Linux-ARM-Kernel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
	Jonathan Corbet <corbet@lwn.net>,
	iommu@lists.linux.dev, "Joerg Roedel (AMD)" <joro@8bytes.org>,
	Jean-Philippe Brucker <jpb@kernel.org>,
	linux-arm-kernel@lists.infradead.org, linux-doc@vger.kernel.org,
	Mark Rutland <mark.rutland@arm.com>,
	Randy Dunlap <rdunlap@infradead.org>,
	Robin Murphy <robin.murphy@arm.com>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Will Deacon <will@kernel.org>
Cc: David Matlack <dmatlack@google.com>,
	Jean-Philippe Brucker <jean-philippe@linaro.org>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Nicolin Chen <nicolinc@nvidia.com>,
	Pasha Tatashin <pasha.tatashin@soleen.com>,
	patches@lists.linux.dev, Pranjal Shrivastava <praan@google.com>,
	Samiullah Khawaja <skhawaja@google.com>,
	Mostafa Saleh <smostafa@google.com>,
	stable@vger.kernel.org,
	Vijayanand Jitta <vijayanand.jitta@oss.qualcomm.com>
Subject: [PATCH v5 2/9] iommu/arm-smmu-v3: Pass the parameters for the invalidation in a struct
Date: Tue,  1 Sep 2026 14:49:51 -0300	[thread overview]
Message-ID: <2-v5-b810cf379bfc+13d738-smmu_tlbi_jgg@nvidia.com> (raw)
In-Reply-To: <0-v5-b810cf379bfc+13d738-smmu_tlbi_jgg@nvidia.com>

These parameters go to a lot of different functions and the next
patches will add more. Put them into a struct to keep things tidy.

Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 90 ++++++++++-----------
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  9 +++
 2 files changed, 54 insertions(+), 45 deletions(-)

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index d6896e25b6632a..03723bb00de412 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2363,8 +2363,8 @@ static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev)
 	return IRQ_WAKE_THREAD;
 }
 
-static struct arm_smmu_cmd
-arm_smmu_atc_inv_to_cmd(u32 sid, int ssid, unsigned long iova, size_t size)
+static struct arm_smmu_cmd arm_smmu_atc_inv_to_cmd(u32 sid, int ssid,
+						   struct arm_smmu_tlbi *tlbi)
 {
 	size_t log2_span;
 	size_t span_mask;
@@ -2386,8 +2386,8 @@ arm_smmu_atc_inv_to_cmd(u32 sid, int ssid, unsigned long iova, size_t size)
 	 * This has the unpleasant side-effect of invalidating all PASID-tagged
 	 * ATC entries within the address range.
 	 */
-	page_start	= iova >> inval_grain_shift;
-	page_end	= (iova + size - 1) >> inval_grain_shift;
+	page_start = tlbi->iova >> inval_grain_shift;
+	page_end = (tlbi->iova + tlbi->size - 1) >> inval_grain_shift;
 
 	/*
 	 * In an ATS Invalidate Request, the address must be aligned on the
@@ -2462,20 +2462,23 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 
 static void arm_smmu_cmdq_batch_add_range(struct arm_smmu_device *smmu,
 					  struct arm_smmu_cmdq_batch *cmds,
-					  struct arm_smmu_cmd *cmd, bool leaf,
-					  unsigned long iova, size_t size,
-					  size_t granule, size_t pgsize)
+					  struct arm_smmu_cmd *cmd,
+					  struct arm_smmu_tlbi *tlbi,
+					  size_t pgsize)
 {
-	unsigned long end = iova + size, num_pages = 0, tg = pgsize;
+	size_t inv_range = tlbi->iopte_size;
+	unsigned long iova = tlbi->iova;
+	unsigned long end = iova + tlbi->size;
+	unsigned long num_pages = 0;
+	unsigned int tg = pgsize;
 	u64 orig_data0 = cmd->data[0];
-	size_t inv_range = granule;
 	u8 ttl = 0, tg_enc = 0;
 
-	if (WARN_ON_ONCE(!size))
+	if (WARN_ON_ONCE(!tlbi->size))
 		return;
 
 	if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) {
-		num_pages = size >> tg;
+		num_pages = tlbi->size >> tg;
 
