This series fixes a set of latent bugs and robustness gaps in the MANA
Hardware Channel (HWC), the control path the driver uses to talk to the
device. The issues range from a use-after-free of completion queues
during teardown to buffer mis-sizing, unsafe teardown ordering, missing
validation of device-supplied RX metadata, and stale-response handling
after a command timeout.
Patch overview:
1 RCU-protect gc->cq_table lookups against concurrent CQ destroy
The EQ interrupt handler dereferences CQ pointers from gc->cq_table
while teardown can free them. Put the table under RCU and wait a
grace period before freeing, closing the use-after-free.
2 fix HWC RQ/SQ buffer size swap
init_queues() sized the RQ with max_req_msg_size and the SQ with
max_resp_msg_size -- backwards. Correct the swap; both sizes are
equal in practice, so this is a latent-correctness fix.
3 free HWC comp_buf after destroying the EQ
Reorder teardown so the EQ is destroyed (readers quiesced) before
comp_buf and the CQ are freed, preventing a late EQ-handler access
to freed memory.
4 validate hardware-supplied values in the HWC RX path
Bounds-check the SGE, verify the recovered slot index and SGE
address, and validate response length and msg_id before use, so
malformed or hostile DMA metadata cannot cause wrong-slot completion
or out-of-bounds access.
5 fix HWC teardown safety with setup_active flag and destroy ordering
Track setup activation explicitly, tear the EQ/CQ down before the
TXQ/RXQ, and on an unrecoverable teardown failure leak the HWC
resources rather than free memory the device may still DMA into.
6 fix stale HWC response after command timeout
Replace the inflight-slot semaphore with a bitmap + waitqueue and
per-slot refcount/lock; latch the channel on timeout so no new slots
are handed out, drop duplicate/late responses, and ignore a zero
firmware-supplied timeout.
7 keep max_num_cqs immutable once cq_table is allocated
gc->max_num_cqs is set once when cq_table is allocated and never
reset, so a spoofed post-init HWC event cannot inflate the bound
past the allocation and drive an out-of-bounds cq_table access.
Follow-up feature work (net-next, sent separately):
The original series also contained two patches that are improvements, not
fixes:
net: mana: support concurrent HWC requests
net: mana: add dynamic HWC queue depth with reinit path
Per the netdev tree rules, fixes go to 'net' and features/improvements go
to 'net-next', and the two must not be combined in a single submission.
Those two patches build on the locking and teardown groundwork in this
series, so they will be posted as a separate net-next series only after
these fixes have propagated from net into net-next through the usual
periodic merge.
Changes since v5:
Addressed the automated reviews of v5 and a net-next apply conflict
reported by the netdev CI. No behavioural change to the patch intent;
the deltas below harden the v5 implementation.
- patch 1: mana_gd_unpublish_cq() and mana_ib_remove_cq_cb() now clear a
cq_table slot only when it still points at the CQ being torn down, so
the two-pass netdev teardown cannot wipe an entry a concurrent RDMA CQ
create legitimately recycled during the grace period.
mana_gd_process_eqe() drops an already-unpublished (NULL) slot quietly
instead of tripping WARN_ON_ONCE() during a normal ifdown/MTU change,
and reads gc->cq_table before gc->max_num_cqs with an smp_rmb()
between them so a shrinking re-establish cannot pair a stale bound
with a newly published, smaller table.
- patch 5: set setup_active before calling mana_smc_setup_hwc(), which
activates the device MST entries before it can report a late failure;
on an unrecoverable teardown failure keep the HWC context reachable
and retry the teardown on the next bring-up instead of orphaning it.
- patch 6: initialise the caller_ctx refcount/state before publishing
the inflight bitmap bit so a racing or forged response cannot observe
an uninitialised slot; honour a response only while the sender still
owns the slot (output_buf published and not yet reclaimed), so a
premature response cannot free the slot while its command is still in
flight; do not latch hwc_timed_out for the deliberate no-wait teardown
(hwc_timeout == 0), applied on both the admission gate and the
post-wait check in mana_hwc_get_msg_index().
- Moved the max_num_cqs/cq_table lifetime documentation onto the
cq_table field so the series no longer rewords the comment above
max_num_cqs, which a pending net-next change (cqe8_coalescing_sup)
also touches; this resolves the netdev CI net-next apply conflict.
Comment-only, no functional change.
- Rebased onto current net/main.
- v5:
https://lore.kernel.org/netdev/[email protected]/
Changes since v4:
- No code changes. Resending as a standalone thread; v4 was
accidentally sent in-reply-to the v3 thread.
- v4:
https://lore.kernel.org/netdev/[email protected]/
Changes since v3:
Addressed the netdev-ai and sashiko.dev automated reviews of v3.
- New patch 7 ("keep max_num_cqs immutable once cq_table is
allocated"): gc->max_num_cqs is set once and never reset, so a
spoofed post-init HWC event cannot inflate the bound past the
allocation and cause an out-of-bounds cq_table access.
- patch 1: replaced the per-CQ synchronize_rcu() in the netdev teardown
paths with a two-pass quiesce/free that takes a single grace period
per teardown; snapshot cq->id and max_num_cqs with READ_ONCE() so the
same value sizes, bounds and indexes cq_table.
- patch 4: removed the short-response early return so a malformed
response reaches verify_resp_msg() -> -EPROTO and completes the
sender instead of hanging it; account leaked RX WQEs and trip
hwc_timeout on RQ exhaustion; read the device-supplied
inline_oob_size_div4 and sge->address with READ_ONCE() and reject any
value other than the one the driver programs.
- patch 5: arm setup_active after mana_smc_setup_hwc() succeeds; destroy
the EQ (IRQ deregister + drain) before the CQ; drop the redundant
teardown in mana_hwc_establish_channel() that caused a double hardware
timeout and masked the original error.
- patch 6: take both the sender and response-side references up front in
mana_hwc_get_msg_index() so an early/stale/forged response cannot free
the slot before the sender posts; changed caller_ctx::error from u32
to int; reject a zero firmware-supplied HWC timeout in the query path
as well as the reconfig path.
- v3:
https://lore.kernel.org/netdev/[email protected]/
Changes since v2:
- Per maintainer feedback, split the original combined series: the
fixes here target 'net'; the two feature patches now go to 'net-next'
and are sent separately (see above). Rebased the fixes onto net.
- Dropped the pcie_flr()-based reset fallback from the teardown path;
on an unrecoverable teardown failure the driver now leaks the HWC
resources instead of touching memory the device may still DMA into.
Long Li (7):
net: mana: RCU-protect gc->cq_table lookups against concurrent CQ
destroy
net: mana: fix HWC RQ/SQ buffer size swap
net: mana: free HWC comp_buf after destroying the EQ
net: mana: validate hardware-supplied values in the HWC RX path
net: mana: fix HWC teardown safety with setup_active flag and destroy
ordering
net: mana: fix stale HWC response after command timeout
net: mana: keep max_num_cqs immutable once cq_table is allocated
drivers/infiniband/hw/mana/cq.c | 51 +-
.../net/ethernet/microsoft/mana/gdma_main.c | 72 ++-
.../net/ethernet/microsoft/mana/hw_channel.c | 521 +++++++++++++++---
drivers/net/ethernet/microsoft/mana/mana_en.c | 136 ++++-
include/net/mana/gdma.h | 37 +-
include/net/mana/hw_channel.h | 44 +-
6 files changed, 743 insertions(+), 118 deletions(-)
base-commit: f1b3416ceaf7ca4cb5cbd986ee8fe3ffaeda2d48
--
2.43.0
