linux/drivers/pci/pcie/portdrv_core.c

579 lines
16 KiB
C
Raw Normal View History

/*
* File: portdrv_core.c
* Purpose: PCI Express Port Bus Driver's Core Functions
*
* Copyright (C) 2004 Intel
* Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
*/
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/pcieport_if.h>
PCI: PCIe: Ask BIOS for control of all native services at once After commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the platform won't provide _OSC control for PCIe) control of the PCIe Capability Structure is unconditionally requested by acpi_pci_root_add(), which in principle may cause problems to happen in two ways. First, the BIOS may refuse to give control of the PCIe Capability Structure if it is not asked for any of the _OSC features depending on it at the same time. Second, the BIOS may assume that control of the _OSC features depending on the PCIe Capability Structure will be requested in the future and may behave incorrectly if that doesn't happen. For this reason, control of the PCIe Capability Structure should always be requested along with control of any other _OSC features that may depend on it (ie. PCIe native PME, PCIe native hot-plug, PCIe AER). Rework the PCIe port driver so that (1) it checks which native PCIe port services can be enabled, according to the BIOS, and (2) it requests control of all these services simultaneously. In particular, this causes pcie_portdrv_probe() to fail if the BIOS refuses to grant control of the PCIe Capability Structure, which means that no native PCIe port services can be enabled for the PCIe Root Complex the given port belongs to. If that happens, ASPM is disabled to avoid problems with mishandling it by the part of the PCIe hierarchy for which control of the PCIe Capability Structure has not been received. Make it possible to override this behavior using 'pcie_ports=native' (use the PCIe native services regardless of the BIOS response to the control request), or 'pcie_ports=compat' (do not use the PCIe native services at all). Accordingly, rework the existing PCIe port service drivers so that they don't request control of the services directly. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2010-08-22 04:02:38 +08:00
#include <linux/aer.h>
#include "../pci.h"
#include "portdrv.h"
PCI: Add pcie_hp=nomsi to disable MSI/MSI-X for pciehp driver Add a parameter to avoid using MSI/MSI-X for PCIe native hotplug; it's known to be buggy on some platforms. In my environment, while shutting down, following stack trace is shown sometimes. irq 16: nobody cared (try booting with the "irqpoll" option) Pid: 1081, comm: reboot Not tainted 3.2.0 #1 Call Trace: <IRQ> [<ffffffff810cec1d>] __report_bad_irq+0x3d/0xe0 [<ffffffff810cee1c>] note_interrupt+0x15c/0x210 [<ffffffff810cc485>] handle_irq_event_percpu+0xb5/0x210 [<ffffffff810cc621>] handle_irq_event+0x41/0x70 [<ffffffff810cf675>] handle_fasteoi_irq+0x55/0xc0 [<ffffffff81015356>] handle_irq+0x46/0xb0 [<ffffffff814fbe9d>] do_IRQ+0x5d/0xe0 [<ffffffff814f146e>] common_interrupt+0x6e/0x6e [<ffffffff8106b040>] ? __do_softirq+0x60/0x210 [<ffffffff8108aeb1>] ? hrtimer_interrupt+0x151/0x240 [<ffffffff814fb5ec>] call_softirq+0x1c/0x30 [<ffffffff810152d5>] do_softirq+0x65/0xa0 [<ffffffff8106ae9d>] irq_exit+0xbd/0xe0 [<ffffffff814fbf8e>] smp_apic_timer_interrupt+0x6e/0x99 [<ffffffff814f9e5e>] apic_timer_interrupt+0x6e/0x80 <EOI> [<ffffffff814f0fb1>] ? _raw_spin_unlock_irqrestore+0x11/0x20 [<ffffffff812629fc>] pci_bus_write_config_word+0x6c/0x80 [<ffffffff81266fc2>] pci_intx+0x52/0xa0 [<ffffffff8127de3d>] pci_intx_for_msi+0x1d/0x30 [<ffffffff8127e4fb>] pci_msi_shutdown+0x7b/0x110 [<ffffffff81269d34>] pci_device_shutdown+0x34/0x50 [<ffffffff81326c4f>] device_shutdown+0x2f/0x140 [<ffffffff8107b981>] kernel_restart_prepare+0x31/0x40 [<ffffffff8107b9e6>] kernel_restart+0x16/0x60 [<ffffffff8107bbfd>] sys_reboot+0x1ad/0x220 [<ffffffff814f4b90>] ? do_page_fault+0x1e0/0x460 [<ffffffff811942d0>] ? __sync_filesystem+0x90/0x90 [<ffffffff8105c9aa>] ? __cond_resched+0x2a/0x40 [<ffffffff814ef090>] ? _cond_resched+0x30/0x40 [<ffffffff81169e17>] ? iterate_supers+0xb7/0xd0 [<ffffffff814f9382>] system_call_fastpath+0x16/0x1b handlers: [<ffffffff8138a0f0>] usb_hcd_irq [<ffffffff8138a0f0>] usb_hcd_irq [<ffffffff8138a0f0>] usb_hcd_irq Disabling IRQ #16 An un-wanted interrupt is generated when PCI driver switches from MSI/MSI-X to INTx while shutting down the device. The interrupt does not happen if MSI/MSI-X is not used on the device. I confirmed that this problem does not happen if pcie_hp=nomsi was specified and hotplug operation worked fine as usual. v2: Automatically disable MSI/MSI-X against following device: PCI bridge: Integrated Device Technology, Inc. Device 807f (rev 02) v3: Based on the review comment, combile the if statements. v4: Removed module parameter. Move some code to build pciehp as a module. Move device specific code to driver/pci/quirks.c. v5: Drop a device specific code until getting a vendor statement. Reviewed-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: MUNEDA Takahiro <muneda.takahiro@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2012-02-03 00:09:22 +08:00
bool pciehp_msi_disabled;
static int __init pciehp_setup(char *str)
{
if (!strncmp(str, "nomsi", 5))
pciehp_msi_disabled = true;
return 1;
}
__setup("pcie_hp=", pciehp_setup);
/**
* release_pcie_device - free PCI Express port service device structure
* @dev: Port service device to release
*
* Invoked automatically when device is being removed in response to
* device_unregister(dev). Release all resources being claimed.
*/
static void release_pcie_device(struct device *dev)
{
kfree(to_pcie_device(dev));
}
/**
* pcie_port_msix_add_entry - add entry to given array of MSI-X entries
* @entries: Array of MSI-X entries
* @new_entry: Index of the entry to add to the array
* @nr_entries: Number of entries already in the array
*
* Return value: Position of the added entry in the array
*/
static int pcie_port_msix_add_entry(
struct msix_entry *entries, int new_entry, int nr_entries)
{
int j;
for (j = 0; j < nr_entries; j++)
if (entries[j].entry == new_entry)
return j;
entries[j].entry = new_entry;
return j;
}
/**
* pcie_port_enable_msix - try to set up MSI-X as interrupt mode for given port
* @dev: PCI Express port to handle
* @vectors: Array of interrupt vectors to populate
* @mask: Bitmask of port capabilities returned by get_port_device_capability()
*
* Return value: 0 on success, error code on failure
*/
static int pcie_port_enable_msix(struct pci_dev *dev, int *vectors, int mask)
{
struct msix_entry *msix_entries;
int idx[PCIE_PORT_DEVICE_MAXSERVICES];
int nr_entries, status, pos, i, nvec;
u16 reg16;
u32 reg32;
nr_entries = pci_msix_vec_count(dev);
if (nr_entries < 0)
return nr_entries;
BUG_ON(!nr_entries);
if (nr_entries > PCIE_PORT_MAX_MSIX_ENTRIES)
nr_entries = PCIE_PORT_MAX_MSIX_ENTRIES;
msix_entries = kzalloc(sizeof(*msix_entries) * nr_entries, GFP_KERNEL);
if (!msix_entries)
return -ENOMEM;
/*
* Allocate as many entries as the port wants, so that we can check
* which of them will be useful. Moreover, if nr_entries is correctly
* equal to the number of entries this port actually uses, we'll happily
* go through without any tricks.
