Merge tag 'dma-mapping-6.6-2023-08-29' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-maping updates from Christoph Hellwig:

 - allow dynamic sizing of the swiotlb buffer, to cater for secure
   virtualization workloads that require all I/O to be bounce buffered
   (Petr Tesarik)

 - move a declaration to a header (Arnd Bergmann)

 - check for memory region overlap in dma-contiguous (Binglei Wang)

 - remove the somewhat dangerous runtime swiotlb-xen enablement and
   unexport is_swiotlb_active (Christoph Hellwig, Juergen Gross)

 - per-node CMA improvements (Yajun Deng)

* tag 'dma-mapping-6.6-2023-08-29' of git://git.infradead.org/users/hch/dma-mapping:
  swiotlb: optimize get_max_slots()
  swiotlb: move slot allocation explanation comment where it belongs
  swiotlb: search the software IO TLB only if the device makes use of it
  swiotlb: allocate a new memory pool when existing pools are full
  swiotlb: determine potential physical address limit
  swiotlb: if swiotlb is full, fall back to a transient memory pool
  swiotlb: add a flag whether SWIOTLB is allowed to grow
  swiotlb: separate memory pool data from other allocator data
  swiotlb: add documentation and rename swiotlb_do_find_slots()
  swiotlb: make io_tlb_default_mem local to swiotlb.c
  swiotlb: bail out of swiotlb_init_late() if swiotlb is already allocated
  dma-contiguous: check for memory region overlap
  dma-contiguous: support numa CMA for specified node
  dma-contiguous: support per-numa CMA for all architectures
  dma-mapping: move arch_dma_set_mask() declaration to header
  swiotlb: unexport is_swiotlb_active
  x86: always initialize xen-swiotlb when xen-pcifront is enabling
  xen/pci: add flag for PCI passthrough being possible

5 files changed, 132 insertions, 29 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index bbaeabd04b0d..6fc808d22bfd 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -625,7 +625,10 @@ struct device_physical_location {
  * @dma_pools:	Dma pools (if dma'ble device).
  * @dma_mem:	Internal for coherent mem override.
  * @cma_area:	Contiguous memory area for dma allocations
- * @dma_io_tlb_mem: Pointer to the swiotlb pool used.  Not for driver use.
+ * @dma_io_tlb_mem: Software IO TLB allocator.  Not for driver use.
+ * @dma_io_tlb_pools:	List of transient swiotlb memory pools.
+ * @dma_io_tlb_lock:	Protects changes to the list of active pools.
+ * @dma_uses_io_tlb: %true if device has used the software IO TLB.
  * @archdata:	For arch-specific additions.
  * @of_node:	Associated device tree node.
  * @fwnode:	Associated device node supplied by platform firmware.
@@ -732,6 +735,11 @@ struct device {
 #ifdef CONFIG_SWIOTLB
 	struct io_tlb_mem *dma_io_tlb_mem;
 #endif
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+	struct list_head dma_io_tlb_pools;
+	spinlock_t dma_io_tlb_lock;
+	bool dma_uses_io_tlb;
+#endif
 	/* arch specific additions */
 	struct dev_archdata	archdata;
 
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 9bf19b5bf755..f2fc203fb8a1 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -169,12 +169,6 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 }
 #endif /* CONFIG_DMA_CMA*/
 
-#ifdef CONFIG_DMA_PERNUMA_CMA
-void dma_pernuma_cma_reserve(void);
-#else
-static inline void dma_pernuma_cma_reserve(void) { }
-#endif /* CONFIG_DMA_PERNUMA_CMA */
-
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		dma_addr_t device_addr, size_t size);
@@ -343,6 +337,12 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
 
