Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 41ac4ad..a65cb49 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -76,6 +76,7 @@
OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift);
OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir);
OFFSET(__VDSO_TS_END, vdso_data, ts_end);
+ OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res);
OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base);
OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time);
OFFSET(__VDSO_CPU_NR, vdso_per_cpu_data, cpu_nr);
@@ -87,7 +88,6 @@
DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID);
- DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC);
BLANK();
/* idle data offsets */
@@ -125,6 +125,8 @@
OFFSET(__LC_EXT_DAMAGE_CODE, lowcore, external_damage_code);
OFFSET(__LC_MCCK_FAIL_STOR_ADDR, lowcore, failing_storage_address);
OFFSET(__LC_LAST_BREAK, lowcore, breaking_event_addr);
+ OFFSET(__LC_RETURN_LPSWE, lowcore, return_lpswe);
+ OFFSET(__LC_RETURN_MCCK_LPSWE, lowcore, return_mcck_lpswe);
OFFSET(__LC_RST_OLD_PSW, lowcore, restart_old_psw);
OFFSET(__LC_EXT_OLD_PSW, lowcore, external_old_psw);
OFFSET(__LC_SVC_OLD_PSW, lowcore, svc_old_psw);
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index af013b4..2da0273 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -37,10 +37,12 @@
static int diag8_response(int cmdlen, char *response, int *rlen)
{
+ unsigned long _cmdlen = cmdlen | 0x40000000L;
+ unsigned long _rlen = *rlen;
register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
register unsigned long reg3 asm ("3") = (addr_t) response;
- register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
- register unsigned long reg5 asm ("5") = *rlen;
+ register unsigned long reg4 asm ("4") = _cmdlen;
+ register unsigned long reg5 asm ("5") = _rlen;
asm volatile(
" diag %2,%0,0x8\n"
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 6d321f5..b1aadc3 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -198,9 +198,10 @@
if (!areas)
goto fail_malloc_areas;
for (i = 0; i < nr_areas; i++) {
+ /* GFP_NOWARN to avoid user triggerable WARN, we handle fails */
areas[i] = kmalloc_array(pages_per_area,
sizeof(debug_entry_t *),
- GFP_KERNEL);
+ GFP_KERNEL | __GFP_NOWARN);
if (!areas[i])
goto fail_malloc_areas2;
for (j = 0; j < pages_per_area; j++) {
@@ -326,24 +327,6 @@
goto out;
rc->mode = mode & ~S_IFMT;
-
- /* create root directory */
- rc->debugfs_root_entry = debugfs_create_dir(rc->name,
- debug_debugfs_root_entry);
-
- /* append new element to linked list */
- if (!debug_area_first) {
- /* first element in list */
- debug_area_first = rc;
- rc->prev = NULL;
- } else {
- /* append element to end of list */
- debug_area_last->next = rc;
- rc->prev = debug_area_last;
- }
- debug_area_last = rc;
- rc->next = NULL;
-
refcount_set(&rc->ref_count, 1);
out:
return rc;
@@ -403,27 +386,10 @@
*/
static void debug_info_put(debug_info_t *db_info)
{
- int i;
-
if (!db_info)
return;
- if (refcount_dec_and_test(&db_info->ref_count)) {
- for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
- if (!db_info->views[i])
- continue;
- debugfs_remove(db_info->debugfs_entries[i]);
- }
- debugfs_remove(db_info->debugfs_root_entry);
- if (db_info == debug_area_first)
- debug_area_first = db_info->next;
- if (db_info == debug_area_last)
- debug_area_last = db_info->prev;
- if (db_info->prev)
- db_info->prev->next = db_info->next;
- if (db_info->next)
- db_info->next->prev = db_info->prev;
+ if (refcount_dec_and_test(&db_info->ref_count))
debug_info_free(db_info);
- }
}
/*
@@ -647,6 +613,31 @@
return 0; /* success */
}
+/* Create debugfs entries and add to internal list. */
+static void _debug_register(debug_info_t *id)
+{
+ /* create root directory */
+ id->debugfs_root_entry = debugfs_create_dir(id->name,
+ debug_debugfs_root_entry);
+
+ /* append new element to linked list */
+ if (!debug_area_first) {
+ /* first element in list */
+ debug_area_first = id;
+ id->prev = NULL;
+ } else {
+ /* append element to end of list */
+ debug_area_last->next = id;
+ id->prev = debug_area_last;
+ }
+ debug_area_last = id;
+ id->next = NULL;
+
+ debug_register_view(id, &debug_level_view);
+ debug_register_view(id, &debug_flush_view);
+ debug_register_view(id, &debug_pages_view);
+}
+
/**
* debug_register_mode() - creates and initializes debug area.
*
@@ -676,19 +667,16 @@
if ((uid != 0) || (gid != 0))
pr_warn("Root becomes the owner of all s390dbf files in sysfs\n");
BUG_ON(!initialized);
- mutex_lock(&debug_mutex);
/* create new debug_info */
rc = debug_info_create(name, pages_per_area, nr_areas, buf_size, mode);
- if (!rc)
- goto out;
- debug_register_view(rc, &debug_level_view);
- debug_register_view(rc, &debug_flush_view);
- debug_register_view(rc, &debug_pages_view);
-out:
- if (!rc)
+ if (rc) {
+ mutex_lock(&debug_mutex);
+ _debug_register(rc);
+ mutex_unlock(&debug_mutex);
+ } else {
pr_err("Registering debug feature %s failed\n", name);
- mutex_unlock(&debug_mutex);
+ }
return rc;
}
EXPORT_SYMBOL(debug_register_mode);
@@ -717,6 +705,27 @@
}
EXPORT_SYMBOL(debug_register);
+/* Remove debugfs entries and remove from internal list. */
+static void _debug_unregister(debug_info_t *id)
+{
+ int i;
+
+ for (i = 0; i < DEBUG_MAX_VIEWS; i++) {
+ if (!id->views[i])
+ continue;
+ debugfs_remove(id->debugfs_entries[i]);
+ }
+ debugfs_remove(id->debugfs_root_entry);
+ if (id == debug_area_first)
+ debug_area_first = id->next;
+ if (id == debug_area_last)
+ debug_area_last = id->prev;
+ if (id->prev)
+ id->prev->next = id->next;
+ if (id->next)
+ id->next->prev = id->prev;
+}
+
/**
* debug_unregister() - give back debug area.
