// SPDX-License-Identifier: GPL-2.0-only/* * * Copyright (c) 2009, Microsoft Corporation. * * Authors: * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * K. Y. Srinivasan <kys@microsoft.com> */#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h>#include <linux/mm.h>#include <linux/hyperv.h>#include <linux/uio.h>#include <linux/vmalloc.h>#include <linux/slab.h>#include <linux/prefetch.h>#include <linux/io.h>#include <asm/mshyperv.h> #include "hyperv_vmbus.h" #define VMBUS_PKT_TRAILER 8 /* * When we write to the ring buffer, check if the host needs to * be signaled. Here is the details of this protocol: * * 1. The host guarantees that while it is draining the * ring buffer, it will set the interrupt_mask to * indicate it does not need to be interrupted when * new data is placed. * * 2. The host guarantees that it will completely drain * the ring buffer before exiting the read loop. Further, * 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 void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel){ struct hv_ring_buffer_info *rbi = &channel->outbound; virt_mb(); if (READ_ONCE(rbi->ring_buffer->interrupt_mask)) return; /* check interrupt_mask before read_index */ virt_rmb(); /* * This is the only case we need to signal when the * ring transitions from being empty to non-empty. */ if (old_write == READ_ONCE(rbi->ring_buffer->read_index)) { ++channel->intr_out_empty; vmbus_setevent(channel); }} /* Get the next write location for the specified ring buffer. */static inline u32hv_get_next_write_location(struct hv_ring_buffer_info *ring_info){ u32 next = ring_info->ring_buffer->write_index; return next;} /* Set the next write location for the specified ring buffer. */static inline voidhv_set_next_write_location(struct hv_ring_buffer_info *ring_info, u32 next_write_location){ ring_info->ring_buffer->write_index = next_write_location;} /* Get the size of the ring buffer. */static inline u32hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info){ return ring_info->ring_datasize;} /* Get the read and write indices as u64 of the specified ring buffer. */static inline u64hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info){ return (u64)ring_info->ring_buffer->write_index << 32;} /* * Helper routine to copy from source to ring buffer. * Assume there is enough room. Handles wrap-around in dest case only!! */static u32 hv_copyto_ringbuffer( struct hv_ring_buffer_info *ring_info, u32 start_write_offset, const void *src, u32 srclen){ void *ring_buffer = hv_get_ring_buffer(ring_info); u32 ring_buffer_size = hv_get_ring_buffersize(ring_info); memcpy(ring_buffer + start_write_offset, src, srclen); start_write_offset += srclen; if (start_write_offset >= ring_buffer_size) start_write_offset -= ring_buffer_size; return start_write_offset;} /* * * hv_get_ringbuffer_availbytes() * * Get number of bytes available to read and to write to * for the specified ring buffer */static voidhv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi, u32 *read, u32 *write){ u32 read_loc, write_loc, dsize; /* Capture the read/write indices before they changed */ read_loc = READ_ONCE(rbi->ring_buffer->read_index); write_loc = READ_ONCE(rbi->ring_buffer->write_index); dsize = rbi->ring_datasize; *write = write_loc >= read_loc ? dsize - (write_loc - read_loc) : read_loc - write_loc; *read = dsize - *write;} /* Get various debug metrics for the specified ring buffer. */int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info){ u32 bytes_avail_towrite; u32 bytes_avail_toread; mutex_lock(&ring_info->ring_buffer_mutex); if (!ring_info->ring_buffer) { mutex_unlock(&ring_info->ring_buffer_mutex); return -EINVAL; } hv_get_ringbuffer_availbytes(ring_info, &bytes_avail_toread, &bytes_avail_towrite); debug_info->bytes_avail_toread = bytes_avail_toread; debug_info->bytes_avail_towrite = bytes_avail_towrite; debug_info->current_read_index = ring_info->ring_buffer->read_index; debug_info->current_write_index = ring_info->ring_buffer->write_index; debug_info->current_interrupt_mask = ring_info->ring_buffer->interrupt_mask; mutex_unlock(&ring_info->ring_buffer_mutex); return 0;}EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo); /* Initialize a channel's