Break up monolithic iommu table/lock into finer graularity pools and lock

Investigation of multithreaded iperf experiments on an ethernet
interface show the iommu->lock as the hottest lock identified by
lockstat, with something of the order of  21M contentions out of
27M acquisitions, and an average wait time of 26 us for the lock.
This is not efficient. A more scalable design is to follow the ppc
model, where the iommu_map_table has multiple pools, each stretching
over a segment of the map, and with a separate lock for each pool.
This model allows for better parallelization of the iommu map search.

This patch adds the iommu range alloc/free function infrastructure.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 51 insertions, 0 deletions

diff --git a/include/linux/iommu-common.h b/include/linux/iommu-common.h
new file mode 100644
index 000000000000..bbced83b32ee
--- /dev/null
+++ b/include/linux/iommu-common.h
@@ -0,0 +1,51 @@
+#ifndef _LINUX_IOMMU_COMMON_H
+#define _LINUX_IOMMU_COMMON_H
+
+#include <linux/spinlock_types.h>
+#include <linux/device.h>
+#include <asm/page.h>
+
+#define IOMMU_POOL_HASHBITS     4
+#define IOMMU_NR_POOLS          (1 << IOMMU_POOL_HASHBITS)
+
+struct iommu_pool {
+	unsigned long	start;
+	unsigned long	end;
+	unsigned long	hint;
+	spinlock_t	lock;
+};
+
+struct iommu_map_table {
+	unsigned long		table_map_base;
+	unsigned long		table_shift;
+	unsigned long		nr_pools;
+	void			(*lazy_flush)(struct iommu_map_table *);
+	unsigned long		poolsize;
+	struct iommu_pool	pools[IOMMU_NR_POOLS];
+	u32			flags;
+#define	IOMMU_HAS_LARGE_POOL	0x00000001
+#define	IOMMU_NO_SPAN_BOUND	0x00000002
+#define	IOMMU_NEED_FLUSH	0x00000004
+	struct iommu_pool	large_pool;
+	unsigned long		*map;
+};
+
+extern void iommu_tbl_pool_init(struct iommu_map_table *iommu,
+				unsigned long num_entries,
+				u32 table_shift,
+				void (*lazy_flush)(struct iommu_map_table *),
+				bool large_pool, u32 npools,
+				bool skip_span_boundary_check);
+
+extern unsigned long iommu_tbl_range_alloc(struct device *dev,
+					   struct iommu_map_table *iommu,
+					   unsigned long npages,
+					   unsigned long *handle,
+					   unsigned long mask,
+					   unsigned int align_order);
+
+extern void iommu_tbl_range_free(struct iommu_map_table *iommu,
+				 u64 dma_addr, unsigned long npages,
+				 unsigned long entry);
+
+#endif