From 7eccf7b227b6d3b1745b937ce35efc9c27f9b0e5 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 5 May 2009 12:50:02 -0700 Subject: x86, srat: do not register nodes beyond e820 map The mem= option will truncate the memory map at a specified address so it's not possible to register nodes with memory beyond the e820 upper bound. unparse_node() is only called when then node had memory associated with it, although with the mem= option it is no longer addressable. [ Impact: fix boot hang on certain (large) systems ] Reported-by: "Zhang, Yanmin" Signed-off-by: David Rientjes Acked-by: Jack Steiner LKML-Reference: Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_64.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 33c5fa57e43d..01765955baaf 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -361,6 +361,7 @@ static void __init unparse_node(int node) { int i; node_clear(node, nodes_parsed); + node_clear(node, cpu_nodes_parsed); for (i = 0; i < MAX_LOCAL_APIC; i++) { if (apicid_to_node[i] == node) apicid_to_node[i] = NUMA_NO_NODE; -- cgit v1.2.2 From e0e5ea3268db428d19e1c5fa00e6f583861cbdbd Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Mon, 4 May 2009 09:08:26 +0530 Subject: x86: Fix a typo in a printk message [ Impact: printk message cleanup ] Signed-off-by: Nikanth Karthikesan LKML-Reference: <200905040908.27299.knikanth@suse.de> Signed-off-by: Ingo Molnar --- arch/x86/mm/srat_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index 16ae70fc57e7..29a0e37114f8 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -216,7 +216,7 @@ int __init get_memcfg_from_srat(void) if (num_memory_chunks == 0) { printk(KERN_WARNING - "could not finy any ACPI SRAT memory areas.\n"); + "could not find any ACPI SRAT memory areas.\n"); goto out_fail; } -- cgit v1.2.2 From 61438766514a2d7f191ce1b3cf6812eabbef4ef7 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 6 May 2009 13:02:19 +0100 Subject: x86: fix boot hang in early_reserve_e820() If the first non-reserved (sub-)range doesn't fit the size requested, an endless loop will be entered. If a range returned from find_e820_area_size() turns out insufficient in size, the range must be skipped before calling the function again. [ Impact: fixes boot hang on some platforms ] Signed-off-by: Jan Beulich Signed-off-by: H. Peter Anvin --- arch/x86/kernel/e820.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index ef2c3563357d..006281302925 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1074,12 +1074,13 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) u64 addr; u64 start; - start = startt; - while (size < sizet && (start + 1)) + for (start = startt; ; start += size) { start = find_e820_area_size(start, &size, align); - - if (size < sizet) - return 0; + if (!(start + 1)) + return 0; + if (size >= sizet) + break; + } #ifdef CONFIG_X86_32 if (start >= MAXMEM) -- cgit v1.2.2 From 498343967613183611ac37dccb2846496d954c06 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 6 May 2009 13:06:47 +0100 Subject: x86-64: finish cleanup_highmaps()'s job wrt. _brk_end With the introduction of the .brk section, special care must be taken that no unused page table entries remain if _brk_end and _end are separated by a 2M page boundary. cleanup_highmap() runs very early and hence cannot take care of that, hence potential entries needing to be removed past _brk_end must be cleared once the brk allocator has done its job. [ Impact: avoids undesirable TLB aliases ] Signed-off-by: Jan Beulich Signed-off-by: H. Peter Anvin --- arch/x86/mm/init.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fd3da1dda1c9..ae4f7b5d7104 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include @@ -304,8 +305,23 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, #endif #ifdef CONFIG_X86_64 - if (!after_bootmem) + if (!after_bootmem && !start) { + pud_t *pud; + pmd_t *pmd; + mmu_cr4_features = read_cr4(); + + /* + * _brk_end cannot change anymore, but it and _end may be + * located on different 2M pages. cleanup_highmap(), however, + * can only consider _end when it runs, so destroy any + * mappings beyond _brk_end here. + */ + pud = pud_offset(pgd_offset_k(_brk_end), _brk_end); + pmd = pmd_offset(pud, _brk_end - 1); + while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1)) + pmd_clear(pmd); + } #endif __flush_tlb_all(); -- cgit v1.2.2 From 6407df5ca54a511054200a1eb23f78f723ca1de4 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 8 May 2009 10:51:41 +0800 Subject: x86, kexec: fix crashdump panic with CONFIG_KEXEC_JUMP Tim Starling reported that crashdump will panic with kernel compiled with CONFIG_KEXEC_JUMP due to null pointer deference in machine_kexec_32.c: machine_kexec(), when deferencing kexec_image. Refering to: http://bugzilla.kernel.org/show_bug.cgi?id=13265 This patch fixes the BUG via replacing global variable reference: kexec_image in machine_kexec() with local variable reference: image, which is more appropriate, and will not be null. Same BUG is in machine_kexec_64.c too, so fixed too in the same way. [ Impact: fix crash on kexec ] Reported-by: Tim Starling Signed-off-by: Huang Ying LKML-Reference: <1241751101.6259.85.camel@yhuang-dev.sh.intel.com> Signed-off-by: H. Peter Anvin --- arch/x86/kernel/machine_kexec_32.c | 4 ++-- arch/x86/kernel/machine_kexec_64.