summaryrefslogtreecommitdiffstats
path: root/drivers/hv/channel_mgmt.c
AgeCommit message (Collapse)AuthorFilesLines
2014-05-03Drivers: hv: vmbus: Implement per-CPU mapping of relid to channelK. Y. Srinivasan1-1/+40
Currently the mapping of the relID to channel is done under the protection of a single spin lock. Starting with ws2012, each channel is bound to a specific VCPU in the guest. Use this binding to eliminate the spin lock by setting up per-cpu state for mapping relId to the channel. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2014-05-03Drivers: hv: Eliminate the channel spinlock in the callback pathK. Y. Srinivasan1-4/+7
By ensuring that we set the callback handler to NULL in the channel close path on the same CPU that the channel is bound to, we can eliminate this lock acquisition and release in a performance critical path. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-10-19Drivers: hv: vmbus: Fix a bug in channel rescind codeK. Y. Srinivasan1-2/+3
Rescind of subchannels were not being correctly handled. Fix the bug. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Cc: <stable@vger.kernel.org> [3.11+] Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-08-27Drivers: hv: vmbus: Fix a bug in the handling of channel offersK. Y. Srinivasan1-7/+7
The channel state should be correctly set before registering the device. In the current code the driver probe would fail for channels that have been rescinded and subsequently re-offered. Fix the bug. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Cc: stable <stable@vger.kernel.org> # 3.11 Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-07-26Drivers: hv: util: Fix a bug in version negotiation code for util servicesK. Y. Srinivasan1-22/+53
The current code picked the highest version advertised by the host. WS2012 R2 has implemented a protocol version for KVP that is not compatible with prior protocol versions of KVP. Fix the bug in the current code by explicitly specifying the protocol version that the guest can support. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-06-03Drivers: hv: vmbus: Implement multi-channel supportK. Y. Srinivasan1-4/+115
Starting with Win8, the host supports multiple sub-channels for a given device. As in the past, the initial channel offer specifies the device and is associated with both the type and the instance GUIDs. For performance critical devices, the host may support multiple sub-channels. The sub-channels share the same type and instance GUID as the primary channel. The number of sub-channels offerrred to the guest depends on the number of virtual CPUs assigned to the guest. The guest can request the creation of these sub-channels and once created and opened, the guest can distribute the traffic across all the channels (the primary and the sub-channels). A request sent on a sub-channel will have the response delivered on the same sub-channel. At channel (sub-channel) creation we bind the channel interrupt to a CPU and with this sub-channel support we will be able to spread the interrupt load of a given device across all available CPUs. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-05-21Drivers: hv: Fix a bug in get_vp_index()K. Y. Srinivasan1-1/+1
Linux' notion of cpuid is different from the Host's notion of CPUID. In the call to bind the channel interrupts, we should use the host's notion of CPU Ids. Fix this bug. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Cc: Stable <stable@vger.kernel.org> (V3.9) Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-03-15Drivers: hv: vmbus: Handle channel rescind message correctlyK. Y. Srinivasan1-0/+11
Properly cleanup the channel state on receipt of the "offer rescind" message. Starting with ws2012, the host requires that the channel "relid" be properly cleaned up when the offer is rescinded. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-02-27Drivers: hv: vmbus: Use the new infrastructure for delivering VMBUS interruptsK. Y. Srinivasan1-1/+1
Use the infrastructure for delivering VMBUS interrupts using a special vector. With this patch, we can now properly handle the VMBUS interrupts that can be delivered on any CPU. Also, turn on interrupt load balancing as well. This patch requires the infrastructure that was implemented in the patch: X86: Handle Hyper-V vmbus interrupts as special hypervisor interrupts Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-01-25Drivers: hv: vmbus: Consolidate all offer GUID definitions in hyperv.hK. Y. Srinivasan1-25/+6
Consolidate all GUID definitions in hyperv.h and use these definitions in implementing channel bindings (as far as interrupt delivery goes). Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-01-18Drivers: hv: Bind all vmbbus interrupts to the boot CPUK. Y. Srinivasan1-1/+1
The default interrupt delivery model in Linux does not support the Hyper-V vmbus delivery model when the guest is configured with multiple VCPUs. I have sent a patch to address this - delivering the vmbus interrupt on a separate IDT vector. Until this patch is applied, bind all vmbus interrupts to the boot CPU. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-01-17Drivers: hv: Add code to distribute channel interrupt loadK. Y. Srinivasan1-1/+84
Implement a simple policy for distributing incoming interrupt load. We classify channels as (a) performance critical and (b) not performance critical. All non-performance critical channels will be bound to the boot cpu. Performance critical channels will be bound to the remaining available CPUs on a round-robin basis. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-01-17Drivers: hv: Add state to manage incoming channel interrupt loadK. Y. Srinivasan1-0/+2
Add state to bind a channel to a specific VCPU. This will help us better distribute incoming interrupt load. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-01-17Drivers: hv: Manage signaling state on a per-connection basisK. Y. Srinivasan1-0/+20
The current code has a global handle for supporting signaling of the host from guest. Make this a per-channel attribute as on some versions of the host we can signal on per-channel handle. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-01-17Drivers: hv: Add state to manage batched readingK. Y. Srinivasan1-0/+7
For the "read" side signaling optimization, the reader has to completely drain the queue before exiting. Add state to manage this "batched" reading. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-10-24Drivers: hv: remove unused variable from channel_mgmt.cWei Yongjun1-8/+0
The variables guidtype, guidinstance and initiate are initialized but never used otherwise, so remove the unused variables. dpatch engine is used to auto generate this patch. (https://github.com/weiyj/dpatch) Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-14Drivers: hv: util: Properly handle version negotiations.K. Y. Srinivasan1-16/+38
The current version negotiation code is not "future proof". Fix this by allowing each service the flexibility to either specify the highest version it can support or it can support the highest version number the host is offering. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-05-14Drivers: hv: Get rid of an unnecessary check in vmbus_prep_negotiate_resp()K. Y. Srinivasan1-22/+21
The vmbus_prep_negotiate_resp() is only invoked when we are negotiating the version; so the current check in vmbus_prep_negotiate_resp() is unnecessary. Get rid of it. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2012-01-24drivers: hv: Get rid of some unnecessary codeK. Y. Srinivasan1-87/+0
The current code unnecessarily limits the number of offers we handle. Get rid of this limitation. As part of this cleanup, also get rid of an unused define - MAX_MSG_TYPES. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-12-12Drivers: hv: Make the vmbus driver unloadableK. Y. Srinivasan1-0/+11
It turns out that the vmbus driver can be made unloadable. Make it unloadable. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-12-12Drivers: hv: Fix a memory leakK. Y. Srinivasan1-0/+1
There was a memory leak in a failure path in vmbus_process_offer(). Fix it. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-10-11hv: remove free_channel() from hyperv.hGreg Kroah-Hartman1-1/+1
This function is only used in the file it is declared in (channel_mgmt.c) so make it static and remove it from the hyperv.h file. Cc: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-10-11hv: rename prep_negotiate_resp() to vmbus_prep_negotiate_resp()Greg Kroah-Hartman1-5/+4
It's a global symbol, so properly prefix it and use the proper EXPORT value as well. Cc: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2011-10-10Staging: hv: move hyperv code out of staging directoryGreg Kroah-Hartman1-0/+647
After many years wandering the desert, it is finally time for the Microsoft HyperV code to move out of the staging directory. Or at least the core hyperv bus code, and the utility driver, the rest still have some review to get through by the various subsystem maintainers. Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-21 07:40:36 +0000