From 23b90cfd7bcf8ae1c0711df1cae7dfec3c01aec8 Mon Sep 17 00:00:00 2001 From: Jesse Barnes Date: Tue, 17 Aug 2010 09:15:24 -0700 Subject: x86/PCI: only define pci_domain_nr if PCI and PCI_DOMAINS are set Otherwise we'll duplicate definitions with the pci.h stubs. Reported-by: Randy Dunlap Acked-by: Randy Dunlap Signed-off-by: Jesse Barnes --- arch/x86/include/asm/pci.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 404a880ea32..d395540ff89 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -27,6 +27,9 @@ extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node); extern struct pci_bus *pci_scan_bus_with_sysdata(int busno); +#ifdef CONFIG_PCI + +#ifdef CONFIG_PCI_DOMAINS static inline int pci_domain_nr(struct pci_bus *bus) { struct pci_sysdata *sd = bus->sysdata; @@ -37,13 +40,12 @@ static inline int pci_proc_domain(struct pci_bus *bus) { return pci_domain_nr(bus); } - +#endif /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the loader */ -#ifdef CONFIG_PCI extern unsigned int pcibios_assign_all_busses(void); extern int pci_legacy_init(void); # ifdef CONFIG_ACPI -- cgit v1.2.3-70-g09d2 From cd7240c0b900eb6d690ccee088a6c9b46dae815a Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 19 Aug 2010 17:03:38 -0700 Subject: x86, tsc, sched: Recompute cyc2ns_offset's during resume from sleep states TSC's get reset after suspend/resume (even on cpu's with invariant TSC which runs at a constant rate across ACPI P-, C- and T-states). And in some systems BIOS seem to reinit TSC to arbitrary large value (still sync'd across cpu's) during resume. This leads to a scenario of scheduler rq->clock (sched_clock_cpu()) less than rq->age_stamp (introduced in 2.6.32). This leads to a big value returned by scale_rt_power() and the resulting big group power set by the update_group_power() is causing improper load balancing between busy and idle cpu's after suspend/resume. This resulted in multi-threaded workloads (like kernel-compilation) go slower after suspend/resume cycle on core i5 laptops. Fix this by recomputing cyc2ns_offset's during resume, so that sched_clock() continues from the point where it was left off during suspend. Reported-by: Florian Pritz Signed-off-by: Suresh Siddha Cc: # [v2.6.32+] Signed-off-by: Peter Zijlstra LKML-Reference: <1282262618.2675.24.camel@sbsiddha-MOBL3.sc.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/tsc.h | 2 ++ arch/x86/kernel/tsc.c | 38 ++++++++++++++++++++++++++++++++++++++ arch/x86/power/cpu.c | 2 ++ 3 files changed, 42 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index c0427295e8f..1ca132fc0d0 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -59,5 +59,7 @@ extern void check_tsc_sync_source(int cpu); extern void check_tsc_sync_target(void); extern int notsc_setup(char *); +extern void save_sched_clock_state(void); +extern void restore_sched_clock_state(void); #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index ce8e5023933..d632934cb63 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -626,6 +626,44 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) local_irq_restore(flags); } +static unsigned long long cyc2ns_suspend; + +void save_sched_clock_state(void) +{ + if (!sched_clock_stable) + return; + + cyc2ns_suspend = sched_clock(); +} + +/* + * Even on processors with invariant TSC, TSC gets reset in some the + * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to + * arbitrary value (still sync'd across cpu's) during resume from such sleep + * states. To cope up with this, recompute the cyc2ns_offset for each cpu so + * that sched_clock() continues from the point where it was left off during + * suspend. + */ +void restore_sched_clock_state(void) +{ + unsigned long long offset; + unsigned long flags; + int cpu; + + if (!sched_clock_stable) + return; + + local_irq_save(flags); + + get_cpu_var(cyc2ns_offset) = 0; + offset = cyc2ns_suspend - sched_clock(); + + for_each_possible_cpu(cpu) + per_cpu(cyc2ns_offset, cpu) = offset; + + local_irq_restore(flags); +} + #ifdef CONFIG_CPU_FREQ /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index e7e8c5f5495..87bb35e34ef 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -113,6 +113,7 @@ static void __save_processor_state(struct saved_context *ctxt) void save_processor_state(void) { __save_processor_state(&saved_context); + save_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(save_processor_state); @@ -229,6 +230,7 @@ static void __restore_processor_state(struct saved_context *ctxt) void restore_processor_state(void) { __restore_processor_state(&saved_context); + restore_sched_clock_state(); } #ifdef CONFIG_X86_32 EXPORT_SYMBOL(restore_processor_state); -- cgit v1.2.3-70-g09d2 From cc1a8e523333bc3d990102140f4d12908fa83caf Mon Sep 17 00:00:00 2001 From: Francisco Jerez Date: Sat, 4 Sep 2010 22:56:43 +0200 Subject: x86: Fix the address space annotations of iomap_atomic_prot_pfn() This patch fixes the sparse warnings when the return pointer of iomap_atomic_prot_pfn() is used as an argument of iowrite32() and friends. Signed-off-by: Francisco Jerez LKML-Reference: <1283633804-11749-1-git-send-email-currojerez@riseup.net> Cc: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/include/asm/iomap.h | 4 ++-- arch/x86/mm/iomap_32.