Merge branch 'pci/endpoint'

- For fixed-size BARs, retain both the actual size and the possibly larger
  size allocated to accommodate iATU alignment requirements (Jerome Brunet)

- Simplify ctrl/SPAD space allocation and avoid allocating more space than
  needed (Jerome Brunet)

- Correct MSI-X PBA offset calculations for DesignWare and Cadence endpoint
  controllers (Niklas Cassel)

- Align the return value (number of interrupts) encoding for
  pci_epc_get_msi()/pci_epc_ops::get_msi() and
  pci_epc_get_msix()/pci_epc_ops::get_msix() (Niklas Cassel)

- Align the nr_irqs parameter encoding for
  pci_epc_set_msi()/pci_epc_ops::set_msi() and
  pci_epc_set_msix()/pci_epc_ops::set_msix() (Niklas Cassel)

* pci/endpoint:
  PCI: endpoint: Align pci_epc_set_msix(), pci_epc_ops::set_msix() nr_irqs encoding
  PCI: endpoint: Align pci_epc_set_msi(), pci_epc_ops::set_msi() nr_irqs encoding
  PCI: endpoint: Align pci_epc_get_msix(), pci_epc_ops::get_msix() return value encoding
  PCI: endpoint: Align pci_epc_get_msi(), pci_epc_ops::get_msi() return value encoding
  PCI: cadence-ep: Correct PBA offset in .set_msix() callback
  PCI: dwc: ep: Correct PBA offset in .set_msix() callback
  PCI: endpoint: pci-epf-vntb: Simplify ctrl/SPAD space allocation
  PCI: endpoint: Retain fixed-size BAR size as well as aligned size

drivers/pci/controller/cadence/pcie-cadence-ep.c

@@ -220,10 +220,11 @@ static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 	clear_bit(r, &ep->ob_region_map);
 }
 
-static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 mmc)
+static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET;
 	u16 flags;
 
@@ -262,7 +263,7 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
 	 */
 	mme = FIELD_GET(PCI_MSI_FLAGS_QSIZE, flags);
 
-	return mme;
+	return 1 << mme;
 }
 
 static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
@@ -281,12 +282,11 @@ static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 
 	val &= PCI_MSIX_FLAGS_QSIZE;
 
-	return val;
+	return val + 1;
 }
 
 static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
-				 u16 interrupts, enum pci_barno bir,
-				 u32 offset)
+				 u16 nr_irqs, enum pci_barno bir, u32 offset)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
@@ -298,7 +298,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
 	reg = cap + PCI_MSIX_FLAGS;
 	val = cdns_pcie_ep_fn_readw(pcie, fn, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
-	val |= interrupts;
+	val |= nr_irqs - 1; /* encoded as N-1 */
 	cdns_pcie_ep_fn_writew(pcie, fn, reg, val);
 
 	/* Set MSI-X BAR and offset */
@@ -308,7 +308,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn,
 
 	/* Set PBA BAR and offset.  BAR must match MSI-X BAR */
 	reg = cap + PCI_MSIX_PBA;
-	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
+	val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir;
 	cdns_pcie_ep_fn_writel(pcie, fn, reg, val);
 
 	return 0;

drivers/pci/controller/dwc/pcie-designware-ep.c

@@ -532,15 +532,16 @@ static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 
 	val = FIELD_GET(PCI_MSI_FLAGS_QSIZE, val);
 
-	return val;
+	return 1 << val;
 }
 
 static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			      u8 interrupts)
+			      u8 nr_irqs)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dw_pcie_ep_func *ep_func;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 val, reg;
 
 	ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no);
@@ -550,7 +551,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	reg = ep_func->msi_cap + PCI_MSI_FLAGS;
 	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSI_FLAGS_QMASK;
-	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts);
+	val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, mmc);
 	dw_pcie_dbi_ro_wr_en(pci);
 	dw_pcie_ep_writew_dbi(ep, func_no, reg, val);
 	dw_pcie_dbi_ro_wr_dis(pci);
@@ -575,11 +576,11 @@ static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 
 	val &= PCI_MSIX_FLAGS_QSIZE;
 
