diff options
Diffstat (limited to 'arch/s390/kernel')
| -rw-r--r-- | arch/s390/kernel/Makefile | 5 | ||||
| -rw-r--r-- | arch/s390/kernel/asm-offsets.c | 2 | ||||
| -rw-r--r-- | arch/s390/kernel/debug.c | 2 | ||||
| -rw-r--r-- | arch/s390/kernel/diag.c | 2 | ||||
| -rw-r--r-- | arch/s390/kernel/dumpstack.c | 13 | ||||
| -rw-r--r-- | arch/s390/kernel/entry.S | 464 | ||||
| -rw-r--r-- | arch/s390/kernel/ftrace.c | 16 | ||||
| -rw-r--r-- | arch/s390/kernel/idle.c | 14 | ||||
| -rw-r--r-- | arch/s390/kernel/ipl.c | 209 | ||||
| -rw-r--r-- | arch/s390/kernel/machine_kexec.c | 1 | ||||
| -rw-r--r-- | arch/s390/kernel/machine_kexec_file.c | 2 | ||||
| -rw-r--r-- | arch/s390/kernel/machine_kexec_reloc.c | 1 | ||||
| -rw-r--r-- | arch/s390/kernel/module.c | 147 | ||||
| -rw-r--r-- | arch/s390/kernel/nmi.c | 23 | ||||
| -rw-r--r-- | arch/s390/kernel/ptrace.c | 3 | ||||
| -rw-r--r-- | arch/s390/kernel/setup.c | 25 | ||||
| -rw-r--r-- | arch/s390/kernel/smp.c | 12 | ||||
| -rw-r--r-- | arch/s390/kernel/syscalls/syscall.tbl | 1 | ||||
| -rw-r--r-- | arch/s390/kernel/topology.c | 2 | ||||
| -rw-r--r-- | arch/s390/kernel/trace.c | 2 | ||||
| -rw-r--r-- | arch/s390/kernel/uv.c | 7 | ||||
| -rw-r--r-- | arch/s390/kernel/vdso.c | 5 |
22 files changed, 468 insertions, 490 deletions
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 75f26d775027..a8f136943deb 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -33,11 +33,6 @@ CFLAGS_stacktrace.o += -fno-optimize-sibling-calls CFLAGS_dumpstack.o += -fno-optimize-sibling-calls CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls -# -# Pass UTS_MACHINE for user_regset definition -# -CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' - obj-y := traps.o time.o process.o base.o early.o setup.o idle.o vtime.o obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index e80f0e6f5972..165031bd3370 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -11,9 +11,9 @@ #include <linux/kvm_host.h> #include <linux/sched.h> #include <linux/purgatory.h> +#include <linux/pgtable.h> #include <asm/idle.h> #include <asm/vdso.h> -#include <asm/pgtable.h> #include <asm/gmap.h> #include <asm/nmi.h> #include <asm/stacktrace.h> diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 6d321f5f101d..636446003a06 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -867,7 +867,7 @@ static int debug_active = 1; * if debug_active is already off */ static int s390dbf_procactive(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { if (!write || debug_stoppable || !debug_active) return proc_dointvec(table, write, buffer, lenp, ppos); diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index 61f2b0412345..ccba63aaeb47 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -133,7 +133,7 @@ void diag_stat_inc(enum diag_stat_enum nr) } EXPORT_SYMBOL(diag_stat_inc); -void diag_stat_inc_norecursion(enum diag_stat_enum nr) +void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr) { this_cpu_inc(diag_stat.counter[nr]); trace_s390_diagnose_norecursion(diag_map[nr].code); diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 2c122d8bab93..0dc4b258b98d 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -126,15 +126,16 @@ unknown: return -EINVAL; } -void show_stack(struct task_struct *task, unsigned long *stack) +void show_stack(struct task_struct *task, unsigned long *stack, + const char *loglvl) { struct unwind_state state; - printk("Call Trace:\n"); + printk("%sCall Trace:\n", loglvl); unwind_for_each_frame(&state, task, NULL, (unsigned long) stack) - printk(state.reliable ? " [<%016lx>] %pSR \n" : - "([<%016lx>] %pSR)\n", - state.ip, (void *) state.ip); + printk(state.reliable ? "%s [<%016lx>] %pSR \n" : + "%s([<%016lx>] %pSR)\n", + loglvl, state.ip, (void *) state.ip); debug_show_held_locks(task ? : current); } @@ -175,7 +176,7 @@ void show_regs(struct pt_regs *regs) show_registers(regs); /* Show stack backtrace if pt_regs is from kernel mode */ if (!user_mode(regs)) - show_stack(NULL, (unsigned long *) regs->gprs[15]); + show_stack(NULL, (unsigned long *) regs->gprs[15], KERN_DEFAULT); show_last_breaking_event(regs); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 3ae64914bd14..50ff6dd0f995 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -55,14 +55,11 @@ _TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \ _TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING) _TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \ _TIF_SYSCALL_TRACEPOINT) -_CIF_WORK = (_CIF_MCCK_PENDING | _CIF_ASCE_PRIMARY | \ - _CIF_ASCE_SECONDARY | _CIF_FPU) +_CIF_WORK = (_CIF_ASCE_PRIMARY | _CIF_ASCE_SECONDARY | _CIF_FPU) _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) _LPP_OFFSET = __LC_LPP -#define BASED(name) name-cleanup_critical(%r13) - .macro TRACE_IRQS_ON #ifdef CONFIG_TRACE_IRQFLAGS basr %r2,%r0 @@ -116,17 +113,39 @@ _LPP_OFFSET = __LC_LPP .macro SWITCH_ASYNC savearea,timer tmhh %r8,0x0001 # interrupting from user ? jnz 2f +#if IS_ENABLED(CONFIG_KVM) lgr %r14,%r9 - cghi %r14,__LC_RETURN_LPSWE - je 0f - slg %r14,BASED(.Lcritical_start) - clg %r14,BASED(.Lcritical_length) - jhe 1f -0: + larl %r13,.Lsie_gmap + slgr %r14,%r13 + lghi %r13,.Lsie_done - .Lsie_gmap + clgr %r14,%r13 + jhe 0f lghi %r11,\savearea # inside critical section, do cleanup - brasl %r14,cleanup_critical - tmhh %r8,0x0001 # retest problem state after cleanup - jnz 2f + brasl %r14,.Lcleanup_sie +#endif +0: larl %r13,.Lpsw_idle_exit + cgr %r13,%r9 + jne 1f + + mvc __CLOCK_IDLE_EXIT(8,%r2), __LC_INT_CLOCK + mvc __TIMER_IDLE_EXIT(8,%r2), __LC_ASYNC_ENTER_TIMER + # account system time going idle + ni __LC_CPU_FLAGS+7,255-_CIF_ENABLED_WAIT + + lg %r13,__LC_STEAL_TIMER + alg %r13,__CLOCK_IDLE_ENTER(%r2) + slg %r13,__LC_LAST_UPDATE_CLOCK + stg %r13,__LC_STEAL_TIMER + + mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2) + + lg %r13,__LC_SYSTEM_TIMER + alg %r13,__LC_LAST_UPDATE_TIMER + slg %r13,__TIMER_IDLE_ENTER(%r2) + stg %r13,__LC_SYSTEM_TIMER + mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) + + nihh %r8,0xfcfd # clear wait state and irq bits 1: lg %r14,__LC_ASYNC_STACK # are we already on the target stack? slgr %r14,%r15 srag %r14,%r14,STACK_SHIFT @@ -152,12 +171,30 @@ _LPP_OFFSET = __LC_LPP mvc __LC_LAST_UPDATE_TIMER(8),\enter_timer .endm - .macro REENABLE_IRQS + .macro RESTORE_SM_CLEAR_PER stg %r8,__LC_RETURN_PSW ni __LC_RETURN_PSW,0xbf ssm __LC_RETURN_PSW .endm + .macro ENABLE_INTS + stosm __SF_EMPTY(%r15),3 + .endm + + .macro ENABLE_INTS_TRACE + TRACE_IRQS_ON + ENABLE_INTS + .endm + + .macro DISABLE_INTS + stnsm __SF_EMPTY(%r15),0xfc + .endm + + .macro DISABLE_INTS_TRACE + DISABLE_INTS + TRACE_IRQS_OFF + .endm + .macro STCK savearea #ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES .insn s,0xb27c0000,\savearea # store clock fast @@ -254,8 +291,6 @@ ENTRY(__switch_to) BR_EX %r14 ENDPROC(__switch_to) -.L__critical_start: - #if IS_ENABLED(CONFIG_KVM) /* * sie64a calling convention: @@ -288,7 +323,6 @@ ENTRY(sie64a) BPEXIT __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) .Lsie_entry: sie 0(%r14) -.Lsie_exit: BPOFF BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) .Lsie_skip: @@ -341,7 +375,6 @@ EXPORT_SYMBOL(sie_exit) ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER -.Lsysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC BPOFF lg %r12,__LC_CURRENT @@ -350,7 +383,6 @@ ENTRY(system_call) .Lsysc_per: lg %r15,__LC_KERNEL_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs -.Lsysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP stmg %r0,%r7,__PT_R0(%r11) @@ -358,6 +390,7 @@ ENTRY(system_call) mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) + ENABLE_INTS .Lsysc_do_svc: # clear user controlled register to prevent speculative use xgr %r0,%r0 @@ -393,26 +426,26 @@ ENTRY(system_call) jnz .Lsysc_work TSTMSK __TI_flags(%r12),_TIF_WORK jnz .Lsysc_work # check for work - TSTMSK __LC_CPU_FLAGS,_CIF_WORK + TSTMSK __LC_CPU_FLAGS,(_CIF_WORK-_CIF_FPU) jnz .Lsysc_work BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP .Lsysc_restore: + DISABLE_INTS + TSTMSK __LC_CPU_FLAGS, _CIF_FPU + jz .Lsysc_skip_fpu + brasl %r14,load_fpu_regs +.Lsysc_skip_fpu: lg %r14,__LC_VDSO_PER_CPU - lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) -.Lsysc_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER - lmg %r11,%r15,__PT_R11(%r11) - b __LC_RETURN_LPSWE(%r0) -.Lsysc_done: + lmg %r0,%r15,__PT_R0(%r11) + b __LC_RETURN_LPSWE # # One of the work bits is on. Find out which one. # .Lsysc_work: - TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING - jo .Lsysc_mcck_pending TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lsysc_reschedule TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL_RESTART @@ -436,11 +469,9 @@ ENTRY(system_call) jo .Lsysc_sigpending TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME jo .Lsysc_notify_resume - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - jo .Lsysc_vxrs TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY) jnz .Lsysc_asce - j .Lsysc_return # beware of critical section cleanup + j .Lsysc_return # # _TIF_NEED_RESCHED is set, call schedule @@ -450,13 +481,6 @@ ENTRY(system_call) jg schedule # -# _CIF_MCCK_PENDING is set, call handler -# -.Lsysc_mcck_pending: - larl %r14,.Lsysc_return - jg s390_handle_mcck # TIF bit will be cleared by handler - -# # _CIF_ASCE_PRIMARY and/or _CIF_ASCE_SECONDARY set, load user space asce # .Lsysc_asce: @@ -475,12 +499,6 @@ ENTRY(system_call) larl %r14,.Lsysc_return jg set_fs_fixup -# -# CIF_FPU is set, restore floating-point controls and floating-point registers. -# -.Lsysc_vxrs: - larl %r14,.Lsysc_return - jg load_fpu_regs # # _TIF_SIGPENDING is set, call do_signal @@ -564,7 +582,6 @@ ENTRY(system_call) jnh .Lsysc_tracenogo sllg %r8,%r2,3 lg %r9,0(%r8,%r10) -.Lsysc_tracego: lmg %r3,%r7,__PT_R3(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lg %r2,__PT_ORIG_GPR2(%r11) @@ -585,8 +602,6 @@ ENTRY(ret_from_fork) la %r11,STACK_FRAME_OVERHEAD(%r15) lg %r12,__LC_CURRENT brasl %r14,schedule_tail - TRACE_IRQS_ON - ssm __LC_SVC_NEW_PSW # reenable interrupts tm __PT_PSW+1(%r11),0x01 # forking a kernel thread ? jne .Lsysc_tracenogo # it's a kernel thread @@ -620,15 +635,16 @@ ENTRY(pgm_check_handler) lghi %r10,1 0: lg %r12,__LC_CURRENT lghi %r11,0 - larl %r13,cleanup_critical lmg %r8,%r9,__LC_PGM_OLD_PSW tmhh %r8,0x0001 # test problem state bit jnz 3f # -> fault in user space #if IS_ENABLED(CONFIG_KVM) # cleanup critical section for program checks in sie64a lgr %r14,%r9 - slg %r14,BASED(.Lsie_critical_start) - clg %r14,BASED(.Lsie_critical_length) + larl %r13,.Lsie_gmap + slgr %r14,%r13 + lghi %r13,.Lsie_done - .Lsie_gmap + clgr %r14,%r13 jhe 1f lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE @@ -680,7 +696,7 @@ ENTRY(pgm_check_handler) mvc __THREAD_per_address(8,%r14),__LC_PER_ADDRESS mvc __THREAD_per_cause(2,%r14),__LC_PER_CODE mvc __THREAD_per_paid(1,%r14),__LC_PER_ACCESS_ID -6: REENABLE_IRQS +6: RESTORE_SM_CLEAR_PER xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) larl %r1,pgm_check_table llgh %r10,__PT_INT_CODE+2(%r11) @@ -702,7 +718,7 @@ ENTRY(pgm_check_handler) # PER event in supervisor state, must be kprobes # .Lpgm_kprobe: - REENABLE_IRQS + RESTORE_SM_CLEAR_PER xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_per_trap @@ -713,11 +729,10 @@ ENTRY(pgm_check_handler) # .Lpgm_svcper: mvc __LC_RETURN_PSW(8),__LC_SVC_NEW_PSW - lghi %r13,__TASK_thread larl %r14,.Lsysc_per stg %r14,__LC_RETURN_PSW+8 lghi %r14,_PIF_SYSCALL | _PIF_PER_TRAP - lpswe __LC_RETURN_PSW # branch to .Lsysc_per and enable irqs + lpswe __LC_RETURN_PSW # branch to .Lsysc_per ENDPROC(pgm_check_handler) /* @@ -729,7 +744,6 @@ ENTRY(io_int_handler) BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT - larl %r13,cleanup_critical lmg %r8,%r9,__LC_IO_OLD_PSW SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER stmg %r0,%r7,__PT_R0(%r11) @@ -749,7 +763,12 @@ ENTRY(io_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore +#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) + tmhh %r8,0x300 + jz 1f TRACE_IRQS_OFF +1: +#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) .Lio_loop: lgr %r2,%r11 # pass pointer to pt_regs @@ -767,25 +786,27 @@ ENTRY(io_int_handler) j .Lio_loop .Lio_return: LOCKDEP_SYS_EXIT - TRACE_IRQS_ON -.Lio_tif: TSTMSK __TI_flags(%r12),_TIF_WORK jnz .Lio_work # there is work to do (signals etc.) TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lio_work .Lio_restore: +#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) + tm __PT_PSW(%r11),3 + jno 0f + TRACE_IRQS_ON +0: +#endif lg %r14,__LC_VDSO_PER_CPU - lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) tm __PT_PSW+1(%r11),0x01 # returning to user ? jno .Lio_exit_kernel BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP -.Lio_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER .Lio_exit_kernel: - lmg %r11,%r15,__PT_R11(%r11) - b __LC_RETURN_LPSWE(%r0) + lmg %r0,%r15,__PT_R0(%r11) + b __LC_RETURN_LPSWE .Lio_done: # @@ -813,9 +834,6 @@ ENTRY(io_int_handler) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) lgr %r15,%r1 - # TRACE_IRQS_ON already done at .Lio_return, call - # TRACE_IRQS_OFF to keep things symmetrical - TRACE_IRQS_OFF brasl %r14,preempt_schedule_irq j .Lio_return #else @@ -835,9 +853,6 @@ ENTRY(io_int_handler) # # One of the work bits is on. Find out which one. # -.Lio_work_tif: - TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING - jo .Lio_mcck_pending TSTMSK __TI_flags(%r12),_TIF_NEED_RESCHED jo .Lio_reschedule #ifdef CONFIG_LIVEPATCH @@ -854,15 +869,6 @@ ENTRY(io_int_handler) jo .Lio_vxrs TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY) jnz .Lio_asce - j .Lio_return # beware of critical section cleanup - -# -# _CIF_MCCK_PENDING is set, call handler -# -.Lio_mcck_pending: - # TRACE_IRQS_ON already done at .Lio_return - brasl %r14,s390_handle_mcck # TIF bit will be cleared by handler - TRACE_IRQS_OFF j .Lio_return # @@ -895,23 +901,19 @@ ENTRY(io_int_handler) # _TIF_GUARDED_STORAGE is set, call guarded_storage_load # .Lio_guarded_storage: - # TRACE_IRQS_ON already done at .Lio_return - ssm __LC_SVC_NEW_PSW # reenable interrupts + ENABLE_INTS_TRACE lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,gs_load_bc_cb - ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts - TRACE_IRQS_OFF + DISABLE_INTS_TRACE j .Lio_return # # _TIF_NEED_RESCHED is set, call