| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1797379132.1309771.1750220576089.JavaMail.zimbra@raptorengineeringinc.com>
Date: Tue, 17 Jun 2025 23:22:56 -0500 (CDT)
From: Timothy Pearson <tpearson@...torengineering.com>
To: linuxppc-dev <linuxppc-dev@...ts.ozlabs.org>
Cc: linux-kernel <linux-kernel@...r.kernel.org>,
linux-pci <linux-pci@...r.kernel.org>,
Timothy Pearson <tpearson@...torengineering.com>,
Madhavan Srinivasan <maddy@...ux.ibm.com>,
Michael Ellerman <mpe@...erman.id.au>,
christophe leroy <christophe.leroy@...roup.eu>,
Naveen N Rao <naveen@...nel.org>,
Bjorn Helgaas <bhelgaas@...gle.com>,
Shawn Anastasio <sanastasio@...torengineering.com>
Subject: [PATCH 4/8] powerpc/eeh: Make EEH driver device hotplug safe
>From 21d8f844bf1971b609e9b07086fddfc76e1d1ec7 Mon Sep 17 00:00:00 2001
From: Timothy Pearson <tpearson@...torengineering.com>
Date: Tue, 17 Jun 2025 23:16:37 -0500
Subject: [PATCH 4/8] powerpc/eeh: Make EEH driver device hotplug safe
Multiple race conditions existed between the PCIe hotplug driver and
the EEH driver, leading to a variety of kernel oopses of the same
general nature:
<pcie device unplug>
<eeh driver trigger>
<hotplug removal trigger>
<pcie tree reconfiguration>
<eeh recovery next step>
<oops in EEH driver bus iteration loop>
A second class of oops is also seen when the underling bus disappears
during device recovery.
Refactor the EEH module to be PCI rescan and remove safe. Also clean
up a few minor formatting / readability issues.
Signed-off-by: Timothy Pearson <tpearson@...torengineering.com>
---
arch/powerpc/kernel/eeh_driver.c | 48 +++++++++++++-------
arch/powerpc/kernel/eeh_pe.c | 10 ++--
arch/powerpc/platforms/powernv/eeh-powernv.c | 1 +
3 files changed, 39 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7efe04c68f0f..dd50de91c438 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -257,13 +257,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
struct pci_driver *driver;
enum pci_ers_result new_result;
- pci_lock_rescan_remove();
pdev = edev->pdev;
if (pdev)
get_device(&pdev->dev);
- pci_unlock_rescan_remove();
if (!pdev) {
eeh_edev_info(edev, "no device");
+ *result = PCI_ERS_RESULT_DISCONNECT;
return;
}
device_lock(&pdev->dev);
@@ -304,8 +303,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root,
struct eeh_dev *edev, *tmp;
pr_info("EEH: Beginning: '%s'\n", name);
- eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
- eeh_pe_report_edev(edev, fn, result);
+ eeh_for_each_pe(root, pe)
+ eeh_pe_for_each_dev(pe, edev, tmp)
+ eeh_pe_report_edev(edev, fn, result);
if (result)
pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
name, pci_ers_result_name(*result));
@@ -383,6 +383,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
if (!edev)
return;
+ pci_lock_rescan_remove();
+
/*
* The content in the config space isn't saved because
* the blocked config space on some adapters. We have
@@ -393,14 +395,19 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
if (list_is_last(&edev->entry, &edev->pe->edevs))
eeh_pe_restore_bars(edev->pe);
+ pci_unlock_rescan_remove();
return;
}
pdev = eeh_dev_to_pci_dev(edev);
- if (!pdev)
+ if (!pdev) {
+ pci_unlock_rescan_remove();
return;
+ }
pci_restore_state(pdev);
+
+ pci_unlock_rescan_remove();
}
/**
@@ -647,9 +654,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) {
eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
} else {
- pci_lock_rescan_remove();
pci_hp_remove_devices(bus);
- pci_unlock_rescan_remove();
}
/*
@@ -665,8 +670,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
if (rc)
return rc;
- pci_lock_rescan_remove();
