diff mbox series

[bpf-next,v7,04/18] ice: Introduce ice_xdp_buff

Message ID 20231115175301.534113-5-larysa.zaremba@intel.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series XDP metadata via kfuncs for ice + VLAN hint | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-15 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-16 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-llvm-16 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-llvm-16 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-llvm-16 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-16 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-16 / veristat
netdev/series_format fail Series longer than 15 patches (and no cover letter)
netdev/tree_selection success Clearly marked for bpf-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 1134 this patch: 1134
netdev/cc_maintainers warning 5 maintainers not CCed: anthony.l.nguyen@intel.com jesse.brandeburg@intel.com pabeni@redhat.com edumazet@google.com intel-wired-lan@lists.osuosl.org
netdev/build_clang success Errors and warnings before: 1161 this patch: 1161
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1161 this patch: 1161
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 91 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 1 this patch: 1
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-5 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-3 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-10 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-11 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-llvm-16 / build / build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-llvm-16 / veristat

Commit Message

Larysa Zaremba Nov. 15, 2023, 5:52 p.m. UTC
In order to use XDP hints via kfuncs we need to put
RX descriptor and miscellaneous data next to xdp_buff.
Same as in hints implementations in other drivers, we achieve
this through putting xdp_buff into a child structure.

Currently, xdp_buff is stored in the ring structure,
so replace it with union that includes child structure.
This way enough memory is available while existing XDP code
remains isolated from hints.

Minimum size of the new child structure (ice_xdp_buff) is exactly
64 bytes (single cache line). To place it at the start of a cache line,
move 'next' field from CL1 to CL4, as it isn't used often. This still
leaves 192 bits available in CL3 for packet context extensions.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c     |  7 +++++--
 drivers/net/ethernet/intel/ice/ice_txrx.h     | 18 +++++++++++++++---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 10 ++++++++++
 3 files changed, 30 insertions(+), 5 deletions(-)

Comments

Larysa Zaremba Nov. 16, 2023, 2:55 a.m. UTC | #1
On Thu, Nov 16, 2023 at 01:52:24PM +0100, Maciej Fijalkowski wrote:
> On Wed, Nov 15, 2023 at 06:52:46PM +0100, Larysa Zaremba wrote:
> > In order to use XDP hints via kfuncs we need to put
> > RX descriptor and miscellaneous data next to xdp_buff.
> > Same as in hints implementations in other drivers, we achieve
> > this through putting xdp_buff into a child structure.
> > 
> > Currently, xdp_buff is stored in the ring structure,
> > so replace it with union that includes child structure.
> > This way enough memory is available while existing XDP code
> > remains isolated from hints.
> > 
> > Minimum size of the new child structure (ice_xdp_buff) is exactly
> > 64 bytes (single cache line). To place it at the start of a cache line,
> > move 'next' field from CL1 to CL4, as it isn't used often. This still
> > leaves 192 bits available in CL3 for packet context extensions.
> > 
> > Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
> > ---
> >  drivers/net/ethernet/intel/ice/ice_txrx.c     |  7 +++++--
> >  drivers/net/ethernet/intel/ice/ice_txrx.h     | 18 +++++++++++++++---
> >  drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 10 ++++++++++
> >  3 files changed, 30 insertions(+), 5 deletions(-)
> > 
> > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
> > index 40f2f6dabb81..4e6546d9cf85 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_txrx.c
> > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
> > @@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
> >   * @xdp_prog: XDP program to run
> >   * @xdp_ring: ring to be used for XDP_TX action
> >   * @rx_buf: Rx buffer to store the XDP action
> > + * @eop_desc: Last descriptor in packet to read metadata from
> >   *
> >   * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
> >   */
> >  static void
> >  ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
> >  	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
> > -	    struct ice_rx_buf *rx_buf)
> > +	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
> >  {
> >  	unsigned int ret = ICE_XDP_PASS;
> >  	u32 act;
> > @@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
> >  	if (!xdp_prog)
> >  		goto exit;
> >  
> > +	ice_xdp_meta_set_desc(xdp, eop_desc);
> > +
> >  	act = bpf_prog_run_xdp(xdp_prog, xdp);
> >  	switch (act) {
> >  	case XDP_PASS:
> > @@ -1240,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
> >  		if (ice_is_non_eop(rx_ring, rx_desc))
> >  			continue;
> >  
> > -		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
> > +		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
> >  		if (rx_buf->act == ICE_XDP_PASS)
> >  			goto construct_skb;
> >  		total_rx_bytes += xdp_get_buff_len(xdp);
> > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > index 166413fc33f4..9efb42f99415 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_txrx.h
> > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > @@ -257,6 +257,14 @@ enum ice_rx_dtype {
> >  	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
> >  };
> >  
> > +struct ice_xdp_buff {
> > +	struct xdp_buff xdp_buff;
> > +	const union ice_32b_rx_flex_desc *eop_desc;
> > +};
> > +
> > +/* Required for compatibility with xdp_buffs from xsk_pool */
> > +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
> 
> That should go to xsk core as a macro and should be used by ZC drivers
> that support hints. Useful stuff similar to XSK_CEHCK_PRIV_TYPE() but
> check is from the other end.

