[dpdk-dev] [PATCH v2 7/9] mem: add external API to retrieve page fd from EAL

[Anatoly Burakov <anatoly.burakov@intel.com>]

Now that we can retrieve page fd's internally, we can expose it
as an external API. This will add two flavors of API - thread-safe
and non-thread-safe. Fix up internal API's to return values we need
without modifying rte_errno internally if called from within EAL.

We do not want calling code to accidentally close an internal fd, so
we make a duplicate of it before we return it to the user. Caller is
therefore responsible for closing this fd.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
 lib/librte_eal/bsdapp/eal/eal_memalloc.c   |  5 ++-
 lib/librte_eal/common/eal_common_memory.c  | 49 ++++++++++++++++++++++
 lib/librte_eal/common/eal_memalloc.h       |  2 +
 lib/librte_eal/common/include/rte_memory.h | 48 +++++++++++++++++++++
 lib/librte_eal/linuxapp/eal/eal_memalloc.c | 21 ++++++----
 lib/librte_eal/rte_eal_version.map         |  2 +
 6 files changed, 118 insertions(+), 9 deletions(-)

diff --git a/lib/librte_eal/bsdapp/eal/eal_memalloc.c b/lib/librte_eal/bsdapp/eal/eal_memalloc.c
index a5fb09f71..80e4c3d4f 100644
--- a/lib/librte_eal/bsdapp/eal/eal_memalloc.c
+++ b/lib/librte_eal/bsdapp/eal/eal_memalloc.c
@@ -4,6 +4,7 @@
 
 #include <inttypes.h>
 
+#include <rte_errno.h>
 #include <rte_log.h>
 #include <rte_memory.h>
 
@@ -50,13 +51,13 @@ eal_memalloc_sync_with_primary(void)
 int
 eal_memalloc_get_seg_fd(int list_idx, int seg_idx)
 {
-	return -1;
+	return -ENOTSUP;
 }
 
 int
 eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd)
 {
-	return -1;
+	return -ENOTSUP;
 }
 
 int
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index 034c2026a..4a80deaf5 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -550,6 +550,55 @@ rte_memseg_list_walk(rte_memseg_list_walk_t func, void *arg)
 	return ret;
 }
 
+int __rte_experimental
+rte_memseg_get_fd_thread_unsafe(const struct rte_memseg *ms)
+{
+	struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+	struct rte_memseg_list *msl;
+	struct rte_fbarray *arr;
+	int msl_idx, seg_idx, ret;
+
+	if (ms == NULL) {
+		rte_errno = EINVAL;
+		return -1;
+	}
+
+	msl = rte_mem_virt2memseg_list(ms->addr);
+	if (msl == NULL) {
+		rte_errno = EINVAL;
+		return -1;
+	}
+	arr = &msl->memseg_arr;
+
+	msl_idx = msl - mcfg->memsegs;
+	seg_idx = rte_fbarray_find_idx(arr, ms);
+
+	if (!rte_fbarray_is_used(arr, seg_idx)) {
+		rte_errno = ENOENT;
+		return -1;
+	}
+
+	ret = eal_memalloc_get_seg_fd(msl_idx, seg_idx);
+	if (ret < 0) {
+		rte_errno = -ret;
+		ret = -1;
+	}
+	return ret;
+}
+
+int __rte_experimental
+rte_memseg_get_fd(const struct rte_memseg *ms)
+{
+	struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+	int ret;
+
+	rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+	ret = rte_memseg_get_fd_thread_unsafe(ms);
+	rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+
+	return ret;
+}
+
 /* init memory subsystem */
 int
 rte_eal_memory_init(void)
diff --git a/lib/librte_eal/common/eal_memalloc.h b/lib/librte_eal/common/eal_memalloc.h
index a46c69c72..70a214de4 100644
--- a/lib/librte_eal/common/eal_memalloc.h
+++ b/lib/librte_eal/common/eal_memalloc.h
@@ -76,9 +76,11 @@ eal_memalloc_mem_alloc_validator_unregister(const char *name, int socket_id);
 int
 eal_memalloc_mem_alloc_validate(int socket_id, size_t new_len);
 
+/* returns fd or -errno */
 int
 eal_memalloc_get_seg_fd(int list_idx, int seg_idx);
 
+/* returns 0 or -errno */
 int
 eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd);
 
diff --git a/lib/librte_eal/common/include/rte_memory.h b/lib/librte_eal/common/include/rte_memory.h
index c4b7f4cff..0d2a30056 100644
--- a/lib/librte_eal/common/include/rte_memory.h
+++ b/lib/librte_eal/common/include/rte_memory.h
@@ -317,6 +317,54 @@ rte_memseg_contig_walk_thread_unsafe(rte_memseg_contig_walk_t func, void *arg);
 int __rte_experimental
 rte_memseg_list_walk_thread_unsafe(rte_memseg_list_walk_t func, void *arg);
 
