Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1320104 > unrolled thread

[PATCH 01/13] tools/hv: Use include/uapi with __EXPORTED_HEADERS__

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  [PATCH 01/13] tools/hv: Use include/uapi with __EXPORTED_HEADERS__ "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 03/13] Drivers: hv: vmbus: avoid scheduling in interrupt context in vmbus_initiate_unload() "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 05/13] Drivers: hv: vmbus: add a helper function to set a channel's pending send size "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 04/13] Drivers: hv: vmbus: don't manipulate with clocksources on crash "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 13/13] Drivers: hv: vmbus: Give control over how the ring access is serialized "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 02/13] Drivers: hv: vmbus: avoid infinite loop in init_vp_index() "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 12/13] Drivers: hv: vmbus: Eliminate the spin lock on the read path "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 07/13] Drivers: hv: vmbus: vmbus_sendpacket_ctl: hvsock: avoid unnecessary signaling "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100
    [PATCH 08/13] Drivers: hv: vmbus: define a new VMBus message type for hvsock "K. Y. Srinivasan" <kys@microsoft.com> - 2016-01-28 00:00 +0100

#1320104 — [PATCH 01/13] tools/hv: Use include/uapi with __EXPORTED_HEADERS__

From: Kamal Mostafa <kamal@canonical.com>

Use the local uapi headers to keep in sync with "recently" added #define's
(e.g. VSS_OP_REGISTER1).

Fixes: 3eb2094c59e8 ("Adding makefile for tools/hv")
Cc: <stable@vger.kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 tools/hv/Makefile |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index a8ab795..a8c4644 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -5,6 +5,8 @@ PTHREAD_LIBS = -lpthread
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS) $(shell getconf LFS_CFLAGS)
 
+CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
+
 all: hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^
-- 
1.7.4.1

[toc] | [next] | [standalone]

#1320105 — [PATCH 03/13] Drivers: hv: vmbus: avoid scheduling in interrupt context in vmbus_initiate_unload()

From: Vitaly Kuznetsov <vkuznets@redhat.com>

We have to call vmbus_initiate_unload() on crash to make kdump work but
the crash can also be happening in interrupt (e.g. Sysrq + c results in
such) where we can't schedule or the following will happen:

[  314.905786] bad: scheduling from the idle thread!

Just skipping the wait (and even adding some random wait here) won't help:
to make host-side magic working we're supposed to receive CHANNELMSG_UNLOAD
(and actually confirm the fact that we received it) but we can't use
interrupt-base path (vmbus_isr()-> vmbus_on_msg_dpc()). Implement a simple
busy wait ignoring all the other messages and use it if we're in an
interrupt context.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |   44 +++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 43 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index af1d82e..d6c6114 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
 #include <linux/hyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -589,6 +590,40 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
 	channel->target_vp = hv_context.vp_index[cur_cpu];
 }
 
+static void vmbus_wait_for_unload(void)
+{
+	int cpu = smp_processor_id();
+	void *page_addr = hv_context.synic_message_page[cpu];
+	struct hv_message *msg = (struct hv_message *)page_addr +
+				  VMBUS_MESSAGE_SINT;
+	struct vmbus_channel_message_header *hdr;
+	bool unloaded = false;
+
+	while (1) {
+		if (msg->header.message_type == HVMSG_NONE) {
+			mdelay(10);
+			continue;
+		}
+
+		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+		if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
+			unloaded = true;
+
+		msg->header.message_type = HVMSG_NONE;
+		/*
+		 * header.message_type needs to be written before we do
+		 * wrmsrl() below.
+		 */
+		mb();
+
+		if (msg->header.message_flags.msg_pending)
+			wrmsrl(HV_X64_MSR_EOM, 0);
+
+		if (unloaded)
+			break;
+	}
+}
+
 /*
  * vmbus_unload_response - Handler for the unload response.
  */
@@ -614,7 +649,14 @@ void vmbus_initiate_unload(void)
 	hdr.msgtype = CHANNELMSG_UNLOAD;
 	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
 