*
@@ -730,8 +739,10 @@
if (!id)
return;
mutex_lock(&debug_mutex);
- debug_info_put(id);
+ _debug_unregister(id);
mutex_unlock(&debug_mutex);
+
+ debug_info_put(id);
}
EXPORT_SYMBOL(debug_unregister);
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index e9dac9a..ccba63a 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -84,7 +84,7 @@
static void *show_diag_stat_start(struct seq_file *m, loff_t *pos)
{
- return *pos <= nr_cpu_ids ? (void *)((unsigned long) *pos + 1) : NULL;
+ return *pos <= NR_DIAG_STAT ? (void *)((unsigned long) *pos + 1) : NULL;
}
static void *show_diag_stat_next(struct seq_file *m, void *v, loff_t *pos)
@@ -133,7 +133,7 @@
}
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/dis.c b/arch/s390/kernel/dis.c
index 7abe6ae..03e35b3 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -461,10 +461,11 @@
ptr += sprintf(ptr, "%%c%i", value);
else if (operand->flags & OPERAND_VR)
ptr += sprintf(ptr, "%%v%i", value);
- else if (operand->flags & OPERAND_PCREL)
- ptr += sprintf(ptr, "%lx", (signed int) value
- + addr);
- else if (operand->flags & OPERAND_SIGNED)
+ else if (operand->flags & OPERAND_PCREL) {
+ void *pcrel = (void *)((int)value + addr);
+
+ ptr += sprintf(ptr, "%px", pcrel);
+ } else if (operand->flags & OPERAND_SIGNED)
ptr += sprintf(ptr, "%i", value);
else
ptr += sprintf(ptr, "%u", value);
@@ -536,7 +537,7 @@
else
*ptr++ = ' ';
addr = regs->psw.addr + start - 32;
- ptr += sprintf(ptr, "%016lx: ", addr);
+ ptr += sprintf(ptr, "%px: ", (void *)addr);
if (start + opsize >= end)
break;
for (i = 0; i < opsize; i++)
@@ -556,7 +557,7 @@
void print_fn_code(unsigned char *code, unsigned long len)
{
- char buffer[64], *ptr;
+ char buffer[128], *ptr;
int opsize, i;
while (len) {
@@ -564,7 +565,7 @@
opsize = insn_length(*code);
if (opsize > len)
break;
- ptr += sprintf(ptr, "%p: ", code);
+ ptr += sprintf(ptr, "%px: ", code);
for (i = 0; i < opsize; i++)
ptr += sprintf(ptr, "%02x", code[i]);
*ptr++ = '\t';
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index b432d63..eb89cb0 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -169,6 +169,8 @@
psw_t psw;
psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+ if (IS_ENABLED(CONFIG_KASAN))
+ psw.mask |= PSW_MASK_DAT;
psw.addr = (unsigned long) s390_base_ext_handler;
S390_lowcore.external_new_psw = psw;
psw.addr = (unsigned long) s390_base_pgm_handler;
@@ -250,6 +252,10 @@
clock_comparator_max = -1ULL >> 1;
__ctl_set_bit(0, 53);
}
+ if (IS_ENABLED(CONFIG_PCI) && test_facility(153)) {
+ S390_lowcore.machine_flags |= MACHINE_FLAG_PCI_MIO;
+ /* the control bit is set during PCI initialization */
+ }
}
static inline void save_vector_registers(void)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 270d1d1..5cba181 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -115,26 +115,29 @@
.macro SWITCH_ASYNC savearea,timer
tmhh %r8,0x0001 # interrupting from user ?
- jnz 1f
+ jnz 2f
lgr %r14,%r9
+ cghi %r14,__LC_RETURN_LPSWE
+ je 0f
slg %r14,BASED(.Lcritical_start)
clg %r14,BASED(.Lcritical_length)
- jhe 0f
+ jhe 1f
+0:
lghi %r11,\savearea # inside critical section, do cleanup
brasl %r14,cleanup_critical
tmhh %r8,0x0001 # retest problem state after cleanup
- jnz 1f
-0: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
+ jnz 2f
+1: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
slgr %r14,%r15
srag %r14,%r14,STACK_SHIFT
- jnz 2f
+ jnz 3f
CHECK_STACK \savearea
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- j 3f
-1: UPDATE_VTIME %r14,%r15,\timer
+ j 4f
+2: UPDATE_VTIME %r14,%r15,\timer
BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
-2: lg %r15,__LC_ASYNC_STACK # load async stack
-3: la %r11,STACK_FRAME_OVERHEAD(%r15)
+3: lg %r15,__LC_ASYNC_STACK # load async stack
+4: la %r11,STACK_FRAME_OVERHEAD(%r15)
.endm
.macro UPDATE_VTIME w1,w2,enter_timer
@@ -365,9 +368,9 @@
jnz .Lsysc_nr_ok
# svc 0: system call number in %r1
llgfr %r1,%r1 # clear high word in r1
+ sth %r1,__PT_INT_CODE+2(%r11)
cghi %r1,NR_syscalls
jnl .Lsysc_nr_ok
- sth %r1,__PT_INT_CODE+2(%r11)
slag %r8,%r1,3
.Lsysc_nr_ok:
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
@@ -401,7 +404,7 @@
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
lmg %r11,%r15,__PT_R11(%r11)
- lpswe __LC_RETURN_PSW
+ b __LC_RETURN_LPSWE(%r0)
.Lsysc_done:
#
@@ -608,43 +611,50 @@
BPOFF
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
lg %r10,__LC_LAST_BREAK
- lg %r12,__LC_CURRENT
+ srag %r11,%r10,12
+ jnz 0f
+ /* if __LC_LAST_BREAK is < 4096, it contains one of
+ * the lpswe addresses in lowcore. Set it to 1 (initial state)
+ * to prevent leaking that address to userspace.
+ */
+ 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 2f # -> fault in user space
+ 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)
- jhe 0f
+ jhe 1f
lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
lghi %r11,_PIF_GUEST_FAULT
#endif
-0: tmhh %r8,0x4000 # PER bit set in old PSW ?
- jnz 1f # -> enabled, can't be a double fault
+1: tmhh %r8,0x4000 # PER bit set in old PSW ?
