From: Long Li <[email protected]>

The HWC starts with depth-one bootstrap queues. Treat the PF-reported depth
as a maximum and rebuild the channel exactly for reports from 2 through
128. Keep the untouched bootstrap queues for depth one and reports above
128, and require a rebuilt channel to repeat the selected depth.

Treat the reported request and response sizes as directional maxima.
Rebuild only when both reports equal the 4096-byte bootstrap allocation.
Keep allocation strides separate from these limits, and share the effective
host-to-PF request budget with the GDMA and RDMA request builders. Bound
RDMA CREATE and ADD_PAGES batches by that budget, checking that the headers
and at least one page address fit before subtracting their sizes.

Reject oversized messages before acquiring a slot or publishing caller
storage. A retained, stopped channel still returns -ENODEV rather than
reporting a size error against uninitialized negotiated limits.

Keep each candidate private through queue creation, establishment and the
direct EQ test. Publish only the final tested channel. If a rebuild fails,
including its functional test, tear it down and restore fresh, tested
bootstrap queues. Stop if teardown is not acknowledged; never reuse
PF-owned mappings. Restore the previous live timeout budget before the
fallback so a failed test's fail-fast reduction does not poison the retry,
without reviving terminal cancellation.

Invalidate the previous HWC doorbell before every ESTABLISH_HWC. Validate
the BAR0 page geometry and reported index before accepting a new doorbell,
and suppress MMIO while it is invalid. This also hardens initial setup,
which previously accepted an unchecked device-supplied index. A malformed
doorbell completes initialization with -EPROTO without relying on later
INIT_DONE events that might require re-arming through that doorbell.

Use the initial PF report to select the queue geometry. Driver-version
advertisement occurs after HWC establishment and cannot negotiate behavior
needed while the channel is being created.

Link: https://lore.kernel.org/r/[email protected]
Link: 
https://lore.kernel.org/r/[email protected]
Signed-off-by: Long Li <[email protected]>
Signed-off-by: Wei Hu <[email protected]>
---
 drivers/infiniband/hw/mana/main.c             |  19 +-
 .../net/ethernet/microsoft/mana/gdma_main.c   |  26 +-
 .../net/ethernet/microsoft/mana/hw_channel.c  | 313 +++++++++++++++---
 include/net/mana/gdma.h                       |   2 +
 include/net/mana/hw_channel.h                 |  18 +-
 5 files changed, 313 insertions(+), 65 deletions(-)

diff --git a/drivers/infiniband/hw/mana/main.c 
b/drivers/infiniband/hw/mana/main.c
index e4414d208d4a..ce840cee42ca 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -406,28 +406,38 @@ static int mana_ib_gd_create_dma_region(struct 
mana_ib_dev *dev, struct ib_umem
        unsigned int create_req_msg_size;
        struct hw_channel_context *hwc;
        struct ib_block_iter biter;
-       size_t max_pgs_add_cmd = 0;
+       size_t max_pgs_add_cmd;
        size_t max_pgs_create_cmd;
        struct gdma_context *gc;
        size_t num_pages_total;
        unsigned int tail = 0;
+       u32 req_limit;
        u64 *page_addr_list;
        void *request_buf;
        int err = 0;
 
        gc = mdev_to_gc(dev);
        hwc = gc->hwc.driver_data;
+       req_limit = mana_hwc_get_max_req_size(hwc);
+       if (req_limit < struct_size(create_req, page_addr_list, 1) ||
+           req_limit < struct_size(add_req, page_addr_list, 1)) {
+               ibdev_dbg(&dev->ib_dev,
+                         "HWC request budget %u is too small for DMA region 
commands\n",
+                         req_limit);
+               return -EMSGSIZE;
+       }
 
        num_pages_total = ib_umem_num_dma_blocks(umem, page_sz);
 
        max_pgs_create_cmd =
-               (hwc->max_req_msg_size - sizeof(*create_req)) / sizeof(u64);
+               (req_limit - sizeof(*create_req)) / sizeof(u64);
+       max_pgs_add_cmd = (req_limit - sizeof(*add_req)) / sizeof(u64);
        num_pages_to_handle =
                min_t(size_t, num_pages_total, max_pgs_create_cmd);
        create_req_msg_size =
                struct_size(create_req, page_addr_list, num_pages_to_handle);
 
