Merge branch 'stable/late-swiotlb.v3.3' into stable/for-linus-3.7

* stable/late-swiotlb.v3.3:
xen/swiotlb: Fix compile warnings when using plain integer instead of NULL pointer.
xen/swiotlb: Remove functions not needed anymore.
xen/pcifront: Use Xen-SWIOTLB when initting if required.
xen/swiotlb: For early initialization, return zero on success.
xen/swiotlb: Use the swiotlb_late_init_with_tbl to init Xen-SWIOTLB late when PV PCI is used.
xen/swiotlb: Move the error strings to its own function.
xen/swiotlb: Move the nr_tbl determination in its own function.
swiotlb: add the late swiotlb initialization function with iotlb memory
xen/swiotlb: With more than 4GB on 64-bit, disable the native SWIOTLB.
xen/swiotlb: Simplify the logic.

Conflicts:
arch/x86/xen/pci-swiotlb-xen.c

Signed-off-by: Konrad Rzeszutek Wilk <[e-mail]>

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

···
 extern int xen_swiotlb;
 extern int __init pci_xen_swiotlb_detect(void);
 extern void __init pci_xen_swiotlb_init(void);
+extern int pci_xen_swiotlb_init_late(void);
 #else
 #define xen_swiotlb (0)
 static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
 static inline void __init pci_xen_swiotlb_init(void) { }
+static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
 #endif
 
 #endif /* _ASM_X86_SWIOTLB_XEN_H */

arch/x86/xen/pci-swiotlb-xen.c

···
 #include <xen/xen.h>
 #include <asm/iommu_table.h>
 
+
 #include <asm/xen/swiotlb-xen.h>
+#ifdef CONFIG_X86_64
+#include <asm/iommu.h>
+#include <asm/dma.h>
+#endif
+#include <linux/export.h>
+
 int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
···
 int __init pci_xen_swiotlb_detect(void)
 {
 
+	if (!xen_pv_domain())
+		return 0;
+
 	/* If running as PV guest, either iommu=soft, or swiotlb=force will
 	 * activate this IOMMU. If running as PV privileged, activate it
 	 * irregardless.
 	 */
-	if ((xen_initial_domain() || swiotlb || swiotlb_force) &&
-	    (xen_pv_domain()))
+	if ((xen_initial_domain() || swiotlb || swiotlb_force))
 		xen_swiotlb = 1;
 
 	/* If we are running under Xen, we MUST disable the native SWIOTLB.
 	 * Don't worry about swiotlb_force flag activating the native, as
 	 * the 'swiotlb' flag is the only one turning it on. */
-	if (xen_pv_domain())
-		swiotlb = 0;
+	swiotlb = 0;
 
+#ifdef CONFIG_X86_64
+	/* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0
+	 * (so no iommu=X command line over-writes).
+	 * Considering that PV guests do not want the *native SWIOTLB* but
+	 * only Xen SWIOTLB it is not useful to us so set no_iommu=1 here.
+	 */
+	if (max_pfn > MAX_DMA32_PFN)
+		no_iommu = 1;
+#endif
 	return xen_swiotlb;
 }
 
 void __init pci_xen_swiotlb_init(void)
 {
 	if (xen_swiotlb) {
-		xen_swiotlb_init(1);
+		xen_swiotlb_init(1, true /* early */);
 		dma_ops = &xen_swiotlb_dma_ops;
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
 }
+
+int pci_xen_swiotlb_init_late(void)
+{
+	int rc;
+
+	if (xen_swiotlb)
+		return 0;
+
+	rc = xen_swiotlb_init(1, false /* late */);
+	if (rc)
+		return rc;
+
+	dma_ops = &xen_swiotlb_dma_ops;
+	/* Make sure ACS will be enabled */
+	pci_request_acs();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+
 IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
 		  NULL,
 		  pci_xen_swiotlb_init,

drivers/pci/xen-pcifront.c

···
 #include <linux/bitops.h>
 #include <linux/time.h>
 
+#include <asm/xen/swiotlb-xen.h>
 #define INVALID_GRANT_REF (0)
 #define INVALID_EVTCHN    (-1)
 
···
 	schedule_pcifront_aer_op(pdev);
 	return IRQ_HANDLED;
 }
-static int pcifront_connect(struct pcifront_device *pdev)
+static int pcifront_connect_and_init_dma(struct pcifront_device *pdev)
 {
 	int err = 0;
 
···
 		dev_err(&pdev->xdev->dev, "PCI frontend already installed!\n");
 		err = -EEXIST;
 	}
-
 	spin_unlock(&pcifront_dev_lock);
 
+	if (!err && !swiotlb_nr_tbl()) {
+		err = pci_xen_swiotlb_init_late();
+		if (err)
+			dev_err(&pdev->xdev->dev, "Could not setup SWIOTLB!\n");
+	}
 	return err;
 }
 
···
 	    XenbusStateInitialised)
 		goto out;
 
-	err = pcifront_connect(pdev);
+	err = pcifront_connect_and_init_dma(pdev);
 	if (err) {
 		xenbus_dev_fatal(pdev->xdev, err,
-				 "Error connecting PCI Frontend");
+				 "Error setting up PCI Frontend");
 		goto out;
 	}
 

drivers/xen/swiotlb-xen.c

···
 	} while (i < nslabs);
 	return 0;
 }
-
-void __init xen_swiotlb_init(int verbose)
+static unsigned long xen_set_nslabs(unsigned long nr_tbl)
 {
-	unsigned long bytes;
-	int rc = -ENOMEM;
-	unsigned long nr_tbl;
-	char *m = NULL;
-	unsigned int repeat = 3;
-
-	nr_tbl = swiotlb_nr_tbl();
-	if (nr_tbl)
-		xen_io_tlb_nslabs = nr_tbl;
-	else {
+	if (!nr_tbl) {
 		xen_io_tlb_nslabs = (64 * 1024 * 1024 >> IO_TLB_SHIFT);
 		xen_io_tlb_nslabs = ALIGN(xen_io_tlb_nslabs, IO_TLB_SEGSIZE);
-	}
-retry:
-	bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+	} else
+		xen_io_tlb_nslabs = nr_tbl;
 
