The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 040026df7088c56ccbad28f7042308f67bde63df Mon Sep 17 00:00:00 2001
From: Tianyu Lan <Tianyu.Lan(a)microsoft.com>
Date: Mon, 6 Apr 2020 08:53:30 -0700
Subject: [PATCH] x86/Hyper-V: Report crash register data when
sysctl_record_panic_msg is not set
When sysctl_record_panic_msg is not set, the panic will
not be reported to Hyper-V via hyperv_report_panic_msg().
So the crash should be reported via hyperv_report_panic().
Fixes: 81b18bce48af ("Drivers: HV: Send one page worth of kmsg dump over Hyper-V during panic")
Reviewed-by: Michael Kelley <mikelley(a)microsoft.com>
Signed-off-by: Tianyu Lan <Tianyu.Lan(a)microsoft.com>
Link: https://lore.kernel.org/r/20200406155331.2105-6-Tianyu.Lan@microsoft.com
Signed-off-by: Wei Liu <wei.liu(a)kernel.org>
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 333dad39b1c1..172ceae69abb 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -48,6 +48,18 @@ static int hyperv_cpuhp_online;
static void *hv_panic_page;
+/*
+ * Boolean to control whether to report panic messages over Hyper-V.
+ *
+ * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
+ */
+static int sysctl_record_panic_msg = 1;
+
+static int hyperv_report_reg(void)
+{
+ return !sysctl_record_panic_msg || !hv_panic_page;
+}
+
static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
void *args)
{
@@ -61,7 +73,7 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
* the notification here.
*/
if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
- && !hv_panic_page) {
+ && hyperv_report_reg()) {
regs = current_pt_regs();
hyperv_report_panic(regs, val);
}
@@ -79,7 +91,7 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
* doing hyperv_report_panic_msg() later with kmsg data, don't do
* the notification here.
*/
- if (!hv_panic_page)
+ if (hyperv_report_reg())
hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
@@ -1267,13 +1279,6 @@ static void vmbus_isr(void)
add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
}
-/*
- * Boolean to control whether to report panic messages over Hyper-V.
- *
- * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
- */
-static int sysctl_record_panic_msg = 1;
-
/*
* Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
* buffer and call into Hyper-V to transfer the data.
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 73f26e526f19afb3a06b76b970a76bcac2cafd05 Mon Sep 17 00:00:00 2001
From: Tianyu Lan <Tianyu.Lan(a)microsoft.com>
Date: Mon, 6 Apr 2020 08:53:28 -0700
Subject: [PATCH] x86/Hyper-V: Trigger crash enlightenment only once during
system crash.
When a guest VM panics, Hyper-V should be notified only once via the
crash synthetic MSRs. Current Linux code might write these crash MSRs
twice during a system panic:
1) hyperv_panic/die_event() calling hyperv_report_panic()
2) hv_kmsg_dump() calling hyperv_report_panic_msg()
Fix this by not calling hyperv_report_panic() if a kmsg dump has been
successfully registered. The notification will happen later via
hyperv_report_panic_msg().
Fixes: 7ed4325a44ea ("Drivers: hv: vmbus: Make panic reporting to be more useful")
Reviewed-by: Michael Kelley <mikelley(a)microsoft.com>
Signed-off-by: Tianyu Lan <Tianyu.Lan(a)microsoft.com>
Link: https://lore.kernel.org/r/20200406155331.2105-4-Tianyu.Lan@microsoft.com
Signed-off-by: Wei Liu <wei.liu(a)kernel.org>
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 00a511f15926..333dad39b1c1 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -55,7 +55,13 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
vmbus_initiate_unload(true);
- if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+ /*
+ * Hyper-V should be notified only once about a panic. If we will be
+ * doing hyperv_report_panic_msg() later with kmsg data, don't do
+ * the notification here.
+ */
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
+ && !hv_panic_page) {
regs = current_pt_regs();
hyperv_report_panic(regs, val);
}
@@ -68,7 +74,13 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
struct die_args *die = (struct die_args *)args;
struct pt_regs *regs = die->regs;
- hyperv_report_panic(regs, val);
+ /*
+ * Hyper-V should be notified only once about a panic. If we will be
+ * doing hyperv_report_panic_msg() later with kmsg data, don't do
+ * the notification here.
