mbox series

[iwl-next,v9,0/6] igb: Add support for AF_XDP zero-copy

Message ID 20241018-b4-igb_zero_copy-v9-0-da139d78d796@linutronix.de (mailing list archive)
Headers show
Series igb: Add support for AF_XDP zero-copy | expand

Message

Kurt Kanzenbach Oct. 18, 2024, 8:39 a.m. UTC 
This is version v8 of the AF_XDP zero-copy support for igb. Since Sriram's
duties changed I am sending this instead. Additionally, I've tested this on
real hardware, Intel i210 [1].

Changes since v8:

 - Collect tags
 - Pass read once xsk_pool pointer to igb_xmit_zc() (Maciej)
 - Change return type of igb_run_xdp_zc() from skb* to int (Maciej)
 - Link to v8: https://lore.kernel.org/r/20241011-b4-igb_zero_copy-v8-0-83862f726a9e@linutronix.de

Changes since v7:

 - Collect tags
 - Split patches (Maciej)
 - Use read once xsk_pool pointer in igb_alloc_rx_buffers_zc() (Maciej)
 - Add FIXME about RS bit in Tx path (Maciej)
 - Link to v7: https://lore.kernel.org/r/20241007-b4-igb_zero_copy-v7-0-23556668adc6@linutronix.de

Changes since v6:

 - Rebase to v6.12
 - Collect tags
 - Merged first patch via -net
 - Inline small functions (Maciej)
 - Read xdp_prog only once per NAPI cycle (Maciej)
 - Use u32 for stack based variables (Maciej)
 - Link to v6: https://lore.kernel.org/r/20240711-b4-igb_zero_copy-v6-0-4bfb68773b18@linutronix.de

Changes since v5:

 - Rebase to 6.11
 - Fix set-but-unused variable warnings
 - Split first patches (Maciej)
 - Add READ/WRITE_ONCE() for xsk_pool and xdp_prog (Maciej)
 - Add synchronize_net() (Maciej)
 - Remove IGB_RING_FLAG_AF_XDP_ZC (Maciej)
 - Add NETDEV_XDP_ACT_XSK_ZEROCOPY to last patch (Maciej)
 - Update Rx ntc handling (Maciej)
 - Move stats update and xdp finalize to common functions (Maciej)
 - "Likelyfy" XDP_REDIRECT case (Maciej)
 - Check Tx disabled and carrier in igb_xmit_zc() (Maciej)
 - RCT (Maciej)
 - Link to v5: https://lore.kernel.org/r/20240711-b4-igb_zero_copy-v5-0-f3f455113b11@linutronix.de

Changes since v4:

 - Rebase to v6.10
 - Fix issue reported by kernel test robot
 - Provide napi_id for xdp_rxq_info_reg() so that busy polling works
 - Set olinfo_status in igb_xmit_zc() so that frames are transmitted

Link to v4: https://lore.kernel.org/intel-wired-lan/20230804084051.14194-1-sriram.yagnaraman@est.tech/

[1] - https://github.com/Linutronix/TSN-Testbench/tree/main/tests/busypolling_i210

Original cover letter:

The first couple of patches adds helper funcctions to prepare for AF_XDP
zero-copy support which comes in the last couple of patches, one each
for Rx and TX paths.

As mentioned in v1 patchset [0], I don't have access to an actual IGB
device to provide correct performance numbers. I have used Intel 82576EB
emulator in QEMU [1] to test the changes to IGB driver.

The tests use one isolated vCPU for RX/TX and one isolated vCPU for the
xdp-sock application [2]. Hope these measurements provide at the least
some indication on the increase in performance when using ZC, especially
in the TX path. It would be awesome if someone with a real IGB NIC can
test the patch.