*/
for (i = 0; i < nr_entries; i++)
msix_entries[i].entry = i;
status = pci_enable_msix_exact(dev, msix_entries, nr_entries);
if (status)
goto Exit;
for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
idx[i] = -1;
status = -EIO;
nvec = 0;
if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) {
int entry;
/*
* The code below follows the PCI Express Base Specification 2.0
* stating in Section 6.1.6 that "PME and Hot-Plug Event
* interrupts (when both are implemented) always share the same
* MSI or MSI-X vector, as indicated by the Interrupt Message
* Number field in the PCI Express Capabilities register", where
* according to Section 7.8.2 of the specification "For MSI-X,
* the value in this field indicates which MSI-X Table entry is
* used to generate the interrupt message."
*/
pcie_capability_read_word(dev, PCI_EXP_FLAGS, &reg16);
entry = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9;
if (entry >= nr_entries)
goto Error;
i = pcie_port_msix_add_entry(msix_entries, entry, nvec);
if (i == nvec)
nvec++;
idx[PCIE_PORT_SERVICE_PME_SHIFT] = i;
idx[PCIE_PORT_SERVICE_HP_SHIFT] = i;
}
if (mask & PCIE_PORT_SERVICE_AER) {
int entry;
/*
* The code below follows Section 7.10.10 of the PCI Express
* Base Specification 2.0 stating that bits 31-27 of the Root
* Error Status Register contain a value indicating which of the
* MSI/MSI-X vectors assigned to the port is going to be used
* for AER, where "For MSI-X, the value in this register
* indicates which MSI-X Table entry is used to generate the
* interrupt message."
*/
pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
entry = reg32 >> 27;
if (entry >= nr_entries)
goto Error;
i = pcie_port_msix_add_entry(msix_entries, entry, nvec);
if (i == nvec)
nvec++;
idx[PCIE_PORT_SERVICE_AER_SHIFT] = i;
}
/*
* If nvec is equal to the allocated number of entries, we can just use
* what we have. Otherwise, the port has some extra entries not for the
* services we know and we need to work around that.
*/
if (nvec == nr_entries) {
status = 0;
} else {
/* Drop the temporary MSI-X setup */
pci_disable_msix(dev);
/* Now allocate the MSI-X vectors for real */
status = pci_enable_msix_exact(dev, msix_entries, nvec);
if (status)
goto Exit;
}
for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
vectors[i] = idx[i] >= 0 ? msix_entries[idx[i]].vector : -1;
Exit:
kfree(msix_entries);
return status;
Error:
pci_disable_msix(dev);
goto Exit;
}
/**
* init_service_irqs - initialize irqs for PCI Express port services
* @dev: PCI Express port to handle
* @irqs: Array of irqs to populate
* @mask: Bitmask of port capabilities returned by get_port_device_capability()
*
* Return value: Interrupt mode associated with the port
*/
static int init_service_irqs(struct pci_dev *dev, int *irqs, int mask)
{
int i, irq = -1;
/*
* If MSI cannot be used for PCIe PME or hotplug, we have to use
* INTx or other interrupts, e.g. system shared interrupt.
*/
PCI: Add pcie_hp=nomsi to disable MSI/MSI-X for pciehp driver Add a parameter to avoid using MSI/MSI-X for PCIe native hotplug; it's known to be buggy on some platforms. In my environment, while shutting down, following stack trace is shown sometimes. irq 16: nobody cared (try booting with the "irqpoll" option) Pid: 1081, comm: reboot Not tainted 3.2.0 #1 Call Trace: <IRQ> [<ffffffff810cec1d>] __report_bad_irq+0x3d/0xe0 [<ffffffff810cee1c>] note_interrupt+0x15c/0x210 [<ffffffff810cc485>] handle_irq_event_percpu+0xb5/0x210 [<ffffffff810cc621>] handle_irq_event+0x41/0x70 [<ffffffff810cf675>] handle_fasteoi_irq+0x55/0xc0 [<ffffffff81015356>] handle_irq+0x46/0xb0 [<ffffffff814fbe9d>] do_IRQ+0x5d/0xe0 [<ffffffff814f146e>] common_interrupt+0x6e/0x6e [<ffffffff8106b040>] ? __do_softirq+0x60/0x210 [<ffffffff8108aeb1>] ? hrtimer_interrupt+0x151/0x240 [<ffffffff814fb5ec>] call_softirq+0x1c/0x30 [<ffffffff810152d5>] do_softirq+0x65/0xa0 [<ffffffff8106ae9d>] irq_exit+0xbd/0xe0 [<ffffffff814fbf8e>] smp_apic_timer_interrupt+0x6e/0x99 [<ffffffff814f9e5e>] apic_timer_interrupt+0x6e/0x80 <EOI> [<ffffffff814f0fb1>] ? _raw_spin_unlock_irqrestore+0x11/0x20 [<ffffffff812629fc>] pci_bus_write_config_word+0x6c/0x80 [<ffffffff81266fc2>] pci_intx+0x52/0xa0 [<ffffffff8127de3d>] pci_intx_for_msi+0x1d/0x30 [<ffffffff8127e4fb>] pci_msi_shutdown+0x7b/0x110 [<ffffffff81269d34>] pci_device_shutdown+0x34/0x50 [<ffffffff81326c4f>] device_shutdown+0x2f/0x140 [<ffffffff8107b981>] kernel_restart_prepare+0x31/0x40 [<ffffffff8107b9e6>] kernel_restart+0x16/0x60 [<ffffffff8107bbfd>] sys_reboot+0x1ad/0x220 [<ffffffff814f4b90>] ? do_page_fault+0x1e0/0x460 [<ffffffff811942d0>] ? __sync_filesystem+0x90/0x90 [<ffffffff8105c9aa>] ? __cond_resched+0x2a/0x40 [<ffffffff814ef090>] ? _cond_resched+0x30/0x40 [<ffffffff81169e17>] ? iterate_supers+0xb7/0xd0 [<ffffffff814f9382>] system_call_fastpath+0x16/0x1b handlers: [<ffffffff8138a0f0>] usb_hcd_irq [<ffffffff8138a0f0>] usb_hcd_irq [<ffffffff8138a0f0>] usb_hcd_irq Disabling IRQ #16 An un-wanted interrupt is generated when PCI driver switches from MSI/MSI-X to INTx while shutting down the device. The interrupt does not happen if MSI/MSI-X is not used on the device. I confirmed that this problem does not happen if pcie_hp=nomsi was specified and hotplug operation worked fine as usual. v2: Automatically disable MSI/MSI-X against following device: PCI bridge: Integrated Device Technology, Inc. Device 807f (rev 02) v3: Based on the review comment, combile the if statements. v4: Removed module parameter. Move some code to build pciehp as a module. Move device specific code to driver/pci/quirks.c. v5: Drop a device specific code until getting a vendor statement. Reviewed-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com> Signed-off-by: MUNEDA Takahiro <muneda.takahiro@jp.fujitsu.com> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2012-02-03 00:09:22 +08:00
if (((mask & PCIE_PORT_SERVICE_PME) && pcie_pme_no_msi()) ||
((mask & PCIE_PORT_SERVICE_HP) && pciehp_no_msi())) {
if (dev->irq)
irq = dev->irq;
goto no_msi;
}
/* Try to use MSI-X if supported */
if (!pcie_port_enable_msix(dev, irqs, mask))
return 0;
/*
* We're not going to use MSI-X, so try MSI and fall back to INTx.
* If neither MSI/MSI-X nor INTx available, try other interrupt. On
* some platforms, root port doesn't support MSI/MSI-X/INTx in RC mode.
*/
if (!pci_enable_msi(dev) || dev->irq)
irq = dev->irq;
no_msi:
for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++)
irqs[i] = irq;
irqs[PCIE_PORT_SERVICE_VC_SHIFT] = -1;
if (irq < 0)
return -ENODEV;
return 0;
}
static void cleanup_service_irqs(struct pci_dev *dev)
{
if (dev->msix_enabled)
pci_disable_msix(dev);
else if (dev->msi_enabled)
pci_disable_msi(dev);
}
/**
* get_port_device_capability - discover capabilities of a PCI Express port
* @dev: PCI Express port to examine
*
* The capabilities are read from the port's PCI Express configuration registers
* as described in PCI Express Base Specification 1.0a sections 7.8.2, 7.8.9 and
* 7.9 - 7.11.