+ */
+ if (!hv_panic_page)
+ hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 74347a99e73ae00b8385f1209aaea193c670f901 Mon Sep 17 00:00:00 2001
From: Tianyu Lan <Tianyu.Lan(a)microsoft.com>
Date: Mon, 6 Apr 2020 08:53:26 -0700
Subject: [PATCH] x86/Hyper-V: Unload vmbus channel in hv panic callback
When kdump is not configured, a Hyper-V VM might still respond to
network traffic after a kernel panic when kernel parameter panic=0.
The panic CPU goes into an infinite loop with interrupts enabled,
and the VMbus driver interrupt handler still works because the
VMbus connection is unloaded only in the kdump path. The network
responses make the other end of the connection think the VM is
still functional even though it has panic'ed, which could affect any
failover actions that should be taken.
Fix this by unloading the VMbus connection during the panic process.
vmbus_initiate_unload() could then be called twice (e.g., by
hyperv_panic_event() and hv_crash_handler(), so reset the connection
state in vmbus_initiate_unload() to ensure the unload is done only
once.
Fixes: 81b18bce48af ("Drivers: HV: Send one page worth of kmsg dump over Hyper-V during panic")
Reviewed-by: Michael Kelley <mikelley(a)microsoft.com>
Signed-off-by: Tianyu Lan <Tianyu.Lan(a)microsoft.com>
Link: https://lore.kernel.org/r/20200406155331.2105-2-Tianyu.Lan@microsoft.com
Signed-off-by: Wei Liu <wei.liu(a)kernel.org>
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 0370364169c4..501c43c5851d 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash)
{
struct vmbus_channel_message_header hdr;
+ if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
+ return;
+
/* Pre-Win2012R2 hosts don't support reconnect */
if (vmbus_proto_version < VERSION_WIN8_1)
return;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 029378c27421..6478240d11ab 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -53,9 +53,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
{
struct pt_regs *regs;
- regs = current_pt_regs();
+ vmbus_initiate_unload(true);
- hyperv_report_panic(regs, val);
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+ regs = current_pt_regs();
+ hyperv_report_panic(regs, val);
+ }
return NOTIFY_DONE;
}
@@ -1391,10 +1394,16 @@ static int vmbus_bus_init(void)
}
register_die_notifier(&hyperv_die_block);
- atomic_notifier_chain_register(&panic_notifier_list,
- &hyperv_panic_block);
}
+ /*
+ * Always register the panic notifier because we need to unload
+ * the VMbus channel connection to prevent any VMbus
+ * activity after the VM panics.
+ */
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &hyperv_panic_block);
+
vmbus_request_offers();
return 0;
@@ -2204,8 +2213,6 @@ static int vmbus_bus_suspend(struct device *dev)
vmbus_initiate_unload(false);
- vmbus_connection.conn_state = DISCONNECTED;
-
/* Reset the event for the next resume. */
reinit_completion(&vmbus_connection.ready_for_resume_event);
@@ -2289,7 +2296,6 @@ static void hv_kexec_handler(void)
{
hv_stimer_global_cleanup();
vmbus_initiate_unload(false);
- vmbus_connection.conn_state = DISCONNECTED;
/* Make sure conn_state is set as hv_synic_cleanup checks for it */
mb();
cpuhp_remove_state(hyperv_cpuhp_online);
@@ -2306,7 +2312,6 @@ static void hv_crash_handler(struct pt_regs *regs)
* doing the cleanup for current CPU only. This should be sufficient
* for kdump.
*/
- vmbus_connection.conn_state = DISCONNECTED;
cpu = smp_processor_id();
hv_stimer_cleanup(cpu);
hv_synic_disable_regs(cpu);
The patch below does not apply to the 4.14-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 216830d2413cc61be3f76bc02ffd905e47d2439e Mon Sep 17 00:00:00 2001
From: Frank Rowand <frank.rowand(a)sony.com>
Date: Thu, 16 Apr 2020 16:42:47 -0500
Subject: [PATCH] of: unittest: kmemleak in of_unittest_platform_populate()
kmemleak reports several memory leaks from devicetree unittest.
