github/linuxkit
1
0
Fork 0
mirror of https://github.com/linuxkit/linuxkit.git synced 2025-07-20 01:29:07 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #1189 from rneugeba/kern-up

Browse Source 
kernel: Update to 4.9.10
This commit is contained in:
Rolf Neugebauer 2017-02-15 17:50:10 +00:00 committed by GitHub
commit 23306101cb
15 changed files with 24 additions and 741 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/Dockerfile
View File

@ -1,6 +1,6 @@
FROM mobylinux/alpine-build-kernel:0e893fbf6fa7638d2f23354de03ea11017bb8065@sha256:3ef3f9d11f0802b759dbd9c43a7706cf0ec37263c99ae90e2b10c29ea85739fa
ARG KERNEL_VERSION=4.9.9
ARG KERNEL_VERSION=4.9.10
ENV KERNEL_SOURCE=https://www.kernel.org/pub/linux/kernel/v4.x/linux-${KERNEL_VERSION}.tar.xz

2
kernel/Dockerfile.aufs
View File

@ -1,6 +1,6 @@
FROM mobylinux/alpine-build-kernel:0e893fbf6fa7638d2f23354de03ea11017bb8065@sha256:3ef3f9d11f0802b759dbd9c43a7706cf0ec37263c99ae90e2b10c29ea85739fa
ARG KERNEL_VERSION=4.9.9
ARG KERNEL_VERSION=4.9.10
ENV KERNEL_SOURCE=https://www.kernel.org/pub/linux/kernel/v4.x/linux-${KERNEL_VERSION}.tar.xz

2
kernel/kernel_config
View File

@ -1,6 +1,6 @@
#
# Automatically generated file; DO NOT EDIT.
# Linux/x86 4.9.9 Kernel Configuration
# Linux/x86 4.9.10 Kernel Configuration
#
CONFIG_64BIT=y
CONFIG_X86_64=y

5
kernel/patches-4.9/0001-VSOCK-Only-allow-host-network-namespace-to-use-AF_VS.patch
View File

@ -1,8 +1,7 @@
From 0d7f0d07b0161db56894ddd9da3c90074d9d5995 Mon Sep 17 00:00:00 2001
From 3d6fce5663241a06b78e10c2b5ae298abd7a72ba Mon Sep 17 00:00:00 2001
From: Ian Campbell <ian.campbell@docker.com>
Date: Mon, 4 Apr 2016 14:50:10 +0100
Subject: [PATCH 01/12] VSOCK: Only allow host network namespace to use
AF_VSOCK.
Subject: [PATCH 1/8] VSOCK: Only allow host network namespace to use AF_VSOCK.
The VSOCK addressing schema does not really lend itself to simply creating an
alternative end point address within a namespace.

10
kernel/patches-4.9/0002-hv_sock-introduce-Hyper-V-Sockets.patch
View File

@ -1,7 +1,7 @@
From ed8ec8533647a523bd510b41b128888adec2d2a7 Mon Sep 17 00:00:00 2001
From c76fa3c421e8d424cab8a048f186fe61e0415f82 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Sat, 23 Jul 2016 01:35:51 +0000
Subject: [PATCH 02/12] hv_sock: introduce Hyper-V Sockets
Subject: [PATCH 2/8] hv_sock: introduce Hyper-V Sockets
Hyper-V Sockets (hv_sock) supplies a byte-stream based communication
mechanism between the host and the guest. It's somewhat like TCP over
@ -56,11 +56,11 @@ index 63cefa62324c..e64920219d88 100644
F: Documentation/ABI/stable/sysfs-bus-vmbus
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index cd184bdca58f..468e15e29f5f 100644
index c92a083bcf16..e34da6846348 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1593,5 +1593,18 @@ static inline void commit_rd_index(struct vmbus_channel *channel)
vmbus_set_event(channel);
@@ -1622,5 +1622,18 @@ static inline void commit_rd_index(struct vmbus_channel *channel)
hv_signal_on_read(channel);
}
+struct vmpipe_proto_header {

6
kernel/patches-4.9/0003-vmbus-Don-t-spam-the-logs-with-unknown-GUIDs.patch
View File