-       request_buf = kzalloc(hwc->max_req_msg_size, GFP_KERNEL);
+       request_buf = kzalloc(req_limit, GFP_KERNEL);
        if (!request_buf)
                return -ENOMEM;
 
@@ -470,9 +480,6 @@ static int mana_ib_gd_create_dma_region(struct mana_ib_dev 
*dev, struct ib_umem
                        if (err)
                                goto out;
 
-                       max_pgs_add_cmd = (hwc->max_req_msg_size -
-                               sizeof(*add_req)) / sizeof(u64);
-
                        add_req = request_buf;
                        add_req->dma_region_handle = *gdma_region;
                        add_req->reserved3 = 0;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c 
b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 429cf2b8e65c..8b08f28bfdb8 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -589,12 +589,26 @@ static int mana_gd_disable_queue(struct gdma_queue *queue)
 #define DOORBELL_OFFSET_EQ     0xFF8
 #define DOORBELL_OFFSET_DIM    0x820
 
+bool mana_gd_is_valid_doorbell(struct gdma_context *gc, u32 db_id)
+{
+       if (!gc->db_page_size || gc->db_page_off >= gc->bar0_size)
+               return false;
+
+       return gc->db_page_off +
+              gc->db_page_size * ((u64)db_id + 1) <= gc->bar0_size;
+}
+
 static void mana_gd_ring_doorbell(struct gdma_context *gc, u32 db_index,
                                  enum gdma_queue_type q_type, u32 qid,
                                  u32 tail_ptr, u8 num_req)
 {
-       void __iomem *addr = gc->db_page_base + gc->db_page_size * db_index;
        union gdma_doorbell_entry e = {};
+       void __iomem *addr;
+
+       if (unlikely(db_index == INVALID_DOORBELL))
+               return;
+
+       addr = gc->db_page_base + gc->db_page_size * db_index;
 
        switch (q_type) {
        case GDMA_EQ:
@@ -1254,7 +1268,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd,
        /* The caller must keep the HWC alive throughout queue creation. */
        hwc = gc->hwc.driver_data;
        req_msg_size = struct_size(req, page_addr_list, num_page);
-       if (req_msg_size > hwc->max_req_msg_size)
+       if (req_msg_size > mana_hwc_get_max_req_size(hwc))
                return -EINVAL;
 
        req = kzalloc(req_msg_size, GFP_KERNEL);
@@ -1534,13 +1548,7 @@ int mana_gd_register_device(struct gdma_dev *gd)
                return err ? err : -EPROTO;
        }
 
-       /* Validate that doorbell page for db_id is within the BAR0 region.
-        * In mana_gd_ring_doorbell(), the address is calculated as:
-        *   addr = db_page_base + db_page_size * db_id
-        *        = (bar0_va + db_page_off) + (db_page_size * db_id)
-        * So we need: db_page_off + db_page_size * (db_id + 1) <= bar0_size
-        */
-       if (gc->db_page_off + gc->db_page_size * ((u64)resp.db_id + 1) > 
gc->bar0_size) {
+       if (!mana_gd_is_valid_doorbell(gc, resp.db_id)) {
                dev_err(gc->dev, "Doorbell ID %u out of range\n", resp.db_id);
                return -EPROTO;
        }
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c 
b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 9ea67c076ebd..c4cae1baaef4 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -38,17 +38,33 @@ static void mana_hwc_timeout_reduce(struct 
hw_channel_context *hwc)
                old_timeout = mana_hwc_timeout_read(hwc);
 }
 
-static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, void *resp,
-                                 u32 resp_len,
+static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u32 req_len,
+                                 void *resp, u32 resp_len,
                                  struct hwc_caller_ctx **caller_ctx)
 {
        struct gdma_resource *r = &hwc->inflight_msg_res;
        struct hwc_caller_ctx *ctx;
        unsigned long flags;
+       u32 req_limit;
+       u32 resp_limit;
        u32 wait_ms;
        u32 index;
        int err;
 
