* [PATCH net-next v10 1/4] net: mana: prepare HWC ownership for safe reinitialization
2026-11-09 15:44 [PATCH net-next v10 0/4] net: mana: concurrent HWC requests and dynamic queue depth Wei Hu
@ 2026-11-09 15:45 ` Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 2/4] net: mana: give each HWC message slot its own completion state Wei Hu
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Wei Hu @ 2026-11-09 15:45 UTC (permalink / raw)
To: longli, kotaranov, kuba, davem, pabeni, edumazet, andrew+netdev,
jgg, leon, haiyangz, wei.liu, decui, shradhagupta, horms, ernis,
stephen
Cc: netdev, linux-rdma, linux-hyperv, linux-kernel, gargaditya,
kees+treewide, kees, mawasthi, weh, edumazet
From: Long Li <longli@microsoft.com>
Dynamic HWC queue sizing tears down the bootstrap queues and establishes a
second channel before publishing it. Prepare the existing HWC ownership and
teardown paths so that sequence cannot free or reuse state still reachable
by either the PF or an EQ handler.
The shared-memory aperture carries one request at a time. Serialize the
complete ESTABLISH_HWC and DESTROY_HWC transactions, including possession
polling and response validation. Record setup_active immediately before the
MMIO submission and clear it only after DESTROY_HWC is acknowledged.
Treat an unacknowledged destroy as retained PF ownership. Fence the HWC EQ
and withdraw its CQ from dispatch, but keep all queue memory and wrappers
for a later teardown retry. A new channel creation retries that retained
context before assigning fresh queues to the PF.
When a PCI or CDX transport permanently discards its gdma_context, no such
retry is possible. After IRQ and service-work teardown, release the
software-only HWC state through a common final-disposal helper. Leave the
coherent DMA allocations unreclaimed rather than exposing freed memory to
a PF whose teardown was not acknowledged.
Snapshot the bootstrap CQ count and CQ ID after INIT_DONE. Publish the
fixed bound with the allocated table so later init events cannot grow the
bound past the allocation. Use a single acquire-loaded table snapshot in
both normal and throttled EQE dispatch, with annotated CQ-slot reads.
On acknowledged teardown, withdraw the CQ table and wait for all existing
IRQ-side RCU readers before freeing the HWC queue bundle. This also covers
a completion dispatched through a different EQ, without a per-event
reference. Fence the dedicated EQ's remaining callbacks before releasing
the CQ, completion buffer and work queues. Keep the parent EQ allocated
until CQ destruction has detached its throttled-EQE child entry. Preserve
the existing generic CQ detach and RCU handling.
Link: https://lore.kernel.org/r/20260908035201.402424-2-longli@microsoft.com
Link: https://lore.kernel.org/r/20260908035201.402424-5-longli@microsoft.com
Link: https://lore.kernel.org/r/178910960115.219967.13830871915506436112@kernel.org
Link: https://lore.kernel.org/r/179196575238.434549.10775387794024020898@kernel.org
Link: https://lore.kernel.org/r/sashiko-outbox-170992@kernel.org
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Wei Hu <weh@microsoft.com>
Copilot-Session: 8c2361e6-c0f4-4b0c-bf01-b5e4cdacec50
---
.../net/ethernet/microsoft/mana/gdma_cdx.c | 4 +-
.../net/ethernet/microsoft/mana/gdma_main.c | 41 +++-
.../net/ethernet/microsoft/mana/gdma_pci.c | 4 +-
.../net/ethernet/microsoft/mana/hw_channel.c | 187 +++++++++++++++---
.../net/ethernet/microsoft/mana/shm_channel.c | 58 +++++-
include/net/mana/gdma.h | 4 +
include/net/mana/hw_channel.h | 5 +
include/net/mana/shm_channel.h | 10 +-
8 files changed, 275 insertions(+), 38 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_cdx.c b/drivers/net/ethernet/microsoft/mana/gdma_cdx.c
index 0d01e3d2f0d9..2e0dcb902d7e 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_cdx.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_cdx.c
@@ -279,7 +279,7 @@ static int mana_cdx_gd_probe(struct cdx_device *cdx_dev)
iounmap(bar0_va);
free_gc:
dev_set_drvdata(&cdx_dev->dev, NULL);
- vfree(gc);
+ mana_gd_free_context(gc);
clear_master:
cdx_clear_master(cdx_dev);
return err;
@@ -298,7 +298,7 @@ static int mana_cdx_gd_remove(struct cdx_device *cdx_dev)
iounmap(gc->bar0_va);
dev_set_drvdata(&cdx_dev->dev, NULL);
- vfree(gc);
+ mana_gd_free_context(gc);
return 0;
}
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index ab942d5bfe05..8df130386da3 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -11,6 +11,7 @@
#include <linux/irqdomain.h>
#include <linux/export.h>
#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
#include <net/mana/mana.h>
#include <net/mana/hw_channel.h>
@@ -760,9 +761,15 @@ void mana_gd_free_service_wq(struct gdma_context *gc)
static void mana_gd_schedule_eq_cqs(struct gdma_queue *eq)
{
struct gdma_context *gc = eq->gdma_dev->gdma_context;
+ struct gdma_queue **cq_table;
struct gdma_queue *cq;
u8 i;
+ /* The IRQ's RCU read-side section protects this table snapshot. */
+ cq_table = smp_load_acquire(&gc->cq_table);
+ if (!cq_table)
+ return;
+
for (i = 0; i < GDMA_EQ_MAX_CHILD_CQ; i++) {
cq = rcu_dereference(eq->eq.child_cq[i]);
@@ -770,7 +777,7 @@ static void mana_gd_schedule_eq_cqs(struct gdma_queue *eq)
continue;
if (cq->id >= READ_ONCE(gc->max_num_cqs) ||
- !gc->cq_table || gc->cq_table[cq->id] != cq)
+ READ_ONCE(cq_table[cq->id]) != cq)
continue;
if (cq->cq.callback)
@@ -785,6 +792,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
union gdma_eqe_info eqe_info;
enum gdma_eqe_type type;
struct gdma_event event;
+ struct gdma_queue **cq_table;
struct gdma_queue *cq;
struct gdma_eqe *eqe;
u32 cq_id;
@@ -796,11 +804,16 @@ static void mana_gd_process_eqe(struct gdma_queue *eq)
switch (type) {
case GDMA_EQE_COMPLETION:
cq_id = eqe->details[0] & 0xFFFFFF;
- if (WARN_ON_ONCE(cq_id >= gc->max_num_cqs))
+ /* The IRQ handler's RCU read-side section protects the table
+ * until HWC teardown has fenced its EQ and waited for readers.
+ */
+ cq_table = smp_load_acquire(&gc->cq_table);
+ if (!cq_table || cq_id >= READ_ONCE(gc->max_num_cqs))
break;
- cq = gc->cq_table[cq_id];
- if (WARN_ON_ONCE(!cq || cq->type != GDMA_CQ || cq->id != cq_id))
+ cq = READ_ONCE(cq_table[cq_id]);
+ if (!cq || WARN_ON_ONCE(cq->type != GDMA_CQ ||
+ cq->id != cq_id))
break;
if (cq->cq.callback)
@@ -1032,23 +1045,32 @@ int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
return err;
}
-static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_evenets,
+static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_events,
struct gdma_queue *queue)
{
int err;
- if (flush_evenets) {
+ if (queue->eq.msix_index == INVALID_PCI_MSIX_INDEX)
+ return;
+
+ if (flush_events) {
err = mana_gd_test_eq(gc, queue);
if (err && mana_need_log(gc, err))
dev_warn(gc->dev, "Failed to flush EQ: %d\n", err);
}
mana_gd_deregister_irq(queue);
+ queue->eq.msix_index = INVALID_PCI_MSIX_INDEX;
if (queue->eq.disable_needed)
mana_gd_disable_queue(queue);
}
+void mana_gd_fence_eq(struct gdma_context *gc, struct gdma_queue *queue)
+{
+ mana_gd_destroy_eq(gc, false, queue);
+}
+
static int mana_gd_create_eq(struct gdma_dev *gd,
const struct gdma_queue_spec *spec,
bool create_hwq, struct gdma_queue *queue)
@@ -2113,6 +2135,13 @@ void mana_gd_cleanup(struct gdma_context *gc)
}
EXPORT_SYMBOL_NS(mana_gd_cleanup, "NET_MANA");
+void mana_gd_free_context(struct gdma_context *gc)
+{
+ mana_hwc_free_retained_channel(gc);
+ vfree(gc);
+}
+EXPORT_SYMBOL_NS(mana_gd_free_context, "NET_MANA");
+
static int __init gdma_core_init(void)
{
mana_debugfs_root = debugfs_create_dir("mana", NULL);
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_pci.c b/drivers/net/ethernet/microsoft/mana/gdma_pci.c
index ed8925296c8a..7935cb274e36 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_pci.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_pci.c
@@ -725,7 +725,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
pci_iounmap(pdev, bar0_va);
free_gc:
pci_set_drvdata(pdev, NULL);
- vfree(gc);
+ mana_gd_free_context(gc);
release_region:
pci_release_regions(pdev);
disable_dev:
@@ -778,7 +778,7 @@ static void mana_gd_remove(struct pci_dev *pdev)
pci_iounmap(pdev, gc->bar0_va);
- vfree(gc);
+ mana_gd_free_context(gc);
pci_release_regions(pdev);
pci_disable_device(pdev);
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index fb9f38f65911..9e0964072af9 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -134,7 +134,7 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
switch (type) {
case HWC_INIT_DATA_CQID:
- hwc->cq->gdma_cq->id = val;
+ WRITE_ONCE(hwc->hwc_init_cq_id, val);
break;
case HWC_INIT_DATA_RQID:
@@ -158,7 +158,11 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
break;
case HWC_INIT_DATA_MAX_NUM_CQS:
- gd->gdma_context->max_num_cqs = val;
+ /* Store only; establish_channel() commits it to
+ * max_num_cqs once, so a later event cannot grow the
+ * bound past the allocation; pairs with READ_ONCE().
