[PATCH v3] PCI: Add pci_enable_atomic_request

[Jay Cornwall <jay@jcornwall.me>]

The PCIe 3.0 AtomicOp (6.15) feature allows atomic transctions to be requested
by, routed through and completed by PCIe components. Routing and completion
do not require software support. Component support for each is detectable via
the DEVCAP2 register.

AtomicOp requests are permitted only if a component's
DEVCTL2.ATOMICOP_REQUESTER_ENABLE field is set. This capability cannot be
detected but is a no-op if set on a component with no support. These requests
can only be serviced if the upstream components support AtomicOp completion
and/or routing to a component which does.

A concrete example is the AMD Fiji-class GPU, which is specified to support
AtomicOp requests, routed through a PLX 8747 switch (advertising AtomicOp
routing) to a Haswell host bridge (advertising AtomicOp completion support).
When AtomicOp requests are disabled the GPU logs attempts to initiate requests
to an MMIO register for debugging.

Add pci_enable_atomic_request for per-device control over AtomicOp requests.
Upstream bridges are checked for AtomicOp routing capability and the call
fails if any lack this capability. The root port is checked for AtomicOp
completion capabilities and the call fails if it does not support any.
Routes to other PCIe components are not checked for AtomicOp routing and
completion capabilities.

v2: Check for AtomicOp route to root port with AtomicOp completion
v3: Style fixes

Signed-off-by: Jay Cornwall <jay@jcornwall.me>
---
 drivers/pci/pci.c             | 70 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h           |  1 +
 include/uapi/linux/pci_regs.h |  5 ++++
 3 files changed, 76 insertions(+)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6a9a111..edc56e4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2453,6 +2453,76 @@ bool pci_acs_path_enabled(struct pci_dev *start,
 }
 
 /**
+ * pci_enable_atomic_request - enable or disable AtomicOp requester
+ * @dev: the PCI device
+ *
+ * Return 0 if the device is capable of generating AtomicOp requests,
+ * all upstream bridges support AtomicOp routing, and the root port supports
+ * 32-bit, 64-bit and/or 128-bit AtomicOp completion, or negative otherwise.
+ */
+int pci_enable_atomic_request(struct pci_dev *dev)
+{
+	struct pci_bus *bus = dev->bus;
+
+	if (!pci_is_pcie(dev))
+		return -EINVAL;
+
+	switch (pci_pcie_type(dev)) {
+	/*
+	 * PCIe 3.0, 6.15 specifies that endpoints and root ports are permitted
+	 * to implement AtomicOp requester capabilities.
+	 */
+	case PCI_EXP_TYPE_ENDPOINT:
+	case PCI_EXP_TYPE_LEG_END:
+	case PCI_EXP_TYPE_RC_END:
+	case PCI_EXP_TYPE_ROOT_PORT:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	while (bus->parent) {
+		struct pci_dev *bridge = bus->self;
+		u32 cap;
+
+		pcie_capability_read_dword(bridge, PCI_EXP_DEVCAP2, &cap);
+
+		switch (pci_pcie_type(bridge)) {
+		/*
+		 * Upstream, downstream and root ports may implement AtomicOp
+		 * routing capabilities. AtomicOp routing via a root port is
+		 * not considered.
+		 */
+		case PCI_EXP_TYPE_UPSTREAM:
+		case PCI_EXP_TYPE_DOWNSTREAM:
+			if (!(cap & PCI_EXP_DEVCAP2_ATOMIC_ROUTING))
+				return -EINVAL;
+			break;
+
+		/*
+		 * Root ports are permitted to implement AtomicOp completion
+		 * capabilities.
+		 */
+		case PCI_EXP_TYPE_ROOT_PORT:
+			if (!(cap & (PCI_EXP_DEVCAP2_ATOMIC_COMP32 |
+				     PCI_EXP_DEVCAP2_ATOMIC_COMP64 |
+				     PCI_EXP_DEVCAP2_ATOMIC_COMP128)))
+				return -EINVAL;
+			break;
+		}
+
+
+		bus = bus->parent;
+	}
+
+	pcie_capability_set_word(dev, PCI_EXP_DEVCTL2,
+				 PCI_EXP_DEVCTL2_ATOMICOP_REQ);
+
+	return 0;
+}
+EXPORT_SYMBOL(pci_enable_atomic_request);
+
+/**
  * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge
  * @dev: the PCI device
  * @pin: the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e90eb22..4e50003 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1801,6 +1801,7 @@ void pci_request_acs(void);
 bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags);
 bool pci_acs_path_enabled(struct pci_dev *start,
 			  struct pci_dev *end, u16 acs_flags);
+int pci_enable_atomic_request(struct pci_dev *dev);
 
 #define PCI_VPD_LRDT			0x80	/* Large Resource Data Type */
 #define PCI_VPD_LRDT_ID(x)		((x) | PCI_VPD_LRDT)
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 413417f..013c2bd 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -571,6 +571,10 @@
  */
 #define PCI_EXP_DEVCAP2		36	/* Device Capabilities 2 */
 #define  PCI_EXP_DEVCAP2_ARI		0x00000020 /* Alternative Routing-ID */
+#define  PCI_EXP_DEVCAP2_ATOMIC_ROUTING	0x00000040 /* AtomicOp routing */
+#define  PCI_EXP_DEVCAP2_ATOMIC_COMP32	0x00000080 /* 32b AtomicOp completion */
+#define  PCI_EXP_DEVCAP2_ATOMIC_COMP64	0x00000100 /* 64b AtomicOp completion */
+#define  PCI_EXP_DEVCAP2_ATOMIC_COMP128	0x00000200 /* 128b AtomicOp completion*/
 #define  PCI_EXP_DEVCAP2_LTR		0x00000800 /* Latency tolerance reporting */
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
@@ -578,6 +582,7 @@
 #define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
 #define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
 #define  PCI_EXP_DEVCTL2_ARI		0x0020	/* Alternative Routing-ID */
+#define  PCI_EXP_DEVCTL2_ATOMICOP_REQ	0x0040	/* Allow AtomicOp requests */
 #define  PCI_EXP_DEVCTL2_IDO_REQ_EN	0x0100	/* Allow IDO for requests */
 #define  PCI_EXP_DEVCTL2_IDO_CMP_EN	0x0200	/* Allow IDO for completions */
 #define  PCI_EXP_DEVCTL2_LTR_EN		0x0400	/* Enable LTR mechanism */
-- 
1.9.1