mem: add function for checking memseg IOVA

A device can suffer addressing limitations. This function checks
memsegs have iovas within the supported range based on dma mask.

PMDs should use this function during initialization if device
suffers addressing limitations, returning an error if this function
returns memsegs out of range.

Another usage is for emulated IOMMU hardware with addressing
limitations.

It is necessary to save the most restricted dma mask for checking out
memory allocated dynamically after initialization.

Signed-off-by: Alejandro Lucero <alejandro.lucero@netronome.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>

diff --git a/doc/guides/rel_notes/release_18_11.rst b/doc/guides/rel_notes/release_18_11.rst
index ae5c96fc2bfbb6189c5fda13f3756386e2db7ae3..376128f684415f7734da0cda276d522216c15dc6 100644 (file)
--- a/doc/guides/rel_notes/release_18_11.rst
+++ b/doc/guides/rel_notes/release_18_11.rst
@@ -60,6 +60,15 @@ New Features
   memory that was created outside of DPDK's own page allocator, and using that
   memory natively with any other DPDK library or data structure.
 
+* **Added check for ensuring allocated memory addressable by devices.**
+
+  Some devices can have addressing limitations so a new function,
+  ``rte_eal_check_dma_mask``, has been added for checking allocated memory is
+  not out of the device range. Because now memory can be dynamically allocated
+  after initialization, a dma mask is kept and any new allocated memory will be
+  checked out against that dma mask and rejected if out of range. If more than
+  one device has addressing limitations, the dma mask is the more restricted one.
+
 * **Added hot-unplug handle mechanism.**
 
   ``rte_dev_hotplug_handle_enable`` and ``rte_dev_hotplug_handle_disable`` are
@@ -385,6 +394,9 @@ ABI Changes
          - structure ``rte_eal_memconfig`` has been extended to contain next
            socket ID for externally allocated segments
 
+* eal: Added ``dma_maskbits`` to ``rte_mem_config`` for keeping more restricted
+       dma mask based on devices addressing limitations.
+
 * eal: The structure ``rte_device`` got a new field to reference a ``rte_bus``.
   It is changing the size of the ``struct rte_device`` and the inherited
   device structures of all buses.

diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index 3971773618f655064fc62e1d55d68d1eaf3a44db..a7559b99d38ae563c0d921214c323b252a9fc860 100644 (file)
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -388,6 +388,66 @@ rte_dump_physmem_layout(FILE *f)
        rte_memseg_walk(dump_memseg, f);
 }
 
+static int
+check_iova(const struct rte_memseg_list *msl __rte_unused,
+               const struct rte_memseg *ms, void *arg)
+{
+       uint64_t *mask = arg;
+       rte_iova_t iova;
+
+       /* higher address within segment */
+       iova = (ms->iova + ms->len) - 1;
+       if (!(iova & *mask))
+               return 0;
+
+       RTE_LOG(DEBUG, EAL, "memseg iova %"PRIx64", len %zx, out of range\n",
+                           ms->iova, ms->len);
+
+       RTE_LOG(DEBUG, EAL, "\tusing dma mask %"PRIx64"\n", *mask);
+       return 1;
+}
+
+#if defined(RTE_ARCH_64)
+#define MAX_DMA_MASK_BITS 63
+#else
+#define MAX_DMA_MASK_BITS 31
+#endif
+
+/* check memseg iovas are within the required range based on dma mask */
+int __rte_experimental
+rte_eal_check_dma_mask(uint8_t maskbits)
+{
+       struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+       uint64_t mask;
+
+       /* sanity check */
+       if (maskbits > MAX_DMA_MASK_BITS) {
+               RTE_LOG(ERR, EAL, "wrong dma mask size %u (Max: %u)\n",
+                                  maskbits, MAX_DMA_MASK_BITS);
+               return -1;
+       }
+
+       /* create dma mask */
+       mask = ~((1ULL << maskbits) - 1);
+
+       if (rte_memseg_walk(check_iova, &mask))
+               /*
+                * Dma mask precludes hugepage usage.
+                * This device can not be used and we do not need to keep
+                * the dma mask.
+                */
+               return 1;
+
+       /*
+        * we need to keep the more restricted maskbit for checking
+        * potential dynamic memory allocation in the future.
+        */
+       mcfg->dma_maskbits = mcfg->dma_maskbits == 0 ? maskbits :
+                            RTE_MIN(mcfg->dma_maskbits, maskbits);
+
+       return 0;
+}
+
 /* return the number of memory channels */
 unsigned rte_memory_get_nchannel(void)
 {

