From ba50bf1ce9a51fc97db58b96d01306aa70bc3979 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 17 Dec 2018 20:16:09 +0000 Subject: [PATCH 1/3] Drivers: hv: vmbus: Check for ring when getting debug info fc96df16a1ce is good and can already fix the "return stack garbage" issue, but let's also improve hv_ringbuffer_get_debuginfo(), which would silently return stack garbage, if people forget to check channel->state or ring_info->ring_buffer, when using the function in the future. Having an error check in the function would eliminate the potential risk. Add a Fixes tag to indicate the patch depdendency. Fixes: fc96df16a1ce ("Drivers: hv: vmbus: Return -EINVAL for the sys files for unopened channels") Cc: stable@vger.kernel.org Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Stephen Hemminger Signed-off-by: Dexuan Cui Signed-off-by: Sasha Levin --- drivers/hv/ring_buffer.c | 29 +++++++------ drivers/hv/vmbus_drv.c | 91 +++++++++++++++++++++++++++------------- include/linux/hyperv.h | 5 ++- 3 files changed, 78 insertions(+), 47 deletions(-) diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 64d0c85d5161..1f1a55e07733 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -164,26 +164,25 @@ hv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi, } /* 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) +int 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); + if (!ring_info->ring_buffer) + return -EINVAL; - 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; - } + 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; + return 0; } EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index d0ff65675292..403fee01572c 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -313,12 +313,16 @@ static ssize_t out_intr_mask_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info outbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, + &outbound); + if (ret < 0) + return ret; + return sprintf(buf, "%d\n", outbound.current_interrupt_mask); } static DEVICE_ATTR_RO(out_intr_mask); @@ -328,12 +332,15 @@ static ssize_t out_read_index_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info outbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, + &outbound); + if (ret < 0) + return ret; return sprintf(buf, "%d\n", outbound.current_read_index); } static DEVICE_ATTR_RO(out_read_index); @@ -344,12 +351,15 @@ static ssize_t out_write_index_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info outbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, + &outbound); + if (ret < 0) + return ret; return sprintf(buf, "%d\n", outbound.current_write_index); } static DEVICE_ATTR_RO(out_write_index); @@ -360,12 +370,15 @@ static ssize_t out_read_bytes_avail_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info outbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, + &outbound); + if (ret < 0) + return ret; return sprintf(buf, "%d\n", outbound.bytes_avail_toread); } static DEVICE_ATTR_RO(out_read_bytes_avail); @@ -376,12 +389,15 @@ static ssize_t out_write_bytes_avail_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info outbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, + &outbound); + if (ret < 0) + return ret; return sprintf(buf, "%d\n", outbound.bytes_avail_towrite); } static DEVICE_ATTR_RO(out_write_bytes_avail); @@ -391,12 +407,15 @@ static ssize_t in_intr_mask_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info inbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + if (ret < 0) + return ret; + return sprintf(buf, "%d\n", inbound.current_interrupt_mask); } static DEVICE_ATTR_RO(in_intr_mask); @@ -406,12 +425,15 @@ static ssize_t in_read_index_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info inbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + if (ret < 0) + return ret; + return sprintf(buf, "%d\n", inbound.current_read_index); } static DEVICE_ATTR_RO(in_read_index); @@ -421,12 +443,15 @@ static ssize_t in_write_index_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info inbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + if (ret < 0) + return ret; + return sprintf(buf, "%d\n", inbound.current_write_index); } static DEVICE_ATTR_RO(in_write_index); @@ -437,12 +462,15 @@ static ssize_t in_read_bytes_avail_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info inbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + if (ret < 0) + return ret; + return sprintf(buf, "%d\n", inbound.bytes_avail_toread); } static DEVICE_ATTR_RO(in_read_bytes_avail); @@ -453,12 +481,15 @@ static ssize_t in_write_bytes_avail_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct hv_ring_buffer_debug_info inbound; + int ret; if (!hv_dev->channel) return -ENODEV; - if (hv_dev->channel->state != CHANNEL_OPENED_STATE) - return -EINVAL; - hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + + ret = hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); + if (ret < 0) + return ret; + return sprintf(buf, "%d\n", inbound.bytes_avail_towrite); } static