From 3ef12c3c97603bad405d30c989718cc9405e2759 Mon Sep 17 00:00:00 2001 From: Cliff Wickman Date: Fri, 14 Aug 2009 13:56:37 -0500 Subject: x86: Fix UV BAU destination subnode id The SGI UV Broadcast Assist Unit is used to send TLB shootdown messages to remote nodes of the system. The header of the message must contain the subnode id of the block in the receiving hub that handles such messages. It should always be 0x10, the id of the "LB" block. It had previously been documented as a "must be zero" field. Signed-off-by: Cliff Wickman Acked-by: Jack Steiner LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/include/asm/uv/uv_bau.h | 2 +- arch/x86/kernel/tlb_uv.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index bddd44f..80e2984 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -133,7 +133,7 @@ struct bau_msg_payload { * see table 4.2.3.0.1 in broacast_assist spec. */ struct bau_msg_header { - unsigned int dest_subnodeid:6; /* must be zero */ + unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */ /* bits 5:0 */ unsigned int base_dest_nodeid:15; /* nasid>>1 (pnode) of */ /* bits 20:6 */ /* first bit in node_map */ diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 8ccabb8..77b9689 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -744,6 +744,7 @@ uv_activation_descriptor_init(int node, int pnode) * note that base_dest_nodeid is actually a nasid. */ ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1; + ad2->header.dest_subnodeid = 0x10; /* the LB */ ad2->header.command = UV_NET_ENDPOINT_INTD; ad2->header.int_both = 1; /* -- cgit v1.1 From 4e5c25d405e18a2f279ca2bfc855508ec3a0186b Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sun, 16 Aug 2009 15:54:37 +0100 Subject: x86, mce: therm_throt: Don't log redundant normality 0d01f31439c1e4d602bf9fdc924ab66f407f5e38 "x86, mce: therm_throt - change when we print messages" removed redundant announcements of "Temperature/speed normal". They're not worth logging and remove their accompanying "Machine check events logged" messages as well from the console. Signed-off-by: Hugh Dickins Cc: Hidetoshi Seto Cc: Andi Kleen Cc: Dmitry Torokhov LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/therm_throt.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 8bc64cf..5957a93 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -116,11 +116,14 @@ static int therm_throt_process(int curr) cpu, __get_cpu_var(thermal_throttle_count)); add_taint(TAINT_MACHINE_CHECK); - } else if (was_throttled) { + return 1; + } + if (was_throttled) { printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu); + return 1; } - return 1; + return 0; } #ifdef CONFIG_SYSFS -- cgit v1.1 From 52459ab91363343af8ae252766e9da762344a2e7 Mon Sep 17 00:00:00 2001 From: Leonardo Potenza Date: Sun, 16 Aug 2009 18:55:48 +0200 Subject: x86: Annotate section mismatch warnings in kernel/apic/x2apic_uv_x.c The function uv_acpi_madt_oem_check() has been marked __init, the struct apic_x2apic_uv_x has been marked __refdata. The aim is to address the following section mismatch messages: WARNING: arch/x86/kernel/apic/built-in.o(.data+0x1368): Section mismatch in reference from the variable apic_x2apic_uv_x to the function .cpuinit.text:uv_wakeup_secondary() The variable apic_x2apic_uv_x references the function __cpuinit uv_wakeup_secondary() If the reference is valid then annotate the variable with __init* or __refdata (see linux/init.h) or name the variable: *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, WARNING: arch/x86/kernel/built-in.o(.data+0x68e8): Section mismatch in reference from the variable apic_x2apic_uv_x to the function .cpuinit.text:uv_wakeup_secondary() The variable apic_x2apic_uv_x references the function __cpuinit uv_wakeup_secondary() If the reference is valid then annotate the variable with __init* or __refdata (see linux/init.h) or name the variable: *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, WARNING: arch/x86/built-in.o(.text+0x7b36f): Section mismatch in reference from the function uv_acpi_madt_oem_check() to the function .init.text:early_ioremap() The function uv_acpi_madt_oem_check() references the function __init early_ioremap(). This is often because uv_acpi_madt_oem_check lacks a __init annotation or the annotation of early_ioremap is wrong. WARNING: arch/x86/built-in.o(.text+0x7b38d): Section mismatch in reference from the function uv_acpi_madt_oem_check() to the function .init.text:early_iounmap() The function uv_acpi_madt_oem_check() references the function __init early_iounmap(). This is often because uv_acpi_madt_oem_check lacks a __init annotation or the annotation of early_iounmap is wrong. WARNING: arch/x86/built-in.o(.data+0x8668): Section mismatch in reference from the variable apic_x2apic_uv_x to the function .cpuinit.text:uv_wakeup_secondary() The variable apic_x2apic_uv_x references the function __cpuinit uv_wakeup_secondary() If the reference is valid then annotate the variable with __init* or __refdata (see linux/init.h) or name the variable: *driver, *_template, *_timer, *_sht, *_ops, *_probe, *_probe_one, *_console, Signed-off-by: Leonardo Potenza LKML-Reference: <200908161855.48302.lpotenza@inwind.it> Signed-off-by: Ingo Molnar --- arch/x86/kernel/apic/x2apic_uv_x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 832e908..6011593 