-	wait_for_completion(&vmbus_connection.unload_event);
+	/*
+	 * vmbus_initiate_unload() is also called on crash and the crash can be
+	 * happening in an interrupt context, where scheduling is impossible.
+	 */
+	if (!in_interrupt())
+		wait_for_completion(&vmbus_connection.unload_event);
+	else
+		vmbus_wait_for_unload();
 }
 
 /*
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320110 — [PATCH 05/13] Drivers: hv: vmbus: add a helper function to set a channel's pending send size

From: Dexuan Cui <decui@microsoft.com>

This will be used by the coming net/hvsock driver.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 include/linux/hyperv.h |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 3172521..4af51a3 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -816,6 +816,12 @@ static inline void *get_per_channel_state(struct vmbus_channel *c)
 	return c->per_channel_state;
 }
 
+static inline void set_channel_pending_send_size(struct vmbus_channel *c,
+						 u32 size)
+{
+	c->outbound.ring_buffer->pending_send_sz = size;
+}
+
 void vmbus_onmessage(void *context);
 
 int vmbus_request_offers(void);
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320111 — [PATCH 04/13] Drivers: hv: vmbus: don't manipulate with clocksources on crash

From: Vitaly Kuznetsov <vkuznets@redhat.com>

clocksource_change_rating() involves mutex usage and can't be called
in interrupt context. It also makes sense to avoid doing redundant work
on crash.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/hv.c |   10 ++++++++--
 1 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 11bca51..257de21 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -295,8 +295,14 @@ void hv_cleanup(void)
 	 * Cleanup the TSC page based CS.
 	 */
 	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		clocksource_change_rating(&hyperv_cs_tsc, 10);
-		clocksource_unregister(&hyperv_cs_tsc);
+		/*
+		 * Crash can happen in an interrupt context and unregistering
+		 * a clocksource is impossible and redundant in this case.
+		 */
+		if (!oops_in_progress) {
+			clocksource_change_rating(&hyperv_cs_tsc, 10);
+			clocksource_unregister(&hyperv_cs_tsc);
+		}
 
 		hypercall_msr.as_uint64 = 0;
 		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320112 — [PATCH 13/13] Drivers: hv: vmbus: Give control over how the ring access is serialized

On the channel send side, many of the VMBUS
device drivers explicity serialize access to the
outgoing ring buffer. Give more control to the
VMBUS device drivers in terms how to serialize
accesss to the outgoing ring buffer.
The default behavior will be to aquire the
ring lock to preserve the current behavior.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel.c      |   15 +++++++++++----
 drivers/hv/channel_mgmt.c |    1 +
 drivers/hv/hyperv_vmbus.h |    2 +-
 drivers/hv/ring_buffer.c  |   13 ++++++++-----
 include/linux/hyperv.h    |   16 ++++++++++++++++
 5 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index fcab234..56dd261 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -639,6 +639,7 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	u64 aligned_data = 0;
 	int ret;
 	bool signal = false;
+	bool lock = channel->acquire_ring_lock;
 	int num_vecs = ((bufferlen != 0) ? 3 : 1);
 
 
@@ -658,7 +659,7 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
 	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, num_vecs,
-				  &signal);
+				  &signal, lock);
 
 	/*
 	 * Signalling the host is conditional on many factors:
@@ -738,6 +739,7 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
 	bool signal = false;
+	bool lock = channel->acquire_ring_lock;
 
 	if (pagecount > MAX_PAGE_BUFFER_COUNT)
 		return -EINVAL;
@@ -774,7 +776,8 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
+	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3,
+				  &signal, lock);
 
 	/*
 	 * Signalling the host is conditional on many factors:
@@ -837,6 +840,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
 	bool signal = false;
+	bool lock = channel->acquire_ring_lock;
 
 	packetlen = desc_size + bufferlen;
 	packetlen_aligned = ALIGN(packetlen, sizeof(u64));
@@ -856,7 +860,8 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
+	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3,
+				  &signal, lock);
 
 	if (ret == 0 && signal)
 		vmbus_setevent(channel);
@@ -881,6 +886,7 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
 	bool signal = false;
+	bool lock = channel->acquire_ring_lock;
 	u32 pfncount = NUM_PAGES_SPANNED(multi_pagebuffer->offset,
 					 multi_pagebuffer->len);
 