+ jnz 2f # -> enabled, can't be a double fault
tm __LC_PGM_ILC+3,0x80 # check for per exception
jnz .Lpgm_svcper # -> single stepped svc
-1: CHECK_STACK __LC_SAVE_AREA_SYNC
+2: CHECK_STACK __LC_SAVE_AREA_SYNC
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- # CHECK_VMAP_STACK branches to stack_overflow or 4f
- CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,4f
-2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
+ # CHECK_VMAP_STACK branches to stack_overflow or 5f
+ CHECK_VMAP_STACK __LC_SAVE_AREA_SYNC,5f
+3: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER
BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lg %r15,__LC_KERNEL_STACK
lgr %r14,%r12
aghi %r14,__TASK_thread # pointer to thread_struct
lghi %r13,__LC_PGM_TDB
tm __LC_PGM_ILC+2,0x02 # check for transaction abort
- jz 3f
+ jz 4f
mvc __THREAD_trap_tdb(256,%r14),0(%r13)
-3: stg %r10,__THREAD_last_break(%r14)
-4: lgr %r13,%r11
+4: stg %r10,__THREAD_last_break(%r14)
+5: lgr %r13,%r11
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
# clear user controlled registers to prevent speculative use
@@ -663,14 +673,14 @@
stg %r13,__PT_FLAGS(%r11)
stg %r10,__PT_ARGS(%r11)
tm __LC_PGM_ILC+3,0x80 # check for per exception
- jz 5f
+ jz 6f
tmhh %r8,0x0001 # kernel per event ?
jz .Lpgm_kprobe
oi __PT_FLAGS+7(%r11),_PIF_PER_TRAP
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
-5: REENABLE_IRQS
+6: REENABLE_IRQS
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
larl %r1,pgm_check_table
llgh %r10,__PT_INT_CODE+2(%r11)
@@ -775,7 +785,7 @@
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
.Lio_exit_kernel:
lmg %r11,%r15,__PT_R11(%r11)
- lpswe __LC_RETURN_PSW
+ b __LC_RETURN_LPSWE(%r0)
.Lio_done:
#
@@ -983,6 +993,7 @@
* Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
*/
ENTRY(psw_idle)
+ stg %r14,(__SF_GPRS+8*8)(%r15)
stg %r3,__SF_EMPTY(%r15)
larl %r1,.Lpsw_idle_lpsw+4
stg %r1,__SF_EMPTY+8(%r15)
@@ -1214,7 +1225,7 @@
stpt __LC_EXIT_TIMER
mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER
0: lmg %r11,%r15,__PT_R11(%r11)
- lpswe __LC_RETURN_MCCK_PSW
+ b __LC_RETURN_MCCK_LPSWE
.Lmcck_panic:
lg %r15,__LC_NODAT_STACK
@@ -1271,6 +1282,8 @@
#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
@@ -1424,6 +1437,7 @@
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:
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 1bb85f6..7df6b26 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -57,6 +57,7 @@
* > brasl %r0,ftrace_caller # offset 0
*/
+void *ftrace_func __read_mostly = ftrace_stub;
unsigned long ftrace_plt;
static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
@@ -166,6 +167,7 @@
int ftrace_update_ftrace_func(ftrace_func_t func)
{
+ ftrace_func = func;
return 0;
}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 8371855..da550cb 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -294,11 +294,6 @@
return IRQ_HANDLED;
}
-static struct irqaction external_interrupt = {
- .name = "EXT",
- .handler = do_ext_interrupt,
-};
-
void __init init_ext_interrupts(void)
{
int idx;
@@ -308,7 +303,8 @@
irq_set_chip_and_handler(EXT_INTERRUPT,
&dummy_irq_chip, handle_percpu_irq);
- setup_irq(EXT_INTERRUPT, &external_interrupt);
+ if (request_irq(EXT_INTERRUPT, do_ext_interrupt, 0, "EXT", NULL))
+ panic("Failed to register EXT interrupt\n");
}
static DEFINE_SPINLOCK(irq_subclass_lock);
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index ab584e8..9156653 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -36,7 +36,7 @@
unsigned char *ipe = (unsigned char *)expected;
unsigned char *ipn = (unsigned char *)new;
- pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc);
+ pr_emerg("Jump label code mismatch at %pS [%px]\n", ipc, ipc);
pr_emerg("Found: %6ph\n", ipc);
pr_emerg("Expected: %6ph\n", ipe);
pr_emerg("New: %6ph\n", ipn);
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 444a191..cb8b1cc 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -164,7 +164,9 @@
#ifdef CONFIG_CRASH_DUMP
int rc;
+ preempt_disable();
rc = CALL_ON_STACK(do_start_kdump, S390_lowcore.nodat_stack, 1, image);
+ preempt_enable();
return rc == 0;
#else
return false;
@@ -254,10 +256,10 @@
VMCOREINFO_SYMBOL(lowcore_ptr);
VMCOREINFO_SYMBOL(high_memory);
VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
- mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
vmcoreinfo_append_str("EDMA=%lx\n", __edma);
vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+ mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
}
void machine_shutdown(void)
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 8415ae7..f9e4baa 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -151,7 +151,7 @@
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 d5035de..b7182ce 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -28,6 +28,7 @@
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/mcount.S b/arch/s390/kernel/mcount.S
index 9e1660a..14bad57 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -26,6 +26,12 @@
#define STACK_PTREGS (STACK_FRAME_OVERHEAD)
#define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS)
#define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW)
+#ifdef __PACK_STACK
+/* allocate just enough for r14, r15 and backchain */
+#define TRACED_FUNC_FRAME_SIZE 24
+#else
+#define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD
+#endif
ENTRY(_mcount)
BR_EX %r14
