cregit-Linux how code gets into the kernel

Release 4.17 drivers/hv/ring_buffer.c

Directory: drivers/hv
/*
 *
 * Copyright (c) 2009, Microsoft Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
 * Place - Suite 330, Boston, MA 02111-1307 USA.
 *
 * 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 "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)) vmbus_setevent(channel); }

Contributors

PersonTokensPropCommitsCommitProp
K. Y. Srinivasan5995.16%583.33%
Jason (Hui) Wang34.84%116.67%
Total62100.00%6100.00%

/* 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; }

Contributors

PersonTokensPropCommitsCommitProp
Hank Janssen1562.50%116.67%
Haiyang Zhang416.67%233.33%
Greg Kroah-Hartman416.67%233.33%
K. Y. Srinivasan14.17%116.67%
Total24100.00%6100.00%

/* 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; }

Contributors

PersonTokensPropCommitsCommitProp
Hank Janssen1356.52%116.67%
Haiyang Zhang626.09%233.33%
Greg Kroah-Hartman313.04%233.33%
K. Y. Srinivasan14.35%116.67%
Total23100.00%6100.00%

/* Set the next read location for the specified ring buffer. */
static inline void hv_set_next_read_location(struct hv_ring_buffer_info *ring_info, u32 next_read_location) { ring_info->ring_buffer->read_index = next_read_location; ring_info->priv_read_index = next_read_location; }

Contributors

PersonTokensPropCommitsCommitProp
Hank Janssen1344.83%114.29%
K. Y. Srinivasan724.14%228.57%
Haiyang Zhang620.69%228.57%
Greg Kroah-Hartman310.34%228.57%
Total29100.00%7100.00%

/* 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; }

Contributors

PersonTokensPropCommitsCommitProp
Hank Janssen1055.56%114.29%
Greg Kroah-Hartman316.67%228.57%
Haiyang Zhang316.67%228.57%
K. Y. Srinivasan15.56%114.29%
Stephen Hemminger15.56%114.29%
Total18100.00%7100.00%

/* 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; }

Contributors

PersonTokensPropCommitsCommitProp
Hank Janssen1562.50%116.67%
Haiyang Zhang416.67%233.33%
Greg Kroah-Hartman416.67%233.33%
K. Y. Srinivasan14.17%116.67%
Total24100.00%6100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
K. Y. Srinivasan4668.66%222.22%
Stephen Hemminger811.94%222.22%
Hank Janssen68.96%111.11%
Greg Kroah-Hartman68.96%333.33%
Haiyang Zhang11.49%111.11%
Total67100.00%9100.00%

/* * * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Stephen Hemminger83100.00%1100.00%
Total83100.00%1100.00%

/* Get various debug metrics for the specified ring buffer. */
void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info) { u32 bytes_avail_towrite; u32 bytes_avail_toread; if (ring_info->ring_buffer) { 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; } }

Contributors

PersonTokensPropCommitsCommitProp
Hank Janssen4351.81%110.00%
Haiyang Zhang2428.92%220.00%
Greg Kroah-Hartman1315.66%440.00%
K. Y. Srinivasan22.41%220.00%
Stephen Hemminger11.20%110.00%
Total83100.00%10100.00%

EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo); /* Initialize the ring buffer. */
int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, struct page *pages, u32 page_cnt) { int i; struct page **pages_wraparound; BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE)); memset(ring_info, 0, sizeof(struct hv_ring_buffer_info)); /* * First page holds struct hv_ring_buffer, do wraparound mapping for * the rest. */ pages_wraparound = kzalloc(sizeof(struct page *) * (page_cnt * 2 - 1), 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, PAGE_KERNEL); kfree(pages_wraparound); if (!ring_info->ring_buffer) return -ENOMEM; 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_datasize = ring_info->ring_size - sizeof(struct hv_ring_buffer); spin_lock_init(&ring_info->ring_lock); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Vitaly Kuznetsov13558.70%215.38%
Hank Janssen5122.17%17.69%
Greg Kroah-Hartman177.39%538.46%
Haiyang Zhang156.52%215.38%
K. Y. Srinivasan114.78%215.38%
Bill Pemberton10.43%17.69%
Total230100.00%13100.00%

/* Cleanup the ring buffer. */
void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) { vunmap(ring_info->ring_buffer); }

Contributors

PersonTokensPropCommitsCommitProp
Vitaly Kuznetsov952.94%116.67%
Greg Kroah-Hartman317.65%233.33%
Hank Janssen317.65%116.67%
K. Y. Srinivasan15.88%116.67%
Haiyang Zhang15.88%116.67%
Total17100.00%6100.00%

