mana_hwc_destroy_channel() decides whether to tear the channel down by looking at gc->max_num_cqs, which is only set when the device delivers an HWC_INIT_DATA_MAX_NUM_CQS bootstrap event. That is a proxy for "the device is using the queues", and it is a poor one: the event arrives well after mana_smc_setup_hwc() has already handed the queue addresses to the PF, so a setup that fails in between leaves no reliable signal.
Record the handover directly instead. mana_smc_setup_hwc() clears the new setup_active flag on entry and sets it immediately before it writes the ESTABLISH_HWC message, so the flag is exact in both directions: the three exits before that write leave the device untouched and clear the flag, while everything after it -- including a failed response -- leaves it set, because the PF has the queue addresses either way. No functional change is intended for the current single-establish flow. This is preparation for the reinit path added later in this series, which tears the channel down and rebuilds it at a larger queue depth and needs to know whether a given attempt left the device holding the queues. Signed-off-by: Long Li <[email protected]> --- .../net/ethernet/microsoft/mana/hw_channel.c | 19 +++++++++++++------ .../net/ethernet/microsoft/mana/shm_channel.c | 11 ++++++++++- include/net/mana/hw_channel.h | 10 ++++++++++ include/net/mana/shm_channel.h | 2 +- 4 files changed, 34 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 263e7c4e2934186af037be4c80350a6e322b6771..75fdccdc8c48201b011a243fd0bd41b84c477076 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -683,7 +683,7 @@ static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth, cq->mem_info.dma_handle, rq->mem_info.dma_handle, sq->mem_info.dma_handle, - eq->eq.msix_index); + eq->eq.msix_index, &hwc->setup_active); if (err) return err; @@ -815,13 +815,20 @@ void mana_hwc_destroy_channel(struct gdma_context *gc) if (!hwc) return; - /* gc->max_num_cqs is set in mana_hwc_init_event_handler(). If it's - * non-zero, the HWC worked and we should tear down the HWC here. + /* Tear down only if setup_hwc() handed the queues to the PF. Until + * then the device never saw them, so there is nothing to undo. */ - if (gc->max_num_cqs > 0) { - mana_smc_teardown_hwc(&gc->shm_channel, false); - gc->max_num_cqs = 0; + if (hwc->setup_active) { + /* Only a successful teardown invalidates the MST entries. If + * it fails the device may still be using the queues, so leave + * the flag set rather than record a clean teardown. + */ + if (!mana_smc_teardown_hwc(&gc->shm_channel, false)) + hwc->setup_active = false; + else + dev_err(hwc->dev, "Failed to tear down HWC\n"); } + gc->max_num_cqs = 0; if (hwc->txq) mana_hwc_destroy_wq(hwc, hwc->txq); diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index d21b5db06e5092d82249fb1053d07f65aa38490c..1ec8e3661721dc8663975477b7ed09fcda72e2ab 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -129,9 +129,15 @@ void mana_smc_init(struct shm_channel *sc, struct device *dev, sc->base = base; } +/* Clear *submitted on entry and set it once the ESTABLISH_HWC message has + * been handed to the PF, i.e. once the device may start using the queues. + * The caller uses it to decide whether a failure still needs + * mana_smc_teardown_hwc(): the exits below leave the device untouched, so + * they must not require one. + */ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, u64 cq_addr, u64 rq_addr, u64 sq_addr, - u32 eq_msix_index) + u32 eq_msix_index, bool *submitted) { union smc_proto_hdr *hdr; u16 all_addr_h4bits = 0; @@ -144,6 +150,8 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, int err; int i; + *submitted = false; + /* Ensure VF already has possession of shared memory */ err = mana_smc_poll_register(sc->base, false); if (err) { @@ -229,6 +237,7 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, /* Write 256-message buffer to shared memory (final 32-bit write * triggers HW to set possession bit to PF). */ + *submitted = true; dword = (u32 *)shm_buf; for (i = 0; i < SMC_APERTURE_DWORDS; i++) writel(*dword++, sc->base + i * SMC_BASIC_UNIT); diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h index 16feb39616c1bead1a043b3fadc2e18a90651516..237608b488e5ee773d7889d3c1d291ca92ebbeb9 100644 --- a/include/net/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h @@ -199,6 +199,16 @@ struct hw_channel_context { u32 pf_dest_vrcq_id; u32 hwc_timeout; + /* True once mana_smc_setup_hwc() has handed the ESTABLISH_HWC message + * to the PF, so the device may DMA into the HWC buffers. That + * function clears it on entry and sets it at the handover, so only a + * failure before the handover leaves it false; a failure after it -- + * including one reported by mana_hwc_establish_channel() -- leaves it + * set, which is what makes teardown attempt DESTROY_HWC. Cleared + * again once that teardown succeeds. + */ + bool setup_active; + struct hwc_caller_ctx *caller_ctx; }; diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h index dbabcfb95daf3e87b39a657e3a5f23a1508d4f31..e96387d795259d52aeec7b3fe0981825d90a3822 100644 --- a/include/net/mana/shm_channel.h +++ b/include/net/mana/shm_channel.h @@ -20,7 +20,7 @@ void mana_smc_init(struct shm_channel *sc, struct device *dev, int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, u64 cq_addr, u64 rq_addr, u64 sq_addr, - u32 eq_msix_index); + u32 eq_msix_index, bool *submitted); int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf); -- 2.43.0
