1
0
Files
kernel-49/arch/powerpc/kernel/eeh_pe.c
Greg Kroah-Hartman 5cb458a786 Merge 4.9.204 into android-4.9-q
Changes in 4.9.204
	net/mlx4_en: fix mlx4 ethtool -N insertion
	net: rtnetlink: prevent underflows in do_setvfinfo()
	sfc: Only cancel the PPS workqueue if it exists
	net/mlx5e: Fix set vf link state error flow
	net/sched: act_pedit: fix WARN() in the traffic path
	gpio: max77620: Fixup debounce delays
	tools: gpio: Correctly add make dependencies for gpio_utils
	Revert "fs: ocfs2: fix possible null-pointer dereferences in ocfs2_xa_prepare_entry()"
	mm/ksm.c: don't WARN if page is still mapped in remove_stable_node()
	platform/x86: asus-nb-wmi: Support ALS on the Zenbook UX430UQ
	platform/x86: asus-wmi: Only Tell EC the OS will handle display hotkeys from asus_nb_wmi
	mwifiex: Fix NL80211_TX_POWER_LIMITED
	ALSA: isight: fix leak of reference to firewire unit in error path of .probe callback
	printk: fix integer overflow in setup_log_buf()
	gfs2: Fix marking bitmaps non-full
	synclink_gt(): fix compat_ioctl()
	powerpc: Fix signedness bug in update_flash_db()
	powerpc/eeh: Fix use of EEH_PE_KEEP on wrong field
	brcmsmac: AP mode: update beacon when TIM changes
	ath10k: allocate small size dma memory in ath10k_pci_diag_write_mem
	spi: sh-msiof: fix deferred probing
	mmc: mediatek: fix cannot receive new request when msdc_cmd_is_ready fail
	btrfs: handle error of get_old_root
	gsmi: Fix bug in append_to_eventlog sysfs handler
	misc: mic: fix a DMA pool free failure
	m68k: fix command-line parsing when passed from u-boot
	amiflop: clean up on errors during setup
	scsi: ips: fix missing break in switch
	KVM/x86: Fix invvpid and invept register operand size in 64-bit mode
	scsi: isci: Use proper enumerated type in atapi_d2h_reg_frame_handler
	scsi: isci: Change sci_controller_start_task's return type to sci_status
	scsi: iscsi_tcp: Explicitly cast param in iscsi_sw_tcp_host_get_param
	clk: mmp2: fix the clock id for sdh2_clk and sdh3_clk
	ASoC: tegra_sgtl5000: fix device_node refcounting
	scsi: dc395x: fix dma API usage in srb_done
	scsi: dc395x: fix DMA API usage in sg_update_list
	net: fix warning in af_unix
	net: ena: Fix Kconfig dependency on X86
	xfs: fix use-after-free race in xfs_buf_rele
	kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack
	ALSA: i2c/cs8427: Fix int to char conversion
	macintosh/windfarm_smu_sat: Fix debug output
	USB: misc: appledisplay: fix backlight update_status return code
	usbip: tools: fix atoi() on non-null terminated string
	SUNRPC: Fix a compile warning for cmpxchg64()
	sunrpc: safely reallow resvport min/max inversion
	atm: zatm: Fix empty body Clang warnings
	s390/perf: Return error when debug_register fails
	spi: omap2-mcspi: Set FIFO DMA trigger level to word length
	sparc: Fix parport build warnings.
	ceph: fix dentry leak in ceph_readdir_prepopulate
	rtc: s35390a: Change buf's type to u8 in s35390a_init
	f2fs: fix to spread clear_cold_data()
	mISDN: Fix type of switch control variable in ctrl_teimanager
	qlcnic: fix a return in qlcnic_dcb_get_capability()
	net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
	mfd: arizona: Correct calling of runtime_put_sync
	mfd: mc13xxx-core: Fix PMIC shutdown when reading ADC values
	mfd: max8997: Enale irq-wakeup unconditionally
	selftests/ftrace: Fix to test kprobe $comm arg only if available
	thermal: rcar_thermal: Prevent hardware access during system suspend
	powerpc/process: Fix flush_all_to_thread for SPE
	sparc64: Rework xchg() definition to avoid warnings.
	fs/ocfs2/dlm/dlmdebug.c: fix a sleep-in-atomic-context bug in dlm_print_one_mle()
	mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock
	macsec: update operstate when lower device changes
	macsec: let the administrator set UP state even if lowerdev is down
	um: Make line/tty semantics use true write IRQ
	linux/bitmap.h: handle constant zero-size bitmaps correctly
	linux/bitmap.h: fix type of nbits in bitmap_shift_right()
	hfsplus: fix BUG on bnode parent update
	hfs: fix BUG on bnode parent update
	hfsplus: prevent btree data loss on ENOSPC
	hfs: prevent btree data loss on ENOSPC
	hfsplus: fix return value of hfsplus_get_block()
	hfs: fix return value of hfs_get_block()
	hfsplus: update timestamps on truncate()
	hfs: update timestamp on truncate()
	fs/hfs/extent.c: fix array out of bounds read of array extent
	mm/memory_hotplug: make add_memory() take the device_hotplug_lock
	igb: shorten maximum PHC timecounter update interval
	ntb_netdev: fix sleep time mismatch
	ntb: intel: fix return value for ndev_vec_mask()
	arm64: makefile fix build of .i file in external module case
	ocfs2: don't put and assigning null to bh allocated outside
	ocfs2: fix clusters leak in ocfs2_defrag_extent()
	net: do not abort bulk send on BQL status
	sched/fair: Don't increase sd->balance_interval on newidle balance
	audit: print empty EXECVE args
	wlcore: Fix the return value in case of error in 'wlcore_vendor_cmd_smart_config_start()'
	rtl8xxxu: Fix missing break in switch
	brcmsmac: never log "tid x is not agg'able" by default
	wireless: airo: potential buffer overflow in sprintf()
	rtlwifi: rtl8192de: Fix misleading REG_MCUFWDL information
	scsi: mpt3sas: Fix Sync cache command failure during driver unload
	scsi: mpt3sas: Fix driver modifying persistent data in Manufacturing page11
	scsi: megaraid_sas: Fix msleep granularity
	scsi: lpfc: fcoe: Fix link down issue after 1000+ link bounces
	dlm: fix invalid free
	dlm: don't leak kernel pointer to userspace
	ACPICA: Use %d for signed int print formatting instead of %u
	net: bcmgenet: return correct value 'ret' from bcmgenet_power_down
	sock: Reset dst when changing sk_mark via setsockopt
	pinctrl: qcom: spmi-gpio: fix gpio-hog related boot issues
	pinctrl: lpc18xx: Use define directive for PIN_CONFIG_GPIO_PIN_INT
	pinctrl: zynq: Use define directive for PIN_CONFIG_IO_STANDARD
	PCI: keystone: Use quirk to limit MRRS for K2G
	spi: omap2-mcspi: Fix DMA and FIFO event trigger size mismatch
	mm/memory_hotplug: Do not unlock when fails to take the device_hotplug_lock
	Bluetooth: Fix invalid-free in bcsp_close()
	KVM: MMU: Do not treat ZONE_DEVICE pages as being reserved
	ath9k_hw: fix uninitialized variable data
	dm: use blk_set_queue_dying() in __dm_destroy()
	arm64: fix for bad_mode() handler to always result in panic
	cpufreq: Skip cpufreq resume if it's not suspended
	ocfs2: remove ocfs2_is_o2cb_active()
	ARM: 8904/1: skip nomap memblocks while finding the lowmem/highmem boundary
	ARC: perf: Accommodate big-endian CPU
	x86/insn: Fix awk regexp warnings
	x86/speculation: Fix incorrect MDS/TAA mitigation status
	x86/speculation: Fix redundant MDS mitigation message
	nfc: port100: handle command failure cleanly
	l2tp: don't use l2tp_tunnel_find() in l2tp_ip and l2tp_ip6
	media: vivid: Set vid_cap_streaming and vid_out_streaming to true
	media: vivid: Fix wrong locking that causes race conditions on streaming stop
	media: usbvision: Fix races among open, close, and disconnect
	cpufreq: Add NULL checks to show() and store() methods of cpufreq
	media: uvcvideo: Fix error path in control parsing failure
	media: b2c2-flexcop-usb: add sanity checking
	media: cxusb: detect cxusb_ctrl_msg error in query
	media: imon: invalid dereference in imon_touch_event