/* Write to the ring buffer. */
int hv_ringbuffer_write(struct vmbus_channel *channel, const struct kvec *kv_list, u32 kv_count) { 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; 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) { spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; } /* 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); } /* 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) return -ENODEV; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
K. Y. Srinivasan10542.86%942.86%
Hank Janssen7831.84%14.76%
Greg Kroah-Hartman2711.02%523.81%
Haiyang Zhang249.80%14.76%
Stephen Hemminger52.04%29.52%
Bill Pemberton31.22%14.76%
Nicolas Palix20.82%14.76%
Vitaly Kuznetsov10.41%14.76%
Total245100.00%21100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Vitaly Kuznetsov7545.18%213.33%
Stephen Hemminger3722.29%213.33%
Hank Janssen2615.66%16.67%
K. Y. Srinivasan116.63%426.67%
Bill Pemberton74.22%16.67%
Greg Kroah-Hartman63.61%426.67%
Haiyang Zhang42.41%16.67%
Total166100.00%15100.00%

/* * 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 = READ_ONCE(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; }

Contributors

PersonTokensPropCommitsCommitProp
Stephen Hemminger54100.00%1100.00%
Total54100.00%1100.00%

/* * 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; if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) return NULL; desc = hv_get_ring_buffer(rbi) + rbi->priv_read_index; if (desc) prefetch((char *)desc + (desc->len8 << 3)); return desc; }

Contributors

PersonTokensPropCommitsCommitProp
Stephen Hemminger78100.00%2100.00%
Total78100.00%2100.00%

EXPORT_SYMBOL_GPL(hv_pkt_iter_first); /* * Get next vmbus packet from ring buffer. * * Advances the current location (priv_read_index) and checks for more * data. If the end of the ring buffer is reached, then return NULL. */
struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, const struct vmpacket_descriptor *desc) { struct hv_ring_buffer_info *rbi = &channel->inbound; u32 packetlen = desc->len8 << 3; u32 dsize = rbi->ring_datasize; /* bump offset to next potential packet */ rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER; if (rbi->priv_read_index >= dsize) rbi->priv_read_index -= dsize; /* more data? */ return hv_pkt_iter_first(channel); }

Contributors

PersonTokensPropCommitsCommitProp
Stephen Hemminger74100.00%2100.00%
Total74100.00%2100.00%

EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); /* How many bytes were read in this iterator cycle */
static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi, u32 start_read_index) { if (rbi->priv_read_index >= start_read_index) return rbi->priv_read_index - start_read_index; else return rbi->ring_datasize - start_read_index + rbi->priv_read_index; }

Contributors

PersonTokensPropCommitsCommitProp
Michael Kelley42100.00%1100.00%
Total42100.00%1100.00%

/* * Update host ring buffer after iterating over packets. */
void hv_pkt_iter_close(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->inbound; u32 curr_write_sz, pending_sz, bytes_read, start_read_index; /* * Make sure all reads are done before we update the read index since * the writer may start writing to the read area once the read index * is updated. */ virt_rmb(); start_read_index = rbi->ring_buffer->read_index; rbi->ring_buffer->read_index = rbi->priv_read_index; if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz) return; /* * Issue a full memory barrier before making the signaling decision. * Here is the reason for having this barrier: * If the reading of the pend_sz (in this function) * were to be reordered and read before we commit the new read * index (in the calling function) we could * have a problem. If the host were to set the pending_sz after we * have sampled pending_sz and go to sleep before we commit the * read index, we could miss sending the interrupt. Issue a full * memory barrier to address this. */ virt_mb(); pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); if (!pending_sz) return; /* * Ensure the read of write_index in hv_get_bytes_to_write() * happens after the read of pending_send_sz. */ virt_rmb(); curr_write_sz = hv_get_bytes_to_write(rbi); bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index); /* * If there was space before we began iteration, * then host was not blocked. */ if (curr_write_sz - bytes_read > pending_sz) return; /* If pending write will not fit, don't give false hope. */ if (curr_write_sz <= pending_sz) return; vmbus_setevent(channel); }

Contributors

PersonTokensPropCommitsCommitProp
Stephen Hemminger7256.69%375.00%
Michael Kelley5543.31%125.00%
Total127100.00%4100.00%

EXPORT_SYMBOL_GPL(hv_pkt_iter_close);

Overall Contributors

PersonTokensPropCommitsCommitProp
Stephen Hemminger44529.30%1220.00%
Hank Janssen28218.56%23.33%
K. Y. Srinivasan25416.72%2440.00%
Vitaly Kuznetsov23615.54%46.67%
Michael Kelley986.45%11.67%
Greg Kroah-Hartman966.32%1016.67%
Haiyang Zhang926.06%23.33%
Bill Pemberton110.72%35.00%
Jason (Hui) Wang30.20%11.67%
Nicolas Palix20.13%11.67%
Total1519100.00%60100.00%
Directory: drivers/hv
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.