All of lore.kernel.org
 help / color / mirror / Atom feed
From: longli@linuxonhyperv.com
To: "K. Y. Srinivasan" <kys@microsoft.com>,
	Haiyang Zhang <haiyangz@microsoft.com>,
	Stephen Hemminger <sthemmin@microsoft.com>,
	Sasha Levin <sashal@kernel.org>,
	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>,
	Andrew Murray <andrew.murray@arm.com>,
	Bjorn Helgaas <bhelgaas@google.com>,
	linux-hyperv@vger.kernel.org, linux-pci@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: Long Li <longli@microsoft.com>
Subject: [Patch v2 2/2] PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2
Date: Tue,  3 Dec 2019 18:53:37 -0800	[thread overview]
Message-ID: <1575428017-87914-2-git-send-email-longli@linuxonhyperv.com> (raw)
In-Reply-To: <1575428017-87914-1-git-send-email-longli@linuxonhyperv.com>

From: Long Li <longli@microsoft.com>

Starting with Hyper-V PCI protocol version 1.3, the host VSP can send
PCI_BUS_RELATIONS2 and pass the vNUMA node information for devices on the bus.
The vNUMA node tells which guest NUMA node this device is on based on guest
VM configuration topology and physical device inforamtion.

The patch adds code to negotiate v1.3 and process PCI_BUS_RELATIONS2.

Signed-off-by: Long Li <longli@microsoft.com>
---

Changes
v2: Changed some spaces to tabs, added put_pcichild() after get_pcichild_wslot(), renamed pci_assign_numa_node() to hv_pci_assign_numa_node()

 drivers/pci/controller/pci-hyperv.c | 109 ++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 8c1533be6ad0..fee0d7fdc672 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -63,6 +63,7 @@
 enum pci_protocol_version_t {
 	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),	/* Win10 */
 	PCI_PROTOCOL_VERSION_1_2 = PCI_MAKE_VERSION(1, 2),	/* RS1 */
+	PCI_PROTOCOL_VERSION_1_3 = PCI_MAKE_VERSION(1, 3),	/* Vibranium */
 };
 
 #define CPU_AFFINITY_ALL	-1ULL
@@ -72,6 +73,7 @@ enum pci_protocol_version_t {
  * first.
  */
 static enum pci_protocol_version_t pci_protocol_versions[] = {
+	PCI_PROTOCOL_VERSION_1_3,
 	PCI_PROTOCOL_VERSION_1_2,
 	PCI_PROTOCOL_VERSION_1_1,
 };
@@ -124,6 +126,7 @@ enum pci_message_type {
 	PCI_RESOURCES_ASSIGNED2		= PCI_MESSAGE_BASE + 0x16,
 	PCI_CREATE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x17,
 	PCI_DELETE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x18, /* unused */
+	PCI_BUS_RELATIONS2		= PCI_MESSAGE_BASE + 0x19,
 	PCI_MESSAGE_MAXIMUM
 };
 
@@ -169,6 +172,26 @@ struct pci_function_description {
 	u32	ser;	/* serial number */
 } __packed;
 
+enum pci_device_description_flags {
+	HV_PCI_DEVICE_FLAG_NONE			= 0x0,
+	HV_PCI_DEVICE_FLAG_NUMA_AFFINITY	= 0x1,
+};
+
+struct pci_function_description2 {
+	u16	v_id;	/* vendor ID */
+	u16	d_id;	/* device ID */
+	u8	rev;
+	u8	prog_intf;
+	u8	subclass;
+	u8	base_class;
+	u32	subsystem_id;
+	union	win_slot_encoding win_slot;
+	u32	ser;	/* serial number */
+	u32	flags;
+	u16	virtual_numa_node;
+	u16	reserved;
+} __packed;
+
 /**
  * struct hv_msi_desc
  * @vector:		IDT entry
@@ -304,6 +327,12 @@ struct pci_bus_relations {
 	struct pci_function_description func[0];
 } __packed;
 
+struct pci_bus_relations2 {
+	struct pci_incoming_message incoming;
+	u32 device_count;
+	struct pci_function_description2 func[0];
+} __packed;
+
 struct pci_q_res_req_response {
 	struct vmpacket_descriptor hdr;
 	s32 status;			/* negative values are failures */
@@ -1417,6 +1446,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_2:
+	case PCI_PROTOCOL_VERSION_1_3:
 		size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
 					dest,
 					hpdev->desc.win_slot.slot,
@@ -1798,6 +1828,27 @@ static void hv_pci_remove_slots(struct hv_pcibus_device *hbus)
 	}
 }
 