	virtio_console: reset on out of memory
	virtio_console: don't tie bufs to a vq
	virtio_console: allocate inbufs in add_port() only if it is needed
	virtio_ring: fix return code on DMA mapping fails
	virtio_console: fix uninitialized variable use
	virtio_console: drop custom control queue cleanup
	virtio_console: move removal code
	usbip: tools: fix fd leakage in the function of read_attr_usbip_status
	usb-serial: cp201x: support Mark-10 digital force gauge
	USB: chaoskey: fix error case of a timeout
	appledisplay: fix error handling in the scheduled work
	USB: serial: mos7840: add USB ID to support Moxa UPort 2210
	USB: serial: mos7720: fix remote wakeup
	USB: serial: mos7840: fix remote wakeup
	USB: serial: option: add support for DW5821e with eSIM support
	USB: serial: option: add support for Foxconn T77W968 LTE modules
	staging: comedi: usbduxfast: usbduxfast_ai_cmdtest rounding error
	powerpc/64s: support nospectre_v2 cmdline option
	powerpc/book3s64: Fix link stack flush on context switch
	KVM: PPC: Book3S HV: Flush link stack on guest exit to host kernel
	Linux 4.9.204

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2019-12-02 12:51:20 +03:00

949 lines
24 KiB
C

/*
* The file intends to implement PE based on the information from
* platforms. Basically, there have 3 types of PEs: PHB/Bus/Device.
* All the PEs should be organized as hierarchy tree. The first level
* of the tree will be associated to existing PHBs since the particular
* PE is only meaningful in one PHB domain.
*
* Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/delay.h>
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/kernel.h>
#include <linux/pci.h>
#include <linux/string.h>
#include <asm/pci-bridge.h>
#include <asm/ppc-pci.h>
static int eeh_pe_aux_size = 0;
static LIST_HEAD(eeh_phb_pe);
/**
* eeh_set_pe_aux_size - Set PE auxillary data size
* @size: PE auxillary data size
*
* Set PE auxillary data size
*/
void eeh_set_pe_aux_size(int size)
{
if (size < 0)
return;
eeh_pe_aux_size = size;
}
/**
* eeh_pe_alloc - Allocate PE
* @phb: PCI controller
* @type: PE type
*
* Allocate PE instance dynamically.
*/
static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type)
{
struct eeh_pe *pe;
size_t alloc_size;
alloc_size = sizeof(struct eeh_pe);
if (eeh_pe_aux_size) {
alloc_size = ALIGN(alloc_size, cache_line_size());
alloc_size += eeh_pe_aux_size;
}
/* Allocate PHB PE */
pe = kzalloc(alloc_size, GFP_KERNEL);
if (!pe) return NULL;
/* Initialize PHB PE */
pe->type = type;
pe->phb = phb;
INIT_LIST_HEAD(&pe->child_list);
INIT_LIST_HEAD(&pe->child);
INIT_LIST_HEAD(&pe->edevs);
pe->data = (void *)pe + ALIGN(sizeof(struct eeh_pe),
cache_line_size());
return pe;
}
/**
* eeh_phb_pe_create - Create PHB PE
* @phb: PCI controller
*
* The function should be called while the PHB is detected during
* system boot or PCI hotplug in order to create PHB PE.
*/
int eeh_phb_pe_create(struct pci_controller *phb)
{
struct eeh_pe *pe;
/* Allocate PHB PE */
pe = eeh_pe_alloc(phb, EEH_PE_PHB);
if (!pe) {
pr_err("%s: out of memory!\n", __func__);
return -ENOMEM;
}
/* Put it into the list */
list_add_tail(&pe->child, &eeh_phb_pe);
pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number);
return 0;
}
/**
* eeh_phb_pe_get - Retrieve PHB PE based on the given PHB
* @phb: PCI controller
*
* The overall PEs form hierarchy tree. The first layer of the
* hierarchy tree is composed of PHB PEs. The function is used
* to retrieve the corresponding PHB PE according to the given PHB.
*/
struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
{
struct eeh_pe *pe;
list_for_each_entry(pe, &eeh_phb_pe, child) {
/*
* Actually, we needn't check the type since
* the PE for PHB has been determined when that
* was created.
