[PATCH v2 0/4] DMA mapping changes for SCSI core

[PATCH v2 0/4] DMA mapping changes for SCSI core

[John Garry]

As reported in [0], DMA mappings whose size exceeds the IOMMU IOVA caching
limit may see a big performance hit.

This series introduces a new DMA mapping API, dma_opt_mapping_size(), so
that drivers may know this limit when performance is a factor in the
mapping.

Robin didn't like using dma_max_mapping_size() for this [1].

The SCSI core code is modified to use this limit.

I also added a patch for libata-scsi as it does not currently honour the
shost max_sectors limit.

[0] https://lore.kernel.org/linux-iommu/20210129092120.1482-1-thunder.leizhen@huawei.com/
[1] https://lore.kernel.org/linux-iommu/f5b78c9c-312e-70ab-ecbb-f14623a4b6e3@arm.com/

Changes since v1:
- Relocate scsi_add_host_with_dma() dma_dev check (Reported by Dan)
- Add tags from Damien and Martin (thanks)
  - note: I only added Martin's tag to the SCSI patch

John Garry (4):
  dma-mapping: Add dma_opt_mapping_size()
  dma-iommu: Add iommu_dma_opt_mapping_size()
  scsi: core: Cap shost max_sectors according to DMA optimum mapping
    limits
  libata-scsi: Cap ata_device->max_sectors according to
    shost->max_sectors

 Documentation/core-api/dma-api.rst |  9 +++++++++
 drivers/ata/libata-scsi.c          |  1 +
 drivers/iommu/dma-iommu.c          |  6 ++++++
 drivers/iommu/iova.c               |  5 +++++
 drivers/scsi/hosts.c               |  5 +++++
 drivers/scsi/scsi_lib.c            |  4 ----
 include/linux/dma-map-ops.h        |  1 +
 include/linux/dma-mapping.h        |  5 +++++
 include/linux/iova.h               |  2 ++
 kernel/dma/mapping.c               | 12 ++++++++++++
 10 files changed, 46 insertions(+), 4 deletions(-)

-- 
2.26.2

[PATCH v2 0/4] DMA mapping changes for SCSI core

[John Garry via iommu]

As reported in [0], DMA mappings whose size exceeds the IOMMU IOVA caching
limit may see a big performance hit.

This series introduces a new DMA mapping API, dma_opt_mapping_size(), so
that drivers may know this limit when performance is a factor in the
mapping.

Robin didn't like using dma_max_mapping_size() for this [1].

The SCSI core code is modified to use this limit.

I also added a patch for libata-scsi as it does not currently honour the
shost max_sectors limit.

[0] https://lore.kernel.org/linux-iommu/20210129092120.1482-1-thunder.leizhen@huawei.com/
[1] https://lore.kernel.org/linux-iommu/f5b78c9c-312e-70ab-ecbb-f14623a4b6e3@arm.com/

Changes since v1:
- Relocate scsi_add_host_with_dma() dma_dev check (Reported by Dan)
- Add tags from Damien and Martin (thanks)
  - note: I only added Martin's tag to the SCSI patch

John Garry (4):
  dma-mapping: Add dma_opt_mapping_size()
  dma-iommu: Add iommu_dma_opt_mapping_size()
  scsi: core: Cap shost max_sectors according to DMA optimum mapping
    limits
  libata-scsi: Cap ata_device->max_sectors according to
    shost->max_sectors

 Documentation/core-api/dma-api.rst |  9 +++++++++
 drivers/ata/libata-scsi.c          |  1 +
 drivers/iommu/dma-iommu.c          |  6 ++++++
 drivers/iommu/iova.c               |  5 +++++
 drivers/scsi/hosts.c               |  5 +++++
 drivers/scsi/scsi_lib.c            |  4 ----
 include/linux/dma-map-ops.h        |  1 +
 include/linux/dma-mapping.h        |  5 +++++
 include/linux/iova.h               |  2 ++
 kernel/dma/mapping.c               | 12 ++++++++++++
 10 files changed, 46 insertions(+), 4 deletions(-)

-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 1/4] dma-mapping: Add dma_opt_mapping_size()

[John Garry]

Streaming DMA mapping involving an IOMMU may be much slower for larger
total mapping size. This is because every IOMMU DMA mapping requires an
IOVA to be allocated and freed. IOVA sizes above a certain limit are not
cached, which can have a big impact on DMA mapping performance.

