Merge tag 'ntb-7.0' of https://github.com/jonmason/ntb

Pull NTB (PCIe non-transparent bridge) updates from Jon Mason:
 "NTB updates include debugfs improvements, correctness fixes, cleanups,
  and new hardware support:

  ntb_transport QP stats are converted to seq_file, a tx_memcpy_offload
  module parameter is introduced with associated ordering fixes, and a
  debugfs queue name truncation bug is corrected.

  Additional fixes address format specifier mismatches in ntb_tool and
  boundary conditions in the Switchtec driver, while unused MSI helpers
  are removed and the codebase migrates to dma_map_phys().

  Intel Gen6 (Diamond Rapids) NTB support is also added"

* tag 'ntb-7.0' of https://github.com/jonmason/ntb:
  NTB: ntb_transport: Use seq_file for QP stats debugfs
  NTB: ntb_transport: Fix too small buffer for debugfs_name
  ntb/ntb_tool: correct sscanf format for u64 and size_t in tool_peer_mw_trans_write
  ntb: intel: Add Intel Gen6 NTB support for DiamondRapids
  NTB/msi: Remove unused functions
  ntb: ntb_hw_switchtec: Increase MAX_MWS limit to 256
  ntb: ntb_hw_switchtec: Fix array-index-out-of-bounds access
  ntb: ntb_hw_switchtec: Fix shift-out-of-bounds for 0 mw lut
  NTB: epf: allow built-in build
  ntb: migrate to dma_map_phys instead of map_page
  NTB: ntb_transport: Add 'tx_memcpy_offload' module option
  NTB: ntb_transport: Remove unused 'retries' field from ntb_queue_entry

Author: torvalds

drivers/ntb/hw/epf/Kconfig

@@ -1,6 +1,5 @@
 config NTB_EPF
 	tristate "Generic EPF Non-Transparent Bridge support"
-	depends on m
 	help
 	  This driver supports EPF NTB on configurable endpoint.
 	  If unsure, say N.

drivers/ntb/hw/intel/ntb_hw_gen1.c

@@ -763,7 +763,8 @@ static ssize_t ndev_debugfs_read(struct file *filp, char __user *ubuf,
 		return ndev_ntb_debugfs_read(filp, ubuf, count, offp);
 	else if (pdev_is_gen3(ndev->ntb.pdev))
 		return ndev_ntb3_debugfs_read(filp, ubuf, count, offp);
-	else if (pdev_is_gen4(ndev->ntb.pdev) || pdev_is_gen5(ndev->ntb.pdev))
+	else if (pdev_is_gen4(ndev->ntb.pdev) || pdev_is_gen5(ndev->ntb.pdev) ||
+		 pdev_is_gen6(ndev->ntb.pdev))
 		return ndev_ntb4_debugfs_read(filp, ubuf, count, offp);
 