*/
if ((pe->type & EEH_PE_PHB) && pe->phb == phb)
return pe;
}
return NULL;
}
/**
* eeh_pe_next - Retrieve the next PE in the tree
* @pe: current PE
* @root: root PE
*
* The function is used to retrieve the next PE in the
* hierarchy PE tree.
*/
static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
struct eeh_pe *root)
{
struct list_head *next = pe->child_list.next;
if (next == &pe->child_list) {
while (1) {
if (pe == root)
return NULL;
next = pe->child.next;
if (next != &pe->parent->child_list)
break;
pe = pe->parent;
}
}
return list_entry(next, struct eeh_pe, child);
}
/**
* eeh_pe_traverse - Traverse PEs in the specified PHB
* @root: root PE
* @fn: callback
* @flag: extra parameter to callback
*
* The function is used to traverse the specified PE and its
* child PEs. The traversing is to be terminated once the
* callback returns something other than NULL, or no more PEs
* to be traversed.
*/
void *eeh_pe_traverse(struct eeh_pe *root,
eeh_traverse_func fn, void *flag)
{
struct eeh_pe *pe;
void *ret;
for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
ret = fn(pe, flag);
if (ret) return ret;
}
return NULL;
}
/**
* eeh_pe_dev_traverse - Traverse the devices from the PE
* @root: EEH PE
* @fn: function callback
* @flag: extra parameter to callback
*
* The function is used to traverse the devices of the specified
* PE and its child PEs.
*/
void *eeh_pe_dev_traverse(struct eeh_pe *root,
eeh_traverse_func fn, void *flag)
{
struct eeh_pe *pe;
struct eeh_dev *edev, *tmp;
void *ret;
if (!root) {
pr_warn("%s: Invalid PE %p\n",
__func__, root);
return NULL;
}
/* Traverse root PE */
for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
eeh_pe_for_each_dev(pe, edev, tmp) {
ret = fn(edev, flag);
if (ret)
return ret;
}
}
return NULL;
}
/**
* __eeh_pe_get - Check the PE address
* @data: EEH PE
* @flag: EEH device
*
* For one particular PE, it can be identified by PE address
* or tranditional BDF address. BDF address is composed of
* Bus/Device/Function number. The extra data referred by flag
* indicates which type of address should be used.
*/
static void *__eeh_pe_get(void *data, void *flag)
{
struct eeh_pe *pe = (struct eeh_pe *)data;
struct eeh_dev *edev = (struct eeh_dev *)flag;
/* Unexpected PHB PE */
if (pe->type & EEH_PE_PHB)
return NULL;
/*
* We prefer PE address. For most cases, we should
* have non-zero PE address
*/
if (eeh_has_flag(EEH_VALID_PE_ZERO)) {
if (edev->pe_config_addr == pe->addr)
return pe;
} else {
if (edev->pe_config_addr &&
(edev->pe_config_addr == pe->addr))
return pe;
}
/* Try BDF address */
if (edev->config_addr &&
(edev->config_addr == pe->config_addr))
return pe;
return NULL;
}
/**
* eeh_pe_get - Search PE based on the given address
* @edev: EEH device
*
* Search the corresponding PE based on the specified address which
* is included in the eeh device. The function is used to check if
* the associated PE has been created against the PE address. It's
* notable that the PE address has 2 format: traditional PE address
* which is composed of PCI bus/device/function number, or unified
* PE address.
*/
struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
{
struct eeh_pe *root = eeh_phb_pe_get(edev->phb);
struct eeh_pe *pe;
pe = eeh_pe_traverse(root, __eeh_pe_get, edev);
return pe;
}
/**
* eeh_pe_get_parent - Retrieve the parent PE
* @edev: EEH device
*
* The whole PEs existing in the system are organized as hierarchy
* tree. The function is used to retrieve the parent PE according
* to the parent EEH device.
*/
static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
{
struct eeh_dev *parent;
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
/*
* It might have the case for the indirect parent
* EEH device already having associated PE, but
* the direct parent EEH device doesn't have yet.
