From 8d3d50bf1913561ef3b1f5b53115c5a481ba9b1e Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 3 Feb 2010 05:56:41 +0000 Subject: powerpc/eeh: Fix a bug when pci structure is null During a EEH recover, the pci_dev structure can be null, mainly if an eeh event is detected during cpi config operation. In this case, the pci_dev will not be known (and will be null) the kernel will crash with the following message: Unable to handle kernel paging request for data at address 0x000000a0 Faulting instruction address: 0xc00000000006b8b4 Oops: Kernel access of bad area, sig: 11 [#1] NIP [c00000000006b8b4] .eeh_event_handler+0x10c/0x1a0 LR [c00000000006b8a8] .eeh_event_handler+0x100/0x1a0 Call Trace: [c0000003a80dff00] [c00000000006b8a8] .eeh_event_handler+0x100/0x1a0 [c0000003a80dff90] [c000000000031f1c] .kernel_thread+0x54/0x70 The bug occurs because pci_name() tries to access a null pointer. This patch just guarantee that pci_name() is not called on Null pointers. Signed-off-by: Breno Leitao Signed-off-by: Linas Vepstas Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/eeh.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/platforms/pseries/eeh.c') diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index ccd8dd03b8c9..3304f32fc7b8 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -491,7 +491,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) pdn->eeh_mode & EEH_MODE_NOCHECK) { ignored_check++; pr_debug("EEH: Ignored check (%x) for %s %s\n", - pdn->eeh_mode, pci_name (dev), dn->full_name); + pdn->eeh_mode, eeh_pci_name(dev), dn->full_name); return 0; } @@ -515,7 +515,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) printk (KERN_ERR "EEH: %d reads ignored for recovering device at " "location=%s driver=%s pci addr=%s\n", pdn->eeh_check_count, location, - dev->driver->name, pci_name(dev)); + dev->driver->name, eeh_pci_name(dev)); printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n", dev->driver->name); dump_stack(); -- cgit v1.2.3 From 3d3726282850761938078cd2013435eeeb2d0375 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 18 Feb 2010 02:23:07 +0000 Subject: powerpc: Convert confirm_error_lock to raw_spinlock confirm_error_lock needs to be a real spinlock in RT. Convert it to raw_spinlock. Signed-off-by: Thomas Gleixner Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/eeh.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/powerpc/platforms/pseries/eeh.c') diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c index 3304f32fc7b8..7df7fbb7cacb 100644 --- a/arch/powerpc/platforms/pseries/eeh.c +++ b/arch/powerpc/platforms/pseries/eeh.c @@ -100,7 +100,7 @@ int eeh_subsystem_enabled; EXPORT_SYMBOL(eeh_subsystem_enabled); /* Lock to avoid races due to multiple reports of an error */ -static DEFINE_SPINLOCK(confirm_error_lock); +static DEFINE_RAW_SPINLOCK(confirm_error_lock); /* Buffer for reporting slot-error-detail rtas calls. Its here * in BSS, and not dynamically alloced, so that it ends up in @@ -436,7 +436,7 @@ static void __eeh_clear_slot(struct device_node *parent, int mode_flag) void eeh_clear_slot (struct device_node *dn, int mode_flag) { unsigned long flags; - spin_lock_irqsave(&confirm_error_lock, flags); + raw_spin_lock_irqsave(&confirm_error_lock, flags); dn = find_device_pe (dn); @@ -447,7 +447,7 @@ void eeh_clear_slot (struct device_node *dn, int mode_flag) PCI_DN(dn)->eeh_mode &= ~mode_flag; PCI_DN(dn)->eeh_check_count = 0; __eeh_clear_slot(dn, mode_flag); - spin_unlock_irqrestore(&confirm_error_lock, flags); + raw_spin_unlock_irqrestore(&confirm_error_lock, flags); } /** @@ -506,7 +506,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) * in one slot might report errors simultaneously, and we * only want one error recovery routine running. */ - spin_lock_irqsave(&confirm_error_lock, flags); + raw_spin_lock_irqsave(&confirm_error_lock, flags); rc = 1; if (pdn->eeh_mode & EEH_MODE_ISOLATED) { pdn->eeh_check_count ++; @@ -575,7 +575,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) * with other functions on this device, and functions under * bridges. */ eeh_mark_slot (dn, EEH_MODE_ISOLATED); - spin_unlock_irqrestore(&confirm_error_lock, flags); + raw_spin_unlock_irqrestore(&confirm_error_lock, flags); eeh_send_failure_event (dn, dev); @@ -586,7 +586,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev) return 1; dn_unlock: - spin_unlock_irqrestore(&confirm_error_lock, flags); + raw_spin_unlock_irqrestore(&confirm_error_lock, flags); return rc; } @@ -1064,7 +1064,7 @@ void __init eeh_init(void) struct device_node *phb, *np; struct eeh_early_enable_info info; - spin_lock_init(&confirm_error_lock); + raw_spin_lock_init(&confirm_error_lock); spin_lock_init(&slot_errbuf_lock); np = of_find_node_by_path("/rtas"); -- cgit v1.2.3