[dpdk-dev] [PATCH v4 3/5] 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 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.

This patch adds an address hint as starting address for 64 bits
systems.

Applicable to v17.11.3 only.

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
---
 lib/librte_eal/linuxapp/eal/eal_memory.c | 55 ++++++++++++++++++++++++++------
 1 file changed, 46 insertions(+), 9 deletions(-)

diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index 17c20d4..2ed4017 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -88,6 +88,23 @@
 
 static uint64_t baseaddr_offset;
 
+#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_dev_check_dma_mask for ensuring all
+ * memory is within supported range.
+ */
+static uint64_t baseaddr = 0x100000000;
+#endif
+
 static bool phys_addrs_available = true;
 
 #define RANDOMIZE_VA_SPACE_FILE "/proc/sys/kernel/randomize_va_space"
@@ -250,6 +267,23 @@
 	}
 }
 
+static void *
+get_addr_hint(void)
+{
+	if (internal_config.base_virtaddr != 0) {
+		return (void *) (uintptr_t)
+			    (internal_config.base_virtaddr +
+			     baseaddr_offset);
+	} else {
+#ifdef RTE_ARCH_64
+		return (void *) (uintptr_t) (baseaddr +
+				baseaddr_offset);
+#else
+		return NULL;
+#endif
+	}
+}
+
 /*
  * Try to mmap *size bytes in /dev/zero. If it is successful, return the
  * pointer to the mmap'd area and keep *size unmodified. Else, retry
@@ -260,16 +294,10 @@
 static void *
 get_virtual_area(size_t *size, size_t hugepage_sz)
 {
-	void *addr;
+	void *addr, *addr_hint;
 	int fd;
 	long aligned_addr;
 
-	if (internal_config.base_virtaddr != 0) {
-		addr = (void*) (uintptr_t) (internal_config.base_virtaddr +
-				baseaddr_offset);
-	}
-	else addr = NULL;
-
 	RTE_LOG(DEBUG, EAL, "Ask a virtual area of 0x%zx bytes\n", *size);
 
 	fd = open("/dev/zero", O_RDONLY);
@@ -278,7 +306,9 @@
 		return NULL;
 	}
 	do {
-		addr = mmap(addr,
+		addr_hint = get_addr_hint();
+
+		addr = mmap(addr_hint,
 				(*size) + hugepage_sz, PROT_READ,
 #ifdef RTE_ARCH_PPC_64
 				MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
@@ -286,8 +316,15 @@
 				MAP_PRIVATE,
 #endif
 				fd, 0);
-		if (addr == MAP_FAILED)
+		if (addr == MAP_FAILED) {
+			/* map failed. Let's try with less memory */
 			*size -= hugepage_sz;
+		} else if (addr_hint && addr != addr_hint) {
+			/* hint was not used. Try with another offset */
+			munmap(addr, (*size) + hugepage_sz);
+			addr = MAP_FAILED;
+			baseaddr_offset += 0x100000000;
+		}
 	} while (addr == MAP_FAILED && *size > 0);
 
 	if (addr == MAP_FAILED) {
-- 
1.9.1