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h index f35eb45d657..c4191b3b705 100644 --- a/arch/x86/include/asm/iomap.h +++ b/arch/x86/include/asm/iomap.h @@ -26,11 +26,11 @@ #include #include -void * +void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); void -iounmap_atomic(void *kvaddr, enum km_type type); +iounmap_atomic(void __iomem *kvaddr, enum km_type type); int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot); diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 84e236ce76b..72fc70cf618 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -74,7 +74,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) /* * Map 'pfn' using fixed map 'type' and protections 'prot' */ -void * +void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) { /* @@ -86,12 +86,12 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC)) prot = PAGE_KERNEL_UC_MINUS; - return kmap_atomic_prot_pfn(pfn, type, prot); + return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, type, prot); } EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn); void -iounmap_atomic(void *kvaddr, enum km_type type) +iounmap_atomic(void __iomem *kvaddr, enum km_type type) { unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); -- cgit v1.2.3-70-g09d2 From 16518d5ada690643453eb0aef3cc7841d3623c2d Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Thu, 26 Aug 2010 14:31:30 +0300 Subject: KVM: x86 emulator: fix regression with cmpxchg8b on i386 hosts operand::val and operand::orig_val are 32-bit on i386, whereas cmpxchg8b operands are 64-bit. Fix by adding val64 and orig_val64 union members to struct operand, and using them where needed. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/include/asm/kvm_emulate.h | 7 ++++++- arch/x86/kvm/emulate.c | 9 ++++----- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 51cfd730ac5..1f99ecfc48e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -152,9 +152,14 @@ struct x86_emulate_ops { struct operand { enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type; unsigned int bytes; - unsigned long orig_val, *ptr; + union { + unsigned long orig_val; + u64 orig_val64; + }; + unsigned long *ptr; union { unsigned long val; + u64 val64; char valptr[sizeof(unsigned long) + 2]; }; }; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b38bd8b92aa..66ca98aafdd 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1870,17 +1870,16 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { struct decode_cache *c = &ctxt->decode; - u64 old = c->dst.orig_val; + u64 old = c->dst.orig_val64; if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) || ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) { - c->regs[VCPU_REGS_RAX] = (u32) (old >> 0); c->regs[VCPU_REGS_RDX] = (u32) (old >> 32); ctxt->eflags &= ~EFLG_ZF; } else { - c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) | - (u32) c->regs[VCPU_REGS_RBX]; + c->dst.val64 = ((u64)c->regs[VCPU_REGS_RCX] << 32) | + (u32) c->regs[VCPU_REGS_RBX]; ctxt->eflags |= EFLG_ZF; } @@ -2616,7 +2615,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) c->src.valptr, c->src.bytes); if (rc != X86EMUL_CONTINUE) goto done; - c->src.orig_val = c->src.val; + c->src.orig_val64 = c->src.val64; } if (c->src2.type == OP_MEM) { -- cgit v1.2.3-70-g09d2 From 2fd818642a3c3a257f3b1262145a52bc1bfebd26 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 30 Aug 2010 09:45:40 +0900 Subject: x86, cpufeature: Suppress compiler warning with gcc 3.x Gcc 3.x generates a warning arch/x86/include/asm/cpufeature.h: In function `__static_cpu_has': arch/x86/include/asm/cpufeature.h:326: warning: asm operand 1 probably doesn't match constraints on each file. But static_cpu_has() for gcc 3.x does not need __static_cpu_has(). Signed-off-by: Tetsuo Handa LKML-Reference: <201008300127.o7U1RC6Z044051@www262.sakura.ne.jp> Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/cpufeature.