From 8c3ba8d049247dc06b6dcee1711a11b26647aa44 Mon Sep 17 00:00:00 2001 From: Kerstin Jonsson Date: Mon, 24 May 2010 12:13:15 -0700 Subject: x86, apic: ack all pending irqs when crashed/on kexec When the SMP kernel decides to crash_kexec() the local APICs may have pending interrupts in their vector tables. The setup routine for the local APIC has a deficient mechanism for clearing these interrupts, it only handles interrupts that has already been dispatched to the local core for servicing (the ISR register) safely, it doesn't consider lower prioritized queued interrupts stored in the IRR register. If you have more than one pending interrupt within the same 32 bit word in the LAPIC vector table registers you may find yourself entering the IO APIC setup with pending interrupts left in the LAPIC. This is a situation for wich the IO APIC setup is not prepared. Depending of what/which interrupt vector/vectors are stuck in the APIC tables your system may show various degrees of malfunctioning. That was the reason why the check_timer() failed in our system, the timer interrupts was blocked by pending interrupts from the old kernel when routed trough the IO APIC. Additional comment from Jiri Bohac: ============== If this should go into stable release, I'd add some kind of limit on the number of iterations, just to be safe from hard to debug lock-ups: +if (loops++ > MAX_LOOPS) { + printk("LAPIC pending clean-up") + break; +} while (queued); with MAX_LOOPS something like 1E9 this would leave plenty of time for the pending IRQs to be cleared and would and still cause at most a second of delay if the loop were to lock-up for whatever reason. [trenn@suse.de: V2: Use tsc if avail to bail out after 1 sec due to possible virtual apic_read calls which may take rather long (suggested by: Avi Kivity ) If no tsc is available bail out quickly after cpu_khz, if we broke out too early and still have irqs pending (which should never happen?) we still get a WARN_ON... V3: - Fixed indentation -> checkpatch clean - max_loops must be signed V4: - Fix typo, mixed up tsc and ntsc in first rdtscll() call V5: Adjust WARN_ON() condition to also catch error in cpu_has_tsc case] Cc: Cc: Yinghai Lu Cc: Kerstin Jonsson Cc: Avi Kivity Cc: Suresh Siddha Tested-by: Eric W. Biederman Signed-off-by: Thomas Renninger LKML-Reference: <201005241913.o4OJDGWM010865@imap1.linux-foundation.org> Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin --- arch/x86/kernel/apic/apic.c | 41 +++++++++++++++++++++++++++++++++-------- 1 file changed, 33 insertions(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index e5a4a1e0161..c02cc692985 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -51,6 +51,7 @@ #include #include #include +#include unsigned int num_processors; @@ -1151,8 +1152,13 @@ static void __cpuinit lapic_setup_esr(void) */ void __cpuinit setup_local_APIC(void) { - unsigned int value; - int i, j; + unsigned int value, queued; + int i, j, acked = 0; + unsigned long long tsc = 0, ntsc; + long long max_loops = cpu_khz; + + if (cpu_has_tsc) + rdtscll(tsc); if (disable_apic) { arch_disable_smp_support(); @@ -1204,13 +1210,32 @@ void __cpuinit setup_local_APIC(void) * the interrupt. Hence a vector might get locked. It was noticed * for timer irq (vector 0x31). Issue an extra EOI to clear ISR. */ - for (i = APIC_ISR_NR - 1; i >= 0; i--) { - value = apic_read(APIC_ISR + i*0x10); - for (j = 31; j >= 0; j--) { - if (value & (1<= 0; i--) + queued |= apic_read(APIC_IRR + i*0x10); + + for (i = APIC_ISR_NR - 1; i >= 0; i--) { + value = apic_read(APIC_ISR + i*0x10); + for (j = 31; j >= 0; j--) { + if (value & (1< 256) { + printk(KERN_ERR "LAPIC pending interrupts after %d EOI\n", + acked); + break; + } + if (cpu_has_tsc) { + rdtscll(ntsc); + max_loops = (cpu_khz << 10) - (ntsc - tsc); + } else + max_loops--; + } while (queued && max_loops > 0); + WARN_ON(max_loops <= 0); /* * Now that we are all set up, enable the APIC -- cgit v1.2.3-70-g09d2 From b46fc5f235be04a7f77fb2af1d8cb809889c25c1 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Mon, 24 May 2010 12:13:16 -0700 Subject: arch/x86/pci: use kasprintf kasprintf combines kmalloc and sprintf, and takes care of the size calculation itself. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // @@ expression a,flag; expression list args; statement S; @@ a = - \(kmalloc\|kzalloc\)(...,flag) + kasprintf(flag,args) <... when != a if (a == NULL || ...) S ...> - sprintf(a,args); // Signed-off-by: Julia Lawall LKML-Reference: <201005241913.o4OJDG3R010871@imap1.linux-foundation.org> Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin --- arch/x86/pci/acpi.