[PATCH 0/4] Genericise the IOVA allocator

[PATCH 0/4] Genericise the IOVA allocator

[Robin Murphy]

Hi all,

Here's an update of my previous RFC[1] in preparation for hooking the
IOVA allocator up to the arm64 DMA mapping API, rebased onto 3.19-rc3.

I tried rebasing patches 3 and 4 onto Sakari's RFC series[2] (the merge
conflict is pretty trivial), however I found that series applied to rc3
causes a build error in intel-iommu.c. Thus for now I've left in my
simpler patches 1 and 2 for breaking out the library. Hopefully we can
reach some consensus on that.

Tested on arm64 (DMA mapping series coming soon), and compile-tested
for x86_64_defconfig.

Changes since RFC:
Patch 1: Use a proper Kconfig symbol rather than a hack
Patch 4: sanity check for powers of two also, and clarify the comment

[1]:http://thread.gmane.org/gmane.linux.kernel.iommu/7480
[2]:http://thread.gmane.org/gmane.linux.kernel.iommu/7436

Robin Murphy (4):
  iommu: allow building iova.c independently
  iommu: consolidate IOVA allocator code
  iommu: make IOVA domain low limit flexible
  iommu: make IOVA domain page size explicit

 drivers/iommu/Kconfig       |  4 ++++
 drivers/iommu/Makefile      |  3 ++-
 drivers/iommu/intel-iommu.c | 45 ++++++++++----------------------------
 drivers/iommu/iova.c        | 53 +++++++++++++++++++++++++++++++++++++++++----
 include/linux/iova.h        | 41 +++++++++++++++++++++++++++++++----
 5 files changed, 103 insertions(+), 43 deletions(-)

-- 
1.9.1

[PATCH 1/4] iommu: allow building iova.c independently

[Robin Murphy]

In preparation for sharing the IOVA allocator, split it out under its
own Kconfig symbol.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/iommu/Kconfig  | 4 ++++
 drivers/iommu/Makefile | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 325188e..a839ca9 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -13,6 +13,9 @@ menuconfig IOMMU_SUPPORT
 
 if IOMMU_SUPPORT
 
+config IOMMU_IOVA
+	bool
+
 config OF_IOMMU
        def_bool y
        depends on OF && IOMMU_API
@@ -91,6 +94,7 @@ config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
 	select IOMMU_API
+	select IOMMU_IOVA
 	select DMAR_TABLE
 	help
 	  DMA remapping (DMAR) devices support enables independent address
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index 7b976f2..0b1b94e 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -1,13 +1,14 @@
 obj-$(CONFIG_IOMMU_API) += iommu.o
 obj-$(CONFIG_IOMMU_API) += iommu-traces.o
 obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o
+obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
-obj-$(CONFIG_INTEL_IOMMU) += iova.o intel-iommu.o
+obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
-- 
1.9.1

[PATCH 2/4] iommu: consolidate IOVA allocator code

[Robin Murphy]

In order to share the IOVA allocator with other architectures, break
the unnecssary dependency on the Intel IOMMU driver and move the
remaining IOVA internals to iova.c

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/iommu/intel-iommu.c | 33 ++-------------------------------
 drivers/iommu/iova.c        | 35 +++++++++++++++++++++++++++++++++++
 include/linux/iova.h        |  3 +++
 3 files changed, 40 insertions(+), 31 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1232336..5699653 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -485,7 +485,6 @@ __setup("intel_iommu=", intel_iommu_setup);
 
 static struct kmem_cache *iommu_domain_cache;
 static struct kmem_cache *iommu_devinfo_cache;
-static struct kmem_cache *iommu_iova_cache;
 
 static inline void *alloc_pgtable_page(int node)
 {
@@ -523,16 +522,6 @@ static inline void free_devinfo_mem(void *vaddr)
 	kmem_cache_free(iommu_devinfo_cache, vaddr);
 }
 
-struct iova *alloc_iova_mem(void)
-{
-	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
-}
-
-void free_iova_mem(struct iova *iova)
-{
-	kmem_cache_free(iommu_iova_cache, iova);
-}
-
 static inline int domain_type_is_vm(struct dmar_domain *domain)
 {
 	return domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE;
@@ -3427,23 +3416,6 @@ static inline int iommu_devinfo_cache_init(void)
 	return ret;
 }
 
