[dpdk-dev] [PATCH] eal/ppc: fix secondary process to map hugepages in correct order

[Gowrishankar]

From: Gowri Shankar <gowrishankar.m at linux.vnet.ibm.com>

For a secondary process address space to map hugepages from every segment of
primary process, hugepage_file entries has to be mapped reversely from the
list that primary process updated for every segment. This is for a reason that,
in ppc64, hugepages are sorted for decrementing addresses.

Signed-off-by: Gowrishankar <gowrishankar.m at linux.vnet.ibm.com>
---
 lib/librte_eal/linuxapp/eal/eal_memory.c |   26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index 5b9132c..6aea5d0 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -1400,7 +1400,7 @@ rte_eal_hugepage_attach(void)
 {
 	const struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
 	const struct hugepage_file *hp = NULL;
-	unsigned num_hp = 0;
+	unsigned num_hp = 0, mapped_hp = 0;
 	unsigned i, s = 0; /* s used to track the segment number */
 	off_t size;
 	int fd, fd_zero = -1, fd_hugepage = -1;
@@ -1486,14 +1486,12 @@ rte_eal_hugepage_attach(void)
 		goto error;
 	}
 
-	num_hp = size / sizeof(struct hugepage_file);
-	RTE_LOG(DEBUG, EAL, "Analysing %u files\n", num_hp);
-
 	s = 0;
 	while (s < RTE_MAX_MEMSEG && mcfg->memseg[s].len > 0){
 		void *addr, *base_addr;
 		uintptr_t offset = 0;
 		size_t mapping_size;
+		unsigned int index;
 #ifdef RTE_LIBRTE_IVSHMEM
 		/*
 		 * if segment has ioremap address set, it's an IVSHMEM segment and
@@ -1504,6 +1502,8 @@ rte_eal_hugepage_attach(void)
 			continue;
 		}
 #endif
+		num_hp = mcfg->memseg[s].len / mcfg->memseg[s].hugepage_sz;
+		RTE_LOG(DEBUG, EAL, "Analysing %u files in segment %u\n", num_hp, s);
 		/*
 		 * free previously mapped memory so we can map the
 		 * hugepages into the space
@@ -1514,18 +1514,23 @@ rte_eal_hugepage_attach(void)
 		/* find the hugepages for this segment and map them
 		 * we don't need to worry about order, as the server sorted the
 		 * entries before it did the second mmap of them */
+#ifdef RTE_ARCH_PPC_64
+		for (i = num_hp-1; i < num_hp && offset < mcfg->memseg[s].len; i--){
+#else
 		for (i = 0; i < num_hp && offset < mcfg->memseg[s].len; i++){
-			if (hp[i].memseg_id == (int)s){
-				fd = open(hp[i].filepath, O_RDWR);
+#endif
+			index = i + mapped_hp;
+			if (hp[index].memseg_id == (int)s){
+				fd = open(hp[index].filepath, O_RDWR);
 				if (fd < 0) {
 					RTE_LOG(ERR, EAL, "Could not open %s\n",
-						hp[i].filepath);
+						hp[index].filepath);
 					goto error;
 				}
 #ifdef RTE_EAL_SINGLE_FILE_SEGMENTS
-				mapping_size = hp[i].size * hp[i].repeated;
+				mapping_size = hp[index].size * hp[index].repeated;
 #else
-				mapping_size = hp[i].size;
+				mapping_size = hp[index].size;
 #endif
 				addr = mmap(RTE_PTR_ADD(base_addr, offset),
 						mapping_size, PROT_READ | PROT_WRITE,
@@ -1534,7 +1539,7 @@ rte_eal_hugepage_attach(void)
 				if (addr == MAP_FAILED ||
 						addr != RTE_PTR_ADD(base_addr, offset)) {
 					RTE_LOG(ERR, EAL, "Could not mmap %s\n",
-						hp[i].filepath);
+						hp[index].filepath);
 					goto error;
 				}
 				offset+=mapping_size;
@@ -1543,6 +1548,7 @@ rte_eal_hugepage_attach(void)
 		RTE_LOG(DEBUG, EAL, "Mapped segment %u of size 0x%llx\n", s,
 				(unsigned long long)mcfg->memseg[s].len);
 		s++;
+		mapped_hp += num_hp;
 	}
 	/* unmap the hugepage config file, since we are done using it */
 	munmap((void *)(uintptr_t)hp, size);
-- 
1.7.10.4