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 7/9] iommu/arm-smmu-v3: Populate the tlbi at the top of the call chain
Date: Tue, 1 Sep 2026 14:49:56 -0300 [thread overview]
Message-ID: <7-v5-b810cf379bfc+13d738-smmu_tlbi_jgg@nvidia.com> (raw)
In-Reply-To: <0-v5-b810cf379bfc+13d738-smmu_tlbi_jgg@nvidia.com>
Each of these have their own unique situation, populate the tlbi right
at the top and pass it into arm_smmu_domain_inv_range(). They will
diverge further when the iommupt invalidation scheme is introduced.
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
.../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 21 ++++----
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 54 ++++++++++---------
drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 15 ++++--
3 files changed, 51 insertions(+), 39 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
index 7acb70d060ec4e..47eba08bd1161f 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -140,16 +140,19 @@ static void arm_smmu_mm_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn,
{
struct arm_smmu_domain *smmu_domain =
container_of(mn, struct arm_smmu_domain, mmu_notifier);
- size_t size;
+ struct arm_smmu_tlbi tlbi = {
+ .tgsz_lg2 = smmu_domain->tgsz_lg2,
+ .iova = start,
+ /*
+ * The mm_types defines vm_end as the first byte after the end
+ * address, different from IOMMU subsystem using the last
+ * address of an address range.
+ */
+ .size = end - start,
+ .iopte_size = PAGE_SIZE,
+ };
- /*
- * The mm_types defines vm_end as the first byte after the end address,
- * different from IOMMU subsystem using the last address of an address
- * range. So do a simple translation here by calculating size correctly.
- */
- size = end - start;
-
- arm_smmu_domain_inv_range(smmu_domain, start, size, PAGE_SIZE, false);
+ arm_smmu_domain_tlbi(&tlbi, smmu_domain);
}
static void arm_smmu_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
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 883dfc584ed6c6..b9efba3404c68b 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -2789,25 +2789,13 @@ static void arm_smmu_domain_tlbi_inv(struct arm_smmu_tlbi *tlbi,
}
}
-void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
- unsigned long iova, size_t size,
- unsigned int granule, bool leaf)
+void arm_smmu_domain_tlbi(struct arm_smmu_tlbi *tlbi,
+ struct arm_smmu_domain *smmu_domain)
{
- struct arm_smmu_tlbi tlbi = {
- .tgsz_lg2 = smmu_domain->tgsz_lg2,
- .iova = iova,
- .size = size,
- .iopte_size = granule,
- .leaf_only = leaf,
- };
struct arm_smmu_invs *invs;
- if (!size || size == SIZE_MAX) {
- tlbi.single.use_full_inv = true;
- tlbi.range.use_full_inv = true;
- } else {
- arm_smmu_tlbi_calc_single(&tlbi);
- }
+ if (!tlbi->single.use_full_inv)
+ arm_smmu_tlbi_calc_single(tlbi);
/*
* An invalidation request must follow some IOPTE change and then load
@@ -2826,7 +2814,7 @@ void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
*
* [CPU0] | [CPU1]
* change IOPTE on new domain: |
- * arm_smmu_domain_inv_range() { | arm_smmu_install_new_domain_invs()
+ * arm_smmu_domain_tlbi() { | arm_smmu_install_new_domain_invs()
* smp_mb(); // ensures IOPTE | arm_smmu_install_ste_for_dev {
* // seen by SMMU | dma_wmb(); // ensures invs update
* // load the updated invs | // before updating STE
@@ -2844,9 +2832,9 @@ void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
* this matches the instances used for invalidation.
*/
if (invs->has_range_inv) {
- if (!tlbi.range.use_full_inv) {
+ if (!tlbi->range.use_full_inv) {
arm_smmu_tlbi_calc_range(
- &tlbi,
+ tlbi,
smmu_domain->stage == ARM_SMMU_DOMAIN_SVA &&
invs->has_full_cont_ril);
}
@@ -2860,10 +2848,10 @@ void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
unsigned long flags;
read_lock_irqsave(&invs->rwlock, flags);
- arm_smmu_domain_tlbi_inv(&tlbi, invs);
+ arm_smmu_domain_tlbi_inv(tlbi, invs);
read_unlock_irqrestore(&invs->rwlock, flags);
} else {
- arm_smmu_domain_tlbi_inv(&tlbi, invs);
+ arm_smmu_domain_tlbi_inv(tlbi, invs);
}
rcu_read_unlock();
@@ -2879,12 +2867,23 @@ static void arm_smmu_tlb_inv_page_nosync(struct iommu_iotlb_gather *gather,
iommu_iotlb_gather_add_page(domain, gather, iova, granule);
}
+/*
+ * Called by io-pgtable-arm.c for each single table level it wants to remove.
+ * size is the size of the table level and granule is the tg in bytes. This must
+ * clear the walk cache and any leaves within the range.
+ */
static void arm_smmu_tlb_inv_walk(unsigned long iova, size_t size,
size_t granule, void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_tlbi tlbi = {
+ .tgsz_lg2 = smmu_domain->tgsz_lg2,
+ .iova = iova,
+ .size = size,
+ .iopte_size = 1 << smmu_domain->tgsz_lg2,
+ };
- arm_smmu_domain_inv_range(smmu_domain, iova, size, granule, false);
+ arm_smmu_domain_tlbi(&tlbi, smmu_domain);
}
static const struct iommu_flush_ops arm_smmu_flush_ops = {
@@ -4157,13 +4156,18 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain,
struct iommu_iotlb_gather *gather)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_tlbi tlbi = {
+ .tgsz_lg2 = smmu_domain->tgsz_lg2,
+ .iova = gather->start,
+ .size = gather->end - gather->start + 1,
+ .iopte_size = gather->pgsize,
+ .leaf_only = true,
+ };
if (!gather->pgsize)
return;
- arm_smmu_domain_inv_range(smmu_domain, gather->start,
- gather->end - gather->start + 1,
- gather->pgsize, true);
+ arm_smmu_domain_tlbi(&tlbi, smmu_domain);
}
static phys_addr_t
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 33ef99775aea87..09befe7b284fed 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1181,14 +1181,19 @@ int arm_smmu_set_pasid(struct arm_smmu_master *master,
struct arm_smmu_domain *smmu_domain, ioasid_t pasid,
struct arm_smmu_cd *cd, struct iommu_domain *old);
-void arm_smmu_domain_inv_range(struct arm_smmu_domain *smmu_domain,
- unsigned long iova, size_t size,
- unsigned int granule, bool leaf);
+void arm_smmu_domain_tlbi(struct arm_smmu_tlbi *tlbi,
+ struct arm_smmu_domain *smmu_domain);
static inline void arm_smmu_domain_inv(struct arm_smmu_domain *smmu_domain)
{
- arm_smmu_domain_inv_range(smmu_domain, 0, 0, 1 << smmu_domain->tgsz_lg2,
- false);
+ /* Prefilled for invalidate all */
+ struct arm_smmu_tlbi tlbi = {
+ .tgsz_lg2 = smmu_domain->tgsz_lg2,
+ .single.use_full_inv = true,
+ .range.use_full_inv = true,
+ };
+
+ arm_smmu_domain_tlbi(&tlbi, smmu_domain);
}
void __arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu,
--
2.43.0
next prev 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 ` [PATCH v5 2/9] iommu/arm-smmu-v3: Pass the parameters for the invalidation in a struct Jason Gunthorpe
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 ` Jason Gunthorpe [this message]
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=7-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;
as well as URLs for NNTP newsgroup(s).