+	return xen_io_tlb_nslabs << IO_TLB_SHIFT;
+}
+
+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 __ref xen_swiotlb_init(int verbose, bool early)
+{
+	unsigned long bytes, order;
+	int rc = -ENOMEM;
+	enum xen_swiotlb_err m_ret = XEN_SWIOTLB_UNKNOWN;
+	unsigned int repeat = 3;
+
+	xen_io_tlb_nslabs = swiotlb_nr_tbl();
+retry:
+	bytes = xen_set_nslabs(xen_io_tlb_nslabs);
+	order = get_order(xen_io_tlb_nslabs << IO_TLB_SHIFT);
 	/*
 	 * Get IO TLB memory from any location.
 	 */
-	xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	if (early)
+		xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
+	else {
+#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) {
+			xen_io_tlb_start = (void *)__get_free_pages(__GFP_NOWARN, order);
+			if (xen_io_tlb_start)
+				break;
+			order--;
+		}
+		if (order != get_order(bytes)) {
+			pr_warn("Warning: only able to allocate %ld MB "
+				"for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+			xen_io_tlb_nslabs = SLABS_PER_PAGE << order;
+			bytes = xen_io_tlb_nslabs << IO_TLB_SHIFT;
+		}
+	}
 	if (!xen_io_tlb_start) {
-		m = "Cannot allocate Xen-SWIOTLB buffer!\n";
+		m_ret = XEN_SWIOTLB_ENOMEM;
 		goto error;
 	}
 	xen_io_tlb_end = xen_io_tlb_start + bytes;
···
 			       bytes,
 			       xen_io_tlb_nslabs);
 	if (rc) {
-		free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
-		m = "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!";
+		if (early)
+			free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
+		else {
+			free_pages((unsigned long)xen_io_tlb_start, order);
+			xen_io_tlb_start = NULL;
+		}
+		m_ret = XEN_SWIOTLB_EFIXUP;
 		goto error;
 	}
 	start_dma_addr = xen_virt_to_bus(xen_io_tlb_start);
-	swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
-
-	return;
+	if (early) {
+		swiotlb_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs, verbose);
+		rc = 0;
+	} else
+		rc = swiotlb_late_init_with_tbl(xen_io_tlb_start, xen_io_tlb_nslabs);
+	return rc;
 error:
 	if (repeat--) {
 		xen_io_tlb_nslabs = max(1024UL, /* Min is 2MB */
···
 		      (xen_io_tlb_nslabs << IO_TLB_SHIFT) >> 20);
 		goto retry;
 	}
-	xen_raw_printk("%s (rc:%d)", m, rc);
-	panic("%s (rc:%d)", m, rc);
+	pr_err("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	if (early)
+		panic("%s (rc:%d)", xen_swiotlb_error(m_ret), rc);
+	else
+		free_pages((unsigned long)xen_io_tlb_start, order);
+	return rc;
 }
-
 void *
 xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,

include/linux/swiotlb.h

···
 extern void swiotlb_init(int verbose);
 extern void swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
+extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
 
 /*
  * Enumeration for sync targets

include/xen/swiotlb-xen.h

···
 
 #include <linux/swiotlb.h>
 
-extern void xen_swiotlb_init(int verbose);
+extern int xen_swiotlb_init(int verbose, bool early);
 
 extern void
 *xen_swiotlb_alloc_coherent(struct device *hwdev, size_t size,

lib/swiotlb.c

···
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
-void __init
+static void __init
 swiotlb_init_with_default_size(size_t default_size, int verbose)
 {
 	unsigned long bytes;
···
 int
 swiotlb_late_init_with_default_size(size_t default_size)
 {
-	unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
+	unsigned long bytes, req_nslabs = io_tlb_nslabs;
 	unsigned int order;
+	int rc = 0;
 
 	if (!io_tlb_nslabs) {
 		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
···
 		order--;
 	}
 
-	if (!io_tlb_start)
-		goto cleanup1;
-
+	if (!io_tlb_start) {
+		io_tlb_nslabs = req_nslabs;
+		return -ENOMEM;
+	}
 	if (order != get_order(bytes)) {
 		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
 		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
 		io_tlb_nslabs = SLABS_PER_PAGE << order;
-		bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 	}
+	rc = swiotlb_late_init_with_tbl(io_tlb_start, io_tlb_nslabs);
+	if (rc)
+		free_pages((unsigned long)io_tlb_start, order);
+	return rc;
+}
+
+int
+swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
+{
+	unsigned long i, bytes;
+
+	bytes = nslabs << IO_TLB_SHIFT;
+
+	io_tlb_nslabs = nslabs;
+	io_tlb_start = tlb;
 	io_tlb_end = io_tlb_start + bytes;
+
 	memset(io_tlb_start, 0, bytes);
 
 	/*
···
 	io_tlb_list = NULL;
 cleanup2:
 	io_tlb_end = NULL;
-	free_pages((unsigned long)io_tlb_start, order);
 	io_tlb_start = NULL;
-cleanup1:
-	io_tlb_nslabs = req_nslabs;
+	io_tlb_nslabs = 0;
 	return -ENOMEM;
 }