* Re: [PATCH v6,1/2] PCI: hv: Detect and fix Hyper-V PCI domain number collision
From: Lorenzo Pieralisi @ 2019-08-20 16:58 UTC (permalink / raw)
To: Haiyang Zhang
Cc: sashal@kernel.org, bhelgaas@google.com,
linux-hyperv@vger.kernel.org, linux-pci@vger.kernel.org,
KY Srinivasan, Stephen Hemminger, olaf@aepfle.de, vkuznets,
linux-kernel@vger.kernel.org
In-Reply-To: <1565888460-38694-1-git-send-email-haiyangz@microsoft.com>
On Thu, Aug 15, 2019 at 05:01:37PM +0000, Haiyang Zhang wrote:
> Currently in Azure cloud, for passthrough devices, the host sets the device
> instance ID's bytes 8 - 15 to a value derived from the host HWID, which is
> the same on all devices in a VM. So, the device instance ID's bytes 8 and 9
> provided by the host are no longer unique. This affects all Azure hosts
> since July 2018, and can cause device passthrough to VMs to fail because
> the bytes 8 and 9 are used as PCI domain number. Collision of domain
> numbers will cause the second device with the same domain number fail to
> load.
>
> In the cases of collision, we will detect and find another number that is
> not in use.
>
> Suggested-by: Michael Kelley <mikelley@microsoft.com>
> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
> Acked-by: Sasha Levin <sashal@kernel.org>
> ---
> drivers/pci/controller/pci-hyperv.c | 92 +++++++++++++++++++++++++++++++------
> 1 file changed, 79 insertions(+), 13 deletions(-)
I have applied both patches to pci/hv for v5.4.
Thanks,
Lorenzo
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index 40b6254..31b8fd5 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -2510,6 +2510,48 @@ static void put_hvpcibus(struct hv_pcibus_device *hbus)
> complete(&hbus->remove_event);
> }
>
> +#define HVPCI_DOM_MAP_SIZE (64 * 1024)
> +static DECLARE_BITMAP(hvpci_dom_map, HVPCI_DOM_MAP_SIZE);
> +
> +/*
> + * PCI domain number 0 is used by emulated devices on Gen1 VMs, so define 0
> + * as invalid for passthrough PCI devices of this driver.
> + */
> +#define HVPCI_DOM_INVALID 0
> +
> +/**
> + * hv_get_dom_num() - Get a valid PCI domain number
> + * Check if the PCI domain number is in use, and return another number if
> + * it is in use.
> + *
> + * @dom: Requested domain number
> + *
> + * return: domain number on success, HVPCI_DOM_INVALID on failure
> + */
> +static u16 hv_get_dom_num(u16 dom)
> +{
> + unsigned int i;
> +
> + if (test_and_set_bit(dom, hvpci_dom_map) == 0)
> + return dom;
> +
> + for_each_clear_bit(i, hvpci_dom_map, HVPCI_DOM_MAP_SIZE) {
> + if (test_and_set_bit(i, hvpci_dom_map) == 0)
> + return i;
> + }
> +
> + return HVPCI_DOM_INVALID;
> +}
> +
> +/**
> + * hv_put_dom_num() - Mark the PCI domain number as free
> + * @dom: Domain number to be freed
> + */
> +static void hv_put_dom_num(u16 dom)
> +{
> + clear_bit(dom, hvpci_dom_map);
> +}
> +
> /**
> * hv_pci_probe() - New VMBus channel probe, for a root PCI bus
> * @hdev: VMBus's tracking struct for this root PCI bus
> @@ -2521,6 +2563,7 @@ static int hv_pci_probe(struct hv_device *hdev,
> const struct hv_vmbus_device_id *dev_id)
> {
> struct hv_pcibus_device *hbus;
> + u16 dom_req, dom;
> int ret;
>
> /*
> @@ -2535,19 +2578,34 @@ static int hv_pci_probe(struct hv_device *hdev,
> hbus->state = hv_pcibus_init;
>
> /*
> - * The PCI bus "domain" is what is called "segment" in ACPI and
> - * other specs. Pull it from the instance ID, to get something
> - * unique. Bytes 8 and 9 are what is used in Windows guests, so
> - * do the same thing for consistency. Note that, since this code
> - * only runs in a Hyper-V VM, Hyper-V can (and does) guarantee
> - * that (1) the only domain in use for something that looks like
> - * a physical PCI bus (which is actually emulated by the
> - * hypervisor) is domain 0 and (2) there will be no overlap
> - * between domains derived from these instance IDs in the same
> - * VM.
> + * The PCI bus "domain" is what is called "segment" in ACPI and other
> + * specs. Pull it from the instance ID, to get something usually
> + * unique. In rare cases of collision, we will find out another number
> + * not in use.
> + *
> + * Note that, since this code only runs in a Hyper-V VM, Hyper-V
> + * together with this guest driver can guarantee that (1) The only
> + * domain used by Gen1 VMs for something that looks like a physical
> + * PCI bus (which is actually emulated by the hypervisor) is domain 0.
> + * (2) There will be no overlap between domains (after fixing possible
> + * collisions) in the same VM.
> */
> - hbus->sysdata.domain = hdev->dev_instance.b[9] |
> - hdev->dev_instance.b[8] << 8;
> + dom_req = hdev->dev_instance.b[8] << 8 | hdev->dev_instance.b[9];
> + dom = hv_get_dom_num(dom_req);
> +
> + if (dom == HVPCI_DOM_INVALID) {
> + dev_err(&hdev->device,
> + "Unable to use dom# 0x%hx or other numbers", dom_req);
> + ret = -EINVAL;
> + goto free_bus;
> + }
> +
> + if (dom != dom_req)
> + dev_info(&hdev->device,
> + "PCI dom# 0x%hx has collision, using 0x%hx",
> + dom_req, dom);
> +
> + hbus->sysdata.domain = dom;
>
> hbus->hdev = hdev;
> refcount_set(&hbus->remove_lock, 1);
> @@ -2562,7 +2620,7 @@ static int hv_pci_probe(struct hv_device *hdev,
> hbus->sysdata.domain);
> if (!hbus->wq) {
> ret = -ENOMEM;
> - goto free_bus;
> + goto free_dom;
> }
>
> ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
> @@ -2639,6 +2697,8 @@ static int hv_pci_probe(struct hv_device *hdev,
> vmbus_close(hdev->channel);
> destroy_wq:
> destroy_workqueue(hbus->wq);
> +free_dom:
> + hv_put_dom_num(hbus->sysdata.domain);
> free_bus:
> free_page((unsigned long)hbus);
> return ret;
> @@ -2720,6 +2780,9 @@ static int hv_pci_remove(struct hv_device *hdev)
> put_hvpcibus(hbus);
> wait_for_completion(&hbus->remove_event);
> destroy_workqueue(hbus->wq);
> +
> + hv_put_dom_num(hbus->sysdata.domain);
> +
> free_page((unsigned long)hbus);
> return 0;
> }
> @@ -2747,6 +2810,9 @@ static void __exit exit_hv_pci_drv(void)
>
> static int __init init_hv_pci_drv(void)
> {
> + /* Set the invalid domain number's bit, so it will not be used */
> + set_bit(HVPCI_DOM_INVALID, hvpci_dom_map);
> +
> return vmbus_driver_register(&hv_pci_drv);
> }
>
> --
> 1.8.3.1
>
^ permalink raw reply
* Re: [PATCH v2 2/3] drivers: hv: vmbus: add test attributes to debugfs
From: Branden Bonaby @ 2019-08-20 18:17 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, sashal; +Cc: linux-hyperv, linux-kernel
In-Reply-To: <e055f27ffc37a9a6a756a3329a60da608db5a04f.1566266609.git.brandonbonaby94@gmail.com>
On Mon, Aug 19, 2019 at 10:44:48PM -0400, Branden Bonaby wrote:
> Expose the test parameters as part of the debugfs channel attributes.
> We will control the testing state via these attributes.
>
> Signed-off-by: Branden Bonaby <brandonbonaby94@gmail.com>
> ---
> Changes in v2:
> - Move test attributes to debugfs.
> - Wrap test code under #ifdef statements.
> - Add new documentation file under Documentation/ABI/testing.
> - Make commit message reflect the change from from sysfs to debugfs.
>
>
> + if (IS_ERR_OR_NULL(dev_root)) {
> + pr_debug("debugfs_hyperv: %s/%s/ not created\n",
> + TESTING, device);
> + return PTR_ERR(dev_root);
> + }
Whoops, that single IS_ERR_OR_NULL shouldn't be there, it should just
be IS_ERR I'll change and resend the patch.
^ permalink raw reply
* Re: [PATCH net-next,v2 2/6] PCI: hv: Add a Hyper-V PCI interface driver for software backchannel interface
From: David Miller @ 2019-08-20 19:29 UTC (permalink / raw)
To: haiyangz
Cc: sashal, saeedm, leon, eranbe, lorenzo.pieralisi, bhelgaas,
linux-pci, linux-hyperv, netdev, kys, sthemmin, linux-kernel
In-Reply-To: <1566242976-108801-3-git-send-email-haiyangz@microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Mon, 19 Aug 2019 19:30:47 +0000
> +static void __exit exit_hv_pci_intf(void)
> +{
> + pr_info("unloaded\n");
> +}
> +
> +static int __init init_hv_pci_intf(void)
> +{
> + pr_info("loaded\n");
> +
Clogging up the logs with useless messages like this is inappropriate.
Please remove these pr_info() calls.
Also, all of these symbols should probably be GPL exported.
^ permalink raw reply
* Re: [PATCH] vsock: Fix a lockdep warning in __vsock_release()
From: David Miller @ 2019-08-20 19:45 UTC (permalink / raw)
To: decui
Cc: jhansen, stefanha, sgarzare, netdev, sthemmin, Alexander.Levin,
sashal, haiyangz, kys, mikelley, linux-hyperv, gregkh,
linux-kernel
In-Reply-To: <1566270830-28981-1-git-send-email-decui@microsoft.com>
From: Dexuan Cui <decui@microsoft.com>
Date: Tue, 20 Aug 2019 03:14:22 +0000
> +static void __vsock_release2(struct sock *sk)
Do not duplicate an entire function just to adjust some aspect of the
lock debugging, please find a cleaner and more minimal way to
implement this fix.
^ permalink raw reply
* RE: [PATCH net-next,v2 2/6] PCI: hv: Add a Hyper-V PCI interface driver for software backchannel interface
From: Haiyang Zhang @ 2019-08-20 23:00 UTC (permalink / raw)
To: David Miller
Cc: sashal@kernel.org, saeedm@mellanox.com, leon@kernel.org,
eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org,
KY Srinivasan, Stephen Hemminger, linux-kernel@vger.kernel.org
In-Reply-To: <20190820.122925.1080288470348205792.davem@davemloft.net>
> -----Original Message-----
> From: David Miller <davem@davemloft.net>
> Sent: Tuesday, August 20, 2019 3:29 PM
> To: Haiyang Zhang <haiyangz@microsoft.com>
> Cc: sashal@kernel.org; saeedm@mellanox.com; leon@kernel.org;
> eranbe@mellanox.com; lorenzo.pieralisi@arm.com; bhelgaas@google.com;
> linux-pci@vger.kernel.org; linux-hyperv@vger.kernel.org;
> netdev@vger.kernel.org; KY Srinivasan <kys@microsoft.com>; Stephen
> Hemminger <sthemmin@microsoft.com>; linux-kernel@vger.kernel.org
> Subject: Re: [PATCH net-next,v2 2/6] PCI: hv: Add a Hyper-V PCI interface
> driver for software backchannel interface
>
> From: Haiyang Zhang <haiyangz@microsoft.com>
> Date: Mon, 19 Aug 2019 19:30:47 +0000
>
> > +static void __exit exit_hv_pci_intf(void) {
> > + pr_info("unloaded\n");
> > +}
> > +
> > +static int __init init_hv_pci_intf(void) {
> > + pr_info("loaded\n");
> > +
>
> Clogging up the logs with useless messages like this is inappropriate.
> Please remove these pr_info() calls.
>
> Also, all of these symbols should probably be GPL exported.
I will update the patch -- remove the pr_info, and use EXPORT_SYMBOL_GPL()
for the symbols.
Thanks,
- Haiyang
^ permalink raw reply
* [PATCH v3 0/3] hv: vmbus: add fuzz testing to hv device
From: Branden Bonaby @ 2019-08-20 23:38 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, sashal
Cc: Branden Bonaby, linux-hyperv, linux-kernel
This patchset introduces a testing framework for Hyper-V drivers.
This framework allows us to introduce delays in the packet receive
path on a per-device basis. While the current code only supports
introducing arbitrary delays in the host/guest communication path,
we intend to expand this to support error injection in the future.
changes in v3:
patch 2: change call to IS_ERR_OR_NULL, to IS_ERR.
patch 3: Align python tool to match Linux coding style.
Changes in v2:
Patch 1: As per Vitaly's suggestion, wrapped the test code under an
#ifdef and updated the Kconfig file, so that the test code
will only be used when the config option is set to true.
(default is false).
Updated hyperv_vmbus header to contain new #ifdef with new
new functions for the test code.
Patch 2: Moved code from under sysfs to debugfs and wrapped it under
the new ifdef.
Updated MAINTAINERS file with new debugfs-hyperv file under
the section for hyperv.
Patch 3: Updated testing tool with new debugfs location.
Branden Bonaby (3):
drivers: hv: vmbus: Introduce latency testing
drivers: hv: vmbus: add fuzz test attributes to debugfs
tools: hv: add vmbus testing tool
Documentation/ABI/testing/debugfs-hyperv | 21 ++
MAINTAINERS | 1 +
drivers/hv/Kconfig | 7 +
drivers/hv/connection.c | 3 +
drivers/hv/hyperv_vmbus.h | 20 ++
drivers/hv/ring_buffer.c | 7 +
drivers/hv/vmbus_drv.c | 167 +++++++++++
include/linux/hyperv.h | 21 ++
tools/hv/vmbus_testing | 342 +++++++++++++++++++++++
9 files changed, 589 insertions(+)
create mode 100644 Documentation/ABI/testing/debugfs-hyperv
create mode 100644 tools/hv/vmbus_testing
--
2.17.1
^ permalink raw reply
* [PATCH v3 1/3] drivers: hv: vmbus: Introduce latency testing
From: Branden Bonaby @ 2019-08-20 23:39 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, sashal
Cc: Branden Bonaby, linux-hyperv, linux-kernel
In-Reply-To: <cover.1566340843.git.brandonbonaby94@gmail.com>
Introduce user specified latency in the packet reception path.
Signed-off-by: Branden Bonaby <brandonbonaby94@gmail.com>
---
Changes in v2:
- Add #ifdef in Kconfig file so test code will not interfere
with non-test code.
- Move test code functions for delay to hyperv_vmbus header
file.
- Wrap test code under #ifdef statement.
drivers/hv/Kconfig | 7 +++++++
drivers/hv/connection.c | 3 +++
drivers/hv/hyperv_vmbus.h | 20 ++++++++++++++++++++
drivers/hv/ring_buffer.c | 7 +++++++
include/linux/hyperv.h | 21 +++++++++++++++++++++
5 files changed, 58 insertions(+)
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 9a59957922d4..d97437ba0626 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -29,4 +29,11 @@ config HYPERV_BALLOON
help
Select this option to enable Hyper-V Balloon driver.
+config HYPERV_TESTING
+ bool "Hyper-V testing"
+ default n
+ depends on HYPERV && DEBUG_FS
+ help
+ Select this option to enable Hyper-V vmbus testing.
+
endmenu
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 09829e15d4a0..c9c63a4033cd 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -357,6 +357,9 @@ void vmbus_on_event(unsigned long data)
trace_vmbus_on_event(channel);
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_delay_test(channel, INTERRUPT_DELAY);
+#endif /* CONFIG_HYPERV_TESTING */
do {
void (*callback_fn)(void *);
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 362e70e9d145..edf14f596d8c 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -357,4 +357,24 @@ enum hvutil_device_state {
HVUTIL_DEVICE_DYING, /* driver unload is in progress */
};
+#ifdef CONFIG_HYPERV_TESTING
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#define TESTING "hyperv"
+
+enum delay {
+ INTERRUPT_DELAY = 0,
+ MESSAGE_DELAY = 1,
+};
+
+int hv_debug_delay_files(struct hv_device *dev, struct dentry *root);
+int hv_debug_add_dev_dir(struct hv_device *dev);
+void hv_debug_rm_dev_dir(struct hv_device *dev);
+void hv_debug_rm_all_dir(void);
+void hv_debug_set_dir_dentry(struct hv_device *dev, struct dentry *root);
+void hv_debug_delay_test(struct vmbus_channel *channel, enum delay delay_type);
+
+#endif /* CONFIG_HYPERV_TESTING */
+
#endif /* _HYPERV_VMBUS_H */
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 9a03b163cbbd..51adda23b398 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -396,6 +396,10 @@ struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
struct hv_ring_buffer_info *rbi = &channel->inbound;
struct vmpacket_descriptor *desc;
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_delay_test(channel, MESSAGE_DELAY);
+#endif /* CONFIG_HYPERV_TESTING */
+
if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
return NULL;
@@ -421,6 +425,9 @@ __hv_pkt_iter_next(struct vmbus_channel *channel,
u32 packetlen = desc->len8 << 3;
u32 dsize = rbi->ring_datasize;
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_delay_test(channel, MESSAGE_DELAY);
+#endif /* CONFIG_HYPERV_TESTING */
/* bump offset to next potential packet */
rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
if (rbi->priv_read_index >= dsize)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6256cc34c4a6..6bf8ef5c780c 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -926,6 +926,21 @@ struct vmbus_channel {
* full outbound ring buffer.
*/
u64 out_full_first;
+
+#ifdef CONFIG_HYPERV_TESTING
+ /* enabling/disabling fuzz testing on the channel (default is false)*/
+ bool fuzz_testing_state;
+
+ /* Interrupt delay will delay the guest from emptying the ring buffer
+ * for a specific amount of time. The delay is in microseconds and will
+ * be between 1 to a maximum of 1000, its default is 0 (no delay).
+ * The Message delay will delay guest reading on a per message basis
+ * in microseconds between 1 to 1000 with the default being 0
+ * (no delay).
