arm64: Clamp segment sizes properly in bounce_bus_dmamap_load_buffer()

Commit 099b595154 ("Improve loading of multipage aligned buffers.")
modified bounce_bus_dmamap_load_buffer() with the assumption that busdma
memory allocations are physically contiguous, which is not always true:
bounce_bus_dmamem_alloc() will allocate memory with
kmem_alloc_attr_domainset() in some cases, and this function is not
guaranteed to return contiguous memory.

The damage seems to have been mitigated for most consumers by clamping
the segment size to maxsegsz, but this was removed in commit
a77e1f0f81 ("busdma: better handling of small segment bouncing"); in
practice, it seems busdma memory is often allocated with maxsegsz ==
PAGE_SIZE.  In particular, after commit a77e1f0f81 I see occasional
random kernel memory corruption when benchmarking TCP through mlx5
interfaces.

Fix the problem by using separate flags for contiguous and
non-contiguous busdma memory allocations, and using that to decide
whether to clamp.

Fixes:	099b595154 ("Improve loading of multipage aligned buffers.")
Fixes:	a77e1f0f81 ("busdma: better handling of small segment bouncing")
Sponsored by:	Klara, Inc.
Sponsored by:	Stormshield
Differential Revision:	https://reviews.freebsd.org/D46238

sys/arm64/arm64/busdma_bounce.c

@@ -63,7 +63,9 @@
 enum {
 	BF_COULD_BOUNCE		= 0x01,
 	BF_MIN_ALLOC_COMP	= 0x02,
-	BF_KMEM_ALLOC		= 0x04,
+	BF_KMEM_ALLOC_PAGES	= 0x04,
+	BF_KMEM_ALLOC_CONTIG	= 0x08,
+	BF_KMEM_ALLOC		= BF_KMEM_ALLOC_PAGES | BF_KMEM_ALLOC_CONTIG,
 	BF_COHERENT		= 0x10,
 };
 
@@ -580,14 +582,14 @@ bounce_bus_dmamem_alloc(bus_dma_tag_t dmat, void** vaddr, int flags,
 		*vaddr = kmem_alloc_attr_domainset(
 		    DOMAINSET_PREF(dmat->common.domain), dmat->alloc_size,
 		    mflags, 0ul, dmat->common.lowaddr, attr);
-		dmat->bounce_flags |= BF_KMEM_ALLOC;
+		dmat->bounce_flags |= BF_KMEM_ALLOC_PAGES;
 	} else {
 		*vaddr = kmem_alloc_contig_domainset(
 		    DOMAINSET_PREF(dmat->common.domain), dmat->alloc_size,
 		    mflags, 0ul, dmat->common.lowaddr,
 		    dmat->alloc_alignment != 0 ? dmat->alloc_alignment : 1ul,
 		    dmat->common.boundary, attr);
-		dmat->bounce_flags |= BF_KMEM_ALLOC;
+		dmat->bounce_flags |= BF_KMEM_ALLOC_CONTIG;
 	}
 	if (*vaddr == NULL) {
 		CTR4(KTR_BUSDMA, "%s: tag %p tag flags 0x%x error %d",
@@ -856,7 +858,8 @@ bounce_bus_dmamap_load_buffer(bus_dma_tag_t dmat, bus_dmamap_t map, void *buf,
 		 * Compute the segment size, and adjust counts.
 		 */
 		sgsize = buflen;
-		if ((map->flags & DMAMAP_FROM_DMAMEM) == 0)
+		if ((map->flags & DMAMAP_FROM_DMAMEM) == 0 ||
+		    (dmat->bounce_flags & BF_KMEM_ALLOC_CONTIG) == 0)
 			sgsize = MIN(sgsize, PAGE_SIZE - (curaddr & PAGE_MASK));
 
 		if (map->pagesneeded != 0 &&