+ */
+ WRITE_ONCE(hwc->hwc_init_max_num_cqs, val);
break;
case HWC_INIT_DATA_PDID:
@@ -382,9 +386,43 @@ static void mana_hwc_comp_event(void *ctx, struct gdma_queue *q_self)
mana_gd_ring_cq(q_self, SET_ARM_BIT);
}
+static int mana_hwc_publish_cq(struct gdma_context *gc,
+ struct gdma_queue *cq)
+{
+ struct gdma_queue **cq_table = READ_ONCE(gc->cq_table);
+ u32 id = READ_ONCE(cq->id);
+
+ if (!cq_table || id >= READ_ONCE(gc->max_num_cqs) ||
+ READ_ONCE(cq_table[id]))
+ return -EINVAL;
+
+ WRITE_ONCE(cq_table[id], cq);
+
+ return 0;
+}
+
+static void mana_hwc_unpublish_cq(struct gdma_context *gc,
+ struct gdma_queue *cq)
+{
+ struct gdma_queue **cq_table = READ_ONCE(gc->cq_table);
+ u32 id;
+
+ if (!cq_table || !cq)
+ return;
+
+ id = READ_ONCE(cq->id);
+ if (id < READ_ONCE(gc->max_num_cqs) &&
+ READ_ONCE(cq_table[id]) == cq)
+ WRITE_ONCE(cq_table[id], NULL);
+}
+
static void mana_hwc_destroy_cq(struct gdma_context *gc, struct hwc_cq *hwc_cq)
{
- kfree(hwc_cq->comp_buf);
+ /* Fence callbacks first, but keep the parent EQ alive until CQ
+ * destruction has detached its child entry.
+ */
+ if (hwc_cq->gdma_eq)
+ mana_gd_fence_eq(gc, hwc_cq->gdma_eq);
if (hwc_cq->gdma_cq)
mana_gd_destroy_queue(gc, hwc_cq->gdma_cq);
@@ -392,6 +430,7 @@ static void mana_hwc_destroy_cq(struct gdma_context *gc, struct hwc_cq *hwc_cq)
if (hwc_cq->gdma_eq)
mana_gd_destroy_queue(gc, hwc_cq->gdma_eq);
+ kfree(hwc_cq->comp_buf);
kfree(hwc_cq);
}
@@ -674,6 +713,9 @@ static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth,
struct gdma_queue *sq = hwc->txq->gdma_wq;
struct gdma_queue *eq = hwc->cq->gdma_eq;
struct gdma_queue *cq = hwc->cq->gdma_cq;
+ struct gdma_queue **cq_table;
+ u32 num_cqs;
+ u32 cq_id;
int err;
init_completion(&hwc->hwc_init_eqe_comp);
@@ -683,7 +725,7 @@ 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;
@@ -694,15 +736,45 @@ static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth,
*max_req_msg_size = hwc->hwc_init_max_req_msg_size;
*max_resp_msg_size = hwc->hwc_init_max_resp_msg_size;
- /* Both were set in mana_hwc_init_event_handler(). */
- if (WARN_ON(cq->id >= gc->max_num_cqs))
+ /* Snapshot the device-reported count and id once, so the same value
+ * sizes, bounds and indexes cq_table even across the sleeping
+ * vcalloc() and a concurrent init event.
+ */
+ num_cqs = READ_ONCE(hwc->hwc_init_max_num_cqs);
+ cq_id = READ_ONCE(hwc->hwc_init_cq_id);
+
+ /* Both operands come from untrusted HWC bootstrap events; a missing
+ * MAX_NUM_CQS leaves num_cqs at 0. Reject rather than WARN_ON() so a
+ * malformed device response cannot panic a panic_on_warn guest.
+ */
+ if (cq_id >= num_cqs) {
+ dev_err_ratelimited(hwc->dev,
+ "HWC: bad CQ id %u >= max %u\n",
+ cq_id, num_cqs);
return -EPROTO;
+ }
+
+ /* Init events remain enabled, so commit the validated CQ ID once. */
+ WRITE_ONCE(cq->id, cq_id);
- gc->cq_table = vcalloc(gc->max_num_cqs, sizeof(struct gdma_queue *));
- if (!gc->cq_table)
+ cq_table = vcalloc(num_cqs, sizeof(*cq_table));
+ if (!cq_table)
return -ENOMEM;
- gc->cq_table[cq->id] = cq;
+ /* Publish the bound and the initialised table together; the release
+ * pairs with smp_load_acquire() in mana_gd_process_eqe().
+ */
+ WRITE_ONCE(gc->max_num_cqs, num_cqs);
+ /* Pairs with smp_load_acquire() in mana_gd_process_eqe(). */
+ smp_store_release(&gc->cq_table, cq_table);
+
+ err = mana_hwc_publish_cq(gc, cq);
+ if (err) {
+ dev_err_ratelimited(hwc->dev,
+ "HWC: failed to publish CQ %u: %d\n",
+ cq_id, err);
+ return err;
+ }
return 0;
}
@@ -751,6 +823,18 @@ static int mana_hwc_init_queues(struct hw_channel_context *hwc, u16 q_depth,
return err;
}
+static void mana_hwc_clear_cq_table(struct gdma_context *gc)
+{
+ struct gdma_queue **cq_table;
+
+ cq_table = READ_ONCE(gc->cq_table);
+ WRITE_ONCE(gc->max_num_cqs, 0);
+ /* Stop new table readers before waiting for prior RCU readers. */
+ smp_store_release(&gc->cq_table, NULL);
+ synchronize_rcu();
+ vfree(cq_table);
+}
+
int mana_hwc_create_channel(struct gdma_context *gc)
{
u32 max_req_msg_size, max_resp_msg_size;
@@ -759,6 +843,13 @@ int mana_hwc_create_channel(struct gdma_context *gc)
u16 q_depth_max;
int err;
+ /* Retry a retained context before assigning queues to the PF again. */
+ if (gd->driver_data) {
+ mana_hwc_destroy_channel(gc);
+ if (gd->driver_data)
+ return -ETIMEDOUT;
+ }
+
hwc = kzalloc_obj(*hwc);
if (!hwc)
return -ENOMEM;
@@ -808,25 +899,45 @@ int mana_hwc_create_channel(struct gdma_context *gc)
return err;
}
+static void mana_hwc_fence_channel(struct gdma_context *gc,
+ struct hw_channel_context *hwc)
+{
+ if (!hwc->cq)
+ return;
+
+ if (hwc->cq->gdma_eq)
+ mana_gd_fence_eq(gc, hwc->cq->gdma_eq);
+
+ if (hwc->cq->gdma_cq)
+ mana_hwc_unpublish_cq(gc, hwc->cq->gdma_cq);
+}
+
void mana_hwc_destroy_channel(struct gdma_context *gc)
{
struct hw_channel_context *hwc = gc->hwc.driver_data;
+ int err;
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.
+ /* An unacknowledged destroy leaves the PF's mappings live. Fence
+ * software dispatch, but retain every PF-visible allocation.
*/
- if (gc->max_num_cqs > 0) {
- mana_smc_teardown_hwc(&gc->shm_channel, false);
- WRITE_ONCE(gc->max_num_cqs, 0);
+ err = mana_smc_teardown_hwc(&gc->shm_channel, false,
+ &hwc->setup_active);
+ if (err) {
+ dev_err(hwc->dev,
+ "HWC teardown failed: %d, retaining PF-visible resources\n",
+ err);
+ mana_hwc_fence_channel(gc, hwc);
+ return;
}
- if (hwc->cq)
- mana_gd_detach_cq(gc, hwc->cq->gdma_cq);
+ mana_hwc_clear_cq_table(gc);
- synchronize_rcu();
+ /* Fence the EQ before releasing the remaining HWC state. */
+ if (hwc->cq)
+ mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
if (hwc->txq)
mana_hwc_destroy_wq(hwc, hwc->txq);
@@ -834,9 +945,6 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
if (hwc->rxq)
mana_hwc_destroy_wq(hwc, hwc->rxq);
- if (hwc->cq)
- mana_hwc_destroy_cq(hwc->gdma_dev->gdma_context, hwc->cq);
-
kfree(hwc->caller_ctx);
hwc->caller_ctx = NULL;
@@ -852,9 +960,44 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
kfree(hwc);
gc->hwc.driver_data = NULL;
gc->hwc.gdma_context = NULL;
+}
- vfree(gc->cq_table);
- gc->cq_table = NULL;
+static void mana_hwc_free_retained_wq(struct hwc_wq *wq)
+{
+ if (!wq)
+ return;
+
+ kfree(wq->msg_buf);
+ kfree(wq->gdma_wq);
+ kfree(wq);
+}
+
+/* Final disposal after IRQ and service-work teardown, not a retry path.
+ * Free only software state: unacknowledged HWC DMA allocations stay live.
+ */
+void mana_hwc_free_retained_channel(struct gdma_context *gc)
+{
+ struct hw_channel_context *hwc = gc->hwc.driver_data;
+
+ if (!hwc)
+ return;
+
+ gc->hwc.driver_data = NULL;
+ mana_hwc_clear_cq_table(gc);
+
+ if (hwc->cq) {
+ kfree(hwc->cq->gdma_eq);
+ kfree(hwc->cq->gdma_cq);
+ kfree(hwc->cq->comp_buf);
+ kfree(hwc->cq);
+ }
+
+ mana_hwc_free_retained_wq(hwc->txq);
+ mana_hwc_free_retained_wq(hwc->rxq);
+ kfree(hwc->caller_ctx);
+ mana_gd_free_res_map(&hwc->inflight_msg_res);
+ kfree(hwc);
+ gc->hwc.gdma_context = NULL;
}
int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c
index d21b5db06e50..df9d05062dd5 100644
--- a/drivers/net/ethernet/microsoft/mana/shm_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c
@@ -125,13 +125,24 @@ static int mana_smc_read_response(struct shm_channel *sc, u32 msg_type,
void mana_smc_init(struct shm_channel *sc, struct device *dev,
void __iomem *base)
{
+ /* The first call precedes channel publication. Later calls refresh the
+ * BAR mapping after reset or resume without reinitializing a live lock.