AF_XDP performance using 64 byte packets in Kpps.
Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
rxdrop		220		235		350
txpush		1.000		1.000		410
l2fwd 		1.000		1.000		200

AF_XDP performance using 1500 byte packets in Kpps.
Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
rxdrop		200		210		310
txpush		1.000		1.000		410
l2fwd 		0.900		1.000		160

[0]: https://lore.kernel.org/intel-wired-lan/20230704095915.9750-1-sriram.yagnaraman@est.tech/
[1]: https://www.qemu.org/docs/master/system/devices/igb.html
[2]: https://github.com/xdp-project/bpf-examples/tree/master/AF_XDP-example

v3->v4:
- NULL check buffer_info in igb_dump before dereferencing (Simon Horman)

v2->v3:
- Avoid TX unit hang when using AF_XDP zero-copy by setting time_stamp
  on the tx_buffer_info
- Fix uninitialized nb_buffs (Simon Horman)

v1->v2:
- Use batch XSK APIs (Maciej Fijalkowski)
- Follow reverse xmas tree convention and remove the ternary operator
  use (Simon Horman)

---
Kurt Kanzenbach (1):
      igb: Add XDP finalize and stats update functions

Sriram Yagnaraman (5):
      igb: Remove static qualifiers
      igb: Introduce igb_xdp_is_enabled()
      igb: Introduce XSK data structures and helpers
      igb: Add AF_XDP zero-copy Rx support
      igb: Add AF_XDP zero-copy Tx support

 drivers/net/ethernet/intel/igb/Makefile   |   2 +-
 drivers/net/ethernet/intel/igb/igb.h      |  58 ++-
 drivers/net/ethernet/intel/igb/igb_main.c | 248 ++++++++-----
 drivers/net/ethernet/intel/igb/igb_xsk.c  | 562 ++++++++++++++++++++++++++++++
 4 files changed, 787 insertions(+), 83 deletions(-)
---
base-commit: 283f6fbb370dc1adf455be5d5ac41d58d215fd8b
change-id: 20240711-b4-igb_zero_copy-bb70a31ecb0f

Best regards,

Comments

Fijalkowski, Maciej Oct. 18, 2024, 10:10 a.m. UTC | #1 
On Fri, Oct 18, 2024 at 10:39:56AM +0200, Kurt Kanzenbach wrote:
> This is version v8 of the AF_XDP zero-copy support for igb. Since Sriram's
> duties changed I am sending this instead. Additionally, I've tested this on
> real hardware, Intel i210 [1].
> 

From my side the series is good to go.