+#ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
+void arch_dma_set_mask(struct device *dev, u64 mask);
+#else
+#define arch_dma_set_mask(dev, mask)	do { } while (0)
+#endif
+
 #ifdef CONFIG_MMU
 /*
  * Page protection so that devices that can't snoop CPU caches can use the
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index e13050eb9777..f0ccca16a0ac 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -418,6 +418,8 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
+
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 4e52cd5e0bdc..b4536626f8ff 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <linux/limits.h>
 #include <linux/spinlock.h>
+#include <linux/workqueue.h>
 
 struct device;
 struct page;
@@ -62,8 +63,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
 #ifdef CONFIG_SWIOTLB
 
 /**
- * struct io_tlb_mem - IO TLB Memory Pool Descriptor
- *
+ * struct io_tlb_pool - IO TLB memory pool descriptor
  * @start:	The start address of the swiotlb memory pool. Used to do a quick
  *		range check to see if the memory was in fact allocated by this
  *		API.
@@ -73,19 +73,48 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
  * @vaddr:	The vaddr of the swiotlb memory pool. The swiotlb memory pool
  *		may be remapped in the memory encrypted case and store virtual
  *		address for bounce buffer operation.
- * @nslabs:	The number of IO TLB blocks (in groups of 64) between @start and
- *		@end. For default swiotlb, this is command line adjustable via
- *		setup_io_tlb_npages.
- * @list:	The free list describing the number of free entries available
- *		from each index.
- * @orig_addr:	The original address corresponding to a mapped entry.
- * @alloc_size:	Size of the allocated buffer.
+ * @nslabs:	The number of IO TLB slots between @start and @end. For the
+ *		default swiotlb, this can be adjusted with a boot parameter,
+ *		see setup_io_tlb_npages().
+ * @late_alloc:	%true if allocated using the page allocator.
+ * @nareas:	Number of areas in the pool.
+ * @area_nslabs: Number of slots in each area.
+ * @areas:	Array of memory area descriptors.
+ * @slots:	Array of slot descriptors.
+ * @node:	Member of the IO TLB memory pool list.
+ * @rcu:	RCU head for swiotlb_dyn_free().
+ * @transient:  %true if transient memory pool.
+ */
+struct io_tlb_pool {
+	phys_addr_t start;
+	phys_addr_t end;
+	void *vaddr;
+	unsigned long nslabs;
+	bool late_alloc;
+	unsigned int nareas;
+	unsigned int area_nslabs;
+	struct io_tlb_area *areas;
+	struct io_tlb_slot *slots;
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+	struct list_head node;
+	struct rcu_head rcu;
+	bool transient;
+#endif
+};
+
+/**
+ * struct io_tlb_mem - Software IO TLB allocator
+ * @defpool:	Default (initial) IO TLB memory pool descriptor.
+ * @pool:	IO TLB memory pool descriptor (if not dynamic).
+ * @nslabs:	Total number of IO TLB slabs in all pools.
  * @debugfs:	The dentry to debugfs.
- * @late_alloc:	%true if allocated using the page allocator
  * @force_bounce: %true if swiotlb bouncing is forced
  * @for_alloc:  %true if the pool is used for memory allocation
- * @nareas:  The area number in the pool.
- * @area_nslabs: The slot number in the area.
+ * @can_grow:	%true if more pools can be allocated dynamically.
+ * @phys_limit:	Maximum allowed physical address.
+ * @lock:	Lock to synchronize changes to the list.
+ * @pools:	List of IO TLB memory pool descriptors (if dynamic).
+ * @dyn_alloc:	Dynamic IO TLB pool allocation work.
  * @total_used:	The total number of slots in the pool that are currently used
  *		across all areas. Used only for calculating used_hiwater in
  *		debugfs.
@@ -93,30 +122,64 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
  *		in debugfs.
  */
 struct io_tlb_mem {
-	phys_addr_t start;
-	phys_addr_t end;
-	void *vaddr;
+	struct io_tlb_pool defpool;
 	unsigned long nslabs;
 	struct dentry *debugfs;
-	bool late_alloc;
 	bool force_bounce;
 	bool for_alloc;
-	unsigned int nareas;
-	unsigned int area_nslabs;
-	struct io_tlb_area *areas;
-	struct io_tlb_slot *slots;
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+	bool can_grow;
+	u64 phys_limit;
+	spinlock_t lock;
+	struct list_head pools;
+	struct work_struct dyn_alloc;
+#endif
 #ifdef CONFIG_DEBUG_FS
 	atomic_long_t total_used;
 	atomic_long_t used_hiwater;
 #endif
 };
-extern struct io_tlb_mem io_tlb_default_mem;
 
