| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAHS8izN+x7vQ_Fs-YGGKawjWttuiJ8bLtcXE1-Jp90_+4rcx5g@mail.gmail.com>
Date: Wed, 9 Apr 2025 21:49:40 -0700
From: Mina Almasry <almasrymina@...gle.com>
To: Taehee Yoo <ap420073@...il.com>
Cc: davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com,
edumazet@...gle.com, andrew+netdev@...n.ch, horms@...nel.org,
michael.chan@...adcom.com, pavan.chebbi@...adcom.com, hawk@...nel.org,
ilias.apalodimas@...aro.org, netdev@...r.kernel.org, dw@...idwei.uk,
kuniyu@...zon.com, sdf@...ichev.me, ahmed.zaki@...el.com,
aleksander.lobakin@...el.com
Subject: Re: [PATCH net-next] eth: bnxt: add support rx side device memory TCP
On Mon, Apr 7, 2025 at 9:36 PM Taehee Yoo <ap420073@...il.com> wrote:
>
> Currently, bnxt_en driver satisfies the requirements of the Device
> memory TCP, which is HDS.
> So, it implements rx-side Device memory TCP for bnxt_en driver.
> It requires only converting the page API to netmem API.
> `struct page` of agg rings are changed to `netmem_ref netmem` and
> corresponding functions are changed to a variant of netmem API.
>
> It also passes PP_FLAG_ALLOW_UNREADABLE_NETMEM flag to a parameter of
> page_pool.
> The netmem will be activated only when a user requests devmem TCP.
>
> When netmem is activated, received data is unreadable and netmem is
> disabled, received data is readable.
> But drivers don't need to handle both cases because netmem core API will
> handle it properly.
> So, using proper netmem API is enough for drivers.
>
> Device memory TCP can be tested with
> tools/testing/selftests/drivers/net/hw/ncdevmem.
> This is tested with BCM57504-N425G and firmware version 232.0.155.8/pkg
> 232.1.132.8.
>
> Signed-off-by: Taehee Yoo <ap420073@...il.com>
> ---
>
> RFC -> PATCH v1:
> - Drop ring buffer descriptor refactoring patch.
> - Do not convert to netmem API for normal ring(non-agg ring).
> - Remove changes of napi_{enable | disable}() to
> napi_{enable | disable}_locked().
> - Relocate a need_head_pool in struct bnxt_rx_ring_info due to
> an alignment hole.
> - Remove *offset parameter of __bnxt_alloc_rx_netmem().
> *offset is always set to 0 in this function. it's unnecessary.
> - Get skb_shared_info outside of loop in __bnxt_rx_agg_netmems().
> - Drop Tested-by tag due to changes of this patch.
>
> drivers/net/ethernet/broadcom/bnxt/bnxt.c | 201 +++++++++++++---------
> drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 +-
> include/linux/netdevice.h | 1 +
> include/net/page_pool/helpers.h | 6 +
> net/core/dev.c | 6 +
> 5 files changed, 137 insertions(+), 80 deletions(-)
>
> diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> index 28ee12186c37..eb36646d2f8b 100644
> --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
> @@ -893,9 +893,9 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
> bnapi->events &= ~BNXT_TX_CMP_EVENT;
> }
>
> -static bool bnxt_separate_head_pool(void)
> +static bool bnxt_separate_head_pool(struct bnxt_rx_ring_info *rxr)
> {
> - return PAGE_SIZE > BNXT_RX_PAGE_SIZE;
> + return rxr->need_head_pool || PAGE_SIZE > BNXT_RX_PAGE_SIZE;
> }
>
> static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
> @@ -919,6 +919,20 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
> return page;
> }
>
> +static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
> + struct bnxt_rx_ring_info *rxr,
> + gfp_t gfp)
> +{
> + netmem_ref netmem;
> +
> + netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
> + if (!netmem)
> + return 0;
> +