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 31930fd30ea..7c0ad634694 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -207,10 +207,9 @@ get_current_resources(struct acpi_device *device, int busnum, if (!info.res) goto res_alloc_fail; - info.name = kmalloc(16, GFP_KERNEL); + info.name = kasprintf(GFP_KERNEL, "PCI Bus %04x:%02x", domain, busnum); if (!info.name) goto name_alloc_fail; - sprintf(info.name, "PCI Bus %04x:%02x", domain, busnum); info.res_num = 0; acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource, -- cgit v1.2.3-70-g09d2 From 5f2eb55026c91f8400ab4469aff88b2e201b5616 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 24 May 2010 12:13:17 -0700 Subject: x86: "nosmp" command line option should force the system into UP mode Bits set in cpu_possible_mask prior to the execution of prefill_possible_map() (i.e. when parsing ACPI or MPS tables) would prevent the SMP alternatives logic from switching to UP mode, plus unnecessary setup of per-CPU data for CPUs that can never come online. Additionally, without CONFIG_HOTPLUG_CPU disabled CPUs can never come online, and hence setting cpu_possible_mask bits for them is again a simple waste of resources. Signed-off-by: Jan Beulich LKML-Reference: <201005241913.o4OJDH3Z010874@imap1.linux-foundation.org> Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin --- arch/x86/kernel/smpboot.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 763d815e27a..37462f1ddba 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1215,9 +1215,17 @@ __init void prefill_possible_map(void) if (!num_processors) num_processors = 1; - if (setup_possible_cpus == -1) - possible = num_processors + disabled_cpus; - else + i = setup_max_cpus ?: 1; + if (setup_possible_cpus == -1) { + possible = num_processors; +#ifdef CONFIG_HOTPLUG_CPU + if (setup_max_cpus) + possible += disabled_cpus; +#else + if (possible > i) + possible = i; +#endif + } else possible = setup_possible_cpus; total_cpus = max_t(int, possible, num_processors + disabled_cpus); @@ -1230,11 +1238,23 @@ __init void prefill_possible_map(void) possible = nr_cpu_ids; } +#ifdef CONFIG_HOTPLUG_CPU + if (!setup_max_cpus) +#endif + if (possible > i) { + printk(KERN_WARNING + "%d Processors exceeds max_cpus limit of %u\n", + possible, setup_max_cpus); + possible = i; + } + printk(KERN_INFO "SMP: Allowing %d CPUs, %d hotplug CPUs\n", possible, max_t(int, possible - num_processors, 0)); for (i = 0; i < possible; i++) set_cpu_possible(i, true); + for (; i < NR_CPUS; i++) + set_cpu_possible(i, false); nr_cpu_ids = possible; } -- cgit v1.2.3-70-g09d2 From 3d6e77a3ddb8e4156b89f4273ff8c7d37abaf781 Mon Sep 17 00:00:00 2001 From: Gabor Gombas Date: Mon, 24 May 2010 12:13:18 -0700 Subject: x86, setup: Phoenix BIOS fixup is needed on Dell Inspiron Mini 1012 The low-memory corruption checker triggers during suspend/resume, so we need to reserve the low 64k. Don't be fooled that the BIOS identifies itself as "Dell Inc.", it's still Phoenix BIOS. [ hpa: I think we blacklist almost every BIOS in existence. We should either change this to a whitelist or just make it unconditional. ] Signed-off-by: Gabor Gombas LKML-Reference: <201005241913.o4OJDIMM010877@imap1.linux-foundation.org> Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin Cc: --- arch/x86/kernel/setup.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index e8029896309..b4ae4acbd03 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -676,6 +676,17 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "DG45FC"), }, }, + /* + * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so + * match on the product name. + */ + { + .callback = dmi_low_memory_corruption, + .ident = "Phoenix BIOS", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"), + }, + }, #endif {} }; -- cgit v1.2.3-70-g09d2 From 48691ff86d91db1090551ec2a5ae0d80ef59105f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 24 May 2010 12:13:19 -0700 Subject: x86: remove last traces of quicklist usage We still have a stray quicklist header included even though we axed quicklist usage quite a while back. Signed-off-by: Peter Zijlstra LKML-Reference: <201005241913.o4OJDJe9010881@imap1.linux-foundation.org> Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin --- arch/x86/mm/pgtable_32.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 792854003ed..cac71849925 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3-70-g09d2 From fe501f1e89cd460793152f500bf25d81d463515b Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 25 May 2010 15:28:58 +0000 Subject: x86, k8: Fix section mismatch for powernowk8_exit() Fix the following warning: "WARNING: arch/x86/kernel/built-in.o(.exit.text+0x72): Section mismatch in reference from the function powernowk8_exit() to the variable .cpuinit.data:cpb_nb The function __exit powernowk8_exit() references a variable __cpuinitdata cpb_nb. This is often seen when error handling in the exit function uses functionality in the init path. The fix is often to remove the __cpuinitdata annotation of cpb_nb so it may be used outside an init section." Cc: Reported-by: H. Peter Anvin Signed-off-by: Borislav Petkov LKML-Reference: <20100525152858.GA24836@aftab> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 6f3dc8fbbfd..7ec2123838e 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -1497,8 +1497,8 @@ static struct cpufreq_driver