Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-12-03

The main changes are:

1) Support BTF in kernel modules, from Andrii.

2) Introduce preferred busy-polling, from Björn.

3) bpf_ima_inode_hash() and bpf_bprm_opts_set() helpers, from KP Singh.

4) Memcg-based memory accounting for bpf objects, from Roman.

5) Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks, from Stanislav.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (118 commits)
  selftests/bpf: Fix invalid use of strncat in test_sockmap
  libbpf: Use memcpy instead of strncpy to please GCC
  selftests/bpf: Add fentry/fexit/fmod_ret selftest for kernel module
  selftests/bpf: Add tp_btf CO-RE reloc test for modules
  libbpf: Support attachment of BPF tracing programs to kernel modules
  libbpf: Factor out low-level BPF program loading helper
  bpf: Allow to specify kernel module BTFs when attaching BPF programs
  bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier
  selftests/bpf: Add CO-RE relocs selftest relying on kernel module BTF
  selftests/bpf: Add support for marking sub-tests as skipped
  selftests/bpf: Add bpf_testmod kernel module for testing
  libbpf: Add kernel module BTF support for CO-RE relocations
  libbpf: Refactor CO-RE relocs to not assume a single BTF object
  libbpf: Add internal helper to load BTF data by FD
  bpf: Keep module's btf_data_size intact after load
  bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address()
  selftests/bpf: Add Userspace tests for TCP_WINDOW_CLAMP
  bpf: Adds support for setting window clamp
  samples/bpf: Fix spelling mistake "recieving" -> "receiving"
  bpf: Fix cold build of test_progs-no_alu32
  ...
====================

Link: https://lore.kernel.org/r/20201204021936.85653-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 113 insertions, 40 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d43ce13a93c9..9f73cd7aee09 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -676,6 +676,8 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring)
 	i40e_clean_tx_ring(tx_ring);
 	kfree(tx_ring->tx_bi);
 	tx_ring->tx_bi = NULL;
+	kfree(tx_ring->xsk_descs);
+	tx_ring->xsk_descs = NULL;
 
 	if (tx_ring->desc) {
 		dma_free_coherent(tx_ring->dev, tx_ring->size,
@@ -1277,6 +1279,13 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
 	if (!tx_ring->tx_bi)
 		goto err;
 
+	if (ring_is_xdp(tx_ring)) {
+		tx_ring->xsk_descs = kcalloc(I40E_MAX_NUM_DESCRIPTORS, sizeof(*tx_ring->xsk_descs),
+					     GFP_KERNEL);
+		if (!tx_ring->xsk_descs)
+			goto err;
+	}
+
 	u64_stats_init(&tx_ring->syncp);
 
 	/* round up to nearest 4K */
@@ -1300,6 +1309,8 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring)
 	return 0;
 
 err:
+	kfree(tx_ring->xsk_descs);
+	tx_ring->xsk_descs = NULL;
 	kfree(tx_ring->tx_bi);
 	tx_ring->tx_bi = NULL;
 	return -ENOMEM;
@@ -1436,7 +1447,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring)
 	/* XDP RX-queue info only needed for RX rings exposed to XDP */
 	if (rx_ring->vsi->type == I40E_VSI_MAIN) {
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
-				       rx_ring->queue_index);
+				       rx_ring->queue_index, rx_ring->q_vector->napi.napi_id);
 		if (err < 0)
 			return err;
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 2feed920ef8a..5f531b195959 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -389,6 +389,7 @@ struct i40e_ring {
 	struct i40e_channel *ch;
 	struct xdp_rxq_info xdp_rxq;
 	struct xsk_buff_pool *xsk_pool;
+	struct xdp_desc *xsk_descs;      /* For storing descriptors in the AF_XDP ZC path */
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ring_uses_build_skb(struct i40e_ring *ring)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 67febc7b6798..bfa84bfb0488 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/stringify.h>
 #include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 
@@ -380,58 +381,102 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 	return failure ? budget : (int)total_rx_packets;
 }
 
-/**
- * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
- * @xdp_ring: XDP Tx ring
- * @budget: NAPI budget
- *
- * Returns true if the work is finished.
- **/
-static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
+static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
+			  unsigned int *total_bytes)
 {
-	unsigned int sent_frames = 0, total_bytes = 0;
-	struct i40e_tx_desc *tx_desc = NULL;
-	struct i40e_tx_buffer *tx_bi;
-	struct xdp_desc desc;
+	struct i40e_tx_desc *tx_desc;
 	dma_addr_t dma;
 
-	while (budget-- > 0) {
-		if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc))
-			break;
+	dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
+	xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
 