schedule # .Lio_reschedule: - # TRACE_IRQS_ON already done at .Lio_return - ssm __LC_SVC_NEW_PSW # reenable interrupts + ENABLE_INTS_TRACE brasl %r14,schedule # call scheduler - ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts - TRACE_IRQS_OFF + DISABLE_INTS_TRACE j .Lio_return # @@ -928,24 +930,20 @@ ENTRY(io_int_handler) # _TIF_SIGPENDING or is set, call do_signal # .Lio_sigpending: - # TRACE_IRQS_ON already done at .Lio_return - ssm __LC_SVC_NEW_PSW # reenable interrupts + ENABLE_INTS_TRACE lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_signal - ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts - TRACE_IRQS_OFF + DISABLE_INTS_TRACE j .Lio_return # # _TIF_NOTIFY_RESUME or is set, call do_notify_resume # .Lio_notify_resume: - # TRACE_IRQS_ON already done at .Lio_return - ssm __LC_SVC_NEW_PSW # reenable interrupts + ENABLE_INTS_TRACE lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,do_notify_resume - ssm __LC_PGM_NEW_PSW # disable I/O and ext. interrupts - TRACE_IRQS_OFF + DISABLE_INTS_TRACE j .Lio_return ENDPROC(io_int_handler) @@ -958,7 +956,6 @@ ENTRY(ext_int_handler) BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT - larl %r13,cleanup_critical lmg %r8,%r9,__LC_EXT_OLD_PSW SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER stmg %r0,%r7,__PT_R0(%r11) @@ -981,7 +978,12 @@ ENTRY(ext_int_handler) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ jo .Lio_restore +#if IS_ENABLED(CONFIG_TRACE_IRQFLAGS) + tmhh %r8,0x300 + jz 1f TRACE_IRQS_OFF +1: +#endif xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs lghi %r3,EXT_INTERRUPT @@ -990,11 +992,11 @@ ENTRY(ext_int_handler) ENDPROC(ext_int_handler) /* - * Load idle PSW. The second "half" of this function is in .Lcleanup_idle. + * Load idle PSW. */ ENTRY(psw_idle) stg %r3,__SF_EMPTY(%r15) - larl %r1,.Lpsw_idle_lpsw+4 + larl %r1,.Lpsw_idle_exit stg %r1,__SF_EMPTY+8(%r15) larl %r1,smp_cpu_mtid llgf %r1,0(%r1) @@ -1006,10 +1008,9 @@ ENTRY(psw_idle) BPON STCK __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) -.Lpsw_idle_lpsw: lpswe __SF_EMPTY(%r15) +.Lpsw_idle_exit: BR_EX %r14 -.Lpsw_idle_end: ENDPROC(psw_idle) /* @@ -1020,6 +1021,7 @@ ENDPROC(psw_idle) * of the register contents at return from io or a system call. */ ENTRY(save_fpu_regs) + stnsm __SF_EMPTY(%r15),0xfc lg %r2,__LC_CURRENT aghi %r2,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU @@ -1051,6 +1053,7 @@ ENTRY(save_fpu_regs) .Lsave_fpu_regs_done: oi __LC_CPU_FLAGS+7,_CIF_FPU .Lsave_fpu_regs_exit: + ssm __SF_EMPTY(%r15) BR_EX %r14 .Lsave_fpu_regs_end: ENDPROC(save_fpu_regs) @@ -1102,8 +1105,6 @@ load_fpu_regs: .Lload_fpu_regs_end: ENDPROC(load_fpu_regs) -.L__critical_end: - /* * Machine check handler routines */ @@ -1116,7 +1117,6 @@ ENTRY(mcck_int_handler) lam %a0,%a15,__LC_AREGS_SAVE_AREA-4095(%r1) # validate acrs lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# validate gprs lg %r12,__LC_CURRENT - larl %r13,cleanup_critical lmg %r8,%r9,__LC_MCK_OLD_PSW TSTMSK __LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE jo .Lmcck_panic # yes -> rest of mcck code invalid @@ -1202,15 +1202,13 @@ ENTRY(mcck_int_handler) xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs brasl %r14,s390_do_machine_check - tm __PT_PSW+1(%r11),0x01 # returning to user ? - jno .Lmcck_return + cghi %r2,0 + je .Lmcck_return lg %r1,__LC_KERNEL_STACK # switch to kernel stack mvc STACK_FRAME_OVERHEAD(__PT_SIZE,%r1),0(%r11) xc __SF_BACKCHAIN(8,%r1),__SF_BACKCHAIN(%r1) la %r11,STACK_FRAME_OVERHEAD(%r1) lgr %r15,%r1 - TSTMSK __LC_CPU_FLAGS,_CIF_MCCK_PENDING - jno .Lmcck_return TRACE_IRQS_OFF brasl %r14,s390_handle_mcck TRACE_IRQS_ON @@ -1280,265 +1278,23 @@ ENTRY(stack_overflow) ENDPROC(stack_overflow) #endif -ENTRY(cleanup_critical) - cghi %r9,__LC_RETURN_LPSWE - je .Lcleanup_lpswe -#if IS_ENABLED(CONFIG_KVM) - clg %r9,BASED(.Lcleanup_table_sie) # .Lsie_gmap - jl 0f - clg %r9,BASED(.Lcleanup_table_sie+8)# .Lsie_done - jl .Lcleanup_sie -#endif - clg %r9,BASED(.Lcleanup_table) # system_call - jl 0f - clg %r9,BASED(.Lcleanup_table+8) # .Lsysc_do_svc - jl .Lcleanup_system_call - clg %r9,BASED(.Lcleanup_table+16) # .Lsysc_tif - jl 0f - clg %r9,BASED(.Lcleanup_table+24) # .Lsysc_restore - jl .Lcleanup_sysc_tif - clg %r9,BASED(.Lcleanup_table+32) # .Lsysc_done - jl .Lcleanup_sysc_restore - clg %r9,BASED(.Lcleanup_table+40) # .Lio_tif - jl 0f - clg %r9,BASED(.Lcleanup_table+48) # .Lio_restore - jl .Lcleanup_io_tif - clg %r9,BASED(.Lcleanup_table+56) # .Lio_done - jl .Lcleanup_io_restore - clg %r9,BASED(.Lcleanup_table+64) # psw_idle - jl 0f - clg %r9,BASED(.Lcleanup_table+72) # .Lpsw_idle_end - jl .Lcleanup_idle - clg %r9,BASED(.Lcleanup_table+80) # save_fpu_regs - jl 0f - clg %r9,BASED(.Lcleanup_table+88) # .Lsave_fpu_regs_end - jl .Lcleanup_save_fpu_regs - clg %r9,BASED(.Lcleanup_table+96) # load_fpu_regs - jl 0f - clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end - jl .Lcleanup_load_fpu_regs -0: BR_EX %r14,%r11 -ENDPROC(cleanup_critical) - - .align 8 -.Lcleanup_table: - .quad system_call - .quad .Lsysc_do_svc - .quad .Lsysc_tif - .quad .Lsysc_restore - .quad .Lsysc_done - .quad .Lio_tif - .quad .Lio_restore - .quad .Lio_done - .quad psw_idle - .quad .Lpsw_idle_end - .quad save_fpu_regs - .quad .Lsave_fpu_regs_end - .quad load_fpu_regs - .quad .Lload_fpu_regs_end - #if IS_ENABLED(CONFIG_KVM) -.Lcleanup_table_sie: - .quad .Lsie_gmap - .quad .Lsie_done - .Lcleanup_sie: - cghi %r11,__LC_SAVE_AREA_ASYNC #Is this in normal interrupt? - je 1f - slg %r9,BASED(.Lsie_crit_mcck_start) - clg %r9,BASED(.Lsie_crit_mcck_length) - jh 1f - oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST -1: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + cghi %r11,__LC_SAVE_AREA_ASYNC #Is this in normal interrupt? + je 1f + larl %r13,.Lsie_entry + slgr %r9,%r13 + larl %r13,.Lsie_skip + clgr %r9,%r13 + jh 1f + oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST +1: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) lg %r9,__SF_SIE_CONTROL(%r15) # get control block pointer ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit BR_EX %r14,%r11 -#endif -.Lcleanup_system_call: - # check if stpt has been executed - clg %r9,BASED(.Lcleanup_system_call_insn) - jh 0f - mvc __LC_SYNC_ENTER_TIMER(8),__LC_ASYNC_ENTER_TIMER - cghi %r11,__LC_SAVE_AREA_ASYNC - je 0f - mvc __LC_SYNC_ENTER_TIMER(8),__LC_MCCK_ENTER_TIMER -0: # check if stmg has been executed - clg %r9,BASED(.Lcleanup_system_call_insn+8) - jh 0f - mvc __LC_SAVE_AREA_SYNC(64),0(%r11) -0: # check if base register setup + TIF bit load has been done - clg %r9,BASED(.Lcleanup_system_call_insn+16) - jhe 0f - # set up saved register r12 task struct pointer - stg %r12,32(%r11) - # set up saved register r13 __TASK_thread offset - mvc 40(8,%r11),BASED(.Lcleanup_system_call_const) -0: # check if the user time update has been done - clg %r9,BASED(.Lcleanup_system_call_insn+24) - jh 0f - lg %r15,__LC_EXIT_TIMER - slg %r15,__LC_SYNC_ENTER_TIMER - alg %r15,__LC_USER_TIMER - stg %r15,__LC_USER_TIMER -0: # check if the system time update has been done - clg %r9,BASED(.Lcleanup_system_call_insn+32) - jh 0f - lg %r15,__LC_LAST_UPDATE_TIMER - slg %r15,__LC_EXIT_TIMER - alg %r15,__LC_SYSTEM_TIMER - stg %r15,__LC_SYSTEM_TIMER -0: # update accounting time stamp - mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER - BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP - # set up saved register r11 - lg %r15,__LC_KERNEL_STACK - la %r9,STACK_FRAME_OVERHEAD(%r15) - stg %r9,24(%r11) # r11 pt_regs pointer - # fill pt_regs - mvc __PT_R8(64,%r9),__LC_SAVE_AREA_SYNC - stmg %r0,%r7,__PT_R0(%r9) - mvc __PT_PSW(16,%r9),__LC_SVC_OLD_PSW - mvc __PT_INT_CODE(4,%r9),__LC_SVC_ILC - xc __PT_FLAGS(8,%r9),__PT_FLAGS(%r9) - mvi __PT_FLAGS+7(%r9),_PIF_SYSCALL - # setup saved register r15 - stg %r15,56(%r11) # r15 stack pointer - # set new psw address and exit - larl %r9,.Lsysc_do_svc - BR_EX %r14,%r11 -.Lcleanup_system_call_insn: - .quad system_call - .quad .Lsysc_stmg - .quad .Lsysc_per - .quad .Lsysc_vtime+36 - .quad .Lsysc_vtime+42 -.Lcleanup_system_call_const: - .quad __TASK_thread - -.Lcleanup_sysc_tif: - larl %r9,.Lsysc_tif - BR_EX %r14,%r11 - -.Lcleanup_sysc_restore: - # check if stpt has been executed - clg %r9,BASED(.Lcleanup_sysc_restore_insn) - jh 0f - mvc __LC_EXIT_TIMER(8),__LC_ASYNC_ENTER_TIMER - cghi %r11,__LC_SAVE_AREA_ASYNC - je 0f - mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER -0: clg %r9,BASED(.Lcleanup_sysc_restore_insn+8) - je 1f - lg %r9,24(%r11) # get saved pointer to pt_regs - mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) - mvc 0(64,%r11),__PT_R8(%r9) - lmg %r0,%r7,__PT_R0(%r9) -.Lcleanup_lpswe: -1: lmg %r8,%r9,__LC_RETURN_PSW - BR_EX %r14,%r11 -.Lcleanup_sysc_restore_insn: - .quad .Lsysc_exit_timer - .quad .Lsysc_done - 4 - -.Lcleanup_io_tif: - larl %r9,.Lio_tif - BR_EX %r14,%r11 - -.Lcleanup_io_restore: - # check if stpt has been executed - clg %r9,BASED(.Lcleanup_io_restore_insn) - jh 0f - mvc __LC_EXIT_TIMER(8),__LC_MCCK_ENTER_TIMER -0: clg %r9,BASED(.Lcleanup_io_restore_insn+8) - je 1f - lg %r9,24(%r11) # get saved r11 pointer to pt_regs - mvc __LC_RETURN_PSW(16),__PT_PSW(%r9) - mvc 0(64,%r11),__PT_R8(%r9) - lmg %r0,%r7,__PT_R0(%r9) -1: lmg %r8,%r9,__LC_RETURN_PSW - BR_EX %r14,%r11 -.Lcleanup_io_restore_insn: - .quad .Lio_exit_timer - .quad .Lio_done - 4 - -.Lcleanup_idle: - ni __LC_CPU_FLAGS+7,255-_CIF_ENABLED_WAIT - # copy interrupt clock & cpu timer - mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_INT_CLOCK - mvc __TIMER_IDLE_EXIT(8,%r2),__LC_ASYNC_ENTER_TIMER - cghi %r11,__LC_SAVE_AREA_ASYNC - je 0f - mvc __CLOCK_IDLE_EXIT(8,%r2),__LC_MCCK_CLOCK - mvc __TIMER_IDLE_EXIT(8,%r2),__LC_MCCK_ENTER_TIMER -0: # check if stck & stpt have been executed - clg %r9,BASED(.Lcleanup_idle_insn) - jhe 1f - mvc __CLOCK_IDLE_ENTER(8,%r2),__CLOCK_IDLE_EXIT(%r2) - mvc __TIMER_IDLE_ENTER(8,%r2),__TIMER_IDLE_EXIT(%r2) -1: # calculate idle cycles - clg %r9,BASED(.Lcleanup_idle_insn) - jl 3f - larl %r1,smp_cpu_mtid - llgf %r1,0(%r1) - ltgr %r1,%r1 - jz 3f - .insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+80(%r15) - larl %r3,mt_cycles - ag %r3,__LC_PERCPU_OFFSET - la %r4,__SF_EMPTY+16(%r15) -2: lg %r0,0(%r3) - slg %r0,0(%r4) - alg %r0,64(%r4) - stg %r0,0(%r3) - la %r3,8(%r3) - la %r4,8(%r4) - brct %r1,2b -3: # account system time going idle - lg %r9,__LC_STEAL_TIMER - alg %r9,__CLOCK_IDLE_ENTER(%r2) - slg %r9,__LC_LAST_UPDATE_CLOCK - stg %r9,__LC_STEAL_TIMER - mvc __LC_LAST_UPDATE_CLOCK(8),__CLOCK_IDLE_EXIT(%r2) - lg %r9,__LC_SYSTEM_TIMER - alg %r9,__LC_LAST_UPDATE_TIMER - slg %r9,__TIMER_IDLE_ENTER(%r2) - stg %r9,__LC_SYSTEM_TIMER - mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) - # prepare return psw - nihh %r8,0xfcfd # clear irq & wait state bits - lg %r9,48(%r11) # return from psw_idle - BR_EX %r14,%r11 -.Lcleanup_idle_insn: - .quad .Lpsw_idle_lpsw - -.Lcleanup_save_fpu_regs: - larl %r9,save_fpu_regs - BR_EX %r14,%r11 - -.Lcleanup_load_fpu_regs: - larl %r9,load_fpu_regs - BR_EX %r14,%r11 - -/* - * Integer constants - */ - .align 8 -.Lcritical_start: - .quad .L__critical_start -.Lcritical_length: - .quad .L__critical_end - .L__critical_start -#if IS_ENABLED(CONFIG_KVM) -.Lsie_critical_start: - .quad .Lsie_gmap -.Lsie_critical_length: - .quad .Lsie_done - .Lsie_gmap -.Lsie_crit_mcck_start: - .quad .Lsie_entry -.Lsie_crit_mcck_length: - .quad .Lsie_skip - .Lsie_entry #endif .section .rodata, "a" #define SYSCALL(esame,emu) .quad __s390x_ ## esame diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 4cd9b1ada834..44e01dd1e624 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -72,22 +72,6 @@ static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn) #endif } -static inline void ftrace_generate_kprobe_nop_insn(struct ftrace_insn *insn) -{ -#ifdef CONFIG_KPROBES - insn->opc = BREAKPOINT_INSTRUCTION; - insn->disp = KPROBE_ON_FTRACE_NOP; -#endif -} - -static inline void ftrace_generate_kprobe_call_insn(struct ftrace_insn *insn) -{ -#ifdef CONFIG_KPROBES - insn->opc = BREAKPOINT_INSTRUCTION; - insn->disp = KPROBE_ON_FTRACE_CALL; -#endif -} - int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 8f8456816d83..0d7fbdfe995a 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -24,19 +24,19 @@ void enabled_wait(void) { struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); unsigned long long idle_time; - unsigned long psw_mask; + unsigned long psw_mask, flags; - trace_hardirqs_on(); /* Wait for external, I/O or machine check interrupt. */ psw_mask = PSW_KERNEL_BITS | PSW_MASK_WAIT | PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; clear_cpu_flag(CIF_NOHZ_DELAY); + local_irq_save(flags); /* Call the assembler magic in entry.S */ psw_idle(idle, psw_mask); + local_irq_restore(flags); - trace_hardirqs_off(); /* Account time spent with enabled wait psw loaded as idle time. */ write_seqcount_begin(&idle->seqcount); @@ -118,22 +118,16 @@ u64 arch_cpu_idle_time(int cpu) void arch_cpu_idle_enter(void) { - local_mcck_disable(); } void arch_cpu_idle(void) { - if (!test_cpu_flag(CIF_MCCK_PENDING)) - /* Halt the cpu and keep track of cpu time accounting. */ - enabled_wait(); + enabled_wait(); local_irq_enable(); } void arch_cpu_idle_exit(void) { - local_mcck_enable(); - if (test_cpu_flag(CIF_MCCK_PENDING)) - s390_handle_mcck(); } void arch_cpu_idle_dead(void) diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 4a71061974fd..ccea9a245867 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -39,6 +39,7 @@ #define IPL_CCW_STR "ccw" #define IPL_FCP_STR "fcp" #define IPL_FCP_DUMP_STR "fcp_dump" +#define IPL_NVME_STR "nvme" #define IPL_NSS_STR "nss" #define DUMP_CCW_STR "ccw" @@ -93,6 +94,8 @@ static char *ipl_type_str(enum ipl_type type) return IPL_FCP_DUMP_STR; case IPL_TYPE_NSS: return IPL_NSS_STR; + case IPL_TYPE_NVME: + return IPL_NVME_STR; case IPL_TYPE_UNKNOWN: default: return IPL_UNKNOWN_STR; @@ -133,6 +136,7 @@ static int reipl_capabilities = IPL_TYPE_UNKNOWN; static enum ipl_type reipl_type = IPL_TYPE_UNKNOWN; static struct ipl_parameter_block *reipl_block_fcp; +static struct ipl_parameter_block *reipl_block_nvme; static struct ipl_parameter_block *reipl_block_ccw; static struct ipl_parameter_block *reipl_block_nss; static struct ipl_parameter_block *reipl_block_actual; @@ -261,6 +265,8 @@ static __init enum ipl_type get_ipl_type(void) return IPL_TYPE_FCP_DUMP; else return