*
* Return value: Bitmask of discovered port capabilities
*/
static int get_port_device_capability(struct pci_dev *dev)
{
int services = 0;
u32 reg32;
int cap_mask = 0;
PCI: PCIe: Ask BIOS for control of all native services at once After commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the platform won't provide _OSC control for PCIe) control of the PCIe Capability Structure is unconditionally requested by acpi_pci_root_add(), which in principle may cause problems to happen in two ways. First, the BIOS may refuse to give control of the PCIe Capability Structure if it is not asked for any of the _OSC features depending on it at the same time. Second, the BIOS may assume that control of the _OSC features depending on the PCIe Capability Structure will be requested in the future and may behave incorrectly if that doesn't happen. For this reason, control of the PCIe Capability Structure should always be requested along with control of any other _OSC features that may depend on it (ie. PCIe native PME, PCIe native hot-plug, PCIe AER). Rework the PCIe port driver so that (1) it checks which native PCIe port services can be enabled, according to the BIOS, and (2) it requests control of all these services simultaneously. In particular, this causes pcie_portdrv_probe() to fail if the BIOS refuses to grant control of the PCIe Capability Structure, which means that no native PCIe port services can be enabled for the PCIe Root Complex the given port belongs to. If that happens, ASPM is disabled to avoid problems with mishandling it by the part of the PCIe hierarchy for which control of the PCIe Capability Structure has not been received. Make it possible to override this behavior using 'pcie_ports=native' (use the PCIe native services regardless of the BIOS response to the control request), or 'pcie_ports=compat' (do not use the PCIe native services at all). Accordingly, rework the existing PCIe port service drivers so that they don't request control of the services directly. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2010-08-22 04:02:38 +08:00
int err;
if (pcie_ports_disabled)
return 0;
cap_mask = PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP
| PCIE_PORT_SERVICE_VC;
if (pci_aer_available())
cap_mask |= PCIE_PORT_SERVICE_AER;
if (pcie_ports_auto) {
err = pcie_port_platform_notify(dev, &cap_mask);
if (err)
return 0;
PCI: PCIe: Ask BIOS for control of all native services at once After commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the platform won't provide _OSC control for PCIe) control of the PCIe Capability Structure is unconditionally requested by acpi_pci_root_add(), which in principle may cause problems to happen in two ways. First, the BIOS may refuse to give control of the PCIe Capability Structure if it is not asked for any of the _OSC features depending on it at the same time. Second, the BIOS may assume that control of the _OSC features depending on the PCIe Capability Structure will be requested in the future and may behave incorrectly if that doesn't happen. For this reason, control of the PCIe Capability Structure should always be requested along with control of any other _OSC features that may depend on it (ie. PCIe native PME, PCIe native hot-plug, PCIe AER). Rework the PCIe port driver so that (1) it checks which native PCIe port services can be enabled, according to the BIOS, and (2) it requests control of all these services simultaneously. In particular, this causes pcie_portdrv_probe() to fail if the BIOS refuses to grant control of the PCIe Capability Structure, which means that no native PCIe port services can be enabled for the PCIe Root Complex the given port belongs to. If that happens, ASPM is disabled to avoid problems with mishandling it by the part of the PCIe hierarchy for which control of the PCIe Capability Structure has not been received. Make it possible to override this behavior using 'pcie_ports=native' (use the PCIe native services regardless of the BIOS response to the control request), or 'pcie_ports=compat' (do not use the PCIe native services at all). Accordingly, rework the existing PCIe port service drivers so that they don't request control of the services directly. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2010-08-22 04:02:38 +08:00
}
/* Hot-Plug Capable */
if ((cap_mask & PCIE_PORT_SERVICE_HP) &&
pcie_caps_reg(dev) & PCI_EXP_FLAGS_SLOT) {
pcie_capability_read_dword(dev, PCI_EXP_SLTCAP, &reg32);
if (reg32 & PCI_EXP_SLTCAP_HPC) {
services |= PCIE_PORT_SERVICE_HP;
/*
* Disable hot-plug interrupts in case they have been
* enabled by the BIOS and the hot-plug service driver
* is not loaded.