-		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr);
-		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma,
-						 desc.len);
+	tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
+	tx_desc->buffer_addr = cpu_to_le64(dma);
+	tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP,
+						  0, desc->len, 0);
 
-		tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use];
-		tx_bi->bytecount = desc.len;
+	*total_bytes += desc->len;
+}
 
-		tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use);
-		tx_desc->buffer_addr = cpu_to_le64(dma);
-		tx_desc->cmd_type_offset_bsz =
-			build_ctob(I40E_TX_DESC_CMD_ICRC
-				   | I40E_TX_DESC_CMD_EOP,
-				   0, desc.len, 0);
+static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *desc,
+				unsigned int *total_bytes)
+{
+	u16 ntu = xdp_ring->next_to_use;
+	struct i40e_tx_desc *tx_desc;
+	dma_addr_t dma;
+	u32 i;
 
-		sent_frames++;
-		total_bytes += tx_bi->bytecount;
+	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
+		xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len);
 
-		xdp_ring->next_to_use++;
-		if (xdp_ring->next_to_use == xdp_ring->count)
-			xdp_ring->next_to_use = 0;
+		tx_desc = I40E_TX_DESC(xdp_ring, ntu++);
+		tx_desc->buffer_addr = cpu_to_le64(dma);
+		tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC |
+							  I40E_TX_DESC_CMD_EOP,
+							  0, desc[i].len, 0);
+
+		*total_bytes += desc[i].len;
 	}
 
-	if (tx_desc) {
-		/* Request an interrupt for the last frame and bump tail ptr. */
-		tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS <<
-						 I40E_TXD_QW1_CMD_SHIFT);
-		i40e_xdp_ring_update_tail(xdp_ring);
+	xdp_ring->next_to_use = ntu;
+}
+
+static void i40e_fill_tx_hw_ring(struct i40e_ring *xdp_ring, struct xdp_desc *descs, u32 nb_pkts,
+				 unsigned int *total_bytes)
+{
+	u32 batched, leftover, i;
+
+	batched = nb_pkts & ~(PKTS_PER_BATCH - 1);
+	leftover = nb_pkts & (PKTS_PER_BATCH - 1);
+	for (i = 0; i < batched; i += PKTS_PER_BATCH)
+		i40e_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
+	for (i = batched; i < batched + leftover; i++)
+		i40e_xmit_pkt(xdp_ring, &descs[i], total_bytes);
+}
 
-		xsk_tx_release(xdp_ring->xsk_pool);
-		i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes);
+static void i40e_set_rs_bit(struct i40e_ring *xdp_ring)
+{
+	u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1;
+	struct i40e_tx_desc *tx_desc;
+
+	tx_desc = I40E_TX_DESC(xdp_ring, ntu);
+	tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT);
+}
+
+/**
+ * i40e_xmit_zc - Performs zero-copy Tx AF_XDP
+ * @xdp_ring: XDP Tx ring
+ * @budget: NAPI budget
+ *
+ * Returns true if the work is finished.
+ **/
+static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
+{
+	struct xdp_desc *descs = xdp_ring->xsk_descs;
+	u32 nb_pkts, nb_processed = 0;
+	unsigned int total_bytes = 0;
+
+	nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget);
+	if (!nb_pkts)
+		return false;
+
+	if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
+		nb_processed = xdp_ring->count - xdp_ring->next_to_use;
+		i40e_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
+		xdp_ring->next_to_use = 0;
 	}
 
-	return !!budget;
+	i40e_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
+			     &total_bytes);
+
+	/* Request an interrupt for the last frame and bump tail ptr. */
+	i40e_set_rs_bit(xdp_ring);
+	i40e_xdp_ring_update_tail(xdp_ring);
+
+	i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes);
+
+	return true;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index 7adfd8539247..ea88f4597a07 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -4,6 +4,22 @@
 #ifndef _I40E_XSK_H_
 #define _I40E_XSK_H_
 
+/* This value should match the pragma in the loop_unrolled_for
+ * macro. Why 4? It is strictly empirical. It seems to be a good
+ * compromise between the advantage of having simultaneous outstanding
+ * reads to the DMA array that can hide each others latency and the
+ * disadvantage of having a larger code path.
+ */
+#define PKTS_PER_BATCH 4
+
+#ifdef __clang__
+#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
+#elif __GNUC__ >= 8
+#define loop_unrolled_for _Pragma("GCC unroll 4") for
+#else
+#define loop_unrolled_for for
+#endif
+
 struct i40e_vsi;
 struct xsk_buff_pool;
 struct zero_copy_allocator;