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

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -696,7 +696,7 @@
 			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
-			[ARM64,KNL,CMA]
+			[KNL,CMA]
 			Sets the size of kernel per-numa memory area for
 			contiguous memory allocations. A value of 0 disables
 			per-numa CMA altogether. And If this option is not
@@ -706,6 +706,17 @@
 			which is located in node nid, if the allocation fails,
 			they will fallback to the global default memory area.
 
+	numa_cma=<node>:nn[MG][,<node>:nn[MG]]
+			[KNL,CMA]
+			Sets the size of kernel numa memory area for
+			contiguous memory allocations. It will reserve CMA
+			area for the specified node.
+
+			With numa CMA enabled, DMA users on node nid will
+			first try to allocate buffer from the numa area
+			which is located in node nid, if the allocation fails,
+			they will fallback to the global default memory area.
+
 	cmo_free_hint=	[PPC] Format: { yes | no }
 			Specify whether pages are marked as being inactive
 			when they are freed.  This is used in CMO environments

arch/arm/xen/mm.c

@@ -125,12 +125,10 @@ static int __init xen_mm_init(void)
 		return 0;
 
 	/* we can work with the default swiotlb */
-	if (!io_tlb_default_mem.nslabs) {
-		rc = swiotlb_init_late(swiotlb_size_or_default(),
-				       xen_swiotlb_gfp(), NULL);
-		if (rc < 0)
-			return rc;
-	}
+	rc = swiotlb_init_late(swiotlb_size_or_default(),
+			       xen_swiotlb_gfp(), NULL);
+	if (rc < 0)
+		return rc;
 
 	cflush.op = 0;
 	cflush.a.dev_bus_addr = 0;

arch/arm64/mm/init.c

@@ -461,8 +461,6 @@ void __init bootmem_init(void)
 	arm64_hugetlb_cma_reserve();
 #endif
 
-	dma_pernuma_cma_reserve();
-
 	kvm_hyp_reserve();
 
 	/*

arch/mips/pci/pci-octeon.c

@@ -664,7 +664,7 @@ static int __init octeon_pci_setup(void)
 
 		/* BAR1 movable regions contiguous to cover the swiotlb */
 		octeon_bar1_pci_phys =
-			io_tlb_default_mem.start & ~((1ull << 22) - 1);
+			default_swiotlb_base() & ~((1ull << 22) - 1);
 
 		for (index = 0; index < 32; index++) {
 			union cvmx_pci_bar1_indexx bar1_index;

arch/powerpc/kernel/dma-mask.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/dma-mapping.h>
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <asm/machdep.h>
 

arch/x86/include/asm/xen/swiotlb-xen.h

@@ -2,12 +2,6 @@
 #ifndef _ASM_X86_SWIOTLB_XEN_H
 #define _ASM_X86_SWIOTLB_XEN_H
 
-#ifdef CONFIG_SWIOTLB_XEN
-extern int pci_xen_swiotlb_init_late(void);
-#else
-static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
-#endif
-
 int xen_swiotlb_fixup(void *buf, unsigned long nslabs);
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
 				unsigned int address_bits,

arch/x86/kernel/pci-dma.c

@@ -72,9 +72,15 @@ static inline void __init pci_swiotlb_detect(void)
 #endif /* CONFIG_SWIOTLB */
 
 #ifdef CONFIG_SWIOTLB_XEN
+static bool xen_swiotlb_enabled(void)
+{
+	return xen_initial_domain() || x86_swiotlb_enable ||
+		(IS_ENABLED(CONFIG_XEN_PCIDEV_FRONTEND) && xen_pv_pci_possible);
+}
+
 static void __init pci_xen_swiotlb_init(void)
 {
-	if (!xen_initial_domain() && !x86_swiotlb_enable)
+	if (!xen_swiotlb_enabled())
 		return;
 	x86_swiotlb_enable = true;
 	x86_swiotlb_flags |= SWIOTLB_ANY;
@@ -83,27 +89,6 @@ static void __init pci_xen_swiotlb_init(void)
 	if (IS_ENABLED(CONFIG_PCI))
 		pci_request_acs();
 }
-
-int pci_xen_swiotlb_init_late(void)
-{
-	if (dma_ops == &xen_swiotlb_dma_ops)
-		return 0;
-
-	/* we can work with the default swiotlb */
-	if (!io_tlb_default_mem.nslabs) {
-		int rc = swiotlb_init_late(swiotlb_size_or_default(),
-					   GFP_KERNEL, xen_swiotlb_fixup);
-		if (rc < 0)
-			return rc;
-	}
-
-	/* XXX: this switches the dma ops under live devices! */
-	dma_ops = &xen_swiotlb_dma_ops;
-	if (IS_ENABLED(CONFIG_PCI))
-		pci_request_acs();
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
 #else
 static inline void __init pci_xen_swiotlb_init(void)
 {

arch/x86/xen/setup.c

@@ -44,6 +44,9 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 /* Number of pages released from the initial allocation. */
 unsigned long xen_released_pages;
 
+/* Memory map would allow PCI passthrough. */
+bool xen_pv_pci_possible;
+
 /* E820 map used during setting up memory. */
 static struct e820_table xen_e820_table __initdata;
 
@@ -814,6 +817,9 @@ char * __init xen_memory_setup(void)
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
 
+		if (type == E820_TYPE_RESERVED)
+			xen_pv_pci_possible = true;
+
 		if (type == E820_TYPE_RAM) {
 			if (addr < mem_end) {
 				chunk_size = min(size, mem_end - addr);

drivers/base/core.c

@@ -3108,9 +3108,7 @@ void device_initialize(struct device *dev)
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	dev->dma_coherent = dma_default_coherent;
 #endif
-#ifdef CONFIG_SWIOTLB
-	dev->dma_io_tlb_mem = &io_tlb_default_mem;
-#endif
+	swiotlb_dev_init(dev);
 }
 EXPORT_SYMBOL_GPL(device_initialize);
 

drivers/pci/xen-pcifront.c

@@ -22,7 +22,6 @@
 #include <linux/bitops.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
-#include <linux/swiotlb.h>
 #include <xen/platform_pci.h>
 
 #include <asm/xen/swiotlb-xen.h>
@@ -669,11 +668,6 @@ static int pcifront_connect_and_init_dma(struct pcifront_device *pdev)
 
 	spin_unlock(&pcifront_dev_lock);
 
-	if (!err && !is_swiotlb_active(&pdev->xdev->dev)) {
-		err = pci_xen_swiotlb_init_late();
-		if (err)
-			dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n");
-	}
 	return err;
 }
 

drivers/xen/swiotlb-xen.c

@@ -381,7 +381,7 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 static int
 xen_swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return xen_phys_to_dma(hwdev, io_tlb_default_mem.end - 1) <= mask;
+	return xen_phys_to_dma(hwdev, default_swiotlb_limit()) <= mask;
 }
 
 const struct dma_map_ops xen_swiotlb_dma_ops = {

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.
@@ -731,6 +734,11 @@ struct device {
 #endif
 #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;

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

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)
 {