DEVICE_ATTR_RO(in_write_bytes_avail); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f0885cc01db6..dcb6977afce9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1159,8 +1159,9 @@ struct hv_ring_buffer_debug_info { u32 bytes_avail_towrite; }; -void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, - struct hv_ring_buffer_debug_info *debug_info); + +int hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, + struct hv_ring_buffer_debug_info *debug_info); /* Vmbus interface */ #define vmbus_driver_register(driver) \ From da8ced360ca8ad72d8f41f5c8fcd5b0e63e1555f Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 4 Jan 2019 15:19:42 +0100 Subject: [PATCH 2/3] hv_balloon: avoid touching uninitialized struct page during tail onlining Hyper-V memory hotplug protocol has 2M granularity and in Linux x86 we use 128M. To deal with it we implement partial section onlining by registering custom page onlining callback (hv_online_page()). Later, when more memory arrives we try to online the 'tail' (see hv_bring_pgs_online()). It was found that in some cases this 'tail' onlining causes issues: BUG: Bad page state in process kworker/0:2 pfn:109e3a page:ffffe08344278e80 count:0 mapcount:1 mapping:0000000000000000 index:0x0 flags: 0xfffff80000000() raw: 000fffff80000000 dead000000000100 dead000000000200 0000000000000000 raw: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 page dumped because: nonzero mapcount ... Workqueue: events hot_add_req [hv_balloon] Call Trace: dump_stack+0x5c/0x80 bad_page.cold.112+0x7f/0xb2 free_pcppages_bulk+0x4b8/0x690 free_unref_page+0x54/0x70 hv_page_online_one+0x5c/0x80 [hv_balloon] hot_add_req.cold.24+0x182/0x835 [hv_balloon] ... Turns out that we now have deferred struct page initialization for memory hotplug so e.g. memory_block_action() in drivers/base/memory.c does pages_correctly_probed() check and in that check it avoids inspecting struct pages and checks sections instead. But in Hyper-V balloon driver we do PageReserved(pfn_to_page()) check and this is now wrong. Switch to checking online_section_nr() instead. Signed-off-by: Vitaly Kuznetsov Cc: stable@kernel.org Signed-off-by: Sasha Levin --- drivers/hv/hv_balloon.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 5301fef16c31..7c6349a50ef1 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -888,12 +888,14 @@ static unsigned long handle_pg_range(unsigned long pg_start, pfn_cnt -= pgs_ol; /* * Check if the corresponding memory block is already - * online by checking its last previously backed page. - * In case it is we need to bring rest (which was not - * backed previously) online too. + * online. It is possible to observe struct pages still + * being uninitialized here so check section instead. + * In case the section is online we need to bring the + * rest of pfns (which were not backed previously) + * online too. */ if (start_pfn > has->start_pfn && - !PageReserved(pfn_to_page(start_pfn - 1))) + online_section_nr(pfn_to_section_nr(start_pfn))) hv_bring_pgs_online(has, start_pfn, pgs_ol); } From b5679cebf780c6f1c2451a73bf1842a4409840e7 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Wed, 9 Jan 2019 20:56:06 +0000 Subject: [PATCH 3/3] vmbus: fix subchannel removal The changes to split ring allocation from open/close, broke the cleanup of subchannels. This resulted in problems using uio on network devices because the subchannel was left behind when the network device was unbound. The cause was in the disconnect logic which used list splice to move the subchannel list into a local variable. This won't work because the subchannel list is needed later during the process of the rescind messages (relid2channel). The fix is to just leave the subchannel list in place which is what the original code did. The list is cleaned up later when the host rescind is processed. Without the fix, we have a lot of "hang" issues in netvsc when we try to change the NIC's MTU, set the number of channels, etc. Fixes: ae6935ed7d42 ("vmbus: split ring buffer allocation from open") Cc: stable@vger.kernel.org Signed-off-by: Stephen Hemminger Signed-off-by: Dexuan Cui Signed-off-by: Sasha Levin --- drivers/hv/channel.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index ce0ba2062723..bea4c9850247 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -701,19 +701,12 @@ static int vmbus_close_internal(struct vmbus_channel *channel) int vmbus_disconnect_ring(struct vmbus_channel *channel) { struct vmbus_channel *cur_channel, *tmp; - unsigned long flags; - LIST_HEAD(list); int ret; if (channel->primary_channel != NULL) return -EINVAL; - /* Snapshot the list of subchannels */ - spin_lock_irqsave(&channel->lock, flags); - list_splice_init(&channel->sc_list, &list); - spin_unlock_irqrestore(&channel->lock, flags); - - list_for_each_entry_safe(cur_channel, tmp, &list, sc_list) { + list_for_each_entry_safe(cur_channel, tmp, &channel->sc_list, sc_list) { if (cur_channel->rescind) wait_for_completion(&cur_channel->rescind_event);