ring buffer info mutex locks */void hv_ringbuffer_pre_init(struct vmbus_channel *channel){ mutex_init(&channel->inbound.ring_buffer_mutex); mutex_init(&channel->outbound.ring_buffer_mutex);} /* Initialize the ring buffer. */int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, struct page *pages, u32 page_cnt, u32 max_pkt_size){ struct page **pages_wraparound; int i; BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE)); /* * First page holds struct hv_ring_buffer, do wraparound mapping for * the rest. */ pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *), GFP_KERNEL); if (!pages_wraparound) return -ENOMEM; pages_wraparound[0] = pages; for (i = 0; i < 2 * (page_cnt - 1); i++) pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1]; ring_info->ring_buffer = (struct hv_ring_buffer *) vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, pgprot_decrypted(PAGE_KERNEL)); kfree(pages_wraparound); if (!ring_info->ring_buffer) return -ENOMEM; /* * Ensure the header page is zero'ed since * encryption status may have changed. */ memset(ring_info->ring_buffer, 0, HV_HYP_PAGE_SIZE); ring_info->ring_buffer->read_index = ring_info->ring_buffer->write_index = 0; /* Set the feature bit for enabling flow control. */ ring_info->ring_buffer->feature_bits.value = 1; ring_info->ring_size = page_cnt << PAGE_SHIFT; ring_info->ring_size_div10_reciprocal = reciprocal_value(ring_info->ring_size / 10); ring_info->ring_datasize = ring_info->ring_size - sizeof(struct hv_ring_buffer); ring_info->priv_read_index = 0; /* Initialize buffer that holds copies of incoming packets */ if (max_pkt_size) { ring_info->pkt_buffer = kzalloc(max_pkt_size, GFP_KERNEL); if (!ring_info->pkt_buffer) return -ENOMEM; ring_info->pkt_buffer_size = max_pkt_size; } spin_lock_init(&ring_info->ring_lock); return 0;} /* Cleanup the ring buffer. */void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info){ mutex_lock(&ring_info->ring_buffer_mutex); vunmap(ring_info->ring_buffer); ring_info->ring_buffer = NULL; mutex_unlock(&ring_info->ring_buffer_mutex); kfree(ring_info->pkt_buffer); ring_info->pkt_buffer = NULL; ring_info->pkt_buffer_size = 0;} /* * Check if the ring buffer spinlock is available to take or not; used on * atomic contexts, like panic path (see the Hyper-V framebuffer driver). */ bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel){ struct hv_ring_buffer_info *rinfo = &channel->outbound; return spin_is_locked(&rinfo->ring_lock);}EXPORT_SYMBOL_GPL(hv_ringbuffer_spinlock_busy); /* Write to the ring buffer. */int hv_ringbuffer_write(struct vmbus_channel *channel, const struct kvec *kv_list, u32 kv_count, u64 requestid, u64 *trans_id){ int i; u32 bytes_avail_towrite; u32 totalbytes_towrite = sizeof(u64); u32 next_write_location; u32 old_write; u64 prev_indices; unsigned long flags; struct hv_ring_buffer_info *outring_info = &channel->outbound; struct vmpacket_descriptor *desc = kv_list[0].iov_base; u64 __trans_id, rqst_id = VMBUS_NO_RQSTOR; if (channel->rescind) return -ENODEV; for (i = 0; i < kv_count; i++) totalbytes_towrite += kv_list[i].iov_len; spin_lock_irqsave(&outring_info->ring_lock, flags); bytes_avail_towrite = hv_get_bytes_to_write(outring_info); /* * If there is only room for the packet, assume it is full. * Otherwise, the next time around, we think the ring buffer * is empty since the read index == write index. */ if (bytes_avail_towrite <= totalbytes_towrite) { ++channel->out_full_total; if (!channel->out_full_flag) { ++channel->out_full_first; channel->out_full_flag = true; } spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; } channel->out_full_flag = false; /* Write to the ring buffer */ next_write_location = hv_get_next_write_location(outring_info); old_write = next_write_location; for (i = 0; i < kv_count; i++) { next_write_location = hv_copyto_ringbuffer(outring_info, next_write_location, kv_list[i].iov_base, kv_list[i].iov_len); } /* * Allocate the request ID after the data has been copied into the * ring buffer. Once this request ID is allocated, the completion * path could find the data and free it. */ if (desc->flags == VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED) { if (channel->next_request_id_callback != NULL) { rqst_id = channel->next_request_id_callback(channel, requestid); if (rqst_id == VMBUS_RQST_ERROR) { spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; } } } desc = hv_get_ring_buffer(outring_info) + old_write; __trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id; /* * Ensure the compiler doesn't generate code that reads the value of * the transaction ID from the ring buffer, which is shared with the * Hyper-V host and subject to being changed at any time. */ WRITE_ONCE(desc->trans_id, __trans_id); if (trans_id) *trans_id = __trans_id; /* Set previous packet start */ prev_indices = hv_get_ring_bufferindices(outring_info); next_write_location = hv_copyto_ringbuffer(outring_info, next_write_location, &prev_indices, sizeof(u64)); /* Issue a full memory barrier before updating the write index */ virt_mb(); /* Now, update the write location */ hv_set_next_write_location(outring_info, next_write_location); spin_unlock_irqrestore(&outring_info->ring_lock, flags); hv_signal_on_write(old_write, channel); if (channel->rescind) { if (rqst_id != VMBUS_NO_RQSTOR) { /* Reclaim request ID to avoid leak of IDs */ if (channel->request_addr_callback != NULL) channel->request_addr_callback(channel, rqst_id); } return -ENODEV; } return 0;} int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, u64 *requestid, bool raw){ struct vmpacket_descriptor *desc; u32 packetlen, offset; if (unlikely(buflen == 0)) return -EINVAL; *buffer_actual_len = 0; *requestid = 0; /* Make sure there is something to read */ desc = hv_pkt_iter_first(channel); if (desc == NULL) { /* * No error is set when there is even no header, drivers are * supposed to analyze buffer_actual_len. */ return 0; } offset = raw ? 0 : (desc->offset8 << 3); packetlen = (desc->len8 << 3) - offset; *buffer_actual_len = packetlen; *requestid = desc->trans_id; if (unlikely(packetlen > buflen)) return -ENOBUFS; /* since ring is double mapped, only one copy is necessary */ memcpy(buffer, (const char *)desc + offset, packetlen); /* Advance ring index to next packet descriptor */ __hv_pkt_iter_next(channel, desc); /* Notify host of update */ hv_pkt_iter_close(channel); return 0;} /* * Determine number of bytes available in ring buffer after * the current iterator (priv_read_index) location. * * This is similar to hv_get_bytes_to_read but with private * read index instead. */static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi){ u32 priv_read_loc = rbi->priv_read_index; u32 write_loc; /* * The Hyper-V host writes the packet data, then uses * store_release() to update the write_index. Use load_acquire() * here to prevent loads of the packet data from being re-ordered * before the read of the write_index and potentially getting * stale data. */ write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; else return (rbi->ring_datasize - priv_read_loc) + write_loc;} /* * Get first vmbus packet from ring buffer after read_index * * If ring buffer is empty, returns NULL and no other action needed. */struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel){ struct hv_ring_buffer_info *rbi = &channel->inbound; struct vmpacket_descriptor *desc, *desc_copy; u32 bytes_avail, pkt_len, pkt_offset; hv_debug_delay_test(channel, MESSAGE_DELAY); bytes_avail = hv_pkt_iter_avail(rbi); if (bytes_avail < sizeof(struct vmpacket_descriptor)) return NULL; bytes_avail = min(rbi->pkt_buffer_size, bytes_avail); desc = (struct vmpacket_descriptor *)(hv_get_ring_buffer(rbi) + rbi->priv_read_index); /* * Ensure the compiler does not use references to incoming Hyper-V values (which * could change at any moment) when reading local variables later in the code */ pkt_len = READ_ONCE(desc->len8) << 3; pkt_offset = READ_ONCE(desc->offset8) << 3; /* * If pkt_len is invalid, set it to the smaller of hv_pkt_iter_avail() and * rbi->pkt_buffer_size */ if (pkt_len < sizeof(struct vmpacket_descriptor) || pkt_len > bytes_avail) pkt_len = bytes_avail; /* * If pkt_offset is invalid, arbitrarily set it to * the size of vmpacket_descriptor */ if (pkt_offset < sizeof(struct vmpacket_descriptor) || pkt_offset > pkt_len) pkt_offset = sizeof(struct vmpacket_descriptor); /* Copy the Hyper-V packet out of the ring buffer */ desc_copy = (struct vmpacket_descriptor *)rbi->pkt_buffer;Lines 1–500 of 654. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (c) 2009, Microsoft Corporation. * * Authors: * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * K. Y. Srinivasan <kys@microsoft.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/hyperv.h> #include <linux/uio.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/prefetch.h> #include <linux/io.h> #include <asm/mshyperv.h> #include "hyperv_vmbus.h" #define VMBUS_PKT_TRAILER 8 /* * When we write to the ring buffer, check if the host needs to * be signaled. Here is the details of this protocol: * * 1. The host guarantees that while it is draining the * ring buffer, it will set the interrupt_mask to * indicate it does not need to be interrupted when * new data is placed. * * 2. The host guarantees that it will completely drain * the ring buffer before exiting the read loop. Further, * 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 void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->outbound; virt_mb(); if (READ_ONCE(rbi->ring_buffer->interrupt_mask)) return; /* check interrupt_mask before read_index */ virt_rmb(); /* * This is the only case we need to signal when the * ring transitions from being empty to non-empty. */ if (old_write == READ_ONCE(rbi->ring_buffer->read_index)) { ++channel->intr_out_empty; vmbus_setevent(channel); } } /* Get the next write location for the specified ring buffer. */ static inline u32 hv_get_next_write_location(struct hv_ring_buffer_info *ring_info) { u32 next = ring_info->ring_buffer->write_index; return next; } /* Set the next write location for the specified ring buffer. */ static inline void hv_set_next_write_location(struct hv_ring_buffer_info *ring_info, u32 next_write_location) { ring_info->ring_buffer->write_index = next_write_location; } /* Get the size of the ring buffer. */ static inline u32 hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info) { return ring_info->ring_datasize; } /* Get the read and write indices as u64 of the specified ring buffer. */ static inline u64 hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info) { return (u64)ring_info->ring_buffer->write_index << 32; } /* * Helper routine to copy from source to ring buffer. * Assume there is enough room. Handles wrap-around in dest case only!! */ static u32 hv_copyto_ringbuffer( struct hv_ring_buffer_info *ring_info, u32 start_write_offset, const void *src, u32 srclen) { void *ring_buffer = hv_get_ring_buffer(ring_info); u32 ring_buffer_size = hv_get_ring_buffersize(ring_info); memcpy(ring_buffer + start_write_offset, src, srclen); start_write_offset += srclen; if (start_write_offset >= ring_buffer_size) start_write_offset -= ring_buffer_size; return start_write_offset; } /* * * hv_get_ringbuffer_availbytes() * * Get number of bytes available to read and to write to * for the specified ring buffer */ static void hv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi, u32 *read, u32 *write) { u32 read_loc, write_loc, dsize; /* Capture the read/write indices before they changed */ read_loc = READ_ONCE(rbi->ring_buffer->read_index); write_loc = READ_ONCE(rbi->ring_buffer->write_index); dsize = rbi->ring_datasize; *write = write_loc >= read_loc ? dsize - (write_loc - read_loc) : read_loc - write_loc; *read = dsize - *write; } /* Get various debug metrics for the specified ring buffer. */ int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info) { u32 bytes_avail_towrite; u32 bytes_avail_toread; mutex_lock(&ring_info->ring_buffer_mutex); if (!ring_info->ring_buffer) { mutex_unlock(&ring_info->ring_buffer_mutex); return -EINVAL; } hv_get_ringbuffer_availbytes(ring_info, &bytes_avail_toread, &bytes_avail_towrite); debug_info->bytes_avail_toread = bytes_avail_toread; debug_info->bytes_avail_towrite = bytes_avail_towrite; debug_info->current_read_index = ring_info->ring_buffer->read_index; debug_info->current_write_index = ring_info->ring_buffer->write_index; debug_info->current_interrupt_mask = ring_info->ring_buffer->interrupt_mask; mutex_unlock(&ring_info->ring_buffer_mutex); return 0; } EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo); /* Initialize a channel's ring buffer