[ Upstream commit ea401499e943c307e6d44af6c2b4e068643e7884 ]
Stuart Hayes reports that an error handled by DPC at a Root Port results
in pciehp gratuitously bringing down a subordinate hotplug port:
RP -- UP -- DP -- UP -- DP (hotplug) -- EP
pciehp brings the slot down because the Link to the Endpoint goes down.
That is caused by a Hot Reset being propagated as a result of DPC.
Per PCIe Base Spec 5.0, section 6.6.1 "Conventional Reset":
For a Switch, the following must cause a hot reset to be sent on all
Downstream Ports: [...]
* The Data Link Layer of the Upstream Port reporting DL_Down status.
In Switches that support Link speeds greater than 5.0 GT/s, the
Upstream Port must direct the LTSSM of each Downstream Port to the
Hot Reset state, but not hold the LTSSMs in that state. This permits
each Downstream Port to begin Link training immediately after its
hot reset completes. This behavior is recommended for all Switches.
* Receiving a hot reset on the Upstream Port.
Once DPC recovers, pcie_do_recovery() walks down the hierarchy and
invokes pcie_portdrv_slot_reset() to restore each port's config space.
At that point, a hotplug interrupt is signaled per PCIe Base Spec r5.0,
section 6.7.3.4 "Software Notification of Hot-Plug Events":
If the Port is enabled for edge-triggered interrupt signaling using
MSI or MSI-X, an interrupt message must be sent every time the logical
AND of the following conditions transitions from FALSE to TRUE: [...]
* The Hot-Plug Interrupt Enable bit in the Slot Control register is
set to 1b.
* At least one hot-plug event status bit in the Slot Status register
and its associated enable bit in the Slot Control register are both
set to 1b.
Prevent pciehp from gratuitously bringing down the slot by clearing the
error-induced Data Link Layer State Changed event before restoring
config space. Afterwards, check whether the link has unexpectedly
failed to retrain and synthesize a DLLSC event if so.
Allow each pcie_port_service_driver (one of them being pciehp) to define
a slot_reset callback and re-use the existing pm_iter() function to
iterate over the callbacks.
Thereby, the Endpoint driver remains bound throughout error recovery and
may restore the device to working state.
Surprise removal during error recovery is detected through a Presence
Detect Changed event. The hotplug port is expected to not signal that
event as a result of a Hot Reset.
The issue isn't DPC-specific, it also occurs when an error is handled by
AER through aer_root_reset(). So while the issue was noticed only now,
it's been around since 2006 when AER support was first introduced.
[bhelgaas: drop PCI_ERROR_RECOVERY Kconfig, split pm_iter() rename to
preparatory patch]
Link: https://lore.kernel.org/linux-pci/08c046b0-c9f2-3489-eeef-7e7aca435bb9@gmail.com/
Fixes: 6c2b374d74 ("PCI-Express AER implemetation: AER core and aerdriver")
Link: https://lore.kernel.org/r/251f4edcc04c14f873ff1c967bc686169cd07d2d.1627638184.git.lukas@wunner.de
Reported-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Tested-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org # v2.6.19+: ba952824e6: PCI/portdrv: Report reset for frozen channel
Cc: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
151 lines
4.6 KiB
C
151 lines
4.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Purpose: PCI Express Port Bus Driver's Internal Data Structures
|
|
*
|
|
* Copyright (C) 2004 Intel
|
|
* Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
|
|
*/
|
|
|
|
#ifndef _PORTDRV_H_
|
|
#define _PORTDRV_H_
|
|
|
|
#include <linux/compiler.h>
|
|
|
|
/* Service Type */
|
|
#define PCIE_PORT_SERVICE_PME_SHIFT 0 /* Power Management Event */
|
|
#define PCIE_PORT_SERVICE_PME (1 << PCIE_PORT_SERVICE_PME_SHIFT)
|
|
#define PCIE_PORT_SERVICE_AER_SHIFT 1 /* Advanced Error Reporting */
|
|
#define PCIE_PORT_SERVICE_AER (1 << PCIE_PORT_SERVICE_AER_SHIFT)
|
|
#define PCIE_PORT_SERVICE_HP_SHIFT 2 /* Native Hotplug */
|
|
#define PCIE_PORT_SERVICE_HP (1 << PCIE_PORT_SERVICE_HP_SHIFT)
|
|
#define PCIE_PORT_SERVICE_DPC_SHIFT 3 /* Downstream Port Containment */
|
|
#define PCIE_PORT_SERVICE_DPC (1 << PCIE_PORT_SERVICE_DPC_SHIFT)
|
|
#define PCIE_PORT_SERVICE_BWNOTIF_SHIFT 4 /* Bandwidth notification */