Provide an API for device drivers to know this "optimal" limit, such that
they may try to produce mapping which don't exceed it.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 Documentation/core-api/dma-api.rst |  9 +++++++++
 include/linux/dma-map-ops.h        |  1 +
 include/linux/dma-mapping.h        |  5 +++++
 kernel/dma/mapping.c               | 12 ++++++++++++
 4 files changed, 27 insertions(+)

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 6d6d0edd2d27..b3cd9763d28b 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -204,6 +204,15 @@ Returns the maximum size of a mapping for the device. The size parameter
 of the mapping functions like dma_map_single(), dma_map_page() and
 others should not be larger than the returned value.
 
+::
+
+	size_t
+	dma_opt_mapping_size(struct device *dev);
+
+Returns the maximum optimal size of a mapping for the device. Mapping large
+buffers may take longer so device drivers are advised to limit total DMA
+streaming mappings length to the returned value.
+
 ::
 
 	bool
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 0d5b06b3a4a6..98ceba6fa848 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -69,6 +69,7 @@ struct dma_map_ops {
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
+	size_t (*opt_mapping_size)(void);
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index dca2b1355bb1..fe3849434b2a 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -144,6 +144,7 @@ int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+size_t dma_opt_mapping_size(struct device *dev);
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
@@ -266,6 +267,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline size_t dma_opt_mapping_size(struct device *dev)
+{
+	return 0;
+}
 static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return false;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index db7244291b74..1bfe11b1edb6 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -773,6 +773,18 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+size_t dma_opt_mapping_size(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	size_t size = SIZE_MAX;
+
+	if (ops && ops->opt_mapping_size)
+		size = ops->opt_mapping_size();
+
+	return min(dma_max_mapping_size(dev), size);
+}
+EXPORT_SYMBOL_GPL(dma_opt_mapping_size);
+
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-- 
2.26.2

[PATCH v2 1/4] dma-mapping: Add dma_opt_mapping_size()

[John Garry via iommu]

Streaming DMA mapping involving an IOMMU may be much slower for larger
total mapping size. This is because every IOMMU DMA mapping requires an
IOVA to be allocated and freed. IOVA sizes above a certain limit are not
cached, which can have a big impact on DMA mapping performance.

Provide an API for device drivers to know this "optimal" limit, such that
they may try to produce mapping which don't exceed it.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 Documentation/core-api/dma-api.rst |  9 +++++++++
 include/linux/dma-map-ops.h        |  1 +
 include/linux/dma-mapping.h        |  5 +++++
 kernel/dma/mapping.c               | 12 ++++++++++++
 4 files changed, 27 insertions(+)

diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 6d6d0edd2d27..b3cd9763d28b 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -204,6 +204,15 @@ Returns the maximum size of a mapping for the device. The size parameter
 of the mapping functions like dma_map_single(), dma_map_page() and
 others should not be larger than the returned value.
 
+::
+
+	size_t
+	dma_opt_mapping_size(struct device *dev);
+
+Returns the maximum optimal size of a mapping for the device. Mapping large
+buffers may take longer so device drivers are advised to limit total DMA
+streaming mappings length to the returned value.
+
 ::
 
 	bool
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 0d5b06b3a4a6..98ceba6fa848 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -69,6 +69,7 @@ struct dma_map_ops {
 	int (*dma_supported)(struct device *dev, u64 mask);
 	u64 (*get_required_mask)(struct device *dev);
 	size_t (*max_mapping_size)(struct device *dev);
+	size_t (*opt_mapping_size)(void);
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index dca2b1355bb1..fe3849434b2a 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -144,6 +144,7 @@ int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
+size_t dma_opt_mapping_size(struct device *dev);
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
@@ -266,6 +267,10 @@ static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
 }
+static inline size_t dma_opt_mapping_size(struct device *dev)
+{
+	return 0;
+}
 static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	return false;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index db7244291b74..1bfe11b1edb6 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -773,6 +773,18 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+size_t dma_opt_mapping_size(struct device *dev)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	size_t size = SIZE_MAX;
+
+	if (ops && ops->opt_mapping_size)
+		size = ops->opt_mapping_size();
+
+	return min(dma_max_mapping_size(dev), size);
+}
+EXPORT_SYMBOL_GPL(dma_opt_mapping_size);
+
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 2/4] dma-iommu: Add iommu_dma_opt_mapping_size()

[John Garry]

Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
allows the drivers to know the optimal mapping limit and thus limit the
requested IOVA lengths.

