From ea08eeccae9297f7aabd2ef7f0c2517ac4549acc Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:18:26 +0000
Subject: [PATCH] write in 30M
---
kernel/drivers/pci/pci.c | 1595 ++++++++++++++++++++++++++++++++++++----------------------
1 files changed, 990 insertions(+), 605 deletions(-)
diff --git a/kernel/drivers/pci/pci.c b/kernel/drivers/pci/pci.c
index 2f72256..e7b45d8 100644
--- a/kernel/drivers/pci/pci.c
+++ b/kernel/drivers/pci/pci.c
@@ -13,8 +13,8 @@
#include <linux/delay.h>
#include <linux/dmi.h>
#include <linux/init.h>
+#include <linux/msi.h>
#include <linux/of.h>
-#include <linux/of_pci.h>
#include <linux/pci.h>
#include <linux/pm.h>
#include <linux/slab.h>
@@ -29,10 +29,11 @@
#include <linux/pm_runtime.h>
#include <linux/pci_hotplug.h>
#include <linux/vmalloc.h>
-#include <linux/pci-ats.h>
-#include <asm/setup.h>
#include <asm/dma.h>
#include <linux/aer.h>
+#ifndef __GENKSYMS__
+#include <trace/hooks/pci.h>
+#endif
#include "pci.h"
DEFINE_MUTEX(pci_slot_mutex);
@@ -48,7 +49,7 @@
int pci_pci_problems;
EXPORT_SYMBOL(pci_pci_problems);
-unsigned int pci_pm_d3_delay;
+unsigned int pci_pm_d3hot_delay;
static void pci_pme_list_scan(struct work_struct *work);
@@ -65,13 +66,17 @@
static void pci_dev_d3_sleep(struct pci_dev *dev)
{
- unsigned int delay = dev->d3_delay;
+ unsigned int delay = dev->d3hot_delay;
+ int err = -EOPNOTSUPP;
- if (delay < pci_pm_d3_delay)
- delay = pci_pm_d3_delay;
+ if (delay < pci_pm_d3hot_delay)
+ delay = pci_pm_d3hot_delay;
- if (delay)
- msleep(delay);
+ if (delay) {
+ trace_android_rvh_pci_d3_sleep(dev, delay, &err);
+ if (err == -EOPNOTSUPP)
+ msleep(delay);
+ }
}
#ifdef CONFIG_PCI_DOMAINS
@@ -85,15 +90,34 @@
unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
#define DEFAULT_HOTPLUG_IO_SIZE (256)
-#define DEFAULT_HOTPLUG_MEM_SIZE (2*1024*1024)
-/* pci=hpmemsize=nnM,hpiosize=nn can override this */
+#define DEFAULT_HOTPLUG_MMIO_SIZE (2*1024*1024)
+#define DEFAULT_HOTPLUG_MMIO_PREF_SIZE (2*1024*1024)
+/* hpiosize=nn can override this */
unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE;
-unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
+/*
+ * pci=hpmmiosize=nnM overrides non-prefetchable MMIO size,
+ * pci=hpmmioprefsize=nnM overrides prefetchable MMIO size;
+ * pci=hpmemsize=nnM overrides both
+ */
+unsigned long pci_hotplug_mmio_size = DEFAULT_HOTPLUG_MMIO_SIZE;
+unsigned long pci_hotplug_mmio_pref_size = DEFAULT_HOTPLUG_MMIO_PREF_SIZE;
#define DEFAULT_HOTPLUG_BUS_SIZE 1
unsigned long pci_hotplug_bus_size = DEFAULT_HOTPLUG_BUS_SIZE;
+
+/* PCIe MPS/MRRS strategy; can be overridden by kernel command-line param */
+#ifdef CONFIG_PCIE_BUS_TUNE_OFF
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF;
+#elif defined CONFIG_PCIE_BUS_SAFE
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_SAFE;
+#elif defined CONFIG_PCIE_BUS_PERFORMANCE
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_PERFORMANCE;
+#elif defined CONFIG_PCIE_BUS_PEER2PEER
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_PEER2PEER;
+#else
enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_DEFAULT;
+#endif
/*
* The default CLS is used if arch didn't set CLS explicitly and not
@@ -123,6 +147,7 @@
{
return pcie_ats_disabled;
}
+EXPORT_SYMBOL_GPL(pci_ats_disabled);
/* Disable bridge_d3 for all PCIe ports */
static bool pci_bridge_d3_disable;
@@ -138,9 +163,6 @@
return 1;
}
__setup("pcie_port_pm=", pcie_port_pm_setup);
-
-/* Time to wait after a reset for device to become responsive */
-#define PCIE_RESET_READY_POLL_MS 60000
/**
* pci_bus_max_busnr - returns maximum PCI bus number of given bus' children
@@ -164,6 +186,29 @@
}
EXPORT_SYMBOL_GPL(pci_bus_max_busnr);
+/**
+ * pci_status_get_and_clear_errors - return and clear error bits in PCI_STATUS
+ * @pdev: the PCI device
+ *
+ * Returns error bits set in PCI_STATUS and clears them.
+ */
+int pci_status_get_and_clear_errors(struct pci_dev *pdev)
+{
+ u16 status;
+ int ret;
+
+ ret = pci_read_config_word(pdev, PCI_STATUS, &status);
+ if (ret != PCIBIOS_SUCCESSFUL)
+ return -EIO;
+
+ status &= PCI_STATUS_ERROR_BITS;
+ if (status)
+ pci_write_config_word(pdev, PCI_STATUS, status);
+
+ return status;
+}
+EXPORT_SYMBOL_GPL(pci_status_get_and_clear_errors);
+
#ifdef CONFIG_HAS_IOMEM
void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
{
@@ -176,7 +221,7 @@
pci_warn(pdev, "can't ioremap BAR %d: %pR\n", bar, res);
return NULL;
}
- return ioremap_nocache(res->start, resource_size(res));
+ return ioremap(res->start, resource_size(res));
}
EXPORT_SYMBOL_GPL(pci_ioremap_bar);
@@ -197,8 +242,8 @@
/**
* pci_dev_str_match_path - test if a path string matches a device
- * @dev: the PCI device to test
- * @p: string to match the device against
+ * @dev: the PCI device to test
+ * @path: string to match the device against
* @endptr: pointer to the string after the match
*
* Test if a string (typically from a kernel parameter) formatted as a
@@ -280,8 +325,8 @@
/**
* pci_dev_str_match - test if a string matches a device
- * @dev: the PCI device to test
- * @p: string to match the device against
+ * @dev: the PCI device to test
+ * @p: string to match the device against
* @endptr: pointer to the string after the match
*
* Test if a string (typically from a kernel parameter) matches a specified
@@ -341,7 +386,7 @@
} else {
/*
* PCI Bus, Device, Function IDs are specified
- * (optionally, may include a path of devfns following it)
+ * (optionally, may include a path of devfns following it)
*/
ret = pci_dev_str_match_path(dev, p, &p);
if (ret < 0)
@@ -425,7 +470,7 @@
* Tell if a device supports a given PCI capability.
* Returns the address of the requested capability structure within the
* device's PCI configuration space or 0 in case the device does not
- * support it. Possible values for @cap:
+ * support it. Possible values for @cap include:
*
* %PCI_CAP_ID_PM Power Management
* %PCI_CAP_ID_AGP Accelerated Graphics Port
@@ -450,11 +495,11 @@
/**
* pci_bus_find_capability - query for devices' capabilities
- * @bus: the PCI bus to query
+ * @bus: the PCI bus to query
* @devfn: PCI device to query
- * @cap: capability code
+ * @cap: capability code
*
- * Like pci_find_capability() but works for pci devices that do not have a
+ * Like pci_find_capability() but works for PCI devices that do not have a
* pci_dev structure set up yet.
*
* Returns the address of the requested capability structure within the
@@ -535,7 +580,7 @@
*
* Returns the address of the requested extended capability structure
* within the device's PCI configuration space or 0 if the device does
- * not support it. Possible values for @cap:
+ * not support it. Possible values for @cap include:
*
* %PCI_EXT_CAP_ID_ERR Advanced Error Reporting
* %PCI_EXT_CAP_ID_VC Virtual Channel
@@ -547,6 +592,40 @@
return pci_find_next_ext_capability(dev, 0, cap);
}
EXPORT_SYMBOL_GPL(pci_find_ext_capability);
+
+/**
+ * pci_get_dsn - Read and return the 8-byte Device Serial Number
+ * @dev: PCI device to query
+ *
+ * Looks up the PCI_EXT_CAP_ID_DSN and reads the 8 bytes of the Device Serial
+ * Number.
+ *
+ * Returns the DSN, or zero if the capability does not exist.
+ */
+u64 pci_get_dsn(struct pci_dev *dev)
+{
+ u32 dword;
+ u64 dsn;
+ int pos;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DSN);
+ if (!pos)
+ return 0;
+
+ /*
+ * The Device Serial Number is two dwords offset 4 bytes from the
+ * capability position. The specification says that the first dword is
+ * the lower half, and the second dword is the upper half.
+ */
+ pos += 4;
+ pci_read_config_dword(dev, pos, &dword);
+ dsn = (u64)dword;
+ pci_read_config_dword(dev, pos + 4, &dword);
+ dsn |= ((u64)dword) << 32;
+
+ return dsn;
+}
+EXPORT_SYMBOL_GPL(pci_get_dsn);
static int __pci_find_next_ht_cap(struct pci_dev *dev, int pos, int ht_cap)
{
@@ -618,12 +697,13 @@
EXPORT_SYMBOL_GPL(pci_find_ht_capability);
/**
- * pci_find_parent_resource - return resource region of parent bus of given region
+ * pci_find_parent_resource - return resource region of parent bus of given
+ * region
* @dev: PCI device structure contains resources to be searched
* @res: child resource record for which parent is sought
*
- * For given resource region of given device, return the resource
- * region of parent bus the given region is contained in.
+ * For given resource region of given device, return the resource region of
+ * parent bus the given region is contained in.
*/
struct resource *pci_find_parent_resource(const struct pci_dev *dev,
struct resource *res)
@@ -673,7 +753,7 @@
{
int i;
- for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+ for (i = 0; i < PCI_STD_NUM_BARS; i++) {
struct resource *r = &dev->resource[i];
if (r->start && resource_contains(r, res))
@@ -683,30 +763,6 @@
return NULL;
}
EXPORT_SYMBOL(pci_find_resource);
-
-/**
- * pci_find_pcie_root_port - return PCIe Root Port
- * @dev: PCI device to query
- *
- * Traverse up the parent chain and return the PCIe Root Port PCI Device
- * for a given PCI Device.
