summaryrefslogtreecommitdiff
path: root/arch/s390/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kernel')
-rw-r--r--arch/s390/kernel/Makefile5
-rw-r--r--arch/s390/kernel/abs_lowcore.c2
-rw-r--r--arch/s390/kernel/alternative.c65
-rw-r--r--arch/s390/kernel/asm-offsets.c26
-rw-r--r--arch/s390/kernel/cert_store.c4
-rw-r--r--arch/s390/kernel/cpacf.c36
-rw-r--r--arch/s390/kernel/cpcmd.c10
-rw-r--r--arch/s390/kernel/cpufeature.c5
-rw-r--r--arch/s390/kernel/crash_dump.c112
-rw-r--r--arch/s390/kernel/debug.c340
-rw-r--r--arch/s390/kernel/diag/Makefile1
-rw-r--r--arch/s390/kernel/diag/diag.c (renamed from arch/s390/kernel/diag.c)20
-rw-r--r--arch/s390/kernel/diag/diag310.c276
-rw-r--r--arch/s390/kernel/diag/diag324.c224
-rw-r--r--arch/s390/kernel/diag/diag_ioctl.h14
-rw-r--r--arch/s390/kernel/diag/diag_misc.c63
-rw-r--r--arch/s390/kernel/dumpstack.c8
-rw-r--r--arch/s390/kernel/early.c120
-rw-r--r--arch/s390/kernel/entry.S112
-rw-r--r--arch/s390/kernel/entry.h3
-rw-r--r--arch/s390/kernel/ftrace.c57
-rw-r--r--arch/s390/kernel/guarded_storage.c3
-rw-r--r--arch/s390/kernel/head64.S4
-rw-r--r--arch/s390/kernel/hiperdispatch.c5
-rw-r--r--arch/s390/kernel/ipl.c278
-rw-r--r--arch/s390/kernel/irq.c22
-rw-r--r--arch/s390/kernel/kprobes.c11
-rw-r--r--arch/s390/kernel/lgr.c2
-rw-r--r--arch/s390/kernel/machine_kexec.c6
-rw-r--r--arch/s390/kernel/mcount.S23
-rw-r--r--arch/s390/kernel/nmi.c9
-rw-r--r--arch/s390/kernel/nospec-sysfs.c10
-rw-r--r--arch/s390/kernel/numa.c8
-rw-r--r--arch/s390/kernel/os_info.c3
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c29
-rw-r--r--arch/s390/kernel/perf_cpum_cf_events.c171
-rw-r--r--arch/s390/kernel/perf_cpum_sf.c136
-rw-r--r--arch/s390/kernel/perf_event.c6
-rw-r--r--arch/s390/kernel/perf_pai_crypto.c5
-rw-r--r--arch/s390/kernel/perf_pai_ext.c5
-rw-r--r--arch/s390/kernel/processor.c30
-rw-r--r--arch/s390/kernel/ptrace.c56
-rw-r--r--arch/s390/kernel/setup.c114
-rw-r--r--arch/s390/kernel/smp.c50
-rw-r--r--arch/s390/kernel/stacktrace.c3
-rw-r--r--arch/s390/kernel/sthyi.c10
-rw-r--r--arch/s390/kernel/syscall.c51
-rw-r--r--arch/s390/kernel/syscalls/Makefile27
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl5
-rw-r--r--arch/s390/kernel/sysinfo.c48
-rw-r--r--arch/s390/kernel/text_amode31.S3
-rw-r--r--arch/s390/kernel/time.c59
-rw-r--r--arch/s390/kernel/topology.c73
-rw-r--r--arch/s390/kernel/traps.c139
-rw-r--r--arch/s390/kernel/uv.c654
-rw-r--r--arch/s390/kernel/vdso.c99
-rw-r--r--arch/s390/kernel/vdso32/Makefile2
-rw-r--r--arch/s390/kernel/vdso32/vdso32.lds.S9
-rw-r--r--arch/s390/kernel/vdso64/Makefile4
-rw-r--r--arch/s390/kernel/vdso64/vdso64.lds.S10
-rw-r--r--arch/s390/kernel/vmcore_info.c3
-rw-r--r--arch/s390/kernel/vmlinux.lds.S1
62 files changed, 2235 insertions, 1454 deletions
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 48caae8c7e10..ea5ed6654050 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -38,14 +38,15 @@ CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls
obj-y := head64.o traps.o time.o process.o early.o setup.o idle.o vtime.o
obj-y += processor.o syscall.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 cpufeature.o
+obj-y += debug.o irq.o ipl.o dis.o vdso.o cpufeature.o
obj-y += sysinfo.o lgr.o os_info.o ctlreg.o
obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
obj-y += entry.o reipl.o kdebugfs.o alternative.o
obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o uv.o wti.o
+obj-y += diag/
-extra-y += vmlinux.lds
+always-$(KBUILD_BUILTIN) += vmlinux.lds
obj-$(CONFIG_SYSFS) += nospec-sysfs.o
CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE)
diff --git a/arch/s390/kernel/abs_lowcore.c b/arch/s390/kernel/abs_lowcore.c
index 09cd24cbe74e..6252b7d115dd 100644
--- a/arch/s390/kernel/abs_lowcore.c
+++ b/arch/s390/kernel/abs_lowcore.c
@@ -2,9 +2,9 @@
#include <linux/pgtable.h>
#include <asm/abs_lowcore.h>
+#include <asm/sections.h>
unsigned long __bootdata_preserved(__abs_lowcore);
-int __bootdata_preserved(relocate_lowcore);
int abs_lowcore_map(int cpu, struct lowcore *lc, bool alloc)
{
diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c
index 8d5d0de35de0..90c0e6408992 100644
--- a/arch/s390/kernel/alternative.c
+++ b/arch/s390/kernel/alternative.c
@@ -1,41 +1,90 @@
// SPDX-License-Identifier: GPL-2.0
+#ifndef pr_fmt
+#define pr_fmt(fmt) "alt: " fmt
+#endif
+
#include <linux/uaccess.h>
+#include <linux/printk.h>
#include <asm/nospec-branch.h>
#include <asm/abs_lowcore.h>
#include <asm/alternative.h>
#include <asm/facility.h>
+#include <asm/sections.h>
+#include <asm/machine.h>
+
+#ifndef a_debug
+#define a_debug pr_debug
+#endif
+
+#ifndef __kernel_va
+#define __kernel_va(x) (void *)(x)
+#endif
+
+unsigned long __bootdata_preserved(machine_features[1]);
+
+struct alt_debug {
+ unsigned long facilities[MAX_FACILITY_BIT / BITS_PER_LONG];
+ unsigned long mfeatures[MAX_MFEATURE_BIT / BITS_PER_LONG];
+ int spec;
+};
+
+static struct alt_debug __bootdata_preserved(alt_debug);
+
+static void alternative_dump(u8 *old, u8 *new, unsigned int len, unsigned int type, unsigned int data)
+{
+ char oinsn[33], ninsn[33];
+ unsigned long kptr;
+ unsigned int pos;
+
+ for (pos = 0; pos < len && 2 * pos < sizeof(oinsn) - 3; pos++)
+ hex_byte_pack(&oinsn[2 * pos], old[pos]);
+ oinsn[2 * pos] = 0;
+ for (pos = 0; pos < len && 2 * pos < sizeof(ninsn) - 3; pos++)
+ hex_byte_pack(&ninsn[2 * pos], new[pos]);
+ ninsn[2 * pos] = 0;
+ kptr = (unsigned long)__kernel_va(old);
+ a_debug("[%d/%3d] %016lx: %s -> %s\n", type, data, kptr, oinsn, ninsn);
+}
void __apply_alternatives(struct alt_instr *start, struct alt_instr *end, unsigned int ctx)
{
- u8 *instr, *replacement;
+ struct alt_debug *d;
struct alt_instr *a;
- bool replace;
+ bool debug, replace;
+ u8 *old, *new;
/*
* The scan order should be from start to end. A later scanned
* alternative code can overwrite previously scanned alternative code.
*/
+ d = &alt_debug;
for (a = start; a < end; a++) {
if (!(a->ctx & ctx))
continue;
switch (a->type) {
case ALT_TYPE_FACILITY:
replace = test_facility(a->data);
+ debug = __test_facility(a->data, d->facilities);
+ break;
+ case ALT_TYPE_FEATURE:
+ replace = test_machine_feature(a->data);
+ debug = __test_machine_feature(a->data, d->mfeatures);
break;
case ALT_TYPE_SPEC:
replace = nobp_enabled();
- break;
- case ALT_TYPE_LOWCORE:
- replace = have_relocated_lowcore();
+ debug = d->spec;
break;
default:
replace = false;
+ debug = false;
}
if (!replace)
continue;
- instr = (u8 *)&a->instr_offset + a->instr_offset;
- replacement = (u8 *)&a->repl_offset + a->repl_offset;
- s390_kernel_write(instr, replacement, a->instrlen);
+ old = (u8 *)&a->instr_offset + a->instr_offset;
+ new = (u8 *)&a->repl_offset + a->repl_offset;
+ if (debug)
+ alternative_dump(old, new, a->instrlen, a->type, a->data);
+ s390_kernel_write(old, new, a->instrlen);
}
}
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 5529248d84fb..95ecad9c7d7d 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -5,16 +5,14 @@
* and format the required data.
*/
-#define ASM_OFFSETS_C
-
#include <linux/kbuild.h>
-#include <linux/kvm_host.h>
#include <linux/sched.h>
#include <linux/purgatory.h>
#include <linux/pgtable.h>
-#include <linux/ftrace.h>
-#include <asm/gmap.h>
+#include <linux/ftrace_regs.h>
+#include <asm/kvm_host_types.h>
#include <asm/stacktrace.h>
+#include <asm/ptrace.h>
int main(void)
{
@@ -50,8 +48,8 @@ int main(void)
OFFSET(__PT_R14, pt_regs, gprs[14]);
OFFSET(__PT_R15, pt_regs, gprs[15]);
OFFSET(__PT_ORIG_GPR2, pt_regs, orig_gpr2);
+ OFFSET(__PT_INT_CODE, pt_regs, int_code);
OFFSET(__PT_FLAGS, pt_regs, flags);
- OFFSET(__PT_CR1, pt_regs, cr1);
OFFSET(__PT_LAST_BREAK, pt_regs, last_break);
DEFINE(__PT_SIZE, sizeof(struct pt_regs));
BLANK();
@@ -77,7 +75,8 @@ int main(void)
OFFSET(__LC_EXT_CPU_ADDR, lowcore, ext_cpu_addr);
OFFSET(__LC_EXT_INT_CODE, lowcore, ext_int_code);
OFFSET(__LC_PGM_ILC, lowcore, pgm_ilc);
- OFFSET(__LC_PGM_INT_CODE, lowcore, pgm_code);
+ OFFSET(__LC_PGM_CODE, lowcore, pgm_code);
+ OFFSET(__LC_PGM_INT_CODE, lowcore, pgm_int_code);
OFFSET(__LC_DATA_EXC_CODE, lowcore, data_exc_code);
OFFSET(__LC_MON_CLASS_NR, lowcore, mon_class_num);
OFFSET(__LC_PER_CODE, lowcore, per_code);
@@ -123,7 +122,6 @@ int main(void)
OFFSET(__LC_LAST_UPDATE_TIMER, lowcore, last_update_timer);
OFFSET(__LC_LAST_UPDATE_CLOCK, lowcore, last_update_clock);
OFFSET(__LC_INT_CLOCK, lowcore, int_clock);
- OFFSET(__LC_BOOT_CLOCK, lowcore, boot_clock);
OFFSET(__LC_CURRENT, lowcore, current_task);
OFFSET(__LC_KERNEL_STACK, lowcore, kernel_stack);
OFFSET(__LC_ASYNC_STACK, lowcore, async_stack);
@@ -138,7 +136,6 @@ int main(void)
OFFSET(__LC_USER_ASCE, lowcore, user_asce);
OFFSET(__LC_LPP, lowcore, lpp);
OFFSET(__LC_CURRENT_PID, lowcore, current_pid);
- OFFSET(__LC_GMAP, lowcore, gmap);
OFFSET(__LC_LAST_BREAK, lowcore, last_break);
/* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */
OFFSET(__LC_DUMP_REIPL, lowcore, ipib);
@@ -161,7 +158,6 @@ int main(void)
OFFSET(__LC_PGM_TDB, lowcore, pgm_tdb);
BLANK();
/* gmap/sie offsets */
- OFFSET(__GMAP_ASCE, gmap, asce);
OFFSET(__SIE_PROG0C, kvm_s390_sie_block, prog0c);
OFFSET(__SIE_PROG20, kvm_s390_sie_block, prog20);
/* kexec_sha_region */
@@ -178,14 +174,8 @@ int main(void)
DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size));
DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line));
DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size));
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- /* function graph return value tracing */
- OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2);
- OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp);
- DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs));
-#endif
- OFFSET(__FTRACE_REGS_PT_REGS, ftrace_regs, regs);
- DEFINE(__FTRACE_REGS_SIZE, sizeof(struct ftrace_regs));
+ OFFSET(__FTRACE_REGS_PT_REGS, __arch_ftrace_regs, regs);
+ DEFINE(__FTRACE_REGS_SIZE, sizeof(struct __arch_ftrace_regs));
OFFSET(__PCPU_FLAGS, pcpu, flags);
return 0;
diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c
index bf983513dd33..c217a5e64094 100644
--- a/arch/s390/kernel/cert_store.c
+++ b/arch/s390/kernel/cert_store.c
@@ -138,7 +138,7 @@ static void cert_store_key_describe(const struct key *key, struct seq_file *m)
* First 64 bytes of the key description is key name in EBCDIC CP 500.
* Convert it to ASCII for displaying in /proc/keys.
*/
- strscpy(ascii, key->description, sizeof(ascii));
+ strscpy(ascii, key->description);
EBCASC_500(ascii, VC_NAME_LEN_BYTES);
seq_puts(m, ascii);
@@ -235,7 +235,7 @@ static int __diag320(unsigned long subcode, void *addr)
{
union register_pair rp = { .even = (unsigned long)addr, };
- asm volatile(
+ asm_inline volatile(
" diag %[rp],%[subcode],0x320\n"
"0: nopr %%r7\n"
EX_TABLE(0b, 0b)
diff --git a/arch/s390/kernel/cpacf.c b/arch/s390/kernel/cpacf.c
index c8575dbc890d..4b9b34f95d72 100644
--- a/arch/s390/kernel/cpacf.c
+++ b/arch/s390/kernel/cpacf.c
@@ -14,7 +14,7 @@
#define CPACF_QUERY(name, instruction) \
static ssize_t name##_query_raw_read(struct file *fp, \
struct kobject *kobj, \
- struct bin_attribute *attr, \
+ const struct bin_attribute *attr, \
char *buf, loff_t offs, \
size_t count) \
{ \
@@ -24,7 +24,7 @@ static ssize_t name##_query_raw_read(struct file *fp, \
return -EOPNOTSUPP; \
return memory_read_from_buffer(buf, count, &offs, &mask, sizeof(mask)); \
} \
-static BIN_ATTR_RO(name##_query_raw, sizeof(cpacf_mask_t))
+static const BIN_ATTR_RO(name##_query_raw, sizeof(cpacf_mask_t))
CPACF_QUERY(km, KM);
CPACF_QUERY(kmc, KMC);
@@ -40,20 +40,20 @@ CPACF_QUERY(prno, PRNO);
CPACF_QUERY(kma, KMA);
CPACF_QUERY(kdsa, KDSA);
-#define CPACF_QAI(name, instruction) \
-static ssize_t name##_query_auth_info_raw_read( \
- struct file *fp, struct kobject *kobj, \
- struct bin_attribute *attr, char *buf, loff_t offs, \
- size_t count) \
-{ \
- cpacf_qai_t qai; \
- \
- if (!cpacf_qai(CPACF_##instruction, &qai)) \
- return -EOPNOTSUPP; \
- return memory_read_from_buffer(buf, count, &offs, &qai, \
- sizeof(qai)); \
-} \
-static BIN_ATTR_RO(name##_query_auth_info_raw, sizeof(cpacf_qai_t))
+#define CPACF_QAI(name, instruction) \
+static ssize_t name##_query_auth_info_raw_read( \
+ struct file *fp, struct kobject *kobj, \
+ const struct bin_attribute *attr, char *buf, loff_t offs, \
+ size_t count) \
+{ \
+ cpacf_qai_t qai; \
+ \
+ if (!cpacf_qai(CPACF_##instruction, &qai)) \
+ return -EOPNOTSUPP; \
+ return memory_read_from_buffer(buf, count, &offs, &qai, \
+ sizeof(qai)); \
+} \
+static const BIN_ATTR_RO(name##_query_auth_info_raw, sizeof(cpacf_qai_t))
CPACF_QAI(km, KM);
CPACF_QAI(kmc, KMC);
@@ -69,7 +69,7 @@ CPACF_QAI(prno, PRNO);
CPACF_QAI(kma, KMA);
CPACF_QAI(kdsa, KDSA);
-static struct bin_attribute *cpacf_attrs[] = {
+static const struct bin_attribute *const cpacf_attrs[] = {
&bin_attr_km_query_raw,
&bin_attr_kmc_query_raw,
&bin_attr_kimd_query_raw,
@@ -101,7 +101,7 @@ static struct bin_attribute *cpacf_attrs[] = {
static const struct attribute_group cpacf_attr_grp = {
.name = "cpacf",
- .bin_attrs = cpacf_attrs,
+ .bin_attrs_new = cpacf_attrs,
};
static int __init cpacf_init(void)
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index b210a29d3ee9..2f4174b961de 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -20,6 +20,7 @@
#include <asm/diag.h>
#include <asm/ebcdic.h>
#include <asm/cpcmd.h>
+#include <asm/asm.h>
static DEFINE_SPINLOCK(cpcmd_lock);
static char cpcmd_buf[241];
@@ -45,12 +46,11 @@ static int diag8_response(int cmdlen, char *response, int *rlen)
ry.odd = *rlen;
asm volatile(
" diag %[rx],%[ry],0x8\n"
- " ipm %[cc]\n"
- " srl %[cc],28\n"
- : [cc] "=&d" (cc), [ry] "+&d" (ry.pair)
+ CC_IPM(cc)
+ : CC_OUT(cc, cc), [ry] "+d" (ry.pair)
: [rx] "d" (rx.pair)
- : "cc");
- if (cc)
+ : CC_CLOBBER);
+ if (CC_TRANSFORM(cc))
*rlen += ry.odd;
else
*rlen = ry.odd;
diff --git a/arch/s390/kernel/cpufeature.c b/arch/s390/kernel/cpufeature.c
index 1b2ae42a0c15..76210f001028 100644
--- a/arch/s390/kernel/cpufeature.c
+++ b/arch/s390/kernel/cpufeature.c
@@ -5,11 +5,13 @@
#include <linux/cpufeature.h>
#include <linux/bug.h>
+#include <asm/machine.h>
#include <asm/elf.h>
enum {
TYPE_HWCAP,
TYPE_FACILITY,
+ TYPE_MACHINE,
};
struct s390_cpu_feature {
@@ -21,6 +23,7 @@ static struct s390_cpu_feature s390_cpu_features[MAX_CPU_FEATURES] = {
[S390_CPU_FEATURE_MSA] = {.type = TYPE_HWCAP, .num = HWCAP_NR_MSA},
[S390_CPU_FEATURE_VXRS] = {.type = TYPE_HWCAP, .num = HWCAP_NR_VXRS},
[S390_CPU_FEATURE_UV] = {.type = TYPE_FACILITY, .num = 158},
+ [S390_CPU_FEATURE_D288] = {.type = TYPE_MACHINE, .num = MFEATURE_DIAG288},
};
/*
@@ -38,6 +41,8 @@ int cpu_have_feature(unsigned int num)
return !!(elf_hwcap & BIT(feature->num));
case TYPE_FACILITY:
return test_facility(feature->num);
+ case TYPE_MACHINE:
+ return test_machine_feature(feature->num);
default:
WARN_ON_ONCE(1);
return 0;
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index edae13416196..adb164223f8c 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -63,9 +63,7 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu)
{
struct save_area *sa;
- sa = memblock_alloc(sizeof(*sa), 8);
- if (!sa)
- return NULL;
+ sa = memblock_alloc_or_panic(sizeof(*sa), 8);
if (is_boot_cpu)
list_add(&sa->list, &dump_save_areas);
@@ -237,14 +235,16 @@ int remap_oldmem_pfn_range(struct vm_area_struct *vma, unsigned long from,
prot);
}
-static const char *nt_name(Elf64_Word type)
+/*
+ * Return true only when in a kdump or stand-alone kdump environment.
+ * Note that /proc/vmcore might also be available in "standard zfcp/nvme dump"
+ * environments, where this function returns false; see dump_available().
+ */
+bool is_kdump_kernel(void)
{
- const char *name = "LINUX";
-
- if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
- name = KEXEC_CORE_NOTE_NAME;
- return name;
+ return oldmem_data.start;
}
+EXPORT_SYMBOL_GPL(is_kdump_kernel);
/*
* Initialize ELF note
@@ -270,10 +270,8 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
return PTR_ADD(buf, len);
}
-static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
-{
- return nt_init_name(buf, type, desc, d_len, nt_name(type));
-}
+#define nt_init(buf, type, desc) \
+ nt_init_name(buf, NT_ ## type, &(desc), sizeof(desc), NN_ ## type)
/*
* Calculate the size of ELF note
@@ -289,10 +287,7 @@ static size_t nt_size_name(int d_len, const char *name)
return size;
}
-static inline size_t nt_size(Elf64_Word type, int d_len)
-{
- return nt_size_name(d_len, nt_name(type));
-}
+#define nt_size(type, desc) nt_size_name(sizeof(desc), NN_ ## type)
/*
* Fill ELF notes for one CPU with save area registers
@@ -313,18 +308,16 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
memcpy(&nt_fpregset.fpc, &sa->fpc, sizeof(sa->fpc));
memcpy(&nt_fpregset.fprs, &sa->fprs, sizeof(sa->fprs));
/* Create ELF notes for the CPU */
- ptr = nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus));
- ptr = nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset));
- ptr = nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer));
- ptr = nt_init(ptr, NT_S390_TODCMP, &sa->todcmp, sizeof(sa->todcmp));
- ptr = nt_init(ptr, NT_S390_TODPREG, &sa->todpreg, sizeof(sa->todpreg));
- ptr = nt_init(ptr, NT_S390_CTRS, &sa->ctrs, sizeof(sa->ctrs));
- ptr = nt_init(ptr, NT_S390_PREFIX, &sa->prefix, sizeof(sa->prefix));
+ ptr = nt_init(ptr, PRSTATUS, nt_prstatus);
+ ptr = nt_init(ptr, PRFPREG, nt_fpregset);
+ ptr = nt_init(ptr, S390_TIMER, sa->timer);
+ ptr = nt_init(ptr, S390_TODCMP, sa->todcmp);
+ ptr = nt_init(ptr, S390_TODPREG, sa->todpreg);
+ ptr = nt_init(ptr, S390_CTRS, sa->ctrs);
+ ptr = nt_init(ptr, S390_PREFIX, sa->prefix);
if (cpu_has_vx()) {
- ptr = nt_init(ptr, NT_S390_VXRS_HIGH,
- &sa->vxrs_high, sizeof(sa->vxrs_high));
- ptr = nt_init(ptr, NT_S390_VXRS_LOW,
- &sa->vxrs_low, sizeof(sa->vxrs_low));
+ ptr = nt_init(ptr, S390_VXRS_HIGH, sa->vxrs_high);
+ ptr = nt_init(ptr, S390_VXRS_LOW, sa->vxrs_low);
}
return ptr;
}
@@ -337,16 +330,16 @@ static size_t get_cpu_elf_notes_size(void)
struct save_area *sa = NULL;
size_t size;
- size = nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
- size += nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
- size += nt_size(NT_S390_TIMER, sizeof(sa->timer));
- size += nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
- size += nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
- size += nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
- size += nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+ size = nt_size(PRSTATUS, struct elf_prstatus);
+ size += nt_size(PRFPREG, elf_fpregset_t);
+ size += nt_size(S390_TIMER, sa->timer);
+ size += nt_size(S390_TODCMP, sa->todcmp);
+ size += nt_size(S390_TODPREG, sa->todpreg);
+ size += nt_size(S390_CTRS, sa->ctrs);
+ size += nt_size(S390_PREFIX, sa->prefix);
if (cpu_has_vx()) {
- size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
- size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+ size += nt_size(S390_VXRS_HIGH, sa->vxrs_high);
+ size += nt_size(S390_VXRS_LOW, sa->vxrs_low);
}
return size;
@@ -361,8 +354,8 @@ static void *nt_prpsinfo(void *ptr)
memset(&prpsinfo, 0, sizeof(prpsinfo));
prpsinfo.pr_sname = 'R';
- strcpy(prpsinfo.pr_fname, "vmlinux");
- return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo));
+ strscpy(prpsinfo.pr_fname, "vmlinux");
+ return nt_init(ptr, PRPSINFO, prpsinfo);
}
/*
@@ -497,6 +490,19 @@ static int get_mem_chunk_cnt(void)
return cnt;
}
+static void fill_ptload(Elf64_Phdr *phdr, unsigned long paddr,
+ unsigned long vaddr, unsigned long size)
+{
+ phdr->p_type = PT_LOAD;
+ phdr->p_vaddr = vaddr;
+ phdr->p_offset = paddr;
+ phdr->p_paddr = paddr;
+ phdr->p_filesz = size;
+ phdr->p_memsz = size;
+ phdr->p_flags = PF_R | PF_W | PF_X;
+ phdr->p_align = PAGE_SIZE;
+}
+
/*
* Initialize ELF loads (new kernel)
*/
@@ -509,14 +515,8 @@ static void loads_init(Elf64_Phdr *phdr, bool os_info_has_vm)
if (os_info_has_vm)
old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
for_each_physmem_range(idx, &oldmem_type, &start, &end) {
- phdr->p_type = PT_LOAD;
- phdr->p_vaddr = old_identity_base + start;
- phdr->p_offset = start;
- phdr->p_paddr = start;
- phdr->p_filesz = end - start;
- phdr->p_memsz = end - start;
- phdr->p_flags = PF_R | PF_W | PF_X;
- phdr->p_align = PAGE_SIZE;
+ fill_ptload(phdr, start, old_identity_base + start,
+ end - start);
phdr++;
}
}
@@ -526,6 +526,22 @@ static bool os_info_has_vm(void)
return os_info_old_value(OS_INFO_KASLR_OFFSET);
}
+#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM
+/*
+ * Fill PT_LOAD for a physical memory range owned by a device and detected by
+ * its device driver.
+ */
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+ unsigned long long paddr, unsigned long long size)
+{
+ unsigned long old_identity_base = 0;
+
+ if (os_info_has_vm())
+ old_identity_base = os_info_old_value(OS_INFO_IDENTITY_BASE);
+ fill_ptload(phdr, paddr, old_identity_base + paddr, size);
+}
+#endif
+
/*
* Prepare PT_LOAD type program header for kernel image region
*/
@@ -578,7 +594,7 @@ static size_t get_elfcorehdr_size(int phdr_count)
/* PT_NOTES */
size += sizeof(Elf64_Phdr);
/* nt_prpsinfo */
- size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+ size += nt_size(PRPSINFO, struct elf_prpsinfo);
/* regsets */
size += get_cpu_cnt() * get_cpu_elf_notes_size();
/* nt_vmcoreinfo */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index e62bea9ab21e..2a41be2f7925 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -24,6 +24,7 @@
#include <linux/export.h>
#include <linux/init.h>
#include <linux/fs.h>
+#include <linux/math.h>
#include <linux/minmax.h>
#include <linux/debugfs.h>
@@ -38,13 +39,13 @@
typedef struct file_private_info {
loff_t offset; /* offset of last read in file */
- int act_area; /* number of last formated area */
+ int act_area; /* number of last formatted area */
int act_page; /* act page in given area */
- int act_entry; /* last formated entry (offset */
+ int act_entry; /* last formatted entry (offset */
/* relative to beginning of last */
- /* formated page) */
+ /* formatted page) */
size_t act_entry_offset; /* up to this offset we copied */
- /* in last read the last formated */
+ /* in last read the last formatted */
/* entry to userland */
char temp_buf[2048]; /* buffer for output */
debug_info_t *debug_info_org; /* original debug information */
@@ -63,7 +64,7 @@ typedef struct {
long args[];
} debug_sprintf_entry_t;
-/* internal function prototyes */
+/* internal function prototypes */
static int debug_init(void);
static ssize_t debug_output(struct file *file, char __user *user_buf,
@@ -77,12 +78,14 @@ static debug_info_t *debug_info_create(const char *name, int pages_per_area,
static void debug_info_get(debug_info_t *);
static void debug_info_put(debug_info_t *);
static int debug_prolog_level_fn(debug_info_t *id,
- struct debug_view *view, char *out_buf);
+ struct debug_view *view, char *out_buf,
+ size_t out_buf_size);
static int debug_input_level_fn(debug_info_t *id, struct debug_view *view,
struct file *file, const char __user *user_buf,
size_t user_buf_size, loff_t *offset);
static int debug_prolog_pages_fn(debug_info_t *id,
- struct debug_view *view, char *out_buf);
+ struct debug_view *view, char *out_buf,
+ size_t out_buf_size);
static int debug_input_pages_fn(debug_info_t *id, struct debug_view *view,
struct file *file, const char __user *user_buf,
size_t user_buf_size, loff_t *offset);
@@ -90,9 +93,8 @@ static int debug_input_flush_fn(debug_info_t *id, struct debug_view *view,
struct file *file, const char __user *user_buf,
size_t user_buf_size, loff_t *offset);
static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
- char *out_buf, const char *in_buf);
-static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
- char *out_buf, const char *inbuf);
+ char *out_buf, size_t out_buf_size,
+ const char *in_buf);
static void debug_areas_swap(debug_info_t *a, debug_info_t *b);
static void debug_events_append(debug_info_t *dest, debug_info_t *src);
@@ -249,7 +251,7 @@ static debug_info_t *debug_info_alloc(const char *name, int pages_per_area,
rc->level = level;
rc->buf_size = buf_size;
rc->entry_size = sizeof(debug_entry_t) + buf_size;
- strscpy(rc->name, name, sizeof(rc->name));
+ strscpy(rc->name, name);
memset(rc->views, 0, DEBUG_MAX_VIEWS * sizeof(struct debug_view *));
memset(rc->debugfs_entries, 0, DEBUG_MAX_VIEWS * sizeof(struct dentry *));
refcount_set(&(rc->ref_count), 0);
@@ -350,7 +352,10 @@ static debug_info_t *debug_info_copy(debug_info_t *in, int mode)
for (i = 0; i < in->nr_areas; i++) {
for (j = 0; j < in->pages_per_area; j++)
memcpy(rc->areas[i][j], in->areas[i][j], PAGE_SIZE);
+ rc->active_pages[i] = in->active_pages[i];
+ rc->active_entries[i] = in->active_entries[i];
}
+ rc->active_area = in->active_area;
out:
spin_unlock_irqrestore(&in->lock, flags);
return rc;
@@ -380,7 +385,7 @@ static void debug_info_put(debug_info_t *db_info)
/*
* debug_format_entry:
- * - format one debug entry and return size of formated data
+ * - format one debug entry and return size of formatted data
*/
static int debug_format_entry(file_private_info_t *p_info)
{
@@ -391,8 +396,10 @@ static int debug_format_entry(file_private_info_t *p_info)
if (p_info->act_entry == DEBUG_PROLOG_ENTRY) {
/* print prolog */
- if (view->prolog_proc)
- len += view->prolog_proc(id_snap, view, p_info->temp_buf);
+ if (view->prolog_proc) {
+ len += view->prolog_proc(id_snap, view, p_info->temp_buf,
+ sizeof(p_info->temp_buf));
+ }
goto out;
}
if (!id_snap->areas) /* this is true, if we have a prolog only view */
@@ -402,21 +409,31 @@ static int debug_format_entry(file_private_info_t *p_info)
if (act_entry->clock == 0LL)
goto out; /* empty entry */
- if (view->header_proc)
+ if (view->header_proc) {
len += view->header_proc(id_snap, view, p_info->act_area,
- act_entry, p_info->temp_buf + len);
- if (view->format_proc)
+ act_entry, p_info->temp_buf + len,
+ sizeof(p_info->temp_buf) - len);
+ }
+ if (view->format_proc) {
len += view->format_proc(id_snap, view, p_info->temp_buf + len,
+ sizeof(p_info->temp_buf) - len,
DEBUG_DATA(act_entry));
+ }
out:
return len;
}
-/*
- * debug_next_entry:
- * - goto next entry in p_info
+/**
+ * debug_next_entry - Go to the next entry
+ * @p_info: Private info that is manipulated
+ *
+ * Sets the current position in @p_info to the next entry. If no further entry
+ * exists the current position is set to one after the end the return value
+ * indicates that no further entries exist.
