From: Andy Lutomirski Date: Mon, 31 Oct 2016 22:18:49 +0000 (-0700) Subject: x86/fpu: Remove clts() X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=af25ed59b5616b389d90877f7085dc5d457a3d49;p=linux-beck.git x86/fpu: Remove clts() The kernel doesn't use clts() any more. Remove it and all of its paravirt infrastructure. A careful reader may notice that xen_clts() appears to have been buggy -- it didn't update xen_cr0_value. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Quentin Casasnovas Cc: Rik van Riel Cc: Rusty Russell Cc: Thomas Gleixner Cc: kvm list Link: http://lkml.kernel.org/r/3d3c8ca62f17579b9849a013d71e59a4d5d1b079.1477951965.git.luto@kernel.org Signed-off-by: Ingo Molnar --- diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index ce932812f142..f1fb4dbe9a3e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -41,11 +41,6 @@ static inline void set_debugreg(unsigned long val, int reg) PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val); } -static inline void clts(void) -{ - PVOP_VCALL0(pv_cpu_ops.clts); -} - static inline unsigned long read_cr0(void) { return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 0f400c0e4979..545426aa61ef 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -103,8 +103,6 @@ struct pv_cpu_ops { unsigned long (*get_debugreg)(int regno); void (*set_debugreg)(int regno, unsigned long value); - void (*clts)(void); - unsigned long (*read_cr0)(void); void (*write_cr0)(unsigned long); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 29b417bd8a68..12af3e35edfa 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -6,11 +6,6 @@ #include -static inline void native_clts(void) -{ - asm volatile("clts"); -} - /* * Volatile isn't enough to prevent the compiler from reordering the * read/write functions for the control registers and messing everything up. @@ -208,12 +203,6 @@ static inline void load_gs_index(unsigned selector) #endif -/* Clear the 'TS' bit */ -static inline void clts(void) -{ - native_clts(); -} - #endif/* CONFIG_PARAVIRT */ static inline void clflush(volatile void *__p) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index bbf3d5933eaa..a1bfba0f7234 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -328,7 +328,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .cpuid = native_cpuid, .get_debugreg = native_get_debugreg, .set_debugreg = native_set_debugreg, - .clts = native_clts, .read_cr0 = native_read_cr0, .write_cr0 = native_write_cr0, .read_cr4 = native_read_cr4, diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index 920c6ae08592..d3f7f14bb328 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -8,7 +8,6 @@ DEF_NATIVE(pv_cpu_ops, iret, "iret"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); -DEF_NATIVE(pv_cpu_ops, clts, "clts"); #if defined(CONFIG_PARAVIRT_SPINLOCKS) DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); @@ -48,7 +47,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_cpu_ops, clts); #if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): if (pv_is_native_spin_unlock()) { diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index bb3840cedb4f..915a4c0b217c 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -10,7 +10,6 @@ DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); -DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); @@ -58,7 +57,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index d74afcdbc580..4ca0d78adcf0 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -517,17 +517,6 @@ static unsigned long lguest_read_cr0(void) return 0; } -/* - * Intel provided a special instruction to clear the TS bit for people too cool - * to use write_cr0() to do it. This "clts" instruction is faster, because all - * the vowels have been optimized out. - */ -static void lguest_clts(void) -{ - lazy_hcall1(LHCALL_TS, 0); - current_cr0 &= ~X86_CR0_TS; -} - /* * cr2 is the virtual address of the last page fault, which the Guest only ever * reads. The Host kindly writes this into our "struct lguest_data", so we @@ -1429,7 +1418,6 @@ __init void lguest_init(void) pv_cpu_ops.load_tls = lguest_load_tls; pv_cpu_ops.get_debugreg = lguest_get_debugreg; pv_cpu_ops.set_debugreg = lguest_set_debugreg; - pv_cpu_ops.clts = lguest_clts; pv_cpu_ops.read_cr0 = lguest_read_cr0; pv_cpu_ops.write_cr0 = lguest_write_cr0; pv_cpu_ops.read_cr4 = lguest_read_cr4; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bdd855685403..ced7027b3fbc 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -980,17 +980,6 @@ static void xen_io_delay(void) { } -static void xen_clts(void) -{ - struct multicall_space mcs; - - mcs = xen_mc_entry(0); - - MULTI_fpu_taskswitch(mcs.mc, 0); - - xen_mc_issue(PARAVIRT_LAZY_CPU); -} - static DEFINE_PER_CPU(unsigned long, xen_cr0_value); static unsigned long xen_read_cr0(void) @@ -1233,8 +1222,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .set_debugreg = xen_set_debugreg, .get_debugreg = xen_get_debugreg, - .clts = xen_clts, - .read_cr0 = xen_read_cr0, .write_cr0 = xen_write_cr0,