+       req_limit = mana_hwc_get_max_req_size(hwc);
+       resp_limit = min(hwc->rx_msg_size_limit, hwc->max_req_msg_size);
+       if (req_len > req_limit || resp_len > resp_limit) {
+               spin_lock_irqsave(&r->lock, flags);
+               err = hwc->channel_up ? -EMSGSIZE : -ENODEV;
+               spin_unlock_irqrestore(&r->lock, flags);
+
+               if (err == -EMSGSIZE)
+                       dev_err(hwc->dev,
+                               "HWC: message sizes req=%u/%u resp=%u/%u exceed 
channel maxima\n",
+                               req_len, req_limit, resp_len, resp_limit);
+               return err;
+       }
+
        wait_ms = mana_hwc_timeout_read(hwc);
        if (down_timeout(&hwc->sema, msecs_to_jiffies(wait_ms))) {
                spin_lock_irqsave(&r->lock, flags);
@@ -247,8 +263,18 @@ static void mana_hwc_init_event_handler(void *ctx, struct 
gdma_queue *q_self,
        switch (event->type) {
        case GDMA_EQE_HWC_INIT_EQ_ID_DB:
                eq_db.as_uint32 = event->details[0];
+               if (!mana_gd_is_valid_doorbell(gd->gdma_context,
+                                              eq_db.doorbell)) {
+                       dev_err(hwc->dev, "HWC: invalid doorbell %u\n",
+                               eq_db.doorbell);
+                       WRITE_ONCE(hwc->hwc_init_error, -EPROTO);
+                       complete(&hwc->hwc_init_eqe_comp);
+                       break;
+               }
+
                hwc->cq->gdma_eq->id = eq_db.eq_id;
                gd->doorbell = eq_db.doorbell;
+               hwc->hwc_init_doorbell = true;
                break;
 
        case GDMA_EQE_HWC_INIT_DATA:
@@ -270,7 +296,8 @@ static void mana_hwc_init_event_handler(void *ctx, struct 
gdma_queue *q_self,
                        break;
 
                case HWC_INIT_DATA_QUEUE_DEPTH:
-                       hwc->hwc_init_q_depth_max = (u16)val;
+                       /* Preserve the full 24-bit report for validation. */
+                       hwc->hwc_init_q_depth_max = val;
                        break;
 
                case HWC_INIT_DATA_MAX_REQUEST:
@@ -637,7 +664,8 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context 
*hwc, u16 q_depth,
 
        dma_buf->num_reqs = q_depth;
 
-       buf_size = MANA_PAGE_ALIGN(q_depth * max_msg_size);
+       /* mana_gd_alloc_memory() requires a power-of-two length. */
+       buf_size = roundup_pow_of_two(MANA_PAGE_ALIGN(q_depth * max_msg_size));
 
        gmi = &dma_buf->mem_info;
        err = mana_gd_alloc_memory(gc, buf_size, gmi, false);
@@ -844,10 +872,15 @@ static int mana_hwc_test_channel(struct 
hw_channel_context *hwc)
        return err;
 }
 
-static int mana_hwc_establish_channel(struct hw_channel_context *hwc,
-                                     u16 *q_depth,
-                                     u32 *max_req_msg_size,
-                                     u32 *max_resp_msg_size)
+struct mana_hwc_init_report {
+       u32 queue_depth;
+       u32 max_req_msg_size;
+       u32 max_resp_msg_size;
+};
+
+static int
+mana_hwc_establish_channel(struct hw_channel_context *hwc,
+                          struct mana_hwc_init_report *report)
 {
        struct gdma_context *gc = hwc->gdma_dev->gdma_context;
        struct gdma_queue *rq = hwc->rxq->gdma_wq;
@@ -859,6 +892,19 @@ static int mana_hwc_establish_channel(struct 
hw_channel_context *hwc,
        u32 cq_id;
        int err;
 