*/
pcie_capability_clear_word(dev, PCI_EXP_SLTCTL,
PCI_EXP_SLTCTL_CCIE | PCI_EXP_SLTCTL_HPIE);
}
}
/* AER capable */
PCI: PCIe: Ask BIOS for control of all native services at once After commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the platform won't provide _OSC control for PCIe) control of the PCIe Capability Structure is unconditionally requested by acpi_pci_root_add(), which in principle may cause problems to happen in two ways. First, the BIOS may refuse to give control of the PCIe Capability Structure if it is not asked for any of the _OSC features depending on it at the same time. Second, the BIOS may assume that control of the _OSC features depending on the PCIe Capability Structure will be requested in the future and may behave incorrectly if that doesn't happen. For this reason, control of the PCIe Capability Structure should always be requested along with control of any other _OSC features that may depend on it (ie. PCIe native PME, PCIe native hot-plug, PCIe AER). Rework the PCIe port driver so that (1) it checks which native PCIe port services can be enabled, according to the BIOS, and (2) it requests control of all these services simultaneously. In particular, this causes pcie_portdrv_probe() to fail if the BIOS refuses to grant control of the PCIe Capability Structure, which means that no native PCIe port services can be enabled for the PCIe Root Complex the given port belongs to. If that happens, ASPM is disabled to avoid problems with mishandling it by the part of the PCIe hierarchy for which control of the PCIe Capability Structure has not been received. Make it possible to override this behavior using 'pcie_ports=native' (use the PCIe native services regardless of the BIOS response to the control request), or 'pcie_ports=compat' (do not use the PCIe native services at all). Accordingly, rework the existing PCIe port service drivers so that they don't request control of the services directly. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2010-08-22 04:02:38 +08:00
if ((cap_mask & PCIE_PORT_SERVICE_AER)
&& pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR)) {
services |= PCIE_PORT_SERVICE_AER;
/*
* Disable AER on this port in case it's been enabled by the
* BIOS (the AER service driver will enable it when necessary).
*/
pci_disable_pcie_error_reporting(dev);
}
/* VC support */
if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_VC))
services |= PCIE_PORT_SERVICE_VC;
/* Root ports are capable of generating PME too */
PCI: PCIe: Ask BIOS for control of all native services at once After commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the platform won't provide _OSC control for PCIe) control of the PCIe Capability Structure is unconditionally requested by acpi_pci_root_add(), which in principle may cause problems to happen in two ways. First, the BIOS may refuse to give control of the PCIe Capability Structure if it is not asked for any of the _OSC features depending on it at the same time. Second, the BIOS may assume that control of the _OSC features depending on the PCIe Capability Structure will be requested in the future and may behave incorrectly if that doesn't happen. For this reason, control of the PCIe Capability Structure should always be requested along with control of any other _OSC features that may depend on it (ie. PCIe native PME, PCIe native hot-plug, PCIe AER). Rework the PCIe port driver so that (1) it checks which native PCIe port services can be enabled, according to the BIOS, and (2) it requests control of all these services simultaneously. In particular, this causes pcie_portdrv_probe() to fail if the BIOS refuses to grant control of the PCIe Capability Structure, which means that no native PCIe port services can be enabled for the PCIe Root Complex the given port belongs to. If that happens, ASPM is disabled to avoid problems with mishandling it by the part of the PCIe hierarchy for which control of the PCIe Capability Structure has not been received. Make it possible to override this behavior using 'pcie_ports=native' (use the PCIe native services regardless of the BIOS response to the control request), or 'pcie_ports=compat' (do not use the PCIe native services at all). Accordingly, rework the existing PCIe port service drivers so that they don't request control of the services directly. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2010-08-22 04:02:38 +08:00
if ((cap_mask & PCIE_PORT_SERVICE_PME)
&& pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) {
services |= PCIE_PORT_SERVICE_PME;
/*
* Disable PME interrupt on this port in case it's been enabled
* by the BIOS (the PME service driver will enable it when
* necessary).
*/
pcie_pme_interrupt_enable(dev, false);
}
return services;
}
/**
* pcie_device_init - allocate and initialize PCI Express port service device
* @pdev: PCI Express port to associate the service device with
* @service: Type of service to associate with the service device
* @irq: Interrupt vector to associate with the service device
*/
static int pcie_device_init(struct pci_dev *pdev, int service, int irq)
{
int retval;
struct pcie_device *pcie;
struct device *device;
pcie = kzalloc(sizeof(*pcie), GFP_KERNEL);
if (!pcie)
return -ENOMEM;
pcie->port = pdev;
pcie->irq = irq;
pcie->service = service;
/* Initialize generic device interface */
device = &pcie->device;
device->bus = &pcie_port_bus_type;
device->release = release_pcie_device; /* callback to free pcie dev */
dev_set_name(device, "%s:pcie%02x",
pci_name(pdev),
get_descriptor_id(pci_pcie_type(pdev), service));
device->parent = &pdev->dev;
device_enable_async_suspend(device);
retval = device_register(device);
if (retval) {
put_device(device);
return retval;
}
return 0;
}
/**
* pcie_port_device_register - register PCI Express port
* @dev: PCI Express port to register
*
* Allocate the port extension structure and register services associated with
* the port.
*/
int pcie_port_device_register(struct pci_dev *dev)
{
int status, capabilities, i, nr_service;
int irqs[PCIE_PORT_DEVICE_MAXSERVICES];
/* Enable PCI Express port device */
status = pci_enable_device(dev);
if (status)
return status;
/* Get and check PCI Express port services */
capabilities = get_port_device_capability(dev);
PCI: Disable ASPM when _OSC control is not granted for PCIe services v3 -> v2: Added text to describe the problem v2 -> v1: Split this patch from v1 v1 : Part of: http://marc.info/?l=linux-pci&m=130042212003242&w=2 Disable ASPM when no _OSC control for PCIe services is granted by the BIOS. This is to protect systems with a buggy BIOS that did not set the ACPI FADT "ASPM Controls" bit even though the underlying HW can't do ASPM. To turn "on" ASPM the minimum the BIOS needs to do: 1. Clear the ACPI FADT "ASPM Controls" bit. 2. Support _OSC appropriately There is no _OSC Control bit for ASPM. However, we expect the BIOS to support _OSC for a Root Bridge that originates a PCIe hierarchy. If this is not the case - we are better off not enabling ASPM on that server. Commit 852972acff8f10f3a15679be2059bb94916cba5d (ACPI: Disable ASPM if the Platform won't provide _OSC control for PCIe) describes the above scenario. To quote verbatim from there: [The PCI SIG documentation for the _OSC OS/firmware handshaking interface states: "If the _OSC control method is absent from the scope of a host bridge device, then the operating system must not enable or attempt to use any features defined in this section for the hierarchy originated by the host bridge." The obvious interpretation of this is that the OS should not attempt to use PCIe hotplug, PME or AER - however, the specification also notes that an _OSC method is *required* for PCIe hierarchies, and experimental validation with An Alternative OS indicates that it doesn't use any PCIe functionality if the _OSC method is missing. That arguably means we shouldn't be using MSI or extended config space, but right now our problems seem to be limited to vendors being surprised when ASPM gets enabled on machines when other OSs refuse to do so. So, for now, let's just disable ASPM if the _OSC method doesn't exist or refuses to hand over PCIe capability control.] Signed-off-by: Naga Chumbalkar <nagananda.chumbalkar@hp.com> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
2011-03-21 11:29:20 +08:00
if (!capabilities)
return 0;
pci_set_master(dev);
/*
* Initialize service irqs. Don't use service devices that
* require interrupts if there is no way to generate them.
* However, some drivers may have a polling mode (e.g. pciehp_poll_mode)
* that can be used in the absence of irqs. Allow them to determine
* if that is to be used.