+ */
+ u32 fuzz_testing_interrupt_delay;
+ u32 fuzz_testing_message_delay;
+#endif /* CONFIG_HYPERV_TESTING */
};
static inline bool is_hvsock_channel(const struct vmbus_channel *c)
@@ -1166,6 +1181,12 @@ struct hv_device {
struct vmbus_channel *channel;
struct kset *channels_kset;
+
+#ifdef CONFIG_HYPERV_TESTING
+ /* place holder to keep track of the dir for hv device in debugfs */
+ struct dentry *debug_dir;
+#endif /* CONFIG_HYPERV_TESTING */
+
};
--
2.17.1
^ permalink raw reply related
* [PATCH v3 2/3] drivers: hv: vmbus: add test attributes to debugfs
From: Branden Bonaby @ 2019-08-20 23:39 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, sashal
Cc: Branden Bonaby, linux-hyperv, linux-kernel
In-Reply-To: <cover.1566340843.git.brandonbonaby94@gmail.com>
Expose the test parameters as part of the debugfs channel attributes.
We will control the testing state via these attributes.
Signed-off-by: Branden Bonaby <brandonbonaby94@gmail.com>
---
Changes in v3:
- Change call to IS_ERR_OR_NULL, to IS_ERR.
Changes in v2:
- Move test attributes to debugfs.
- Wrap test code under #ifdef statements.
- Add new documentation file under Documentation/ABI/testing.
- Make commit message reflect the change from from sysfs to debugfs.
Documentation/ABI/testing/debugfs-hyperv | 21 +++
MAINTAINERS | 1 +
drivers/hv/vmbus_drv.c | 167 +++++++++++++++++++++++
3 files changed, 189 insertions(+)
create mode 100644 Documentation/ABI/testing/debugfs-hyperv
diff --git a/Documentation/ABI/testing/debugfs-hyperv b/Documentation/ABI/testing/debugfs-hyperv
new file mode 100644
index 000000000000..b25f751fafa8
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-hyperv
@@ -0,0 +1,21 @@
+What: /sys/kernel/debug/hyperv/<UUID>/fuzz_test_state
+Date: August 2019
+KernelVersion: 5.3
+Contact: Branden Bonaby <brandonbonaby94@gmail.com>
+Description: Fuzz testing status of a vmbus device, whether its in an ON
+ state or a OFF state
+Users: Debugging tools
+
+What: /sys/kernel/debug/hyperv/<UUID>/delay/fuzz_test_buffer_interrupt_delay
+Date: August 2019
+KernelVersion: 5.3
+Contact: Branden Bonaby <brandonbonaby94@gmail.com>
+Description: Fuzz testing buffer delay value between 0 - 1000
+Users: Debugging tools
+
+What: /sys/kernel/debug/hyperv/<UUID>/delay/fuzz_test_message_delay
+Date: August 2019
+KernelVersion: 5.3
+Contact: Branden Bonaby <brandonbonaby94@gmail.com>
+Description: Fuzz testing message delay value between 0 - 1000
+Users: Debugging tools
diff --git a/MAINTAINERS b/MAINTAINERS
index e81e60bd7c26..120284a8185f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7460,6 +7460,7 @@ F: include/uapi/linux/hyperv.h
F: include/asm-generic/mshyperv.h
F: tools/hv/
F: Documentation/ABI/stable/sysfs-bus-vmbus
+F: Documentation/ABI/testing/debugfs-hyperv
HYPERBUS SUPPORT
M: Vignesh Raghavendra <vigneshr@ti.com>
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index ebd35fc35290..d2e47f04d172 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -919,6 +919,10 @@ static void vmbus_device_release(struct device *device)
struct hv_device *hv_dev = device_to_hv_device(device);
struct vmbus_channel *channel = hv_dev->channel;
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_rm_dev_dir(hv_dev);
+#endif /* CONFIG_HYPERV_TESTING */
+
mutex_lock(&vmbus_connection.channel_mutex);
hv_process_channel_removal(channel);
mutex_unlock(&vmbus_connection.channel_mutex);
@@ -1727,6 +1731,9 @@ int vmbus_device_register(struct hv_device *child_device_obj)
pr_err("Unable to register primary channeln");
goto err_kset_unregister;
}
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_add_dev_dir(child_device_obj);
+#endif /* CONFIG_HYPERV_TESTING */
return 0;
@@ -2086,6 +2093,159 @@ static void hv_crash_handler(struct pt_regs *regs)
hyperv_cleanup();
};
+#ifdef CONFIG_HYPERV_TESTING
+
+struct dentry *hv_root;
+
+static int hv_debugfs_delay_get(void *data, u64 *val)
+{
+ *val = *(u32 *)data;
+ return 0;
+}
+
+static int hv_debugfs_delay_set(void *data, u64 val)
+{
+ if (val >= 1 && val <= 1000)
+ *(u32 *)data = val;
+ /*Best to not use else statement here since we want
+ * the delay to remain the same if val > 1000
+ */
+ else if (val <= 0)
+ *(u32 *)data = 0;
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(hv_debugfs_delay_fops, hv_debugfs_delay_get,
+ hv_debugfs_delay_set, "%llu\n");
+
+/* Setup delay files to store test values */
+int hv_debug_delay_files(struct hv_device *dev, struct dentry *root)
+{
+ struct vmbus_channel *channel = dev->channel;
+ char *buffer = "fuzz_test_buffer_interrupt_delay";
+ char *message = "fuzz_test_message_delay";
+ int *buffer_val = &channel->fuzz_testing_interrupt_delay;
+ int *message_val = &channel->fuzz_testing_message_delay;
+ struct dentry *buffer_file, *message_file;
+
+ buffer_file = debugfs_create_file(buffer, 0644, root,
+ buffer_val,
+ &hv_debugfs_delay_fops);
+ if (IS_ERR(buffer_file)) {
+ pr_debug("debugfs_hyperv: file %s not created\n", buffer);
+ return PTR_ERR(buffer_file);
+ }
+
+ message_file = debugfs_create_file(message, 0644, root,
+ message_val,
+ &hv_debugfs_delay_fops);
+ if (IS_ERR(message_file)) {
+ pr_debug("debugfs_hyperv: file %s not created\n", message);
+ return PTR_ERR(message_file);
+ }
+
+ return 0;
+}
+
+/* Setup test state value for vmbus device */
+int hv_debug_set_test_state(struct hv_device *dev, struct dentry *root)
+{
+ struct vmbus_channel *channel = dev->channel;
+ bool *state = &channel->fuzz_testing_state;
+ char *status = "fuzz_test_state";
+ struct dentry *test_state;
+
+ test_state = debugfs_create_bool(status, 0644, root, state);
+ if (IS_ERR(test_state)) {
+ pr_debug("debugfs_hyperv: file %s not created\n", status);
+ return PTR_ERR(test_state);
+ }
+
+ return 0;
+}
+
+/* Bind hv device to a dentry for debugfs */
+void hv_debug_set_dir_dentry(struct hv_device *dev, struct dentry *root)
+{
+ if (hv_root)
+ dev->debug_dir = root;
+}
+
+/* Create all test dentry's and names for fuzz testing */
+int hv_debug_add_dev_dir(struct hv_device *dev)
+{
+ const char *device = dev_name(&dev->device);
+ char *delay_name = "delay";
+ struct dentry *delay, *dev_root;
+ int ret;
+
+ if (!IS_ERR(hv_root)) {
+ dev_root = debugfs_create_dir(device, hv_root);
+ if (IS_ERR(dev_root)) {
+ pr_debug("debugfs_hyperv: %s/%s/ not created\n",
+ TESTING, device);
+ return PTR_ERR(dev_root);
+ }
+
+ hv_debug_set_test_state(dev, dev_root);
+ hv_debug_set_dir_dentry(dev, dev_root);
+ delay = debugfs_create_dir(delay_name, dev_root);
+
+ if (IS_ERR(delay)) {
+ pr_debug("debugfs_hyperv: %s/%s/%s/ not created\n",
+ TESTING, device, delay_name);
+ return PTR_ERR(delay);
+ }
+ ret = hv_debug_delay_files(dev, delay);
+
+ return ret;
+ }
+ pr_debug("debugfs_hyperv: %s/ not in root debugfs path\n", TESTING);
+ return PTR_ERR(hv_root);
+}
+
+/* Remove dentry associated with released hv device */
+void hv_debug_rm_dev_dir(struct hv_device *dev)
+{
+ if (!IS_ERR(hv_root))
+ debugfs_remove_recursive(dev->debug_dir);
+}
+
+/* Remove all dentrys associated with vmbus testing */
+void hv_debug_rm_all_dir(void)
+{
+ debugfs_remove_recursive(hv_root);
+}
+
+/* Delay buffer/message reads on a vmbus channel */
+void hv_debug_delay_test(struct vmbus_channel *channel, enum delay delay_type)
+{
+ struct vmbus_channel *test_channel = channel->primary_channel ?
+ channel->primary_channel :
+ channel;
+ bool state = test_channel->fuzz_testing_state;
+
+ if (state) {
+ if (delay_type == 0)
+ udelay(test_channel->fuzz_testing_interrupt_delay);
+ else
+ udelay(test_channel->fuzz_testing_message_delay);
+ }
+}
+
+/* Initialize top dentry for vmbus testing */
+int hv_debug_init(void)
+{
+ hv_root = debugfs_create_dir(TESTING, NULL);
+ if (IS_ERR(hv_root)) {
+ pr_debug("debugfs_hyperv: %s/ not created\n", TESTING);
+ return PTR_ERR(hv_root);
+ }
+
+ return 0;
+}
+#endif /* CONFIG_HYPERV_TESTING */
+
static int __init hv_acpi_init(void)
{
int ret, t;
@@ -2108,6 +2268,9 @@ static int __init hv_acpi_init(void)
ret = -ETIMEDOUT;
goto cleanup;
}
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_init();
+#endif /* CONFIG_HYPERV_TESTING */
ret = vmbus_bus_init();
if (ret)
@@ -2140,6 +2303,10 @@ static void __exit vmbus_exit(void)
tasklet_kill(&hv_cpu->msg_dpc);
}
+#ifdef CONFIG_HYPERV_TESTING
+ hv_debug_rm_all_dir();
+#endif /* CONFIG_HYPERV_TESTING */
+
vmbus_free_channels();
if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
--
2.17.1
^ permalink raw reply related
* [PATCH v3 3/3] tools: hv: add vmbus testing tool
From: Branden Bonaby @ 2019-08-20 23:40 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, sashal
Cc: Branden Bonaby, linux-hyperv, linux-kernel
In-Reply-To: <cover.1566340843.git.brandonbonaby94@gmail.com>
This is a userspace tool to drive the testing. Currently it supports
introducing user specified delay in the host to guest communication
path on a per-channel basis.
Signed-off-by: Branden Bonaby <brandonbonaby94@gmail.com>
---
Changes in v3:
- Align python tool to match Linux coding style.
Changes in v2:
- Move testing location to new location in debugfs.
tools/hv/vmbus_testing | 342 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 342 insertions(+)
create mode 100644 tools/hv/vmbus_testing
diff --git a/tools/hv/vmbus_testing b/tools/hv/vmbus_testing
new file mode 100644
index 000000000000..0f249f6ee698
--- /dev/null
+++ b/tools/hv/vmbus_testing
@@ -0,0 +1,342 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Program to allow users to fuzz test Hyper-V drivers
+# by interfacing with Hyper-V debugfs directories
+# author: Branden Bonaby
+
+import os
+import cmd
+import argparse
+from collections import defaultdict
+from argparse import RawDescriptionHelpFormatter
+
+# debugfs paths for vmbus must exist (same as in lsvmbus)
+debugfs_sys_path = "/sys/kernel/debug/hyperv"
+if not os.path.isdir(debugfs_sys_path):
+ print("{} doesn't exist/check permissions".format(debugfs_sys_path))
+ exit(-1)
+# Do not change unless, you change the debugfs attributes
+# in "/sys/kernel/debug/hyperv/<UUID>/". All fuzz testing
+# attributes will start with "fuzz_test".
+pathlen = len(debugfs_sys_path)
+fuzz_state_location = "fuzz_test_state"
+fuzz_states = {
+ 0 : "Disable",
+ 1 : "Enable"
+}
+
+fuzz_methods = {
+ 1 : "Delay_testing"
+}
+
+fuzz_delay_types = {
+ 1 : "fuzz_test_buffer_interrupt_delay",
+ 2 : "fuzz_test_message_delay"
+}
+
+def parse_args():
+ parser = argparse.ArgumentParser(description = "vmbus_testing "
+ "[-s] [0|1] [-q] [-p] <debugfs-path>\n""vmbus_testing [-s]"
+ " [0|1] [-q][-p] <debugfs-path> delay [-d] [val][val] [-E|-D]\n"
+ "vmbus_testing [-q] disable-all\n"
+ "vmbus_testing [-q] view [-v|-V]\n"
+ "vmbus_testing --version",
+ epilog = "Current testing options {}".format(fuzz_methods),
+ prog = 'vmbus_testing',
+ formatter_class = RawDescriptionHelpFormatter)
+ subparsers = parser.add_subparsers(dest = "action")
+ parser.add_argument("--version", action = "version",
+ version = '%(prog)s 1.0')
+ parser.add_argument("-q","--quiet", action = "store_true",
+ help = "silence none important test messages")
+ parser.add_argument("-s","--state", metavar = "", type = int,
+ choices = range(0, 2),
+ help = "Turn testing ON or OFF for a single device."
+ " The value (1) will turn testing ON. The value"
+ " of (0) will turn testing OFF with the default set"
+ " to (0).")
+ parser.add_argument("-p","--path", metavar = "",
+ help = "Refers to the debugfs path to a vmbus device."
+ " If the path is not a valid path to a vmbus device,"
+ " the program will exit. The path must be the"
+ " absolute path; use the lsvmbus command to find"
+ " the path.")
+ parser_delay = subparsers.add_parser("delay",
+ help = "Delay buffer/message reads in microseconds.",
+ description = "vmbus_testing -s [0|1] [-q] -p "
+ "<debugfs-path> delay -d "
+ "[buffer-delay-value] [message-delay-value]\n"
+ "vmbus_testing [-q] delay [buffer-delay-value] "
+ "[message-delay-value] -E\n"
+ "vmbus_testing [-q] delay [buffer-delay-value] "
+ "[message-delay-value] -D",
+ formatter_class = RawDescriptionHelpFormatter)
+ delay_group = parser_delay.add_mutually_exclusive_group()
+ delay_group.add_argument("-E", "--en_all", action = "store_true",
+ help = "Enable Buffer/Message Delay testing on ALL"
+ " devices. Use -d option with this to set the values"
+ " for both the buffer delay and the message delay. No"
+ " value can be (0) or less than (-1). If testing is"
+ " disabled on a device prior to running this command,"
+ " testing will be enabled on the device as a result"
+ " of this command.")
+ delay_group.add_argument("-D", "--dis_all", action = "store_true",
+ help = "Disable Buffer/Message delay testing on ALL"
+ " devices. A value equal to (-1) will keep the"
+ " current delay value, and a value equal to (0) will"
+ " remove delay testing for the specfied delay column."
+ " only values (-1) and (0) will be accepted but at"
+ " least one value must be a (0) or a (-1).")
+ parser_delay.add_argument("-d", "--delay_time", metavar = "", nargs = 2,
+ type = check_range, default = [0, 0], required = (True),
+ help = "Buffer/message delay time. A value of (0) will"
+ "disable delay testing on the specified delay column,"
+ " while a value of (-1) will ignore the specified"
+ " delay column. The default values are [0] & [0]."
+ " The first column represents the buffer delay value"
+ " and the second represents the message delay value."
+ " Value constraints: -1 <= value <= 1000.")
+ parser_dis_all = subparsers.add_parser("disable-all",
+ help = "Disable ALL testing on all vmbus devices.",
+ description = "vmbus_testing disable-all",
+ formatter_class = RawDescriptionHelpFormatter)
+ parser_view = subparsers.add_parser("view",
+ help = "View testing on vmbus devices.",
+ description = "vmbus_testing view -V\n"
+ "vmbus_testing -p <debugfs-path> view -v",
+ formatter_class = RawDescriptionHelpFormatter)
+ view_group = parser_view.add_mutually_exclusive_group()
+ view_group.add_argument("-V", "--view_all", action = "store_true",
+ help = "View the test status for all vmbus devices.")
+ view_group.add_argument("-v", "--view_single", action = "store_true",
+ help = "View test values for a single vmbus device.")
+
+ return parser.parse_args()
+
+# value checking for range checking input in parser
+def check_range(arg1):
+ try:
+ val = int(arg1)
+ except ValueError as err:
+ raise argparse.ArgumentTypeError(str(err))
+ if val < -1 or val > 1000:
+ message = ("\n\nExpected -1 <= value <= 1000, got value"
+ " {}\n").format(val)
+ raise argparse.ArgumentTypeError(message)
+ return val
+
+def main():
+ try:
+ dev_list = []
+ for dir in os.listdir(debugfs_sys_path):
+ dev_list.append(os.path.join(debugfs_sys_path, dir))
+ #key value, pairs
+ #key = debugfs device path
+ #value = list of fuzz testing attributes.