@ -1,7 +1,7 @@
From 3572be36490b411085bf2c28c2a6f06a698bd80d Mon Sep 17 00:00:00 2001
From 7ffe2cc44e33996ad39c2cdbf37f958691489e81 Mon Sep 17 00:00:00 2001
From: Rolf Neugebauer <rolf.neugebauer@gmail.com>
Date: Mon, 23 May 2016 18:55:45 +0100
Subject: [PATCH 03/12] vmbus: Don't spam the logs with unknown GUIDs
Subject: [PATCH 3/8] vmbus: Don't spam the logs with unknown GUIDs
With Hyper-V sockets device types are introduced on the fly. The pr_info()
then prints a message on every connection, which is way too verbose. Since
@ -14,7 +14,7 @@ Signed-off-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
1 file changed, 1 deletion(-)
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 1bc1d4795243..db5bccf4fa7e 100644
index caf341842464..8f3d9f787288 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -169,7 +169,6 @@ static u16 hv_get_dev_type(const struct vmbus_channel *channel)

6
kernel/patches-4.9/0004-Drivers-hv-utils-Fix-the-mapping-between-host-versio.patch
View File

@ -1,8 +1,8 @@
From 550e05bf72b6be4bc525b0274c02fc00c2d20e52 Mon Sep 17 00:00:00 2001
From 3bc5a0bf749b3d7758c2dec93f5044480b506e5a Mon Sep 17 00:00:00 2001
From: Alex Ng <alexng@messages.microsoft.com>
Date: Sun, 6 Nov 2016 13:14:07 -0800
Subject: [PATCH 04/12] Drivers: hv: utils: Fix the mapping between host
version and protocol to use
Subject: [PATCH 4/8] Drivers: hv: utils: Fix the mapping between host version
and protocol to use
We should intentionally declare the protocols to use for every known host
and default to using the latest protocol if the host is unknown or new.

103
kernel/patches-4.9/0005-Drivers-hv-vmbus-Base-host-signaling-strictly-on-the.patch
View File

@ -1,103 +0,0 @@
From 085b322dfe10994050e8b6c0310d9b89cd6d0437 Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Sun, 6 Nov 2016 13:14:16 -0800
Subject: [PATCH 05/12] Drivers: hv: vmbus: Base host signaling strictly on the
ring state
One of the factors that can result in the host concluding that a given
guest in mounting a DOS attack is if the guest generates interrupts
to the host when the host is not expecting it. If these "spurious"
interrupts reach a certain rate, the host can throttle the guest to
minimize the impact. The host computation of the "expected number
of interrupts" is strictly based on the ring transitions. Until
the host logic is fixed, base the guest logic to interrupt solely
on the ring state.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit 74198eb4a42c4a3c4fbef08fa01a291a282f7c2e)
---
drivers/hv/channel.c | 23 ++++++++++++++++++++---
drivers/hv/channel_mgmt.c | 2 --
drivers/hv/ring_buffer.c | 7 -------
3 files changed, 20 insertions(+), 12 deletions(-)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 16f91c8490fe..5e482d7f60cb 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -676,10 +676,18 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
* 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.
+ *
+ * KYS: Oct. 30, 2016:
+ * It looks like Windows hosts have logic to deal with DOS attacks that
+ * can be triggered if it receives interrupts when it is not expecting
+ * the interrupt. The host expects interrupts only when the ring
+ * transitions from empty to non-empty (or full to non full on the guest
+ * to host ring).
+ * So, base the signaling decision solely on the ring state until the
+ * host logic is fixed.
*/
- if (((ret == 0) && kick_q && signal) ||
- (ret && !is_hvsock_channel(channel)))
+ if (((ret == 0) && signal))
vmbus_setevent(channel);
return ret;
@@ -786,9 +794,18 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
* 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.
+ *
+ * KYS: Oct. 30, 2016:
+ * It looks like Windows hosts have logic to deal with DOS attacks that
+ * can be triggered if it receives interrupts when it is not expecting
+ * the interrupt. The host expects interrupts only when the ring
+ * transitions from empty to non-empty (or full to non full on the guest
+ * to host ring).
+ * So, base the signaling decision solely on the ring state until the
+ * host logic is fixed.
*/
- if (((ret == 0) && kick_q && signal) || (ret))
+ if (((ret == 0) && signal))
vmbus_setevent(channel);
return ret;
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index db5bccf4fa7e..8f3d9f787288 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -448,8 +448,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
}
dev_type = hv_get_dev_type(newchannel);
- if (dev_type == HV_NIC)
- set_channel_signal_state(newchannel, HV_SIGNAL_POLICY_EXPLICIT);
init_vp_index(newchannel, dev_type);
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 08043da1a61c..5d11d93eedf4 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -75,13 +75,6 @@ static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi,
if (READ_ONCE(rbi->ring_buffer->interrupt_mask))
return false;
- /*
- * When the client wants to control signaling,
- * we only honour the host interrupt mask.
- */
- if (policy == HV_SIGNAL_POLICY_EXPLICIT)
- return true;
-
/* check interrupt_mask before read_index */
virt_rmb();
/*
--
2.11.0

