From 754209850df8367c954ac1de7671c7430b1f342c Mon Sep 17 00:00:00 2001
From: Bernard Metzler <bmt@zurich.ibm.com>
Date: Tue, 20 Sep 2022 10:12:02 +0200
Subject: [PATCH 1/1] RDMA/siw: Always consume all skbuf data in
 sk_data_ready() upcall.
Git-commit: 754209850df8367c954ac1de7671c7430b1f342c
Patch-mainline: v6.1-rc1
References: git-fixes

For header and trailer/padding processing, siw did not consume new
skb data until minimum amount present to fill current header or trailer
structure, including potential payload padding. Not consuming any
data during upcall may cause a receive stall, since tcp_read_sock()
is not upcalling again if no new data arrive.
A NFSoRDMA client got stuck at RDMA Write reception of unaligned
payload, if the current skb did contain only the expected 3 padding
bytes, but not the 4 bytes CRC trailer. Expecting 4 more bytes already
arrived in another skb, and not consuming those 3 bytes in the current
upcall left the Write incomplete, waiting for the CRC forever.

Fixes: 8b6a361b8c48 ("rdma/siw: receive path")
Reported-by: Olga Kornievskaia <kolga@netapp.com>
Tested-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Bernard Metzler <bmt@zurich.ibm.com>
Link: https://lore.kernel.org/r/20220920081202.223629-1-bmt@zurich.ibm.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Acked-by: Nicolas Morey-Chaisemartin <nmoreychaisemartin@suse.com>
---
 drivers/infiniband/sw/siw/siw_qp_rx.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c
index 875ea6f1b04a..fd721cc19682 100644
--- a/drivers/infiniband/sw/siw/siw_qp_rx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_rx.c
@@ -961,27 +961,28 @@ out:
 static int siw_get_trailer(struct siw_qp *qp, struct siw_rx_stream *srx)
 {
 	struct sk_buff *skb = srx->skb;
+	int avail = min(srx->skb_new, srx->fpdu_part_rem);
 	u8 *tbuf = (u8 *)&srx->trailer.crc - srx->pad;
 	__wsum crc_in, crc_own = 0;
 
 	siw_dbg_qp(qp, "expected %d, available %d, pad %u\n",
 		   srx->fpdu_part_rem, srx->skb_new, srx->pad);
 
-	if (srx->skb_new < srx->fpdu_part_rem)
-		return -EAGAIN;
-
-	skb_copy_bits(skb, srx->skb_offset, tbuf, srx->fpdu_part_rem);
+	skb_copy_bits(skb, srx->skb_offset, tbuf, avail);
 
-	if (srx->mpa_crc_hd && srx->pad)
-		crypto_shash_update(srx->mpa_crc_hd, tbuf, srx->pad);
+	srx->skb_new -= avail;
+	srx->skb_offset += avail;
+	srx->skb_copied += avail;
+	srx->fpdu_part_rem -= avail;
 
-	srx->skb_new -= srx->fpdu_part_rem;
-	srx->skb_offset += srx->fpdu_part_rem;
-	srx->skb_copied += srx->fpdu_part_rem;
+	if (srx->fpdu_part_rem)
+		return -EAGAIN;
 
 	if (!srx->mpa_crc_hd)
 		return 0;
 
+	if (srx->pad)
+		crypto_shash_update(srx->mpa_crc_hd, tbuf, srx->pad);
 	/*
 	 * CRC32 is computed, transmitted and received directly in NBO,
 	 * so there's never a reason to convert byte order.
@@ -1083,10 +1084,9 @@ static int siw_get_hdr(struct siw_rx_stream *srx)
 	 * completely received.
 	 */
 	if (iwarp_pktinfo[opcode].hdr_len > sizeof(struct iwarp_ctrl_tagged)) {
-		bytes = iwarp_pktinfo[opcode].hdr_len - MIN_DDP_HDR;
+		int hdrlen = iwarp_pktinfo[opcode].hdr_len;
 
-		if (srx->skb_new < bytes)
-			return -EAGAIN;
+		bytes = min_t(int, hdrlen - MIN_DDP_HDR, srx->skb_new);
 
 		skb_copy_bits(skb, srx->skb_offset,
 			      (char *)c_hdr + srx->fpdu_part_rcvd, bytes);
@@ -1096,6 +1096,9 @@ static int siw_get_hdr(struct siw_rx_stream *srx)
 		srx->skb_new -= bytes;
 		srx->skb_offset += bytes;
 		srx->skb_copied += bytes;
+
+		if (srx->fpdu_part_rcvd < hdrlen)
+			return -EAGAIN;
 	}
 
 	/*
-- 
2.38.0.1.gee35aeee4b76