From 0100301bfdf56a2a370c7157b5ab0fbf9313e1cd Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:19 -0400 Subject: sched/x86: Rewrite the switch_to() code Move the low-level context switch code to an out-of-line asm stub instead of using complex inline asm. This allows constructing a new stack frame for the child process to make it seamlessly flow to ret_from_fork without an extra test and branch in __switch_to(). It also improves code generation for __schedule() by using the C calling convention instead of clobbering all registers. Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-5-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 9 ++++++--- 1 file changed, 6 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 d86be29c38c7..4bedbc08e53c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -133,17 +133,20 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); + struct fork_frame *fork_frame = container_of(childregs, struct fork_frame, regs); + struct inactive_task_frame *frame = &fork_frame->frame; struct task_struct *tsk; int err; - p->thread.sp = (unsigned long) childregs; + frame->bp = 0; + p->thread.sp = (unsigned long) fork_frame; p->thread.sp0 = (unsigned long) (childregs+1); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - p->thread.ip = (unsigned long) ret_from_kernel_thread; + frame->ret_addr = (unsigned long) ret_from_kernel_thread; task_user_gs(p) = __KERNEL_STACK_CANARY; childregs->ds = __USER_DS; childregs->es = __USER_DS; @@ -161,7 +164,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, if (sp) childregs->sp = sp; - p->thread.ip = (unsigned long) ret_from_fork; + frame->ret_addr = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); p->thread.io_bitmap_ptr = NULL; -- cgit v1.2.3 From 616d24835eeafa8ef3466479db028abfdfc77531 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:20 -0400 Subject: sched/x86: Pass kernel thread parameters in 'struct fork_frame' Instead of setting up a fake pt_regs context, put the kernel thread function pointer and arg into the unused callee-restored registers of 'struct fork_frame'. Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-6-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 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 4bedbc08e53c..18714a191b2d 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,9 +55,6 @@ #include #include -asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); -asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); - /* * Return saved PC of a blocked thread. */ @@ -139,6 +136,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, int err; frame->bp = 0; + frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; p->thread.sp0 = (unsigned long) (childregs+1); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); @@ -146,25 +144,17 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - frame->ret_addr = (unsigned long) ret_from_kernel_thread; - task_user_gs(p) = __KERNEL_STACK_CANARY; - childregs->ds = __USER_DS; - childregs->es = __USER_DS; - childregs->fs = __KERNEL_PERCPU; - childregs->bx = sp; /* function */ - childregs->bp = arg; - childregs->orig_ax = -1; - childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; + frame->bx = sp; /* function */ + frame->di = arg; p->thread.io_bitmap_ptr = NULL; return 0; } + frame->bx = 0; *childregs = *current_pt_regs(); childregs->ax = 0; if (sp) childregs->sp = sp; - frame->ret_addr = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); p->thread.io_bitmap_ptr = NULL; -- cgit v1.2.3 From ffcb043ba524d3fbd979a9dac2c9ce8ad352000d Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:21 -0400 Subject: sched/x86: Fix thread_saved_pc() thread_saved_pc() was using a completely bogus method to get the return address. Since switch_to() was previously inlined, there was no sane way to know where on the stack the return address was stored. Now with the frame of a sleeping thread well defined, this can be implemented correctly. Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-7-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/process_32.c | 8 -------- 1 file changed, 8 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 18714a191b2d..404efdfa083b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,14 +55,6 @@ #include #include -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return ((unsigned long *)tsk->thread.sp)[3]; -} - void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; -- cgit v1.2.3 From 1ef55be16ed69538f89e0a6508be5e62fdc9851c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 29 Sep 2016 12:48:12 -0700 Subject: x86/asm: Get rid of __read_cr4_safe() We use __read_cr4() vs __read_cr4_safe() inconsistently. On CR4-less CPUs, all CR4 bits are effectively clear, so we can make the code simpler and more robust by making __read_cr4() always fix up faults on 32-bit kernels. This may fix some bugs on old 486-like CPUs, but I don't have any easy way to test that. Signed-off-by: Andy Lutomirski Cc: Brian Gerst Cc: Borislav Petkov Cc: david@saggiorato.net Link: http://lkml.kernel.org/r/ea647033d357d9ce2ad2bbde5a631045f5052fb6.1475178370.git.luto@kernel.org Signed-off-by: Thomas Gleixner --- 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 404efdfa083b..bd7be8efdc4c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -90,7 +90,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); cr3 = read_cr3(); - cr4 = __read_cr4_safe(); + cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); -- cgit v1.2.3