4
kernel/patches-4.9/0009-Drivers-hv-vss-Improve-log-messages.patch → kernel/patches-4.9/0005-Drivers-hv-vss-Improve-log-messages.patch
View File

@ -1,7 +1,7 @@
From fcb33d2dd7fa294c410f37f40a3ffb579ca04811 Mon Sep 17 00:00:00 2001
From e351f71f036780c5764b81874b417da5b361473b Mon Sep 17 00:00:00 2001
From: Alex Ng <alexng@messages.microsoft.com>
Date: Sun, 6 Nov 2016 13:14:10 -0800
Subject: [PATCH 09/12] Drivers: hv: vss: Improve log messages.
Subject: [PATCH 5/8] Drivers: hv: vss: Improve log messages.
Adding log messages to help troubleshoot error cases and transaction
handling.

321
kernel/patches-4.9/0006-Drivers-hv-vmbus-On-write-cleanup-the-logic-to-inter.patch
View File

@ -1,321 +0,0 @@
From 78777547745d7f0bf25e55cbf323ce5191e4b89a Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Sun, 6 Nov 2016 13:14:17 -0800
Subject: [PATCH 06/12] Drivers: hv: vmbus: On write cleanup the logic to
interrupt the host
Signal the host when we determine the host is to be signaled.
The currrent code determines the need to signal in the ringbuffer
code and actually issues the signal elsewhere. This can result
in the host viewing this interrupt as spurious since the host may also
poll the channel. Make the necessary adjustments.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit 1f6ee4e7d83586c8b10bd4f2f4346353d04ce884)
---
drivers/hv/channel.c | 99 +++++------------------------------------------
drivers/hv/hyperv_vmbus.h | 6 +--
drivers/hv/ring_buffer.c | 30 +++++++++-----
include/linux/hyperv.h | 1 +
4 files changed, 35 insertions(+), 101 deletions(-)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 5e482d7f60cb..8a8148f7b842 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -39,7 +39,7 @@
* vmbus_setevent- Trigger an event notification on the specified
* channel.
*/
-static void vmbus_setevent(struct vmbus_channel *channel)
+void vmbus_setevent(struct vmbus_channel *channel)
{
struct hv_monitor_page *monitorpage;
@@ -65,6 +65,7 @@ static void vmbus_setevent(struct vmbus_channel *channel)
vmbus_set_event(channel);
}
}
+EXPORT_SYMBOL_GPL(vmbus_setevent);
/*
* vmbus_open - Open the specified channel.
@@ -635,8 +636,6 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64));
struct kvec bufferlist[3];
u64 aligned_data = 0;
- int ret;
- bool signal = false;
bool lock = channel->acquire_ring_lock;
int num_vecs = ((bufferlen != 0) ? 3 : 1);
@@ -656,41 +655,9 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
bufferlist[2].iov_base = &aligned_data;
bufferlist[2].iov_len = (packetlen_aligned - packetlen);
- ret = hv_ringbuffer_write(&channel->outbound, bufferlist, num_vecs,
- &signal, lock, channel->signal_policy);
-
- /*
- * Signalling the host is conditional on many factors:
- * 1. The ring state changed from being empty to non-empty.
- * This is tracked by the variable "signal".
- * 2. The variable kick_q tracks if more data will be placed
- * on the ring. We will not signal if more data is
- * to be placed.
- *
- * Based on the channel signal state, we will decide
- * which signaling policy will be applied.
- *
- * 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.
- *
- * KYS: Oct. 30, 2016:
- * It looks like Windows hosts have logic to deal with DOS attacks that
- * can be triggered if it receives interrupts when it is not expecting
- * the interrupt. The host expects interrupts only when the ring
- * transitions from empty to non-empty (or full to non full on the guest
- * to host ring).
- * So, base the signaling decision solely on the ring state until the
- * host logic is fixed.
- */
-
- if (((ret == 0) && signal))
- vmbus_setevent(channel);
+ return hv_ringbuffer_write(channel, bufferlist, num_vecs,
+ lock, kick_q);
- return ret;
}
EXPORT_SYMBOL(vmbus_sendpacket_ctl);
@@ -731,7 +698,6 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
u32 flags,
bool kick_q)
{
- int ret;
int i;
struct vmbus_channel_packet_page_buffer desc;
u32 descsize;
@@ -739,7 +705,6 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
u32 packetlen_aligned;
struct kvec bufferlist[3];
u64 aligned_data = 0;
- bool signal = false;
bool lock = channel->acquire_ring_lock;
if (pagecount > MAX_PAGE_BUFFER_COUNT)
@@ -777,38 +742,8 @@ 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, lock, channel->signal_policy);
-
- /*
- * Signalling the host is conditional on many factors:
- * 1. The ring state changed from being empty to non-empty.
- * This is tracked by the variable "signal".
- * 2. The variable kick_q tracks if more data will be placed
- * on the ring. We will not signal if more data is
- * to be placed.
- *
- * Based on the channel signal state, we will decide
- * which signaling policy will be applied.
- *
- * 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.
- *
- * KYS: Oct. 30, 2016:
- * It looks like Windows hosts have logic to deal with DOS attacks that