-	return val;
+	return val + 1;
 }
 
 static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			       u16 interrupts, enum pci_barno bir, u32 offset)
+			       u16 nr_irqs, enum pci_barno bir, u32 offset)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
@@ -595,7 +596,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	reg = ep_func->msix_cap + PCI_MSIX_FLAGS;
 	val = dw_pcie_ep_readw_dbi(ep, func_no, reg);
 	val &= ~PCI_MSIX_FLAGS_QSIZE;
-	val |= interrupts;
+	val |= nr_irqs - 1; /* encoded as N-1 */
 	dw_pcie_writew_dbi(pci, reg, val);
 
 	reg = ep_func->msix_cap + PCI_MSIX_TABLE;
@@ -603,7 +604,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	reg = ep_func->msix_cap + PCI_MSIX_PBA;
-	val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir;
+	val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir;
 	dw_pcie_ep_writel_dbi(ep, func_no, reg, val);
 
 	dw_pcie_dbi_ro_wr_dis(pci);

drivers/pci/controller/pcie-rcar-ep.c

@@ -256,15 +256,15 @@ static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn,
 	clear_bit(atu_index + 1, ep->ib_window_map);
 }
 
-static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
-				u8 interrupts)
+static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs)
 {
 	struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc);
 	struct rcar_pcie *pcie = &ep->pcie;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 flags;
 
 	flags = rcar_pci_read_reg(pcie, MSICAP(fn));
-	flags |= interrupts << MSICAP0_MMESCAP_OFFSET;
+	flags |= mmc << MSICAP0_MMESCAP_OFFSET;
 	rcar_pci_write_reg(pcie, flags, MSICAP(fn));
 
 	return 0;
@@ -280,7 +280,7 @@ static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
 	if (!(flags & MSICAP0_MSIE))
 		return -EINVAL;
 
-	return ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET);
+	return 1 << ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET);
 }
 
 static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,

drivers/pci/controller/pcie-rockchip-ep.c

@@ -308,10 +308,11 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 }
 
 static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
-				    u8 multi_msg_cap)
+				    u8 nr_irqs)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 	struct rockchip_pcie *rockchip = &ep->rockchip;
+	u8 mmc = order_base_2(nr_irqs);
 	u32 flags;
 
 	flags = rockchip_pcie_read(rockchip,
@@ -319,7 +320,7 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn,
 				   ROCKCHIP_PCIE_EP_MSI_CTRL_REG);
 	flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK;
 	flags |=
-	   (multi_msg_cap << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) |
+	   (mmc << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) |
 	   (PCI_MSI_FLAGS_64BIT << ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET);
 	flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP;
 	rockchip_pcie_write(rockchip, flags,
@@ -340,8 +341,8 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn)
 	if (!(flags & ROCKCHIP_PCIE_EP_MSI_CTRL_ME))
 		return -EINVAL;
 
-	return ((flags & ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK) >>
-			ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET);
+	return 1 << ((flags & ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK) >>
+		     ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET);
 }
 
 static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn,

drivers/pci/endpoint/functions/pci-epf-vntb.c

@@ -408,11 +408,9 @@ static void epf_ntb_config_spad_bar_free(struct epf_ntb *ntb)
  */
 static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
 {
-	size_t align;
 	enum pci_barno barno;
 	struct epf_ntb_ctrl *ctrl;
 	u32 spad_size, ctrl_size;
-	u64 size;
 	struct pci_epf *epf = ntb->epf;
 	struct device *dev = &epf->dev;
 	u32 spad_count;
@@ -422,31 +420,13 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb)
 								epf->func_no,
 								epf->vfunc_no);
 	barno = ntb->epf_ntb_bar[BAR_CONFIG];
-	size = epc_features->bar[barno].fixed_size;
-	align = epc_features->align;
-
-	if ((!IS_ALIGNED(size, align)))
-		return -EINVAL;
-
 	spad_count = ntb->spad_count;
 