-static inline int iommu_iova_cache_init(void)
-{
-	int ret = 0;
-
-	iommu_iova_cache = kmem_cache_create("iommu_iova",
-					 sizeof(struct iova),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!iommu_iova_cache) {
-		printk(KERN_ERR "Couldn't create iova cache\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
 static int __init iommu_init_mempool(void)
 {
 	int ret;
@@ -3461,7 +3433,7 @@ static int __init iommu_init_mempool(void)
 
 	kmem_cache_destroy(iommu_domain_cache);
 domain_error:
-	kmem_cache_destroy(iommu_iova_cache);
+	iommu_iova_cache_destroy();
 
 	return -ENOMEM;
 }
@@ -3470,8 +3442,7 @@ static void __init iommu_exit_mempool(void)
 {
 	kmem_cache_destroy(iommu_devinfo_cache);
 	kmem_cache_destroy(iommu_domain_cache);
-	kmem_cache_destroy(iommu_iova_cache);
-
+	iommu_iova_cache_destroy();
 }
 
 static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index f6b17e6..520b8c8 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -18,6 +18,41 @@
  */
 
 #include <linux/iova.h>
+#include <linux/slab.h>
+
+static struct kmem_cache *iommu_iova_cache;
+
+int iommu_iova_cache_init(void)
+{
+	int ret = 0;
+
+	iommu_iova_cache = kmem_cache_create("iommu_iova",
+					 sizeof(struct iova),
+					 0,
+					 SLAB_HWCACHE_ALIGN,
+					 NULL);
+	if (!iommu_iova_cache) {
+		pr_err("Couldn't create iova cache\n");
+		ret = -ENOMEM;
+	}
+
+	return ret;
+}
+
+void iommu_iova_cache_destroy(void)
+{
+	kmem_cache_destroy(iommu_iova_cache);
+}
+
+struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
+}
+
+void free_iova_mem(struct iova *iova)
+{
+	kmem_cache_free(iommu_iova_cache, iova);
+}
 
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 19e81d5..ad0507c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -39,6 +39,9 @@ static inline unsigned long iova_size(struct iova *iova)
 	return iova->pfn_hi - iova->pfn_lo + 1;
 }
 
+int iommu_iova_cache_init(void);
+void iommu_iova_cache_destroy(void);
+
 struct iova *alloc_iova_mem(void);
 void free_iova_mem(struct iova *iova);
 void free_iova(struct iova_domain *iovad, unsigned long pfn);
-- 
1.9.1

[PATCH 3/4] iommu: make IOVA domain low limit flexible

[Robin Murphy]

To share the IOVA allocator with other architectures, it needs to
accommodate more general aperture restrictions; move the lower limit
from a compile-time constant to a runtime domain property to allow
IOVA domains with different requirements to co-exist.

Also reword the slightly unclear description of alloc_iova since we're
touching it anyway.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/iommu/intel-iommu.c |  9 ++++++---
 drivers/iommu/iova.c        | 10 ++++++----
 include/linux/iova.h        |  7 +++----
 3 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 5699653..275d056 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -71,6 +71,9 @@
 				__DOMAIN_MAX_PFN(gaw), (unsigned long)-1))
 #define DOMAIN_MAX_ADDR(gaw)	(((uint64_t)__DOMAIN_MAX_PFN(gaw)) << VTD_PAGE_SHIFT)
 
+/* IO virtual address start page frame number */
+#define IOVA_START_PFN		(1)
+
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 #define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 #define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
@@ -1632,7 +1635,7 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, IOVA_START_PFN, DMA_32BIT_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1690,7 +1693,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	int adjust_width, agaw;
 	unsigned long sagaw;
 
-	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -4321,7 +4324,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 520b8c8..a3dbba8 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -55,11 +55,13 @@ void free_iova_mem(struct iova *iova)
 }
 
 void
-init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit)
+init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
+	unsigned long pfn_32bit)
 {
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
 	iovad->cached32_node = NULL;
+	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = pfn_32bit;
 }
 
@@ -162,7 +164,7 @@ move_left:
 	if (!curr) {
 		if (size_aligned)
 			pad_size = iova_get_pad_size(size, limit_pfn);
-		if ((IOVA_START_PFN + size + pad_size) > limit_pfn) {
+		if ((iovad->start_pfn + size + pad_size) > limit_pfn) {
 			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 			return -ENOMEM;
 		}
@@ -237,8 +239,8 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
  * @size: - size of page frames to allocate
  * @limit_pfn: - max limit address
  * @size_aligned: - set if size_aligned address range is required
- * This function allocates an iova in the range limit_pfn to IOVA_START_PFN
- * looking from limit_pfn instead from IOVA_START_PFN. If the size_aligned
+ * This function allocates an iova in the range iovad->start_pfn to limit_pfn,
+ * searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
  * flag is set then the allocated address iova->pfn_lo will be naturally
  * aligned on roundup_power_of_two(size).
  */
diff --git a/include/linux/iova.h b/include/linux/iova.h
index ad0507c..591b196 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -16,9 +16,6 @@
 #include <linux/rbtree.h>
 #include <linux/dma-mapping.h>
 