@@ -35,25 +41,33 @@
ENTRY(ftrace_caller)
.globl ftrace_regs_caller
.set ftrace_regs_caller,ftrace_caller
+ stg %r14,(__SF_GPRS+8*8)(%r15) # save traced function caller
lgr %r1,%r15
#if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT))
aghi %r0,MCOUNT_RETURN_FIXUP
#endif
- aghi %r15,-STACK_FRAME_SIZE
+ # allocate stack frame for ftrace_caller to contain traced function
+ aghi %r15,-TRACED_FUNC_FRAME_SIZE
stg %r1,__SF_BACKCHAIN(%r15)
+ stg %r0,(__SF_GPRS+8*8)(%r15)
+ stg %r15,(__SF_GPRS+9*8)(%r15)
+ # allocate pt_regs and stack frame for ftrace_trace_function
+ aghi %r15,-STACK_FRAME_SIZE
stg %r1,(STACK_PTREGS_GPRS+15*8)(%r15)
+ aghi %r1,-TRACED_FUNC_FRAME_SIZE
+ stg %r1,__SF_BACKCHAIN(%r15)
stg %r0,(STACK_PTREGS_PSW+8)(%r15)
stmg %r2,%r14,(STACK_PTREGS_GPRS+2*8)(%r15)
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
aghik %r2,%r0,-MCOUNT_INSN_SIZE
lgrl %r4,function_trace_op
- lgrl %r1,ftrace_trace_function
+ lgrl %r1,ftrace_func
#else
lgr %r2,%r0
aghi %r2,-MCOUNT_INSN_SIZE
larl %r4,function_trace_op
lg %r4,0(%r4)
- larl %r1,ftrace_trace_function
+ larl %r1,ftrace_func
lg %r1,0(%r1)
#endif
lgr %r3,%r14
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 48d48b6..0eb1d1c 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -199,7 +199,7 @@
[PERF_COUNT_HW_BUS_CYCLES] = -1,
};
-static int __hw_perf_event_init(struct perf_event *event)
+static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
{
struct perf_event_attr *attr = &event->attr;
struct hw_perf_event *hwc = &event->hw;
@@ -207,7 +207,7 @@
int err = 0;
u64 ev;
- switch (attr->type) {
+ switch (type) {
case PERF_TYPE_RAW:
/* Raw events are used to access counters directly,
* hence do not permit excludes */
@@ -294,17 +294,16 @@
static int cpumf_pmu_event_init(struct perf_event *event)
{
+ unsigned int type = event->attr.type;
int err;
- switch (event->attr.type) {
- case PERF_TYPE_HARDWARE:
- case PERF_TYPE_HW_CACHE:
- case PERF_TYPE_RAW:
- err = __hw_perf_event_init(event);
- break;
- default:
+ if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW)
+ err = __hw_perf_event_init(event, type);
+ else if (event->pmu->type == type)
+ /* Registered as unknown PMU */
+ err = __hw_perf_event_init(event, PERF_TYPE_RAW);
+ else
return -ENOENT;
- }
if (unlikely(err) && event->destroy)
event->destroy(event);
@@ -553,7 +552,7 @@
return -ENODEV;
cpumf_pmu.attr_groups = cpumf_cf_event_group();
- rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
+ rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", -1);
if (rc)
pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
return rc;
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 2654e34..e949ab8 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -243,13 +243,13 @@
int err = -ENOENT;
debug_sprintf_event(cf_diag_dbg, 5,
- "%s event %p cpu %d config %#llx "
+ "%s event %p cpu %d config %#llx type:%u "
"sample_type %#llx cf_diag_events %d\n", __func__,
- event, event->cpu, attr->config, attr->sample_type,
- atomic_read(&cf_diag_events));
+ event, event->cpu, attr->config, event->pmu->type,
+ attr->sample_type, atomic_read(&cf_diag_events));
if (event->attr.config != PERF_EVENT_CPUM_CF_DIAG ||
- event->attr.type != PERF_TYPE_RAW)
+ event->attr.type != event->pmu->type)
goto out;
/* Raw events are used to access counters directly,
@@ -693,7 +693,7 @@
}
debug_register_view(cf_diag_dbg, &debug_sprintf_view);
- rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", PERF_TYPE_RAW);
+ rc = perf_pmu_register(&cf_diag, "cpum_cf_diag", -1);
if (rc) {
debug_unregister_view(cf_diag_dbg, &debug_sprintf_view);
debug_unregister(cf_diag_dbg);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3d8b12a..b83bddf 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -193,7 +193,7 @@
unsigned long num_sdb, gfp_t gfp_flags)
{
int i, rc;
- unsigned long *new, *tail;
+ unsigned long *new, *tail, *tail_prev = NULL;
if (!sfb->sdbt || !sfb->tail)
return -EINVAL;
@@ -232,6 +232,7 @@
sfb->num_sdbt++;
/* Link current page to tail of chain */
*tail = (unsigned long)(void *) new + 1;
+ tail_prev = tail;
tail = new;
}
@@ -241,10 +242,22 @@
* issue, a new realloc call (if required) might succeed.
*/
rc = alloc_sample_data_block(tail, gfp_flags);
- if (rc)
+ if (rc) {
+ /* Undo last SDBT. An SDBT with no SDB at its first
+ * entry but with an SDBT entry instead can not be
+ * handled by the interrupt handler code.
+ * Avoid this situation.
+ */
+ if (tail_prev) {
+ sfb->num_sdbt--;
+ free_page((unsigned long) new);
+ tail = tail_prev;
+ }
break;
+ }
sfb->num_sdb++;
tail++;
+ tail_prev = new = NULL; /* Allocated at least one SBD */
}
/* Link sampling buffer to its origin */
@@ -1300,18 +1313,28 @@
*/
if (flush_all && done)
break;
-
- /* If an event overflow happened, discard samples by
- * processing any remaining sample-data-blocks.
- */
- if (event_overflow)
- flush_all = 1;
}
/* Account sample overflows in the event hardware structure */
if (sampl_overflow)
OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
sampl_overflow, 1 + num_sdb);
+
+ /* Perf_event_overflow() and perf_event_account_interrupt() limit
+ * the interrupt rate to an upper limit. Roughly 1000 samples per
+ * task tick.
+ * Hitting this limit results in a large number
+ * of throttled REF_REPORT_THROTTLE entries and the samples
+ * are dropped.
+ * Slightly increase the interval to avoid hitting this limit.
