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

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add the ability to use unaligned chunks in the AF_XDP umem. By
   relaxing where the chunks can be placed, it allows to use an
   arbitrary buffer size and place whenever there is a free
   address in the umem. Helps more seamless DPDK AF_XDP driver
   integration. Support for i40e, ixgbe and mlx5e, from Kevin and
   Maxim.

2) Addition of a wakeup flag for AF_XDP tx and fill rings so the
   application can wake up the kernel for rx/tx processing which
   avoids busy-spinning of the latter, useful when app and driver
   is located on the same core. Support for i40e, ixgbe and mlx5e,
   from Magnus and Maxim.

3) bpftool fixes for printf()-like functions so compiler can actually
   enforce checks, bpftool build system improvements for custom output
   directories, and addition of 'bpftool map freeze' command, from Quentin.

4) Support attaching/detaching XDP programs from 'bpftool net' command,
   from Daniel.

5) Automatic xskmap cleanup when AF_XDP socket is released, and several
   barrier/{read,write}_once fixes in AF_XDP code, from Björn.

6) Relicense of bpf_helpers.h/bpf_endian.h for future libbpf
   inclusion as well as libbpf versioning improvements, from Andrii.

7) Several new BPF kselftests for verifier precision tracking, from Alexei.

8) Several BPF kselftest fixes wrt endianess to run on s390x, from Ilya.

9) And more BPF kselftest improvements all over the place, from Stanislav.

10) Add simple BPF map op cache for nfp driver to batch dumps, from Jakub.

11) AF_XDP socket umem mapping improvements for 32bit archs, from Ivan.

12) Add BPF-to-BPF call and BTF line info support for s390x JIT, from Yauheni.

13) Small optimization in arm64 JIT to spare 1 insns for BPF_MOD, from Jerin.

14) Fix an error check in bpf_tcp_gen_syncookie() helper, from Petar.

15) Various minor fixes and cleanups, from Nathan, Masahiro, Masanari,
    Peter, Wei, Yue.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 76 insertions, 39 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index fdf43d87e983..3c8a2f55c43a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12530,7 +12530,8 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	if (need_reset && prog)
 		for (i = 0; i < vsi->num_queue_pairs; i++)
 			if (vsi->xdp_rings[i]->xsk_umem)
-				(void)i40e_xsk_async_xmit(vsi->netdev, i);
+				(void)i40e_xsk_wakeup(vsi->netdev, i,
+						      XDP_WAKEUP_RX);
 
 	return 0;
 }
@@ -12852,7 +12853,7 @@ static const struct net_device_ops i40e_netdev_ops = {
 	.ndo_bridge_setlink	= i40e_ndo_bridge_setlink,
 	.ndo_bpf		= i40e_xdp,
 	.ndo_xdp_xmit		= i40e_xdp_xmit,
-	.ndo_xsk_async_xmit	= i40e_xsk_async_xmit,
+	.ndo_xsk_wakeup	        = i40e_xsk_wakeup,
 	.ndo_dfwd_add_station	= i40e_fwd_add,
 	.ndo_dfwd_del_station	= i40e_fwd_del,
 };
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 32bad014d76c..0373bc6c7e61 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -116,7 +116,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 			return err;
 
 		/* Kick start the NAPI context so that receiving will start */
-		err = i40e_xsk_async_xmit(vsi->netdev, qid);
+		err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX);
 		if (err)
 			return err;
 	}
@@ -190,7 +190,9 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
  **/
 static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 {
+	struct xdp_umem *umem = rx_ring->xsk_umem;
 	int err, result = I40E_XDP_PASS;
+	u64 offset = umem->headroom;
 	struct i40e_ring *xdp_ring;
 	struct bpf_prog *xdp_prog;
 	u32 act;
@@ -201,7 +203,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
 	 */
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	xdp->handle += xdp->data - xdp->data_hard_start;
+	offset += xdp->data - xdp->data_hard_start;
+
+	xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
+
 	switch (act) {
 	case XDP_PASS:
 		break;
@@ -262,7 +267,7 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring,
 	bi->addr = xdp_umem_get_data(umem, handle);
 	bi->addr += hr;
 
-	bi->handle = handle + umem->headroom;
+	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
 
 	xsk_umem_discard_addr(umem);
 	return true;
@@ -299,7 +304,7 @@ static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring,
 	bi->addr = xdp_umem_get_data(umem, handle);
 	bi->addr += hr;
 
-	bi->handle = handle + umem->headroom;
+	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
 
 	xsk_umem_discard_addr_rq(umem);
 	return true;
@@ -420,8 +425,6 @@ static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
 				    struct i40e_rx_buffer *old_bi)
 {
 	struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc];
-	unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask;
-	u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
 	u16 nta = rx_ring->next_to_alloc;
 
 	/* update, and store next to alloc */
@@ -429,14 +432,9 @@ static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	new_bi->dma = old_bi->dma & mask;
-	new_bi->dma += hr;
-
-	new_bi->addr = (void *)((unsigned long)old_bi->addr & mask);
-	new_bi->addr += hr;
-
-	new_bi->handle = old_bi->handle & mask;
-	new_bi->handle += rx_ring->xsk_umem->headroom;
+	new_bi->dma = old_bi->dma;
+	new_bi->addr = old_bi->addr;
+	new_bi->handle = old_bi->handle;
 
 	old_bi->addr = NULL;
 }
@@ -471,7 +469,8 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
 	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
 	bi->addr += hr;
 
-	bi->handle = (u64)handle + rx_ring->xsk_umem->headroom;
+	bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
+					    rx_ring->xsk_umem->headroom);
 }
 
 /**
@@ -626,6 +625,15 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
 
 	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
 	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
+
+	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+		else
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+
+		return (int)total_rx_packets;
+	}
 	return failure ? budget : (int)total_rx_packets;
 }
 
@@ -681,6 +689,8 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 		i40e_xdp_ring_update_tail(xdp_ring);
 
 		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+		if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
+			xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem);
 	}
 
 	return !!budget && work_done;
@@ -759,19 +769,27 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
 	i40e_update_tx_stats(tx_ring, completed_frames, total_bytes);
 
 out_xmit:
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) {
+		if (tx_ring->next_to_clean == tx_ring->next_to_use)
+			xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+		else
+			xsk_clear_tx_need_wakeup(tx_ring->xsk_umem);
+	}
+
 	xmit_done = i40e_xmit_zc(tx_ring, budget);
 
 	return work_done && xmit_done;
 }
 
 /**
- * i40e_xsk_async_xmit - Implements the ndo_xsk_async_xmit
+ * i40e_xsk_wakeup - Implements the ndo_xsk_wakeup
  * @dev: the netdevice
  * @queue_id: queue id to wake up
+ * @flags: ignored in our case since we have Rx and Tx in the same NAPI.
  *
  * Returns <0 for errors, 0 otherwise.
  **/
-int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id)
+int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index 8cc0a2e7d9a2..9ed59c14eb55 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -18,6 +18,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget);
 
 bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
 			   struct i40e_ring *tx_ring, int napi_budget);
-int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id);
+int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
 
 #endif /* _I40E_XSK_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 17b7ae9f46ec..9bcae44e9883 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10260,7 +10260,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	if (need_reset && prog)
 		for (i = 0; i < adapter->num_rx_queues; i++)
 			if (adapter->xdp_ring[i]->xsk_umem)
-				(void)ixgbe_xsk_async_xmit(adapter->netdev, i);
+				(void)ixgbe_xsk_wakeup(adapter->netdev, i,
+						       XDP_WAKEUP_RX);
 
 	return 0;
 }
@@ -10379,7 +10380,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_features_check	= ixgbe_features_check,
 	.ndo_bpf		= ixgbe_xdp,
 	.ndo_xdp_xmit		= ixgbe_xdp_xmit,
-	.ndo_xsk_async_xmit	= ixgbe_xsk_async_xmit,
+	.ndo_xsk_wakeup         = ixgbe_xsk_wakeup,
 };
 
 static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index d93a690aff74..6d01700b46bc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -42,7 +42,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring);
 bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 			    struct ixgbe_ring *tx_ring, int napi_budget);
-int ixgbe_xsk_async_xmit(struct net_device *dev, u32 queue_id);
+int ixgbe_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
 void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring);
 
 #endif /* #define _IXGBE_TXRX_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 6b609553329f..ad802a8909e0 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -100,7 +100,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 		ixgbe_txrx_ring_enable(adapter, qid);
 
 		/* Kick start the NAPI context so that receiving will start */
-		err = ixgbe_xsk_async_xmit(adapter->netdev, qid);
+		err = ixgbe_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX);
 		if (err)
 			return err;
 	}
@@ -143,7 +143,9 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 			    struct ixgbe_ring *rx_ring,
 			    struct xdp_buff *xdp)
 {
+	struct xdp_umem *umem = rx_ring->xsk_umem;
 	int err, result = IXGBE_XDP_PASS;
+	u64 offset = umem->headroom;
 	struct bpf_prog *xdp_prog;
 	struct xdp_frame *xdpf;
 	u32 act;
@@ -151,7 +153,10 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 	rcu_read_lock();
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
-	xdp->handle += xdp->data - xdp->data_hard_start;
+	offset += xdp->data - xdp->data_hard_start;
+
+	xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset);
+
 	switch (act) {
 	case XDP_PASS:
 		break;
@@ -201,8 +206,6 @@ ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring,
 static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring,
 				     struct ixgbe_rx_buffer *obi)
 {
-	unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask;
-	u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM;
 	u16 nta = rx_ring->next_to_alloc;
 	struct ixgbe_rx_buffer *nbi;
 
@@ -212,14 +215,9 @@ static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring,
 	rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0;
 
 	/* transfer page from old buffer to new buffer */
-	nbi->dma = obi->dma & mask;
-	nbi->dma += hr;
-
-	nbi->addr = (void *)((unsigned long)obi->addr & mask);
-	nbi->addr += hr;
-
-	nbi->handle = obi->handle & mask;
-	nbi->handle += rx_ring->xsk_umem->headroom;
+	nbi->dma = obi->dma;
+	nbi->addr = obi->addr;
+	nbi->handle = obi->handle;
 
 	obi->addr = NULL;
 	obi->skb = NULL;
@@ -250,7 +248,8 @@ void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle)
 	bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle);
 	bi->addr += hr;
 
-	bi->handle = (u64)handle + rx_ring->xsk_umem->headroom;
+	bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle,
+					    rx_ring->xsk_umem->headroom);
 }
 
 static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring,
@@ -276,7 +275,7 @@ static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring,
 	bi->addr = xdp_umem_get_data(umem, handle);
 	bi->addr += hr;
 
-	bi->handle = handle + umem->headroom;
+	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
 
 	xsk_umem_discard_addr(umem);
 	return true;
@@ -303,7 +302,7 @@ static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring,
 	bi->addr = xdp_umem_get_data(umem, handle);
 	bi->addr += hr;
 
-	bi->handle = handle + umem->headroom;
+	bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom);
 
 	xsk_umem_discard_addr_rq(umem);
 	return true;
@@ -547,6 +546,14 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 	q_vector->rx.total_packets += total_rx_packets;
 	q_vector->rx.total_bytes += total_rx_bytes;
 
+	if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) {
+		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
+			xsk_set_rx_need_wakeup(rx_ring->xsk_umem);
+		else
+			xsk_clear_rx_need_wakeup(rx_ring->xsk_umem);
+
+		return (int)total_rx_packets;
+	}
 	return failure ? budget : (int)total_rx_packets;
 }
 
@@ -615,6 +622,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	if (tx_desc) {
 		ixgbe_xdp_ring_update_tail(xdp_ring);
 		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
+		if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
+			xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem);
 	}
 
 	return !!budget && work_done;
@@ -688,11 +697,19 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 	if (xsk_frames)
 		xsk_umem_complete_tx(umem, xsk_frames);
 
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) {
+		if (tx_ring->next_to_clean == tx_ring->next_to_use)
+			xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
+		else
+			xsk_clear_tx_need_wakeup(tx_ring->xsk_umem);
+	}
+
 	xmit_done = ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
+
 	return budget > 0 && xmit_done;
 }
 
-int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid)
+int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct ixgbe_ring *ring;