swiotlb: merge swiotlb-xen initialization into swiotlb

Reuse the generic swiotlb initialization for xen-swiotlb.  For ARM/ARM64
this works trivially, while for x86 xen_swiotlb_fixup needs to be passed
as the remap argument to swiotlb_init_remap/swiotlb_init_late.

Note that the lower bound of the swiotlb size is changed to the smaller
IO_TLB_MIN_SLABS based value with this patch, but that is fine as the
2MB value used in Xen before was just an optimization and is not the
hard lower bound.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

arch/arm/xen/mm.c

@@ -23,22 +23,20 @@
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
-unsigned long xen_get_swiotlb_free_pages(unsigned int order)
+static gfp_t xen_swiotlb_gfp(void)
 {
 	phys_addr_t base;
-	gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM;
 	u64 i;
 
 	for_each_mem_range(i, &base, NULL) {
 		if (base < (phys_addr_t)0xffffffff) {
 			if (IS_ENABLED(CONFIG_ZONE_DMA32))
-				flags |= __GFP_DMA32;
-			else
-				flags |= __GFP_DMA;
-			break;
+				return __GFP_DMA32;
+			return __GFP_DMA;
 		}
 	}
-	return __get_free_pages(flags, order);
+
+	return GFP_KERNEL;
 }
 
 static bool hypercall_cflush = false;
@@ -140,10 +138,13 @@ static int __init xen_mm_init(void)
 	if (!xen_swiotlb_detect())
 		return 0;
 
-	rc = xen_swiotlb_init();
 	/* we can work with the default swiotlb */
-	if (rc < 0 && rc != -EEXIST)
-		return rc;
+	if (!io_tlb_default_mem.nslabs) {
+		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/x86/include/asm/xen/page.h

@@ -357,9 +357,4 @@ static inline bool xen_arch_need_swiotlb(struct device *dev,
 	return false;
 }
 
-static inline unsigned long xen_get_swiotlb_free_pages(unsigned int order)
-{
-	return __get_free_pages(__GFP_NOWARN, order);
-}
-
 #endif /* _ASM_X86_XEN_PAGE_H */

arch/x86/kernel/pci-dma.c

@@ -72,15 +72,13 @@ static inline void __init pci_swiotlb_detect(void)
 #endif /* CONFIG_SWIOTLB */
 
 #ifdef CONFIG_SWIOTLB_XEN
-static bool xen_swiotlb;
-
 static void __init pci_xen_swiotlb_init(void)
 {
 	if (!xen_initial_domain() && !x86_swiotlb_enable)
 		return;
 	x86_swiotlb_enable = true;
-	xen_swiotlb = true;
-	xen_swiotlb_init_early();
+	x86_swiotlb_flags |= SWIOTLB_ANY;
+	swiotlb_init_remap(true, x86_swiotlb_flags, xen_swiotlb_fixup);
 	dma_ops = &xen_swiotlb_dma_ops;
 	if (IS_ENABLED(CONFIG_PCI))
 		pci_request_acs();
@@ -88,14 +86,16 @@ static void __init pci_xen_swiotlb_init(void)
 
 int pci_xen_swiotlb_init_late(void)
 {
-	int rc;
-
-	if (xen_swiotlb)
+	if (dma_ops == &xen_swiotlb_dma_ops)
 		return 0;
 
-	rc = xen_swiotlb_init();
-	if (rc)
-		return rc;
+	/* 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;

drivers/xen/swiotlb-xen.c

@@ -104,7 +104,7 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
-static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
+int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 {
 	int rc;
 	unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT);
@@ -130,132 +130,6 @@ static int xen_swiotlb_fixup(void *buf, unsigned long nslabs)
 	return 0;
 }
 
