From 5f57fbeaaf7c4cd33152d7f2e449caab4d4209d9 Mon Sep 17 00:00:00 2001 From: Tiwei Bie Date: Thu, 24 May 2018 18:33:32 +0800 Subject: vhost-user: allow slave to send fds via slave channel Introduce VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD protocol feature to allow slave to send at most 8 descriptors in each message to master via ancillary data using the slave channel. Suggested-by: Michael S. Tsirkin Signed-off-by: Tiwei Bie Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/interop/vhost-user.txt | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'docs') diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt index 534caab18a..682a683eb4 100644 --- a/docs/interop/vhost-user.txt +++ b/docs/interop/vhost-user.txt @@ -367,6 +367,10 @@ The fd is provided via VHOST_USER_SET_SLAVE_REQ_FD ancillary data. A slave may then send VHOST_USER_SLAVE_* messages to the master using this fd communication channel. +If VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD protocol feature is negotiated, +slave can send file descriptors (at most 8 descriptors in each message) +to master via ancillary data using this fd communication channel. + Protocol features ----------------- @@ -380,6 +384,7 @@ Protocol features #define VHOST_USER_PROTOCOL_F_CRYPTO_SESSION 7 #define VHOST_USER_PROTOCOL_F_PAGEFAULT 8 #define VHOST_USER_PROTOCOL_F_CONFIG 9 +#define VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD 10 Master message types -------------------- -- cgit v1.2.3 From 44866521bd6ea8e5152a87664dea1eee90c9438b Mon Sep 17 00:00:00 2001 From: Tiwei Bie Date: Thu, 24 May 2018 18:33:34 +0800 Subject: vhost-user: support registering external host notifiers This patch introduces VHOST_USER_PROTOCOL_F_HOST_NOTIFIER. With this feature negotiated, vhost-user backend can register memory region based host notifiers. And it will allow the guest driver in the VM to notify the hardware accelerator at the vhost-user backend directly. Signed-off-by: Tiwei Bie Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/interop/vhost-user.txt | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'docs') diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt index 682a683eb4..d51fd58242 100644 --- a/docs/interop/vhost-user.txt +++ b/docs/interop/vhost-user.txt @@ -132,6 +132,16 @@ Depending on the request type, payload can be: Payload: Size bytes array holding the contents of the virtio device's configuration space + * Vring area description + ----------------------- + | u64 | size | offset | + ----------------------- + + u64: a 64-bit integer contains vring index and flags + Size: a 64-bit size of this area + Offset: a 64-bit offset of this area from the start of the + supplied file descriptor + In QEMU the vhost-user message is implemented with the following struct: typedef struct VhostUserMsg { @@ -146,6 +156,7 @@ typedef struct VhostUserMsg { VhostUserLog log; struct vhost_iotlb_msg iotlb; VhostUserConfig config; + VhostUserVringArea area; }; } QEMU_PACKED VhostUserMsg; @@ -385,6 +396,7 @@ Protocol features #define VHOST_USER_PROTOCOL_F_PAGEFAULT 8 #define VHOST_USER_PROTOCOL_F_CONFIG 9 #define VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD 10 +#define VHOST_USER_PROTOCOL_F_HOST_NOTIFIER 11 Master message types -------------------- @@ -782,6 +794,27 @@ Slave message types the VHOST_USER_NEED_REPLY flag, master must respond with zero when operation is successfully completed, or non-zero otherwise. + * VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG + + Id: 3 + Equivalent ioctl: N/A + Slave payload: vring area description + Master payload: N/A + + Sets host notifier for a specified queue. The queue index is contained + in the u64 field of the vring area description. The host notifier is + described by the file descriptor (typically it's a VFIO device fd) which + is passed as ancillary data and the size (which is mmap size and should + be the same as host page size) and offset (which is mmap offset) carried + in the vring area description. QEMU can mmap the file descriptor based + on the size and offset to get a memory range. Registering a host notifier + means mapping this memory range to the VM as the specified queue's notify + MMIO region. Slave sends this request to tell QEMU to de-register the + existing notifier if any and register the new notifier if the request is + sent with a file descriptor. + This request should be sent only when VHOST_USER_PROTOCOL_F_HOST_NOTIFIER + protocol feature has been successfully negotiated. + VHOST_USER_PROTOCOL_F_REPLY_ACK: ------------------------------- The original vhost-user specification only demands replies for certain -- cgit v1.2.3 From 9ab3aad2813ce5d9e79c86cb65a013016b61a08f Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Mon, 21 May 2018 10:32:02 -0600 Subject: nvdimm, acpi: support NFIT platform capabilities Add a machine command line option to allow the user to control the Platform Capabilities Structure in the virtualized NFIT. This Platform Capabilities Structure was added in ACPI 6.2 Errata A. Signed-off-by: Ross Zwisler Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- docs/nvdimm.txt | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'docs') diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt index e903d8bb09..8b48fb4633 100644 --- a/docs/nvdimm.txt +++ b/docs/nvdimm.txt @@ -153,3 +153,30 @@ guest NVDIMM region mapping structure. This unarmed flag indicates guest software that this vNVDIMM device contains a region that cannot accept persistent writes. In result, for example, the guest Linux NVDIMM driver, marks such vNVDIMM device as read-only. + +Platform Capabilities +--------------------- + +ACPI 6.2 Errata A added support for a new Platform Capabilities Structure +which allows the platform to communicate what features it supports related to +NVDIMM data durability. Users can provide a capabilities value to a guest via +the optional "nvdimm-cap" machine command line option: + + -machine pc,accel=kvm,nvdimm,nvdimm-cap=2 + +This "nvdimm-cap" field is an integer, and is the combined value of the +various capability bits defined in table 5-137 of the ACPI 6.2 Errata A spec. + +Here is a quick summary of the three bits that are defined as of that spec: + +Bit[0] - CPU Cache Flush to NVDIMM Durability on Power Loss Capable. +Bit[1] - Memory Controller Flush to NVDIMM Durability on Power Loss Capable. + Note: If bit 0 is set to 1 then this bit shall be set to 1 as well. +Bit[2] - Byte Addressable Persistent Memory Hardware Mirroring Capable. + +So, a "nvdimm-cap" value of 2 would mean that the platform supports Memory +Controller Flush on Power Loss, a value of 3 would mean that the platform +supports CPU Cache Flush and Memory Controller Flush on Power Loss, etc. + +For a complete list of the flags available and for more detailed descriptions, +please consult the ACPI spec. -- cgit v1.2.3