[dpdk-dev] [PATCH v2] eal: use madvise to exclude unmapped memory from being dumped

[Li Feng]

Currently, even though memory is mapped with PROT_NONE, this does not
cause it to be excluded from core dumps. This is counter-productive,
because in a lot of cases, this memory will go unused (e.g. when the
memory subsystem preallocates VA space but hasn't yet mapped physical
pages into it).

Use `madvise()` call with MADV_DONTDUMP parameter to exclude the
unmapped memory from being dumped.

Signed-off-by: Li Feng <fen...@smartx.com>
---
V2:
- add support for freebsd.
- when free_seg is called, mark the memory MADV_DONTDUMP.
- when alloc_seg is called, mark the memory MADV_DODUMP.

 lib/librte_eal/common/eal_common_memory.c | 26 ++++++++++++++++++++++++++
 lib/librte_eal/linux/eal_memalloc.c       |  6 ++++++
 2 files changed, 32 insertions(+)

diff --git a/lib/librte_eal/common/eal_common_memory.c 
b/lib/librte_eal/common/eal_common_memory.c
index cc7d54e0c..83be94a20 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -177,6 +177,32 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
                after_len = RTE_PTR_DIFF(map_end, aligned_end);
                if (after_len > 0)
                        munmap(aligned_end, after_len);
+
+               /*
+                * Exclude this pages from a core dump.
+                */
+#ifdef RTE_EXEC_ENV_LINUX
+               if (madvise(aligned_addr, *size, MADV_DONTDUMP) != 0)
+                       RTE_LOG(DEBUG, EAL, "madvise failed: %s\n",
+                               strerror(errno));
+#elif RTE_EXEC_ENV_FREEBSD
+               if (madvise(aligned_addr, *size, MADV_NOCORE) != 0)
+                       RTE_LOG(DEBUG, EAL, "madvise failed: %s\n",
+                               strerror(errno));
+#endif
+       } else {
+               /*
+                * Exclude this pages from a core dump.
+                */
+#ifdef RTE_EXEC_ENV_LINUX
+               if (madvise(mapped_addr, map_sz, MADV_DONTDUMP) != 0)
+                       RTE_LOG(DEBUG, EAL, "madvise failed: %s\n",
+                               strerror(errno));
+#elif RTE_EXEC_ENV_FREEBSD
+               if (madvise(mapped_addr, map_sz, MADV_NOCORE) != 0)
+                       RTE_LOG(DEBUG, EAL, "madvise failed: %s\n",
+                               strerror(errno));
+#endif
        }
 
        return aligned_addr;
diff --git a/lib/librte_eal/linux/eal_memalloc.c 
b/lib/librte_eal/linux/eal_memalloc.c
index af6d0d023..9d2a6fc6f 100644
--- a/lib/librte_eal/linux/eal_memalloc.c
+++ b/lib/librte_eal/linux/eal_memalloc.c
@@ -571,6 +571,9 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
                goto resized;
        }
 
+       if (madvise(addr, alloc_sz, MADV_DODUMP) != 0)
+               RTE_LOG(DEBUG, EAL, "madvise failed: %s\n", strerror(errno));
+
        /* In linux, hugetlb limitations, like cgroup, are
         * enforced at fault time instead of mmap(), even
         * with the option of MAP_POPULATE. Kernel will send
@@ -687,6 +690,9 @@ free_seg(struct rte_memseg *ms, struct hugepage_info *hi,
                return -1;
        }
 
+       if (madvise(ms->addr, ms->len, MADV_DONTDUMP) != 0)
+               RTE_LOG(DEBUG, EAL, "madvise failed: %s\n", strerror(errno));
+
        exit_early = false;
 
        /* if we're using anonymous hugepages, nothing to be done */
-- 
2.11.0


-- 
The SmartX email address is only for business purpose. Any sent message 
that is not related to the business is not authorized or permitted by 
SmartX.
本邮箱为北京志凌海纳科技有限公司（SmartX）工作邮箱. 如本邮箱发出的邮件与工作无关,该邮件未得到本公司任何的明示或默示的授权.