+ */
+ if (!sc->transaction_lock_initialized) {
+ mutex_init(&sc->transaction_lock);
+ sc->transaction_lock_initialized = true;
+ }
+
+ mutex_lock(&sc->transaction_lock);
sc->dev = dev;
sc->base = base;
+ mutex_unlock(&sc->transaction_lock);
}
-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)
+static int mana_smc_setup_hwc_locked(struct shm_channel *sc, bool reset_vf,
+ u64 eq_addr, u64 cq_addr, u64 rq_addr,
+ u64 sq_addr, u32 eq_msix_index,
+ bool *submitted)
{
union smc_proto_hdr *hdr;
u16 all_addr_h4bits = 0;
@@ -144,6 +155,9 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr,
int err;
int i;
+ lockdep_assert_held(&sc->transaction_lock);
+ *submitted = false;
+
/* Ensure VF already has possession of shared memory */
err = mana_smc_poll_register(sc->base, false);
if (err) {
@@ -229,6 +243,7 @@ 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);
@@ -248,11 +263,32 @@ int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr,
return 0;
}
-int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf)
+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, bool *submitted)
+{
+ int err;
+
+ mutex_lock(&sc->transaction_lock);
+ err = mana_smc_setup_hwc_locked(sc, reset_vf, eq_addr, cq_addr,
+ rq_addr, sq_addr, eq_msix_index,
+ submitted);
+ mutex_unlock(&sc->transaction_lock);
+
+ return err;
+}
+
+static int mana_smc_teardown_hwc_locked(struct shm_channel *sc, bool reset_vf,
+ bool *setup_active)
{
union smc_proto_hdr hdr = {};
int err;
+ lockdep_assert_held(&sc->transaction_lock);
+
+ if (!*setup_active)
+ return 0;
+
/* Ensure already has possession of shared memory */
err = mana_smc_poll_register(sc->base, false);
if (err) {
@@ -283,5 +319,19 @@ int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf)
return err;
}
+ *setup_active = false;
+
return 0;
}
+
+int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf,
+ bool *setup_active)
+{
+ int err;
+
+ mutex_lock(&sc->transaction_lock);
+ err = mana_smc_teardown_hwc_locked(sc, reset_vf, setup_active);
+ mutex_unlock(&sc->transaction_lock);
+
+ return err;
+}
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 29d152e18596..af62cd6d771e 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -596,6 +596,9 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue);
+/* Remove an EQ from interrupt dispatch without freeing its queue memory. */
+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);
void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit);
@@ -1146,6 +1149,7 @@ int mana_gd_verify_vf_version(struct gdma_context *gc);
int mana_gd_query_max_resources(struct gdma_context *gc);
int mana_gd_setup(struct gdma_context *gc);
void mana_gd_cleanup(struct gdma_context *gc);
+void mana_gd_free_context(struct gdma_context *gc);
int mana_gd_detect_devices(struct gdma_context *gc);
int mana_gd_init_registers(struct gdma_context *gc);
irqreturn_t mana_gd_intr(int irq, void *arg);
diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h
index 1ab2d66c891e..1320bdfa9d2a 100644
--- a/include/net/mana/hw_channel.h
+++ b/include/net/mana/hw_channel.h
@@ -185,6 +185,8 @@ struct hw_channel_context {
u16 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;
struct completion hwc_init_eqe_comp;
@@ -199,11 +201,14 @@ struct hw_channel_context {
u32 dest_vrcq_id;
u32 hwc_timeout;
+ /* The PF may own the HWC queues while this is true. */
+ bool setup_active;
struct hwc_caller_ctx *caller_ctx;
};
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);
int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
const void *req, u32 resp_len, void *resp);
diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h
index dbabcfb95daf..c8daa61fa759 100644
--- a/include/net/mana/shm_channel.h
+++ b/include/net/mana/shm_channel.h
@@ -4,6 +4,8 @@
#ifndef _SHM_CHANNEL_H
#define _SHM_CHANNEL_H
+#include <linux/mutex.h>
+
#define SMC_APERTURE_BITS 256
#define SMC_BASIC_UNIT (sizeof(u32))
#define SMC_APERTURE_DWORDS (SMC_APERTURE_BITS / (SMC_BASIC_UNIT * 8))
@@ -13,6 +15,9 @@
struct shm_channel {
struct device *dev;
void __iomem *base;
+ /* Protects base and complete aperture request/response transactions. */
+ struct mutex transaction_lock;
+ bool transaction_lock_initialized;
};
void mana_smc_init(struct shm_channel *sc, struct device *dev,
@@ -20,8 +25,9 @@ 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);
+int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf,
+ bool *setup_active);
#endif /* _SHM_CHANNEL_H */
--
2.43.0
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH net-next v10 2/4] net: mana: give each HWC message slot its own completion state
2026-11-09 15:44 [PATCH net-next v10 0/4] net: mana: concurrent HWC requests and dynamic queue depth Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 1/4] net: mana: prepare HWC ownership for safe reinitialization Wei Hu
@ 2026-11-09 15:45 ` Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 3/4] net: mana: support concurrent HWC requests Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 4/4] net: mana: add dynamic HWC queue depth with reinit path Wei Hu
3 siblings, 0 replies; 5+ messages in thread
From: Wei Hu @ 2026-11-09 15:45 UTC (permalink / raw)
To: longli, kotaranov, kuba, davem, pabeni, edumazet, andrew+netdev,
jgg, leon, haiyangz, wei.liu, decui, shradhagupta, horms, ernis,
stephen
Cc: netdev, linux-rdma, linux-hyperv, linux-kernel, gargaditya,
kees+treewide, kees, mawasthi, weh, edumazet
From: Long Li <longli@microsoft.com>
Concurrent requests require the response handler and the waiting sender to
agree on the lifetime and result state of each message slot.
Protect the caller's output buffer, Linux error and device status with a
per-slot lock. Publish the output buffer only while the sender is waiting
and withdraw it before every return. A late response cannot copy through a
pointer to caller storage whose lifetime has ended.
Reinitialize completion and result state under both the allocation and
per-slot locks when acquiring the slot. A response handler can still hold
the per-slot lock after the previous sender has returned its admission
permit, so an unpublished bitmap bit alone is not sufficient protection.
If the response records its result while the timed wait expires, return
that result instead of reporting a false timeout.
Keep the baseline's post-timeout admission behavior at this step rather
than introducing a temporary channel-wide latch that suppresses subsequent
teardown commands. This does not solve late-response correlation after ID
reuse. The next patch adds response ownership, per-slot quarantine and the
associated admission and teardown rules together.
Split response-status handling and request cleanup into helpers so the send
path has structured returns rather than phase-jumping gotos.
Link: https://lore.kernel.org/r/20260908035201.402424-3-longli@microsoft.com
Link: https://lore.kernel.org/r/20260908035201.402424-4-longli@microsoft.com
Link: https://lore.kernel.org/r/179196575434.434549.4428132041097324407@kernel.org
Link: https://lore.kernel.org/r/179196575640.434549.9102950927041409151@kernel.org
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Wei Hu <weh@microsoft.com>
Copilot-Session: 8c2361e6-c0f4-4b0c-bf01-b5e4cdacec50
---
.../net/ethernet/microsoft/mana/hw_channel.c | 125 +++++++++++++-----
include/net/mana/hw_channel.h | 4 +-
2 files changed, 95 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 9e0964072af9..6f0ccdeffc4f 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -9,6 +9,7 @@
static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id)
{
struct gdma_resource *r = &hwc->inflight_msg_res;
+ struct hwc_caller_ctx *ctx;
unsigned long flags;
u32 index;
@@ -19,8 +20,17 @@ static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id)
index = find_first_zero_bit(hwc->inflight_msg_res.map,
hwc->inflight_msg_res.size);
+ ctx = &hwc->caller_ctx[index];
+ spin_lock(&ctx->lock);
+ reinit_completion(&ctx->comp_event);
+ ctx->output_buf = NULL;
+ ctx->output_buflen = 0;
+ ctx->error = -EINPROGRESS;
+ ctx->status_code = 0;
+
bitmap_set(hwc->inflight_msg_res.map, index, 1);
+ spin_unlock(&ctx->lock);
spin_unlock_irqrestore(&r->lock, flags);
*msg_id = index;
@@ -90,14 +100,21 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
}
ctx = hwc->caller_ctx + msg_id;
- err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
- if (err)
- goto out;
- ctx->status_code = resp_msg->status;
+ spin_lock(&ctx->lock);
+ if (!ctx->output_buf) {
+ spin_unlock(&ctx->lock);
+ mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+ return;
+ }
- memcpy(ctx->output_buf, resp_msg, resp_len);
-out:
+ err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
+ if (!err) {
+ ctx->status_code = resp_msg->status;
+ memcpy(ctx->output_buf, resp_msg, resp_len);
+ }
+
+ ctx->output_buf = NULL;
ctx->error = err;
/* Must post rx wqe before complete(), otherwise the next rx may
@@ -106,6 +123,7 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
complete(&ctx->comp_event);
+ spin_unlock(&ctx->lock);
}
static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
@@ -696,8 +714,10 @@ static int mana_hwc_test_channel(struct hw_channel_context *hwc, u16 q_depth,
if (!ctx)
return -ENOMEM;
- for (i = 0; i < q_depth; ++i)
+ for (i = 0; i < q_depth; ++i) {
init_completion(&ctx[i].comp_event);
+ spin_lock_init(&ctx[i].lock);
+ }
hwc->caller_ctx = ctx;
@@ -1000,6 +1020,37 @@ void mana_hwc_free_retained_channel(struct gdma_context *gc)
gc->hwc.gdma_context = NULL;
}
+static int mana_hwc_response_status(struct hw_channel_context *hwc,
+ u32 command, int error, u32 status)
+{
+ if (error)
+ return error;
+
+ if (!status || status == GDMA_STATUS_MORE_ENTRIES)
+ return 0;
+
+ if (status == GDMA_STATUS_CMD_UNSUPPORTED)
+ return -EOPNOTSUPP;
+
+ if (command != MANA_QUERY_PHY_STAT)
+ dev_err(hwc->dev, "Command 0x%x failed with status: 0x%x\n",
+ command, status);
+
+ return -EPROTO;
+}
+
+static void mana_hwc_finish_request(struct hw_channel_context *hwc,