-
/* Restore PE */
eeh_ops->configure_bridge(pe);
eeh_pe_restore_bars(pe);
@@ -674,7 +677,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
/* Clear frozen state */
rc = eeh_clear_pe_frozen_state(pe, false);
if (rc) {
- pci_unlock_rescan_remove();
return rc;
}
@@ -709,7 +711,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
pe->tstamp = tstamp;
pe->freeze_count = cnt;
- pci_unlock_rescan_remove();
return 0;
}
@@ -843,10 +844,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
int devices = 0;
+ pci_lock_rescan_remove();
+
bus = eeh_pe_bus_get(pe);
if (!bus) {
pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
__func__, pe->phb->global_number, pe->addr);
+ pci_unlock_rescan_remove();
return;
}
@@ -1094,10 +1098,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
- pci_lock_rescan_remove();
- pci_hp_remove_devices(bus);
- pci_unlock_rescan_remove();
+ bus = eeh_pe_bus_get(pe);
+ if (bus)
+ pci_hp_remove_devices(bus);
+ else
+ pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n",
+ __func__, pe->phb->global_number, pe->addr);
+
/* The passed PE should no longer be used */
+ pci_unlock_rescan_remove();
return;
}
@@ -1114,6 +1123,8 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
eeh_clear_slot_attention(edev->pdev);
eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+
+ pci_unlock_rescan_remove();
}
/**
@@ -1132,6 +1143,7 @@ void eeh_handle_special_event(void)
unsigned long flags;
int rc;
+ pci_lock_rescan_remove();
do {
rc = eeh_ops->next_error(&pe);
@@ -1171,10 +1183,12 @@ void eeh_handle_special_event(void)
break;
case EEH_NEXT_ERR_NONE:
+ pci_unlock_rescan_remove();
return;
default:
pr_warn("%s: Invalid value %d from next_error()\n",
__func__, rc);
+ pci_unlock_rescan_remove();
return;
}
@@ -1186,7 +1200,9 @@ void eeh_handle_special_event(void)
if (rc == EEH_NEXT_ERR_FROZEN_PE ||
rc == EEH_NEXT_ERR_FENCED_PHB) {
eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+ pci_unlock_rescan_remove();
eeh_handle_normal_event(pe);
+ pci_lock_rescan_remove();
} else {
eeh_for_each_pe(pe, tmp_pe)
eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
@@ -1199,7 +1215,6 @@ void eeh_handle_special_event(void)
eeh_report_failure, NULL);
eeh_set_channel_state(pe, pci_channel_io_perm_failure);
- pci_lock_rescan_remove();
list_for_each_entry(hose, &hose_list, list_node) {
phb_pe = eeh_phb_pe_get(hose);
if (!phb_pe ||
@@ -1218,7 +1233,6 @@ void eeh_handle_special_event(void)
}
pci_hp_remove_devices(bus);
}
- pci_unlock_rescan_remove();
}
/*
@@ -1228,4 +1242,6 @@ void eeh_handle_special_event(void)
if (rc == EEH_NEXT_ERR_DEAD_IOC)
break;
} while (rc != EEH_NEXT_ERR_NONE);
+
+ pci_unlock_rescan_remove();
}
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index d283d281d28e..e740101fadf3 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -671,10 +671,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
/* Check link */
- if (!edev->pdev->link_active_reporting) {
- eeh_edev_dbg(edev, "No link reporting capability\n");
- msleep(1000);
- return;
+ if (edev->pdev) {
+ if (!edev->pdev->link_active_reporting) {
+ eeh_edev_dbg(edev, "No link reporting capability\n");
+ msleep(1000);
+ return;
+ }
}
/* Wait the link is up until timeout (5s) */
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index db3370d1673c..5694fc8ee60f 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1117,6 +1117,7 @@ static int pnv_eeh_reset(struct eeh_pe *pe, int option)
if (pci_is_root_bus(bus->parent))
return pnv_eeh_root_reset(hose, option);
return pnv_eeh_bridge_reset(bus->self, option);
+
}
/**
--
2.39.5
Powered by blists - more mailing lists