This value is based on the IOVA rcache range limit, as IOVAs allocated
above this limit must always be newly allocated, which may be quite slow.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/iommu/dma-iommu.c | 6 ++++++
 drivers/iommu/iova.c      | 5 +++++
 include/linux/iova.h      | 2 ++
 3 files changed, 13 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 09f6e1c0f9c0..f619e41b9172 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1442,6 +1442,11 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
+static size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
@@ -1462,6 +1467,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.opt_mapping_size	= iommu_dma_opt_mapping_size,
 };
 
 /*
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index db77aa675145..9f00b58d546e 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
+unsigned long iova_rcache_range(void)
+{
+	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
+}
+
 static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct iova_domain *iovad;
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 320a70e40233..c6ba6d95d79c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
+unsigned long iova_rcache_range(void);
+
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
-- 
2.26.2

[PATCH v2 2/4] dma-iommu: Add iommu_dma_opt_mapping_size()

[John Garry via iommu]

Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
allows the drivers to know the optimal mapping limit and thus limit the
requested IOVA lengths.

This value is based on the IOVA rcache range limit, as IOVAs allocated
above this limit must always be newly allocated, which may be quite slow.

Signed-off-by: John Garry <john.garry@huawei.com>
---
 drivers/iommu/dma-iommu.c | 6 ++++++
 drivers/iommu/iova.c      | 5 +++++
 include/linux/iova.h      | 2 ++
 3 files changed, 13 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 09f6e1c0f9c0..f619e41b9172 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1442,6 +1442,11 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
+static size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
@@ -1462,6 +1467,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.map_resource		= iommu_dma_map_resource,
 	.unmap_resource		= iommu_dma_unmap_resource,
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
+	.opt_mapping_size	= iommu_dma_opt_mapping_size,
 };
 
 /*
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index db77aa675145..9f00b58d546e 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 
+unsigned long iova_rcache_range(void)
+{
+	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
+}
+
 static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct iova_domain *iovad;
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 320a70e40233..c6ba6d95d79c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 int iova_cache_get(void);
 void iova_cache_put(void);
 
+unsigned long iova_rcache_range(void);
+
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
 void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 3/4] scsi: core: Cap shost max_sectors according to DMA optimum mapping limits

[John Garry]

Streaming DMA mappings may be considerably slower when mappings go through
an IOMMU and the total mapping length is somewhat long. This is because the
IOMMU IOVA code allocates and free an IOVA for each mapping, which may
affect performance.

For performance reasons set the request_queue max_sectors from
dma_opt_mapping_size(), which knows this mapping limit.

In addition, the shost->max_sectors is repeatedly set for each sdev in
__scsi_init_queue(). This is unnecessary, so set once when adding the
host.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hosts.c    | 5 +++++
 drivers/scsi/scsi_lib.c | 4 ----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index f69b77cbf538..9563c0ac567a 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -240,6 +240,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 
 	shost->dma_dev = dma_dev;
 
+	if (dma_dev->dma_mask) {
+		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
+	}
+
 	/*
 	 * Increase usage count temporarily here so that calling
 	 * scsi_autopm_put_host() will trigger runtime idle if there is
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 8d18cc7e510e..2d43bb8799bd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1884,10 +1884,6 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
 	}
 
-	if (dev->dma_mask) {
-		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
-				dma_max_mapping_size(dev) >> SECTOR_SHIFT);
-	}
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	blk_queue_segment_boundary(q, shost->dma_boundary);
 	dma_set_seg_boundary(dev, shost->dma_boundary);
-- 
2.26.2

[PATCH v2 3/4] scsi: core: Cap shost max_sectors according to DMA optimum mapping limits

[John Garry via iommu]

Streaming DMA mappings may be considerably slower when mappings go through
an IOMMU and the total mapping length is somewhat long. This is because the
IOMMU IOVA code allocates and free an IOVA for each mapping, which may
affect performance.

