netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Aurelien Aptel <aaptel@nvidia.com>
To: Max Gurtovoy <mgurtovoy@nvidia.com>,
	linux-nvme@lists.infradead.org, netdev@vger.kernel.org,
	sagi@grimberg.me, hch@lst.de, kbusch@kernel.org, axboe@fb.com,
	chaitanyak@nvidia.com, davem@davemloft.net, kuba@kernel.org
Cc: Boris Pismenny <borisp@nvidia.com>,
	aurelien.aptel@gmail.com, smalin@nvidia.com, malin1024@gmail.com,
	ogerlitz@nvidia.com, yorayz@nvidia.com, galshalom@nvidia.com,
	brauner@kernel.org
Subject: Re: [PATCH v21 05/20] nvme-tcp: Add DDP offload control path
Date: Mon, 18 Dec 2023 22:00:46 +0200	[thread overview]
Message-ID: <2535y0vi8lt.fsf@nvidia.com> (raw)
In-Reply-To: <51446197-3791-dc89-5772-1496b768cd4d@nvidia.com>

Max Gurtovoy <mgurtovoy@nvidia.com> writes:
>> @@ -739,6 +937,9 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
>>   	size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining);
>>   	int ret;
>>   
>> +	if (test_bit(NVME_TCP_Q_OFF_DDP, &queue->flags))
>> +		nvme_tcp_resync_response(queue, skb, *offset);
>
> lets try to optimize the fast path with:
>
> if (IS_ENABLED(CONFIG_ULP_DDP) && test_bit(NVME_TCP_Q_OFF_DDP, 
> &queue->flags))
>      nvme_tcp_resync_response(queue, skb, *offset);
>

For this one, when ULP_DDP is disabled, I do see 1 extra mov instruction
but no branching... I think it's negligible personally.

$ gdb drivers/nvme/host/nvme-tcp.ko
(gdb) disass /s nvme_tcp_recv_skb
...
1088    static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
1089                    unsigned int *offset, size_t *len)
1090    {
1091            struct nvme_tcp_hdr *hdr;
1092            char *pdu = queue->pdu;
   0x00000000000046a6 <+118>:   mov    %rsi,-0x70(%rbp)

880             return  (queue->pdu_remaining) ? NVME_TCP_RECV_PDU :
   0x00000000000046aa <+122>:   test   %ebx,%ebx
   0x00000000000046ac <+124>:   je     0x4975 <nvme_tcp_recv_skb+837>

1093            size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining);
   0x00000000000046b2 <+130>:   cmp    %r14,%rbx

1100                    &pdu[queue->pdu_offset], rcv_len);
   0x00000000000046b5 <+133>:   movslq 0x19c(%r12),%rdx

1099            ret = skb_copy_bits(skb, *offset,
   0x00000000000046bd <+141>:   mov    -0x58(%rbp),%rdi

1093            size_t rcv_len = min_t(size_t, *len, queue->pdu_remaining);
   0x00000000000046c1 <+145>:   cmova  %r14,%rbx

./arch/x86/include/asm/bitops.h:
205             return ((1UL << (nr & (BITS_PER_LONG-1)))
   0x00000000000046c5 <+149>:   mov    0x1d8(%r12),%rax

Extra mov of queue->flags offset here ^^^^^^^^

  (gdb) p &((struct nvme_tcp_queue *)0)->flags
  $1 = (unsigned long *) 0x1d8

  reply	other threads:[~2023-12-18 20:00 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-14 13:26 [PATCH v21 00/20] nvme-tcp receive offloads Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 01/20] net: Introduce direct data placement tcp offload Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 02/20] netlink: add new family to manage ULP_DDP enablement and stats Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 03/20] iov_iter: skip copy if src == dst for direct data placement Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 04/20] net/tls,core: export get_netdev_for_sock Aurelien Aptel
2023-12-15  2:11   ` Jakub Kicinski
2023-12-15 13:46     ` Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 05/20] nvme-tcp: Add DDP offload control path Aurelien Aptel
2023-12-17  0:18   ` Max Gurtovoy
2023-12-18 20:00     ` Aurelien Aptel [this message]
2023-12-20 11:30       ` Max Gurtovoy
2023-12-14 13:26 ` [PATCH v21 06/20] nvme-tcp: Add DDP data-path Aurelien Aptel
2023-12-17 17:06   ` Max Gurtovoy
2023-12-18 18:08     ` Aurelien Aptel
2023-12-18 18:47       ` Max Gurtovoy
2023-12-14 13:26 ` [PATCH v21 07/20] nvme-tcp: RX DDGST offload Aurelien Aptel
2023-12-20 13:35   ` Max Gurtovoy
2023-12-14 13:26 ` [PATCH v21 08/20] nvme-tcp: Deal with netdevice DOWN events Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 09/20] Documentation: add ULP DDP offload documentation Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 10/20] net/mlx5e: Rename from tls to transport static params Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 11/20] net/mlx5e: Refactor ico sq polling to get budget Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 12/20] net/mlx5: Add NVMEoTCP caps, HW bits, 128B CQE and enumerations Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 13/20] net/mlx5e: NVMEoTCP, offload initialization Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 14/20] net/mlx5e: TCP flow steering for nvme-tcp acceleration Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 15/20] net/mlx5e: NVMEoTCP, use KLM UMRs for buffer registration Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 16/20] net/mlx5e: NVMEoTCP, queue init/teardown Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 17/20] net/mlx5e: NVMEoTCP, ddp setup and resync Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 18/20] net/mlx5e: NVMEoTCP, async ddp invalidation Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 19/20] net/mlx5e: NVMEoTCP, data-path for DDP+DDGST offload Aurelien Aptel
2023-12-14 13:26 ` [PATCH v21 20/20] net/mlx5e: NVMEoTCP, statistics Aurelien Aptel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2535y0vi8lt.fsf@nvidia.com \
    --to=aaptel@nvidia.com \
    --cc=aurelien.aptel@gmail.com \
    --cc=axboe@fb.com \
    --cc=borisp@nvidia.com \
    --cc=brauner@kernel.org \
    --cc=chaitanyak@nvidia.com \
    --cc=davem@davemloft.net \
    --cc=galshalom@nvidia.com \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=malin1024@gmail.com \
    --cc=mgurtovoy@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=ogerlitz@nvidia.com \
    --cc=sagi@grimberg.me \
    --cc=smalin@nvidia.com \
    --cc=yorayz@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).