IPL_TYPE_FCP; + case IPL_PBT_NVME: + return IPL_TYPE_NVME; } return IPL_TYPE_UNKNOWN; } @@ -317,6 +323,8 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj, case IPL_TYPE_FCP: case IPL_TYPE_FCP_DUMP: return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno); + case IPL_TYPE_NVME: + return sprintf(page, "%08ux\n", ipl_block.nvme.fid); default: return 0; } @@ -345,15 +353,35 @@ static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, scp_data, size); } + +static ssize_t ipl_nvme_scp_data_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count) +{ + unsigned int size = ipl_block.nvme.scp_data_len; + void *scp_data = &ipl_block.nvme.scp_data; + + return memory_read_from_buffer(buf, count, &off, scp_data, size); +} + static struct bin_attribute ipl_scp_data_attr = __BIN_ATTR(scp_data, S_IRUGO, ipl_scp_data_read, NULL, PAGE_SIZE); +static struct bin_attribute ipl_nvme_scp_data_attr = + __BIN_ATTR(scp_data, S_IRUGO, ipl_nvme_scp_data_read, NULL, PAGE_SIZE); + static struct bin_attribute *ipl_fcp_bin_attrs[] = { &ipl_parameter_attr, &ipl_scp_data_attr, NULL, }; +static struct bin_attribute *ipl_nvme_bin_attrs[] = { + &ipl_parameter_attr, + &ipl_nvme_scp_data_attr, + NULL, +}; + /* FCP ipl device attributes */ DEFINE_IPL_ATTR_RO(ipl_fcp, wwpn, "0x%016llx\n", @@ -365,6 +393,16 @@ DEFINE_IPL_ATTR_RO(ipl_fcp, bootprog, "%lld\n", DEFINE_IPL_ATTR_RO(ipl_fcp, br_lba, "%lld\n", (unsigned long long)ipl_block.fcp.br_lba); +/* NVMe ipl device attributes */ +DEFINE_IPL_ATTR_RO(ipl_nvme, fid, "0x%08llx\n", + (unsigned long long)ipl_block.nvme.fid); +DEFINE_IPL_ATTR_RO(ipl_nvme, nsid, "0x%08llx\n", + (unsigned long long)ipl_block.nvme.nsid); +DEFINE_IPL_ATTR_RO(ipl_nvme, bootprog, "%lld\n", + (unsigned long long)ipl_block.nvme.bootprog); +DEFINE_IPL_ATTR_RO(ipl_nvme, br_lba, "%lld\n", + (unsigned long long)ipl_block.nvme.br_lba); + static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { @@ -399,6 +437,24 @@ static struct attribute_group ipl_fcp_attr_group = { .bin_attrs = ipl_fcp_bin_attrs, }; +static struct attribute *ipl_nvme_attrs[] = { + &sys_ipl_type_attr.attr, + &sys_ipl_nvme_fid_attr.attr, + &sys_ipl_nvme_nsid_attr.attr, + &sys_ipl_nvme_bootprog_attr.attr, + &sys_ipl_nvme_br_lba_attr.attr, + &sys_ipl_ccw_loadparm_attr.attr, + &sys_ipl_secure_attr.attr, + &sys_ipl_has_secure_attr.attr, + NULL, +}; + +static struct attribute_group ipl_nvme_attr_group = { + .attrs = ipl_nvme_attrs, + .bin_attrs = ipl_nvme_bin_attrs, +}; + + /* CCW ipl device attributes */ static struct attribute *ipl_ccw_attrs_vm[] = { @@ -474,6 +530,9 @@ static int __init ipl_init(void) case IPL_TYPE_FCP_DUMP: rc = sysfs_create_group(&ipl_kset->kobj, &ipl_fcp_attr_group); break; + case IPL_TYPE_NVME: + rc = sysfs_create_group(&ipl_kset->kobj, &ipl_nvme_attr_group); + break; default: rc = sysfs_create_group(&ipl_kset->kobj, &ipl_unknown_attr_group); @@ -727,6 +786,93 @@ static struct attribute_group reipl_fcp_attr_group = { static struct kobj_attribute sys_reipl_fcp_clear_attr = __ATTR(clear, 0644, reipl_fcp_clear_show, reipl_fcp_clear_store); +/* NVME reipl device attributes */ + +static ssize_t reipl_nvme_scpdata_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t size = reipl_block_nvme->nvme.scp_data_len; + void *scp_data = reipl_block_nvme->nvme.scp_data; + + return memory_read_from_buffer(buf, count, &off, scp_data, size); +} + +static ssize_t reipl_nvme_scpdata_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, size_t count) +{ + size_t scpdata_len = count; + size_t padding; + + if (off) + return -EINVAL; + + memcpy(reipl_block_nvme->nvme.scp_data, buf, count); + if (scpdata_len % 8) { + padding = 8 - (scpdata_len % 8); + memset(reipl_block_nvme->nvme.scp_data + scpdata_len, + 0, padding); + scpdata_len += padding; + } + + reipl_block_nvme->hdr.len = IPL_BP_FCP_LEN + scpdata_len; + reipl_block_nvme->nvme.len = IPL_BP0_FCP_LEN + scpdata_len; + reipl_block_nvme->nvme.scp_data_len = scpdata_len; + + return count; +} + +static struct bin_attribute sys_reipl_nvme_scp_data_attr = + __BIN_ATTR(scp_data, (S_IRUGO | S_IWUSR), reipl_nvme_scpdata_read, + reipl_nvme_scpdata_write, DIAG308_SCPDATA_SIZE); + +static struct bin_attribute *reipl_nvme_bin_attrs[] = { + &sys_reipl_nvme_scp_data_attr, + NULL, +}; + +DEFINE_IPL_ATTR_RW(reipl_nvme, fid, "0x%08llx\n", "%llx\n", + reipl_block_nvme->nvme.fid); +DEFINE_IPL_ATTR_RW(reipl_nvme, nsid, "0x%08llx\n", "%llx\n", + reipl_block_nvme->nvme.nsid); +DEFINE_IPL_ATTR_RW(reipl_nvme, bootprog, "%lld\n", "%lld\n", + reipl_block_nvme->nvme.bootprog); +DEFINE_IPL_ATTR_RW(reipl_nvme, br_lba, "%lld\n", "%lld\n", + reipl_block_nvme->nvme.br_lba); + +/* nvme wrapper */ +static ssize_t reipl_nvme_loadparm_show(struct kobject *kobj, + struct kobj_attribute *attr, char *page) +{ + return reipl_generic_loadparm_show(reipl_block_nvme, page); +} + +static ssize_t reipl_nvme_loadparm_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t len) +{ + return reipl_generic_loadparm_store(reipl_block_nvme, buf, len); +} + +static struct kobj_attribute sys_reipl_nvme_loadparm_attr = + __ATTR(loadparm, S_IRUGO | S_IWUSR, reipl_nvme_loadparm_show, + reipl_nvme_loadparm_store); + +static struct attribute *reipl_nvme_attrs[] = { + &sys_reipl_nvme_fid_attr.attr, + &sys_reipl_nvme_nsid_attr.attr, + &sys_reipl_nvme_bootprog_attr.attr, + &sys_reipl_nvme_br_lba_attr.attr, + &sys_reipl_nvme_loadparm_attr.attr, + NULL, +}; + +static struct attribute_group reipl_nvme_attr_group = { + .attrs = reipl_nvme_attrs, + .bin_attrs = reipl_nvme_bin_attrs +}; + /* CCW reipl device attributes */ DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw); @@ -891,6 +1037,9 @@ static int reipl_set_type(enum ipl_type type) case IPL_TYPE_FCP: reipl_block_actual = reipl_block_fcp; break; + case IPL_TYPE_NVME: + reipl_block_actual = reipl_block_nvme; + break; case IPL_TYPE_NSS: reipl_block_actual = reipl_block_nss; break; @@ -917,6 +1066,8 @@ static ssize_t reipl_type_store(struct kobject *kobj, rc = reipl_set_type(IPL_TYPE_CCW); else if (strncmp(buf, IPL_FCP_STR, strlen(IPL_FCP_STR)) == 0) rc = reipl_set_type(IPL_TYPE_FCP); + else if (strncmp(buf, IPL_NVME_STR, strlen(IPL_NVME_STR)) == 0) + rc = reipl_set_type(IPL_TYPE_NVME); else if (strncmp(buf, IPL_NSS_STR, strlen(IPL_NSS_STR)) == 0) rc = reipl_set_type(IPL_TYPE_NSS); return (rc != 0) ? rc : len; @@ -927,6 +1078,7 @@ static struct kobj_attribute reipl_type_attr = static struct kset *reipl_kset; static struct kset *reipl_fcp_kset; +static struct kset *reipl_nvme_kset; static void __reipl_run(void *unused) { @@ -945,6 +1097,10 @@ static void __reipl_run(void *unused) else diag308(DIAG308_LOAD_NORMAL, NULL); break; + case IPL_TYPE_NVME: + diag308(DIAG308_SET, reipl_block_nvme); + diag308(DIAG308_LOAD_CLEAR, NULL); + break; case IPL_TYPE_NSS: diag308(DIAG308_SET, reipl_block_nss); diag308(DIAG308_LOAD_CLEAR, NULL); @@ -1093,6 +1249,49 @@ out1: return rc; } +static int __init reipl_nvme_init(void) +{ + int rc; + + reipl_block_nvme = (void *) get_zeroed_page(GFP_KERNEL); + if (!reipl_block_nvme) + return -ENOMEM; + + /* sysfs: create kset for mixing attr group and bin attrs */ + reipl_nvme_kset = kset_create_and_add(IPL_NVME_STR, NULL, + &reipl_kset->kobj); + if (!reipl_nvme_kset) { + free_page((unsigned long) reipl_block_nvme); + return -ENOMEM; + } + + rc = sysfs_create_group(&reipl_nvme_kset->kobj, &reipl_nvme_attr_group); + if (rc) { + kset_unregister(reipl_nvme_kset); + free_page((unsigned long) reipl_block_nvme); + return rc; + } + + if (ipl_info.type == IPL_TYPE_NVME) { + memcpy(reipl_block_nvme, &ipl_block, sizeof(ipl_block)); + /* + * Fix loadparm: There are systems where the (SCSI) LOADPARM + * is invalid in the IPL parameter block, so take it + * always from sclp_ipl_info. + */ + memcpy(reipl_block_nvme->nvme.loadparm, sclp_ipl_info.loadparm, + LOADPARM_LEN); + } else { + reipl_block_nvme->hdr.len = IPL_BP_NVME_LEN; + reipl_block_nvme->hdr.version = IPL_PARM_BLOCK_VERSION; + reipl_block_nvme->nvme.len = IPL_BP0_NVME_LEN; + reipl_block_nvme->nvme.pbt = IPL_PBT_NVME; + reipl_block_nvme->nvme.opt = IPL_PB0_NVME_OPT_IPL; + } + reipl_capabilities |= IPL_TYPE_NVME; + return 0; +} + static int __init reipl_type_init(void) { enum ipl_type reipl_type = ipl_info.type; @@ -1108,6 +1307,9 @@ static int __init reipl_type_init(void) if (reipl_block->pb0_hdr.pbt == IPL_PBT_FCP) { memcpy(reipl_block_fcp, reipl_block, size); reipl_type = IPL_TYPE_FCP; + } else if (reipl_block->pb0_hdr.pbt == IPL_PBT_NVME) { + memcpy(reipl_block_nvme, reipl_block, size); + reipl_type = IPL_TYPE_NVME; } else if (reipl_block->pb0_hdr.pbt == IPL_PBT_CCW) { memcpy(reipl_block_ccw, reipl_block, size); reipl_type = IPL_TYPE_CCW; @@ -1134,6 +1336,9 @@ static int __init reipl_init(void) rc = reipl_fcp_init(); if (rc) return rc; + rc = reipl_nvme_init(); + if (rc) + return rc; rc = reipl_nss_init(); if (rc) return rc; @@ -1750,6 +1955,10 @@ void __init setup_ipl(void) ipl_info.data.fcp.wwpn = ipl_block.fcp.wwpn; ipl_info.data.fcp.lun = ipl_block.fcp.lun; break; + case IPL_TYPE_NVME: + ipl_info.data.nvme.fid = ipl_block.nvme.fid; + ipl_info.data.nvme.nsid = ipl_block.nvme.nsid; + break; case IPL_TYPE_NSS: case IPL_TYPE_UNKNOWN: /* We have no info to copy */ diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 3a854cb5a4c6..93c6b8932fbd 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -16,7 +16,6 @@ #include <linux/debug_locks.h> #include <asm/cio.h> #include <asm/setup.h> -#include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/smp.h> #include <asm/ipl.h> diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 8415ae7d2a23..f9e4baa64b67 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -151,7 +151,7 @@ static int kexec_file_add_initrd(struct kimage *image, buf.mem += crashk_res.start; buf.memsz = buf.bufsz; - data->parm->initrd_start = buf.mem; + data->parm->initrd_start = data->memsz; data->parm->initrd_size = buf.memsz; data->memsz += buf.memsz; diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c index d5035de9020e..b7182cec48dc 100644 --- a/arch/s390/kernel/machine_kexec_reloc.c +++ b/arch/s390/kernel/machine_kexec_reloc.c @@ -28,6 +28,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val, break; case R_390_64: /* Direct 64 bit. */ case R_390_GLOB_DAT: + case R_390_JMP_SLOT: *(u64 *)loc = val; break; case R_390_PC16: /* PC relative 16 bit. */ diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index ba8f19bb438b..4055f1c49814 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -19,6 +19,7 @@ #include <linux/kasan.h> #include <linux/moduleloader.h> #include <linux/bug.h> +#include <linux/memory.h> #include <asm/alternative.h> #include <asm/nospec-branch.h> #include <asm/facility.h> @@ -174,10 +175,12 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, } static int apply_rela_bits(Elf_Addr loc, Elf_Addr val, - int sign, int bits, int shift) + int sign, int bits, int shift, + void *(*write)(void *dest, const void *src, size_t len)) { unsigned long umax; long min, max; + void *dest = (void *)loc; if (val & ((1UL << shift) - 1)) return -ENOEXEC; @@ -194,26 +197,33 @@ static int apply_rela_bits(Elf_Addr loc, Elf_Addr val, return -ENOEXEC; } - if (bits == 8) - *(unsigned char *) loc = val; - else if (bits == 12) - *(unsigned short *) loc = (val & 0xfff) | + if (bits == 8) { + unsigned char tmp = val; + write(dest, &tmp, 1); + } else if (bits == 12) { + unsigned short tmp = (val & 0xfff) | (*(unsigned short *) loc & 0xf000); - else if (bits == 16) - *(unsigned short *) loc = val; - else if (bits == 20) - *(unsigned int *) loc = (val & 0xfff) << 16 | - (val & 0xff000) >> 4 | - (*(unsigned int *) loc & 0xf00000ff); - else if (bits == 32) - *(unsigned int *) loc = val; - else if (bits == 64) - *(unsigned long *) loc = val; + write(dest, &tmp, 2); + } else if (bits == 16) { + unsigned short tmp = val; + write(dest, &tmp, 2); + } else if (bits == 20) { + unsigned int tmp = (val & 0xfff) << 16 | + (val & 0xff000) >> 4 | (*(unsigned int *) loc & 0xf00000ff); + write(dest, &tmp, 4); + } else if (bits == 32) { + unsigned int tmp = val; + write(dest, &tmp, 4); + } else if (bits == 64) { + unsigned long tmp = val; + write(dest, &tmp, 8); + } return 0; } static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, - const char *strtab, struct module *me) + const char *strtab, struct module *me, + void *(*write)(void *dest, const void *src, size_t len)) { struct mod_arch_syminfo *info; Elf_Addr loc, val; @@ -241,17 +251,17 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_64: /* Direct 64 bit. */ val += rela->r_addend; if (r_type == R_390_8) - rc = apply_rela_bits(loc, val, 0, 8, 0); + rc = apply_rela_bits(loc, val, 0, 8, 0, write); else if (r_type == R_390_12) - rc = apply_rela_bits(loc, val, 0, 12, 0); + rc = apply_rela_bits(loc, val, 0, 12, 0, write); else if (r_type == R_390_16) - rc = apply_rela_bits(loc, val, 0, 16, 0); + rc = apply_rela_bits(loc, val, 0, 16, 0, write); else if (r_type == R_390_20) - rc = apply_rela_bits(loc, val, 1, 20, 0); + rc = apply_rela_bits(loc, val, 1, 20, 0, write); else if (r_type == R_390_32) - rc = apply_rela_bits(loc, val, 0, 32, 0); + rc = apply_rela_bits(loc, val, 0, 32, 0, write); else if (r_type == R_390_64) - rc = apply_rela_bits(loc, val, 0, 64, 0); + rc = apply_rela_bits(loc, val, 0, 64, 0, write); break; case R_390_PC16: /* PC relative 16 bit. */ case R_390_PC16DBL: /* PC relative 16 bit shifted by 1. */ @@ -260,15 +270,15 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PC64: /* PC relative 64 bit. */ val += rela->r_addend - loc; if (r_type == R_390_PC16) - rc = apply_rela_bits(loc, val, 1, 16, 0); + rc = apply_rela_bits(loc, val, 1, 16, 0, write); else if (r_type == R_390_PC16DBL) - rc = apply_rela_bits(loc, val, 1, 16, 1); + rc = apply_rela_bits(loc, val, 1, 16, 1, write); else if (r_type == R_390_PC32DBL) - rc = apply_rela_bits(loc, val, 1, 32, 1); + rc = apply_rela_bits(loc, val, 1, 32, 1, write); else if (r_type == R_390_PC32) - rc = apply_rela_bits(loc, val, 1, 32, 0); + rc = apply_rela_bits(loc, val, 1, 32, 0, write); else if (r_type == R_390_PC64) - rc = apply_rela_bits(loc, val, 1, 64, 0); + rc = apply_rela_bits(loc, val, 1, 64, 0, write); break; case R_390_GOT12: /* 12 bit GOT offset. */ case R_390_GOT16: /* 16 bit GOT offset. */ @@ -283,33 +293,33 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_GOTPLT64: /* 64 bit offset