 		/* Convert page size of 12,14,16 (log2) to 1,2,3 */
 		tg_enc = (tg - 10) / 2;
@@ -2488,8 +2491,8 @@ static void arm_smmu_cmdq_batch_add_range(struct arm_smmu_device *smmu,
 		 * want to use a range command, so avoid the SVA corner case
 		 * where both scale and num could be 0 as well.
 		 */
-		if (leaf)
-			ttl = 4 - ((ilog2(granule) - 3) / (tg - 3));
+		if (tlbi->leaf_only)
+			ttl = 4 - ((ilog2(tlbi->iopte_size) - 3) / (tg - 3));
 		else if ((num_pages & CMDQ_TLBI_RANGE_NUM_MAX) == 1)
 			num_pages++;
 	}
@@ -2528,7 +2531,7 @@ static void arm_smmu_cmdq_batch_add_range(struct arm_smmu_device *smmu,
 		 * command and something would be very broken if iova had them
 		 * set.
 		 */
-		cmd->data[1] = FIELD_PREP(CMDQ_TLBI_1_LEAF, leaf) |
+		cmd->data[1] = FIELD_PREP(CMDQ_TLBI_1_LEAF, tlbi->leaf_only) |
 			       FIELD_PREP(CMDQ_TLBI_1_TTL, ttl) |
 			       FIELD_PREP(CMDQ_TLBI_1_TG, tg_enc) |
 			       (iova & ~GENMASK_U64(11, 0));
@@ -2568,13 +2571,13 @@ static bool arm_smmu_cmdq_batch_add_ril(struct arm_smmu_device *smmu,
 	return true;
 }
 
-static bool arm_smmu_inv_size_too_big(struct arm_smmu_device *smmu, size_t size,
-				      size_t granule)
+static bool arm_smmu_inv_size_too_big(struct arm_smmu_device *smmu,
+				      struct arm_smmu_tlbi *tlbi)
 {
 	size_t max_tlbi_ops;
 
 	/* 0 size means invalidate all */
-	if (!size || size == SIZE_MAX)
+	if (!tlbi->size || tlbi->size == SIZE_MAX)
 		return true;
 
 	if (smmu->features & ARM_SMMU_FEAT_RANGE_INV)
@@ -2587,32 +2590,31 @@ static bool arm_smmu_inv_size_too_big(struct arm_smmu_device *smmu, size_t size,
 	 * invalidation feature, where there can be too many per-granule TLBIs,
 	 * resulting in a soft lockup.
 	 */
-	max_tlbi_ops = 1 << (ilog2(granule) - 3);
-	return size >= max_tlbi_ops * granule;
+	max_tlbi_ops = 1 << (ilog2(tlbi->iopte_size) - 3);
+	return tlbi->size >= max_tlbi_ops * tlbi->iopte_size;
 }
 
 /* Used by non INV_TYPE_ATS* invalidations */
 static void arm_smmu_inv_to_cmdq_batch(struct arm_smmu_inv *inv,
 				       struct arm_smmu_cmdq_batch *cmds,
 				       struct arm_smmu_cmd *cmd,
-				       bool single_ril, bool leaf,
-				       unsigned long iova, size_t size,
-				       unsigned int granule)
+				       struct arm_smmu_tlbi *tlbi)
 {
 	struct arm_smmu_cmd nsize_cmd;
 
-	if (arm_smmu_inv_size_too_big(inv->smmu, size, granule))
+	if (arm_smmu_inv_size_too_big(inv->smmu, tlbi))
 		goto full_inv;
 
-	if (single_ril && size > granule) {
-		if (!arm_smmu_cmdq_batch_add_ril(inv->smmu, cmds, cmd, iova,
-						 size, inv->pgsize))
+	if (tlbi->has_cont && tlbi->size > tlbi->iopte_size &&
+	    (inv->smmu->options & ARM_SMMU_OPT_FULL_CONT_RIL)) {
+		if (!arm_smmu_cmdq_batch_add_ril(inv->smmu, cmds, cmd,
+						 tlbi->iova, tlbi->size,
+						 inv->pgsize))
 			goto full_inv;
 		return;
 	}
 
