diff options
Diffstat (limited to 'arch')
59 files changed, 471 insertions, 331 deletions
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index d400a2161935..8ee41e988169 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -78,9 +78,6 @@ struct task_struct; #endif -#define copy_segments(tsk, mm) do { } while (0) -#define release_segments(mm) do { } while (0) - #define KSTK_EIP(tsk) (task_pt_regs(tsk)->ret) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 9b41f1e3b1a0..939b310913cf 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -50,17 +50,22 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) KBUILD_AFLAGS += $(lseinstr) $(brokengasinst) +KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) +KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ AS += -EB LD += -EB +LDFLAGS += -maarch64linuxb UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__AARCH64EL__ AS += -EL LD += -EL +LDFLAGS += -maarch64linux UTS_MACHINE := aarch64 endif diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 636c1bced7d4..1b266292f0be 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -1,7 +1,7 @@ #ifndef __ASM_LINKAGE_H #define __ASM_LINKAGE_H -#define __ALIGN .align 4 -#define __ALIGN_STR ".align 4" +#define __ALIGN .align 2 +#define __ALIGN_STR ".align 2" #endif diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 3a68cf38a6b3..f444f374bd7b 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -321,6 +321,8 @@ void kernel_neon_end(void) } EXPORT_SYMBOL(kernel_neon_end); +#ifdef CONFIG_EFI + static DEFINE_PER_CPU(struct fpsimd_state, efi_fpsimd_state); static DEFINE_PER_CPU(bool, efi_fpsimd_state_used); @@ -370,6 +372,8 @@ void __efi_fpsimd_end(void) kernel_neon_end(); } +#endif /* CONFIG_EFI */ + #endif /* CONFIG_KERNEL_MODE_NEON */ #ifdef CONFIG_CPU_PM diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h index 7c87b5be53b5..8f7cce829f8e 100644 --- a/arch/c6x/include/asm/processor.h +++ b/arch/c6x/include/asm/processor.h @@ -92,9 +92,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -#define copy_segments(tsk, mm) do { } while (0) -#define release_segments(mm) do { } while (0) - /* * saved kernel SP and DP of a blocked thread. */ diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h index e4d08d74ed9f..021cce78b401 100644 --- a/arch/frv/include/asm/processor.h +++ b/arch/frv/include/asm/processor.h @@ -92,10 +92,6 @@ static inline void release_thread(struct task_struct *dead_task) extern asmlinkage void save_user_regs(struct user_context *target); extern asmlinkage void *restore_user_regs(const struct user_context *target, ...); -#define copy_segments(tsk, mm) do { } while (0) -#define release_segments(mm) do { } while (0) -#define forget_segments() do { } while (0) - unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.frame0->pc) diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h index 657874eeeccc..c70fa9ac7169 100644 --- a/arch/m32r/include/asm/processor.h +++ b/arch/m32r/include/asm/processor.h @@ -118,14 +118,6 @@ struct mm_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Copy and release all segment info associated with a VM */ -extern void copy_segments(struct task_struct *p, struct mm_struct * mm); -extern void release_segments(struct mm_struct * mm); - -/* Copy and release all segment info associated with a VM */ -#define copy_segments(p, mm) do { } while (0) -#define release_segments(mm) do { } while (0) - unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.lr) #define KSTK_ESP(tsk) ((tsk)->thread.sp) diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index ec6a49076980..8ae92d6abfd2 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -131,9 +131,6 @@ static inline void release_thread(struct task_struct *dead_task) { } -#define copy_segments(tsk, mm) do { } while (0) -#define release_segments(mm) do { } while (0) - /* * Return saved PC of a blocked thread. */ diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index e4ed1bc9a734..a6810923b3f0 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -1377,29 +1377,32 @@ do { \ #define __write_64bit_c0_split(source, sel, val) \ do { \ + unsigned long long __tmp; \ unsigned long __flags; \ \ local_irq_save(__flags); \ if (sel == 0) \ __asm__ __volatile__( \ ".set\tmips64\n\t" \ - "dsll\t%L0, %L0, 32\n\t" \ + "dsll\t%L0, %L1, 32\n\t" \ "dsrl\t%L0, %L0, 32\n\t" \ - "dsll\t%M0, %M0, 32\n\t" \ + "dsll\t%M0, %M1, 32\n\t" \ "or\t%L0, %L0, %M0\n\t" \ "dmtc0\t%L0, " #source "\n\t" \ ".set\tmips0" \ - : : "r" (val)); \ + : "=&r,r" (__tmp) \ + : "r,0" (val)); \ else \ __asm__ __volatile__( \ ".set\tmips64\n\t" \ - "dsll\t%L0, %L0, 32\n\t" \ + "dsll\t%L0, %L1, 32\n\t" \ "dsrl\t%L0, %L0, 32\n\t" \ - "dsll\t%M0, %M0, 32\n\t" \ + "dsll\t%M0, %M1, 32\n\t" \ "or\t%L0, %L0, %M0\n\t" \ "dmtc0\t%L0, " #source ", " #sel "\n\t" \ ".set\tmips0" \ - : : "r" (val)); \ + : "=&r,r" (__tmp) \ + : "r,0" (val)); \ local_irq_restore(__flags); \ } while (0) diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c index 9e6c74bf66c4..6668f67a61c3 100644 --- a/arch/mips/kernel/perf_event_mipsxx.c +++ b/arch/mips/kernel/perf_event_mipsxx.c @@ -618,8 +618,7 @@ static int mipspmu_event_init(struct perf_event *event) return -ENOENT; } - if ((unsigned int)event->cpu >= nr_cpumask_bits || - (event->cpu >= 0 && !cpu_online(event->cpu))) + if (event->cpu >= 0 && !cpu_online(event->cpu)) return -ENODEV; if (!atomic_inc_not_zero(&active_events)) { diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c index ffa0f7101a97..2b08242ade62 100644 --- a/arch/mips/pmcs-msp71xx/msp_smp.c +++ b/arch/mips/pmcs-msp71xx/msp_smp.c @@ -22,6 +22,8 @@ #include <linux/smp.h> #include <linux/interrupt.h> +#include <asm/setup.h> + #ifdef CONFIG_MIPS_MT_SMP #define MIPS_CPU_IPI_RESCHED_IRQ 0 /* SW int 0 for resched */ #define MIPS_CPU_IPI_CALL_IRQ 1 /* SW int 1 for call */ diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c index 89e8027e07fb..7c475fd99c46 100644 --- a/arch/mn10300/kernel/process.c +++ b/arch/mn10300/kernel/process.c @@ -59,10 +59,6 @@ void arch_cpu_idle(void) } #endif -void release_segments(struct mm_struct *mm) -{ -} - void machine_restart(char *cmd) { #ifdef CONFIG_KERNEL_DEBUGGER @@ -113,14 +109,6 @@ void release_thread(struct task_struct *dead_task) } /* - * we do not have to muck with descriptors here, that is - * done in switch_mm() as needed. - */ -void copy_segments(struct task_struct *p, struct mm_struct *new_mm) -{ -} - -/* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. */ diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index e084fa548d73..063817fee61c 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -138,10 +138,11 @@ CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m -CONFIG_SND_SEQUENCER=m +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQUENCER_OSS=m CONFIG_SND_POWERMAC=m CONFIG_SND_AOA=m CONFIG_SND_AOA_FABRIC_LAYOUT=m diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig index 79bbc8238b32..805b0f87653c 100644 --- a/arch/powerpc/configs/gamecube_defconfig +++ b/arch/powerpc/configs/gamecube_defconfig @@ -64,11 +64,12 @@ CONFIG_LOGO=y # CONFIG_LOGO_LINUX_CLUT224 is not set CONFIG_SOUND=y CONFIG_SND=y -CONFIG_SND_SEQUENCER=y +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=y CONFIG_SND_PCM_OSS=y -CONFIG_SND_SEQUENCER_OSS=y # CONFIG_SND_VERBOSE_PROCFS is not set +CONFIG_SND_SEQUENCER=y +CONFIG_SND_SEQUENCER_OSS=y # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_GENERIC=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 8cf4a46bef86..6daa56f8895c 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -115,9 +115,10 @@ CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y -CONFIG_SND_SEQUENCER=y +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=y CONFIG_SND_PCM_OSS=y +CONFIG_SND_SEQUENCER=y CONFIG_SND_SEQUENCER_OSS=y CONFIG_SND_USB_AUDIO=y CONFIG_SND_USB_USX2Y=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 8e798b1fbc99..1aab9a62a681 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -227,11 +227,12 @@ CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m -CONFIG_SND_SEQUENCER=m -CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_SEQUENCER_OSS=m CONFIG_SND_DUMMY=m CONFIG_SND_POWERMAC=m CONFIG_SND_AOA=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 791db775a09c..6ddca80c52c3 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -222,11 +222,12 @@ CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m -CONFIG_SND_SEQUENCER=m -CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_SEQUENCER_OSS=m CONFIG_SND_POWERMAC=m CONFIG_SND_AOA=m CONFIG_SND_AOA_FABRIC_LAYOUT=m diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index d0fe0f8f77c2..41d85cb3c9a2 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -141,11 +141,12 @@ CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m -CONFIG_SND_SEQUENCER=m -CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_SEQUENCER_OSS=m CONFIG_HID_DRAGONRISE=y CONFIG_HID_GYRATION=y CONFIG_HID_TWINHAN=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index ae6eba482d75..da0e8d535eb8 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -789,17 +789,18 @@ CONFIG_LOGO=y # CONFIG_LOGO_LINUX_VGA16 is not set CONFIG_SOUND=m CONFIG_SND=m -CONFIG_SND_SEQUENCER=m -CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y CONFIG_SND_DYNAMIC_MINORS=y # CONFIG_SND_SUPPORT_OLD_API is not set CONFIG_SND_VERBOSE_PRINTK=y CONFIG_SND_DEBUG=y CONFIG_SND_DEBUG_VERBOSE=y CONFIG_SND_PCM_XRUN_DEBUG=y +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_SEQUENCER_OSS=m CONFIG_SND_DUMMY=m CONFIG_SND_VIRMIDI=m CONFIG_SND_MTPAV=m diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index aef41b17a8bc..9c7400a19e9d 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -79,11 +79,12 @@ CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_SOUND=y CONFIG_SND=y -CONFIG_SND_SEQUENCER=y +CONFIG_SND_OSSEMUL=y CONFIG_SND_MIXER_OSS=y CONFIG_SND_PCM_OSS=y -CONFIG_SND_SEQUENCER_OSS=y # CONFIG_SND_VERBOSE_PROCFS is not set +CONFIG_SND_SEQUENCER=y +CONFIG_SND_SEQUENCER_OSS=y CONFIG_HID_APPLE=m CONFIG_HID_WACOM=m CONFIG_MMC=y diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 9e816787c0d4..116000b45531 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1019,6 +1019,10 @@ int eeh_init(void) } else if ((ret = eeh_ops->init())) return ret; + /* Initialize PHB PEs */ + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) + eeh_dev_phb_init_dynamic(hose); + /* Initialize EEH event */ ret = eeh_event_init(); if (ret) diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index ad04ecd63c20..a34e6912c15e 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -78,21 +78,3 @@ void eeh_dev_phb_init_dynamic(struct pci_controller *phb) /* EEH PE for PHB */ eeh_phb_pe_create(phb); } - -/** - * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs - * - * Scan all the existing PHBs and create EEH devices for their OF - * nodes and their children OF nodes - */ -static int __init eeh_dev_phb_init(void) -{ - struct pci_controller *phb, *tmp; - - list_for_each_entry_safe(phb, tmp, &hose_list, list_node) - eeh_dev_phb_init_dynamic(phb); - - return 0; -} - -core_initcall(eeh_dev_phb_init); diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index 6f8273f5e988..91e037ab20a1 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -104,8 +104,10 @@ static unsigned long can_optimize(struct kprobe *p) * and that can be emulated. */ if (!is_conditional_branch(*p->ainsn.insn) && - analyse_instr(&op, ®s, *p->ainsn.insn)) + analyse_instr(&op, ®s, *p->ainsn.insn) == 1) { + emulate_update_regs(®s, &op); nip = regs.nip; + } return nip; } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 07cd22e35405..f52ad5bb7109 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -131,7 +131,7 @@ static void flush_tmregs_to_thread(struct task_struct *tsk) * in the appropriate thread structures from live. */ - if (tsk != current) + if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current)) return; if (MSR_TM_SUSPENDED(mfmsr())) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index ec74e203ee04..13c9dcdcba69 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -437,6 +437,7 @@ static inline int check_io_access(struct pt_regs *regs) int machine_check_e500mc(struct pt_regs *regs) { unsigned long mcsr = mfspr(SPRN_MCSR); + unsigned long pvr = mfspr(SPRN_PVR); unsigned long reason = mcsr; int recoverable = 1; @@ -478,8 +479,15 @@ int machine_check_e500mc(struct pt_regs *regs) * may still get logged and cause a machine check. We should * only treat the non-write shadow case as non-recoverable. */ - if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS)) - recoverable = 0; + /* On e6500 core, L1 DCWS (Data cache write shadow mode) bit + * is not implemented but L1 data cache always runs in write + * shadow mode. Hence on data cache parity errors HW will + * automatically invalidate the L1 Data Cache. + */ + if (PVR_VER(pvr) != PVR_VER_E6500) { + if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS)) + recoverable = 0; + } } if (reason & MCSR_L2MMU_MHIT) { diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index fb9f58b868e7..5e8418c28bd8 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -944,9 +944,9 @@ NOKPROBE_SYMBOL(emulate_dcbz); : "r" (addr), "i" (-EFAULT), "0" (err)) static nokprobe_inline void set_cr0(const struct pt_regs *regs, - struct instruction_op *op, int rd) + struct instruction_op *op) { - long val = regs->gpr[rd]; + long val = op->val; op->type |= SETCC; op->ccval = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000); @@ -1326,7 +1326,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 13: /* addic. */ imm = (short) instr; add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0); - set_cr0(regs, op, rd); + set_cr0(regs, op); return 1; case 14: /* addi */ @@ -1397,13 +1397,13 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 28: /* andi. */ op->val = regs->gpr[rd] & (unsigned short) instr; - set_cr0(regs, op, ra); + set_cr0(regs, op); goto logical_done_nocc; case 29: /* andis. */ imm = (unsigned short) instr; op->val = regs->gpr[rd] & (imm << 16); - set_cr0(regs, op, ra); + set_cr0(regs, op); goto logical_done_nocc; #ifdef __powerpc64__ @@ -1513,10 +1513,10 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->type = COMPUTE + SETCC; imm = 0xf0000000UL; val = regs->gpr[rd]; - op->val = regs->ccr; + op->ccval = regs->ccr; for (sh = 0; sh < 8; ++sh) { if (instr & (0x80000 >> sh)) - op->val = (op->val & ~imm) | + op->ccval = (op->ccval & ~imm) | (val & imm); imm >>= 4; } @@ -1651,8 +1651,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, goto arith_done; case 235: /* mullw */ - op->val = (unsigned int) regs->gpr[ra] * - (unsigned int) regs->gpr[rb]; + op->val = (long)(int) regs->gpr[ra] * + (int) regs->gpr[rb]; + goto arith_done; case 266: /* add */ @@ -2526,7 +2527,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, logical_done: if (instr & 1) - set_cr0(regs, op, ra); + set_cr0(regs, op); logical_done_nocc: op->reg = ra; op->type |= SETREG; @@ -2534,7 +2535,7 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, arith_done: if (instr & 1) - set_cr0(regs, op, rd); + set_cr0(regs, op); compute_done: op->reg = rd; op->type |= SETREG; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 2e3eb7431571..9e3da168d54c 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -793,6 +793,11 @@ void perf_event_print_debug(void) u32 pmcs[MAX_HWEVENTS]; int i; + if (!ppmu) { + pr_info("Performance monitor hardware not registered.\n"); + return; + } + if (!ppmu->n_counter) return; diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 9f59041a172b..443d5ca71995 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -393,7 +393,13 @@ static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val) u64 pir = get_hard_smp_processor_id(cpu); mtspr(SPRN_LPCR, lpcr_val); - opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val); + + /* + * Program the LPCR via stop-api only if the deepest stop state + * can lose hypervisor context. + */ + if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) + opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val); } /* diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 783f36364690..e45b5f10645a 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -266,7 +266,6 @@ int dlpar_attach_node(struct device_node *dn, struct device_node *parent) return rc; } - of_node_put(dn->parent); return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index fc0d8f97c03a..fadb95efbb9e 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -462,15 +462,19 @@ static ssize_t dlpar_cpu_add(u32 drc_index) } dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent); - of_node_put(parent); if (!dn) { pr_warn("Failed call to configure-connector, drc index: %x\n", drc_index); dlpar_release_drc(drc_index); + of_node_put(parent); return -EINVAL; } rc = dlpar_attach_node(dn, parent); + + /* Regardless we are done with parent now */ + of_node_put(parent); + if (rc) { saved_rc = rc; pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n", diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 210ce632d63e..f7042ad492ba 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -226,8 +226,10 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index) return -ENOENT; dn = dlpar_configure_connector(drc_index, parent_dn); - if (!dn) + if (!dn) { + of_node_put(parent_dn); return -ENOENT; + } rc = dlpar_attach_node(dn, parent_dn); if (rc) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index dce708e061ea..20e75a2ca93a 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1507,7 +1507,9 @@ static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, static inline void pmdp_invalidate(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { - pmdp_xchg_direct(vma->vm_mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY)); + pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID); + + pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index ca8cd80e8feb..60181caf8e8a 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -404,18 +404,6 @@ static inline void save_vector_registers(void) #endif } -static int __init topology_setup(char *str) -{ - bool enabled; - int rc; - - rc = kstrtobool(str, &enabled); - if (!rc && !enabled) - S390_lowcore.machine_flags &= ~MACHINE_FLAG_TOPOLOGY; - return rc; -} -early_param("topology", topology_setup); - static int __init disable_vector_extension(char *str) { S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX; diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index c1bf75ffb875..7e1e40323b78 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -823,9 +823,12 @@ static int cpumsf_pmu_event_init(struct perf_event *event) } /* Check online status of the CPU to which the event is pinned */ - if ((unsigned int)event->cpu >= nr_cpumask_bits || - (event->cpu >= 0 && !cpu_online(event->cpu))) - return -ENODEV; + if (event->cpu >= 0) { + if ((unsigned int)event->cpu >= nr_cpumask_bits) + return -ENODEV; + if (!cpu_online(event->cpu)) + return -ENODEV; + } /* Force reset of idle/hv excludes regardless of what the * user requested. diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index bb47c92476f0..ed0bdd220e1a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -8,6 +8,8 @@ #include <linux/workqueue.h> #include <linux/bootmem.h> +#include <linux/uaccess.h> +#include <linux/sysctl.h> #include <linux/cpuset.h> #include <linux/device.h> #include <linux/export.h> @@ -29,12 +31,20 @@ #define PTF_VERTICAL (1UL) #define PTF_CHECK (2UL) +enum { + TOPOLOGY_MODE_HW, + TOPOLOGY_MODE_SINGLE, + TOPOLOGY_MODE_PACKAGE, + TOPOLOGY_MODE_UNINITIALIZED +}; + struct mask_info { struct mask_info *next; unsigned char id; cpumask_t mask; }; +static int topology_mode = TOPOLOGY_MODE_UNINITIALIZED; static void set_topology_timer(void); static void topology_work_fn(struct work_struct *work); static struct sysinfo_15_1_x *tl_info; @@ -59,11 +69,26 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu) cpumask_t mask; cpumask_copy(&mask, cpumask_of(cpu)); - if (!MACHINE_HAS_TOPOLOGY) - return mask; - for (; info; info = info->next) { - if (cpumask_test_cpu(cpu, &info->mask)) - return info->mask; + switch (topology_mode) { + case TOPOLOGY_MODE_HW: + while (info) { + if (cpumask_test_cpu(cpu, &info->mask)) { + mask = info->mask; + break; + } + info = info->next; + } + if (cpumask_empty(&mask)) + cpumask_copy(&mask, cpumask_of(cpu)); + break; + case TOPOLOGY_MODE_PACKAGE: + cpumask_copy(&mask, cpu_present_mask); + break; + default: + /* fallthrough */ + case TOPOLOGY_MODE_SINGLE: + cpumask_copy(&mask, cpumask_of(cpu)); + break; } return mask; } @@ -74,7 +99,7 @@ static cpumask_t cpu_thread_map(unsigned int cpu) int i; cpumask_copy(&mask, cpumask_of(cpu)); - if (!MACHINE_HAS_TOPOLOGY) + if (topology_mode != TOPOLOGY_MODE_HW) return mask; cpu -= cpu % (smp_cpu_mtid + 1); for (i = 0; i <= smp_cpu_mtid; i++) @@ -184,10 +209,8 @@ static void topology_update_polarization_simple(void) { int cpu; - mutex_lock(&smp_cpu_state_mutex); for_each_possible_cpu(cpu) smp_cpu_set_polarization(cpu, POLARIZATION_HRZ); - mutex_unlock(&smp_cpu_state_mutex); } static int ptf(unsigned long fc) @@ -223,7 +246,7 @@ int topology_set_cpu_management(int fc) static void update_cpu_masks(void) { struct cpu_topology_s390 *topo; - int cpu; + int cpu, id; for_each_possible_cpu(cpu) { topo = &cpu_topology[cpu]; @@ -231,12 +254,13 @@ static void update_cpu_masks(void) topo->core_mask = cpu_group_map(&socket_info, cpu); topo->book_mask = cpu_group_map(&book_info, cpu); topo->drawer_mask = cpu_group_map(&drawer_info, cpu); - if (!MACHINE_HAS_TOPOLOGY) { + if (topology_mode != TOPOLOGY_MODE_HW) { + id = topology_mode == TOPOLOGY_MODE_PACKAGE ? 0 : cpu; topo->thread_id = cpu; topo->core_id = cpu; - topo->socket_id = cpu; - topo->book_id = cpu; - topo->drawer_id = cpu; + topo->socket_id = id; + topo->book_id = id; + topo->drawer_id = id; if (cpu_present(cpu)) cpumask_set_cpu(cpu, &cpus_with_topology); } @@ -254,6 +278,7 @@ static int __arch_update_cpu_topology(void) struct sysinfo_15_1_x *info = tl_info; int rc = 0; + mutex_lock(&smp_cpu_state_mutex); cpumask_clear(&cpus_with_topology); if (MACHINE_HAS_TOPOLOGY) { rc = 1; @@ -263,6 +288,7 @@ static int __arch_update_cpu_topology(void) update_cpu_masks(); if (!MACHINE_HAS_TOPOLOGY) topology_update_polarization_simple(); + mutex_unlock(&smp_cpu_state_mutex); return rc; } @@ -289,6 +315,11 @@ void topology_schedule_update(void) schedule_work(&topology_work); } +static void topology_flush_work(void) +{ + flush_work(&topology_work); +} + static void topology_timer_fn(unsigned long ignored) { if (ptf(PTF_CHECK)) @@ -459,6 +490,12 @@ void __init topology_init_early(void) struct sysinfo_15_1_x *info; set_sched_topology(s390_topology); + if (topology_mode == TOPOLOGY_MODE_UNINITIALIZED) { + if (MACHINE_HAS_TOPOLOGY) + topology_mode = TOPOLOGY_MODE_HW; + else + topology_mode = TOPOLOGY_MODE_SINGLE; + } if (!MACHINE_HAS_TOPOLOGY) goto out; tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE); @@ -474,12 +511,97 @@ out: __arch_update_cpu_topology(); } +static inline int topology_get_mode(int enabled) +{ + if (!enabled) + return TOPOLOGY_MODE_SINGLE; + return MACHINE_HAS_TOPOLOGY ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE; +} + +static inline int topology_is_enabled(void) +{ + return topology_mode != TOPOLOGY_MODE_SINGLE; +} + +static int __init topology_setup(char *str) +{ + bool enabled; + int rc; + + rc = kstrtobool(str, &enabled); + if (rc) + return rc; + topology_mode = topology_get_mode(enabled); + return 0; +} +early_param("topology", topology_setup); + +static int topology_ctl_handler(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int len; + int new_mode; + char buf[2]; + + if (!*lenp || *ppos) { + *lenp = 0; + return 0; + } + if (!write) { + strncpy(buf, topology_is_enabled() ? "1\n" : "0\n", + ARRAY_SIZE(buf)); + len = strnlen(buf, ARRAY_SIZE(buf)); + if (len > *lenp) + len = *lenp; + if (copy_to_user(buffer, buf, len)) + return -EFAULT; + goto out; + } + len = *lenp; + if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) + return -EFAULT; + if (buf[0] != '0' && buf[0] != '1') + return -EINVAL; + mutex_lock(&smp_cpu_state_mutex); + new_mode = topology_get_mode(buf[0] == '1'); + if (topology_mode != new_mode) { + topology_mode = new_mode; + topology_schedule_update(); + } + mutex_unlock(&smp_cpu_state_mutex); + topology_flush_work(); +out: + *lenp = len; + *ppos += len; + return 0; +} + +static struct ctl_table topology_ctl_table[] = { + { + .procname = "topology", + .mode = 0644, + .proc_handler = topology_ctl_handler, + }, + { }, +}; + +static struct ctl_table topology_dir_table[] = { + { + .procname = "s390", + .maxlen = 0, + .mode = 0555, + .child = topology_ctl_table, + }, + { }, +}; + static int __init topology_init(void) { if (MACHINE_HAS_TOPOLOGY) set_topology_timer(); else topology_update_polarization_simple(); + register_sysctl_table(topology_dir_table); return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 8ecc25e760fa..98ffe3ee9411 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -56,13 +56,12 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - unsigned long mask, result; struct page *head, *page; + unsigned long mask; int refs; - result = write ? 0 : _SEGMENT_ENTRY_PROTECT; - mask = result | _SEGMENT_ENTRY_INVALID; - if ((pmd_val(pmd) & mask) != result) + mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID; + if ((pmd_val(pmd) & mask) != 0) return 0; VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT)); diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index 18e0377f72bb..88ce1e22237b 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -136,10 +136,6 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_pc, unsigned lo /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Copy and release all segment info associated with a VM */ -#define copy_segments(p, mm) do { } while(0) -#define release_segments(mm) do { } while(0) - /* * FPU lazy state save handling. */ diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h index eedd4f625d07..777a16318aff 100644 --- a/arch/sh/include/asm/processor_64.h +++ b/arch/sh/include/asm/processor_64.h @@ -170,10 +170,6 @@ struct mm_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Copy and release all segment info