to jump slot. */ case R_390_GOTPLTENT: /* 32 bit rel. offset to jump slot >> 1. */ if (info->got_initialized == 0) { - Elf_Addr *gotent; + Elf_Addr *gotent = me->core_layout.base + + me->arch.got_offset + + info->got_offset; - gotent = me->core_layout.base + me->arch.got_offset + - info->got_offset; - *gotent = val; + write(gotent, &val, sizeof(*gotent)); info->got_initialized = 1; } val = info->got_offset + rela->r_addend; if (r_type == R_390_GOT12 || r_type == R_390_GOTPLT12) - rc = apply_rela_bits(loc, val, 0, 12, 0); + rc = apply_rela_bits(loc, val, 0, 12, 0, write); else if (r_type == R_390_GOT16 || r_type == R_390_GOTPLT16) - rc = apply_rela_bits(loc, val, 0, 16, 0); + rc = apply_rela_bits(loc, val, 0, 16, 0, write); else if (r_type == R_390_GOT20 || r_type == R_390_GOTPLT20) - rc = apply_rela_bits(loc, val, 1, 20, 0); + rc = apply_rela_bits(loc, val, 1, 20, 0, write); else if (r_type == R_390_GOT32 || r_type == R_390_GOTPLT32) - rc = apply_rela_bits(loc, val, 0, 32, 0); + rc = apply_rela_bits(loc, val, 0, 32, 0, write); else if (r_type == R_390_GOT64 || r_type == R_390_GOTPLT64) - rc = apply_rela_bits(loc, val, 0, 64, 0); + rc = apply_rela_bits(loc, val, 0, 64, 0, write); else if (r_type == R_390_GOTENT || r_type == R_390_GOTPLTENT) { val += (Elf_Addr) me->core_layout.base - loc; - rc = apply_rela_bits(loc, val, 1, 32, 1); + rc = apply_rela_bits(loc, val, 1, 32, 1, write); } break; case R_390_PLT16DBL: /* 16 bit PC rel. PLT shifted by 1. */ @@ -320,25 +330,29 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF32: /* 32 bit offset from GOT to PLT. */ case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { - unsigned int *ip; - ip = me->core_layout.base + me->arch.plt_offset + - info->plt_offset; - ip[0] = 0x0d10e310; /* basr 1,0 */ - ip[1] = 0x100a0004; /* lg 1,10(1) */ + unsigned int insn[5]; + unsigned int *ip = me->core_layout.base + + me->arch.plt_offset + + info->plt_offset; + + insn[0] = 0x0d10e310; /* basr 1,0 */ + insn[1] = 0x100a0004; /* lg 1,10(1) */ if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) { unsigned int *ij; ij = me->core_layout.base + me->arch.plt_offset + me->arch.plt_size - PLT_ENTRY_SIZE; - ip[2] = 0xa7f40000 + /* j __jump_r1 */ + insn[2] = 0xa7f40000 + /* j __jump_r1 */ (unsigned int)(u16) (((unsigned long) ij - 8 - (unsigned long) ip) / 2); } else { - ip[2] = 0x07f10000; /* br %r1 */ + insn[2] = 0x07f10000; /* br %r1 */ } - ip[3] = (unsigned int) (val >> 32); - ip[4] = (unsigned int) val; + insn[3] = (unsigned int) (val >> 32); + insn[4] = (unsigned int) val; + + write(ip, insn, sizeof(insn)); info->plt_initialized = 1; } if (r_type == R_390_PLTOFF16 || @@ -357,17 +371,17 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val += rela->r_addend - loc; } if (r_type == R_390_PLT16DBL) - rc = apply_rela_bits(loc, val, 1, 16, 1); + rc = apply_rela_bits(loc, val, 1, 16, 1, write); else if (r_type == R_390_PLTOFF16) - rc = apply_rela_bits(loc, val, 0, 16, 0); + rc = apply_rela_bits(loc, val, 0, 16, 0, write); else if (r_type == R_390_PLT32DBL) - rc = apply_rela_bits(loc, val, 1, 32, 1); + rc = apply_rela_bits(loc, val, 1, 32, 1, write); else if (r_type == R_390_PLT32 || r_type == R_390_PLTOFF32) - rc = apply_rela_bits(loc, val, 0, 32, 0); + rc = apply_rela_bits(loc, val, 0, 32, 0, write); else if (r_type == R_390_PLT64 || r_type == R_390_PLTOFF64) - rc = apply_rela_bits(loc, val, 0, 64, 0); + rc = apply_rela_bits(loc, val, 0, 64, 0, write); break; case R_390_GOTOFF16: /* 16 bit offset to GOT. */ case R_390_GOTOFF32: /* 32 bit offset to GOT. */ @@ -375,20 +389,20 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, val = val + rela->r_addend - ((Elf_Addr) me->core_layout.base + me->arch.got_offset); if (r_type == R_390_GOTOFF16) - rc = apply_rela_bits(loc, val, 0, 16, 0); + rc = apply_rela_bits(loc, val, 0, 16, 0, write); else if (r_type == R_390_GOTOFF32) - rc = apply_rela_bits(loc, val, 0, 32, 0); + rc = apply_rela_bits(loc, val, 0, 32, 0, write); else if (r_type == R_390_GOTOFF64) - rc = apply_rela_bits(loc, val, 0, 64, 0); + rc = apply_rela_bits(loc, val, 0, 64, 0, write); break; case R_390_GOTPC: /* 32 bit PC relative offset to GOT. */ case R_390_GOTPCDBL: /* 32 bit PC rel. off. to GOT shifted by 1. */ val = (Elf_Addr) me->core_layout.base + me->arch.got_offset + rela->r_addend - loc; if (r_type == R_390_GOTPC) - rc = apply_rela_bits(loc, val, 1, 32, 0); + rc = apply_rela_bits(loc, val, 1, 32, 0, write); else if (r_type == R_390_GOTPCDBL) - rc = apply_rela_bits(loc, val, 1, 32, 1); + rc = apply_rela_bits(loc, val, 1, 32, 1, write); break; case R_390_COPY: case R_390_GLOB_DAT: /* Create GOT entry. */ @@ -412,9 +426,10 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, return 0; } -int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, +static int __apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, unsigned int symindex, unsigned int relsec, - struct module *me) + struct module *me, + void *(*write)(void *dest, const void *src, size_t len)) { Elf_Addr base; Elf_Sym *symtab; @@ -430,13 +445,27 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, n = sechdrs[relsec].sh_size / sizeof(Elf_Rela); for (i = 0; i < n; i++, rela++) { - rc = apply_rela(rela, base, symtab, strtab, me); + rc = apply_rela(rela, base, symtab, strtab, me, write); if (rc) return rc; } return 0; } +int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + bool early = me->state == MODULE_STATE_UNFORMED; + void *(*write)(void *, const void *, size_t) = memcpy; + + if (!early) + write = s390_kernel_write; + + return __apply_relocate_add(sechdrs, strtab, symindex, relsec, me, + write); +} + int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 0a487fae763e..86c8d5370e7f 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -148,7 +148,6 @@ void s390_handle_mcck(void) local_mcck_disable(); mcck = *this_cpu_ptr(&cpu_mcck); memset(this_cpu_ptr(&cpu_mcck), 0, sizeof(mcck)); - clear_cpu_flag(CIF_MCCK_PENDING); local_mcck_enable(); local_irq_restore(flags); @@ -333,7 +332,7 @@ NOKPROBE_SYMBOL(s390_backup_mcck_info); /* * machine check handler. */ -void notrace s390_do_machine_check(struct pt_regs *regs) +int notrace s390_do_machine_check(struct pt_regs *regs) { static int ipd_count; static DEFINE_SPINLOCK(ipd_lock); @@ -342,6 +341,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) unsigned long long tmp; union mci mci; unsigned long mcck_dam_code; + int mcck_pending = 0; nmi_enter(); inc_irq_stat(NMI_NMI); @@ -400,7 +400,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) */ mcck->kill_task = 1; mcck->mcck_code = mci.val; - set_cpu_flag(CIF_MCCK_PENDING); + mcck_pending = 1; } /* @@ -420,8 +420,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) mcck->stp_queue |= stp_sync_check(); if (S390_lowcore.external_damage_code & (1U << ED_STP_ISLAND)) mcck->stp_queue |= stp_island_check(); - if (mcck->stp_queue) - set_cpu_flag(CIF_MCCK_PENDING); + mcck_pending = 1; } /* @@ -442,12 +441,12 @@ void notrace s390_do_machine_check(struct pt_regs *regs) if (mci.cp) { /* Channel report word pending */ mcck->channel_report = 1; - set_cpu_flag(CIF_MCCK_PENDING); + mcck_pending = 1; } if (mci.w) { /* Warning pending */ mcck->warning = 1; - set_cpu_flag(CIF_MCCK_PENDING); + mcck_pending = 1; } /* @@ -462,7 +461,17 @@ void notrace s390_do_machine_check(struct pt_regs *regs) *((long *)(regs->gprs[15] + __SF_SIE_REASON)) = -EINTR; } clear_cpu_flag(CIF_MCCK_GUEST); + + if (user_mode(regs) && mcck_pending) { + nmi_exit(); + return 1; + } + + if (mcck_pending) + schedule_mcck_handler(); + nmi_exit(); + return 0; } NOKPROBE_SYMBOL(s390_do_machine_check); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 58faa12542a1..ce60a459a143 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -25,7 +25,6 @@ #include <linux/compat.h> #include <trace/syscall.h> #include <asm/page.h> -#include <asm/pgtable.