*/
status = init_service_irqs(dev, irqs, capabilities);
if (status) {
capabilities &= PCIE_PORT_SERVICE_VC | PCIE_PORT_SERVICE_HP;
if (!capabilities)
goto error_disable;
}
/* Allocate child services if any */
status = -ENODEV;
nr_service = 0;
for (i = 0; i < PCIE_PORT_DEVICE_MAXSERVICES; i++) {
int service = 1 << i;
if (!(capabilities & service))
continue;
if (!pcie_device_init(dev, service, irqs[i]))
nr_service++;
}
if (!nr_service)
goto error_cleanup_irqs;
return 0;
error_cleanup_irqs:
cleanup_service_irqs(dev);
error_disable:
pci_disable_device(dev);
return status;
}
#ifdef CONFIG_PM
static int suspend_iter(struct device *dev, void *data)
{
struct pcie_port_service_driver *service_driver;
if ((dev->bus == &pcie_port_bus_type) && dev->driver) {
service_driver = to_service_driver(dev->driver);
if (service_driver->suspend)
service_driver->suspend(to_pcie_device(dev));
}
return 0;
}
/**
* pcie_port_device_suspend - suspend port services associated with a PCIe port
* @dev: PCI Express port to handle
*/
int pcie_port_device_suspend(struct device *dev)
{
return device_for_each_child(dev, NULL, suspend_iter);
}
static int resume_iter(struct device *dev, void *data)
{
struct pcie_port_service_driver *service_driver;
if ((dev->bus == &pcie_port_bus_type) &&
(dev->driver)) {
service_driver = to_service_driver(dev->driver);
if (service_driver->resume)
service_driver->resume(to_pcie_device(dev));
}
return 0;
}
/**
* pcie_port_device_resume - resume port services associated with a PCIe port
* @dev: PCI Express port to handle
*/
int pcie_port_device_resume(struct device *dev)
{
return device_for_each_child(dev, NULL, resume_iter);
}
#endif /* PM */
static int remove_iter(struct device *dev, void *data)
{
if (dev->bus == &pcie_port_bus_type)
device_unregister(dev);
return 0;
}
/**
* pcie_port_device_remove - unregister PCI Express port service devices
* @dev: PCI Express port the service devices to unregister are associated with
*
* Remove PCI Express port service devices associated with given port and
* disable MSI-X or MSI for the port.
*/
void pcie_port_device_remove(struct pci_dev *dev)
{
device_for_each_child(&dev->dev, NULL, remove_iter);
cleanup_service_irqs(dev);
pci_disable_device(dev);
}
/**
* pcie_port_probe_service - probe driver for given PCI Express port service
* @dev: PCI Express port service device to probe against
*
* If PCI Express port service driver is registered with
* pcie_port_service_register(), this function will be called by the driver core
* whenever match is found between the driver and a port service device.
*/
static int pcie_port_probe_service(struct device *dev)
{
struct pcie_device *pciedev;
struct pcie_port_service_driver *driver;
int status;
if (!dev || !dev->driver)
return -ENODEV;
driver = to_service_driver(dev->driver);
if (!driver || !driver->probe)
return -ENODEV;
pciedev = to_pcie_device(dev);
status = driver->probe(pciedev);
if (status)
return status;
dev_printk(KERN_DEBUG, dev, "service driver %s loaded\n", driver->name);
get_device(dev);
return 0;
}
/**
* pcie_port_remove_service - detach driver from given PCI Express port service
* @dev: PCI Express port service device to handle
*
* If PCI Express port service driver is registered with
* pcie_port_service_register(), this function will be called by the driver core
* when device_unregister() is called for the port service device associated
* with the driver.
*/
static int pcie_port_remove_service(struct device *dev)
{
struct pcie_device *pciedev;
struct pcie_port_service_driver *driver;
if (!dev || !dev->driver)
return 0;
pciedev = to_pcie_device(dev);
driver = to_service_driver(dev->driver);
if (driver && driver->remove) {
dev_printk(KERN_DEBUG, dev, "unloading service driver %s\n",
driver->name);
driver->remove(pciedev);
put_device(dev);
}
return 0;
}
/**
* pcie_port_shutdown_service - shut down given PCI Express port service
* @dev: PCI Express port service device to handle
*
* If PCI Express port service driver is registered with
* pcie_port_service_register(), this function will be called by the driver core
* when device_shutdown() is called for the port service device associated
* with the driver.
*/
static void pcie_port_shutdown_service(struct device *dev) {}
/**
* pcie_port_service_register - register PCI Express port service driver
* @new: PCI Express port service driver to register
*/
int pcie_port_service_register(struct pcie_port_service_driver *new)
{
if (pcie_ports_disabled)
return -ENODEV;
new->driver.name = new->name;
new->driver.bus = &pcie_port_bus_type;
new->driver.probe = pcie_port_probe_service;
new->driver.remove = pcie_port_remove_service;
new->driver.shutdown = pcie_port_shutdown_service;
return driver_register(&new->driver);
}
EXPORT_SYMBOL(pcie_port_service_register);
/**
* pcie_port_service_unregister - unregister PCI Express port service driver
* @drv: PCI Express port service driver to unregister
*/
void pcie_port_service_unregister(struct pcie_port_service_driver *drv)
{
driver_unregister(&drv->driver);
}
EXPORT_SYMBOL(pcie_port_service_unregister);