linux-stable/arch/s390/include/asm/processor.h
Linus Torvalds de927f6c0b s390 updates for 6.8 merge window
- Add machine variable capacity information to /proc/sysinfo.
 
 - Limit the waste of page tables and always align vmalloc area size
   and base address on segment boundary.
 
 - Fix a memory leak when an attempt to register interruption sub class
   (ISC) for the adjunct-processor (AP) guest failed.
 
 - Reset response code AP_RESPONSE_INVALID_GISA to understandable
   by guest AP_RESPONSE_INVALID_ADDRESS in response to a failed
   interruption sub class (ISC) registration attempt.
 
 - Improve reaction to adjunct-processor (AP) AP_RESPONSE_OTHERWISE_CHANGED
   response code when enabling interrupts on behalf of a guest.
 
 - Fix incorrect sysfs 'status' attribute of adjunct-processor (AP) queue
   device bound to the vfio_ap device driver when the mediated device is
   attached to a guest, but the queue device is not passed through.
 
 - Rework struct ap_card to hold the whole adjunct-processor (AP) card
   hardware information. As result, all the ugly bit checks are replaced
   by simple evaluations of the required bit fields.
 
 - Improve handling of some weird scenarios between service element (SE)
   host and SE guest with adjunct-processor (AP) pass-through support.
 
 - Change local_ctl_set_bit() and local_ctl_clear_bit() so they return the
   previous value of the to be changed control register. This is useful if
   a bit is only changed temporarily and the previous content needs to be
   restored.
 
 - The kernel starts with machine checks disabled and is expected to enable
   it once trap_init() is called. However the implementation allows machine
   checks early. Consistently enable it in trap_init() only.
 
 - local_mcck_disable() and local_mcck_enable() assume that machine checks
   are always enabled. Instead implement and use local_mcck_save() and
   local_mcck_restore() to disable machine checks and restore the previous
   state.
 
 - Modification of floating point control (FPC) register of a traced
   process using ptrace interface may lead to corruption of the FPC
   register of the tracing process. Fix this.
 
 - kvm_arch_vcpu_ioctl_set_fpu() allows to set the floating point control
   (FPC) register in vCPU, but may lead to corruption of the FPC register
   of the host process. Fix this.
 
 - Use READ_ONCE() to read a vCPU floating point register value from the
   memory mapped area. This avoids that, depending on code generation,
   a different value is tested for validity than the one that is used.
 
 - Get rid of test_fp_ctl(), since it is quite subtle to use it correctly.
   Instead copy a new floating point control register value into its save
   area and test the validity of the new value when loading it.
 
 - Remove superfluous save_fpu_regs() call.
 
 - Remove s390 support for ARCH_WANTS_DYNAMIC_TASK_STRUCT. All machines
   provide the vector facility since many years and the need to make the
   task structure size dependent on the vector facility does not exist.
 
 - Remove the "novx" kernel command line option, as the vector code runs
   without any problems since many years.
 
 - Add the vector facility to the z13 architecture level set (ALS).
   All hypervisors support the vector facility since many years.
   This allows compile time optimizations of the kernel.
 
 - Get rid of MACHINE_HAS_VX and replace it with cpu_has_vx(). As result,
   the compiled code will have less runtime checks and less code.
 
 - Convert pgste_get_lock() and pgste_set_unlock() ASM inlines to C.
 
 - Convert the struct subchannel spinlock from pointer to member.
 -----BEGIN PGP SIGNATURE-----
 
 iI0EABYIADUWIQQrtrZiYVkVzKQcYivNdxKlNrRb8AUCZZxnchccYWdvcmRlZXZA
 bGludXguaWJtLmNvbQAKCRDNdxKlNrRb8PyGAP9Z0Z1Pm3hPf24M4FgY5uuRqBHo
 VoiuohOZRGONwifnsgEAmN/3ba/7d/j0iMwpUdUFouiqtwTUihh15wYx1sH2IA8=
 =F6YD
 -----END PGP SIGNATURE-----

Merge tag 's390-6.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux

Pull s390 updates from Alexander Gordeev:

 - Add machine variable capacity information to /proc/sysinfo.

 - Limit the waste of page tables and always align vmalloc area size and
   base address on segment boundary.

