PCI: dwc: Support ECAM mechanism by enabling iATU 'CFG Shift Feature'

Designware databook r5.20a, sec 3.10.10.3 documents the 'CFG Shift Feature'
of the internal Address Translation Unit (iATU). When this feature is
enabled, it shifts/maps the BDF contained in the bits [27:12] of the target
address in MEM TLP to become BDF of the CFG TLP. This essentially
implements the Enhanced Configuration Address Mapping (ECAM) mechanism as
defined in PCIe r6.0, sec 7.2.2.

Currently, the driver is not making use of this CFG shift feature, thereby
creating the iATU outbound map for each config access to the devices,
causing latency and wasting CPU cycles.

So to avoid this, configure the controller to enable CFG shift feature by
enabling the 'CFG Shift' bit of the 'iATU Control 2 Register'.

As a result of enabling CFG shift (ECAM), there is no longer a need to map
the DBI register space separately as the DBI region falls under the
'config' space used for ECAM (as DBI is used to access the Root Port).

For enabling ECAM using CFG shift, the platform has to satisfy following
requirements:

  1. Size of the 'config' memory space to be used as ECAM memory should be
     able to accommodate the number of buses defined in the 'bus-range'
     property of the host bridge DT node.

  2. The 'config' memory space should be 256 MiB aligned. This requirement
     comes from PCIe r6.0, sec 7.2.2, which says the base address of ECAM
     memory should be aligned to a 2^(n+20) byte address boundary. For the
     DWC cores, n is 8, so this results in 2^28 byte alignment requirement.

It should be noted that some DWC vendor glue drivers like pcie-al may use
their own ECAM mechanism. For those controllers, set
'dw_pcie_rp::native_ecam' flag and skip enabling the CFG Shift feature in
the DWC core.

Signed-off-by: Krishna Chaitanya Chundru <[email protected]>
[mani: code split, reworded subject/description, comment, native_ecam flag]
Signed-off-by: Manivannan Sadhasivam <[email protected]>
Link: https://patch.msgid.link/[email protected]

Author: krishnachaitanya-linux

drivers/pci/controller/dwc/pcie-al.c

@@ -352,6 +352,7 @@ static int al_pcie_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 	al_pcie->ecam_size = resource_size(ecam_res);
+	pci->pp.native_ecam = true;
 
 	controller_res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 						      "controller");

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

@@ -8,6 +8,7 @@
  * Author: Jingoo Han <[email protected]>
  */
 
+#include <linux/align.h>
 #include <linux/iopoll.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/irq-msi-lib.h>
@@ -32,6 +33,8 @@ static struct pci_ops dw_child_pcie_ops;
 				     MSI_FLAG_PCI_MSIX			| \
 				     MSI_GENERIC_FLAGS_MASK)
 
+#define IS_256MB_ALIGNED(x) IS_ALIGNED(x, SZ_256M)
+
 static const struct msi_parent_ops dw_pcie_msi_parent_ops = {
 	.required_flags		= DW_PCIE_MSI_FLAGS_REQUIRED,
 	.supported_flags	= DW_PCIE_MSI_FLAGS_SUPPORTED,
@@ -474,6 +477,34 @@ static int dw_pcie_create_ecam_window(struct dw_pcie_rp *pp, struct resource *re
 	return 0;
 }
 
+static bool dw_pcie_ecam_enabled(struct dw_pcie_rp *pp, struct resource *config_res)
+{
+	struct resource *bus_range;
+	u64 nr_buses;
+
+	/* Vendor glue drivers may implement their own ECAM mechanism */
+	if (pp->native_ecam)
+		return false;
+
+	/*
+	 * PCIe spec r6.0, sec 7.2.2 mandates the base address used for ECAM to
+	 * be aligned on a 2^(n+20) byte boundary, where n is the number of bits
+	 * used for representing 'bus' in BDF. Since the DWC cores always use 8
+	 * bits for representing 'bus', the base address has to be aligned to
+	 * 2^28 byte boundary, which is 256 MiB.
+	 */
+	if (!IS_256MB_ALIGNED(config_res->start))
+		return false;
+
+	bus_range = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS)->res;
+	if (!bus_range)
+		return false;
+
+	nr_buses = resource_size(config_res) >> PCIE_ECAM_BUS_SHIFT;
+
+	return nr_buses >= resource_size(bus_range);
+}
+
 static int dw_pcie_host_get_resources(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
@@ -492,6 +523,7 @@ static int dw_pcie_host_get_resources(struct dw_pcie_rp *pp)
 	pp->cfg0_size = resource_size(res);
 	pp->cfg0_base = res->start;
 
+	pp->ecam_enabled = dw_pcie_ecam_enabled(pp, res);
 	if (pp->ecam_enabled) {
 		ret = dw_pcie_create_ecam_window(pp, res);
 		if (ret)

drivers/pci/controller/dwc/pcie-designware.h

@@ -429,6 +429,7 @@ struct dw_pcie_rp {
 	struct pci_eq_presets	presets;
 	struct pci_config_window *cfg;
 	bool			ecam_enabled;
+	bool			native_ecam;
 };
 
 struct dw_pcie_ep_ops {