Seems like there will be a v8 anyway, so I might as well do this :)

> 
> > +
> >  /* indices into GLINT_ITR registers */
> >  #define ICE_RX_ITR	ICE_IDX_ITR0
> >  #define ICE_TX_ITR	ICE_IDX_ITR1
> > @@ -298,7 +306,6 @@ enum ice_dynamic_itr {
> >  /* descriptor ring, associated with a VSI */
> >  struct ice_rx_ring {
> >  	/* CL1 - 1st cacheline starts here */
> > -	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
> >  	void *desc;			/* Descriptor ring memory */
> >  	struct device *dev;		/* Used for DMA mapping */
> >  	struct net_device *netdev;	/* netdev ring maps to */
> > @@ -310,12 +317,16 @@ struct ice_rx_ring {
> >  	u16 count;			/* Number of descriptors */
> >  	u16 reg_idx;			/* HW register index of the ring */
> >  	u16 next_to_alloc;
> > -	/* CL2 - 2nd cacheline starts here */
> > +
> >  	union {
> >  		struct ice_rx_buf *rx_buf;
> >  		struct xdp_buff **xdp_buf;
> >  	};
> > -	struct xdp_buff xdp;
> > +	/* CL2 - 2nd cacheline starts here */
> > +	union {
> > +		struct ice_xdp_buff xdp_ext;
> > +		struct xdp_buff xdp;
> > +	};
> >  	/* CL3 - 3rd cacheline starts here */
> >  	struct bpf_prog *xdp_prog;
> >  	u16 rx_offset;
> > @@ -332,6 +343,7 @@ struct ice_rx_ring {
> >  	/* CL4 - 4th cacheline starts here */
> >  	struct ice_channel *ch;
> >  	struct ice_tx_ring *xdp_ring;
> > +	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
> >  	struct xsk_buff_pool *xsk_pool;
> >  	dma_addr_t dma;			/* physical address of ring */
> >  	u64 cached_phctime;
> > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > index e1d49e1235b3..81b8856d8e13 100644
> > --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > @@ -151,4 +151,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
> >  		       struct sk_buff *skb);
> >  void
> >  ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
> > +
> > +static inline void
> > +ice_xdp_meta_set_desc(struct xdp_buff *xdp,
> > +		      union ice_32b_rx_flex_desc *eop_desc)
> > +{
> > +	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
> > +						    xdp_buff);
> > +
> > +	xdp_ext->eop_desc = eop_desc;
> > +}
> >  #endif /* !_ICE_TXRX_LIB_H_ */
> > -- 
> > 2.41.0
> >
Fijalkowski, Maciej Nov. 16, 2023, 12:52 p.m. UTC | #2
On Wed, Nov 15, 2023 at 06:52:46PM +0100, Larysa Zaremba wrote:
> In order to use XDP hints via kfuncs we need to put
> RX descriptor and miscellaneous data next to xdp_buff.
> Same as in hints implementations in other drivers, we achieve
> this through putting xdp_buff into a child structure.
> 
> Currently, xdp_buff is stored in the ring structure,
> so replace it with union that includes child structure.
> This way enough memory is available while existing XDP code
> remains isolated from hints.
> 
> Minimum size of the new child structure (ice_xdp_buff) is exactly
> 64 bytes (single cache line). To place it at the start of a cache line,
> move 'next' field from CL1 to CL4, as it isn't used often. This still
> leaves 192 bits available in CL3 for packet context extensions.
> 
> Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
> ---
>  drivers/net/ethernet/intel/ice/ice_txrx.c     |  7 +++++--
>  drivers/net/ethernet/intel/ice/ice_txrx.h     | 18 +++++++++++++++---
>  drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 10 ++++++++++
>  3 files changed, 30 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
> index 40f2f6dabb81..4e6546d9cf85 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx.c
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
> @@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
>   * @xdp_prog: XDP program to run
>   * @xdp_ring: ring to be used for XDP_TX action
>   * @rx_buf: Rx buffer to store the XDP action
> + * @eop_desc: Last descriptor in packet to read metadata from
>   *
>   * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
>   */
>  static void
>  ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
>  	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
> -	    struct ice_rx_buf *rx_buf)
> +	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
>  {
>  	unsigned int ret = ICE_XDP_PASS;
>  	u32 act;
> @@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
>  	if (!xdp_prog)
>  		goto exit;
>  
> +	ice_xdp_meta_set_desc(xdp, eop_desc);
> +
>  	act = bpf_prog_run_xdp(xdp_prog, xdp);
>  	switch (act) {
>  	case XDP_PASS:
> @@ -1240,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
>  		if (ice_is_non_eop(rx_ring, rx_desc))
>  			continue;
>  
> -		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
> +		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
>  		if (rx_buf->act == ICE_XDP_PASS)
>  			goto construct_skb;
>  		total_rx_bytes += xdp_get_buff_len(xdp);
> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
> index 166413fc33f4..9efb42f99415 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx.h
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
> @@ -257,6 +257,14 @@ enum ice_rx_dtype {
>  	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
>  };
>  
> +struct ice_xdp_buff {
> +	struct xdp_buff xdp_buff;
> +	const union ice_32b_rx_flex_desc *eop_desc;
> +};
> +
> +/* Required for compatibility with xdp_buffs from xsk_pool */
> +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);