- * can be triggered if it receives interrupts when it is not expecting
- * the interrupt. The host expects interrupts only when the ring
- * transitions from empty to non-empty (or full to non full on the guest
- * to host ring).
- * So, base the signaling decision solely on the ring state until the
- * host logic is fixed.
- */
-
- if (((ret == 0) && signal))
- vmbus_setevent(channel);
-
- return ret;
+ return hv_ringbuffer_write(channel, bufferlist, 3,
+ lock, kick_q);
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer_ctl);
@@ -839,12 +774,10 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
u32 desc_size,
void *buffer, u32 bufferlen, u64 requestid)
{
- int ret;
u32 packetlen;
u32 packetlen_aligned;
struct kvec bufferlist[3];
u64 aligned_data = 0;
- bool signal = false;
bool lock = channel->acquire_ring_lock;
packetlen = desc_size + bufferlen;
@@ -865,13 +798,8 @@ 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, lock, channel->signal_policy);
-
- if (ret == 0 && signal)
- vmbus_setevent(channel);
-
- return ret;
+ return hv_ringbuffer_write(channel, bufferlist, 3,
+ lock, true);
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
@@ -883,14 +811,12 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
struct hv_multipage_buffer *multi_pagebuffer,
void *buffer, u32 bufferlen, u64 requestid)
{
- int ret;
struct vmbus_channel_packet_multipage_buffer desc;
u32 descsize;
u32 packetlen;
u32 packetlen_aligned;
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);
@@ -930,13 +856,8 @@ 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, lock, channel->signal_policy);
-
- if (ret == 0 && signal)
- vmbus_setevent(channel);
-
- return ret;
+ return hv_ringbuffer_write(channel, bufferlist, 3,
+ lock, true);
}
EXPORT_SYMBOL_GPL(vmbus_sendpacket_multipagebuffer);
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index a5b4442433c8..fa782e13c8da 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -527,10 +527,10 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
-int hv_ringbuffer_write(struct hv_ring_buffer_info *ring_info,
+int hv_ringbuffer_write(struct vmbus_channel *channel,
struct kvec *kv_list,
- u32 kv_count, bool *signal, bool lock,
- enum hv_signal_policy policy);
+ u32 kv_count, bool lock,
+ bool kick_q);
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 5d11d93eedf4..4af71306d0ff 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -66,14 +66,25 @@ u32 hv_end_read(struct hv_ring_buffer_info *rbi)
* once the ring buffer is empty, it will clear the
* interrupt_mask and re-check to see if new data has
* arrived.
+ *
+ * KYS: Oct. 30, 2016:
+ * It looks like Windows hosts have logic to deal with DOS attacks that
+ * can be triggered if it receives interrupts when it is not expecting
+ * the interrupt. The host expects interrupts only when the ring
+ * transitions from empty to non-empty (or full to non full on the guest
+ * to host ring).
+ * So, base the signaling decision solely on the ring state until the
+ * host logic is fixed.
*/
-static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi,
- enum hv_signal_policy policy)
+static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel,
+ bool kick_q)
{
+ struct hv_ring_buffer_info *rbi = &channel->outbound;
+
virt_mb();
if (READ_ONCE(rbi->ring_buffer->interrupt_mask))
- return false;
+ return;
/* check interrupt_mask before read_index */
virt_rmb();
@@ -82,9 +93,9 @@ static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi,
* ring transitions from being empty to non-empty.
*/
if (old_write == READ_ONCE(rbi->ring_buffer->read_index))
- return true;
+ vmbus_setevent(channel);
- return false;
+ return;
}
/* Get the next write location for the specified ring buffer. */
@@ -273,9 +284,9 @@ 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, bool lock,
- enum hv_signal_policy policy)
+int hv_ringbuffer_write(struct vmbus_channel *channel,
+ struct kvec *kv_list, u32 kv_count, bool lock,
+ bool kick_q)
{
int i = 0;
u32 bytes_avail_towrite;
@@ -285,6 +296,7 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
u32 old_write;
u64 prev_indices = 0;
unsigned long flags = 0;
+ struct hv_ring_buffer_info *outring_info = &channel->outbound;
for (i = 0; i < kv_count; i++)
totalbytes_towrite += kv_list[i].iov_len;
@@ -337,7 +349,7 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
if (lock)
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
- *signal = hv_need_to_signal(old_write, outring_info, policy);
+ hv_signal_on_write(old_write, channel, kick_q);
return 0;
}
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 468e15e29f5f..9a2d657a7fe7 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1447,6 +1447,7 @@ void hv_event_tasklet_enable(struct vmbus_channel *channel);
void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid);
+void vmbus_setevent(struct vmbus_channel *channel);
/*
* Negotiated version with the Host.
*/
--
2.11.0

4
kernel/patches-4.9/0010-Drivers-hv-vss-Operation-timeouts-should-match-host-.patch → kernel/patches-4.9/0006-Drivers-hv-vss-Operation-timeouts-should-match-host-.patch
View File

@ -1,7 +1,7 @@
From 603fe73ad632d1acd4c1351c8b902d103c4aed44 Mon Sep 17 00:00:00 2001
From adb4437c3ee5973a5f84864cdfb06c00b3b3c651 Mon Sep 17 00:00:00 2001
From: Alex Ng <alexng@messages.microsoft.com>
Date: Sun, 6 Nov 2016 13:14:11 -0800
Subject: [PATCH 10/12] Drivers: hv: vss: Operation timeouts should match host
Subject: [PATCH 6/8] Drivers: hv: vss: Operation timeouts should match host
expectation
Increase the timeout of backup operations. When system is under I/O load,

142
kernel/patches-4.9/0007-Drivers-hv-vmbus-On-the-read-path-cleanup-the-logic-.patch
View File

@ -1,142 +0,0 @@
From 983afbbd6d063c25e8bb8b4e0cbaa840e7ddb0b6 Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Sun, 6 Nov 2016 13:14:18 -0800
Subject: [PATCH 07/12] Drivers: hv: vmbus: On the read path cleanup the logic
to interrupt the host
Signal the host when we determine the host is to be signaled -
on th read path. The currrent code determines the need to signal in the
ringbuffer code and actually issues the signal elsewhere. This can result
in the host viewing this interrupt as spurious since the host may also
poll the channel. Make the necessary adjustments.
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
(cherry picked from commit 3372592a140db69fd63837e81f048ab4abf8111e)
---
drivers/hv/channel.c | 11 ++---------
drivers/hv/hyperv_vmbus.h | 4 ++--
drivers/hv/ring_buffer.c | 7 ++++---
include/linux/hyperv.h | 12 ++++++------
4 files changed, 14 insertions(+), 20 deletions(-)
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 8a8148f7b842..5fb4c6d9209b 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -879,16 +879,9 @@ __vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
u32 bufferlen, u32 *buffer_actual_len, u64 *requestid,
bool raw)
{
- int ret;
- bool signal = false;
-
- ret = hv_ringbuffer_read(&channel->inbound, buffer, bufferlen,
- buffer_actual_len, requestid, &signal, raw);
+ return hv_ringbuffer_read(channel, buffer, bufferlen,
+ buffer_actual_len, requestid, raw);
- if (signal)
- vmbus_setevent(channel);
-
- return ret;
}
int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer,
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index fa782e13c8da..2b13f2a0a71e 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -532,9 +532,9 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
u32 kv_count, bool lock,
bool kick_q);
-int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
+int hv_ringbuffer_read(struct vmbus_channel *channel,
void *buffer, u32 buflen, u32 *buffer_actual_len,
- u64 *requestid, bool *signal, bool raw);
+ u64 *requestid, bool raw);
void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
struct hv_ring_buffer_debug_info *debug_info);
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 4af71306d0ff..cd49cb17eb7f 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -353,9 +353,9 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
return 0;
}
-int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
+int hv_ringbuffer_read(struct vmbus_channel *channel,
void *buffer, u32 buflen, u32 *buffer_actual_len,
- u64 *requestid, bool *signal, bool raw)
+ u64 *requestid, bool raw)
{
u32 bytes_avail_toread;
u32 next_read_location = 0;
@@ -364,6 +364,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
u32 offset;
u32 packetlen;
int ret = 0;
+ struct hv_ring_buffer_info *inring_info = &channel->inbound;
if (buflen <= 0)
return -EINVAL;
@@ -421,7 +422,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info,
/* Update the read index */
hv_set_next_read_location(inring_info, next_read_location);
- *signal = hv_need_to_signal_on_read(inring_info);
+ hv_signal_on_read(channel);
return ret;
}
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 9a2d657a7fe7..5343b7406acc 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1480,10 +1480,11 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info)
* there is room for the producer to send the pending packet.
*/
-static inline bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi)
+static inline void hv_signal_on_read(struct vmbus_channel *channel)
{
u32 cur_write_sz;
u32 pending_sz;
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
/*
* Issue a full memory barrier before making the signaling decision.
@@ -1501,14 +1502,14 @@ static inline bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi)
pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
/* If the other end is not blocked on write don't bother. */
if (pending_sz == 0)
- return false;
+ return;
cur_write_sz = hv_get_bytes_to_write(rbi);
if (cur_write_sz >= pending_sz)
- return true;
+ vmbus_setevent(channel);
- return false;
+ return;
}
/*
@@ -1590,8 +1591,7 @@ static inline void commit_rd_index(struct vmbus_channel *channel)
virt_rmb();
ring_info->ring_buffer->read_index = ring_info->priv_read_index;
- if (hv_need_to_signal_on_read(ring_info))
- vmbus_set_event(channel);
+ hv_signal_on_read(channel);
}
struct vmpipe_proto_header {
--
2.11.0

4
kernel/patches-4.9/0011-Drivers-hv-vmbus-Use-all-supported-IC-versions-to-ne.patch → kernel/patches-4.9/0007-Drivers-hv-vmbus-Use-all-supported-IC-versions-to-ne.patch
View File

@ -1,7 +1,7 @@
From 364e61023027502953bb24666508073d73f39d4b Mon Sep 17 00:00:00 2001
From 3ffbfea0d7cf206fec3fbd2a090778d882ddcf83 Mon Sep 17 00:00:00 2001
From: Alex Ng <alexng@messages.microsoft.com>
Date: Sat, 28 Jan 2017 12:37:17 -0700
Subject: [PATCH 11/12] Drivers: hv: vmbus: Use all supported IC versions to
Subject: [PATCH 7/8] Drivers: hv: vmbus: Use all supported IC versions to
negotiate
Previously, we were assuming that each IC protocol version was tied to a

4
kernel/patches-4.9/0012-Drivers-hv-Log-the-negotiated-IC-versions.patch → kernel/patches-4.9/0008-Drivers-hv-Log-the-negotiated-IC-versions.patch
View File

@ -1,7 +1,7 @@
From 0c2c1129f54f01a7889f4e114cace61ec2c833e7 Mon Sep 17 00:00:00 2001
From 2b6c873e6f7bde90f4d60dac6b4d933c4ed2610d Mon Sep 17 00:00:00 2001
From: Alex Ng <alexng@messages.microsoft.com>
Date: Sat, 28 Jan 2017 12:37:18 -0700
Subject: [PATCH 12/12] Drivers: hv: Log the negotiated IC versions.
Subject: [PATCH 8/8] Drivers: hv: Log the negotiated IC versions.
Log the negotiated IC versions.

150
kernel/patches-4.9/0008-Drivers-hv-vmbus-finally-fix-hv_need_to_signal_on_re.patch
View File

@ -1,150 +0,0 @@
From 4e662fc5eed67dbc95569ee89fc628d27a1646d3 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Tue, 24 Jan 2017 06:54:46 +0000
Subject: [PATCH 08/12] Drivers: hv: vmbus: finally fix
hv_need_to_signal_on_read()
Commit a389fcfd2cb5 ("Drivers: hv: vmbus: Fix signaling logic in hv_need_to_signal_on_read()")
added the proper mb(), but removed the test "prev_write_sz < pending_sz"
when making the signal decision.
As a result, the guest can signal the host unnecessarily,
and then the host can throttle the guest because the host
thinks the guest is buggy or malicious; finally the user
running stress test can perceive intermittent freeze of
the guest.
This patch brings back the test, and properly handles the
in-place consumption APIs used by NetVSC (see get_next_pkt_raw(),
put_pkt_raw() and commit_rd_index()).
Fixes: a389fcfd2cb5 ("Drivers: hv: vmbus: Fix signaling logic in hv_need_to_signal_on_read()")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reported-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Tested-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: <stable@vger.kernel.org>
Origin: https://patchwork.kernel.org/patch/9534107/
---
drivers/hv/ring_buffer.c | 1 +
drivers/net/hyperv/netvsc.c | 6 ++++++
include/linux/hyperv.h | 32 ++++++++++++++++++++++++++++++--
3 files changed, 37 insertions(+), 2 deletions(-)
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index cd49cb17eb7f..308dbda700eb 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -383,6 +383,7 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
return ret;
}
+ init_cached_read_index(channel);
next_read_location = hv_get_next_read_location(inring_info);
next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
sizeof(desc),
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 720b5fa9e625..c2ac39a940f7 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1288,6 +1288,9 @@ void netvsc_channel_cb(void *context)
ndev = hv_get_drvdata(device);
buffer = get_per_channel_state(channel);
+ /* commit_rd_index() -> hv_signal_on_read() needs this. */
+ init_cached_read_index(channel);
+
do {
desc = get_next_pkt_raw(channel);
if (desc != NULL) {
@@ -1340,6 +1343,9 @@ void netvsc_channel_cb(void *context)
bufferlen = bytes_recvd;
}
+
+ init_cached_read_index(channel);
+
} while (1);
if (bufferlen > NETVSC_PACKET_SIZE)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 5343b7406acc..e34da6846348 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -128,6 +128,7 @@ struct hv_ring_buffer_info {
u32 ring_data_startoffset;
u32 priv_write_index;
u32 priv_read_index;
+ u32 cached_read_index;
};
/*
@@ -180,6 +181,19 @@ static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi)
return write;
}
+static inline u32 hv_get_cached_bytes_to_write(
+ const struct hv_ring_buffer_info *rbi)
+{
+ u32 read_loc, write_loc, dsize, write;
+
+ dsize = rbi->ring_datasize;
+ read_loc = rbi->cached_read_index;
+ write_loc = rbi->ring_buffer->write_index;
+
+ write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
+ read_loc - write_loc;
+ return write;
+}
/*
* VMBUS version is 32 bit entity broken up into
* two 16 bit quantities: major_number. minor_number.
@@ -1482,7 +1496,7 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info)
static inline void hv_signal_on_read(struct vmbus_channel *channel)
{
- u32 cur_write_sz;
+ u32 cur_write_sz, cached_write_sz;
u32 pending_sz;
struct hv_ring_buffer_info *rbi = &channel->inbound;
@@ -1506,12 +1520,24 @@ static inline void hv_signal_on_read(struct vmbus_channel *channel)
cur_write_sz = hv_get_bytes_to_write(rbi);
- if (cur_write_sz >= pending_sz)
+ if (cur_write_sz < pending_sz)
+ return;
+
+ cached_write_sz = hv_get_cached_bytes_to_write(rbi);
+ if (cached_write_sz < pending_sz)
vmbus_setevent(channel);
return;
}
+static inline void
+init_cached_read_index(struct vmbus_channel *channel)
+{
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+ rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
/*
* An API to support in-place processing of incoming VMBUS packets.
*/
@@ -1573,6 +1599,8 @@ static inline void put_pkt_raw(struct vmbus_channel *channel,
* This call commits the read index and potentially signals the host.
* Here is the pattern for using the "in-place" consumption APIs:
*
+ * init_cached_read_index();
+ *
* while (get_next_pkt_raw() {
* process the packet "in-place";
* put_pkt_raw();
--
2.11.0