|
|
#define PCIE_PORT_SERVICE_BWNOTIF (1 << PCIE_PORT_SERVICE_BWNOTIF_SHIFT)
|
|
|
|
#define PCIE_PORT_DEVICE_MAXSERVICES 5
|
|
|
|
extern bool pcie_ports_dpc_native;
|
|
|
|
#ifdef CONFIG_PCIEAER
|
|
int pcie_aer_init(void);
|
|
int pcie_aer_is_native(struct pci_dev *dev);
|
|
#else
|
|
static inline int pcie_aer_init(void) { return 0; }
|
|
static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; }
|
|
#endif
|
|
|
|
#ifdef CONFIG_HOTPLUG_PCI_PCIE
|
|
int pcie_hp_init(void);
|
|
#else
|
|
static inline int pcie_hp_init(void) { return 0; }
|
|
#endif
|
|
|
|
#ifdef CONFIG_PCIE_PME
|
|
int pcie_pme_init(void);
|
|
#else
|
|
static inline int pcie_pme_init(void) { return 0; }
|
|
#endif
|
|
|
|
#ifdef CONFIG_PCIE_DPC
|
|
int pcie_dpc_init(void);
|
|
#else
|
|
static inline int pcie_dpc_init(void) { return 0; }
|
|
#endif
|
|
|
|
/* Port Type */
|
|
#define PCIE_ANY_PORT (~0)
|
|
|
|
struct pcie_device {
|
|
int irq; /* Service IRQ/MSI/MSI-X Vector */
|
|
struct pci_dev *port; /* Root/Upstream/Downstream Port */
|
|
u32 service; /* Port service this device represents */
|
|
void *priv_data; /* Service Private Data */
|
|
struct device device; /* Generic Device Interface */
|
|
};
|
|
#define to_pcie_device(d) container_of(d, struct pcie_device, device)
|
|
|
|
static inline void set_service_data(struct pcie_device *dev, void *data)
|
|
{
|
|
dev->priv_data = data;
|
|
}
|
|
|
|
static inline void *get_service_data(struct pcie_device *dev)
|
|
{
|
|
return dev->priv_data;
|
|
}
|
|
|
|
struct pcie_port_service_driver {
|
|
const char *name;
|
|
int (*probe)(struct pcie_device *dev);
|
|
void (*remove)(struct pcie_device *dev);
|
|
int (*suspend)(struct pcie_device *dev);
|
|
int (*resume_noirq)(struct pcie_device *dev);
|
|
int (*resume)(struct pcie_device *dev);
|
|
int (*runtime_suspend)(struct pcie_device *dev);
|
|
int (*runtime_resume)(struct pcie_device *dev);
|
|
|
|
int (*slot_reset)(struct pcie_device *dev);
|
|
|
|
/* Device driver may resume normal operations */
|
|
void (*error_resume)(struct pci_dev *dev);
|
|
|
|
int port_type; /* Type of the port this driver can handle */
|
|
u32 service; /* Port service this device represents */
|
|
|
|
struct device_driver driver;
|
|
};
|
|
#define to_service_driver(d) \
|
|
container_of(d, struct pcie_port_service_driver, driver)
|
|
|
|
int pcie_port_service_register(struct pcie_port_service_driver *new);
|
|
void pcie_port_service_unregister(struct pcie_port_service_driver *new);
|
|
|
|
/*
|
|
* The PCIe Capability Interrupt Message Number (PCIe r3.1, sec 7.8.2) must
|
|
* be one of the first 32 MSI-X entries. Per PCI r3.0, sec 6.8.3.1, MSI
|
|
* supports a maximum of 32 vectors per function.
|
|
*/
|
|
#define PCIE_PORT_MAX_MSI_ENTRIES 32
|
|
|
|
#define get_descriptor_id(type, service) (((type - 4) << 8) | service)
|
|
|
|
extern struct bus_type pcie_port_bus_type;
|
|
int pcie_port_device_register(struct pci_dev *dev);
|
|
int pcie_port_device_iter(struct device *dev, void *data);
|
|
#ifdef CONFIG_PM
|
|
int pcie_port_device_suspend(struct device *dev);
|
|
int pcie_port_device_resume_noirq(struct device *dev);
|
|
int pcie_port_device_resume(struct device *dev);
|
|
int pcie_port_device_runtime_suspend(struct device *dev);
|
|
int pcie_port_device_runtime_resume(struct device *dev);
|
|
#endif
|
|
void pcie_port_device_remove(struct pci_dev *dev);
|
|
int __must_check pcie_port_bus_register(void);
|
|
void pcie_port_bus_unregister(void);
|
|
|
|
struct pci_dev;
|
|
|
|
#ifdef CONFIG_PCIE_PME
|
|
extern bool pcie_pme_msi_disabled;
|
|
|
|
static inline void pcie_pme_disable_msi(void)
|
|
{
|
|
pcie_pme_msi_disabled = true;
|
|
}
|
|
|
|
static inline bool pcie_pme_no_msi(void)
|
|
{
|
|
return pcie_pme_msi_disabled;
|
|
}
|
|
|
|
void pcie_pme_interrupt_enable(struct pci_dev *dev, bool enable);
|
|
#else /* !CONFIG_PCIE_PME */
|
|
static inline void pcie_pme_disable_msi(void) {}
|
|
static inline bool pcie_pme_no_msi(void) { return false; }
|
|
static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {}
|
|
#endif /* !CONFIG_PCIE_PME */
|
|
|
|
struct device *pcie_port_find_device(struct pci_dev *dev, u32 service);
|
|
#endif /* _PORTDRV_H_ */
|