- */
-struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev)
-{
- struct pci_dev *bridge, *highest_pcie_bridge = dev;
-
- bridge = pci_upstream_bridge(dev);
- while (bridge && pci_is_pcie(bridge)) {
- highest_pcie_bridge = bridge;
- bridge = pci_upstream_bridge(bridge);
- }
-
- if (pci_pcie_type(highest_pcie_bridge) != PCI_EXP_TYPE_ROOT_PORT)
- return NULL;
-
- return highest_pcie_bridge;
-}
-EXPORT_SYMBOL(pci_find_pcie_root_port);
/**
* pci_wait_for_pending - wait for @mask bit(s) to clear in status word @pos
@@ -732,6 +788,137 @@
}
return 0;
+}
+
+static int pci_acs_enable;
+
+/**
+ * pci_request_acs - ask for ACS to be enabled if supported
+ */
+void pci_request_acs(void)
+{
+ pci_acs_enable = 1;
+}
+
+static const char *disable_acs_redir_param;
+
+/**
+ * pci_disable_acs_redir - disable ACS redirect capabilities
+ * @dev: the PCI device
+ *
+ * For only devices specified in the disable_acs_redir parameter.
+ */
+static void pci_disable_acs_redir(struct pci_dev *dev)
+{
+ int ret = 0;
+ const char *p;
+ int pos;
+ u16 ctrl;
+
+ if (!disable_acs_redir_param)
+ return;
+
+ p = disable_acs_redir_param;
+ while (*p) {
+ ret = pci_dev_str_match(dev, p, &p);
+ if (ret < 0) {
+ pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n",
+ disable_acs_redir_param);
+
+ break;
+ } else if (ret == 1) {
+ /* Found a match */
+ break;
+ }
+
+ if (*p != ';' && *p != ',') {
+ /* End of param or invalid format */
+ break;
+ }
+ p++;
+ }
+
+ if (ret != 1)
+ return;
+
+ if (!pci_dev_specific_disable_acs_redir(dev))
+ return;
+
+ pos = dev->acs_cap;
+ if (!pos) {
+ pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
+ return;
+ }
+
+ pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+ /* P2P Request & Completion Redirect */
+ ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+ pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+
+ pci_info(dev, "disabled ACS redirect\n");
+}
+
+/**
+ * pci_std_enable_acs - enable ACS on devices using standard ACS capabilities
+ * @dev: the PCI device
+ */
+static void pci_std_enable_acs(struct pci_dev *dev)
+{
+ int pos;
+ u16 cap;
+ u16 ctrl;
+
+ pos = dev->acs_cap;
+ if (!pos)
+ return;
+
+ pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap);
+ pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+ /* Source Validation */
+ ctrl |= (cap & PCI_ACS_SV);
+
+ /* P2P Request Redirect */
+ ctrl |= (cap & PCI_ACS_RR);
+
+ /* P2P Completion Redirect */
+ ctrl |= (cap & PCI_ACS_CR);
+
+ /* Upstream Forwarding */
+ ctrl |= (cap & PCI_ACS_UF);
+
+ /* Enable Translation Blocking for external devices */
+ if (dev->external_facing || dev->untrusted)
+ ctrl |= (cap & PCI_ACS_TB);
+
+ pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+}
+
+/**
+ * pci_enable_acs - enable ACS if hardware support it
+ * @dev: the PCI device
+ */
+static void pci_enable_acs(struct pci_dev *dev)
+{
+ if (!pci_acs_enable)
+ goto disable_acs_redir;
+
+ if (!pci_dev_specific_enable_acs(dev))
+ goto disable_acs_redir;
+
+ pci_std_enable_acs(dev);
+
+disable_acs_redir:
+ /*
+ * Note: pci_disable_acs_redir() must be called even if ACS was not
+ * enabled by the kernel because it may have been enabled by
+ * platform firmware. So if we are told to disable it, we should
+ * always disable it after setting the kernel's default
+ * preferences.
+ */
+ pci_disable_acs_redir(dev);
}
/**
@@ -776,6 +963,12 @@
return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN;
}
+static inline void platform_pci_refresh_power_state(struct pci_dev *dev)
+{
+ if (pci_platform_pm && pci_platform_pm->refresh_state)
+ pci_platform_pm->refresh_state(dev);
+}
+
static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev)
{
return pci_platform_pm ?
@@ -793,9 +986,16 @@
return pci_platform_pm ? pci_platform_pm->need_resume(dev) : false;
}
+static inline bool platform_pci_bridge_d3(struct pci_dev *dev)
+{
+ if (pci_platform_pm && pci_platform_pm->bridge_d3)
+ return pci_platform_pm->bridge_d3(dev);
+ return false;
+}
+
/**
* pci_raw_set_power_state - Use PCI PM registers to set the power state of
- * given PCI device
+ * given PCI device
* @dev: PCI device to handle.
* @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
*
@@ -821,25 +1021,35 @@
if (state < PCI_D0 || state > PCI_D3hot)
return -EINVAL;
- /* Validate current state:
- * Can enter D0 from any state, but if we can only go deeper
- * to sleep if we're already in a low power state
+ /*
+ * Validate transition: We can enter D0 from any state, but if
+ * we're already in a low-power state, we can only go deeper. E.g.,
+ * we can go from D1 to D3, but we can't go directly from D3 to D1;
+ * we'd have to go from D3 to D0, then to D1.
*/
if (state != PCI_D0 && dev->current_state <= PCI_D3cold
&& dev->current_state > state) {
- pci_err(dev, "invalid power transition (from state %d to %d)\n",
- dev->current_state, state);
+ pci_err(dev, "invalid power transition (from %s to %s)\n",
+ pci_power_name(dev->current_state),
+ pci_power_name(state));
return -EINVAL;
}
- /* check if this device supports the desired state */
+ /* Check if this device supports the desired state */
if ((state == PCI_D1 && !dev->d1_support)
|| (state == PCI_D2 && !dev->d2_support))
return -EIO;
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
+ if (pmcsr == (u16) ~0) {
+ pci_err(dev, "can't change power state from %s to %s (config space inaccessible)\n",
+ pci_power_name(dev->current_state),
+ pci_power_name(state));
+ return -EIO;
+ }
- /* If we're (effectively) in D3, force entire word to 0.
+ /*
+ * If we're (effectively) in D3, force entire word to 0.
* This doesn't affect PME_Status, disables PME_En, and
* sets PowerState to 0.
*/
@@ -856,17 +1066,19 @@
if ((pmcsr & PCI_PM_CTRL_STATE_MASK) == PCI_D3hot
&& !(pmcsr & PCI_PM_CTRL_NO_SOFT_RESET))
need_restore = true;
- /* Fall-through: force to D0 */
+ fallthrough; /* force to D0 */
default:
pmcsr = 0;
break;
}
- /* enter specified state */
+ /* Enter specified state */
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, pmcsr);
- /* Mandatory power management transition delays */
- /* see PCI PM 1.1 5.6.1 table 18 */
+ /*
+ * Mandatory power management transition delays; see PCI PM 1.1
+ * 5.6.1 table 18
+ */
if (state == PCI_D3hot || dev->current_state == PCI_D3hot)
pci_dev_d3_sleep(dev);
else if (state == PCI_D2 || dev->current_state == PCI_D2)
@@ -874,9 +1086,10 @@
pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr);
dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
- if (dev->current_state != state && printk_ratelimit())
- pci_info(dev, "Refused to change power state, currently in D%d\n",
- dev->current_state);
+ if (dev->current_state != state)
+ pci_info_ratelimited(dev, "refused to change power state from %s to %s\n",
+ pci_power_name(dev->current_state),
+ pci_power_name(state));
/*
* According to section 5.4.1 of the "PCI BUS POWER MANAGEMENT
@@ -928,11 +1141,26 @@
}
/**
+ * pci_refresh_power_state - Refresh the given device's power state data
+ * @dev: Target PCI device.
+ *
+ * Ask the platform to refresh the devices power state information and invoke
+ * pci_update_current_state() to update its current PCI power state.
+ */
+void pci_refresh_power_state(struct pci_dev *dev)
+{
+ if (platform_pci_power_manageable(dev))
+ platform_pci_refresh_power_state(dev);
+
+ pci_update_current_state(dev, dev->current_state);
+}
+
+/**
* pci_platform_power_transition - Use platform to change device power state
* @dev: PCI device to handle.
* @state: State to put the device into.
*/
-static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
+int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state)
{
int error;
@@ -948,6 +1176,7 @@
return error;
}
+EXPORT_SYMBOL_GPL(pci_platform_power_transition);
/**
* pci_wakeup - Wake up a PCI device
@@ -971,34 +1200,70 @@
pci_walk_bus(bus, pci_wakeup, NULL);
}
-/**
- * __pci_start_power_transition - Start power transition of a PCI device
- * @dev: PCI device to handle.
- * @state: State to put the device into.
- */
-static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state)
+static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
{
- if (state == PCI_D0) {
- pci_platform_power_transition(dev, PCI_D0);
- /*
- * Mandatory power management transition delays, see
- * PCI Express Base Specification Revision 2.0 Section
- * 6.6.1: Conventional Reset. Do not delay for
- * devices powered on/off by corresponding bridge,
- * because have already delayed for the bridge.
- */
- if (dev->runtime_d3cold) {
- if (dev->d3cold_delay)
- msleep(dev->d3cold_delay);
- /*
- * When powering on a bridge from D3cold, the
- * whole hierarchy may be powered on into
- * D0uninitialized state, resume them to give
- * them a chance to suspend again
- */
- pci_wakeup_bus(dev->subordinate);
+ int delay = 1;
+ u32 id;
+
+ /*
+ * After reset, the device should not silently discard config
+ * requests, but it may still indicate that it needs more time by
+ * responding to them with CRS completions. The Root Port will
+ * generally synthesize ~0 data to complete the read (except when
+ * CRS SV is enabled and the read was for the Vendor ID; in that
+ * case it synthesizes 0x0001 data).
+ *
+ * Wait for the device to return a non-CRS completion. Read the
+ * Command register instead of Vendor ID so we don't have to
+ * contend with the CRS SV value.
+ */
+ pci_read_config_dword(dev, PCI_COMMAND, &id);
+ while (id == ~0) {
+ if (delay > timeout) {
+ pci_warn(dev, "not ready %dms after %s; giving up\n",
+ delay - 1, reset_type);
+ return -ENOTTY;
}
+
+ if (delay > PCI_RESET_WAIT)
+ pci_info(dev, "not ready %dms after %s; waiting\n",
+ delay - 1, reset_type);
+
+ msleep(delay);
+ delay *= 2;
+ pci_read_config_dword(dev, PCI_COMMAND, &id);
}
+
+ if (delay > PCI_RESET_WAIT)
+ pci_info(dev, "ready %dms after %s\n", delay - 1,
+ reset_type);
+
+ return 0;
+}
+
+/**
+ * pci_power_up - Put the given device into D0
+ * @dev: PCI device to power up
+ */
+int pci_power_up(struct pci_dev *dev)
+{
+ pci_platform_power_transition(dev, PCI_D0);
+
+ /*
+ * Mandatory power management transition delays are handled in
+ * pci_pm_resume_noirq() and pci_pm_runtime_resume() of the
+ * corresponding bridge.
