[dpdk-dev] [PATCH 1/5] mem: add function for checking memsegs IOVAs addresses

[Alejandro Lucero]

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

PMD should use this during initialization if supported devices
suffer addressing limitations, returning an error if this function
returns memsegs out of range.

Another potential usage is for emulated IOMMU hardware with addressing
limitations.

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

Signed-off-by: Alejandro Lucero <alejandro.lucero at netronome.com>
---
 lib/librte_eal/common/eal_common_memory.c         | 56 +++++++++++++++++++++++
 lib/librte_eal/common/include/rte_eal_memconfig.h |  3 ++
 lib/librte_eal/common/include/rte_memory.h        |  3 ++
 lib/librte_eal/common/malloc_heap.c               | 12 +++++
 lib/librte_eal/linuxapp/eal/eal.c                 |  2 +
 lib/librte_eal/rte_eal_version.map                |  1 +
 6 files changed, 77 insertions(+)

diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index fbfb1b0..1e8312b 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -383,6 +383,62 @@ struct virtiova {
 	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(INFO, EAL, "memseg iova %"PRIx64", len %zx, out of range\n",
+			   ms->iova, ms->len);
+
+	RTE_LOG(INFO, EAL, "\tusing dma mask %"PRIx64"\n", *mask);
+	/* Stop the walk and change mask */
+	*mask = 0;
+	return 1;
+}
+
+#if defined(RTE_ARCH_64)
+#define X86_VA_WIDTH 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(INFO, EAL, "wrong dma mask size %u (Max: %u)\n",
+				   maskbits, MAX_DMA_MASK_BITS);
+		return -1;
+	}
+
+	/* keep the more restricted maskbit */
+	if (!mcfg->dma_maskbits || maskbits < mcfg->dma_maskbits)
+		mcfg->dma_maskbits = maskbits;
+
+	/* create dma mask */
+	mask = ~((1ULL << maskbits) - 1);
+
+	rte_memseg_walk(check_iova, &mask);
+
+	if (!mask)
+		return -1;
+
+	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 aff0688..aea44cb 100644
--- a/lib/librte_eal/common/include/rte_eal_memconfig.h
+++ b/lib/librte_eal/common/include/rte_eal_memconfig.h
@@ -77,6 +77,9 @@ struct rte_mem_config {
 	 * exact same address the primary process maps it.
 	 */
 	uint64_t mem_cfg_addr;
+
+	/* 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 c4b7f4c..cd439e3 100644
--- a/lib/librte_eal/common/include/rte_memory.h
+++ b/lib/librte_eal/common/include/rte_memory.h
@@ -357,6 +357,9 @@ typedef int (*rte_memseg_list_walk_t)(const struct rte_memseg_list *msl,
  */
 unsigned rte_memory_get_nrank(void);
 
+/* check memsegs iovas are within a range based on dma mask */
+int 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 12aaf2d..255d717 100644
--- a/lib/librte_eal/common/malloc_heap.c
+++ b/lib/librte_eal/common/malloc_heap.c
@@ -259,11 +259,13 @@ struct malloc_elem *
 		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;
 
@@ -291,6 +293,16 @@ struct malloc_elem *
 		goto fail;
 	}
 
+	if (mcfg->dma_maskbits) {
+		mask = ~((1ULL << mcfg->dma_maskbits) - 1);
+		if (rte_eal_check_dma_mask(mask)) {
+			RTE_LOG(DEBUG, 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 e59ac65..616723e 100644
--- a/lib/librte_eal/linuxapp/eal/eal.c
+++ b/lib/librte_eal/linuxapp/eal/eal.c
@@ -263,6 +263,8 @@ enum rte_iova_mode
 	 * 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 344a43d..85e6212 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -284,6 +284,7 @@ EXPERIMENTAL {
 	rte_devargs_parsef;
 	rte_devargs_remove;
 	rte_devargs_type_count;
+	rte_eal_check_dma_mask;
 	rte_eal_cleanup;
 	rte_eal_hotplug_add;
 	rte_eal_hotplug_remove;
-- 
1.9.1