 	return -ENXIO;
@@ -1872,7 +1873,8 @@ static int intel_ntb_pci_probe(struct pci_dev *pdev,
 		rc = gen3_init_dev(ndev);
 		if (rc)
 			goto err_init_dev;
-	} else if (pdev_is_gen4(pdev) || pdev_is_gen5(pdev)) {
+	} else if (pdev_is_gen4(pdev) || pdev_is_gen5(pdev) ||
+		   pdev_is_gen6(pdev)) {
 		ndev->ntb.ops = &intel_ntb4_ops;
 		rc = intel_ntb_init_pci(ndev, pdev);
 		if (rc)
@@ -1903,7 +1905,8 @@ static int intel_ntb_pci_probe(struct pci_dev *pdev,
 err_register:
 	ndev_deinit_debugfs(ndev);
 	if (pdev_is_gen1(pdev) || pdev_is_gen3(pdev) ||
-	    pdev_is_gen4(pdev) || pdev_is_gen5(pdev))
+	    pdev_is_gen4(pdev) || pdev_is_gen5(pdev) ||
+	    pdev_is_gen6(pdev))
 		xeon_deinit_dev(ndev);
 err_init_dev:
 	intel_ntb_deinit_pci(ndev);
@@ -1920,7 +1923,8 @@ static void intel_ntb_pci_remove(struct pci_dev *pdev)
 	ntb_unregister_device(&ndev->ntb);
 	ndev_deinit_debugfs(ndev);
 	if (pdev_is_gen1(pdev) || pdev_is_gen3(pdev) ||
-	    pdev_is_gen4(pdev) || pdev_is_gen5(pdev))
+	    pdev_is_gen4(pdev) || pdev_is_gen5(pdev) ||
+	    pdev_is_gen6(pdev))
 		xeon_deinit_dev(ndev);
 	intel_ntb_deinit_pci(ndev);
 	kfree(ndev);
@@ -2049,6 +2053,8 @@ static const struct pci_device_id intel_ntb_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_ICX)},
 	/* GEN5 PCIe */
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_GNR)},
+	/* GEN6 PCIe */
+	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_DMR)},
 	{0}
 };
 MODULE_DEVICE_TABLE(pci, intel_ntb_pci_tbl);

drivers/ntb/hw/intel/ntb_hw_gen4.c

@@ -46,6 +46,16 @@ static const struct intel_ntb_alt_reg gen4_b2b_reg = {
 	.spad			= GEN4_EM_SPAD_OFFSET,
 };
 
+static u64 get_ppd0(struct pci_dev *pdev)
+{
+	if (pdev_is_gen4(pdev) || pdev_is_gen5(pdev))
+		return GEN4_PPD0_OFFSET;
+	else if (pdev_is_gen6(pdev))
+		return GEN6_PPD0_OFFSET;
+
+	return ULLONG_MAX;
+}
+
 static int gen4_poll_link(struct intel_ntb_dev *ndev)
 {
 	u16 reg_val;
@@ -183,7 +193,7 @@ static enum ntb_topo spr_ppd_topo(struct intel_ntb_dev *ndev, u32 ppd)
 int gen4_init_dev(struct intel_ntb_dev *ndev)
 {
 	struct pci_dev *pdev = ndev->ntb.pdev;
-	u32 ppd1/*, ppd0*/;
+	u32 ppd1;
 	u16 lnkctl;
 	int rc;
 
@@ -197,7 +207,7 @@ int gen4_init_dev(struct intel_ntb_dev *ndev)
 	ppd1 = ioread32(ndev->self_mmio + GEN4_PPD1_OFFSET);
 	if (pdev_is_ICX(pdev))
 		ndev->ntb.topo = gen4_ppd_topo(ndev, ppd1);
-	else if (pdev_is_SPR(pdev) || pdev_is_gen5(pdev))
+	else if (pdev_is_SPR(pdev) || pdev_is_gen5(pdev) || pdev_is_gen6(pdev))
 		ndev->ntb.topo = spr_ppd_topo(ndev, ppd1);
 	dev_dbg(&pdev->dev, "ppd %#x topo %s\n", ppd1,
 		ntb_topo_string(ndev->ntb.topo));
@@ -432,10 +442,12 @@ static int intel_ntb4_link_enable(struct ntb_dev *ntb,
 		enum ntb_speed max_speed, enum ntb_width max_width)
 {
 	struct intel_ntb_dev *ndev;
+	struct pci_dev *pdev;
 	u32 ntb_ctl, ppd0;
 	u16 lnkctl;
 
 	ndev = container_of(ntb, struct intel_ntb_dev, ntb);
+	pdev = ntb->pdev;
 
 	dev_dbg(&ntb->pdev->dev,
 			"Enabling link with max_speed %d max_width %d\n",
@@ -476,12 +488,12 @@ static int intel_ntb4_link_enable(struct ntb_dev *ntb,
 	iowrite16(lnkctl, ndev->self_mmio + GEN4_LINK_CTRL_OFFSET);
 
