iommu/iova: introduce per-cpu caching to iova allocation

IOVA allocation has two problems that impede high-throughput I/O.
First, it can do a linear search over the allocated IOVA ranges.
Second, the rbtree spinlock that serializes IOVA allocations becomes
contended.

Address these problems by creating an API for caching allocated IOVA
ranges, so that the IOVA allocator isn't accessed frequently.  This
patch adds a per-CPU cache, from which CPUs can alloc/free IOVAs
without taking the rbtree spinlock.  The per-CPU caches are backed by
a global cache, to avoid invoking the (linear-time) IOVA allocator
without needing to make the per-CPU cache size excessive.  This design
is based on magazines, as described in "Magazines and Vmem: Extending
the Slab Allocator to Many CPUs and Arbitrary Resources" (currently
available at https://www.usenix.org/legacy/event/usenix01/bonwick.html)

Adding caching on top of the existing rbtree allocator maintains the
property that IOVAs are densely packed in the IO virtual address space,
which is important for keeping IOMMU page table usage low.

To keep the cache size reasonable, we bound the IOVA space a CPU can
cache by 32 MiB (we cache a bounded number of IOVA ranges, and only
ranges of size <= 128 KiB).  The shared global cache is bounded at
4 MiB of IOVA space.

Signed-off-by: Omer Peleg <omer@cs.technion.ac.il>
[mad@cs.technion.ac.il: rebased, cleaned up and reworded the commit message]
Signed-off-by: Adam Morrison <mad@cs.technion.ac.il>
Reviewed-by: Shaohua Li <shli@fb.com>
Reviewed-by: Ben Serebrin <serebrin@google.com>
[dwmw2: split out VT-d part into a separate patch]
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

1 files changed, 21 insertions, 2 deletions

diff --git a/include/linux/iova.h b/include/linux/iova.h
index 92f7177..f27bb2c 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -19,8 +19,21 @@
 /* iova structure */
 struct iova {
 	struct rb_node	node;
-	unsigned long	pfn_hi; /* IOMMU dish out addr hi */
-	unsigned long	pfn_lo; /* IOMMU dish out addr lo */
+	unsigned long	pfn_hi; /* Highest allocated pfn */
+	unsigned long	pfn_lo; /* Lowest allocated pfn */
+};
+
+struct iova_magazine;
+struct iova_cpu_rcache;
+
+#define IOVA_RANGE_CACHE_MAX_SIZE 6	/* log of max cached IOVA range size (in pages) */
+#define MAX_GLOBAL_MAGS 32	/* magazines per bin */
+
+struct iova_rcache {
+	spinlock_t lock;
+	unsigned long depot_size;
+	struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+	struct iova_cpu_rcache __percpu *cpu_rcaches;
 };
 
 /* holds all the iova translations for a domain */
@@ -31,6 +44,7 @@ struct iova_domain {
 	unsigned long	granule;	/* pfn granularity for this domain */
 	unsigned long	start_pfn;	/* Lower limit for this domain */
 	unsigned long	dma_32bit_pfn;
+	struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE];	/* IOVA range caches */
 };
 
 static inline unsigned long iova_size(struct iova *iova)
@@ -78,6 +92,10 @@ void __free_iova(struct iova_domain *iovad, struct iova *iova);
 struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
 	unsigned long limit_pfn,
 	bool size_aligned);
+void free_iova_fast(struct iova_domain *iovad, unsigned long pfn,
+		    unsigned long size);
+unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
+			      unsigned long limit_pfn);
 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);
@@ -87,5 +105,6 @@ 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,
 	struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi);
+void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 
 #endif