+ dev_files = defaultdict(list)
+ for dev in dev_list:
+ path = os.path.join(dev, "delay")
+ for f in os.listdir(path):
+ if (f.startswith("fuzz_test")):
+ dev_files[path].append(f)
+
+ dev_files.default_factory = None
+ args = parse_args()
+ path = args.path
+ state = args.state
+ quiet = args.quiet
+ if (not quiet):
+ print("*** Use lsvmbus to get vmbus device type"
+ " information.*** ")
+ if (state is not None and validate_args_path(path, dev_list)):
+ if (state is not get_test_state(path)):
+ change_test_state(path, quiet)
+ state = get_test_state(path)
+ if (state == 0 and path is not None):
+ disable_testing_single_device(path, 0, quiet)
+ return
+ #Use subparsers as the key for different fuzz testing methods
+ if (args.action == "delay"):
+ delay = args.delay_time
+ if (validate_delay_values(args, delay)):
+ delay_test_all_devices(dev_list, delay, quiet)
+ elif (validate_args_path(path, dev_list)):
+ if(get_test_state(path) == 1):
+ delay_test_store(path, delay, quiet)
+ return
+ print("device testing OFF, use -s 1 to turn ON")
+ elif (args.action == "disable-all"):
+ disable_all_testing(dev_list, quiet)
+ elif (args.action == "view"):
+ if (args.view_all):
+ all_devices_test_status(dev_list)
+ elif (args.view_single):
+ if (validate_args_path(path, dev_list)):
+ device_test_values(dev_files, path)
+ return
+ print("Error,(check path) usage: -p"\
+ " <debugfs device path> view -v")
+ except AttributeError:
+ print("check usage, 1 or more elements not provided")
+ exit(-1)
+
+# Validate delay values to make sure they are acceptable to
+# to either enable all delays on a device or disable all
+# delays on a device
+def validate_delay_values(args, delay):
+ if (args.en_all):
+ for i in delay:
+ if (i < -1 or i == 0):
+ print("\nError, Values must be"
+ " equal to -1 or be > 0, use"
+ " -d option")
+ exit(-1)
+ return True
+ elif (args.dis_all):
+ for i in delay:
+ if (i < -1 or i > 0):
+ print("\nError, at least 1 value"
+ " is not a (0) or a (-1)")
+ exit(-1)
+ return True
+ else:
+ return False
+
+
+# Validate argument path
+def validate_args_path(path, dev_list):
+ if (path in dev_list):
+ return True
+ else:
+ return False
+
+# display Testing status of single device
+def device_test_values(dev_files, path):
+
+ delay_path = os.path.join(path, 'delay')
+ for test in dev_files.get(delay_path):
+ print("{}".format(test), end = '')
+ print((" value = {}")\
+ .format(read_test_files(os.path.join(delay_path, test))))
+
+# display Testing state of devices
+def all_devices_test_status(dev_list):
+ for device in dev_list:
+ if (get_test_state(device) is 1):
+ print("Testing = ON for: {}".format(device.split("/")[5]))
+ else:
+ print("Testing = OFF for: {}".format(device.split("/")[5]))
+
+# read the vmbus device files, path must be absolute path before calling
+def read_test_files(path):
+ try:
+ with open(path,"r") as f:
+ state = f.readline().strip()
+ if (state == 'N'):
+ state = 0
+ elif (state == 'Y'):
+ state = 1
+ return int(state)
+
+ except IOError as e:
+ errno, strerror = e.args
+ print("I/O error({0}): {1} on file {2}"
+ .format(errno, strerror, path))
+ exit(-1)
+ except ValueError:
+ print ("Element to int conversion error in: \n{}".format(path))
+ exit(-1)
+
+# writing to vmbus device files, path must be absolute path before calling
+def write_test_files(path, value):
+ try:
+ with open(path,"w") as f:
+ f.write("{}".format(value))
+ except IOError as e:
+ errno, strerror = e.args
+ print("I/O error({0}): {1} on file {2}"
+ .format(errno, strerror, path))
+ exit(-1)
+
+# change testing state of device
+def change_test_state(device, quiet):
+ state_path = os.path.join(device, fuzz_state_location)
+ if (get_test_state(device) is 0):
+ write_test_files(state_path, 1)
+ if (not quiet):
+ print("Testing = ON for device: {}"
+ .format(state_path.split("/")[5]))
+ else:
+ write_test_files(state_path, 0)
+ if (not quiet):
+ print("Testing = OFF for device: {}"
+ .format(state_path.split("/")[5]))
+
+# get testing state of device
+def get_test_state(device):
+ #state == 1 - test = ON
+ #state == 0 - test = OFF
+ return read_test_files(os.path.join(device, fuzz_state_location))
+
+# Enter 1 - 1000 microseconds, into a single device using the
+# fuzz_test_buffer_interrupt_delay and fuzz_test_message_delay
+# debugfs attributes
+def delay_test_store(device,delay_length, quiet):
+
+ try:
+ # delay[0]- buffer delay, delay[1]- message delay
+ buff_test = os.path.join(os.path.sep,device, 'delay',
+ fuzz_delay_types.get(1))
+ mess_test = os.path.join(os.path.sep,device, 'delay',
+ fuzz_delay_types.get(2))
+
+ if (delay_length[0] >= 0):
+ write_test_files(buff_test, delay_length[0])
+ if (delay_length[1] >= 0):
+ write_test_files(mess_test, delay_length[1])
+ if (not quiet):
+ print("Buffer delay testing = {} for: {}"
+ .format(read_test_files(buff_test),
+ buff_test.split("/")[5]))
+ print("Message delay testing = {} for: {}"
+ .format(read_test_files(mess_test),
+ mess_test.split("/")[5]))
+ except IOError as e:
+ errno, strerror = e.args
+ print("I/O error({0}): {1} on files {2}{3}"
+ .format(errno, strerror, buff_test, mess_test))
+ exit(-1)
+
+#enabling/disabling delay testing on all devices
+def delay_test_all_devices(dev_list,delay,quiet):
+
+ for device in (dev_list):
+ if (get_test_state(device) is 0):
+ change_test_state(device,quiet)
+ delay_test_store(device, delay, quiet)
+
+#disabling testing on single device
+def disable_testing_single_device(device,test_type,quiet):
+
+ #test_type represents corresponding key
+ #delay method in delay_methods dict.
+ #special type 0 , used to disable all
+ #testing on SINGLE device.
+
+ if (test_type is 1 or test_type is 0):
+ #disable list [buffer,message]
+ disable_delay = [0, 0]
+ if (get_test_state(device) is 1):
+ change_test_state(device, quiet)
+ delay_test_store(device, disable_delay, quiet)
+
+#disabling testing on ALL devices
+def disable_all_testing(dev_list,quiet):
+
+ #delay disable list [buffer,message]
+ for device in dev_list:
+ disable_testing_single_device(device, 0, quiet)
+
+if __name__ == "__main__":
+ main()
--
2.17.1
^ permalink raw reply related
* [PATCH net-next,v3, 0/6] Add software backchannel and mlx5e HV VHCA stats
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org
This patch set adds paravirtual backchannel in software in pci_hyperv,
which is required by the mlx5e driver HV VHCA stats agent.
The stats agent is responsible on running a periodic rx/tx packets/bytes
stats update.
Dexuan Cui (1):
PCI: hv: Add a paravirtual backchannel in software
Eran Ben Elisha (4):
net/mlx5: Add wrappers for HyperV PCIe operations
net/mlx5: Add HV VHCA infrastructure
net/mlx5: Add HV VHCA control agent
net/mlx5e: Add mlx5e HV VHCA stats agent
Haiyang Zhang (1):
PCI: hv: Add a Hyper-V PCI interface driver for software backchannel
interface
MAINTAINERS | 1 +
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +
drivers/net/ethernet/mellanox/mlx5/core/en.h | 13 +
.../ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c | 162 +++++++++
.../ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h | 25 ++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +
drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c | 64 ++++
drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h | 22 ++
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c | 371 +++++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h | 104 ++++++
drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +
drivers/pci/Kconfig | 1 +
drivers/pci/controller/Kconfig | 7 +
drivers/pci/controller/Makefile | 1 +
drivers/pci/controller/pci-hyperv-intf.c | 67 ++++
drivers/pci/controller/pci-hyperv.c | 308 +++++++++++++++++
include/linux/hyperv.h | 29 ++
include/linux/mlx5/driver.h | 2 +
18 files changed, 1189 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
create mode 100644 drivers/pci/controller/pci-hyperv-intf.c
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next,v3, 6/6] net/mlx5e: Add mlx5e HV VHCA stats agent
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org
In-Reply-To: <1566346948-69497-1-git-send-email-haiyangz@microsoft.com>
From: Eran Ben Elisha <eranbe@mellanox.com>
HV VHCA stats agent is responsible on running a preiodic rx/tx
packets/bytes stats update. Currently the supported format is version
MLX5_HV_VHCA_STATS_VERSION. Block ID 1 is dedicated for statistics data
transfer from the VF to the PF.
The reporter fetch the statistics data from all opened channels, fill it
in a buffer and send it to mlx5_hv_vhca_write_agent.
As the stats layer should include some metadata per block (sequence and
offset), the HV VHCA layer shall modify the buffer before actually send it
over block 1.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 1 +
drivers/net/ethernet/mellanox/mlx5/core/en.h | 13 ++
.../ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c | 162 +++++++++++++++++++++
.../ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h | 25 ++++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h | 1 +
6 files changed, 205 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index fc59a40..a889a38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -36,6 +36,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \
lib/geneve.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
en/tc_tun_geneve.o
+mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
#
# Core extra
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8fc5107..4a8008b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -54,6 +54,7 @@
#include "mlx5_core.h"
#include "en_stats.h"
#include "en/fs.h"
+#include "lib/hv_vhca.h"
extern const struct net_device_ops mlx5e_netdev_ops;
struct page_pool;
@@ -777,6 +778,15 @@ struct mlx5e_modify_sq_param {
int rl_index;
};
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+struct mlx5e_hv_vhca_stats_agent {
+ struct mlx5_hv_vhca_agent *agent;
+ struct delayed_work work;
+ u16 delay;
+ void *buf;
+};
+#endif
+
struct mlx5e_xsk {
/* UMEMs are stored separately from channels, because we don't want to
* lose them when channels are recreated. The kernel also stores UMEMs,
@@ -848,6 +858,9 @@ struct mlx5e_priv {
struct devlink_health_reporter *tx_reporter;
struct devlink_health_reporter *rx_reporter;
struct mlx5e_xsk xsk;
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+ struct mlx5e_hv_vhca_stats_agent stats_agent;
+#endif
};
struct mlx5e_profile {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
new file mode 100644
index 0000000..c37b4ac
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include "en.h"
+#include "en/hv_vhca_stats.h"
+#include "lib/hv_vhca.h"
+#include "lib/hv.h"
+
+struct mlx5e_hv_vhca_per_ring_stats {
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 tx_packets;
+ u64 tx_bytes;
+};
+
+static void
+mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch,
+ struct mlx5e_hv_vhca_per_ring_stats *data)
+{
+ struct mlx5e_channel_stats *stats;
+ int tc;
+
+ stats = &priv->channel_stats[ch];
+ data->rx_packets = stats->rq.packets;
+ data->rx_bytes = stats->rq.bytes;
+
+ for (tc = 0; tc < priv->max_opened_tc; tc++) {
+ data->tx_packets += stats->sq[tc].packets;
+ data->tx_bytes += stats->sq[tc].bytes;
+ }
+}
+
+static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, u64 *data,
+ int buf_len)
+{
+ int ch, i = 0;
+
+ for (ch = 0; ch < priv->max_nch; ch++) {
+ u64 *buf = data + i;
+
+ if (WARN_ON_ONCE(buf +
+ sizeof(struct mlx5e_hv_vhca_per_ring_stats) >
+ data + buf_len))
+ return;
+
+ mlx5e_hv_vhca_fill_ring_stats(priv, ch,
+ (struct mlx5e_hv_vhca_per_ring_stats *)buf);
+ i += sizeof(struct mlx5e_hv_vhca_per_ring_stats) / sizeof(u64);
+ }
+}
+
+static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv)
+{
+ return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) *
+ priv->max_nch);
+}
+
+static void mlx5e_hv_vhca_stats_work(struct work_struct *work)
+{
+ struct mlx5e_hv_vhca_stats_agent *sagent;
+ struct mlx5_hv_vhca_agent *agent;
+ struct delayed_work *dwork;
+ struct mlx5e_priv *priv;
+ int buf_len, rc;
+ void *buf;
+
+ dwork = to_delayed_work(work);
+ sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work);
+ priv = container_of(sagent, struct mlx5e_priv, stats_agent);
+ buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
+ agent = sagent->agent;
+ buf = sagent->buf;
+
+ memset(buf, 0, buf_len);
+ mlx5e_hv_vhca_fill_stats(priv, buf, buf_len);
+
+ rc = mlx5_hv_vhca_agent_write(agent, buf, buf_len);
+ if (rc) {
+ mlx5_core_err(priv->mdev,
+ "%s: Failed to write stats, err = %d\n",
+ __func__, rc);
+ return;
+ }
+
+ if (sagent->delay)
+ queue_delayed_work(priv->wq, &sagent->work, sagent->delay);
+}
+
+enum {
+ MLX5_HV_VHCA_STATS_VERSION = 1,
+ MLX5_HV_VHCA_STATS_UPDATE_ONCE = 0xFFFF,
+};
+
+static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent,
+ struct mlx5_hv_vhca_control_block *block)
+{
+ struct mlx5e_hv_vhca_stats_agent *sagent;
+ struct mlx5e_priv *priv;
+
+ priv = mlx5_hv_vhca_agent_priv(agent);
+ sagent = &priv->stats_agent;
+
+ block->version = MLX5_HV_VHCA_STATS_VERSION;
+ block->rings = priv->max_nch;
+
+ if (!block->command) {
+ cancel_delayed_work_sync(&priv->stats_agent.work);
+ return;
+ }
+
+ sagent->delay = block->command == MLX5_HV_VHCA_STATS_UPDATE_ONCE ? 0 :
+ msecs_to_jiffies(block->command * 100);
+
+ queue_delayed_work(priv->wq, &sagent->work, sagent->delay);
+}
+
+static void mlx5e_hv_vhca_stats_cleanup(struct mlx5_hv_vhca_agent *agent)
+{
+ struct mlx5e_priv *priv = mlx5_hv_vhca_agent_priv(agent);
+
+ cancel_delayed_work_sync(&priv->stats_agent.work);
+}
+
+int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
+{
+ int buf_len = mlx5e_hv_vhca_stats_buf_size(priv);
+ struct mlx5_hv_vhca_agent *agent;
+
+ priv->stats_agent.buf = kvzalloc(buf_len, GFP_KERNEL);
+ if (!priv->stats_agent.buf)
+ return -ENOMEM;
+
+ agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca,
+ MLX5_HV_VHCA_AGENT_STATS,
+ mlx5e_hv_vhca_stats_control, NULL,
+ mlx5e_hv_vhca_stats_cleanup,
+ priv);
+
+ if (IS_ERR_OR_NULL(agent)) {
+ if (IS_ERR(agent))
+ netdev_warn(priv->netdev,
+ "Failed to create hv vhca stats agent, err = %ld\n",
+ PTR_ERR(agent));
+
+ kfree(priv->stats_agent.buf);
+ return IS_ERR_OR_NULL(agent);
+ }
+
+ priv->stats_agent.agent = agent;
+ INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work);
+
+ return 0;
+}
+
+void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
+{
+ if (IS_ERR_OR_NULL(priv->stats_agent.agent))
+ return;
+
+ mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent);
+ kfree(priv->stats_agent.buf);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h
new file mode 100644
index 0000000..664463f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_STATS_VHCA_H__
+#define __MLX5_EN_STATS_VHCA_H__
+#include "en.h"
+
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+
+int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv);
+void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv);
+
+#else
+
+static inline int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
+{
+ return 0;
+}
+
+static inline void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
+{
+}
+#endif
+
+#endif /* __MLX5_EN_STATS_VHCA_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5721d3d..fac8455 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -64,6 +64,7 @@
#include "en/xsk/setup.h"
#include "en/xsk/rx.h"
#include "en/xsk/tx.h"
+#include "en/hv_vhca_stats.h"
bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
@@ -5103,6 +5104,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
if (mlx5e_monitor_counter_supported(priv))
mlx5e_monitor_counter_init(priv);
+ mlx5e_hv_vhca_stats_create(priv);
if (netdev->reg_state != NETREG_REGISTERED)
return;
#ifdef CONFIG_MLX5_CORE_EN_DCB
@@ -5135,6 +5137,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
queue_work(priv->wq, &priv->set_rx_mode_work);
+ mlx5e_hv_vhca_stats_destroy(priv);
if (mlx5e_monitor_counter_supported(priv))
mlx5e_monitor_counter_cleanup(priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
index 984e7ad..4bad6a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
@@ -13,6 +13,7 @@
enum mlx5_hv_vhca_agent_type {
MLX5_HV_VHCA_AGENT_CONTROL = 0,
+ MLX5_HV_VHCA_AGENT_STATS = 1,
MLX5_HV_VHCA_AGENT_MAX = 32,
};
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next,v3, 5/6] net/mlx5: Add HV VHCA control agent
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org
In-Reply-To: <1566346948-69497-1-git-send-email-haiyangz@microsoft.com>
From: Eran Ben Elisha <eranbe@mellanox.com>
Control agent is responsible over of the control block (ID 0). It should
update the PF via this block about every capability change. In addition,
upon block 0 invalidate, it should activate all other supported agents
with data requests from the PF.
Upon agent create/destroy, the invalidate callback of the control agent
is being called in order to update the PF driver about this change.