+ */
+ if (dev->runtime_d3cold) {
+ /*
+ * When powering on a bridge from D3cold, the whole hierarchy
+ * may be powered on into D0uninitialized state, resume them to
+ * give them a chance to suspend again
+ */
+ pci_wakeup_bus(dev->subordinate);
+ }
+
+ return pci_raw_set_power_state(dev, PCI_D0);
}
/**
@@ -1026,27 +1291,6 @@
}
/**
- * __pci_complete_power_transition - Complete power transition of a PCI device
- * @dev: PCI device to handle.
- * @state: State to put the device into.
- *
- * This function should not be called directly by device drivers.
- */
-int __pci_complete_power_transition(struct pci_dev *dev, pci_power_t state)
-{
- int ret;
-
- if (state <= PCI_D0)
- return -EINVAL;
- ret = pci_platform_power_transition(dev, state);
- /* Power off the bridge may power off the whole hierarchy */
- if (!ret && state == PCI_D3cold)
- pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
- return ret;
-}
-EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
-
-/**
* pci_set_power_state - Set the power state of a PCI device
* @dev: PCI device to handle.
* @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
@@ -1067,16 +1311,18 @@
{
int error;
- /* bound the state we're entering */
+ /* Bound the state we're entering */
if (state > PCI_D3cold)
state = PCI_D3cold;
else if (state < PCI_D0)
state = PCI_D0;
else if ((state == PCI_D1 || state == PCI_D2) && pci_no_d1d2(dev))
+
/*
- * If the device or the parent bridge do not support PCI PM,
- * ignore the request if we're doing anything other than putting
- * it into D0 (which would only happen on boot).
+ * If the device or the parent bridge do not support PCI
+ * PM, ignore the request if we're doing anything other
+ * than putting it into D0 (which would only happen on
+ * boot).
*/
return 0;
@@ -1084,10 +1330,13 @@
if (dev->current_state == state)
return 0;
- __pci_start_power_transition(dev, state);
+ if (state == PCI_D0)
+ return pci_power_up(dev);
- /* This device is quirked not to be put into D3, so
- don't put it in D3 */
+ /*
+ * This device is quirked not to be put into D3, so don't put it in
+ * D3
+ */
if (state >= PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
return 0;
@@ -1098,34 +1347,26 @@
error = pci_raw_set_power_state(dev, state > PCI_D3hot ?
PCI_D3hot : state);
- if (!__pci_complete_power_transition(dev, state))
- error = 0;
+ if (pci_platform_power_transition(dev, state))
+ return error;
- return error;
+ /* Powering off a bridge may power off the whole hierarchy */
+ if (state == PCI_D3cold)
+ pci_bus_set_current_state(dev->subordinate, PCI_D3cold);
+
+ return 0;
}
EXPORT_SYMBOL(pci_set_power_state);
-
-/**
- * pci_power_up - Put the given device into D0 forcibly
- * @dev: PCI device to power up
- */
-void pci_power_up(struct pci_dev *dev)
-{
- __pci_start_power_transition(dev, PCI_D0);
- pci_raw_set_power_state(dev, PCI_D0);
- pci_update_current_state(dev, PCI_D0);
-}
/**
* pci_choose_state - Choose the power state of a PCI device
* @dev: PCI device to be suspended
* @state: target sleep state for the whole system. This is the value
- * that is passed to suspend() function.
+ * that is passed to suspend() function.
*
* Returns PCI power state suitable for given device and given system
* message.
*/
-
pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state)
{
pci_power_t ret;
@@ -1226,7 +1467,6 @@
pcie_capability_write_word(dev, PCI_EXP_SLTCTL2, cap[i++]);
}
-
static int pci_save_pcix_state(struct pci_dev *dev)
{
int pos;
@@ -1263,17 +1503,60 @@
pci_write_config_word(dev, pos + PCI_X_CMD, cap[i++]);
}
+static void pci_save_ltr_state(struct pci_dev *dev)
+{
+ int ltr;
+ struct pci_cap_saved_state *save_state;
+ u16 *cap;
+
+ if (!pci_is_pcie(dev))
+ return;
+
+ ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR);
+ if (!ltr)
+ return;
+
+ save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR);
+ if (!save_state) {
+ pci_err(dev, "no suspend buffer for LTR; ASPM issues possible after resume\n");
+ return;
+ }
+
+ cap = (u16 *)&save_state->cap.data[0];
+ pci_read_config_word(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, cap++);
+ pci_read_config_word(dev, ltr + PCI_LTR_MAX_NOSNOOP_LAT, cap++);
+}
+
+static void pci_restore_ltr_state(struct pci_dev *dev)
+{
+ struct pci_cap_saved_state *save_state;
+ int ltr;
+ u16 *cap;
+
+ save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_LTR);
+ ltr = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_LTR);
+ if (!save_state || !ltr)
+ return;
+
+ cap = (u16 *)&save_state->cap.data[0];
+ pci_write_config_word(dev, ltr + PCI_LTR_MAX_SNOOP_LAT, *cap++);
+ pci_write_config_word(dev, ltr + PCI_LTR_MAX_NOSNOOP_LAT, *cap++);
+}
/**
- * pci_save_state - save the PCI configuration space of a device before suspending
- * @dev: - PCI device that we're dealing with
+ * pci_save_state - save the PCI configuration space of a device before
+ * suspending
+ * @dev: PCI device that we're dealing with
*/
int pci_save_state(struct pci_dev *dev)
{
int i;
/* XXX: 100% dword access ok here? */
- for (i = 0; i < 16; i++)
+ for (i = 0; i < 16; i++) {
pci_read_config_dword(dev, i * 4, &dev->saved_config_space[i]);
+ pci_dbg(dev, "saving config space at offset %#x (reading %#x)\n",
+ i * 4, dev->saved_config_space[i]);
+ }
dev->state_saved = true;
i = pci_save_pcie_state(dev);
@@ -1284,6 +1567,9 @@
if (i != 0)
return i;
+ pci_save_ltr_state(dev);
+ pci_save_dpc_state(dev);
+ pci_save_aer_state(dev);
return pci_save_vc_state(dev);
}
EXPORT_SYMBOL(pci_save_state);
@@ -1375,22 +1661,29 @@
/**
* pci_restore_state - Restore the saved state of a PCI device
- * @dev: - PCI device that we're dealing with
+ * @dev: PCI device that we're dealing with
*/
void pci_restore_state(struct pci_dev *dev)
{
if (!dev->state_saved)
return;
- /* PCI Express register must be restored first */
+ /*
+ * Restore max latencies (in the LTR capability) before enabling
+ * LTR itself (in the PCIe capability).
+ */
+ pci_restore_ltr_state(dev);
+
pci_restore_pcie_state(dev);
pci_restore_pasid_state(dev);
pci_restore_pri_state(dev);
pci_restore_ats_state(dev);
pci_restore_vc_state(dev);
pci_restore_rebar_state(dev);
+ pci_restore_dpc_state(dev);
- pci_cleanup_aer_error_status_regs(dev);
+ pci_aer_clear_status(dev);
+ pci_restore_aer_state(dev);
pci_restore_config_space(dev);
@@ -1407,7 +1700,7 @@
struct pci_saved_state {
u32 config_space[16];
- struct pci_cap_saved_data cap[0];
+ struct pci_cap_saved_data cap[];
};
/**
@@ -1546,8 +1839,8 @@
* pci_reenable_device - Resume abandoned device
* @dev: PCI device to be resumed
*
- * Note this function is a backend of pci_default_resume and is not supposed
- * to be called by normal code, write proper resume handler and use it instead.
+ * NOTE: This function is a backend of pci_default_resume() and is not supposed
+ * to be called by normal code, write proper resume handler and use it instead.
*/
int pci_reenable_device(struct pci_dev *dev)
{
@@ -1618,9 +1911,9 @@
* pci_enable_device_io - Initialize a device for use with IO space
* @dev: PCI device to be initialized
*
- * Initialize device before it's used by a driver. Ask low-level code
- * to enable I/O resources. Wake up the device if it was suspended.
- * Beware, this function can fail.
+ * Initialize device before it's used by a driver. Ask low-level code
+ * to enable I/O resources. Wake up the device if it was suspended.
+ * Beware, this function can fail.
*/
int pci_enable_device_io(struct pci_dev *dev)
{
@@ -1632,9 +1925,9 @@
* pci_enable_device_mem - Initialize a device for use with Memory space
* @dev: PCI device to be initialized
*
- * Initialize device before it's used by a driver. Ask low-level code
- * to enable Memory resources. Wake up the device if it was suspended.
- * Beware, this function can fail.
+ * Initialize device before it's used by a driver. Ask low-level code
+ * to enable Memory resources. Wake up the device if it was suspended.
+ * Beware, this function can fail.
*/
int pci_enable_device_mem(struct pci_dev *dev)
{
@@ -1646,12 +1939,12 @@
* pci_enable_device - Initialize device before it's used by a driver.
* @dev: PCI device to be initialized
*
- * Initialize device before it's used by a driver. Ask low-level code
- * to enable I/O and memory. Wake up the device if it was suspended.
- * Beware, this function can fail.
+ * Initialize device before it's used by a driver. Ask low-level code
+ * to enable I/O and memory. Wake up the device if it was suspended.
+ * Beware, this function can fail.
*
- * Note we don't actually enable the device many times if we call
- * this function repeatedly (we just increment the count).
+ * Note we don't actually enable the device many times if we call
+ * this function repeatedly (we just increment the count).
*/
int pci_enable_device(struct pci_dev *dev)
{
@@ -1660,8 +1953,8 @@
EXPORT_SYMBOL(pci_enable_device);
/*
- * Managed PCI resources. This manages device on/off, intx/msi/msix
- * on/off and BAR regions. pci_dev itself records msi/msix status, so
+ * Managed PCI resources. This manages device on/off, INTx/MSI/MSI-X
+ * on/off and BAR regions. pci_dev itself records MSI/MSI-X status, so
* there's no need to track it separately. pci_devres is initialized
* when a device is enabled using managed PCI device enable interface.
*/
@@ -1779,7 +2072,8 @@
}
/**
- * pcibios_release_device - provide arch specific hooks when releasing device dev
+ * pcibios_release_device - provide arch specific hooks when releasing
+ * device dev
* @dev: the PCI device being released
*
* Permits the platform to provide architecture specific functionality when
@@ -1870,8 +2164,7 @@
* @dev: the PCIe device reset
* @state: Reset state to enter into
*
- *
- * Sets the PCIe reset state for the device. This is the default
+ * Set the PCIe reset state for the device. This is the default
* implementation. Architecture implementations can override this.
*/
int __weak pcibios_set_pcie_reset_state(struct pci_dev *dev,
@@ -1885,7 +2178,6 @@
* @dev: the PCIe device reset
* @state: Reset state to enter into
*
- *
* Sets the PCI reset state for the device.
