Implement a stall timer which fails H2G CTBs once a period of time with no forward progress is reached to prevent deadlock. Also update to ct_write to return -EIO rather than -EPIPE on a corrupted descriptor. Signed-off-by: John Harrison <John.C.Harrison@xxxxxxxxx> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@xxxxxxxxx> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx> --- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 47 +++++++++++++++++++++-- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h | 4 ++ 2 files changed, 48 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index c9a65d05911f..27ec30b5ef47 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -319,6 +319,7 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct) goto err_deregister; ct->enabled = true; + ct->stall_time = KTIME_MAX; return 0; @@ -392,7 +393,7 @@ static int ct_write(struct intel_guc_ct *ct, unsigned int i; if (unlikely(ctb->broken)) - return -EPIPE; + return -EIO; if (unlikely(desc->status)) goto corrupted; @@ -464,7 +465,7 @@ static int ct_write(struct intel_guc_ct *ct, CT_ERROR(ct, "Corrupted descriptor head=%u tail=%u status=%#x\n", desc->head, desc->tail, desc->status); ctb->broken = true; - return -EPIPE; + return -EIO; } /** @@ -507,6 +508,18 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status) return err; } +#define GUC_CTB_TIMEOUT_MS 1500 +static inline bool ct_deadlocked(struct intel_guc_ct *ct) +{ + long timeout = GUC_CTB_TIMEOUT_MS; + bool ret = ktime_ms_delta(ktime_get(), ct->stall_time) > timeout; + + if (unlikely(ret)) + CT_ERROR(ct, "CT deadlocked\n"); + + return ret; +} + static inline bool h2g_has_room(struct intel_guc_ct_buffer *ctb, u32 len_dw) { struct guc_ct_buffer_desc *desc = ctb->desc; @@ -518,6 +531,26 @@ static inline bool h2g_has_room(struct intel_guc_ct_buffer *ctb, u32 len_dw) return space >= len_dw; } +static int has_room_nb(struct intel_guc_ct *ct, u32 len_dw) +{ + struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; + + lockdep_assert_held(&ct->ctbs.send.lock); + + if (unlikely(!h2g_has_room(ctb, len_dw))) { + if (ct->stall_time == KTIME_MAX) + ct->stall_time = ktime_get(); + + if (unlikely(ct_deadlocked(ct))) + return -EIO; + else + return -EBUSY; + } + + ct->stall_time = KTIME_MAX; + return 0; +} + static int ct_send_nb(struct intel_guc_ct *ct, const u32 *action, u32 len, @@ -530,7 +563,7 @@ static int ct_send_nb(struct intel_guc_ct *ct, spin_lock_irqsave(&ctb->lock, spin_flags); - ret = h2g_has_room(ctb, len + 1); + ret = has_room_nb(ct, len + 1); if (unlikely(ret)) goto out; @@ -574,11 +607,19 @@ static int ct_send(struct intel_guc_ct *ct, retry: spin_lock_irqsave(&ct->ctbs.send.lock, flags); if (unlikely(!h2g_has_room(ctb, len + 1))) { + if (ct->stall_time == KTIME_MAX) + ct->stall_time = ktime_get(); spin_unlock_irqrestore(&ct->ctbs.send.lock, flags); + + if (unlikely(ct_deadlocked(ct))) + return -EIO; + cond_resched(); goto retry; } + ct->stall_time = KTIME_MAX; + fence = ct_get_next_fence(ct); request.fence = fence; request.status = 0; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h index eb69263324ba..55ef7c52472f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h @@ -9,6 +9,7 @@ #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/workqueue.h> +#include <linux/ktime.h> #include "intel_guc_fwif.h" @@ -68,6 +69,9 @@ struct intel_guc_ct { struct list_head incoming; /* incoming requests */ struct work_struct worker; /* handler for incoming requests */ } requests; + + /** @stall_time: time of first time a CTB submission is stalled */ + ktime_t stall_time; }; void intel_guc_ct_init_early(struct intel_guc_ct *ct); -- 2.28.0 _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx