From: Georgi Djakov <quic_c_gdjako@quicinc.com>
To: <will@kernel.org>, <robin.murphy@arm.com>
Cc: <joro@8bytes.org>, <isaacm@codeaurora.org>,
<baolu.lu@linux.intel.com>, <pratikp@codeaurora.org>,
<iommu@lists.linux-foundation.org>,
<linux-arm-kernel@lists.infradead.org>,
<linux-kernel@vger.kernel.org>, <djakov@kernel.org>
Subject: [PATCH v6 09/15] iommu/io-pgtable-arm: Prepare PTE methods for handling multiple entries
Date: Tue, 15 Jun 2021 10:08:27 -0700 [thread overview]
Message-ID: <1623776913-390160-10-git-send-email-quic_c_gdjako@quicinc.com> (raw)
In-Reply-To: <1623776913-390160-1-git-send-email-quic_c_gdjako@quicinc.com>
From: "Isaac J. Manjarres" <isaacm@codeaurora.org>
The PTE methods currently operate on a single entry. In preparation
for manipulating multiple PTEs in one map or unmap call, allow them
to handle multiple PTEs.
Signed-off-by: Isaac J. Manjarres <isaacm@codeaurora.org>
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Georgi Djakov <quic_c_gdjako@quicinc.com>
---
drivers/iommu/io-pgtable-arm.c | 78 ++++++++++++++++++++++++------------------
1 file changed, 44 insertions(+), 34 deletions(-)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 87def58e79b5..ea66b10c04c4 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -232,20 +232,23 @@ static void __arm_lpae_free_pages(void *pages, size_t size,
free_pages((unsigned long)pages, get_order(size));
}
-static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep,
+static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
struct io_pgtable_cfg *cfg)
{
dma_sync_single_for_device(cfg->iommu_dev, __arm_lpae_dma_addr(ptep),
- sizeof(*ptep), DMA_TO_DEVICE);
+ sizeof(*ptep) * num_entries, DMA_TO_DEVICE);
}
static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
- struct io_pgtable_cfg *cfg)
+ int num_entries, struct io_pgtable_cfg *cfg)
{
- *ptep = pte;
+ int i;
+
+ for (i = 0; i < num_entries; i++)
+ ptep[i] = pte;
if (!cfg->coherent_walk)
- __arm_lpae_sync_pte(ptep, cfg);
+ __arm_lpae_sync_pte(ptep, num_entries, cfg);
}
static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
@@ -255,47 +258,54 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
phys_addr_t paddr, arm_lpae_iopte prot,
- int lvl, arm_lpae_iopte *ptep)
+ int lvl, int num_entries, arm_lpae_iopte *ptep)
{
arm_lpae_iopte pte = prot;
+ struct io_pgtable_cfg *cfg = &data->iop.cfg;
+ size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
+ int i;
if (data->iop.fmt != ARM_MALI_LPAE && lvl == ARM_LPAE_MAX_LEVELS - 1)
pte |= ARM_LPAE_PTE_TYPE_PAGE;
else
pte |= ARM_LPAE_PTE_TYPE_BLOCK;
- pte |= paddr_to_iopte(paddr, data);
+ for (i = 0; i < num_entries; i++)
+ ptep[i] = pte | paddr_to_iopte(paddr + i * sz, data);
- __arm_lpae_set_pte(ptep, pte, &data->iop.cfg);
+ if (!cfg->coherent_walk)
+ __arm_lpae_sync_pte(ptep, num_entries, cfg);
}
static int arm_lpae_init_pte(struct arm_lpae_io_pgtable *data,
unsigned long iova, phys_addr_t paddr,
- arm_lpae_iopte prot, int lvl,
+ arm_lpae_iopte prot, int lvl, int num_entries,
arm_lpae_iopte *ptep)
{
- arm_lpae_iopte pte = *ptep;
-
- if (iopte_leaf(pte, lvl, data->iop.fmt)) {
- /* We require an unmap first */
- WARN_ON(!selftest_running);
- return -EEXIST;
- } else if (iopte_type(pte) == ARM_LPAE_PTE_TYPE_TABLE) {
- /*
- * We need to unmap and free the old table before
- * overwriting it with a block entry.
- */
- arm_lpae_iopte *tblp;
- size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
-
- tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
- if (__arm_lpae_unmap(data, NULL, iova, sz, lvl, tblp) != sz) {
- WARN_ON(1);
- return -EINVAL;
+ int i;
+
+ for (i = 0; i < num_entries; i++)
+ if (iopte_leaf(ptep[i], lvl, data->iop.fmt)) {
+ /* We require an unmap first */
+ WARN_ON(!selftest_running);
+ return -EEXIST;
+ } else if (iopte_type(ptep[i]) == ARM_LPAE_PTE_TYPE_TABLE) {
+ /*
+ * We need to unmap and free the old table before
+ * overwriting it with a block entry.