+ *
+ * Return: True if there are more following entries, false otherwise
*/
-static inline int debug_next_entry(file_private_info_t *p_info)
+static inline bool debug_next_entry(file_private_info_t *p_info)
{
debug_info_t *id;
@@ -424,10 +441,10 @@ static inline int debug_next_entry(file_private_info_t *p_info)
if (p_info->act_entry == DEBUG_PROLOG_ENTRY) {
p_info->act_entry = 0;
p_info->act_page = 0;
- goto out;
+ return true;
}
if (!id->areas)
- return 1;
+ return false;
p_info->act_entry += id->entry_size;
/* switch to next page, if we reached the end of the page */
if (p_info->act_entry > (PAGE_SIZE - id->entry_size)) {
@@ -440,16 +457,93 @@ static inline int debug_next_entry(file_private_info_t *p_info)
p_info->act_page = 0;
}
if (p_info->act_area >= id->nr_areas)
- return 1;
+ return false;
}
-out:
- return 0;
+ return true;
+}
+
+/**
+ * debug_to_act_entry - Go to the currently active entry
+ * @p_info: Private info that is manipulated
+ *
+ * Sets the current position in @p_info to the currently active
+ * entry of @p_info->debug_info_snap
+ */
+static void debug_to_act_entry(file_private_info_t *p_info)
+{
+ debug_info_t *snap_id;
+
+ snap_id = p_info->debug_info_snap;
+ p_info->act_area = snap_id->active_area;
+ p_info->act_page = snap_id->active_pages[snap_id->active_area];
+ p_info->act_entry = snap_id->active_entries[snap_id->active_area];
+}
+
+/**
+ * debug_prev_entry - Go to the previous entry
+ * @p_info: Private info that is manipulated
+ *
+ * Sets the current position in @p_info to the previous entry. If no previous entry
+ * exists the current position is set left as DEBUG_PROLOG_ENTRY and the return value
+ * indicates that no previous entries exist.
+ *
+ * Return: True if there are more previous entries, false otherwise
+ */
+
+static inline bool debug_prev_entry(file_private_info_t *p_info)
+{
+ debug_info_t *id;
+
+ id = p_info->debug_info_snap;
+ if (p_info->act_entry == DEBUG_PROLOG_ENTRY)
+ debug_to_act_entry(p_info);
+ if (!id->areas)
+ return false;
+ p_info->act_entry -= id->entry_size;
+ /* switch to prev page, if we reached the beginning of the page */
+ if (p_info->act_entry < 0) {
+ /* end of previous page */
+ p_info->act_entry = rounddown(PAGE_SIZE, id->entry_size) - id->entry_size;
+ p_info->act_page--;
+ if (p_info->act_page < 0) {
+ /* previous area */
+ p_info->act_area--;
+ p_info->act_page = id->pages_per_area - 1;
+ }
+ if (p_info->act_area < 0)
+ p_info->act_area = (id->nr_areas - 1) % id->nr_areas;
+ }
+ /* check full circle */
+ if (id->active_area == p_info->act_area &&
+ id->active_pages[id->active_area] == p_info->act_page &&
+ id->active_entries[id->active_area] == p_info->act_entry)
+ return false;
+ return true;
+}
+
+/**
+ * debug_move_entry - Go to next entry in either the forward or backward direction
+ * @p_info: Private info that is manipulated
+ * @reverse: If true go to the next entry in reverse i.e. previous
+ *
+ * Sets the current position in @p_info to the next (@reverse == false) or
+ * previous (@reverse == true) entry.
+ *
+ * Return: True if there are further entries in that direction,
+ * false otherwise.
+ */
+static bool debug_move_entry(file_private_info_t *p_info, bool reverse)
+{
+ if (reverse)
+ return debug_prev_entry(p_info);
+ else
+ return debug_next_entry(p_info);
}
/*
* debug_output:
* - called for user read()
- * - copies formated debug entries to the user buffer
+ * - copies formatted debug entries to the user buffer
*/
static ssize_t debug_output(struct file *file, /* file descriptor */
char __user *user_buf, /* user buffer */
@@ -485,7 +579,7 @@ static ssize_t debug_output(struct file *file, /* file descriptor */
}
if (copy_size == formatted_line_residue) {
entry_offset = 0;
- if (debug_next_entry(p_info))
+ if (!debug_next_entry(p_info))
goto out;
}
}
@@ -520,15 +614,51 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf,
return rc; /* number of input characters */
}
+static file_private_info_t *debug_file_private_alloc(debug_info_t *debug_info,
+ struct debug_view *view)
+{
+ debug_info_t *debug_info_snapshot;
+ file_private_info_t *p_info;
+
+ /*
+ * Make snapshot of current debug areas to get it consistent.
+ * To copy all the areas is only needed, if we have a view which
+ * formats the debug areas.
+ */
+ if (!view->format_proc && !view->header_proc)
+ debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS);
+ else
+ debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS);
+
+ if (!debug_info_snapshot)
+ return NULL;
+ p_info = kmalloc(sizeof(file_private_info_t), GFP_KERNEL);
+ if (!p_info) {
+ debug_info_free(debug_info_snapshot);
+ return NULL;
+ }
+ p_info->offset = 0;
+ p_info->debug_info_snap = debug_info_snapshot;
+ p_info->debug_info_org = debug_info;
+ p_info->view = view;
+ p_info->act_area = 0;
+ p_info->act_page = 0;
+ p_info->act_entry = DEBUG_PROLOG_ENTRY;
+ p_info->act_entry_offset = 0;
+ debug_info_get(debug_info);
+
+ return p_info;
+}
+
/*
* debug_open:
* - called for user open()
- * - copies formated output to private_data area of the file
+ * - copies formatted output to private_data area of the file
* handle
*/
static int debug_open(struct inode *inode, struct file *file)
{
- debug_info_t *debug_info, *debug_info_snapshot;
+ debug_info_t *debug_info;
file_private_info_t *p_info;
int i, rc = 0;
@@ -546,42 +676,26 @@ static int debug_open(struct inode *inode, struct file *file)
goto out;
found:
-
- /* Make snapshot of current debug areas to get it consistent. */
- /* To copy all the areas is only needed, if we have a view which */
- /* formats the debug areas. */
-
- if (!debug_info->views[i]->format_proc && !debug_info->views[i]->header_proc)
- debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS);
- else
- debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS);
-
- if (!debug_info_snapshot) {
- rc = -ENOMEM;
- goto out;
- }
- p_info = kmalloc(sizeof(file_private_info_t), GFP_KERNEL);
+ p_info = debug_file_private_alloc(debug_info, debug_info->views[i]);
if (!p_info) {
- debug_info_free(debug_info_snapshot);
rc = -ENOMEM;
goto out;
}
- p_info->offset = 0;
- p_info->debug_info_snap = debug_info_snapshot;
- p_info->debug_info_org = debug_info;
- p_info->view = debug_info->views[i];
- p_info->act_area = 0;
- p_info->act_page = 0;
- p_info->act_entry = DEBUG_PROLOG_ENTRY;
- p_info->act_entry_offset = 0;
file->private_data = p_info;
- debug_info_get(debug_info);
nonseekable_open(inode, file);
out:
mutex_unlock(&debug_mutex);
return rc;
}
+static void debug_file_private_free(file_private_info_t *p_info)
+{
+ if (p_info->debug_info_snap)
+ debug_info_free(p_info->debug_info_snap);
+ debug_info_put(p_info->debug_info_org);
+ kfree(p_info);
+}
+
/*
* debug_close:
* - called for user close()
@@ -592,13 +706,59 @@ static int debug_close(struct inode *inode, struct file *file)
file_private_info_t *p_info;
p_info = (file_private_info_t *) file->private_data;
- if (p_info->debug_info_snap)
- debug_info_free(p_info->debug_info_snap);
- debug_info_put(p_info->debug_info_org);
- kfree(file->private_data);
+ debug_file_private_free(p_info);
+ file->private_data = NULL;
return 0; /* success */
}
+/**
+ * debug_dump - Get a textual representation of debug info, or as much as fits
+ * @id: Debug information to use
+ * @view: View with which to dump the debug information
+ * @buf: Buffer the textual debug data representation is written to
+ * @buf_size: Size of the buffer, including the trailing '\0' byte
+ * @reverse: Go backwards from the last written entry
+ *
+ * This function may be used whenever a textual representation of the debug
+ * information is required without using an s390dbf file.
+ *
+ * Note: It is the callers responsibility to supply a view that is compatible
+ * with the debug information data.
+ *
+ * Return: On success returns the number of bytes written to the buffer not
+ * including the trailing '\0' byte. If bug_size == 0 the function returns 0.
+ * On failure an error code less than 0 is returned.
+ */
+ssize_t debug_dump(debug_info_t *id, struct debug_view *view,
+ char *buf, size_t buf_size, bool reverse)
+{
+ file_private_info_t *p_info;
+ size_t size, offset = 0;
+
+ /* Need space for '\0' byte */
+ if (buf_size < 1)
+ return 0;
+ buf_size--;
+
+ p_info = debug_file_private_alloc(id, view);
+ if (!p_info)
+ return -ENOMEM;
+
+ /* There is always at least the DEBUG_PROLOG_ENTRY */
+ do {
+ size = debug_format_entry(p_info);
+ size = min(size, buf_size - offset);
+ memcpy(buf + offset, p_info->temp_buf, size);
+ offset += size;
+ if (offset >= buf_size)
+ break;
+ } while (debug_move_entry(p_info, reverse));
+ debug_file_private_free(p_info);
+ buf[offset] = '\0';
+
+ return offset;
+}
+
/* Create debugfs entries and add to internal list. */
static void _debug_register(debug_info_t *id)
{
@@ -962,7 +1122,7 @@ static int s390dbf_procactive(const struct ctl_table *table, int write,
return 0;
}
-static struct ctl_table s390dbf_table[] = {
+static const struct ctl_table s390dbf_table[] = {
{
.procname = "debug_stoppable",
.data = &debug_stoppable,
@@ -1292,9 +1452,9 @@ static inline int debug_get_uint(char *buf)
*/
static int debug_prolog_pages_fn(debug_info_t *id, struct debug_view *view,
- char *out_buf)
+ char *out_buf, size_t out_buf_size)
{
- return sprintf(out_buf, "%i\n", id->pages_per_area);
+ return scnprintf(out_buf, out_buf_size, "%i\n", id->pages_per_area);
}
/*
@@ -1341,14 +1501,14 @@ out:
* prints out actual debug level
*/
static int debug_prolog_level_fn(debug_info_t *id, struct debug_view *view,
- char *out_buf)
+ char *out_buf, size_t out_buf_size)
{
int rc = 0;
if (id->level == DEBUG_OFF_LEVEL)
- rc = sprintf(out_buf, "-\n");
+ rc = scnprintf(out_buf, out_buf_size, "-\n");
else
- rc = sprintf(out_buf, "%i\n", id->level);
+ rc = scnprintf(out_buf, out_buf_size, "%i\n", id->level);
return rc;
}
@@ -1465,22 +1625,24 @@ out:
* prints debug data in hex/ascii format
*/
static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
- char *out_buf, const char *in_buf)
+ char *out_buf, size_t out_buf_size, const char *in_buf)
{
int i, rc = 0;
- for (i = 0; i < id->buf_size; i++)
- rc += sprintf(out_buf + rc, "%02x ", ((unsigned char *) in_buf)[i]);
- rc += sprintf(out_buf + rc, "| ");
+ for (i = 0; i < id->buf_size; i++) {
+ rc += scnprintf(out_buf + rc, out_buf_size - rc,
+ "%02x ", ((unsigned char *)in_buf)[i]);
+ }
+ rc += scnprintf(out_buf + rc, out_buf_size - rc, "| ");
for (i = 0; i < id->buf_size; i++) {
unsigned char c = in_buf[i];
if (isascii(c) && isprint(c))
- rc += sprintf(out_buf + rc, "%c", c);
+ rc += scnprintf(out_buf + rc, out_buf_size - rc, "%c", c);
else
- rc += sprintf(out_buf + rc, ".");
+ rc += scnprintf(out_buf + rc, out_buf_size - rc, ".");
}
- rc += sprintf(out_buf + rc, "\n");
+ rc += scnprintf(out_buf + rc, out_buf_size - rc, "\n");
return rc;
}
@@ -1488,7 +1650,8 @@ static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view,
* prints header for debug entry
*/
int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
- int area, debug_entry_t *entry, char *out_buf)
+ int area, debug_entry_t *entry, char *out_buf,
+ size_t out_buf_size)
{
unsigned long sec, usec;
unsigned long caller;
@@ -1505,22 +1668,22 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view,
else
except_str = "-";
caller = (unsigned long) entry->caller;
- rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %04u %px ",
- area, sec, usec, level, except_str,
- entry->cpu, (void *)caller);
+ rc += scnprintf(out_buf, out_buf_size, "%02i %011ld:%06lu %1u %1s %04u %px ",
+ area, sec, usec, level, except_str,
+ entry->cpu, (void *)caller);
return rc;
}
EXPORT_SYMBOL(debug_dflt_header_fn);
/*
- * prints debug data sprintf-formated:
+ * prints debug data sprintf-formatted:
* debug_sprinf_event/exception calls must be used together with this view
*/
#define DEBUG_SPRINTF_MAX_ARGS 10
-static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
- char *out_buf, const char *inbuf)
+int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
+ char *out_buf, size_t out_buf_size, const char *inbuf)
{
debug_sprintf_entry_t *curr_event = (debug_sprintf_entry_t *)inbuf;
int num_longs, num_used_args = 0, i, rc = 0;
@@ -1533,8 +1696,9 @@ static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
goto out; /* bufsize of entry too small */
if (num_longs == 1) {
/* no args, we use only the string */
- strcpy(out_buf, curr_event->string);
- rc = strlen(curr_event->string);
+ rc = strscpy(out_buf, curr_event->string, out_buf_size);
+ if (rc == -E2BIG)
+ rc = out_buf_size;
goto out;
}
@@ -1546,15 +1710,17 @@ static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view,
for (i = 0; i < num_used_args; i++)
index[i] = i;
- rc = sprintf(out_buf, curr_event->string, curr_event->args[index[0]],
- curr_event->args[index[1]], curr_event->args[index[2]],
- curr_event->args[index[3]], curr_event->args[index[4]],
- curr_event->args[index[5]], curr_event->args[index[6]],
- curr_event->args[index[7]], curr_event->args[index[8]],
- curr_event->args[index[9]]);
+ rc = scnprintf(out_buf, out_buf_size,
+ curr_event->string, curr_event->args[index[0]],
+ curr_event->args[index[1]], curr_event->args[index[2]],
+ curr_event->args[index[3]], curr_event->args[index[4]],
+ curr_event->args[index[5]], curr_event->args[index[6]],
+ curr_event->args[index[7]], curr_event->args[index[8]],
+ curr_event->args[index[9]]);
out:
return rc;
}
+EXPORT_SYMBOL(debug_sprintf_format_fn);
/*
* debug_init:
diff --git a/arch/s390/kernel/diag/Makefile b/arch/s390/kernel/diag/Makefile
new file mode 100644
index 000000000000..956aee6c4090
--- /dev/null
+++ b/arch/s390/kernel/diag/Makefile
@@ -0,0 +1 @@
+obj-y := diag_misc.o diag324.o diag.o diag310.o
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag/diag.c
index 007e1795670e..56b862ba9be8 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag/diag.c
@@ -16,7 +16,8 @@
#include <asm/diag.h>
#include <asm/trace/diag.h>
#include <asm/sections.h>
-#include "entry.h"
+#include <asm/asm.h>
+#include "../entry.h"
struct diag_stat {
unsigned int counter[NR_DIAG_STAT];
@@ -50,8 +51,10 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
[DIAG_STAT_X2FC] = { .code = 0x2fc, .name = "Guest Performance Data" },
[DIAG_STAT_X304] = { .code = 0x304, .name = "Partition-Resource Service" },
[DIAG_STAT_X308] = { .code = 0x308, .name = "List-Directed IPL" },
+ [DIAG_STAT_X310] = { .code = 0x310, .name = "Memory Topology Information" },
[DIAG_STAT_X318] = { .code = 0x318, .name = "CP Name and Version Codes" },
[DIAG_STAT_X320] = { .code = 0x320, .name = "Certificate Store" },
+ [DIAG_STAT_X324] = { .code = 0x324, .name = "Power Information Block" },
[DIAG_STAT_X49C] = { .code = 0x49c, .name = "Warning-Track Interruption" },
[DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" },
};
@@ -192,7 +195,7 @@ static inline int __diag204(unsigned long *subcode, unsigned long size, void *ad
{
union register_pair rp = { .even = *subcode, .odd = size };
- asm volatile(
+ asm_inline volatile(
" diag %[addr],%[rp],0x204\n"
"0: nopr %%r7\n"
EX_TABLE(0b,0b)
@@ -283,7 +286,7 @@ int diag224(void *ptr)
int rc = -EOPNOTSUPP;
diag_stat_inc(DIAG_STAT_X224);
- asm volatile("\n"
+ asm_inline volatile("\n"
" diag %[type],%[addr],0x224\n"
"0: lhi %[rc],0\n"
"1:\n"
@@ -307,16 +310,15 @@ EXPORT_SYMBOL(diag26c);
int diag49c(unsigned long subcode)
{
- int rc;
+ int cc;
diag_stat_inc(DIAG_STAT_X49C);
asm volatile(
" diag %[subcode],0,0x49c\n"
- " ipm %[rc]\n"
- " srl %[rc],28\n"
- : [rc] "=d" (rc)
+ CC_IPM(cc)
+ : CC_OUT(cc, cc)
: [subcode] "d" (subcode)
- : "cc");
- return rc;
+ : CC_CLOBBER);
+ return CC_TRANSFORM(cc);
}
EXPORT_SYMBOL(diag49c);
diff --git a/arch/s390/kernel/diag/diag310.c b/arch/s390/kernel/diag/diag310.c
new file mode 100644
index 000000000000..d6a34454aa5a
--- /dev/null
+++ b/arch/s390/kernel/diag/diag310.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Request memory topology information via diag0x310.
+ *
+ * Copyright IBM Corp. 2025
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <asm/diag.h>
+#include <asm/sclp.h>
+#include <uapi/asm/diag.h>
+#include "diag_ioctl.h"
+
+#define DIAG310_LEVELMIN 1
+#define DIAG310_LEVELMAX 6
+
+enum diag310_sc {
+ DIAG310_SUBC_0 = 0,
+ DIAG310_SUBC_1 = 1,
+ DIAG310_SUBC_4 = 4,
+ DIAG310_SUBC_5 = 5
+};
+
+enum diag310_retcode {
+ DIAG310_RET_SUCCESS = 0x0001,
+ DIAG310_RET_BUSY = 0x0101,
+ DIAG310_RET_OPNOTSUPP = 0x0102,
+ DIAG310_RET_SC4_INVAL = 0x0401,
+ DIAG310_RET_SC4_NODATA = 0x0402,
+ DIAG310_RET_SC5_INVAL = 0x0501,
+ DIAG310_RET_SC5_NODATA = 0x0502,
+ DIAG310_RET_SC5_ESIZE = 0x0503
+};
+
+union diag310_response {
+ u64 response;
+ struct {
+ u64 result : 32;
+ u64 : 16;
+ u64 rc : 16;
+ };
+};
+
+union diag310_req_subcode {
+ u64 subcode;
+ struct {
+ u64 : 48;
+ u64 st : 8;
+ u64 sc : 8;
+ };
+};
+
+union diag310_req_size {
+ u64 size;
+ struct {
+ u64 page_count : 32;
+ u64 : 32;
+ };
+};
+
+static inline unsigned long diag310(unsigned long subcode, unsigned long size, void *addr)
+{
+ union register_pair rp = { .even = (unsigned long)addr, .odd = size };
+
+ diag_stat_inc(DIAG_STAT_X310);
+ asm volatile("diag %[rp],%[subcode],0x310\n"
+ : [rp] "+d" (rp.pair)
+ : [subcode] "d" (subcode)
+ : "memory");
+ return rp.odd;
+}
+
+static int diag310_result_to_errno(unsigned int result)
+{
+ switch (result) {
+ case DIAG310_RET_BUSY:
+ return -EBUSY;
+ case DIAG310_RET_OPNOTSUPP:
+ return -EOPNOTSUPP;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int diag310_get_subcode_mask(unsigned long *mask)
+{
+ union diag310_response res;
+
+ res.response = diag310(DIAG310_SUBC_0, 0, NULL);
+ if (res.rc != DIAG310_RET_SUCCESS)
+ return diag310_result_to_errno(res.rc);
+ *mask = res.response;
+ return 0;
+}
+
+static int diag310_get_memtop_stride(unsigned long *stride)
+{
+ union diag310_response res;
+
+ res.response = diag310(DIAG310_SUBC_1, 0, NULL);
+ if (res.rc != DIAG310_RET_SUCCESS)
+ return diag310_result_to_errno(res.rc);
+ *stride = res.result;
+ return 0;
+}
+
+static int diag310_get_memtop_size(unsigned long *pages, unsigned long level)
+{
+ union diag310_req_subcode req = { .sc = DIAG310_SUBC_4, .st = level };
+ union diag310_response res;
+
+ res.response = diag310(req.subcode, 0, NULL);
+ switch (res.rc) {
+ case DIAG310_RET_SUCCESS:
+ *pages = res.result;
+ return 0;
+ case DIAG310_RET_SC4_NODATA:
+ return -ENODATA;
+ case DIAG310_RET_SC4_INVAL:
+ return -EINVAL;
+ default:
+ return diag310_result_to_errno(res.rc);
+ }
+}
+
+static int diag310_store_topology_map(void *buf, unsigned long pages, unsigned long level)
+{
+ union diag310_req_subcode req_sc = { .sc = DIAG310_SUBC_5, .st = level };
+ union diag310_req_size req_size = { .page_count = pages };
+ union diag310_response res;
+
+ res.response = diag310(req_sc.subcode, req_size.size, buf);
+ switch (res.rc) {
+ case DIAG310_RET_SUCCESS:
+ return 0;
+ case DIAG310_RET_SC5_NODATA:
+ return -ENODATA;
+ case DIAG310_RET_SC5_ESIZE:
+ return -EOVERFLOW;
+ case DIAG310_RET_SC5_INVAL:
+ return -EINVAL;
+ default:
+ return diag310_result_to_errno(res.rc);
+ }
+}
+
+static int diag310_check_features(void)
+{
+ static int features_available;
+ unsigned long mask;
+ int rc;
+
+ if (READ_ONCE(features_available))
+ return 0;
+ if (!sclp.has_diag310)
+ return -EOPNOTSUPP;
+ rc = diag310_get_subcode_mask(&mask);
+ if (rc)
+ return rc;
+ if (!test_bit_inv(DIAG310_SUBC_1, &mask))
+ return -EOPNOTSUPP;
+ if (!test_bit_inv(DIAG310_SUBC_4, &mask))
+ return -EOPNOTSUPP;
+ if (!test_bit_inv(DIAG310_SUBC_5, &mask))
+ return -EOPNOTSUPP;
+ WRITE_ONCE(features_available, 1);
+ return 0;
+}
+
+static int memtop_get_stride_len(unsigned long *res)
+{
+ static unsigned long memtop_stride;
+ unsigned long stride;
+ int rc;
+
+ stride = READ_ONCE(memtop_stride);
+ if (!stride) {
+ rc = diag310_get_memtop_stride(&stride);
+ if (rc)
+ return rc;
+ WRITE_ONCE(memtop_stride, stride);
+ }
+ *res = stride;
+ return 0;
+}
+
+static int memtop_get_page_count(unsigned long *res, unsigned long level)
+{
+ static unsigned long memtop_pages[DIAG310_LEVELMAX];
+ unsigned long pages;
+ int rc;
+
+ if (level > DIAG310_LEVELMAX || level < DIAG310_LEVELMIN)
+ return -EINVAL;
+ pages = READ_ONCE(memtop_pages[level - 1]);
+ if (!pages) {
+ rc = diag310_get_memtop_size(&pages, level);
+ if (rc)
+ return rc;
+ WRITE_ONCE(memtop_pages[level - 1], pages);
+ }
+ *res = pages;
+ return 0;
+}
+
+long diag310_memtop_stride(unsigned long arg)
+{
+ size_t __user *argp = (void __user *)arg;
+ unsigned long stride;
+ int rc;
+
+ rc = diag310_check_features();
+ if (rc)
+ return rc;
+ rc = memtop_get_stride_len(&stride);
+ if (rc)
+ return rc;
+ if (put_user(stride, argp))
+ return -EFAULT;
+ return 0;
+}
+
+long diag310_memtop_len(unsigned long arg)
+{
+ size_t __user *argp = (void __user *)arg;
+ unsigned long pages, level;
+ int rc;
+
+ rc = diag310_check_features();
+ if (rc)
+ return rc;
+ if (get_user(level, argp))
+ return -EFAULT;
+ rc = memtop_get_page_count(&pages, level);
+ if (rc)
+ return rc;
+ if (put_user(pages * PAGE_SIZE, argp))
+ return -EFAULT;
+ return 0;
+}
+
+long diag310_memtop_buf(unsigned long arg)
+{
+ struct diag310_memtop __user *udata = (struct diag310_memtop __user *)arg;
+ unsigned long level, pages, data_size;
+ u64 address;
+ void *buf;
+ int rc;
+
+ rc = diag310_check_features();
+ if (rc)
+ return rc;
+ if (get_user(level, &udata->nesting_lvl))
+ return -EFAULT;
+ if (get_user(address, &udata->address))
+ return -EFAULT;
+ rc = memtop_get_page_count(&pages, level);
+ if (rc)
+ return rc;
+ data_size = pages * PAGE_SIZE;
+ buf = __vmalloc_node(data_size, PAGE_SIZE, GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT,
+ NUMA_NO_NODE, __builtin_return_address(0));
+ if (!buf)
+ return -ENOMEM;
+ rc = diag310_store_topology_map(buf, pages, level);
+ if (rc)
+ goto out;
+ if (copy_to_user((void __user *)address, buf, data_size))
+ rc = -EFAULT;
+out:
+ vfree(buf);
+ return rc;
+}
diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c
new file mode 100644
index 000000000000..7fa4c0b7eb6c
--- /dev/null
+++ b/arch/s390/kernel/diag/diag324.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Request power readings for resources in a computing environment via
+ * diag 0x324. diag 0x324 stores the power readings in the power information
+ * block (pib).
+ *
+ * Copyright IBM Corp. 2024
+ */
+
+#define pr_fmt(fmt) "diag324: " fmt
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/ioctl.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/ktime.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+
+#include <asm/diag.h>
+#include <asm/sclp.h>
+#include <asm/timex.h>
+#include <uapi/asm/diag.h>
+#include "diag_ioctl.h"
+
+enum subcode {
+ DIAG324_SUBC_0 = 0,
+ DIAG324_SUBC_1 = 1,
+ DIAG324_SUBC_2 = 2,
+};
+
+enum retcode {
+ DIAG324_RET_SUCCESS = 0x0001,
+ DIAG324_RET_SUBC_NOTAVAIL = 0x0103,
+ DIAG324_RET_INSUFFICIENT_SIZE = 0x0104,
+ DIAG324_RET_READING_UNAVAILABLE = 0x0105,
+};
+
+union diag324_response {
+ u64 response;
+ struct {
+ u64 installed : 32;
+ u64 : 16;
+ u64 rc : 16;
+ } sc0;
+ struct {
+ u64 format : 16;
+ u64 : 16;
+ u64 pib_len : 16;
+ u64 rc : 16;
+ } sc1;
+ struct {
+ u64 : 48;
+ u64 rc : 16;
+ } sc2;
+};
+
+union diag324_request {
+ u64 request;
+ struct {
+ u64 : 32;
+ u64 allocated : 16;
+ u64 : 12;
+ u64 sc : 4;
+ } sc2;
+};
+
+struct pib {
+ u32 : 8;
+ u32 num : 8;
+ u32 len : 16;
+ u32 : 24;
+ u32 hlen : 8;
+ u64 : 64;
+ u64 intv;
+ u8 r[];
+} __packed;
+
+struct pibdata {
+ struct pib *pib;
+ ktime_t expire;
+ u64 sequence;
+ size_t len;
+ int rc;
+};
+
+static DEFINE_MUTEX(pibmutex);
+static struct pibdata pibdata;
+
+#define PIBWORK_DELAY (5 * NSEC_PER_SEC)
+
+static void pibwork_handler(struct work_struct *work);
+static DECLARE_DELAYED_WORK(pibwork, pibwork_handler);
+
+static unsigned long diag324(unsigned long subcode, void *addr)
+{
+ union register_pair rp = { .even = (unsigned long)addr };
+
+ diag_stat_inc(DIAG_STAT_X324);
+ asm volatile("diag %[rp],%[subcode],0x324\n"
+ : [rp] "+d" (rp.pair)
+ : [subcode] "d" (subcode)
+ : "memory");
+ return rp.odd;
+}
+
+static void pibwork_handler(struct work_struct *work)
+{
+ struct pibdata *data = &pibdata;
+ ktime_t timedout;
+
+ mutex_lock(&pibmutex);
+ timedout = ktime_add_ns(data->expire, PIBWORK_DELAY);
+ if (ktime_before(ktime_get(), timedout)) {
+ mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY));
+ goto out;
+ }
+ vfree(data->pib);
+ data->pib = NULL;
+out:
+ mutex_unlock(&pibmutex);
+}
+
+static void pib_update(struct pibdata *data)
+{
+ union diag324_request req = { .sc2.sc = DIAG324_SUBC_2, .sc2.allocated = data->len };
+ union diag324_response res;
+ int rc;
+
+ memset(data->pib, 0, data->len);
+ res.response = diag324(req.request, data->pib);
+ switch (res.sc2.rc) {
+ case DIAG324_RET_SUCCESS:
+ rc = 0;
+ break;
+ case DIAG324_RET_SUBC_NOTAVAIL:
+ rc = -ENOENT;
+ break;
+ case DIAG324_RET_INSUFFICIENT_SIZE:
+ rc = -EMSGSIZE;
+ break;
+ case DIAG324_RET_READING_UNAVAILABLE:
+ rc = -EBUSY;
+ break;
+ default:
+ rc = -EINVAL;
+ }
+ data->rc = rc;
+}
+
+long diag324_pibbuf(unsigned long arg)
+{
+ struct diag324_pib __user *udata = (struct diag324_pib __user *)arg;
+ struct pibdata *data = &pibdata;
+ static bool first = true;
+ u64 address;
+ int rc;
+
+ if (!data->len)
+ return -EOPNOTSUPP;
+ if (get_user(address, &udata->address))
+ return -EFAULT;
+ mutex_lock(&pibmutex);
+ rc = -ENOMEM;
+ if (!data->pib)
+ data->pib = vmalloc(data->len);
+ if (!data->pib)
+ goto out;
+ if (first || ktime_after(ktime_get(), data->expire)) {
+ pib_update(data);
+ data->sequence++;
+ data->expire = ktime_add_ns(ktime_get(), tod_to_ns(data->pib->intv));
+ mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY));
+ first = false;
+ }
+ rc = data->rc;
+ if (rc != 0 && rc != -EBUSY)
+ goto out;
+ rc = copy_to_user((void __user *)address, data->pib, data->pib->len);
+ rc |= put_user(data->sequence, &udata->sequence);
+ if (rc)
+ rc = -EFAULT;
+out:
+ mutex_unlock(&pibmutex);
+ return rc;
+}
+
+long diag324_piblen(unsigned long arg)
+{
+ struct pibdata *data = &pibdata;
+
+ if (!data->len)
+ return -EOPNOTSUPP;
+ if (put_user(data->len, (size_t __user *)arg))
+ return -EFAULT;
+ return 0;
+}
+
+static int __init diag324_init(void)
+{
+ union diag324_response res;
+ unsigned long installed;
+
+ if (!sclp.has_diag324)
+ return -EOPNOTSUPP;
+ res.response = diag324(DIAG324_SUBC_0, NULL);
+ if (res.sc0.rc != DIAG324_RET_SUCCESS)
+ return -EOPNOTSUPP;
+ installed = res.response;
+ if (!test_bit_inv(DIAG324_SUBC_1, &installed))
+ return -EOPNOTSUPP;
+ if (!test_bit_inv(DIAG324_SUBC_2, &installed))
+ return -EOPNOTSUPP;
+ res.response = diag324(DIAG324_SUBC_1, NULL);
+ if (res.sc1.rc != DIAG324_RET_SUCCESS)
+ return -EOPNOTSUPP;
+ pibdata.len = res.sc1.pib_len;
+ return 0;
+}
+device_initcall(diag324_init);
diff --git a/arch/s390/kernel/diag/diag_ioctl.h b/arch/s390/kernel/diag/diag_ioctl.h
new file mode 100644
index 000000000000..7080be946785
--- /dev/null
+++ b/arch/s390/kernel/diag/diag_ioctl.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _DIAG_IOCTL_H
+#define _DIAG_IOCTL_H
+
+#include <linux/types.h>
+
+long diag324_pibbuf(unsigned long arg);
+long diag324_piblen(unsigned long arg);
+
+long diag310_memtop_stride(unsigned long arg);
+long diag310_memtop_len(unsigned long arg);
+long diag310_memtop_buf(unsigned long arg);
+
+#endif /* _DIAG_IOCTL_H */
diff --git a/arch/s390/kernel/diag/diag_misc.c b/arch/s390/kernel/diag/diag_misc.c
new file mode 100644
index 000000000000..efffe02ea02e
--- /dev/null
+++ b/arch/s390/kernel/diag/diag_misc.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Provide diagnose information via misc device /dev/diag.