info mutex locks */ void hv_ringbuffer_pre_init(struct vmbus_channel *channel) { mutex_init(&channel->inbound.ring_buffer_mutex); mutex_init(&channel->outbound.ring_buffer_mutex); } /* Initialize the ring buffer. */ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, struct page *pages, u32 page_cnt, u32 max_pkt_size) { struct page **pages_wraparound; int i; BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE)); /* * First page holds struct hv_ring_buffer, do wraparound mapping for * the rest. */ pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *), GFP_KERNEL); if (!pages_wraparound) return -ENOMEM; pages_wraparound[0] = pages; for (i = 0; i < 2 * (page_cnt - 1); i++) pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1]; ring_info->ring_buffer = (struct hv_ring_buffer *) vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, pgprot_decrypted(PAGE_KERNEL)); kfree(pages_wraparound); if (!ring_info->ring_buffer) return -ENOMEM; /* * Ensure the header page is zero'ed since * encryption status may have changed. */ memset(ring_info->ring_buffer, 0, HV_HYP_PAGE_SIZE); ring_info->ring_buffer->read_index = ring_info->ring_buffer->write_index = 0; /* Set the feature bit for enabling flow control. */ ring_info->ring_buffer->feature_bits.value = 1; ring_info->ring_size = page_cnt << PAGE_SHIFT; ring_info->ring_size_div10_reciprocal = reciprocal_value(ring_info->ring_size / 10); ring_info->ring_datasize = ring_info->ring_size - sizeof(struct hv_ring_buffer); ring_info->priv_read_index = 0; /* Initialize buffer that holds copies of incoming packets */ if (max_pkt_size) { ring_info->pkt_buffer = kzalloc(max_pkt_size, GFP_KERNEL); if (!ring_info->pkt_buffer) return -ENOMEM; ring_info->pkt_buffer_size = max_pkt_size; } spin_lock_init(&ring_info->ring_lock); return 0; } /* Cleanup the ring buffer. */ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) { mutex_lock(&ring_info->ring_buffer_mutex); vunmap(ring_info->ring_buffer); ring_info->ring_buffer = NULL; mutex_unlock(&ring_info->ring_buffer_mutex); kfree(ring_info->pkt_buffer); ring_info->pkt_buffer = NULL; ring_info->pkt_buffer_size = 0; } /* * Check if the ring buffer spinlock is available to take or not; used on * atomic contexts, like panic path (see the Hyper-V framebuffer driver). */ bool hv_ringbuffer_spinlock_busy(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rinfo = &channel->outbound; return spin_is_locked(&rinfo->ring_lock); } EXPORT_SYMBOL_GPL(hv_ringbuffer_spinlock_busy); /* Write to the ring buffer. */ int hv_ringbuffer_write(struct vmbus_channel *channel, const struct kvec *kv_list, u32 kv_count, u64 requestid, u64 *trans_id) { int i; u32 bytes_avail_towrite; u32 totalbytes_towrite = sizeof(u64); u32 next_write_location; u32 old_write; u64 prev_indices; unsigned long flags; struct hv_ring_buffer_info *outring_info = &channel->outbound; struct vmpacket_descriptor *desc = kv_list[0].iov_base; u64 __trans_id, rqst_id = VMBUS_NO_RQSTOR; if (channel->rescind) return -ENODEV; for (i = 0; i < kv_count; i++) totalbytes_towrite += kv_list[i].iov_len; spin_lock_irqsave(&outring_info->ring_lock, flags); bytes_avail_towrite = hv_get_bytes_to_write(outring_info); /* * If there is only room for the packet, assume it is full. * Otherwise, the next time around, we think the ring buffer * is empty since the read index == write index. */ if (bytes_avail_towrite <= totalbytes_towrite) { ++channel->out_full_total; if (!channel->out_full_flag) { ++channel->out_full_first; channel->out_full_flag = true; } spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; } channel->out_full_flag = false; /* Write to the ring buffer */ next_write_location = hv_get_next_write_location(outring_info); old_write = next_write_location; for (i = 0; i < kv_count; i++) { next_write_location = hv_copyto_ringbuffer(outring_info, next_write_location, kv_list[i].iov_base, kv_list[i].iov_len); } /* * Allocate the request ID after the data has been copied into the * ring buffer. Once this request ID is allocated, the completion * path could find the data and free it. */ if (desc->flags == VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED) { if (channel->next_request_id_callback != NULL) { rqst_id = channel->next_request_id_callback(channel, requestid); if (rqst_id == VMBUS_RQST_ERROR) { spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; } } } desc = hv_get_ring_buffer(outring_info) + old_write; __trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id; /* * Ensure the compiler doesn't generate code that reads the value of * the transaction ID from the ring buffer, which is shared with the * Hyper-V host and subject to being changed at any time. */ WRITE_ONCE(desc->trans_id, __trans_id); if (trans_id) *trans_id = __trans_id; /* Set previous packet start */ prev_indices = hv_get_ring_bufferindices(outring_info); next_write_location = hv_copyto_ringbuffer(outring_info, next_write_location, &prev_indices, sizeof(u64)); /* Issue a full memory barrier before updating the write index */ virt_mb(); /* Now, update the write location */ hv_set_next_write_location(outring_info, next_write_location); spin_unlock_irqrestore(&outring_info->ring_lock, flags); hv_signal_on_write(old_write, channel); if (channel->rescind) { if (rqst_id != VMBUS_NO_RQSTOR) { /* Reclaim request ID to avoid leak of IDs */ if (channel->request_addr_callback != NULL) channel->request_addr_callback(channel, rqst_id); } return -ENODEV; } return 0; } int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, u64 *requestid, bool raw) { struct vmpacket_descriptor *desc; u32 packetlen, offset; if (unlikely(buflen == 0)) return -EINVAL; *buffer_actual_len = 0; *requestid = 0; /* Make sure there is something to read */ desc = hv_pkt_iter_first(channel); if (desc == NULL) { /* * No error is set when there is even no header, drivers are * supposed to analyze buffer_actual_len. */ return 0; } offset = raw ? 0 : (desc->offset8 << 3); packetlen = (desc->len8 << 3) - offset; *buffer_actual_len = packetlen; *requestid = desc->trans_id; if (unlikely(packetlen > buflen)) return -ENOBUFS; /* since ring is double mapped, only one copy is necessary */ memcpy(buffer, (const char *)desc + offset, packetlen); /* Advance ring index to next packet descriptor */ __hv_pkt_iter_next(channel, desc); /* Notify host of update */ hv_pkt_iter_close(channel); return 0; } /* * Determine number of bytes available in ring buffer after * the current iterator (priv_read_index) location. * * This is similar to hv_get_bytes_to_read but with private * read index instead. */ static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) { u32 priv_read_loc = rbi->priv_read_index; u32 write_loc; /* * The Hyper-V host writes the packet data, then uses * store_release() to update the write_index. Use load_acquire() * here to prevent loads of the packet data from being re-ordered * before the read of the write_index and potentially getting * stale data. */ write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; else return (rbi->ring_datasize - priv_read_loc) + write_loc; } /* * Get first vmbus packet from ring buffer after read_index * * If ring buffer is empty, returns NULL and no other action needed. */ struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->inbound; struct vmpacket_descriptor *desc, *desc_copy; u32 bytes_avail, pkt_len, pkt_offset; hv_debug_delay_test(channel, MESSAGE_DELAY); bytes_avail = hv_pkt_iter_avail(rbi); if (bytes_avail < sizeof(struct vmpacket_descriptor)) return NULL; bytes_avail = min(rbi->pkt_buffer_size, bytes_avail); desc = (struct vmpacket_descriptor *)(hv_get_ring_buffer(rbi) + rbi->priv_read_index); /* * Ensure the compiler does not use references to incoming Hyper-V values (which * could change at any moment) when reading local variables later in the code */ pkt_len = READ_ONCE(desc->len8) << 3; pkt_offset = READ_ONCE(desc->offset8) << 3; /* * If pkt_len is invalid, set it to the smaller of hv_pkt_iter_avail() and * rbi->pkt_buffer_size */ if (pkt_len < sizeof(struct vmpacket_descriptor) || pkt_len > bytes_avail) pkt_len = bytes_avail; /* * If pkt_offset is invalid, arbitrarily set it to * the size of vmpacket_descriptor */ if (pkt_offset < sizeof(struct vmpacket_descriptor) || pkt_offset > pkt_len) pkt_offset = sizeof(struct vmpacket_descriptor); /* Copy the Hyper-V packet out of the ring buffer */ desc_copy = (struct vmpacket_descriptor *)rbi->pkt_buffer;