*/
int pci_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
@@ -1893,6 +2185,14 @@
return pcibios_set_pcie_reset_state(dev, state);
}
EXPORT_SYMBOL_GPL(pci_set_pcie_reset_state);
+
+void pcie_clear_device_status(struct pci_dev *dev)
+{
+ u16 sta;
+
+ pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta);
+ pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta);
+}
/**
* pcie_clear_root_pme_status - Clear root port PME interrupt status.
@@ -2147,10 +2447,13 @@
int ret = 0;
/*
- * Bridges can only signal wakeup on behalf of subordinate devices,
- * but that is set up elsewhere, so skip them.
+ * Bridges that are not power-manageable directly only signal
+ * wakeup on behalf of subordinate devices which is set up
+ * elsewhere, so skip them. However, bridges that are
+ * power-manageable may signal wakeup for themselves (for example,
+ * on a hotplug event) and they need to be covered here.
*/
- if (pci_has_subordinate(dev))
+ if (!pci_power_manageable(dev))
return 0;
/* Don't do the same thing twice in a row for one device. */
@@ -2258,7 +2561,7 @@
case PCI_D2:
if (pci_no_d1d2(dev))
break;
- /* else: fall through */
+ fallthrough;
default:
target_state = state;
}
@@ -2297,7 +2600,8 @@
}
/**
- * pci_prepare_to_sleep - prepare PCI device for system-wide transition into a sleep state
+ * pci_prepare_to_sleep - prepare PCI device for system-wide transition
+ * into a sleep state
* @dev: Device to handle.
*
* Choose the power state appropriate for the device depending on whether
@@ -2325,7 +2629,8 @@
EXPORT_SYMBOL(pci_prepare_to_sleep);
/**
- * pci_back_from_sleep - turn PCI device on during system-wide transition into working state
+ * pci_back_from_sleep - turn PCI device on during system-wide transition
+ * into working state
* @dev: Device to handle.
*
* Disable device's system wake-up capability and put it into D0.
@@ -2407,45 +2712,56 @@
EXPORT_SYMBOL_GPL(pci_dev_run_wake);
/**
- * pci_dev_keep_suspended - Check if the device can stay in the suspended state.
+ * pci_dev_need_resume - Check if it is necessary to resume the device.
* @pci_dev: Device to check.
*
- * Return 'true' if the device is runtime-suspended, it doesn't have to be
+ * Return 'true' if the device is not runtime-suspended or it has to be
* reconfigured due to wakeup settings difference between system and runtime
- * suspend and the current power state of it is suitable for the upcoming
- * (system) transition.
- *
- * If the device is not configured for system wakeup, disable PME for it before
- * returning 'true' to prevent it from waking up the system unnecessarily.
+ * suspend, or the current power state of it is not suitable for the upcoming
+ * (system-wide) transition.
*/
-bool pci_dev_keep_suspended(struct pci_dev *pci_dev)
+bool pci_dev_need_resume(struct pci_dev *pci_dev)
{
struct device *dev = &pci_dev->dev;
- bool wakeup = device_may_wakeup(dev);
+ pci_power_t target_state;
- if (!pm_runtime_suspended(dev)
- || pci_target_state(pci_dev, wakeup) != pci_dev->current_state
- || platform_pci_need_resume(pci_dev))
- return false;
+ if (!pm_runtime_suspended(dev) || platform_pci_need_resume(pci_dev))
+ return true;
+
+ target_state = pci_target_state(pci_dev, device_may_wakeup(dev));
/*
- * At this point the device is good to go unless it's been configured
- * to generate PME at the runtime suspend time, but it is not supposed
- * to wake up the system. In that case, simply disable PME for it
- * (it will have to be re-enabled on exit from system resume).
- *
- * If the device's power state is D3cold and the platform check above
- * hasn't triggered, the device's configuration is suitable and we don't
- * need to manipulate it at all.
+ * If the earlier platform check has not triggered, D3cold is just power
+ * removal on top of D3hot, so no need to resume the device in that
+ * case.
*/
+ return target_state != pci_dev->current_state &&
+ target_state != PCI_D3cold &&
+ pci_dev->current_state != PCI_D3hot;
+}
+
+/**
+ * pci_dev_adjust_pme - Adjust PME setting for a suspended device.
+ * @pci_dev: Device to check.
+ *
+ * If the device is suspended and it is not configured for system wakeup,
+ * disable PME for it to prevent it from waking up the system unnecessarily.
+ *
+ * Note that if the device's power state is D3cold and the platform check in
+ * pci_dev_need_resume() has not triggered, the device's configuration need not
+ * be changed.
+ */
+void pci_dev_adjust_pme(struct pci_dev *pci_dev)
+{
+ struct device *dev = &pci_dev->dev;
+
spin_lock_irq(&dev->power.lock);
- if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold &&
- !wakeup)
+ if (pm_runtime_suspended(dev) && !device_may_wakeup(dev) &&
+ pci_dev->current_state < PCI_D3cold)
__pci_pme_active(pci_dev, false);
spin_unlock_irq(&dev->power.lock);
- return true;
}
/**
@@ -2518,6 +2834,18 @@
DMI_MATCH(DMI_BOARD_NAME, "X299 DESIGNARE EX-CF"),
},
},
+ {
+ /*
+ * Downstream device is not accessible after putting a root port
+ * into D3cold and back into D0 on Elo Continental Z2 board
+ */
+ .ident = "Elo Continental Z2",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Elo Touch Solutions"),
+ DMI_MATCH(DMI_BOARD_NAME, "Geminilake"),
+ DMI_MATCH(DMI_BOARD_VERSION, "Continental Z2"),
+ },
+ },
#endif
{ }
};
@@ -2553,6 +2881,10 @@
/* Even the oldest 2010 Thunderbolt controller supports D3. */
if (bridge->is_thunderbolt)
+ return true;
+
+ /* Platform might know better if the bridge supports D3 */
+ if (platform_pci_bridge_d3(bridge))
return true;
/*
@@ -2691,6 +3023,7 @@
void pci_pm_init(struct pci_dev *dev)
{
int pm;
+ u16 status;
u16 pmc;
pm_runtime_forbid(&dev->dev);
@@ -2716,7 +3049,7 @@
}
dev->pm_cap = pm;
- dev->d3_delay = PCI_PM_D3_WAIT;
+ dev->d3hot_delay = PCI_PM_D3HOT_WAIT;
dev->d3cold_delay = PCI_PM_D3COLD_WAIT;
dev->bridge_d3 = pci_bridge_d3_possible(dev);
dev->d3cold_allowed = true;
@@ -2730,18 +3063,18 @@
dev->d2_support = true;
if (dev->d1_support || dev->d2_support)
- pci_printk(KERN_DEBUG, dev, "supports%s%s\n",
+ pci_info(dev, "supports%s%s\n",
dev->d1_support ? " D1" : "",
dev->d2_support ? " D2" : "");
}
pmc &= PCI_PM_CAP_PME_MASK;
if (pmc) {
- pci_printk(KERN_DEBUG, dev, "PME# supported from%s%s%s%s%s\n",
+ pci_info(dev, "PME# supported from%s%s%s%s%s\n",
(pmc & PCI_PM_CAP_PME_D0) ? " D0" : "",
(pmc & PCI_PM_CAP_PME_D1) ? " D1" : "",
(pmc & PCI_PM_CAP_PME_D2) ? " D2" : "",
- (pmc & PCI_PM_CAP_PME_D3) ? " D3hot" : "",
+ (pmc & PCI_PM_CAP_PME_D3hot) ? " D3hot" : "",
(pmc & PCI_PM_CAP_PME_D3cold) ? " D3cold" : "");
dev->pme_support = pmc >> PCI_PM_CAP_PME_SHIFT;
dev->pme_poll = true;
@@ -2753,6 +3086,10 @@
/* Disable the PME# generation functionality */
pci_pme_active(dev, false);
}
+
+ pci_read_config_word(dev, PCI_STATUS, &status);
+ if (status & PCI_STATUS_IMM_READY)
+ dev->imm_ready = 1;
}
static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop)
@@ -2901,16 +3238,16 @@
res->flags = flags;
if (bei <= PCI_EA_BEI_BAR5)
- pci_printk(KERN_DEBUG, dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
+ pci_info(dev, "BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
bei, res, prop);
else if (bei == PCI_EA_BEI_ROM)
- pci_printk(KERN_DEBUG, dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n",
+ pci_info(dev, "ROM: %pR (from Enhanced Allocation, properties %#02x)\n",
res, prop);
else if (bei >= PCI_EA_BEI_VF_BAR0 && bei <= PCI_EA_BEI_VF_BAR5)
- pci_printk(KERN_DEBUG, dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
+ pci_info(dev, "VF BAR %d: %pR (from Enhanced Allocation, properties %#02x)\n",
bei - PCI_EA_BEI_VF_BAR0, res, prop);
else
- pci_printk(KERN_DEBUG, dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n",
+ pci_info(dev, "BEI %d res: %pR (from Enhanced Allocation, properties %#02x)\n",
bei, res, prop);
out:
@@ -2954,7 +3291,7 @@
/**
* _pci_add_cap_save_buffer - allocate buffer for saving given
- * capability registers
+ * capability registers
* @dev: the PCI device
* @cap: the capability to allocate the buffer for
* @extended: Standard or Extended capability ID
@@ -3013,6 +3350,11 @@
if (error)
pci_err(dev, "unable to preallocate PCI-X save buffer\n");
+ error = pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_LTR,
+ 2 * sizeof(u16));
+ if (error)
+ pci_err(dev, "unable to allocate suspend buffer for LTR\n");
+
pci_allocate_vc_save_buffers(dev);
}
@@ -3059,140 +3401,12 @@
}
}
-static int pci_acs_enable;
-
-/**
- * pci_request_acs - ask for ACS to be enabled if supported
- */
-void pci_request_acs(void)
-{
- pci_acs_enable = 1;
-}
-EXPORT_SYMBOL_GPL(pci_request_acs);
-
-static const char *disable_acs_redir_param;
-
-/**
- * pci_disable_acs_redir - disable ACS redirect capabilities
- * @dev: the PCI device
- *
- * For only devices specified in the disable_acs_redir parameter.