+ struct hwc_caller_ctx *ctx, u16 msg_id)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->output_buf = NULL;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ mana_hwc_put_msg_index(hwc, msg_id);
+}
+
int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
const void *req, u32 resp_len, void *resp)
{
@@ -1007,26 +1058,32 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
struct hwc_wq *txq = hwc->txq;
struct gdma_req_hdr *req_msg;
struct hwc_caller_ctx *ctx;
+ unsigned long flags;
u32 dest_vrcq;
u32 dest_vrq;
u32 command;
+ u32 status;
u16 msg_id;
int err;
- mana_hwc_get_msg_index(hwc, &msg_id);
+ err = mana_hwc_get_msg_index(hwc, &msg_id);
+ if (err)
+ return err;
tx_wr = &txq->msg_buf->reqs[msg_id];
+ ctx = hwc->caller_ctx + msg_id;
if (req_len > tx_wr->buf_len) {
dev_err(hwc->dev, "HWC: req msg size: %d > %d\n", req_len,
tx_wr->buf_len);
- err = -EINVAL;
- goto out;
+ mana_hwc_finish_request(hwc, ctx, msg_id);
+ return -EINVAL;
}
- ctx = hwc->caller_ctx + msg_id;
+ spin_lock_irqsave(&ctx->lock, flags);
ctx->output_buf = resp;
ctx->output_buflen = resp_len;
+ spin_unlock_irqrestore(&ctx->lock, flags);
req_msg = (struct gdma_req_hdr *)tx_wr->buf_va;
if (req)
@@ -1048,11 +1105,24 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
err = mana_hwc_post_tx_wqe(txq, tx_wr, dest_vrq, dest_vrcq, false);
if (err) {
dev_err(hwc->dev, "HWC: Failed to post send WQE: %d\n", err);
- goto out;
+ mana_hwc_finish_request(hwc, ctx, msg_id);
+ return err;
}
if (!wait_for_completion_timeout(&ctx->comp_event,
- (msecs_to_jiffies(hwc->hwc_timeout)))) {
+ msecs_to_jiffies(hwc->hwc_timeout))) {
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->output_buf = NULL;
+ err = ctx->error;
+ status = ctx->status_code;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ if (err != -EINPROGRESS) {
+ mana_hwc_finish_request(hwc, ctx, msg_id);
+ return mana_hwc_response_status(hwc, command, err,
+ status);
+ }
+
if (hwc->hwc_timeout != 0)
dev_err(hwc->dev, "Command 0x%x timed out: %u ms\n",
command, hwc->hwc_timeout);
@@ -1061,27 +1131,16 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
if (hwc->hwc_timeout > 1)
hwc->hwc_timeout = 1;
- err = -ETIMEDOUT;
- goto out;
+ mana_hwc_finish_request(hwc, ctx, msg_id);
+ return -ETIMEDOUT;
}
- if (ctx->error) {
- err = ctx->error;
- goto out;
- }
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->output_buf = NULL;
+ err = ctx->error;
+ status = ctx->status_code;
+ spin_unlock_irqrestore(&ctx->lock, flags);
- if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
- if (ctx->status_code == GDMA_STATUS_CMD_UNSUPPORTED) {
- err = -EOPNOTSUPP;
- goto out;
- }
- if (command != MANA_QUERY_PHY_STAT)
- dev_err(hwc->dev, "Command 0x%x failed with status: 0x%x\n",
- command, ctx->status_code);
- err = -EPROTO;
- goto out;
- }
-out:
- mana_hwc_put_msg_index(hwc, msg_id);
- return err;
+ mana_hwc_finish_request(hwc, ctx, msg_id);
+ return mana_hwc_response_status(hwc, command, err, status);
}
diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h
index 1320bdfa9d2a..c7570a5f7376 100644
--- a/include/net/mana/hw_channel.h
+++ b/include/net/mana/hw_channel.h
@@ -168,10 +168,12 @@ struct hwc_wq {
struct hwc_caller_ctx {
struct completion comp_event;
+ /* Protects initialization, output storage and response state. */
+ spinlock_t lock;
void *output_buf;
u32 output_buflen;
- u32 error; /* Linux error code */
+ int error; /* Linux error code */
u32 status_code;
};
--
2.43.0
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH net-next v10 3/4] net: mana: support concurrent HWC requests
2026-11-09 15:44 [PATCH net-next v10 0/4] net: mana: concurrent HWC requests and dynamic queue depth Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 1/4] net: mana: prepare HWC ownership for safe reinitialization Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 2/4] net: mana: give each HWC message slot its own completion state Wei Hu
@ 2026-11-09 15:45 ` Wei Hu
2026-11-09 15:45 ` [PATCH net-next v10 4/4] net: mana: add dynamic HWC queue depth with reinit path Wei Hu
3 siblings, 0 replies; 5+ messages in thread
From: Wei Hu @ 2026-11-09 15:45 UTC (permalink / raw)
To: longli, kotaranov, kuba, davem, pabeni, edumazet, andrew+netdev,
jgg, leon, haiyangz, wei.liu, decui, shradhagupta, horms, ernis,
stephen
Cc: netdev, linux-rdma, linux-hyperv, linux-kernel, gargaditya,
kees+treewide, kees, mawasthi, weh, edumazet
From: Long Li <longli@microsoft.com>
Give HWC message slots separate sender and response ownership. Initialize
each slot under the inflight resource and per-slot locks, publish its
bitmap bit last, and release the slot only after both references are
released. The per-slot lock also excludes an older duplicate callback from
resetting or consuming the next caller's state.
Serialize SQ posting so concurrent senders cannot corrupt the producer
state. A posted request which times out keeps its response reference and
slot until its late response arrives or teardown cancels it. The bootstrap
channel remains depth one here; the next patch selects and allocates
larger queues.
Wait for a free slot while the channel is healthy instead of imposing a
separate admission deadline. A congestion-only -EBUSY can make destructive
callers skip a teardown command and still free its DMA memory. Keeping
healthy callers queued avoids introducing that failure into the existing
cleanup paths. The response wait of an admitted command remains bounded.
Wake admission waiters when a slot is released, a response is abandoned,
waits are cancelled or the channel stops. If no slot is available, return
-ETIMEDOUT for outstanding abandoned responses or cancelled waits, and
-ENODEV for a stopped channel. This also handles waiters which arrived
before abandonment was recorded, without mistaking healthy contention
for a failed command. Retire the abandoned-response count with its
response reference exactly once.
Keep available slots usable for best-effort commands when waits have been
cancelled, preserving the existing cleanup policy. Suppress expected
timeout/device-gone logging after cancellation or unpublication, but keep
logging live-channel failures and other error classes. This does not
repair the wider data-queue DMA policy after a real control-command
failure or establish device quiescence.
Synchronize hwc_timeout updates with atomic access helpers. Cancellation
is terminal for a channel instance; firmware and query updates may replace
only a live timeout, and fail-fast may only lower a live value to one
millisecond.
Keep setup private until queues, admission state, caller contexts and
the direct EQ test are ready. Runtime teardown unpublishes the channel,
rejects new admissions, wakes waiters and drains active senders before
releasing or retaining PF-owned mappings. Apply the same unpublication
and sender-drain rules to final disposal of retained software state.
Split admission, submission, waiting, response status and unwind into
helpers so mana_hwc_send_request() uses structured returns.
Link: https://lore.kernel.org/r/20260908035201.402424-4-longli@microsoft.com
Link: https://lore.kernel.org/r/20260914175044.2a26bb46@kernel.org
Link: https://lore.kernel.org/r/179196575640.434549.9102950927041409151@kernel.org
Link: https://lore.kernel.org/r/179250339266.3135.15035365058593192217@kernel.org
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Wei Hu <weh@microsoft.com>
Copilot-Session: 8c2361e6-c0f4-4b0c-bf01-b5e4cdacec50
---
.../net/ethernet/microsoft/mana/gdma_cdx.c | 1 +
.../net/ethernet/microsoft/mana/gdma_main.c | 95 ++-
.../net/ethernet/microsoft/mana/gdma_pci.c | 11 +-
.../net/ethernet/microsoft/mana/hw_channel.c | 598 +++++++++++++-----
include/net/mana/gdma.h | 11 +
include/net/mana/hw_channel.h | 46 +-
6 files changed, 574 insertions(+), 188 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_cdx.c b/drivers/net/ethernet/microsoft/mana/gdma_cdx.c
index 2e0dcb902d7e..fa10681fd793 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_cdx.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_cdx.c
@@ -221,6 +221,7 @@ static int mana_cdx_gd_probe(struct cdx_device *cdx_dev)
mutex_init(&gc->eq_test_event_mutex);
mutex_init(&gc->gic_mutex);
+ spin_lock_init(&gc->hwc_lock);
dev_set_drvdata(&cdx_dev->dev, gc);
gc->bar0_pa = cdx_resource_start(cdx_dev, 0);
gc->bar0_size = cdx_resource_len(cdx_dev, 0);
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 8df130386da3..bb4a963c2cf5 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -142,22 +142,26 @@ int mana_gd_init_registers(struct gdma_context *gc)
return mana_gd_init_vf_regs(gc);
}
-/* Suppress logging when we set timeout to zero */
+/* Cancellation and unpublication make teardown request failures expected. */
bool mana_need_log(struct gdma_context *gc, int err)
{
struct hw_channel_context *hwc;
+ bool need_log = true;
+ unsigned long flags;
- if (err != -ETIMEDOUT)
+ if (err != -ETIMEDOUT && err != -ENODEV)
return true;
if (!gc)
return true;
+ spin_lock_irqsave(&gc->hwc_lock, flags);
hwc = gc->hwc.driver_data;
- if (hwc && hwc->hwc_timeout == 0)
- return false;
+ if (!hwc || !mana_hwc_timeout_read(hwc))
+ need_log = false;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
- return true;
+ return need_log;
}
int mana_gd_query_max_resources(struct gdma_context *gc)
@@ -310,7 +314,8 @@ int mana_gd_query_max_resources(struct gdma_context *gc)
return 0;
}
-static int mana_gd_query_hwc_timeout(struct gdma_context *gc, u32 *timeout_val)
+static int mana_gd_query_hwc_timeout(struct gdma_context *gc, u32 timeout_ms,
+ u32 *new_timeout_ms)
{
struct gdma_query_hwc_timeout_resp resp = {};
struct gdma_query_hwc_timeout_req req = {};
@@ -318,12 +323,12 @@ static int mana_gd_query_hwc_timeout(struct gdma_context *gc, u32 *timeout_val)
mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_HWC_TIMEOUT,
sizeof(req), sizeof(resp));
- req.timeout_ms = *timeout_val;
+ req.timeout_ms = timeout_ms;
err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
if (err || resp.hdr.status)
return err ? err : -EPROTO;
- *timeout_val = resp.timeout_ms;
+ *new_timeout_ms = resp.timeout_ms;
return 0;
}