+       hwc->hwc_init_q_depth_max = 0;
+       hwc->hwc_init_max_req_msg_size = 0;
+       hwc->hwc_init_max_resp_msg_size = 0;
+       hwc->hwc_init_max_num_cqs = 0;
+       hwc->hwc_init_cq_id = 0;
+       hwc->hwc_init_doorbell = false;
+       WRITE_ONCE(hwc->hwc_init_error, 0);
+       gc->hwc.pdid = INVALID_PDID;
+       /* Re-establish must not rearm through the previous channel's doorbell. 
*/
+       gc->hwc.doorbell = INVALID_DOORBELL;
+       hwc->dest_vrq_id = 0;
+       hwc->dest_vrcq_id = 0;
+
        init_completion(&hwc->hwc_init_eqe_comp);
 
        err = mana_smc_setup_hwc(&gc->shm_channel, false,
@@ -873,9 +919,18 @@ static int mana_hwc_establish_channel(struct 
hw_channel_context *hwc,
        if (!wait_for_completion_timeout(&hwc->hwc_init_eqe_comp, 60 * HZ))
                return -ETIMEDOUT;
 
-       *q_depth = hwc->hwc_init_q_depth_max;
-       *max_req_msg_size = hwc->hwc_init_max_req_msg_size;
-       *max_resp_msg_size = hwc->hwc_init_max_resp_msg_size;
+       err = READ_ONCE(hwc->hwc_init_error);
+       if (err)
+               return err;
+
+       if (!hwc->hwc_init_doorbell) {
+               dev_err(hwc->dev, "HWC: missing valid doorbell in init data\n");
+               return -EPROTO;
+       }
+
+       report->queue_depth = hwc->hwc_init_q_depth_max;
+       report->max_req_msg_size = hwc->hwc_init_max_req_msg_size;
+       report->max_resp_msg_size = hwc->hwc_init_max_resp_msg_size;
 
        /* Snapshot the device-reported count and id once, so the same value
         * sizes, bounds and indexes cq_table even across the sleeping
@@ -925,6 +980,9 @@ static int mana_hwc_init_queues(struct hw_channel_context 
*hwc, u16 q_depth,
 {
        int err;
 
+       if (q_depth > U16_MAX / 2)
+               return -EINVAL;
+
        err = mana_hwc_init_inflight_msg(hwc, q_depth);
        if (err)
                return err;
@@ -957,10 +1015,11 @@ static int mana_hwc_init_queues(struct 
hw_channel_context *hwc, u16 q_depth,
 
        hwc->num_inflight_msg = q_depth;
        hwc->max_req_msg_size = max_req_msg_size;
+       hwc->max_resp_msg_size = max_resp_msg_size;
 
        return 0;
 out:
-       /* mana_hwc_create_channel() will do the cleanup.*/
+       /* The setup path tears down any partially initialized queues. */
        return err;
 }
 
@@ -976,6 +1035,33 @@ static void mana_hwc_clear_cq_table(struct gdma_context 
*gc)
        vfree(cq_table);
 }
 
+/* Setup is private; runtime teardown has unpublished and drained senders. */
+static void mana_hwc_destroy_queues(struct hw_channel_context *hwc)
+{
+       struct gdma_context *gc = hwc->gdma_dev->gdma_context;
+
+       mana_hwc_clear_cq_table(gc);
+
+       if (hwc->cq) {
+               mana_hwc_destroy_cq(gc, hwc->cq);
+               hwc->cq = NULL;
+       }
+
+       if (hwc->txq) {
+               mana_hwc_destroy_wq(hwc, hwc->txq);
+               hwc->txq = NULL;
+       }
+       if (hwc->rxq) {
+               mana_hwc_destroy_wq(hwc, hwc->rxq);
+               hwc->rxq = NULL;
+       }
+
+       kfree(hwc->caller_ctx);
+       hwc->caller_ctx = NULL;
+       mana_gd_free_res_map(&hwc->inflight_msg_res);
+       hwc->num_inflight_msg = 0;
+}
+
 static int mana_hwc_publish_channel(struct hw_channel_context *hwc)
 {
        struct gdma_context *gc = hwc->gdma_dev->gdma_context;
@@ -1092,16 +1178,11 @@ static void mana_hwc_fence_channel(struct gdma_context 
*gc,
                mana_hwc_unpublish_cq(gc, hwc->cq->gdma_cq);
 }
 
-static bool mana_hwc_release_channel(struct hw_channel_context *hwc)
+static int mana_hwc_teardown_queues(struct hw_channel_context *hwc)
 {
        struct gdma_context *gc = hwc->gdma_dev->gdma_context;
        int err;
 