- */
-static void pci_disable_acs_redir(struct pci_dev *dev)
-{
- int ret = 0;
- const char *p;
- int pos;
- u16 ctrl;
-
- if (!disable_acs_redir_param)
- return;
-
- p = disable_acs_redir_param;
- while (*p) {
- ret = pci_dev_str_match(dev, p, &p);
- if (ret < 0) {
- pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n",
- disable_acs_redir_param);
-
- break;
- } else if (ret == 1) {
- /* Found a match */
- break;
- }
-
- if (*p != ';' && *p != ',') {
- /* End of param or invalid format */
- break;
- }
- p++;
- }
-
- if (ret != 1)
- return;
-
- if (!pci_dev_specific_disable_acs_redir(dev))
- return;
-
- pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
- if (!pos) {
- pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
- return;
- }
-
- pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
-
- /* P2P Request & Completion Redirect */
- ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
-
- pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
-
- pci_info(dev, "disabled ACS redirect\n");
-}
-
-/**
- * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
- * @dev: the PCI device
- */
-static void pci_std_enable_acs(struct pci_dev *dev)
-{
- int pos;
- u16 cap;
- u16 ctrl;
-
- pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
- if (!pos)
- return;
-
- pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap);
- pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
-
- /* Source Validation */
- ctrl |= (cap & PCI_ACS_SV);
-
- /* P2P Request Redirect */
- ctrl |= (cap & PCI_ACS_RR);
-
- /* P2P Completion Redirect */
- ctrl |= (cap & PCI_ACS_CR);
-
- /* Upstream Forwarding */
- ctrl |= (cap & PCI_ACS_UF);
-
- pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
-}
-
-/**
- * pci_enable_acs - enable ACS if hardware support it
- * @dev: the PCI device
- */
-void pci_enable_acs(struct pci_dev *dev)
-{
- if (!pci_acs_enable)
- goto disable_acs_redir;
-
- if (!pci_dev_specific_enable_acs(dev))
- goto disable_acs_redir;
-
- pci_std_enable_acs(dev);
-
-disable_acs_redir:
- /*
- * Note: pci_disable_acs_redir() must be called even if ACS was not
- * enabled by the kernel because it may have been enabled by
- * platform firmware. So if we are told to disable it, we should
- * always disable it after setting the kernel's default
- * preferences.
- */
- pci_disable_acs_redir(dev);
-}
-
static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
{
int pos;
u16 cap, ctrl;
- pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS);
+ pos = pdev->acs_cap;
if (!pos)
return false;
@@ -3315,6 +3529,23 @@
} while (pdev != end);
return true;
+}
+
+/**
+ * pci_acs_init - Initialize ACS if hardware supports it
+ * @dev: the PCI device
+ */
+void pci_acs_init(struct pci_dev *dev)
+{
+ dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+
+ /*
+ * Attempt to enable ACS regardless of capability because some Root
+ * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have
+ * the standard ACS capability but still support ACS via those
+ * quirks.
+ */
+ pci_enable_acs(dev);
}
/**
@@ -3484,7 +3715,7 @@
}
/* Ensure upstream ports don't block AtomicOps on egress */
- if (!bridge->has_secondary_link) {
+ if (pci_pcie_type(bridge) == PCI_EXP_TYPE_UPSTREAM) {
pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2,
&ctl2);
if (ctl2 & PCI_EXP_DEVCTL2_ATOMIC_EGRESS_BLOCK)
@@ -3561,13 +3792,14 @@
EXPORT_SYMBOL_GPL(pci_common_swizzle);
/**
- * pci_release_region - Release a PCI bar
- * @pdev: PCI device whose resources were previously reserved by pci_request_region
- * @bar: BAR to release
+ * pci_release_region - Release a PCI bar
+ * @pdev: PCI device whose resources were previously reserved by
+ * pci_request_region()
+ * @bar: BAR to release
*
- * Releases the PCI I/O and memory resources previously reserved by a
- * successful call to pci_request_region. Call this function only
- * after all use of the PCI regions has ceased.
+ * Releases the PCI I/O and memory resources previously reserved by a
+ * successful call to pci_request_region(). Call this function only
+ * after all use of the PCI regions has ceased.
*/
void pci_release_region(struct pci_dev *pdev, int bar)
{
@@ -3589,23 +3821,23 @@
EXPORT_SYMBOL(pci_release_region);
/**
- * __pci_request_region - Reserved PCI I/O and memory resource
- * @pdev: PCI device whose resources are to be reserved
- * @bar: BAR to be reserved
- * @res_name: Name to be associated with resource.
- * @exclusive: whether the region access is exclusive or not
+ * __pci_request_region - Reserved PCI I/O and memory resource
+ * @pdev: PCI device whose resources are to be reserved
+ * @bar: BAR to be reserved
+ * @res_name: Name to be associated with resource.
+ * @exclusive: whether the region access is exclusive or not
*
- * Mark the PCI region associated with PCI device @pdev BR @bar as
- * being reserved by owner @res_name. Do not access any
- * address inside the PCI regions unless this call returns
- * successfully.
+ * Mark the PCI region associated with PCI device @pdev BAR @bar as
+ * being reserved by owner @res_name. Do not access any
+ * address inside the PCI regions unless this call returns
+ * successfully.
*
- * If @exclusive is set, then the region is marked so that userspace
- * is explicitly not allowed to map the resource via /dev/mem or
- * sysfs MMIO access.
+ * If @exclusive is set, then the region is marked so that userspace
+ * is explicitly not allowed to map the resource via /dev/mem or
+ * sysfs MMIO access.
*
- * Returns 0 on success, or %EBUSY on error. A warning
- * message is also printed on failure.
+ * Returns 0 on success, or %EBUSY on error. A warning
+ * message is also printed on failure.
*/
static int __pci_request_region(struct pci_dev *pdev, int bar,
const char *res_name, int exclusive)
@@ -3639,49 +3871,24 @@
}
/**
- * pci_request_region - Reserve PCI I/O and memory resource
- * @pdev: PCI device whose resources are to be reserved
- * @bar: BAR to be reserved
- * @res_name: Name to be associated with resource
+ * pci_request_region - Reserve PCI I/O and memory resource
+ * @pdev: PCI device whose resources are to be reserved
+ * @bar: BAR to be reserved
+ * @res_name: Name to be associated with resource
*
- * Mark the PCI region associated with PCI device @pdev BAR @bar as
- * being reserved by owner @res_name. Do not access any
- * address inside the PCI regions unless this call returns
- * successfully.
+ * Mark the PCI region associated with PCI device @pdev BAR @bar as
+ * being reserved by owner @res_name. Do not access any
+ * address inside the PCI regions unless this call returns
+ * successfully.
*
- * Returns 0 on success, or %EBUSY on error. A warning
- * message is also printed on failure.
+ * Returns 0 on success, or %EBUSY on error. A warning
+ * message is also printed on failure.
*/
int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
{
return __pci_request_region(pdev, bar, res_name, 0);
}
EXPORT_SYMBOL(pci_request_region);
-
-/**
- * pci_request_region_exclusive - Reserved PCI I/O and memory resource
- * @pdev: PCI device whose resources are to be reserved
- * @bar: BAR to be reserved
- * @res_name: Name to be associated with resource.
- *
- * Mark the PCI region associated with PCI device @pdev BR @bar as
- * being reserved by owner @res_name. Do not access any
- * address inside the PCI regions unless this call returns
- * successfully.
- *
- * Returns 0 on success, or %EBUSY on error. A warning
- * message is also printed on failure.
- *
- * The key difference that _exclusive makes it that userspace is
- * explicitly not allowed to map the resource via /dev/mem or
- * sysfs.
- */
-int pci_request_region_exclusive(struct pci_dev *pdev, int bar,
- const char *res_name)
-{
- return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE);
-}
-EXPORT_SYMBOL(pci_request_region_exclusive);
/**
* pci_release_selected_regions - Release selected PCI I/O and memory resources
@@ -3695,7 +3902,7 @@
{
int i;
- for (i = 0; i < 6; i++)
+ for (i = 0; i < PCI_STD_NUM_BARS; i++)
if (bars & (1 << i))
pci_release_region(pdev, i);
}
@@ -3706,7 +3913,7 @@
{
int i;
- for (i = 0; i < 6; i++)
+ for (i = 0; i < PCI_STD_NUM_BARS; i++)
if (bars & (1 << i))
if (__pci_request_region(pdev, i, res_name, excl))
goto err_out;
@@ -3743,65 +3950,66 @@
EXPORT_SYMBOL(pci_request_selected_regions_exclusive);
/**
- * pci_release_regions - Release reserved PCI I/O and memory resources
- * @pdev: PCI device whose resources were previously reserved by pci_request_regions
+ * pci_release_regions - Release reserved PCI I/O and memory resources
+ * @pdev: PCI device whose resources were previously reserved by
+ * pci_request_regions()
*
- * Releases all PCI I/O and memory resources previously reserved by a
- * successful call to pci_request_regions. Call this function only
- * after all use of the PCI regions has ceased.
+ * Releases all PCI I/O and memory resources previously reserved by a
+ * successful call to pci_request_regions(). Call this function only
+ * after all use of the PCI regions has ceased.
*/
void pci_release_regions(struct pci_dev *pdev)
{
- pci_release_selected_regions(pdev, (1 << 6) - 1);
+ pci_release_selected_regions(pdev, (1 << PCI_STD_NUM_BARS) - 1);
}
EXPORT_SYMBOL(pci_release_regions);
/**
- * pci_request_regions - Reserved PCI I/O and memory resources
- * @pdev: PCI device whose resources are to be reserved
- * @res_name: Name to be associated with resource.
+ * pci_request_regions - Reserve PCI I/O and memory resources
+ * @pdev: PCI device whose resources are to be reserved
+ * @res_name: Name to be associated with resource.
*
- * Mark all PCI regions associated with PCI device @pdev as
- * being reserved by owner @res_name. Do not access any
- * address inside the PCI regions unless this call returns
- * successfully.
+ * Mark all PCI regions associated with PCI device @pdev as
+ * being reserved by owner @res_name. Do not access any
+ * address inside the PCI regions unless this call returns
+ * successfully.
*
- * Returns 0 on success, or %EBUSY on error. A warning
- * message is also printed on failure.
+ * Returns 0 on success, or %EBUSY on error. A warning
+ * message is also printed on failure.
*/
int pci_request_regions(struct pci_dev *pdev, const char *res_name)
{
- return pci_request_selected_regions(pdev, ((1 << 6) - 1), res_name);
+ return pci_request_selected_regions(pdev,
+ ((1 << PCI_STD_NUM_BARS) - 1), res_name);
}
EXPORT_SYMBOL(pci_request_regions);
/**
- * pci_request_regions_exclusive - Reserved PCI I/O and memory resources
- * @pdev: PCI device whose resources are to be reserved
- * @res_name: Name to be associated with resource.
+ * pci_request_regions_exclusive - Reserve PCI I/O and memory resources
+ * @pdev: PCI device whose resources are to be reserved
+ * @res_name: Name to be associated with resource.
*
- * Mark all PCI regions associated with PCI device @pdev as
- * being reserved by owner @res_name. Do not access any
- * address inside the PCI regions unless this call returns
- * successfully.
+ * Mark all PCI regions associated with PCI device @pdev as being reserved
+ * by owner @res_name. Do not access any address inside the PCI regions
+ * unless this call returns successfully.
*
- * pci_request_regions_exclusive() will mark the region so that
- * /dev/mem and the sysfs MMIO access will not be allowed.
+ * pci_request_regions_exclusive() will mark the region so that /dev/mem
+ * and the sysfs MMIO access will not be allowed.
*
- * Returns 0 on success, or %EBUSY on error. A warning
- * message is also printed on failure.
+ * Returns 0 on success, or %EBUSY on error. A warning message is also
+ * printed on failure.