-	arm_smmu_cmdq_batch_add_range(inv->smmu, cmds, cmd, leaf, iova, size,
-				      granule, inv->pgsize);
+	arm_smmu_cmdq_batch_add_range(inv->smmu, cmds, cmd, tlbi, inv->pgsize);
 	return;
 
 full_inv:
@@ -2637,10 +2639,8 @@ static inline bool arm_smmu_invs_end_batch(struct arm_smmu_inv *cur,
 	return false;
 }
 
-static void __arm_smmu_domain_inv_range(struct arm_smmu_invs *invs,
-					unsigned long iova, size_t size,
-					unsigned int granule, bool single_ril,
-					bool leaf)
+static void __arm_smmu_domain_inv_range(struct arm_smmu_tlbi *tlbi,
+					struct arm_smmu_invs *invs)
 {
 	struct arm_smmu_cmdq_batch cmds = {};
 	struct arm_smmu_inv *cur;
@@ -2670,18 +2670,16 @@ static void __arm_smmu_domain_inv_range(struct arm_smmu_invs *invs,
 		case INV_TYPE_S1_ASID:
 			cmd = arm_smmu_make_cmd_tlbi(cur->size_opcode,
 						     cur->id, 0);
-			arm_smmu_inv_to_cmdq_batch(cur, &cmds, &cmd, single_ril,
-						   leaf, iova, size, granule);
+			arm_smmu_inv_to_cmdq_batch(cur, &cmds, &cmd, tlbi);
 			break;
 		case INV_TYPE_S2_VMID:
 			cmd = arm_smmu_make_cmd_tlbi(cur->size_opcode,
 						     0, cur->id);
-			arm_smmu_inv_to_cmdq_batch(cur, &cmds, &cmd, single_ril,
-						   leaf, iova, size, granule);
+			arm_smmu_inv_to_cmdq_batch(cur, &cmds, &cmd, tlbi);
 			break;
 		case INV_TYPE_S2_VMID_S1_CLEAR:
 			/* CMDQ_OP_TLBI_S12_VMALL already flushed S1 entries */
-			if (arm_smmu_inv_size_too_big(cur->smmu, size, granule))
+			if (arm_smmu_inv_size_too_big(cur->smmu, tlbi))
 				break;
 			arm_smmu_cmdq_batch_add_cmd(
 				smmu, &cmds,
@@ -2692,7 +2690,7 @@ static void __arm_smmu_domain_inv_range(struct arm_smmu_invs *invs,
 			arm_smmu_cmdq_batch_add_cmd(
 				smmu, &cmds,
 				arm_smmu_atc_inv_to_cmd(cur->id, cur->ssid,
-							iova, size));
+							tlbi));
 			break;
 		case INV_TYPE_ATS_FULL:
 			arm_smmu_cmdq_batch_add_cmd(
@@ -2723,10 +2721,14 @@ void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
 			       unsigned long iova, size_t size,
 			       unsigned int granule, bool leaf)
 {
+	struct arm_smmu_tlbi tlbi = {
+		.iova = iova,
+		.size = size,
+		.iopte_size = granule,
+		.has_cont = smmu_domain->stage == ARM_SMMU_DOMAIN_SVA,
+		.leaf_only = leaf,
+	};
 	struct arm_smmu_invs *invs;
-	bool single_ril =
-		smmu_domain->stage == ARM_SMMU_DOMAIN_SVA &&
-		(smmu_domain->smmu->options & ARM_SMMU_OPT_FULL_CONT_RIL);
 
 	/*
 	 * An invalidation request must follow some IOPTE change and then load
@@ -2766,12 +2768,10 @@ void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
 		unsigned long flags;
 
 		read_lock_irqsave(&invs->rwlock, flags);
-		__arm_smmu_domain_inv_range(invs, iova, size, granule,
-					    single_ril, leaf);
+		__arm_smmu_domain_inv_range(&tlbi, invs);
 		read_unlock_irqrestore(&invs->rwlock, flags);
 	} else {
-		__arm_smmu_domain_inv_range(invs, iova, size, granule,
-					    single_ril, leaf);
+		__arm_smmu_domain_inv_range(&tlbi, invs);
 	}
 
 	rcu_read_unlock();
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 065d76eb148119..d3e81056f24afc 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -805,6 +805,15 @@ static inline struct arm_smmu_invs *arm_smmu_invs_alloc(size_t num_invs)
 	return new_invs;
 }
 