+ */
+ if (event_overflow) {
+ SAMPL_RATE(hwc) += DIV_ROUND_UP(SAMPL_RATE(hwc), 10);
+ debug_sprintf_event(sfdbg, 1, "%s: rate adjustment %ld\n",
+ __func__,
+ DIV_ROUND_UP(SAMPL_RATE(hwc), 10));
+ }
+
if (sampl_overflow || event_overflow)
debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
"overflow stats: sample=%llu event=%llu\n",
@@ -1406,8 +1429,8 @@
idx = aux->empty_mark + 1;
for (i = 0; i < range_scan; i++, idx++) {
te = aux_sdb_trailer(aux, idx);
- te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
- te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK;
+ te->flags &= ~(SDB_TE_BUFFER_FULL_MASK |
+ SDB_TE_ALERT_REQ_MASK);
te->overflow = 0;
}
/* Save the position of empty SDBs */
@@ -1454,8 +1477,7 @@
te = aux_sdb_trailer(aux, alert_index);
do {
orig_flags = te->flags;
- orig_overflow = te->overflow;
- *overflow = orig_overflow;
+ *overflow = orig_overflow = te->overflow;
if (orig_flags & SDB_TE_BUFFER_FULL_MASK) {
/*
* SDB is already set by hardware.
@@ -1566,6 +1588,7 @@
perf_aux_output_end(handle, size);
num_sdb = aux->sfb.num_sdb;
+ num_sdb = aux->sfb.num_sdb;
while (!done) {
/* Get an output handle */
aux = perf_aux_output_begin(handle, cpuhw->event);
@@ -1688,7 +1711,7 @@
}
/* Allocate aux_buffer struct for the event */
- aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL);
+ aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL);
if (!aux)
goto no_aux;
sfb = &aux->sfb;
@@ -2194,4 +2217,4 @@
}
arch_initcall(init_cpum_sampling_pmu);
-core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0644);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index fcb6c2e..1e75cc9 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -224,9 +224,13 @@
struct pt_regs *regs)
{
struct unwind_state state;
+ unsigned long addr;
- unwind_for_each_frame(&state, current, regs, 0)
- perf_callchain_store(entry, state.ip);
+ unwind_for_each_frame(&state, current, regs, 0) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || perf_callchain_store(entry, addr))
+ return;
+ }
}
/* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b0afec6..4e6299e 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -105,6 +105,7 @@
p->thread.system_timer = 0;
p->thread.hardirq_timer = 0;
p->thread.softirq_timer = 0;
+ p->thread.last_break = 1;
frame->sf.back_chain = 0;
/* new return point is ret_from_fork */
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 6ebc211..91b9b3f 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -165,8 +165,9 @@
static int show_cpuinfo(struct seq_file *m, void *v)
{
unsigned long n = (unsigned long) v - 1;
+ unsigned long first = cpumask_first(cpu_online_mask);
- if (!n)
+ if (n == first)
show_cpu_summary(m, v);
if (!machine_has_cpu_mhz)
return 0;
@@ -179,6 +180,8 @@
{
if (*pos)
*pos = cpumask_next(*pos - 1, cpu_online_mask);
+ else
+ *pos = cpumask_first(cpu_online_mask);
return *pos < nr_cpu_ids ? (void *)*pos + 1 : NULL;
}
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index ad71132..ad74472 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -324,6 +324,25 @@
child->thread.per_user.end = data;
}
+static void fixup_int_code(struct task_struct *child, addr_t data)
+{
+ struct pt_regs *regs = task_pt_regs(child);
+ int ilc = regs->int_code >> 16;
+ u16 insn;
+
+ if (ilc > 6)
+ return;
+
+ if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16),
+ &insn, sizeof(insn), FOLL_FORCE) != sizeof(insn))
+ return;
+
+ /* double check that tracee stopped on svc instruction */
+ if ((insn >> 8) != 0xa)
+ return;
+
+ regs->int_code = 0x20000 | (data & 0xffff);
+}
/*
* Write a word to the user area of a process at location addr. This
* operation does have an additional problem compared to peek_user.
@@ -335,7 +354,9 @@
struct user *dummy = NULL;
addr_t offset;
+
if (addr < (addr_t) &dummy->regs.acrs) {
+ struct pt_regs *regs = task_pt_regs(child);
/*
* psw and gprs are stored on the stack
*/
@@ -353,7 +374,11 @@
/* Invalid addressing mode bits */
return -EINVAL;
}
- *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
+
+ if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+ addr == offsetof(struct user, regs.gprs[2]))
+ fixup_int_code(child, data);
+ *(addr_t *)((addr_t) ®s->psw + addr) = data;
} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
/*
@@ -719,6 +744,10 @@
regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
(__u64)(tmp & PSW32_ADDR_AMODE);
} else {
+
+ if (test_pt_regs_flag(regs, PIF_SYSCALL) &&
+ addr == offsetof(struct compat_user, regs.gprs[2]))
+ fixup_int_code(child, data);
/* gpr 0-15 */
*(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp;
}
@@ -838,40 +867,45 @@
asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
{
unsigned long mask = -1UL;
+ long ret = -1;
/*
* The sysc_tracesys code in entry.S stored the system
* call number to gprs[2].
*/
if (test_thread_flag(TIF_SYSCALL_TRACE) &&
- (tracehook_report_syscall_entry(regs) ||
- regs->gprs[2] >= NR_syscalls)) {
+ tracehook_report_syscall_entry(regs)) {
/*
- * Tracing decided this syscall should not happen or the
- * debugger stored an invalid system call number. Skip
+ * Tracing decided this syscall should not happen. Skip
* the system call and the system call restart handling.
*/
- clear_pt_regs_flag(regs, PIF_SYSCALL);
- return -1;
+ goto skip;
}
/* Do the secure computing check after ptrace. */
if (secure_computing(NULL)) {
/* seccomp failures shouldn't expose any additional code. */
- return -1;
+ goto skip;
}
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
- trace_sys_enter(regs, regs->gprs[2]);
+ trace_sys_enter(regs, regs->int_code & 0xffff);
if (is_compat_task())
mask = 0xffffffff;
- audit_syscall_entry(regs->gprs[2], regs->orig_gpr2 & mask,
+ audit_syscall_entry(regs->int_code & 0xffff, regs->orig_gpr2 & mask,
regs->gprs[3] &mask, regs->gprs[4] &mask,
regs->gprs[5] &mask);
+ if ((signed long)regs->gprs[2] >= NR_syscalls) {
+ regs->gprs[2] = -ENOSYS;
+ ret = -ENOSYS;
+ }
return regs->gprs[2];
+skip:
+ clear_pt_regs_flag(regs, PIF_SYSCALL);
+ return ret;
}
asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
@@ -1256,7 +1290,6 @@
cb->pc == 1 &&
cb->qc == 0 &&
cb->reserved2 == 0 &&
- cb->key == PAGE_DEFAULT_KEY &&
cb->reserved3 == 0 &&
cb->reserved4 == 0 &&
cb->reserved5 == 0 &&
@@ -1320,7 +1353,11 @@
kfree(data);
return -EINVAL;
}
-
+ /*
+ * Override access key in any case, since user space should
+ * not be able to set it, nor should it care about it.