cpufreq_amd64_driver = { * simply keep the boost-disable flag in sync with the current global * state. */ -static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action, - void *hcpu) +static int cpb_notify(struct notifier_block *nb, unsigned long action, + void *hcpu) { unsigned cpu = (long)hcpu; u32 lo, hi; @@ -1528,7 +1528,7 @@ static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_OK; } -static struct notifier_block __cpuinitdata cpb_nb = { +static struct notifier_block cpb_nb = { .notifier_call = cpb_notify, }; -- cgit v1.2.3-70-g09d2 From 20413f27163fb1b8b806c0c219dc95eae67c633a Mon Sep 17 00:00:00 2001 From: Xiaotian Feng Date: Wed, 26 May 2010 09:51:10 +0800 Subject: x86, pat: Fix memory leak in free_memtype Reserve_memtype will allocate memory for new memtype, but in free_memtype, after the memtype erased from rbtree, the memory is not freed. Changes since V1: make rbt_memtype_erase return erased memtype so that it can be freed in free_memtype. [ hpa: not for -stable: 2.6.34 and earlier not affected ] Signed-off-by: Xiaotian Feng LKML-Reference: <1274838670-8731-1-git-send-email-dfeng@redhat.com> Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Venkatesh Pallipadi Cc: Jack Steiner Acked-by: Suresh Siddha Signed-off-by: H. Peter Anvin --- arch/x86/mm/pat.c | 10 +++++++--- arch/x86/mm/pat_internal.h | 6 +++--- arch/x86/mm/pat_rbtree.c | 7 ++++--- 3 files changed, 14 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index bbe5502ee1c..acc15b23b74 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -336,6 +336,7 @@ int free_memtype(u64 start, u64 end) { int err = -EINVAL; int is_range_ram; + struct memtype *entry; if (!pat_enabled) return 0; @@ -355,17 +356,20 @@ int free_memtype(u64 start, u64 end) } spin_lock(&memtype_lock); - err = rbt_memtype_erase(start, end); + entry = rbt_memtype_erase(start, end); spin_unlock(&memtype_lock); - if (err) { + if (!entry) { printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n", current->comm, current->pid, start, end); + return -EINVAL; } + kfree(entry); + dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end); - return err; + return 0; } diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h index 4f39eefa3e6..77e5ba153fa 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat_internal.h @@ -28,15 +28,15 @@ static inline char *cattr_name(unsigned long flags) #ifdef CONFIG_X86_PAT extern int rbt_memtype_check_insert(struct memtype *new, unsigned long *new_type); -extern int rbt_memtype_erase(u64 start, u64 end); +extern struct memtype *rbt_memtype_erase(u64 start, u64 end); extern struct memtype *rbt_memtype_lookup(u64 addr); extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos); #else static inline int rbt_memtype_check_insert(struct memtype *new, unsigned long *new_type) { return 0; } -static inline int rbt_memtype_erase(u64 start, u64 end) -{ return 0; } +static inline struct memtype *rbt_memtype_erase(u64 start, u64 end) +{ return NULL; } static inline struct memtype *rbt_memtype_lookup(u64 addr) { return NULL; } static inline int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos) diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 07de4cb8cc3..f537087bb74 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -231,16 +231,17 @@ int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type) return err; } -int rbt_memtype_erase(u64 start, u64 end) +struct memtype *rbt_memtype_erase(u64 start, u64 end) { struct memtype *data; data = memtype_rb_exact_match(&memtype_rbroot, start, end); if (!data) - return -EINVAL; + goto out; rb_erase(&data->rb, &memtype_rbroot); - return 0; +out: + return data; } struct memtype *rbt_memtype_lookup(u64 addr) -- cgit v1.2.3-70-g09d2 From 1ba4f22c426ba04b00fd717318d50620c621a0e1 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 27 May 2010 12:02:00 -0700 Subject: x86, cpufeature: Unbreak compile with gcc 3.x gcc 3 is too braindamaged to be able to compile static_cpu_has() -- apparently it can't tell that a constant passed to an inline function is still a constant -- so if we're using gcc 3, just use the dynamic test. This is bad for performance, but if you care about performance, don't use an ancient, known-to-optimize-poorly compiler. Reported-and-tested-by: Eric Dumazet LKML-Reference: <4BF2FF82.7090005@zytor.com> Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/cpufeature.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index dca9c545f44..46814591438 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -332,6 +332,7 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) #endif } +#if __GNUC__ >= 4 #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ @@ -340,6 +341,12 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) __static_cpu_has(bit) : \ boot_cpu_has(bit) \ ) +#else +/* + * gcc 3.x is too stupid to do the static test; fall back to dynamic. + */ +#define static_cpu_has(bit) boot_cpu_has(bit) +#endif #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ -- cgit v1.2.3-70-g09d2