+ *
+ * Copyright IBM Corp. 2024
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/ioctl.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/types.h>
+
+#include <uapi/asm/diag.h>
+#include "diag_ioctl.h"
+
+static long diag_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ long rc;
+
+ switch (cmd) {
+ case DIAG324_GET_PIBLEN:
+ rc = diag324_piblen(arg);
+ break;
+ case DIAG324_GET_PIBBUF:
+ rc = diag324_pibbuf(arg);
+ break;
+ case DIAG310_GET_STRIDE:
+ rc = diag310_memtop_stride(arg);
+ break;
+ case DIAG310_GET_MEMTOPLEN:
+ rc = diag310_memtop_len(arg);
+ break;
+ case DIAG310_GET_MEMTOPBUF:
+ rc = diag310_memtop_buf(arg);
+ break;
+ default:
+ rc = -ENOIOCTLCMD;
+ break;
+ }
+ return rc;
+}
+
+static const struct file_operations fops = {
+ .owner = THIS_MODULE,
+ .open = nonseekable_open,
+ .unlocked_ioctl = diag_ioctl,
+};
+
+static struct miscdevice diagdev = {
+ .name = "diag",
+ .minor = MISC_DYNAMIC_MINOR,
+ .fops = &fops,
+ .mode = 0444,
+};
+
+static int diag_init(void)
+{
+ return misc_register(&diagdev);
+}
+
+device_initcall(diag_init);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 1ecd0580561f..dd410962ecbe 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -17,6 +17,7 @@
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
+#include <asm/asm-offsets.h>
#include <asm/processor.h>
#include <asm/debug.h>
#include <asm/dis.h>
@@ -198,13 +199,8 @@ void __noreturn die(struct pt_regs *regs, const char *str)
console_verbose();
spin_lock_irq(&die_lock);
bust_spinlocks(1);
- printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff,
+ printk("%s: %04x ilc:%d [#%d]", str, regs->int_code & 0xffff,
regs->int_code >> 17, ++die_counter);
-#ifdef CONFIG_PREEMPT
- pr_cont("PREEMPT ");
-#elif defined(CONFIG_PREEMPT_RT)
- pr_cont("PREEMPT_RT ");
-#endif
pr_cont("SMP ");
if (debug_pagealloc_enabled())
pr_cont("DEBUG_PAGEALLOC");
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 62f8f5a750a3..54cf0923050f 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -8,6 +8,7 @@
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/sched/debug.h>
+#include <linux/cpufeature.h>
#include <linux/compiler.h>
#include <linux/init.h>
#include <linux/errno.h>
@@ -21,6 +22,8 @@
#include <asm/asm-extable.h>
#include <linux/memblock.h>
#include <asm/access-regs.h>
+#include <asm/asm-offsets.h>
+#include <asm/machine.h>
#include <asm/diag.h>
#include <asm/ebcdic.h>
#include <asm/fpu.h>
@@ -36,12 +39,14 @@
#include <asm/boot_data.h>
#include "entry.h"
-#define decompressor_handled_param(param) \
-static int __init ignore_decompressor_param_##param(char *s) \
+#define __decompressor_handled_param(func, param) \
+static int __init ignore_decompressor_param_##func(char *s) \
{ \
return 0; \
} \
-early_param(#param, ignore_decompressor_param_##param)
+early_param(#param, ignore_decompressor_param_##func)
+
+#define decompressor_handled_param(param) __decompressor_handled_param(param, param)
decompressor_handled_param(mem);
decompressor_handled_param(vmalloc);
@@ -50,6 +55,8 @@ decompressor_handled_param(facilities);
decompressor_handled_param(nokaslr);
decompressor_handled_param(cmma);
decompressor_handled_param(relocate_lowcore);
+decompressor_handled_param(bootdebug);
+__decompressor_handled_param(debug_alternative, debug-alternative);
#if IS_ENABLED(CONFIG_KVM)
decompressor_handled_param(prot_virt);
#endif
@@ -58,25 +65,10 @@ static void __init kasan_early_init(void)
{
#ifdef CONFIG_KASAN
init_task.kasan_depth = 0;
- sclp_early_printk("KernelAddressSanitizer initialized\n");
+ pr_info("KernelAddressSanitizer initialized\n");
#endif
}
-static void __init reset_tod_clock(void)
-{
- union tod_clock clk;
-
- if (store_tod_clock_ext_cc(&clk) == 0)
- return;
- /* TOD clock not running. Set the clock to Unix Epoch. */
- if (set_tod_clock(TOD_UNIX_EPOCH) || store_tod_clock_ext_cc(&clk))
- disabled_wait();
-
- memset(&tod_clock_base, 0, sizeof(tod_clock_base));
- tod_clock_base.tod = TOD_UNIX_EPOCH;
- get_lowcore()->last_update_clock = TOD_UNIX_EPOCH;
-}
-
/*
* Initialize storage key for kernel pages
*/
@@ -95,26 +87,6 @@ static noinline __init void init_kernel_storage_key(void)
static __initdata char sysinfo_page[PAGE_SIZE] __aligned(PAGE_SIZE);
-static noinline __init void detect_machine_type(void)
-{
- struct sysinfo_3_2_2 *vmms = (struct sysinfo_3_2_2 *)&sysinfo_page;
-
- /* Check current-configuration-level */
- if (stsi(NULL, 0, 0, 0) <= 2) {
- get_lowcore()->machine_flags |= MACHINE_FLAG_LPAR;
- return;
- }
- /* Get virtual-machine cpu information. */
- if (stsi(vmms, 3, 2, 2) || !vmms->count)
- return;
-
- /* Detect known hypervisors */
- if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
- get_lowcore()->machine_flags |= MACHINE_FLAG_KVM;
- else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
- get_lowcore()->machine_flags |= MACHINE_FLAG_VM;
-}
-
/* Remove leading, trailing and double whitespace. */
static inline void strim_all(char *str)
{
@@ -155,9 +127,9 @@ static noinline __init void setup_arch_string(void)
strim_all(hvstr);
} else {
sprintf(hvstr, "%s",
- MACHINE_IS_LPAR ? "LPAR" :
- MACHINE_IS_VM ? "z/VM" :
- MACHINE_IS_KVM ? "KVM" : "unknown");
+ machine_is_lpar() ? "LPAR" :
+ machine_is_vm() ? "z/VM" :
+ machine_is_kvm() ? "KVM" : "unknown");
}
dump_stack_set_arch_desc("%s (%s)", mstr, hvstr);
}
@@ -166,9 +138,8 @@ static __init void setup_topology(void)
{
int max_mnest;
- if (!test_facility(11))
+ if (!cpu_has_topology())
return;
- get_lowcore()->machine_flags |= MACHINE_FLAG_TOPOLOGY;
for (max_mnest = 6; max_mnest > 1; max_mnest--) {
if (stsi(&sysinfo_page, 15, 1, max_mnest) == 0)
break;
@@ -217,65 +188,10 @@ static noinline __init void setup_lowcore_early(void)
lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
}
-static __init void detect_diag9c(void)
-{
- unsigned int cpu_address;
- int rc;
-
- cpu_address = stap();
- diag_stat_inc(DIAG_STAT_X09C);
- asm volatile(
- " diag %2,0,0x9c\n"
- "0: la %0,0\n"
- "1:\n"
- EX_TABLE(0b,1b)
- : "=d" (rc) : "0" (-EOPNOTSUPP), "d" (cpu_address) : "cc");
- if (!rc)
- get_lowcore()->machine_flags |= MACHINE_FLAG_DIAG9C;
-}
-
-static __init void detect_machine_facilities(void)
-{
- if (test_facility(8)) {
- get_lowcore()->machine_flags |= MACHINE_FLAG_EDAT1;
- system_ctl_set_bit(0, CR0_EDAT_BIT);
- }
- if (test_facility(78))
- get_lowcore()->machine_flags |= MACHINE_FLAG_EDAT2;
- if (test_facility(3))
- get_lowcore()->machine_flags |= MACHINE_FLAG_IDTE;
- if (test_facility(50) && test_facility(73)) {
- get_lowcore()->machine_flags |= MACHINE_FLAG_TE;
- system_ctl_set_bit(0, CR0_TRANSACTIONAL_EXECUTION_BIT);
- }
- if (test_facility(51))
- get_lowcore()->machine_flags |= MACHINE_FLAG_TLB_LC;
- if (test_facility(129))
- system_ctl_set_bit(0, CR0_VECTOR_BIT);
- if (test_facility(130))
- get_lowcore()->machine_flags |= MACHINE_FLAG_NX;
- if (test_facility(133))
- get_lowcore()->machine_flags |= MACHINE_FLAG_GS;
- if (test_facility(139) && (tod_clock_base.tod >> 63)) {
- /* Enabled signed clock comparator comparisons */
- get_lowcore()->machine_flags |= MACHINE_FLAG_SCC;
- clock_comparator_max = -1ULL >> 1;
- system_ctl_set_bit(0, CR0_CLOCK_COMPARATOR_SIGN_BIT);
- }
- if (IS_ENABLED(CONFIG_PCI) && test_facility(153)) {
- get_lowcore()->machine_flags |= MACHINE_FLAG_PCI_MIO;
- /* the control bit is set during PCI initialization */
- }
- if (test_facility(194))
- get_lowcore()->machine_flags |= MACHINE_FLAG_RDP;
- if (test_facility(85))
- get_lowcore()->machine_flags |= MACHINE_FLAG_SEQ_INSN;
-}
-
static inline void save_vector_registers(void)
{
#ifdef CONFIG_CRASH_DUMP
- if (test_facility(129))
+ if (cpu_has_vx())
save_vx_regs(boot_cpu_vector_save_area);
#endif
}
@@ -307,17 +223,13 @@ static void __init sort_amode31_extable(void)
void __init startup_init(void)
{
kasan_early_init();
- reset_tod_clock();
time_early_init();
init_kernel_storage_key();
lockdep_off();
sort_amode31_extable();
setup_lowcore_early();
- detect_machine_type();
setup_arch_string();
setup_boot_command_line();
- detect_diag9c();
- detect_machine_facilities();
save_vector_registers();
setup_topology();
sclp_early_detect();
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index d6d5317f768e..0f00f4b06d51 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -29,6 +29,7 @@
#include <asm/nmi.h>
#include <asm/nospec-insn.h>
#include <asm/lowcore.h>
+#include <asm/machine.h>
_LPP_OFFSET = __LC_LPP
@@ -44,7 +45,7 @@ _LPP_OFFSET = __LC_LPP
ALTERNATIVE_2 "b \lpswe;nopr", \
".insn siy,0xeb0000000071,\address,0", ALT_FACILITY(193), \
__stringify(.insn siy,0xeb0000000071,LOWCORE_ALT_ADDRESS+\address,0), \
- ALT_LOWCORE
+ ALT_FEATURE(MFEATURE_LOWCORE)
.endm
.macro MBEAR reg, lowcore
@@ -52,16 +53,7 @@ _LPP_OFFSET = __LC_LPP
ALT_FACILITY(193)
.endm
- .macro CHECK_STACK savearea, lowcore
-#ifdef CONFIG_CHECK_STACK
- tml %r15,THREAD_SIZE - CONFIG_STACK_GUARD
- la %r14,\savearea(\lowcore)
- jz stack_overflow
-#endif
- .endm
-
.macro CHECK_VMAP_STACK savearea, lowcore, oklabel
-#ifdef CONFIG_VMAP_STACK
lgr %r14,%r15
nill %r14,0x10000 - THREAD_SIZE
oill %r14,STACK_INIT_OFFSET
@@ -76,10 +68,7 @@ _LPP_OFFSET = __LC_LPP
clg %r14,__LC_RESTART_STACK(\lowcore)
je \oklabel
la %r14,\savearea(\lowcore)
- j stack_overflow
-#else
- j \oklabel
-#endif
+ j stack_invalid
.endm
/*
@@ -127,7 +116,7 @@ _LPP_OFFSET = __LC_LPP
.macro SIEEXIT sie_control,lowcore
lg %r9,\sie_control # get control block pointer
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
- lctlg %c1,%c1,__LC_KERNEL_ASCE(\lowcore) # load primary asce
+ lctlg %c1,%c1,__LC_USER_ASCE(\lowcore) # load primary asce
lg %r9,__LC_CURRENT(\lowcore)
mvi __TI_sie(%r9),0
larl %r9,sie_exit # skip forward to sie_exit
@@ -219,20 +208,9 @@ SYM_FUNC_START(__sie64a)
lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
GET_LC %r14
- lctlg %c1,%c1,__LC_KERNEL_ASCE(%r14) # load primary asce
+ lctlg %c1,%c1,__LC_USER_ASCE(%r14) # load primary asce
lg %r14,__LC_CURRENT(%r14)
mvi __TI_sie(%r14),0
-# some program checks are suppressing. C code (e.g. do_protection_exception)
-# will rewind the PSW by the ILC, which is often 4 bytes in case of SIE. There
-# are some corner cases (e.g. runtime instrumentation) where ILC is unpredictable.
-# Other instructions between __sie64a and .Lsie_done should not cause program
-# interrupts. So lets use 3 nops as a landing pad for all possible rewinds.
-.Lrewind_pad6:
- nopr 7
-.Lrewind_pad4:
- nopr 7
-.Lrewind_pad2:
- nopr 7
SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL)
lg %r14,__SF_SIE_SAVEAREA(%r15) # load guest register save area
stmg %r0,%r13,0(%r14) # save guest gprs 0-13
@@ -244,15 +222,6 @@ SYM_INNER_LABEL(sie_exit, SYM_L_GLOBAL)
lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers
lg %r2,__SF_SIE_REASON(%r15) # return exit reason code
BR_EX %r14
-.Lsie_fault:
- lghi %r14,-EFAULT
- stg %r14,__SF_SIE_REASON(%r15) # set exit reason code
- j sie_exit
-
- EX_TABLE(.Lrewind_pad6,.Lsie_fault)
- EX_TABLE(.Lrewind_pad4,.Lsie_fault)
- EX_TABLE(.Lrewind_pad2,.Lsie_fault)
- EX_TABLE(sie_exit,.Lsie_fault)
SYM_FUNC_END(__sie64a)
EXPORT_SYMBOL(__sie64a)
EXPORT_SYMBOL(sie_exit)
@@ -271,7 +240,6 @@ SYM_CODE_START(system_call)
lghi %r14,0
.Lsysc_per:
STBEAR __LC_LAST_BREAK(%r13)
- lctlg %c1,%c1,__LC_KERNEL_ASCE(%r13)
lg %r15,__LC_KERNEL_STACK(%r13)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
stmg %r0,%r7,STACK_FRAME_OVERHEAD+__PT_R0(%r15)
@@ -292,7 +260,6 @@ SYM_CODE_START(system_call)
lgr %r3,%r14
brasl %r14,__do_syscall
STACKLEAK_ERASE
- lctlg %c1,%c1,__LC_USER_ASCE(%r13)
mvc __LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
BPON
LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
@@ -309,7 +276,6 @@ SYM_CODE_START(ret_from_fork)
brasl %r14,__ret_from_fork
STACKLEAK_ERASE
GET_LC %r13
- lctlg %c1,%c1,__LC_USER_ASCE(%r13)
mvc __LC_RETURN_PSW(16,%r13),STACK_FRAME_OVERHEAD+__PT_PSW(%r15)
BPON
LBEAR STACK_FRAME_OVERHEAD+__PT_LAST_BREAK(%r15)
@@ -327,38 +293,33 @@ SYM_CODE_START(pgm_check_handler)
GET_LC %r13
stpt __LC_SYS_ENTER_TIMER(%r13)
BPOFF
- lgr %r10,%r15
lmg %r8,%r9,__LC_PGM_OLD_PSW(%r13)
+ xgr %r10,%r10
tmhh %r8,0x0001 # coming from user space?
- jno .Lpgm_skip_asce
- lctlg %c1,%c1,__LC_KERNEL_ASCE(%r13)
- j 3f # -> fault in user space
-.Lpgm_skip_asce:
+ jo 3f # -> fault in user space
+#if IS_ENABLED(CONFIG_KVM)
+ lg %r11,__LC_CURRENT(%r13)
+ tm __TI_sie(%r11),0xff
+ jz 1f
+ BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
+ SIEEXIT __SF_SIE_CONTROL(%r15),%r13
+ lghi %r10,_PIF_GUEST_FAULT
+#endif
1: tmhh %r8,0x4000 # PER bit set in old PSW ?
jnz 2f # -> enabled, can't be a double fault
tm __LC_PGM_ILC+3(%r13),0x80 # check for per exception
jnz .Lpgm_svcper # -> single stepped svc
-2: CHECK_STACK __LC_SAVE_AREA,%r13
- aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- # CHECK_VMAP_STACK branches to stack_overflow or 4f
+2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+ # CHECK_VMAP_STACK branches to stack_invalid or 4f
CHECK_VMAP_STACK __LC_SAVE_AREA,%r13,4f
3: lg %r15,__LC_KERNEL_STACK(%r13)
4: la %r11,STACK_FRAME_OVERHEAD(%r15)
- xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
+ stg %r10,__PT_FLAGS(%r11)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
stmg %r0,%r7,__PT_R0(%r11)
mvc __PT_R8(64,%r11),__LC_SAVE_AREA(%r13)
mvc __PT_LAST_BREAK(8,%r11),__LC_PGM_LAST_BREAK(%r13)
- stctg %c1,%c1,__PT_CR1(%r11)
-#if IS_ENABLED(CONFIG_KVM)
- ltg %r12,__LC_GMAP(%r13)
- jz 5f
- clc __GMAP_ASCE(8,%r12), __PT_CR1(%r11)
- jne 5f
- BPENTER __SF_SIE_FLAGS(%r10),_TIF_ISOLATE_BP_GUEST
- SIEEXIT __SF_SIE_CONTROL(%r10),%r13
-#endif
-5: stmg %r8,%r9,__PT_PSW(%r11)
+ stmg %r8,%r9,__PT_PSW(%r11)
# clear user controlled registers to prevent speculative use
xgr %r0,%r0
xgr %r1,%r1
@@ -367,12 +328,12 @@ SYM_CODE_START(pgm_check_handler)
xgr %r5,%r5
xgr %r6,%r6
xgr %r7,%r7
+ xgr %r12,%r12
lgr %r2,%r11
brasl %r14,__do_pgm_check
tmhh %r8,0x0001 # returning to user space?
jno .Lpgm_exit_kernel
STACKLEAK_ERASE
- lctlg %c1,%c1,__LC_USER_ASCE(%r13)
BPON
stpt __LC_EXIT_TIMER(%r13)
.Lpgm_exit_kernel:
@@ -414,11 +375,9 @@ SYM_CODE_START(\name)
BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
SIEEXIT __SF_SIE_CONTROL(%r15),%r13
#endif
-0: CHECK_STACK __LC_SAVE_AREA,%r13
- aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
+0: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
j 2f
-1: lctlg %c1,%c1,__LC_KERNEL_ASCE(%r13)
- lg %r15,__LC_KERNEL_STACK(%r13)
+1: lg %r15,__LC_KERNEL_STACK(%r13)
2: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
@@ -441,7 +400,6 @@ SYM_CODE_START(\name)
tmhh %r8,0x0001 # returning to user ?
jno 2f
STACKLEAK_ERASE
- lctlg %c1,%c1,__LC_USER_ASCE(%r13)
BPON
stpt __LC_EXIT_TIMER(%r13)
2: LBEAR __PT_LAST_BREAK(%r11)
@@ -450,9 +408,13 @@ SYM_CODE_START(\name)
SYM_CODE_END(\name)
.endm
+ .section .irqentry.text, "ax"
+
INT_HANDLER ext_int_handler,__LC_EXT_OLD_PSW,do_ext_irq
INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq
+ .section .kprobes.text, "ax"
+
/*
* Machine check handler routines
*/
@@ -497,7 +459,7 @@ SYM_CODE_START(mcck_int_handler)
clgrjl %r9,%r14, 4f
larl %r14,.Lsie_leave
clgrjhe %r9,%r14, 4f
- lg %r10,__LC_PCPU
+ lg %r10,__LC_PCPU(%r13)
oi __PCPU_FLAGS+7(%r10), _CIF_MCCK_GUEST
4: BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
SIEEXIT __SF_SIE_CONTROL(%r15),%r13
@@ -505,8 +467,6 @@ SYM_CODE_START(mcck_int_handler)
.Lmcck_user:
lg %r15,__LC_MCCK_STACK(%r13)
la %r11,STACK_FRAME_OVERHEAD(%r15)
- stctg %c1,%c1,__PT_CR1(%r11)
- lctlg %c1,%c1,__LC_KERNEL_ASCE(%r13)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lay %r14,__LC_GPREGS_SAVE_AREA(%r13)
mvc __PT_R0(128,%r11),0(%r14)
@@ -524,7 +484,6 @@ SYM_CODE_START(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
- lctlg %c1,%c1,__PT_CR1(%r11)
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_MCCK_PSW(16,%r13),__PT_PSW(%r11) # move return PSW
tm __LC_RETURN_MCCK_PSW+1(%r13),0x01 # returning to user ?
@@ -619,25 +578,24 @@ SYM_CODE_END(early_pgm_check_handler)
.section .kprobes.text, "ax"
-#if defined(CONFIG_CHECK_STACK) || defined(CONFIG_VMAP_STACK)
/*
- * The synchronous or the asynchronous stack overflowed. We are dead.
+ * The synchronous or the asynchronous stack pointer is invalid. We are dead.
* No need to properly save the registers, we are going to panic anyway.
* Setup a pt_regs so that show_trace can provide a good call trace.
*/
-SYM_CODE_START(stack_overflow)
+SYM_CODE_START(stack_invalid)
GET_LC %r15
lg %r15,__LC_NODAT_STACK(%r15) # change to panic stack
la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
stmg %r8,%r9,__PT_PSW(%r11)
mvc __PT_R8(64,%r11),0(%r14)
- stg %r10,__PT_ORIG_GPR2(%r11) # store last break to orig_gpr2
+ GET_LC %r2
+ mvc __PT_ORIG_GPR2(8,%r11),__LC_PGM_LAST_BREAK(%r2)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
- jg kernel_stack_overflow
-SYM_CODE_END(stack_overflow)
-#endif
+ jg kernel_stack_invalid
+SYM_CODE_END(stack_invalid)
.section .data, "aw"
.balign 4
@@ -653,7 +611,7 @@ SYM_DATA_END(daton_psw)
.balign 8
#define SYSCALL(esame,emu) .quad __s390x_ ## esame
SYM_DATA_START(sys_call_table)
-#include "asm/syscall_table.h"
+#include <asm/syscall_table.h>
SYM_DATA_END(sys_call_table)
#undef SYSCALL
@@ -661,7 +619,7 @@ SYM_DATA_END(sys_call_table)
#define SYSCALL(esame,emu) .quad __s390_ ## emu
SYM_DATA_START(sys_call_table_emu)
-#include "asm/syscall_table.h"
+#include <asm/syscall_table.h>
SYM_DATA_END(sys_call_table_emu)
#undef SYSCALL
#endif
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 21969520f947..dd55cc6bbc28 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -31,7 +31,7 @@ void do_secure_storage_access(struct pt_regs *regs);
void do_non_secure_storage_access(struct pt_regs *regs);
void do_secure_storage_violation(struct pt_regs *regs);
void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str);
-void kernel_stack_overflow(struct pt_regs * regs);
+void kernel_stack_invalid(struct pt_regs *regs);
void handle_signal32(struct ksignal *ksig, sigset_t *oldset,
struct pt_regs *regs);
@@ -41,7 +41,6 @@ void do_restart(void *arg);
void __init startup_init(void);
void die(struct pt_regs *regs, const char *str);
int setup_profiling_timer(unsigned int multiplier);
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip);
struct s390_mmap_arg_struct;
struct fadvise64_64_args;
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 0b6e62d1d8b8..e94bb98f5231 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -13,6 +13,7 @@
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/kmsan-checks.h>
+#include <linux/cpufeature.h>
#include <linux/kprobes.h>
#include <linux/execmem.h>
#include <trace/syscall.h>
@@ -69,7 +70,7 @@ static const char *ftrace_shared_hotpatch_trampoline(const char **end)
bool ftrace_need_init_nop(void)
{
- return !MACHINE_HAS_SEQ_INSN;
+ return !cpu_has_seq_insn();
}
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
@@ -189,7 +190,7 @@ static int ftrace_modify_trampoline_call(struct dyn_ftrace *rec,
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
- if (MACHINE_HAS_SEQ_INSN)
+ if (cpu_has_seq_insn())
return ftrace_patch_branch_insn(rec->ip, old_addr, addr);
else
return ftrace_modify_trampoline_call(rec, old_addr, addr);
@@ -213,8 +214,8 @@ static int ftrace_patch_branch_mask(void *addr, u16 expected, bool enable)
int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
unsigned long addr)
{
- /* Expect brcl 0xf,... for the !MACHINE_HAS_SEQ_INSN case */
- if (MACHINE_HAS_SEQ_INSN)
+ /* Expect brcl 0xf,... for the !cpu_has_seq_insn() case */
+ if (cpu_has_seq_insn())
return ftrace_patch_branch_insn(rec->ip, addr, 0);
else
return ftrace_patch_branch_mask((void *)rec->ip, 0xc0f4, false);
@@ -234,7 +235,7 @@ static int ftrace_make_trampoline_call(struct dyn_ftrace *rec, unsigned long add
int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
- if (MACHINE_HAS_SEQ_INSN)
+ if (cpu_has_seq_insn())
return ftrace_patch_branch_insn(rec->ip, 0, addr);
else
return ftrace_make_trampoline_call(rec, addr);
@@ -261,43 +262,19 @@ void ftrace_arch_code_modify_post_process(void)
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-/*
- * Hook the return address and push it in the stack of return addresses
- * in current thread info.
- */
-unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp,
- unsigned long ip)
-{
- if (unlikely(ftrace_graph_is_dead()))
- goto out;
- if (unlikely(atomic_read(&current->tracing_graph_pause)))
- goto out;
- ip -= MCOUNT_INSN_SIZE;
- if (!function_graph_enter(ra, ip, 0, (void *) sp))
- ra = (unsigned long) return_to_handler;
-out:
- return ra;
-}
-NOKPROBE_SYMBOL(prepare_ftrace_return);
-/*
- * Patch the kernel code at ftrace_graph_caller location. The instruction
- * there is branch relative on condition. To enable the ftrace graph code
- * block, we simply patch the mask field of the instruction to zero and
- * turn the instruction into a nop.
- * To disable the ftrace graph code the mask field will be patched to
- * all ones, which turns the instruction into an unconditional branch.
- */
-int ftrace_enable_ftrace_graph_caller(void)
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- /* Expect brc 0xf,... */
- return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa7f4, false);
-}
+ unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+ unsigned long sp = arch_ftrace_regs(fregs)->regs.gprs[15];
-int ftrace_disable_ftrace_graph_caller(void)
-{
- /* Expect brc 0x0,... */
- return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa704, true);
+ if (unlikely(ftrace_graph_is_dead()))
+ return;
+ if (unlikely(atomic_read(&current->tracing_graph_pause)))
+ return;
+ if (!function_graph_enter_regs(*parent, ip, 0, (unsigned long *)sp, fregs))
+ *parent = (unsigned long)&return_to_handler;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -318,7 +295,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
if (bit < 0)
return;
- kmsan_unpoison_memory(fregs, sizeof(*fregs));
+ kmsan_unpoison_memory(fregs, ftrace_regs_size());
regs = ftrace_get_regs(fregs);
p = get_kprobe((kprobe_opcode_t *)ip);
if (!regs || unlikely(!p) || kprobe_disabled(p))
diff --git a/arch/s390/kernel/guarded_storage.c b/arch/s390/kernel/guarded_storage.c
index 0b68168d9566..cf26d7a37425 100644
--- a/arch/s390/kernel/guarded_storage.c
+++ b/arch/s390/kernel/guarded_storage.c
@@ -4,6 +4,7 @@
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
*/
+#include <linux/cpufeature.h>
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
@@ -109,7 +110,7 @@ static int gs_broadcast(void)
SYSCALL_DEFINE2(s390_guarded_storage, int, command,
struct gs_cb __user *, gs_cb)
{
- if (!MACHINE_HAS_GS)
+ if (!cpu_has_gs())
return -EOPNOTSUPP;
switch (command) {
case GS_ENABLE:
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 396034b2fe67..7edb9ded199c 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -18,12 +18,10 @@
__HEAD
SYM_CODE_START(startup_continue)
- larl %r1,tod_clock_base
- GET_LC %r2
- mvc 0(16,%r1),__LC_BOOT_CLOCK(%r2)
#
# Setup stack
#
+ GET_LC %r2
larl %r14,init_task
stg %r14,__LC_CURRENT(%r2)
larl %r15,init_thread_union+STACK_INIT_OFFSET
diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c
index 2a99a216ab62..e7b66d046e8d 100644
--- a/arch/s390/kernel/hiperdispatch.c
+++ b/arch/s390/kernel/hiperdispatch.c
@@ -45,6 +45,7 @@
* therefore delaying the throughput loss caused by using SMP threads.