-	ctrl_size = sizeof(struct epf_ntb_ctrl);
+	ctrl_size = ALIGN(sizeof(struct epf_ntb_ctrl), sizeof(u32));
 	spad_size = 2 * spad_count * sizeof(u32);
 
-	if (!align) {
-		ctrl_size = roundup_pow_of_two(ctrl_size);
-		spad_size = roundup_pow_of_two(spad_size);
-	} else {
-		ctrl_size = ALIGN(ctrl_size, align);
-		spad_size = ALIGN(spad_size, align);
-	}
-
-	if (!size)
-		size = ctrl_size + spad_size;
-	else if (size < ctrl_size + spad_size)
-		return -EINVAL;
-
-	base = pci_epf_alloc_space(epf, size, barno, epc_features, 0);
+	base = pci_epf_alloc_space(epf, ctrl_size + spad_size,
+				   barno, epc_features, 0);
 	if (!base) {
 		dev_err(dev, "Config/Status/SPAD alloc region fail\n");
 		return -ENOMEM;

drivers/pci/endpoint/pci-epc-core.c

@@ -293,8 +293,6 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 	if (interrupt < 0)
 		return 0;
 
-	interrupt = 1 << interrupt;
-
 	return interrupt;
 }
 EXPORT_SYMBOL_GPL(pci_epc_get_msi);
@@ -304,28 +302,25 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msi);
  * @epc: the EPC device on which MSI has to be configured
  * @func_no: the physical endpoint function number in the EPC device
  * @vfunc_no: the virtual endpoint function number in the physical function
- * @interrupts: number of MSI interrupts required by the EPF
+ * @nr_irqs: number of MSI interrupts required by the EPF
  *
  * Invoke to set the required number of MSI interrupts.
  */
-int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 interrupts)
+int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 nr_irqs)
 {
 	int ret;
-	u8 encode_int;
 
 	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
-	if (interrupts < 1 || interrupts > 32)
+	if (nr_irqs < 1 || nr_irqs > 32)
 		return -EINVAL;
 
 	if (!epc->ops->set_msi)
 		return 0;
 
-	encode_int = order_base_2(interrupts);
-
 	mutex_lock(&epc->lock);
-	ret = epc->ops->set_msi(epc, func_no, vfunc_no, encode_int);
+	ret = epc->ops->set_msi(epc, func_no, vfunc_no, nr_irqs);
 	mutex_unlock(&epc->lock);
 
 	return ret;
@@ -357,7 +352,7 @@ int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no)
 	if (interrupt < 0)
 		return 0;
 
-	return interrupt + 1;
+	return interrupt;
 }
 EXPORT_SYMBOL_GPL(pci_epc_get_msix);
 
@@ -366,29 +361,28 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msix);
  * @epc: the EPC device on which MSI-X has to be configured
  * @func_no: the physical endpoint function number in the EPC device
  * @vfunc_no: the virtual endpoint function number in the physical function
- * @interrupts: number of MSI-X interrupts required by the EPF
+ * @nr_irqs: number of MSI-X interrupts required by the EPF
  * @bir: BAR where the MSI-X table resides
  * @offset: Offset pointing to the start of MSI-X table
  *
  * Invoke to set the required number of MSI-X interrupts.
  */
-int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		     u16 interrupts, enum pci_barno bir, u32 offset)
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u16 nr_irqs,
+		     enum pci_barno bir, u32 offset)
 {
 	int ret;
 
 	if (!pci_epc_function_is_valid(epc, func_no, vfunc_no))
 		return -EINVAL;
 
-	if (interrupts < 1 || interrupts > 2048)
+	if (nr_irqs < 1 || nr_irqs > 2048)
 		return -EINVAL;
 
 	if (!epc->ops->set_msix)
 		return 0;
 
 	mutex_lock(&epc->lock);
-	ret = epc->ops->set_msix(epc, func_no, vfunc_no, interrupts - 1, bir,
-				 offset);
+	ret = epc->ops->set_msix(epc, func_no, vfunc_no, nr_irqs, bir, offset);
 	mutex_unlock(&epc->lock);
 
 	return ret;

