mem: allow usage of non-heap external memory in multiprocess

Add multiprocess support for externally allocated memory areas that
are not added to DPDK heap (and add relevant doc sections).

Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>

diff --git a/doc/guides/prog_guide/env_abstraction_layer.rst b/doc/guides/prog_guide/env_abstraction_layer.rst
index 190662e805776b912b9485d57add48e740010962..5aaac0bd2533e1180bf4ff56baf713f82d144379 100644 (file)
--- a/doc/guides/prog_guide/env_abstraction_layer.rst
+++ b/doc/guides/prog_guide/env_abstraction_layer.rst
@@ -290,11 +290,14 @@ The expected workflow is as follows:
 * Register memory within DPDK
     - If IOVA table is not specified, IOVA addresses will be assumed to be
       unavailable
+    - Other processes must attach to the memory area before they can use it
 * Perform DMA mapping with ``rte_vfio_dma_map`` if needed
 * Use the memory area in your application
 * If memory area is no longer needed, it can be unregistered
     - If the area was mapped for DMA, unmapping must be performed before
       unregistering memory
+    - Other processes must detach from the memory area before it can be
+      unregistered
 
 Since these externally allocated memory areas will not be managed by DPDK, it is
 therefore up to the user application to decide how to use them and what to do

diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index ea43c1362e50f186a258f320b7427eb34c335469..051159f8035432c98e06f042487f7b6851c8bb9b 100644 (file)
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -852,6 +852,48 @@ unlock:
        return ret;
 }
 
+static int
+sync_memory(void *va_addr, size_t len, bool attach)
+{
+       struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+       struct rte_memseg_list *msl;
+       int ret = 0;
+
+       if (va_addr == NULL || len == 0) {
+               rte_errno = EINVAL;
+               return -1;
+       }
+       rte_rwlock_write_lock(&mcfg->memory_hotplug_lock);
+
+       /* find our segment */
+       msl = malloc_heap_find_external_seg(va_addr, len);
+       if (msl == NULL) {
+               rte_errno = ENOENT;
+               ret = -1;
+               goto unlock;
+       }
+       if (attach)
+               ret = rte_fbarray_attach(&msl->memseg_arr);
+       else
+               ret = rte_fbarray_detach(&msl->memseg_arr);
+
+unlock:
+       rte_rwlock_write_unlock(&mcfg->memory_hotplug_lock);
+       return ret;
+}
+
+int __rte_experimental
+rte_extmem_attach(void *va_addr, size_t len)
+{
+       return sync_memory(va_addr, len, true);
+}
+
+int __rte_experimental
+rte_extmem_detach(void *va_addr, size_t len)
+{
+       return sync_memory(va_addr, len, false);
+}
+
 /* init memory subsystem */
 int
 rte_eal_memory_init(void)

diff --git a/lib/librte_eal/common/include/rte_memory.h b/lib/librte_eal/common/include/rte_memory.h
index ff23fc2c1208c2782501055ea11e94c08b1e6fc5..7ca703bb190897f59d3065e2e1a04f6d664f08a6 100644 (file)
--- a/lib/librte_eal/common/include/rte_memory.h
+++ b/lib/librte_eal/common/include/rte_memory.h
@@ -435,6 +435,10 @@ rte_memseg_get_fd_offset_thread_unsafe(const struct rte_memseg *ms,
  * @note This API will not perform any DMA mapping. It is expected that user
  *   will do that themselves.
  *
+ * @note Before accessing this memory in other processes, it needs to be
+ *   attached in each of those processes by calling ``rte_extmem_attach`` in
+ *   each other process.
+ *
  * @param va_addr
  *   Start of virtual area to register. Must be aligned by ``page_sz``.
  * @param len
@@ -472,6 +476,9 @@ rte_extmem_register(void *va_addr, size_t len, rte_iova_t iova_addrs[],
  * @note This API will not perform any DMA unmapping. It is expected that user
  *   will do that themselves.
  *
+ * @note Before calling this function, all other processes must call
+ *   ``rte_extmem_detach`` to detach from the memory area.
+ *
  * @param va_addr
  *   Start of virtual area to unregister
  * @param len
@@ -486,6 +493,58 @@ rte_extmem_register(void *va_addr, size_t len, rte_iova_t iova_addrs[],
 int __rte_experimental
 rte_extmem_unregister(void *va_addr, size_t len);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Attach to external memory chunk registered in another process.
+ *
+ * @note Using this API is mutually exclusive with ``rte_malloc`` family of
+ *   API's.
+ *
+ * @note This API will not perform any DMA mapping. It is expected that user
+ *   will do that themselves.
+ *
+ * @param va_addr
+ *   Start of virtual area to register
+ * @param len
+ *   Length of virtual area to register
+ *
+ * @return
+ *   - 0 on success
+ *   - -1 in case of error, with rte_errno set to one of the following:
+ *     EINVAL - one of the parameters was invalid
+ *     ENOENT - memory chunk was not found
+ */
+int __rte_experimental
+rte_extmem_attach(void *va_addr, size_t len);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Detach from external memory chunk registered in another process.
+ *
+ * @note Using this API is mutually exclusive with ``rte_malloc`` family of
+ *   API's.
+ *
+ * @note This API will not perform any DMA unmapping. It is expected that user
+ *   will do that themselves.
+ *
+ * @param va_addr
+ *   Start of virtual area to unregister
+ * @param len
+ *   Length of virtual area to unregister
+ *
+ * @return
+ *   - 0 on success
+ *   - -1 in case of error, with rte_errno set to one of the following:
+ *     EINVAL - one of the parameters was invalid
+ *     ENOENT - memory chunk was not found
+ */
+int __rte_experimental
+rte_extmem_detach(void *va_addr, size_t len);
+
 /**
  * Dump the physical memory layout to a file.
  *

diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index 593691a14f083f6ccf99cc936fc9196d081ab053..eb5f7b9cbd9cd9bce6e0d09f382678deabac3aa3 100644 (file)
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -296,6 +296,8 @@ EXPERIMENTAL {
        rte_devargs_remove;
        rte_devargs_type_count;
        rte_eal_cleanup;
+       rte_extmem_attach;
+       rte_extmem_detach;
        rte_extmem_register;
        rte_extmem_unregister;
        rte_fbarray_attach;