 	/* start link training in PPD0 */
-	ppd0 = ioread32(ndev->self_mmio + GEN4_PPD0_OFFSET);
+	ppd0 = ioread32(ndev->self_mmio + get_ppd0(pdev));
 	ppd0 |= GEN4_PPD_LINKTRN;
-	iowrite32(ppd0, ndev->self_mmio + GEN4_PPD0_OFFSET);
+	iowrite32(ppd0, ndev->self_mmio + get_ppd0(pdev));
 
 	/* make sure link training has started */
-	ppd0 = ioread32(ndev->self_mmio + GEN4_PPD0_OFFSET);
+	ppd0 = ioread32(ndev->self_mmio + get_ppd0(pdev));
 	if (!(ppd0 & GEN4_PPD_LINKTRN)) {
 		dev_warn(&ntb->pdev->dev, "Link is not training\n");
 		return -ENXIO;

drivers/ntb/hw/intel/ntb_hw_gen4.h

@@ -103,6 +103,8 @@
 #define NTB_LTR_IDLE_LATSCALE		0x0800  /* 1us scale */
 #define NTB_LTR_IDLE_REQMNT		0x8000  /* snoop req enable */
 
+#define GEN6_PPD0_OFFSET		0xf0d4
+
 ssize_t ndev_ntb4_debugfs_read(struct file *filp, char __user *ubuf,
 				      size_t count, loff_t *offp);
 int gen4_init_dev(struct intel_ntb_dev *ndev);

drivers/ntb/hw/intel/ntb_hw_intel.h

@@ -71,6 +71,7 @@
 #define PCI_DEVICE_ID_INTEL_NTB_B2B_SKX	0x201C
 #define PCI_DEVICE_ID_INTEL_NTB_B2B_ICX	0x347e
 #define PCI_DEVICE_ID_INTEL_NTB_B2B_GNR	0x0db4
+#define PCI_DEVICE_ID_INTEL_NTB_B2B_DMR	0x7868
 
 /* Ntb control and link status */
 #define NTB_CTL_CFG_LOCK		BIT(0)
@@ -235,4 +236,9 @@ static inline int pdev_is_gen5(struct pci_dev *pdev)
 	return pdev->device == PCI_DEVICE_ID_INTEL_NTB_B2B_GNR;
 }
 
+static inline int pdev_is_gen6(struct pci_dev *pdev)
+{
+	return pdev->device == PCI_DEVICE_ID_INTEL_NTB_B2B_DMR;
+}
+
 #endif

drivers/ntb/hw/mscc/ntb_hw_switchtec.c

@@ -29,7 +29,7 @@ MODULE_PARM_DESC(use_lut_mws,
 		 "Enable the use of the LUT based memory windows");
 
 #define SWITCHTEC_NTB_MAGIC 0x45CC0001
-#define MAX_MWS     128
+#define MAX_MWS     256
 
 struct shared_mw {
 	u32 magic;
@@ -1202,7 +1202,8 @@ static void switchtec_ntb_init_mw(struct switchtec_ntb *sndev)
 				       sndev->mmio_self_ctrl);
 
 	sndev->nr_lut_mw = ioread16(&sndev->mmio_self_ctrl->lut_table_entries);
-	sndev->nr_lut_mw = rounddown_pow_of_two(sndev->nr_lut_mw);
+	if (sndev->nr_lut_mw)
+		sndev->nr_lut_mw = rounddown_pow_of_two(sndev->nr_lut_mw);
 
 	dev_dbg(&sndev->stdev->dev, "MWs: %d direct, %d lut\n",
 		sndev->nr_direct_mw, sndev->nr_lut_mw);
@@ -1212,7 +1213,8 @@ static void switchtec_ntb_init_mw(struct switchtec_ntb *sndev)
 