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+
+struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr);
+
+#else
+
+static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev,
+						    phys_addr_t paddr)
+{
+	return &dev->dma_io_tlb_mem->defpool;
+}
+
+#endif
+
+/**
+ * is_swiotlb_buffer() - check if a physical address belongs to a swiotlb
+ * @dev:        Device which has mapped the buffer.
+ * @paddr:      Physical address within the DMA buffer.
+ *
+ * Check if @paddr points into a bounce buffer.
+ *
+ * Return:
+ * * %true if @paddr points into a bounce buffer
+ * * %false otherwise
+ */
 static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
 {
 	struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
 
-	return mem && paddr >= mem->start && paddr < mem->end;
+	if (!mem)
+		return false;
+
+	if (IS_ENABLED(CONFIG_SWIOTLB_DYNAMIC)) {
+		/* Pairs with smp_wmb() in swiotlb_find_slots() and
+		 * swiotlb_dyn_alloc(), which modify the RCU lists.
+		 */
+		smp_rmb();
+		return swiotlb_find_pool(dev, paddr);
+	}
+	return paddr >= mem->defpool.start && paddr < mem->defpool.end;
 }
 
 static inline bool is_swiotlb_force_bounce(struct device *dev)
@@ -128,13 +191,22 @@ static inline bool is_swiotlb_force_bounce(struct device *dev)
 
 void swiotlb_init(bool addressing_limited, unsigned int flags);
 void __init swiotlb_exit(void);
+void swiotlb_dev_init(struct device *dev);
 size_t swiotlb_max_mapping_size(struct device *dev);
+bool is_swiotlb_allocated(void);
 bool is_swiotlb_active(struct device *dev);
 void __init swiotlb_adjust_size(unsigned long size);
+phys_addr_t default_swiotlb_base(void);
+phys_addr_t default_swiotlb_limit(void);
 #else
 static inline void swiotlb_init(bool addressing_limited, unsigned int flags)
 {
 }
+
+static inline void swiotlb_dev_init(struct device *dev)
+{
+}
+
 static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr)
 {
 	return false;
@@ -151,6 +223,11 @@ static inline size_t swiotlb_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
+static inline bool is_swiotlb_allocated(void)
+{
+	return false;
+}
+
 static inline bool is_swiotlb_active(struct device *dev)
 {
 	return false;
@@ -159,6 +236,16 @@ static inline bool is_swiotlb_active(struct device *dev)
 static inline void swiotlb_adjust_size(unsigned long size)
 {
 }
+
+static inline phys_addr_t default_swiotlb_base(void)
+{
+	return 0;
+}
+
+static inline phys_addr_t default_swiotlb_limit(void)
+{
+	return 0;
+}
 #endif /* CONFIG_SWIOTLB */
 
 extern void swiotlb_print_info(void);
diff --git a/include/xen/xen.h b/include/xen/xen.h
index f989162983c3..a1e5b3f18d69 100644
--- a/include/xen/xen.h
+++ b/include/xen/xen.h
@@ -29,6 +29,12 @@ extern bool xen_pvh;
 
 extern uint32_t xen_start_flags;
 
+#ifdef CONFIG_XEN_PV
+extern bool xen_pv_pci_possible;
+#else
+#define xen_pv_pci_possible	0
+#endif
+
 #include <xen/interface/hvm/start_info.h>
 extern struct hvm_start_info pvh_start_info;
 void xen_prepare_pvh(void);