-       mana_hwc_stop_channel(hwc);
-
-       /* An unacknowledged destroy leaves the PF's mappings live.  Fence
-        * software dispatch, but retain every PF-visible allocation.
-        */
        err = mana_smc_teardown_hwc(&gc->shm_channel, false,
                                    &hwc->setup_active);
        if (err) {
@@ -1109,28 +1190,26 @@ static bool mana_hwc_release_channel(struct 
hw_channel_context *hwc)
                        "HWC teardown failed: %d, retaining PF-visible 
resources\n",
                        err);
                mana_hwc_fence_channel(gc, hwc);
-               mana_hwc_retain_channel(hwc);
-               return false;
+               return err;
        }
 
-       mana_hwc_clear_cq_table(gc);
-
-       /* Fence the EQ before releasing the remaining HWC state. */
-       if (hwc->cq)
-               mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
+       mana_hwc_destroy_queues(hwc);
 
-       if (hwc->txq)
-               mana_hwc_destroy_wq(hwc, hwc->txq);
-
-       if (hwc->rxq)
-               mana_hwc_destroy_wq(hwc, hwc->rxq);
+       return 0;
+}
 
-       kfree(hwc->caller_ctx);
-       hwc->caller_ctx = NULL;
+static bool mana_hwc_release_channel(struct hw_channel_context *hwc)
+{
+       struct gdma_context *gc = hwc->gdma_dev->gdma_context;
+       int err;
 
-       mana_gd_free_res_map(&hwc->inflight_msg_res);
+       mana_hwc_stop_channel(hwc);
 
-       hwc->num_inflight_msg = 0;
+       err = mana_hwc_teardown_queues(hwc);
+       if (err) {
+               mana_hwc_retain_channel(hwc);
+               return false;
+       }
 
        hwc->gdma_dev->doorbell = INVALID_DOORBELL;
        hwc->gdma_dev->pdid = INVALID_PDID;
@@ -1179,32 +1258,168 @@ void mana_hwc_free_retained_channel(struct 
gdma_context *gc)
        gc->hwc.gdma_context = NULL;
 }
 
-static int mana_hwc_create_bootstrap_channel(struct hw_channel_context *hwc)
+static int
+mana_hwc_validate_report(struct hw_channel_context *hwc,
+                        const struct mana_hwc_init_report *report,
+                        u32 expected_depth, bool check_depth,
+                        bool require_exact_msg_sizes)
+{
+       if (!report->queue_depth || !report->max_req_msg_size ||
+           !report->max_resp_msg_size) {
+               dev_err(hwc->dev,
+                       "HWC: invalid maxima depth=%u req=%u resp=%u\n",
+                       report->queue_depth, report->max_req_msg_size,
+                       report->max_resp_msg_size);
+               return -EPROTO;
+       }
+
+       if (require_exact_msg_sizes &&
+           (report->max_req_msg_size != HW_CHANNEL_MAX_REQUEST_SIZE ||
+            report->max_resp_msg_size != HW_CHANNEL_MAX_RESPONSE_SIZE)) {
+               dev_err(hwc->dev,
+                       "HWC: rebuilt message maxima req=%u resp=%u, expected 
%u/%u\n",
+                       report->max_req_msg_size, report->max_resp_msg_size,
+                       HW_CHANNEL_MAX_REQUEST_SIZE,
+                       HW_CHANNEL_MAX_RESPONSE_SIZE);
+               return -EPROTO;
+       }
+
+       if (check_depth && report->queue_depth != expected_depth) {
+               dev_err(hwc->dev, "HWC: rebuilt depth %u, expected %u\n",
+                       report->queue_depth, expected_depth);
+               return -EPROTO;
+       }
+
+       return 0;
+}
+
+static int mana_hwc_finish_channel(struct hw_channel_context *hwc,
+                                  const struct mana_hwc_init_report *report)
+{
+       int err;
+
+       /* MAX_REQUEST sizes the RQ; MAX_RESPONSE sizes the SQ. */
+       hwc->rx_msg_size_limit = report->max_req_msg_size;
+       hwc->tx_msg_size_limit = report->max_resp_msg_size;
+
+       err = mana_hwc_test_channel(hwc);
+       if (err)
+               dev_err(hwc->dev, "Failed to test HWC: %d\n", err);
+
+       return err;
+}
+
+static int mana_hwc_build_channel(struct hw_channel_context *hwc, u16 q_depth,
+                                 struct mana_hwc_init_report *report)
 {
-       u32 max_req_msg_size, max_resp_msg_size;
-       u16 q_depth_max;
        int err;
 
