From 62111195800d80c66cdc69063ea3145878c99fbf Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 7 Dec 2006 02:14:02 +0100 Subject: [PATCH] i386: Initialize the per-CPU data area When a CPU is brought up, a PDA and GDT are allocated for it. The GDT's __KERNEL_PDA entry is pointed to the allocated PDA memory, so that all references using this segment descriptor will refer to the PDA. This patch rearranges CPU initialization a bit, so that the GDT/PDA are set up as early as possible in cpu_init(). Also for secondary CPUs, GDT+PDA are preallocated and initialized so all the secondary CPU needs to do is set up the ldt and load %gs. This will be important once smp_processor_id() and current use the PDA. In all cases, the PDA is set up in head.S, before a CPU starts running C code, so the PDA is always available. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Andi Kleen Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden Cc: Jan Beulich Cc: Andi Kleen Cc: James Bottomley Cc: Matt Tolentino Signed-off-by: Andrew Morton --- include/asm-i386/processor.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index e0ddca94d50..a9f2041c7c8 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -727,4 +727,7 @@ extern unsigned long boot_option_idle_override; extern void enable_sep_cpu(void); extern int sysenter_setup(void); +extern int init_gdt(int cpu, struct task_struct *idle); +extern void secondary_cpu_init(void); + #endif /* __ASM_I386_PROCESSOR_H */ -- cgit From f95d47caae5302a63d92be9a0292abc90e2a14e1 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 7 Dec 2006 02:14:02 +0100 Subject: [PATCH] i386: Use %gs as the PDA base-segment in the kernel This patch is the meat of the PDA change. This patch makes several related changes: 1: Most significantly, %gs is now used in the kernel. This means that on entry, the old value of %gs is saved away, and it is reloaded with __KERNEL_PDA. 2: entry.S constructs the stack in the shape of struct pt_regs, and this is passed around the kernel so that the process's saved register state can be accessed. Unfortunately struct pt_regs doesn't currently have space for %gs (or %fs). This patch extends pt_regs to add space for gs (no space is allocated for %fs, since it won't be used, and it would just complicate the code in entry.S to work around the space). 3: Because %gs is now saved on the stack like %ds, %es and the integer registers, there are a number of places where it no longer needs to be handled specially; namely context switch, and saving/restoring the register state in a signal context. 4: And since kernel threads run in kernel space and call normal kernel code, they need to be created with their %gs == __KERNEL_PDA. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Andi Kleen Cc: Chuck Ebbert <76306.1226@compuserve.com> Cc: Zachary Amsden Cc: Jan Beulich Cc: Andi Kleen Signed-off-by: Andrew Morton --- include/asm-i386/processor.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index a9f2041c7c8..f73cf836e64 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -473,6 +473,7 @@ struct thread_struct { .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ + .gs = __KERNEL_PDA, \ } /* @@ -500,7 +501,8 @@ static inline void load_esp0(struct tss_struct *tss, struct thread_struct *threa } #define start_thread(regs, new_eip, new_esp) do { \ - __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \ + __asm__("movl %0,%%fs": :"r" (0)); \ + regs->xgs = 0; \ set_fs(USER_DS); \ regs->xds = __USER_DS; \ regs->xes = __USER_DS; \ -- cgit From 770d132f03ac15b12919f1bac481f4beda13e094 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 7 Dec 2006 02:14:05 +0100 Subject: [PATCH] i386: Retrieve CLFLUSH size from CPUID Also report it in /proc/cpuinfo similar to x86-64. Needed for followon patch Signed-off-by: Andi Kleen --- include/asm-i386/processor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index f73cf836e64..98fa73b7176 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -72,6 +72,7 @@ struct cpuinfo_x86 { #endif unsigned char x86_max_cores; /* cpuid returned max cores value */ unsigned char apicid; + unsigned short x86_clflush_size; #ifdef CONFIG_SMP unsigned char booted_cores; /* number of cores as seen by OS */ __u8 phys_proc_id; /* Physical processor id. */ -- cgit From d3561b7fa0fb0fc583bab0eeda32bec9e4c4056d Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 7 Dec 2006 02:14:07 +0100 Subject: [PATCH] paravirt: header and stubs for paravirtualisation Create a paravirt.h header for all the critical operations which need to be replaced with hypervisor calls, and include that instead of defining native operations, when CONFIG_PARAVIRT. This patch does the dumbest possible replacement of paravirtualized instructions: calls through a "paravirt_ops" structure. Currently these are function implementations of native