> Changes since v8:
> 
>  - Collect tags
>  - Pass read once xsk_pool pointer to igb_xmit_zc() (Maciej)
>  - Change return type of igb_run_xdp_zc() from skb* to int (Maciej)
>  - Link to v8: https://lore.kernel.org/r/20241011-b4-igb_zero_copy-v8-0-83862f726a9e@linutronix.de
> 
> Changes since v7:
> 
>  - Collect tags
>  - Split patches (Maciej)
>  - Use read once xsk_pool pointer in igb_alloc_rx_buffers_zc() (Maciej)
>  - Add FIXME about RS bit in Tx path (Maciej)
>  - Link to v7: https://lore.kernel.org/r/20241007-b4-igb_zero_copy-v7-0-23556668adc6@linutronix.de
> 
> Changes since v6:
> 
>  - Rebase to v6.12
>  - Collect tags
>  - Merged first patch via -net
>  - Inline small functions (Maciej)
>  - Read xdp_prog only once per NAPI cycle (Maciej)
>  - Use u32 for stack based variables (Maciej)
>  - Link to v6: https://lore.kernel.org/r/20240711-b4-igb_zero_copy-v6-0-4bfb68773b18@linutronix.de
> 
> Changes since v5:
> 
>  - Rebase to 6.11
>  - Fix set-but-unused variable warnings
>  - Split first patches (Maciej)
>  - Add READ/WRITE_ONCE() for xsk_pool and xdp_prog (Maciej)
>  - Add synchronize_net() (Maciej)
>  - Remove IGB_RING_FLAG_AF_XDP_ZC (Maciej)
>  - Add NETDEV_XDP_ACT_XSK_ZEROCOPY to last patch (Maciej)
>  - Update Rx ntc handling (Maciej)
>  - Move stats update and xdp finalize to common functions (Maciej)
>  - "Likelyfy" XDP_REDIRECT case (Maciej)
>  - Check Tx disabled and carrier in igb_xmit_zc() (Maciej)
>  - RCT (Maciej)
>  - Link to v5: https://lore.kernel.org/r/20240711-b4-igb_zero_copy-v5-0-f3f455113b11@linutronix.de
> 
> Changes since v4:
> 
>  - Rebase to v6.10
>  - Fix issue reported by kernel test robot
>  - Provide napi_id for xdp_rxq_info_reg() so that busy polling works
>  - Set olinfo_status in igb_xmit_zc() so that frames are transmitted
> 
> Link to v4: https://lore.kernel.org/intel-wired-lan/20230804084051.14194-1-sriram.yagnaraman@est.tech/
> 
> [1] - https://github.com/Linutronix/TSN-Testbench/tree/main/tests/busypolling_i210
> 
> Original cover letter:
> 
> The first couple of patches adds helper funcctions to prepare for AF_XDP
> zero-copy support which comes in the last couple of patches, one each
> for Rx and TX paths.
> 
> As mentioned in v1 patchset [0], I don't have access to an actual IGB
> device to provide correct performance numbers. I have used Intel 82576EB
> emulator in QEMU [1] to test the changes to IGB driver.
> 
> The tests use one isolated vCPU for RX/TX and one isolated vCPU for the
> xdp-sock application [2]. Hope these measurements provide at the least
> some indication on the increase in performance when using ZC, especially
> in the TX path. It would be awesome if someone with a real IGB NIC can
> test the patch.
> 
> AF_XDP performance using 64 byte packets in Kpps.
> Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
> rxdrop		220		235		350
> txpush		1.000		1.000		410
> l2fwd 		1.000		1.000		200
> 
> AF_XDP performance using 1500 byte packets in Kpps.
> Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
> rxdrop		200		210		310
> txpush		1.000		1.000		410
> l2fwd 		0.900		1.000		160
> 
> [0]: https://lore.kernel.org/intel-wired-lan/20230704095915.9750-1-sriram.yagnaraman@est.tech/
> [1]: https://www.qemu.org/docs/master/system/devices/igb.html
> [2]: https://github.com/xdp-project/bpf-examples/tree/master/AF_XDP-example
> 
> v3->v4:
> - NULL check buffer_info in igb_dump before dereferencing (Simon Horman)
> 
> v2->v3:
> - Avoid TX unit hang when using AF_XDP zero-copy by setting time_stamp
>   on the tx_buffer_info
> - Fix uninitialized nb_buffs (Simon Horman)
> 
> v1->v2:
> - Use batch XSK APIs (Maciej Fijalkowski)
> - Follow reverse xmas tree convention and remove the ternary operator
>   use (Simon Horman)
> 
> ---
> Kurt Kanzenbach (1):
>       igb: Add XDP finalize and stats update functions
> 
> Sriram Yagnaraman (5):
>       igb: Remove static qualifiers
>       igb: Introduce igb_xdp_is_enabled()
>       igb: Introduce XSK data structures and helpers
>       igb: Add AF_XDP zero-copy Rx support
>       igb: Add AF_XDP zero-copy Tx support
> 
>  drivers/net/ethernet/intel/igb/Makefile   |   2 +-
>  drivers/net/ethernet/intel/igb/igb.h      |  58 ++-
>  drivers/net/ethernet/intel/igb/igb_main.c | 248 ++++++++-----
>  drivers/net/ethernet/intel/igb/igb_xsk.c  | 562 ++++++++++++++++++++++++++++++
>  4 files changed, 787 insertions(+), 83 deletions(-)
> ---
> base-commit: 283f6fbb370dc1adf455be5d5ac41d58d215fd8b
> change-id: 20240711-b4-igb_zero_copy-bb70a31ecb0f
> 
> Best regards,
> -- 
> Kurt Kanzenbach <kurt@linutronix.de>
>