associated with a VM */ -#define copy_segments(p, mm) do { } while (0) -#define release_segments(mm) do { } while (0) -#define forget_segments() do { } while (0) /* * FPU lazy state save handling. */ diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig index 0d925fa0f0c1..9f94435cc44f 100644 --- a/arch/tile/configs/tilegx_defconfig +++ b/arch/tile/configs/tilegx_defconfig @@ -409,5 +409,4 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig index 149d8e8eacb8..1c5bd4f8ffca 100644 --- a/arch/tile/configs/tilepro_defconfig +++ b/arch/tile/configs/tilepro_defconfig @@ -189,7 +189,6 @@ CONFIG_IP_NF_MATCH_ECN=m CONFIG_IP_NF_MATCH_TTL=m CONFIG_IP_NF_FILTER=y CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_IP_NF_TARGET_ULOG=m CONFIG_IP_NF_MANGLE=m CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m @@ -521,7 +520,6 @@ CONFIG_CRYPTO_SEED=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_ZLIB=m CONFIG_CRYPTO_LZO=m CONFIG_CRC_CCITT=m CONFIG_CRC7=m diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 6becb96c60a0..ad83c1e66dbd 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -140,7 +140,7 @@ static int __init setup_maxnodemem(char *str) { char *endp; unsigned long long maxnodemem; - long node; + unsigned long node; node = str ? simple_strtoul(str, &endp, 0) : INT_MAX; if (node >= MAX_NUMNODES || *endp != ':') diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index f6d1a3f747a9..86942a492454 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -58,11 +58,6 @@ static inline void release_thread(struct task_struct *task) { } -static inline void mm_copy_segments(struct mm_struct *from_mm, - struct mm_struct *new_mm) -{ -} - #define init_stack (init_thread_union.stack) /* diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 246c67006ed0..8c1fcb6bad21 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -33,7 +33,7 @@ #define s3 ((16 + 2 + (3 * 256)) * 4) /* register macros */ -#define CTX %rdi +#define CTX %r12 #define RIO %rsi #define RX0 %rax @@ -56,12 +56,12 @@ #define RX2bh %ch #define RX3bh %dh -#define RT0 %rbp +#define RT0 %rdi #define RT1 %rsi #define RT2 %r8 #define RT3 %r9 -#define RT0d %ebp +#define RT0d %edi #define RT1d %esi #define RT2d %r8d #define RT3d %r9d @@ -120,13 +120,14 @@ ENTRY(__blowfish_enc_blk) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src * %rcx: bool, if true: xor output */ - movq %rbp, %r11; + movq %r12, %r11; + movq %rdi, CTX; movq %rsi, %r10; movq %rdx, RIO; @@ -142,7 +143,7 @@ ENTRY(__blowfish_enc_blk) round_enc(14); add_roundkey_enc(16); - movq %r11, %rbp; + movq %r11, %r12; movq %r10, RIO; test %cl, %cl; @@ -157,12 +158,13 @@ ENDPROC(__blowfish_enc_blk) ENTRY(blowfish_dec_blk) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ - movq %rbp, %r11; + movq %r12, %r11; + movq %rdi, CTX; movq %rsi, %r10; movq %rdx, RIO; @@ -181,7 +183,7 @@ ENTRY(blowfish_dec_blk) movq %r10, RIO; write_block(); - movq %r11, %rbp; + movq %r11, %r12; ret; ENDPROC(blowfish_dec_blk) @@ -298,20 +300,21 @@ ENDPROC(blowfish_dec_blk) ENTRY(__blowfish_enc_blk_4way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src * %rcx: bool, if true: xor output */ - pushq %rbp; + pushq %r12; pushq %rbx; pushq %rcx; - preload_roundkey_enc(0); - + movq %rdi, CTX movq %rsi, %r11; movq %rdx, RIO; + preload_roundkey_enc(0); + read_block4(); round_enc4(0); @@ -324,39 +327,40 @@ ENTRY(__blowfish_enc_blk_4way) round_enc4(14); add_preloaded_roundkey4(); - popq %rbp; + popq %r12; movq %r11, RIO; - test %bpl, %bpl; + test %r12b, %r12b; jnz .L__enc_xor4; write_block4(); popq %rbx; - popq %rbp; + popq %r12; ret; .L__enc_xor4: xor_block4(); popq %rbx; - popq %rbp; + popq %r12; ret; ENDPROC(__blowfish_enc_blk_4way) ENTRY(blowfish_dec_blk_4way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ - pushq %rbp; + pushq %r12; pushq %rbx; - preload_roundkey_dec(17); - movq %rsi, %r11; + movq %rdi, CTX; + movq %rsi, %r11 movq %rdx, RIO; + preload_roundkey_dec(17); read_block4(); round_dec4(17); @@ -373,7 +377,7 @@ ENTRY(blowfish_dec_blk_4way) write_block4(); popq %rbx; - popq %rbp; + popq %r12; ret; ENDPROC(blowfish_dec_blk_4way) diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S index 310319c601ed..95ba6956a7f6 100644 --- a/arch/x86/crypto/camellia-x86_64-asm_64.S +++ b/arch/x86/crypto/camellia-x86_64-asm_64.S @@ -75,17 +75,17 @@ #define RCD1bh %dh #define RT0 %rsi -#define RT1 %rbp +#define RT1 %r12 #define RT2 %r8 #define RT0d %esi -#define RT1d %ebp +#define RT1d %r12d #define RT2d %r8d #define RT2bl %r8b #define RXOR %r9 -#define RRBP %r10 +#define RR12 %r10 #define RDST %r11 #define RXORd %r9d @@ -197,7 +197,7 @@ ENTRY(__camellia_enc_blk) * %rdx: src * %rcx: bool xor */ - movq %rbp, RRBP; + movq %r12, RR12; movq %rcx, RXOR; movq %rsi, RDST; @@ -227,13 +227,13 @@ ENTRY(__camellia_enc_blk) enc_outunpack(mov, RT1); - movq RRBP, %rbp; + movq RR12, %r12; ret; .L__enc_xor: enc_outunpack(xor, RT1); - movq RRBP, %rbp; + movq RR12, %r12; ret; ENDPROC(__camellia_enc_blk) @@ -248,7 +248,7 @@ ENTRY(camellia_dec_blk) movl $24, RXORd; cmovel RXORd, RT2d; /* max */ - movq %rbp, RRBP; + movq %r12, RR12; movq %rsi, RDST; movq %rdx, RIO; @@ -271,7 +271,7 @@ ENTRY(camellia_dec_blk) dec_outunpack(); - movq RRBP, %rbp; + movq RR12, %r12; ret; ENDPROC(camellia_dec_blk) @@ -433,7 +433,7 @@ ENTRY(__camellia_enc_blk_2way) */ pushq %rbx; - movq %rbp, RRBP; + movq %r12, RR12; movq %rcx, RXOR; movq %rsi, RDST; movq %rdx, RIO; @@ -461,14 +461,14 @@ ENTRY(__camellia_enc_blk_2way) enc_outunpack2(mov, RT2); - movq RRBP, %rbp; + movq RR12, %r12; popq %rbx; ret; .L__enc2_xor: enc_outunpack2(xor, RT2); - movq RRBP, %rbp; + movq RR12, %r12; popq %rbx; ret; ENDPROC(__camellia_enc_blk_2way) @@ -485,7 +485,7 @@ ENTRY(camellia_dec_blk_2way) cmovel RXORd, RT2d; /* max */ movq %rbx, RXOR; - movq %rbp, RRBP; + movq %r12, RR12; movq %rsi, RDST; movq %rdx, RIO; @@ -508,7 +508,7 @@ ENTRY(camellia_dec_blk_2way) dec_outunpack2(); - movq RRBP, %rbp; + movq RR12, %r12; movq RXOR, %rbx; ret; ENDPROC(camellia_dec_blk_2way) diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index b4a8806234ea..86107c961bb4 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -47,7 +47,7 @@ /********************************************************************** 16-way AVX cast5 **********************************************************************/ -#define CTX %rdi +#define CTX %r15 #define RL1 %xmm0 #define RR1 %xmm1 @@ -70,8 +70,8 @@ #define RTMP %xmm15 -#define RID1 %rbp -#define RID1d %ebp +#define RID1 %rdi +#define RID1d %edi #define RID2 %rsi #define RID2d %esi @@ -226,7 +226,7 @@ .align 16 __cast5_enc_blk16: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RL1: blocks 1 and 2 * RR1: blocks 3 and 4 * RL2: blocks 5 and 6 @@ -246,9 +246,11 @@ __cast5_enc_blk16: * RR4: encrypted blocks 15 and 16 */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -283,7 +285,7 @@ __cast5_enc_blk16: .L__skip_enc: popq %rbx; - popq %rbp; + popq %r15; vmovdqa .Lbswap_mask, RKM; @@ -298,7 +300,7 @@ ENDPROC(__cast5_enc_blk16) .align 16 __cast5_dec_blk16: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RL1: encrypted blocks 1 and 2 * RR1: encrypted blocks 3 and 4 * RL2: encrypted blocks 5 and 6 @@ -318,9 +320,11 @@ __cast5_dec_blk16: * RR4: decrypted blocks 15 and 16 */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -356,7 +360,7 @@ __cast5_dec_blk16: vmovdqa .Lbswap_mask, RKM; popq %rbx; - popq %rbp; + popq %r15; outunpack_blocks(RR1, RL1, RTMP, RX, RKM); outunpack_blocks(RR2, RL2, RTMP, RX, RKM); @@ -372,12 +376,14 @@ ENDPROC(__cast5_dec_blk16) ENTRY(cast5_ecb_enc_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; vmovdqu (0*4*4)(%rdx), RL1; @@ -400,18 +406,22 @@ ENTRY(cast5_ecb_enc_16way) vmovdqu RR4, (6*4*4)(%r11); vmovdqu RL4, (7*4*4)(%r11); + popq %r15; FRAME_END ret; ENDPROC(cast5_ecb_enc_16way) ENTRY(cast5_ecb_dec_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + + movq %rdi, CTX; movq %rsi, %r11; vmovdqu (0*4*4)(%rdx), RL1; @@ -434,20 +444,22 @@ ENTRY(cast5_ecb_dec_16way) vmovdqu RR4, (6*4*4)(%r11); vmovdqu RL4, (7*4*4)(%r11); + popq %r15; FRAME_END ret; ENDPROC(cast5_ecb_dec_16way) ENTRY(cast5_cbc_dec_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN - pushq %r12; + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -483,23 +495,24 @@ ENTRY(cast5_cbc_dec_16way) vmovdqu RR4, (6*16)(%r11); vmovdqu RL4, (7*16)(%r11); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast5_cbc_dec_16way) ENTRY(cast5_ctr_16way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src * %rcx: iv (big endian, 64bit) */ FRAME_BEGIN - pushq %r12; + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -558,8 +571,8 @@ ENTRY(cast5_ctr_16way) vmovdqu RR4, (6*16)(%r11); vmovdqu RL4, (7*16)(%r11); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast5_ctr_16way) diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index 952d3156a933..7f30b6f0d72c 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -47,7 +47,7 @@ /********************************************************************** 8-way AVX cast6 **********************************************************************/ -#define CTX %rdi +#define CTX %r15 #define RA1 %xmm0 #define RB1 %xmm1 @@ -70,8 +70,8 @@ #define RTMP %xmm15 -#define RID1 %rbp -#define RID1d %ebp +#define RID1 %rdi +#define RID1d %edi #define RID2 %rsi #define RID2d %esi @@ -264,15 +264,17 @@ .align 8 __cast6_enc_blk8: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks * output: * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -297,7 +299,7 @@ __cast6_enc_blk8: QBAR(11); popq %rbx; - popq %rbp; + popq %r15; vmovdqa .Lbswap_mask, RKM; @@ -310,15 +312,17 @@ ENDPROC(__cast6_enc_blk8) .align 8 __cast6_dec_blk8: /* input: - * %rdi: ctx, CTX + * %rdi: ctx * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks * output: * RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks */ - pushq %rbp; + pushq %r15; pushq %rbx; + movq %rdi, CTX; + vmovdqa .Lbswap_mask, RKM; vmovd .Lfirst_mask, R1ST; vmovd .L32_mask, R32; @@ -343,7 +347,7 @@ __cast6_dec_blk8: QBAR(0); popq %rbx; - popq %rbp; + popq %r15; vmovdqa .Lbswap_mask, RKM; outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM); @@ -354,12 +358,14 @@ ENDPROC(__cast6_dec_blk8) ENTRY(cast6_ecb_enc_8way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); @@ -368,18 +374,21 @@ ENTRY(cast6_ecb_enc_8way) store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_ecb_enc_8way) ENTRY(cast6_ecb_dec_8way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); @@ -388,20 +397,22 @@ ENTRY(cast6_ecb_dec_8way) store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_ecb_dec_8way) ENTRY(cast6_cbc_dec_8way) /* input: - * %rdi: ctx, CTX + * %rdi: ctx * %rsi: dst * %rdx: src */ FRAME_BEGIN - pushq %r12; + pushq %r15; + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -411,8 +422,8 @@ ENTRY(cast6_cbc_dec_8way) store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast6_cbc_dec_8way) @@ -425,9 +436,10 @@ ENTRY(cast6_ctr_8way) * %rcx: iv (little endian, 128bit) */ FRAME_BEGIN - pushq %r12; + pushq %r15 + movq %rdi, CTX; movq %rsi, %r11; movq %rdx, %r12; @@ -438,8 +450,8 @@ ENTRY(cast6_ctr_8way) store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; popq %r12; - FRAME_END ret; ENDPROC(cast6_ctr_8way) @@ -452,7 +464,9 @@ ENTRY(cast6_xts_enc_8way) * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX movq %rsi, %r11; /* regs <= src, dst <= IVs, regs <= regs xor IVs */ @@ -464,6 +478,7 @@ ENTRY(cast6_xts_enc_8way) /* dst <= regs xor IVs(in dst) */ store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_xts_enc_8way) @@ -476,7 +491,9 @@ ENTRY(cast6_xts_dec_8way) * %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸)) */ FRAME_BEGIN + pushq %r15; + movq %rdi, CTX movq %rsi, %r11; /* regs <= src, dst <= IVs, regs <= regs xor IVs */ @@ -488,6 +505,7 @@ ENTRY(cast6_xts_dec_8way) /* dst <= regs xor IVs(in dst) */ store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2); + popq %r15; FRAME_END ret; ENDPROC(cast6_xts_dec_8way) diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S index f3e91647ca27..8e49ce117494 100644 --- a/arch/x86/crypto/des3_ede-asm_64.S +++ b/arch/x86/crypto/des3_ede-asm_64.S @@ -64,12 +64,12 @@ #define RW2bh %ch #define RT0 %r15 -#define RT1 %rbp +#define RT1 %rsi #define RT2 %r14 #define RT3 %rdx #define RT0d %r15d -#define RT1d %ebp +#define RT1d %esi #define RT2d %r14d #define RT3d %edx @@ -177,13 +177,14 @@ ENTRY(des3_ede_x86_64_crypt_blk) * %rsi: dst * %rdx: src */ - pushq %rbp; pushq %rbx; pushq %r12; pushq %r13; pushq %r14; pushq %r15; + pushq %rsi; /* dst */ + read_block(%rdx, RL0, RR0); initial_permutation(RL0, RR0); @@ -241,6 +242,8 @@ ENTRY(des3_ede_x86_64_crypt_blk) round1(32+15, RL0, RR0, dummy2); final_permutation(RR0, RL0); + + popq %rsi /* dst */ write_block(%rsi, RR0, RL0); popq %r15; @@ -248,7 +251,6 @@ ENTRY(des3_ede_x86_64_crypt_blk) popq %r13; popq %r12; popq %rbx; - popq %rbp; ret; ENDPROC(des3_ede_x86_64_crypt_blk) @@ -432,13 +434,14 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) * %rdx: src (3 blocks) */ - pushq %rbp; pushq %rbx; pushq %r12; pushq %r13; pushq %r14; pushq %r15; + pushq %rsi /* dst */ + /* load input */ movl 0 * 4(%rdx), RL0d; movl 1 * 4(%rdx), RR0d; @@ -520,6 +523,7 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) bswapl RR2d; bswapl RL2d; + popq %rsi /* dst */ movl RR0d, 0 * 4(%rsi); movl RL0d, 1 * 4(%rsi); movl RR1d, 2 * 4(%rsi); @@ -532,7 +536,6 @@ ENTRY(des3_ede_x86_64_crypt_blk_3way) popq %r13; popq %r12; popq %rbx; - popq %rbp; ret; ENDPROC(des3_ede_x86_64_crypt_blk_3way) diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1eab79c9ac48..9f712a7dfd79 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -89,7 +89,7 @@ #define REG_RE %rdx #define REG_RTA %r12 #define REG_RTB %rbx -#define REG_T1 %ebp +#define REG_T1 %r11d #define xmm_mov vmovups #define avx2_zeroupper vzeroupper #define RND_F1 1 @@ -637,7 +637,6 @@ _loop3: ENTRY(\name) push %rbx - push %rbp push %r12 push %r13 push %r14 @@ -673,7 +672,6 @@ _loop3: pop %r14 pop %r13 pop %r12 - pop %rbp pop %rbx ret diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index a4109506a5e8..6204bd53528c 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -37,7 +37,7 @@ #define REG_A %ecx #define REG_B %esi #define REG_C %edi -#define REG_D %ebp +#define REG_D %r12d #define REG_E %edx #define REG_T1 %eax @@ -74,10 +74,10 @@ ENTRY(\name) push %rbx - push %rbp push %r12 + push %rbp + mov %rsp, %rbp - mov %rsp, %r12 sub $64, %rsp # allocate workspace and $~15, %rsp # align stack @@ -99,10 +99,9 @@ xor %rax, %rax rep stosq - mov %r12, %rsp # deallocate workspace - - pop %r12 + mov %rbp, %rsp # deallocate workspace pop %rbp + pop %r12 pop %rbx ret diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index e08888a1a5f2..001bbcf93c79 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -103,7 +103,7 @@ SRND = %rsi # clobbers INP c = %ecx d = %r8d e = %edx -TBL = %rbp +TBL = %r12 a = %eax b = %ebx @@ -350,13 +350,13 @@ a = TMP_ ENTRY(sha256_transform_avx) .align 32 pushq %rbx - pushq %rbp + pushq %r12 pushq %r13 pushq %r14 pushq %r15 - pushq %r12 + pushq %rbp + movq %rsp, %rbp - mov %rsp, %r12 subq $STACK_SIZE, %rsp # allocate stack space and $~15, %rsp # align stack pointer @@ -452,13 +452,12 @@ loop2: done_hash: - mov %r12, %rsp - - popq %r12 + mov %rbp, %rsp + popq %rbp popq %r15 popq %r14 popq %r13 - popq %rbp + popq %r12 popq %rbx ret ENDPROC(sha256_transform_avx) diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 89c8f09787d2..1420db15dcdd 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -98,8 +98,6 @@ d = %r8d e = %edx # clobbers NUM_BLKS y3 = %esi # clobbers INP - -TBL = %rbp SRND = CTX # SRND is same register as CTX a = %eax @@ -531,7 +529,6 @@ STACK_SIZE = _RSP + _RSP_SIZE ENTRY(sha256_transform_rorx) .align 32 pushq %rbx - pushq %rbp pushq %r12 pushq %r13 pushq %r14 @@ -568,8 +565,6 @@ ENTRY(sha256_transform_rorx) mov CTX, _CTX(%rsp) loop0: - lea K256(%rip), TBL - ## Load first 16 dwords from two blocks VMOVDQ 0*32(INP),XTMP0 VMOVDQ 1*32(INP),XTMP1 @@ -597,19 +592,19 @@ last_block_enter: .align 16 loop1: - vpaddd 0*32(TBL, SRND), X0, XFER + vpaddd K256+0*32(SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 0*32 - vpaddd 1*32(TBL, SRND), X0, XFER + vpaddd K256+1*32(SRND), X0, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 1*32 - vpaddd 2*32(TBL, SRND), X0, XFER + vpaddd K256+2*32(SRND), X0, XFER vmovdqa XFER, 2*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 2*32 - vpaddd 3*32(TBL, SRND), X0, XFER + vpaddd K256+3*32(SRND), X0, XFER vmovdqa XFER, 3*32+_XFER(%rsp, SRND) FOUR_ROUNDS_AND_SCHED _XFER + 3*32 @@ -619,10 +614,11 @@ loop1: loop2: ## Do last 16 rounds with no scheduling - vpaddd 0*32(TBL, SRND), X0, XFER + vpaddd K256+0*32(SRND), X0, XFER vmovdqa XFER, 0*32+_XFER(%rsp, SRND) DO_4ROUNDS _XFER + 0*32 - vpaddd 1*32(TBL, SRND), X1, XFER + + vpaddd K256+1*32(SRND), X1, XFER vmovdqa XFER, 1*32+_XFER(%rsp, SRND) DO_4ROUNDS _XFER + 1*32 add $2*32, SRND @@ -676,9 +672,6 @@ loop3: ja done_hash do_last_block: - #### do last block - lea K256(%rip), TBL - VMOVDQ 0*16(INP),XWORD0 VMOVDQ 1*16(INP),XWORD1 VMOVDQ 2*16(INP),XWORD2 @@ -718,7 +711,6 @@ done_hash: popq %r14 popq %r13 popq %r12 - popq %rbp popq %rbx ret ENDPROC(sha256_transform_rorx) diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index 39b83c93e7fd..c6c05ed2c16a 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -95,7 +95,7 @@ SRND = %rsi # clobbers INP c = %ecx d = %r8d e = %edx -TBL = %rbp +TBL = %r12 a = %eax b = %ebx @@ -356,13 +356,13 @@ a = TMP_ ENTRY(sha256_transform_ssse3) .align 32 pushq %rbx - pushq %rbp + pushq %r12 pushq %r13 pushq %r14 pushq %r15 - pushq %r12 + pushq %rbp + mov %rsp, %rbp - mov %rsp, %r12 subq $STACK_SIZE, %rsp and $~15, %rsp @@ -462,13 +462,12 @@ loop2: done_hash: - mov %r12, %rsp - - popq %r12 + mov %rbp, %rsp + popq %rbp popq %r15 popq %r14 popq %r13 - popq %rbp + popq %r12 popq %rbx ret diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 7f5f6c6ec72e..b16d56005162 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -69,8 +69,9 @@ XFER = YTMP0 BYTE_FLIP_MASK = %ymm9 -# 1st arg -CTX = %rdi +# 1st arg is %rdi, which is saved to the stack and accessed later via %r12 +CTX1 = %rdi +CTX2 = %r12 # 2nd arg INP = %rsi # 3rd arg @@ -81,7 +82,7 @@ d = %r8 e = %rdx y3 = %rsi -TBL = %rbp +TBL = %rdi # clobbers CTX1 a = %rax b = %rbx @@ -91,26 +92,26 @@ g = %r10 h = %r11 old_h = %r11 -T1 = %r12 +T1 = %r12 # clobbers CTX2 y0 = %r13 y1 = %r14 y2 = %r15 -y4 = %r12 - # Local variables (stack frame) XFER_SIZE = 4*8 SRND_SIZE = 1*8 INP_SIZE = 1*8 INPEND_SIZE = 1*8 +CTX_SIZE = 1*8 RSPSAVE_SIZE = 1*8 -GPRSAVE_SIZE = 6*8 +GPRSAVE_SIZE = 5*8 frame_XFER = 0 frame_SRND = frame_XFER + XFER_SIZE frame_INP = frame_SRND + SRND_SIZE frame_INPEND = frame_INP + INP_SIZE -frame_RSPSAVE = frame_INPEND + INPEND_SIZE +frame_CTX = frame_INPEND + INPEND_SIZE +frame_RSPSAVE = frame_CTX + CTX_SIZE frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE frame_size = frame_GPRSAVE + GPRSAVE_SIZE @@ -576,12 +577,11 @@ ENTRY(sha512_transform_rorx) mov %rax, frame_RSPSAVE(%rsp) # Save GPRs - mov %rbp, frame_GPRSAVE(%rsp) - mov %rbx, 8*1+frame_GPRSAVE(%rsp) - mov %r12, 8*2+frame_GPRSAVE(%rsp) - mov %r13, 8*3+frame_GPRSAVE(%rsp) - mov %r14, 8*4+frame_GPRSAVE(%rsp) - mov %r15, 8*5+frame_GPRSAVE(%rsp) + mov %rbx, 8*0+frame_GPRSAVE(%rsp) + mov %r12, 8*1+frame_GPRSAVE(%rsp) + mov %r13, 8*2+frame_GPRSAVE(%rsp) + mov %r14, 8*3+frame_GPRSAVE(%rsp) + mov %r15, 8*4+frame_GPRSAVE(%rsp) shl $7, NUM_BLKS # convert to bytes jz done_hash @@ -589,14 +589,17 @@ ENTRY(sha512_transform_rorx) mov NUM_BLKS, frame_INPEND(%rsp) ## load initial digest - mov 8*0(CTX),a - mov 8*1(CTX),b - mov 8*2(CTX),c - mov 8*3(CTX),d - mov 