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 781a50b29a4..c6fbb7b430d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -296,6 +296,7 @@ extern const char * const x86_power_flags[32]; #endif /* CONFIG_X86_64 */ +#if __GNUC__ >= 4 /* * Static testing of CPU features. Used the same as boot_cpu_has(). * These are only valid after alternatives have run, but will statically @@ -304,7 +305,7 @@ extern const char * const x86_power_flags[32]; */ static __always_inline __pure bool __static_cpu_has(u16 bit) { -#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5) +#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5 asm goto("1: jmp %l[t_no]\n" "2:\n" ".section .altinstructions,\"a\"\n" @@ -345,7 +346,6 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) #endif } -#if __GNUC__ >= 4 #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ -- cgit v1.2.3-70-g09d2 From 54ff7e595d763d894104d421b103a89f7becf47c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 14 Sep 2010 22:10:21 +0200 Subject: x86: hpet: Work around hardware stupidity This more or less reverts commits 08be979 (x86: Force HPET readback_cmp for all ATI chipsets) and 30a564be (x86, hpet: Restrict read back to affected ATI chipsets) to the status of commit 8da854c (x86, hpet: Erratum workaround for read after write of HPET comparator). The delta to commit 8da854c is mostly comments and the change from WARN_ONCE to printk_once as we know the call path of this function already. This needs really in depth explanation: First of all the HPET design is a complete failure. Having a counter compare register which generates an interrupt on matching values forces the software to do at least one superfluous readback of the counter register. While it is nice in theory to program "absolute" time events it is practically useless because the timer runs at some absurd frequency which can never be matched to real world units. So we are forced to calculate a relative delta and this forces a readout of the actual counter value, adding the delta and programming the compare register. When the delta is small enough we run into the danger that we program a compare value which is already in the past. Due to the compare for equal nature of HPET we need to read back the counter value after writing the compare rehgister (btw. this is necessary for absolute timeouts as well) to make sure that we did not miss the timer event. We try to work around that by setting the minimum delta to a value which is larger than the theoretical time which elapses between the counter readout and the compare register write, but that's only true in theory. A NMI or SMI which hits between the readout and the write can easily push us beyond that limit. This would result in waiting for the next HPET timer interrupt until the 32bit wraparound of the counter happens which takes about 306 seconds. So we designed the next event function to look like: match = read_cnt() + delta; write_compare_ref(match); return read_cnt() < match ? 0 : -ETIME; At some point we got into trouble with certain ATI chipsets. Even the above "safe" procedure failed. The reason was that the write to the compare register was delayed probably for performance reasons. The theory was that they wanted to avoid the synchronization of the write with the HPET clock, which is understandable. So the write does not hit the compare register directly instead it goes to some intermediate register which is copied to the real compare register in sync with the HPET clock. That opens another window for hitting the dreaded "wait for a wraparound" problem. To work around that "optimization" we added a read back of the compare register which either enforced the update of the just written value or just delayed the readout of the counter enough to avoid the issue. We unfortunately never got any affirmative info from ATI/AMD about this. One thing is sure, that we nuked the performance "optimization" that way completely and I'm pretty sure that the result is worse than before some HW folks came up with those. Just for paranoia reasons I added a check whether the read back compare register value was the same as the value we wrote right before. That paranoia check triggered a couple of years after it was added on an Intel ICH9 chipset. Venki added a workaround (commit 8da854c) which was reading the compare register twice when the first check failed. We considered this to be a penalty in general and restricted the readback (thus the wasted CPU cycles) to the known to be affected ATI chipsets. This turned out to be a utterly wrong decision. 2.6.35 testers experienced massive problems and finally one of them bisected it down to commit 30a564be which spured some further investigation. Finally we got confirmation that the write to the compare register can be delayed by up to two HPET clock cycles which explains the problems nicely. All we can do about this is to go back to Venki's initial workaround in a slightly modified version. Just for the record I need to say, that all of this could have been avoided if hardware designers and of course the HPET committee would have thought about the consequences for a split second. It's out of my comprehension why designing a working timer is so hard. There are two ways to achieve it: 1) Use a counter wrap around aware compare_reg <= counter_reg implementation instead of the easy compare_reg == counter_reg Downsides: - It needs more silicon. - It needs a readout of the counter to apply a relative timeout. This is necessary as the counter does not run in any useful (and adjustable) frequency