-/* IO virtual address start page frame number */
-#define IOVA_START_PFN		(1)
-
 /* iova structure */
 struct iova {
 	struct rb_node	node;
@@ -31,6 +28,7 @@ struct iova_domain {
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
 	struct rb_node	*cached32_node; /* Save last alloced node */
+	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
 };
 
@@ -52,7 +50,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
 struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
 	unsigned long pfn_hi);
 void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
-void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit);
+void init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
+	unsigned long pfn_32bit);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
 struct iova *split_and_remove_iova(struct iova_domain *iovad,
-- 
1.9.1

[PATCH 4/4] iommu: make IOVA domain page size explicit

[Robin Murphy]

Systems may contain heterogeneous IOMMUs supporting differing minimum
page sizes, which may also not be common with the CPU page size.
Thus it is practical to have an explicit notion of IOVA granularity
to simplify handling of mapping and allocation constraints.

As an initial step, move the IOVA page granularity from an implicit
compile-time constant to a per-domain property so we can make use
of it in IOVA domain context at runtime. To keep the abstraction tidy,
extend the little API of inline iova_* helpers to parallel some of the
equivalent PAGE_* macros.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
 drivers/iommu/intel-iommu.c |  9 ++++++---
 drivers/iommu/iova.c        | 12 ++++++++++--
 include/linux/iova.h        | 35 +++++++++++++++++++++++++++++++++--
 3 files changed, 49 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 275d056..a0f5817 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1635,7 +1635,8 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1693,7 +1694,8 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	int adjust_width, agaw;
 	unsigned long sagaw;
 
-	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
@@ -4324,7 +4326,8 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
+			DMA_32BIT_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index a3dbba8..9dd8208 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -55,12 +55,20 @@ void free_iova_mem(struct iova *iova)
 }
 
 void
-init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
-	unsigned long pfn_32bit)
+init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn, unsigned long pfn_32bit)
 {
+	/*
+	 * IOVA granularity will normally be equal to the smallest
+	 * supported IOMMU page size; both *must* be capable of
+	 * representing individual CPU pages exactly.
+	 */
+	BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));
+
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
 	iovad->cached32_node = NULL;
+	iovad->granule = granule;
 	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = pfn_32bit;
 }
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 591b196..3920a19 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -28,6 +28,7 @@ struct iova_domain {
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
 	struct rb_node	*cached32_node; /* Save last alloced node */
+	unsigned long	granule;	/* pfn granularity for this domain */
 	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
 };
@@ -37,6 +38,36 @@ static inline unsigned long iova_size(struct iova *iova)
 	return iova->pfn_hi - iova->pfn_lo + 1;
 }
 
+static inline unsigned long iova_shift(struct iova_domain *iovad)
+{
+	return __ffs(iovad->granule);
+}
+
+static inline unsigned long iova_mask(struct iova_domain *iovad)
+{
+	return iovad->granule - 1;
+}
+
+static inline size_t iova_offset(struct iova_domain *iovad, dma_addr_t iova)
+{
+	return iova & iova_mask(iovad);
+}
+
+static inline size_t iova_align(struct iova_domain *iovad, size_t size)
+{
+	return ALIGN(size, iovad->granule);
+}
+
+static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova)
+{
+	return (dma_addr_t)iova->pfn_lo << iova_shift(iovad);
+}
+
+static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
+{
+	return iova >> iova_shift(iovad);
+}
+
 int iommu_iova_cache_init(void);
 void iommu_iova_cache_destroy(void);
 
@@ -50,8 +81,8 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
 struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
 	unsigned long pfn_hi);
 void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
-void init_iova_domain(struct iova_domain *iovad, unsigned long start_pfn,
-	unsigned long pfn_32bit);
+void init_iova_domain(struct iova_domain *iovad, unsigned long granule,
+	unsigned long start_pfn, unsigned long pfn_32bit);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
 struct iova *split_and_remove_iova(struct iova_domain *iovad,
-- 
1.9.1

[PATCH 0/4] Genericise the IOVA allocator

[Joerg Roedel]

On Mon, Jan 12, 2015 at 05:51:12PM +0000, Robin Murphy wrote:
> Robin Murphy (4):
>   iommu: allow building iova.c independently
>   iommu: consolidate IOVA allocator code
>   iommu: make IOVA domain low limit flexible
>   iommu: make IOVA domain page size explicit

Applied to core, thanks Robin.