+ */
+ arm_lpae_iopte *tblp;
+ size_t sz = ARM_LPAE_BLOCK_SIZE(lvl, data);
+
+ tblp = ptep - ARM_LPAE_LVL_IDX(iova, lvl, data);
+ if (__arm_lpae_unmap(data, NULL, iova + i * sz, sz,
+ lvl, tblp) != sz) {
+ WARN_ON(1);
+ return -EINVAL;
+ }
}
- }
- __arm_lpae_init_pte(data, paddr, prot, lvl, ptep);
+ __arm_lpae_init_pte(data, paddr, prot, lvl, num_entries, ptep);
return 0;
}
@@ -323,7 +333,7 @@ static arm_lpae_iopte arm_lpae_install_table(arm_lpae_iopte *table,
return old;
/* Even if it's not ours, there's no point waiting; just kick it */
- __arm_lpae_sync_pte(ptep, cfg);
+ __arm_lpae_sync_pte(ptep, 1, cfg);
if (old == curr)
WRITE_ONCE(*ptep, new | ARM_LPAE_PTE_SW_SYNC);
@@ -344,7 +354,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
/* If we can install a leaf entry at this level, then do so */
if (size == block_size)
- return arm_lpae_init_pte(data, iova, paddr, prot, lvl, ptep);
+ return arm_lpae_init_pte(data, iova, paddr, prot, lvl, 1, ptep);
/* We can't allocate tables at the final level */
if (WARN_ON(lvl >= ARM_LPAE_MAX_LEVELS - 1))
@@ -361,7 +371,7 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
if (pte)
__arm_lpae_free_pages(cptep, tblsz, cfg);
} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
- __arm_lpae_sync_pte(ptep, cfg);
+ __arm_lpae_sync_pte(ptep, 1, cfg);
}
if (pte && !iopte_leaf(pte, lvl, data->iop.fmt)) {
@@ -543,7 +553,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
if (i == unmap_idx)
continue;
- __arm_lpae_init_pte(data, blk_paddr, pte, lvl, &tablep[i]);
+ __arm_lpae_init_pte(data, blk_paddr, pte, lvl, 1, &tablep[i]);
}
pte = arm_lpae_install_table(tablep, ptep, blk_pte, cfg);
@@ -585,7 +595,7 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
/* If the size matches this level, we're in the right place */
if (size == ARM_LPAE_BLOCK_SIZE(lvl, data)) {
- __arm_lpae_set_pte(ptep, 0, &iop->cfg);
+ __arm_lpae_set_pte(ptep, 0, 1, &iop->cfg);
if (!iopte_leaf(pte, lvl, iop->fmt)) {
/* Also flush any partial walks */
next prev parent reply other threads:[~2021-06-15 17:09 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-15 17:08 [PATCH v6 00/15] Optimizing iommu_[map/unmap] performance Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 01/15] iommu/io-pgtable: Introduce unmap_pages() as a page table op Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 02/15] iommu: Add an unmap_pages() op for IOMMU drivers Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 03/15] iommu/io-pgtable: Introduce map_pages() as a page table op Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 04/15] iommu: Add a map_pages() op for IOMMU drivers Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 05/15] iommu: Use bitmap to calculate page size in iommu_pgsize() Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 06/15] iommu: Split 'addr_merge' argument to iommu_pgsize() into separate parts Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 07/15] iommu: Hook up '->unmap_pages' driver callback Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 08/15] iommu: Add support for the map_pages() callback Georgi Djakov
2021-06-15 17:08 ` Georgi Djakov [this message]
2021-06-15 17:08 ` [PATCH v6 10/15] iommu/io-pgtable-arm: Implement arm_lpae_unmap_pages() Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 11/15] iommu/io-pgtable-arm: Implement arm_lpae_map_pages() Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 12/15] iommu/io-pgtable-arm-v7s: Implement arm_v7s_unmap_pages() Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 13/15] iommu/io-pgtable-arm-v7s: Implement arm_v7s_map_pages() Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 14/15] iommu/arm-smmu: Implement the unmap_pages() IOMMU driver callback Georgi Djakov
2021-06-15 17:08 ` [PATCH v6 15/15] iommu/arm-smmu: Implement the map_pages() " Georgi Djakov
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=1623776913-390160-10-git-send-email-quic_c_gdjako@quicinc.com \
--to=quic_c_gdjako@quicinc.com \
--cc=baolu.lu@linux.intel.com \
--cc=djakov@kernel.org \
--cc=iommu@lists.linux-foundation.org \
--cc=isaacm@codeaurora.org \
--cc=joro@8bytes.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pratikp@codeaurora.org \
--cc=robin.murphy@arm.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).