*/
+#include <linux/cpufeature.h>
#include <linux/cpumask.h>
#include <linux/debugfs.h>
#include <linux/device.h>
@@ -87,7 +88,7 @@ static DECLARE_DELAYED_WORK(hd_capacity_work, hd_capacity_work_fn);
static int hd_set_hiperdispatch_mode(int enable)
{
- if (!MACHINE_HAS_TOPOLOGY)
+ if (!cpu_has_topology())
enable = 0;
if (hd_enabled == enable)
return 0;
@@ -292,7 +293,7 @@ static int hiperdispatch_ctl_handler(const struct ctl_table *ctl, int write,
return 0;
}
-static struct ctl_table hiperdispatch_ctl_table[] = {
+static const struct ctl_table hiperdispatch_ctl_table[] = {
{
.procname = "hiperdispatch",
.mode = 0644,
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index f17bb7bf9392..ff15f91affde 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -22,6 +22,7 @@
#include <linux/debug_locks.h>
#include <linux/vmalloc.h>
#include <asm/asm-extable.h>
+#include <asm/machine.h>
#include <asm/diag.h>
#include <asm/ipl.h>
#include <asm/smp.h>
@@ -185,7 +186,7 @@ static inline int __diag308(unsigned long subcode, unsigned long addr)
r1.even = addr;
r1.odd = 0;
- asm volatile(
+ asm_inline volatile(
" diag %[r1],%[subcode],0x308\n"
"0: nopr %%r7\n"
EX_TABLE(0b,0b)
@@ -209,7 +210,7 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \
struct kobj_attribute *attr, \
char *page) \
{ \
- return scnprintf(page, PAGE_SIZE, _format, ##args); \
+ return sysfs_emit(page, _format, ##args); \
}
#define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk) \
@@ -269,8 +270,8 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \
{ \
if (len >= sizeof(_value)) \
return -E2BIG; \
- len = strscpy(_value, buf, sizeof(_value)); \
- if (len < 0) \
+ len = strscpy(_value, buf); \
+ if ((ssize_t)len < 0) \
return len; \
strim(_value); \
return len; \
@@ -280,58 +281,58 @@ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \
sys_##_prefix##_##_name##_show, \
sys_##_prefix##_##_name##_store)
-#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
-static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \
- struct kobject *kobj, \
- struct bin_attribute *attr, \
- char *buf, loff_t off, \
- size_t count) \
-{ \
- size_t size = _ipl_block.scp_data_len; \
- void *scp_data = _ipl_block.scp_data; \
- \
- return memory_read_from_buffer(buf, count, &off, \
- scp_data, size); \
+#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
+static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \
+ struct kobject *kobj, \
+ const struct bin_attribute *attr, \
+ char *buf, loff_t off, \
+ size_t count) \
+{ \
+ size_t size = _ipl_block.scp_data_len; \
+ void *scp_data = _ipl_block.scp_data; \
+ \
+ return memory_read_from_buffer(buf, count, &off, \
+ scp_data, size); \
}
#define IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\
-static ssize_t sys_##_prefix##_scp_data_store(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(_ipl_block.scp_data, buf, count); \
- if (scpdata_len % 8) { \
- padding = 8 - (scpdata_len % 8); \
- memset(_ipl_block.scp_data + scpdata_len, \
- 0, padding); \
- scpdata_len += padding; \
- } \
- \
- _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \
- _ipl_block.len = _ipl_bp0_len + scpdata_len; \
- _ipl_block.scp_data_len = scpdata_len; \
- \
- return count; \
+static ssize_t sys_##_prefix##_scp_data_store(struct file *filp, \
+ struct kobject *kobj, \
+ const 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(_ipl_block.scp_data, buf, count); \
+ if (scpdata_len % 8) { \
+ padding = 8 - (scpdata_len % 8); \
+ memset(_ipl_block.scp_data + scpdata_len, \
+ 0, padding); \
+ scpdata_len += padding; \
+ } \
+ \
+ _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \
+ _ipl_block.len = _ipl_bp0_len + scpdata_len; \
+ _ipl_block.scp_data_len = scpdata_len; \
+ \
+ return count; \
}
#define DEFINE_IPL_ATTR_SCP_DATA_RO(_prefix, _ipl_block, _size) \
IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
-static struct bin_attribute sys_##_prefix##_scp_data_attr = \
+static const struct bin_attribute sys_##_prefix##_scp_data_attr = \
__BIN_ATTR(scp_data, 0444, sys_##_prefix##_scp_data_show, \
NULL, _size)
#define DEFINE_IPL_ATTR_SCP_DATA_RW(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len, _size)\
IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \
IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\
-static struct bin_attribute sys_##_prefix##_scp_data_attr = \
+static const struct bin_attribute sys_##_prefix##_scp_data_attr = \
__BIN_ATTR(scp_data, 0644, sys_##_prefix##_scp_data_show, \
sys_##_prefix##_scp_data_store, _size)
@@ -372,7 +373,7 @@ EXPORT_SYMBOL_GPL(ipl_info);
static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr,
char *page)
{
- return sprintf(page, "%s\n", ipl_type_str(ipl_info.type));
+ return sysfs_emit(page, "%s\n", ipl_type_str(ipl_info.type));
}
static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type);
@@ -380,7 +381,7 @@ static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type);
static ssize_t ipl_secure_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%i\n", !!ipl_secure_flag);
+ return sysfs_emit(page, "%i\n", !!ipl_secure_flag);
}
static struct kobj_attribute sys_ipl_secure_attr =
@@ -389,7 +390,7 @@ static struct kobj_attribute sys_ipl_secure_attr =
static ssize_t ipl_has_secure_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%i\n", !!sclp.has_sipl);
+ return sysfs_emit(page, "%i\n", !!sclp.has_sipl);
}
static struct kobj_attribute sys_ipl_has_secure_attr =
@@ -402,7 +403,7 @@ static ssize_t ipl_vm_parm_show(struct kobject *kobj,
if (ipl_block_valid && (ipl_block.pb0_hdr.pbt == IPL_PBT_CCW))
ipl_block_get_ascii_vmparm(parm, sizeof(parm), &ipl_block);
- return sprintf(page, "%s\n", parm);
+ return sysfs_emit(page, "%s\n", parm);
}
static struct kobj_attribute sys_ipl_vm_parm_attr =
@@ -413,18 +414,18 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
{
switch (ipl_info.type) {
case IPL_TYPE_CCW:
- return sprintf(page, "0.%x.%04x\n", ipl_block.ccw.ssid,
- ipl_block.ccw.devno);
+ return sysfs_emit(page, "0.%x.%04x\n", ipl_block.ccw.ssid,
+ ipl_block.ccw.devno);
case IPL_TYPE_ECKD:
case IPL_TYPE_ECKD_DUMP:
- return sprintf(page, "0.%x.%04x\n", ipl_block.eckd.ssid,
- ipl_block.eckd.devno);
+ return sysfs_emit(page, "0.%x.%04x\n", ipl_block.eckd.ssid,
+ ipl_block.eckd.devno);
case IPL_TYPE_FCP:
case IPL_TYPE_FCP_DUMP:
- return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno);
+ return sysfs_emit(page, "0.0.%04x\n", ipl_block.fcp.devno);
case IPL_TYPE_NVME:
case IPL_TYPE_NVME_DUMP:
- return sprintf(page, "%08ux\n", ipl_block.nvme.fid);
+ return sysfs_emit(page, "%08ux\n", ipl_block.nvme.fid);
default:
return 0;
}
@@ -434,19 +435,19 @@ static struct kobj_attribute sys_ipl_device_attr =
__ATTR(device, 0444, sys_ipl_device_show, NULL);
static ssize_t sys_ipl_parameter_read(struct file *filp, struct kobject *kobj,
- struct bin_attribute *attr, char *buf,
+ const struct bin_attribute *attr, char *buf,
loff_t off, size_t count)
{
return memory_read_from_buffer(buf, count, &off, &ipl_block,
ipl_block.hdr.len);
}
-static struct bin_attribute sys_ipl_parameter_attr =
+static const struct bin_attribute sys_ipl_parameter_attr =
__BIN_ATTR(binary_parameter, 0444, sys_ipl_parameter_read, NULL,
PAGE_SIZE);
DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_fcp, ipl_block.fcp, PAGE_SIZE);
-static struct bin_attribute *ipl_fcp_bin_attrs[] = {
+static const struct bin_attribute *const ipl_fcp_bin_attrs[] = {
&sys_ipl_parameter_attr,
&sys_ipl_fcp_scp_data_attr,
NULL,
@@ -454,7 +455,7 @@ static struct bin_attribute *ipl_fcp_bin_attrs[] = {
DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_nvme, ipl_block.nvme, PAGE_SIZE);
-static struct bin_attribute *ipl_nvme_bin_attrs[] = {
+static const struct bin_attribute *const ipl_nvme_bin_attrs[] = {
&sys_ipl_parameter_attr,
&sys_ipl_nvme_scp_data_attr,
NULL,
@@ -462,7 +463,7 @@ static struct bin_attribute *ipl_nvme_bin_attrs[] = {
DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_eckd, ipl_block.eckd, PAGE_SIZE);
-static struct bin_attribute *ipl_eckd_bin_attrs[] = {
+static const struct bin_attribute *const ipl_eckd_bin_attrs[] = {
&sys_ipl_parameter_attr,
&sys_ipl_eckd_scp_data_attr,
NULL,
@@ -503,12 +504,12 @@ static ssize_t eckd_##_name##_br_chr_show(struct kobject *kobj, \
if (!ipb->br_chr.cyl && \
!ipb->br_chr.head && \
!ipb->br_chr.record) \
- return sprintf(buf, "auto\n"); \
+ return sysfs_emit(buf, "auto\n"); \
\
- return sprintf(buf, "0x%x,0x%x,0x%x\n", \
- ipb->br_chr.cyl, \
- ipb->br_chr.head, \
- ipb->br_chr.record); \
+ return sysfs_emit(buf, "0x%x,0x%x,0x%x\n", \
+ ipb->br_chr.cyl, \
+ ipb->br_chr.head, \
+ ipb->br_chr.record); \
}
#define IPL_ATTR_BR_CHR_STORE_FN(_name, _ipb) \
@@ -573,11 +574,11 @@ static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj,
char loadparm[LOADPARM_LEN + 1] = {};
if (!sclp_ipl_info.is_valid)
- return sprintf(page, "#unknown#\n");
+ return sysfs_emit(page, "#unknown#\n");
memcpy(loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
EBCASC(loadparm, LOADPARM_LEN);
strim(loadparm);
- return sprintf(page, "%s\n", loadparm);
+ return sysfs_emit(page, "%s\n", loadparm);
}
static struct kobj_attribute sys_ipl_ccw_loadparm_attr =
@@ -593,9 +594,9 @@ static struct attribute *ipl_fcp_attrs[] = {
NULL,
};
-static struct attribute_group ipl_fcp_attr_group = {
+static const struct attribute_group ipl_fcp_attr_group = {
.attrs = ipl_fcp_attrs,
- .bin_attrs = ipl_fcp_bin_attrs,
+ .bin_attrs_new = ipl_fcp_bin_attrs,
};
static struct attribute *ipl_nvme_attrs[] = {
@@ -607,9 +608,9 @@ static struct attribute *ipl_nvme_attrs[] = {
NULL,
};
-static struct attribute_group ipl_nvme_attr_group = {
+static const struct attribute_group ipl_nvme_attr_group = {
.attrs = ipl_nvme_attrs,
- .bin_attrs = ipl_nvme_bin_attrs,
+ .bin_attrs_new = ipl_nvme_bin_attrs,
};
static struct attribute *ipl_eckd_attrs[] = {
@@ -620,9 +621,9 @@ static struct attribute *ipl_eckd_attrs[] = {
NULL,
};
-static struct attribute_group ipl_eckd_attr_group = {
+static const struct attribute_group ipl_eckd_attr_group = {
.attrs = ipl_eckd_attrs,
- .bin_attrs = ipl_eckd_bin_attrs,
+ .bin_attrs_new = ipl_eckd_bin_attrs,
};
/* CCW ipl device attributes */
@@ -640,11 +641,11 @@ static struct attribute *ipl_ccw_attrs_lpar[] = {
NULL,
};
-static struct attribute_group ipl_ccw_attr_group_vm = {
+static const struct attribute_group ipl_ccw_attr_group_vm = {
.attrs = ipl_ccw_attrs_vm,
};
-static struct attribute_group ipl_ccw_attr_group_lpar = {
+static const struct attribute_group ipl_ccw_attr_group_lpar = {
.attrs = ipl_ccw_attrs_lpar
};
@@ -655,7 +656,7 @@ static struct attribute *ipl_common_attrs[] = {
NULL,
};
-static struct attribute_group ipl_common_attr_group = {
+static const struct attribute_group ipl_common_attr_group = {
.attrs = ipl_common_attrs,
};
@@ -685,7 +686,7 @@ static int __init ipl_init(void)
goto out;
switch (ipl_info.type) {
case IPL_TYPE_CCW:
- if (MACHINE_IS_VM)
+ if (machine_is_vm())
rc = sysfs_create_group(&ipl_kset->kobj,
&ipl_ccw_attr_group_vm);
else
@@ -731,7 +732,7 @@ static ssize_t reipl_generic_vmparm_show(struct ipl_parameter_block *ipb,
char vmparm[DIAG308_VMPARM_SIZE + 1] = {};
ipl_block_get_ascii_vmparm(vmparm, sizeof(vmparm), ipb);
- return sprintf(page, "%s\n", vmparm);
+ return sysfs_emit(page, "%s\n", vmparm);
}
static ssize_t reipl_generic_vmparm_store(struct ipl_parameter_block *ipb,
@@ -808,7 +809,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_fcp, reipl_block_fcp->hdr,
IPL_BP_FCP_LEN, IPL_BP0_FCP_LEN,
DIAG308_SCPDATA_SIZE);
-static struct bin_attribute *reipl_fcp_bin_attrs[] = {
+static const struct bin_attribute *const reipl_fcp_bin_attrs[] = {
&sys_reipl_fcp_scp_data_attr,
NULL,
};
@@ -839,7 +840,7 @@ static ssize_t reipl_generic_loadparm_show(struct ipl_parameter_block *ipb,
char buf[LOADPARM_LEN + 1];
reipl_get_ascii_loadparm(buf, ipb);
- return sprintf(page, "%s\n", buf);
+ return sysfs_emit(page, "%s\n", buf);
}
static ssize_t reipl_generic_loadparm_store(struct ipl_parameter_block *ipb,
@@ -895,7 +896,7 @@ DEFINE_GENERIC_LOADPARM(eckd);
static ssize_t reipl_fcp_clear_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%u\n", reipl_fcp_clear);
+ return sysfs_emit(page, "%u\n", reipl_fcp_clear);
}
static ssize_t reipl_fcp_clear_store(struct kobject *kobj,
@@ -917,9 +918,9 @@ static struct attribute *reipl_fcp_attrs[] = {
NULL,
};
-static struct attribute_group reipl_fcp_attr_group = {
+static const struct attribute_group reipl_fcp_attr_group = {
.attrs = reipl_fcp_attrs,
- .bin_attrs = reipl_fcp_bin_attrs,
+ .bin_attrs_new = reipl_fcp_bin_attrs,
};
static struct kobj_attribute sys_reipl_fcp_clear_attr =
@@ -932,7 +933,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_nvme, reipl_block_nvme->hdr,
IPL_BP_NVME_LEN, IPL_BP0_NVME_LEN,
DIAG308_SCPDATA_SIZE);
-static struct bin_attribute *reipl_nvme_bin_attrs[] = {
+static const struct bin_attribute *const reipl_nvme_bin_attrs[] = {
&sys_reipl_nvme_scp_data_attr,
NULL,
};
@@ -955,15 +956,15 @@ static struct attribute *reipl_nvme_attrs[] = {
NULL,
};
-static struct attribute_group reipl_nvme_attr_group = {
+static const struct attribute_group reipl_nvme_attr_group = {
.attrs = reipl_nvme_attrs,
- .bin_attrs = reipl_nvme_bin_attrs
+ .bin_attrs_new = reipl_nvme_bin_attrs
};
static ssize_t reipl_nvme_clear_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%u\n", reipl_nvme_clear);
+ return sysfs_emit(page, "%u\n", reipl_nvme_clear);
}
static ssize_t reipl_nvme_clear_store(struct kobject *kobj,
@@ -984,7 +985,7 @@ DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw);
static ssize_t reipl_ccw_clear_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%u\n", reipl_ccw_clear);
+ return sysfs_emit(page, "%u\n", reipl_ccw_clear);
}
static ssize_t reipl_ccw_clear_store(struct kobject *kobj,
@@ -1031,7 +1032,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_eckd, reipl_block_eckd->hdr,
IPL_BP_ECKD_LEN, IPL_BP0_ECKD_LEN,
DIAG308_SCPDATA_SIZE);
-static struct bin_attribute *reipl_eckd_bin_attrs[] = {
+static const struct bin_attribute *const reipl_eckd_bin_attrs[] = {
&sys_reipl_eckd_scp_data_attr,
NULL,
};
@@ -1048,15 +1049,15 @@ static struct attribute *reipl_eckd_attrs[] = {
NULL,
};
-static struct attribute_group reipl_eckd_attr_group = {
+static const struct attribute_group reipl_eckd_attr_group = {
.attrs = reipl_eckd_attrs,
- .bin_attrs = reipl_eckd_bin_attrs
+ .bin_attrs_new = reipl_eckd_bin_attrs
};
static ssize_t reipl_eckd_clear_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%u\n", reipl_eckd_clear);
+ return sysfs_emit(page, "%u\n", reipl_eckd_clear);
}
static ssize_t reipl_eckd_clear_store(struct kobject *kobj,
@@ -1086,7 +1087,7 @@ static ssize_t reipl_nss_name_show(struct kobject *kobj,
char nss_name[NSS_NAME_SIZE + 1] = {};
reipl_get_ascii_nss_name(nss_name, reipl_block_nss);
- return sprintf(page, "%s\n", nss_name);
+ return sysfs_emit(page, "%s\n", nss_name);
}
static ssize_t reipl_nss_name_store(struct kobject *kobj,
@@ -1171,7 +1172,7 @@ static int reipl_set_type(enum ipl_type type)
static ssize_t reipl_type_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", ipl_type_str(reipl_type));
+ return sysfs_emit(page, "%s\n", ipl_type_str(reipl_type));
}
static ssize_t reipl_type_store(struct kobject *kobj,
@@ -1272,7 +1273,7 @@ static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
ipb->ccw.flags = IPL_PB0_FLAG_LOADPARM;
/* VM PARM */
- if (MACHINE_IS_VM && ipl_block_valid &&
+ if (machine_is_vm() && ipl_block_valid &&
(ipl_block.ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP)) {
ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
@@ -1286,7 +1287,7 @@ static int __init reipl_nss_init(void)
{
int rc;
- if (!MACHINE_IS_VM)
+ if (!machine_is_vm())
return 0;
reipl_block_nss = (void *) get_zeroed_page(GFP_KERNEL);
@@ -1311,8 +1312,8 @@ static int __init reipl_ccw_init(void)
return -ENOMEM;
rc = sysfs_create_group(&reipl_kset->kobj,
- MACHINE_IS_VM ? &reipl_ccw_attr_group_vm
- : &reipl_ccw_attr_group_lpar);
+ machine_is_vm() ? &reipl_ccw_attr_group_vm
+ : &reipl_ccw_attr_group_lpar);
if (rc)
return rc;
@@ -1587,15 +1588,15 @@ static struct attribute *dump_fcp_attrs[] = {
NULL,
};
-static struct bin_attribute *dump_fcp_bin_attrs[] = {
+static const struct bin_attribute *const dump_fcp_bin_attrs[] = {
&sys_dump_fcp_scp_data_attr,
NULL,
};
-static struct attribute_group dump_fcp_attr_group = {
+static const struct attribute_group dump_fcp_attr_group = {
.name = IPL_FCP_STR,
.attrs = dump_fcp_attrs,
- .bin_attrs = dump_fcp_bin_attrs,
+ .bin_attrs_new = dump_fcp_bin_attrs,
};
/* NVME dump device attributes */
@@ -1621,15 +1622,15 @@ static struct attribute *dump_nvme_attrs[] = {
NULL,
};
-static struct bin_attribute *dump_nvme_bin_attrs[] = {
+static const struct bin_attribute *const dump_nvme_bin_attrs[] = {
&sys_dump_nvme_scp_data_attr,
NULL,
};
-static struct attribute_group dump_nvme_attr_group = {
+static const struct attribute_group dump_nvme_attr_group = {
.name = IPL_NVME_STR,
.attrs = dump_nvme_attrs,
- .bin_attrs = dump_nvme_bin_attrs,
+ .bin_attrs_new = dump_nvme_bin_attrs,
};
/* ECKD dump device attributes */
@@ -1655,15 +1656,15 @@ static struct attribute *dump_eckd_attrs[] = {
NULL,
};
-static struct bin_attribute *dump_eckd_bin_attrs[] = {
+static const struct bin_attribute *const dump_eckd_bin_attrs[] = {
&sys_dump_eckd_scp_data_attr,
NULL,
};
-static struct attribute_group dump_eckd_attr_group = {
+static const struct attribute_group dump_eckd_attr_group = {
.name = IPL_ECKD_STR,
.attrs = dump_eckd_attrs,
- .bin_attrs = dump_eckd_bin_attrs,
+ .bin_attrs_new = dump_eckd_bin_attrs,
};
/* CCW dump device attributes */
@@ -1692,7 +1693,7 @@ static int dump_set_type(enum dump_type type)
static ssize_t dump_type_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", dump_type_str(dump_type));
+ return sysfs_emit(page, "%s\n", dump_type_str(dump_type));
}
static ssize_t dump_type_store(struct kobject *kobj,
@@ -1717,6 +1718,24 @@ static ssize_t dump_type_store(struct kobject *kobj,
static struct kobj_attribute dump_type_attr =
__ATTR(dump_type, 0644, dump_type_show, dump_type_store);
+static ssize_t dump_area_size_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *page)
+{
+ return sysfs_emit(page, "%lu\n", sclp.hsa_size);
+}
+
+static struct kobj_attribute dump_area_size_attr = __ATTR_RO(dump_area_size);
+
+static struct attribute *dump_attrs[] = {
+ &dump_type_attr.attr,
+ &dump_area_size_attr.attr,
+ NULL,
+};
+
+static struct attribute_group dump_attr_group = {
+ .attrs = dump_attrs,
+};
+
static struct kset *dump_kset;
static void diag308_dump(void *dump_block)
@@ -1853,7 +1872,7 @@ static int __init dump_init(void)
dump_kset = kset_create_and_add("dump", NULL, firmware_kobj);
if (!dump_kset)
return -ENOMEM;
- rc = sysfs_create_file(&dump_kset->kobj, &dump_type_attr.attr);
+ rc = sysfs_create_group(&dump_kset->kobj, &dump_attr_group);
if (rc) {
kset_unregister(dump_kset);
return rc;
@@ -1969,7 +1988,7 @@ static void vmcmd_run(struct shutdown_trigger *trigger)
static int vmcmd_init(void)
{
- if (!MACHINE_IS_VM)
+ if (!machine_is_vm())
return -EOPNOTSUPP;
vmcmd_kset = kset_create_and_add("vmcmd", NULL, firmware_kobj);
if (!vmcmd_kset)
@@ -2034,7 +2053,7 @@ static struct shutdown_trigger on_reboot_trigger = {ON_REIPL_STR,
static ssize_t on_reboot_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", on_reboot_trigger.action->name);
+ return sysfs_emit(page, "%s\n", on_reboot_trigger.action->name);
}
static ssize_t on_reboot_store(struct kobject *kobj,
@@ -2060,7 +2079,7 @@ static struct shutdown_trigger on_panic_trigger = {ON_PANIC_STR, &stop_action};
static ssize_t on_panic_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", on_panic_trigger.action->name);
+ return sysfs_emit(page, "%s\n", on_panic_trigger.action->name);
}
static ssize_t on_panic_store(struct kobject *kobj,
@@ -2086,7 +2105,7 @@ static struct shutdown_trigger on_restart_trigger = {ON_RESTART_STR,
static ssize_t on_restart_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", on_restart_trigger.action->name);
+ return sysfs_emit(page, "%s\n", on_restart_trigger.action->name);
}
static ssize_t on_restart_store(struct kobject *kobj,
@@ -2122,7 +2141,7 @@ static struct shutdown_trigger on_halt_trigger = {ON_HALT_STR, &stop_action};
static ssize_t on_halt_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", on_halt_trigger.action->name);
+ return sysfs_emit(page, "%s\n", on_halt_trigger.action->name);
}
static ssize_t on_halt_store(struct kobject *kobj,
@@ -2148,7 +2167,7 @@ static struct shutdown_trigger on_poff_trigger = {ON_POFF_STR, &stop_action};
static ssize_t on_poff_show(struct kobject *kobj,
struct kobj_attribute *attr, char *page)
{
- return sprintf(page, "%s\n", on_poff_trigger.action->name);
+ return sysfs_emit(page, "%s\n", on_poff_trigger.action->name);
}
static ssize_t on_poff_store(struct kobject *kobj,
@@ -2230,26 +2249,28 @@ static int __init s390_ipl_init(void)
__initcall(s390_ipl_init);
-static void __init strncpy_skip_quote(char *dst, char *src, int n)
+static void __init strscpy_skip_quote(char *dst, char *src, int n)
{
int sx, dx;
- dx = 0;
- for (sx = 0; src[sx] != 0; sx++) {
+ if (!n)
+ return;
+ for (sx = 0, dx = 0; src[sx]; sx++) {
if (src[sx] == '"')
continue;
- dst[dx++] = src[sx];
- if (dx >= n)
+ dst[dx] = src[sx];
+ if (dx + 1 == n)
break;
+ dx++;
}
+ dst[dx] = '\0';
}
static int __init vmcmd_on_reboot_setup(char *str)
{
- if (!MACHINE_IS_VM)
+ if (!machine_is_vm())
return 1;
- strncpy_skip_quote(vmcmd_on_reboot, str, VMCMD_MAX_SIZE);
- vmcmd_on_reboot[VMCMD_MAX_SIZE] = 0;
+ strscpy_skip_quote(vmcmd_on_reboot, str, sizeof(vmcmd_on_reboot));
on_reboot_trigger.action = &vmcmd_action;
return 1;
}
@@ -2257,10 +2278,9 @@ __setup("vmreboot=", vmcmd_on_reboot_setup);
static int __init vmcmd_on_panic_setup(char *str)
{
- if (!MACHINE_IS_VM)
+ if (!machine_is_vm())
return 1;
- strncpy_skip_quote(vmcmd_on_panic, str, VMCMD_MAX_SIZE);
- vmcmd_on_panic[VMCMD_MAX_SIZE] = 0;
+ strscpy_skip_quote(vmcmd_on_panic, str, sizeof(vmcmd_on_panic));
on_panic_trigger.action = &vmcmd_action;
return 1;
}
@@ -2268,10 +2288,9 @@ __setup("vmpanic=", vmcmd_on_panic_setup);
static int __init vmcmd_on_halt_setup(char *str)
{
- if (!MACHINE_IS_VM)
+ if (!machine_is_vm())
return 1;
- strncpy_skip_quote(vmcmd_on_halt, str, VMCMD_MAX_SIZE);
- vmcmd_on_halt[VMCMD_MAX_SIZE] = 0;
+ strscpy_skip_quote(vmcmd_on_halt, str, sizeof(vmcmd_on_halt));
on_halt_trigger.action = &vmcmd_action;
return 1;
}
@@ -2279,10 +2298,9 @@ __setup("vmhalt=", vmcmd_on_halt_setup);
static int __init vmcmd_on_poff_setup(char *str)
{
- if (!MACHINE_IS_VM)
+ if (!machine_is_vm())
return 1;
- strncpy_skip_quote(vmcmd_on_poff, str, VMCMD_MAX_SIZE);
- vmcmd_on_poff[VMCMD_MAX_SIZE] = 0;
+ strscpy_skip_quote(vmcmd_on_poff, str, sizeof(vmcmd_on_poff));
on_poff_trigger.action = &vmcmd_action;
return 1;
}
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 2639a3d12736..bdf9c7cb5685 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -9,6 +9,7 @@
*/
#include <linux/kernel_stat.h>
+#include <linux/cpufeature.h>
#include <linux/interrupt.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
@@ -25,11 +26,13 @@
#include <asm/irq_regs.h>
#include <asm/cputime.h>
#include <asm/lowcore.h>
+#include <asm/machine.h>
#include <asm/irq.h>
#include <asm/hw_irq.h>
#include <asm/stacktrace.h>
#include <asm/softirq_stack.h>
#include <asm/vtime.h>
+#include <asm/asm.h>
#include "entry.h"
DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -83,7 +86,6 @@ static const struct irq_class irqclass_sub_desc[] = {
{.irq = IRQIO_C70, .name = "C70", .desc = "[I/O] 3270"},
{.irq = IRQIO_TAP, .name = "TAP", .desc = "[I/O] Tape"},
{.irq = IRQIO_VMR, .name = "VMR", .desc = "[I/O] Unit Record Devices"},
- {.irq = IRQIO_LCS, .name = "LCS", .desc = "[I/O] LCS"},
{.irq = IRQIO_CTC, .name = "CTC", .desc = "[I/O] CTC"},
{.irq = IRQIO_ADM, .name = "ADM", .desc = "[I/O] EADM Subchannel"},
{.irq = IRQIO_CSC, .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
@@ -129,9 +131,13 @@ static int irq_pending(struct pt_regs *regs)
{
int cc;
- asm volatile("tpi 0\n"
- "ipm %0" : "=d" (cc) : : "cc");
- return cc >> 28;
+ asm volatile(
+ " tpi 0\n"
+ CC_IPM(cc)
+ : CC_OUT(cc, cc)
+ :
+ : CC_CLOBBER);
+ return CC_TRANSFORM(cc);
}
void noinstr do_io_irq(struct pt_regs *regs)
@@ -144,7 +150,7 @@ void noinstr do_io_irq(struct pt_regs *regs)
if (user_mode(regs)) {
update_timer_sys();
- if (static_branch_likely(&cpu_has_bear))
+ if (cpu_has_bear())
current->thread.last_break = regs->last_break;
}
@@ -159,7 +165,7 @@ void noinstr do_io_irq(struct pt_regs *regs)
do_irq_async(regs, THIN_INTERRUPT);
else
do_irq_async(regs, IO_INTERRUPT);
- } while (MACHINE_IS_LPAR && irq_pending(regs));
+ } while (machine_is_lpar() && irq_pending(regs));
irq_exit_rcu();
@@ -180,7 +186,7 @@ void noinstr do_ext_irq(struct pt_regs *regs)
if (user_mode(regs)) {
update_timer_sys();
- if (static_branch_likely(&cpu_has_bear))
+ if (cpu_has_bear())
current->thread.last_break = regs->last_break;
}
@@ -253,7 +259,7 @@ int show_interrupts(struct seq_file *p, void *v)
seq_putc(p, '\n');
goto out;
}
- if (index < nr_irqs) {
+ if (index < irq_get_nr_irqs()) {
show_msi_interrupt(p, index);
goto out;
}
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 6295faf0987d..c450120b4474 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -13,6 +13,7 @@
#include <linux/ptrace.h>
#include <linux/preempt.h>
#include <linux/stop_machine.h>
+#include <linux/cpufeature.h>
#include <linux/kdebug.h>
#include <linux/uaccess.h>
#include <linux/extable.h>
@@ -153,7 +154,7 @@ void arch_arm_kprobe(struct kprobe *p)
{
struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
- if (MACHINE_HAS_SEQ_INSN) {
+ if (cpu_has_seq_insn()) {
swap_instruction(&args);
text_poke_sync();
} else {
@@ -166,7 +167,7 @@ void arch_disarm_kprobe(struct kprobe *p)
{
struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
- if (MACHINE_HAS_SEQ_INSN) {
+ if (cpu_has_seq_insn()) {
swap_instruction(&args);
text_poke_sync();
} else {
@@ -489,6 +490,12 @@ int __init arch_init_kprobes(void)
return 0;
}
+int __init arch_populate_kprobe_blacklist(void)
+{
+ return kprobe_add_area_blacklist((unsigned long)__irqentry_text_start,
+ (unsigned long)__irqentry_text_end);
+}
+
int arch_trampoline_kprobe(struct kprobe *p)
{
return 0;
diff --git a/arch/s390/kernel/lgr.c b/arch/s390/kernel/lgr.c
index 6652e54cf3db..6d1ffca5f798 100644
--- a/arch/s390/kernel/lgr.c
+++ b/arch/s390/kernel/lgr.c
@@ -166,7 +166,7 @@ static struct timer_list lgr_timer;
*/
static void lgr_timer_set(void)
{
- mod_timer(&lgr_timer, jiffies + msecs_to_jiffies(LGR_TIMER_INTERVAL_SECS * MSEC_PER_SEC));
+ mod_timer(&lgr_timer, jiffies + secs_to_jiffies(LGR_TIMER_INTERVAL_SECS));
}
/*
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index 8f681ccfb83a..baeb3dcfc1c8 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -13,7 +13,9 @@
#include <linux/reboot.h>
#include <linux/ftrace.h>
#include <linux/debug_locks.h>
+#include <linux/cpufeature.h>
#include <asm/guarded_storage.h>
+#include <asm/machine.h>
#include <asm/pfault.h>
#include <asm/cio.h>
#include <asm/fpu.h>
@@ -94,7 +96,7 @@ static noinline void __machine_kdump(void *image)
mcesa = __va(get_lowcore()->mcesad & MCESA_ORIGIN_MASK);
if (cpu_has_vx())
save_vx_regs((__vector128 *) mcesa->vector_save_area);
- if (MACHINE_HAS_GS) {
+ if (cpu_has_gs()) {
local_ctl_store(2, &cr2_old.reg);
cr2_new = cr2_old;
cr2_new.gse = 1;
@@ -178,7 +180,7 @@ void arch_kexec_unprotect_crashkres(void)
static int machine_kexec_prepare_kdump(void)
{
#ifdef CONFIG_CRASH_DUMP
- if (MACHINE_IS_VM)
+ if (machine_is_vm())
diag10_range(PFN_DOWN(crashk_res.start),
PFN_DOWN(crashk_res.end - crashk_res.start + 1));
return 0;
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 7e267ef63a7f..1fec370fecf4 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -104,17 +104,6 @@ SYM_CODE_START(ftrace_common)
lgr %r3,%r14
la %r5,STACK_FREGS(%r15)
BASR_EX %r14,%r1
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-# The j instruction gets runtime patched to a nop instruction.
-# See ftrace_enable_ftrace_graph_caller.
-SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL)
- j .Lftrace_graph_caller_end
- lmg %r2,%r3,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15)
- lg %r4,(STACK_FREGS_PTREGS_PSW+8)(%r15)
- brasl %r14,prepare_ftrace_return
- stg %r2,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15)
-.Lftrace_graph_caller_end:
-#endif
lg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15)
#ifdef MARCH_HAS_Z196_FEATURES
ltg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15)
@@ -134,14 +123,14 @@ SYM_CODE_END(ftrace_common)
SYM_FUNC_START(return_to_handler)
stmg %r2,%r5,32(%r15)
lgr %r1,%r15
- aghi %r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE)
+ # allocate ftrace_regs and stack frame for ftrace_return_to_handler
+ aghi %r15,-STACK_FRAME_SIZE_FREGS
stg %r1,__SF_BACKCHAIN(%r15)
- la %r3,STACK_FRAME_OVERHEAD(%r15)
- stg %r1,__FGRAPH_RET_FP(%r3)
- stg %r2,__FGRAPH_RET_GPR2(%r3)
- lgr %r2,%r3
+ stg %r2,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15)
+ stg %r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15)
+ la %r2,STACK_FRAME_OVERHEAD(%r15)
brasl %r14,ftrace_return_to_handler
- aghi %r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE
+ aghi %r15,STACK_FRAME_SIZE_FREGS
lgr %r14,%r2
lmg %r2,%r5,32(%r15)
BR_EX %r14
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index fbd218b6fc8e..3da371c144eb 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -9,6 +9,7 @@
*/
#include <linux/kernel_stat.h>
+#include <linux/cpufeature.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/entry-common.h>
@@ -45,7 +46,7 @@ static DEFINE_PER_CPU(struct mcck_struct, cpu_mcck);
static inline int nmi_needs_mcesa(void)
{
- return cpu_has_vx() || MACHINE_HAS_GS;
+ return cpu_has_vx() || cpu_has_gs();
}
/*
@@ -61,7 +62,7 @@ void __init nmi_alloc_mcesa_early(u64 *mcesad)
if (!nmi_needs_mcesa())
return;
*mcesad = __pa(&boot_mcesa);
- if (MACHINE_HAS_GS)
+ if (cpu_has_gs())
*mcesad |= ilog2(MCESA_MAX_SIZE);
}
@@ -73,14 +74,14 @@ int nmi_alloc_mcesa(u64 *mcesad)
*mcesad = 0;
if (!nmi_needs_mcesa())
return 0;
- size = MACHINE_HAS_GS ? MCESA_MAX_SIZE : MCESA_MIN_SIZE;
+ size = cpu_has_gs() ? MCESA_MAX_SIZE : MCESA_MIN_SIZE;
origin = kmalloc(size, GFP_KERNEL);
if (!origin)
return -ENOMEM;
/* The pointer is stored with mcesa_bits ORed in */
kmemleak_not_leak(origin);
*mcesad = __pa(origin);
- if (MACHINE_HAS_GS)
+ if (cpu_has_gs())
*mcesad |= ilog2(MCESA_MAX_SIZE);
return 0;
}
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index a95188818637..5970dd3ee7c5 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -7,17 +7,17 @@
ssize_t cpu_show_spectre_v1(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+ return sysfs_emit(buf, "Mitigation: __user pointer sanitization\n");
}
ssize_t cpu_show_spectre_v2(struct device *dev,
struct device_attribute *attr, char *buf)
{
if (test_facility(156))
- return sprintf(buf, "Mitigation: etokens\n");
+ return sysfs_emit(buf, "Mitigation: etokens\n");
if (nospec_uses_trampoline())
- return sprintf(buf, "Mitigation: execute trampolines\n");
+ return sysfs_emit(buf, "Mitigation: execute trampolines\n");
if (nobp_enabled())
- return sprintf(buf, "Mitigation: limited branch prediction\n");
- return sprintf(buf, "Vulnerable\n");
+ return sysfs_emit(buf, "Mitigation: limited branch prediction\n");
+ return sysfs_emit(buf, "Vulnerable\n");
}
diff --git a/arch/s390/kernel/numa.c b/arch/s390/kernel/numa.c
index ddc1448ea2e1..2fc40f97c0ad 100644
--- a/arch/s390/kernel/numa.c
+++ b/arch/s390/kernel/numa.c
@@ -21,12 +21,8 @@ void __init numa_setup(void)
nodes_clear(node_possible_map);
node_set(0, node_possible_map);
node_set_online(0);
- for (nid = 0; nid < MAX_NUMNODES; nid++) {
- NODE_DATA(nid) = memblock_alloc(sizeof(pg_data_t), 8);
- if (!NODE_DATA(nid))
- panic("%s: Failed to allocate %zu bytes align=0x%x\n",
- __func__, sizeof(pg_data_t), 8);
- }
+ for (nid = 0; nid < MAX_NUMNODES; nid++)
+ NODE_DATA(nid) = memblock_alloc_or_panic(sizeof(pg_data_t), 8);
NODE_DATA(0)->node_spanned_pages = memblock_end_of_DRAM() >> PAGE_SHIFT;
NODE_DATA(0)->node_id = 0;
}
diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c
index b695f980bbde..c2a468986212 100644
--- a/arch/s390/kernel/os_info.c
+++ b/arch/s390/kernel/os_info.c
@@ -18,6 +18,7 @@
#include <asm/physmem_info.h>
#include <asm/maccess.h>
#include <asm/asm-offsets.h>
+#include <asm/sections.h>
#include <asm/ipl.h>
/*
@@ -180,7 +181,7 @@ fail:
}
/*
- * Return pointer to os infor entry and its size
+ * Return pointer to os info entry and its size
*/
void *os_info_old_entry(int nr, unsigned long *size)
{
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index e2e0aa463fbd..6a262e198e35 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -442,7 +442,7 @@ static void cpum_cf_make_setsize(enum cpumf_ctr_set ctrset)
ctrset_size = 48;
else if (cpumf_ctr_info.csvn >= 3 && cpumf_ctr_info.csvn <= 5)
ctrset_size = 128;
- else if (cpumf_ctr_info.csvn == 6 || cpumf_ctr_info.csvn == 7)
+ else if (cpumf_ctr_info.csvn >= 6 && cpumf_ctr_info.csvn <= 8)
ctrset_size = 160;
break;
case CPUMF_CTR_SET_MT_DIAG:
@@ -835,7 +835,7 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type)
return validate_ctr_version(hwc->config, set);
}
-/* Events CPU_CYLCES and INSTRUCTIONS can be submitted with two different
+/* Events CPU_CYCLES and INSTRUCTIONS can be submitted with two different
* attribute::type values:
* - PERF_TYPE_HARDWARE:
* - pmu->type:
@@ -858,18 +858,13 @@ static int cpumf_pmu_event_type(struct perf_event *event)
static int cpumf_pmu_event_init(struct perf_event *event)
{
unsigned int type = event->attr.type;
- int err;
+ int err = -ENOENT;
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, cpumf_pmu_event_type(event));
- else
- return -ENOENT;
-
- if (unlikely(err) && event->destroy)
- event->destroy(event);
return err;
}
@@ -879,8 +874,8 @@ static int hw_perf_event_reset(struct perf_event *event)
u64 prev, new;
int err;
+ prev = local64_read(&event->hw.prev_count);
do {
- prev = local64_read(&event->hw.prev_count);
err = ecctr(event->hw.config, &new);
if (err) {
if (err != 3)
@@ -892,7 +887,7 @@ static int hw_perf_event_reset(struct perf_event *event)
*/
new = 0;
}
- } while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
+ } while (!local64_try_cmpxchg(&event->hw.prev_count, &prev, new));
return err;
}
@@ -902,12 +897,12 @@ static void hw_perf_event_update(struct perf_event *event)
u64 prev, new, delta;
int err;
+ prev = local64_read(&event->hw.prev_count);
do {
- prev = local64_read(&event->hw.prev_count);
err = ecctr(event->hw.config, &new);
if (err)
return;
- } while (local64_cmpxchg(&event->hw.prev_count, prev, new) != prev);
+ } while (!local64_try_cmpxchg(&event->hw.prev_count, &prev, new));
delta = (prev <= new) ? new - prev
: (-1ULL - prev) + new + 1; /* overflow */
@@ -981,12 +976,10 @@ static int cfdiag_push_sample(struct perf_event *event,
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
raw.frag.size = cpuhw->usedss;
raw.frag.data = cpuhw->stop;
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
overflow = perf_event_overflow(event, &data, &regs);
- if (overflow)
- event->pmu->stop(event, 0);
perf_event_update_userpage(event);
return overflow;
@@ -1054,7 +1047,7 @@ static void cpumf_pmu_del(struct perf_event *event, int flags)
*
* When a new perf event has been added but not yet started, this can
* clear enable control and resets all counters in a set. Therefore,
- * cpumf_pmu_start() always has to reenable a counter set.
+ * cpumf_pmu_start() always has to re-enable a counter set.
*/
for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i)
if (!atomic_read(&cpuhw->ctr_set[i]))
@@ -1819,8 +1812,6 @@ static int cfdiag_event_init(struct perf_event *event)
event->destroy = hw_perf_event_destroy;
err = cfdiag_event_init2(event);
- if (unlikely(err))
- event->destroy(event);
out:
return err;
}
@@ -1863,7 +1854,7 @@ static const struct attribute_group *cfdiag_attr_groups[] = {
/* Performance monitoring unit for event CF_DIAG. Since this event
* is also started and stopped via the perf_event_open() system call, use
* the same event enable/disable call back functions. They do not
- * have a pointer to the perf_event strcture as first parameter.
+ * have a pointer to the perf_event structure as first parameter.
*
* The functions XXX_add, XXX_del, XXX_start and XXX_stop are also common.
* Reuse them and distinguish the event (always first parameter) via
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index e4a6bfc91080..7ace1f9e4ccf 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -237,7 +237,6 @@ CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_NO_SPECIAL, 0x00f4);
CPUMF_EVENT_ATTR(cf_z14, TX_C_TABORT_SPECIAL, 0x00f5);
CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z14, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
-
CPUMF_EVENT_ATTR(cf_z15, L1D_RO_EXCL_WRITES, 0x0080);
CPUMF_EVENT_ATTR(cf_z15, DTLB2_WRITES, 0x0081);
CPUMF_EVENT_ATTR(cf_z15, DTLB2_MISSES, 0x0082);
@@ -291,8 +290,8 @@ CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_NO_SPECIAL, 0x00f4);
CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_SPECIAL, 0x00f5);
CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7);
CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x0108);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x0109);
CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
CPUMF_EVENT_ATTR(cf_z16, L1D_RO_EXCL_WRITES, 0x0080);
@@ -365,6 +364,83 @@ CPUMF_EVENT_ATTR(cf_z16, NNPA_WAIT_LOCK, 0x010d);
CPUMF_EVENT_ATTR(cf_z16, NNPA_HOLD_LOCK, 0x010e);
CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
CPUMF_EVENT_ATTR(cf_z16, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
+CPUMF_EVENT_ATTR(cf_z17, L1D_RO_EXCL_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z17, CRSTE_1MB_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z17, DTLB2_GPAGE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z17, ITLB2_MISSES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_PTE_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_CRSTE_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z17, TLB2_ENGINES_BUSY, 0x008b);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TEND, 0x008c);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TEND, 0x008d);
+CPUMF_EVENT_ATTR(cf_z17, L1C_TLB2_MISSES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ, 0x0091);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_IV, 0x0092);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_CHIP_HIT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z17, DCW_REQ_DRAWER_HIT, 0x0094);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP, 0x0095);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_CHIP_HIT, 0x0097);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT, 0x0098);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE, 0x0099);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER, 0x009a);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER, 0x009b);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_CHIP_MEMORY, 0x009c);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_MODULE_MEMORY, 0x009d);
+CPUMF_EVENT_ATTR(cf_z17, DCW_ON_DRAWER_MEMORY, 0x009e);
+CPUMF_EVENT_ATTR(cf_z17, DCW_OFF_DRAWER_MEMORY, 0x009f);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT, 0x00a1);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT, 0x00a2);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_IV, 0x00a3);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT, 0x00a4);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT, 0x00a5);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_IV, 0x00a6);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT, 0x00a7);
+CPUMF_EVENT_ATTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT, 0x00a8);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ, 0x00a9);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_IV, 0x00aa);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_CHIP_HIT, 0x00ab);
+CPUMF_EVENT_ATTR(cf_z17, ICW_REQ_DRAWER_HIT, 0x00ac);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP, 0x00ad);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_IV, 0x00ae);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_CHIP_HIT, 0x00af);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT, 0x00b0);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_MODULE, 0x00b1);
+CPUMF_EVENT_ATTR(cf_z17, ICW_ON_DRAWER, 0x00b2);
+CPUMF_EVENT_ATTR(cf_z17, ICW_OFF_DRAWER, 0x00b3);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_SAMETHRD, 0x00ca);
+CPUMF_EVENT_ATTR(cf_z17, CYCLES_DIFFTHRD, 0x00cb);
+CPUMF_EVENT_ATTR(cf_z17, INST_SAMETHRD, 0x00cc);
+CPUMF_EVENT_ATTR(cf_z17, INST_DIFFTHRD, 0x00cd);
+CPUMF_EVENT_ATTR(cf_z17, WRONG_BRANCH_PREDICTION, 0x00ce);
+CPUMF_EVENT_ATTR(cf_z17, VX_BCD_EXECUTION_SLOTS, 0x00e1);
+CPUMF_EVENT_ATTR(cf_z17, DECIMAL_INSTRUCTIONS, 0x00e2);
+CPUMF_EVENT_ATTR(cf_z17, LAST_HOST_TRANSLATIONS, 0x00e8);
+CPUMF_EVENT_ATTR(cf_z17, TX_NC_TABORT, 0x00f4);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_NO_SPECIAL, 0x00f5);
+CPUMF_EVENT_ATTR(cf_z17, TX_C_TABORT_SPECIAL, 0x00f6);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_ACCESS, 0x00f8);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CYCLES, 0x00fd);
+CPUMF_EVENT_ATTR(cf_z17, SORTL, 0x0100);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CC, 0x0109);
+CPUMF_EVENT_ATTR(cf_z17, DFLT_CCFINISH, 0x010a);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INVOCATIONS, 0x010b);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPLETIONS, 0x010c);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_WAIT_LOCK, 0x010d);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_HOLD_LOCK, 0x010e);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_ONCHIP, 0x0110);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_OFFCHIP, 0x0111);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_INST_DIFF, 0x0112);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_4K_PREFETCH, 0x0114);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_COMPL_LOCK, 0x0115);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK, 0x0116);
+CPUMF_EVENT_ATTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO, 0x0117);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
+CPUMF_EVENT_ATTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
static struct attribute *cpumcf_fvn1_pmu_event_attr[] __initdata = {
CPUMF_EVENT_PTR(cf_fvn1, CPU_CYCLES),
@@ -414,7 +490,7 @@ static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
NULL,
};
-static struct attribute *cpumcf_svn_67_pmu_event_attr[] __initdata = {
+static struct attribute *cpumcf_svn_678_pmu_event_attr[] __initdata = {
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
@@ -779,6 +855,87 @@ static struct attribute *cpumcf_z16_pmu_event_attr[] __initdata = {
NULL,
};
+static struct attribute *cpumcf_z17_pmu_event_attr[] __initdata = {
+ CPUMF_EVENT_PTR(cf_z17, L1D_RO_EXCL_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, DTLB2_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, DTLB2_MISSES),
+ CPUMF_EVENT_PTR(cf_z17, CRSTE_1MB_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, DTLB2_GPAGE_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, ITLB2_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, ITLB2_MISSES),
+ CPUMF_EVENT_PTR(cf_z17, TLB2_PTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, TLB2_CRSTE_WRITES),
+ CPUMF_EVENT_PTR(cf_z17, TLB2_ENGINES_BUSY),
+ CPUMF_EVENT_PTR(cf_z17, TX_C_TEND),
+ CPUMF_EVENT_PTR(cf_z17, TX_NC_TEND),
+ CPUMF_EVENT_PTR(cf_z17, L1C_TLB2_MISSES),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ_IV),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_REQ_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_IV),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_CHIP_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_MODULE_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, DCW_ON_DRAWER_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, DCW_OFF_DRAWER_MEMORY),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_IV),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_MODULE_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_IV),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_ON_DRAWER_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_IV),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, IDCW_OFF_DRAWER_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ_IV),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_REQ_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_IV),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_CHIP_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_CHIP_DRAWER_HIT),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_MODULE),
+ CPUMF_EVENT_PTR(cf_z17, ICW_ON_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, ICW_OFF_DRAWER),
+ CPUMF_EVENT_PTR(cf_z17, CYCLES_SAMETHRD),
+ CPUMF_EVENT_PTR(cf_z17, CYCLES_DIFFTHRD),
+ CPUMF_EVENT_PTR(cf_z17, INST_SAMETHRD),
+ CPUMF_EVENT_PTR(cf_z17, INST_DIFFTHRD),
+ CPUMF_EVENT_PTR(cf_z17, WRONG_BRANCH_PREDICTION),
+ CPUMF_EVENT_PTR(cf_z17, VX_BCD_EXECUTION_SLOTS),
+ CPUMF_EVENT_PTR(cf_z17, DECIMAL_INSTRUCTIONS),
+ CPUMF_EVENT_PTR(cf_z17, LAST_HOST_TRANSLATIONS),
+ CPUMF_EVENT_PTR(cf_z17, TX_NC_TABORT),
+ CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_NO_SPECIAL),
+ CPUMF_EVENT_PTR(cf_z17, TX_C_TABORT_SPECIAL),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_ACCESS),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_CYCLES),
+ CPUMF_EVENT_PTR(cf_z17, SORTL),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_CC),
+ CPUMF_EVENT_PTR(cf_z17, DFLT_CCFINISH),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INVOCATIONS),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_COMPLETIONS),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_WAIT_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_HOLD_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INST_ONCHIP),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INST_OFFCHIP),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_INST_DIFF),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_4K_PREFETCH),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_COMPL_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK),
+ CPUMF_EVENT_PTR(cf_z17, NNPA_RETRY_LOCK_WITH_PLO),
+ CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
+ CPUMF_EVENT_PTR(cf_z17, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
+ NULL,
+};
+
/* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
static struct attribute_group cpumcf_pmu_events_group = {
@@ -859,7 +1016,7 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
if (ci.csvn >= 1 && ci.csvn <= 5)
csvn = cpumcf_svn_12345_pmu_event_attr;
else if (ci.csvn >= 6)
- csvn = cpumcf_svn_67_pmu_event_attr;
+ csvn = cpumcf_svn_678_pmu_event_attr;
/* Determine model-specific counter set(s) */
get_cpu_id(&cpu_id);
@@ -892,6 +1049,10 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
case 0x3932:
model = cpumcf_z16_pmu_event_attr;
break;
+ case 0x9175:
+ case 0x9176:
+ model = cpumcf_z17_pmu_event_attr;
+ break;
default:
model = none;
break;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 5b765e3ccf0c..91469401f2c9 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -180,39 +180,27 @@ static int sf_buffer_available(struct cpu_hw_sf *cpuhw)
*/
static void free_sampling_buffer(struct sf_buffer *sfb)
{
- unsigned long *sdbt, *curr;
-
- if (!sfb->sdbt)
- return;
+ unsigned long *sdbt, *curr, *head;
sdbt = sfb->sdbt;
- curr = sdbt;
-
+ if (!sdbt)
+ return;
+ sfb->sdbt = NULL;
/* Free the SDBT after all SDBs are processed... */
- while (1) {
- if (!*curr || !sdbt)
- break;
-
- /* Process table-link entries */
+ head = sdbt;
+ curr = sdbt;
+ do {
if (is_link_entry(curr)) {
+ /* Process table-link entries */
curr = get_next_sdbt(curr);
- if (sdbt)
- free_page((unsigned long)sdbt);
-
- /* If the origin is reached, sampling buffer is freed */
- if (curr == sfb->sdbt)
- break;
- else
- sdbt = curr;
+ free_page((unsigned long)sdbt);
+ sdbt = curr;
} else {
/* Process SDB pointer */
- if (*curr) {
- free_page((unsigned long)phys_to_virt(*curr));
- curr++;
- }
+ free_page((unsigned long)phys_to_virt(*curr));
+ curr++;
}
- }
-
+ } while (curr != head);
memset(sfb, 0, sizeof(*sfb));
}
@@ -404,7 +392,7 @@ static void sfb_init_allocs(unsigned long num, struct hw_perf_event *hwc)
static void deallocate_buffers(struct cpu_hw_sf *cpuhw)
{
- if (cpuhw->sfb.sdbt)
+ if (sf_buffer_available(cpuhw))
free_sampling_buffer(&cpuhw->sfb);
}
@@ -559,16 +547,15 @@ static void setup_pmc_cpu(void *flags)
{
struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf);
+ sf_disable();
switch (*((int *)flags)) {
case PMC_INIT:
memset(cpuhw, 0, sizeof(*cpuhw));
qsi(&cpuhw->qsi);
cpuhw->flags |= PMU_F_RESERVED;
- sf_disable();
break;
case PMC_RELEASE:
cpuhw->flags &= ~PMU_F_RESERVED;
- sf_disable();
deallocate_buffers(cpuhw);
break;
}
@@ -759,7 +746,6 @@ static int __hw_perf_event_init(struct perf_event *event)
reserve_pmc_hardware();
refcount_set(&num_events, 1);
}
- mutex_unlock(&pmc_reserve_mutex);
event->destroy = hw_perf_event_destroy;
/* Access per-CPU sampling information (query sampling info) */
@@ -818,7 +804,7 @@ static int __hw_perf_event_init(struct perf_event *event)
/* Use AUX buffer. No need to allocate it by ourself */
if (attr->config == PERF_EVENT_CPUM_SF_DIAG)
- return 0;
+ goto out;
/* Allocate the per-CPU sampling buffer using the CPU information
* from the event. If the event is not pinned to a particular
@@ -848,6 +834,7 @@ static int __hw_perf_event_init(struct perf_event *event)
if (is_default_overflow_handler(event))
event->overflow_handler = cpumsf_output_event_pid;
out:
+ mutex_unlock(&pmc_reserve_mutex);
return err;
}
@@ -898,9 +885,6 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
event->attr.exclude_idle = 0;
err = __hw_perf_event_init(event);
- if (unlikely(err))
- if (event->destroy)
- event->destroy(event);
return err;
}
@@ -910,10 +894,14 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
struct hw_perf_event *hwc;
int err;
- if (cpuhw->flags & PMU_F_ENABLED)
- return;
-
- if (cpuhw->flags & PMU_F_ERR_MASK)
+ /*
+ * Event must be
+ * - added/started on this CPU (PMU_F_IN_USE set)
+ * - and CPU must be available (PMU_F_RESERVED set)
+ * - and not already enabled (PMU_F_ENABLED not set)
+ * - and not in error condition (PMU_F_ERR_MASK not set)
+ */
+ if (cpuhw->flags != (PMU_F_IN_USE | PMU_F_RESERVED))
return;
/* Check whether to extent the sampling buffer.
@@ -927,33 +915,27 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
* facility, but it can be fully re-enabled using sampling controls that
* have been saved in cpumsf_pmu_disable().
*/
- if (cpuhw->event) {
- hwc = &cpuhw->event->hw;
- if (!(SAMPL_DIAG_MODE(hwc))) {
- /*
- * Account number of overflow-designated
- * buffer extents
- */
- sfb_account_overflows(cpuhw, hwc);
- extend_sampling_buffer(&cpuhw->sfb, hwc);
- }
- /* Rate may be adjusted with ioctl() */
- cpuhw->lsctl.interval = SAMPL_RATE(hwc);
+ hwc = &cpuhw->event->hw;
+ if (!(SAMPL_DIAG_MODE(hwc))) {
+ /*
+ * Account number of overflow-designated buffer extents
+ */
+ sfb_account_overflows(cpuhw, hwc);
+ extend_sampling_buffer(&cpuhw->sfb, hwc);
}
+ /* Rate may be adjusted with ioctl() */
+ cpuhw->lsctl.interval = SAMPL_RATE(hwc);
/* (Re)enable the PMU and sampling facility */
- cpuhw->flags |= PMU_F_ENABLED;
- barrier();
-
err = lsctl(&cpuhw->lsctl);
if (err) {
- cpuhw->flags &= ~PMU_F_ENABLED;
pr_err("Loading sampling controls failed: op 1 err %i\n", err);
return;
}
/* Load current program parameter */
lpp(&get_lowcore()->lpp);
+ cpuhw->flags |= PMU_F_ENABLED;
}
static void cpumsf_pmu_disable(struct pmu *pmu)
@@ -996,7 +978,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
cpuhw->flags &= ~PMU_F_ENABLED;
}
-/* perf_exclude_event() - Filter event
+/* perf_event_exclude() - Filter event
* @event: The perf event
* @regs: pt_regs structure
* @sde_regs: Sample-data-entry (sde) regs structure
@@ -1005,7 +987,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
*
* Return non-zero if the event shall be excluded.
*/
-static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs,
+static int perf_event_exclude(struct perf_event *event, struct pt_regs *regs,
struct perf_sf_sde_regs *sde_regs)
{
if (event->attr.exclude_user && user_mode(regs))
@@ -1088,12 +1070,9 @@ static int perf_push_sample(struct perf_event *event,
data.tid_entry.pid = basic->hpp & LPP_PID_MASK;
overflow = 0;
- if (perf_exclude_event(event, &regs, sde_regs))
+ if (perf_event_exclude(event, &regs, sde_regs))
goto out;
- if (perf_event_overflow(event, &data, &regs)) {
- overflow = 1;
- event->pmu->stop(event, 0);
- }
+ overflow = perf_event_overflow(event, &data, &regs);
perf_event_update_userpage(event);
out:
return overflow;
@@ -1191,8 +1170,8 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
static void hw_perf_event_update(struct perf_event *event, int flush_all)
{
unsigned long long event_overflow, sampl_overflow, num_sdb;
- union hws_trailer_header old, prev, new;
struct hw_perf_event *hwc = &event->hw;
+ union hws_trailer_header prev, new;
struct hws_trailer_entry *te;
unsigned long *sdbt, sdb;
int done;
@@ -1236,13 +1215,11 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
/* Reset trailer (using compare-double-and-swap) */
prev.val = READ_ONCE_ALIGNED_128(te->header.val);
do {
- old.val = prev.val;
new.val = prev.val;
new.f = 0;
new.a = 1;
new.overflow = 0;
- prev.val = cmpxchg128(&te->header.val, old.val, new.val);
- } while (prev.val != old.val);
+ } while (!try_cmpxchg128(&te->header.val, &prev.val, new.val));
/* Advance to next sample-data-block */
sdbt++;
@@ -1408,16 +1385,15 @@ static int aux_output_begin(struct perf_output_handle *handle,
static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
unsigned long long *overflow)
{
- union hws_trailer_header old, prev, new;
+ union hws_trailer_header prev, new;
struct hws_trailer_entry *te;
te = aux_sdb_trailer(aux, alert_index);
prev.val = READ_ONCE_ALIGNED_128(te->header.val);
do {
- old.val = prev.val;
new.val = prev.val;
- *overflow = old.overflow;
- if (old.f) {
+ *overflow = prev.overflow;
+ if (prev.f) {
/*
* SDB is already set by hardware.