@@ -378,12 +383,48 @@ int mana_gd_detect_devices(struct gdma_context *gc)
int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,
u32 resp_len, void *resp)
{
- struct hw_channel_context *hwc = gc->hwc.driver_data;
+ struct hw_channel_context *hwc;
+ unsigned long flags;
+ int err;
+
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ hwc = gc->hwc.driver_data;
+ if (!hwc) {
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
+ return -ENODEV;
+ }
+ hwc->active_senders++;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
+
+ err = mana_hwc_send_request(hwc, req_len, req, resp_len, resp);
- return mana_hwc_send_request(hwc, req_len, req, resp_len, resp);
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ if (--hwc->active_senders == 0)
+ wake_up(&gc->hwc_drain_waitq);
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
+
+ return err;
}
EXPORT_SYMBOL_NS(mana_gd_send_request, "NET_MANA");
+int mana_gd_cancel_hwc_timeout(struct gdma_context *gc)
+{
+ struct hw_channel_context *hwc;
+ unsigned long flags;
+ int err = 0;
+
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ hwc = gc->hwc.driver_data;
+ if (hwc)
+ mana_hwc_timeout_cancel(hwc);
+ else
+ err = -ENODEV;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
+
+ return err;
+}
+EXPORT_SYMBOL_NS(mana_gd_cancel_hwc_timeout, "NET_MANA");
+
int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length,
struct gdma_mem_info *gmi, bool allow_scatter)
{
@@ -996,7 +1037,9 @@ static void mana_gd_deregister_irq(struct gdma_queue *queue)
synchronize_rcu();
}
-int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
+static int mana_gd_test_eq_request(struct gdma_context *gc,
+ struct hw_channel_context *hwc,
+ struct gdma_queue *eq)
{
struct gdma_generate_test_event_req req = {};
struct gdma_general_resp resp = {};
@@ -1014,7 +1057,12 @@ int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
req.hdr.dev_id = eq->gdma_dev->dev_id;
req.queue_index = eq->id;
- err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp);
+ if (hwc)
+ err = mana_hwc_send_request(hwc, sizeof(req), &req,
+ sizeof(resp), &resp);
+ else
+ err = mana_gd_send_request(gc, sizeof(req), &req,
+ sizeof(resp), &resp);
if (err) {
if (mana_need_log(gc, err))
dev_err(dev, "test_eq failed: %d\n", err);
@@ -1045,6 +1093,17 @@ int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
return err;
}
+int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq)
+{
+ return mana_gd_test_eq_request(gc, NULL, eq);
+}
+
+int mana_gd_test_hwc_eq(struct hw_channel_context *hwc,
+ struct gdma_queue *eq)
+{
+ return mana_gd_test_eq_request(hwc->gdma_dev->gdma_context, hwc, eq);
+}
+
static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_events,
struct gdma_queue *queue)
{
@@ -1280,6 +1339,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd,
if (gmi->nr_pages == 0 && !MANA_PAGE_ALIGNED(gmi->virt_addr))
return -EINVAL;
+ /* 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)
@@ -1482,9 +1542,12 @@ int mana_gd_verify_vf_version(struct gdma_context *gc)
struct gdma_verify_ver_resp resp = {};
struct gdma_verify_ver_req req = {};
struct hw_channel_context *hwc;
+ u32 timeout_ms;
int err;
+ /* The setup caller must exclude concurrent HWC teardown. */
hwc = gc->hwc.driver_data;
+
mana_gd_init_req_hdr(&req.hdr, GDMA_VERIFY_VF_DRIVER_VERSION,
sizeof(req), sizeof(resp));
@@ -1522,12 +1585,16 @@ int mana_gd_verify_vf_version(struct gdma_context *gc)
&gc->pf_cap_flags1);
if (resp.pf_cap_flags1 & GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG) {
- err = mana_gd_query_hwc_timeout(gc, &hwc->hwc_timeout);
+ err = mana_gd_query_hwc_timeout(gc,
+ mana_hwc_timeout_read(hwc),
+ &timeout_ms);
if (err) {
dev_err(gc->dev, "Failed to set the hwc timeout %d\n", err);
return err;
}
- dev_dbg(gc->dev, "set the hwc timeout to %u\n", hwc->hwc_timeout);
+ mana_hwc_timeout_update(hwc, timeout_ms);
+ dev_dbg(gc->dev, "set the hwc timeout to %u\n",
+ mana_hwc_timeout_read(hwc));
}
return 0;
}
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_pci.c b/drivers/net/ethernet/microsoft/mana/gdma_pci.c
index 7935cb274e36..636d9b0dd581 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_pci.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_pci.c
@@ -14,7 +14,6 @@
#include <linux/xarray.h>
#include <net/mana/mana.h>
-#include <net/mana/hw_channel.h>
struct mana_dev_recovery {
struct list_head list;
@@ -85,7 +84,6 @@ static void mana_serv_fpga(struct pci_dev *pdev)
static void mana_serv_reset(struct pci_dev *pdev)
{
struct gdma_context *gc = pci_get_drvdata(pdev);
- struct hw_channel_context *hwc;
int ret;
if (!gc) {
@@ -95,15 +93,13 @@ static void mana_serv_reset(struct pci_dev *pdev)
return;
}
- hwc = gc->hwc.driver_data;
- if (!hwc) {
+ /* HWC is not responding in this case, so don't wait */
+ ret = mana_gd_cancel_hwc_timeout(gc);
+ if (ret) {
dev_err(&pdev->dev, "MANA service: no HWC\n");
goto out;
}
- /* HWC is not responding in this case, so don't wait */
- hwc->hwc_timeout = 0;
-
dev_info(&pdev->dev, "MANA reset cycle start\n");
mana_gd_suspend(pdev, PMSG_SUSPEND);
@@ -674,6 +670,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
mutex_init(&gc->eq_test_event_mutex);
mutex_init(&gc->gic_mutex);
+ spin_lock_init(&gc->hwc_lock);
pci_set_drvdata(pdev, gc);
gc->bar0_pa = pci_resource_start(pdev, 0);
gc->bar0_size = pci_resource_len(pdev, 0);
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 6f0ccdeffc4f..8bc00001d20e 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -6,48 +6,140 @@
#include <net/mana/hw_channel.h>
#include <linux/vmalloc.h>
-static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id)
+u32 mana_hwc_timeout_read(const struct hw_channel_context *hwc)
+{
+ return READ_ONCE(hwc->hwc_timeout);
+}
+
+void mana_hwc_timeout_update(struct hw_channel_context *hwc, u32 timeout_ms)
+{
+ u32 old_timeout;
+
+ if (!timeout_ms)
+ return;
+
+ old_timeout = mana_hwc_timeout_read(hwc);
+ while (old_timeout &&
+ cmpxchg(&hwc->hwc_timeout, old_timeout,
+ timeout_ms) != old_timeout)
+ old_timeout = mana_hwc_timeout_read(hwc);
+}
+
+void mana_hwc_timeout_cancel(struct hw_channel_context *hwc)
+{
+ xchg(&hwc->hwc_timeout, 0);
+ wake_up_all(&hwc->admission_waitq);
+}
+
+static void mana_hwc_timeout_reduce(struct hw_channel_context *hwc)
+{
+ u32 old_timeout = mana_hwc_timeout_read(hwc);
+
+ while (old_timeout > 1 &&
+ cmpxchg(&hwc->hwc_timeout, old_timeout, 1) != old_timeout)
+ old_timeout = mana_hwc_timeout_read(hwc);
+}
+
+static int mana_hwc_try_get_msg_index(struct hw_channel_context *hwc,
+ 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 index;
-
- down(&hwc->sema);
+ int err;
spin_lock_irqsave(&r->lock, flags);
+ if (!hwc->channel_up) {
+ spin_unlock_irqrestore(&r->lock, flags);
+ return -ENODEV;
+ }
- index = find_first_zero_bit(hwc->inflight_msg_res.map,
- hwc->inflight_msg_res.size);
+ index = find_first_zero_bit(r->map, r->size);
+ if (index >= r->size) {
+ err = -EBUSY;
+ if (!mana_hwc_timeout_read(hwc) ||
+ atomic_read(&hwc->abandoned_msgs))
+ err = -ETIMEDOUT;
+ spin_unlock_irqrestore(&r->lock, flags);
+ return err;
+ }
ctx = &hwc->caller_ctx[index];
spin_lock(&ctx->lock);
reinit_completion(&ctx->comp_event);
- ctx->output_buf = NULL;
- ctx->output_buflen = 0;
+ /* Take both references (sender + response handler) before publishing
+ * the slot, so an early response cannot free it under the sender.
+ */
+ refcount_set(&ctx->refcnt, 2);
+ ctx->output_buf = resp;
+ ctx->output_buflen = resp_len;
ctx->error = -EINPROGRESS;
ctx->status_code = 0;
+ ctx->responded = false;
+ ctx->resp_pending = true;
+ ctx->msg_id = index;
- bitmap_set(hwc->inflight_msg_res.map, index, 1);
+ /* The response path takes r->lock before ctx->lock, so publishing the
+ * bitmap last makes every field above visible before it can consume
+ * the response-side reference.
+ */
+ bitmap_set(r->map, index, 1);
spin_unlock(&ctx->lock);
spin_unlock_irqrestore(&r->lock, flags);
- *msg_id = index;
+ *caller_ctx = ctx;
return 0;
}
+static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, void *resp,
+ u32 resp_len,
+ struct hwc_caller_ctx **caller_ctx)
+{
+ int err;
+
+ /* Healthy contention must not skip a destructive control request. */
+ wait_event(hwc->admission_waitq,
+ (err = mana_hwc_try_get_msg_index(hwc, resp, resp_len,
+ caller_ctx)) != -EBUSY);
+ return err;
+}
+
static void mana_hwc_put_msg_index(struct hw_channel_context *hwc, u16 msg_id)
{
struct gdma_resource *r = &hwc->inflight_msg_res;
unsigned long flags;
spin_lock_irqsave(&r->lock, flags);
- bitmap_clear(hwc->inflight_msg_res.map, msg_id, 1);
+ bitmap_clear(r->map, msg_id, 1);
spin_unlock_irqrestore(&r->lock, flags);
- up(&hwc->sema);
+ wake_up(&hwc->admission_waitq);
+}
+
+static void hwc_ctx_put(struct hw_channel_context *hwc,
+ struct hwc_caller_ctx *ctx)
+{
+ if (refcount_dec_and_test(&ctx->refcnt))
+ mana_hwc_put_msg_index(hwc, ctx->msg_id);
+}
+
+static bool mana_hwc_clear_resp_pending(struct hw_channel_context *hwc,
+ struct hwc_caller_ctx *ctx)
+{
+ lockdep_assert_held(&ctx->lock);
+
+ if (!ctx->resp_pending)
+ return false;
+
+ ctx->resp_pending = false;
+ if (ctx->error == -ETIMEDOUT)
+ atomic_dec(&hwc->abandoned_msgs);
+
+ return true;
}
static int mana_hwc_verify_resp_msg(const struct hwc_caller_ctx *caller_ctx,
@@ -90,40 +182,53 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
struct hwc_work_request *rx_req, u16 msg_id)
{
const struct gdma_resp_hdr *resp_msg = rx_req->buf_va;
+ struct gdma_resource *r = &hwc->inflight_msg_res;
struct hwc_caller_ctx *ctx;
+ bool release;
int err;
- if (!test_bit(msg_id, hwc->inflight_msg_res.map)) {
+ spin_lock(&r->lock);
+ if (!test_bit(msg_id, r->map)) {
+ spin_unlock(&r->lock);
dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n", msg_id);
mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
return;
}
ctx = hwc->caller_ctx + msg_id;
-
spin_lock(&ctx->lock);
- if (!ctx->output_buf) {
+ spin_unlock(&r->lock);
+
+ /* Consume the response-side reference exactly once. This releases a
+ * quarantined slot after its late response arrives.
