Merge tag 'dma-mapping-6.5-2023-07-09' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping fixes from Christoph Hellwig:

 - swiotlb area sizing fixes (Petr Tesarik)

* tag 'dma-mapping-6.5-2023-07-09' of git://git.infradead.org/users/hch/dma-mapping:
  swiotlb: reduce the number of areas to match actual memory pool size
  swiotlb: always set the number of areas before allocating the pool

kernel/dma/swiotlb.c

@@ -115,9 +115,16 @@ static bool round_up_default_nslabs(void)
 	return true;
 }
 
+/**
+ * swiotlb_adjust_nareas() - adjust the number of areas and slots
+ * @nareas:	Desired number of areas. Zero is treated as 1.
+ *
+ * Adjust the default number of areas in a memory pool.
+ * The default size of the memory pool may also change to meet minimum area
+ * size requirements.
+ */
 static void swiotlb_adjust_nareas(unsigned int nareas)
 {
-	/* use a single area when non is specified */
 	if (!nareas)
 		nareas = 1;
 	else if (!is_power_of_2(nareas))
@@ -131,6 +138,23 @@ static void swiotlb_adjust_nareas(unsigned int nareas)
 			(default_nslabs << IO_TLB_SHIFT) >> 20);
 }
 
+/**
+ * limit_nareas() - get the maximum number of areas for a given memory pool size
+ * @nareas:	Desired number of areas.
+ * @nslots:	Total number of slots in the memory pool.
+ *
+ * Limit the number of areas to the maximum possible number of areas in
+ * a memory pool of the given size.
+ *
+ * Return: Maximum possible number of areas.
+ */
+static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots)
+{
+	if (nslots < nareas * IO_TLB_SEGSIZE)
+		return nslots / IO_TLB_SEGSIZE;
+	return nareas;
+}
+
 static int __init
 setup_io_tlb_npages(char *str)
 {
@@ -290,6 +314,7 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs;
+	unsigned int nareas;
 	size_t alloc_size;
 	void *tlb;
 
@@ -298,18 +323,16 @@ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
 	if (swiotlb_force_disable)
 		return;
 
-	/*
-	 * default_nslabs maybe changed when adjust area number.
-	 * So allocate bounce buffer after adjusting area number.
-	 */
 	if (!default_nareas)
 		swiotlb_adjust_nareas(num_possible_cpus());
 
 	nslabs = default_nslabs;
+	nareas = limit_nareas(default_nareas, nslabs);
 	while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) {
 		if (nslabs <= IO_TLB_MIN_SLABS)
 			return;
 		nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
+		nareas = limit_nareas(nareas, nslabs);
 	}
 
 	if (default_nslabs != nslabs) {
@@ -355,6 +378,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 {
 	struct io_tlb_mem *mem = &io_tlb_default_mem;
 	unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
+	unsigned int nareas;
 	unsigned char *vstart = NULL;
 	unsigned int order, area_order;
 	bool retried = false;
@@ -363,6 +387,9 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 	if (swiotlb_force_disable)
 		return 0;
 
+	if (!default_nareas)
+		swiotlb_adjust_nareas(num_possible_cpus());
+
 retry:
 	order = get_order(nslabs << IO_TLB_SHIFT);
 	nslabs = SLABS_PER_PAGE << order;
@@ -397,11 +424,8 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 			(PAGE_SIZE << order) >> 20);
 	}
 
-	if (!default_nareas)
-		swiotlb_adjust_nareas(num_possible_cpus());
-
-	area_order = get_order(array_size(sizeof(*mem->areas),
-		default_nareas));
+	nareas = limit_nareas(default_nareas, nslabs);
+	area_order = get_order(array_size(sizeof(*mem->areas), nareas));
 	mem->areas = (struct io_tlb_area *)
 		__get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order);
 	if (!mem->areas)
@@ -415,7 +439,7 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask,
 	set_memory_decrypted((unsigned long)vstart,
 			     (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
 	swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true,
-				default_nareas);
+				nareas);
 
 	swiotlb_print_info();
 	return 0;