hardware: hypervisors will override the ops structure with their own variants. All the pv-ops functions are declared "fastcall" so that a specific register-based ABI is used, to make inlining assember easier. And: +From: Andy Whitcroft The paravirt ops introduce a 'weak' attribute onto memory_setup(). Code ordering leads to the following warnings on x86: arch/i386/kernel/setup.c:651: warning: weak declaration of `memory_setup' after first use results in unspecified behavior Move memory_setup() to avoid this. Signed-off-by: Rusty Russell Signed-off-by: Chris Wright Signed-off-by: Andi Kleen Cc: Jeremy Fitzhardinge Cc: Zachary Amsden Signed-off-by: Andrew Morton Signed-off-by: Andy Whitcroft --- include/asm-i386/processor.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 98fa73b7176..6c2c4457be0 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -144,8 +144,8 @@ static inline void detect_ht(struct cpuinfo_x86 *c) {} #define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ #define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ -static inline void __cpuid(unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx) +static inline fastcall void native_cpuid(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) { /* ecx is often an input as well as an output. */ __asm__("cpuid" @@ -491,6 +491,12 @@ struct thread_struct { .io_bitmap = { [ 0 ... IO_BITMAP_LONGS] = ~0 }, \ } +#ifdef CONFIG_PARAVIRT +#include +#else +#define paravirt_enabled() 0 +#define __cpuid native_cpuid + static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) { tss->esp0 = thread->esp0; @@ -524,10 +530,13 @@ static inline void load_esp0(struct tss_struct *tss, struct thread_struct *threa : /* no output */ \ :"r" (value)) +#define set_iopl_mask native_set_iopl_mask +#endif /* CONFIG_PARAVIRT */ + /* * Set IOPL bits in EFLAGS from given mask */ -static inline void set_iopl_mask(unsigned mask) +static fastcall inline void native_set_iopl_mask(unsigned mask) { unsigned int reg; __asm__ __volatile__ ("pushfl;" -- cgit From 139ec7c416248b9ea227d21839235344edfee1e0 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 7 Dec 2006 02:14:08 +0100 Subject: [PATCH] paravirt: Patch inline replacements for paravirt intercepts It turns out that the most called ops, by several orders of magnitude, are the interrupt manipulation ops. These are obvious candidates for patching, so mark them up and create infrastructure for it. The method used is that the ops structure has a patch function, which is called for each place which needs to be patched: this returns a number of instructions (the rest are NOP-padded). Usually we can spare a register (%eax) for the binary patched code to use, but in a couple of critical places in entry.S we can't: we make the clobbers explicit at the call site, and manually clobber the allowed registers in debug mode as an extra check. And: Don't abuse CONFIG_DEBUG_KERNEL, add CONFIG_DEBUG_PARAVIRT. And: AK: Fix warnings in x86-64 alternative.c build And: AK: Fix compilation with defconfig And: ^From: Andrew Morton Some binutlises still like to emit references to __stop_parainstructions and __start_parainstructions. And: AK: Fix warnings about unused variables when PARAVIRT is disabled. Signed-off-by: Rusty Russell Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Chris Wright Signed-off-by: Zachary Amsden Signed-off-by: Andi Kleen Signed-off-by: Andrew Morton --- include/asm-i386/processor.h | 198 +++++++++++++++++++++---------------------- 1 file changed, 99 insertions(+), 99 deletions(-) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 6c2c4457be0..5f0418d0078 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -156,59 +156,6 @@ static inline fastcall void native_cpuid(unsigned int *eax, unsigned int *ebx, : "0" (*eax), "2" (*ecx)); } -/* - * Generic CPUID function - * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx - * resulting in stale register contents being returned. - */ -static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) -{ - *eax = op; - *ecx = 0; - __cpuid(eax, ebx, ecx, edx); -} - -/* Some CPUID calls want 'count' to be placed in ecx */ -static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx, - int *edx) -{ - *eax = op; - *ecx = count; - __cpuid(eax, ebx, ecx, edx); -} - -/* - * CPUID functions returning a single datum - */ -static inline unsigned int cpuid_eax(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - return eax; -} -static inline unsigned int cpuid_ebx(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - return ebx; -} -static inline unsigned int cpuid_ecx(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - return ecx; -} -static inline unsigned int cpuid_edx(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - return edx; -} - #define load_cr3(pgdir) write_cr3(__pa(pgdir)) /* @@ -491,22 +438,6 @@ struct