The control agent is an integral part of HV VHCA and will be created
and destroy as part of the HV VHCA init/cleanup flow.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c | 122 ++++++++++++++++++++-
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h | 1 +
2 files changed, 121 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
index 84d1d75..4047629 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
@@ -109,22 +109,131 @@ void mlx5_hv_vhca_invalidate(void *context, u64 block_mask)
queue_work(hv_vhca->work_queue, &work->invalidate_work);
}
+#define AGENT_MASK(type) (type ? BIT(type - 1) : 0 /* control */)
+
+static void mlx5_hv_vhca_agents_control(struct mlx5_hv_vhca *hv_vhca,
+ struct mlx5_hv_vhca_control_block *block)
+{
+ int i;
+
+ for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) {
+ struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i];
+
+ if (!agent || !agent->control)
+ continue;
+
+ if (!(AGENT_MASK(agent->type) & block->control))
+ continue;
+
+ agent->control(agent, block);
+ }
+}
+
+static void mlx5_hv_vhca_capabilities(struct mlx5_hv_vhca *hv_vhca,
+ u32 *capabilities)
+{
+ int i;
+
+ for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) {
+ struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i];
+
+ if (agent)
+ *capabilities |= AGENT_MASK(agent->type);
+ }
+}
+
+static void
+mlx5_hv_vhca_control_agent_invalidate(struct mlx5_hv_vhca_agent *agent,
+ u64 block_mask)
+{
+ struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca;
+ struct mlx5_core_dev *dev = hv_vhca->dev;
+ struct mlx5_hv_vhca_control_block *block;
+ u32 capabilities = 0;
+ int err;
+
+ block = kzalloc(sizeof(*block), GFP_KERNEL);
+ if (!block)
+ return;
+
+ err = mlx5_hv_read_config(dev, block, sizeof(*block), 0);
+ if (err)
+ goto free_block;
+
+ mlx5_hv_vhca_capabilities(hv_vhca, &capabilities);
+
+ /* In case no capabilities, send empty block in return */
+ if (!capabilities) {
+ memset(block, 0, sizeof(*block));
+ goto write;
+ }
+
+ if (block->capabilities != capabilities)
+ block->capabilities = capabilities;
+
+ if (block->control & ~capabilities)
+ goto free_block;
+
+ mlx5_hv_vhca_agents_control(hv_vhca, block);
+ block->command_ack = block->command;
+
+write:
+ mlx5_hv_write_config(dev, block, sizeof(*block), 0);
+
+free_block:
+ kfree(block);
+}
+
+static struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_control_agent_create(struct mlx5_hv_vhca *hv_vhca)
+{
+ return mlx5_hv_vhca_agent_create(hv_vhca, MLX5_HV_VHCA_AGENT_CONTROL,
+ NULL,
+ mlx5_hv_vhca_control_agent_invalidate,
+ NULL, NULL);
+}
+
+static void mlx5_hv_vhca_control_agent_destroy(struct mlx5_hv_vhca_agent *agent)
+{
+ mlx5_hv_vhca_agent_destroy(agent);
+}
+
int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca)
{
+ struct mlx5_hv_vhca_agent *agent;
+ int err;
+
if (IS_ERR_OR_NULL(hv_vhca))
return IS_ERR_OR_NULL(hv_vhca);
- return mlx5_hv_register_invalidate(hv_vhca->dev, hv_vhca,
- mlx5_hv_vhca_invalidate);
+ err = mlx5_hv_register_invalidate(hv_vhca->dev, hv_vhca,
+ mlx5_hv_vhca_invalidate);
+ if (err)
+ return err;
+
+ agent = mlx5_hv_vhca_control_agent_create(hv_vhca);
+ if (IS_ERR_OR_NULL(agent)) {
+ mlx5_hv_unregister_invalidate(hv_vhca->dev);
+ return IS_ERR_OR_NULL(agent);
+ }
+
+ hv_vhca->agents[MLX5_HV_VHCA_AGENT_CONTROL] = agent;
+
+ return 0;
}
void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca)
{
+ struct mlx5_hv_vhca_agent *agent;
int i;
if (IS_ERR_OR_NULL(hv_vhca))
return;
+ agent = hv_vhca->agents[MLX5_HV_VHCA_AGENT_CONTROL];
+ if (agent)
+ mlx5_hv_vhca_control_agent_destroy(agent);
+
mutex_lock(&hv_vhca->agents_lock);
for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++)
WARN_ON(hv_vhca->agents[i]);
@@ -134,6 +243,11 @@ void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca)
mlx5_hv_unregister_invalidate(hv_vhca->dev);
}
+static void mlx5_hv_vhca_agents_update(struct mlx5_hv_vhca *hv_vhca)
+{
+ mlx5_hv_vhca_invalidate(hv_vhca, BIT(MLX5_HV_VHCA_AGENT_CONTROL));
+}
+
struct mlx5_hv_vhca_agent *
mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
enum mlx5_hv_vhca_agent_type type,
@@ -174,6 +288,8 @@ struct mlx5_hv_vhca_agent *
hv_vhca->agents[type] = agent;
mutex_unlock(&hv_vhca->agents_lock);
+ mlx5_hv_vhca_agents_update(hv_vhca);
+
return agent;
}
@@ -195,6 +311,8 @@ void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent)
agent->cleanup(agent);
kfree(agent);
+
+ mlx5_hv_vhca_agents_update(hv_vhca);
}
static int mlx5_hv_vhca_data_block_prepare(struct mlx5_hv_vhca_agent *agent,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
index cdf1303..984e7ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
@@ -12,6 +12,7 @@
struct mlx5_hv_vhca_control_block;
enum mlx5_hv_vhca_agent_type {
+ MLX5_HV_VHCA_AGENT_CONTROL = 0,
MLX5_HV_VHCA_AGENT_MAX = 32,
};
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next,v3, 4/6] net/mlx5: Add HV VHCA infrastructure
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org
In-Reply-To: <1566346948-69497-1-git-send-email-haiyangz@microsoft.com>
From: Eran Ben Elisha <eranbe@mellanox.com>
HV VHCA is a layer which provides PF to VF communication channel based on
HyperV PCI config channel. It implements Mellanox's Inter VHCA control
communication protocol. The protocol contains control block in order to
pass messages between the PF and VF drivers, and data blocks in order to
pass actual data.
The infrastructure is agent based. Each agent will be responsible of
contiguous buffer blocks in the VHCA config space. This infrastructure will
bind agents to their blocks, and those agents can only access read/write
the buffer blocks assigned to them. Each agent will provide three
callbacks (control, invalidate, cleanup). Control will be invoked when
block-0 is invalidated with a command that concerns this agent. Invalidate
callback will be invoked if one of the blocks assigned to this agent was
invalidated. Cleanup will be invoked before the agent is being freed in
order to clean all of its open resources or deferred works.
Block-0 serves as the control block. All execution commands from the PF
will be written by the PF over this block. VF will ack on those by
writing on block-0 as well. Its format is described by struct
mlx5_hv_vhca_control_block layout.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +-
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c | 253 +++++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h | 102 +++++++++
drivers/net/ethernet/mellanox/mlx5/core/main.c | 7 +
include/linux/mlx5/driver.h | 2 +
5 files changed, 365 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 247295b..fc59a40 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -45,7 +45,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offlo
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
-mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o
+mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o lib/hv_vhca.o
#
# Ipoib netdev
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
new file mode 100644
index 0000000..84d1d75
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c
@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/hyperv.h>
+#include "mlx5_core.h"
+#include "lib/hv.h"
+#include "lib/hv_vhca.h"
+
+struct mlx5_hv_vhca {
+ struct mlx5_core_dev *dev;
+ struct workqueue_struct *work_queue;
+ struct mlx5_hv_vhca_agent *agents[MLX5_HV_VHCA_AGENT_MAX];
+ struct mutex agents_lock; /* Protect agents array */
+};
+
+struct mlx5_hv_vhca_work {
+ struct work_struct invalidate_work;
+ struct mlx5_hv_vhca *hv_vhca;
+ u64 block_mask;
+};
+
+struct mlx5_hv_vhca_data_block {
+ u16 sequence;
+ u16 offset;
+ u8 reserved[4];
+ u64 data[15];
+};
+
+struct mlx5_hv_vhca_agent {
+ enum mlx5_hv_vhca_agent_type type;
+ struct mlx5_hv_vhca *hv_vhca;
+ void *priv;
+ u16 seq;
+ void (*control)(struct mlx5_hv_vhca_agent *agent,
+ struct mlx5_hv_vhca_control_block *block);
+ void (*invalidate)(struct mlx5_hv_vhca_agent *agent,
+ u64 block_mask);
+ void (*cleanup)(struct mlx5_hv_vhca_agent *agent);
+};
+
+struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev)
+{
+ struct mlx5_hv_vhca *hv_vhca = NULL;
+
+ hv_vhca = kzalloc(sizeof(*hv_vhca), GFP_KERNEL);
+ if (!hv_vhca)
+ return ERR_PTR(-ENOMEM);
+
+ hv_vhca->work_queue = create_singlethread_workqueue("mlx5_hv_vhca");
+ if (!hv_vhca->work_queue) {
+ kfree(hv_vhca);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ hv_vhca->dev = dev;
+ mutex_init(&hv_vhca->agents_lock);
+
+ return hv_vhca;
+}
+
+void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca)
+{
+ if (IS_ERR_OR_NULL(hv_vhca))
+ return;
+
+ destroy_workqueue(hv_vhca->work_queue);
+ kfree(hv_vhca);
+}
+
+static void mlx5_hv_vhca_invalidate_work(struct work_struct *work)
+{
+ struct mlx5_hv_vhca_work *hwork;
+ struct mlx5_hv_vhca *hv_vhca;
+ int i;
+
+ hwork = container_of(work, struct mlx5_hv_vhca_work, invalidate_work);
+ hv_vhca = hwork->hv_vhca;
+
+ mutex_lock(&hv_vhca->agents_lock);
+ for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) {
+ struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i];
+
+ if (!agent || !agent->invalidate)
+ continue;
+
+ if (!(BIT(agent->type) & hwork->block_mask))
+ continue;
+
+ agent->invalidate(agent, hwork->block_mask);
+ }
+ mutex_unlock(&hv_vhca->agents_lock);
+
+ kfree(hwork);
+}
+
+void mlx5_hv_vhca_invalidate(void *context, u64 block_mask)
+{
+ struct mlx5_hv_vhca *hv_vhca = (struct mlx5_hv_vhca *)context;
+ struct mlx5_hv_vhca_work *work;
+
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work)
+ return;
+
+ INIT_WORK(&work->invalidate_work, mlx5_hv_vhca_invalidate_work);
+ work->hv_vhca = hv_vhca;
+ work->block_mask = block_mask;
+
+ queue_work(hv_vhca->work_queue, &work->invalidate_work);
+}
+
+int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca)
+{
+ if (IS_ERR_OR_NULL(hv_vhca))
+ return IS_ERR_OR_NULL(hv_vhca);
+
+ return mlx5_hv_register_invalidate(hv_vhca->dev, hv_vhca,
+ mlx5_hv_vhca_invalidate);
+}
+
+void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca)
+{
+ int i;
+
+ if (IS_ERR_OR_NULL(hv_vhca))
+ return;
+
+ mutex_lock(&hv_vhca->agents_lock);
+ for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++)
+ WARN_ON(hv_vhca->agents[i]);
+
+ mutex_unlock(&hv_vhca->agents_lock);
+
+ mlx5_hv_unregister_invalidate(hv_vhca->dev);
+}
+
+struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
+ enum mlx5_hv_vhca_agent_type type,
+ void (*control)(struct mlx5_hv_vhca_agent*,
+ struct mlx5_hv_vhca_control_block *block),
+ void (*invalidate)(struct mlx5_hv_vhca_agent*,
+ u64 block_mask),
+ void (*cleaup)(struct mlx5_hv_vhca_agent *agent),
+ void *priv)
+{
+ struct mlx5_hv_vhca_agent *agent;
+
+ if (IS_ERR_OR_NULL(hv_vhca))
+ return ERR_PTR(-ENOMEM);
+
+ if (type >= MLX5_HV_VHCA_AGENT_MAX)
+ return ERR_PTR(-EINVAL);
+
+ mutex_lock(&hv_vhca->agents_lock);
+ if (hv_vhca->agents[type]) {
+ mutex_unlock(&hv_vhca->agents_lock);
+ return ERR_PTR(-EINVAL);
+ }
+ mutex_unlock(&hv_vhca->agents_lock);
+
+ agent = kzalloc(sizeof(*agent), GFP_KERNEL);
+ if (!agent)
+ return ERR_PTR(-ENOMEM);
+
+ agent->type = type;
+ agent->hv_vhca = hv_vhca;
+ agent->priv = priv;
+ agent->control = control;
+ agent->invalidate = invalidate;
+ agent->cleanup = cleaup;
+
+ mutex_lock(&hv_vhca->agents_lock);
+ hv_vhca->agents[type] = agent;
+ mutex_unlock(&hv_vhca->agents_lock);
+
+ return agent;
+}
+
+void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent)
+{
+ struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca;
+
+ mutex_lock(&hv_vhca->agents_lock);
+
+ if (WARN_ON(agent != hv_vhca->agents[agent->type])) {
+ mutex_unlock(&hv_vhca->agents_lock);
+ return;
+ }
+
+ hv_vhca->agents[agent->type] = NULL;
+ mutex_unlock(&hv_vhca->agents_lock);
+
+ if (agent->cleanup)
+ agent->cleanup(agent);
+
+ kfree(agent);
+}
+
+static int mlx5_hv_vhca_data_block_prepare(struct mlx5_hv_vhca_agent *agent,
+ struct mlx5_hv_vhca_data_block *data_block,
+ void *src, int len, int *offset)
+{
+ int bytes = min_t(int, (int)sizeof(data_block->data), len);
+
+ data_block->sequence = agent->seq;
+ data_block->offset = (*offset)++;
+ memcpy(data_block->data, src, bytes);
+
+ return bytes;
+}
+
+static void mlx5_hv_vhca_agent_seq_update(struct mlx5_hv_vhca_agent *agent)
+{
+ agent->seq++;
+}
+
+int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent,
+ void *buf, int len)
+{
+ int offset = agent->type * HV_CONFIG_BLOCK_SIZE_MAX;
+ int block_offset = 0;
+ int total = 0;
+ int err;
+
+ while (len) {
+ struct mlx5_hv_vhca_data_block data_block = {0};
+ int bytes;
+
+ bytes = mlx5_hv_vhca_data_block_prepare(agent, &data_block,
+ buf + total,
+ len, &block_offset);
+ if (!bytes)
+ return -ENOMEM;
+
+ err = mlx5_hv_write_config(agent->hv_vhca->dev, &data_block,
+ sizeof(data_block), offset);
+ if (err)
+ return err;
+
+ total += bytes;
+ len -= bytes;
+ }
+
+ mlx5_hv_vhca_agent_seq_update(agent);
+
+ return 0;
+}
+
+void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent)
+{
+ return agent->priv;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
new file mode 100644
index 0000000..cdf1303
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __LIB_HV_VHCA_H__
+#define __LIB_HV_VHCA_H__
+
+#include "en.h"
+#include "lib/hv.h"
+
+struct mlx5_hv_vhca_agent;
+struct mlx5_hv_vhca;
+struct mlx5_hv_vhca_control_block;
+
+enum mlx5_hv_vhca_agent_type {
+ MLX5_HV_VHCA_AGENT_MAX = 32,
+};
+
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+
+struct mlx5_hv_vhca_control_block {
+ u32 capabilities;
+ u32 control;
+ u16 command;
+ u16 command_ack;
+ u16 version;
+ u16 rings;
+ u32 reserved1[28];
+};
+
+struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev);
+void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca);
+int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca);
+void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca);
+void mlx5_hv_vhca_invalidate(void *context, u64 block_mask);
+
+struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
+ enum mlx5_hv_vhca_agent_type type,
+ void (*control)(struct mlx5_hv_vhca_agent*,
+ struct mlx5_hv_vhca_control_block *block),
+ void (*invalidate)(struct mlx5_hv_vhca_agent*,
+ u64 block_mask),
+ void (*cleanup)(struct mlx5_hv_vhca_agent *agent),
+ void *context);
+
+void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent);
+int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent,
+ void *buf, int len);
+void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent);
+
+#else
+
+static inline struct mlx5_hv_vhca *
+mlx5_hv_vhca_create(struct mlx5_core_dev *dev)
+{
+ return NULL;
+}
+
+static inline void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca)
+{
+}
+
+static inline int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca)
+{
+ return 0;
+}
+
+static inline void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca)
+{
+}
+
+static inline void mlx5_hv_vhca_invalidate(void *context,
+ u64 block_mask)
+{
+}
+
+static inline struct mlx5_hv_vhca_agent *
+mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca,
+ enum mlx5_hv_vhca_agent_type type,
+ void (*control)(struct mlx5_hv_vhca_agent*,
+ struct mlx5_hv_vhca_control_block *block),
+ void (*invalidate)(struct mlx5_hv_vhca_agent*,
+ u64 block_mask),
+ void (*cleanup)(struct mlx5_hv_vhca_agent *agent),
+ void *context)
+{
+ return NULL;
+}
+
+static inline void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent)
+{
+}
+
+static inline int
+mlx5_hv_vhca_write_agent(struct mlx5_hv_vhca_agent *agent,
+ void *buf, int len)
+{
+ return 0;
+}
+#endif
+
+#endif /* __LIB_HV_VHCA_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 80437d4..4b74315 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -69,6 +69,7 @@
#include "lib/pci_vsc.h"
#include "diag/fw_tracer.h"
#include "ecpf.h"
+#include "lib/hv_vhca.h"
MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -868,6 +869,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
}
dev->tracer = mlx5_fw_tracer_create(dev);
+ dev->hv_vhca = mlx5_hv_vhca_create(dev);
return 0;
@@ -897,6 +899,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
{
+ mlx5_hv_vhca_destroy(dev->hv_vhca);
mlx5_fw_tracer_destroy(dev->tracer);
mlx5_fpga_cleanup(dev);
mlx5_eswitch_cleanup(dev->priv.eswitch);
@@ -1063,6 +1066,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
goto err_fw_tracer;
}
+ mlx5_hv_vhca_init(dev->hv_vhca);
+
err = mlx5_fpga_device_start(dev);
if (err) {
mlx5_core_err(dev, "fpga device start failed %d\n", err);
@@ -1118,6 +1123,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
err_ipsec_start:
mlx5_fpga_device_stop(dev);
err_fpga_start:
+ mlx5_hv_vhca_cleanup(dev->hv_vhca);
mlx5_fw_tracer_cleanup(dev->tracer);
err_fw_tracer:
mlx5_eq_table_destroy(dev);
@@ -1138,6 +1144,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
mlx5_accel_ipsec_cleanup(dev);
mlx5_accel_tls_cleanup(dev);
mlx5_fpga_device_stop(dev);
+ mlx5_hv_vhca_cleanup(dev->hv_vhca);
mlx5_fw_tracer_cleanup(dev->tracer);
mlx5_eq_table_destroy(dev);
mlx5_irq_table_destroy(dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 467de34..0e00cbc 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -638,6 +638,7 @@ struct mlx5_clock {
struct mlx5_fw_tracer;
struct mlx5_vxlan;
struct mlx5_geneve;
+struct mlx5_hv_vhca;
struct mlx5_core_dev {
struct device *device;
@@ -685,6 +686,7 @@ struct mlx5_core_dev {
struct mlx5_ib_clock_info *clock_info;
struct mlx5_fw_tracer *tracer;
u32 vsc_addr;
+ struct mlx5_hv_vhca *hv_vhca;
};
struct mlx5_db {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next,v3, 3/6] net/mlx5: Add wrappers for HyperV PCIe operations
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org
In-Reply-To: <1566346948-69497-1-git-send-email-haiyangz@microsoft.com>
From: Eran Ben Elisha <eranbe@mellanox.com>
Add wrapper functions for HyperV PCIe read / write /
block_invalidate_register operations. This will be used as an
infrastructure in the downstream patch for software communication.
