From 93fa7636dfdc059b25df148f230c0991096afdef Mon Sep 17 00:00:00 2001 From: Markus Metzger Date: Tue, 8 Apr 2008 11:01:58 +0200 Subject: x86, ptrace: PEBS support Polish the ds.h interface and add support for PEBS. Ds.c is meant to be the resource allocator for per-thread and per-cpu BTS and PEBS recording. It is used by ptrace/utrace to provide execution tracing of debugged tasks. It will be used by profilers (e.g. perfmon2). It may be used by kernel debuggers to provide a kernel execution trace. Changes in detail: - guard DS and ptrace by CONFIG macros - separate DS and BTS more clearly - simplify field accesses - add functions to manage PEBS buffers - add simple protection/allocation mechanism - added support for Atom Opens: - buffer overflow handling Currently, only circular buffers are supported. This is all we need for debugging. Profilers would want an overflow notification. This is planned to be added when perfmon2 is made to use the ds.h interface. - utrace intermediate layer Signed-off-by: Markus Metzger Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/process_64.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) (limited to 'arch/x86/kernel/process_64.c') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e2319f39988..ad213494a22 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -267,6 +267,14 @@ void exit_thread(void) t->io_bitmap_max = 0; put_cpu(); } +#ifdef CONFIG_X86_DS + /* Free any DS contexts that have not been properly released. */ + if (unlikely(t->ds_ctx)) { + /* we clear debugctl to make sure DS is not used. */ + update_debugctlmsr(0); + ds_free(t->ds_ctx); + } +#endif /* CONFIG_X86_DS */ } void flush_thread(void) @@ -492,18 +500,27 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, { struct thread_struct *prev, *next; unsigned long debugctl; + unsigned long ds_prev = 0, ds_next = 0; prev = &prev_p->thread, next = &next_p->thread; debugctl = prev->debugctlmsr; - if (next->ds_area_msr != prev->ds_area_msr) { + +#ifdef CONFIG_X86_DS + if (prev->ds_ctx) + ds_prev = (unsigned long)prev->ds_ctx->ds; + if (next->ds_ctx) + ds_next = (unsigned long)next->ds_ctx->ds; + + if (ds_next != ds_prev) { /* we clear debugctl to make sure DS * is not in use when we change it */ debugctl = 0; update_debugctlmsr(0); - wrmsrl(MSR_IA32_DS_AREA, next->ds_area_msr); + wrmsrl(MSR_IA32_DS_AREA, ds_next); } +#endif /* CONFIG_X86_DS */ if (next->debugctlmsr != debugctl) update_debugctlmsr(next->debugctlmsr); @@ -541,13 +558,13 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } -#ifdef X86_BTS +#ifdef CONFIG_X86_PTRACE_BTS if (test_tsk_thread_flag(prev_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(prev_p, BTS_TASK_DEPARTS); if (test_tsk_thread_flag(next_p, TIF_BTS_TRACE_TS)) ptrace_bts_take_timestamp(next_p, BTS_TASK_ARRIVES); -#endif +#endif /* CONFIG_X86_PTRACE_BTS */ } /* -- cgit v1.2.3 From 34b2cd5b688b012975fcfc3b3970fc3508fa82c4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 17 May 2008 08:30:07 +0200 Subject: x86: PEBS cleanup Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_64.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) (limited to 'arch/x86/kernel/process_64.c') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ad213494a22..4a93c98a60a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -500,7 +500,6 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, { struct thread_struct *prev, *next; unsigned long debugctl; - unsigned long ds_prev = 0, ds_next = 0; prev = &prev_p->thread, next = &next_p->thread; @@ -508,17 +507,23 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, debugctl = prev->debugctlmsr; #ifdef CONFIG_X86_DS - if (prev->ds_ctx) - ds_prev = (unsigned long)prev->ds_ctx->ds; - if (next->ds_ctx) - ds_next = (unsigned long)next->ds_ctx->ds; - - if (ds_next != ds_prev) { - /* we clear debugctl to make sure DS - * is not in use when we change it */ - debugctl = 0; - update_debugctlmsr(0); - wrmsrl(MSR_IA32_DS_AREA, ds_next); + { + unsigned long ds_prev = 0, ds_next = 0; + + if (prev->ds_ctx) + ds_prev = (unsigned long)prev->ds_ctx->ds; + if (next->ds_ctx) + ds_next = (unsigned long)next->ds_ctx->ds; + + if (ds_next != ds_prev) { + /* + * We clear debugctl to make sure DS + * is not in use when we change it: + */ + debugctl = 0; + update_debugctlmsr(0); + wrmsrl(MSR_IA32_DS_AREA, ds_next); + } } #endif /* CONFIG_X86_DS */ -- cgit v1.2.3 From bbc1f698a508927d21324b57500e863f9bd562b9 Mon Sep 17 00:00:00 2001 From: Jaswinder Singh Date: Mon, 21 Jul 2008 21:34:13 +0530 Subject: x86: Introducing asm/syscalls.h Declaring arch-dependent syscalls for x86 architecture Signed-off-by: Jaswinder Singh --- arch/x86/kernel/process_64.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel/process_64.c') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e8a8e1b9981..c78090dd0c5 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -51,6 +51,7 @@ #include #include #include +#include asmlinkage extern void ret_from_fork(void); -- cgit v1.2.3 From 7de08b4e1ed8d80e6086f71b7e99fc4b397aae39 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Tue, 29 Jul 2008 02:48:51 -0300 Subject: x86: coding styles fixes to arch/x86/kernel/process_64.c Fix about 50 errors and many warnings without change process_64.o arch/x86/kernel/process_64.o: text data bss dec hex filename 5236 8 24 5268 1494 process_64.o.after 5236 8 24 5268 1494 process_64.o.before md5: 9c35e9debdea4e471288c6e8ca267a75 process_64.o.after 9c35e9debdea4e471288c6e8ca267a75 process_64.o.before Signed-off-by: Gustavo F. Padovan Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_64.c | 101 +++++++++++++++++++++---------------------- 1 file changed, 50 insertions(+), 51 deletions(-) (limited to 'arch/x86/kernel/process_64.c') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3fb62a7d9a1..4da8514dd25 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -37,11 +37,11 @@ #include #include #include +#include +#include -#include #include #include -#include #include #include #include @@ -88,7 +88,7 @@ void exit_idle(void) #ifdef CONFIG_HOTPLUG_CPU DECLARE_PER_CPU(int, cpu_state); -#include +#include /* We halt the CPU with physical CPU hotplug */ static inline void play_dead(void) { @@ -152,7 +152,7 @@ void cpu_idle(void) } /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs * regs) +void __show_regs(struct pt_regs *regs) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -177,28 +177,28 @@ void __show_regs(struct pt_regs * regs) printk("RBP: %016lx R08: %016lx R09: %016lx\n", regs->bp, regs->r8, regs->r9); printk("R10: %016lx R11: %016lx R12: %016lx\n", - regs->r10, regs->r11, regs->r12); + regs->r10, regs->r11, regs->r12); printk("R13: %016lx R14: %016lx R15: %016lx\n", - regs->r13, regs->r14, regs->r15); + regs->r13, regs->r14, regs->r15); - asm("movl %%ds,%0" : "=r" (ds)); - asm("movl %%cs,%0" : "=r" (cs)); - asm("movl %%es,%0" : "=r" (es)); + asm("movl %%ds,%0" : "=r" (ds)); + asm("movl %%cs,%0" : "=r" (cs)); + asm("movl %%es,%0" : "=r" (es)); asm("movl %%fs,%0" : "=r" (fsindex)); asm("movl %%gs,%0" : "=r" (gsindex)); rdmsrl(MSR_FS_BASE, fs); - rdmsrl(MSR_GS_BASE, gs); - rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + rdmsrl(MSR_GS_BASE, gs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); cr0 = read_cr0(); cr2 = read_cr2(); cr3 = read_cr3(); cr4 = read_cr4(); - printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", - fs,fsindex,gs,gsindex,shadowgs); - printk("CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); + printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", + fs, fsindex, gs, gsindex, shadowgs); + printk("CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4); get_debugreg(d0, 0); @@ -314,10 +314,10 @@ void prepare_to_copy(struct task_struct *tsk) int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, unsigned long unused, - struct task_struct * p, struct pt_regs * regs) + struct task_struct *p, struct pt_regs *regs) { int err; - struct pt_regs * childregs; + struct pt_regs *childregs; struct task_struct *me = current; childregs = ((struct pt_regs *) @@ -362,10 +362,10 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, if (test_thread_flag(TIF_IA32)) err = do_set_thread_area(p, -1, (struct user_desc __user *)childregs->si, 0); - else -#endif - err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); - if (err) + else +#endif + err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); + if (err) goto out; } err = 0; @@ -544,7 +544,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) unsigned fsindex, gsindex; /* we're going to use this soon, after a few expensive things */ - if (next_p->fpu_counter>5) + if (next_p->fpu_counter > 5) prefetch(next->xstate); /* @@ -552,13 +552,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ load_sp0(tss, next); - /* + /* * Switch DS and ES. * This won't pick up thread selector changes, but I guess that is ok. */ savesegment(es, prev->es); if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); + loadsegment(es, next->es); savesegment(ds, prev->ds); if (unlikely(next->ds | prev->ds)) @@ -584,7 +584,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_leave_lazy_cpu_mode(); - /* + /* * Switch FS and GS. * * Segment register != 0 always requires a reload. Also @@ -593,13 +593,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); - /* + /* * Check if the user used a selector != 0; if yes * clear 64bit base, since overloaded base is always * mapped to the Null selector */ if (fsindex) - prev->fs = 0; + prev->fs = 0; } /* when next process has a 64bit base use it */ if (next->fs) @@ -609,7 +609,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); if (gsindex) - prev->gs = 0; + prev->gs = 0; } if (next->gs) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); @@ -618,12 +618,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* Must be after DS reload */ unlazy_fpu(prev_p); - /* + /* * Switch the PDA and FPU contexts. */ prev->usersp = read_pda(oldrsp); write_pda(oldrsp, next->usersp); - write_pda(pcurrent, next_p); + write_pda(pcurrent, next_p); write_pda(kernelstack, (unsigned long)task_stack_page(next_p) + @@ -664,7 +664,7 @@ long sys_execve(char __user *name, char __user * __user *argv, char __user * __user *envp, struct pt_regs *regs) { long error; - char * filename; + char *filename; filename = getname(name); error = PTR_ERR(filename); @@ -722,55 +722,55 @@ asmlinkage long sys_vfork(struct pt_regs *regs) unsigned long get_wchan(struct task_struct *p) { unsigned long stack; - u64 fp,ip; + u64 fp, ip; int count = 0; - if (!p || p == current || p->state==TASK_RUNNING) - return 0; + if (!p || p == current || p->state == TASK_RUNNING) + return 0; stack = (unsigned long)task_stack_page(p); if (p->thread.sp < stack || p->thread.sp > stack+THREAD_SIZE) return 0; fp = *(u64 *)(p->thread.sp); - do { + do { if (fp < (unsigned long)stack || fp > (unsigned long)stack+THREAD_SIZE) - return 0; + return 0; ip = *(u64 *)(fp+8); if (!in_sched_functions(ip)) return ip; - fp = *(u64 *)fp; - } while (count++ < 16); + fp = *(u64 *)fp; + } while (count++ < 16); return 0; } long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) -{ - int ret = 0; +{ + int ret = 0; int doit = task == current; int cpu; - switch (code) { + switch (code) { case ARCH_SET_GS: if (addr >= TASK_SIZE_OF(task)) - return -EPERM; + return -EPERM; cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to + /* handle small bases via the GDT because that's faster to switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, GS_TLS, addr); - if (doit) { + if (addr <= 0xffffffff) { + set_32bit_tls(task, GS_TLS, addr); + if (doit) { load_TLS(&task->thread, cpu); - load_gs_index(GS_TLS_SEL); + load_gs_index(GS_TLS_SEL); } - task->thread.gsindex = GS_TLS_SEL; + task->thread.gsindex = GS_TLS_SEL; task->thread.gs = 0; - } else { + } else { task->thread.gsindex = 0; task->thread.gs = addr; if (doit) { load_gs_index(0); ret = checking_wrmsrl(MSR_KERNEL_GS_BASE, addr); - } + } } put_cpu(); break; @@ -824,8 +824,7 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) rdmsrl(MSR_KERNEL_GS_BASE, base); else base = task->thread.gs; - } - else + } else base = task->thread.gs; ret = put_user(base, (unsigned long __user *)addr); break; -- cgit v1.2.3 From 8092c654de9a964c14d89da56834f73a80548a58 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Tue, 29 Jul 2008 02:48:52 -0300 Subject: x86: add KERN_INFO to printks on process_64.c Fix many coding style warnings. Signed-off-by: Gustavo F. Padovan Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_64.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/process_64.c') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4da8514dd25..3560d7f4d74 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -161,24 +161,24 @@ void __show_regs(struct pt_regs *regs) printk("\n"); print_modules(); - printk("Pid: %d, comm: %.20s %s %s %.*s\n", + printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n", current->pid, current->comm, print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); - printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); + printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); - printk("RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->sp, - regs->flags); - printk("RAX: %016lx RBX: %016lx RCX: %016lx\n", + printk(KERN_INFO "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, + regs->sp, regs->flags); + printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n", regs->ax, regs->bx, regs->cx); - printk("RDX: %016lx RSI: %016lx RDI: %016lx\n", + printk(KERN_INFO "RDX: %016lx RSI: %016lx RDI: %016lx\n", regs->dx, regs->si, regs->di); - printk("RBP: %016lx R08: %016lx R09: %016lx\n", + printk(KERN_INFO "RBP: %016lx R08: %016lx R09: %016lx\n", regs->bp, regs->r8, regs->r9); - printk("R10: %016lx R11: %016lx R12: %016lx\n", + printk(KERN_INFO "R10: %016lx R11: %016lx R12: %016lx\n", regs->r10, regs->r11, regs->r12); - printk("R13: %016lx R14: %016lx R15: %016lx\n", + printk(KERN_INFO "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); asm("movl %%ds,%0" : "=r" (ds)); @@ -196,24 +196,26 @@ void __show_regs(struct pt_regs *regs) cr3 = read_cr3(); cr4 = read_cr4(); - printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", + printk(KERN_INFO "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", fs, fsindex, gs, gsindex, shadowgs); - printk("CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); - printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4); + printk(KERN_INFO "CS: %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, + es, cr0); + printk(KERN_INFO "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, + cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); get_debugreg(d2, 2); - printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); + printk(KERN_INFO "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2); get_debugreg(d3, 3); get_debugreg(d6, 6); get_debugreg(d7, 7); - printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); + printk(KERN_INFO "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7); } void show_regs(struct pt_regs *regs) { - printk("CPU %d:", smp_processor_id()); + printk(KERN_INFO "CPU %d:", smp_processor_id()); __show_regs(regs); show_trace(NULL, regs, (void *)(regs + 1), regs->bp); } -- cgit v1.2.3 From 4faac97d44ac27bdbb010a9c3597401a8f89341f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 22 Sep 2008 18:54:29 +0200 Subject: x86: prevent stale state of c1e_mask across CPU offline/online Impact: hang which happens across CPU offline/online on AMD C1E systems. When a CPU goes offline then the corresponding bit in the broadcast mask is cleared. For AMD C1E enabled CPUs we do not reenable the broadcast when the CPU comes online again as we do not clear the corresponding bit in the c1e_mask, which keeps track which CPUs have been switched to broadcast already. So on those !$@#& machines we never switch back to broadcasting after a CPU offline/online cycle. Clear the bit when the CPU plays dead. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/process_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/kernel/process_64.c') diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 71553b664e2..e12e0e4dd25 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -93,6 +93,8 @@ DECLARE_PER_CPU(int, cpu_state); static inline void play_dead(void) { idle_task_exit(); + c1e_remove_cpu(raw_smp_processor_id()); + mb(); /* Ack it */ __get_cpu_var(cpu_state) = CPU_DEAD; -- cgit v1.2.3