[dpdk-dev] [PATCH 14/16] malloc: allow attaching to external memory chunks

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

In order to use external memory in multiple processes, we need to
attach to primary process's memseg lists, so add a new API to do
that. It is the responsibility of the user to ensure that memory
is accessible and that it has been previously added to the malloc
heap by another process.

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
---
 lib/librte_eal/common/include/rte_malloc.h | 32 +++++++++
 lib/librte_eal/common/rte_malloc.c         | 83 ++++++++++++++++++++++
 lib/librte_eal/rte_eal_version.map         |  1 +
 3 files changed, 116 insertions(+)

diff --git a/lib/librte_eal/common/include/rte_malloc.h b/lib/librte_eal/common/include/rte_malloc.h
index 9bbe8e3af..37af0e481 100644
--- a/lib/librte_eal/common/include/rte_malloc.h
+++ b/lib/librte_eal/common/include/rte_malloc.h
@@ -268,6 +268,10 @@ rte_malloc_get_socket_stats(int socket,
  *
  * @note Multiple memory chunks can be added to the same heap
  *
+ * @note Before accessing this memory in other processes, it needs to be
+ *   attached in each of those processes by calling
+ *   ``rte_malloc_heap_memory_attach`` in each other process.
+ *
  * @note Memory must be previously allocated for DPDK to be able to use it as a
  *   malloc heap. Failing to do so will result in undefined behavior, up to and
  *   including segmentation faults.
@@ -329,12 +333,38 @@ rte_malloc_heap_memory_add(const char *heap_name, void *va_addr, size_t len,
 int __rte_experimental
 rte_malloc_heap_memory_remove(const char *heap_name, void *va_addr, size_t len);
 
+/**
+ * Attach to an already existing chunk of external memory in another process.
+ *
+ * @note This function must be called before any attempt is made to use an
+ *   already existing external memory chunk. This function does *not* need to
+ *   be called if a call to ``rte_malloc_heap_memory_add`` was made in the
+ *   current process.
+ *
+ * @param heap_name
+ *   Heap name to which this chunk of memory belongs
+ * @param va_addr
+ *   Start address of memory chunk to attach to
+ * @param len
+ *   Length of memory chunk to attach to
+ * @return
+ *   0 on successful attach
+ *   -1 on unsuccessful attach, with rte_errno set to indicate cause for error:
+ *     EINVAL - one of the parameters was invalid
+ *     EPERM  - attempted to attach memory to a reserved heap
+ *     ENOENT - heap or memory chunk was not found
+ */
+int __rte_experimental
+rte_malloc_heap_memory_attach(const char *heap_name, void *va_addr, size_t len);
+
 /**
  * Creates a new empty malloc heap with a specified name.
  *
  * @note Heaps created via this call will automatically get assigned a unique
  *   socket ID, which can be found using ``rte_malloc_heap_get_socket()``
  *
+ * @note This function has to only be called in one process.
+ *
  * @param heap_name
  *   Name of the heap to create.
  *
@@ -357,6 +387,8 @@ rte_malloc_heap_create(const char *heap_name);
  * @note This function will return a failure result if not all memory segments
  *   were removed from the heap prior to its destruction
  *
+ * @note This function has to only be called in one process.
+ *
  * @param heap_name
  *   Name of the heap to create.
  *
diff --git a/lib/librte_eal/common/rte_malloc.c b/lib/librte_eal/common/rte_malloc.c
index 5093c4a46..2ed173466 100644
--- a/lib/librte_eal/common/rte_malloc.c
+++ b/lib/librte_eal/common/rte_malloc.c
@@ -393,6 +393,89 @@ rte_malloc_heap_memory_remove(const char *heap_name, void *va_addr, size_t len)
 	return ret;
 }
 
+struct sync_mem_walk_arg {
+	void *va_addr;
+	size_t len;
+	int result;
+};
+
+static int
+attach_mem_walk(const struct rte_memseg_list *msl, void *arg)
+{
+	struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+	struct sync_mem_walk_arg *wa = arg;
+	size_t len = msl->page_sz * msl->memseg_arr.len;
+
+	if (msl->base_va == wa->va_addr &&
+			len == wa->len) {
+		struct rte_memseg_list *found_msl;
+		int msl_idx, ret;
+
+		/* msl is const */
+		msl_idx = msl - mcfg->memsegs;
+		found_msl = &mcfg->memsegs[msl_idx];
+
+		ret = rte_fbarray_attach(&found_msl->memseg_arr);
+
+		if (ret < 0)
+			wa->result = -rte_errno;
+		else
+			wa->result = 0;
+		return 1;
+	}
+	return 0;
+}
+
+int
+rte_malloc_heap_memory_attach(const char *heap_name, void *va_addr, size_t len)
+{
+	struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+	struct malloc_heap *heap = NULL;
+	struct sync_mem_walk_arg wa;
+	int ret;
+
+	if (heap_name == NULL || va_addr == NULL || len == 0 ||
+			strnlen(heap_name, RTE_HEAP_NAME_MAX_LEN) == 0 ||
+			strnlen(heap_name, RTE_HEAP_NAME_MAX_LEN) ==
+				RTE_HEAP_NAME_MAX_LEN) {
+		rte_errno = EINVAL;
+		return -1;
+	}
+	rte_rwlock_read_lock(&mcfg->memory_hotplug_lock);
+
+	/* find our heap */
+	heap = find_named_heap(heap_name);
+	if (heap == NULL) {
+		rte_errno = ENOENT;
+		ret = -1;
+		goto unlock;
+	}
+	/* we shouldn't be able to attach to internal heaps */
+	if (heap->socket_id < RTE_MAX_NUMA_NODES) {
+		rte_errno = EPERM;
+		ret = -1;
+		goto unlock;
+	}
+
+	/* find corresponding memseg list to attach to */
+	wa.va_addr = va_addr;
+	wa.len = len;
+	wa.result = -ENOENT; /* fail unless explicitly told to succeed */
+
+	/* we're already holding a read lock */
+	rte_memseg_list_walk_thread_unsafe(attach_mem_walk, &wa);
+
+	if (wa.result < 0) {
+		rte_errno = -wa.result;
+		ret = -1;
+	} else {
+		ret = 0;
+	}
+unlock:
+	rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+	return ret;
+}
+
 int
 rte_malloc_heap_create(const char *heap_name)
 {
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index f10c34130..822c5693a 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -315,6 +315,7 @@ EXPERIMENTAL {
 	rte_malloc_heap_destroy;
 	rte_malloc_heap_get_socket;
 	rte_malloc_heap_memory_add;
+	rte_malloc_heap_memory_attach;
 	rte_malloc_heap_memory_remove;
 	rte_mem_alloc_validator_register;
 	rte_mem_alloc_validator_unregister;
-- 
2.17.1