diff --git a/lib/librte_eal/common/include/rte_eal_memconfig.h b/lib/librte_eal/common/include/rte_eal_memconfig.h
index a22709f555f7ce755d5503b43f5e1d080b152f12..84aabe36c29fdae3b4bb33b3f8fab5fce0f8fbcb 100644 (file)
--- a/lib/librte_eal/common/include/rte_eal_memconfig.h
+++ b/lib/librte_eal/common/include/rte_eal_memconfig.h
@@ -86,6 +86,9 @@ struct rte_mem_config {
        /* legacy mem and single file segments options are shared */
        uint32_t legacy_mem;
        uint32_t single_file_segments;
+
+       /* keeps the more restricted dma mask */
+       uint8_t dma_maskbits;
 } __attribute__((__packed__));
 
 

diff --git a/lib/librte_eal/common/include/rte_memory.h b/lib/librte_eal/common/include/rte_memory.h
index ffdd56bfba3497c43f712b82b209600a662fd1c7..ce9370582c1c83ebb4e724c2cd9bb357509211f6 100644 (file)
--- a/lib/librte_eal/common/include/rte_memory.h
+++ b/lib/librte_eal/common/include/rte_memory.h
@@ -463,6 +463,9 @@ unsigned rte_memory_get_nchannel(void);
  */
 unsigned rte_memory_get_nrank(void);
 
+/* check memsegs iovas are within a range based on dma mask */
+int __rte_experimental rte_eal_check_dma_mask(uint8_t maskbits);
+
 /**
  * Drivers based on uio will not load unless physical
  * addresses are obtainable. It is only possible to get

diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c
index 363f306cc72d560ca15399ecbf320a133a33a574..1973b6e6eca7f5179c45918e0f2af85709f3fe01 100644 (file)
--- a/lib/librte_eal/common/malloc_heap.c
+++ b/lib/librte_eal/common/malloc_heap.c
@@ -288,11 +288,13 @@ alloc_pages_on_heap(struct malloc_heap *heap, uint64_t pg_sz, size_t elt_size,
                int socket, unsigned int flags, size_t align, size_t bound,
                bool contig, struct rte_memseg **ms, int n_segs)
 {
+       struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
        struct rte_memseg_list *msl;
        struct malloc_elem *elem = NULL;
        size_t alloc_sz;
        int allocd_pages;
        void *ret, *map_addr;
+       uint64_t mask;
 
        alloc_sz = (size_t)pg_sz * n_segs;
 
@@ -320,6 +322,16 @@ alloc_pages_on_heap(struct malloc_heap *heap, uint64_t pg_sz, size_t elt_size,
                goto fail;
        }
 
+       if (mcfg->dma_maskbits) {
+               mask = ~((1ULL << mcfg->dma_maskbits) - 1);
+               if (rte_eal_check_dma_mask(mask)) {
+                       RTE_LOG(ERR, EAL,
+                               "%s(): couldn't allocate memory due to DMA mask\n",
+                               __func__);
+                       goto fail;
+               }
+       }
+
        /* add newly minted memsegs to malloc heap */
        elem = malloc_heap_add_memory(heap, msl, map_addr, alloc_sz);
 

diff --git a/lib/librte_eal/linuxapp/eal/eal.c b/lib/librte_eal/linuxapp/eal/eal.c
index 67116eee227314457928b150b4a8550ecfd34708..6a3395f3c954357d07338f47b7f28f1bc685612d 100644 (file)
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -264,6 +264,8 @@ rte_eal_config_create(void)
         * processes could later map the config into this exact location */
        rte_config.mem_config->mem_cfg_addr = (uintptr_t) rte_mem_cfg_addr;
 
+       rte_config.mem_config->dma_maskbits = 0;
+
 }
 
 /* attach to an existing shared memory config */

diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index 28bfa495023f565db27a1c90dfd0a5aa49bccf07..04f6242460b78cec5cea74396976f3af2e4ba323 100644 (file)
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -295,6 +295,7 @@ EXPERIMENTAL {
        rte_devargs_parsef;
        rte_devargs_remove;
        rte_devargs_type_count;
+       rte_eal_check_dma_mask;
        rte_eal_cleanup;
        rte_fbarray_attach;
        rte_fbarray_destroy;