*/
int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
{
return pci_request_selected_regions_exclusive(pdev,
- ((1 << 6) - 1), res_name);
+ ((1 << PCI_STD_NUM_BARS) - 1), res_name);
}
EXPORT_SYMBOL(pci_request_regions_exclusive);
/*
* Record the PCI IO range (expressed as CPU physical address + size).
- * Return a negative value if an error has occured, zero otherwise
+ * Return a negative value if an error has occurred, zero otherwise
*/
int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr,
resource_size_t size)
@@ -3847,6 +4055,7 @@
return address;
}
+EXPORT_SYMBOL_GPL(pci_pio_to_address);
unsigned long __weak pci_address_to_pio(phys_addr_t address)
{
@@ -3861,14 +4070,14 @@
}
/**
- * pci_remap_iospace - Remap the memory mapped I/O space
- * @res: Resource describing the I/O space
- * @phys_addr: physical address of range to be mapped
+ * pci_remap_iospace - Remap the memory mapped I/O space
+ * @res: Resource describing the I/O space
+ * @phys_addr: physical address of range to be mapped
*
- * Remap the memory mapped I/O space described by the @res
- * and the CPU physical address @phys_addr into virtual address space.
- * Only architectures that have memory mapped IO functions defined
- * (and the PCI_IOBASE value defined) should call this function.
+ * Remap the memory mapped I/O space described by the @res and the CPU
+ * physical address @phys_addr into virtual address space. Only
+ * architectures that have memory mapped IO functions defined (and the
+ * PCI_IOBASE value defined) should call this function.
*/
int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
{
@@ -3884,8 +4093,10 @@
return ioremap_page_range(vaddr, vaddr + resource_size(res), phys_addr,
pgprot_device(PAGE_KERNEL));
#else
- /* this architecture does not have memory mapped I/O space,
- so this function should never be called */
+ /*
+ * This architecture does not have memory mapped I/O space,
+ * so this function should never be called
+ */
WARN_ONCE(1, "This architecture does not support memory mapped I/O\n");
return -ENODEV;
#endif
@@ -3893,12 +4104,12 @@
EXPORT_SYMBOL(pci_remap_iospace);
/**
- * pci_unmap_iospace - Unmap the memory mapped I/O space
- * @res: resource to be unmapped
+ * pci_unmap_iospace - Unmap the memory mapped I/O space
+ * @res: resource to be unmapped
*
- * Unmap the CPU virtual address @res from virtual address space.
- * Only architectures that have memory mapped IO functions defined
- * (and the PCI_IOBASE value defined) should call this function.
+ * Unmap the CPU virtual address @res from virtual address space. Only
+ * architectures that have memory mapped IO functions defined (and the
+ * PCI_IOBASE value defined) should call this function.
*/
void pci_unmap_iospace(struct resource *res)
{
@@ -4141,7 +4352,7 @@
if (cacheline_size == pci_cache_line_size)
return 0;
- pci_printk(KERN_DEBUG, dev, "cache line size of %d is not supported\n",
+ pci_info(dev, "cache line size of %d is not supported\n",
pci_cache_line_size << 2);
return -EINVAL;
@@ -4244,7 +4455,7 @@
* @pdev: the PCI device to operate on
* @enable: boolean: whether to enable or disable PCI INTx
*
- * Enables/disables PCI INTx for device dev
+ * Enables/disables PCI INTx for device @pdev
*/
void pci_intx(struct pci_dev *pdev, int enable)
{
@@ -4320,9 +4531,8 @@
* pci_check_and_mask_intx - mask INTx on pending interrupt
* @dev: the PCI device to operate on
*
- * Check if the device dev has its INTx line asserted, mask it and
- * return true in that case. False is returned if no interrupt was
- * pending.
+ * Check if the device dev has its INTx line asserted, mask it and return
+ * true in that case. False is returned if no interrupt was pending.
*/
bool pci_check_and_mask_intx(struct pci_dev *dev)
{
@@ -4334,9 +4544,9 @@
* pci_check_and_unmask_intx - unmask INTx if no interrupt is pending
* @dev: the PCI device to operate on
*
- * Check if the device dev has its INTx line asserted, unmask it if not
- * and return true. False is returned and the mask remains active if
- * there was still an interrupt pending.
+ * Check if the device dev has its INTx line asserted, unmask it if not and
+ * return true. False is returned and the mask remains active if there was
+ * still an interrupt pending.
*/
bool pci_check_and_unmask_intx(struct pci_dev *dev)
{
@@ -4345,7 +4555,7 @@
EXPORT_SYMBOL_GPL(pci_check_and_unmask_intx);
/**
- * pci_wait_for_pending_transaction - waits for pending transaction
+ * pci_wait_for_pending_transaction - wait for pending transaction
* @dev: the PCI device to operate on
*
* Return 0 if transaction is pending 1 otherwise.
@@ -4360,50 +4570,9 @@
}
EXPORT_SYMBOL(pci_wait_for_pending_transaction);
-static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
-{
- int delay = 1;
- u32 id;
-
- /*
- * After reset, the device should not silently discard config
- * requests, but it may still indicate that it needs more time by
- * responding to them with CRS completions. The Root Port will
- * generally synthesize ~0 data to complete the read (except when
- * CRS SV is enabled and the read was for the Vendor ID; in that
- * case it synthesizes 0x0001 data).
- *
- * Wait for the device to return a non-CRS completion. Read the
- * Command register instead of Vendor ID so we don't have to
- * contend with the CRS SV value.
- */
- pci_read_config_dword(dev, PCI_COMMAND, &id);
- while (id == ~0) {
- if (delay > timeout) {
- pci_warn(dev, "not ready %dms after %s; giving up\n",
- delay - 1, reset_type);
- return -ENOTTY;
- }
-
- if (delay > 1000)
- pci_info(dev, "not ready %dms after %s; waiting\n",
- delay - 1, reset_type);
-
- msleep(delay);
- delay *= 2;
- pci_read_config_dword(dev, PCI_COMMAND, &id);
- }
-
- if (delay > 1000)
- pci_info(dev, "ready %dms after %s\n", delay - 1,
- reset_type);
-
- return 0;
-}
-
/**
* pcie_has_flr - check if a device supports function level resets
- * @dev: device to check
+ * @dev: device to check
*
* Returns true if the device advertises support for PCIe function level
* resets.
@@ -4422,7 +4591,7 @@
/**
* pcie_flr - initiate a PCIe function level reset
- * @dev: device to reset
+ * @dev: device to reset
*
* Initiate a function level reset on @dev. The caller should ensure the
* device supports FLR before calling this function, e.g. by using the
@@ -4434,6 +4603,9 @@
pci_err(dev, "timed out waiting for pending transaction; performing function level reset anyway\n");
pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR);
+
+ if (dev->imm_ready)
+ return 0;
/*
* Per PCIe r4.0, sec 6.6.2, a device must complete an FLR within
@@ -4467,7 +4639,7 @@
/*
* Wait for Transaction Pending bit to clear. A word-aligned test
- * is used, so we use the conrol offset rather than status and shift
+ * is used, so we use the control offset rather than status and shift
* the test bit to match.
*/
if (!pci_wait_for_pending(dev, pos + PCI_AF_CTRL,
@@ -4475,6 +4647,9 @@
pci_err(dev, "timed out waiting for pending transaction; performing AF function level reset anyway\n");
pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
+
+ if (dev->imm_ready)
+ return 0;
/*
* Per Advanced Capabilities for Conventional PCI ECN, 13 April 2006,
@@ -4499,7 +4674,7 @@
*
* NOTE: This causes the caller to sleep for twice the device power transition
* cooldown period, which for the D0->D3hot and D3hot->D0 transitions is 10 ms
- * by default (i.e. unless the @dev's d3_delay field has a different value).
+ * by default (i.e. unless the @dev's d3hot_delay field has a different value).
* Moreover, only devices in D0 can be reset by this function.
*/
static int pci_pm_reset(struct pci_dev *dev, int probe)
@@ -4529,8 +4704,60 @@
pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr);
pci_dev_d3_sleep(dev);
- return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS);
+ return pci_dev_wait(dev, "PM D3hot->D0", PCIE_RESET_READY_POLL_MS);
}
+
+/**
+ * pcie_wait_for_link_delay - Wait until link is active or inactive
+ * @pdev: Bridge device
+ * @active: waiting for active or inactive?
+ * @delay: Delay to wait after link has become active (in ms)
+ *
+ * Use this to wait till link becomes active or inactive.
+ */
+static bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active,
+ int delay)
+{
+ int timeout = 1000;
+ bool ret;
+ u16 lnk_status;
+
+ /*
+ * Some controllers might not implement link active reporting. In this
+ * case, we wait for 1000 ms + any delay requested by the caller.
+ */
+ if (!pdev->link_active_reporting) {
+ msleep(timeout + delay);
+ return true;
+ }
+
+ /*
+ * PCIe r4.0 sec 6.6.1, a component must enter LTSSM Detect within 20ms,
+ * after which we should expect an link active if the reset was
+ * successful. If so, software must wait a minimum 100ms before sending
+ * configuration requests to devices downstream this port.
+ *
+ * If the link fails to activate, either the device was physically
+ * removed or the link is permanently failed.
+ */
+ if (active)
+ msleep(20);
+ for (;;) {
+ pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+ ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+ if (ret == active)
+ break;
+ if (timeout <= 0)
+ break;
+ msleep(10);
+ timeout -= 10;
+ }
+ if (active && ret)
+ msleep(delay);
+
+ return ret == active;
+}
+
/**
* pcie_wait_for_link - Wait until link is active or inactive
* @pdev: Bridge device
@@ -4540,25 +4767,129 @@
*/
bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
{
- int timeout = 1000;
- bool ret;
- u16 lnk_status;
+ return pcie_wait_for_link_delay(pdev, active, 100);
+}
- for (;;) {
- pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
- ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
- if (ret == active)
- return true;
- if (timeout <= 0)
- break;
- msleep(10);
- timeout -= 10;
+/*
+ * Find maximum D3cold delay required by all the devices on the bus. The
+ * spec says 100 ms, but firmware can lower it and we allow drivers to
+ * increase it as well.
+ *
+ * Called with @pci_bus_sem locked for reading.
+ */
+static int pci_bus_max_d3cold_delay(const struct pci_bus *bus)
+{
+ const struct pci_dev *pdev;
+ int min_delay = 100;
+ int max_delay = 0;
+
+ list_for_each_entry(pdev, &bus->devices, bus_list) {
+ if (pdev->d3cold_delay < min_delay)
+ min_delay = pdev->d3cold_delay;
+ if (pdev->d3cold_delay > max_delay)
+ max_delay = pdev->d3cold_delay;
}
- pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n",
- active ? "set" : "cleared");
+ return max(min_delay, max_delay);
+}
- return false;
+/**
+ * pci_bridge_wait_for_secondary_bus - Wait for secondary bus to be accessible
+ * @dev: PCI bridge
+ * @reset_type: reset type in human-readable form
+ * @timeout: maximum time to wait for devices on secondary bus (milliseconds)
+ *
+ * Handle necessary delays before access to the devices on the secondary
+ * side of the bridge are permitted after D3cold to D0 transition
+ * or Conventional Reset.