That should go to xsk core as a macro and should be used by ZC drivers
that support hints. Useful stuff similar to XSK_CEHCK_PRIV_TYPE() but
check is from the other end.

> +
>  /* indices into GLINT_ITR registers */
>  #define ICE_RX_ITR	ICE_IDX_ITR0
>  #define ICE_TX_ITR	ICE_IDX_ITR1
> @@ -298,7 +306,6 @@ enum ice_dynamic_itr {
>  /* descriptor ring, associated with a VSI */
>  struct ice_rx_ring {
>  	/* CL1 - 1st cacheline starts here */
> -	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
>  	void *desc;			/* Descriptor ring memory */
>  	struct device *dev;		/* Used for DMA mapping */
>  	struct net_device *netdev;	/* netdev ring maps to */
> @@ -310,12 +317,16 @@ struct ice_rx_ring {
>  	u16 count;			/* Number of descriptors */
>  	u16 reg_idx;			/* HW register index of the ring */
>  	u16 next_to_alloc;
> -	/* CL2 - 2nd cacheline starts here */
> +
>  	union {
>  		struct ice_rx_buf *rx_buf;
>  		struct xdp_buff **xdp_buf;
>  	};
> -	struct xdp_buff xdp;
> +	/* CL2 - 2nd cacheline starts here */
> +	union {
> +		struct ice_xdp_buff xdp_ext;
> +		struct xdp_buff xdp;
> +	};
>  	/* CL3 - 3rd cacheline starts here */
>  	struct bpf_prog *xdp_prog;
>  	u16 rx_offset;
> @@ -332,6 +343,7 @@ struct ice_rx_ring {
>  	/* CL4 - 4th cacheline starts here */
>  	struct ice_channel *ch;
>  	struct ice_tx_ring *xdp_ring;
> +	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
>  	struct xsk_buff_pool *xsk_pool;
>  	dma_addr_t dma;			/* physical address of ring */
>  	u64 cached_phctime;
> diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> index e1d49e1235b3..81b8856d8e13 100644
> --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> @@ -151,4 +151,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
>  		       struct sk_buff *skb);
>  void
>  ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
> +
> +static inline void
> +ice_xdp_meta_set_desc(struct xdp_buff *xdp,
> +		      union ice_32b_rx_flex_desc *eop_desc)
> +{
> +	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
> +						    xdp_buff);
> +
> +	xdp_ext->eop_desc = eop_desc;
> +}
>  #endif /* !_ICE_TXRX_LIB_H_ */
> -- 
> 2.41.0
>
Larysa Zaremba Dec. 1, 2023, 1:51 p.m. UTC | #3
On Thu, Nov 16, 2023 at 03:55:19AM +0100, Larysa Zaremba wrote:
> On Thu, Nov 16, 2023 at 01:52:24PM +0100, Maciej Fijalkowski wrote:
> > On Wed, Nov 15, 2023 at 06:52:46PM +0100, Larysa Zaremba wrote:
> > > In order to use XDP hints via kfuncs we need to put
> > > RX descriptor and miscellaneous data next to xdp_buff.
> > > Same as in hints implementations in other drivers, we achieve
> > > this through putting xdp_buff into a child structure.
> > > 
> > > Currently, xdp_buff is stored in the ring structure,
> > > so replace it with union that includes child structure.
> > > This way enough memory is available while existing XDP code
> > > remains isolated from hints.
> > > 
> > > Minimum size of the new child structure (ice_xdp_buff) is exactly
> > > 64 bytes (single cache line). To place it at the start of a cache line,
> > > move 'next' field from CL1 to CL4, as it isn't used often. This still
> > > leaves 192 bits available in CL3 for packet context extensions.
> > > 
> > > Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
> > > ---
> > >  drivers/net/ethernet/intel/ice/ice_txrx.c     |  7 +++++--
