| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20220124184154.642601971@linuxfoundation.org>
Date: Mon, 24 Jan 2022 19:44:22 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, "Theodore Tso" <tytso@....edu>,
Hans de Goede <hdegoede@...hat.com>,
Bjorn Helgaas <bhelgaas@...gle.com>,
Lukas Wunner <lukas@...ner.de>
Subject: [PATCH 5.16 0873/1039] PCI: pciehp: Use down_read/write_nested(reset_lock) to fix lockdep errors
From: Hans de Goede <hdegoede@...hat.com>
commit 085a9f43433f30cbe8a1ade62d9d7827c3217f4d upstream.
Use down_read_nested() and down_write_nested() when taking the
ctrl->reset_lock rw-sem, passing the number of PCIe hotplug controllers in
the path to the PCI root bus as lock subclass parameter.
This fixes the following false-positive lockdep report when unplugging a
Lenovo X1C8 from a Lenovo 2nd gen TB3 dock:
pcieport 0000:06:01.0: pciehp: Slot(1): Link Down
pcieport 0000:06:01.0: pciehp: Slot(1): Card not present
============================================
WARNING: possible recursive locking detected
5.16.0-rc2+ #621 Not tainted
--------------------------------------------
irq/124-pciehp/86 is trying to acquire lock:
ffff8e5ac4299ef8 (&ctrl->reset_lock){.+.+}-{3:3}, at: pciehp_check_presence+0x23/0x80
but task is already holding lock:
ffff8e5ac4298af8 (&ctrl->reset_lock){.+.+}-{3:3}, at: pciehp_ist+0xf3/0x180
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&ctrl->reset_lock);
lock(&ctrl->reset_lock);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by irq/124-pciehp/86:
#0: ffff8e5ac4298af8 (&ctrl->reset_lock){.+.+}-{3:3}, at: pciehp_ist+0xf3/0x180
#1: ffffffffa3b024e8 (pci_rescan_remove_lock){+.+.}-{3:3}, at: pciehp_unconfigure_device+0x31/0x110
#2: ffff8e5ac1ee2248 (&dev->mutex){....}-{3:3}, at: device_release_driver+0x1c/0x40
stack backtrace:
CPU: 4 PID: 86 Comm: irq/124-pciehp Not tainted 5.16.0-rc2+ #621
Hardware name: LENOVO 20U90SIT19/20U90SIT19, BIOS N2WET30W (1.20 ) 08/26/2021
Call Trace:
<TASK>
dump_stack_lvl+0x59/0x73
__lock_acquire.cold+0xc5/0x2c6
lock_acquire+0xb5/0x2b0
down_read+0x3e/0x50
pciehp_check_presence+0x23/0x80
pciehp_runtime_resume+0x5c/0xa0
device_for_each_child+0x45/0x70
pcie_port_device_runtime_resume+0x20/0x30
pci_pm_runtime_resume+0xa7/0xc0
__rpm_callback+0x41/0x110
rpm_callback+0x59/0x70
rpm_resume+0x512/0x7b0
__pm_runtime_resume+0x4a/0x90
__device_release_driver+0x28/0x240
device_release_driver+0x26/0x40
pci_stop_bus_device+0x68/0x90
pci_stop_bus_device+0x2c/0x90
pci_stop_and_remove_bus_device+0xe/0x20
pciehp_unconfigure_device+0x6c/0x110
pciehp_disable_slot+0x5b/0xe0
pciehp_handle_presence_or_link_change+0xc3/0x2f0
pciehp_ist+0x179/0x180
This lockdep warning is triggered because with Thunderbolt, hotplug ports
are nested. When removing multiple devices in a daisy-chain, each hotplug
port's reset_lock may be acquired recursively. It's never the same lock, so
the lockdep splat is a false positive.
Because locks at the same hierarchy level are never acquired recursively, a
per-level lockdep class is sufficient to fix the lockdep warning.
The choice to use one lockdep subclass per pcie-hotplug controller in the
path to the root-bus was made to conserve class keys because their number
is limited and the complexity grows quadratically with number of keys
according to Documentation/locking/lockdep-design.rst.
Link: https://lore.kernel.org/linux-pci/20190402021933.GA2966@mit.edu/
Link: https://lore.kernel.org/linux-pci/de684a28-9038-8fc6-27ca-3f6f2f6400d7@redhat.com/
Link: https://lore.kernel.org/r/20211217141709.379663-1-hdegoede@redhat.com
Link: https://bugzilla.kernel.org/show_bug.cgi?id=208855
Reported-by: "Theodore Ts'o" <tytso@....edu>
Signed-off-by: Hans de Goede <hdegoede@...hat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@...gle.com>
Reviewed-by: Lukas Wunner <lukas@...ner.de>
Cc: stable@...r.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
drivers/pci/hotplug/pciehp.h | 3 +++
drivers/pci/hotplug/pciehp_core.c | 2 +-
drivers/pci/hotplug/pciehp_hpc.c | 21 ++++++++++++++++++---
3 files changed, 22 insertions(+), 4 deletions(-)
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -75,6 +75,8 @@ extern int pciehp_poll_time;
* @reset_lock: prevents access to the Data Link Layer Link Active bit in the
* Link Status register and to the Presence Detect State bit in the Slot
* Status register during a slot reset which may cause them to flap
+ * @depth: Number of additional hotplug ports in the path to the root bus,
+ * used as lock subclass for @reset_lock
* @ist_running: flag to keep user request waiting while IRQ thread is running
* @request_result: result of last user request submitted to the IRQ thread
* @requester: wait queue to wake up on completion of user request,
@@ -106,6 +108,7 @@ struct controller {
struct hotplug_slot hotplug_slot; /* hotplug core interface */
struct rw_semaphore reset_lock;
+ unsigned int depth;
unsigned int ist_running;
int request_result;
wait_queue_head_t requester;
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -166,7 +166,7 @@ static void pciehp_check_presence(struct
{
int occupied;
- down_read(&ctrl->reset_lock);
+ down_read_nested(&ctrl->reset_lock, ctrl->depth);
mutex_lock(&ctrl->state_lock);
occupied = pciehp_card_present_or_link_active(ctrl);
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -583,7 +583,7 @@ static void pciehp_ignore_dpc_link_chang
* the corresponding link change may have been ignored above.
* Synthesize it to ensure that it is acted on.
*/
- down_read(&ctrl->reset_lock);
+ down_read_nested(&ctrl->reset_lock, ctrl->depth);
if (!pciehp_check_link_active(ctrl))
pciehp_request(ctrl, PCI_EXP_SLTSTA_DLLSC);
up_read(&ctrl->reset_lock);
@@ -746,7 +746,7 @@ static irqreturn_t pciehp_ist(int irq, v
* Disable requests have higher priority than Presence Detect Changed
* or Data Link Layer State Changed events.
*/
- down_read(&ctrl->reset_lock);
+ down_read_nested(&ctrl->reset_lock, ctrl->depth);
if (events & DISABLE_SLOT)
pciehp_handle_disable_request(ctrl);
else if (events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC))
@@ -906,7 +906,7 @@ int pciehp_reset_slot(struct hotplug_slo
if (probe)
return 0;
- down_write(&ctrl->reset_lock);
+ down_write_nested(&ctrl->reset_lock, ctrl->depth);
if (!ATTN_BUTTN(ctrl)) {
ctrl_mask |= PCI_EXP_SLTCTL_PDCE;
@@ -962,6 +962,20 @@ static inline void dbg_ctrl(struct contr
#define FLAG(x, y) (((x) & (y)) ? '+' : '-')
+static inline int pcie_hotplug_depth(struct pci_dev *dev)
+{
+ struct pci_bus *bus = dev->bus;
+ int depth = 0;
+
+ while (bus->parent) {
+ bus = bus->parent;
+ if (bus->self && bus->self->is_hotplug_bridge)
+ depth++;
+ }
+
+ return depth;
+}
+
struct controller *pcie_init(struct pcie_device *dev)
{
struct controller *ctrl;
@@ -975,6 +989,7 @@ struct controller *pcie_init(struct pcie
return NULL;
ctrl->pcie = dev;
+ ctrl->depth = pcie_hotplug_depth(dev->port);
pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, &slot_cap);
if (pdev->hotplug_user_indicators)
Powered by blists - more mailing lists