+ *
+ * For PCIe this means the delays in PCIe 5.0 section 6.6.1. For
+ * conventional PCI it means Tpvrh + Trhfa specified in PCI 3.0 section
+ * 4.3.2.
+ *
+ * Return 0 on success or -ENOTTY if the first device on the secondary bus
+ * failed to become accessible.
+ */
+int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type,
+ int timeout)
+{
+ struct pci_dev *child;
+ int delay;
+
+ if (pci_dev_is_disconnected(dev))
+ return 0;
+
+ if (!pci_is_bridge(dev))
+ return 0;
+
+ down_read(&pci_bus_sem);
+
+ /*
+ * We only deal with devices that are present currently on the bus.
+ * For any hot-added devices the access delay is handled in pciehp
+ * board_added(). In case of ACPI hotplug the firmware is expected
+ * to configure the devices before OS is notified.
+ */
+ if (!dev->subordinate || list_empty(&dev->subordinate->devices)) {
+ up_read(&pci_bus_sem);
+ return 0;
+ }
+
+ /* Take d3cold_delay requirements into account */
+ delay = pci_bus_max_d3cold_delay(dev->subordinate);
+ if (!delay) {
+ up_read(&pci_bus_sem);
+ return 0;
+ }
+
+ child = list_first_entry(&dev->subordinate->devices, struct pci_dev,
+ bus_list);
+ up_read(&pci_bus_sem);
+
+ /*
+ * Conventional PCI and PCI-X we need to wait Tpvrh + Trhfa before
+ * accessing the device after reset (that is 1000 ms + 100 ms).
+ */
+ if (!pci_is_pcie(dev)) {
+ pci_dbg(dev, "waiting %d ms for secondary bus\n", 1000 + delay);
+ msleep(1000 + delay);
+ return 0;
+ }
+
+ /*
+ * For PCIe downstream and root ports that do not support speeds
+ * greater than 5 GT/s need to wait minimum 100 ms. For higher
+ * speeds (gen3) we need to wait first for the data link layer to
+ * become active.
+ *
+ * However, 100 ms is the minimum and the PCIe spec says the
+ * software must allow at least 1s before it can determine that the
+ * device that did not respond is a broken device. There is
+ * evidence that 100 ms is not always enough, for example certain
+ * Titan Ridge xHCI controller does not always respond to
+ * configuration requests if we only wait for 100 ms (see
+ * https://bugzilla.kernel.org/show_bug.cgi?id=203885).
+ *
+ * Therefore we wait for 100 ms and check for the device presence
+ * until the timeout expires.
+ */
+ if (!pcie_downstream_port(dev))
+ return 0;
+
+ if (pcie_get_speed_cap(dev) <= PCIE_SPEED_5_0GT) {
+ pci_dbg(dev, "waiting %d ms for downstream link\n", delay);
+ msleep(delay);
+ } else {
+ pci_dbg(dev, "waiting %d ms for downstream link, after activation\n",
+ delay);
+ if (!pcie_wait_for_link_delay(dev, true, delay)) {
+ /* Did not train, no need to wait any further */
+ pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n");
+ return -ENOTTY;
+ }
+ }
+
+ return pci_dev_wait(child, reset_type, timeout - delay);
}
void pci_reset_secondary_bus(struct pci_dev *dev)
@@ -4577,15 +4908,6 @@
ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl);
-
- /*
- * Trhfa for conventional PCI is 2^25 clock cycles.
- * Assuming a minimum 33MHz clock this results in a 1s
- * delay before we can consider subordinate devices to
- * be re-initialized. PCIe has some ways to shorten this,
- * but we don't make use of them yet.
- */
- ssleep(1);
}
void __weak pcibios_reset_secondary_bus(struct pci_dev *dev)
@@ -4604,7 +4926,8 @@
{
pcibios_reset_secondary_bus(dev);
- return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS);
+ return pci_bridge_wait_for_secondary_bus(dev, "bus reset",
+ PCIE_RESET_READY_POLL_MS);
}
EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset);
@@ -4630,46 +4953,40 @@
{
int rc = -ENOTTY;
- if (!hotplug || !try_module_get(hotplug->ops->owner))
+ if (!hotplug || !try_module_get(hotplug->owner))
return rc;
if (hotplug->ops->reset_slot)
rc = hotplug->ops->reset_slot(hotplug, probe);
- module_put(hotplug->ops->owner);
+ module_put(hotplug->owner);
return rc;
}
static int pci_dev_reset_slot_function(struct pci_dev *dev, int probe)
{
- struct pci_dev *pdev;
-
- if (dev->subordinate || !dev->slot ||
+ if (dev->multifunction || dev->subordinate || !dev->slot ||
dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)
return -ENOTTY;
-
- list_for_each_entry(pdev, &dev->bus->devices, bus_list)
- if (pdev != dev && pdev->slot == dev->slot)
- return -ENOTTY;
return pci_reset_hotplug_slot(dev->slot->hotplug, probe);
}
static void pci_dev_lock(struct pci_dev *dev)
{
- pci_cfg_access_lock(dev);
/* block PM suspend, driver probe, etc. */
device_lock(&dev->dev);
+ pci_cfg_access_lock(dev);
}
/* Return 1 on successful lock, 0 on contention */
static int pci_dev_trylock(struct pci_dev *dev)
{
- if (pci_cfg_access_trylock(dev)) {
- if (device_trylock(&dev->dev))
+ if (device_trylock(&dev->dev)) {
+ if (pci_cfg_access_trylock(dev))
return 1;
- pci_cfg_access_unlock(dev);
+ device_unlock(&dev->dev);
}
return 0;
@@ -4677,8 +4994,8 @@
static void pci_dev_unlock(struct pci_dev *dev)
{
- device_unlock(&dev->dev);
pci_cfg_access_unlock(dev);
+ device_unlock(&dev->dev);
}
static void pci_dev_save_and_disable(struct pci_dev *dev)
@@ -4739,6 +5056,7 @@
*
* The device function is presumed to be unused and the caller is holding
* the device mutex lock when this function is called.
+ *
* Resetting the device will make the contents of PCI configuration space
* random, so any caller of this must be prepared to reinitialise the
* device including MSI, bus mastering, BARs, decoding IO and memory spaces,
@@ -5302,8 +5620,8 @@
* pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
* @dev: PCI device to query
*
- * Returns mmrbc: maximum designed memory read count in bytes
- * or appropriate error value.
+ * Returns mmrbc: maximum designed memory read count in bytes or
+ * appropriate error value.
*/
int pcix_get_max_mmrbc(struct pci_dev *dev)
{
@@ -5325,8 +5643,8 @@
* pcix_get_mmrbc - get PCI-X maximum memory read byte count
* @dev: PCI device to query
*
- * Returns mmrbc: maximum memory read count in bytes
- * or appropriate error value.
+ * Returns mmrbc: maximum memory read count in bytes or appropriate error
+ * value.
*/
int pcix_get_mmrbc(struct pci_dev *dev)
{
@@ -5350,7 +5668,7 @@
* @mmrbc: maximum memory read count in bytes
* valid values are 512, 1024, 2048, 4096
*
- * If possible sets maximum memory read byte count, some bridges have erratas
+ * If possible sets maximum memory read byte count, some bridges have errata
* that prevent this.
*/
int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc)
@@ -5395,8 +5713,7 @@
* pcie_get_readrq - get PCI Express read request size
* @dev: PCI device to query
*
- * Returns maximum memory read request in bytes
- * or appropriate error value.
+ * Returns maximum memory read request in bytes or appropriate error value.
*/
int pcie_get_readrq(struct pci_dev *dev)
{
@@ -5419,15 +5736,15 @@
int pcie_set_readrq(struct pci_dev *dev, int rq)
{
u16 v;
+ int ret;
if (rq < 128 || rq > 4096 || !is_power_of_2(rq))
return -EINVAL;
/*
- * If using the "performance" PCIe config, we clamp the
- * read rq size to the max packet size to prevent the
- * host bridge generating requests larger than we can
- * cope with
+ * If using the "performance" PCIe config, we clamp the read rq
+ * size to the max packet size to keep the host bridge from
+ * generating requests larger than we can cope with.
*/
if (pcie_bus_config == PCIE_BUS_PERFORMANCE) {
int mps = pcie_get_mps(dev);
@@ -5438,8 +5755,10 @@
v = (ffs(rq) - 8) << 12;
- return pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
+ ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
PCI_EXP_DEVCTL_READRQ, v);
+
+ return pcibios_err_to_errno(ret);
}
EXPORT_SYMBOL(pcie_set_readrq);
@@ -5470,6 +5789,7 @@
int pcie_set_mps(struct pci_dev *dev, int mps)
{
u16 v;
+ int ret;
if (mps < 128 || mps > 4096 || !is_power_of_2(mps))
return -EINVAL;
@@ -5479,8 +5799,10 @@
return -EINVAL;
v <<= 5;
- return pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
+ ret = pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL,
PCI_EXP_DEVCTL_PAYLOAD, v);
+
+ return pcibios_err_to_errno(ret);
}
EXPORT_SYMBOL(pcie_set_mps);
@@ -5563,17 +5885,10 @@
* where only 2.5 GT/s and 5.0 GT/s speeds were defined.
*/
pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2);
- if (lnkcap2) { /* PCIe r3.0-compliant */
- if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_16_0GB)
- return PCIE_SPEED_16_0GT;
- else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
- return PCIE_SPEED_8_0GT;
- else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB)
- return PCIE_SPEED_5_0GT;
- else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB)
- return PCIE_SPEED_2_5GT;
- return PCI_SPEED_UNKNOWN;
- }
+
+ /* PCIe r3.0-compliant */
+ if (lnkcap2)
+ return PCIE_LNKCAP2_SLS2SPEED(lnkcap2);
pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB)
@@ -5649,14 +5964,14 @@
if (bw_avail >= bw_cap && verbose)
pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
bw_cap / 1000, bw_cap % 1000,
- PCIE_SPEED2STR(speed_cap), width_cap);
+ pci_speed_string(speed_cap), width_cap);
else if (bw_avail < bw_cap)
pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
bw_avail / 1000, bw_avail % 1000,
- PCIE_SPEED2STR(speed), width,
+ pci_speed_string(speed), width,
limiting_dev ? pci_name(limiting_dev) : "<unknown>",
bw_cap / 1000, bw_cap % 1000,
- PCIE_SPEED2STR(speed_cap), width_cap);
+ pci_speed_string(speed_cap), width_cap);
}
/**
@@ -5730,7 +6045,7 @@
if (flags & PCI_VGA_STATE_CHANGE_DECODES) {
pci_read_config_word(dev, PCI_COMMAND, &cmd);
- if (decode == true)
+ if (decode)
cmd |= command_bits;
else
cmd &= ~command_bits;
@@ -5746,7 +6061,7 @@
if (bridge) {
pci_read_config_word(bridge, PCI_BRIDGE_CONTROL,
&cmd);
- if (decode == true)
+ if (decode)
cmd |= PCI_BRIDGE_CTL_VGA;
else
cmd &= ~PCI_BRIDGE_CTL_VGA;
@@ -5758,10 +6073,29 @@
return 0;
}
+#ifdef CONFIG_ACPI
+bool pci_pr3_present(struct pci_dev *pdev)
+{
+ struct acpi_device *adev;
+
+ if (acpi_disabled)
+ return false;
+
+ adev = ACPI_COMPANION(&pdev->dev);
+ if (!adev)
+ return false;
+
+ return adev->power.flags.power_resources &&
+ acpi_has_method(adev->handle, "_PR3");
+}
+EXPORT_SYMBOL_GPL(pci_pr3_present);
+#endif
+
/**
* pci_add_dma_alias - Add a DMA devfn alias for a device
* @dev: the PCI device for which alias is added
- * @devfn: alias slot and function
+ * @devfn_from: alias slot and function
+ * @nr_devfns: number of subsequent devfns to alias
*
* This helper encodes an 8-bit devfn as a bit number in dma_alias_mask
* which is used to program permissible bus-devfn source addresses for DMA
@@ -5777,19 +6111,29 @@
* cannot be left as a userspace activity). DMA aliases should therefore
* be configured via quirks, such as the PCI fixup header quirk.
*/
-void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
+void pci_add_dma_alias(struct pci_dev *dev, u8 devfn_from, unsigned nr_devfns)
{
+ int devfn_to;
+
+ nr_devfns = min(nr_devfns, (unsigned) MAX_NR_DEVFNS - devfn_from);
+ devfn_to = devfn_from + nr_devfns - 1;
+
if (!dev->dma_alias_mask)
- dev->dma_alias_mask = kcalloc(BITS_TO_LONGS(U8_MAX),
- sizeof(long), GFP_KERNEL);
+ dev->dma_alias_mask = bitmap_zalloc(MAX_NR_DEVFNS, GFP_KERNEL);
if (!dev->dma_alias_mask) {
pci_warn(dev, "Unable to allocate DMA alias mask\n");
return;
}
- set_bit(devfn, dev->dma_alias_mask);
- pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
- PCI_SLOT(devfn), PCI_FUNC(devfn));
+ bitmap_set(dev->dma_alias_mask, devfn_from, nr_devfns);
+
+ if (nr_devfns == 1)
+ pci_info(dev, "Enabling fixed DMA alias to %02x.%d\n",
+ PCI_SLOT(devfn_from), PCI_FUNC(devfn_from));
+ else if (nr_devfns > 1)
+ pci_info(dev, "Enabling fixed DMA alias for devfn range from %02x.%d to %02x.%d\n",
+ PCI_SLOT(devfn_from), PCI_FUNC(devfn_from),
+ PCI_SLOT(devfn_to), PCI_FUNC(devfn_to));
}
bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2)
@@ -5797,13 +6141,17 @@
return (dev1->dma_alias_mask &&
test_bit(dev2->devfn, dev1->dma_alias_mask)) ||
(dev2->dma_alias_mask &&
- test_bit(dev1->devfn, dev2->dma_alias_mask));
+ test_bit(dev1->devfn, dev2->dma_alias_mask)) ||
+ pci_real_dma_dev(dev1) == dev2 ||
+ pci_real_dma_dev(dev2) == dev1;
}
bool pci_device_is_present(struct pci_dev *pdev)
{
u32 v;
+ /* Check PF if pdev is a VF, since VF Vendor/Device IDs are 0xffff */
+ pdev = pci_physfn(pdev);
if (pci_dev_is_disconnected(pdev))
return false;
return pci_bus_read_dev_vendor_id(pdev->bus, pdev->devfn, &v, 0);
@@ -5821,13 +6169,39 @@
}
EXPORT_SYMBOL_GPL(pci_ignore_hotplug);
+/**
+ * pci_real_dma_dev - Get PCI DMA device for PCI device
+ * @dev: the PCI device that may have a PCI DMA alias
+ *
+ * Permits the platform to provide architecture-specific functionality to
+ * devices needing to alias DMA to another PCI device on another PCI bus. If
+ * the PCI device is on the same bus, it is recommended to use
+ * pci_add_dma_alias(). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+struct pci_dev __weak *pci_real_dma_dev(struct pci_dev *dev)
+{
+ return dev;
+}
+
resource_size_t __weak pcibios_default_alignment(void)
{
return 0;
}
-#define RESOURCE_ALIGNMENT_PARAM_SIZE COMMAND_LINE_SIZE
-static char resource_alignment_param[RESOURCE_ALIGNMENT_PARAM_SIZE] = {0};
+/*
+ * Arches that don't want to expose struct resource to userland as-is in
+ * sysfs and /proc can implement their own pci_resource_to_user().
+ */
+void __weak pci_resource_to_user(const struct pci_dev *dev, int bar,
+ const struct resource *rsrc,
+ resource_size_t *start, resource_size_t *end)
+{
+ *start = rsrc->start;
+ *end = rsrc->end;
+}
+
+static char *resource_alignment_param;
static DEFINE_SPINLOCK(resource_alignment_lock);
/**
@@ -5848,7 +6222,7 @@
spin_lock(&resource_alignment_lock);
p = resource_alignment_param;
- if (!*p && !align)
+ if (!p || !*p)
goto out;
if (pci_has_flag(PCI_PROBE_ONLY)) {
align = 0;
@@ -6001,8 +6375,7 @@
* to enable the kernel to reassign new resource
* window later on.
*/
- if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE &&
- (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI) {
+ if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) {
r = &dev->resource[i];
if (!(r->flags & IORESOURCE_MEM))
@@ -6015,39 +6388,44 @@
}
}
-static ssize_t pci_set_resource_alignment_param(const char *buf, size_t count)
+static ssize_t resource_alignment_show(struct bus_type *bus, char *buf)
{
- if (count > RESOURCE_ALIGNMENT_PARAM_SIZE - 1)
- count = RESOURCE_ALIGNMENT_PARAM_SIZE - 1;
+ size_t count = 0;
+
spin_lock(&resource_alignment_lock);
- strncpy(resource_alignment_param, buf, count);
- resource_alignment_param[count] = '\0';
+ if (resource_alignment_param)
+ count = scnprintf(buf, PAGE_SIZE, "%s", resource_alignment_param);
spin_unlock(&resource_alignment_lock);
+
+ /*
+ * When set by the command line, resource_alignment_param will not
+ * have a trailing line feed, which is ugly. So conditionally add
+ * it here.
+ */
+ if (count >= 2 && buf[count - 2] != '\n' && count < PAGE_SIZE - 1) {
+ buf[count - 1] = '\n';
+ buf[count++] = 0;
+ }
+
return count;
}
-static ssize_t pci_get_resource_alignment_param(char *buf, size_t size)
-{
- size_t count;
- spin_lock(&resource_alignment_lock);
- count = snprintf(buf, size, "%s", resource_alignment_param);
- spin_unlock(&resource_alignment_lock);
- return count;
-}
-
-static ssize_t pci_resource_alignment_show(struct bus_type *bus, char *buf)
-{
- return pci_get_resource_alignment_param(buf, PAGE_SIZE);
-}
-
-static ssize_t pci_resource_alignment_store(struct bus_type *bus,
+static ssize_t resource_alignment_store(struct bus_type *bus,
const char *buf, size_t count)
{
- return pci_set_resource_alignment_param(buf, count);
+ char *param = kstrndup(buf, count, GFP_KERNEL);
+
+ if (!param)
+ return -ENOMEM;
+
+ spin_lock(&resource_alignment_lock);
+ kfree(resource_alignment_param);
+ resource_alignment_param = param;
+ spin_unlock(&resource_alignment_lock);
+ return count;
}
-static BUS_ATTR(resource_alignment, 0644, pci_resource_alignment_show,
- pci_resource_alignment_store);
+static BUS_ATTR_RW(resource_alignment);
static int __init pci_resource_alignment_sysfs_init(void)
{
@@ -6078,6 +6456,7 @@
if (parent)
domain = of_get_pci_domain_nr(parent->of_node);
+
/*
* Check DT domain and use_dt_domains values.
*
@@ -6172,14 +6551,18 @@
} else if (!strncmp(str, "cbmemsize=", 10)) {
pci_cardbus_mem_size = memparse(str + 10, &str);
} else if (!strncmp(str, "resource_alignment=", 19)) {
- pci_set_resource_alignment_param(str + 19,
- strlen(str + 19));
+ resource_alignment_param = str + 19;
} else if (!strncmp(str, "ecrc=", 5)) {
pcie_ecrc_get_policy(str + 5);
} else if (!strncmp(str, "hpiosize=", 9)) {
pci_hotplug_io_size = memparse(str + 9, &str);
+ } else if (!strncmp(str, "hpmmiosize=", 11)) {
+ pci_hotplug_mmio_size = memparse(str + 11, &str);
+ } else if (!strncmp(str, "hpmmioprefsize=", 15)) {
+ pci_hotplug_mmio_pref_size = memparse(str + 15, &str);
} else if (!strncmp(str, "hpmemsize=", 10)) {
- pci_hotplug_mem_size = memparse(str + 10, &str);
+ pci_hotplug_mmio_size = memparse(str + 10, &str);
+ pci_hotplug_mmio_pref_size = pci_hotplug_mmio_size;
} else if (!strncmp(str, "hpbussize=", 10)) {
pci_hotplug_bus_size =
simple_strtoul(str + 10, &str, 0);
@@ -6198,8 +6581,7 @@
} else if (!strncmp(str, "disable_acs_redir=", 18)) {
disable_acs_redir_param = str + 18;
} else {
- printk(KERN_ERR "PCI: Unknown option `%s'\n",
- str);
+ pr_err("PCI: Unknown option `%s'\n", str);
}
}
str = k;
@@ -6209,15 +6591,18 @@
early_param("pci", pci_setup);
/*
- * 'disable_acs_redir_param' is initialized in pci_setup(), above, to point
- * to data in the __initdata section which will be freed after the init
- * sequence is complete. We can't allocate memory in pci_setup() because some
- * architectures do not have any memory allocation service available during
- * an early_param() call. So we allocate memory and copy the variable here
- * before the init section is freed.
+ * 'resource_alignment_param' and 'disable_acs_redir_param' are initialized
+ * in pci_setup(), above, to point to data in the __initdata section which
+ * will be freed after the init sequence is complete. We can't allocate memory
+ * in pci_setup() because some architectures do not have any memory allocation
+ * service available during an early_param() call. So we allocate memory and
+ * copy the variable here before the init section is freed.
+ *
*/
static int __init pci_realloc_setup_params(void)
{
+ resource_alignment_param = kstrdup(resource_alignment_param,
+ GFP_KERNEL);
disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL);
return 0;
--
Gitblit v1.6.2