Hi Or alternatively the following two patches in sequence, but again, not tested on my end.
Regards, Salvatore
>From c1eddc8c4ee7dc0ef651d87c51676fe4cd60a9df Mon Sep 17 00:00:00 2001 From: Uros Bizjak <[email protected]> Date: Mon, 7 Oct 2024 10:43:31 +0200 Subject: [PATCH 1/2] iommu/amd: Use atomic64_inc_return() in iommu.c commit 5ce73c524f5fb5abd7b1bfed0115474b4fb437b4 upstream. Use atomic64_inc_return(&ref) instead of atomic64_add_return(1, &ref) to use optimized implementation and ease register pressure around the primitive for targets that implement optimized variant. Signed-off-by: Uros Bizjak <[email protected]> Cc: Joerg Roedel <[email protected]> Cc: Suravee Suthikulpanit <[email protected]> Cc: Will Deacon <[email protected]> Cc: Robin Murphy <[email protected]> Reviewed-by: Jason Gunthorpe <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Joerg Roedel <[email protected]> Signed-off-by: Salvatore Bonaccorso <[email protected]> --- drivers/iommu/amd/iommu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index fecca5c32e8a..24e2de90ac2e 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1266,7 +1266,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu) if (!iommu->need_sync) return 0; - data = atomic64_add_return(1, &iommu->cmd_sem_val); + data = atomic64_inc_return(&iommu->cmd_sem_val); build_completion_wait(&cmd, iommu, data); raw_spin_lock_irqsave(&iommu->lock, flags); @@ -2929,7 +2929,7 @@ static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid) return; build_inv_irt(&cmd, devid); - data = atomic64_add_return(1, &iommu->cmd_sem_val); + data = atomic64_inc_return(&iommu->cmd_sem_val); build_completion_wait(&cmd2, iommu, data); raw_spin_lock_irqsave(&iommu->lock, flags); -- 2.53.0
>From 99a2ed65c1d088c749b25ad13dcc057913e62664 Mon Sep 17 00:00:00 2001 From: Ankit Soni <[email protected]> Date: Thu, 22 Jan 2026 15:30:38 +0000 Subject: [PATCH 2/2] iommu/amd: serialize sequence allocation under concurrent TLB invalidations commit 9e249c48412828e807afddc21527eb734dc9bd3d. With concurrent TLB invalidations, completion wait randomly gets timed out because cmd_sem_val was incremented outside the IOMMU spinlock, allowing CMD_COMPL_WAIT commands to be queued out of sequence and breaking the ordering assumption in wait_on_sem(). Move the cmd_sem_val increment under iommu->lock so completion sequence allocation is serialized with command queuing. And remove the unnecessary return. Fixes: d2a0cac10597 ("iommu/amd: move wait_on_sem() out of spinlock") Tested-by: Srikanth Aithal <[email protected]> Reported-by: Srikanth Aithal <[email protected]> Signed-off-by: Ankit Soni <[email protected]> Reviewed-by: Vasant Hegde <[email protected]> Signed-off-by: Joerg Roedel <[email protected]> [Salvatore Bonaccorso: Backport to v6.12.y where f32fe7cb0198 ("iommu/amd: Add support to remap/unmap IOMMU buffers for kdump") is not present] Signed-off-by: Salvatore Bonaccorso <[email protected]> --- drivers/iommu/amd/amd_iommu_types.h | 2 +- drivers/iommu/amd/init.c | 2 +- drivers/iommu/amd/iommu.c | 18 ++++++++++++------ 3 files changed, 14 insertions(+), 8 deletions(-) diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index a14ee649d3da..df2aa1c4fafc 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -781,7 +781,7 @@ struct amd_iommu { u32 flags; volatile u64 *cmd_sem; - atomic64_t cmd_sem_val; + u64 cmd_sem_val; #ifdef CONFIG_AMD_IOMMU_DEBUGFS /* DebugFS Info */ diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index e1816ae8699d..78e9ceda2338 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1742,7 +1742,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h, iommu->pci_seg = pci_seg; raw_spin_lock_init(&iommu->lock); - atomic64_set(&iommu->cmd_sem_val, 0); + iommu->cmd_sem_val = 0; /* Add IOMMU to internal data structures */ list_add_tail(&iommu->list, &amd_iommu_list); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 24e2de90ac2e..d0e53a03eff0 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -1252,6 +1252,12 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) return iommu_queue_command_sync(iommu, cmd, true); } +static u64 get_cmdsem_val(struct amd_iommu *iommu) +{ + lockdep_assert_held(&iommu->lock); + return ++iommu->cmd_sem_val; +} + /* * This function queues a completion wait command into the command * buffer of an IOMMU @@ -1266,11 +1272,11 @@ static int iommu_completion_wait(struct amd_iommu *iommu) if (!iommu->need_sync) return 0; - data = atomic64_inc_return(&iommu->cmd_sem_val); - build_completion_wait(&cmd, iommu, data); - raw_spin_lock_irqsave(&iommu->lock, flags); + data = get_cmdsem_val(iommu); + build_completion_wait(&cmd, iommu, data); + ret = __iommu_queue_command_sync(iommu, &cmd, false); raw_spin_unlock_irqrestore(&iommu->lock, flags); @@ -2929,10 +2935,11 @@ static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid) return; build_inv_irt(&cmd, devid); - data = atomic64_inc_return(&iommu->cmd_sem_val); - build_completion_wait(&cmd2, iommu, data); raw_spin_lock_irqsave(&iommu->lock, flags); + data = get_cmdsem_val(iommu); + build_completion_wait(&cmd2, iommu, data); + ret = __iommu_queue_command_sync(iommu, &cmd, true); if (ret) goto out_err; @@ -2946,7 +2953,6 @@ static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid) out_err: raw_spin_unlock_irqrestore(&iommu->lock, flags); - return; } static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid, -- 2.53.0