8*4(CTX),e - mov 8*5(CTX),f - mov 8*6(CTX),g - mov 8*7(CTX),h + mov 8*0(CTX1), a + mov 8*1(CTX1), b + mov 8*2(CTX1), c + mov 8*3(CTX1), d + mov 8*4(CTX1), e + mov 8*5(CTX1), f + mov 8*6(CTX1), g + mov 8*7(CTX1), h + + # save %rdi (CTX) before it gets clobbered + mov %rdi, frame_CTX(%rsp) vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK @@ -652,14 +655,15 @@ loop2: subq $1, frame_SRND(%rsp) jne loop2 - addm 8*0(CTX),a - addm 8*1(CTX),b - addm 8*2(CTX),c - addm 8*3(CTX),d - addm 8*4(CTX),e - addm 8*5(CTX),f - addm 8*6(CTX),g - addm 8*7(CTX),h + mov frame_CTX(%rsp), CTX2 + addm 8*0(CTX2), a + addm 8*1(CTX2), b + addm 8*2(CTX2), c + addm 8*3(CTX2), d + addm 8*4(CTX2), e + addm 8*5(CTX2), f + addm 8*6(CTX2), g + addm 8*7(CTX2), h mov frame_INP(%rsp), INP add $128, INP @@ -669,12 +673,11 @@ loop2: done_hash: # Restore GPRs - mov frame_GPRSAVE(%rsp) ,%rbp - mov 8*1+frame_GPRSAVE(%rsp) ,%rbx - mov 8*2+frame_GPRSAVE(%rsp) ,%r12 - mov 8*3+frame_GPRSAVE(%rsp) ,%r13 - mov 8*4+frame_GPRSAVE(%rsp) ,%r14 - mov 8*5+frame_GPRSAVE(%rsp) ,%r15 + mov 8*0+frame_GPRSAVE(%rsp), %rbx + mov 8*1+frame_GPRSAVE(%rsp), %r12 + mov 8*2+frame_GPRSAVE(%rsp), %r13 + mov 8*3+frame_GPRSAVE(%rsp), %r14 + mov 8*4+frame_GPRSAVE(%rsp), %r15 # Restore Stack Pointer mov frame_RSPSAVE(%rsp), %rsp diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index b3f49d286348..73b471da3622 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -76,8 +76,8 @@ #define RT %xmm14 #define RR %xmm15 -#define RID1 %rbp -#define RID1d %ebp +#define RID1 %r13 +#define RID1d %r13d #define RID2 %rsi #define RID2d %esi @@ -259,7 +259,7 @@ __twofish_enc_blk8: vmovdqu w(CTX), RK1; - pushq %rbp; + pushq %r13; pushq %rbx; pushq %rcx; @@ -282,7 +282,7 @@ __twofish_enc_blk8: popq %rcx; popq %rbx; - popq %rbp; + popq %r13; outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2); outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2); @@ -301,7 +301,7 @@ __twofish_dec_blk8: vmovdqu (w+4*4)(CTX), RK1; - pushq %rbp; + pushq %r13; pushq %rbx; inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2); @@ -322,7 +322,7 @@ __twofish_dec_blk8: vmovdqu (w)(CTX), RK1; popq %rbx; - popq %rbp; + popq %r13; outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2); outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9862e2cd6d93..d58184b7cd44 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -763,6 +763,16 @@ static void init_amd_bd(struct cpuinfo_x86 *c) } } +static void init_amd_zn(struct cpuinfo_x86 *c) +{ + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects + * all up to and including B1. + */ + if (c->x86_model <= 1 && c->x86_mask <= 1) + set_cpu_cap(c, X86_FEATURE_CPB); +} + static void init_amd(struct cpuinfo_x86 *c) { early_init_amd(c); @@ -791,6 +801,7 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x10: init_amd_gh(c); break; case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; + case 0x17: init_amd_zn(c); break; } /* Enable workaround for FXSAVE leak */ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 16bf6655aa85..15f527b44aa7 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4102,10 +4102,12 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) { u64 maxphyaddr; - u32 eax = 0x80000008; + u32 eax, ebx, ecx, edx; - if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL, - NULL, false)) + eax = 0x80000008; + ecx = 0; + if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, + &edx, false)) maxphyaddr = eax & 0xff; else maxphyaddr = 36; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 06c0c6d0541e..0726ca7a1b02 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5077,21 +5077,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu, int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR; if (vcpu->mode == IN_GUEST_MODE) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * Currently, we don't support urgent interrupt, - * all interrupts are recognized as non-urgent - * interrupt, so we cannot post interrupts when - * 'SN' is set. + * The vector of interrupt to be delivered to vcpu had + * been set in PIR before this function. + * + * Following cases will be reached in this block, and + * we always send a notification event in all cases as + * explained below. + * + * Case 1: vcpu keeps in non-root mode. Sending a + * notification event posts the interrupt to vcpu. * - * If the vcpu is in guest mode, it means it is - * running instead of being scheduled out and - * waiting in the run queue, and that's the only - * case when 'SN' is set currently, warning if - * 'SN' is set. + * Case 2: vcpu exits to root mode and is still + * runnable. PIR will be synced to vIRR before the + * next vcpu entry. Sending a notification event in + * this case has no effect, as vcpu is not in root + * mode. + * + * Case 3: vcpu exits to root mode and is blocked. + * vcpu_block() has already synced PIR to vIRR and + * never blocks vcpu if vIRR is not cleared. Therefore, + * a blocked vcpu here does not wait for any requested + * interrupts in PIR, and sending a notification event + * which has no effect is safe here. */ - WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec); return true; @@ -11911,12 +11920,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, if (set) ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else { - /* suppress notification event before unposting */ - pi_set_sn(vcpu_to_pi_desc(vcpu)); + else ret = irq_set_vcpu_affinity(host_irq, NULL); - pi_clear_sn(vcpu_to_pi_desc(vcpu)); - } if (ret < 0) { printk(KERN_INFO "%s: failed to update PI IRTE\n", diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 509f560bd0c6..7330cb3b2283 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2220,7 +2220,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) * not the first page table in the page table pool. * Iterate through the initial page tables to find the real page table base. */ -static phys_addr_t xen_find_pt_base(pmd_t *pmd) +static phys_addr_t __init xen_find_pt_base(pmd_t *pmd) { phys_addr_t pt_base, paddr; unsigned pmdidx; diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 30ee8c608853..5b0027d4ecc0 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -208,11 +208,6 @@ struct mm_struct; /* Free all resources held by a thread. */ #define release_thread(thread) do { } while(0) -/* Copy and release all segment info associated with a VM */ -#define copy_segments(p, mm) do { } while(0) -#define release_segments(mm) do { } while(0) -#define forget_segments() do { } while (0) - extern unsigned long get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) |