This is the fix for problem 2 of 5.
of_unittest_platform_populate() left an elevated reference count for
grandchild nodes (which are platform devices). Fix the platform
device reference counts so that the memory will be freed.
Fixes: fb2caa50fbac ("of/selftest: add testcase for nodes with same name and address")
Reported-by: Erhard F. <erhard_f(a)mailbox.org>
Signed-off-by: Frank Rowand <frank.rowand(a)sony.com>
Signed-off-by: Rob Herring <robh(a)kernel.org>
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 20ff2dfc3143..4c7818276857 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1247,10 +1247,13 @@ static void __init of_unittest_platform_populate(void)
of_platform_populate(np, match, NULL, &test_bus->dev);
for_each_child_of_node(np, child) {
- for_each_child_of_node(child, grandchild)
- unittest(of_find_device_by_node(grandchild),
+ for_each_child_of_node(child, grandchild) {
+ pdev = of_find_device_by_node(grandchild);
+ unittest(pdev,
"Could not create device for node '%pOFn'\n",
grandchild);
+ of_dev_put(pdev);
+ }
}
of_platform_depopulate(&test_bus->dev);
The patch below does not apply to the 4.19-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 99e3a236dd43d06c65af0a2ef9cb44306aef6e02 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson(a)intel.com>
Date: Tue, 14 Apr 2020 09:35:15 +0200
Subject: [PATCH] xsk: Add missing check on user supplied headroom size
Add a check that the headroom cannot be larger than the available
space in the chunk. In the current code, a malicious user can set the
headroom to a value larger than the chunk size minus the fixed XDP
headroom. That way packets with a length larger than the supported
size in the umem could get accepted and result in an out-of-bounds
write.
Fixes: c0c77d8fb787 ("xsk: add user memory registration support sockopt")
Reported-by: Bui Quang Minh <minhquangbui99(a)gmail.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson(a)intel.com>
Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=207225
Link: https://lore.kernel.org/bpf/1586849715-23490-1-git-send-email-magnus.karlss…
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index fa7bb5e060d0..ed7a6060f73c 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -343,7 +343,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
u32 chunk_size = mr->chunk_size, headroom = mr->headroom;
unsigned int chunks, chunks_per_page;
u64 addr = mr->addr, size = mr->len;
- int size_chk, err;
+ int err;
if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) {
/* Strictly speaking we could support this, if:
@@ -382,8 +382,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
return -EINVAL;
}
- size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM;
- if (size_chk < 0)
+ if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
return -EINVAL;
umem->address = (unsigned long)addr;
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 952c48b0ed18919bff7528501e9a3fff8a24f8cd Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov(a)gmail.com>
Date: Mon, 16 Mar 2020 15:52:54 +0100
Subject: [PATCH] rbd: call rbd_dev_unprobe() after unwatching and flushing
notifies
rbd_dev_unprobe() is supposed to undo most of rbd_dev_image_probe(),
including rbd_dev_header_info(), which means that rbd_dev_header_info()
isn't supposed to be called after rbd_dev_unprobe().
However, rbd_dev_image_release() calls rbd_dev_unprobe() before
rbd_unregister_watch(). This is racy because a header update notify
can sneak in:
"rbd unmap" thread ceph-watch-notify worker
rbd_dev_image_release()
rbd_dev_unprobe()
free and zero out header
rbd_watch_cb()
rbd_dev_refresh()
rbd_dev_header_info()
read in header
The same goes for "rbd map" because rbd_dev_image_probe() calls
rbd_dev_unprobe() on errors. In both cases this results in a memory
leak.