@@ -919,7 +925,8 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
+	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3,
+				  &signal, lock);
 
 	if (ret == 0 && signal)
 		vmbus_setevent(channel);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 4bcfada..fb1734c 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -259,6 +259,7 @@ static struct vmbus_channel *alloc_channel(void)
 		return NULL;
 
 	channel->id = atomic_inc_return(&chan_num);
+	channel->acquire_ring_lock = true;
 	spin_lock_init(&channel->inbound_lock);
 	spin_lock_init(&channel->lock);
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 4ebc796..822566f 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -531,7 +531,7 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
 
 int hv_ringbuffer_write(struct hv_ring_buffer_info *ring_info,
 		    struct kvec *kv_list,
-		    u32 kv_count, bool *signal);
+		    u32 kv_count, bool *signal, bool lock);
 
 int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 1145f3b..5613e2b 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -314,7 +314,7 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
 
 /* Write to the ring buffer. */
 int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
-		    struct kvec *kv_list, u32 kv_count, bool *signal)
+		    struct kvec *kv_list, u32 kv_count, bool *signal, bool lock)
 {
 	int i = 0;
 	u32 bytes_avail_towrite;
@@ -324,14 +324,15 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
 	u32 next_write_location;
 	u32 old_write;
 	u64 prev_indices = 0;
-	unsigned long flags;
+	unsigned long flags = 0;
 
 	for (i = 0; i < kv_count; i++)
 		totalbytes_towrite += kv_list[i].iov_len;
 
 	totalbytes_towrite += sizeof(u64);
 
-	spin_lock_irqsave(&outring_info->ring_lock, flags);
+	if (lock)
+		spin_lock_irqsave(&outring_info->ring_lock, flags);
 
 	hv_get_ringbuffer_availbytes(outring_info,
 				&bytes_avail_toread,
@@ -343,7 +344,8 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
 	 * is empty since the read index == write index.
 	 */
 	if (bytes_avail_towrite <= totalbytes_towrite) {
-		spin_unlock_irqrestore(&outring_info->ring_lock, flags);
+		if (lock)
+			spin_unlock_irqrestore(&outring_info->ring_lock, flags);
 		return -EAGAIN;
 	}
 
@@ -374,7 +376,8 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
 	hv_set_next_write_location(outring_info, next_write_location);
 
 
-	spin_unlock_irqrestore(&outring_info->ring_lock, flags);
+	if (lock)
+		spin_unlock_irqrestore(&outring_info->ring_lock, flags);
 
 	*signal = hv_need_to_signal(old_write, outring_info);
 	return 0;
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index c056f05..d23dab0 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -811,8 +811,24 @@ struct vmbus_channel {
 	 * signaling control.
 	 */
 	enum hv_signal_policy  signal_policy;
+	/*
+	 * On the channel send side, many of the VMBUS
+	 * device drivers explicity serialize access to the
+	 * outgoing ring buffer. Give more control to the
+	 * VMBUS device drivers in terms how to serialize
+	 * accesss to the outgoing ring buffer.
+	 * The default behavior will be to aquire the
+	 * ring lock to preserve the current behavior.
+	 */
+	bool acquire_ring_lock;
+
 };
 
+static inline void set_channel_lock_state(struct vmbus_channel *c, bool state)
+{
+	c->acquire_ring_lock = state;
+}
+
 static inline bool is_hvsock_channel(const struct vmbus_channel *c)
 {
 	return !!(c->offermsg.offer.chn_flags &
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320114 — [PATCH 02/13] Drivers: hv: vmbus: avoid infinite loop in init_vp_index()

From: Vitaly Kuznetsov <vkuznets@redhat.com>

When we pick a CPU to use for a new subchannel we try find a non-used one
on the appropriate NUMA node, we keep track of them with the
primary->alloced_cpus_in_node mask. Under normal circumstances we don't run
out of available CPUs but it is possible when we we don't initialize some
cpus in Linux, e.g. when we boot with 'nr_cpus=' limitation.