For performance reasons set the request_queue max_sectors from
dma_opt_mapping_size(), which knows this mapping limit.

In addition, the shost->max_sectors is repeatedly set for each sdev in
__scsi_init_queue(). This is unnecessary, so set once when adding the
host.

Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hosts.c    | 5 +++++
 drivers/scsi/scsi_lib.c | 4 ----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index f69b77cbf538..9563c0ac567a 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -240,6 +240,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 
 	shost->dma_dev = dma_dev;
 
+	if (dma_dev->dma_mask) {
+		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_opt_mapping_size(dma_dev) >> SECTOR_SHIFT);
+	}
+
 	/*
 	 * Increase usage count temporarily here so that calling
 	 * scsi_autopm_put_host() will trigger runtime idle if there is
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 8d18cc7e510e..2d43bb8799bd 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1884,10 +1884,6 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
 	}
 
-	if (dev->dma_mask) {
-		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
-				dma_max_mapping_size(dev) >> SECTOR_SHIFT);
-	}
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	blk_queue_segment_boundary(q, shost->dma_boundary);
 	dma_set_seg_boundary(dev, shost->dma_boundary);
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH v2 4/4] libata-scsi: Cap ata_device->max_sectors according to shost->max_sectors

[John Garry]

ATA devices (struct ata_device) have a max_sectors field which is
configured internally in libata. This is then used to (re)configure the
associated sdev request queue max_sectors value from how it is earlier set
in __scsi_init_queue(). In __scsi_init_queue() the max_sectors value is set
according to shost limits, which includes host DMA mapping limits.

Cap the ata_device max_sectors according to shost->max_sectors to respect
this shost limit.

Signed-off-by: John Garry <john.garry@huawei.com>
Acked-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 drivers/ata/libata-scsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 06c9d90238d9..25fe89791641 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1036,6 +1036,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
 	/* configure max sectors */
+	dev->max_sectors = min(dev->max_sectors, sdev->host->max_sectors);
 	blk_queue_max_hw_sectors(q, dev->max_sectors);
 
 	if (dev->class == ATA_DEV_ATAPI) {
-- 
2.26.2

[PATCH v2 4/4] libata-scsi: Cap ata_device->max_sectors according to shost->max_sectors

[John Garry via iommu]

ATA devices (struct ata_device) have a max_sectors field which is
configured internally in libata. This is then used to (re)configure the
associated sdev request queue max_sectors value from how it is earlier set
in __scsi_init_queue(). In __scsi_init_queue() the max_sectors value is set
according to shost limits, which includes host DMA mapping limits.

Cap the ata_device max_sectors according to shost->max_sectors to respect
this shost limit.

Signed-off-by: John Garry <john.garry@huawei.com>
Acked-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
---
 drivers/ata/libata-scsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 06c9d90238d9..25fe89791641 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1036,6 +1036,7 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev)
 		dev->flags |= ATA_DFLAG_NO_UNLOAD;
 
 	/* configure max sectors */
+	dev->max_sectors = min(dev->max_sectors, sdev->host->max_sectors);
 	blk_queue_max_hw_sectors(q, dev->max_sectors);
 
 	if (dev->class == ATA_DEV_ATAPI) {
-- 
2.26.2

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: [PATCH v2 2/4] dma-iommu: Add iommu_dma_opt_mapping_size()

[Damien Le Moal]