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index e7368c1da01d..c1c429d00130 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -194,7 +194,7 @@ void machine_kexec(struct kimage *image) unsigned int preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) save_processor_state(); #endif @@ -253,7 +253,7 @@ void machine_kexec(struct kimage *image) image->preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) restore_processor_state(); #endif diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 89cea4d44679..84c3bf209e98 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -274,7 +274,7 @@ void machine_kexec(struct kimage *image) int save_ftrace_enabled; #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) save_processor_state(); #endif @@ -333,7 +333,7 @@ void machine_kexec(struct kimage *image) image->preserve_context); #ifdef CONFIG_KEXEC_JUMP - if (kexec_image->preserve_context) + if (image->preserve_context) restore_processor_state(); #endif -- cgit v1.2.2 From 33df4db04a79660150e1948e3296eeb451ac121b Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 7 May 2009 11:56:44 -0700 Subject: x86: xen, i386: reserve Xen pagetables The Xen pagetables are no longer implicitly reserved as part of the other i386_start_kernel reservations, so make sure we explicitly reserve them. This prevents them from being released into the general kernel free page pool and reused. [ Impact: fix Xen guest crash ] Also-Bisected-by: Bryan Donlan Signed-off-by: Jeremy Fitzhardinge Cc: Xen-devel Cc: Linus Torvalds LKML-Reference: <4A032EEC.30509@goop.org> Signed-off-by: Ingo Molnar --- arch/x86/xen/mmu.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 9842b1212407..e25a78e1113a 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1794,6 +1794,11 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); + reserve_early(__pa(xen_start_info->pt_base), + __pa(xen_start_info->pt_base + + xen_start_info->nr_pt_frames * PAGE_SIZE), + "XEN PAGETABLES"); + return swapper_pg_dir; } #endif /* CONFIG_X86_64 */ -- cgit v1.2.2 From e5299926d7459d9fa7c7f856983147817aedb10e Mon Sep 17 00:00:00 2001 From: Hidetoshi Seto Date: Fri, 8 May 2009 17:28:40 +0900 Subject: x86: MCE: make cmci_discover_lock irq-safe Lockdep reports the warning below when Li tries to offline one cpu: [ 110.835487] ================================= [ 110.835616] [ INFO: inconsistent lock state ] [ 110.835688] 2.6.30-rc4-00336-g8c9ed89 #52 [ 110.835757] --------------------------------- [ 110.835828] inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. [ 110.835908] swapper/0 [HC1[1]:SC0[0]:HE0:SE1] takes: [ 110.835982] (cmci_discover_lock){?.+...}, at: [] cmci_clear+0x30/0x9b cmci_clear() can be called via smp_call_function_single(). It is better to disable interrupt while holding cmci_discover_lock, to turn it into an irq-safe lock - we can deadlock otherwise. [ Impact: fix possible deadlock in the MCE code ] Reported-by: Shaohua Li Signed-off-by: Hidetoshi Seto Cc: Andi Kleen Cc: Andrew Morton LKML-Reference: <4A03ED38.8000700@jp.fujitsu.com> Signed-off-by: Ingo Molnar Reported-by: Shaohua Li --- arch/x86/kernel/cpu/mcheck/mce_intel_64.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index d6b72df89d69..cef3ee30744b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -151,10 +151,11 @@ static void print_update(char *type, int *hdr, int num) static void cmci_discover(int banks, int boot) { unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned); + unsigned long flags; int hdr = 0; int i; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; @@ -184,7 +185,7 @@ static void cmci_discover(int banks, int boot) WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks))); } } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); if (hdr) printk(KERN_CONT "\n"); } @@ -211,13 +212,14 @@ void cmci_recheck(void) */ void cmci_clear(void) { + unsigned long flags; int i; int banks; u64 val; if (!cmci_supported(&banks)) return; - spin_lock(&cmci_discover_lock); + spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { if (!test_bit(i, __get_cpu_var(mce_banks_owned))) continue; @@ -227,7 +229,7 @@ void cmci_clear(void) wrmsrl(MSR_IA32_MC0_CTL2 + i, val); __clear_bit(i, __get_cpu_var(mce_banks_owned)); } - spin_unlock(&cmci_discover_lock); + spin_unlock_irqrestore(&cmci_discover_lock, flags); } /* -- cgit v1.2.2