[dpdk-dev] [PATCH v2 2/6] mem: use address hint for mapping hugepages

[Alejandro Lucero <alejandro.lucero@netronome.com>]

Linux kernel uses a really high address as starting address for
serving mmaps calls. If there exist addressing limitations and
IOVA mode is VA, this starting address is likely too high for
those devices. However, it is possible to use a lower address in
the process virtual address space as with 64 bits there is a lot
of available space.

This patch adds an address hint as starting address for 64 bits
systems and increments the hint for next invocations. If the mmap
call does not use the hint address, repeat the mmap call using
the hint address incremented by page size.

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
---
 lib/librte_eal/common/eal_common_memory.c | 34 ++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index 7555e76..366e454 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -37,6 +37,23 @@
 static void *next_baseaddr;
 static uint64_t system_page_sz;
 
+#ifdef RTE_ARCH_64
+/*
+ * Linux kernel uses a really high address as starting address for serving
+ * mmaps calls. If there exists addressing limitations and IOVA mode is VA,
+ * this starting address is likely too high for those devices. However, it
+ * is possible to use a lower address in the process virtual address space
+ * as with 64 bits there is a lot of available space.
+ *
+ * Current known limitations are 39 or 40 bits. Setting the starting address
+ * at 4GB implies there are 508GB or 1020GB for mapping the available
+ * hugepages. This is likely enough for most systems, although a device with
+ * addressing limitations should call rte_eal_check_dma_mask for ensuring all
+ * memory is within supported range.
+ */
+static uint64_t baseaddr = 0x100000000;
+#endif
+
 void *
 eal_get_virtual_area(void *requested_addr, size_t *size,
 		size_t page_sz, int flags, int mmap_flags)
@@ -60,6 +77,11 @@
 			rte_eal_process_type() == RTE_PROC_PRIMARY)
 		next_baseaddr = (void *) internal_config.base_virtaddr;
 
+#ifdef RTE_ARCH_64
+	if (next_baseaddr == NULL && internal_config.base_virtaddr == 0 &&
+			rte_eal_process_type() == RTE_PROC_PRIMARY)
+		next_baseaddr = (void *) baseaddr;
+#endif
 	if (requested_addr == NULL && next_baseaddr != NULL) {
 		requested_addr = next_baseaddr;
 		requested_addr = RTE_PTR_ALIGN(requested_addr, page_sz);
@@ -91,7 +113,17 @@
 				mmap_flags, -1, 0);
 		if (mapped_addr == MAP_FAILED && allow_shrink)
 			*size -= page_sz;
-	} while (allow_shrink && mapped_addr == MAP_FAILED && *size > 0);
+
+		if (mapped_addr != MAP_FAILED && addr_is_hint &&
+		    mapped_addr != requested_addr) {
+			/* hint was not used. Try with another offset */
+			munmap(mapped_addr, map_sz);
+			mapped_addr = MAP_FAILED;
+			next_baseaddr = RTE_PTR_ADD(next_baseaddr, page_sz);
+			requested_addr = next_baseaddr;
+		}
+	} while ((allow_shrink || addr_is_hint) &&
+		 mapped_addr == MAP_FAILED && *size > 0);
 
 	/* align resulting address - if map failed, we will ignore the value
 	 * anyway, so no need to add additional checks.
-- 
1.9.1