*/
if (edev->physfn)
pdn = pci_get_pdn(edev->physfn);
else
pdn = pdn ? pdn->parent : NULL;
while (pdn) {
/* We're poking out of PCI territory */
parent = pdn_to_eeh_dev(pdn);
if (!parent)
return NULL;
if (parent->pe)
return parent->pe;
pdn = pdn->parent;
}
return NULL;
}
/**
* eeh_add_to_parent_pe - Add EEH device to parent PE
* @edev: EEH device
*
* Add EEH device to the parent PE. If the parent PE already
* exists, the PE type will be changed to EEH_PE_BUS. Otherwise,
* we have to create new PE to hold the EEH device and the new
* PE will be linked to its parent PE as well.
*/
int eeh_add_to_parent_pe(struct eeh_dev *edev)
{
struct eeh_pe *pe, *parent;
/* Check if the PE number is valid */
if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) {
pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%d\n",
__func__, edev->config_addr, edev->phb->global_number);
return -EINVAL;
}
/*
* Search the PE has been existing or not according
* to the PE address. If that has been existing, the
* PE should be composed of PCI bus and its subordinate
* components.
*/
pe = eeh_pe_get(edev);
if (pe && !(pe->type & EEH_PE_INVALID)) {
/* Mark the PE as type of PCI bus */
pe->type = EEH_PE_BUS;
edev->pe = pe;
/* Put the edev to PE */
list_add_tail(&edev->list, &pe->edevs);
pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n",
edev->phb->global_number,
edev->config_addr >> 8,
PCI_SLOT(edev->config_addr & 0xFF),
PCI_FUNC(edev->config_addr & 0xFF),
pe->addr);
return 0;
} else if (pe && (pe->type & EEH_PE_INVALID)) {
list_add_tail(&edev->list, &pe->edevs);
edev->pe = pe;
/*
* We're running to here because of PCI hotplug caused by
* EEH recovery. We need clear EEH_PE_INVALID until the top.
*/
parent = pe;
while (parent) {
if (!(parent->type & EEH_PE_INVALID))
break;
parent->type &= ~EEH_PE_INVALID;
parent = parent->parent;
}
pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device "
"PE#%x, Parent PE#%x\n",
edev->phb->global_number,
edev->config_addr >> 8,
PCI_SLOT(edev->config_addr & 0xFF),
PCI_FUNC(edev->config_addr & 0xFF),
pe->addr, pe->parent->addr);
return 0;
}
/* Create a new EEH PE */
if (edev->physfn)
pe = eeh_pe_alloc(edev->phb, EEH_PE_VF);
else
pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
if (!pe) {
pr_err("%s: out of memory!\n", __func__);
return -ENOMEM;
}
pe->addr = edev->pe_config_addr;
pe->config_addr = edev->config_addr;
/*
* Put the new EEH PE into hierarchy tree. If the parent
* can't be found, the newly created PE will be attached
* to PHB directly. Otherwise, we have to associate the
* PE with its parent.
*/
parent = eeh_pe_get_parent(edev);
if (!parent) {
parent = eeh_phb_pe_get(edev->phb);
if (!parent) {
pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
__func__, edev->phb->global_number);
edev->pe = NULL;
kfree(pe);
return -EEXIST;
}
}
pe->parent = parent;
/*
* Put the newly created PE into the child list and
* link the EEH device accordingly.
*/
list_add_tail(&pe->child, &parent->child_list);
list_add_tail(&edev->list, &pe->edevs);
edev->pe = pe;
pr_debug("EEH: Add %04x:%02x:%02x.%01x to "
"Device PE#%x, Parent PE#%x\n",
edev->phb->global_number,
edev->config_addr >> 8,
PCI_SLOT(edev->config_addr & 0xFF),
PCI_FUNC(edev->config_addr & 0xFF),
pe->addr, pe->parent->addr);
return 0;
}
/**
* eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
* @edev: EEH device
*
* The PE hierarchy tree might be changed when doing PCI hotplug.
* Also, the PCI devices or buses could be removed from the system
* during EEH recovery. So we have to call the function remove the
* corresponding PE accordingly if necessary.
*/
int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
{
struct eeh_pe *pe, *parent, *child;
int cnt;
if (!edev->pe) {
pr_debug("%s: No PE found for device %04x:%02x:%02x.%01x\n",
__func__, edev->phb->global_number,
edev->config_addr >> 8,
PCI_SLOT(edev->config_addr & 0xFF),
PCI_FUNC(edev->config_addr & 0xFF));
return -EEXIST;
}
/* Remove the EEH device */
pe = eeh_dev_to_pe(edev);
edev->pe = NULL;
list_del(&edev->list);
/*
* Check if the parent PE includes any EEH devices.