On 2022/05/26 19:28, John Garry wrote:
> Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
> allows the drivers to know the optimal mapping limit and thus limit the
> requested IOVA lengths.
> 
> This value is based on the IOVA rcache range limit, as IOVAs allocated
> above this limit must always be newly allocated, which may be quite slow.
> 
> Signed-off-by: John Garry <john.garry@huawei.com>
> ---
>  drivers/iommu/dma-iommu.c | 6 ++++++
>  drivers/iommu/iova.c      | 5 +++++
>  include/linux/iova.h      | 2 ++
>  3 files changed, 13 insertions(+)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 09f6e1c0f9c0..f619e41b9172 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -1442,6 +1442,11 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
>  	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
>  }
>  
> +static size_t iommu_dma_opt_mapping_size(void)
> +{
> +	return iova_rcache_range();
> +}
> +
>  static const struct dma_map_ops iommu_dma_ops = {
>  	.alloc			= iommu_dma_alloc,
>  	.free			= iommu_dma_free,
> @@ -1462,6 +1467,7 @@ static const struct dma_map_ops iommu_dma_ops = {
>  	.map_resource		= iommu_dma_map_resource,
>  	.unmap_resource		= iommu_dma_unmap_resource,
>  	.get_merge_boundary	= iommu_dma_get_merge_boundary,
> +	.opt_mapping_size	= iommu_dma_opt_mapping_size,
>  };
>  
>  /*
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index db77aa675145..9f00b58d546e 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
>  static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
>  static void free_iova_rcaches(struct iova_domain *iovad);
>  
> +unsigned long iova_rcache_range(void)
> +{
> +	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
> +}
> +
>  static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
>  {
>  	struct iova_domain *iovad;
> diff --git a/include/linux/iova.h b/include/linux/iova.h
> index 320a70e40233..c6ba6d95d79c 100644
> --- a/include/linux/iova.h
> +++ b/include/linux/iova.h
> @@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
>  int iova_cache_get(void);
>  void iova_cache_put(void);
>  
> +unsigned long iova_rcache_range(void);
> +
>  void free_iova(struct iova_domain *iovad, unsigned long pfn);
>  void __free_iova(struct iova_domain *iovad, struct iova *iova);
>  struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,

Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>

-- 
Damien Le Moal
Western Digital Research

Re: [PATCH v2 2/4] dma-iommu: Add iommu_dma_opt_mapping_size()

[Damien Le Moal via iommu]

On 2022/05/26 19:28, John Garry wrote:
> Add the IOMMU callback for DMA mapping API dma_opt_mapping_size(), which
> allows the drivers to know the optimal mapping limit and thus limit the
> requested IOVA lengths.
> 
> This value is based on the IOVA rcache range limit, as IOVAs allocated
> above this limit must always be newly allocated, which may be quite slow.
> 
> Signed-off-by: John Garry <john.garry@huawei.com>
> ---
>  drivers/iommu/dma-iommu.c | 6 ++++++
>  drivers/iommu/iova.c      | 5 +++++
>  include/linux/iova.h      | 2 ++
>  3 files changed, 13 insertions(+)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 09f6e1c0f9c0..f619e41b9172 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -1442,6 +1442,11 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
>  	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
>  }
>  
> +static size_t iommu_dma_opt_mapping_size(void)
> +{
> +	return iova_rcache_range();
> +}
> +
>  static const struct dma_map_ops iommu_dma_ops = {
>  	.alloc			= iommu_dma_alloc,
>  	.free			= iommu_dma_free,
> @@ -1462,6 +1467,7 @@ static const struct dma_map_ops iommu_dma_ops = {
>  	.map_resource		= iommu_dma_map_resource,
>  	.unmap_resource		= iommu_dma_unmap_resource,
>  	.get_merge_boundary	= iommu_dma_get_merge_boundary,
> +	.opt_mapping_size	= iommu_dma_opt_mapping_size,
>  };
>  
>  /*
> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
> index db77aa675145..9f00b58d546e 100644
> --- a/drivers/iommu/iova.c
> +++ b/drivers/iommu/iova.c
> @@ -26,6 +26,11 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
>  static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
>  static void free_iova_rcaches(struct iova_domain *iovad);
>  
> +unsigned long iova_rcache_range(void)
> +{
> +	return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
> +}
> +
>  static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
>  {
>  	struct iova_domain *iovad;
> diff --git a/include/linux/iova.h b/include/linux/iova.h
> index 320a70e40233..c6ba6d95d79c 100644
> --- a/include/linux/iova.h
> +++ b/include/linux/iova.h
> @@ -79,6 +79,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
>  int iova_cache_get(void);
>  void iova_cache_put(void);
>  
> +unsigned long iova_rcache_range(void);
> +
>  void free_iova(struct iova_domain *iovad, unsigned long pfn);
>  void __free_iova(struct iova_domain *iovad, struct iova *iova);
>  struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,

Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>

-- 
Damien Le Moal
Western Digital Research
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu