ice: Robustify cleaning/completing XDP Tx buffers

When queueing frames from a Page Pool for redirecting to a device backed
by the ice driver, `perf top` shows heavy load on page_alloc() and
page_frag_free(), despite that on a properly working system it must be
fully or at least almost zero-alloc. The problem is in fact a bit deeper
and raises from how ice cleans up completed Tx buffers.

The story so far: when cleaning/freeing the resources related to
a particular completed Tx frame (skbs, DMA mappings etc.), ice uses some
heuristics only without setting any type explicitly (except for dummy
Flow Director packets, which are marked via ice_tx_buf::tx_flags).
This kinda works, but only up to some point. For example, currently ice
assumes that each frame coming to __ice_xmit_xdp_ring(), is backed by
either plain order-0 page or plain page frag, while it may also be
backed by Page Pool or any other possible memory models introduced in
future. This means any &xdp_frame must be freed properly via
xdp_return_frame() family with no assumptions.

In order to do that, the whole heuristics must be replaced with setting
the Tx buffer/frame type explicitly, just how it's always been done via
an enum. Let us reuse 16 bits from ::tx_flags -- 1 bit-and instr won't
hurt much -- especially given that sometimes there was a check for
%ICE_TX_FLAGS_DUMMY_PKT, which is now turned from a flag to an enum
member. The rest of the changes is straightforward and most of it is
just a conversion to rely now on the type set in &ice_tx_buf rather than
to some secondary properties.
For now, no functional changes intended, the change only prepares the
ground for starting freeing XDP frames properly next step. And it must
be done atomically/synchronously to not break stuff.

Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20230210170618.1973430-5-alexandr.lobakin@intel.com

1 files changed, 25 insertions, 9 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index efa3d378f19e..18d8ba0396e8 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -121,10 +121,7 @@ static inline int ice_skb_pad(void)
 #define ICE_TX_FLAGS_TSO	BIT(0)
 #define ICE_TX_FLAGS_HW_VLAN	BIT(1)
 #define ICE_TX_FLAGS_SW_VLAN	BIT(2)
-/* ICE_TX_FLAGS_DUMMY_PKT is used to mark dummy packets that should be
- * freed instead of returned like skb packets.
- */
-#define ICE_TX_FLAGS_DUMMY_PKT	BIT(3)
+/* Free, was ICE_TX_FLAGS_DUMMY_PKT */
 #define ICE_TX_FLAGS_TSYN	BIT(4)
 #define ICE_TX_FLAGS_IPV4	BIT(5)
 #define ICE_TX_FLAGS_IPV6	BIT(6)
@@ -149,22 +146,41 @@ static inline int ice_skb_pad(void)
 
 #define ICE_TXD_LAST_DESC_CMD (ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)
 
+/**
+ * enum ice_tx_buf_type - type of &ice_tx_buf to act on Tx completion
+ * @ICE_TX_BUF_EMPTY: unused OR XSk frame, no action required
+ * @ICE_TX_BUF_DUMMY: dummy Flow Director packet, unmap and kfree()
+ * @ICE_TX_BUF_FRAG: mapped skb OR &xdp_buff frag, only unmap DMA
+ * @ICE_TX_BUF_SKB: &sk_buff, unmap and consume_skb(), update stats
+ * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free(), stats
+ * @ICE_TX_BUF_XSK_TX: &xdp_buff on XSk queue, xsk_buff_free(), stats
+ */
+enum ice_tx_buf_type {
+	ICE_TX_BUF_EMPTY	= 0U,
+	ICE_TX_BUF_DUMMY,
+	ICE_TX_BUF_FRAG,
+	ICE_TX_BUF_SKB,
+	ICE_TX_BUF_XDP_TX,
+	ICE_TX_BUF_XSK_TX,
+};
+
 struct ice_tx_buf {
 	union {
 		struct ice_tx_desc *next_to_watch;
 		u32 rs_idx;
 	};
 	union {
-		struct sk_buff *skb;
-		void *raw_buf; /* used for XDP */
-		struct xdp_buff *xdp; /* used for XDP_TX ZC */
+		void *raw_buf;		/* used for XDP_TX and FDir rules */
+		struct sk_buff *skb;	/* used for .ndo_start_xmit() */
+		struct xdp_buff *xdp;	/* used for XDP_TX ZC */
 	};
 	unsigned int bytecount;
 	union {
 		unsigned int gso_segs;
-		unsigned int nr_frags; /* used for mbuf XDP */
+		unsigned int nr_frags;	/* used for mbuf XDP */
 	};
-	u32 tx_flags;
+	u32 type:16;			/* &ice_tx_buf_type */
+	u32 tx_flags:16;
 	DEFINE_DMA_UNMAP_LEN(len);
 	DEFINE_DMA_UNMAP_ADDR(dma);
 };