* If not, we should delete that. Also, we should
* delete the parent PE if it doesn't have associated
* child PEs and EEH devices.
*/
while (1) {
parent = pe->parent;
if (pe->type & EEH_PE_PHB)
break;
if (!(pe->state & EEH_PE_KEEP)) {
if (list_empty(&pe->edevs) &&
list_empty(&pe->child_list)) {
list_del(&pe->child);
kfree(pe);
} else {
break;
}
} else {
if (list_empty(&pe->edevs)) {
cnt = 0;
list_for_each_entry(child, &pe->child_list, child) {
if (!(child->type & EEH_PE_INVALID)) {
cnt++;
break;
}
}
if (!cnt)
pe->type |= EEH_PE_INVALID;
else
break;
}
}
pe = parent;
}
return 0;
}
/**
* eeh_pe_update_time_stamp - Update PE's frozen time stamp
* @pe: EEH PE
*
* We have time stamp for each PE to trace its time of getting
* frozen in last hour. The function should be called to update
* the time stamp on first error of the specific PE. On the other
* handle, we needn't account for errors happened in last hour.
*/
void eeh_pe_update_time_stamp(struct eeh_pe *pe)
{
struct timeval tstamp;
if (!pe) return;
if (pe->freeze_count <= 0) {
pe->freeze_count = 0;
do_gettimeofday(&pe->tstamp);
} else {
do_gettimeofday(&tstamp);
if (tstamp.tv_sec - pe->tstamp.tv_sec > 3600) {
pe->tstamp = tstamp;
pe->freeze_count = 0;
}
}
}
/**
* __eeh_pe_state_mark - Mark the state for the PE
* @data: EEH PE
* @flag: state
*
* The function is used to mark the indicated state for the given
* PE. Also, the associated PCI devices will be put into IO frozen
* state as well.
*/
static void *__eeh_pe_state_mark(void *data, void *flag)
{
struct eeh_pe *pe = (struct eeh_pe *)data;
int state = *((int *)flag);
struct eeh_dev *edev, *tmp;
struct pci_dev *pdev;
/* Keep the state of permanently removed PE intact */
if (pe->state & EEH_PE_REMOVED)
return NULL;
pe->state |= state;
/* Offline PCI devices if applicable */
if (!(state & EEH_PE_ISOLATED))
return NULL;
eeh_pe_for_each_dev(pe, edev, tmp) {
pdev = eeh_dev_to_pci_dev(edev);
if (pdev)
pdev->error_state = pci_channel_io_frozen;
}
/* Block PCI config access if required */
if (pe->state & EEH_PE_CFG_RESTRICTED)
pe->state |= EEH_PE_CFG_BLOCKED;
return NULL;
}
/**
* eeh_pe_state_mark - Mark specified state for PE and its associated device
* @pe: EEH PE
*
* EEH error affects the current PE and its child PEs. The function
* is used to mark appropriate state for the affected PEs and the
* associated devices.
*/
void eeh_pe_state_mark(struct eeh_pe *pe, int state)
{
eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
}
EXPORT_SYMBOL_GPL(eeh_pe_state_mark);
static void *__eeh_pe_dev_mode_mark(void *data, void *flag)
{
struct eeh_dev *edev = data;
int mode = *((int *)flag);
edev->mode |= mode;
return NULL;
}
/**
* eeh_pe_dev_state_mark - Mark state for all device under the PE
* @pe: EEH PE
*
* Mark specific state for all child devices of the PE.
*/
void eeh_pe_dev_mode_mark(struct eeh_pe *pe, int mode)
{
eeh_pe_dev_traverse(pe, __eeh_pe_dev_mode_mark, &mode);
}
/**
* __eeh_pe_state_clear - Clear state for the PE
* @data: EEH PE
* @flag: state
*
* The function is used to clear the indicated state from the
* given PE. Besides, we also clear the check count of the PE
* as well.