 - Fix a memory leak when an attempt to register interruption sub class
   (ISC) for the adjunct-processor (AP) guest failed.

 - Reset response code AP_RESPONSE_INVALID_GISA to understandable by
   guest AP_RESPONSE_INVALID_ADDRESS in response to a failed
   interruption sub class (ISC) registration attempt.

 - Improve reaction to adjunct-processor (AP)
   AP_RESPONSE_OTHERWISE_CHANGED response code when enabling interrupts
   on behalf of a guest.

 - Fix incorrect sysfs 'status' attribute of adjunct-processor (AP)
   queue device bound to the vfio_ap device driver when the mediated
   device is attached to a guest, but the queue device is not passed
   through.

 - Rework struct ap_card to hold the whole adjunct-processor (AP) card
   hardware information. As result, all the ugly bit checks are replaced
   by simple evaluations of the required bit fields.

 - Improve handling of some weird scenarios between service element (SE)
   host and SE guest with adjunct-processor (AP) pass-through support.

 - Change local_ctl_set_bit() and local_ctl_clear_bit() so they return
   the previous value of the to be changed control register. This is
   useful if a bit is only changed temporarily and the previous content
   needs to be restored.

 - The kernel starts with machine checks disabled and is expected to
   enable it once trap_init() is called. However the implementation
   allows machine checks early. Consistently enable it in trap_init()
   only.

 - local_mcck_disable() and local_mcck_enable() assume that machine
   checks are always enabled. Instead implement and use
   local_mcck_save() and local_mcck_restore() to disable machine checks
   and restore the previous state.

 - Modification of floating point control (FPC) register of a traced
   process using ptrace interface may lead to corruption of the FPC
   register of the tracing process. Fix this.

 - kvm_arch_vcpu_ioctl_set_fpu() allows to set the floating point
   control (FPC) register in vCPU, but may lead to corruption of the FPC
   register of the host process. Fix this.

 - Use READ_ONCE() to read a vCPU floating point register value from the
   memory mapped area. This avoids that, depending on code generation, a
   different value is tested for validity than the one that is used.

 - Get rid of test_fp_ctl(), since it is quite subtle to use it
   correctly. Instead copy a new floating point control register value
   into its save area and test the validity of the new value when
   loading it.

 - Remove superfluous save_fpu_regs() call.

 - Remove s390 support for ARCH_WANTS_DYNAMIC_TASK_STRUCT. All machines
   provide the vector facility since many years and the need to make the
   task structure size dependent on the vector facility does not exist.

 - Remove the "novx" kernel command line option, as the vector code runs
   without any problems since many years.

 - Add the vector facility to the z13 architecture level set (ALS). All
   hypervisors support the vector facility since many years. This allows
   compile time optimizations of the kernel.

 - Get rid of MACHINE_HAS_VX and replace it with cpu_has_vx(). As
   result, the compiled code will have less runtime checks and less
   code.

 - Convert pgste_get_lock() and pgste_set_unlock() ASM inlines to C.

 - Convert the struct subchannel spinlock from pointer to member.

* tag 's390-6.8-1' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: (24 commits)
  Revert "s390: update defconfigs"
  s390/cio: make sch->lock spinlock pointer a member
  s390: update defconfigs
  s390/mm: convert pgste locking functions to C
  s390/fpu: get rid of MACHINE_HAS_VX
  s390/als: add vector facility to z13 architecture level set
  s390/fpu: remove "novx" option
  s390/fpu: remove ARCH_WANTS_DYNAMIC_TASK_STRUCT support
  KVM: s390: remove superfluous save_fpu_regs() call
  s390/fpu: get rid of test_fp_ctl()
  KVM: s390: use READ_ONCE() to read fpc register value
  KVM: s390: fix setting of fpc register
  s390/ptrace: handle setting of fpc register correctly
  s390/nmi: implement and use local_mcck_save() / local_mcck_restore()
  s390/nmi: consistently enable machine checks in trap_init()
  s390/ctlreg: return old register contents when changing bits
  s390/ap: handle outband SE bind state change
  s390/ap: store TAPQ hwinfo in struct ap_card
  s390/vfio-ap: fix sysfs status attribute for AP queue devices
  s390/vfio-ap: improve reaction to response code 07 from PQAP(AQIC) command
  ...
2024-01-10 18:18:20 -08:00