+ */
+ ri_cb.key = PAGE_DEFAULT_KEY >> 4;
preempt_disable();
if (!target->thread.ri_cb)
target->thread.ri_cb = data;
diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c
index 125c7f6..1788a54 100644
--- a/arch/s390/kernel/runtime_instr.c
+++ b/arch/s390/kernel/runtime_instr.c
@@ -57,7 +57,7 @@
cb->k = 1;
cb->ps = 1;
cb->pc = 1;
- cb->key = PAGE_DEFAULT_KEY;
+ cb->key = PAGE_DEFAULT_KEY >> 4;
cb->v = 1;
}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 3ff291b..f661f17 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -73,6 +73,7 @@
#include <asm/nospec-branch.h>
#include <asm/mem_detect.h>
#include <asm/uv.h>
+#include <asm/asm-offsets.h>
#include "entry.h"
/*
@@ -161,7 +162,7 @@
else if (CONSOLE_IS_3270)
add_preferred_console("tty3270", 0, NULL);
else if (CONSOLE_IS_VT220)
- add_preferred_console("ttyS", 1, NULL);
+ add_preferred_console("ttysclp", 0, NULL);
else if (CONSOLE_IS_HVC)
add_preferred_console("hvc", 0, NULL);
}
@@ -355,7 +356,6 @@
void __init arch_call_rest_init(void)
{
- struct stack_frame *frame;
unsigned long stack;
stack = stack_alloc();
@@ -368,13 +368,7 @@
set_task_stack_end_magic(current);
stack += STACK_INIT_OFFSET;
S390_lowcore.kernel_stack = stack;
- frame = (struct stack_frame *) stack;
- memset(frame, 0, sizeof(*frame));
- /* Branch to rest_init on the new stack, never returns */
- asm volatile(
- " la 15,0(%[_frame])\n"
- " jg rest_init\n"
- : : [_frame] "a" (frame));
+ CALL_ON_STACK_NORETURN(rest_init, stack);
}
static void __init setup_lowcore_dat_off(void)
@@ -457,6 +451,8 @@
lc->spinlock_index = 0;
arch_spin_lock_setup(0);
lc->br_r1_trampoline = 0x07f1; /* br %r1 */
+ lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
+ lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
set_prefix((u32)(unsigned long) lc);
lowcore_ptr[0] = lc;
@@ -631,7 +627,7 @@
/*
* Make sure that the area behind memory_end is protected
*/
-static void reserve_memory_end(void)
+static void __init reserve_memory_end(void)
{
if (memory_end_set)
memblock_reserve(memory_end, ULONG_MAX);
@@ -640,7 +636,7 @@
/*
* Make sure that oldmem, where the dump is stored, is protected
*/
-static void reserve_oldmem(void)
+static void __init reserve_oldmem(void)
{
#ifdef CONFIG_CRASH_DUMP
if (OLDMEM_BASE)
@@ -652,7 +648,7 @@
/*
* Make sure that oldmem, where the dump is stored, is protected
*/
-static void remove_oldmem(void)
+static void __init remove_oldmem(void)
{
#ifdef CONFIG_CRASH_DUMP
if (OLDMEM_BASE)
@@ -926,9 +922,9 @@
if (MACHINE_HAS_VX) {
elf_hwcap |= HWCAP_S390_VXRS;
if (test_facility(134))
- elf_hwcap |= HWCAP_S390_VXRS_EXT;
- if (test_facility(135))
elf_hwcap |= HWCAP_S390_VXRS_BCD;
+ if (test_facility(135))
+ elf_hwcap |= HWCAP_S390_VXRS_EXT;
if (test_facility(148))
elf_hwcap |= HWCAP_S390_VXRS_EXT2;
if (test_facility(152))
@@ -1059,7 +1055,7 @@
if (!early_ipl_comp_list_addr)
return;
- if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+ if (ipl_block.hdr.flags & IPL_PL_FLAG_SIPL)
pr_info("Linux is running with Secure-IPL enabled\n");
else
pr_info("Linux is running with Secure-IPL disabled\n");
@@ -1117,6 +1113,7 @@
if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
nospec_auto_detect();
+ jump_label_init();
parse_early_param();
#ifdef CONFIG_CRASH_DUMP
/* Deactivate elfcorehdr= kernel parameter */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 4497465..8c51462 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -212,6 +212,8 @@
lc->spinlock_lockval = arch_spin_lockval(cpu);
lc->spinlock_index = 0;
lc->br_r1_trampoline = 0x07f1; /* br %r1 */
+ lc->return_lpswe = gen_lpswe(__LC_RETURN_PSW);
+ lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
if (nmi_alloc_per_cpu(lc))
goto out_async;
if (vdso_alloc_per_cpu(lc))
@@ -262,10 +264,13 @@
lc->spinlock_index = 0;
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = S390_lowcore.kernel_asce;
+ lc->user_asce = S390_lowcore.kernel_asce;
lc->machine_flags = S390_lowcore.machine_flags;
lc->user_timer = lc->system_timer =
lc->steal_timer = lc->avg_steal_timer = 0;
__ctl_store(lc->cregs_save_area, 0, 15);
+ lc->cregs_save_area[1] = lc->kernel_asce;
+ lc->cregs_save_area[7] = lc->vdso_asce;
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
sizeof(lc->stfle_fac_list));
@@ -398,7 +403,7 @@
return -1;
}
-bool arch_vcpu_is_preempted(int cpu)
+bool notrace arch_vcpu_is_preempted(int cpu)
{
if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
return false;
@@ -408,7 +413,7 @@
}
EXPORT_SYMBOL(arch_vcpu_is_preempted);
-void smp_yield_cpu(int cpu)
+void notrace smp_yield_cpu(int cpu)
{
if (MACHINE_HAS_DIAG9C) {
diag_stat_inc_norecursion(DIAG_STAT_X09C);
@@ -724,39 +729,67 @@
static int smp_add_present_cpu(int cpu);
-static int __smp_rescan_cpus(struct sclp_core_info *info, int sysfs_add)
+static int smp_add_core(struct sclp_core_entry *core, cpumask_t *avail,
+ bool configured, bool early)
{
struct pcpu *pcpu;
- cpumask_t avail;
- int cpu, nr, i, j;
+ int cpu, nr, i;
u16 address;
nr = 0;
- cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
- cpu = cpumask_first(&avail);
- for (i = 0; (i < info->combined) && (cpu < nr_cpu_ids); i++) {
- if (sclp.has_core_type && info->core[i].type != boot_core_type)
+ if (sclp.has_core_type && core->type != boot_core_type)
+ return nr;
+ cpu = cpumask_first(avail);
+ address = core->core_id << smp_cpu_mt_shift;
+ for (i = 0; (i <= smp_cpu_mtid) && (cpu < nr_cpu_ids); i++) {
+ if (pcpu_find_address(cpu_present_mask, address + i))
continue;
- address = info->core[i].core_id << smp_cpu_mt_shift;
- for (j = 0; j <= smp_cpu_mtid; j++) {
- if (pcpu_find_address(cpu_present_mask, address + j))
- continue;
- pcpu = pcpu_devices + cpu;
- pcpu->address = address + j;
- pcpu->state =
- (cpu >= info->configured*(smp_cpu_mtid + 1)) ?