-enum xen_swiotlb_err {
-	XEN_SWIOTLB_UNKNOWN = 0,
-	XEN_SWIOTLB_ENOMEM,
-	XEN_SWIOTLB_EFIXUP
-};
-
-static const char *xen_swiotlb_error(enum xen_swiotlb_err err)
-{
-	switch (err) {
-	case XEN_SWIOTLB_ENOMEM:
-		return "Cannot allocate Xen-SWIOTLB buffer\n";
-	case XEN_SWIOTLB_EFIXUP:
-		return "Failed to get contiguous memory for DMA from Xen!\n"\
-		    "You either: don't have the permissions, do not have"\
-		    " enough free memory under 4GB, or the hypervisor memory"\
-		    " is too fragmented!";
-	default:
-		break;
-	}
-	return "";
-}
-
-int xen_swiotlb_init(void)
-{
-	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
-	unsigned long bytes = swiotlb_size_or_default();
-	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
-	unsigned int order, repeat = 3;
-	int rc = -ENOMEM;
-	char *start;
-
-	if (io_tlb_default_mem.nslabs) {
-		pr_warn("swiotlb buffer already initialized\n");
-		return -EEXIST;
-	}
-
-retry:
-	m_ret = XEN_SWIOTLB_ENOMEM;
-	order = get_order(bytes);
-
-	/*
-	 * Get IO TLB memory from any location.
-	 */
-#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
-#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
-	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		start = (void *)xen_get_swiotlb_free_pages(order);
-		if (start)
-			break;
-		order--;
-	}
-	if (!start)
-		goto exit;
-	if (order != get_order(bytes)) {
-		pr_warn("Warning: only able to allocate %ld MB for software IO TLB\n",
-			(PAGE_SIZE << order) >> 20);
-		nslabs = SLABS_PER_PAGE << order;
-		bytes = nslabs << IO_TLB_SHIFT;
-	}
-
-	/*
-	 * And replace that memory with pages under 4GB.
-	 */
-	rc = xen_swiotlb_fixup(start, nslabs);
-	if (rc) {
-		free_pages((unsigned long)start, order);
-		m_ret = XEN_SWIOTLB_EFIXUP;
-		goto error;
-	}
-	rc = swiotlb_late_init_with_tbl(start, nslabs);
-	if (rc)
-		return rc;
-	return 0;
-error:
-	if (nslabs > 1024 && repeat--) {
-		/* Min is 2MB */
-		nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
-		bytes = nslabs << IO_TLB_SHIFT;
-		pr_info("Lowering to %luMB\n", bytes >> 20);
-		goto retry;
-	}
-exit:
-	pr_err("%s (rc:%d)\n", xen_swiotlb_error(m_ret), rc);
-	return rc;
-}
-
-#ifdef CONFIG_X86
-void __init xen_swiotlb_init_early(void)
-{
-	unsigned long bytes = swiotlb_size_or_default();
-	unsigned long nslabs = bytes >> IO_TLB_SHIFT;
-	unsigned int repeat = 3;
-	char *start;
-	int rc;
-
-retry:
-	/*
-	 * Get IO TLB memory from any location.
-	 */
-	start = memblock_alloc(PAGE_ALIGN(bytes),
-			       IO_TLB_SEGSIZE << IO_TLB_SHIFT);
-	if (!start)
-		panic("%s: Failed to allocate %lu bytes\n",
-		      __func__, PAGE_ALIGN(bytes));
-
-	/*
-	 * And replace that memory with pages under 4GB.
-	 */
-	rc = xen_swiotlb_fixup(start, nslabs);
-	if (rc) {
-		memblock_free(start, PAGE_ALIGN(bytes));
-		if (nslabs > 1024 && repeat--) {
-			/* Min is 2MB */
-			nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE));
-			bytes = nslabs << IO_TLB_SHIFT;
-			pr_info("Lowering to %luMB\n", bytes >> 20);
-			goto retry;
-		}
-		panic("%s (rc:%d)", xen_swiotlb_error(XEN_SWIOTLB_EFIXUP), rc);
-	}
-
-	if (swiotlb_init_with_tbl(start, nslabs, SWIOTLB_VERBOSE))
-		panic("Cannot allocate SWIOTLB buffer");
-}
-#endif /* CONFIG_X86 */
-
 static void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,

include/xen/arm/page.h

@@ -115,6 +115,5 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 bool xen_arch_need_swiotlb(struct device *dev,
 			   phys_addr_t phys,
 			   dma_addr_t dev_addr);
-unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */

include/xen/swiotlb-xen.h

@@ -10,8 +10,12 @@ void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
 void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
 			     size_t size, enum dma_data_direction dir);
 
-int xen_swiotlb_init(void);
-void __init xen_swiotlb_init_early(void);
+#ifdef CONFIG_SWIOTLB_XEN
+int xen_swiotlb_fixup(void *buf, unsigned long nslabs);
+#else
+#define xen_swiotlb_fixup NULL
+#endif
+
 extern const struct dma_map_ops xen_swiotlb_dma_ops;
 
 #endif /* __LINUX_SWIOTLB_XEN_H */