+ */
+ release = mana_hwc_clear_resp_pending(hwc, ctx);
+
+ if (ctx->responded) {
spin_unlock(&ctx->lock);
mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+ if (release)
+ hwc_ctx_put(hwc, ctx);
return;
}
+ ctx->responded = true;
err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
if (!err) {
ctx->status_code = resp_msg->status;
memcpy(ctx->output_buf, resp_msg, resp_len);
}
-
- ctx->output_buf = NULL;
ctx->error = err;
- /* Must post rx wqe before complete(), otherwise the next rx may
- * hit no_wqe error.
+ /* Post RX WQE before completing; the next response may arrive
+ * immediately and needs a posted buffer.
*/
mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
-
complete(&ctx->comp_event);
spin_unlock(&ctx->lock);
+
+ if (release)
+ hwc_ctx_put(hwc, ctx);
}
static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
@@ -214,7 +319,7 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
switch (type) {
case HWC_DATA_CFG_HWC_TIMEOUT:
- hwc->hwc_timeout = val;
+ mana_hwc_timeout_update(hwc, val);
break;
case HWC_DATA_HW_LINK_CONNECT:
@@ -617,6 +722,7 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc,
hwc_wq->gdma_wq = queue;
hwc_wq->queue_depth = q_depth;
hwc_wq->hwc_cq = hwc_cq;
+ spin_lock_init(&hwc_wq->lock);
err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size,
&hwc_wq->msg_buf);
@@ -634,7 +740,7 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc,
return err;
}
-static int mana_hwc_post_tx_wqe(const struct hwc_wq *hwc_txq,
+static int mana_hwc_post_tx_wqe(struct hwc_wq *hwc_txq,
struct hwc_work_request *req,
u32 dest_virt_rq_id, u32 dest_virt_rcq_id,
bool dest_pf)
@@ -673,7 +779,10 @@ static int mana_hwc_post_tx_wqe(const struct hwc_wq *hwc_txq,
req->wqe_req.inline_oob_data = tx_oob;
req->wqe_req.client_data_unit = 0;
+ spin_lock(&hwc_txq->lock);
err = mana_gd_post_and_ring(hwc_txq->gdma_wq, &req->wqe_req, NULL);
+ spin_unlock(&hwc_txq->lock);
+
if (err)
dev_err(dev, "Failed to post WQE on HWC SQ: %d\n", err);
return err;
@@ -684,7 +793,7 @@ static int mana_hwc_init_inflight_msg(struct hw_channel_context *hwc,
{
int err;
- sema_init(&hwc->sema, num_msg);
+ atomic_set(&hwc->abandoned_msgs, 0);
err = mana_gd_alloc_res_map(num_msg, &hwc->inflight_msg_res);
if (err)
@@ -692,43 +801,55 @@ static int mana_hwc_init_inflight_msg(struct hw_channel_context *hwc,
return err;
}
-static int mana_hwc_test_channel(struct hw_channel_context *hwc, u16 q_depth,
- u32 max_req_msg_size, u32 max_resp_msg_size)
+static int mana_hwc_test_channel(struct hw_channel_context *hwc)
{
- struct gdma_context *gc = hwc->gdma_dev->gdma_context;
struct hwc_wq *hwc_rxq = hwc->rxq;
struct hwc_work_request *req;
struct hwc_caller_ctx *ctx;
+ unsigned long flags;
int err;
int i;
/* Post all WQEs on the RQ */
- for (i = 0; i < q_depth; i++) {
+ for (i = 0; i < hwc->num_inflight_msg; i++) {
req = &hwc_rxq->msg_buf->reqs[i];
err = mana_hwc_post_rx_wqe(hwc_rxq, req);
if (err)
return err;
}
- ctx = kzalloc_objs(*ctx, q_depth);
+ ctx = kzalloc_objs(*ctx, hwc->num_inflight_msg);
if (!ctx)
return -ENOMEM;
- for (i = 0; i < q_depth; ++i) {
+ for (i = 0; i < hwc->num_inflight_msg; ++i) {
init_completion(&ctx[i].comp_event);
spin_lock_init(&ctx[i].lock);
}
hwc->caller_ctx = ctx;
- return mana_gd_test_eq(gc, hwc->cq->gdma_eq);
+ /* Setup owns hwc directly; runtime publication follows this test. */
+ spin_lock_irqsave(&hwc->inflight_msg_res.lock, flags);
+ hwc->channel_up = true;
+ spin_unlock_irqrestore(&hwc->inflight_msg_res.lock, flags);
+
+ err = mana_gd_test_hwc_eq(hwc, hwc->cq->gdma_eq);
+ if (err) {
+ spin_lock_irqsave(&hwc->inflight_msg_res.lock, flags);
+ hwc->channel_up = false;
+ spin_unlock_irqrestore(&hwc->inflight_msg_res.lock, flags);
+ }
+
+ return err;
}
-static int mana_hwc_establish_channel(struct gdma_context *gc, u16 *q_depth,
+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 hw_channel_context *hwc = gc->hwc.driver_data;
+ struct gdma_context *gc = hwc->gdma_dev->gdma_context;
struct gdma_queue *rq = hwc->rxq->gdma_wq;
struct gdma_queue *sq = hwc->txq->gdma_wq;
struct gdma_queue *eq = hwc->cq->gdma_eq;
@@ -855,68 +976,103 @@ static void mana_hwc_clear_cq_table(struct gdma_context *gc)
vfree(cq_table);
}
-int mana_hwc_create_channel(struct gdma_context *gc)
+static int mana_hwc_publish_channel(struct hw_channel_context *hwc)
+{
+ struct gdma_context *gc = hwc->gdma_dev->gdma_context;
+ unsigned long flags;
+ int err = 0;
+
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ if (WARN_ON_ONCE(gc->hwc.driver_data))
+ err = -EBUSY;
+ else
+ gc->hwc.driver_data = hwc;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
+
+ return err;
+}
+
+static struct hw_channel_context *
+mana_hwc_unpublish_channel(struct gdma_context *gc)
{
- u32 max_req_msg_size, max_resp_msg_size;
- struct gdma_dev *gd = &gc->hwc;
struct hw_channel_context *hwc;
- u16 q_depth_max;
- int err;
+ unsigned long flags;
- /* Retry a retained context before assigning queues to the PF again. */
- if (gd->driver_data) {
- mana_hwc_destroy_channel(gc);
- if (gd->driver_data)
- return -ETIMEDOUT;
- }
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ hwc = gc->hwc.driver_data;
+ gc->hwc.driver_data = NULL;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
- hwc = kzalloc_obj(*hwc);
- if (!hwc)
- return -ENOMEM;
+ return hwc;
+}
- gd->gdma_context = gc;
- gd->driver_data = hwc;
- hwc->gdma_dev = gd;
- hwc->dev = gc->dev;
- hwc->hwc_timeout = HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS;
+static void mana_hwc_retain_channel(struct hw_channel_context *hwc)
+{
+ struct gdma_context *gc = hwc->gdma_dev->gdma_context;
+ unsigned long flags;
- /* HWC's instance number is always 0. */
- gd->dev_id.as_uint32 = 0;
- gd->dev_id.type = GDMA_DEVICE_HWC;
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ if (WARN_ON_ONCE(gc->hwc.driver_data))
+ dev_err(hwc->dev, "HWC retention slot is already occupied\n");
+ else
+ gc->hwc.driver_data = hwc;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
+}
- gd->pdid = INVALID_PDID;
- gd->doorbell = INVALID_DOORBELL;
+static bool mana_hwc_senders_drained(struct gdma_context *gc,
+ struct hw_channel_context *hwc)
+{
+ unsigned long flags;
+ bool drained;
- /* mana_hwc_init_queues() only creates the required data structures,
- * and doesn't touch the HWC device.