+struct arm_smmu_tlbi {
+	unsigned long iova;
+	size_t size;
+	/* page or block size of the leaf iopte */
+	unsigned int iopte_size;
+	bool has_cont;
+	bool leaf_only;
+};
+
 struct arm_smmu_evtq {
 	struct arm_smmu_queue		q;
 	struct iopf_queue		*iopf;
-- 
2.43.0



  parent reply	other threads:[~2026-09-01 17:50 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-01 17:49 [PATCH v5 0/9] Organize the SMMUv3 invalidation flow so iommupt can use it Jason Gunthorpe
2026-09-01 17:49 ` [PATCH v5 1/9] iommu/arm-smmu-v3: Handle ARM erratum for CONT under invalidation with SVA Jason Gunthorpe
2026-09-07 14:21   ` Mostafa Saleh
2026-09-07 15:11     ` Jason Gunthorpe
2026-09-07 15:17       ` Mostafa Saleh
2026-09-07 15:18         ` Jason Gunthorpe
2026-09-01 17:49 ` Jason Gunthorpe [this message]
2026-09-01 17:49 ` [PATCH v5 3/9] iommu/arm-smmu-v3: Move pgsize out of arm_smmu_inv Jason Gunthorpe
2026-09-07 14:22   ` Mostafa Saleh
2026-09-01 17:49 ` [PATCH v5 4/9] iommu/arm-smmu-v3: Optimize range invalidation for latency Jason Gunthorpe
2026-09-07 14:26   ` Mostafa Saleh
2026-09-07 15:23     ` Jason Gunthorpe
2026-09-07 19:34       ` Jason Gunthorpe
2026-09-01 17:49 ` [PATCH v5 5/9] iommu/arm-smmu-v3: Keep track in the arm_smmu_invs if RIL is used Jason Gunthorpe
2026-09-01 17:49 ` [PATCH v5 6/9] iommu/arm-smmu-v3: Precompute the invalidation commands Jason Gunthorpe
2026-09-07 14:27   ` Mostafa Saleh
2026-09-07 15:19     ` Jason Gunthorpe
2026-09-01 17:49 ` [PATCH v5 7/9] iommu/arm-smmu-v3: Populate the tlbi at the top of the call chain Jason Gunthorpe
2026-09-01 17:49 ` [PATCH v5 8/9] iommu/arm-smmu-v3: Change how the tlbi describes the invalidation Jason Gunthorpe
2026-09-07 14:42   ` Mostafa Saleh
2026-09-07 15:34     ` Jason Gunthorpe
2026-09-09 15:57       ` Jason Gunthorpe
2026-09-01 17:49 ` [PATCH v5 9/9] iommu/arm-smmu-v3: Support the DS expansion of RIL's SCALE Jason Gunthorpe
2026-09-07 14:44   ` Mostafa Saleh
2026-09-07 19:39     ` Jason Gunthorpe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2-v5-b810cf379bfc+13d738-smmu_tlbi_jgg@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=dmatlack@google.com \
    --cc=iommu@lists.linux.dev \
    --cc=jean-philippe@linaro.org \
    --cc=joro@8bytes.org \
    --cc=jpb@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=nicolinc@nvidia.com \
    --cc=pasha.tatashin@soleen.com \
    --cc=patches@lists.linux.dev \
    --cc=praan@google.com \
    --cc=rdunlap@infradead.org \
    --cc=robin.murphy@arm.com \
    --cc=skhan@linuxfoundation.org \
    --cc=skhawaja@google.com \
    --cc=smostafa@google.com \
    --cc=stable@vger.kernel.org \
    --cc=vijayanand.jitta@oss.qualcomm.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox