diff options
Diffstat (limited to 'include/linux/hyperv.h')
| -rw-r--r-- | include/linux/hyperv.h | 219 |
1 files changed, 123 insertions, 96 deletions
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index cd184bdca58f..970771a5f739 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -32,11 +32,10 @@ #include <linux/scatterlist.h> #include <linux/list.h> #include <linux/timer.h> -#include <linux/workqueue.h> #include <linux/completion.h> #include <linux/device.h> #include <linux/mod_devicetable.h> - +#include <linux/interrupt.h> #define MAX_PAGE_BUFFER_COUNT 32 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ @@ -128,6 +127,7 @@ struct hv_ring_buffer_info { u32 ring_data_startoffset; u32 priv_write_index; u32 priv_read_index; + u32 cached_read_index; }; /* @@ -138,8 +138,8 @@ struct hv_ring_buffer_info { * for the specified ring buffer */ static inline void -hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, - u32 *read, u32 *write) +hv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi, + u32 *read, u32 *write) { u32 read_loc, write_loc, dsize; @@ -153,7 +153,7 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi, *read = dsize - *write; } -static inline u32 hv_get_bytes_to_read(struct hv_ring_buffer_info *rbi) +static inline u32 hv_get_bytes_to_read(const struct hv_ring_buffer_info *rbi) { u32 read_loc, write_loc, dsize, read; @@ -167,7 +167,7 @@ static inline u32 hv_get_bytes_to_read(struct hv_ring_buffer_info *rbi) return read; } -static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi) +static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) { u32 read_loc, write_loc, dsize, write; @@ -180,6 +180,19 @@ 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. @@ -627,6 +640,7 @@ struct vmbus_channel_msginfo { /* Synchronize the request/response if needed */ struct completion waitevent; + struct vmbus_channel *waiting_channel; union { struct vmbus_channel_version_supported version_supported; struct vmbus_channel_open_result open_result; @@ -669,11 +683,6 @@ struct hv_input_signal_event_buffer { struct hv_input_signal_event event; }; -enum hv_signal_policy { - HV_SIGNAL_POLICY_DEFAULT = 0, - HV_SIGNAL_POLICY_EXPLICIT, -}; - enum hv_numa_policy { HV_BALANCED = 0, HV_LOCALIZED, @@ -696,7 +705,7 @@ enum vmbus_device_type { HV_FCOPY, HV_BACKUP, HV_DM, - HV_UNKOWN, + HV_UNKNOWN, }; struct vmbus_device { @@ -733,26 +742,27 @@ struct vmbus_channel { struct vmbus_close_msg close_msg; - /* Channel callback are invoked in this workqueue context */ - /* HANDLE dataWorkQueue; */ - + /* Channel callback's invoked in softirq context */ + struct tasklet_struct callback_event; void (*onchannel_callback)(void *context); void *channel_callback_context; /* - * A channel can be marked for efficient (batched) - * reading: - * If batched_reading is set to "true", we read until the - * channel is empty and hold off interrupts from the host - * during the entire read process. - * If batched_reading is set to "false", the client is not - * going to perform batched reading. - * - * By default we will enable batched reading; specific - * drivers that don't want this behavior can turn it off. + * A channel can be marked for one of three modes of reading: + * BATCHED - callback called from taslket and should read + * channel until empty. Interrupts from the host + * are masked while read is in process (default). + * DIRECT - callback called from tasklet (softirq). + * ISR - callback called in interrupt context and must + * invoke its own deferred processing. + * Host interrupts are disabled and must be re-enabled + * when ring is empty. */ - - bool batched_reading; + enum hv_callback_mode { + HV_CALL_BATCHED, + HV_CALL_DIRECT, + HV_CALL_ISR + } callback_mode; bool is_dedicated_interrupt; struct hv_input_signal_event_buffer sig_buf; @@ -835,23 +845,13 @@ struct vmbus_channel { * link up channels based on their CPU affinity. */ struct list_head percpu_list; + /* - * Host signaling policy: The default policy will be - * based on the ring buffer state. We will also support - * a policy where the client driver can have explicit - * 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. + * Defer freeing channel until after all cpu's have + * gone through grace period. */ - bool acquire_ring_lock; + struct rcu_head rcu; + /* * For performance critical channels (storage, networking * etc,), Hyper-V has a mechanism to enhance the throughput @@ -892,32 +892,22 @@ struct vmbus_channel { }; -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 & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER); } -static inline void set_channel_signal_state(struct vmbus_channel *c, - enum hv_signal_policy policy) -{ - c->signal_policy = policy; -} - static inline void set_channel_affinity_state(struct vmbus_channel *c, enum hv_numa_policy policy) { c->affinity_policy = policy; } -static inline void set_channel_read_state(struct vmbus_channel *c, bool state) +static inline void set_channel_read_mode(struct vmbus_channel *c, + enum hv_callback_mode mode) { - c->batched_reading = state; + c->callback_mode = mode; } static inline void set_per_channel_state(struct vmbus_channel *c, void *s) @@ -1040,8 +1030,7 @@ extern int vmbus_sendpacket_ctl(struct vmbus_channel *channel, u32 bufferLen, u64 requestid, enum vmbus_packet_type type, - u32 flags, - bool kick_q); + u32 flags); extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, struct hv_page_buffer pagebuffers[], @@ -1056,8 +1045,7 @@ extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, void *buffer, u32 bufferlen, u64 requestid, - u32 flags, - bool kick_q); + u32 flags); extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, struct hv_multipage_buffer *mpb, @@ -1119,6 +1107,12 @@ struct hv_driver { struct device_driver driver; + /* dynamic device GUID's */ + struct { + spinlock_t lock; + struct list_head list; + } dynids; + int (*probe)(struct hv_device *, const struct hv_vmbus_device_id *); int (*remove)(struct hv_device *); void (*shutdown)(struct hv_device *); @@ -1438,15 +1432,14 @@ struct hyperv_service_callback { }; #define MAX_SRV_VER 0x7ffffff -extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *, - struct icmsg_negotiate *, u8 *, int, - int); - -void hv_event_tasklet_disable(struct vmbus_channel *channel); -void hv_event_tasklet_enable(struct vmbus_channel *channel); +extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, + const int *fw_version, int fw_vercnt, + const int *srv_version, int srv_vercnt, + int *nego_fw_version, int *nego_srv_version); void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); +void vmbus_setevent(struct vmbus_channel *channel); /* * Negotiated version with the Host. */ @@ -1459,9 +1452,9 @@ void vmbus_set_event(struct vmbus_channel *channel); /* Get the start of the ring buffer. */ static inline void * -hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info) +hv_get_ring_buffer(const struct hv_ring_buffer_info *ring_info) { - return (void *)ring_info->ring_buffer->buffer; + return ring_info->ring_buffer->buffer; } /* @@ -1479,10 +1472,11 @@ 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 cur_write_sz, cached_write_sz; u32 pending_sz; + struct hv_ring_buffer_info *rbi = &channel->inbound; /* * Issue a full memory barrier before making the signaling decision. @@ -1500,14 +1494,56 @@ 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; + 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 false; + 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; +} + +/* + * Mask off host interrupt callback notifications + */ +static inline void hv_begin_read(struct hv_ring_buffer_info *rbi) +{ + rbi->ring_buffer->interrupt_mask = 1; + + /* make sure mask update is not reordered */ + virt_mb(); +} + +/* + * Re-enable host callback and return number of outstanding bytes + */ +static inline u32 hv_end_read(struct hv_ring_buffer_info *rbi) +{ + + rbi->ring_buffer->interrupt_mask = 0; + + /* make sure mask update is not reordered */ + virt_mb(); + + /* + * Now check to see if the ring buffer is still empty. + * If it is not, we raced and we need to process new + * incoming messages. + */ + return hv_get_bytes_to_read(rbi); } /* @@ -1519,31 +1555,23 @@ static inline struct vmpacket_descriptor * get_next_pkt_raw(struct vmbus_channel *channel) { struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 read_loc = ring_info->priv_read_index; + u32 priv_read_loc = ring_info->priv_read_index; void *ring_buffer = hv_get_ring_buffer(ring_info); - struct vmpacket_descriptor *cur_desc; - u32 packetlen; u32 dsize = ring_info->ring_datasize; - u32 delta = read_loc - ring_info->ring_buffer->read_index; + /* + * delta is the difference between what is available to read and + * what was already consumed in place. We commit read index after + * the whole batch is processed. + */ + u32 delta = priv_read_loc >= ring_info->ring_buffer->read_index ? + priv_read_loc - ring_info->ring_buffer->read_index : + (dsize - ring_info->ring_buffer->read_index) + priv_read_loc; u32 bytes_avail_toread = (hv_get_bytes_to_read(ring_info) - delta); if (bytes_avail_toread < sizeof(struct vmpacket_descriptor)) return NULL; - if ((read_loc + sizeof(*cur_desc)) > dsize) - return NULL; - - cur_desc = ring_buffer + read_loc; - packetlen = cur_desc->len8 << 3; - - /* - * If the packet under consideration is wrapping around, - * return failure. - */ - if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > (dsize - 1)) - return NULL; - - return cur_desc; + return ring_buffer + priv_read_loc; } /* @@ -1555,22 +1583,22 @@ static inline void put_pkt_raw(struct vmbus_channel *channel, struct vmpacket_descriptor *desc) { struct hv_ring_buffer_info *ring_info = &channel->inbound; - u32 read_loc = ring_info->priv_read_index; u32 packetlen = desc->len8 << 3; u32 dsize = ring_info->ring_datasize; - if ((read_loc + packetlen + VMBUS_PKT_TRAILER) > dsize) - BUG(); /* * Include the packet trailer. */ ring_info->priv_read_index += packetlen + VMBUS_PKT_TRAILER; + ring_info->priv_read_index %= dsize; } /* * 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(); @@ -1589,8 +1617,7 @@ 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); } |