This will be enabled by default if CONFIG_PCI_HYPERV_INTERFACE is set.
Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 1 +
drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c | 64 ++++++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h | 22 ++++++++
3 files changed, 87 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 8b7edaa..247295b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -45,6 +45,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offlo
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
+mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o
#
# Ipoib netdev
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c
new file mode 100644
index 0000000..cf08d02
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/hyperv.h>
+#include "mlx5_core.h"
+#include "lib/hv.h"
+
+static int mlx5_hv_config_common(struct mlx5_core_dev *dev, void *buf, int len,
+ int offset, bool read)
+{
+ int rc = -EOPNOTSUPP;
+ int bytes_returned;
+ int block_id;
+
+ if (offset % HV_CONFIG_BLOCK_SIZE_MAX || len % HV_CONFIG_BLOCK_SIZE_MAX)
+ return -EINVAL;
+
+ block_id = offset / HV_CONFIG_BLOCK_SIZE_MAX;
+
+ rc = read ?
+ hyperv_read_cfg_blk(dev->pdev, buf,
+ HV_CONFIG_BLOCK_SIZE_MAX, block_id,
+ &bytes_returned) :
+ hyperv_write_cfg_blk(dev->pdev, buf,
+ HV_CONFIG_BLOCK_SIZE_MAX, block_id);
+
+ /* Make sure len bytes were read successfully */
+ if (read)
+ rc |= !(len == bytes_returned);
+
+ if (rc) {
+ mlx5_core_err(dev, "Failed to %s hv config, err = %d, len = %d, offset = %d\n",
+ read ? "read" : "write", rc, len,
+ offset);
+ return rc;
+ }
+
+ return 0;
+}
+
+int mlx5_hv_read_config(struct mlx5_core_dev *dev, void *buf, int len,
+ int offset)
+{
+ return mlx5_hv_config_common(dev, buf, len, offset, true);
+}
+
+int mlx5_hv_write_config(struct mlx5_core_dev *dev, void *buf, int len,
+ int offset)
+{
+ return mlx5_hv_config_common(dev, buf, len, offset, false);
+}
+
+int mlx5_hv_register_invalidate(struct mlx5_core_dev *dev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask))
+{
+ return hyperv_reg_block_invalidate(dev->pdev, context,
+ block_invalidate);
+}
+
+void mlx5_hv_unregister_invalidate(struct mlx5_core_dev *dev)
+{
+ hyperv_reg_block_invalidate(dev->pdev, NULL, NULL);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h
new file mode 100644
index 0000000..f9a4557
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __LIB_HV_H__
+#define __LIB_HV_H__
+
+#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
+
+#include <linux/hyperv.h>
+#include <linux/mlx5/driver.h>
+
+int mlx5_hv_read_config(struct mlx5_core_dev *dev, void *buf, int len,
+ int offset);
+int mlx5_hv_write_config(struct mlx5_core_dev *dev, void *buf, int len,
+ int offset);
+int mlx5_hv_register_invalidate(struct mlx5_core_dev *dev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask));
+void mlx5_hv_unregister_invalidate(struct mlx5_core_dev *dev);
+#endif
+
+#endif /* __LIB_HV_H__ */
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next,v3, 2/6] PCI: hv: Add a Hyper-V PCI interface driver for software backchannel interface
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org
In-Reply-To: <1566346948-69497-1-git-send-email-haiyangz@microsoft.com>
This interface driver is a helper driver allows other drivers to
have a common interface with the Hyper-V PCI frontend driver.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
MAINTAINERS | 1 +
drivers/pci/Kconfig | 1 +
drivers/pci/controller/Kconfig | 7 ++++
drivers/pci/controller/Makefile | 1 +
drivers/pci/controller/pci-hyperv-intf.c | 67 ++++++++++++++++++++++++++++++++
drivers/pci/controller/pci-hyperv.c | 12 ++++--
include/linux/hyperv.h | 30 ++++++++++----
7 files changed, 108 insertions(+), 11 deletions(-)
create mode 100644 drivers/pci/controller/pci-hyperv-intf.c
diff --git a/MAINTAINERS b/MAINTAINERS
index e352550..866ae88 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7453,6 +7453,7 @@ F: drivers/hid/hid-hyperv.c
F: drivers/hv/
F: drivers/input/serio/hyperv-keyboard.c
F: drivers/pci/controller/pci-hyperv.c
+F: drivers/pci/controller/pci-hyperv-intf.c
F: drivers/net/hyperv/
F: drivers/scsi/storvsc_drv.c
F: drivers/uio/uio_hv_generic.c
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 2ab9240..c313de9 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -182,6 +182,7 @@ config PCI_LABEL
config PCI_HYPERV
tristate "Hyper-V PCI Frontend"
depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+ select PCI_HYPERV_INTERFACE
help
The PCI device frontend driver allows the kernel to import arbitrary
PCI devices from a PCI backend to support PCI driver domains.
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index fe9f9f1..70e0782 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -281,5 +281,12 @@ config VMD
To compile this driver as a module, choose M here: the
module will be called vmd.
+config PCI_HYPERV_INTERFACE
+ tristate "Hyper-V PCI Interface"
+ depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+ help
+ The Hyper-V PCI Interface is a helper driver allows other drivers to
+ have a common interface with the Hyper-V PCI frontend driver.
+
source "drivers/pci/controller/dwc/Kconfig"
endmenu
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index d56a507..a2a22c9 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host.o
obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o
obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o
obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
+obj-$(CONFIG_PCI_HYPERV_INTERFACE) += pci-hyperv-intf.o
obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o
obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o
diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c
new file mode 100644
index 0000000..cc96be4
--- /dev/null
+++ b/drivers/pci/controller/pci-hyperv-intf.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) Microsoft Corporation.
+ *
+ * Author:
+ * Haiyang Zhang <haiyangz@microsoft.com>
+ *
+ * This small module is a helper driver allows other drivers to
+ * have a common interface with the Hyper-V PCI frontend driver.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/hyperv.h>
+
+struct hyperv_pci_block_ops hvpci_block_ops;
+EXPORT_SYMBOL_GPL(hvpci_block_ops);
+
+int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len,
+ unsigned int block_id, unsigned int *bytes_returned)
+{
+ if (!hvpci_block_ops.read_block)
+ return -EOPNOTSUPP;
+
+ return hvpci_block_ops.read_block(dev, buf, buf_len, block_id,
+ bytes_returned);
+}
+EXPORT_SYMBOL_GPL(hyperv_read_cfg_blk);
+
+int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len,
+ unsigned int block_id)
+{
+ if (!hvpci_block_ops.write_block)
+ return -EOPNOTSUPP;
+
+ return hvpci_block_ops.write_block(dev, buf, len, block_id);
+}
+EXPORT_SYMBOL_GPL(hyperv_write_cfg_blk);
+
+int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask))
+{
+ if (!hvpci_block_ops.reg_blk_invalidate)
+ return -EOPNOTSUPP;
+
+ return hvpci_block_ops.reg_blk_invalidate(dev, context,
+ block_invalidate);
+}
+EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate);
+
+static void __exit exit_hv_pci_intf(void)
+{
+}
+
+static int __init init_hv_pci_intf(void)
+{
+ return 0;
+}
+
+module_init(init_hv_pci_intf);
+module_exit(exit_hv_pci_intf);
+
+MODULE_DESCRIPTION("Hyper-V PCI Interface");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 57adeca..9c93ac2 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -983,7 +983,6 @@ int hv_read_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
*bytes_returned = comp_pkt.bytes_returned;
return 0;
}
-EXPORT_SYMBOL(hv_read_config_block);
/**
* hv_pci_write_config_compl() - Invoked when a response packet for a write
@@ -1070,7 +1069,6 @@ int hv_write_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
return 0;
}
-EXPORT_SYMBOL(hv_write_config_block);
/**
* hv_register_block_invalidate() - Invoked when a config block invalidation
@@ -1101,7 +1099,6 @@ int hv_register_block_invalidate(struct pci_dev *pdev, void *context,
return 0;
}
-EXPORT_SYMBOL(hv_register_block_invalidate);
/* Interrupt management hooks */
static void hv_int_desc_free(struct hv_pci_dev *hpdev,
@@ -3045,10 +3042,19 @@ static int hv_pci_remove(struct hv_device *hdev)
static void __exit exit_hv_pci_drv(void)
{
vmbus_driver_unregister(&hv_pci_drv);
+
+ hvpci_block_ops.read_block = NULL;
+ hvpci_block_ops.write_block = NULL;
+ hvpci_block_ops.reg_blk_invalidate = NULL;
}
static int __init init_hv_pci_drv(void)
{
+ /* Initialize PCI block r/w interface */
+ hvpci_block_ops.read_block = hv_read_config_block;
+ hvpci_block_ops.write_block = hv_write_config_block;
+ hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate;
+
return vmbus_driver_register(&hv_pci_drv);
}
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 9d37f8c..2afe6fd 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1579,18 +1579,32 @@ struct vmpacket_descriptor *
pkt = hv_pkt_iter_next(channel, pkt))
/*
- * Functions for passing data between SR-IOV PF and VF drivers. The VF driver
+ * Interface for passing data between SR-IOV PF and VF drivers. The VF driver
* sends requests to read and write blocks. Each block must be 128 bytes or
* smaller. Optionally, the VF driver can register a callback function which
* will be invoked when the host says that one or more of the first 64 block
* IDs is "invalid" which means that the VF driver should reread them.
*/
#define HV_CONFIG_BLOCK_SIZE_MAX 128
-int hv_read_config_block(struct pci_dev *dev, void *buf, unsigned int buf_len,
- unsigned int block_id, unsigned int *bytes_returned);
-int hv_write_config_block(struct pci_dev *dev, void *buf, unsigned int len,
- unsigned int block_id);
-int hv_register_block_invalidate(struct pci_dev *dev, void *context,
- void (*block_invalidate)(void *context,
- u64 block_mask));
+
+int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len,
+ unsigned int block_id, unsigned int *bytes_returned);
+int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len,
+ unsigned int block_id);
+int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask));
+
+struct hyperv_pci_block_ops {
+ int (*read_block)(struct pci_dev *dev, void *buf, unsigned int buf_len,
+ unsigned int block_id, unsigned int *bytes_returned);
+ int (*write_block)(struct pci_dev *dev, void *buf, unsigned int len,
+ unsigned int block_id);
+ int (*reg_blk_invalidate)(struct pci_dev *dev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask));
+};
+
+extern struct hyperv_pci_block_ops hvpci_block_ops;
+
#endif /* _HYPERV_H */
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next,v3, 1/6] PCI: hv: Add a paravirtual backchannel in software
From: Haiyang Zhang @ 2019-08-21 0:23 UTC (permalink / raw)
To: sashal@kernel.org, davem@davemloft.net, saeedm@mellanox.com,
leon@kernel.org, eranbe@mellanox.com, lorenzo.pieralisi@arm.com,
bhelgaas@google.com, linux-pci@vger.kernel.org,
linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, KY Srinivasan, Stephen Hemminger,
linux-kernel@vger.kernel.org, Dexuan Cui, Jake Oshins
In-Reply-To: <1566346948-69497-1-git-send-email-haiyangz@microsoft.com>
From: Dexuan Cui <decui@microsoft.com>
Windows SR-IOV provides a backchannel mechanism in software for communication
between a VF driver and a PF driver. These "configuration blocks" are
similar in concept to PCI configuration space, but instead of doing reads and
writes in 32-bit chunks through a very slow path, packets of up to 128 bytes
can be sent or received asynchronously.
Nearly every SR-IOV device contains just such a communications channel in
hardware, so using this one in software is usually optional. Using the
software channel, however, allows driver implementers to leverage software
tools that fuzz the communications channel looking for vulnerabilities.
The usage model for these packets puts the responsibility for reading or
writing on the VF driver. The VF driver sends a read or a write packet,
indicating which "block" is being referred to by number.
If the PF driver wishes to initiate communication, it can "invalidate" one or
more of the first 64 blocks. This invalidation is delivered via a callback
supplied by the VF driver by this driver.
No protocol is implied, except that supplied by the PF and VF drivers.
Signed-off-by: Jake Oshins <jakeo@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/pci/controller/pci-hyperv.c | 302 ++++++++++++++++++++++++++++++++++++
include/linux/hyperv.h | 15 ++
2 files changed, 317 insertions(+)
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 40b6254..57adeca 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -365,6 +365,39 @@ struct pci_delete_interrupt {
struct tran_int_desc int_desc;
} __packed;
+/*
+ * Note: the VM must pass a valid block id, wslot and bytes_requested.
+ */
+struct pci_read_block {
+ struct pci_message message_type;
+ u32 block_id;
+ union win_slot_encoding wslot;
+ u32 bytes_requested;
+} __packed;
+
+struct pci_read_block_response {
+ struct vmpacket_descriptor hdr;
+ u32 status;
+ u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
+} __packed;
+
+/*
+ * Note: the VM must pass a valid block id, wslot and byte_count.
+ */
+struct pci_write_block {
+ struct pci_message message_type;
+ u32 block_id;
+ union win_slot_encoding wslot;
+ u32 byte_count;
+ u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
+} __packed;
+
+struct pci_dev_inval_block {
+ struct pci_incoming_message incoming;
+ union win_slot_encoding wslot;
+ u64 block_mask;
+} __packed;
+
struct pci_dev_incoming {
struct pci_incoming_message incoming;
union win_slot_encoding wslot;
@@ -499,6 +532,9 @@ struct hv_pci_dev {
struct hv_pcibus_device *hbus;
struct work_struct wrk;
+ void (*block_invalidate)(void *context, u64 block_mask);
+ void *invalidate_context;
+
/*
* What would be observed if one wrote 0xFFFFFFFF to a BAR and then
* read it back, for each of the BAR offsets within config space.
@@ -817,6 +853,256 @@ static int hv_pcifront_write_config(struct pci_bus *bus, unsigned int devfn,
.write = hv_pcifront_write_config,
};
+/*
+ * Paravirtual backchannel
+ *
+ * Hyper-V SR-IOV provides a backchannel mechanism in software for
+ * communication between a VF driver and a PF driver. These
+ * "configuration blocks" are similar in concept to PCI configuration space,
+ * but instead of doing reads and writes in 32-bit chunks through a very slow
+ * path, packets of up to 128 bytes can be sent or received asynchronously.
+ *
+ * Nearly every SR-IOV device contains just such a communications channel in
+ * hardware, so using this one in software is usually optional. Using the
+ * software channel, however, allows driver implementers to leverage software
+ * tools that fuzz the communications channel looking for vulnerabilities.
+ *
+ * The usage model for these packets puts the responsibility for reading or
+ * writing on the VF driver. The VF driver sends a read or a write packet,
+ * indicating which "block" is being referred to by number.
+ *
+ * If the PF driver wishes to initiate communication, it can "invalidate" one or
+ * more of the first 64 blocks. This invalidation is delivered via a callback
+ * supplied by the VF driver by this driver.
+ *
+ * No protocol is implied, except that supplied by the PF and VF drivers.
+ */
+
+struct hv_read_config_compl {
+ struct hv_pci_compl comp_pkt;
+ void *buf;
+ unsigned int len;
+ unsigned int bytes_returned;
+};
+
+/**
+ * hv_pci_read_config_compl() - Invoked when a response packet
+ * for a read config block operation arrives.
+ * @context: Identifies the read config operation
+ * @resp: The response packet itself
+ * @resp_packet_size: Size in bytes of the response packet
+ */
+static void hv_pci_read_config_compl(void *context, struct pci_response *resp,
+ int resp_packet_size)
+{
+ struct hv_read_config_compl *comp = context;
+ struct pci_read_block_response *read_resp =
+ (struct pci_read_block_response *)resp;
+ unsigned int data_len, hdr_len;
+
+ hdr_len = offsetof(struct pci_read_block_response, bytes);
+ if (resp_packet_size < hdr_len) {
+ comp->comp_pkt.completion_status = -1;
+ goto out;
+ }
+
+ data_len = resp_packet_size - hdr_len;
+ if (data_len > 0 && read_resp->status == 0) {
+ comp->bytes_returned = min(comp->len, data_len);
+ memcpy(comp->buf, read_resp->bytes, comp->bytes_returned);
+ } else {
+ comp->bytes_returned = 0;
+ }
+
+ comp->comp_pkt.completion_status = read_resp->status;
+out:
+ complete(&comp->comp_pkt.host_event);
+}
+
+/**
+ * hv_read_config_block() - Sends a read config block request to
+ * the back-end driver running in the Hyper-V parent partition.
+ * @pdev: The PCI driver's representation for this device.
+ * @buf: Buffer into which the config block will be copied.
+ * @len: Size in bytes of buf.
+ * @block_id: Identifies the config block which has been requested.
+ * @bytes_returned: Size which came back from the back-end driver.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_read_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
+ unsigned int block_id, unsigned int *bytes_returned)
+{
+ struct hv_pcibus_device *hbus =
+ container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+ sysdata);
+ struct {
+ struct pci_packet pkt;
+ char buf[sizeof(struct pci_read_block)];
+ } pkt;
+ struct hv_read_config_compl comp_pkt;
+ struct pci_read_block *read_blk;
+ int ret;
+
+ if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
+ return -EINVAL;
+
+ init_completion(&comp_pkt.comp_pkt.host_event);
+ comp_pkt.buf = buf;
+ comp_pkt.len = len;
+
+ memset(&pkt, 0, sizeof(pkt));
+ pkt.pkt.completion_func = hv_pci_read_config_compl;
+ pkt.pkt.compl_ctxt = &comp_pkt;
+ read_blk = (struct pci_read_block *)&pkt.pkt.message;
+ read_blk->message_type.type = PCI_READ_BLOCK;
+ read_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
+ read_blk->block_id = block_id;
+ read_blk->bytes_requested = len;
+
+ ret = vmbus_sendpacket(hbus->hdev->channel, read_blk,
+ sizeof(*read_blk), (unsigned long)&pkt.pkt,
+ VM_PKT_DATA_INBAND,
+ VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+ if (ret)
+ return ret;
+
+ ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event);
+ if (ret)
+ return ret;
+
+ if (comp_pkt.comp_pkt.completion_status != 0 ||
+ comp_pkt.bytes_returned == 0) {
+ dev_err(&hbus->hdev->device,
+ "Read Config Block failed: 0x%x, bytes_returned=%d\n",
+ comp_pkt.comp_pkt.completion_status,
+ comp_pkt.bytes_returned);
+ return -EIO;
+ }
+
+ *bytes_returned = comp_pkt.bytes_returned;
+ return 0;
+}
+EXPORT_SYMBOL(hv_read_config_block);
+
+/**
+ * hv_pci_write_config_compl() - Invoked when a response packet for a write
+ * config block operation arrives.
