp_res)
+				      unsigned int xdp_res,
+				      bool *failure)
 {
 	struct sk_buff *skb;
 
@@ -281,11 +287,15 @@  static void i40e_handle_xdp_result_zc(struct i40e_ring *rx_ring,
 	if (likely(xdp_res == I40E_XDP_REDIR) || xdp_res == I40E_XDP_TX)
 		return;
 
+	if (xdp_res == I40E_XDP_EXIT) {
+		*failure = true;
+		return;
+	}
+
 	if (xdp_res == I40E_XDP_CONSUMED) {
 		xsk_buff_free(xdp_buff);
 		return;
 	}
-
 	if (xdp_res == I40E_XDP_PASS) {
 		/* NB! We are not checking for errors using
 		 * i40e_test_staterr with
@@ -371,7 +381,9 @@  int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 
 		xdp_res = i40e_run_xdp_zc(rx_ring, bi);
 		i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
-					  &rx_bytes, size, xdp_res);
+					  &rx_bytes, size, xdp_res, &failure);
+		if (failure)
+			break;
 		total_rx_packets += rx_packets;
 		total_rx_bytes += rx_bytes;
 		xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR);
@@ -382,7 +394,7 @@  int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask;
 
 	if (cleaned_count >= I40E_RX_BUFFER_WRITE)
-		failure = !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);
+		failure |= !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);
 
 	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);