 	sndev->peer_nr_lut_mw =
 		ioread16(&sndev->mmio_peer_ctrl->lut_table_entries);
-	sndev->peer_nr_lut_mw = rounddown_pow_of_two(sndev->peer_nr_lut_mw);
+	if (sndev->peer_nr_lut_mw)
+		sndev->peer_nr_lut_mw = rounddown_pow_of_two(sndev->peer_nr_lut_mw);
 
 	dev_dbg(&sndev->stdev->dev, "Peer MWs: %d direct, %d lut\n",
 		sndev->peer_nr_direct_mw, sndev->peer_nr_lut_mw);
@@ -1314,6 +1316,12 @@ static void switchtec_ntb_init_shared(struct switchtec_ntb *sndev)
 	for (i = 0; i < sndev->nr_lut_mw; i++) {
 		int idx = sndev->nr_direct_mw + i;
 
+		if (idx >= MAX_MWS) {
+			dev_err(&sndev->stdev->dev,
+				"Total number of MW cannot be bigger than %d", MAX_MWS);
+			break;
+		}
+
 		sndev->self_shared->mw_sizes[idx] = LUT_SIZE;
 	}
 }

drivers/ntb/msi.c

@@ -315,37 +315,6 @@ int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler,
 }
 EXPORT_SYMBOL(ntbm_msi_request_threaded_irq);
 
-static int ntbm_msi_callback_match(struct device *dev, void *res, void *data)
-{
-	struct ntb_dev *ntb = dev_ntb(dev);
-	struct ntb_msi_devres *dr = res;
-
-	return dr->ntb == ntb && dr->entry == data;
-}
-
-/**
- * ntbm_msi_free_irq() - free an interrupt
- * @ntb:	NTB device context
- * @irq:	Interrupt line to free
- * @dev_id:	Device identity to free
- *
- * This function should be used to manually free IRQs allocated with
- * ntbm_request_[threaded_]irq().
- */
-void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, void *dev_id)
-{
-	struct msi_desc *entry = irq_get_msi_desc(irq);
-
-	entry->write_msi_msg = NULL;
-	entry->write_msi_msg_data = NULL;
-
-	WARN_ON(devres_destroy(&ntb->dev, ntbm_msi_callback_release,
-			       ntbm_msi_callback_match, entry));
-
-	devm_free_irq(&ntb->dev, irq, dev_id);
-}
-EXPORT_SYMBOL(ntbm_msi_free_irq);
-
 /**
  * ntb_msi_peer_trigger() - Trigger an interrupt handler on a peer
  * @ntb:	NTB device context
@@ -373,36 +342,3 @@ int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer,
 	return 0;
 }
 EXPORT_SYMBOL(ntb_msi_peer_trigger);
-
-/**
- * ntb_msi_peer_addr() - Get the DMA address to trigger a peer's MSI interrupt
- * @ntb:	NTB device context
- * @peer:	Peer index
- * @desc:	MSI descriptor data which triggers the interrupt
- * @msi_addr:   Physical address to trigger the interrupt
- *
- * This function allows using DMA engines to trigger an interrupt
- * (for example, trigger an interrupt to process the data after
- * sending it). To trigger the interrupt, write @desc.data to the address
- * returned in @msi_addr
- *
- * Return: Zero on success, otherwise a negative error number.
- */
-int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer,
-		      struct ntb_msi_desc *desc,
-		      phys_addr_t *msi_addr)
-{
-	int peer_widx = ntb_peer_mw_count(ntb) - 1 - peer;
-	phys_addr_t mw_phys_addr;
-	int ret;
-
-	ret = ntb_peer_mw_get_addr(ntb, peer_widx, &mw_phys_addr, NULL);
-	if (ret)
-		return ret;
-
-	if (msi_addr)
-		*msi_addr = mw_phys_addr + desc->addr_offset;
-
-	return 0;
-}
-EXPORT_SYMBOL(ntb_msi_peer_addr);