diff options
author | Linus Torvalds | 2020-12-16 11:49:46 -0800 |
---|---|---|
committer | Linus Torvalds | 2020-12-16 11:49:46 -0800 |
commit | 571b12dd1ad41f371448b693c0bd2e64968c7af4 (patch) | |
tree | 6d8450241759ed4f8f965eaf24a56facdb1759b1 /drivers/hv | |
parent | e994cc240a3b75744c33ca9b8d74f71f0fcd8852 (diff) | |
parent | d1df458cbfdb0c3384c03c7fbcb1689bc02a746c (diff) |
Merge tag 'hyperv-next-signed-20201214' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux
Pull Hyper-V updates from Wei Liu:
- harden VMBus (Andres Beltran)
- clean up VMBus driver (Matheus Castello)
- fix hv_balloon reporting (Vitaly Kuznetsov)
- fix a potential OOB issue (Andrea Parri)
- remove an obsolete TODO item (Stefan Eschenbacher)
* tag 'hyperv-next-signed-20201214' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
hv_balloon: do adjust_managed_page_count() when ballooning/un-ballooning
hv_balloon: simplify math in alloc_balloon_pages()
drivers/hv: remove obsolete TODO and fix misleading typo in comment
drivers: hv: vmbus: Fix checkpatch SPLIT_STRING
hv_netvsc: Validate number of allocated sub-channels
drivers: hv: vmbus: Fix call msleep using < 20ms
drivers: hv: vmbus: Fix checkpatch LINE_SPACING
drivers: hv: vmbus: Replace symbolic permissions by octal permissions
drivers: hv: Fix hyperv_record_panic_msg path on comment
hv_netvsc: Use vmbus_requestor to generate transaction IDs for VMBus hardening
scsi: storvsc: Use vmbus_requestor to generate transaction IDs for VMBus hardening
Drivers: hv: vmbus: Add vmbus_requestor data structure for VMBus hardening
Diffstat (limited to 'drivers/hv')
-rw-r--r-- | drivers/hv/channel.c | 174 | ||||
-rw-r--r-- | drivers/hv/hv_balloon.c | 5 | ||||
-rw-r--r-- | drivers/hv/hyperv_vmbus.h | 6 | ||||
-rw-r--r-- | drivers/hv/ring_buffer.c | 29 | ||||
-rw-r--r-- | drivers/hv/vmbus_drv.c | 52 |
5 files changed, 232 insertions, 34 deletions
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index fbdda9938039..6fb0c76bfbf8 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -503,6 +503,70 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } EXPORT_SYMBOL_GPL(vmbus_establish_gpadl); +/** + * request_arr_init - Allocates memory for the requestor array. Each slot + * keeps track of the next available slot in the array. Initially, each + * slot points to the next one (as in a Linked List). The last slot + * does not point to anything, so its value is U64_MAX by default. + * @size The size of the array + */ +static u64 *request_arr_init(u32 size) +{ + int i; + u64 *req_arr; + + req_arr = kcalloc(size, sizeof(u64), GFP_KERNEL); + if (!req_arr) + return NULL; + + for (i = 0; i < size - 1; i++) + req_arr[i] = i + 1; + + /* Last slot (no more available slots) */ + req_arr[i] = U64_MAX; + + return req_arr; +} + +/* + * vmbus_alloc_requestor - Initializes @rqstor's fields. + * Index 0 is the first free slot + * @size: Size of the requestor array + */ +static int vmbus_alloc_requestor(struct vmbus_requestor *rqstor, u32 size) +{ + u64 *rqst_arr; + unsigned long *bitmap; + + rqst_arr = request_arr_init(size); + if (!rqst_arr) + return -ENOMEM; + + bitmap = bitmap_zalloc(size, GFP_KERNEL); + if (!bitmap) { + kfree(rqst_arr); + return -ENOMEM; + } + + rqstor->req_arr = rqst_arr; + rqstor->req_bitmap = bitmap; + rqstor->size = size; + rqstor->next_request_id = 0; + spin_lock_init(&rqstor->req_lock); + + return 0; +} + +/* + * vmbus_free_requestor - Frees memory allocated for @rqstor + * @rqstor: Pointer to the requestor struct + */ +static void vmbus_free_requestor(struct vmbus_requestor *rqstor) +{ + kfree(rqstor->req_arr); + bitmap_free(rqstor->req_bitmap); +} + static int __vmbus_open(struct vmbus_channel *newchannel, void *userdata, u32 userdatalen, void (*onchannelcallback)(void *context), void *context) @@ -523,6 +587,12 @@ static int __vmbus_open(struct vmbus_channel *newchannel, if (newchannel->state != CHANNEL_OPEN_STATE) return -EINVAL; + /* Create and init requestor */ + if (newchannel->rqstor_size) { + if (vmbus_alloc_requestor(&newchannel->requestor, newchannel->rqstor_size)) + return -ENOMEM; + } + newchannel->state = CHANNEL_OPENING_STATE; newchannel->onchannel_callback = onchannelcallback; newchannel->channel_callback_context = context; @@ -626,6 +696,7 @@ error_free_gpadl: error_clean_ring: hv_ringbuffer_cleanup(&newchannel->outbound); hv_ringbuffer_cleanup(&newchannel->inbound); + vmbus_free_requestor(&newchannel->requestor); newchannel->state = CHANNEL_OPEN_STATE; return err; } @@ -808,6 +879,9 @@ static int vmbus_close_internal(struct vmbus_channel *channel) channel->ringbuffer_gpadlhandle = 0; } + if (!ret) + vmbus_free_requestor(&channel->requestor); + return ret; } @@ -888,7 +962,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, /* in 8-bytes granularity */ desc.offset8 = sizeof(struct vmpacket_descriptor) >> 3; desc.len8 = (u16)(packetlen_aligned >> 3); - desc.trans_id = requestid; + desc.trans_id = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ bufferlist[0].iov_base = &desc; bufferlist[0].iov_len = sizeof(struct vmpacket_descriptor); @@ -897,7 +971,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - return hv_ringbuffer_write(channel, bufferlist, num_vecs); + return hv_ringbuffer_write(channel, bufferlist, num_vecs, requestid); } EXPORT_SYMBOL(vmbus_sendpacket); @@ -939,7 +1013,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, desc.flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; desc.dataoffset8 = descsize >> 3; /* in 8-bytes granularity */ desc.length8 = (u16)(packetlen_aligned >> 3); - desc.transactionid = requestid; + desc.transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc.reserved = 0; desc.rangecount = pagecount; @@ -956,7 +1030,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - return hv_ringbuffer_write(channel, bufferlist, 3); + return hv_ringbuffer_write(channel, bufferlist, 3, requestid); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer); @@ -983,7 +1057,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, desc->flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED; desc->dataoffset8 = desc_size >> 3; /* in 8-bytes granularity */ desc->length8 = (u16)(packetlen_aligned >> 3); - desc->transactionid = requestid; + desc->transactionid = VMBUS_RQST_ERROR; /* will be updated in hv_ringbuffer_write() */ desc->reserved = 0; desc->rangecount = 1; @@ -994,7 +1068,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - return hv_ringbuffer_write(channel, bufferlist, 3); + return hv_ringbuffer_write(channel, bufferlist, 3, requestid); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc); @@ -1042,3 +1116,91 @@ int vmbus_recvpacket_raw(struct vmbus_channel *channel, void *buffer, buffer_actual_len, requestid, true); } EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw); + +/* + * vmbus_next_request_id - Returns a new request id. It is also + * the index at which the guest memory address is stored. + * Uses a spin lock to avoid race conditions. + * @rqstor: Pointer to the requestor struct + * @rqst_add: Guest memory address to be stored in the array + */ +u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr) +{ + unsigned long flags; + u64 current_id; + const struct vmbus_channel *channel = + container_of(rqstor, const struct vmbus_channel, requestor); + + /* Check rqstor has been initialized */ + if (!channel->rqstor_size) + return VMBUS_NO_RQSTOR; + + spin_lock_irqsave(&rqstor->req_lock, flags); + current_id = rqstor->next_request_id; + + /* Requestor array is full */ + if (current_id >= rqstor->size) { + spin_unlock_irqrestore(&rqstor->req_lock, flags); + return VMBUS_RQST_ERROR; + } + + rqstor->next_request_id = rqstor->req_arr[current_id]; + rqstor->req_arr[current_id] = rqst_addr; + + /* The already held spin lock provides atomicity */ + bitmap_set(rqstor->req_bitmap, current_id, 1); + + spin_unlock_irqrestore(&rqstor->req_lock, flags); + + /* + * Cannot return an ID of 0, which is reserved for an unsolicited + * message from Hyper-V. + */ + return current_id + 1; +} +EXPORT_SYMBOL_GPL(vmbus_next_request_id); + +/* + * vmbus_request_addr - Returns the memory address stored at @trans_id + * in @rqstor. Uses a spin lock to avoid race conditions. + * @rqstor: Pointer to the requestor struct + * @trans_id: Request id sent back from Hyper-V. Becomes the requestor's + * next request id. + */ +u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id) +{ + unsigned long flags; + u64 req_addr; + const struct vmbus_channel *channel = + container_of(rqstor, const struct vmbus_channel, requestor); + + /* Check rqstor has been initialized */ + if (!channel->rqstor_size) + return VMBUS_NO_RQSTOR; + + /* Hyper-V can send an unsolicited message with ID of 0 */ + if (!trans_id) + return trans_id; + + spin_lock_irqsave(&rqstor->req_lock, flags); + + /* Data corresponding to trans_id is stored at trans_id - 1 */ + trans_id--; + + /* Invalid trans_id */ + if (trans_id >= rqstor->size || !test_bit(trans_id, rqstor->req_bitmap)) { + spin_unlock_irqrestore(&rqstor->req_lock, flags); + return VMBUS_RQST_ERROR; + } + + req_addr = rqstor->req_arr[trans_id]; + rqstor->req_arr[trans_id] = rqstor->next_request_id; + rqstor->next_request_id = trans_id; + + /* The already held spin lock provides atomicity */ + bitmap_clear(rqstor->req_bitmap, trans_id, 1); + + spin_unlock_irqrestore(&rqstor->req_lock, flags); + return req_addr; +} +EXPORT_SYMBOL_GPL(vmbus_request_addr); diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index eb56e09ae15f..8c471823a5af 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1198,6 +1198,7 @@ static void free_balloon_pages(struct hv_dynmem_device *dm, __ClearPageOffline(pg); __free_page(pg); dm->num_pages_ballooned--; + adjust_managed_page_count(pg, 1); } } @@ -1238,8 +1239,10 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, split_page(pg, get_order(alloc_unit << PAGE_SHIFT)); /* mark all pages offline */ - for (j = 0; j < (1 << get_order(alloc_unit << PAGE_SHIFT)); j++) + for (j = 0; j < alloc_unit; j++) { __SetPageOffline(pg + j); + adjust_managed_page_count(pg + j, -1); + } bl_resp->range_count++; bl_resp->range_array[i].finfo.start_page = diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 40e2b9f91163..9416e09ebd58 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -179,21 +179,21 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info); int hv_ringbuffer_write(struct vmbus_channel *channel, - const struct kvec *kv_list, u32 kv_count); + const struct kvec *kv_list, u32 kv_count, + u64 requestid); int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, u64 *requestid, bool raw); /* - * The Maximum number of channels (16348) is determined by the size of the + * The Maximum number of channels (16384) is determined by the size of the * interrupt page, which is HV_HYP_PAGE_SIZE. 1/2 of HV_HYP_PAGE_SIZE is to * send endpoint interrupts, and the other is to receive endpoint interrupts. */ #define MAX_NUM_CHANNELS ((HV_HYP_PAGE_SIZE >> 1) << 3) /* The value here must be in multiple of 32 */ -/* TODO: Need to make this configurable */ #define MAX_NUM_CHANNELS_SUPPORTED 256 #define MAX_CHANNEL_RELIDS \ diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 356e22159e83..35833d4d1a1d 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -248,7 +248,8 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) /* Write to the ring buffer. */ int hv_ringbuffer_write(struct vmbus_channel *channel, - const struct kvec *kv_list, u32 kv_count) + const struct kvec *kv_list, u32 kv_count, + u64 requestid) { int i; u32 bytes_avail_towrite; @@ -258,6 +259,8 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, 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 rqst_id = VMBUS_NO_RQSTOR; if (channel->rescind) return -ENODEV; @@ -300,6 +303,23 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, 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) { + rqst_id = vmbus_next_request_id(&channel->requestor, requestid); + if (rqst_id == VMBUS_RQST_ERROR) { + spin_unlock_irqrestore(&outring_info->ring_lock, flags); + pr_err("No request id available\n"); + return -EAGAIN; + } + } + desc = hv_get_ring_buffer(outring_info) + old_write; + desc->trans_id = (rqst_id == VMBUS_NO_RQSTOR) ? requestid : rqst_id; + /* Set previous packet start */ prev_indices = hv_get_ring_bufferindices(outring_info); @@ -319,8 +339,13 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, hv_signal_on_write(old_write, channel); - if (channel->rescind) + if (channel->rescind) { + if (rqst_id != VMBUS_NO_RQSTOR) { + /* Reclaim request ID to avoid leak of IDs */ + vmbus_request_addr(&channel->requestor, rqst_id); + } return -ENODEV; + } return 0; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 4fad3e6745e5..502f8cd95f6d 