- */
- err = mana_hwc_init_queues(hwc, HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH,
- HW_CHANNEL_MAX_REQUEST_SIZE,
- HW_CHANNEL_MAX_RESPONSE_SIZE);
- if (err) {
- dev_err(hwc->dev, "Failed to initialize HWC: %d\n", err);
- goto out;
- }
+ spin_lock_irqsave(&gc->hwc_lock, flags);
+ drained = hwc->active_senders == 0;
+ spin_unlock_irqrestore(&gc->hwc_lock, flags);
- err = mana_hwc_establish_channel(gc, &q_depth_max, &max_req_msg_size,
- &max_resp_msg_size);
- if (err) {
- dev_err(hwc->dev, "Failed to establish HWC: %d\n", err);
- goto out;
+ return drained;
+}
+
+static void mana_hwc_stop_channel(struct hw_channel_context *hwc)
+{
+ struct gdma_resource *r = &hwc->inflight_msg_res;
+ struct gdma_context *gc = hwc->gdma_dev->gdma_context;
+ unsigned long flags;
+ int i;
+
+ if (hwc->num_inflight_msg) {
+ spin_lock_irqsave(&r->lock, flags);
+ hwc->channel_up = false;
+ spin_unlock_irqrestore(&r->lock, flags);
}
+ mana_hwc_timeout_cancel(hwc);
- err = mana_hwc_test_channel(gc->hwc.driver_data,
- HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH,
- max_req_msg_size, max_resp_msg_size);
- if (err) {
- dev_err(hwc->dev, "Failed to test HWC: %d\n", err);
- goto out;
+ for (i = 0; hwc->caller_ctx && i < hwc->num_inflight_msg; i++) {
+ struct hwc_caller_ctx *ctx;
+ bool drop_resp_ref;
+
+ spin_lock_irqsave(&r->lock, flags);
+ if (!test_bit(i, r->map)) {
+ spin_unlock_irqrestore(&r->lock, flags);
+ continue;
+ }
+
+ ctx = &hwc->caller_ctx[i];
+ spin_lock(&ctx->lock);
+ spin_unlock(&r->lock);
+
+ if (!ctx->responded)
+ ctx->error = -ENODEV;
+ ctx->output_buf = NULL;
+ drop_resp_ref = mana_hwc_clear_resp_pending(hwc, ctx);
+ ctx->responded = true;
+ complete(&ctx->comp_event);
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ if (drop_resp_ref)
+ hwc_ctx_put(hwc, ctx);
}
- return 0;
-out:
- mana_hwc_destroy_channel(gc);
- return err;
+ wait_event(gc->hwc_drain_waitq, mana_hwc_senders_drained(gc, hwc));
}
static void mana_hwc_fence_channel(struct gdma_context *gc,
@@ -932,13 +1088,12 @@ static void mana_hwc_fence_channel(struct gdma_context *gc,
mana_hwc_unpublish_cq(gc, hwc->cq->gdma_cq);
}
-void mana_hwc_destroy_channel(struct gdma_context *gc)
+static bool mana_hwc_release_channel(struct hw_channel_context *hwc)
{
- struct hw_channel_context *hwc = gc->hwc.driver_data;
+ struct gdma_context *gc = hwc->gdma_dev->gdma_context;
int err;
- if (!hwc)
- return;
+ mana_hwc_stop_channel(hwc);
/* An unacknowledged destroy leaves the PF's mappings live. Fence
* software dispatch, but retain every PF-visible allocation.
@@ -950,7 +1105,8 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
"HWC teardown failed: %d, retaining PF-visible resources\n",
err);
mana_hwc_fence_channel(gc, hwc);
- return;
+ mana_hwc_retain_channel(hwc);
+ return false;
}
mana_hwc_clear_cq_table(gc);
@@ -975,11 +1131,10 @@ void mana_hwc_destroy_channel(struct gdma_context *gc)
hwc->gdma_dev->doorbell = INVALID_DOORBELL;
hwc->gdma_dev->pdid = INVALID_PDID;
- hwc->hwc_timeout = 0;
-
kfree(hwc);
- gc->hwc.driver_data = NULL;
gc->hwc.gdma_context = NULL;
+
+ return true;
}
static void mana_hwc_free_retained_wq(struct hwc_wq *wq)
@@ -997,12 +1152,12 @@ static void mana_hwc_free_retained_wq(struct hwc_wq *wq)
*/
void mana_hwc_free_retained_channel(struct gdma_context *gc)
{
- struct hw_channel_context *hwc = gc->hwc.driver_data;
+ struct hw_channel_context *hwc = mana_hwc_unpublish_channel(gc);
if (!hwc)
return;
- gc->hwc.driver_data = NULL;
+ mana_hwc_stop_channel(hwc);
mana_hwc_clear_cq_table(gc);
if (hwc->cq) {
@@ -1020,11 +1175,146 @@ void mana_hwc_free_retained_channel(struct gdma_context *gc)
gc->hwc.gdma_context = NULL;
}
-static int mana_hwc_response_status(struct hw_channel_context *hwc,
- u32 command, int error, u32 status)
+static int mana_hwc_create_bootstrap_channel(struct hw_channel_context *hwc)
{
- if (error)
- return error;
+ 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,
+ HW_CHANNEL_MAX_REQUEST_SIZE,
+ HW_CHANNEL_MAX_RESPONSE_SIZE);
+ if (err) {
+ dev_err(hwc->dev, "Failed to initialize HWC: %d\n", 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);
+ return err;
+ }
+
+ err = mana_hwc_test_channel(hwc);
+ if (err)
+ dev_err(hwc->dev, "Failed to test HWC: %d\n", err);
+
+ return err;
+}
+
+int mana_hwc_create_channel(struct gdma_context *gc)
+{
+ struct gdma_dev *gd = &gc->hwc;
+ struct hw_channel_context *hwc;
+ int err;
+
+ /* Retry a retained context before assigning queues to the PF again. */
+ if (gd->driver_data) {
+ mana_hwc_destroy_channel(gc);
+ if (gd->driver_data)
+ return -ETIMEDOUT;
+ }
+
+ hwc = kzalloc_obj(*hwc);
+ if (!hwc)
+ return -ENOMEM;
+
+ gd->gdma_context = gc;
+ hwc->gdma_dev = gd;
+ hwc->dev = gc->dev;
+ WRITE_ONCE(hwc->hwc_timeout, HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS);
+ init_waitqueue_head(&hwc->admission_waitq);
+ init_waitqueue_head(&gc->hwc_drain_waitq);
+
+ /* HWC's instance number is always 0. */
+ gd->dev_id.as_uint32 = 0;
+ gd->dev_id.type = GDMA_DEVICE_HWC;
+
+ gd->pdid = INVALID_PDID;
+ gd->doorbell = INVALID_DOORBELL;
+
+ err = mana_hwc_create_bootstrap_channel(hwc);
+ if (err) {
+ mana_hwc_release_channel(hwc);
+ return err;
+ }
+
+ err = mana_hwc_publish_channel(hwc);
+ if (err) {
+ mana_hwc_release_channel(hwc);
+ return err;
+ }
+
+ return 0;
+}
+
+void mana_hwc_destroy_channel(struct gdma_context *gc)
+{
+ struct hw_channel_context *hwc;
+
+ hwc = mana_hwc_unpublish_channel(gc);
+ if (!hwc)
+ return;
+
+ mana_hwc_release_channel(hwc);
+}
+
+static void mana_hwc_abort_request(struct hw_channel_context *hwc,
+ struct hwc_caller_ctx *ctx)
+{
+ unsigned long flags;
+ bool drop_resp_ref;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->output_buf = NULL;
+ drop_resp_ref = mana_hwc_clear_resp_pending(hwc, ctx);
+ ctx->responded = true;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ if (drop_resp_ref)
+ hwc_ctx_put(hwc, ctx);
+ hwc_ctx_put(hwc, ctx);
+}
+
+static int mana_hwc_submit_request(struct hw_channel_context *hwc,
+ struct hwc_caller_ctx *ctx,
+ struct hwc_work_request *tx_wr)
+{
+ unsigned long flags;
+ bool drop_resp_ref = false;
+ int err;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ if (ctx->responded) {
+ err = ctx->error ?: -ENODEV;
+ } else {
+ err = mana_hwc_post_tx_wqe(hwc->txq, tx_wr,
+ hwc->dest_vrq_id,
+ hwc->dest_vrcq_id, false);
+ if (err) {
+ ctx->output_buf = NULL;
+ drop_resp_ref = mana_hwc_clear_resp_pending(hwc, ctx);
+ ctx->responded = true;
+ }
+ }
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ if (!err)
+ return 0;
+
+ if (drop_resp_ref)
+ hwc_ctx_put(hwc, ctx);
+ hwc_ctx_put(hwc, ctx);
+
+ return err;
+}
+
+static int mana_hwc_response_result(struct hw_channel_context *hwc,
+ u32 command, int err, u32 status)
+{
+ if (err)
+ return err;
if (!status || status == GDMA_STATUS_MORE_ENTRIES)
return 0;
@@ -1039,108 +1329,90 @@ static int mana_hwc_response_status(struct hw_channel_context *hwc,
return -EPROTO;
}
-static void mana_hwc_finish_request(struct hw_channel_context *hwc,
- struct hwc_caller_ctx *ctx, u16 msg_id)
+static int mana_hwc_wait_for_response(struct hw_channel_context *hwc,
+ struct hwc_caller_ctx *ctx,
+ u32 command)
{
unsigned long flags;
+ bool abandoned = false;
+ u32 wait_ms;
+ u32 status;
+ int err;
+
+ wait_ms = mana_hwc_timeout_read(hwc);
+ if (wait_for_completion_timeout(&ctx->comp_event,
+ msecs_to_jiffies(wait_ms))) {
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->output_buf = NULL;
+ err = ctx->error;
+ status = ctx->status_code;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+ hwc_ctx_put(hwc, ctx);
+
+ return mana_hwc_response_result(hwc, command, err, status);
+ }
spin_lock_irqsave(&ctx->lock, flags);
ctx->output_buf = NULL;
+ err = ctx->error;
+ status = ctx->status_code;
+ if (err == -EINPROGRESS) {
+ ctx->error = -ETIMEDOUT;
+ ctx->responded = true;
+ atomic_inc(&hwc->abandoned_msgs);
+ abandoned = true;
+ }
spin_unlock_irqrestore(&ctx->lock, flags);
- mana_hwc_put_msg_index(hwc, msg_id);
+ if (!abandoned) {
+ hwc_ctx_put(hwc, ctx);
+ return mana_hwc_response_result(hwc, command, err, status);
+ }
+
+ wake_up_all(&hwc->admission_waitq);
+
+ if (wait_ms)
+ dev_err(hwc->dev, "Command 0x%x timed out: %u ms\n",
+ command, wait_ms);
+
+ mana_hwc_timeout_reduce(hwc);
+ hwc_ctx_put(hwc, ctx);
+
+ return -ETIMEDOUT;
}
int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
const void *req, u32 resp_len, void *resp)
{
struct hwc_work_request *tx_wr;
- struct hwc_wq *txq = hwc->txq;
struct gdma_req_hdr *req_msg;
struct hwc_caller_ctx *ctx;
- unsigned long flags;
- u32 dest_vrcq;
- u32 dest_vrq;
u32 command;
- u32 status;
- u16 msg_id;
int err;
- err = mana_hwc_get_msg_index(hwc, &msg_id);
+ err = mana_hwc_get_msg_index(hwc, resp, resp_len, &ctx);
if (err)
return err;
- tx_wr = &txq->msg_buf->reqs[msg_id];
- ctx = hwc->caller_ctx + msg_id;
-
+ tx_wr = &hwc->txq->msg_buf->reqs[ctx->msg_id];
if (req_len > tx_wr->buf_len) {
dev_err(hwc->dev, "HWC: req msg size: %d > %d\n", req_len,
tx_wr->buf_len);
- mana_hwc_finish_request(hwc, ctx, msg_id);
+ mana_hwc_abort_request(hwc, ctx);
return -EINVAL;
}
- spin_lock_irqsave(&ctx->lock, flags);
- ctx->output_buf = resp;
- ctx->output_buflen = resp_len;
- spin_unlock_irqrestore(&ctx->lock, flags);
-
- req_msg = (struct gdma_req_hdr *)tx_wr->buf_va;
+ req_msg = tx_wr->buf_va;
if (req)
memcpy(req_msg, req, req_len);
-
- req_msg->req.hwc_msg_id = msg_id;
+ req_msg->req.hwc_msg_id = ctx->msg_id;
tx_wr->msg_size = req_len;
command = req_msg->req.msg_type;
- /* The hardware reports the HWC destination queues through
- * HWC_INIT_DATA_DEST_RQ_ID and HWC_INIT_DATA_DEST_CQ_ID, and
- * always supplies values that are valid for this function, so no
- * PF-specific handling is needed here.