397 lines
10 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* S390 version
* Copyright IBM Corp. 1999
* Author(s): Hartmut Penner (hp@de.ibm.com),
* Martin Schwidefsky (schwidefsky@de.ibm.com)
*
* Derived from "include/asm-i386/processor.h"
* Copyright (C) 1994, Linus Torvalds
*/
#ifndef __ASM_S390_PROCESSOR_H
#define __ASM_S390_PROCESSOR_H
#include <linux/bits.h>
#define CIF_NOHZ_DELAY 2 /* delay HZ disable for a tick */
#define CIF_FPU 3 /* restore FPU registers */
#define CIF_ENABLED_WAIT 5 /* in enabled wait state */
#define CIF_MCCK_GUEST 6 /* machine check happening in guest */
#define CIF_DEDICATED_CPU 7 /* this CPU is dedicated */
#define _CIF_NOHZ_DELAY BIT(CIF_NOHZ_DELAY)
#define _CIF_FPU BIT(CIF_FPU)
#define _CIF_ENABLED_WAIT BIT(CIF_ENABLED_WAIT)
#define _CIF_MCCK_GUEST BIT(CIF_MCCK_GUEST)
#define _CIF_DEDICATED_CPU BIT(CIF_DEDICATED_CPU)
#define RESTART_FLAG_CTLREGS _AC(1 << 0, U)
#ifndef __ASSEMBLY__
#include <linux/cpumask.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
#include <asm/cpu.h>
#include <asm/page.h>
#include <asm/ptrace.h>
#include <asm/setup.h>
#include <asm/runtime_instr.h>
#include <asm/fpu/types.h>
#include <asm/fpu/internal.h>
#include <asm/irqflags.h>
typedef long (*sys_call_ptr_t)(struct pt_regs *regs);
static __always_inline void set_cpu_flag(int flag)
{
S390_lowcore.cpu_flags |= (1UL << flag);
}
static __always_inline void clear_cpu_flag(int flag)
{
S390_lowcore.cpu_flags &= ~(1UL << flag);
}
static __always_inline bool test_cpu_flag(int flag)
{
return S390_lowcore.cpu_flags & (1UL << flag);
}
static __always_inline bool test_and_set_cpu_flag(int flag)
{
if (test_cpu_flag(flag))
return true;
set_cpu_flag(flag);
return false;
}
static __always_inline bool test_and_clear_cpu_flag(int flag)
{
if (!test_cpu_flag(flag))
return false;
clear_cpu_flag(flag);
return true;
}
/*
* Test CIF flag of another CPU. The caller needs to ensure that
* CPU hotplug can not happen, e.g. by disabling preemption.
*/
static __always_inline bool test_cpu_flag_of(int flag, int cpu)
{
struct lowcore *lc = lowcore_ptr[cpu];
return lc->cpu_flags & (1UL << flag);
}
#define arch_needs_cpu() test_cpu_flag(CIF_NOHZ_DELAY)
static inline void get_cpu_id(struct cpuid *ptr)
{
asm volatile("stidp %0" : "=Q" (*ptr));
}
void s390_adjust_jiffies(void);
void s390_update_cpu_mhz(void);
void cpu_detect_mhz_feature(void);
extern const struct seq_operations cpuinfo_op;
extern void execve_tail(void);
unsigned long vdso_size(void);
/*
* User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit.
*/
#define TASK_SIZE (test_thread_flag(TIF_31BIT) ? \
_REGION3_SIZE : TASK_SIZE_MAX)
#define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \
(_REGION3_SIZE >> 1) : (_REGION2_SIZE >> 1))
#define TASK_SIZE_MAX (-PAGE_SIZE)
#define VDSO_BASE (STACK_TOP + PAGE_SIZE)
#define VDSO_LIMIT (test_thread_flag(TIF_31BIT) ? _REGION3_SIZE : _REGION2_SIZE)
#define STACK_TOP (VDSO_LIMIT - vdso_size() - PAGE_SIZE)
#define STACK_TOP_MAX (_REGION2_SIZE - vdso_size() - PAGE_SIZE)
#define HAVE_ARCH_PICK_MMAP_LAYOUT
#define __stackleak_poison __stackleak_poison
static __always_inline void __stackleak_poison(unsigned long erase_low,
unsigned long erase_high,
unsigned long poison)
{
unsigned long tmp, count;
count = erase_high - erase_low;
if (!count)
return;
asm volatile(
" cghi %[count],8\n"
" je 2f\n"
" aghi %[count],-(8+1)\n"