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -1416,7 +1415,7 @@ static const struct user_regset s390_regsets[] = { }; static const struct user_regset_view user_s390_view = { - .name = UTS_MACHINE, + .name = "s390x", .e_machine = EM_S390, .regsets = s390_regsets, .n = ARRAY_SIZE(s390_regsets) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 36445dd40fdb..5853c9872dfe 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -305,12 +305,9 @@ void *restart_stack __section(.data); unsigned long stack_alloc(void) { #ifdef CONFIG_VMAP_STACK - return (unsigned long) - __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE, - VMALLOC_START, VMALLOC_END, - THREADINFO_GFP, - PAGE_KERNEL, 0, NUMA_NO_NODE, - __builtin_return_address(0)); + return (unsigned long)__vmalloc_node(THREAD_SIZE, THREAD_SIZE, + THREADINFO_GFP, NUMA_NO_NODE, + __builtin_return_address(0)); #else return __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER); #endif @@ -384,8 +381,7 @@ static void __init setup_lowcore_dat_off(void) lc->restart_psw.addr = (unsigned long) restart_int_handler; lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; lc->external_new_psw.addr = (unsigned long) ext_int_handler; - lc->svc_new_psw.mask = PSW_KERNEL_BITS | - PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK; + lc->svc_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; lc->svc_new_psw.addr = (unsigned long) system_call; lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK; lc->program_new_psw.addr = (unsigned long) pgm_check_handler; @@ -597,9 +593,10 @@ static void __init setup_memory_end(void) #ifdef CONFIG_CRASH_DUMP /* - * When kdump is enabled, we have to ensure that no memory from - * the area [0 - crashkernel memory size] and - * [crashk_res.start - crashk_res.end] is set offline. + * When kdump is enabled, we have to ensure that no memory from the area + * [0 - crashkernel memory size] is set offline - it will be exchanged with + * the crashkernel memory region when kdump is triggered. The crashkernel + * memory region can never get offlined (pages are unmovable). */ static int kdump_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) @@ -610,11 +607,7 @@ static int kdump_mem_notifier(struct notifier_block *nb, return NOTIFY_OK; if (arg->start_pfn < PFN_DOWN(resource_size(&crashk_res))) return NOTIFY_BAD; - if (arg->start_pfn > PFN_DOWN(crashk_res.end)) - return NOTIFY_OK; - if (arg->start_pfn + arg->nr_pages - 1 < PFN_DOWN(crashk_res.start)) - return NOTIFY_OK; - return NOTIFY_BAD; + return NOTIFY_OK; } static struct notifier_block kdump_mem_nb = { diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 7eaabbab2213..e6be63ff162a 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -61,6 +61,7 @@ enum { ec_schedule = 0, ec_call_function_single, ec_stop_cpu, + ec_mcck_pending, }; enum { @@ -403,7 +404,12 @@ int smp_find_processor_id(u16 address) return -1; } -bool arch_vcpu_is_preempted(int cpu) +void schedule_mcck_handler(void) +{ + pcpu_ec_call(pcpu_devices + smp_processor_id(), ec_mcck_pending); +} + +bool notrace arch_vcpu_is_preempted(int cpu) { if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu)) return false; @@ -413,7 +419,7 @@ bool arch_vcpu_is_preempted(int cpu) } EXPORT_SYMBOL(arch_vcpu_is_preempted); -void smp_yield_cpu(int cpu) +void notrace smp_yield_cpu(int cpu) { if (!MACHINE_HAS_DIAG9C) return; @@ -497,6 +503,8 @@ static void smp_handle_ext_call(void) scheduler_ipi(); if (test_bit(ec_call_function_single, &bits)) generic_smp_call_function_single_interrupt(); + if (test_bit(ec_mcck_pending, &bits)) + s390_handle_mcck(); } static void do_ext_call_interrupt(struct ext_code ext_code, diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index bd7bd3581a0f..bfdcb7633957 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -440,3 +440,4 @@ 435 common clone3 sys_clone3 sys_clone3 437 common openat2 sys_openat2 sys_openat2 438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd +439 common faccessat2 sys_faccessat2 sys_faccessat2 diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 5f70cefc13e4..332b542548cd 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -594,7 +594,7 @@ static int __init topology_setup(char *str) 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) + void *buffer, size_t *lenp, loff_t *ppos) { int enabled = topology_is_enabled(); int new_mode; diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c index 490b52e85014..11a669f3cc93 100644 --- a/arch/s390/kernel/trace.c +++ b/arch/s390/kernel/trace.c @@ -14,7 +14,7 @@ EXPORT_TRACEPOINT_SYMBOL(s390_diagnose); static DEFINE_PER_CPU(unsigned int, diagnose_trace_depth); -void trace_s390_diagnose_norecursion(int diag_nr) +void notrace trace_s390_diagnose_norecursion(int diag_nr) { unsigned long flags; unsigned int *depth; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index c86d654351d1..66e89b2866d7 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -23,10 +23,11 @@ int __bootdata_preserved(prot_virt_guest); #endif +struct uv_info __bootdata_preserved(uv_info); + #if IS_ENABLED(CONFIG_KVM) int prot_virt_host; EXPORT_SYMBOL(prot_virt_host); -struct uv_info __bootdata_preserved(uv_info); EXPORT_SYMBOL(uv_info); static int __init prot_virt_setup(char *val) @@ -204,7 +205,7 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) again: rc = -EFAULT; - down_read(&gmap->mm->mmap_sem); + mmap_read_lock(gmap->mm); uaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(uaddr)) @@ -233,7 +234,7 @@ again: pte_unmap_unlock(ptep, ptelock); unlock_page(page); out: - up_read(&gmap->mm->mmap_sem); + mmap_read_unlock(gmap->mm); if (rc == -EAGAIN) { wait_on_page_writeback(page); diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index bcc9bdb39ba2..c4baefaa6e34 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -21,7 +21,6 @@ #include <linux/memblock.h> #include <linux/compat.h> #include <asm/asm-offsets.h> -#include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mmu.h> #include <asm/mmu_context.h> @@ -208,7 +207,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * it at vdso_base which is the "natural" base for it, but we might * fail and end up putting it elsewhere. */ - if (down_write_killable(&mm->mmap_sem)) + if (mmap_write_lock_killable(mm)) return -EINTR; vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0); if (IS_ERR_VALUE(vdso_base)) { @@ -239,7 +238,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) rc = 0; out_up: - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); return rc; } |