and there is no guarantee that the counter which is used for timer events is the same which is used for reading the actual time (and therefor for calculating the delta) Upsides: - None 2) Use a simple down counter for relative timer events Downsides: - Absolute timeouts are not possible, which is not a problem at all in the context of an OS and the expected max. latencies/jitter (also see Downsides of #1) Upsides: - It needs less or equal silicon. - It works ALWAYS - It is way faster than a compare register based solution (One write versus one write plus at least one and up to four reads) I would not be so grumpy about all of this, if I would not have been ignored for many years when pointing out these flaws to various hardware folks. I really hate timers (at least those which seem to be designed by janitors). Though finally we got a reasonable explanation plus a solution and I want to thank all the folks involved in chasing it down and providing valuable input to this. Bisected-by: Nix Reported-by: Artur Skawina Reported-by: Damien Wyart Reported-by: John Drescher Cc: Venkatesh Pallipadi Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Arjan van de Ven Cc: Andreas Herrmann Cc: Borislav Petkov Cc: stable@kernel.org Acked-by: Suresh Siddha Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/hpet.h | 1 - arch/x86/kernel/early-quirks.c | 18 ------------------ arch/x86/kernel/hpet.c | 31 +++++++++++++++++-------------- 3 files changed, 17 insertions(+), 33 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 004e6e25e91..1d5c08a1bdf 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -68,7 +68,6 @@ extern unsigned long force_hpet_address; extern u8 hpet_blockid; extern int hpet_force_user; extern u8 hpet_msi_disable; -extern u8 hpet_readback_cmp; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index e5cc7e82e60..ebdb85cf268 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -18,7 +18,6 @@ #include #include #include -#include static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -192,21 +191,6 @@ static void __init ati_bugs_contd(int num, int slot, int func) } #endif -/* - * Force the read back of the CMP register in hpet_next_event() - * to work around the problem that the CMP register write seems to be - * delayed. See hpet_next_event() for details. - * - * We do this on all SMBUS incarnations for now until we have more - * information about the affected chipsets. - */ -static void __init ati_hpet_bugs(int num, int slot, int func) -{ -#ifdef CONFIG_HPET_TIMER - hpet_readback_cmp = 1; -#endif -} - #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 #define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED) @@ -236,8 +220,6 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs }, { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, - { PCI_VENDOR_ID_ATI, PCI_ANY_ID, - PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_hpet_bugs }, {} }; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 351f9c0fea1..410fdb3f193 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -35,7 +35,6 @@ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ u8 hpet_msi_disable; -u8 hpet_readback_cmp; #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; @@ -395,23 +394,27 @@ static int hpet_next_event(unsigned long delta, * at that point and we would wait for the next hpet interrupt * forever. We found out that reading the CMP register back * forces the transfer so we can rely on the comparison with - * the counter register below. + * the counter register below. If the read back from the + * compare register does not match the value we programmed + * then we might have a real hardware problem. We can not do + * much about it here, but at least alert the user/admin with + * a prominent warning. * - * That works fine on those ATI chipsets, but on newer Intel - * chipsets (ICH9...) this triggers due to an erratum: Reading - * the comparator immediately following a write is returning - * the old value. + * An erratum on some chipsets (ICH9,..), results in + * comparator read immediately following a write returning old + * value. Workaround for this is to read this value second + * time, when first read returns old value. * - * We restrict the read back to the affected ATI chipsets (set - * by quirks) and also run it with hpet=verbose for debugging - * purposes. + * In fact the write to the comparator register is delayed up + * to two HPET cycles so the workaround we tried to restrict + * the readback to those known to be borked ATI chipsets + * failed miserably. So we give up on optimizations forever + * and penalize all HPET incarnations unconditionally. */ - if (hpet_readback_cmp || hpet_verbose) { - u32 cmp = hpet_readl(HPET_Tn_CMP(timer)); - - if (cmp != cnt) + if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) { + if (hpet_readl(HPET_Tn_CMP(timer)) != cnt) printk_once(KERN_WARNING - "hpet: compare register read back failed.\n"); + "hpet: compare register read back failed.\n"); } return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; -- cgit v1.2.3-70-g09d2 From c41d68a513c71e35a14f66d71782d27a79a81ea6 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 7 Sep 2010 16:16:18 -0700 Subject: compat: Make compat_alloc_user_space() incorporate the access_ok() compat_alloc_user_space() expects the caller to independently call access_ok() to verify the returned area. A missing call could introduce problems on some architectures. This patch incorporates the access_ok() check into compat_alloc_user_space() and also adds a sanity check on the length. The existing compat_alloc_user_space() implementations are renamed arch_compat_alloc_user_space() and are used as part of the implementation of the new global function. This patch assumes NULL will cause __get_user()/__put_user() to either fail or access userspace on all architectures. This should be followed by checking the return value of compat_access_user_space() for NULL in the callers, at which time the access_ok() in the callers can also be removed. Reported-by: Ben Hawkes Signed-off-by: H. Peter Anvin Acked-by: Benjamin Herrenschmidt Acked-by: Chris Metcalf Acked-by: David S. Miller Acked-by: Ingo Molnar Acked-by: Thomas Gleixner Acked-by: Tony Luck Cc: Andrew Morton Cc: Arnd Bergmann Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Heiko Carstens Cc: Helge Deller Cc: James Bottomley Cc: Kyle McMartin Cc: Martin Schwidefsky Cc: Paul Mackerras Cc: Ralf Baechle Cc: --- arch/ia64/include/asm/compat.h | 2 +- arch/mips/include/asm/compat.h | 2 +- arch/parisc/include/asm/compat.h | 2 +- arch/powerpc/include/asm/compat.h | 2 +- arch/s390/include/asm/compat.h | 2 +- arch/sparc/include/asm/compat.h | 2 +- arch/tile/include/asm/compat.h | 2 +- arch/x86/include/asm/compat.h | 2 +- include/linux/compat.h | 3 +++ kernel/compat.c | 21 +++++++++++++++++++++ 10 files changed, 32 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/ia64/include/asm/compat.h b/arch/ia64/include/asm/compat.h index f90edc85b50..9301a282161 100644 --- a/arch/ia64/include/asm/compat.h +++ b/arch/ia64/include/asm/compat.h @@ -199,7 +199,7 @@ ptr_to_compat(void __user *uptr) } static __inline__ void __user * -compat_alloc_user_space (long len) +arch_compat_alloc_user_space (long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *) (((regs->r12 & 0xffffffff) & -16) - len); diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h index 613f6912dfc..dbc51065df5 100644 --- a/arch/mips/include/asm/compat.h +++ b/arch/mips/include/asm/compat.h @@ -145,7 +145,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = (struct pt_regs *) ((unsigned long) current_thread_info() + THREAD_SIZE - 32) - 1; diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h index 02b77baa5da..efa0b60c63f 100644 --- a/arch/parisc/include/asm/compat.h +++ b/arch/parisc/include/asm/compat.h @@ -147,7 +147,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static __inline__ void __user *compat_alloc_user_space(long len) +static __inline__ void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = ¤t->thread.regs; return (void __user *)regs->gr[30]; diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 396d21a8005..a11d4eac4f9 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -134,7 +134,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current->thread.regs; unsigned long usp = regs->gpr[1]; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index 104f2007f09..a875c2f542e 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -181,7 +181,7 @@ static inline int is_compat_task(void) #endif -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { unsigned long stack; diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 5016f76ea98..6f57325bb88 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -167,7 +167,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = current_thread_info()->kregs; unsigned long usp = regs->u_regs[UREG_I6]; diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h index 5a34da6cdd7..345d81ce44b 100644 --- a/arch/tile/include/asm/compat.h +++ b/arch/tile/include/asm/compat.h @@ -195,7 +195,7 @@ static inline unsigned long ptr_to_compat_reg(void __user *uptr) return (long)(int)(long __force)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 306160e58b4..1d9cd27c292 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -205,7 +205,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -static inline void __user *compat_alloc_user_space(long len) +static inline void __user *arch_compat_alloc_user_space(long len) { struct pt_regs *regs = task_pt_regs(current); return (void __user *)regs->sp - len; diff --git a/include/linux/compat.h b/include/linux/compat.h index 9ddc8780e8d..5778b559d59 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -360,5 +360,8 @@ extern ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer); + +extern