+ * @context: Identifies the write config operation
+ * @resp: The response packet itself
+ * @resp_packet_size: Size in bytes of the response packet
+ */
+static void hv_pci_write_config_compl(void *context, struct pci_response *resp,
+ int resp_packet_size)
+{
+ struct hv_pci_compl *comp_pkt = context;
+
+ comp_pkt->completion_status = resp->status;
+ complete(&comp_pkt->host_event);
+}
+
+/**
+ * hv_write_config_block() - Sends a write config block request to the
+ * back-end driver running in the Hyper-V parent partition.
+ * @pdev: The PCI driver's representation for this device.
+ * @buf: Buffer from which the config block will be copied.
+ * @len: Size in bytes of buf.
+ * @block_id: Identifies the config block which is being written.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_write_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
+ unsigned int block_id)
+{
+ struct hv_pcibus_device *hbus =
+ container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+ sysdata);
+ struct {
+ struct pci_packet pkt;
+ char buf[sizeof(struct pci_write_block)];
+ u32 reserved;
+ } pkt;
+ struct hv_pci_compl comp_pkt;
+ struct pci_write_block *write_blk;
+ u32 pkt_size;
+ int ret;
+
+ if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
+ return -EINVAL;
+
+ init_completion(&comp_pkt.host_event);
+
+ memset(&pkt, 0, sizeof(pkt));
+ pkt.pkt.completion_func = hv_pci_write_config_compl;
+ pkt.pkt.compl_ctxt = &comp_pkt;
+ write_blk = (struct pci_write_block *)&pkt.pkt.message;
+ write_blk->message_type.type = PCI_WRITE_BLOCK;
+ write_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
+ write_blk->block_id = block_id;
+ write_blk->byte_count = len;
+ memcpy(write_blk->bytes, buf, len);
+ pkt_size = offsetof(struct pci_write_block, bytes) + len;
+ /*
+ * This quirk is required on some hosts shipped around 2018, because
+ * these hosts don't check the pkt_size correctly (new hosts have been
+ * fixed since early 2019). The quirk is also safe on very old hosts
+ * and new hosts, because, on them, what really matters is the length
+ * specified in write_blk->byte_count.
+ */
+ pkt_size += sizeof(pkt.reserved);
+
+ ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size,
+ (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND,
+ VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+ if (ret)
+ return ret;
+
+ ret = wait_for_response(hbus->hdev, &comp_pkt.host_event);
+ if (ret)
+ return ret;
+
+ if (comp_pkt.completion_status != 0) {
+ dev_err(&hbus->hdev->device,
+ "Write Config Block failed: 0x%x\n",
+ comp_pkt.completion_status);
+ return -EIO;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(hv_write_config_block);
+
+/**
+ * hv_register_block_invalidate() - Invoked when a config block invalidation
+ * arrives from the back-end driver.
+ * @pdev: The PCI driver's representation for this device.
+ * @context: Identifies the device.
+ * @block_invalidate: Identifies all of the blocks being invalidated.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_register_block_invalidate(struct pci_dev *pdev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask))
+{
+ struct hv_pcibus_device *hbus =
+ container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+ sysdata);
+ struct hv_pci_dev *hpdev;
+
+ hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+ if (!hpdev)
+ return -ENODEV;
+
+ hpdev->block_invalidate = block_invalidate;
+ hpdev->invalidate_context = context;
+
+ put_pcichild(hpdev);
+ return 0;
+
+}
+EXPORT_SYMBOL(hv_register_block_invalidate);
+
/* Interrupt management hooks */
static void hv_int_desc_free(struct hv_pci_dev *hpdev,
struct tran_int_desc *int_desc)
@@ -1968,6 +2254,7 @@ 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_dev_inval_block *inval;
struct pci_dev_incoming *dev_message;
struct hv_pci_dev *hpdev;
@@ -2045,6 +2332,21 @@ static void hv_pci_onchannelcallback(void *context)
}
break;
+ case PCI_INVALIDATE_BLOCK:
+
+ inval = (struct pci_dev_inval_block *)buffer;
+ hpdev = get_pcichild_wslot(hbus,
+ inval->wslot.slot);
+ if (hpdev) {
+ if (hpdev->block_invalidate) {
+ hpdev->block_invalidate(
+ hpdev->invalidate_context,
+ inval->block_mask);
+ }
+ put_pcichild(hpdev);
+ }
+ break;
+
default:
dev_warn(&hbus->hdev->device,
"Unimplemented protocol message %x\n",
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6256cc3..9d37f8c 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1578,4 +1578,19 @@ struct vmpacket_descriptor *
for (pkt = hv_pkt_iter_first(channel); pkt; \
pkt = hv_pkt_iter_next(channel, pkt))
+/*
+ * Functions for passing data between SR-IOV PF and VF drivers. The VF driver
+ * sends requests to read and write blocks. Each block must be 128 bytes or
+ * smaller. Optionally, the VF driver can register a callback function which
+ * will be invoked when the host says that one or more of the first 64 block
+ * IDs is "invalid" which means that the VF driver should reread them.
+ */
+#define HV_CONFIG_BLOCK_SIZE_MAX 128
+int hv_read_config_block(struct pci_dev *dev, void *buf, unsigned int buf_len,
+ unsigned int block_id, unsigned int *bytes_returned);
+int hv_write_config_block(struct pci_dev *dev, void *buf, unsigned int len,
+ unsigned int block_id);
+int hv_register_block_invalidate(struct pci_dev *dev, void *context,
+ void (*block_invalidate)(void *context,
+ u64 block_mask));
#endif /* _HYPERV_H */
--
1.8.3.1
^ permalink raw reply related
* RE: [PATCH 0/2] clocksource/Hyper-V: Add Hyper-V specific sched clock function
From: Vitaly Kuznetsov @ 2019-08-21 7:15 UTC (permalink / raw)
To: Michael Kelley, Tianyu Lan
Cc: Peter Zijlstra, Tianyu Lan, linux-arch@vger.kernel.org,
linux-hyperv@vger.kernel.org, linux-kernel@vger kernel org,
Andy Lutomirski, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
H. Peter Anvin, the arch/x86 maintainers, KY Srinivasan,
Haiyang Zhang, Stephen Hemminger, Sasha Levin, Daniel Lezcano,
Arnd Bergmann, ashal@kernel.org
In-Reply-To: <DM5PR21MB013730EB79A17AF02C170BD7D7AB0@DM5PR21MB0137.namprd21.prod.outlook.com>
Michael Kelley <mikelley@microsoft.com> writes:
> From: Vitaly Kuznetsov <vkuznets@redhat.com> Sent: Tuesday, August 13, 2019 1:34 AM
>>
>> Michael Kelley <mikelley@microsoft.com> writes:
>>
>> > From: Tianyu Lan <lantianyu1986@gmail.com> Sent: Tuesday, July 30, 2019 6:41 AM
>> >>
>> >> On Mon, Jul 29, 2019 at 8:13 PM Vitaly Kuznetsov <vkuznets@redhat.com> wrote:
>> >> >
>> >> > Peter Zijlstra <peterz@infradead.org> writes:
>> >> >
>> >> > > On Mon, Jul 29, 2019 at 12:59:26PM +0200, Vitaly Kuznetsov wrote:
>> >> > >> lantianyu1986@gmail.com writes:
>> >> > >>
>> >> > >> > From: Tianyu Lan <Tianyu.Lan@microsoft.com>
>> >> > >> >
>> >> > >> > Hyper-V guests use the default native_sched_clock() in pv_ops.time.sched_clock
>> >> > >> > on x86. But native_sched_clock() directly uses the raw TSC value, which
>> >> > >> > can be discontinuous in a Hyper-V VM. Add the generic hv_setup_sched_clock()
>> >> > >> > to set the sched clock function appropriately. On x86, this sets
>> >> > >> > pv_ops.time.sched_clock to read the Hyper-V reference TSC value that is
>> >> > >> > scaled and adjusted to be continuous.
>> >> > >>
>> >> > >> Hypervisor can, in theory, disable TSC page and then we're forced to use
>> >> > >> MSR-based clocksource but using it as sched_clock() can be very slow,
>> >> > >> I'm afraid.
>> >> > >>
>> >> > >> On the other hand, what we have now is probably worse: TSC can,
>> >> > >> actually, jump backwards (e.g. on migration) and we're breaking the
>> >> > >> requirements for sched_clock().
>> >> > >
>> >> > > That (obviously) also breaks the requirements for using TSC as
>> >> > > clocksource.
>> >> > >
>> >> > > IOW, it breaks the entire purpose of having TSC in the first place.
>> >> >
>> >> > Currently, we mark raw TSC as unstable when running on Hyper-V (see
>> >> > 88c9281a9fba6), 'TSC page' (which is TSC * scale + offset) is being used
>> >> > instead. The problem is that 'TSC page' can be disabled by the
>> >> > hypervisor and in that case the only remaining clocksource is MSR-based
>> >> > (slow).
>> >> >
>> >>
>> >> Yes, that will be slow if Hyper-V doesn't expose hv tsc page and
>> >> kernel uses MSR based
>> >> clocksource. Each MSR read will trigger one VM-EXIT. This also happens on other
>> >> hypervisors (e,g, KVM doesn't expose KVM clock). Hypervisor should
>> >> take this into
>> >> account and determine which clocksource should be exposed or not.
>> >>
>> >
>> > We've confirmed with the Hyper-V team that the TSC page is always available
>> > on Hyper-V 2016 and later, and on Hyper-V 2012 R2 when the physical
>> > hardware presents an InvariantTSC.
>>
>> Currently we check that TSC page is valid on every read and it seems
>> this is redundant, right? It is either available on boot or not. I can
>> only imagine migrating a VM to a non-InvariantTSC host when Hyper-V will
>> likely disable the page (and we can get reenlightenment notification
>> then).
>
> I think Hyper-V can have brief intervals when the TSC page is not valid, so
> the code checks for the "sequence" value being zero. Otherwise, yes, it
> should always be there or not be there. Is there some other validity
> check on every read that you are thinking of?
>
No, it's this one. In case these 'invalidity periods' are real there's
nothing to improve in the current code.
>>
>> > But the Linux Kconfig's are set up so
>> > the TSC page is not used for 32-bit guests -- all clock reads are synthetic MSR
>> > reads. For 32-bit, this set of changes will add more overhead because the
>> > sched clock reads will now be MSR reads.
>> >
>> > I would be inclined to fix the problem, even with the perf hit on 32-bit Linux.
>> > I don’t have any data on 32-bit Linux being used in a Hyper-V guest, but it's not
>> > supported in Azure so usage is pretty small. The alternative would be to continue
>> > to use the raw TSC value on 32-bit, even with the risk of a discontinuity in case of
>> > live migration or similar scenarios.
>>
>> The issue needs fixing, I agree, however using MSR based clocksource as
>> sched clock may give us too big of a performance hit (not sure who cares
>> about 32 bit guest performance nowadays but still). What stops us from
>> enabling TSC page for 32 bit guests if it is available?
>
> I talked to KY Srinivasan for any history about TSC page on 32-bit. He said
> there was no technical reason not to implement it, but our focus was always
> 64-bit Linux, so the 32-bit was much less important. Also, on 32-bit Linux,
> the required 64x64 multiply and shift is more complex and takes more
> more cycles (compare 32-bit implementation of mul_u64_u64_shr vs.
> the 64-bit implementation), so the win over a MSR read is less. I
> don't know of any actual measurements being made to compare vs.
> MSR read.
VMExit is 1000 CPU cycles or so, I would guess that TSC page
calculations are better. Let me try to build 32bit kernel and do some
quick measurements.
--
Vitaly
^ permalink raw reply
* RE: [PATCH 0/2] clocksource/Hyper-V: Add Hyper-V specific sched clock function
From: Vitaly Kuznetsov @ 2019-08-21 8:54 UTC (permalink / raw)
To: Michael Kelley, Tianyu Lan
Cc: Peter Zijlstra, Tianyu Lan, linux-arch@vger.kernel.org,
linux-hyperv@vger.kernel.org, linux-kernel@vger kernel org,
Andy Lutomirski, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
H. Peter Anvin, the arch/x86 maintainers, KY Srinivasan,
Haiyang Zhang, Stephen Hemminger, Sasha Levin, Daniel Lezcano,
Arnd Bergmann
In-Reply-To: <87o90jq99w.fsf@vitty.brq.redhat.com>
Vitaly Kuznetsov <vkuznets@redhat.com> writes:
> Michael Kelley <mikelley@microsoft.com> writes:
>
>> I talked to KY Srinivasan for any history about TSC page on 32-bit. He said
>> there was no technical reason not to implement it, but our focus was always
>> 64-bit Linux, so the 32-bit was much less important. Also, on 32-bit Linux,
>> the required 64x64 multiply and shift is more complex and takes more
>> more cycles (compare 32-bit implementation of mul_u64_u64_shr vs.
>> the 64-bit implementation), so the win over a MSR read is less. I
>> don't know of any actual measurements being made to compare vs.
>> MSR read.
>
> VMExit is 1000 CPU cycles or so, I would guess that TSC page
> calculations are better. Let me try to build 32bit kernel and do some
> quick measurements.
So I tried and the difference is HUGE.
For in-kernel clocksource reads (like sched_clock()), the testing code
was:
before = rdtsc_ordered();
for (i = 0; i < 1000; i++)
(void)read_hv_sched_clock_msr();
after = rdtsc_ordered();
printk("MSR based clocksource: %d cycles\n", ((u32)(after - before))/1000);
before = rdtsc_ordered();
for (i = 0; i < 1000; i++)
(void)read_hv_sched_clock_tsc();
after = rdtsc_ordered();
printk("TSC page clocksource: %d cycles\n", ((u32)(after - before))/1000);
The result (WS2016) is:
[ 1.101910] MSR based clocksource: 3361 cycles
[ 1.105224] TSC page clocksource: 49 cycles
For userspace reads the absolute difference is even bigger as TSC page
gives us functional vDSO:
Testing code:
before = rdtsc();
for (i = 0; i < COUNT; i++)
clock_gettime(CLOCK_REALTIME, &tp);
after = rdtsc();
printf("%d\n", (after - before)/COUNT);
Result:
TSC page:
# ./gettime_cycles
131
MSR:
# ./gettime_cycles
5664
With all that I see no reason for us to not enable TSC page on 32bit,
even if the number of users is negligible, this will allow us to get rid
of ugly #ifdef CONFIG_HYPERV_TSCPAGE in the code.
I'll send a patch for discussion.
--
Vitaly
^ permalink raw reply
* [PATCH] x86/hyper-v: enable TSC page clocksource on 32bit
From: Vitaly Kuznetsov @ 2019-08-21 9:56 UTC (permalink / raw)
To: linux-hyperv
Cc: linux-kernel, x86, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
H. Peter Anvin, K. Y. Srinivasan, Haiyang Zhang,
Stephen Hemminger, Sasha Levin, Daniel Lezcano, Michael Kelley,
Tianyu Lan, Peter Zijlstra
There is no particular reason to not enable TSC page clocksource
on 32-bit. mul_u64_u64_shr() is available and despite the increased
computational complexity (compared to 64bit) TSC page is still a huge
win compared to MSR-based clocksource.