" srlg %[tmp],%[count],8\n"
" ltgr %[tmp],%[tmp]\n"
" jz 1f\n"
"0: stg %[poison],0(%[addr])\n"
" mvc 8(256-8,%[addr]),0(%[addr])\n"
" la %[addr],256(%[addr])\n"
" brctg %[tmp],0b\n"
"1: stg %[poison],0(%[addr])\n"
" larl %[tmp],3f\n"
" ex %[count],0(%[tmp])\n"
" j 4f\n"
"2: stg %[poison],0(%[addr])\n"
" j 4f\n"
"3: mvc 8(1,%[addr]),0(%[addr])\n"
"4:\n"
: [addr] "+&a" (erase_low), [count] "+&d" (count), [tmp] "=&a" (tmp)
: [poison] "d" (poison)
: "memory", "cc"
);
}
/*
* Thread structure
*/
struct thread_struct {
unsigned int acrs[NUM_ACRS];
unsigned long ksp; /* kernel stack pointer */
unsigned long user_timer; /* task cputime in user space */
unsigned long guest_timer; /* task cputime in kvm guest */
unsigned long system_timer; /* task cputime in kernel space */
unsigned long hardirq_timer; /* task cputime in hardirq context */
unsigned long softirq_timer; /* task cputime in softirq context */
const sys_call_ptr_t *sys_call_table; /* system call table address */
unsigned long gmap_addr; /* address of last gmap fault. */
unsigned int gmap_write_flag; /* gmap fault write indication */
unsigned int gmap_int_code; /* int code of last gmap fault */
unsigned int gmap_pfault; /* signal of a pending guest pfault */
/* Per-thread information related to debugging */
struct per_regs per_user; /* User specified PER registers */
struct per_event per_event; /* Cause of the last PER trap */
unsigned long per_flags; /* Flags to control debug behavior */
unsigned int system_call; /* system call number in signal */
unsigned long last_break; /* last breaking-event-address. */
/* pfault_wait is used to block the process on a pfault event */
unsigned long pfault_wait;
struct list_head list;
/* cpu runtime instrumentation */
struct runtime_instr_cb *ri_cb;
struct gs_cb *gs_cb; /* Current guarded storage cb */
struct gs_cb *gs_bc_cb; /* Broadcast guarded storage cb */
struct pgm_tdb trap_tdb; /* Transaction abort diagnose block */
struct fpu fpu; /* FP and VX register save area */
};
/* Flag to disable transactions. */
#define PER_FLAG_NO_TE 1UL
/* Flag to enable random transaction aborts. */
#define PER_FLAG_TE_ABORT_RAND 2UL
/* Flag to specify random transaction abort mode:
* - abort each transaction at a random instruction before TEND if set.
* - abort random transactions at a random instruction if cleared.
*/
#define PER_FLAG_TE_ABORT_RAND_TEND 4UL
typedef struct thread_struct thread_struct;
#define ARCH_MIN_TASKALIGN 8
#define INIT_THREAD { \
.ksp = sizeof(init_stack) + (unsigned long) &init_stack, \
.fpu.regs = (void *) init_task.thread.fpu.fprs, \
.last_break = 1, \
}
/*
* Do necessary setup to start up a new thread.
*/
#define start_thread(regs, new_psw, new_stackp) do { \
regs->psw.mask = PSW_USER_BITS | PSW_MASK_EA | PSW_MASK_BA; \
regs->psw.addr = new_psw; \
regs->gprs[15] = new_stackp; \
execve_tail(); \
} while (0)
#define start_thread31(regs, new_psw, new_stackp) do { \
regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \
regs->psw.addr = new_psw; \
regs->gprs[15] = new_stackp; \
execve_tail(); \
} while (0)
struct task_struct;
struct mm_struct;
struct seq_file;
struct pt_regs;
void show_registers(struct pt_regs *regs);
void show_cacheinfo(struct seq_file *m);
/* Free guarded storage control block */
void guarded_storage_release(struct task_struct *tsk);
void gs_load_bc_cb(struct pt_regs *regs);
unsigned long __get_wchan(struct task_struct *p);