Avoid the infinite loop in init_vp_index() by checking that we still have
non-used CPUs in the alloced_cpus_in_node mask and resetting it in case
we don't.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel_mgmt.c |   11 +++++++++++
 1 files changed, 11 insertions(+), 0 deletions(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 107d72f..af1d82e 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -549,6 +549,17 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
 		    cpumask_of_node(primary->numa_node));
 
 	cur_cpu = -1;
+
+	/*
+	 * Normally Hyper-V host doesn't create more subchannels than there
+	 * are VCPUs on the node but it is possible when not all present VCPUs
+	 * on the node are initialized by guest. Clear the alloced_cpus_in_node
+	 * to start over.
+	 */
+	if (cpumask_equal(&primary->alloced_cpus_in_node,
+			  cpumask_of_node(primary->numa_node)))
+		cpumask_clear(&primary->alloced_cpus_in_node);
+
 	while (true) {
 		cur_cpu = cpumask_next(cur_cpu, &available_mask);
 		if (cur_cpu >= nr_cpu_ids) {
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320116 — [PATCH 12/13] Drivers: hv: vmbus: Eliminate the spin lock on the read path

The function hv_ringbuffer_read() is called always on a pre-assigned
CPU. Each chnnel is bound to a specific CPU and this function is
always called on the CPU the channel is bound. There is no need to
acquire the spin lock; get rid of this overhead.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/ring_buffer.c |   18 +++++-------------
 1 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index b53702c..1145f3b 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -388,7 +388,6 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 	u32 bytes_avail_toread;
 	u32 next_read_location = 0;
 	u64 prev_indices = 0;
-	unsigned long flags;
 	struct vmpacket_descriptor desc;
 	u32 offset;
 	u32 packetlen;
@@ -397,7 +396,6 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 	if (buflen <= 0)
 		return -EINVAL;
 
-	spin_lock_irqsave(&inring_info->ring_lock, flags);
 
 	*buffer_actual_len = 0;
 	*requestid = 0;
@@ -412,7 +410,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 		 * No error is set when there is even no header, drivers are
 		 * supposed to analyze buffer_actual_len.
 		 */
-		goto out_unlock;
+		return ret;
 	}
 
 	next_read_location = hv_get_next_read_location(inring_info);
@@ -425,15 +423,11 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 	*buffer_actual_len = packetlen;
 	*requestid = desc.trans_id;
 
-	if (bytes_avail_toread < packetlen + offset) {
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
+	if (bytes_avail_toread < packetlen + offset)
+		return -EAGAIN;
 
-	if (packetlen > buflen) {
-		ret = -ENOBUFS;
-		goto out_unlock;
-	}
+	if (packetlen > buflen)
+		return -ENOBUFS;
 
 	next_read_location =
 		hv_get_next_readlocation_withoffset(inring_info, offset);
@@ -460,7 +454,5 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
 
 	*signal = hv_need_to_signal_on_read(bytes_avail_towrite, inring_info);
 
-out_unlock:
-	spin_unlock_irqrestore(&inring_info->ring_lock, flags);
 	return ret;
 }
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320119 — [PATCH 07/13] Drivers: hv: vmbus: vmbus_sendpacket_ctl: hvsock: avoid unnecessary signaling

From: Dexuan Cui <decui@microsoft.com>

When the hvsock channel's outbound ringbuffer is full (i.e.,
hv_ringbuffer_write() returns -EAGAIN), we should avoid the unnecessary
signaling the host.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel.c |    6 +++++-
 1 files changed, 5 insertions(+), 1 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 1161d68..3f04533 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -659,6 +659,9 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	 * If we cannot write to the ring-buffer; signal the host
 	 * even if we may not have written anything. This is a rare
 	 * enough condition that it should not matter.
+	 * NOTE: in this case, the hvsock channel is an exception, because
+	 * it looks the host side's hvsock implementation has a throttling
+	 * mechanism which can hurt the performance otherwise.
 	 */
 
 	if (channel->signal_policy)
@@ -666,7 +669,8 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	else
 		kick_q = true;
 