drivers/pci/endpoint/pci-epf-core.c

@@ -236,12 +236,13 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar,
 	}
 
 	dev = epc->dev.parent;
-	dma_free_coherent(dev, epf_bar[bar].size, addr,
+	dma_free_coherent(dev, epf_bar[bar].aligned_size, addr,
 			  epf_bar[bar].phys_addr);
 
 	epf_bar[bar].phys_addr = 0;
 	epf_bar[bar].addr = NULL;
 	epf_bar[bar].size = 0;
+	epf_bar[bar].aligned_size = 0;
 	epf_bar[bar].barno = 0;
 	epf_bar[bar].flags = 0;
 }
@@ -264,7 +265,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			  enum pci_epc_interface_type type)
 {
 	u64 bar_fixed_size = epc_features->bar[bar].fixed_size;
-	size_t align = epc_features->align;
+	size_t aligned_size, align = epc_features->align;
 	struct pci_epf_bar *epf_bar;
 	dma_addr_t phys_addr;
 	struct pci_epc *epc;
@@ -285,12 +286,18 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			return NULL;
 		}
 		size = bar_fixed_size;
+	} else {
+		/* BAR size must be power of two */
+		size = roundup_pow_of_two(size);
 	}
 
-	if (align)
-		size = ALIGN(size, align);
-	else
-		size = roundup_pow_of_two(size);
+	/*
+	 * Allocate enough memory to accommodate the iATU alignment
+	 * requirement.  In most cases, this will be the same as .size but
+	 * it might be different if, for example, the fixed size of a BAR
+	 * is smaller than align.
+	 */
+	aligned_size = align ? ALIGN(size, align) : size;
 
 	if (type == PRIMARY_INTERFACE) {
 		epc = epf->epc;
@@ -301,7 +308,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 	}
 
 	dev = epc->dev.parent;
-	space = dma_alloc_coherent(dev, size, &phys_addr, GFP_KERNEL);
+	space = dma_alloc_coherent(dev, aligned_size, &phys_addr, GFP_KERNEL);
 	if (!space) {
 		dev_err(dev, "failed to allocate mem space\n");
 		return NULL;
@@ -310,6 +317,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 	epf_bar[bar].phys_addr = phys_addr;
 	epf_bar[bar].addr = space;
 	epf_bar[bar].size = size;
+	epf_bar[bar].aligned_size = aligned_size;
 	epf_bar[bar].barno = bar;
 	if (upper_32_bits(size) || epc_features->bar[bar].only_64bit)
 		epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64;

include/linux/pci-epc.h

@@ -100,10 +100,10 @@ struct pci_epc_ops {
 	void	(*unmap_addr)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			      phys_addr_t addr);
 	int	(*set_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			   u8 interrupts);
+			   u8 nr_irqs);
 	int	(*get_msi)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*set_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-			    u16 interrupts, enum pci_barno, u32 offset);
+			    u16 nr_irqs, enum pci_barno, u32 offset);
 	int	(*get_msix)(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			     unsigned int type, u16 interrupt_num);
@@ -286,11 +286,10 @@ int pci_epc_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 		     u64 pci_addr, size_t size);
 void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr);
-int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		    u8 interrupts);
+int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 nr_irqs);
 int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
-int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
-		     u16 interrupts, enum pci_barno, u32 offset);
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u16 nr_irqs,
+		     enum pci_barno, u32 offset);
 int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no);
 int pci_epc_map_msi_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			phys_addr_t phys_addr, u8 interrupt_num,

include/linux/pci-epf.h

@@ -114,6 +114,8 @@ struct pci_epf_driver {
  * @phys_addr: physical address that should be mapped to the BAR
  * @addr: virtual address corresponding to the @phys_addr
  * @size: the size of the address space present in BAR
+ * @aligned_size: the size actually allocated to accommodate the iATU alignment
+ *                requirement
  * @barno: BAR number
  * @flags: flags that are set for the BAR
  */
@@ -121,6 +123,7 @@ struct pci_epf_bar {
 	dma_addr_t	phys_addr;
 	void		*addr;
 	size_t		size;
+	size_t		aligned_size;
 	enum pci_barno	barno;
 	int		flags;
 };