Merge tag 'dma-mapping-6.4-2023-04-28' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - fix a PageHighMem check in dma-coherent initialization (Doug Berger)

 - clean up the coherency defaul initialiation (Jiaxun Yang)

 - add cacheline to user/kernel dma-debug space dump messages (Desnes
   Nunes, Geert Uytterhoeve)

 - swiotlb statistics improvements (Michael Kelley)

 - misc cleanups (Petr Tesarik)

* tag 'dma-mapping-6.4-2023-04-28' of git://git.infradead.org/users/hch/dma-mapping:
  swiotlb: Omit total_used and used_hiwater if !CONFIG_DEBUG_FS
  swiotlb: track and report io_tlb_used high water marks in debugfs
  swiotlb: fix debugfs reporting of reserved memory pools
  swiotlb: relocate PageHighMem test away from rmem_swiotlb_setup
  of: address: always use dma_default_coherent for default coherency
  dma-mapping: provide CONFIG_ARCH_DMA_DEFAULT_COHERENT
  dma-mapping: provide a fallback dma_default_coherent
  dma-debug: Use %pa to format phys_addr_t
  dma-debug: add cacheline to user/kernel space dump messages
  dma-debug: small dma_debug_entry's comment and variable name updates
  dma-direct: cleanup parameters to dma_direct_optimal_gfp_mask

1 files changed, 87 insertions, 10 deletions

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 0fb16bdbbcae..af2e304c672c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -566,6 +566,40 @@ static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index)
 }
 
 /*
+ * Track the total used slots with a global atomic value in order to have
+ * correct information to determine the high water mark. The mem_used()
+ * function gives imprecise results because there's no locking across
+ * multiple areas.
+ */
+#ifdef CONFIG_DEBUG_FS
+static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
+{
+	unsigned long old_hiwater, new_used;
+
+	new_used = atomic_long_add_return(nslots, &mem->total_used);
+	old_hiwater = atomic_long_read(&mem->used_hiwater);
+	do {
+		if (new_used <= old_hiwater)
+			break;
+	} while (!atomic_long_try_cmpxchg(&mem->used_hiwater,
+					  &old_hiwater, new_used));
+}
+
+static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
+{
+	atomic_long_sub(nslots, &mem->total_used);
+}
+
+#else /* !CONFIG_DEBUG_FS */
+static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
+{
+}
+static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+/*
  * Find a suitable number of IO TLB entries size that will fit this request and
  * allocate a buffer from that IO TLB pool.
  */
@@ -659,6 +693,8 @@ found:
 	area->index = wrap_area_index(mem, index + nslots);
 	area->used += nslots;
 	spin_unlock_irqrestore(&area->lock, flags);
+
+	inc_used_and_hiwater(mem, nslots);
 	return slot_index;
 }
 
@@ -791,6 +827,8 @@ static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
 		mem->slots[i].list = ++count;
 	area->used -= nslots;
 	spin_unlock_irqrestore(&area->lock, flags);
+
+	dec_used(mem, nslots);
 }
 
 /*
@@ -885,34 +923,73 @@ bool is_swiotlb_active(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(is_swiotlb_active);
 
+#ifdef CONFIG_DEBUG_FS
+
 static int io_tlb_used_get(void *data, u64 *val)
 {
-	*val = mem_used(&io_tlb_default_mem);
+	struct io_tlb_mem *mem = data;
+
+	*val = mem_used(mem);
 	return 0;
 }
+
+static int io_tlb_hiwater_get(void *data, u64 *val)
+{
+	struct io_tlb_mem *mem = data;
+
+	*val = atomic_long_read(&mem->used_hiwater);
+	return 0;
+}
+
+static int io_tlb_hiwater_set(void *data, u64 val)
+{
+	struct io_tlb_mem *mem = data;
+
+	/* Only allow setting to zero */
+	if (val != 0)
+		return -EINVAL;
+
+	atomic_long_set(&mem->used_hiwater, val);
+	return 0;
+}
+
 DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get,
+				io_tlb_hiwater_set, "%llu\n");
 
 static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
 					 const char *dirname)
 {
+	atomic_long_set(&mem->total_used, 0);
+	atomic_long_set(&mem->used_hiwater, 0);
+
 	mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
 	if (!mem->nslabs)
 		return;
 
 	debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
-	debugfs_create_file("io_tlb_used", 0400, mem->debugfs, NULL,
+	debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem,
 			&fops_io_tlb_used);
+	debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
+			&fops_io_tlb_hiwater);
 }
 
-static int __init __maybe_unused swiotlb_create_default_debugfs(void)
+static int __init swiotlb_create_default_debugfs(void)
 {
 	swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb");
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_FS
 late_initcall(swiotlb_create_default_debugfs);
-#endif
+
+#else  /* !CONFIG_DEBUG_FS */
+
+static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
+						const char *dirname)
+{
+}
+
+#endif	/* CONFIG_DEBUG_FS */
 
 #ifdef CONFIG_DMA_RESTRICTED_POOL
 
@@ -955,6 +1032,11 @@ static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
 	/* Set Per-device io tlb area to one */
 	unsigned int nareas = 1;
 
+	if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) {
+		dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping.");
+		return -EINVAL;
+	}
+
 	/*
 	 * Since multiple devices can share the same pool, the private data,
 	 * io_tlb_mem struct, will be initialized by the first device attached
@@ -1016,11 +1098,6 @@ static int __init rmem_swiotlb_setup(struct reserved_mem *rmem)
 	    of_get_flat_dt_prop(node, "no-map", NULL))
 		return -EINVAL;
 
-	if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) {
-		pr_err("Restricted DMA pool must be accessible within the linear mapping.");
-		return -EINVAL;
-	}
-
 	rmem->ops = &rmem_swiotlb_ops;
 	pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n",
 		&rmem->base, (unsigned long)rmem->size / SZ_1M);