- CPU_STATE_STANDBY : CPU_STATE_CONFIGURED;
- smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
- set_cpu_present(cpu, true);
- if (sysfs_add && smp_add_present_cpu(cpu) != 0)
- set_cpu_present(cpu, false);
- else
- nr++;
- cpu = cpumask_next(cpu, &avail);
- if (cpu >= nr_cpu_ids)
+ pcpu = pcpu_devices + cpu;
+ pcpu->address = address + i;
+ if (configured)
+ pcpu->state = CPU_STATE_CONFIGURED;
+ else
+ pcpu->state = CPU_STATE_STANDBY;
+ smp_cpu_set_polarization(cpu, POLARIZATION_UNKNOWN);
+ set_cpu_present(cpu, true);
+ if (!early && smp_add_present_cpu(cpu) != 0)
+ set_cpu_present(cpu, false);
+ else
+ nr++;
+ cpumask_clear_cpu(cpu, avail);
+ cpu = cpumask_next(cpu, avail);
+ }
+ return nr;
+}
+
+static int __smp_rescan_cpus(struct sclp_core_info *info, bool early)
+{
+ struct sclp_core_entry *core;
+ static cpumask_t avail;
+ bool configured;
+ u16 core_id;
+ int nr, i;
+
+ nr = 0;
+ cpumask_xor(&avail, cpu_possible_mask, cpu_present_mask);
+ /*
+ * Add IPL core first (which got logical CPU number 0) to make sure
+ * that all SMT threads get subsequent logical CPU numbers.
+ */
+ if (early) {
+ core_id = pcpu_devices[0].address >> smp_cpu_mt_shift;
+ for (i = 0; i < info->configured; i++) {
+ core = &info->core[i];
+ if (core->core_id == core_id) {
+ nr += smp_add_core(core, &avail, true, early);
break;
+ }
}
}
+ for (i = 0; i < info->combined; i++) {
+ configured = i < info->configured;
+ nr += smp_add_core(&info->core[i], &avail, configured, early);
+ }
return nr;
}
@@ -805,18 +838,21 @@
/* Add CPUs present at boot */
get_online_cpus();
- __smp_rescan_cpus(info, 0);
+ __smp_rescan_cpus(info, true);
put_online_cpus();
memblock_free_early((unsigned long)info, sizeof(*info));
}
static void smp_init_secondary(void)
{
- int cpu = smp_processor_id();
+ int cpu = raw_smp_processor_id();
S390_lowcore.last_update_clock = get_tod_clock();
restore_access_regs(S390_lowcore.access_regs_save_area);
+ set_cpu_flag(CIF_ASCE_PRIMARY);
+ set_cpu_flag(CIF_ASCE_SECONDARY);
cpu_init();
+ rcu_cpu_starting(cpu);
preempt_disable();
init_cpu_timer();
vtime_init();
@@ -843,30 +879,18 @@
S390_lowcore.restart_source = -1UL;
__ctl_load(S390_lowcore.cregs_save_area, 0, 15);
__load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT);
- CALL_ON_STACK(smp_init_secondary, S390_lowcore.kernel_stack, 0);
+ CALL_ON_STACK_NORETURN(smp_init_secondary, S390_lowcore.kernel_stack);
}
/* Upping and downing of CPUs */
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
- struct pcpu *pcpu;
- int base, i, rc;
+ struct pcpu *pcpu = pcpu_devices + cpu;
+ int rc;
- pcpu = pcpu_devices + cpu;
if (pcpu->state != CPU_STATE_CONFIGURED)
return -EIO;
- base = smp_get_base_cpu(cpu);
- for (i = 0; i <= smp_cpu_mtid; i++) {
- if (base + i < nr_cpu_ids)
- if (cpu_online(base + i))
- break;
- }
- /*
- * If this is the first CPU of the core to get online
- * do an initial CPU reset.