+/*
+ * Set NUMA node for the devices on the bus
+ */
+static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
+{
+	struct pci_dev *dev;
+	struct pci_bus *bus = hbus->pci_bus;
+	struct hv_pci_dev *hv_dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		hv_dev = get_pcichild_wslot(hbus, devfn_to_wslot(dev->devfn));
+		if (!hv_dev)
+			continue;
+
+		if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY)
+			set_dev_node(&dev->dev, hv_dev->desc.virtual_numa_node);
+
+		put_pcichild(hv_dev);
+	}
+}
+
 /**
  * create_root_hv_pci_bus() - Expose a new root PCI bus
  * @hbus:	Root PCI bus, as understood by this driver
@@ -1820,6 +1871,7 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
 
 	pci_lock_rescan_remove();
 	pci_scan_child_bus(hbus->pci_bus);
+	hv_pci_assign_numa_node(hbus);
 	pci_bus_assign_resources(hbus->pci_bus);
 	hv_pci_assign_slots(hbus);
 	pci_bus_add_devices(hbus->pci_bus);
@@ -2088,6 +2140,7 @@ static void pci_devices_present_work(struct work_struct *work)
 		 */
 		pci_lock_rescan_remove();
 		pci_scan_child_bus(hbus->pci_bus);
+		hv_pci_assign_numa_node(hbus);
 		hv_pci_assign_slots(hbus);
 		pci_unlock_rescan_remove();
 		break;
@@ -2183,6 +2236,46 @@ static void hv_pci_devices_present(struct hv_pcibus_device *hbus,
 		kfree(dr);
 }
 
+/**
+ * hv_pci_devices_present2() - Handles list of new children
+ * @hbus:	Root PCI bus, as understood by this driver
+ * @relations2:	Packet from host listing children
+ *
+ * This function is the v2 version of hv_pci_devices_present()
+ */
+static void hv_pci_devices_present2(struct hv_pcibus_device *hbus,
+				    struct pci_bus_relations2 *relations)
+{
+	struct hv_dr_state *dr;
+	int i;
+
+	dr = kzalloc(offsetof(struct hv_dr_state, func) +
+		     (sizeof(struct hv_pcidev_description) *
+		      (relations->device_count)), GFP_NOWAIT);
+
+	if (!dr)
+		return;
+
+	dr->device_count = relations->device_count;
+	for (i = 0; i < dr->device_count; i++) {
+		dr->func[i].v_id = relations->func[i].v_id;
+		dr->func[i].d_id = relations->func[i].d_id;
+		dr->func[i].rev = relations->func[i].rev;
+		dr->func[i].prog_intf = relations->func[i].prog_intf;
+		dr->func[i].subclass = relations->func[i].subclass;
+		dr->func[i].base_class = relations->func[i].base_class;
+		dr->func[i].subsystem_id = relations->func[i].subsystem_id;
+		dr->func[i].win_slot = relations->func[i].win_slot;
+		dr->func[i].ser = relations->func[i].ser;
+		dr->func[i].flags = relations->func[i].flags;
+		dr->func[i].virtual_numa_node =
+			relations->func[i].virtual_numa_node;
+	}
+
+	if (hv_pci_start_relations_work(hbus, dr))
+		kfree(dr);
+}
+
 /**
  * hv_eject_device_work() - Asynchronously handles ejection
  * @work:	Work struct embedded in internal device struct
@@ -2288,6 +2381,7 @@ static void hv_pci_onchannelcallback(void *context)
 	struct pci_response *response;
 	struct pci_incoming_message *new_message;
 	struct pci_bus_relations *bus_rel;
+	struct pci_bus_relations2 *bus_rel2;
 	struct pci_dev_inval_block *inval;
 	struct pci_dev_incoming *dev_message;
 	struct hv_pci_dev *hpdev;
@@ -2355,6 +2449,21 @@ static void hv_pci_onchannelcallback(void *context)
 				hv_pci_devices_present(hbus, bus_rel);
 				break;
 
+			case PCI_BUS_RELATIONS2:
+
+				bus_rel2 = (struct pci_bus_relations2 *)buffer;
+				if (bytes_recvd <
+				    offsetof(struct pci_bus_relations2, func) +
+				    (sizeof(struct pci_function_description2) *
+				     (bus_rel2->device_count))) {
+					dev_err(&hbus->hdev->device,
+						"bus relations v2 too small\n");
+					break;
+				}
+
+				hv_pci_devices_present2(hbus, bus_rel2);
+				break;
+
 			case PCI_EJECT:
 
 				dev_message = (struct pci_dev_incoming *)buffer;
-- 
2.17.1


  reply	other threads:[~2019-12-04  2:53 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-04  2:53 [Patch v2 1/2] PCI: hv: decouple the func definition in hv_dr_state from VSP message longli
2019-12-04  2:53 ` longli [this message]
2019-12-04 19:44   ` [Patch v2 2/2] PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2 Michael Kelley
2019-12-04 19:41 ` [Patch v2 1/2] PCI: hv: decouple the func definition in hv_dr_state from VSP message Michael Kelley
2019-12-10 23:54 ` Bjorn Helgaas
2019-12-22  2:47   ` Long Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1575428017-87914-2-git-send-email-longli@linuxonhyperv.com \
    --to=longli@linuxonhyperv.com \
    --cc=andrew.murray@arm.com \
    --cc=bhelgaas@google.com \
    --cc=haiyangz@microsoft.com \
    --cc=kys@microsoft.com \
    --cc=linux-hyperv@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=longli@microsoft.com \
    --cc=lorenzo.pieralisi@arm.com \
    --cc=sashal@kernel.org \
    --cc=sthemmin@microsoft.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.