Hi Gary,
First, thanks for all the help and testing -- I really appreciate
it.
* Gary Hade <garyhade@xxxxxxxxxx>:
>
> I'm getting back to you but unfortunately with not so good
> news. Sorry Alex.
:-/
> On the x3950 (configured single node) I encountered the below
> problem when attempting to hotplug a PCIe adapter when 'pci_slot'
> was loaded prior to 'acpiphp'. I did not see the problem when
> the drivers were loaded in the opposite order.
Very bizarre, especially given the stack trace below, which
doesn't really make any sense to me at all.
> FYI, the node contains 2 hotpluggable PCIe slots and 5
> non-hotpluggable PCIe slots but 'pci_slot' only exposed
> the 2 hotpluggable slots. This does not appear to be due
> to a 'pci_slot' driver problem since I looked at the DSDT
> and SSDT and found that there are currently no _SUN methods
> for the non-hotpluggable slots.
Ok, this is not too surprising, but it's a different can o'
worms. ;) Let's save this for another day...
> invalid opcode: 0000 [1] SMP
> CPU 1
> Modules linked in: acpiphp pci_slot e1000 aic79xx scsi_transport_spi shpchp dock pci_hotplug ipt_LOG xt_limit xt_pkttype button battery ac power_supply ip6t_REJECT xt_tcpudp ipt_REJECT iptable_mangle iptable_filter ip6table_mangle ip_tables ip6table_filter ip6_tables x_tables ipv6 usbhid ff_memless ext3 jbd loop dm_mod ehci_hcd uhci_hcd usbcore ide_cd bnx2 cdrom rng_core reiserfs ata_piix ahci libata thermal processor piix sg megaraid_sas fan edd sd_mod scsi_mod ide_disk ide_core
> Pid: 121, comm: kacpi_notify Not tainted 2.6.24-rc3-gh-smp #1
> RIP: 0010:[<ffffffff882c2344>] [<ffffffff882c2344>] :pci_slot:__this_module+0x21c4/0xfffffffffffff204
> RSP: 0018:ffff81103fa43ea8 EFLAGS: 00010216
> RAX: ffff81103f944a18 RBX: ffff81103d4fe910 RCX: 000000000000000f
> RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8110400d13d0
> RBP: ffffffff8032d97b R08: ffff8110400fc7e0 R09: 0000000000000002
> R10: 0000000000000000 R11: ffffffff8021d193 R12: ffff811040105cf0
> R13: ffffffffffffffff R14: ffffffff80635820 R15: 0000000000000000
> FS: 0000000000000000(0000) GS:ffff8110400ed8c0(0000) knlGS:0000000000000000
> CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b
> CR2: 00002b266d876471 CR3: 000000103c825000 CR4: 00000000000006e0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> Process kacpi_notify (pid: 121, threadinfo ffff81103fa42000, task ffff81103f9f8040)
> Stack: ffffffff8033339c ffff81103d119a00 ffffffff8032d99e ffff81103f9fc540
> ffffffff8024618d ffff81103f9fc540 ffff81103f9fc540 ffffffff8024696c
> ffffffff80246a46 0000000000000000 ffff81103f9f8040 ffffffff80249ada
> Call Trace:
> [<ffffffff8033339c>] acpi_ev_notify_dispatch+0x57/0x60
> [<ffffffff8032d99e>] acpi_os_execute_notify+0x23/0x2c
> [<ffffffff8024618d>] run_workqueue+0x7f/0x10b
> [<ffffffff8024696c>] worker_thread+0x0/0xe4
> [<ffffffff80246a46>] worker_thread+0xda/0xe4
> [<ffffffff80249ada>] autoremove_wake_function+0x0/0x2e
> [<ffffffff802499bc>] kthread+0x47/0x73
> [<ffffffff8020cc98>] child_rip+0xa/0x12
> [<ffffffff80249975>] kthread+0x0/0x73
> [<ffffffff8020cc8e>] child_rip+0x0/0x12
Maybe we're trying to kick off a hotplug event on the wrong slot?
I really have no idea...
> Code: ff ff ff ff 40 23 2c 88 ff ff ff ff 00 c8 c6 3b 10 81 ff ff
> RIP [<ffffffff882c2344>] :pci_slot:__this_module+0x21c4/0xfffffffffffff204
> RSP <ffff81103fa43ea8>
Can you apply this debug patch on top of your tree, and send me
the output?
I'd be curious to see the output for your failure case:
# modprobe pci_slot debug=1
# modprobe acpiphp debug=1
Thanks.