- */
- if (i > smp_cpu_mtid &&
- pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) !=
+ if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) !=
SIGP_CC_ORDER_CODE_ACCEPTED)
return -EIO;
@@ -1148,7 +1172,7 @@
smp_get_core_info(info, 0);
get_online_cpus();
mutex_lock(&smp_cpu_state_mutex);
- nr = __smp_rescan_cpus(info, 1);
+ nr = __smp_rescan_cpus(info, false);
mutex_unlock(&smp_cpu_state_mutex);
put_online_cpus();
kfree(info);
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index e8766be..11c32b2 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -310,6 +310,7 @@
vdso_data->tk_mult = tk->tkr_mono.mult;
vdso_data->tk_shift = tk->tkr_mono.shift;
+ vdso_data->hrtimer_res = hrtimer_resolution;
smp_wmb();
++vdso_data->tb_update_count;
}
@@ -353,8 +354,9 @@
static DEFINE_MUTEX(clock_sync_mutex);
static unsigned long clock_sync_flags;
-#define CLOCK_SYNC_HAS_STP 0
-#define CLOCK_SYNC_STP 1
+#define CLOCK_SYNC_HAS_STP 0
+#define CLOCK_SYNC_STP 1
+#define CLOCK_SYNC_STPINFO_VALID 2
/*
* The get_clock function for the physical clock. It will get the current
@@ -591,6 +593,22 @@
queue_work(time_sync_wq, &stp_work);
}
+static int __store_stpinfo(void)
+{
+ int rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+
+ if (rc)
+ clear_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+ else
+ set_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+ return rc;
+}
+
+static int stpinfo_valid(void)
+{
+ return stp_online && test_bit(CLOCK_SYNC_STPINFO_VALID, &clock_sync_flags);
+}
+
static int stp_sync_clock(void *data)
{
struct clock_sync_data *sync = data;
@@ -612,8 +630,7 @@
if (rc == 0) {
sync->clock_delta = clock_delta;
clock_sync_global(clock_delta);
- rc = chsc_sstpi(stp_page, &stp_info,
- sizeof(struct stp_sstpi));
+ rc = __store_stpinfo();
if (rc == 0 && stp_info.tmd != 2)
rc = -EAGAIN;
}
@@ -658,7 +675,7 @@
if (rc)
goto out_unlock;
- rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+ rc = __store_stpinfo();
if (rc || stp_info.c == 0)
goto out_unlock;
@@ -695,10 +712,14 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%016llx\n",
- *(unsigned long long *) stp_info.ctnid);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%016llx\n",
+ *(unsigned long long *) stp_info.ctnid);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(ctn_id, 0400, stp_ctn_id_show, NULL);
@@ -707,9 +728,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", stp_info.ctn);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", stp_info.ctn);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(ctn_type, 0400, stp_ctn_type_show, NULL);
@@ -718,9 +743,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x2000))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x2000))
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(dst_offset, 0400, stp_dst_offset_show, NULL);
@@ -729,9 +758,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x8000))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x8000))
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(leap_seconds, 0400, stp_leap_seconds_show, NULL);
@@ -740,9 +773,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(stratum, 0400, stp_stratum_show, NULL);
@@ -751,9 +788,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x0800))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int) stp_info.tto);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x0800))
+ ret = sprintf(buf, "%i\n", (int) stp_info.tto);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(time_offset, 0400, stp_time_offset_show, NULL);
@@ -762,9 +803,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online || !(stp_info.vbits & 0x4000))
- return -ENODATA;
- return sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid() && (stp_info.vbits & 0x4000))
+ ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(time_zone_offset, 0400,
@@ -774,9 +819,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", stp_info.tmd);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", stp_info.tmd);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(timing_mode, 0400, stp_timing_mode_show, NULL);
@@ -785,9 +834,13 @@
struct device_attribute *attr,
char *buf)
{
- if (!stp_online)
- return -ENODATA;
- return sprintf(buf, "%i\n", stp_info.tst);
+ ssize_t ret = -ENODATA;
+
+ mutex_lock(&stp_work_mutex);
+ if (stpinfo_valid())
+ ret = sprintf(buf, "%i\n", stp_info.tst);
+ mutex_unlock(&stp_work_mutex);
+ return ret;
}
static DEVICE_ATTR(timing_state, 0400, stp_timing_state_show, NULL);
diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c
index 490b52e..11a669f 100644
--- a/arch/s390/kernel/trace.c
+++ b/arch/s390/kernel/trace.c
@@ -14,7 +14,7 @@
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/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index a8204f9..6e609b1 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -60,6 +60,11 @@
ip = READ_ONCE_NOCHECK(sf->gprs[8]);
reliable = false;
regs = NULL;
+ if (!__kernel_text_address(ip)) {
+ /* skip bogus %r14 */
+ state->regs = NULL;
+ return unwind_next_frame(state);
+ }
} else {
sf = (struct stack_frame *) state->sp;
sp = READ_ONCE_NOCHECK(sf->back_chain);
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index bec19e7..4a66a1c 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -18,8 +18,8 @@
KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
-KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
- -Wl,--hash-style=both
+ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \
+ --hash-style=both --build-id -T
$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
@@ -37,8 +37,8 @@
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
- $(call if_changed,vdso64ld)
+$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE
+ $(call if_changed,ld)
# strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -50,8 +50,6 @@
$(call if_changed_dep,vdso64as)
# actual build commands
-quiet_cmd_vdso64ld = VDSO64L $@
- cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@
quiet_cmd_vdso64as = VDSO64A $@
cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
index 0814353..0c79caa 100644
--- a/arch/s390/kernel/vdso64/clock_getres.S
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -17,12 +17,14 @@
.type __kernel_clock_getres,@function
__kernel_clock_getres:
CFI_STARTPROC
- larl %r1,4f
+ larl %r1,3f
+ lg %r0,0(%r1)
cghi %r2,__CLOCK_REALTIME_COARSE
je 0f
cghi %r2,__CLOCK_MONOTONIC_COARSE
je 0f
- larl %r1,3f
+ larl %r1,_vdso_data
+ llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1)
cghi %r2,__CLOCK_REALTIME
je 0f
cghi %r2,__CLOCK_MONOTONIC
@@ -36,7 +38,6 @@
jz 2f
0: ltgr %r3,%r3
jz 1f /* res == NULL */
- lg %r0,0(%r1)
xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */
stg %r0,8(%r3) /* store tp->tv_usec */
1: lghi %r2,0
@@ -45,6 +46,5 @@
svc 0
br %r14
CFI_ENDPROC
-3: .quad __CLOCK_REALTIME_RES
-4: .quad __CLOCK_COARSE_RES
+3: .quad __CLOCK_COARSE_RES
.size __kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index c475ca4..6e60cc2 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -136,7 +136,8 @@
" stck %1" /* Store current tod clock value */
#endif
: "=Q" (S390_lowcore.last_update_timer),
- "=Q" (S390_lowcore.last_update_clock));
+ "=Q" (S390_lowcore.last_update_clock)
+ : : "cc");
clock = S390_lowcore.last_update_clock - clock;
timer -= S390_lowcore.last_update_timer;
@@ -216,7 +217,7 @@
avg_steal = S390_lowcore.avg_steal_timer / 2;
if ((s64) steal > 0) {
S390_lowcore.steal_timer = 0;
- account_steal_time(steal);
+ account_steal_time(cputime_to_nsecs(steal));
avg_steal += steal;
}
S390_lowcore.avg_steal_timer = avg_steal;