-       err = mana_hwc_init_queues(hwc, HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH,
+       err = mana_hwc_init_queues(hwc, q_depth,
                                   HW_CHANNEL_MAX_REQUEST_SIZE,
                                   HW_CHANNEL_MAX_RESPONSE_SIZE);
        if (err) {
-               dev_err(hwc->dev, "Failed to initialize HWC: %d\n", err);
+               dev_err(hwc->dev, "Failed to initialize HWC depth %u: %d\n",
+                       q_depth, err);
                return err;
        }
 
-       err = mana_hwc_establish_channel(hwc, &q_depth_max, &max_req_msg_size,
-                                        &max_resp_msg_size);
-       if (err) {
-               dev_err(hwc->dev, "Failed to establish HWC: %d\n", err);
+       err = mana_hwc_establish_channel(hwc, report);
+       if (err)
+               dev_err(hwc->dev, "Failed to establish HWC depth %u: %d\n",
+                       q_depth, err);
+
+       return err;
+}
+
+static int
+mana_hwc_restore_bootstrap(struct hw_channel_context *hwc,
+                          struct mana_hwc_init_report *report)
+{
+       int err;
+
+       err = mana_hwc_build_channel(hwc,
+                                    HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH,
+                                    report);
+       if (err)
                return err;
-       }
 
-       err = mana_hwc_test_channel(hwc);
+       err = mana_hwc_validate_report(hwc, report, 0, false, false);
        if (err)
-               dev_err(hwc->dev, "Failed to test HWC: %d\n", err);
+               return err;
 
-       return err;
+       return mana_hwc_finish_channel(hwc, report);
+}
+
+static int mana_hwc_rebuild_channel(struct hw_channel_context *hwc,
+                                   u16 q_depth,
+                                   struct mana_hwc_init_report *report)
+{
+       u32 timeout_ms = mana_hwc_timeout_read(hwc);
+       int cleanup_err;
+       int err;
+
+       err = mana_hwc_teardown_queues(hwc);
+       if (err)
+               return err;
+
+       err = mana_hwc_build_channel(hwc, q_depth, report);
+       if (!err)
+               err = mana_hwc_validate_report(hwc, report, q_depth, true, 
true);
+       if (!err)
+               err = mana_hwc_finish_channel(hwc, report);
+       if (!err)
+               return 0;
+
+       dev_warn(hwc->dev,
+                "HWC depth %u rebuild failed, restoring bootstrap: %d\n",
+                q_depth, err);
+
+       cleanup_err = mana_hwc_teardown_queues(hwc);
+       if (cleanup_err)
+               return cleanup_err;
+
+       /* Do not carry the failed test's reduced wait into the retry. */
+       mana_hwc_timeout_update(hwc, timeout_ms);
+
+       return mana_hwc_restore_bootstrap(hwc, report);
+}
+
+static int mana_hwc_prepare_channel(struct hw_channel_context *hwc)
+{
+       struct mana_hwc_init_report report;
+       u16 rebuild_depth;
+       int err;
+
+       err = mana_hwc_build_channel(hwc,
+                                    HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH,
+                                    &report);
+       if (err)
+               return err;
+
+       err = mana_hwc_validate_report(hwc, &report, 0, false, false);
+       if (err)
+               return err;
+
+       if (report.queue_depth > HW_CHANNEL_MAX_QUEUE_DEPTH) {
+               dev_warn(hwc->dev,
+                        "HWC depth %u exceeds limit %u, keeping bootstrap\n",
+                        report.queue_depth, HW_CHANNEL_MAX_QUEUE_DEPTH);
+       } else if (report.queue_depth >
+                  HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH &&
+                  (report.max_req_msg_size != HW_CHANNEL_MAX_REQUEST_SIZE ||
+                   report.max_resp_msg_size != HW_CHANNEL_MAX_RESPONSE_SIZE)) {
+               dev_warn(hwc->dev,
+                        "HWC maxima req=%u resp=%u differ from rebuild policy 
%u/%u, keeping bootstrap\n",
+                        report.max_req_msg_size, report.max_resp_msg_size,
+                        HW_CHANNEL_MAX_REQUEST_SIZE,
+                        HW_CHANNEL_MAX_RESPONSE_SIZE);
+       } else if (report.queue_depth >
+                  HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH) {
+               rebuild_depth = report.queue_depth;
+               return mana_hwc_rebuild_channel(hwc, rebuild_depth, &report);
+       }
+
+       return mana_hwc_finish_channel(hwc, &report);
 }
 