> > >  drivers/net/ethernet/intel/ice/ice_txrx.h     | 18 +++++++++++++++---
> > >  drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 10 ++++++++++
> > >  3 files changed, 30 insertions(+), 5 deletions(-)
> > > 
> > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
> > > index 40f2f6dabb81..4e6546d9cf85 100644
> > > --- a/drivers/net/ethernet/intel/ice/ice_txrx.c
> > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
> > > @@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
> > >   * @xdp_prog: XDP program to run
> > >   * @xdp_ring: ring to be used for XDP_TX action
> > >   * @rx_buf: Rx buffer to store the XDP action
> > > + * @eop_desc: Last descriptor in packet to read metadata from
> > >   *
> > >   * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
> > >   */
> > >  static void
> > >  ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
> > >  	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
> > > -	    struct ice_rx_buf *rx_buf)
> > > +	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
> > >  {
> > >  	unsigned int ret = ICE_XDP_PASS;
> > >  	u32 act;
> > > @@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
> > >  	if (!xdp_prog)
> > >  		goto exit;
> > >  
> > > +	ice_xdp_meta_set_desc(xdp, eop_desc);
> > > +
> > >  	act = bpf_prog_run_xdp(xdp_prog, xdp);
> > >  	switch (act) {
> > >  	case XDP_PASS:
> > > @@ -1240,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
> > >  		if (ice_is_non_eop(rx_ring, rx_desc))
> > >  			continue;
> > >  
> > > -		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
> > > +		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
> > >  		if (rx_buf->act == ICE_XDP_PASS)
> > >  			goto construct_skb;
> > >  		total_rx_bytes += xdp_get_buff_len(xdp);
> > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > > index 166413fc33f4..9efb42f99415 100644
> > > --- a/drivers/net/ethernet/intel/ice/ice_txrx.h
> > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
> > > @@ -257,6 +257,14 @@ enum ice_rx_dtype {
> > >  	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
> > >  };
> > >  
> > > +struct ice_xdp_buff {
> > > +	struct xdp_buff xdp_buff;
> > > +	const union ice_32b_rx_flex_desc *eop_desc;
> > > +};
> > > +
> > > +/* Required for compatibility with xdp_buffs from xsk_pool */
> > > +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
> > 
> > That should go to xsk core as a macro and should be used by ZC drivers
> > that support hints. Useful stuff similar to XSK_CEHCK_PRIV_TYPE() but
> > check is from the other end.
> 
> Seems like there will be a v8 anyway, so I might as well do this :)
>

After going back and forth about this for a few days, I think this is not a good 
idea to include such change into the series.

But I do have to change the comment, this assert is mostly needed, 
because my code converts ice_xdp_buff <-> xdp_buff on multiple occasions (and 
this flooding code with container_of is not a solution).

Currently, XSK_CHECK_PRIV_TYPE() performs the most important task of ensuring 
nothing outside cb[] is overwritten, just fine. Offset check macro could be 
added in a separate patch to the xdp header (instead of xsk_buff_pool.h),  ice 
isn't the only driver relying on xdp_buff inheritance. This will happen only if
I (or someone else) can make such generic macro not look ugly, though.

> > 
> > > +
> > >  /* indices into GLINT_ITR registers */
> > >  #define ICE_RX_ITR	ICE_IDX_ITR0
> > >  #define ICE_TX_ITR	ICE_IDX_ITR1
> > > @@ -298,7 +306,6 @@ enum ice_dynamic_itr {
> > >  /* descriptor ring, associated with a VSI */
> > >  struct ice_rx_ring {
> > >  	/* CL1 - 1st cacheline starts here */
> > > -	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
> > >  	void *desc;			/* Descriptor ring memory */
> > >  	struct device *dev;		/* Used for DMA mapping */
> > >  	struct net_device *netdev;	/* netdev ring maps to */
> > > @@ -310,12 +317,16 @@ struct ice_rx_ring {
> > >  	u16 count;			/* Number of descriptors */
> > >  	u16 reg_idx;			/* HW register index of the ring */
> > >  	u16 next_to_alloc;
> > > -	/* CL2 - 2nd cacheline starts here */
> > > +
> > >  	union {
> > >  		struct ice_rx_buf *rx_buf;
> > >  		struct xdp_buff **xdp_buf;
> > >  	};
> > > -	struct xdp_buff xdp;
> > > +	/* CL2 - 2nd cacheline starts here */
> > > +	union {
> > > +		struct ice_xdp_buff xdp_ext;
> > > +		struct xdp_buff xdp;
> > > +	};
> > >  	/* CL3 - 3rd cacheline starts here */
> > >  	struct bpf_prog *xdp_prog;
> > >  	u16 rx_offset;
> > > @@ -332,6 +343,7 @@ struct ice_rx_ring {
> > >  	/* CL4 - 4th cacheline starts here */
> > >  	struct ice_channel *ch;
> > >  	struct ice_tx_ring *xdp_ring;
> > > +	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
> > >  	struct xsk_buff_pool *xsk_pool;
> > >  	dma_addr_t dma;			/* physical address of ring */
> > >  	u64 cached_phctime;
> > > diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > > index e1d49e1235b3..81b8856d8e13 100644
> > > --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > > +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
> > > @@ -151,4 +151,14 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
> > >  		       struct sk_buff *skb);
> > >  void
> > >  ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
> > > +
> > > +static inline void
> > > +ice_xdp_meta_set_desc(struct xdp_buff *xdp,
> > > +		      union ice_32b_rx_flex_desc *eop_desc)
> > > +{
> > > +	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
> > > +						    xdp_buff);
> > > +
> > > +	xdp_ext->eop_desc = eop_desc;
> > > +}
> > >  #endif /* !_ICE_TXRX_LIB_H_ */
> > > -- 
> > > 2.41.0
> > > 
>
diff mbox series

Patch

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 40f2f6dabb81..4e6546d9cf85 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -557,13 +557,14 @@  ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
  * @rx_buf: Rx buffer to store the XDP action
+ * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static void
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf)
+	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -571,6 +572,8 @@  ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	if (!xdp_prog)
 		goto exit;
 
+	ice_xdp_meta_set_desc(xdp, eop_desc);
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
@@ -1240,7 +1243,7 @@  int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
+		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
 		if (rx_buf->act == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 166413fc33f4..9efb42f99415 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -257,6 +257,14 @@  enum ice_rx_dtype {
 	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
 };
 
+struct ice_xdp_buff {
+	struct xdp_buff xdp_buff;
+	const union ice_32b_rx_flex_desc *eop_desc;
+};
+
+/* Required for compatibility with xdp_buffs from xsk_pool */
+static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
+
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
@@ -298,7 +306,6 @@  enum ice_dynamic_itr {
 /* descriptor ring, associated with a VSI */
 struct ice_rx_ring {
 	/* CL1 - 1st cacheline starts here */
-	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
 	struct net_device *netdev;	/* netdev ring maps to */
@@ -310,12 +317,16 @@  struct ice_rx_ring {
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 next_to_alloc;
-	/* CL2 - 2nd cacheline starts here */
+
 	union {
 		struct ice_rx_buf *rx_buf;
 		struct xdp_buff **xdp_buf;
 	};
-	struct xdp_buff xdp;
+	/* CL2 - 2nd cacheline starts here */
+	union {
+		struct ice_xdp_buff xdp_ext;
+		struct xdp_buff xdp;
+	};
 	/* CL3 - 3rd cacheline starts here */
 	struct bpf_prog *xdp_prog;
 	u16 rx_offset;
@@ -332,6 +343,7 @@  struct ice_rx_ring {
 	/* CL4 - 4th cacheline starts here */
 	struct ice_channel *ch;
 	struct ice_tx_ring *xdp_ring;
+	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
 	dma_addr_t dma;			/* physical address of ring */
 	u64 cached_phctime;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index e1d49e1235b3..81b8856d8e13 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -151,4 +151,14 @@  ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       struct sk_buff *skb);
 void
 ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
+
+static inline void
+ice_xdp_meta_set_desc(struct xdp_buff *xdp,
+		      union ice_32b_rx_flex_desc *eop_desc)
+{
+	struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff,
+						    xdp_buff);
+
+	xdp_ext->eop_desc = eop_desc;
+}
 #endif /* !_ICE_TXRX_LIB_H_ */