From 155dd720d06a219ddf5a56b473cb3325441fc879 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Fri, 13 Mar 2009 14:49:53 +1030 Subject: cpumask: convert struct cpuinfo_x86's llc_shared_map to cpumask_var_t Impact: reduce kernel memory usage when CONFIG_CPUMASK_OFFSTACK=y Signed-off-by: Rusty Russell --- arch/x86/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 76139506c3e4..d794d9483c56 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -94,7 +94,7 @@ struct cpuinfo_x86 { unsigned long loops_per_jiffy; #ifdef CONFIG_SMP /* cpus sharing the last level cache: */ - cpumask_t llc_shared_map; + cpumask_var_t llc_shared_map; #endif /* cpuid returned max cores value: */ u16 x86_max_cores; -- cgit v1.2.3 From 30e1e6d1af2b67558bccf322af2b3e0676b209ae Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Tue, 17 Mar 2009 14:50:34 +1030 Subject: cpumask: fix CONFIG_CPUMASK_OFFSTACK=y cpu hotunplug crash Impact: Fix cpu offline when CONFIG_MAXSMP=y Changeset bc9b83dd1f66402b870301c3c7117b9c1484abb4 "cpumask: convert c1e_mask in arch/x86/kernel/process.c to cpumask_var_t" contained a bug: c1e_mask is manipulated even if C1E isn't detected (and hence not allocated). This is simply fixed by checking for NULL (which gcc optimizes out anyway of CONFIG_CPUMASK_OFFSTACK=n, since it knows ce1_mask can never be NULL). In addition, fix a leak where select_idle_routine re-allocates (and re-clears) c1e_mask on every cpu init. Reported-by: Ingo Molnar Signed-off-by: Rusty Russell Cc: Mike Travis LKML-Reference: <200903171450.34549.rusty@rustcorp.com.au> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d794d9483c56..9874dd98a29f 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -733,6 +733,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); extern void select_idle_routine(const struct cpuinfo_x86 *c); +extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; -- cgit v1.2.3 From a30469e7921a6dd2067e9e836d7787cfa0105627 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Fri, 10 Apr 2009 15:21:24 -0700 Subject: x86: add linux kernel support for YMM state Impact: save/restore Intel-AVX state properly between tasks Intel Advanced Vector Extensions (AVX) introduce 256-bit vector processing capability. More about AVX at http://software.intel.com/sites/avx Add OS support for YMM state management using xsave/xrstor infrastructure to support AVX. Signed-off-by: Suresh Siddha LKML-Reference: <1239402084.27006.8057.camel@localhost.localdomain> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 34c52370f2fe..fcf4d92e7e04 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -352,6 +352,11 @@ struct i387_soft_struct { u32 entry_eip; }; +struct ymmh_struct { + /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ + u32 ymmh_space[64]; +}; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -361,6 +366,7 @@ struct xsave_hdr_struct { struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; + struct ymmh_struct ymmh; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); -- cgit v1.2.3 From 9b8de7479d0dbab1ed98b5b015d44232c9d3d08e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 21 Apr 2009 23:00:24 +0100 Subject: FRV: Fix the section attribute on UP DECLARE_PER_CPU() In non-SMP mode, the variable section attribute specified by DECLARE_PER_CPU() does not agree with that specified by DEFINE_PER_CPU(). This means that architectures that have a small data section references relative to a base register may throw up linkage errors due to too great a displacement between where the base register points and the per-CPU variable. On FRV, the .h declaration says that the variable is in the .sdata section, but the .c definition says it's actually in the .data section. The linker throws up the following errors: kernel/built-in.o: In function `release_task': kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o kernel/exit.c:78: relocation truncated to fit: R_FRV_GPREL12 against symbol `per_cpu__process_counts' defined in .data section in kernel/built-in.o To fix this, DECLARE_PER_CPU() should simply apply the same section attribute as does DEFINE_PER_CPU(). However, this is made slightly more complex by virtue of the fact that there are several variants on DEFINE, so these need to be matched by variants on DECLARE. Signed-off-by: David Howells Signed-off-by: Linus Torvalds --- arch/x86/include/asm/processor.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/include/asm/processor.h') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index fcf4d92e7e04..c2cceae709c8 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -138,7 +138,7 @@ extern struct tss_struct doublefault_tss; extern __u32 cleared_cpu_caps[NCAPINTS]; #ifdef CONFIG_SMP -DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info); +DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) #define current_cpu_data __get_cpu_var(cpu_info) #else @@ -270,7 +270,7 @@ struct tss_struct { } ____cacheline_aligned; -DECLARE_PER_CPU(struct tss_struct, init_tss); +DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss); /* * Save the original ist values for checking stack pointers during debugging @@ -393,7 +393,7 @@ union irq_stack_union { }; }; -DECLARE_PER_CPU(union irq_stack_union, irq_stack_union); +DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union); DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); -- cgit v1.2.3