+/**
+ * Return file descriptor associated with a particular memseg (if available).
+ *
+ * @note This function read-locks the memory hotplug subsystem, and thus cannot
+ *       be used within memory-related callback functions.
+ *
+ * @note This returns an internal file descriptor. Performing any operations on
+ *       this file descriptor is inherently dangerous, so it should be treated
+ *       as read-only for all intents and purposes.
+ *
+ * @param ms
+ *   A pointer to memseg for which to get file descriptor.
+ *
+ * @return
+ *   Valid file descriptor in case of success.
+ *   -1 in case of error, with ``rte_errno`` set to the following values:
+ *     - EINVAL  - ``ms`` pointer was NULL or did not point to a valid memseg
+ *     - ENODEV  - ``ms`` fd is not available
+ *     - ENOENT  - ``ms`` is an unused segment
+ *     - ENOTSUP - segment fd's are not supported
+ */
+int __rte_experimental
+rte_memseg_get_fd(const struct rte_memseg *ms);
+
+/**
+ * Return file descriptor associated with a particular memseg (if available).
+ *
+ * @note This function does not perform any locking, and is only safe to call
+ *       from within memory-related callback functions.
+ *
+ * @note This returns an internal file descriptor. Performing any operations on
+ *       this file descriptor is inherently dangerous, so it should be treated
+ *       as read-only for all intents and purposes.
+ *
+ * @param ms
+ *   A pointer to memseg for which to get file descriptor.
+ *
+ * @return
+ *   Valid file descriptor in case of success.
+ *   -1 in case of error, with ``rte_errno`` set to the following values:
+ *     - EINVAL  - ``ms`` pointer was NULL or did not point to a valid memseg
+ *     - ENODEV  - ``ms`` fd is not available
+ *     - ENOENT  - ``ms`` is an unused segment
+ *     - ENOTSUP - segment fd's are not supported
+ */
+int __rte_experimental
+rte_memseg_get_fd_thread_unsafe(const struct rte_memseg *ms);
+
 /**
  * Dump the physical memory layout to a file.
  *
diff --git a/lib/librte_eal/linuxapp/eal/eal_memalloc.c b/lib/librte_eal/linuxapp/eal/eal_memalloc.c
index b820989e9..21f842753 100644
--- a/lib/librte_eal/linuxapp/eal/eal_memalloc.c
+++ b/lib/librte_eal/linuxapp/eal/eal_memalloc.c
@@ -34,6 +34,7 @@
 #include <rte_log.h>
 #include <rte_eal_memconfig.h>
 #include <rte_eal.h>
+#include <rte_errno.h>
 #include <rte_memory.h>
 #include <rte_spinlock.h>
 
@@ -1381,7 +1382,7 @@ eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd)
 		int len = mcfg->memsegs[list_idx].memseg_arr.len;
 
 		if (alloc_list(list_idx, len) < 0)
-			return -1;
+			return -ENOMEM;
 	}
 	fd_list[list_idx].fds[seg_idx] = fd;
 
@@ -1391,12 +1392,18 @@ eal_memalloc_set_seg_fd(int list_idx, int seg_idx, int fd)
 int
 eal_memalloc_get_seg_fd(int list_idx, int seg_idx)
 {
-	if (internal_config.single_file_segments)
-		return fd_list[list_idx].memseg_list_fd;
-	/* list not initialized */
-	if (fd_list[list_idx].len == 0)
-		return -1;
-	return fd_list[list_idx].fds[seg_idx];
+	int fd;
+	if (internal_config.single_file_segments) {
+		fd = fd_list[list_idx].memseg_list_fd;
+	} else if (fd_list[list_idx].len == 0) {
+		/* list not initialized */
+		fd = -1;
+	} else {
+		fd = fd_list[list_idx].fds[seg_idx];
+	}
+	if (fd < 0)
+		return -ENODEV;
+	return fd;
 }
 
 int
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index 344a43d32..e659e19d6 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -320,6 +320,8 @@ EXPERIMENTAL {
 	rte_mem_virt2memseg_list;
 	rte_memseg_contig_walk;
 	rte_memseg_contig_walk_thread_unsafe;
+	rte_memseg_get_fd;
+	rte_memseg_get_fd_thread_unsafe;
 	rte_memseg_list_walk;
 	rte_memseg_list_walk_thread_unsafe;
 	rte_memseg_walk;
-- 
2.17.1