#define task_pt_regs(tsk) ((struct pt_regs *) \
(task_stack_page(tsk) + THREAD_SIZE) - 1)
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->psw.addr)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->gprs[15])
/* Has task runtime instrumentation enabled ? */
#define is_ri_task(tsk) (!!(tsk)->thread.ri_cb)
/* avoid using global register due to gcc bug in versions < 8.4 */
#define current_stack_pointer (__current_stack_pointer())
static __always_inline unsigned long __current_stack_pointer(void)
{
unsigned long sp;
asm volatile("lgr %0,15" : "=d" (sp));
return sp;
}
static __always_inline bool on_thread_stack(void)
{
unsigned long ksp = S390_lowcore.kernel_stack;
return !((ksp ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
}
static __always_inline unsigned short stap(void)
{
unsigned short cpu_address;
asm volatile("stap %0" : "=Q" (cpu_address));
return cpu_address;
}
#define cpu_relax() barrier()
#define ECAG_CACHE_ATTRIBUTE 0
#define ECAG_CPU_ATTRIBUTE 1
static inline unsigned long __ecag(unsigned int asi, unsigned char parm)
{
unsigned long val;
asm volatile("ecag %0,0,0(%1)" : "=d" (val) : "a" (asi << 8 | parm));
return val;
}
static inline void psw_set_key(unsigned int key)
{
asm volatile("spka 0(%0)" : : "d" (key));
}
/*
* Set PSW to specified value.
*/
static inline void __load_psw(psw_t psw)
{
asm volatile("lpswe %0" : : "Q" (psw) : "cc");
}
/*
* Set PSW mask to specified value, while leaving the
* PSW addr pointing to the next instruction.
*/
static __always_inline void __load_psw_mask(unsigned long mask)
{
unsigned long addr;
psw_t psw;
psw.mask = mask;
asm volatile(
" larl %0,1f\n"
" stg %0,%1\n"
" lpswe %2\n"
"1:"
: "=&d" (addr), "=Q" (psw.addr) : "Q" (psw) : "memory", "cc");
}
/*
* Extract current PSW mask
*/
static inline unsigned long __extract_psw(void)
{
unsigned int reg1, reg2;
asm volatile("epsw %0,%1" : "=d" (reg1), "=a" (reg2));
return (((unsigned long) reg1) << 32) | ((unsigned long) reg2);
}
static inline unsigned long __local_mcck_save(void)
{
unsigned long mask = __extract_psw();
__load_psw_mask(mask & ~PSW_MASK_MCHECK);
return mask & PSW_MASK_MCHECK;
}
#define local_mcck_save(mflags) \
do { \
typecheck(unsigned long, mflags); \
mflags = __local_mcck_save(); \
} while (0)
static inline void local_mcck_restore(unsigned long mflags)
{
unsigned long mask = __extract_psw();
mask &= ~PSW_MASK_MCHECK;
__load_psw_mask(mask | mflags);
}
static inline void local_mcck_disable(void)
{
__local_mcck_save();
}
static inline void local_mcck_enable(void)
{
__load_psw_mask(__extract_psw() | PSW_MASK_MCHECK);
}
/*
* Rewind PSW instruction address by specified number of bytes.
*/
static inline unsigned long __rewind_psw(psw_t psw, unsigned long ilc)
{
unsigned long mask;
mask = (psw.mask & PSW_MASK_EA) ? -1UL :
(psw.mask & PSW_MASK_BA) ? (1UL << 31) - 1 :
(1UL << 24) - 1;
return (psw.addr - ilc) & mask;
}
/*
* Function to drop a processor into disabled wait state
*/
static __always_inline void __noreturn disabled_wait(void)
{
psw_t psw;
psw.mask = PSW_MASK_BASE | PSW_MASK_WAIT | PSW_MASK_BA | PSW_MASK_EA;
psw.addr = _THIS_IP_;
__load_psw(psw);
while (1);
}
#define ARCH_LOW_ADDRESS_LIMIT 0x7fffffffUL
static __always_inline bool regs_irqs_disabled(struct pt_regs *regs)
{
return arch_irqs_disabled_flags(regs->psw.mask);
}
#endif /* __ASSEMBLY__ */
#endif /* __ASM_S390_PROCESSOR_H */