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -55,7 +55,7 @@ int vmbus_interrupt; /* * Boolean to control whether to report panic messages over Hyper-V. * - * It can be set via /proc/sys/kernel/hyperv/record_panic_msg + * It can be set via /proc/sys/kernel/hyperv_record_panic_msg */ static int sysctl_record_panic_msg = 1; @@ -156,6 +156,7 @@ static u32 channel_conn_id(struct vmbus_channel *channel, { u8 monitor_group = channel_monitor_group(channel); u8 monitor_offset = channel_monitor_offset(channel); + return monitor_page->parameter[monitor_group][monitor_offset].connectionid.u.id; } @@ -550,6 +551,7 @@ static ssize_t vendor_show(struct device *dev, char *buf) { struct hv_device *hv_dev = device_to_hv_device(dev); + return sprintf(buf, "0x%x\n", hv_dev->vendor_id); } static DEVICE_ATTR_RO(vendor); @@ -559,6 +561,7 @@ static ssize_t device_show(struct device *dev, char *buf) { struct hv_device *hv_dev = device_to_hv_device(dev); + return sprintf(buf, "0x%x\n", hv_dev->device_id); } static DEVICE_ATTR_RO(device); @@ -1384,6 +1387,24 @@ static struct kmsg_dumper hv_kmsg_dumper = { .dump = hv_kmsg_dump, }; +static void hv_kmsg_dump_register(void) +{ + int ret; + + hv_panic_page = hv_alloc_hyperv_zeroed_page(); + if (!hv_panic_page) { + pr_err("Hyper-V: panic message page memory allocation failed\n"); + return; + } + + ret = kmsg_dump_register(&hv_kmsg_dumper); + if (ret) { + pr_err("Hyper-V: kmsg dump register error 0x%x\n", ret); + hv_free_hyperv_page((unsigned long)hv_panic_page); + hv_panic_page = NULL; + } +} + static struct ctl_table_header *hv_ctl_table_hdr; /* @@ -1474,21 +1495,8 @@ static int vmbus_bus_init(void) * capability is supported by the hypervisor. */ hv_get_crash_ctl(hyperv_crash_ctl); - if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) { - hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page(); - if (hv_panic_page) { - ret = kmsg_dump_register(&hv_kmsg_dumper); - if (ret) { - pr_err("Hyper-V: kmsg dump register " - "error 0x%x\n", ret); - hv_free_hyperv_page( - (unsigned long)hv_panic_page); - hv_panic_page = NULL; - } - } else - pr_err("Hyper-V: panic message page memory " - "allocation failed"); - } + if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) + hv_kmsg_dump_register(); register_die_notifier(&hyperv_die_block); } @@ -1812,7 +1820,7 @@ static ssize_t channel_pending_show(struct vmbus_channel *channel, channel_pending(channel, vmbus_connection.monitor_pages[1])); } -static VMBUS_CHAN_ATTR(pending, S_IRUGO, channel_pending_show, NULL); +static VMBUS_CHAN_ATTR(pending, 0444, channel_pending_show, NULL); static ssize_t channel_latency_show(struct vmbus_channel *channel, char *buf) @@ -1821,19 +1829,19 @@ static ssize_t channel_latency_show(struct vmbus_channel *channel, channel_latency(channel, vmbus_connection.monitor_pages[1])); } -static VMBUS_CHAN_ATTR(latency, S_IRUGO, channel_latency_show, NULL); +static VMBUS_CHAN_ATTR(latency, 0444, channel_latency_show, NULL); static ssize_t channel_interrupts_show(struct vmbus_channel *channel, char *buf) { return sprintf(buf, "%llu\n", channel->interrupts); } -static VMBUS_CHAN_ATTR(interrupts, S_IRUGO, channel_interrupts_show, NULL); +static VMBUS_CHAN_ATTR(interrupts, 0444, channel_interrupts_show, NULL); static ssize_t channel_events_show(struct vmbus_channel *channel, char *buf) { return sprintf(buf, "%llu\n", channel->sig_events); } -static VMBUS_CHAN_ATTR(events, S_IRUGO, channel_events_show, NULL); +static VMBUS_CHAN_ATTR(events, 0444, channel_events_show, NULL); static ssize_t channel_intr_in_full_show(struct vmbus_channel *channel, char *buf) @@ -1872,7 +1880,7 @@ static ssize_t subchannel_monitor_id_show(struct vmbus_channel *channel, { return sprintf(buf, "%u\n", channel->offermsg.monitorid); } -static VMBUS_CHAN_ATTR(monitor_id, S_IRUGO, subchannel_monitor_id_show, NULL); +static VMBUS_CHAN_ATTR(monitor_id, 0444, subchannel_monitor_id_show, NULL); static ssize_t subchannel_id_show(struct vmbus_channel *channel, char *buf) @@ -2377,7 +2385,7 @@ static int vmbus_bus_suspend(struct device *dev) * We wait here until the completion of any channel * offers that are currently in progress. */ - msleep(1); + usleep_range(1000, 2000); } mutex_lock(&vmbus_connection.channel_mutex); |