thread_struct { .io_bitmap = { [ 0 ... IO_BITMAP_LONGS] = ~0 }, \ } -#ifdef CONFIG_PARAVIRT -#include -#else -#define paravirt_enabled() 0 -#define __cpuid native_cpuid - -static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) -{ - tss->esp0 = thread->esp0; - /* This can only happen when SEP is enabled, no need to test "SEP"arately */ - if (unlikely(tss->ss1 != thread->sysenter_cs)) { - tss->ss1 = thread->sysenter_cs; - wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); - } -} - #define start_thread(regs, new_eip, new_esp) do { \ __asm__("movl %0,%%fs": :"r" (0)); \ regs->xgs = 0; \ @@ -519,36 +450,6 @@ static inline void load_esp0(struct tss_struct *tss, struct thread_struct *threa regs->esp = new_esp; \ } while (0) -/* - * These special macros can be used to get or set a debugging register - */ -#define get_debugreg(var, register) \ - __asm__("movl %%db" #register ", %0" \ - :"=r" (var)) -#define set_debugreg(value, register) \ - __asm__("movl %0,%%db" #register \ - : /* no output */ \ - :"r" (value)) - -#define set_iopl_mask native_set_iopl_mask -#endif /* CONFIG_PARAVIRT */ - -/* - * Set IOPL bits in EFLAGS from given mask - */ -static fastcall inline void native_set_iopl_mask(unsigned mask) -{ - unsigned int reg; - __asm__ __volatile__ ("pushfl;" - "popl %0;" - "andl %1, %0;" - "orl %2, %0;" - "pushl %0;" - "popfl" - : "=&r" (reg) - : "i" (~X86_EFLAGS_IOPL), "r" (mask)); -} - /* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; @@ -640,6 +541,105 @@ static inline void rep_nop(void) #define cpu_relax() rep_nop() +#ifdef CONFIG_PARAVIRT +#include +#else +#define paravirt_enabled() 0 +#define __cpuid native_cpuid + +static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) +{ + tss->esp0 = thread->esp0; + /* This can only happen when SEP is enabled, no need to test "SEP"arately */ + if (unlikely(tss->ss1 != thread->sysenter_cs)) { + tss->ss1 = thread->sysenter_cs; + wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); + } +} + +/* + * These special macros can be used to get or set a debugging register + */ +#define get_debugreg(var, register) \ + __asm__("movl %%db" #register ", %0" \ + :"=r" (var)) +#define set_debugreg(value, register) \ + __asm__("movl %0,%%db" #register \ + : /* no output */ \ + :"r" (value)) + +#define set_iopl_mask native_set_iopl_mask +#endif /* CONFIG_PARAVIRT */ + +/* + * Set IOPL bits in EFLAGS from given mask + */ +static fastcall inline void native_set_iopl_mask(unsigned mask) +{ + unsigned int reg; + __asm__ __volatile__ ("pushfl;" + "popl %0;" + "andl %1, %0;" + "orl %2, %0;" + "pushl %0;" + "popfl" + : "=&r" (reg) + : "i" (~X86_EFLAGS_IOPL), "r" (mask)); +} + +/* + * Generic CPUID function + * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx + * resulting in stale register contents being returned. + */ +static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) +{ + *eax = op; + *ecx = 0; + __cpuid(eax, ebx, ecx, edx); +} + +/* Some CPUID calls want 'count' to be placed in ecx */ +static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx, + int *edx) +{ + *eax = op; + *ecx = count; + __cpuid(eax, ebx, ecx, edx); +} + +/* + * CPUID functions returning a single datum + */ +static inline unsigned int cpuid_eax(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + return eax; +} +static inline unsigned int cpuid_ebx(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + return ebx; +} +static inline unsigned int cpuid_ecx(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + return ecx; +} +static inline unsigned int cpuid_edx(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + return edx; +} + /* generic versions from gas */ #define GENERIC_NOP1 ".byte 0x90\n" #define GENERIC_NOP2 ".byte 0x89,0xf6\n" -- cgit From d7cd56111f30259e1b532a12e06f59f8e0a20355 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 7 Dec 2006 02:14:08 +0100 Subject: [PATCH] i386: cpu_detect extraction Both lhype and Xen want to call the core of the x86 cpu detect code before calling start_kernel. (extracted from larger patch) AK: folded in start_kernel header patch Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Rusty Russell Signed-off-by: Andi Kleen Cc: Jeremy Fitzhardinge Cc: Andi Kleen Signed-off-by: Andrew Morton --- include/asm-i386/processor.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/asm-i386/processor.h') diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index 5f0418d0078..a52d6544042 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -20,6 +20,7 @@ #include #include #include +#include /* flag for disabling the tsc */ extern int tsc_disable; @@ -112,6 +113,8 @@ extern struct cpuinfo_x86 cpu_data[]; extern int cpu_llc_id[NR_CPUS]; extern char ignore_fpu_irq; +void __init cpu_detect(struct cpuinfo_x86 *c); + extern void identify_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); -- cgit