*/
static void *__eeh_pe_state_clear(void *data, void *flag)
{
struct eeh_pe *pe = (struct eeh_pe *)data;
int state = *((int *)flag);
struct eeh_dev *edev, *tmp;
struct pci_dev *pdev;
/* Keep the state of permanently removed PE intact */
if (pe->state & EEH_PE_REMOVED)
return NULL;
pe->state &= ~state;
/*
* Special treatment on clearing isolated state. Clear
* check count since last isolation and put all affected
* devices to normal state.
*/
if (!(state & EEH_PE_ISOLATED))
return NULL;
pe->check_count = 0;
eeh_pe_for_each_dev(pe, edev, tmp) {
pdev = eeh_dev_to_pci_dev(edev);
if (!pdev)
continue;
pdev->error_state = pci_channel_io_normal;
}
/* Unblock PCI config access if required */
if (pe->state & EEH_PE_CFG_RESTRICTED)
pe->state &= ~EEH_PE_CFG_BLOCKED;
return NULL;
}
/**
* eeh_pe_state_clear - Clear state for the PE and its children
* @pe: PE
* @state: state to be cleared
*
* When the PE and its children has been recovered from error,
* we need clear the error state for that. The function is used
* for the purpose.
*/
void eeh_pe_state_clear(struct eeh_pe *pe, int state)
{
eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
}
/**
* eeh_pe_state_mark_with_cfg - Mark PE state with unblocked config space
* @pe: PE
* @state: PE state to be set
*
* Set specified flag to PE and its child PEs. The PCI config space
* of some PEs is blocked automatically when EEH_PE_ISOLATED is set,
* which isn't needed in some situations. The function allows to set
* the specified flag to indicated PEs without blocking their PCI
* config space.
*/
void eeh_pe_state_mark_with_cfg(struct eeh_pe *pe, int state)
{
eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
if (!(state & EEH_PE_ISOLATED))
return;
/* Clear EEH_PE_CFG_BLOCKED, which might be set just now */
state = EEH_PE_CFG_BLOCKED;
eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
}
/*
* Some PCI bridges (e.g. PLX bridges) have primary/secondary
* buses assigned explicitly by firmware, and we probably have
* lost that after reset. So we have to delay the check until
* the PCI-CFG registers have been restored for the parent
* bridge.
*
* Don't use normal PCI-CFG accessors, which probably has been
* blocked on normal path during the stage. So we need utilize
* eeh operations, which is always permitted.
*/
static void eeh_bridge_check_link(struct eeh_dev *edev)
{
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
int cap;
uint32_t val;
int timeout = 0;
/*
* We only check root port and downstream ports of
* PCIe switches
*/
if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
return;
pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n",
__func__, edev->phb->global_number,
edev->config_addr >> 8,
PCI_SLOT(edev->config_addr & 0xFF),
PCI_FUNC(edev->config_addr & 0xFF));
/* Check slot status */
cap = edev->pcie_cap;
eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val);
if (!(val & PCI_EXP_SLTSTA_PDS)) {
pr_debug(" No card in the slot (0x%04x) !\n", val);
return;
}
/* Check power status if we have the capability */
eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val);
if (val & PCI_EXP_SLTCAP_PCP) {
eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val);
if (val & PCI_EXP_SLTCTL_PCC) {
pr_debug(" In power-off state, power it on ...\n");
val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val);
msleep(2 * 1000);
}
}
/* Enable link */
eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val);
val &= ~PCI_EXP_LNKCTL_LD;
eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val);
/* Check link */
eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val);
if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
pr_debug(" No link reporting capability (0x%08x) \n", val);
msleep(1000);
return;
}
/* Wait the link is up until timeout (5s) */
timeout = 0;
while (timeout < 5000) {
msleep(20);
timeout += 20;
eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val);
if (val & PCI_EXP_LNKSTA_DLLLA)
break;
}
if (val & PCI_EXP_LNKSTA_DLLLA)
pr_debug(" Link up (%s)\n",
(val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB");
else
pr_debug(" Link not ready (0x%04x)\n", val);
}
#define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
static void eeh_restore_bridge_bars(struct eeh_dev *edev)
{
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
int i;
/*
* Device BARs: 0x10 - 0x18