In-kernel reads:
MSR based clocksource: 3361 cycles
TSC page clocksource: 49 cycles
Reads from userspace (unilizing vDSO in case of TSC page):
MSR based clocksource: 5664 cycles
TSC page clocksource: 131 cycles
Enabling TSC page on 32bits allows us to get rid of CONFIG_HYPERV_TSCPAGE
as it is now not any different from CONFIG_HYPERV_TIMER.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
arch/x86/include/asm/vdso/gettimeofday.h | 6 +++---
drivers/clocksource/hyperv_timer.c | 11 -----------
drivers/hv/Kconfig | 3 ---
include/clocksource/hyperv_timer.h | 6 ++----
4 files changed, 5 insertions(+), 21 deletions(-)
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index ba71a63cdac4..e9ee139cf29e 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -51,7 +51,7 @@ extern struct pvclock_vsyscall_time_info pvclock_page
__attribute__((visibility("hidden")));
#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
+#ifdef CONFIG_HYPERV_TIMER
extern struct ms_hyperv_tsc_page hvclock_page
__attribute__((visibility("hidden")));
#endif
@@ -228,7 +228,7 @@ static u64 vread_pvclock(void)
}
#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
+#ifdef CONFIG_HYPERV_TIMER
static u64 vread_hvclock(void)
{
return hv_read_tsc_page(&hvclock_page);
@@ -251,7 +251,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode)
return vread_pvclock();
}
#endif
-#ifdef CONFIG_HYPERV_TSCPAGE
+#ifdef CONFIG_HYPERV_TIMER
if (clock_mode == VCLOCK_HVCLOCK) {
barrier();
return vread_hvclock();
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index ba2c79e6a0ee..b6083faab540 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -212,8 +212,6 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
struct clocksource *hyperv_cs;
EXPORT_SYMBOL_GPL(hyperv_cs);
-#ifdef CONFIG_HYPERV_TSCPAGE
-
static struct ms_hyperv_tsc_page *tsc_pg;
struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
@@ -244,7 +242,6 @@ static struct clocksource hyperv_cs_tsc = {
.mask = CLOCKSOURCE_MASK(64),
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-#endif
static u64 notrace read_hv_sched_clock_msr(void)
{
@@ -271,7 +268,6 @@ static struct clocksource hyperv_cs_msr = {
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-#ifdef CONFIG_HYPERV_TSCPAGE
static bool __init hv_init_tsc_clocksource(void)
{
u64 tsc_msr;
@@ -306,13 +302,6 @@ static bool __init hv_init_tsc_clocksource(void)
sched_clock_register(read_hv_sched_clock_tsc, 64, HV_CLOCK_HZ);
return true;
}
-#else
-static bool __init hv_init_tsc_clocksource(void)
-{
- return false;
-}
-#endif
-
void __init hv_init_clocksource(void)
{
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 9a59957922d4..79e5356a737a 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -14,9 +14,6 @@ config HYPERV
config HYPERV_TIMER
def_bool HYPERV
-config HYPERV_TSCPAGE
- def_bool HYPERV && X86_64
-
config HYPERV_UTILS
tristate "Microsoft Hyper-V Utilities driver"
depends on HYPERV && CONNECTOR && NLS
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index a821deb8ecb2..f72e4619d0a7 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -28,12 +28,10 @@ extern void hv_stimer_cleanup(unsigned int cpu);
extern void hv_stimer_global_cleanup(void);
extern void hv_stimer0_isr(void);
-#if IS_ENABLED(CONFIG_HYPERV)
+#ifdef CONFIG_HYPERV_TIMER
extern struct clocksource *hyperv_cs;
extern void hv_init_clocksource(void);
-#endif /* CONFIG_HYPERV */
-#ifdef CONFIG_HYPERV_TSCPAGE
extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
static inline notrace u64
@@ -102,6 +100,6 @@ static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
{
return U64_MAX;
}
-#endif /* CONFIG_HYPERV_TSCPAGE */
+#endif /* CONFIG_HYPERV_TIMER */
#endif
--
2.20.1
^ permalink raw reply related
* [PATCH v2] video: hyperv: hyperv_fb: Obtain screen resolution from Hyper-V host
From: Wei Hu @ 2019-08-21 11:10 UTC (permalink / raw)
To: b.zolnierkie@samsung.com, linux-hyperv@vger.kernel.org,
dri-devel@lists.freedesktop.org, linux-fbdev@vger.kernel.org,
linux-kernel@vger.kernel.org, sashal@kernel.org,
Stephen Hemminger, Haiyang Zhang, KY Srinivasan, Dexuan Cui,
Michael Kelley
Cc: Wei Hu, Iouri Tarassov
Beginning from Windows 10 RS5+, VM screen resolution is obtained from host.
The "video=hyperv_fb" boot time option is not needed, but still can be
used to overwrite what the host specifies. The VM resolution on the host
could be set by executing the powershell "set-vmvideo" command.
v2:
- Implemented fallback when version negotiation failed.
- Defined full size for supported_resolution array.
Signed-off-by: Iouri Tarassov <iourit@microsoft.com>
Signed-off-by: Wei Hu <weh@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
drivers/video/fbdev/hyperv_fb.c | 145 +++++++++++++++++++++++++++++---
1 file changed, 133 insertions(+), 12 deletions(-)
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 00f5bdcc6c6f..2ca400c0d621 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -23,6 +23,14 @@
*
* Portrait orientation is also supported:
* For example: video=hyperv_fb:864x1152
+ *
+ * When a Windows 10 RS5+ host is used, the virtual machine screen
+ * resolution is obtained from the host. The "video=hyperv_fb" option is
+ * not needed, but still can be used to overwrite what the host specifies.
+ * The VM resolution on the host could be set by executing the powershell
+ * "set-vmvideo" command. For example
+ * set-vmvideo -vmname name -horizontalresolution:1920 \
+ * -verticalresolution:1200 -resolutiontype single
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -44,6 +52,7 @@
#define SYNTHVID_VERSION(major, minor) ((minor) << 16 | (major))
#define SYNTHVID_VERSION_WIN7 SYNTHVID_VERSION(3, 0)
#define SYNTHVID_VERSION_WIN8 SYNTHVID_VERSION(3, 2)
+#define SYNTHVID_VERSION_WIN10 SYNTHVID_VERSION(3, 5)
#define SYNTHVID_DEPTH_WIN7 16
#define SYNTHVID_DEPTH_WIN8 32
@@ -82,16 +91,25 @@ enum synthvid_msg_type {
SYNTHVID_POINTER_SHAPE = 8,
SYNTHVID_FEATURE_CHANGE = 9,
SYNTHVID_DIRT = 10,
+ SYNTHVID_RESOLUTION_REQUEST = 13,
+ SYNTHVID_RESOLUTION_RESPONSE = 14,
- SYNTHVID_MAX = 11
+ SYNTHVID_MAX = 15
};
+#define SYNTHVID_EDID_BLOCK_SIZE 128
+#define SYNTHVID_MAX_RESOLUTION_COUNT 64
+
+struct hvd_screen_info {
+ u16 width;
+ u16 height;
+} __packed;
+
struct synthvid_msg_hdr {
u32 type;
u32 size; /* size of this header + payload after this field*/
} __packed;
-
struct synthvid_version_req {
u32 version;
} __packed;
@@ -102,6 +120,19 @@ struct synthvid_version_resp {
u8 max_video_outputs;
} __packed;
+struct synthvid_supported_resolution_req {
+ u8 maximum_resolution_count;
+} __packed;
+
+struct synthvid_supported_resolution_resp {
+ u8 edid_block[SYNTHVID_EDID_BLOCK_SIZE];
+ u8 resolution_count;
+ u8 default_resolution_index;
+ u8 is_standard;
+ struct hvd_screen_info
+ supported_resolution[SYNTHVID_MAX_RESOLUTION_COUNT];
+} __packed;
+
struct synthvid_vram_location {
u64 user_ctx;
u8 is_vram_gpa_specified;
@@ -187,6 +218,8 @@ struct synthvid_msg {
struct synthvid_pointer_shape ptr_shape;
struct synthvid_feature_change feature_chg;
struct synthvid_dirt dirt;
+ struct synthvid_supported_resolution_req resolution_req;
+ struct synthvid_supported_resolution_resp resolution_resp;
};
} __packed;
@@ -224,6 +257,8 @@ struct hvfb_par {
static uint screen_width = HVFB_WIDTH;
static uint screen_height = HVFB_HEIGHT;
+static uint screen_width_max = HVFB_WIDTH;
+static uint screen_height_max = HVFB_HEIGHT;
static uint screen_depth;
static uint screen_fb_size;
@@ -354,6 +389,7 @@ static void synthvid_recv_sub(struct hv_device *hdev)
/* Complete the wait event */
if (msg->vid_hdr.type == SYNTHVID_VERSION_RESPONSE ||
+ msg->vid_hdr.type == SYNTHVID_RESOLUTION_RESPONSE ||
msg->vid_hdr.type == SYNTHVID_VRAM_LOCATION_ACK) {
memcpy(par->init_buf, msg, MAX_VMBUS_PKT_SIZE);
complete(&par->wait);
@@ -428,6 +464,64 @@ static int synthvid_negotiate_ver(struct hv_device *hdev, u32 ver)
}
par->synthvid_version = ver;
+ pr_info("Synthvid Version major %d, minor %d\n",
+ ver & 0x0000ffff, (ver & 0xffff0000) >> 16);
+
+out:
+ return ret;
+}
+
+/* Get current resolution from the host */
+static int synthvid_get_supported_resolution(struct hv_device *hdev)
+{
+ struct fb_info *info = hv_get_drvdata(hdev);
+ struct hvfb_par *par = info->par;
+ struct synthvid_msg *msg = (struct synthvid_msg *)par->init_buf;
+ int ret = 0;
+ unsigned long t;
+ u8 index;
+ int i;
+
+ memset(msg, 0, sizeof(struct synthvid_msg));
+ msg->vid_hdr.type = SYNTHVID_RESOLUTION_REQUEST;
+ msg->vid_hdr.size = sizeof(struct synthvid_msg_hdr) +
+ sizeof(struct synthvid_supported_resolution_req);
+
+ msg->resolution_req.maximum_resolution_count =
+ SYNTHVID_MAX_RESOLUTION_COUNT;
+ synthvid_send(hdev, msg);
+
+ t = wait_for_completion_timeout(&par->wait, VSP_TIMEOUT);
+ if (!t) {
+ pr_err("Time out on waiting resolution response\n");
+ ret = -ETIMEDOUT;
+ goto out;
+ }
+
+ if (msg->resolution_resp.resolution_count == 0) {
+ pr_err("No supported resolutions\n");
+ ret = -ENODEV;
+ goto out;
+ }
+
+ index = msg->resolution_resp.default_resolution_index;
+ if (index >= msg->resolution_resp.resolution_count) {
+ pr_err("Invalid resolution index: %d\n", index);
+ ret = -ENODEV;
+ goto out;
+ }
+
+ for (i = 0; i < msg->resolution_resp.resolution_count; i++) {
+ screen_width_max = max_t(unsigned int, screen_width_max,
+ msg->resolution_resp.supported_resolution[i].width);
+ screen_height_max = max_t(unsigned int, screen_height_max,
+ msg->resolution_resp.supported_resolution[i].height);
+ }
+
+ screen_width =
+ msg->resolution_resp.supported_resolution[index].width;
+ screen_height =
+ msg->resolution_resp.supported_resolution[index].height;
out:
return ret;
@@ -448,11 +542,27 @@ static int synthvid_connect_vsp(struct hv_device *hdev)
}
/* Negotiate the protocol version with host */
- if (vmbus_proto_version == VERSION_WS2008 ||
- vmbus_proto_version == VERSION_WIN7)
- ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN7);
- else
+ switch (vmbus_proto_version) {
+ case VERSION_WIN10:
+ case VERSION_WIN10_V5:
+ ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN10);
+ if (!ret)
+ break;
+ /* Fallthrough */
+ case VERSION_WIN8:
+ case VERSION_WIN8_1:
ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN8);
+ if (!ret)
+ break;
+ /* Fallthrough */
+ case VERSION_WS2008:
+ case VERSION_WIN7:
+ ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN7);
+ break;
+ default:
+ ret = synthvid_negotiate_ver(hdev, SYNTHVID_VERSION_WIN10);
+ break;
+ }
if (ret) {
pr_err("Synthetic video device version not accepted\n");
@@ -464,6 +574,12 @@ static int synthvid_connect_vsp(struct hv_device *hdev)
else
screen_depth = SYNTHVID_DEPTH_WIN8;
+ if (par->synthvid_version >= SYNTHVID_VERSION_WIN10) {
+ ret = synthvid_get_supported_resolution(hdev);
+ if (ret)
+ pr_info("Failed to get supported resolution from host, use default\n");
+ }
+
screen_fb_size = hdev->channel->offermsg.offer.
mmio_megabytes * 1024 * 1024;
@@ -653,6 +769,8 @@ static void hvfb_get_option(struct fb_info *info)
}
if (x < HVFB_WIDTH_MIN || y < HVFB_HEIGHT_MIN ||
+ (par->synthvid_version >= SYNTHVID_VERSION_WIN10 &&
+ (x > screen_width_max || y > screen_height_max)) ||
(par->synthvid_version == SYNTHVID_VERSION_WIN8 &&
x * y * screen_depth / 8 > SYNTHVID_FB_SIZE_WIN8) ||
(par->synthvid_version == SYNTHVID_VERSION_WIN7 &&
@@ -689,8 +807,12 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
}
if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM) ||
- pci_resource_len(pdev, 0) < screen_fb_size)
+ pci_resource_len(pdev, 0) < screen_fb_size) {
+ pr_err("Resource not available or (0x%lx < 0x%lx)\n",
+ (unsigned long) pci_resource_len(pdev, 0),
+ (unsigned long) screen_fb_size);
goto err1;
+ }
pot_end = pci_resource_end(pdev, 0);
pot_start = pot_end - screen_fb_size + 1;
@@ -781,17 +903,16 @@ static int hvfb_probe(struct hv_device *hdev,
goto error1;
}
+ hvfb_get_option(info);
+ pr_info("Screen resolution: %dx%d, Color depth: %d\n",
+ screen_width, screen_height, screen_depth);
+
ret = hvfb_getmem(hdev, info);
if (ret) {
pr_err("No memory for framebuffer\n");
goto error2;
}
- hvfb_get_option(info);
- pr_info("Screen resolution: %dx%d, Color depth: %d\n",
- screen_width, screen_height, screen_depth);
-
-
/* Set up fb_info */
info->flags = FBINFO_DEFAULT;
--
2.20.1
^ permalink raw reply related
* RE: [PATCH] video: hyperv: hyperv_fb: Support deferred IO for Hyper-V frame buffer driver
From: Wei Hu @ 2019-08-21 11:59 UTC (permalink / raw)
To: Michael Kelley, rdunlap@infradead.org, shc_work@mail.ru,
gregkh@linuxfoundation.org, lee.jones@linaro.org,
alexandre.belloni@bootlin.com, baijiaju1990@gmail.com,
fthain@telegraphics.com.au, info@metux.net,
linux-hyperv@vger.kernel.org, dri-devel@lists.freedesktop.org,
linux-fbdev@vger.kernel.org, linux-kernel@vger.kernel.org,
sashal@kernel.org, Stephen Hemminger, Haiyang Zhang,
KY Srinivasan, Dexuan Cui, Iouri Tarassov
In-Reply-To: <DM5PR21MB0137E0BB19D8A0E6385BB316D7A90@DM5PR21MB0137.namprd21.prod.outlook.com>
Thanks Michael. See my reply inline to some of your comments.
> -----Original Message-----
> From: Michael Kelley <mikelley@microsoft.com>
> Sent: Monday, August 19, 2019 6:41 AM
> To: Wei Hu <weh@microsoft.com>; rdunlap@infradead.org; shc_work@mail.ru;
> > - msg.dirt.rect[0].x1 = 0;
> > - msg.dirt.rect[0].y1 = 0;
> > - msg.dirt.rect[0].x2 = info->var.xres;
> > - msg.dirt.rect[0].y2 = info->var.yres;
> > + msg.dirt.rect[0].x1 = (x1 < 0 || x1 > x2) ? 0 : x1;
> > + msg.dirt.rect[0].y1 = (y2 < 0 || y1 > y2) ? 0 : y1;
>
> This should be:
>
> msg.dirt.rect[0].y1 = (y1 < 0 || y1 > y2) ? 0 : y1;
>
> Also, throughout the code, I don't think there are any places where
> x or y coordinate values are ever negative. INT_MAX or 0 is used as the
> sentinel value indicating "not set". So can all the tests for less than 0
> now be eliminated, both in this function and in other functions?
>
> > + msg.dirt.rect[0].x2 =
> > + (x2 < x1 || x2 > info->var.xres) ? info->var.xres : x2;
> > + msg.dirt.rect[0].y2 =
> > + (y2 < y1 || y2 > info->var.yres) ? info->var.yres : y2;
>
> How exactly is the dirty rectangle specified to Hyper-V? Suppose the frame
> buffer resolution is 100x200. If you want to specify the entire rectangle, the
> first coordinate is (0, 0). But what is the second coordinate? Should it be
> (99, 199) or (100, 200)? The above code (and original code) implies it
> should specified as (100, 200), which is actually a point outside the
> maximum resolution, which is counter-intuitive and makes me wonder
> if the code is correct.
>
[Wei Hu]
The current code treat the entire framebuffer rectangle as (0,0) -> (var.xres, var.yres).
Every time it sends refresh request, these are two points sent to host and host
seems accept it. See the above (x1, y1) and (x2, y2) in the deleted lines.
So in your example the second coordinate is (100, 200).
> > +/* Deferred IO callback */
> > +static void synthvid_deferred_io(struct fb_info *p,
> > + struct list_head *pagelist)
> > +{
> > + struct hvfb_par *par = p->par;
> > + struct page *page;
> > + unsigned long start, end;
> > + int y1, y2, miny, maxy;
> > + unsigned long flags;
> > +
> > + miny = INT_MAX;
> > + maxy = 0;
> > +
> > + list_for_each_entry(page, pagelist, lru) {
> > + start = page->index << PAGE_SHIFT;
> > + end = start + PAGE_SIZE - 1;
> > + y1 = start / p->fix.line_length;
> > + y2 = end / p->fix.line_length;
>
> The above division rounds down because any remainder is discarded. I
> wondered whether rounding down is correct, which got me to thinking
> about how the dirty rectangle is specified. Is y2 the index of the last
> dirty row? If so, that's not consistent with the code in synthvid_update(),
> which might choose var.yres as y2, and that's the index of a row outside
> of the frame buffer.
>
[Wei Hu]
In this place we try to figure out and merge all the faulted pages into one
big dirty rectangle. A page in memory represents one or multiple lines in
frame buffer. For example, one faulted page could represent all the linear
pixels from (x, y) to (x-1, y+1). In this case we just form the dirty rectangle
as (0, y) -> (var.xres, y+1). Also keep in mind we need to merge multiple
pages. That's why in the end the dirty rectangle is (0, miny) -> (var.xres, maxy).
> > + if (y2 > p->var.yres)
> > + y2 = p->var.yres;
> > + miny = min_t(int, miny, y1);
> > + maxy = max_t(int, maxy, y2);
> > +
> > + /* Copy from dio space to mmio address */
> > + if (par->fb_ready) {
> > + spin_lock_irqsave(&par->docopy_lock, flags);
> > + hvfb_docopy(par, start, PAGE_SIZE);
> > + spin_unlock_irqrestore(&par->docopy_lock, flags);
> > + }
> > + }
> > +
> > + if (par->fb_ready)
> > + synthvid_update(p, 0, miny, p->var.xres, maxy);
> > +}
> > +
> > + if (j == info->var.yres)
> > + break;
> > + hvfb_docopy(par,
> > + j * info->fix.line_length +
> > + (x1 * screen_depth / 8),
> > + (x2 - x1 + 1) * screen_depth / 8);
>
> Whether the +1 is needed above gets back to the question I
> raised earlier about how to interpret the coordinates -- whether
> the (x2, y2) coordinate is just outside the dirty rectangle or
> just inside the dirty rectangle. Most of the code seems to treat
> it as being just outside the dirty rectangle, in which case the +1
> should not be used.
>
[Wei Hu]
This dirty rectangle is not from page fault, but rather from frame buffer
framework when the screen is in text mode. I am not 100% sure if the dirty
rectangle given from kernel includes on extra line outside or not. Here I
just play it safe by copying one extra line in the worst case.