> + *mapping = page_pool_get_dma_addr_netmem(netmem);
> + return netmem;
> +}
> +
> static inline u8 *__bnxt_alloc_rx_frag(struct bnxt *bp, dma_addr_t *mapping,
> struct bnxt_rx_ring_info *rxr,
> gfp_t gfp)
> @@ -999,21 +1013,20 @@ static inline u16 bnxt_find_next_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx)
> return next;
> }
>
> -static inline int bnxt_alloc_rx_page(struct bnxt *bp,
> - struct bnxt_rx_ring_info *rxr,
> - u16 prod, gfp_t gfp)
> +static inline int bnxt_alloc_rx_netmem(struct bnxt *bp,
> + struct bnxt_rx_ring_info *rxr,
> + u16 prod, gfp_t gfp)
> {
> struct rx_bd *rxbd =
> &rxr->rx_agg_desc_ring[RX_AGG_RING(bp, prod)][RX_IDX(prod)];
> struct bnxt_sw_rx_agg_bd *rx_agg_buf;
> - struct page *page;
> - dma_addr_t mapping;
> u16 sw_prod = rxr->rx_sw_agg_prod;
> unsigned int offset = 0;
> + dma_addr_t mapping;
> + netmem_ref netmem;
>
> - page = __bnxt_alloc_rx_page(bp, &mapping, rxr, &offset, gfp);
> -
> - if (!page)
> + netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp);
> + if (!netmem)
> return -ENOMEM;
>
> if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap)))
> @@ -1023,7 +1036,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp,
> rx_agg_buf = &rxr->rx_agg_ring[sw_prod];
> rxr->rx_sw_agg_prod = RING_RX_AGG(bp, NEXT_RX_AGG(sw_prod));
>
> - rx_agg_buf->page = page;
> + rx_agg_buf->netmem = netmem;
> rx_agg_buf->offset = offset;
> rx_agg_buf->mapping = mapping;
> rxbd->rx_bd_haddr = cpu_to_le64(mapping);
> @@ -1067,11 +1080,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
> p5_tpa = true;
>
> for (i = 0; i < agg_bufs; i++) {
> - u16 cons;
> - struct rx_agg_cmp *agg;
> struct bnxt_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf;
> + struct rx_agg_cmp *agg;
> struct rx_bd *prod_bd;
> - struct page *page;
> + netmem_ref netmem;
> + u16 cons;
>
> if (p5_tpa)
> agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i);
> @@ -1088,11 +1101,11 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx,
> cons_rx_buf = &rxr->rx_agg_ring[cons];
>
> /* It is possible for sw_prod to be equal to cons, so
> - * set cons_rx_buf->page to NULL first.
> + * set cons_rx_buf->netmem to 0 first.
> */
> - page = cons_rx_buf->page;
> - cons_rx_buf->page = NULL;
> - prod_rx_buf->page = page;
> + netmem = cons_rx_buf->netmem;
> + cons_rx_buf->netmem = 0;
> + prod_rx_buf->netmem = netmem;
> prod_rx_buf->offset = cons_rx_buf->offset;
>
> prod_rx_buf->mapping = cons_rx_buf->mapping;
> @@ -1218,29 +1231,36 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp,
> return skb;
> }
>
> -static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
> - struct bnxt_cp_ring_info *cpr,
> - struct skb_shared_info *shinfo,
> - u16 idx, u32 agg_bufs, bool tpa,
> - struct xdp_buff *xdp)
> +static u32 __bnxt_rx_agg_netmems(struct bnxt *bp,
> + struct bnxt_cp_ring_info *cpr,
> + u16 idx, u32 agg_bufs, bool tpa,
> + struct sk_buff *skb,
> + struct xdp_buff *xdp)
> {
> struct bnxt_napi *bnapi = cpr->bnapi;
> - struct pci_dev *pdev = bp->pdev;
> - struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
> - u16 prod = rxr->rx_agg_prod;
> + struct skb_shared_info *shinfo;
> + struct bnxt_rx_ring_info *rxr;
> u32 i, total_frag_len = 0;
> bool p5_tpa = false;
> + u16 prod;
> +
> + rxr = bnapi->rx_ring;
> + prod = rxr->rx_agg_prod;
>
> if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) && tpa)
> p5_tpa = true;
>
> + if (skb)
> + shinfo = skb_shinfo(skb);
> + else
> + shinfo = xdp_get_shared_info_from_buff(xdp);
> +
> for (i = 0; i < agg_bufs; i++) {
> - skb_frag_t *frag = &shinfo->frags[i];
> - u16 cons, frag_len;
> - struct rx_agg_cmp *agg;
> struct bnxt_sw_rx_agg_bd *cons_rx_buf;
> - struct page *page;
> + struct rx_agg_cmp *agg;
> + u16 cons, frag_len;
> dma_addr_t mapping;
> + netmem_ref netmem;
>
> if (p5_tpa)
> agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i);
> @@ -1251,27 +1271,42 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
> RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT;
>
> cons_rx_buf = &rxr->rx_agg_ring[cons];
> - skb_frag_fill_page_desc(frag, cons_rx_buf->page,
> - cons_rx_buf->offset, frag_len);
> - shinfo->nr_frags = i + 1;
> + if (skb) {
> + skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem,
> + cons_rx_buf->offset,
> + frag_len, BNXT_RX_PAGE_SIZE);
> + } else {
> + skb_frag_t *frag = &shinfo->frags[i];
> +
> + skb_frag_fill_netmem_desc(frag, cons_rx_buf->netmem,
> + cons_rx_buf->offset,
> + frag_len);
> + shinfo->nr_frags = i + 1;
> + }
> __clear_bit(cons, rxr->rx_agg_bmap);
>
> - /* It is possible for bnxt_alloc_rx_page() to allocate
> + /* It is possible for bnxt_alloc_rx_netmem() to allocate
> * a sw_prod index that equals the cons index, so we
> * need to clear the cons entry now.
> */
> mapping = cons_rx_buf->mapping;
> - page = cons_rx_buf->page;
> - cons_rx_buf->page = NULL;
> + netmem = cons_rx_buf->netmem;
> + cons_rx_buf->netmem = 0;
>
> - if (xdp && page_is_pfmemalloc(page))
> + if (xdp && netmem_is_pfmemalloc(netmem))
> xdp_buff_set_frag_pfmemalloc(xdp);
>
> - if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_ATOMIC) != 0) {
> + if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_ATOMIC) != 0) {
> + if (skb) {
> + skb->len -= frag_len;
> + skb->data_len -= frag_len;
> + skb->truesize -= BNXT_RX_PAGE_SIZE;
> + }
> +
> --shinfo->nr_frags;
> - cons_rx_buf->page = page;
> + cons_rx_buf->netmem = netmem;
>
> - /* Update prod since possibly some pages have been
> + /* Update prod since possibly some netmems have been
> * allocated already.
> */
> rxr->rx_agg_prod = prod;
> @@ -1279,8 +1314,8 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
> return 0;
> }
>
> - dma_sync_single_for_cpu(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE,
> - bp->rx_dir);
> + page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0,
> + BNXT_RX_PAGE_SIZE);
>
> total_frag_len += frag_len;
> prod = NEXT_RX_AGG(prod);
> @@ -1289,32 +1324,28 @@ static u32 __bnxt_rx_agg_pages(struct bnxt *bp,
> return total_frag_len;
> }
>
> -static struct sk_buff *bnxt_rx_agg_pages_skb(struct bnxt *bp,
> - struct bnxt_cp_ring_info *cpr,
> - struct sk_buff *skb, u16 idx,
> - u32 agg_bufs, bool tpa)
> +static struct sk_buff *bnxt_rx_agg_netmems_skb(struct bnxt *bp,
> + struct bnxt_cp_ring_info *cpr,
> + struct sk_buff *skb, u16 idx,
> + u32 agg_bufs, bool tpa)
> {
> - struct skb_shared_info *shinfo = skb_shinfo(skb);
> u32 total_frag_len = 0;
>
> - total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo, idx,
> - agg_bufs, tpa, NULL);
> + total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
> + skb, NULL);
> if (!total_frag_len) {
> skb_mark_for_recycle(skb);
> dev_kfree_skb(skb);
> return NULL;
> }
>
> - skb->data_len += total_frag_len;
> - skb->len += total_frag_len;
> - skb->truesize += BNXT_RX_PAGE_SIZE * agg_bufs;
> return skb;
> }
>
> -static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
> - struct bnxt_cp_ring_info *cpr,
> - struct xdp_buff *xdp, u16 idx,
> - u32 agg_bufs, bool tpa)
> +static u32 bnxt_rx_agg_netmems_xdp(struct bnxt *bp,
> + struct bnxt_cp_ring_info *cpr,
> + struct xdp_buff *xdp, u16 idx,
> + u32 agg_bufs, bool tpa)
> {
> struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp);
> u32 total_frag_len = 0;
> @@ -1322,8 +1353,8 @@ static u32 bnxt_rx_agg_pages_xdp(struct bnxt *bp,
> if (!xdp_buff_has_frags(xdp))
> shinfo->nr_frags = 0;
>
> - total_frag_len = __bnxt_rx_agg_pages(bp, cpr, shinfo,
> - idx, agg_bufs, tpa, xdp);
> + total_frag_len = __bnxt_rx_agg_netmems(bp, cpr, idx, agg_bufs, tpa,
> + NULL, xdp);
> if (total_frag_len) {
> xdp_buff_set_frags_flag(xdp);
> shinfo->nr_frags = agg_bufs;
> @@ -1895,7 +1926,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
> }
>
> if (agg_bufs) {
> - skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, idx, agg_bufs, true);
> + skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, idx, agg_bufs,
> + true);
> if (!skb) {
> /* Page reuse already handled by bnxt_rx_pages(). */
> cpr->sw_stats->rx.rx_oom_discards += 1;
> @@ -2175,9 +2207,10 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
> if (bnxt_xdp_attached(bp, rxr)) {
> bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
> if (agg_bufs) {
> - u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
> - cp_cons, agg_bufs,
> - false);
> + u32 frag_len = bnxt_rx_agg_netmems_xdp(bp, cpr, &xdp,
> + cp_cons,
> + agg_bufs,
> + false);
> if (!frag_len)
> goto oom_next_rx;
>
> @@ -2229,7 +2262,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
>
> if (agg_bufs) {
> if (!xdp_active) {
> - skb = bnxt_rx_agg_pages_skb(bp, cpr, skb, cp_cons, agg_bufs, false);
> + skb = bnxt_rx_agg_netmems_skb(bp, cpr, skb, cp_cons,
> + agg_bufs, false);
> if (!skb)
> goto oom_next_rx;
> } else {
> @@ -3445,15 +3479,15 @@ static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info
>
> for (i = 0; i < max_idx; i++) {
> struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i];
> - struct page *page = rx_agg_buf->page;
> + netmem_ref netmem = rx_agg_buf->netmem;
>
> - if (!page)
> + if (!netmem)
> continue;
>
> - rx_agg_buf->page = NULL;
> + rx_agg_buf->netmem = 0;
> __clear_bit(i, rxr->rx_agg_bmap);
>
> - page_pool_recycle_direct(rxr->page_pool, page);
> + page_pool_recycle_direct_netmem(rxr->page_pool, netmem);
> }
> }
>
> @@ -3746,7 +3780,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp)
> xdp_rxq_info_unreg(&rxr->xdp_rxq);
>
> page_pool_destroy(rxr->page_pool);
> - if (bnxt_separate_head_pool())
> + if (bnxt_separate_head_pool(rxr))
> page_pool_destroy(rxr->head_pool);
> rxr->page_pool = rxr->head_pool = NULL;
>
> @@ -3777,15 +3811,20 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
> pp.dev = &bp->pdev->dev;
> pp.dma_dir = bp->rx_dir;
> pp.max_len = PAGE_SIZE;
> - pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
> + pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV |
> + PP_FLAG_ALLOW_UNREADABLE_NETMEM;
FWIW I had expected drivers to only set
PP_FLAG_ALLOW_UNREADABLE_NETMEM if the driver is capable of handling
unreadable netmem in this configuration, i.e. header split is turned
on and headersplit threshold is 0, and I think we're planning to do
that for GVE.
I know that there is a core check on binding for this, but in my
experience some of these settings may get reset on driver resets? And
core could miss a check here and there. Checking here on page_pool
create seems like a straightforward way to prevent some bugs. although
it could be seen as a defensive check.
But this is fine too, no strong feelings here:
Reviewed-by: Mina Almasry <almasrymina@...gle.com>
Powered by blists - more mailing lists