[dpdk-dev] [PATCH v3 68/68] eal: prevent preallocated pages from being freed

[Anatoly Burakov]

It is common sense to expect for DPDK process to not deallocate any
pages that were preallocated by "-m" or "--socket-mem" flags - yet,
currently, DPDK memory subsystem will do exactly that once it finds
that the pages are unused.

Fix this by marking pages as unfreebale, and preventing malloc from
ever trying to free them.

Signed-off-by: Anatoly Burakov <anatoly.burakov at intel.com>
---
 lib/librte_eal/common/include/rte_memory.h |  3 +++
 lib/librte_eal/common/malloc_heap.c        | 23 +++++++++++++++++++++++
 lib/librte_eal/linuxapp/eal/eal_memalloc.c |  7 +++++++
 lib/librte_eal/linuxapp/eal/eal_memory.c   | 18 +++++++++++++++---
 4 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/lib/librte_eal/common/include/rte_memory.h b/lib/librte_eal/common/include/rte_memory.h
index 0318bfe..58b607b 100644
--- a/lib/librte_eal/common/include/rte_memory.h
+++ b/lib/librte_eal/common/include/rte_memory.h
@@ -83,6 +83,8 @@ typedef uint64_t rte_iova_t;
 /**
  * Physical memory segment descriptor.
  */
+#define RTE_MEMSEG_FLAG_DO_NOT_FREE (1 << 0)
+/**< Prevent this segment from being freed back to the OS. */
 struct rte_memseg {
 	RTE_STD_C11
 	union {
@@ -99,6 +101,7 @@ struct rte_memseg {
 	int32_t socket_id;          /**< NUMA socket ID. */
 	uint32_t nchannel;          /**< Number of channels. */
 	uint32_t nrank;             /**< Number of ranks. */
+	uint32_t flags;             /**< Memseg-specific flags */
 } __rte_packed;
 
 /**
diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c
index f8daf84..41c14a8 100644
--- a/lib/librte_eal/common/malloc_heap.c
+++ b/lib/librte_eal/common/malloc_heap.c
@@ -606,6 +606,7 @@ malloc_heap_free(struct malloc_elem *elem)
 	void *start, *aligned_start, *end, *aligned_end;
 	size_t len, aligned_len, page_sz;
 	struct rte_memseg_list *msl;
+	unsigned int i, n_segs;
 	int ret;
 
 	if (!malloc_elem_cookies_ok(elem) || elem->state != ELEM_BUSY)
@@ -647,6 +648,28 @@ malloc_heap_free(struct malloc_elem *elem)
 	if (aligned_len < page_sz)
 		goto free_unlock;
 
+	/* we can free something. however, some of these pages may be marked as
+	 * unfreeable, so also check that as well
+	 */
+	n_segs = aligned_len / page_sz;
+	for (i = 0; i < n_segs; i++) {
+		const struct rte_memseg *tmp =
+				rte_mem_virt2memseg(aligned_start, msl);
+
+		if (tmp->flags & RTE_MEMSEG_FLAG_DO_NOT_FREE) {
+			/* this is an unfreeable segment, so move start */
+			aligned_start = RTE_PTR_ADD(tmp->addr, tmp->len);
+		}
+	}
+
+	/* recalculate length and number of segments */
+	aligned_len = RTE_PTR_DIFF(aligned_end, aligned_start);
+	n_segs = aligned_len / page_sz;
+
+	/* check if we can still free some pages */
+	if (n_segs == 0)
+		goto free_unlock;
+
 	rte_rwlock_write_lock(&mcfg->memory_hotplug_lock);
 
 	/*
diff --git a/lib/librte_eal/linuxapp/eal/eal_memalloc.c b/lib/librte_eal/linuxapp/eal/eal_memalloc.c
index 87c1bdb..0da2e3c 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memalloc.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memalloc.c
@@ -806,6 +806,13 @@ eal_memalloc_free_seg_bulk(struct rte_memseg **ms, int n_segs)
 		struct free_walk_param wa;
 		int i, walk_res;
 
+		/* if this page is marked as unfreeable, fail */
+		if (cur->flags & RTE_MEMSEG_FLAG_DO_NOT_FREE) {
+			RTE_LOG(DEBUG, EAL, "Page is not allowed to be freed\n");
+			ret = -1;
+			continue;
+		}
+
 		memset(&wa, 0, sizeof(wa));
 
 		for (i = 0; i < (int)RTE_DIM(internal_config.hugepage_info);
diff --git a/lib/librte_eal/linuxapp/eal/eal_memory.c b/lib/librte_eal/linuxapp/eal/eal_memory.c
index 7ec7129..2bd9c30 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -1637,21 +1637,33 @@ eal_hugepage_init(void)
 			hp_sz_idx++) {
 		for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES;
 				socket_id++) {
+			struct rte_memseg **pages;
 			struct hugepage_info *hpi = &used_hp[hp_sz_idx];
 			unsigned int num_pages = hpi->num_pages[socket_id];
-			int num_pages_alloc;
+			int num_pages_alloc, i;
 
 			if (num_pages == 0)
 				continue;
 
+			pages = malloc(sizeof(*pages) * num_pages);
+
 			RTE_LOG(DEBUG, EAL, "Allocating %u pages of size %" PRIu64 "M on socket %i\n",
 				num_pages, hpi->hugepage_sz >> 20, socket_id);
 
-			num_pages_alloc = eal_memalloc_alloc_seg_bulk(NULL,
+			num_pages_alloc = eal_memalloc_alloc_seg_bulk(pages,
 					num_pages, hpi->hugepage_sz,
 					socket_id, true);
-			if (num_pages_alloc < 0)
+			if (num_pages_alloc < 0) {
+				free(pages);
 				return -1;
+			}
+
+			/* mark preallocated pages as unfreeable */
+			for (i = 0; i < num_pages_alloc; i++) {
+				struct rte_memseg *ms = pages[i];
+				ms->flags |= RTE_MEMSEG_FLAG_DO_NOT_FREE;
+			}
+			free(pages);
 		}
 	}
 	return 0;
-- 
2.7.4