/ac
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index 724f4f0..5a62def 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -30,12 +30,16 @@
#include <acpi/acpi_bus.h>
#include <acpi/acpi_drivers.h>
+static int debug;
+
#define DRIVER_VERSION "0.1"
#define DRIVER_AUTHOR "Alex Chiang <achiang@xxxxxx>"
#define DRIVER_DESC "ACPI PCI Slot Detection Driver"
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
MODULE_LICENSE("GPL");
+MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
+module_param(debug, bool, 0644);
#define _COMPONENT ACPI_PCI_COMPONENT
ACPI_MODULE_NAME("pci_slot");
@@ -43,6 +47,12 @@ ACPI_MODULE_NAME("pci_slot");
#define MY_NAME "pci_slot"
#define err(format, arg...) printk(KERN_ERR "%s: " format , MY_NAME , ## arg)
#define info(format, arg...) printk(KERN_INFO "%s: " format , MY_NAME , ## arg)
+#define dbg(format, arg...) \
+ do { \
+ if (debug) \
+ printk(KERN_DEBUG "%s: " format, \
+ MY_NAME , ## arg); \
+ } while (0)
static int acpi_pci_slot_add(acpi_handle handle);
static void acpi_pci_slot_remove(acpi_handle handle);
@@ -125,6 +135,9 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
if (IS_ERR(pci_slot))
err("pci_create_slot returned %ld\n", PTR_ERR(pci_slot));
+ dbg("pci_slot: %#lx, pci_bus: %x, device: %d, name: %s\n",
+ (uint64_t)pci_slot, pci_bus->number, device, name);
+
return AE_OK;
}
@@ -174,6 +187,7 @@ walk_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv)
if (!dev || !dev->subordinate)
goto out;
+ dbg("p2p bridge walk, pci_bus = %x\n", dev->subordinate->number);
status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1,
user_function, dev->subordinate, NULL);
if (ACPI_FAILURE(status))
@@ -231,6 +245,7 @@ walk_root_bridge(acpi_handle handle, acpi_walk_callback user_function)
if (!pci_bus)
return 0;
+ dbg("root bridge walk, pci_bus = %x\n", pci_bus->number);
status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, (u32)1,
user_function, pci_bus, NULL);
if (ACPI_FAILURE(status))
@@ -283,7 +298,6 @@ acpi_pci_slot_init(void)
return 0;
}
-
static void __exit
acpi_pci_slot_exit(void)
{
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index f16e0af..80c4928 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -9,6 +9,15 @@
#include <linux/pci.h>
#include "pci.h"
+static int pci_slot_debug;
+#define MY_NAME "slot"
+#define dbg(format, arg...) \
+ do { \
+ if (pci_slot_debug) \
+ printk(KERN_DEBUG "%s: " format, \
+ MY_NAME , ## arg); \
+ } while (0)
+
struct kset pci_slots_subsys;
EXPORT_SYMBOL_GPL(pci_slots_subsys);
@@ -63,6 +72,9 @@ static void pci_slot_release(struct kobject *kobj)
struct pci_slot **pprev;
struct pci_slot *slot = to_pci_slot(kobj);
+ dbg("%s: releasing pci_slot on %x:%d\n", __FUNCTION__,
+ slot->bus->number, slot->number);
+
for (pprev = &slot->bus->slot; *pprev; pprev = &(*pprev)->next) {
if (*pprev == slot) {
*pprev = slot->next;
@@ -103,15 +115,19 @@ int pci_slot_add_hotplug(struct pci_bus *parent, int slot_nr,
}
if (!found) {
+ dbg("%s: slot not found\n", __FUNCTION__);
retval = -EEXIST;
goto out;
}
if (slot->release) {
+ dbg("%s: already claimed\n", __FUNCTION__);
retval = -EBUSY;
goto out;
}
+ dbg("%s: adding release function to %x:%d\n",
+ __FUNCTION__, parent->number, slot_nr);
slot->release = release;
out:
up_write(&pci_bus_sem);
@@ -131,6 +147,9 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
for (slot = parent->slot; slot; slot = slot->next) {
if (slot->number == slot_nr) {
kobject_get(&slot->kobj);
+ dbg("%s: bumped refcount to %d on %x:%d\n",
+ __FUNCTION__, slot->kobj.kref.refcount,
+ parent->number, slot_nr);
goto out;
}
}
@@ -159,6 +178,9 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
slot->next = parent->slot;
parent->slot = slot;
+ dbg("%s: created pci_slot on %x:%d\n",
+ __FUNCTION__, parent->number, slot_nr);
+
out:
up_write(&pci_bus_sem);
return slot;
@@ -175,6 +197,10 @@ EXPORT_SYMBOL_GPL(pci_create_slot);
int pci_destroy_slot(struct pci_slot *slot)
{
kobject_put(&slot->kobj);
+
+ dbg("%s: decreased refcount to %d on %x:%d\n", __FUNCTION__,
+ slot->kobj.kref.refcount, slot->bus->number, slot->number);
+
if (atomic_read(&slot->kobj.kref.refcount) == 1)
kobject_unregister(&slot->kobj);
@@ -186,6 +212,8 @@ static int pci_slot_init(void)
{
int result;
+ pci_slot_debug = 1;
+
kobj_set_kset_s(&pci_slots_subsys, pci_bus_type.subsys);
result = subsystem_register(&pci_slots_subsys);
if (result)
-
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