Fixes: fd22aef8b47c ("rbd: move rbd_unregister_watch() call into rbd_dev_image_release()")
Signed-off-by: Ilya Dryomov <idryomov(a)gmail.com>
Reviewed-by: Jason Dillaman <dillaman(a)redhat.com>
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index ff2377e6d12c..7aec8bc5df6e 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -6898,9 +6898,10 @@ static void rbd_print_dne(struct rbd_device *rbd_dev, bool is_snap)
static void rbd_dev_image_release(struct rbd_device *rbd_dev)
{
- rbd_dev_unprobe(rbd_dev);
if (rbd_dev->opts)
rbd_unregister_watch(rbd_dev);
+
+ rbd_dev_unprobe(rbd_dev);
rbd_dev->image_format = 0;
kfree(rbd_dev->spec->image_id);
rbd_dev->spec->image_id = NULL;
@@ -6950,7 +6951,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
if (ret) {
if (ret == -ENOENT && !need_watch)
rbd_print_dne(rbd_dev, false);
- goto err_out_watch;
+ goto err_out_probe;
}
/*
@@ -6995,12 +6996,11 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
return 0;
err_out_probe:
- rbd_dev_unprobe(rbd_dev);
-err_out_watch:
if (!depth)
up_write(&rbd_dev->header_rwsem);
if (need_watch)
rbd_unregister_watch(rbd_dev);
+ rbd_dev_unprobe(rbd_dev);
err_out_format:
rbd_dev->image_format = 0;
kfree(rbd_dev->spec->image_id);
The patch below does not apply to the 5.4-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 0e4e1de5b63fa423b13593337a27fd2d2b0bcf77 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <idryomov(a)gmail.com>
Date: Fri, 13 Mar 2020 11:20:51 +0100
Subject: [PATCH] rbd: avoid a deadlock on header_rwsem when flushing notifies
rbd_unregister_watch() flushes notifies and therefore cannot be called
under header_rwsem because a header update notify takes header_rwsem to
synchronize with "rbd map". If mapping an image fails after the watch
is established and a header update notify sneaks in, we deadlock when
erroring out from rbd_dev_image_probe().
Move watch registration and unregistration out of the critical section.
The only reason they were put there was to make header_rwsem management
slightly more obvious.
Fixes: 811c66887746 ("rbd: fix rbd map vs notify races")
Signed-off-by: Ilya Dryomov <idryomov(a)gmail.com>
Reviewed-by: Jason Dillaman <dillaman(a)redhat.com>
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 1e0a6b19ae0d..ff2377e6d12c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4527,6 +4527,10 @@ static void cancel_tasks_sync(struct rbd_device *rbd_dev)
cancel_work_sync(&rbd_dev->unlock_work);
}
+/*
+ * header_rwsem must not be held to avoid a deadlock with
+ * rbd_dev_refresh() when flushing notifies.
+ */
static void rbd_unregister_watch(struct rbd_device *rbd_dev)
{
cancel_tasks_sync(rbd_dev);
@@ -6907,6 +6911,9 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
* device. If this image is the one being mapped (i.e., not a
* parent), initiate a watch on its header object before using that
* object to get detailed information about the rbd image.
+ *
+ * On success, returns with header_rwsem held for write if called
+ * with @depth == 0.
*/
static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
{
@@ -6936,6 +6943,9 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
}
}
+ if (!depth)
+ down_write(&rbd_dev->header_rwsem);
+
ret = rbd_dev_header_info(rbd_dev);
if (ret) {
if (ret == -ENOENT && !need_watch)
@@ -6987,6 +6997,8 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
err_out_probe:
rbd_dev_unprobe(rbd_dev);
err_out_watch:
+ if (!depth)
+ up_write(&rbd_dev->header_rwsem);
if (need_watch)
rbd_unregister_watch(rbd_dev);
err_out_format:
@@ -7050,12 +7062,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
goto err_out_rbd_dev;
}
- down_write(&rbd_dev->header_rwsem);
rc = rbd_dev_image_probe(rbd_dev, 0);
- if (rc < 0) {
- up_write(&rbd_dev->header_rwsem);
+ if (rc < 0)
goto err_out_rbd_dev;
- }
if (rbd_dev->opts->alloc_size > rbd_dev->layout.object_size) {
rbd_warn(rbd_dev, "alloc_size adjusted to %u",