From 30d746c68025ee69ac17219aacc9b1614d951f01 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 7 Apr 2011 14:13:15 +0200 Subject: x86/ce4100: Add reg property to bridges without the reg property Ben's new code won't find the PCI & ISA bridge and the devices won't get the DT-node attached. Signed-off-by: Sebastian Andrzej Siewior Acked-by: Thomas Gleixner Cc: davem@davemloft.net Cc: monstr@monstr.eu Cc: Benjamin Herrenschmidt Link: http://lkml.kernel.org/r/20110407121315.GA9204@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/platform/ce4100/falconfalls.dts | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/platform/ce4100/falconfalls.dts b/arch/x86/platform/ce4100/falconfalls.dts index dc701ea5854..2d6d226f2b1 100644 --- a/arch/x86/platform/ce4100/falconfalls.dts +++ b/arch/x86/platform/ce4100/falconfalls.dts @@ -74,6 +74,7 @@ compatible = "intel,ce4100-pci", "pci"; device_type = "pci"; bus-range = <1 1>; + reg = <0x0800 0x0 0x0 0x0 0x0>; ranges = <0x2000000 0 0xdffe0000 0x2000000 0 0xdffe0000 0 0x1000>; interrupt-parent = <&ioapic2>; @@ -412,6 +413,7 @@ #address-cells = <2>; #size-cells = <1>; compatible = "isa"; + reg = <0xf800 0x0 0x0 0x0 0x0>; ranges = <1 0 0 0 0 0x100>; rtc@70 { -- cgit v1.2.3-18-g5258 From 9d90e49da57fe73a2f35334fdd2fb60dbf3933ed Mon Sep 17 00:00:00 2001 From: Jacob Pan Date: Fri, 8 Apr 2011 11:23:00 -0700 Subject: x86/mrst: Fix boot crash caused by incorrect pin to irq mapping Moorestown systems crash on boot because the secondary CPU clockevent (apbt1) will fail to request irq#1, which does not have ioapic chip in its irq_desc[] entry. Background: Moorestown platform does not have ISA bus nor legacy IRQs. It reuses the range of legacy IRQs for regular device interrupts. The routing information of early system device IRQs (timers) are obtained from firmware provided SFI tables. We reuse/fake MP configuration table to facilitate IRQ setup with IOAPIC. Maintaining a 1:1 mapping of IOAPIC pin (RTE entry) and IRQ# makes routing information clean and easy to understand on Moorestown. Though optional. This patch allows SFI timer and vRTC IRQ to be treated as ISA IRQ so that pin2irq mapping will be 1:1. Also fixed MP table type and use macros to clearly set MP IRQ entries. As a result, apbt timer and RTC interrupts on Moorestown are within legacy IRQ range: # cat /proc/interrupts CPU0 CPU1 0: 11249 0 IO-APIC-edge apbt0 1: 0 12271 IO-APIC-edge apbt1 8: 887 0 IO-APIC-fasteoi dw_spi 13: 0 0 IO-APIC-fasteoi INTEL_MID_DMAC2 14: 0 0 IO-APIC-fasteoi rtc0 Further discussion of this patch can be found at: https://lkml.org/lkml/2010/6/10/70 Suggested-by: "Eric W. Biederman" Signed-off-by: Jacob Pan Cc: Feng Tang Cc: Alan Cox Cc: Arjan van de Ven Link: http://lkml.kernel.org/r/1302286980-21139-1-git-send-email-jacob.jun.pan@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/platform/mrst/mrst.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c index 5c0207bf959..275dbc19e2c 100644 --- a/arch/x86/platform/mrst/mrst.c +++ b/arch/x86/platform/mrst/mrst.c @@ -97,11 +97,11 @@ static int __init sfi_parse_mtmr(struct sfi_table_header *table) pentry->freq_hz, pentry->irq); if (!pentry->irq) continue; - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; /* triggering mode edge bit 2-3, active high polarity bit 0-1 */ mp_irq.irqflag = 5; - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -168,10 +168,10 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) { pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->irq); - mp_irq.type = MP_IOAPIC; + mp_irq.type = MP_INTSRC; mp_irq.irqtype = mp_INT; mp_irq.irqflag = 0xf; /* level trigger and active low */ - mp_irq.srcbus = 0; + mp_irq.srcbus = MP_BUS_ISA; mp_irq.srcbusirq = pentry->irq; /* IRQ */ mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; @@ -282,7 +282,7 @@ void __init x86_mrst_early_setup(void) /* Avoid searching for BIOS MP tables */ x86_init.mpparse.find_smp_config = x86_init_noop; x86_init.mpparse.get_smp_config = x86_init_uint_noop; - + set_bit(MP_BUS_ISA, mp_bus_not_pci); } /* -- cgit v1.2.3-18-g5258 From 7d6b46707f2491a94f4bd3b4329d2d7f809e9368 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 15 Apr 2011 20:39:01 +0900 Subject: x86, NUMA: Fix fakenuma boot failure Currently, numa=fake boot parameter is broken. If it's used, kernel may panic due to devide by zero error depending on CPU configuration Call Trace: [] find_busiest_group+0x38c/0xd30 [] ? local_clock+0x6f/0x80 [] load_balance+0xa3/0x600 [] idle_balance+0xf3/0x180 [] schedule+0x722/0x7d0 [] ? wait_for_common+0x128/0x190 [] schedule_timeout+0x265/0x320 [] ? lock_release_holdtime+0x35/0x1a0 [] ? wait_for_common+0x128/0x190 [] ? __lock_release+0x9c/0x1d0 [] ? _raw_spin_unlock_irq+0x30/0x40 [] ? _raw_spin_unlock_irq+0x30/0x40 [] wait_for_common+0x130/0x190 [] ? try_to_wake_up+0x510/0x510 [] wait_for_completion+0x1d/0x20 [] kthread_create_on_node+0xac/0x150 [] ? process_scheduled_works+0x40/0x40 [] ? wait_for_common+0x4f/0x190 [] __alloc_workqueue_key+0x1a3/0x590 [] cpuset_init_smp+0x6b/0x7b [] kernel_init+0xc3/0x182 [] kernel_thread_helper+0x4/0x10 [] ? retint_restore_args+0x13/0x13 [] ? start_kernel+0x400/0x400 [] ? gs_change+0x13/0x13 The divede by zero is caused by the following line, group->cpu_power==0: kernel/sched_fair.c::update_sg_lb_stats() /* Adjust by relative CPU power of the group */ sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; This regression was caused by commit e23bba6044 ("x86-64, NUMA: Unify emulated distance mapping") because it changes cpu -> node mapping in the process of dropping fake_physnodes(). old) all cpus are assinged node 0 now) cpus are assigned round robin (the logic is implemented by numa_init_array()) Note: The change in behavior only happens if the system doesn't have neither ACPI SRAT table nor AMD northbridge NUMA information. Round robin assignment doesn't work because init_numa_sched_groups_power() assumes all logical cpus in the same physical cpu share the same node (then it only accounts for group_first_cpu()), and the simple round robin breaks the above assumption. Thus, this patch implements a reassignment of node-ids if buggy firmware or numa emulation makes wrong cpu node map. Tt enforce all logical cpus in the same physical cpu share the same node. Signed-off-by: KOSAKI Motohiro Acked-by: Tejun Heo Cc: Yinghai Lu Cc: Brian Gerst Cc: Cyrill Gorcunov Cc: Shaohui Zheng Cc: David Rientjes Cc: H. Peter Anvin Link: http://lkml.kernel.org/r/20110415203928.1303.A69D9226@jp.fujitsu.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'arch') diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2871d3c71b..8ed8908cc9f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -312,6 +312,26 @@ void __cpuinit smp_store_cpu_info(int id) identify_secondary_cpu(c); } +static void __cpuinit check_cpu_siblings_on_same_node(int cpu1, int cpu2) +{ + int node1 = early_cpu_to_node(cpu1); + int node2 = early_cpu_to_node(cpu2); + + /* + * Our CPU scheduler assumes all logical cpus in the same physical cpu + * share the same node. But, buggy ACPI or NUMA emulation might assign + * them to different node. Fix it. + */ + if (node1 != node2) { + pr_warning("CPU %d in node %d and CPU %d in node %d are in the same physical CPU. forcing same node %d\n", + cpu1, node1, cpu2, node2, node2); + + numa_remove_cpu(cpu1); + numa_set_node(cpu1, node2); + numa_add_cpu(cpu1); + } +} + static void __cpuinit link_thread_siblings(int cpu1, int cpu2) { cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2)); @@ -320,6 +340,7 @@ static void __cpuinit link_thread_siblings(int cpu1, int cpu2) cpumask_set_cpu(cpu2, cpu_core_mask(cpu1)); cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2)); cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1)); + check_cpu_siblings_on_same_node(cpu1, cpu2); } @@ -361,10 +382,12 @@ void __cpuinit set_cpu_sibling_map(int cpu) per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { cpumask_set_cpu(i, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); + check_cpu_siblings_on_same_node(cpu, i); /* * Does this new cpu bringup a new core? */ -- cgit v1.2.3-18-g5258 From 5bbc097d890409d8eff4e3f1d26f11a9d6b7c07e Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Fri, 15 Apr 2011 14:47:40 +0200 Subject: x86, amd: Disable GartTlbWlkErr when BIOS forgets it This patch disables GartTlbWlk errors on AMD Fam10h CPUs if the BIOS forgets to do is (or is just too old). Letting these errors enabled can cause a sync-flood on the CPU causing a reboot. The AMD BKDG recommends disabling GART TLB Wlk Error completely. This patch is the fix for https://bugzilla.kernel.org/show_bug.cgi?id=33012 on my machine. Signed-off-by: Joerg Roedel Link: http://lkml.kernel.org/r/20110415131152.GJ18463@8bytes.org Tested-by: Alexandre Demers Cc: Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/msr-index.h | 4 ++++ arch/x86/kernel/cpu/amd.c | 19 +++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index fd5a1f365c9..3cce71413d0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -96,11 +96,15 @@ #define MSR_IA32_MC0_ADDR 0x00000402 #define MSR_IA32_MC0_MISC 0x00000403 +#define MSR_AMD64_MC0_MASK 0xc0010044 + #define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) #define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x)) #define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x)) #define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x)) +#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x)) + /* These are consecutive and not in the normal 4er MCE bank block */ #define MSR_IA32_MC0_CTL2 0x00000280 #define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 3ecece0217e..3532d3bf810 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -615,6 +615,25 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* As a rule processors have APIC timer running in deep C states */ if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400)) set_cpu_cap(c, X86_FEATURE_ARAT); + + /* + * Disable GART TLB Walk Errors on Fam10h. We do this here + * because this is always needed when GART is enabled, even in a + * kernel which has no MCE support built in. + */ + if (c->x86 == 0x10) { + /* + * BIOS should disable GartTlbWlk Errors themself. If + * it doesn't do it here as suggested by the BKDG. + * + * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012 + */ + u64 mask; + + rdmsrl(MSR_AMD64_MCx_MASK(4), mask); + mask |= (1 << 10); + wrmsrl(MSR_AMD64_MCx_MASK(4), mask); + } } #ifdef CONFIG_X86_32 -- cgit v1.2.3-18-g5258