This helper iterates through the SG list to find the best page size to use
from a bitmap of HW supported page sizes. Drivers that support multiple
page sizes, but not mixed pages in an MR can use this API.
Suggested-by: Jason Gunthorpe <jgg@xxxxxxxx>
Reviewed-by: Michael J. Ruhl <michael.j.ruhl@xxxxxxxxx>
Signed-off-by: Shiraz Saleem <shiraz.saleem@xxxxxxxxx>
---
drivers/infiniband/core/umem.c | 86 ++++++++++++++++++++++++++++++++++++++++++
include/rdma/ib_umem.h | 9 +++++
2 files changed, 95 insertions(+)
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 64bacc5..b2f2d75 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -119,6 +119,92 @@ static void ib_umem_add_sg_table(struct scatterlist **cur,
}
/**
+ * ib_umem_find_pg_bit - Find the page bit to use for phyaddr
+ *
+ * @phyaddr: Physical address after DMA translation
+ * @supported_pgsz: bitmask of HW supported page sizes
+ */
+static unsigned int ib_umem_find_pg_bit(unsigned long phyaddr,
+ unsigned long supported_pgsz)
+{
+ unsigned long num_zeroes;
+ unsigned long pgsz;
+
+ /* Trailing zero bits in the address */
+ num_zeroes = __ffs(phyaddr);
+
+ /* Find page bit such that phyaddr is aligned to the highest supported
+ * HW page size
+ */
+ pgsz = supported_pgsz & (BIT_ULL(num_zeroes + 1) - 1);
+ if (!pgsz)
+ return __ffs(supported_pgsz);
+
+ return (fls64(pgsz) - 1);
+}
+
+/**
+ * ib_umem_find_single_pg_size - Find best HW page size to use for this MR
+ * @umem: umem struct
+ * @supported_pgsz: bitmask of HW supported page sizes
+ * @uvirt_addr: user-space virtual MR base address
+ *
+ * This helper is intended for HW that support multiple page
+ * sizes but can do only a single page size in an MR.
+ */
+unsigned long ib_umem_find_single_pg_size(struct ib_umem *umem,
+ unsigned long supported_pgsz,
+ unsigned long uvirt_addr)
+{
+ struct scatterlist *sg;
+ unsigned int pg_bit_sg, min_pg_bit, best_pg_bit;
+ int i;
+
+ if (!supported_pgsz)
+ return 0;
+
+ min_pg_bit = __ffs(supported_pgsz);
+ best_pg_bit = fls64(supported_pgsz) - 1;
+
+ for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i) {
+ unsigned long dma_addr_start, dma_addr_end;
+
+ dma_addr_start = sg_dma_address(sg);
+ dma_addr_end = sg_dma_address(sg) + sg_dma_len(sg);
+ if (!i) {
+ pg_bit_sg = ib_umem_find_pg_bit(dma_addr_end, supported_pgsz);
+
+ /* The start offset of the MR into a first _large_ page
+ * should line up exactly for the user-space virtual buf
+ * and physical buffer, in order to upgrade the page bit
+ */
+ if (pg_bit_sg > PAGE_SHIFT) {
+ unsigned int uvirt_pg_bit;
+
+ uvirt_pg_bit = ib_umem_find_pg_bit(uvirt_addr + sg_dma_len(sg),
+ supported_pgsz);
+ pg_bit_sg = min_t(unsigned int, uvirt_pg_bit, pg_bit_sg);
+ }
+ } else if (i == (umem->nmap - 1)) {
+ /* last SGE: Does not matter if MR ends at an
+ * unaligned offset.
+ */
+ pg_bit_sg = ib_umem_find_pg_bit(dma_addr_start, supported_pgsz);
+ } else {
+ pg_bit_sg = ib_umem_find_pg_bit(dma_addr_start,
+ supported_pgsz & (BIT_ULL(__ffs(sg_dma_len(sg)) + 1) - 1));
+ }
+
+ best_pg_bit = min_t(unsigned int, best_pg_bit, pg_bit_sg);
+ if (best_pg_bit == min_pg_bit)
+ break;
+ }
+
+ return BIT_ULL(best_pg_bit);
+}
+EXPORT_SYMBOL(ib_umem_find_single_pg_size);
+
+/**
* ib_umem_get - Pin and DMA map userspace memory.
*
* If access flags indicate ODP memory, avoid pinning. Instead, stores
diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 5d3755e..3e8e1ed 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -86,6 +86,9 @@ void ib_umem_release(struct ib_umem *umem);
int ib_umem_page_count(struct ib_umem *umem);
int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
size_t length);
+unsigned long ib_umem_find_single_pg_size(struct ib_umem *umem,
+ unsigned long supported_pgsz,
+ unsigned long uvirt_addr);
#else /* CONFIG_INFINIBAND_USER_MEM */
@@ -102,6 +105,12 @@ static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offs
size_t length) {
return -EINVAL;
}
+static inline int ib_umem_find_single_pg_size(struct ib_umem *umem,
+ unsigned long supported_pgsz,
+ unsigned long uvirt_addr) {
+ return -EINVAL;
+}
+
#endif /* CONFIG_INFINIBAND_USER_MEM */
#endif /* IB_UMEM_H */
--
2.8.3
