From 6c2e94033df5ca11149e52dd179b8dde3172e9bf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 7 Nov 2008 12:33:49 +0100 Subject: x86: apic honour irq affinity which was set in early boot setup_ioapic_dest() is called after the non boot cpus have been brought up. It sets the irq affinity of all already configured interrupts to all cpus and ignores affinity settings which were done by the early bootup code. If the IRQ_NO_BALANCING or IRQ_AFFINITY_SET flags are set then use the affinity mask from the irq descriptor and not TARGET_CPUS. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/kernel/io_apic.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 7a3f2028e2eb..988ee89467d3 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -3761,7 +3761,9 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity) void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; + struct irq_desc *desc; struct irq_cfg *cfg; + cpumask_t mask; if (skip_ioapic_setup == 1) return; @@ -3778,16 +3780,30 @@ void __init setup_ioapic_dest(void) * cpu is online. */ cfg = irq_cfg(irq); - if (!cfg->vector) + if (!cfg->vector) { setup_IO_APIC_irq(ioapic, pin, irq, irq_trigger(irq_entry), irq_polarity(irq_entry)); + continue; + + } + + /* + * Honour affinities which have been set in early boot + */ + desc = irq_to_desc(irq); + if (desc->status & + (IRQ_NO_BALANCING | IRQ_AFFINITY_SET)) + mask = desc->affinity; + else + mask = TARGET_CPUS; + #ifdef CONFIG_INTR_REMAP - else if (intr_remapping_enabled) - set_ir_ioapic_affinity_irq(irq, TARGET_CPUS); -#endif + if (intr_remapping_enabled) + set_ir_ioapic_affinity_irq(irq, mask); else - set_ioapic_affinity_irq(irq, TARGET_CPUS); +#endif + set_ioapic_affinity_irq(irq, mask); } } -- cgit v1.2.1 From a266d9f1253a38ec2d5655ebcd6846298b0554f4 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Fri, 21 Nov 2008 14:49:25 +0100 Subject: [CPUFREQ] powernow-k8: ignore out-of-range PstateStatus value A workaround for AMD CPU family 11h erratum 311 might cause that the P-state Status Register shows a "current P-state" which is larger than the "current P-state limit" in P-state Current Limit Register. For the wrong P-state value there is no ACPI _PSS object defined and powernow-k8/cpufreq can't determine the proper CPU frequency for that state. As a consequence this can cause a panic during boot (potentially with all recent kernel versions -- at least I have reproduced it with various 2.6.27 kernels and with the current .28 series), as an example: powernow-k8: Found 1 AMD Turion(tm)X2 Ultra DualCore Mobile ZM-82 processors (2 \ ) powernow-k8: 0 : pstate 0 (2200 MHz) powernow-k8: 1 : pstate 1 (1100 MHz) powernow-k8: 2 : pstate 2 (600 MHz) BUG: unable to handle kernel paging request at ffff88086e7528b8 IP: [] cpufreq_stats_update+0x4a/0x5f PGD 202063 PUD 0 Oops: 0002 [#1] SMP last sysfs file: CPU 1 Modules linked in: Pid: 1, comm: swapper Not tainted 2.6.28-rc3-dirty #16 RIP: 0010:[] [] cpufreq_stats_update+0x4a/0\ f Synaptics claims to have extended capabilities, but I'm not able to read them.<6\ 6 RAX: 0000000000000000 RBX: 0000000000000001 RCX: ffff88006e7528c0 RDX: 00000000ffffffff RSI: ffff88006e54af00 RDI: ffffffff808f056c RBP: 00000000fffee697 R08: 0000000000000003 R09: ffff88006e73f080 R10: 0000000000000001 R11: 00000000002191c0 R12: ffff88006fb83c10 R13: 00000000ffffffff R14: 0000000000000001 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88006fb50740(0000) knlGS:0000000000000000 Unable to initialize Synaptics hardware. CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: ffff88086e7528b8 CR3: 0000000000201000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process swapper (pid: 1, threadinfo ffff88006fb82000, task ffff88006fb816d0) Stack: ffff88006e74da50 0000000000000000 ffff88006e54af00 ffffffff804863c7 ffff88006e74da50 0000000000000000 00000000ffffffff 0000000000000000 ffff88006fb83c10 ffffffff8024b46c ffffffff808f0560 ffff88006fb83c10 Call Trace: [] ? cpufreq_stat_notifier_trans+0x51/0x83 [] ? notifier_call_chain+0x29/0x4c [] ? __srcu_notifier_call_chain+0x46/0x61 [] ? cpufreq_notify_transition+0x93/0xa9 [] ? powernowk8_target+0x1e8/0x5f3 [] ? cpufreq_governor_performance+0x1b/0x20 [] ? __cpufreq_governor+0x71/0xa8 [] ? __cpufreq_set_policy+0x101/0x13e [] ? cpufreq_add_dev+0x3f0/0x4cd [] ? handle_update+0x0/0x8 [] ? sysdev_driver_register+0xb6/0x10d [] ? powernowk8_init+0x0/0x7e [] ? cpufreq_register_driver+0x8f/0x140 [] ? _stext+0x56/0x14f [] ? proc_register+0x122/0x17d [] ? create_proc_entry+0x73/0x8a [] ? register_irq_proc+0x92/0xaa [] ? init_irq_proc+0x57/0x69 [] ? kernel_init+0x116/0x169 [] ? child_rip+0xa/0x11 [] ? kernel_init+0x0/0x169 [] ? child_rip+0x0/0x11 Code: 05 c5 83 36 00 48 c7 c2 48 5d 86 80 48 8b 04 d8 48 8b 40 08 48 8b 34 02 48\ RIP [] cpufreq_stats_update+0x4a/0x5f RSP CR2: ffff88086e7528b8 ---[ end trace 0678bac75e67a2f7 ]--- Kernel panic - not syncing: Attempted to kill init! In short, aftereffect of the wrong P-state is that cpufreq_stats_update() uses "-1" as index for some array in cpufreq_stats_update (unsigned int cpu) { ... if (stat->time_in_state) stat->time_in_state[stat->last_index] = cputime64_add(stat->time_in_state[stat->last_index], cputime_sub(cur_time, stat->last_time)); ... } Fortunately, the wrong P-state value is returned only if the core is in P-state 0. This fix solves the problem by detecting the out-of-range P-state, ignoring it, and using "0" instead. Cc: Mark Langsdorf Signed-off-by: Andreas Herrmann Signed-off-by: Dave Jones --- arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 18 +++++++++++++++--- arch/x86/kernel/cpu/cpufreq/powernow-k8.h | 17 ++++++++++++++++- 2 files changed, 31 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index d3dcd58b87cd..7f05f44b97e9 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -115,9 +115,20 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data) u32 i = 0; if (cpu_family == CPU_HW_PSTATE) { - rdmsr(MSR_PSTATE_STATUS, lo, hi); - i = lo & HW_PSTATE_MASK; - data->currpstate = i; + if (data->currpstate == HW_PSTATE_INVALID) { + /* read (initial) hw pstate if not yet set */ + rdmsr(MSR_PSTATE_STATUS, lo, hi); + i = lo & HW_PSTATE_MASK; + + /* + * a workaround for family 11h erratum 311 might cause + * an "out-of-range Pstate if the core is in Pstate-0 + */ + if (i >= data->numps) + data->currpstate = HW_PSTATE_0; + else + data->currpstate = i; + } return 0; } do { @@ -1121,6 +1132,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) } data->cpu = pol->cpu; + data->currpstate = HW_PSTATE_INVALID; if (powernow_k8_cpu_init_acpi(data)) { /* diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index ab48cfed4d96..65cfb5d7f77f 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -5,6 +5,19 @@ * http://www.gnu.org/licenses/gpl.html */ + +enum pstate { + HW_PSTATE_INVALID = 0xff, + HW_PSTATE_0 = 0, + HW_PSTATE_1 = 1, + HW_PSTATE_2 = 2, + HW_PSTATE_3 = 3, + HW_PSTATE_4 = 4, + HW_PSTATE_5 = 5, + HW_PSTATE_6 = 6, + HW_PSTATE_7 = 7, +}; + struct powernow_k8_data { unsigned int cpu; @@ -23,7 +36,9 @@ struct powernow_k8_data { u32 exttype; /* extended interface = 1 */ /* keep track of the current fid / vid or pstate */ - u32 currvid, currfid, currpstate; + u32 currvid; + u32 currfid; + enum pstate currpstate; /* the powernow_table includes all frequency and vid/fid pairings: * fid are the lower 8 bits of the index, vid are the upper 8 bits. -- cgit v1.2.1 From ffd565a8b817d1eb4b25184e8418e8d96c3f56f6 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Tue, 25 Nov 2008 17:18:03 +0100 Subject: x86: fixup config space size of CPU functions for AMD family 11h Impact: extend allowed configuration space access on 11h CPUs from 256 to 4K Signed-off-by: Andreas Herrmann Acked-by: Jesse Barnes Signed-off-by: Ingo Molnar --- arch/x86/pci/fixup.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 3c27a809393b..2051dc96b8e9 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -496,21 +496,24 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015, pci_siemens_interrupt_controller); /* - * Regular PCI devices have 256 bytes, but AMD Family 10h Opteron ext config - * have 4096 bytes. Even if the device is capable, that doesn't mean we can - * access it. Maybe we don't have a way to generate extended config space - * accesses. So check it + * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have + * 4096 bytes configuration space for each function of their processor + * configuration space. */ -static void fam10h_pci_cfg_space_size(struct pci_dev *dev) +static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev) { dev->cfg_size = pci_cfg_space_size_ext(dev); } - -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, fam10h_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, fam10h_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, fam10h_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, fam10h_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, fam10h_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size); /* * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from -- cgit v1.2.1 From b627c8b17ccacba38c975bc0f69a49fc4e5261c9 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 20 Nov 2008 20:49:56 +0100 Subject: x86: always define DECLARE_PCI_UNMAP* macros Impact: fix boot crash on AMD IOMMU if CONFIG_GART_IOMMU is off Currently these macros evaluate to a no-op except the kernel is compiled with GART or Calgary support. But we also need these macros when we have SWIOTLB, VT-d or AMD IOMMU in the kernel. Since we always compile at least with SWIOTLB we can define these macros always. This patch is also for stable backport for the same reason the SWIOTLB default selection patch is. Signed-off-by: Joerg Roedel Cc: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/pci_64.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index 5b28995d664e..d02d936840a3 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -34,8 +34,6 @@ extern void pci_iommu_alloc(void); */ #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) -#if defined(CONFIG_GART_IOMMU) || defined(CONFIG_CALGARY_IOMMU) - #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ dma_addr_t ADDR_NAME; #define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ @@ -49,18 +47,6 @@ extern void pci_iommu_alloc(void); #define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ (((PTR)->LEN_NAME) = (VAL)) -#else -/* No IOMMU */ - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) -#define pci_unmap_addr(PTR, ADDR_NAME) (0) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) -#define pci_unmap_len(PTR, LEN_NAME) (0) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) - -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_X86_PCI_64_H */ -- cgit v1.2.1 From 2236d252e001ea57d53cec1954f680e503f3b8bc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Nov 2008 17:37:34 +0000 Subject: enable_IR_x2apic() needs to be __init calls __init, called only from __init Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- arch/x86/kernel/apic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c index 04a7f960bbc0..16f94879b525 100644 --- a/arch/x86/kernel/apic.c +++ b/arch/x86/kernel/apic.c @@ -1315,7 +1315,7 @@ void enable_x2apic(void) } } -void enable_IR_x2apic(void) +void __init enable_IR_x2apic(void) { #ifdef CONFIG_INTR_REMAP int ret; -- cgit v1.2.1 From 23a14b9e9db49ed5f7683857557c26c874d4abb6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Nov 2008 17:37:44 +0000 Subject: kvm_setup_secondary_clock() is cpuinit Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- arch/x86/kernel/kvmclock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1c9cc431ea4f..e169ae9b6a62 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -128,7 +128,7 @@ static int kvm_register_clock(char *txt) } #ifdef CONFIG_X86_LOCAL_APIC -static void __devinit kvm_setup_secondary_clock(void) +static void __cpuinit kvm_setup_secondary_clock(void) { /* * Now that the first cpu already had this clocksource initialized, -- cgit v1.2.1 From 37af46efa5413c6f4c25d9a24b4c43f2cc718eed Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Nov 2008 17:37:54 +0000 Subject: xen_setup_vcpu_info_placement() is not init on x86 ... so get xen-ops.h in agreement with xen/smp.c Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- arch/x86/xen/xen-ops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index d7422dc2a55c..9e1afae8461f 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -49,7 +49,7 @@ bool xen_vcpu_stolen(int vcpu); void xen_mark_init_mm_pinned(void); -void __init xen_setup_vcpu_info_placement(void); +void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP void xen_smp_init(void); -- cgit v1.2.1 From df6b07949b6cab9d119363d02ef63379160f6c82 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 22 Nov 2008 17:38:04 +0000 Subject: xen_play_dead() is __cpuinit Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- arch/x86/xen/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d77da613b1d2..acd9b6705e02 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -362,7 +362,7 @@ static void xen_cpu_die(unsigned int cpu) alternatives_smp_switch(0); } -static void xen_play_dead(void) +static void __cpuinit xen_play_dead(void) /* used only with CPU_HOTPLUG */ { play_dead_common(); HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL); -- cgit v1.2.1 From 96b8936a9ed08746e47081458a5eb9e43a751e24 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 25 Nov 2008 08:10:03 +0100 Subject: remove __ARCH_WANT_COMPAT_SYS_PTRACE All architectures now use the generic compat_sys_ptrace, as should every new architecture that needs 32bit compat (if we'll ever get another). Remove the now superflous __ARCH_WANT_COMPAT_SYS_PTRACE define, and also kill a comment about __ARCH_SYS_PTRACE that was added after __ARCH_SYS_PTRACE was already gone. Signed-off-by: Christoph Hellwig Acked-by: David S. Miller Signed-off-by: Linus Torvalds --- arch/x86/include/asm/ptrace.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index d1531c8480b7..eefb0594b058 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -271,8 +271,6 @@ extern int do_get_thread_area(struct task_struct *p, int idx, extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); -#define __ARCH_WANT_COMPAT_SYS_PTRACE - #endif /* __KERNEL__ */ #endif /* !__ASSEMBLY__ */ -- cgit v1.2.1