Suppose dirty rectangle only contain one pixel, for example (0,0) is the only
pixel changed in the entire frame buffer. If kernel sends me dirty rectangle as
(0, 0) -> (0, 0), the above function works correctly. If the kernel sends
(0, 0) -> (1, 1), then the above function just copies one extra row and one extra
column, which should also be fine. The hvfb_docopy() takes care of the
edge cases.
Thanks,
Wei
^ permalink raw reply
* RE: [PATCH] x86/hyper-v: enable TSC page clocksource on 32bit
From: Michael Kelley @ 2019-08-21 21:16 UTC (permalink / raw)
To: vkuznets, linux-hyperv@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, x86@kernel.org, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, H. Peter Anvin, KY Srinivasan,
Haiyang Zhang, Stephen Hemminger, Sasha Levin, Daniel Lezcano,
Tianyu Lan, Peter Zijlstra
In-Reply-To: <20190821095650.1841-1-vkuznets@redhat.com>
From: Vitaly Kuznetsov <vkuznets@redhat.com> Sent: Wednesday, August 21, 2019 2:57 AM
>
> There is no particular reason to not enable TSC page clocksource
> on 32-bit. mul_u64_u64_shr() is available and despite the increased
> computational complexity (compared to 64bit) TSC page is still a huge
> win compared to MSR-based clocksource.
>
> In-kernel reads:
> MSR based clocksource: 3361 cycles
> TSC page clocksource: 49 cycles
>
> Reads from userspace (unilizing vDSO in case of TSC page):
s/unilizing/utilizing/
> MSR based clocksource: 5664 cycles
> TSC page clocksource: 131 cycles
>
> Enabling TSC page on 32bits allows us to get rid of CONFIG_HYPERV_TSCPAGE
> as it is now not any different from CONFIG_HYPERV_TIMER.
>
> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
> ---
> arch/x86/include/asm/vdso/gettimeofday.h | 6 +++---
> drivers/clocksource/hyperv_timer.c | 11 -----------
> drivers/hv/Kconfig | 3 ---
> include/clocksource/hyperv_timer.h | 6 ++----
> 4 files changed, 5 insertions(+), 21 deletions(-)
>
> diff --git a/arch/x86/include/asm/vdso/gettimeofday.h
> b/arch/x86/include/asm/vdso/gettimeofday.h
> index ba71a63cdac4..e9ee139cf29e 100644
> --- a/arch/x86/include/asm/vdso/gettimeofday.h
> +++ b/arch/x86/include/asm/vdso/gettimeofday.h
> @@ -51,7 +51,7 @@ extern struct pvclock_vsyscall_time_info pvclock_page
> __attribute__((visibility("hidden")));
> #endif
>
> -#ifdef CONFIG_HYPERV_TSCPAGE
> +#ifdef CONFIG_HYPERV_TIMER
> extern struct ms_hyperv_tsc_page hvclock_page
> __attribute__((visibility("hidden")));
> #endif
> @@ -228,7 +228,7 @@ static u64 vread_pvclock(void)
> }
> #endif
>
> -#ifdef CONFIG_HYPERV_TSCPAGE
> +#ifdef CONFIG_HYPERV_TIMER
> static u64 vread_hvclock(void)
> {
> return hv_read_tsc_page(&hvclock_page);
> @@ -251,7 +251,7 @@ static inline u64 __arch_get_hw_counter(s32 clock_mode)
> return vread_pvclock();
> }
> #endif
> -#ifdef CONFIG_HYPERV_TSCPAGE
> +#ifdef CONFIG_HYPERV_TIMER
> if (clock_mode == VCLOCK_HVCLOCK) {
> barrier();
> return vread_hvclock();
> diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
> index ba2c79e6a0ee..b6083faab540 100644
> --- a/drivers/clocksource/hyperv_timer.c
> +++ b/drivers/clocksource/hyperv_timer.c
> @@ -212,8 +212,6 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
> struct clocksource *hyperv_cs;
> EXPORT_SYMBOL_GPL(hyperv_cs);
>
> -#ifdef CONFIG_HYPERV_TSCPAGE
> -
> static struct ms_hyperv_tsc_page *tsc_pg;
>
> struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
> @@ -244,7 +242,6 @@ static struct clocksource hyperv_cs_tsc = {
> .mask = CLOCKSOURCE_MASK(64),
> .flags = CLOCK_SOURCE_IS_CONTINUOUS,
> };
> -#endif
>
> static u64 notrace read_hv_sched_clock_msr(void)
> {
> @@ -271,7 +268,6 @@ static struct clocksource hyperv_cs_msr = {
> .flags = CLOCK_SOURCE_IS_CONTINUOUS,
> };
>
> -#ifdef CONFIG_HYPERV_TSCPAGE
> static bool __init hv_init_tsc_clocksource(void)
> {
> u64 tsc_msr;
> @@ -306,13 +302,6 @@ static bool __init hv_init_tsc_clocksource(void)
> sched_clock_register(read_hv_sched_clock_tsc, 64, HV_CLOCK_HZ);
> return true;
> }
> -#else
> -static bool __init hv_init_tsc_clocksource(void)
> -{
> - return false;
> -}
> -#endif
> -
>
> void __init hv_init_clocksource(void)
> {
> diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
> index 9a59957922d4..79e5356a737a 100644
> --- a/drivers/hv/Kconfig
> +++ b/drivers/hv/Kconfig
> @@ -14,9 +14,6 @@ config HYPERV
> config HYPERV_TIMER
> def_bool HYPERV
>
> -config HYPERV_TSCPAGE
> - def_bool HYPERV && X86_64
> -
> config HYPERV_UTILS
> tristate "Microsoft Hyper-V Utilities driver"
> depends on HYPERV && CONNECTOR && NLS
> diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
> index a821deb8ecb2..f72e4619d0a7 100644
> --- a/include/clocksource/hyperv_timer.h
> +++ b/include/clocksource/hyperv_timer.h
> @@ -28,12 +28,10 @@ extern void hv_stimer_cleanup(unsigned int cpu);
> extern void hv_stimer_global_cleanup(void);
> extern void hv_stimer0_isr(void);
>
> -#if IS_ENABLED(CONFIG_HYPERV)
> +#ifdef CONFIG_HYPERV_TIMER
> extern struct clocksource *hyperv_cs;
> extern void hv_init_clocksource(void);
> -#endif /* CONFIG_HYPERV */
>
> -#ifdef CONFIG_HYPERV_TSCPAGE
> extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
>
> static inline notrace u64
> @@ -102,6 +100,6 @@ static inline u64 hv_read_tsc_page_tsc(const struct
> ms_hyperv_tsc_page *tsc_pg,
> {
> return U64_MAX;
> }
> -#endif /* CONFIG_HYPERV_TSCPAGE */
> +#endif /* CONFIG_HYPERV_TIMER */
There's a #else prior to the #endif that has TSCPAGE misspelled
as TSC_PAGE in the comment. Should probably fix the comment ...
>
> #endif
> --
> 2.20.1
Overall an excellent removal of unnecessary complexity. Thx.
Two minor nits notwithstanding,
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
^ permalink raw reply
* Re: [PATCH] x86/hyper-v: enable TSC page clocksource on 32bit
From: Thomas Gleixner @ 2019-08-21 21:17 UTC (permalink / raw)
To: Vitaly Kuznetsov
Cc: linux-hyperv, linux-kernel, x86, Ingo Molnar, Borislav Petkov,
H. Peter Anvin, K. Y. Srinivasan, Haiyang Zhang,
Stephen Hemminger, Sasha Levin, Daniel Lezcano, Michael Kelley,
Tianyu Lan, Peter Zijlstra
In-Reply-To: <20190821095650.1841-1-vkuznets@redhat.com>
On Wed, 21 Aug 2019, Vitaly Kuznetsov wrote:
> There is no particular reason to not enable TSC page clocksource
> on 32-bit. mul_u64_u64_shr() is available and despite the increased
> computational complexity (compared to 64bit) TSC page is still a huge
> win compared to MSR-based clocksource.
>
> In-kernel reads:
> MSR based clocksource: 3361 cycles
> TSC page clocksource: 49 cycles
>
> Reads from userspace (unilizing vDSO in case of TSC page):
> MSR based clocksource: 5664 cycles
> TSC page clocksource: 131 cycles
>
> Enabling TSC page on 32bits allows us to get rid of CONFIG_HYPERV_TSCPAGE
s/allows us/allows/
> as it is now not any different from CONFIG_HYPERV_TIMER.
>
> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
> ---
> arch/x86/include/asm/vdso/gettimeofday.h | 6 +++---
> drivers/clocksource/hyperv_timer.c | 11 -----------
> drivers/hv/Kconfig | 3 ---
> include/clocksource/hyperv_timer.h | 6 ++----
> 4 files changed, 5 insertions(+), 21 deletions(-)
Really nice cleanup as a side effect of adding functionality.
Thanks,
tglx
^ permalink raw reply
* Re: [PATCH] x86/hyper-v: enable TSC page clocksource on 32bit
From: Thomas Gleixner @ 2019-08-21 21:23 UTC (permalink / raw)
To: Vitaly Kuznetsov
Cc: linux-hyperv, linux-kernel, x86, Ingo Molnar, Borislav Petkov,
H. Peter Anvin, K. Y. Srinivasan, Haiyang Zhang,
Stephen Hemminger, Sasha Levin, Daniel Lezcano, Michael Kelley,
Tianyu Lan, Peter Zijlstra
In-Reply-To: <alpine.DEB.2.21.1908212316040.1983@nanos.tec.linutronix.de>
On Wed, 21 Aug 2019, Thomas Gleixner wrote:
> On Wed, 21 Aug 2019, Vitaly Kuznetsov wrote:
>
> > There is no particular reason to not enable TSC page clocksource
> > on 32-bit. mul_u64_u64_shr() is available and despite the increased
> > computational complexity (compared to 64bit) TSC page is still a huge
> > win compared to MSR-based clocksource.
> >
> > In-kernel reads:
> > MSR based clocksource: 3361 cycles
> > TSC page clocksource: 49 cycles
> >
> > Reads from userspace (unilizing vDSO in case of TSC page):
> > MSR based clocksource: 5664 cycles
> > TSC page clocksource: 131 cycles
> >
> > Enabling TSC page on 32bits allows us to get rid of CONFIG_HYPERV_TSCPAGE
>
> s/allows us/allows/
>
> > as it is now not any different from CONFIG_HYPERV_TIMER.
> >
> > Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
> > ---
> > arch/x86/include/asm/vdso/gettimeofday.h | 6 +++---
> > drivers/clocksource/hyperv_timer.c | 11 -----------
> > drivers/hv/Kconfig | 3 ---
> > include/clocksource/hyperv_timer.h | 6 ++----
> > 4 files changed, 5 insertions(+), 21 deletions(-)
>
> Really nice cleanup as a side effect of adding functionality.
That said, could you please rebase that on
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core
as I just applied the TSC page patches there and this conflicts left and
right.
Thanks,
tglx
^ permalink raw reply
* RE: [PATCH v2 1/3] drivers: hv: vmbus: Introduce latency testing
From: Michael Kelley @ 2019-08-21 22:52 UTC (permalink / raw)
To: brandonbonaby94, KY Srinivasan, Haiyang Zhang, Stephen Hemminger,
sashal@kernel.org
Cc: brandonbonaby94, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org
In-Reply-To: <ebca54bf70d2af53de419c1b7ac8db5b77b888cb.1566266609.git.brandonbonaby94@gmail.com>
From: Branden Bonaby <brandonbonaby94@gmail.com> Sent: Monday, August 19, 2019 7:45 PM
>
> Introduce user specified latency in the packet reception path.
>
> Signed-off-by: Branden Bonaby <brandonbonaby94@gmail.com>
> ---
> Changes in v2:
> - Add #ifdef in Kconfig file so test code will not interfere
> with non-test code.
> - Move test code functions for delay to hyperv_vmbus header
> file.
> - Wrap test code under #ifdef statement.
>
> drivers/hv/Kconfig | 7 +++++++
> drivers/hv/connection.c | 3 +++
> drivers/hv/hyperv_vmbus.h | 20 ++++++++++++++++++++
> drivers/hv/ring_buffer.c | 7 +++++++
> include/linux/hyperv.h | 21 +++++++++++++++++++++
> 5 files changed, 58 insertions(+)
>
> diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
> index 9a59957922d4..d97437ba0626 100644
> --- a/drivers/hv/Kconfig
> +++ b/drivers/hv/Kconfig
> @@ -29,4 +29,11 @@ config HYPERV_BALLOON
> help
> Select this option to enable Hyper-V Balloon driver.
>
> +config HYPERV_TESTING
> + bool "Hyper-V testing"
> + default n
> + depends on HYPERV && DEBUG_FS
> + help
> + Select this option to enable Hyper-V vmbus testing.
> +
> endmenu
> diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
> index 09829e15d4a0..c9c63a4033cd 100644
> --- a/drivers/hv/connection.c
> +++ b/drivers/hv/connection.c
> @@ -357,6 +357,9 @@ void vmbus_on_event(unsigned long data)
>
> trace_vmbus_on_event(channel);
>
> +#ifdef CONFIG_HYPERV_TESTING
> + hv_debug_delay_test(channel, INTERRUPT_DELAY);
> +#endif /* CONFIG_HYPERV_TESTING */
You are following Vitaly's suggestion to use #ifdef's so no code is
generated when HYPERV_TESTING is not enabled. However, this
direct approach to using #ifdef's really clutters the code and makes
it harder to read and follow. The better approach is to use the
#ifdef in the include file where the functions are defined. If
HYPERV_TESTING is not enabled, provide a #else that defines
the function with an empty implementation for which the compiler
will generate no code. An as example, see the function definition
for hyperv_init() in arch/x86/include/asm/mshyperv.h. There are
several functions treated similarly in that include file.
> do {
> void (*callback_fn)(void *);
>
> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
> index 362e70e9d145..edf14f596d8c 100644
> --- a/drivers/hv/hyperv_vmbus.h
> +++ b/drivers/hv/hyperv_vmbus.h
> @@ -357,4 +357,24 @@ enum hvutil_device_state {
> HVUTIL_DEVICE_DYING, /* driver unload is in progress */
> };
>
> +#ifdef CONFIG_HYPERV_TESTING
> +#include <linux/debugfs.h>
> +#include <linux/delay.h>
> +#include <linux/err.h>
Generally #include files should go at the top of the file, even if they
are only needed conditionally.
> +#define TESTING "hyperv"
I'm not seeing what this line is for, or how it is used.
> +
> +enum delay {
> + INTERRUPT_DELAY = 0,
> + MESSAGE_DELAY = 1,
> +};
> +
> +int hv_debug_delay_files(struct hv_device *dev, struct dentry *root);
> +int hv_debug_add_dev_dir(struct hv_device *dev);
> +void hv_debug_rm_dev_dir(struct hv_device *dev);
> +void hv_debug_rm_all_dir(void);
> +void hv_debug_set_dir_dentry(struct hv_device *dev, struct dentry *root);
> +void hv_debug_delay_test(struct vmbus_channel *channel, enum delay delay_type);
> +
This is where you could put a #else and the null implementation of
the above functions.
> +#endif /* CONFIG_HYPERV_TESTING */
> +
> #endif /* _HYPERV_VMBUS_H */
> diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
> index 9a03b163cbbd..51adda23b398 100644
> --- a/drivers/hv/ring_buffer.c
> +++ b/drivers/hv/ring_buffer.c
> @@ -396,6 +396,10 @@ struct vmpacket_descriptor *hv_pkt_iter_first(struct
> vmbus_channel *channel)
> struct hv_ring_buffer_info *rbi = &channel->inbound;
> struct vmpacket_descriptor *desc;
>
> +#ifdef CONFIG_HYPERV_TESTING
> + hv_debug_delay_test(channel, MESSAGE_DELAY);
> +#endif /* CONFIG_HYPERV_TESTING */
> +
> if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
> return NULL;
>
> @@ -421,6 +425,9 @@ __hv_pkt_iter_next(struct vmbus_channel *channel,
> u32 packetlen = desc->len8 << 3;
> u32 dsize = rbi->ring_datasize;
>
> +#ifdef CONFIG_HYPERV_TESTING
> + hv_debug_delay_test(channel, MESSAGE_DELAY);
> +#endif /* CONFIG_HYPERV_TESTING */
> /* bump offset to next potential packet */
> rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
> if (rbi->priv_read_index >= dsize)
> diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
> index 6256cc34c4a6..6bf8ef5c780c 100644
> --- a/include/linux/hyperv.h
> +++ b/include/linux/hyperv.h
> @@ -926,6 +926,21 @@ struct vmbus_channel {
> * full outbound ring buffer.
> */
> u64 out_full_first;
> +
> +#ifdef CONFIG_HYPERV_TESTING
> + /* enabling/disabling fuzz testing on the channel (default is false)*/
> + bool fuzz_testing_state;
> +
> + /* Interrupt delay will delay the guest from emptying the ring buffer
> + * for a specific amount of time. The delay is in microseconds and will
> + * be between 1 to a maximum of 1000, its default is 0 (no delay).
> + * The Message delay will delay guest reading on a per message basis
> + * in microseconds between 1 to 1000 with the default being 0
> + * (no delay).
> + */
> + u32 fuzz_testing_interrupt_delay;
> + u32 fuzz_testing_message_delay;
> +#endif /* CONFIG_HYPERV_TESTING */
For fields in a data structure like this, you don't have much choice
but to put the #ifdef directly inline. However, for small fields like this
and where the data structure isn't size sensitive, you could consider
omitting the #ifdef and just always including the fields even when
HYPERV_TESTING is not enabled. I don't have a strong preference
either way.
> };
>
> static inline bool is_hvsock_channel(const struct vmbus_channel *c)
> @@ -1166,6 +1181,12 @@ struct hv_device {
>
> struct vmbus_channel *channel;
> struct kset *channels_kset;
> +
> +#ifdef CONFIG_HYPERV_TESTING
> + /* place holder to keep track of the dir for hv device in debugfs */
> + struct dentry *debug_dir;
> +#endif /* CONFIG_HYPERV_TESTING */
Same here.
Michael
> +
> };
>
>
> --
> 2.17.1
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox