From 6dbde3530850d4d8bfc1b6bd4006d92786a2787f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 15 Jan 2009 22:15:53 +0900 Subject: percpu: add optimized generic percpu accessors It is an optimization and a cleanup, and adds the following new generic percpu methods: percpu_read() percpu_write() percpu_add() percpu_sub() percpu_and() percpu_or() percpu_xor() and implements support for them on x86. (other architectures will fall back to a default implementation) The advantage is that for example to read a local percpu variable, instead of this sequence: return __get_cpu_var(var); ffffffff8102ca2b: 48 8b 14 fd 80 09 74 mov -0x7e8bf680(,%rdi,8),%rdx ffffffff8102ca32: 81 ffffffff8102ca33: 48 c7 c0 d8 59 00 00 mov $0x59d8,%rax ffffffff8102ca3a: 48 8b 04 10 mov (%rax,%rdx,1),%rax We can get a single instruction by using the optimized variants: return percpu_read(var); ffffffff8102ca3f: 65 48 8b 05 91 8f fd mov %gs:0x7efd8f91(%rip),%rax I also cleaned up the x86-specific APIs and made the x86 code use these new generic percpu primitives. tj: * fixed generic percpu_sub() definition as Roel Kluin pointed out * added percpu_and() for completeness's sake * made generic percpu ops atomic against preemption Signed-off-by: Ingo Molnar Signed-off-by: Tejun Heo --- arch/x86/kernel/process_32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a546f55c77b4..77d546817d94 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -591,7 +591,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) loadsegment(gs, next->gs); - x86_write_percpu(current_task, next_p); + percpu_write(current_task, next_p); return prev_p; } -- cgit v1.2.3 From ea9279066de44053d0c20ea855bc9f4706652d84 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Mon, 19 Jan 2009 00:38:58 +0900 Subject: x86-64: Move cpu number from PDA to per-cpu and consolidate with 32-bit. tj: moved cpu_number definition out of CONFIG_HAVE_SETUP_PER_CPU_AREA for voyager. Signed-off-by: Brian Gerst Signed-off-by: Tejun Heo --- arch/x86/kernel/process_32.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 77d546817d94..2c00a57ccb90 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -66,9 +66,6 @@ asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); -DEFINE_PER_CPU(int, cpu_number); -EXPORT_PER_CPU_SYMBOL(cpu_number); - /* * Return saved PC of a blocked thread. */ -- cgit v1.2.3 From 03d2989df9c1c7df5b33c7a87e0790465461836a Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Fri, 23 Jan 2009 11:03:28 +0900 Subject: x86: remove idle_timestamp from 32bit irq_cpustat_t Impact: bogus irq_cpustat field removed idle_timestamp is left over from the removed irqbalance code. Signed-off-by: Brian Gerst Signed-off-by: Tejun Heo --- arch/x86/kernel/process_32.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2c00a57ccb90..1a1ae8edc40c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -108,7 +108,6 @@ void cpu_idle(void) play_dead(); local_irq_disable(); - __get_cpu_var(irq_stat).idle_timestamp = jiffies; /* Don't trace irqs off for idle */ stop_critical_timings(); pm_idle(); -- cgit v1.2.3 From d9a89a26e02ef9ed03f74a755a8b4d8f3a066622 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 9 Feb 2009 22:17:40 +0900 Subject: x86: add %gs accessors for x86_32 Impact: cleanup On x86_32, %gs is handled lazily. It's not saved and restored on kernel entry/exit but only when necessary which usually is during task switch but there are few other places. Currently, it's done by calling savesegment() and loadsegment() explicitly. Define get_user_gs(), set_user_gs() and task_user_gs() and use them instead. While at it, clean up register access macros in signal.c. This cleans up code a bit and will help future changes. Signed-off-by: Tejun Heo Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 1a1ae8edc40c..d58a340e1be3 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -131,7 +131,7 @@ void __show_regs(struct pt_regs *regs, int all) if (user_mode_vm(regs)) { sp = regs->sp; ss = regs->ss & 0xffff; - savesegment(gs, gs); + gs = get_user_gs(regs); } else { sp = (unsigned long) (®s->sp); savesegment(ss, ss); @@ -304,7 +304,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, p->thread.ip = (unsigned long) ret_from_fork; - savesegment(gs, p->thread.gs); + task_user_gs(p) = get_user_gs(regs); tsk = current; if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { @@ -342,7 +342,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) { - __asm__("movl %0, %%gs" : : "r"(0)); + set_user_gs(regs, 0); regs->fs = 0; set_fs(USER_DS); regs->ds = __USER_DS; -- cgit v1.2.3 From ccbeed3a05908d201b47b6c3dd1a373138bba566 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 9 Feb 2009 22:17:40 +0900 Subject: x86: make lazy %gs optional on x86_32 Impact: pt_regs changed, lazy gs handling made optional, add slight overhead to SAVE_ALL, simplifies error_code path a bit On x86_32, %gs hasn't been used by kernel and handled lazily. pt_regs doesn't have place for it and gs is saved/loaded only when necessary. In preparation for stack protector support, this patch makes lazy %gs handling optional by doing the followings. * Add CONFIG_X86_32_LAZY_GS and place for gs in pt_regs. * Save and restore %gs along with other registers in entry_32.S unless LAZY_GS. Note that this unfortunately adds "pushl $0" on SAVE_ALL even when LAZY_GS. However, it adds no overhead to common exit path and simplifies entry path with error code. * Define different user_gs accessors depending on LAZY_GS and add lazy_save_gs() and lazy_load_gs() which are noop if !LAZY_GS. The lazy_*_gs() ops are used to save, load and clear %gs lazily. * Define ELF_CORE_COPY_KERNEL_REGS() which always read %gs directly. xen and lguest changes need to be verified. Signed-off-by: Tejun Heo Cc: Jeremy Fitzhardinge Cc: Rusty Russell Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index d58a340e1be3..86122fa2a1ba 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -539,7 +539,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * used %fs or %gs (it does not today), or if the kernel is * running inside of a hypervisor layer. */ - savesegment(gs, prev->gs); + lazy_save_gs(prev->gs); /* * Load the per-thread Thread-Local Storage descriptor. @@ -585,7 +585,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Restore %gs if needed (which is common) */ if (prev->gs | next->gs) - loadsegment(gs, next->gs); + lazy_load_gs(next->gs); percpu_write(current_task, next_p); -- cgit v1.2.3 From 60a5317ff0f42dd313094b88f809f63041568b08 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 9 Feb 2009 22:17:40 +0900 Subject: x86: implement x86_32 stack protector Impact: stack protector for x86_32 Implement stack protector for x86_32. GDT entry 28 is used for it. It's set to point to stack_canary-20 and have the length of 24 bytes. CONFIG_CC_STACKPROTECTOR turns off CONFIG_X86_32_LAZY_GS and sets %gs to the stack canary segment on entry. As %gs is otherwise unused by the kernel, the canary can be anywhere. It's defined as a percpu variable. x86_32 exception handlers take register frame on stack directly as struct pt_regs. With -fstack-protector turned on, gcc copies the whole structure after the stack canary and (of course) doesn't copy back on return thus losing all changed. For now, -fno-stack-protector is added to all files which contain those functions. We definitely need something better. Signed-off-by: Tejun Heo Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 86122fa2a1ba..9a62383e7c3c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -212,6 +212,7 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) regs.ds = __USER_DS; regs.es = __USER_DS; regs.fs = __KERNEL_PERCPU; + regs.gs = __KERNEL_STACK_CANARY; regs.orig_ax = -1; regs.ip = (unsigned long) kernel_thread_helper; regs.cs = __KERNEL_CS | get_kernel_rpl(); -- cgit v1.2.3 From 5c79d2a517a9905599d192db8ce77ab5f1a2faca Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 11 Feb 2009 16:31:00 +0900 Subject: x86: fix x86_32 stack protector bugs Impact: fix x86_32 stack protector Brian Gerst found out that %gs was being initialized to stack_canary instead of stack_canary - 20, which basically gave the same canary value for all threads. Fixing this also exposed the following bugs. * cpu_idle() didn't call boot_init_stack_canary() * stack canary switching in switch_to() was being done too late making the initial run of a new thread use the old stack canary value. Fix all of them and while at it update comment in cpu_idle() about calling boot_init_stack_canary(). Reported-by: Brian Gerst Signed-off-by: Tejun Heo Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 9a62383e7c3c..b50604bb1e41 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -11,6 +11,7 @@ #include +#include #include #include #include @@ -91,6 +92,15 @@ void cpu_idle(void) { int cpu = smp_processor_id(); + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. CPU0 already has it initialized but no harm in + * doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); + current_thread_info()->status |= TS_POLLING; /* endless idle loop with no priority at all */ -- cgit v1.2.3 From 253f29a4ae9cc6cdc7b94f96517f27a93885a6ce Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Tue, 10 Feb 2009 09:51:46 -0500 Subject: x86: pass in pt_regs pointer for syscalls that need it Some syscalls need to access the pt_regs structure, either to copy user register state or to modifiy it. This patch adds stubs to load the address of the pt_regs struct into the %eax register, and changes the syscalls to regparm(1) to receive the pt_regs pointer as the first argument. Signed-off-by: Brian Gerst Acked-by: Tejun Heo Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index b50604bb1e41..5a9dcfb01f71 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -603,24 +603,18 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -asmlinkage int sys_fork(struct pt_regs regs) +ptregscall int sys_fork(struct pt_regs *regs) { - return do_fork(SIGCHLD, regs.sp, ®s, 0, NULL, NULL); + return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); } -asmlinkage int sys_clone(struct pt_regs regs) +ptregscall int sys_clone(struct pt_regs *regs, unsigned long clone_flags, + unsigned long newsp, int __user *parent_tidptr, + unsigned long unused, int __user *child_tidptr) { - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs.bx; - newsp = regs.cx; - parent_tidptr = (int __user *)regs.dx; - child_tidptr = (int __user *)regs.di; if (!newsp) - newsp = regs.sp; - return do_fork(clone_flags, newsp, ®s, 0, parent_tidptr, child_tidptr); + newsp = regs->sp; + return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); } /* @@ -633,27 +627,26 @@ asmlinkage int sys_clone(struct pt_regs regs) * do not have enough call-clobbered registers to hold all * the information you need. */ -asmlinkage int sys_vfork(struct pt_regs regs) +ptregscall int sys_vfork(struct pt_regs *regs) { - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.sp, ®s, 0, NULL, NULL); + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, NULL, NULL); } /* * sys_execve() executes a new program. */ -asmlinkage int sys_execve(struct pt_regs regs) +ptregscall int sys_execve(struct pt_regs *regs, char __user *u_filename, + char __user * __user *argv, + char __user * __user *envp) { int error; char *filename; - filename = getname((char __user *) regs.bx); + filename = getname(u_filename); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, - (char __user * __user *) regs.cx, - (char __user * __user *) regs.dx, - ®s); + error = do_execve(filename, argv, envp, regs); if (error == 0) { /* Make sure we don't return using sysenter.. */ set_thread_flag(TIF_IRET); -- cgit v1.2.3 From b12bdaf11f935d7be030207e3c77faeaeab8ded3 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Wed, 11 Feb 2009 16:43:58 -0500 Subject: x86: use regparm(3) for passed-in pt_regs pointer Some syscalls need to access the pt_regs structure, either to copy user register state or to modifiy it. This patch adds stubs to load the address of the pt_regs struct into the %eax register, and changes the syscalls to take the pointer as an argument instead of relying on the assumption that the pt_regs structure overlaps the function arguments. Drop the use of regparm(1) due to concern about gcc bugs, and to move in the direction of the eventual removal of regparm(0) for asmlinkage. Signed-off-by: Brian Gerst Signed-off-by: H. Peter Anvin --- arch/x86/kernel/process_32.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 5a9dcfb01f71..fec79ad85dc6 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -603,15 +603,21 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -ptregscall int sys_fork(struct pt_regs *regs) +int sys_fork(struct pt_regs *regs) { return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); } -ptregscall int sys_clone(struct pt_regs *regs, unsigned long clone_flags, - unsigned long newsp, int __user *parent_tidptr, - unsigned long unused, int __user *child_tidptr) +int sys_clone(struct pt_regs *regs) { + unsigned long clone_flags; + unsigned long newsp; + int __user *parent_tidptr, *child_tidptr; + + clone_flags = regs->bx; + newsp = regs->cx; + parent_tidptr = (int __user *)regs->dx; + child_tidptr = (int __user *)regs->di; if (!newsp) newsp = regs->sp; return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); @@ -627,7 +633,7 @@ ptregscall int sys_clone(struct pt_regs *regs, unsigned long clone_flags, * do not have enough call-clobbered registers to hold all * the information you need. */ -ptregscall int sys_vfork(struct pt_regs *regs) +int sys_vfork(struct pt_regs *regs) { return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, NULL, NULL); } @@ -635,18 +641,19 @@ ptregscall int sys_vfork(struct pt_regs *regs) /* * sys_execve() executes a new program. */ -ptregscall int sys_execve(struct pt_regs *regs, char __user *u_filename, - char __user * __user *argv, - char __user * __user *envp) +int sys_execve(struct pt_regs *regs) { int error; char *filename; - filename = getname(u_filename); + filename = getname((char __user *) regs->bx); error = PTR_ERR(filename); if (IS_ERR(filename)) goto out; - error = do_execve(filename, argv, envp, regs); + error = do_execve(filename, + (char __user * __user *) regs->cx, + (char __user * __user *) regs->dx, + regs); if (error == 0) { /* Make sure we don't return using sysenter.. */ set_thread_flag(TIF_IRET); -- cgit v1.2.3 From db949bba3c7cf2e664ac12e237c6d4c914f0c69d Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 27 Feb 2009 13:25:21 -0800 Subject: x86-32: use non-lazy io bitmap context switching Impact: remove 32-bit optimization to prepare unification x86-32 and -64 differ in the way they context-switch tasks with io permission bitmaps. x86-64 simply copies the next tasks io bitmap into place (if any) on context switch. x86-32 invalidates the bitmap on context switch, so that the next IO instruction will fault; at that point it installs the appropriate IO bitmap. This makes context switching IO-bitmap-using tasks a bit more less expensive, at the cost of making the next IO instruction slower due to the extra fault. This tradeoff only makes sense if IO-bitmap-using processes are relatively common, but they don't actually use IO instructions very often. However, in a typical desktop system, the only process likely to be using IO bitmaps is the X server, and nothing at all on a server. Therefore the lazy context switch doesn't really win all that much, and its just a gratuitious difference from 64-bit code. This patch removes the lazy context switch, with a view to unifying this code in a later change. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 36 +++++++++--------------------------- 1 file changed, 9 insertions(+), 27 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 646da41a620a..a59314e877f0 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -248,11 +248,8 @@ void exit_thread(void) /* * Careful, clear this in the TSS too: */ - memset(tss->io_bitmap, 0xff, tss->io_bitmap_max); + memset(tss->io_bitmap, 0xff, t->io_bitmap_max); t->io_bitmap_max = 0; - tss->io_bitmap_owner = NULL; - tss->io_bitmap_max = 0; - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET; put_cpu(); } @@ -458,34 +455,19 @@ __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, hard_enable_TSC(); } - if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { + if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { /* - * Disable the bitmap via an invalid offset. We still cache - * the previous bitmap owner and the IO bitmap contents: + * Copy the relevant range of the IO bitmap. + * Normally this is 128 bytes or less: */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET; - return; - } - - if (likely(next == tss->io_bitmap_owner)) { + memcpy(tss->io_bitmap, next->io_bitmap_ptr, + max(prev->io_bitmap_max, next->io_bitmap_max)); + } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { /* - * Previous owner of the bitmap (hence the bitmap content) - * matches the next task, we dont have to do anything but - * to set a valid offset in the TSS: + * Clear any possible leftover bits: */ - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; - return; + memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } - /* - * Lazy TSS's I/O bitmap copy. We set an invalid offset here - * and we let the task to get a GPF in case an I/O instruction - * is performed. The handler of the GPF will verify that the - * faulting task has a valid I/O bitmap and, it true, does the - * real copy and restart the instruction. This will save us - * redundant copies when the currently switched task does not - * perform any I/O during its timeslice. - */ - tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET_LAZY; } /* -- cgit v1.2.3 From 389d1fb11e5f2a16b5e34c547756f0c4dec641f7 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 27 Feb 2009 13:25:28 -0800 Subject: x86: unify chunks of kernel/process*.c With x86-32 and -64 using the same mechanism for managing the tss io permissions bitmap, large chunks of process*.c are trivially unifyable, including: - exit_thread - flush_thread - __switch_to_xtra (along with tsc enable/disable) and as bonus pickups: - sys_fork - sys_vfork (Note: asmlinkage expands to empty on x86-64) Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 172 ------------------------------------------- 1 file changed, 172 deletions(-) (limited to 'arch/x86/kernel/process_32.c') diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index a59314e877f0..14014d766cad 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -230,52 +230,6 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) } EXPORT_SYMBOL(kernel_thread); -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - /* The process may have allocated an io port bitmap... nuke it. */ - if (unlikely(test_thread_flag(TIF_IO_BITMAP))) { - struct task_struct *tsk = current; - struct thread_struct *t = &tsk->thread; - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - clear_thread_flag(TIF_IO_BITMAP); - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); - t->io_bitmap_max = 0; - put_cpu(); - } - - ds_exit_thread(current); -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - clear_tsk_thread_flag(tsk, TIF_DEBUG); - /* - * Forget coprocessor state.. - */ - tsk->fpu_counter = 0; - clear_fpu(tsk); - clear_used_math(); -} - void release_thread(struct task_struct *dead_task) { BUG_ON(dead_task->mm); @@ -363,112 +317,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) } EXPORT_SYMBOL_GPL(start_thread); -static void hard_disable_TSC(void) -{ - write_cr4(read_cr4() | X86_CR4_TSD); -} - -void disable_TSC(void) -{ - preempt_disable(); - if (!test_and_set_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_disable_TSC(); - preempt_enable(); -} - -static void hard_enable_TSC(void) -{ - write_cr4(read_cr4() & ~X86_CR4_TSD); -} - -static void enable_TSC(void) -{ - preempt_disable(); - if (test_and_clear_thread_flag(TIF_NOTSC)) - /* - * Must flip the CPU state synchronously with - * TIF_NOTSC in the current running context. - */ - hard_enable_TSC(); - preempt_enable(); -} - -int get_tsc_mode(unsigned long adr) -{ - unsigned int val; - - if (test_thread_flag(TIF_NOTSC)) - val = PR_TSC_SIGSEGV; - else - val = PR_TSC_ENABLE; - - return put_user(val, (unsigned int __user *)adr); -} - -int set_tsc_mode(unsigned int val) -{ - if (val == PR_TSC_SIGSEGV) - disable_TSC(); - else if (val == PR_TSC_ENABLE) - enable_TSC(); - else - return -EINVAL; - - return 0; -} - -static noinline void -__switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) -{ - struct thread_struct *prev, *next; - - prev = &prev_p->thread; - next = &next_p->thread; - - if (test_tsk_thread_flag(next_p, TIF_DS_AREA_MSR) || - test_tsk_thread_flag(prev_p, TIF_DS_AREA_MSR)) - ds_switch_to(prev_p, next_p); - else if (next->debugctlmsr != prev->debugctlmsr) - update_debugctlmsr(next->debugctlmsr); - - if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { - set_debugreg(next->debugreg0, 0); - set_debugreg(next->debugreg1, 1); - set_debugreg(next->debugreg2, 2); - set_debugreg(next->debugreg3, 3); - /* no 4 and 5 */ - set_debugreg(next->debugreg6, 6); - set_debugreg(next->debugreg7, 7); - } - - if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^ - test_tsk_thread_flag(next_p, TIF_NOTSC)) { - /* prev and next are different */ - if (test_tsk_thread_flag(next_p, TIF_NOTSC)) - hard_disable_TSC(); - else - hard_enable_TSC(); - } - - if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { - /* - * Copy the relevant range of the IO bitmap. - * Normally this is 128 bytes or less: - */ - memcpy(tss->io_bitmap, next->io_bitmap_ptr, - max(prev->io_bitmap_max, next->io_bitmap_max)); - } else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) { - /* - * Clear any possible leftover bits: - */ - memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); - } -} /* * switch_to(x,yn) should switch tasks from x to y. @@ -582,11 +430,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) return prev_p; } -int sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - int sys_clone(struct pt_regs *regs) { unsigned long clone_flags; @@ -602,21 +445,6 @@ int sys_clone(struct pt_regs *regs) return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr); } -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -int sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->sp, regs, 0, NULL, NULL); -} - /* * sys_execve() executes a new program. */ -- cgit v1.2.3