 int mana_hwc_create_channel(struct gdma_context *gc)
@@ -1237,7 +1452,7 @@ int mana_hwc_create_channel(struct gdma_context *gc)
        gd->pdid = INVALID_PDID;
        gd->doorbell = INVALID_DOORBELL;
 
-       err = mana_hwc_create_bootstrap_channel(hwc);
+       err = mana_hwc_prepare_channel(hwc);
        if (err) {
                mana_hwc_release_channel(hwc);
                return err;
@@ -1391,7 +1606,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, 
u32 req_len,
        u32 command;
        int err;
 
-       err = mana_hwc_get_msg_index(hwc, resp, resp_len, &ctx);
+       err = mana_hwc_get_msg_index(hwc, req_len, resp, resp_len, &ctx);
        if (err)
                return err;
 
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 67430faecc44..a2e5ad3543ae 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -594,6 +594,8 @@ void mana_gd_fence_eq(struct gdma_context *gc, struct 
gdma_queue *queue);
 
 int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int 
num_cqe);
 
+bool mana_gd_is_valid_doorbell(struct gdma_context *gc, u32 db_id);
+
 void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit);
 
 ssize_t mana_gd_read_ring(struct gdma_queue *q, char __user *buf,
diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h
index 9d6a0a535e7a..73315aca2e00 100644
--- a/include/net/mana/hw_channel.h
+++ b/include/net/mana/hw_channel.h
@@ -5,6 +5,7 @@
 #define _HW_CHANNEL_H
 
 #include <linux/atomic.h>
+#include <linux/minmax.h>
 
 #define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ  4
 
@@ -13,6 +14,9 @@
 
 #define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1
 
+/* Largest supported rebuild depth; larger reports retain bootstrap queues. */
+#define HW_CHANNEL_MAX_QUEUE_DEPTH 128
+
 #define HWC_INIT_DATA_CQID             1
 #define HWC_INIT_DATA_RQID             2
 #define HWC_INIT_DATA_SQID             3
@@ -200,12 +204,18 @@ struct hw_channel_context {
 
        u16 num_inflight_msg;
        u32 max_req_msg_size;
+       u32 max_resp_msg_size;
+       /* Immutable reported maxima for the final RQ and SQ directions. */
+       u32 rx_msg_size_limit;
+       u32 tx_msg_size_limit;
 
-       u16 hwc_init_q_depth_max;
+       u32 hwc_init_q_depth_max;
        u32 hwc_init_max_req_msg_size;
        u32 hwc_init_max_resp_msg_size;
        u32 hwc_init_max_num_cqs;
        u32 hwc_init_cq_id;
+       bool hwc_init_doorbell;
+       int hwc_init_error;
 
        struct completion hwc_init_eqe_comp;
 
@@ -242,6 +252,12 @@ struct hw_channel_context {
        struct hwc_caller_ctx *caller_ctx;
 };
 
+/* Host-to-PF requests are bounded by the negotiated TX limit and SQ stride. */
+static inline u32 mana_hwc_get_max_req_size(const struct hw_channel_context 
*hwc)
+{
+       return min(hwc->tx_msg_size_limit, hwc->max_resp_msg_size);
+}
+
 int mana_hwc_create_channel(struct gdma_context *gc);
 void mana_hwc_destroy_channel(struct gdma_context *gc);
 void mana_hwc_free_retained_channel(struct gdma_context *gc);
-- 
2.43.0


Reply via email to