void __user *compat_alloc_user_space(unsigned long len); + #endif /* CONFIG_COMPAT */ #endif /* _LINUX_COMPAT_H */ diff --git a/kernel/compat.c b/kernel/compat.c index e167efce842..c9e2ec0b34a 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -1126,3 +1126,24 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info) return 0; } + +/* + * Allocate user-space memory for the duration of a single system call, + * in order to marshall parameters inside a compat thunk. + */ +void __user *compat_alloc_user_space(unsigned long len) +{ + void __user *ptr; + + /* If len would occupy more than half of the entire compat space... */ + if (unlikely(len > (((compat_uptr_t)~0) >> 1))) + return NULL; + + ptr = arch_compat_alloc_user_space(len); + + if (unlikely(!access_ok(VERIFY_WRITE, ptr, len))) + return NULL; + + return ptr; +} +EXPORT_SYMBOL_GPL(compat_alloc_user_space); -- cgit v1.2.3-70-g09d2 From 89e45aac42d40426c97e6901811309bf49c4993f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 17 Sep 2010 03:24:13 +0200 Subject: x86: Fix instruction breakpoint encoding Lengths and types of breakpoints are encoded in a half byte into CPU registers. However when we extract these values and store them, we add a high half byte part to them: 0x40 to the length and 0x80 to the type. When that gets reloaded to the CPU registers, the high part is masked. While making the instruction breakpoints available for perf, I zapped that high part on instruction breakpoint encoding and that broke the arch -> generic translation used by ptrace instruction breakpoints. Writing dr7 to set an inst breakpoint was then failing. There is no apparent reason for these high parts so we could get rid of them altogether. That's an invasive change though so let's do that later and for now fix the problem by restoring that inst breakpoint high part encoding in this sole patch. Reported-by: Kelvie Wong Signed-off-by: Frederic Weisbecker Cc: Prasad Cc: Mahesh Salgaonkar Cc: Will Deacon --- arch/x86/include/asm/hw_breakpoint.h | 2 +- arch/x86/kernel/hw_breakpoint.c | 40 +++++++++++++++++------------------- 2 files changed, 20 insertions(+), 22 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 528a11e8d3e..824ca07860d 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,7 +20,7 @@ struct arch_hw_breakpoint { #include /* Available HW breakpoint length encodings */ -#define X86_BREAKPOINT_LEN_X 0x00 +#define X86_BREAKPOINT_LEN_X 0x40 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a474ec37c32..ff15c9dcc25 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -206,11 +206,27 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) int arch_bp_generic_fields(int x86_len, int x86_type, int *gen_len, int *gen_type) { - /* Len */ - switch (x86_len) { - case X86_BREAKPOINT_LEN_X: + /* Type */ + switch (x86_type) { + case X86_BREAKPOINT_EXECUTE: + if (x86_len != X86_BREAKPOINT_LEN_X) + return -EINVAL; + + *gen_type = HW_BREAKPOINT_X; *gen_len = sizeof(long); + return 0; + case X86_BREAKPOINT_WRITE: + *gen_type = HW_BREAKPOINT_W; break; + case X86_BREAKPOINT_RW: + *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (x86_len) { case X86_BREAKPOINT_LEN_1: *gen_len = HW_BREAKPOINT_LEN_1; break; @@ -229,21 +245,6 @@ int arch_bp_generic_fields(int x86_len, int x86_type, return -EINVAL; } - /* Type */ - switch (x86_type) { - case X86_BREAKPOINT_EXECUTE: - *gen_type = HW_BREAKPOINT_X; - break; - case X86_BREAKPOINT_WRITE: - *gen_type = HW_BREAKPOINT_W; - break; - case X86_BREAKPOINT_RW: - *gen_type = HW_BREAKPOINT_W | HW_BREAKPOINT_R; - break; - default: - return -EINVAL; - } - return 0; } @@ -316,9 +317,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) ret = -EINVAL; switch (info->len) { - case X86_BREAKPOINT_LEN_X: - align = sizeof(long) -1; - break; case X86_BREAKPOINT_LEN_1: align = 0; break; -- cgit v1.2.3-70-g09d2 From e9bf51971157e367aabfc111a8219db010f69cd4 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 20 Sep 2010 14:33:07 +0200 Subject: x86/amd-iommu: Set iommu configuration flags in enable-loop This patch moves the setting of the configuration and feature flags out out the acpi table parsing path and moves it into the iommu-enable path. This is needed to reliably fix resume-from-s3. Cc: stable@kernel.org Signed-off-by: Joerg Roedel --- arch/x86/include/asm/amd_iommu_types.h | 3 +++ arch/x86/kernel/amd_iommu_init.c | 49 +++++++++++++++++++--------------- 2 files changed, 30 insertions(+), 22 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index 7014e88bc77..ef2d5cd7d7e 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -368,6 +368,9 @@ struct amd_iommu { /* capabilities of that IOMMU read from ACPI */ u32 cap; + /* flags read from acpi table */ + u8 acpi_flags; + /* * Capability pointer. There could be more than one IOMMU per PCI * device function if there are more than one AMD IOMMU capability diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 3cc63e2b8dd..85e9817ead4 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -649,29 +649,9 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu, struct ivhd_entry *e; /* - * First set the recommended feature enable bits from ACPI - * into the IOMMU control registers + * First save the recommended feature enable bits from ACPI */ - h->flags & IVHD_FLAG_HT_TUN_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : - iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); - - h->flags & IVHD_FLAG_PASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_PASSPW_EN); - - h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : - iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); - - h->flags & IVHD_FLAG_ISOC_EN_MASK ? - iommu_feature_enable(iommu, CONTROL_ISOC_EN) : - iommu_feature_disable(iommu, CONTROL_ISOC_EN); - - /* - * make IOMMU memory accesses cache coherent - */ - iommu_feature_enable(iommu, CONTROL_COHERENT_EN); + iommu->acpi_flags = h->flags; /* * Done. Now parse the device entries @@ -1116,6 +1096,30 @@ static void init_device_table(void) } } +static void iommu_init_flags(struct amd_iommu *iommu) +{ + iommu->acpi_flags & IVHD_FLAG_HT_TUN_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) : + iommu_feature_disable(iommu, CONTROL_HT_TUN_EN); + + iommu->acpi_flags & IVHD_FLAG_PASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_PASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_PASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_RESPASSPW_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) : + iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN); + + iommu->acpi_flags & IVHD_FLAG_ISOC_EN_MASK ? + iommu_feature_enable(iommu, CONTROL_ISOC_EN) : + iommu_feature_disable(iommu, CONTROL_ISOC_EN); + + /* + * make IOMMU memory accesses cache coherent + */ + iommu_feature_enable(iommu, CONTROL_COHERENT_EN); +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1126,6 +1130,7 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); -- cgit v1.2.3-70-g09d2 From 4c894f47bb49284008073d351c0ddaac8860864e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 23 Sep 2010 15:15:19 +0200 Subject: x86/amd-iommu: Work around S3 BIOS bug This patch adds a workaround for an IOMMU BIOS problem to the AMD IOMMU driver. The result of the bug is that the IOMMU does not execute commands anymore when the system comes out of the S3 state resulting in system failure. The bug in the BIOS is that is does not restore certain hardware specific registers correctly. This workaround reads out the contents of these registers at boot time and restores them on resume from S3. The workaround is limited to the specific IOMMU chipset where this problem occurs. Cc: stable@kernel.org Signed-off-by: Joerg Roedel --- arch/x86/include/asm/amd_iommu_proto.h | 6 ++++++ arch/x86/include/asm/amd_iommu_types.h | 9 +++++++++ arch/x86/kernel/amd_iommu_init.c | 18 ++++++++++++++++++ include/linux/pci_ids.h | 3 +++ 4 files changed, 36 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h index d2544f1d705..cb030374b90 100644 --- a/arch/x86/include/asm/amd_iommu_proto.h +++ b/arch/x86/include/asm/amd_iommu_proto.h @@ -38,4 +38,10 @@ static inline void amd_iommu_stats_init(void) { } #endif /* !CONFIG_AMD_IOMMU_STATS */ +static inline bool is_rd890_iommu(struct pci_dev *pdev) +{ + return (pdev->vendor == PCI_VENDOR_ID_ATI) && + (pdev->device == PCI_DEVICE_ID_RD890_IOMMU); +} + #endif /* _ASM_X86_AMD_IOMMU_PROTO_H */ diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h index ef2d5cd7d7e..08616180dea 100644 --- a/arch/x86/include/asm/amd_iommu_types.h +++ b/arch/x86/include/asm/amd_iommu_types.h @@ -414,6 +414,15 @@ struct amd_iommu { /* default dma_ops domain for that IOMMU */ struct dma_ops_domain *default_dom; + + /* + * This array is required to work around a potential BIOS bug. + * The BIOS may miss to restore parts of the PCI configuration + * space when the system resumes from S3. The result is that the + * IOMMU does not execute commands anymore which leads to system + * failure. + */ + u32 cache_cfg[4]; }; /* diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 85e9817ead4..5a170cbbbed 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -632,6 +632,13 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu) iommu->last_device = calc_devid(MMIO_GET_BUS(range), MMIO_GET_LD(range)); iommu->evt_msi_num = MMIO_MSI_NUM(misc); + + if (is_rd890_iommu(iommu->dev)) { + pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]); + pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]); + pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]); + pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]); + } } /* @@ -1120,6 +1127,16 @@ static void iommu_init_flags(struct amd_iommu *iommu) iommu_feature_enable(iommu, CONTROL_COHERENT_EN); } +static void iommu_apply_quirks(struct amd_iommu *iommu) +{ + if (is_rd890_iommu(iommu->dev)) { + pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]); + pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]); + pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]); + pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]); + } +} + /* * This function finally enables all IOMMUs found in the system after * they have been initialized @@ -1130,6 +1147,7 @@ static void enable_iommus(void) for_each_iommu(iommu) { iommu_disable(iommu); + iommu_apply_quirks(iommu); iommu_init_flags(iommu); iommu_set_device_table(iommu); iommu_enable_command_buffer(iommu); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 10d33309e9a..570fddeb038 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -393,6 +393,9 @@ #define PCI_DEVICE_ID_VLSI_82C147 0x0105 #define PCI_DEVICE_ID_VLSI_VAS96011 0x0702 +/* AMD RD890 Chipset */ +#define PCI_DEVICE_ID_RD890_IOMMU 0x5a23 + #define PCI_VENDOR_ID_ADL 0x1005 #define PCI_DEVICE_ID_ADL_2301 0x2301 -- cgit v1.2.3-70-g09d2 From a46590533ad7b0f3f640732081d7e1658145c0ba Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 23 Sep 2010 22:21:34 -0700 Subject: x86/hwmon: fix initialization of coretemp Using cpuid_eax() to determine feature availability on other than the current CPU is invalid. And feature availability should also be checked in the hotplug code path. Signed-off-by: Jan Beulich Cc: Rudolf Marek Cc: Fenghua Yu Signed-off-by: Guenter Roeck --- arch/x86/include/asm/cpufeature.h | 1 + arch/x86/kernel/cpu/scattered.c | 1 + drivers/hwmon/coretemp.c | 29 +++++++++++++---------------- 3 files changed, 15 insertions(+), 16 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index c6fbb7b430d..3f76523589a 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -168,6 +168,7 @@ #define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ #define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ #define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 34b4dad6f0b..d4907951512 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { + { X86_FEATURE_DTS, CR_EAX, 0, 0x00000006, 0 }, { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c index 6b3ef553bd1..5850da64ae2 100644 --- a/drivers/hwmon/coretemp.c +++ b/drivers/hwmon/coretemp.c @@ -423,9 +423,18 @@ static int __cpuinit coretemp_device_add(unsigned int cpu) int err; struct platform_device *pdev; struct pdev_entry *pdev_entry; -#ifdef CONFIG_SMP struct cpuinfo_x86 *c = &cpu_data(cpu); -#endif + + /* + * CPUID.06H.EAX[0] indicates whether the CPU has thermal + * sensors. We check this bit only, all the early CPUs + * without thermal sensors will be filtered out. + */ + if (!cpu_has(c, X86_FEATURE_DTS)) { + printk(KERN_INFO DRVNAME ": CPU (model=0x%x)" + " has no thermal sensor.\n", c->x86_model); + return 0; + } mutex_lock(&pdev_list_mutex); @@ -527,20 +536,8 @@ static int __init coretemp_init(void) if (err) goto exit; - for_each_online_cpu(i) { - struct cpuinfo_x86 *c = &cpu_data(i); - /* - * CPUID.06H.EAX[0] indicates whether the CPU has thermal - * sensors. We check this bit only, all the early CPUs - * without thermal sensors will be filtered out. - */ - if (c->cpuid_level >= 6 && (cpuid_eax(0x06) & 0x01)) - coretemp_device_add(i); - else { - printk(KERN_INFO DRVNAME ": CPU (model=0x%x)" - " has no thermal sensor.\n", c->x86_model); - } - } + for_each_online_cpu(i) + coretemp_device_add(i); #ifndef CONFIG_HOTPLUG_CPU if (list_empty(&pdev_list)) { -- cgit v1.2.3-70-g09d2 From c9e2fbd909c20b165b2b9ffb59f8b674cf0a55b0 Mon Sep 17 00:00:00 2001 From: Alexander Chumachenko Date: Thu, 1 Apr 2010 15:34:52 +0300 Subject: x86: Avoid 'constant_test_bit()' misoptimization due to cast to non-volatile While debugging bit_spin_lock() hang, it was tracked down to gcc-4.4 misoptimization of non-inlined constant_test_bit() due to non-volatile addr when 'const volatile unsigned long *addr' cast to 'unsigned long *' with subsequent unconditional jump to pause (and not to the test) leading to hang. Compiling with gcc-4.3 or disabling CONFIG_OPTIMIZE_INLINING yields inlined constant_test_bit() and correct jump, thus working around the kernel bug. Other arches than asm-x86 may implement this slightly differently; 2.6.29 mitigates the misoptimization by changing the function prototype (commit c4295fbb6048d85f0b41c5ced5cbf63f6811c46c) but probably fixing the issue itself is better. Signed-off-by: Alexander Chumachenko Signed-off-by: Michael Shigorin Acked-by: Linus Torvalds Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 545776efeb1..bafd80defa4 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -309,7 +309,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) { return ((1UL << (nr % BITS_PER_LONG)) & - (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0; + (addr[nr / BITS_PER_LONG])) != 0; } static inline int variable_test_bit(int nr, volatile const unsigned long *addr) -- cgit v1.2.3-70-g09d2