* Bus numbers and windows: 0x18 - 0x30
*/
for (i = 4; i < 13; i++)
eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
/* Rom: 0x38 */
eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]);
/* Cache line & Latency timer: 0xC 0xD */
eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
SAVED_BYTE(PCI_CACHE_LINE_SIZE));
eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
SAVED_BYTE(PCI_LATENCY_TIMER));
/* Max latency, min grant, interrupt ping and line: 0x3C */
eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
/* PCI Command: 0x4 */
eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] |
PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
/* Check the PCIe link is ready */
eeh_bridge_check_link(edev);
}
static void eeh_restore_device_bars(struct eeh_dev *edev)
{
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
int i;
u32 cmd;
for (i = 4; i < 10; i++)
eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
/* 12 == Expansion ROM Address */
eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]);
eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
SAVED_BYTE(PCI_CACHE_LINE_SIZE));
eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
SAVED_BYTE(PCI_LATENCY_TIMER));
/* max latency, min grant, interrupt pin and line */
eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
/*
* Restore PERR & SERR bits, some devices require it,
* don't touch the other command bits
*/
eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd);
if (edev->config_space[1] & PCI_COMMAND_PARITY)
cmd |= PCI_COMMAND_PARITY;
else
cmd &= ~PCI_COMMAND_PARITY;
if (edev->config_space[1] & PCI_COMMAND_SERR)
cmd |= PCI_COMMAND_SERR;
else
cmd &= ~PCI_COMMAND_SERR;
eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd);
}
/**
* eeh_restore_one_device_bars - Restore the Base Address Registers for one device
* @data: EEH device
* @flag: Unused
*
* Loads the PCI configuration space base address registers,
* the expansion ROM base address, the latency timer, and etc.
* from the saved values in the device node.
*/
static void *eeh_restore_one_device_bars(void *data, void *flag)
{
struct eeh_dev *edev = (struct eeh_dev *)data;
struct pci_dn *pdn = eeh_dev_to_pdn(edev);
/* Do special restore for bridges */
if (edev->mode & EEH_DEV_BRIDGE)
eeh_restore_bridge_bars(edev);
else
eeh_restore_device_bars(edev);
if (eeh_ops->restore_config && pdn)
eeh_ops->restore_config(pdn);
return NULL;
}
/**
* eeh_pe_restore_bars - Restore the PCI config space info
* @pe: EEH PE
*
* This routine performs a recursive walk to the children
* of this device as well.
*/
void eeh_pe_restore_bars(struct eeh_pe *pe)
{
/*
* We needn't take the EEH lock since eeh_pe_dev_traverse()
* will take that.
*/
eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL);
}
/**
* eeh_pe_loc_get - Retrieve location code binding to the given PE
* @pe: EEH PE
*
* Retrieve the location code of the given PE. If the primary PE bus
* is root bus, we will grab location code from PHB device tree node
* or root port. Otherwise, the upstream bridge's device tree node
* of the primary PE bus will be checked for the location code.
*/
const char *eeh_pe_loc_get(struct eeh_pe *pe)
{
struct pci_bus *bus = eeh_pe_bus_get(pe);
struct device_node *dn;
const char *loc = NULL;
while (bus) {
dn = pci_bus_to_OF_node(bus);
if (!dn) {
bus = bus->parent;
continue;
}
if (pci_is_root_bus(bus))
loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
else
loc = of_get_property(dn, "ibm,slot-location-code",
NULL);
if (loc)
return loc;
bus = bus->parent;
}
return "N/A";
}
/**
* eeh_pe_bus_get - Retrieve PCI bus according to the given PE
* @pe: EEH PE
*
* Retrieve the PCI bus according to the given PE. Basically,
* there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the
* primary PCI bus will be retrieved. The parent bus will be
* returned for BUS PE. However, we don't have associated PCI
* bus for DEVICE PE.
*/
struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
{
struct eeh_dev *edev;
struct pci_dev *pdev;
if (pe->type & EEH_PE_PHB)
return pe->phb->bus;
/* The primary bus might be cached during probe time */
if (pe->state & EEH_PE_PRI_BUS)
return pe->bus;
/* Retrieve the parent PCI bus of first (top) PCI device */
edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, list);
pdev = eeh_dev_to_pci_dev(edev);
if (pdev)
return pdev->bus;
return NULL;
}