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -46,7 +46,7 @@ static int early_get_nodeid(void) return node_id.s.node_id; } -static int uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { if (!strcmp(oem_id, "SGI")) { if (!strcmp(oem_table_id, "UVL")) @@ -253,7 +253,7 @@ static void uv_send_IPI_self(int vector) apic_write(APIC_SELF_IPI, vector); } -struct apic apic_x2apic_uv_x = { +struct apic __refdata apic_x2apic_uv_x = { .name = "UV large system", .probe = NULL, -- cgit v1.1 From c7f6fa44115d401e89db730f357629d39f8e4ba6 Mon Sep 17 00:00:00 2001 From: Bartlomiej Zolnierkiewicz Date: Tue, 28 Jul 2009 23:52:54 +0200 Subject: x86, mce: don't log boot MCEs on Pentium M (model == 13) CPUs On my legacy Pentium M laptop (Acer Extensa 2900) I get bogus MCE on a cold boot with CONFIG_X86_NEW_MCE enabled, i.e. (after decoding it with mcelog): MCE 0 HARDWARE ERROR. This is *NOT* a software problem! Please contact your hardware vendor CPU 0 BANK 1 MCG status: MCi status: Error overflow Uncorrected error Error enabled Processor context corrupt MCA: Data CACHE Level-1 UNKNOWN Error STATUS f200000000000195 MCGSTATUS 0 [ The other STATUS values observed: f2000000000001b5 (... UNKNOWN error) and f200000000000115 (... READ Error). To verify that this is not a CONFIG_X86_NEW_MCE bug I also modified the CONFIG_X86_OLD_MCE code (which doesn't log any MCEs) to dump content of STATUS MSR before it is cleared during initialization. ] Since the bogus MCE results in a kernel taint (which in turn disables lockdep support) don't log boot MCEs on Pentium M (model == 13) CPUs by default ("mce=bootlog" boot parameter can be be used to get the old behavior). Signed-off-by: Bartlomiej Zolnierkiewicz Reviewed-by: Andi Kleen Signed-off-by: H. Peter Anvin Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 1cfb623..a0c2910 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1273,6 +1273,10 @@ static void mce_cpu_quirks(struct cpuinfo_x86 *c) if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && monarch_timeout < 0) monarch_timeout = USEC_PER_SEC; + + /* There are also broken BIOSes on some Pentium M systems. */ + if (c->x86 == 6 && c->x86_model == 13 && mce_bootlog < 0) + mce_bootlog = 0; } if (monarch_timeout < 0) monarch_timeout = 0; -- cgit v1.1 From e412cd257e0d51e0ecbb89f50953835b5a0681b2 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 17 Aug 2009 10:19:00 +0200 Subject: x86, mce: Don't initialize MCEs on unknown CPUs An older test-box started hanging at the following point during bootup: [ 0.022996] Mount-cache hash table entries: 512 [ 0.024996] Initializing cgroup subsys debug [ 0.025996] Initializing cgroup subsys cpuacct [ 0.026995] Initializing cgroup subsys devices [ 0.027995] Initializing cgroup subsys freezer [ 0.028995] mce: CPU supports 5 MCE banks I've bisected it down to commit 4efc0670 ("x86, mce: use 64bit machine check code on 32bit"), which utilizes the MCE code on 32-bit systems too. The problem is caused by this detail in my config: # CONFIG_CPU_SUP_INTEL is not set This disables the quirks in mce_cpu_quirks() but still enables MCE support - which then hangs due to the missing quirk workaround needed on this CPU: if (c->x86 == 6 && c->x86_model < 0x1A && banks > 0) mce_banks[0].init = 0; The safe solution is to not initialize MCEs if we dont know on what CPU we are running (or if that CPU's support code got disabled in the config). Also be a bit more defensive on 32-bit systems: dont do a boot-time dump of pending MCEs not just on the specific system that we found a problem with (Pentium-M), but earlier ones as well. Now this problem is probably not common and disabling CPU support is rare - but still being more defensive in something we turned on for a wide range of CPUs is prudent. Cc: Hidetoshi Seto LKML-Reference: Message-ID: <4A88E3E4.40506@jp.fujitsu.com> Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/mcheck/mce.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index a0c2910..0121304 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1226,8 +1226,13 @@ static void mce_init(void) } /* Add per CPU specific workarounds here */ -static void mce_cpu_quirks(struct cpuinfo_x86 *c) +static int mce_cpu_quirks(struct cpuinfo_x86 *c) { + if (c->x86_vendor == X86_VENDOR_UNKNOWN) { + pr_info("MCE: unknown CPU type - not enabling MCE support.\n"); + return -EOPNOTSUPP; + } + /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD) { if (c->x86 == 15 && banks > 4) { @@ -1274,14 +1279,19 @@ static void mce_cpu_quirks(struct cpuinfo_x86 *c) monarch_timeout < 0) monarch_timeout = USEC_PER_SEC; - /* There are also broken BIOSes on some Pentium M systems. */ - if (c->x86 == 6 && c->x86_model == 13 && mce_bootlog < 0) + /* + * There are also broken BIOSes on some Pentium M and + * earlier systems: + */ + if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0) mce_bootlog = 0; } if (monarch_timeout < 0) monarch_timeout = 0; if (mce_bootlog != 0) mce_panic_timeout = 30; + + return 0; } static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c) @@ -1342,11 +1352,10 @@ void __cpuinit mcheck_init(struct cpuinfo_x86 *c) if (!mce_available(c)) return; - if (mce_cap_init() < 0) { + if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) { mce_disabled = 1; return; } - mce_cpu_quirks(c); machine_check_vector = do_machine_check; -- cgit v1.1