- */
- dest_vrq = hwc->dest_vrq_id;
- dest_vrcq = hwc->dest_vrcq_id;
-
- err = mana_hwc_post_tx_wqe(txq, tx_wr, dest_vrq, dest_vrcq, false);
- if (err) {
- dev_err(hwc->dev, "HWC: Failed to post send WQE: %d\n", err);
- mana_hwc_finish_request(hwc, ctx, msg_id);
+ err = mana_hwc_submit_request(hwc, ctx, tx_wr);
+ if (err)
return err;
- }
-
- if (!wait_for_completion_timeout(&ctx->comp_event,
- msecs_to_jiffies(hwc->hwc_timeout))) {
- spin_lock_irqsave(&ctx->lock, flags);
- ctx->output_buf = NULL;
- err = ctx->error;
- status = ctx->status_code;
- spin_unlock_irqrestore(&ctx->lock, flags);
-
- if (err != -EINPROGRESS) {
- mana_hwc_finish_request(hwc, ctx, msg_id);
- return mana_hwc_response_status(hwc, command, err,
- status);
- }
-
- if (hwc->hwc_timeout != 0)
- dev_err(hwc->dev, "Command 0x%x timed out: %u ms\n",
- command, hwc->hwc_timeout);
-
- /* Reduce further waiting if HWC no response */
- if (hwc->hwc_timeout > 1)
- hwc->hwc_timeout = 1;
-
- mana_hwc_finish_request(hwc, ctx, msg_id);
- return -ETIMEDOUT;
- }
-
- spin_lock_irqsave(&ctx->lock, flags);
- ctx->output_buf = NULL;
- err = ctx->error;
- status = ctx->status_code;
- spin_unlock_irqrestore(&ctx->lock, flags);
- mana_hwc_finish_request(hwc, ctx, msg_id);
- return mana_hwc_response_status(hwc, command, err, status);
+ return mana_hwc_wait_for_response(hwc, ctx, command);
}
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index af62cd6d771e..47255e662fc3 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -544,6 +544,15 @@ struct gdma_context {
/* Hardware communication channel (HWC) */
struct gdma_dev hwc;
+ /* Sender drain; the final wakeup runs under hwc_lock. */
+ wait_queue_head_t hwc_drain_waitq;
+
+ /* Protects runtime HWC publication and active sender references.
+ * Setup owns an unpublished HWC directly; timeout updates use atomic
+ * access helpers and do not require this lock.
+ */
+ spinlock_t hwc_lock;
+
/* Azure network adapter */
struct gdma_dev mana;
@@ -1192,6 +1201,8 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi);
int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req,
u32 resp_len, void *resp);
+int mana_gd_cancel_hwc_timeout(struct gdma_context *gc);
+
int mana_gd_destroy_dma_region(struct gdma_context *gc, u64 dma_region_handle);
void mana_register_debugfs(void);
void mana_unregister_debugfs(void);
diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h
index c7570a5f7376..8f2ac3d37770 100644
--- a/include/net/mana/hw_channel.h
+++ b/include/net/mana/hw_channel.h
@@ -4,6 +4,8 @@
#ifndef _HW_CHANNEL_H
#define _HW_CHANNEL_H
+#include <linux/atomic.h>
+
#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ 4
#define HW_CHANNEL_MAX_REQUEST_SIZE 0x1000
@@ -164,17 +166,32 @@ struct hwc_wq {
u16 queue_depth;
struct hwc_cq *hwc_cq;
+
+ /* Serializes SQ posting; unused for the RQ. */
+ spinlock_t lock;
};
struct hwc_caller_ctx {
struct completion comp_event;
- /* Protects initialization, output storage and response state. */
+
+ /* Initialize under inflight_msg_res.lock and lock, before publication.
+ * Once its bitmap bit is set, lock protects every field below except
+ * msg_id and refcnt. The sender owns output_buf; the response handler
+ * may write it only while holding lock.
+ */
spinlock_t lock;
void *output_buf;
u32 output_buflen;
-
- int error; /* Linux error code */
+ int error;
u32 status_code;
+ bool responded;
+ bool resp_pending;
+
+ /* Tracks sender + response-handler ownership. The last put releases
+ * the bitmap slot under inflight_msg_res.lock.
+ */
+ refcount_t refcnt;
+ u16 msg_id;
};
struct hw_channel_context {
@@ -196,15 +213,30 @@ struct hw_channel_context {
struct hwc_wq *txq;
struct hwc_cq *cq;
- struct semaphore sema;
+ /* Wait for a slot, a response timeout, cancellation or channel stop. */
+ wait_queue_head_t admission_waitq;
struct gdma_resource inflight_msg_res;
+ /* Response references still outstanding after a sender timed out. */
+ atomic_t abandoned_msgs;
u32 dest_vrq_id;
u32 dest_vrcq_id;
+
+ /* Zero permanently cancels waits for this channel instance. Firmware
+ * and query updates may replace a live nonzero value; fail-fast may
+ * only reduce a live value to one millisecond.
+ */
u32 hwc_timeout;
+ /* Checked during admission; cleared on teardown to reject sends. */
+ bool channel_up;
+
/* The PF may own the HWC queues while this is true. */
bool setup_active;
+
+ /* mana_gd_send_request() callers, including waiters; under hwc_lock. */
+ unsigned int active_senders;
+
struct hwc_caller_ctx *caller_ctx;
};
@@ -214,5 +246,11 @@ void mana_hwc_free_retained_channel(struct gdma_context *gc);
int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
const void *req, u32 resp_len, void *resp);
+int mana_gd_test_hwc_eq(struct hw_channel_context *hwc,
+ struct gdma_queue *eq);
+
+u32 mana_hwc_timeout_read(const struct hw_channel_context *hwc);
+void mana_hwc_timeout_update(struct hw_channel_context *hwc, u32 timeout_ms);
+void mana_hwc_timeout_cancel(struct hw_channel_context *hwc);
#endif /* _HW_CHANNEL_H */
--
2.43.0
^ permalink raw reply [flat|nested] 5+ messages in thread* [PATCH net-next v10 4/4] net: mana: add dynamic HWC queue depth with reinit path
2026-11-09 15:44 [PATCH net-next v10 0/4] net: mana: concurrent HWC requests and dynamic queue depth Wei Hu
` (2 preceding siblings ...)
2026-11-09 15:45 ` [PATCH net-next v10 3/4] net: mana: support concurrent HWC requests Wei Hu
@ 2026-11-09 15:45 ` Wei Hu
3 siblings, 0 replies; 5+ messages in thread
From: Wei Hu @ 2026-11-09 15:45 UTC (permalink / raw)
To: longli, kotaranov, kuba, davem, pabeni, edumazet, andrew+netdev,
jgg, leon, haiyangz, wei.liu, decui, shradhagupta, horms, ernis,
stephen
Cc: netdev, linux-rdma, linux-hyperv, linux-kernel, gargaditya,
kees+treewide, kees, mawasthi, weh, edumazet
From: Long Li <longli@microsoft.com>
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/20260908035201.402424-5-longli@microsoft.com
Link: https://lore.kernel.org/r/179196575846.434549.7933818740976196422@kernel.org
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Wei Hu <weh@microsoft.com>
Copilot-Session: 8c2361e6-c0f4-4b0c-bf01-b5e4cdacec50
---
drivers/infiniband/hw/mana/main.c | 19 +-
.../net/ethernet/microsoft/mana/gdma_main.c | 26 +-
.../net/ethernet/microsoft/mana/hw_channel.c | 316 +++++++++++++++---
include/net/mana/gdma.h | 2 +
include/net/mana/hw_channel.h | 19 +-
5 files changed, 317 insertions(+), 65 deletions(-)
diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 858bbc325eb2..e2ddbcb1f646 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -414,28 +414,38 @@ 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;
@@ -478,9 +488,6 @@ 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 bb4a963c2cf5..dace16eaeaa5 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, u8 client_offset)
{
- 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;
addr += client_offset;
@@ -1342,7 +1356,7 @@ 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);
@@ -1622,13 +1636,7 @@ 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 8bc00001d20e..867f8dd3ea54 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -95,12 +95,30 @@ static int mana_hwc_try_get_msg_index(struct hw_channel_context *hwc,
return 0;
}
-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;
+ unsigned long flags;
+ u32 req_limit;
+ u32 resp_limit;
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;
+ }
+
/* Healthy contention must not skip a destructive control request. */
wait_event(hwc->admission_waitq,
(err = mana_hwc_try_get_msg_index(hwc, resp, resp_len,
@@ -246,8 +264,18 @@ 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:
@@ -269,7 +297,8 @@ 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:
@@ -638,7 +667,8 @@ 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 +874,15 @@ 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 +894,19 @@ 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;
+ /* Do 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 +921,18 @@ 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 +982,9 @@ 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 +1017,11 @@ 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 +1037,33 @@ 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;
@@ -1088,16 +1176,11 @@ 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) {
@@ -1105,28 +1188,26 @@ 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);
-
- if (hwc->txq)
- mana_hwc_destroy_wq(hwc, hwc->txq);
+ mana_hwc_destroy_queues(hwc);
- 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;
@@ -1175,32 +1256,169 @@ 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)
@@ -1234,7 +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;
@@ -1390,7 +1608,7 @@ 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 47255e662fc3..21fdb0cbcb5a 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -610,6 +610,8 @@ 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 8f2ac3d37770..fd6d04e1e5cb 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;
@@ -240,6 +250,13 @@ 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
^ permalink raw reply [flat|nested] 5+ messages in thread