[dpdk-dev] [PATCH 2/2] mem: fix mempool for --no-huge

Damien Millescamps damien.millescamps at 6wind.com
Fri Jul 26 16:39:13 CEST 2013


In --no-huge mode, mempool provides objects with their associated
header/trailer fitting in a standard page (usually 4KB).
This means all non-UIO driver should work correctly in this mode,
since UIO drivers allocate ring sizes that cannot fit in a page.

Extend rte_mempool_virt2phy to obtain the correct physical address when
elements of the pool are not on the same physically contiguous memory region.
This is a first step for enhancement PR #29696.

Reason for this patch is to be able to run on a kernel < 2.6.37 without
the need to patch it, since all kernel below are either bugged or don't
have huge page support at all (< 2.6.28).

Signed-off-by: Damien Millescamps <damien.millescamps at 6wind.com>
---
 lib/librte_eal/linuxapp/eal/eal_memory.c |    2 +-
 lib/librte_mempool/rte_mempool.c         |   54 +++++++++++++++++++++++++++++-
 lib/librte_mempool/rte_mempool.h         |   20 +++++++----
 3 files changed, 67 insertions(+), 9 deletions(-)

diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index ce0c2d8..00b5952 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -780,7 +780,7 @@ rte_eal_hugepage_init(void)
 	/* get pointer to global configuration */
 	mcfg = rte_eal_get_configuration()->mem_config;
 
-	/* for debug purposes, hugetlbfs can be disabled */
+	/* hugetlbfs can be disabled */
 	if (internal_config.no_hugetlbfs) {
 		addr = malloc(internal_config.memory);
 		mcfg->memseg[0].phys_addr = (phys_addr_t)(uintptr_t)addr;
diff --git a/lib/librte_mempool/rte_mempool.c b/lib/librte_mempool/rte_mempool.c
index aa8e76a..87183df 100644
--- a/lib/librte_mempool/rte_mempool.c
+++ b/lib/librte_mempool/rte_mempool.c
@@ -36,6 +36,7 @@
 #include <string.h>
 #include <stdint.h>
 #include <stdarg.h>
+#include <unistd.h>
 #include <inttypes.h>
 #include <errno.h>
 #include <sys/queue.h>
@@ -139,6 +140,8 @@ rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
 	uint32_t header_size, trailer_size;
 	unsigned i;
 	void *obj;
+	void *startaddr;
+	int page_size = getpagesize();
 
 	/* compilation-time checks */
 	RTE_BUILD_BUG_ON((sizeof(struct rte_mempool) &
@@ -227,6 +230,20 @@ rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
 						trailer_size);
 		trailer_size = new_size - header_size - elt_size;
 	}
+	if (! rte_eal_has_hugepages()) {
+		/*
+		 * compute trailer size so that pool elements fit exactly in
+		 * a standard page
+		 */
+		int new_size = page_size - header_size - elt_size;
+		if (new_size < 0 || (unsigned int)new_size < trailer_size) {
+			printf("When hugepages are disabled, pool objects "
+			       "can't exceed PAGE_SIZE: %d + %d + %d > %d\n",
+			       header_size, elt_size, trailer_size, page_size);
+			return NULL;
+		}
+		trailer_size = new_size;
+	}
 
 	/* this is the size of an object, including header and trailer */
 	total_elt_size = header_size + elt_size + trailer_size;
@@ -235,8 +252,31 @@ rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
 	 * cache-aligned */
 	private_data_size = (private_data_size +
 			     CACHE_LINE_MASK) & (~CACHE_LINE_MASK);
+
+	if (! rte_eal_has_hugepages()) {
+		/*
+		 * expand private data size to a whole page, so that the
+		 * first pool element will start on a new standard page
+		 */
+		int head = sizeof(struct rte_mempool);
+		int new_size = (private_data_size + head) % page_size;
+		if (new_size) {
+			private_data_size += page_size - new_size;
+		}
+	}
+
 	mempool_size = total_elt_size * n +
 		sizeof(struct rte_mempool) + private_data_size;
+
+	if (! rte_eal_has_hugepages()) {
+		/*
+		 * we want the memory pool to start on a page boundary,
+		 * because pool elements crossing page boundaries would
+		 * result in discontiguous physical addresses
+		 */
+		mempool_size += page_size;
+	}
+
 	rte_snprintf(mz_name, sizeof(mz_name), "MP_%s", name);
 
 	mz = rte_memzone_reserve(mz_name, mempool_size, socket_id, mz_flags);
@@ -248,8 +288,20 @@ rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
 	if (mz == NULL)
 		goto exit;
 
+	if (rte_eal_has_hugepages()) {
+		startaddr = (void*)mz->addr;
+	} else {
+		/* align memory pool start address on a page boundary */
+		unsigned long addr = (unsigned long)mz->addr;
+		if (addr & (page_size - 1)) {
+			addr += page_size;
+			addr &= ~(page_size - 1);
+		}
+		startaddr = (void*)addr;
+	}
+
 	/* init the mempool structure */
-	mp = mz->addr;
+	mp = startaddr;
 	memset(mp, 0, sizeof(*mp));
 	rte_snprintf(mp->name, sizeof(mp->name), "%s", name);
 	mp->phys_addr = mz->phys_addr;
diff --git a/lib/librte_mempool/rte_mempool.h b/lib/librte_mempool/rte_mempool.h
index 67d7f09..33ce35c 100644
--- a/lib/librte_mempool/rte_mempool.h
+++ b/lib/librte_mempool/rte_mempool.h
@@ -950,16 +950,22 @@ rte_mempool_empty(const struct rte_mempool *mp)
  * @return
  *   The physical address of the elt element.
  */
-static inline phys_addr_t rte_mempool_virt2phy(const struct rte_mempool *mp,
-	const void *elt)
+static inline phys_addr_t
+rte_mempool_virt2phy(const struct rte_mempool *mp, const void *elt)
 {
-	uintptr_t off;
-
-	off = (const char *)elt - (const char *)mp;
-	return mp->phys_addr + off;
+	if (rte_eal_has_hugepages()) {
+		uintptr_t offset = (const char *)elt - (const char *)mp;
+		return mp->phys_addr + offset;
+	} else {
+		/*
+		 * If huge pages are disabled, we cannot assume the
+		 * memory region to be physically contiguous.
+		 * Lookup for each element.
+		 */
+		return rte_mem_virt2phy(elt);
+	}
 }
 
-
 /**
  * Check the consistency of mempool objects.
  *
-- 
1.7.2.5



More information about the dev mailing list