-	if (((ret == 0) && kick_q && signal) || (ret))
+	if (((ret == 0) && kick_q && signal) ||
+	    (ret && !is_hvsock_channel(channel)))
 		vmbus_setevent(channel);
 
 	return ret;
-- 
1.7.4.1

[toc] | [prev] | [next] | [standalone]

#1320120 — [PATCH 08/13] Drivers: hv: vmbus: define a new VMBus message type for hvsock

From: Dexuan Cui <decui@microsoft.com>

A function to send the type of message is also added.

The coming net/hvsock driver will use this function to proactively request
the host to offer a VMBus channel for a new hvsock connection.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
---
 drivers/hv/channel.c      |   15 +++++++++++++++
 drivers/hv/channel_mgmt.c |    4 ++++
 include/linux/hyperv.h    |   13 +++++++++++++
 3 files changed, 32 insertions(+), 0 deletions(-)

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 3f04533..fcab234 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -219,6 +219,21 @@ error0:
 }
 EXPORT_SYMBOL_GPL(vmbus_open);
 
+/* Used for Hyper-V Socket: a guest client's connect() to the host */
+int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id,
+				  const uuid_le *shv_host_servie_id)
+{
+	struct vmbus_channel_tl_connect_request conn_msg;
+
+	memset(&conn_msg, 0, sizeof(conn_msg));
+	conn_msg.header.msgtype = CHANNELMSG_TL_CONNECT_REQUEST;
+	conn_msg.guest_endpoint_id = *shv_guest_servie_id;
+	conn_msg.host_service_id = *shv_host_servie_id;
+
+	return vmbus_post_msg(&conn_msg, sizeof(conn_msg));
+}
+EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
+
 /*
  * create_gpadl_header - Creates a gpadl for the specified buffer
  */
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index d6c6114..60ca25b 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -958,6 +958,10 @@ struct vmbus_channel_message_table_entry
 	{CHANNELMSG_VERSION_RESPONSE,		1, vmbus_onversion_response},
 	{CHANNELMSG_UNLOAD,			0, NULL},
 	{CHANNELMSG_UNLOAD_RESPONSE,		1, vmbus_unload_response},
+	{CHANNELMSG_18,				0, NULL},
+	{CHANNELMSG_19,				0, NULL},
+	{CHANNELMSG_20,				0, NULL},
+	{CHANNELMSG_TL_CONNECT_REQUEST,		0, NULL},
 };
 
 /*
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 79c4aa7..898eac9 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -392,6 +392,10 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_VERSION_RESPONSE		= 15,
 	CHANNELMSG_UNLOAD			= 16,
 	CHANNELMSG_UNLOAD_RESPONSE		= 17,
+	CHANNELMSG_18				= 18,
+	CHANNELMSG_19				= 19,
+	CHANNELMSG_20				= 20,
+	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
 	CHANNELMSG_COUNT
 };
 
@@ -562,6 +566,13 @@ struct vmbus_channel_initiate_contact {
 	u64 monitor_page2;
 } __packed;
 
+/* Hyper-V socket: guest's connect()-ing to host */
+struct vmbus_channel_tl_connect_request {
+	struct vmbus_channel_message_header header;
+	uuid_le guest_endpoint_id;
+	uuid_le host_service_id;
+} __packed;
+
 struct vmbus_channel_version_response {
 	struct vmbus_channel_message_header header;
 	u8 version_supported;
@@ -1283,4 +1294,6 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
 
 extern __u32 vmbus_proto_version;
 
+int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id,
+				  const uuid_le *shv_host_servie_id);
 #endif /* _HYPERV_H */
-- 
1.7.4.1

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web