* Abort and try to set somewhere
@@ -1427,8 +1403,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
}
new.a = 1;
new.overflow = 0;
- prev.val = cmpxchg128(&te->header.val, old.val, new.val);
- } while (prev.val != old.val);
+ } while (!try_cmpxchg128(&te->header.val, &prev.val, new.val));
return true;
}
@@ -1457,7 +1432,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index,
static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
unsigned long long *overflow)
{
- union hws_trailer_header old, prev, new;
+ union hws_trailer_header prev, new;
unsigned long i, range_scan, idx;
unsigned long long orig_overflow;
struct hws_trailer_entry *te;
@@ -1489,17 +1464,15 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range,
te = aux_sdb_trailer(aux, idx);
prev.val = READ_ONCE_ALIGNED_128(te->header.val);
do {
- old.val = prev.val;
new.val = prev.val;
- orig_overflow = old.overflow;
+ orig_overflow = prev.overflow;
new.f = 0;
new.overflow = 0;
if (idx == aux->alert_mark)
new.a = 1;
else
new.a = 0;
- prev.val = cmpxchg128(&te->header.val, old.val, new.val);
- } while (prev.val != old.val);
+ } while (!try_cmpxchg128(&te->header.val, &prev.val, new.val));
*overflow += orig_overflow;
}
@@ -1780,7 +1753,9 @@ static void cpumsf_pmu_stop(struct perf_event *event, int flags)
event->hw.state |= PERF_HES_STOPPED;
if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
- hw_perf_event_update(event, 1);
+ /* CPU hotplug off removes SDBs. No samples to extract. */
+ if (cpuhw->flags & PMU_F_RESERVED)
+ hw_perf_event_update(event, 1);
event->hw.state |= PERF_HES_UPTODATE;
}
perf_pmu_enable(event->pmu);
@@ -1795,7 +1770,7 @@ static int cpumsf_pmu_add(struct perf_event *event, int flags)
if (cpuhw->flags & PMU_F_IN_USE)
return -EAGAIN;
- if (!SAMPL_DIAG_MODE(&event->hw) && !cpuhw->sfb.sdbt)
+ if (!SAMPL_DIAG_MODE(&event->hw) && !sf_buffer_available(cpuhw))
return -EINVAL;
perf_pmu_disable(event->pmu);
@@ -1957,13 +1932,12 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
/* Program alert request */
if (alert & CPU_MF_INT_SF_PRA) {
- if (cpuhw->flags & PMU_F_IN_USE)
+ if (cpuhw->flags & PMU_F_IN_USE) {
if (SAMPL_DIAG_MODE(&cpuhw->event->hw))
hw_collect_aux(cpuhw);
else
hw_perf_event_update(cpuhw->event, 0);
- else
- WARN_ON_ONCE(!(cpuhw->flags & PMU_F_IN_USE));
+ }
}
/* Report measurement alerts only for non-PRA codes */
@@ -1984,7 +1958,7 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
/* Invalid sampling buffer entry */
if (alert & (CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE)) {
- pr_err("A sampling buffer entry is incorrect (alert=0x%x)\n",
+ pr_err("A sampling buffer entry is incorrect (alert=%#x)\n",
alert);
cpuhw->flags |= PMU_F_ERR_IBE;
sf_disable();
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 5fff629b1a89..2b9611c4718e 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -57,7 +57,7 @@ static unsigned long instruction_pointer_guest(struct pt_regs *regs)
return sie_block(regs)->gpsw.addr;
}
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
{
return is_in_guest(regs) ? instruction_pointer_guest(regs)
: instruction_pointer(regs);
@@ -84,7 +84,7 @@ static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
return flags;
}
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
{
/* Check if the cpum_sf PMU has created the pt_regs structure.
* In this case, perf misc flags can be easily extracted. Otherwise,
@@ -228,5 +228,5 @@ ssize_t cpumf_events_sysfs_show(struct device *dev,
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+ return sysfs_emit(page, "event=0x%04llx\n", pmu_attr->id);
}
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index fa7325454266..63875270941b 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -478,7 +478,7 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump,
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
raw.frag.size = rawsize;
raw.frag.data = cpump->save;
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
overflow = perf_event_overflow(event, &data, &regs);
@@ -518,7 +518,8 @@ static void paicrypt_have_samples(void)
/* Called on schedule-in and schedule-out. No access to event structure,
* but for sampling only event CRYPTO_ALL is allowed.
*/
-static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx,
+ struct task_struct *task, bool sched_in)
{
/* We started with a clean page on event installation. So read out
* results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 7f462bef1fc0..fd14d5ebccbc 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -503,7 +503,7 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump,
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
raw.frag.size = rawsize;
raw.frag.data = cpump->save;
- perf_sample_save_raw_data(&data, &raw);
+ perf_sample_save_raw_data(&data, event, &raw);
}
overflow = perf_event_overflow(event, &data, &regs);
@@ -542,7 +542,8 @@ static void paiext_have_samples(void)
/* Called on schedule-in and schedule-out. No access to event structure,
* but for sampling only event NNPA_ALL is allowed.
*/
-static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx,
+ struct task_struct *task, bool sched_in)
{
/* We started with a clean page on event installation. So read out
* results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 5ce9a795a0fe..11f70c1e2797 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -8,6 +8,7 @@
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/stop_machine.h>
+#include <linux/cpufeature.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/random.h>
@@ -19,6 +20,7 @@
#include <linux/cpu.h>
#include <linux/smp.h>
#include <asm/text-patching.h>
+#include <asm/machine.h>
#include <asm/diag.h>
#include <asm/facility.h>
#include <asm/elf.h>
@@ -72,7 +74,7 @@ void notrace stop_machine_yield(const struct cpumask *cpumask)
this_cpu = smp_processor_id();
if (__this_cpu_inc_return(cpu_relax_retry) >= spin_retry) {
__this_cpu_write(cpu_relax_retry, 0);
- cpu = cpumask_next_wrap(this_cpu, cpumask, this_cpu, false);
+ cpu = cpumask_next_wrap(this_cpu, cpumask);
if (cpu >= nr_cpu_ids)
return;
if (arch_vcpu_is_preempted(cpu))
@@ -209,14 +211,14 @@ static int __init setup_hwcaps(void)
elf_hwcap |= HWCAP_DFP;
/* huge page support */
- if (MACHINE_HAS_EDAT1)
+ if (cpu_has_edat1())
elf_hwcap |= HWCAP_HPAGE;
/* 64-bit register support for 31-bit processes */
elf_hwcap |= HWCAP_HIGH_GPRS;
/* transactional execution */
- if (MACHINE_HAS_TE)
+ if (machine_has_tx())
elf_hwcap |= HWCAP_TE;
/* vector */
@@ -244,10 +246,10 @@ static int __init setup_hwcaps(void)
elf_hwcap |= HWCAP_NNPA;
/* guarded storage */
- if (MACHINE_HAS_GS)
+ if (cpu_has_gs())
elf_hwcap |= HWCAP_GS;
- if (MACHINE_HAS_PCI_MIO)
+ if (test_machine_feature(MFEATURE_PCI_MIO))
elf_hwcap |= HWCAP_PCI_MIO;
/* virtualization support */
@@ -266,31 +268,35 @@ static int __init setup_elf_platform(void)
add_device_randomness(&cpu_id, sizeof(cpu_id));
switch (cpu_id.machine) {
default: /* Use "z10" as default. */
- strcpy(elf_platform, "z10");
+ strscpy(elf_platform, "z10");
break;
case 0x2817:
case 0x2818:
- strcpy(elf_platform, "z196");
+ strscpy(elf_platform, "z196");
break;
case 0x2827:
case 0x2828:
- strcpy(elf_platform, "zEC12");
+ strscpy(elf_platform, "zEC12");
break;
case 0x2964:
case 0x2965:
- strcpy(elf_platform, "z13");
+ strscpy(elf_platform, "z13");
break;
case 0x3906:
case 0x3907:
- strcpy(elf_platform, "z14");
+ strscpy(elf_platform, "z14");
break;
case 0x8561:
case 0x8562:
- strcpy(elf_platform, "z15");
+ strscpy(elf_platform, "z15");
break;
case 0x3931:
case 0x3932:
- strcpy(elf_platform, "z16");
+ strscpy(elf_platform, "z16");
+ break;
+ case 0x9175:
+ case 0x9176:
+ strscpy(elf_platform, "z17");
break;
}
return 0;
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 1cfed8b710b8..e1240f6b29fa 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -7,10 +7,10 @@
* Martin Schwidefsky (schwidefsky@de.ibm.com)
*/
-#include "asm/ptrace.h"
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
+#include <linux/cpufeature.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
@@ -31,6 +31,9 @@
#include <asm/unistd.h>
#include <asm/runtime_instr.h>
#include <asm/facility.h>
+#include <asm/machine.h>
+#include <asm/ptrace.h>
+#include <asm/rwonce.h>
#include <asm/fpu.h>
#include "entry.h"
@@ -60,7 +63,7 @@ void update_cr_regs(struct task_struct *task)
cr0_new = cr0_old;
cr2_new = cr2_old;
/* Take care of the enable/disable of transactional execution. */
- if (MACHINE_HAS_TE) {
+ if (machine_has_tx()) {
/* Set or clear transaction execution TXC bit 8. */
cr0_new.tcx = 1;
if (task->thread.per_flags & PER_FLAG_NO_TE)
@@ -75,7 +78,7 @@ void update_cr_regs(struct task_struct *task)
}
}
/* Take care of enable/disable of guarded storage. */
- if (MACHINE_HAS_GS) {
+ if (cpu_has_gs()) {
cr2_new.gse = 0;
if (task->thread.gs_cb)
cr2_new.gse = 1;
@@ -470,18 +473,18 @@ long arch_ptrace(struct task_struct *child, long request,
case PTRACE_GET_LAST_BREAK:
return put_user(child->thread.last_break, (unsigned long __user *)data);
case PTRACE_ENABLE_TE:
- if (!MACHINE_HAS_TE)
+ if (!machine_has_tx())
return -EIO;
child->thread.per_flags &= ~PER_FLAG_NO_TE;
return 0;
case PTRACE_DISABLE_TE:
- if (!MACHINE_HAS_TE)
+ if (!machine_has_tx())
return -EIO;
child->thread.per_flags |= PER_FLAG_NO_TE;
child->thread.per_flags &= ~PER_FLAG_TE_ABORT_RAND;
return 0;
case PTRACE_TE_ABORT_RAND:
- if (!MACHINE_HAS_TE || (child->thread.per_flags & PER_FLAG_NO_TE))
+ if (!machine_has_tx() || (child->thread.per_flags & PER_FLAG_NO_TE))
return -EIO;
switch (data) {
case 0UL:
@@ -1033,7 +1036,7 @@ static int s390_gs_cb_get(struct task_struct *target,
{
struct gs_cb *data = target->thread.gs_cb;
- if (!MACHINE_HAS_GS)
+ if (!cpu_has_gs())
return -ENODEV;
if (!data)
return -ENODATA;
@@ -1050,7 +1053,7 @@ static int s390_gs_cb_set(struct task_struct *target,
struct gs_cb gs_cb = { }, *data = NULL;
int rc;
- if (!MACHINE_HAS_GS)
+ if (!cpu_has_gs())
return -ENODEV;
if (!target->thread.gs_cb) {
data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -1087,7 +1090,7 @@ static int s390_gs_bc_get(struct task_struct *target,
{
struct gs_cb *data = target->thread.gs_bc_cb;
- if (!MACHINE_HAS_GS)
+ if (!cpu_has_gs())
return -ENODEV;
if (!data)
return -ENODATA;
@@ -1101,7 +1104,7 @@ static int s390_gs_bc_set(struct task_struct *target,
{
struct gs_cb *data = target->thread.gs_bc_cb;
- if (!MACHINE_HAS_GS)
+ if (!cpu_has_gs())
return -ENODEV;
if (!data) {
data = kzalloc(sizeof(*data), GFP_KERNEL);
@@ -1521,13 +1524,6 @@ static const char *gpr_names[NUM_GPRS] = {
"r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15",
};
-unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset)
-{
- if (offset >= NUM_GPRS)
- return 0;
- return regs->gprs[offset];
-}
-
int regs_query_register_offset(const char *name)
{
unsigned long offset;
@@ -1547,29 +1543,3 @@ const char *regs_query_register_name(unsigned int offset)
return NULL;
return gpr_names[offset];
}
-
-static int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
-{
- unsigned long ksp = kernel_stack_pointer(regs);
-
- return (addr & ~(THREAD_SIZE - 1)) == (ksp & ~(THREAD_SIZE - 1));
-}
-
-/**
- * regs_get_kernel_stack_nth() - get Nth entry of the stack
- * @regs:pt_regs which contains kernel stack pointer.
- * @n:stack entry number.
- *
- * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
- * is specifined by @regs. If the @n th entry is NOT in the kernel stack,
- * this returns 0.
- */
-unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
-{
- unsigned long addr;
-
- addr = kernel_stack_pointer(regs) + n * sizeof(long);
- if (!regs_within_kernel_stack(regs, addr))
- return 0;
- return *(unsigned long *)addr;
-}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index a3fea683b227..f244c5560e7f 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -54,6 +54,7 @@
#include <asm/archrandom.h>
#include <asm/boot_data.h>
+#include <asm/machine.h>
#include <asm/ipl.h>
#include <asm/facility.h>
#include <asm/smp.h>
@@ -157,25 +158,29 @@ u64 __bootdata_preserved(stfle_fac_list[16]);
EXPORT_SYMBOL(stfle_fac_list);
struct oldmem_data __bootdata_preserved(oldmem_data);
-unsigned long VMALLOC_START;
+char __bootdata(boot_rb)[PAGE_SIZE * 2];
+bool __bootdata(boot_earlyprintk);
+size_t __bootdata(boot_rb_off);
+char __bootdata(bootdebug_filter)[128];
+bool __bootdata(bootdebug);
+
+unsigned long __bootdata_preserved(VMALLOC_START);
EXPORT_SYMBOL(VMALLOC_START);
-unsigned long VMALLOC_END;
+unsigned long __bootdata_preserved(VMALLOC_END);
EXPORT_SYMBOL(VMALLOC_END);
-struct page *vmemmap;
+struct page *__bootdata_preserved(vmemmap);
EXPORT_SYMBOL(vmemmap);
-unsigned long vmemmap_size;
+unsigned long __bootdata_preserved(vmemmap_size);
-unsigned long MODULES_VADDR;
-unsigned long MODULES_END;
+unsigned long __bootdata_preserved(MODULES_VADDR);
+unsigned long __bootdata_preserved(MODULES_END);
/* An array with a pointer to the lowcore of every CPU. */
struct lowcore *lowcore_ptr[NR_CPUS];
EXPORT_SYMBOL(lowcore_ptr);
-DEFINE_STATIC_KEY_FALSE(cpu_has_bear);
-
/*
* The Write Back bit position in the physaddr is given by the SLPC PCI.
* Leaving the mask zero always uses write through which is safe
@@ -245,7 +250,7 @@ static void __init conmode_default(void)
char query_buffer[1024];
char *ptr;
- if (MACHINE_IS_VM) {
+ if (machine_is_vm()) {
cpcmd("QUERY CONSOLE", query_buffer, 1024, NULL);
console_devno = simple_strtoul(query_buffer + 5, NULL, 16);
ptr = strstr(query_buffer, "SUBCHANNEL =");
@@ -283,7 +288,7 @@ static void __init conmode_default(void)
SET_CONSOLE_SCLP;
#endif
}
- } else if (MACHINE_IS_KVM) {
+ } else if (machine_is_kvm()) {
if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE))
SET_CONSOLE_VT220;
else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE))
@@ -359,36 +364,24 @@ void *restart_stack;
unsigned long stack_alloc(void)
{
-#ifdef CONFIG_VMAP_STACK
- void *ret;
+ void *stack;
- ret = __vmalloc_node(THREAD_SIZE, THREAD_SIZE, THREADINFO_GFP,
- NUMA_NO_NODE, __builtin_return_address(0));
- kmemleak_not_leak(ret);
- return (unsigned long)ret;
-#else
- return __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER);
-#endif
+ stack = __vmalloc_node(THREAD_SIZE, THREAD_SIZE, THREADINFO_GFP,
+ NUMA_NO_NODE, __builtin_return_address(0));
+ kmemleak_not_leak(stack);
+ return (unsigned long)stack;
}
void stack_free(unsigned long stack)
{
-#ifdef CONFIG_VMAP_STACK
- vfree((void *) stack);
-#else
- free_pages(stack, THREAD_SIZE_ORDER);
-#endif
+ vfree((void *)stack);
}
static unsigned long __init stack_alloc_early(void)
{
unsigned long stack;
- stack = (unsigned long)memblock_alloc(THREAD_SIZE, THREAD_SIZE);
- if (!stack) {
- panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
- __func__, THREAD_SIZE, THREAD_SIZE);
- }
+ stack = (unsigned long)memblock_alloc_or_panic(THREAD_SIZE, THREAD_SIZE);
return stack;
}
@@ -421,7 +414,6 @@ static void __init setup_lowcore(void)
lc->clock_comparator = clock_comparator_max;
lc->current_task = (unsigned long)&init_task;
lc->lpp = LPP_MAGIC;
- lc->machine_flags = get_lowcore()->machine_flags;
lc->preempt_count = get_lowcore()->preempt_count;
nmi_alloc_mcesa_early(&lc->mcesad);
lc->sys_enter_timer = get_lowcore()->sys_enter_timer;
@@ -512,10 +504,7 @@ static void __init setup_resources(void)
bss_resource.end = __pa_symbol(__bss_stop) - 1;
for_each_mem_range(i, &start, &end) {
- res = memblock_alloc(sizeof(*res), 8);
- if (!res)
- panic("%s: Failed to allocate %zu bytes align=0x%x\n",
- __func__, sizeof(*res), 8);
+ res = memblock_alloc_or_panic(sizeof(*res), 8);
res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
res->name = "System RAM";
@@ -534,10 +523,7 @@ static void __init setup_resources(void)
std_res->start > res->end)
continue;
if (std_res->end > res->end) {
- sub_res = memblock_alloc(sizeof(*sub_res), 8);
- if (!sub_res)
- panic("%s: Failed to allocate %zu bytes align=0x%x\n",
- __func__, sizeof(*sub_res), 8);
+ sub_res = memblock_alloc_or_panic(sizeof(*sub_res), 8);
*sub_res = *std_res;
sub_res->end = res->end;
std_res->start = res->end + 1;
@@ -664,7 +650,7 @@ static void __init reserve_crashkernel(void)
return;
}
- if (!oldmem_data.start && MACHINE_IS_VM)
+ if (!oldmem_data.start && machine_is_vm())
diag10_range(PFN_DOWN(crash_base), PFN_DOWN(crash_size));
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
@@ -704,7 +690,7 @@ static void __init reserve_physmem_info(void)
{
unsigned long addr, size;
- if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size))
+ if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size))
memblock_reserve(addr, size);
}
@@ -712,7 +698,7 @@ static void __init free_physmem_info(void)
{
unsigned long addr, size;
- if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size))
+ if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size))
memblock_phys_free(addr, size);
}
@@ -742,7 +728,7 @@ static void __init reserve_lowcore(void)
void *lowcore_end = lowcore_start + sizeof(struct lowcore);
void *start, *end;
- if ((void *)__identity_base < lowcore_end) {
+ if (absolute_pointer(__identity_base) < lowcore_end) {
start = max(lowcore_start, (void *)__identity_base);
end = min(lowcore_end, (void *)(__identity_base + ident_map_size));
memblock_reserve(__pa(start), __pa(end));
@@ -824,9 +810,7 @@ static void __init setup_randomness(void)
{
struct sysinfo_3_2_2 *vmms;
- vmms = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- if (!vmms)
- panic("Failed to allocate memory for sysinfo structure\n");
+ vmms = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
memblock_free(vmms, PAGE_SIZE);
@@ -886,6 +870,23 @@ static void __init log_component_list(void)
}
/*
+ * Print avoiding interpretation of % in buf and taking bootdebug option
+ * into consideration.
+ */
+static void __init print_rb_entry(const char *buf)
+{
+ char fmt[] = KERN_SOH "0boot: %s";
+ int level = printk_get_level(buf);
+
+ buf = skip_timestamp(printk_skip_level(buf));
+ if (level == KERN_DEBUG[1] && (!bootdebug || !bootdebug_filter_match(buf)))
+ return;
+
+ fmt[1] = level;
+ printk(fmt, buf);
+}
+
+/*
* Setup function called from init/main.c just after the banner
* was printed.
*/
@@ -895,17 +896,20 @@ void __init setup_arch(char **cmdline_p)
/*
* print what head.S has found out about the machine
*/
- if (MACHINE_IS_VM)
+ if (machine_is_vm())
pr_info("Linux is running as a z/VM "
"guest operating system in 64-bit mode\n");
- else if (MACHINE_IS_KVM)
+ else if (machine_is_kvm())
pr_info("Linux is running under KVM in 64-bit mode\n");
- else if (MACHINE_IS_LPAR)
+ else if (machine_is_lpar())
pr_info("Linux is running natively in 64-bit mode\n");
else
pr_info("Linux is running as a guest in 64-bit mode\n");
+ /* Print decompressor messages if not already printed */
+ if (!boot_earlyprintk)
+ boot_rb_foreach(print_rb_entry);
- if (have_relocated_lowcore())
+ if (machine_has_relocated_lowcore())
pr_info("Lowcore relocated to 0x%px\n", get_lowcore());
log_component_list();
@@ -955,7 +959,7 @@ void __init setup_arch(char **cmdline_p)
setup_uv();
dma_contiguous_reserve(ident_map_size);
vmcp_cma_reserve();
- if (MACHINE_HAS_EDAT2)
+ if (cpu_has_edat2())
hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
reserve_crashkernel();
@@ -975,10 +979,7 @@ void __init setup_arch(char **cmdline_p)
numa_setup();
smp_detect_cpus();
topology_init_early();
-
- if (test_facility(193))
- static_branch_enable(&cpu_has_bear);
-
+ setup_protection_map();
/*
* Create kernel page tables.
*/
@@ -1006,3 +1007,8 @@ void __init setup_arch(char **cmdline_p)
/* Add system specific data to the random pool */
setup_randomness();
}
+
+void __init arch_cpu_finalize_init(void)
+{
+ sclp_init();
+}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 4df56fdb2488..81f12bb77f62 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -18,6 +18,7 @@
#define KMSG_COMPONENT "cpu"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <linux/cpufeature.h>
#include <linux/workqueue.h>
#include <linux/memblock.h>
#include <linux/export.h>
@@ -38,6 +39,7 @@
#include <linux/kprobes.h>
#include <asm/access-regs.h>
#include <asm/asm-offsets.h>
+#include <asm/machine.h>
#include <asm/ctlreg.h>
#include <asm/pfault.h>
#include <asm/diag.h>
@@ -97,13 +99,6 @@ __vector128 __initdata boot_cpu_vector_save_area[__NUM_VXRS];
static unsigned int smp_max_threads __initdata = -1U;
cpumask_t cpu_setup_mask;
-static int __init early_nosmt(char *s)
-{
- smp_max_threads = 1;
- return 0;
-}
-early_param("nosmt", early_nosmt);
-
static int __init early_smt(char *s)
{
get_option(&s, &smp_max_threads);
@@ -263,13 +258,12 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = get_lowcore()->kernel_asce;
lc->user_asce = s390_invalid_asce;
- lc->machine_flags = get_lowcore()->machine_flags;
lc->user_timer = lc->system_timer =
lc->steal_timer = lc->avg_steal_timer = 0;
abs_lc = get_abs_lowcore();
memcpy(lc->cregs_save_area, abs_lc->cregs_save_area, sizeof(lc->cregs_save_area));
put_abs_lowcore(abs_lc);
- lc->cregs_save_area[1] = lc->kernel_asce;
+ lc->cregs_save_area[1] = lc->user_asce;
lc->cregs_save_area[7] = lc->user_asce;
save_access_regs((unsigned int *) lc->access_regs_save_area);
arch_spin_lock_setup(cpu);
@@ -416,7 +410,7 @@ EXPORT_SYMBOL(arch_vcpu_is_preempted);
void notrace smp_yield_cpu(int cpu)
{
- if (!MACHINE_HAS_DIAG9C)
+ if (!machine_has_diag9c())
return;
diag_stat_inc_norecursion(DIAG_STAT_X09C);
asm volatile("diag %0,0,0x9c"
@@ -561,10 +555,10 @@ int smp_store_status(int cpu)
if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_STATUS_AT_ADDRESS,
pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
return -EIO;
- if (!cpu_has_vx() && !MACHINE_HAS_GS)
+ if (!cpu_has_vx() && !cpu_has_gs())
return 0;
pa = lc->mcesad & MCESA_ORIGIN_MASK;
- if (MACHINE_HAS_GS)
+ if (cpu_has_gs())
pa |= lc->mcesad & MCESA_LC_MASK;
if (__pcpu_sigp_relax(pcpu->address, SIGP_STORE_ADDITIONAL_STATUS,
pa) != SIGP_CC_ORDER_CODE_ACCEPTED)
@@ -574,7 +568,7 @@ int smp_store_status(int cpu)
/*
* Collect CPU state of the previous, crashed system.
- * There are four cases:
+ * There are three cases:
* 1) standard zfcp/nvme dump
* condition: OLDMEM_BASE == NULL && is_ipl_type_dump() == true
* The state for all CPUs except the boot CPU needs to be collected
@@ -587,16 +581,16 @@ int smp_store_status(int cpu)
* with sigp stop-and-store-status. The firmware or the boot-loader
* stored the registers of the boot CPU in the absolute lowcore in the
* memory of the old system.
- * 3) kdump and the old kernel did not store the CPU state,
- * or stand-alone kdump for DASD
- * condition: OLDMEM_BASE != NULL && !is_kdump_kernel()
+ * 3) kdump or stand-alone kdump for DASD
+ * condition: OLDMEM_BASE != NULL && is_ipl_type_dump() == false
* The state for all CPUs except the boot CPU needs to be collected
* with sigp stop-and-store-status. The kexec code or the boot-loader
* stored the registers of the boot CPU in the memory of the old system.
- * 4) kdump and the old kernel stored the CPU state
- * condition: OLDMEM_BASE != NULL && is_kdump_kernel()
- * This case does not exist for s390 anymore, setup_arch explicitly
- * deactivates the elfcorehdr= kernel parameter
+ *
+ * Note that the legacy kdump mode where the old kernel stored the CPU states
+ * does no longer exist: setup_arch() explicitly deactivates the elfcorehdr=
+ * kernel parameter. The is_kdump_kernel() implementation on s390 is independent
+ * of the elfcorehdr= parameter.
*/
static bool dump_available(void)
{
@@ -611,9 +605,7 @@ void __init smp_save_dump_ipl_cpu(void)
if (!dump_available())
return;
sa = save_area_alloc(true);
- regs = memblock_alloc(512, 8);
- if (!sa || !regs)
- panic("could not allocate memory for boot CPU save area\n");
+ regs = memblock_alloc_or_panic(512, 8);
copy_oldmem_kernel(regs, __LC_FPREGS_SAVE_AREA, 512);
save_area_add_regs(sa, regs);
memblock_free(regs, 512);
@@ -646,8 +638,6 @@ void __init smp_save_dump_secondary_cpus(void)
SIGP_CC_NOT_OPERATIONAL)
continue;
sa = save_area_alloc(false);
- if (!sa)
- panic("could not allocate memory for save area\n");
__pcpu_sigp_relax(addr, SIGP_STORE_STATUS_AT_ADDRESS, __pa(page));
save_area_add_regs(sa, page);
if (cpu_has_vx()) {
@@ -792,10 +782,7 @@ void __init smp_detect_cpus(void)
u16 address;
/* Get CPU information */
- info = memblock_alloc(sizeof(*info), 8);
- if (!info)
- panic("%s: Failed to allocate %zu bytes align=0x%x\n",
- __func__, sizeof(*info), 8);
+ info = memblock_alloc_or_panic(sizeof(*info), 8);
smp_get_core_info(info, 1);
/* Find boot CPU type */
if (sclp.has_core_type) {
@@ -814,6 +801,7 @@ void __init smp_detect_cpus(void)
mtid = boot_core_type ? sclp.mtid : sclp.mtid_cp;
mtid = (mtid < smp_max_threads) ? mtid : smp_max_threads - 1;
pcpu_set_smt(mtid);
+ cpu_smt_set_num_threads(smp_cpu_mtid + 1, smp_cpu_mtid + 1);
/* Print number of CPUs */
c_cpus = s_cpus = 0;
@@ -1011,7 +999,7 @@ static ssize_t cpu_configure_show(struct device *dev,
ssize_t count;
mutex_lock(&smp_cpu_state_mutex);
- count = sprintf(buf, "%d\n", per_cpu(pcpu_devices, dev->id).state);
+ count = sysfs_emit(buf, "%d\n", per_cpu(pcpu_devices, dev->id).state);
mutex_unlock(&smp_cpu_state_mutex);
return count;
}
@@ -1083,7 +1071,7 @@ static DEVICE_ATTR(configure, 0644, cpu_configure_show, cpu_configure_store);
static ssize_t show_cpu_address(struct device *dev,
struct device_attribute *attr, char *buf)
{
- return sprintf(buf, "%d\n", per_cpu(pcpu_devices, dev->id).address);
+ return sysfs_emit(buf, "%d\n", per_cpu(pcpu_devices, dev->id).address);
}
static DEVICE_ATTR(address, 0444, show_cpu_address, NULL);
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 9f59837d159e..b153a395f46d 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -9,6 +9,7 @@
#include <linux/stacktrace.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
+#include <asm/asm-offsets.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
#include <asm/kprobes.h>
@@ -151,7 +152,7 @@ void arch_stack_walk_user_common(stack_trace_consume_fn consume_entry, void *coo
break;
}
if (!store_ip(consume_entry, cookie, entry, perf, ip))
- return;
+ break;
first = false;
}
pagefault_enable();
diff --git a/arch/s390/kernel/sthyi.c b/arch/s390/kernel/sthyi.c
index 1cf2ad04f8e9..d40f0b983e74 100644
--- a/arch/s390/kernel/sthyi.c
+++ b/arch/s390/kernel/sthyi.c
@@ -17,6 +17,7 @@
#include <asm/ebcdic.h>
#include <asm/facility.h>
#include <asm/sthyi.h>
+#include <asm/asm.h>
#include "entry.h"
#define DED_WEIGHT 0xffff
@@ -425,13 +426,12 @@ static int sthyi(u64 vaddr, u64 *rc)
asm volatile(
".insn rre,0xB2560000,%[r1],%[r2]\n"
- "ipm %[cc]\n"
- "srl %[cc],28\n"
- : [cc] "=&d" (cc), [r2] "+&d" (r2.pair)
+ CC_IPM(cc)
+ : CC_OUT(cc, cc), [r2] "+&d" (r2.pair)
: [r1] "d" (r1.pair)
- : "memory", "cc");
+ : CC_CLOBBER_LIST("memory"));
*rc = r2.odd;
- return cc;
+ return CC_TRANSFORM(cc);
}
static int fill_dst(void *dst, u64 *rc)
diff --git a/arch/s390/kernel/syscall.c b/arch/s390/kernel/syscall.c
index 5ec28028315b..4fee74553ca2 100644
--- a/arch/s390/kernel/syscall.c
+++ b/arch/s390/kernel/syscall.c
@@ -12,6 +12,7 @@
* platform.
*/
+#include <linux/cpufeature.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/mm.h>
@@ -81,25 +82,35 @@ SYSCALL_DEFINE0(ni_syscall)
return -ENOSYS;
}
-static void do_syscall(struct pt_regs *regs)
+void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
{
unsigned long nr;
+ add_random_kstack_offset();
+ enter_from_user_mode(regs);
+ regs->psw = get_lowcore()->svc_old_psw;
+ regs->int_code = get_lowcore()->svc_int_code;
+ update_timer_sys();
+ if (cpu_has_bear())
+ current->thread.last_break = regs->last_break;
+ local_irq_enable();
+ regs->orig_gpr2 = regs->gprs[2];
+ if (unlikely(per_trap))
+ set_thread_flag(TIF_PER_TRAP);
+ regs->flags = 0;
+ set_pt_regs_flag(regs, PIF_SYSCALL);
nr = regs->int_code & 0xffff;
- if (!nr) {
+ if (likely(!nr)) {
nr = regs->gprs[1] & 0xffff;
regs->int_code &= ~0xffffUL;
regs->int_code |= nr;
}
-
regs->gprs[2] = nr;
-
if (nr == __NR_restart_syscall && !(current->restart_block.arch_data & 1)) {
regs->psw.addr = current->restart_block.arch_data;
current->restart_block.arch_data = 1;
}
nr = syscall_enter_from_user_mode_work(regs, nr);
-
/*
* In the s390 ptrace ABI, both the syscall number and the return value
* use gpr2. However, userspace puts the syscall number either in the
@@ -107,37 +118,11 @@ static void do_syscall(struct pt_regs *regs)
* work, the ptrace code sets PIF_SYSCALL_RET_SET, which is checked here
* and if set, the syscall will be skipped.
*/
-
if (unlikely(test_and_clear_pt_regs_flag(regs, PIF_SYSCALL_RET_SET)))
goto out;
regs->gprs[2] = -ENOSYS;
- if (likely(nr >= NR_syscalls))
- goto out;
- do {
+ if (likely(nr < NR_syscalls))
regs->gprs[2] = current->thread.sys_call_table[nr](regs);
- } while (test_and_clear_pt_regs_flag(regs, PIF_EXECVE_PGSTE_RESTART));
out:
- syscall_exit_to_user_mode_work(regs);
-}
-
-void noinstr __do_syscall(struct pt_regs *regs, int per_trap)
-{
- add_random_kstack_offset();
- enter_from_user_mode(regs);
- regs->psw = get_lowcore()->svc_old_psw;
- regs->int_code = get_lowcore()->svc_int_code;
- update_timer_sys();
- if (static_branch_likely(&cpu_has_bear))
- current->thread.last_break = regs->last_break;
-
- local_irq_enable();
- regs->orig_gpr2 = regs->gprs[2];
-
- if (per_trap)
- set_thread_flag(TIF_PER_TRAP);
-
- regs->flags = 0;
- set_pt_regs_flag(regs, PIF_SYSCALL);
- do_syscall(regs);
- exit_to_user_mode();
+ syscall_exit_to_user_mode(regs);
}
diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile
index 1bb78b9468e8..c5d958a09ff4 100644
--- a/arch/s390/kernel/syscalls/Makefile
+++ b/arch/s390/kernel/syscalls/Makefile
@@ -12,7 +12,7 @@ kapi-hdrs-y := $(kapi)/unistd_nr.h
uapi-hdrs-y := $(uapi)/unistd_32.h
uapi-hdrs-y += $(uapi)/unistd_64.h
-targets += $(addprefix ../../../,$(gen-y) $(kapi-hdrs-y) $(uapi-hdrs-y))
+targets += $(addprefix ../../../../,$(gen-y) $(kapi-hdrs-y) $(uapi-hdrs-y))
PHONY += kapi uapi
@@ -23,23 +23,26 @@ uapi: $(uapi-hdrs-y)
# Create output directory if not already present
$(shell mkdir -p $(uapi) $(kapi))
-filechk_syshdr = $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $<
+quiet_cmd_syshdr = SYSHDR $@
+ cmd_syshdr = $(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$@" < $< > $@
-filechk_sysnr = $(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) < $<
+quiet_cmd_sysnr = SYSNR $@
+ cmd_sysnr = $(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) < $< > $@
-filechk_syscalls = $(CONFIG_SHELL) '$(systbl)' -S < $<
+quiet_cmd_syscalls = SYSTBL $@
+ cmd_syscalls = $(CONFIG_SHELL) '$(systbl)' -S < $< > $@
syshdr_abi_unistd_32 := common,32
-$(uapi)/unistd_32.h: $(syscall) FORCE
- $(call filechk,syshdr,$@)
+$(uapi)/unistd_32.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,syshdr)
syshdr_abi_unistd_64 := common,64
-$(uapi)/unistd_64.h: $(syscall) FORCE
- $(call filechk,syshdr,$@)
+$(uapi)/unistd_64.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,syshdr)
-$(kapi)/syscall_table.h: $(syscall) FORCE
- $(call filechk,syscalls)
+$(kapi)/syscall_table.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,syscalls)
sysnr_abi_unistd_nr := common,32,64
-$(kapi)/unistd_nr.h: $(syscall) FORCE
- $(call filechk,sysnr)
+$(kapi)/unistd_nr.h: $(syscall) $(systbl) FORCE
+ $(call if_changed,sysnr)
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 01071182763e..a4569b96ef06 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -465,3 +465,8 @@
460 common lsm_set_self_attr sys_lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules sys_lsm_list_modules
462 common mseal sys_mseal sys_mseal
+463 common setxattrat sys_setxattrat sys_setxattrat
+464 common getxattrat sys_getxattrat sys_getxattrat
+465 common listxattrat sys_listxattrat sys_listxattrat
+466 common removexattrat sys_removexattrat sys_removexattrat
+467 common open_tree_attr sys_open_tree_attr sys_open_tree_attr
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 88055f58fbda..1ea84e942bd4 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -5,6 +5,7 @@
* Martin Schwidefsky <schwidefsky@de.ibm.com>,
*/
+#include <linux/cpufeature.h>
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
@@ -15,54 +16,17 @@
#include <linux/export.h>
#include <linux/slab.h>
#include <asm/asm-extable.h>
+#include <asm/machine.h>
#include <asm/ebcdic.h>
#include <asm/debug.h>
#include <asm/sysinfo.h>
#include <asm/cpcmd.h>
#include <asm/topology.h>
#include <asm/fpu.h>
+#include <asm/asm.h>
int topology_max_mnest;
-static inline int __stsi(void *sysinfo, int fc, int sel1, int sel2, int *lvl)
-{
- int r0 = (fc << 28) | sel1;
- int rc = 0;
-
- asm volatile(
- " lr 0,%[r0]\n"
- " lr 1,%[r1]\n"
- " stsi 0(%[sysinfo])\n"
- "0: jz 2f\n"
- "1: lhi %[rc],%[retval]\n"
- "2: lr %[r0],0\n"
- EX_TABLE(0b, 1b)
- : [r0] "+d" (r0), [rc] "+d" (rc)
- : [r1] "d" (sel2),
- [sysinfo] "a" (sysinfo),
- [retval] "K" (-EOPNOTSUPP)
- : "cc", "0", "1", "memory");
- *lvl = ((unsigned int) r0) >> 28;
- return rc;
-}
-
-/*
- * stsi - store system information
- *
- * Returns the current configuration level if function code 0 was specified.
- * Otherwise returns 0 on success or a negative value on error.
- */
-int stsi(void *sysinfo, int fc, int sel1, int sel2)
-{
- int lvl, rc;
-
- rc = __stsi(sysinfo, fc, sel1, sel2, &lvl);
- if (rc)
- return rc;
- return fc ? 0 : lvl;
-}
-EXPORT_SYMBOL(stsi);
-
#ifdef CONFIG_PROC_FS
static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
@@ -154,7 +118,7 @@ static void stsi_15_1_x(struct seq_file *m, struct sysinfo_15_1_x *info)
int i;
seq_putc(m, '\n');
- if (!MACHINE_HAS_TOPOLOGY)
+ if (!cpu_has_topology())
return;
if (stsi(info, 15, 1, topology_max_mnest))
return;
@@ -415,7 +379,7 @@ static struct service_level service_level_vm = {
static __init int create_proc_service_level(void)
{
proc_create_seq("service_levels", 0, NULL, &service_level_seq_ops);
- if (MACHINE_IS_VM)
+ if (machine_is_vm())
register_service_level(&service_level_vm);
return 0;
}
@@ -559,7 +523,7 @@ static __init int stsi_init_debugfs(void)
sf = &stsi_file[i];
debugfs_create_file(sf->name, 0400, stsi_root, NULL, sf->fops);
}
- if (IS_ENABLED(CONFIG_SCHED_TOPOLOGY) && MACHINE_HAS_TOPOLOGY) {
+ if (IS_ENABLED(CONFIG_SCHED_TOPOLOGY) && cpu_has_topology()) {
char link_to[10];
sprintf(link_to, "15_1_%d", topology_mnest_limit());
diff --git a/arch/s390/kernel/text_amode31.S b/arch/s390/kernel/text_amode31.S
index c0a70efa2426..26f2981aa09e 100644
--- a/arch/s390/kernel/text_amode31.S
+++ b/arch/s390/kernel/text_amode31.S
@@ -18,8 +18,7 @@
* affects a few functions that are not performance-relevant.
*/
.macro BR_EX_AMODE31_r14
- larl %r1,0f
- ex 0,0(%r1)
+ exrl 0,0f
j .
0: br %r14
.endm
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index b713effe0579..fed17d407a44 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -36,7 +36,6 @@
#include <linux/profile.h>
#include <linux/timex.h>
#include <linux/notifier.h>
-#include <linux/timekeeper_internal.h>
#include <linux/clockchips.h>
#include <linux/gfp.h>
#include <linux/kprobes.h>
@@ -55,10 +54,10 @@
#include <asm/cio.h>
#include "entry.h"
-union tod_clock tod_clock_base __section(".data");
+union tod_clock __bootdata_preserved(tod_clock_base);
EXPORT_SYMBOL_GPL(tod_clock_base);
-u64 clock_comparator_max = -1ULL;
+u64 __bootdata_preserved(clock_comparator_max);
EXPORT_SYMBOL_GPL(clock_comparator_max);
static DEFINE_PER_CPU(struct clock_event_device, comparators);
@@ -80,12 +79,10 @@ void __init time_early_init(void)
{
struct ptff_qto qto;
struct ptff_qui qui;
- int cs;
/* Initialize TOD steering parameters */
tod_steering_end = tod_clock_base.tod;
- for (cs = 0; cs < CS_BASES; cs++)
- vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
+ vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
if (!test_facility(28))
return;
@@ -255,6 +252,7 @@ static struct clocksource clocksource_tod = {
.shift = 24,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.vdso_clock_mode = VDSO_CLOCKMODE_TOD,
+ .id = CSID_S390_TOD,
};
struct clocksource * __init clocksource_default_clock(void)
@@ -373,7 +371,6 @@ static void clock_sync_global(long delta)
{
unsigned long now, adj;
struct ptff_qto qto;
- int cs;
/* Fixup the monotonic sched clock. */
tod_clock_base.eitod += delta;
@@ -389,10 +386,8 @@ static void clock_sync_global(long delta)
panic("TOD clock sync offset %li is too large to drift\n",
tod_steering_delta);
tod_steering_end = now + (abs(tod_steering_delta) << 15);
- for (cs = 0; cs < CS_BASES; cs++) {
- vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
- vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
- }
+ vdso_k_time_data->arch_data.tod_steering_end = tod_steering_end;
+ vdso_k_time_data->arch_data.tod_steering_delta = tod_steering_delta;
/* Update LPAR offset. */
if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
@@ -468,6 +463,12 @@ static void __init stp_reset(void)
}
}
+bool stp_enabled(void)
+{
+ return test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags) && stp_online;
+}
+EXPORT_SYMBOL(stp_enabled);
+
static void stp_timeout(struct timer_list *unused)
{
queue_work(time_sync_wq, &stp_work);
@@ -656,12 +657,12 @@ static void stp_check_leap(void)
if (ret < 0)
pr_err("failed to set leap second flags\n");
/* arm Timer to clear leap second flags */
- mod_timer(&stp_timer, jiffies + msecs_to_jiffies(14400 * MSEC_PER_SEC));
+ mod_timer(&stp_timer, jiffies + secs_to_jiffies(14400));
} else {
/* The day the leap second is scheduled for hasn't been reached. Retry
* in one hour.
*/
- mod_timer(&stp_timer, jiffies + msecs_to_jiffies(3600 * MSEC_PER_SEC));
+ mod_timer(&stp_timer, jiffies + secs_to_jiffies(3600));
}
}
@@ -679,7 +680,7 @@ static void stp_work_fn(struct work_struct *work)
if (!stp_online) {
chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000, NULL);
- del_timer_sync(&stp_timer);
+ timer_delete_sync(&stp_timer);
goto out_unlock;
}
@@ -729,8 +730,8 @@ static ssize_t ctn_id_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%016lx\n",
- *(unsigned long *) stp_info.ctnid);
+ ret = sysfs_emit(buf, "%016lx\n",
+ *(unsigned long *)stp_info.ctnid);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -745,7 +746,7 @@ static ssize_t ctn_type_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%i\n", stp_info.ctn);
+ ret = sysfs_emit(buf, "%i\n", stp_info.ctn);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -760,7 +761,7 @@ static ssize_t dst_offset_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid() && (stp_info.vbits & 0x2000))
- ret = sprintf(buf, "%i\n", (int)(s16) stp_info.dsto);
+ ret = sysfs_emit(buf, "%i\n", (int)(s16)stp_info.dsto);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -775,7 +776,7 @@ static ssize_t leap_seconds_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid() && (stp_info.vbits & 0x8000))
- ret = sprintf(buf, "%i\n", (int)(s16) stp_info.leaps);
+ ret = sysfs_emit(buf, "%i\n", (int)(s16)stp_info.leaps);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -801,11 +802,11 @@ static ssize_t leap_seconds_scheduled_show(struct device *dev,
return ret;
if (!stzi.lsoib.p)
- return sprintf(buf, "0,0\n");
+ return sysfs_emit(buf, "0,0\n");
- return sprintf(buf, "%lu,%d\n",
- tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
- stzi.lsoib.nlso - stzi.lsoib.also);
+ return sysfs_emit(buf, "%lu,%d\n",
+ tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
+ stzi.lsoib.nlso - stzi.lsoib.also);
}
static DEVICE_ATTR_RO(leap_seconds_scheduled);
@@ -818,7 +819,7 @@ static ssize_t stratum_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%i\n", (int)(s16) stp_info.stratum);
+ ret = sysfs_emit(buf, "%i\n", (int)(s16)stp_info.stratum);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -833,7 +834,7 @@ static ssize_t time_offset_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid() && (stp_info.vbits & 0x0800))
- ret = sprintf(buf, "%i\n", (int) stp_info.tto);
+ ret = sysfs_emit(buf, "%i\n", (int)stp_info.tto);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -848,7 +849,7 @@ static ssize_t time_zone_offset_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid() && (stp_info.vbits & 0x4000))
- ret = sprintf(buf, "%i\n", (int)(s16) stp_info.tzo);
+ ret = sysfs_emit(buf, "%i\n", (int)(s16)stp_info.tzo);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -863,7 +864,7 @@ static ssize_t timing_mode_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%i\n", stp_info.tmd);
+ ret = sysfs_emit(buf, "%i\n", stp_info.tmd);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -878,7 +879,7 @@ static ssize_t timing_state_show(struct device *dev,
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%i\n", stp_info.tst);
+ ret = sysfs_emit(buf, "%i\n", stp_info.tst);
mutex_unlock(&stp_mutex);
return ret;
}
@@ -889,7 +890,7 @@ static ssize_t online_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- return sprintf(buf, "%i\n", stp_online);
+ return sysfs_emit(buf, "%i\n", stp_online);
}
static ssize_t online_store(struct device *dev,
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 813e5da9a973..3df048e190b1 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -6,6 +6,7 @@
#define KMSG_COMPONENT "cpu"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <linux/cpufeature.h>
#include <linux/workqueue.h>
#include <linux/memblock.h>
#include <linux/uaccess.h>
@@ -26,6 +27,7 @@
#include <linux/node.h>
#include <asm/hiperdispatch.h>
#include <asm/sysinfo.h>
+#include <asm/asm.h>
#define PTF_HORIZONTAL (0UL)
#define PTF_VERTICAL (1UL)
@@ -224,22 +226,22 @@ static void topology_update_polarization_simple(void)
static int ptf(unsigned long fc)
{
- int rc;
+ int cc;
asm volatile(
- " .insn rre,0xb9a20000,%1,%1\n"
- " ipm %0\n"
- " srl %0,28\n"
- : "=d" (rc)
- : "d" (fc) : "cc");
- return rc;
+ " .insn rre,0xb9a20000,%[fc],%[fc]\n"
+ CC_IPM(cc)
+ : CC_OUT(cc, cc)
+ : [fc] "d" (fc)
+ : CC_CLOBBER);
+ return CC_TRANSFORM(cc);
}
int topology_set_cpu_management(int fc)
{
int cpu, rc;
- if (!MACHINE_HAS_TOPOLOGY)
+ if (!cpu_has_topology())
return -EOPNOTSUPP;
if (fc)
rc = ptf(PTF_VERTICAL);
@@ -314,13 +316,13 @@ static int __arch_update_cpu_topology(void)
hd_status = 0;
rc = 0;
mutex_lock(&smp_cpu_state_mutex);
- if (MACHINE_HAS_TOPOLOGY) {
+ if (cpu_has_topology()) {
rc = 1;
store_topology(info);
tl_to_masks(info);
}
update_cpu_masks();
- if (!MACHINE_HAS_TOPOLOGY)
+ if (!cpu_has_topology())
topology_update_polarization_simple();
if (cpu_management == 1)
hd_status = hd_enable_hiperdispatch();
@@ -370,12 +372,12 @@ static void set_topology_timer(void)
if (atomic_add_unless(&topology_poll, -1, 0))
mod_timer(&topology_timer, jiffies + msecs_to_jiffies(100));
else
- mod_timer(&topology_timer, jiffies + msecs_to_jiffies(60 * MSEC_PER_SEC));
+ mod_timer(&topology_timer, jiffies + secs_to_jiffies(60));
}
void topology_expect_change(void)
{
- if (!MACHINE_HAS_TOPOLOGY)
+ if (!cpu_has_topology())
return;
/* This is racy, but it doesn't matter since it is just a heuristic.
* Worst case is that we poll in a higher frequency for a bit longer.
@@ -412,7 +414,7 @@ static ssize_t dispatching_show(struct device *dev,
ssize_t count;
mutex_lock(&smp_cpu_state_mutex);
- count = sprintf(buf, "%d\n", cpu_management);
+ count = sysfs_emit(buf, "%d\n", cpu_management);
mutex_unlock(&smp_cpu_state_mutex);
return count;
}
@@ -443,19 +445,19 @@ static ssize_t cpu_polarization_show(struct device *dev,
mutex_lock(&smp_cpu_state_mutex);
switch (smp_cpu_get_polarization(cpu)) {
case POLARIZATION_HRZ:
- count = sprintf(buf, "horizontal\n");
+ count = sysfs_emit(buf, "horizontal\n");
break;
case POLARIZATION_VL:
- count = sprintf(buf, "vertical:low\n");
+ count = sysfs_emit(buf, "vertical:low\n");
break;
case POLARIZATION_VM:
- count = sprintf(buf, "vertical:medium\n");
+ count = sysfs_emit(buf, "vertical:medium\n");
break;
case POLARIZATION_VH:
- count = sprintf(buf, "vertical:high\n");
+ count = sysfs_emit(buf, "vertical:high\n");
break;
default:
- count = sprintf(buf, "unknown\n");
+ count = sysfs_emit(buf, "unknown\n");
break;
}
mutex_unlock(&smp_cpu_state_mutex);
@@ -479,7 +481,7 @@ static ssize_t cpu_dedicated_show(struct device *dev,
ssize_t count;
mutex_lock(&smp_cpu_state_mutex);
- count = sprintf(buf, "%d\n", topology_cpu_dedicated(cpu));
+ count = sysfs_emit(buf, "%d\n", topology_cpu_dedicated(cpu));
mutex_unlock(&smp_cpu_state_mutex);
return count;
}
@@ -499,7 +501,7 @@ int topology_cpu_init(struct cpu *cpu)
int rc;
rc = sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group);
- if (rc || !MACHINE_HAS_TOPOLOGY)
+ if (rc || !cpu_has_topology())
return rc;
rc = sysfs_create_group(&cpu->dev.kobj, &topology_extra_cpu_attr_group);
if (rc)
@@ -547,33 +549,38 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info,
nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i];
nr_masks = max(nr_masks, 1);
for (i = 0; i < nr_masks; i++) {
- mask->next = memblock_alloc(sizeof(*mask->next), 8);
- if (!mask->next)
- panic("%s: Failed to allocate %zu bytes align=0x%x\n",
- __func__, sizeof(*mask->next), 8);
+ mask->next = memblock_alloc_or_panic(sizeof(*mask->next), 8);
mask = mask->next;
}
}
+static int __init detect_polarization(union topology_entry *tle)
+{
+ struct topology_core *tl_core;
+
+ while (tle->nl)
+ tle = next_tle(tle);
+ tl_core = (struct topology_core *)tle;
+ return tl_core->pp != POLARIZATION_HRZ;
+}
+
void __init topology_init_early(void)
{
struct sysinfo_15_1_x *info;
set_sched_topology(s390_topology);
if (topology_mode == TOPOLOGY_MODE_UNINITIALIZED) {
- if (MACHINE_HAS_TOPOLOGY)
+ if (cpu_has_topology())
topology_mode = TOPOLOGY_MODE_HW;
else
topology_mode = TOPOLOGY_MODE_SINGLE;
}
- if (!MACHINE_HAS_TOPOLOGY)
+ if (!cpu_has_topology())
goto out;
- tl_info = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
- if (!tl_info)
- panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
- __func__, PAGE_SIZE, PAGE_SIZE);
+ tl_info = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE);
info = tl_info;
store_topology(info);
+ cpu_management = detect_polarization(info->tle);
pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n",
info->mag[0], info->mag[1], info->mag[2], info->mag[3],
info->mag[4], info->mag[5], info->mnest);
@@ -590,7 +597,7 @@ static inline int topology_get_mode(int enabled)
{
if (!enabled)
return TOPOLOGY_MODE_SINGLE;
- return MACHINE_HAS_TOPOLOGY ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE;
+ return cpu_has_topology() ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE;
}
static inline int topology_is_enabled(void)
@@ -661,7 +668,7 @@ static int polarization_ctl_handler(const struct ctl_table *ctl, int write,
return set_polarization(polarization);
}
-static struct ctl_table topology_ctl_table[] = {
+static const struct ctl_table topology_ctl_table[] = {
{
.procname = "topology",
.mode = 0644,
@@ -680,7 +687,7 @@ static int __init topology_init(void)
int rc = 0;
timer_setup(&topology_timer, topology_timer_fn, TIMER_DEFERRABLE);
- if (MACHINE_HAS_TOPOLOGY)
+ if (cpu_has_topology())
set_topology_timer();
else
topology_update_polarization_simple();
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 160b2acba8db..19687dab32f7 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -3,18 +3,13 @@
* S390 version
* Copyright IBM Corp. 1999, 2000
* Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
- * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
+ * Denis Joseph Barrow (djbarrow@de.ibm.com,barrow_dj@yahoo.com),
*
* Derived from "arch/i386/kernel/traps.c"
* Copyright (C) 1991, 1992 Linus Torvalds
*/
-/*
- * 'Traps.c' handles hardware traps and faults after we have saved some
- * state in 'asm.s'.
- */
-#include "asm/irqflags.h"
-#include "asm/ptrace.h"
+#include <linux/cpufeature.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/randomize_kstack.h>
@@ -29,8 +24,11 @@
#include <linux/entry-common.h>
#include <linux/kmsan.h>
#include <asm/asm-extable.h>
+#include <asm/irqflags.h>
+#include <asm/ptrace.h>
#include <asm/vtime.h>
#include <asm/fpu.h>
+#include <asm/fault.h>
#include "entry.h"
static inline void __user *get_trap_ip(struct pt_regs *regs)
@@ -41,7 +39,7 @@ static inline void __user *get_trap_ip(struct pt_regs *regs)
address = current->thread.trap_tdb.data[3];
else
address = regs->psw.addr;
- return (void __user *) (address - (regs->int_code >> 16));
+ return (void __user *)(address - (regs->int_code >> 16));
}
#ifdef CONFIG_GENERIC_BUG
@@ -56,16 +54,15 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
if (user_mode(regs)) {
force_sig_fault(si_signo, si_code, get_trap_ip(regs));
report_user_fault(regs, si_signo, 0);
- } else {
+ } else {
if (!fixup_exception(regs))
die(regs, str);
- }
+ }
}
static void do_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
{
- if (notify_die(DIE_TRAP, str, regs, 0,
- regs->int_code, si_signo) == NOTIFY_STOP)
+ if (notify_die(DIE_TRAP, str, regs, 0, regs->int_code, si_signo) == NOTIFY_STOP)
return;
do_report_trap(regs, si_signo, si_code, str);
}
@@ -77,8 +74,7 @@ void do_per_trap(struct pt_regs *regs)
return;
if (!current->ptrace)
return;
- force_sig_fault(SIGTRAP, TRAP_HWBKPT,
- (void __force __user *) current->thread.per_event.address);
+ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __force __user *)current->thread.per_event.address);
}
NOKPROBE_SYMBOL(do_per_trap);
@@ -97,36 +93,25 @@ static void name(struct pt_regs *regs) \
do_trap(regs, signr, sicode, str); \
}
-DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR,
- "addressing exception")
-DO_ERROR_INFO(execute_exception, SIGILL, ILL_ILLOPN,
- "execute exception")
-DO_ERROR_INFO(divide_exception, SIGFPE, FPE_INTDIV,
- "fixpoint divide exception")
-DO_ERROR_INFO(overflow_exception, SIGFPE, FPE_INTOVF,
- "fixpoint overflow exception")
-DO_ERROR_INFO(hfp_overflow_exception, SIGFPE, FPE_FLTOVF,
- "HFP overflow exception")
-DO_ERROR_INFO(hfp_underflow_exception, SIGFPE, FPE_FLTUND,
- "HFP underflow exception")
-DO_ERROR_INFO(hfp_significance_exception, SIGFPE, FPE_FLTRES,
- "HFP significance exception")
-DO_ERROR_INFO(hfp_divide_exception, SIGFPE, FPE_FLTDIV,
- "HFP divide exception")
-DO_ERROR_INFO(hfp_sqrt_exception, SIGFPE, FPE_FLTINV,
- "HFP square root exception")
-DO_ERROR_INFO(operand_exception, SIGILL, ILL_ILLOPN,
- "operand exception")
-DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC,
- "privileged operation")
-DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN,
- "special operation exception")
-DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN,
- "transaction constraint exception")
+DO_ERROR_INFO(addressing_exception, SIGILL, ILL_ILLADR, "addressing exception")
+DO_ERROR_INFO(divide_exception, SIGFPE, FPE_INTDIV, "fixpoint divide exception")
+DO_ERROR_INFO(execute_exception, SIGILL, ILL_ILLOPN, "execute exception")
+DO_ERROR_INFO(hfp_divide_exception, SIGFPE, FPE_FLTDIV, "HFP divide exception")
+DO_ERROR_INFO(hfp_overflow_exception, SIGFPE, FPE_FLTOVF, "HFP overflow exception")
+DO_ERROR_INFO(hfp_significance_exception, SIGFPE, FPE_FLTRES, "HFP significance exception")
+DO_ERROR_INFO(hfp_sqrt_exception, SIGFPE, FPE_FLTINV, "HFP square root exception")
+DO_ERROR_INFO(hfp_underflow_exception, SIGFPE, FPE_FLTUND, "HFP underflow exception")
+DO_ERROR_INFO(operand_exception, SIGILL, ILL_ILLOPN, "operand exception")
+DO_ERROR_INFO(overflow_exception, SIGFPE, FPE_INTOVF, "fixpoint overflow exception")
+DO_ERROR_INFO(privileged_op, SIGILL, ILL_PRVOPC, "privileged operation")
+DO_ERROR_INFO(special_op_exception, SIGILL, ILL_ILLOPN, "special operation exception")
+DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN, "specification exception");
+DO_ERROR_INFO(transaction_exception, SIGILL, ILL_ILLOPN, "transaction constraint exception")
static inline void do_fp_trap(struct pt_regs *regs, __u32 fpc)
{
int si_code = 0;
+
/* FPC[2] is Data Exception Code */
if ((fpc & 0x00000300) == 0) {
/* bits 6 and 7 of DXC are 0 iff IEEE exception */
@@ -152,36 +137,35 @@ static void translation_specification_exception(struct pt_regs *regs)
static void illegal_op(struct pt_regs *regs)
{
- __u8 opcode[6];
- __u16 __user *location;
int is_uprobe_insn = 0;
+ u16 __user *location;
int signal = 0;
+ u16 opcode;
location = get_trap_ip(regs);
-
if (user_mode(regs)) {
- if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
+ if (get_user(opcode, location))
return;
- if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
+ if (opcode == S390_BREAKPOINT_U16) {
if (current->ptrace)
force_sig_fault(SIGTRAP, TRAP_BRKPT, location);
else
signal = SIGILL;
#ifdef CONFIG_UPROBES
- } else if (*((__u16 *) opcode) == UPROBE_SWBP_INSN) {
+ } else if (opcode == UPROBE_SWBP_INSN) {
is_uprobe_insn = 1;
#endif
- } else
+ } else {
signal = SIGILL;
+ }
}
/*
- * We got either an illegal op in kernel mode, or user space trapped
+ * This is either an illegal op in kernel mode, or user space trapped
* on a uprobes illegal instruction. See if kprobes or uprobes picks
* it up. If not, SIGILL.
*/
if (is_uprobe_insn || !user_mode(regs)) {
- if (notify_die(DIE_BPT, "bpt", regs, 0,
- 3, SIGTRAP) != NOTIFY_STOP)
+ if (notify_die(DIE_BPT, "bpt", regs, 0, 3, SIGTRAP) != NOTIFY_STOP)
signal = SIGILL;
}
if (signal)
@@ -189,18 +173,10 @@ static void illegal_op(struct pt_regs *regs)
}
NOKPROBE_SYMBOL(illegal_op);
-DO_ERROR_INFO(specification_exception, SIGILL, ILL_ILLOPN,
- "specification exception");
-
static void vector_exception(struct pt_regs *regs)
{
int si_code, vic;
- if (!cpu_has_vx()) {
- do_trap(regs, SIGILL, ILL_ILLOPN, "illegal operation");
- return;
- }
-
/* get vector interrupt code from fpc */
save_user_fpu_regs();
vic = (current->thread.ufpu.fpc & 0xf00) >> 8;
@@ -248,7 +224,6 @@ static void monitor_event_exception(struct pt_regs *regs)
{
if (user_mode(regs))
return;
-
switch (report_bug(regs->psw.addr - (regs->int_code >> 16), regs)) {
case BUG_TRAP_TYPE_NONE:
fixup_exception(regs);
@@ -261,7 +236,7 @@ static void monitor_event_exception(struct pt_regs *regs)
}
}
-void kernel_stack_overflow(struct pt_regs *regs)
+void kernel_stack_invalid(struct pt_regs *regs)
{
/*
* Normally regs are unpoisoned by the generic entry code, but
@@ -269,12 +244,12 @@ void kernel_stack_overflow(struct pt_regs *regs)
*/
kmsan_unpoison_entry_regs(regs);
bust_spinlocks(1);
- printk("Kernel stack overflow.\n");
+ pr_emerg("Kernel stack pointer invalid\n");
show_regs(regs);
bust_spinlocks(0);
- panic("Corrupt kernel stack, can't continue.");
+ panic("Invalid kernel stack pointer, cannot continue");
}
-NOKPROBE_SYMBOL(kernel_stack_overflow);
+NOKPROBE_SYMBOL(kernel_stack_invalid);
static void __init test_monitor_call(void)
{
@@ -282,12 +257,12 @@ static void __init test_monitor_call(void)
if (!IS_ENABLED(CONFIG_BUG))
return;
- asm volatile(
+ asm_inline volatile(
" mc 0,0\n"
- "0: xgr %0,%0\n"
+ "0: lhi %[val],0\n"
"1:\n"
- EX_TABLE(0b,1b)
- : "+d" (val));
+ EX_TABLE(0b, 1b)
+ : [val] "+d" (val));
if (!val)
panic("Monitor call doesn't work!\n");
}
@@ -317,26 +292,36 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
struct lowcore *lc = get_lowcore();
irqentry_state_t state;
unsigned int trapnr;
+ union teid teid;
+ teid.val = lc->trans_exc_code;
regs->int_code = lc->pgm_int_code;
- regs->int_parm_long = lc->trans_exc_code;
-
+ regs->int_parm_long = teid.val;
+ /*
+ * In case of a guest fault, short-circuit the fault handler and return.
+ * This way the sie64a() function will return 0; fault address and
+ * other relevant bits are saved in current->thread.gmap_teid, and
+ * the fault number in current->thread.gmap_int_code. KVM will be
+ * able to use this information to handle the fault.
+ */
+ if (test_pt_regs_flag(regs, PIF_GUEST_FAULT)) {
+ current->thread.gmap_teid.val = regs->int_parm_long;
+ current->thread.gmap_int_code = regs->int_code & 0xffff;
+ return;
+ }
state = irqentry_enter(regs);
-
if (user_mode(regs)) {
update_timer_sys();
- if (!static_branch_likely(&cpu_has_bear)) {
+ if (!cpu_has_bear()) {
if (regs->last_break < 4096)
regs->last_break = 1;
}
current->thread.last_break = regs->last_break;
}
-
if (lc->pgm_code & 0x0200) {
/* transaction abort */
current->thread.trap_tdb = lc->pgm_tdb;
}
-
if (lc->pgm_code & PGM_INT_CODE_PER) {
if (user_mode(regs)) {
struct per_event *ev = &current->thread.per_event;
@@ -352,11 +337,9 @@ void noinstr __do_pgm_check(struct pt_regs *regs)
goto out;
}
}
-
if (!irqs_disabled_flags(regs->psw.mask))
trace_hardirqs_on();
__arch_local_irq_ssm(regs->psw.mask & ~PSW_MASK_PER);
-
trapnr = regs->int_code & PGM_INT_CODE_MASK;
if (trapnr)
pgm_check_table[trapnr](regs);
@@ -408,8 +391,8 @@ static void (*pgm_check_table[128])(struct pt_regs *regs) = {
[0x3b] = do_dat_exception,
[0x3c] = default_trap_handler,
[0x3d] = do_secure_storage_access,
- [0x3e] = do_non_secure_storage_access,
- [0x3f] = do_secure_storage_violation,
+ [0x3e] = default_trap_handler,
+ [0x3f] = default_trap_handler,
[0x40] = monitor_event_exception,
[0x41 ... 0x7f] = default_trap_handler,
};
@@ -420,5 +403,3 @@ static void (*pgm_check_table[128])(struct pt_regs *regs) = {
__stringify(default_trap_handler))
COND_TRAP(do_secure_storage_access);
-COND_TRAP(do_non_secure_storage_access);
-COND_TRAP(do_secure_storage_violation);
diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
index 9646f773208a..b99478e84da4 100644
--- a/arch/s390/kernel/uv.c
+++ b/arch/s390/kernel/uv.c
@@ -2,7 +2,7 @@
/*
* Common Ultravisor functions and initialization
*
- * Copyright IBM Corp. 2019, 2020
+ * Copyright IBM Corp. 2019, 2024
*/
#define KMSG_COMPONENT "prot_virt"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
@@ -15,23 +15,11 @@
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/pagewalk.h>
+#include <linux/backing-dev.h>
#include <asm/facility.h>
#include <asm/sections.h>
#include <asm/uv.h>
-#if !IS_ENABLED(CONFIG_KVM)
-unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
-{
- return 0;
-}
-
-int gmap_fault(struct gmap *gmap, unsigned long gaddr,
- unsigned int fault_flags)
-{
- return 0;
-}
-#endif
-
/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
int __bootdata_preserved(prot_virt_guest);
EXPORT_SYMBOL(prot_virt_guest);
@@ -148,7 +136,7 @@ int uv_destroy_folio(struct folio *folio)
{
int rc;
- /* See gmap_make_secure(): large folios cannot be secure */
+ /* Large folios cannot be secure */
if (unlikely(folio_test_large(folio)))
return 0;
@@ -159,6 +147,7 @@ int uv_destroy_folio(struct folio *folio)
folio_put(folio);
return rc;
}
+EXPORT_SYMBOL(uv_destroy_folio);
/*
* The present PTE still indirectly holds a folio reference through the mapping.
@@ -175,7 +164,7 @@ int uv_destroy_pte(pte_t pte)
*
* @paddr: Absolute host address of page to be exported
*/
-static int uv_convert_from_secure(unsigned long paddr)
+int uv_convert_from_secure(unsigned long paddr)
{
struct uv_cb_cfs uvcb = {
.header.cmd = UVC_CMD_CONV_FROM_SEC_STOR,
@@ -187,15 +176,16 @@ static int uv_convert_from_secure(unsigned long paddr)
return -EINVAL;
return 0;
}
+EXPORT_SYMBOL_GPL(uv_convert_from_secure);
/*
* The caller must already hold a reference to the folio.
*/
-static int uv_convert_from_secure_folio(struct folio *folio)
+int uv_convert_from_secure_folio(struct folio *folio)
{
int rc;
- /* See gmap_make_secure(): large folios cannot be secure */
+ /* Large folios cannot be secure */
if (unlikely(folio_test_large(folio)))
return 0;
@@ -206,6 +196,7 @@ static int uv_convert_from_secure_folio(struct folio *folio)
folio_put(folio);
return rc;
}
+EXPORT_SYMBOL_GPL(uv_convert_from_secure_folio);
/*
* The present PTE still indirectly holds a folio reference through the mapping.
@@ -216,6 +207,39 @@ int uv_convert_from_secure_pte(pte_t pte)
return uv_convert_from_secure_folio(pfn_folio(pte_pfn(pte)));
}
+/**
+ * should_export_before_import - Determine whether an export is needed
+ * before an import-like operation
+ * @uvcb: the Ultravisor control block of the UVC to be performed
+ * @mm: the mm of the process
+ *
+ * Returns whether an export is needed before every import-like operation.
+ * This is needed for shared pages, which don't trigger a secure storage
+ * exception when accessed from a different guest.
+ *
+ * Although considered as one, the Unpin Page UVC is not an actual import,
+ * so it is not affected.
+ *
+ * No export is needed also when there is only one protected VM, because the
+ * page cannot belong to the wrong VM in that case (there is no "other VM"
+ * it can belong to).
+ *
+ * Return: true if an export is needed before every import, otherwise false.
+ */
+static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+{
+ /*
+ * The misc feature indicates, among other things, that importing a
+ * shared page from a different protected VM will automatically also
+ * transfer its ownership.
+ */
+ if (uv_has_feature(BIT_UV_FEAT_MISC))
+ return false;
+ if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
+ return false;
+ return atomic_read(&mm->context.protected_count) > 1;
+}
+
/*
* Calculate the expected ref_count for a folio that would otherwise have no
* further pins. This was cribbed from similar functions in other places in
@@ -237,13 +261,31 @@ static int expected_folio_refs(struct folio *folio)
return res;
}
-static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
+/**
+ * __make_folio_secure() - make a folio secure
+ * @folio: the folio to make secure
+ * @uvcb: the uvcb that describes the UVC to be used
+ *
+ * The folio @folio will be made secure if possible, @uvcb will be passed
+ * as-is to the UVC.
+ *
+ * Return: 0 on success;
+ * -EBUSY if the folio is in writeback or has too many references;
+ * -EAGAIN if the UVC needs to be attempted again;
+ * -ENXIO if the address is not mapped;
+ * -EINVAL if the UVC failed for other reasons.
+ *
+ * Context: The caller must hold exactly one extra reference on the folio
+ * (it's the same logic as split_folio()), and the folio must be
+ * locked.
+ */
+static int __make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
{
int expected, cc = 0;
if (folio_test_writeback(folio))
- return -EAGAIN;
- expected = expected_folio_refs(folio);
+ return -EBUSY;
+ expected = expected_folio_refs(folio) + 1;
if (!folio_ref_freeze(folio, expected))
return -EBUSY;
set_bit(PG_arch_1, &folio->flags);
@@ -268,262 +310,167 @@ static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
}
-/**
- * should_export_before_import - Determine whether an export is needed
- * before an import-like operation
- * @uvcb: the Ultravisor control block of the UVC to be performed
- * @mm: the mm of the process
- *
- * Returns whether an export is needed before every import-like operation.
- * This is needed for shared pages, which don't trigger a secure storage
- * exception when accessed from a different guest.
- *
- * Although considered as one, the Unpin Page UVC is not an actual import,
- * so it is not affected.
- *
- * No export is needed also when there is only one protected VM, because the
- * page cannot belong to the wrong VM in that case (there is no "other VM"
- * it can belong to).
- *
- * Return: true if an export is needed before every import, otherwise false.
- */
-static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
+static int make_folio_secure(struct mm_struct *mm, struct folio *folio, struct uv_cb_header *uvcb)
{
- /*
- * The misc feature indicates, among other things, that importing a
- * shared page from a different protected VM will automatically also
- * transfer its ownership.
- */
- if (uv_has_feature(BIT_UV_FEAT_MISC))
- return false;
- if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
- return false;
- return atomic_read(&mm->context.protected_count) > 1;
-}
+ int rc;
-/*
- * Drain LRU caches: the local one on first invocation and the ones of all
- * CPUs on successive invocations. Returns "true" on the first invocation.
- */
-static bool drain_lru(bool *drain_lru_called)
-{
- /*
- * If we have tried a local drain and the folio refcount
- * still does not match our expected safe value, try with a
- * system wide drain. This is needed if the pagevecs holding
- * the page are on a different CPU.
- */
- if (*drain_lru_called) {
- lru_add_drain_all();
- /* We give up here, don't retry immediately. */
- return false;
- }
- /*
- * We are here if the folio refcount does not match the
- * expected safe value. The main culprits are usually
- * pagevecs. With lru_add_drain() we drain the pagevecs
- * on the local CPU so that hopefully the refcount will
- * reach the expected safe value.
- */
- lru_add_drain();
- *drain_lru_called = true;
- /* The caller should try again immediately */
- return true;
+ if (!folio_trylock(folio))
+ return -EAGAIN;
+ if (should_export_before_import(uvcb, mm))
+ uv_convert_from_secure(folio_to_phys(folio));
+ rc = __make_folio_secure(folio, uvcb);
+ folio_unlock(folio);
+
+ return rc;
}
-/*
- * Requests the Ultravisor to make a page accessible to a guest.
- * If it's brought in the first time, it will be cleared. If
- * it has been exported before, it will be decrypted and integrity
- * checked.
+/**
+ * s390_wiggle_split_folio() - try to drain extra references to a folio and
+ * split the folio if it is large.
+ * @mm: the mm containing the folio to work on
+ * @folio: the folio
+ *
+ * Context: Must be called while holding an extra reference to the folio;
+ * the mm lock should not be held.
+ * Return: 0 if the operation was successful;
+ * -EAGAIN if splitting the large folio was not successful,
+ * but another attempt can be made;
+ * -EINVAL in case of other folio splitting errors. See split_folio().
*/
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
+static int s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio)
{
- struct vm_area_struct *vma;
- bool drain_lru_called = false;
- spinlock_t *ptelock;
- unsigned long uaddr;
- struct folio *folio;
- pte_t *ptep;
- int rc;
+ int rc, tried_splits;
-again:
- rc = -EFAULT;
- mmap_read_lock(gmap->mm);
+ lockdep_assert_not_held(&mm->mmap_lock);
+ folio_wait_writeback(folio);
+ lru_add_drain_all();
- uaddr = __gmap_translate(gmap, gaddr);
- if (IS_ERR_VALUE(uaddr))
- goto out;
- vma = vma_lookup(gmap->mm, uaddr);
- if (!vma)
- goto out;
- /*
- * Secure pages cannot be huge and userspace should not combine both.
- * In case userspace does it anyway this will result in an -EFAULT for
- * the unpack. The guest is thus never reaching secure mode. If
- * userspace is playing dirty tricky with mapping huge pages later
- * on this will result in a segmentation fault.
- */
- if (is_vm_hugetlb_page(vma))
- goto out;
-
- rc = -ENXIO;
- ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
- if (!ptep)
- goto out;
- if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
- folio = page_folio(pte_page(*ptep));
- rc = -EAGAIN;
- if (folio_test_large(folio)) {
- rc = -E2BIG;
- } else if (folio_trylock(folio)) {
- if (should_export_before_import(uvcb, gmap->mm))
- uv_convert_from_secure(PFN_PHYS(folio_pfn(folio)));
- rc = make_folio_secure(folio, uvcb);
+ if (!folio_test_large(folio))
+ return 0;
+
+ for (tried_splits = 0; tried_splits < 2; tried_splits++) {
+ struct address_space *mapping;
+ loff_t lstart, lend;
+ struct inode *inode;
+
+ folio_lock(folio);
+ rc = split_folio(folio);
+ if (rc != -EBUSY) {
folio_unlock(folio);
+ return rc;
}
/*
- * Once we drop the PTL, the folio may get unmapped and
- * freed immediately. We need a temporary reference.
+ * Splitting with -EBUSY can fail for various reasons, but we
+ * have to handle one case explicitly for now: some mappings
+ * don't allow for splitting dirty folios; writeback will
+ * mark them clean again, including marking all page table
+ * entries mapping the folio read-only, to catch future write
+ * attempts.
+ *
+ * While the system should be writing back dirty folios in the
+ * background, we obtained this folio by looking up a writable
+ * page table entry. On these problematic mappings, writable
+ * page table entries imply dirty folios, preventing the
+ * split in the first place.
+ *
+ * To prevent a livelock when trigger writeback manually and
+ * letting the caller look up the folio again in the page
+ * table (turning it dirty), immediately try to split again.
+ *
+ * This is only a problem for some mappings (e.g., XFS);
+ * mappings that do not support writeback (e.g., shmem) do not
+ * apply.
*/
- if (rc == -EAGAIN || rc == -E2BIG)
- folio_get(folio);
- }
- pte_unmap_unlock(ptep, ptelock);
-out:
- mmap_read_unlock(gmap->mm);
-
- switch (rc) {
- case -E2BIG:
- folio_lock(folio);
- rc = split_folio(folio);
- folio_unlock(folio);
- folio_put(folio);
-
- switch (rc) {
- case 0:
- /* Splitting succeeded, try again immediately. */
- goto again;
- case -EAGAIN:
- /* Additional folio references. */
- if (drain_lru(&drain_lru_called))
- goto again;
- return -EAGAIN;
- case -EBUSY:
- /* Unexpected race. */
- return -EAGAIN;
+ if (!folio_test_dirty(folio) || folio_test_anon(folio) ||
+ !folio->mapping || !mapping_can_writeback(folio->mapping)) {
+ folio_unlock(folio);
+ break;
}
- WARN_ON_ONCE(1);
- return -ENXIO;
- case -EAGAIN:
+
/*
- * If we are here because the UVC returned busy or partial
- * completion, this is just a useless check, but it is safe.
+ * Ideally, we'd only trigger writeback on this exact folio. But
+ * there is no easy way to do that, so we'll stabilize the
+ * mapping while we still hold the folio lock, so we can drop
+ * the folio lock to trigger writeback on the range currently
+ * covered by the folio instead.
*/
- folio_wait_writeback(folio);
- folio_put(folio);
- return -EAGAIN;
- case -EBUSY:
- /* Additional folio references. */
- if (drain_lru(&drain_lru_called))
- goto again;
- return -EAGAIN;
- case -ENXIO:
- if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE))
- return -EFAULT;
- return -EAGAIN;
- }
- return rc;
-}
-EXPORT_SYMBOL_GPL(gmap_make_secure);
+ mapping = folio->mapping;
+ lstart = folio_pos(folio);
+ lend = lstart + folio_size(folio) - 1;
+ inode = igrab(mapping->host);
+ folio_unlock(folio);
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
-{
- struct uv_cb_cts uvcb = {
- .header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
- .header.len = sizeof(uvcb),
- .guest_handle = gmap->guest_handle,
- .gaddr = gaddr,
- };
+ if (unlikely(!inode))
+ break;
- return gmap_make_secure(gmap, gaddr, &uvcb);
+ filemap_write_and_wait_range(mapping, lstart, lend);
+ iput(mapping->host);
+ }
+ return -EAGAIN;
}
-EXPORT_SYMBOL_GPL(gmap_convert_to_secure);
-/**
- * gmap_destroy_page - Destroy a guest page.
- * @gmap: the gmap of the guest
- * @gaddr: the guest address to destroy
- *
- * An attempt will be made to destroy the given guest page. If the attempt
- * fails, an attempt is made to export the page. If both attempts fail, an
- * appropriate error is returned.
- */
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb)
{
struct vm_area_struct *vma;
struct folio_walk fw;
- unsigned long uaddr;
struct folio *folio;
int rc;
- rc = -EFAULT;
- mmap_read_lock(gmap->mm);
-
- uaddr = __gmap_translate(gmap, gaddr);
- if (IS_ERR_VALUE(uaddr))
- goto out;
- vma = vma_lookup(gmap->mm, uaddr);
- if (!vma)
- goto out;
- /*
- * Huge pages should not be able to become secure
- */
- if (is_vm_hugetlb_page(vma))
- goto out;
+ mmap_read_lock(mm);
+ vma = vma_lookup(mm, hva);
+ if (!vma) {
+ mmap_read_unlock(mm);
+ return -EFAULT;
+ }
+ folio = folio_walk_start(&fw, vma, hva, 0);
+ if (!folio) {
+ mmap_read_unlock(mm);
+ return -ENXIO;
+ }
- rc = 0;
- folio = folio_walk_start(&fw, vma, uaddr, 0);
- if (!folio)
- goto out;
- /*
- * See gmap_make_secure(): large folios cannot be secure. Small
- * folio implies FW_LEVEL_PTE.
- */
- if (folio_test_large(folio) || !pte_write(fw.pte))
- goto out_walk_end;
- rc = uv_destroy_folio(folio);
+ folio_get(folio);
/*
- * Fault handlers can race; it is possible that two CPUs will fault
- * on the same secure page. One CPU can destroy the page, reboot,
- * re-enter secure mode and import it, while the second CPU was
- * stuck at the beginning of the handler. At some point the second
- * CPU will be able to progress, and it will not be able to destroy
- * the page. In that case we do not want to terminate the process,
- * we instead try to export the page.
+ * Secure pages cannot be huge and userspace should not combine both.
+ * In case userspace does it anyway this will result in an -EFAULT for
+ * the unpack. The guest is thus never reaching secure mode.
+ * If userspace plays dirty tricks and decides to map huge pages at a
+ * later point in time, it will receive a segmentation fault or
+ * KVM_RUN will return -EFAULT.
*/
- if (rc)
- rc = uv_convert_from_secure_folio(folio);
-out_walk_end:
+ if (folio_test_hugetlb(folio))
+ rc = -EFAULT;
+ else if (folio_test_large(folio))
+ rc = -E2BIG;
+ else if (!pte_write(fw.pte) || (pte_val(fw.pte) & _PAGE_INVALID))
+ rc = -ENXIO;
+ else
+ rc = make_folio_secure(mm, folio, uvcb);
folio_walk_end(&fw, vma);
-out:
- mmap_read_unlock(gmap->mm);
+ mmap_read_unlock(mm);
+
+ if (rc == -E2BIG || rc == -EBUSY) {
+ rc = s390_wiggle_split_folio(mm, folio);
+ if (!rc)
+ rc = -EAGAIN;
+ }
+ folio_put(folio);
+
return rc;
}
-EXPORT_SYMBOL_GPL(gmap_destroy_page);
+EXPORT_SYMBOL_GPL(make_hva_secure);
/*
* To be called with the folio locked or with an extra reference! This will
- * prevent gmap_make_secure from touching the folio concurrently. Having 2
- * parallel arch_make_folio_accessible is fine, as the UV calls will become a
- * no-op if the folio is already exported.
+ * prevent kvm_s390_pv_make_secure() from touching the folio concurrently.
+ * Having 2 parallel arch_make_folio_accessible is fine, as the UV calls will
+ * become a no-op if the folio is already exported.
*/
int arch_make_folio_accessible(struct folio *folio)
{
int rc = 0;
- /* See gmap_make_secure(): large folios cannot be secure */
+ /* Large folios cannot be secure */
if (unlikely(folio_test_large(folio)))
return 0;
@@ -696,12 +643,32 @@ static struct kobj_attribute uv_query_supp_secret_types_attr =
static ssize_t uv_query_max_secrets(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
- return sysfs_emit(buf, "%d\n", uv_info.max_secrets);
+ return sysfs_emit(buf, "%d\n",
+ uv_info.max_assoc_secrets + uv_info.max_retr_secrets);
}
static struct kobj_attribute uv_query_max_secrets_attr =
__ATTR(max_secrets, 0444, uv_query_max_secrets, NULL);
+static ssize_t uv_query_max_retr_secrets(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", uv_info.max_retr_secrets);
+}
+
+static struct kobj_attribute uv_query_max_retr_secrets_attr =
+ __ATTR(max_retr_secrets, 0444, uv_query_max_retr_secrets, NULL);
+
+static ssize_t uv_query_max_assoc_secrets(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%d\n", uv_info.max_assoc_secrets);
+}
+
+static struct kobj_attribute uv_query_max_assoc_secrets_attr =
+ __ATTR(max_assoc_secrets, 0444, uv_query_max_assoc_secrets, NULL);
+
static struct attribute *uv_query_attrs[] = {
&uv_query_facilities_attr.attr,
&uv_query_feature_indications_attr.attr,
@@ -719,13 +686,81 @@ static struct attribute *uv_query_attrs[] = {
&uv_query_supp_add_secret_pcf_attr.attr,
&uv_query_supp_secret_types_attr.attr,
&uv_query_max_secrets_attr.attr,
+ &uv_query_max_assoc_secrets_attr.attr,
+ &uv_query_max_retr_secrets_attr.attr,
NULL,
};
+static inline struct uv_cb_query_keys uv_query_keys(void)
+{
+ struct uv_cb_query_keys uvcb = {
+ .header.cmd = UVC_CMD_QUERY_KEYS,
+ .header.len = sizeof(uvcb)
+ };
+
+ uv_call(0, (uint64_t)&uvcb);
+ return uvcb;
+}
+
+static inline ssize_t emit_hash(struct uv_key_hash *hash, char *buf, int at)
+{
+ return sysfs_emit_at(buf, at, "%016llx%016llx%016llx%016llx\n",
+ hash->dword[0], hash->dword[1], hash->dword[2], hash->dword[3]);
+}
+
+static ssize_t uv_keys_host_key(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct uv_cb_query_keys uvcb = uv_query_keys();
+
+ return emit_hash(&uvcb.key_hashes[UVC_QUERY_KEYS_IDX_HK], buf, 0);
+}
+
+static struct kobj_attribute uv_keys_host_key_attr =
+ __ATTR(host_key, 0444, uv_keys_host_key, NULL);
+
+static ssize_t uv_keys_backup_host_key(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct uv_cb_query_keys uvcb = uv_query_keys();
+
+ return emit_hash(&uvcb.key_hashes[UVC_QUERY_KEYS_IDX_BACK_HK], buf, 0);
+}
+
+static struct kobj_attribute uv_keys_backup_host_key_attr =
+ __ATTR(backup_host_key, 0444, uv_keys_backup_host_key, NULL);
+
+static ssize_t uv_keys_all(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct uv_cb_query_keys uvcb = uv_query_keys();
+ ssize_t len = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(uvcb.key_hashes); i++)
+ len += emit_hash(uvcb.key_hashes + i, buf, len);
+
+ return len;
+}
+
+static struct kobj_attribute uv_keys_all_attr =
+ __ATTR(all, 0444, uv_keys_all, NULL);
+
static struct attribute_group uv_query_attr_group = {
.attrs = uv_query_attrs,
};
+static struct attribute *uv_keys_attrs[] = {
+ &uv_keys_host_key_attr.attr,
+ &uv_keys_backup_host_key_attr.attr,
+ &uv_keys_all_attr.attr,
+ NULL,
+};
+
+static struct attribute_group uv_keys_attr_group = {
+ .attrs = uv_keys_attrs,
+};
+
static ssize_t uv_is_prot_virt_guest(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -751,9 +786,27 @@ static const struct attribute *uv_prot_virt_attrs[] = {
};
static struct kset *uv_query_kset;
+static struct kset *uv_keys_kset;
static struct kobject *uv_kobj;
-static int __init uv_info_init(void)
+static int __init uv_sysfs_dir_init(const struct attribute_group *grp,
+ struct kset **uv_dir_kset, const char *name)
+{
+ struct kset *kset;
+ int rc;
+
+ kset = kset_create_and_add(name, NULL, uv_kobj);
+ if (!kset)
+ return -ENOMEM;
+ *uv_dir_kset = kset;
+
+ rc = sysfs_create_group(&kset->kobj, grp);
+ if (rc)
+ kset_unregister(kset);
+ return rc;
+}
+
+static int __init uv_sysfs_init(void)
{
int rc = -ENOMEM;
@@ -768,17 +821,16 @@ static int __init uv_info_init(void)
if (rc)
goto out_kobj;
- uv_query_kset = kset_create_and_add("query", NULL, uv_kobj);
- if (!uv_query_kset) {
- rc = -ENOMEM;
+ rc = uv_sysfs_dir_init(&uv_query_attr_group, &uv_query_kset, "query");
+ if (rc)
goto out_ind_files;
- }
- rc = sysfs_create_group(&uv_query_kset->kobj, &uv_query_attr_group);
- if (!rc)
- return 0;
+ /* Get installed key hashes if available, ignore any errors */
+ if (test_bit_inv(BIT_UVC_CMD_QUERY_KEYS, uv_info.inst_calls_list))
+ uv_sysfs_dir_init(&uv_keys_attr_group, &uv_keys_kset, "keys");
+
+ return 0;
- kset_unregister(uv_query_kset);
out_ind_files:
sysfs_remove_files(uv_kobj, uv_prot_virt_attrs);
out_kobj:
@@ -786,4 +838,110 @@ out_kobj:
kobject_put(uv_kobj);
return rc;
}
-device_initcall(uv_info_init);
+device_initcall(uv_sysfs_init);
+
+/*
+ * Locate a secret in the list by its id.
+ * @secret_id: search pattern.
+ * @list: ephemeral buffer space
+ * @secret: output data, containing the secret's metadata.
+ *
+ * Search for a secret with the given secret_id in the Ultravisor secret store.
+ *
+ * Context: might sleep.
+ */
+static int find_secret_in_page(const u8 secret_id[UV_SECRET_ID_LEN],
+ const struct uv_secret_list *list,
+ struct uv_secret_list_item_hdr *secret)
+{
+ u16 i;
+
+ for (i = 0; i < list->total_num_secrets; i++) {
+ if (memcmp(secret_id, list->secrets[i].id, UV_SECRET_ID_LEN) == 0) {
+ *secret = list->secrets[i].hdr;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+/*
+ * Do the actual search for `uv_get_secret_metadata`.
+ * @secret_id: search pattern.
+ * @list: ephemeral buffer space
+ * @secret: output data, containing the secret's metadata.
+ *
+ * Context: might sleep.
+ */
+int uv_find_secret(const u8 secret_id[UV_SECRET_ID_LEN],
+ struct uv_secret_list *list,
+ struct uv_secret_list_item_hdr *secret)
+{
+ u16 start_idx = 0;
+ u16 list_rc;
+ int ret;
+
+ do {
+ uv_list_secrets(list, start_idx, &list_rc, NULL);
+ if (list_rc != UVC_RC_EXECUTED && list_rc != UVC_RC_MORE_DATA) {
+ if (list_rc == UVC_RC_INV_CMD)
+ return -ENODEV;
+ else
+ return -EIO;
+ }
+ ret = find_secret_in_page(secret_id, list, secret);
+ if (ret == 0)
+ return ret;
+ start_idx = list->next_secret_idx;
+ } while (list_rc == UVC_RC_MORE_DATA && start_idx < list->next_secret_idx);
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(uv_find_secret);
+
+/**
+ * uv_retrieve_secret() - get the secret value for the secret index.
+ * @secret_idx: Secret index for which the secret should be retrieved.
+ * @buf: Buffer to store retrieved secret.
+ * @buf_size: Size of the buffer. The correct buffer size is reported as part of
+ * the result from `uv_get_secret_metadata`.
+ *
+ * Calls the Retrieve Secret UVC and translates the UV return code into an errno.
+ *
+ * Context: might sleep.
+ *
+ * Return:
+ * * %0 - Entry found; buffer contains a valid secret.
+ * * %ENOENT: - No entry found or secret at the index is non-retrievable.
+ * * %ENODEV: - Not supported: UV not available or command not available.
+ * * %EINVAL: - Buffer too small for content.
+ * * %EIO: - Other unexpected UV error.
+ */
+int uv_retrieve_secret(u16 secret_idx, u8 *buf, size_t buf_size)
+{
+ struct uv_cb_retr_secr uvcb = {
+ .header.len = sizeof(uvcb),
+ .header.cmd = UVC_CMD_RETR_SECRET,
+ .secret_idx = secret_idx,
+ .buf_addr = (u64)buf,
+ .buf_size = buf_size,
+ };
+
+ uv_call_sched(0, (u64)&uvcb);
+
+ switch (uvcb.header.rc) {
+ case UVC_RC_EXECUTED:
+ return 0;
+ case UVC_RC_INV_CMD:
+ return -ENODEV;
+ case UVC_RC_RETR_SECR_STORE_EMPTY:
+ case UVC_RC_RETR_SECR_INV_SECRET:
+ case UVC_RC_RETR_SECR_INV_IDX:
+ return -ENOENT;
+ case UVC_RC_RETR_SECR_BUF_SMALL:
+ return -EINVAL;
+ default:
+ return -EIO;
+ }
+}
+EXPORT_SYMBOL_GPL(uv_retrieve_secret);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 598b512cde01..430feb1a5013 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -16,8 +16,8 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/smp.h>
-#include <linux/time_namespace.h>
#include <linux/random.h>
+#include <linux/vdso_datastore.h>
#include <vdso/datapage.h>
#include <asm/vdso/vsyscall.h>
#include <asm/alternative.h>
@@ -26,85 +26,6 @@
extern char vdso64_start[], vdso64_end[];
extern char vdso32_start[], vdso32_end[];
-static struct vm_special_mapping vvar_mapping;
-
-static union vdso_data_store vdso_data_store __page_aligned_data;
-
-struct vdso_data *vdso_data = vdso_data_store.data;
-
-#ifdef CONFIG_TIME_NS
-struct vdso_data *arch_get_vdso_data(void *vvar_page)
-{
- return (struct vdso_data *)(vvar_page);
-}
-
-/*
- * The VVAR page layout depends on whether a task belongs to the root or
- * non-root time namespace. Whenever a task changes its namespace, the VVAR
- * page tables are cleared and then they will be re-faulted with a
- * corresponding layout.
- * See also the comment near timens_setup_vdso_data() for details.
- */
-int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
-{
- struct mm_struct *mm = task->mm;
- VMA_ITERATOR(vmi, mm, 0);
- struct vm_area_struct *vma;
-
- mmap_read_lock(mm);
- for_each_vma(vmi, vma) {
- if (!vma_is_special_mapping(vma, &vvar_mapping))
- continue;
- zap_vma_pages(vma);
- break;
- }
- mmap_read_unlock(mm);
- return 0;
-}
-#endif
-
-static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
- struct vm_area_struct *vma, struct vm_fault *vmf)
-{
- struct page *timens_page = find_timens_vvar_page(vma);
- unsigned long addr, pfn;
- vm_fault_t err;
-
- switch (vmf->pgoff) {
- case VVAR_DATA_PAGE_OFFSET:
- pfn = virt_to_pfn(vdso_data);
- if (timens_page) {
- /*
- * Fault in VVAR page too, since it will be accessed
- * to get clock data anyway.
- */
- addr = vmf->address + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
- err = vmf_insert_pfn(vma, addr, pfn);
- if (unlikely(err & VM_FAULT_ERROR))
- return err;
- pfn = page_to_pfn(timens_page);
- }
- break;
-#ifdef CONFIG_TIME_NS
- case VVAR_TIMENS_PAGE_OFFSET:
- /*
- * If a task belongs to a time namespace then a namespace
- * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
- * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
- * offset.
- * See also the comment near timens_setup_vdso_data().
- */
- if (!timens_page)
- return VM_FAULT_SIGBUS;
- pfn = virt_to_pfn(vdso_data);
- break;
-#endif /* CONFIG_TIME_NS */
- default:
- return VM_FAULT_SIGBUS;
- }
- return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *vma)
{
@@ -112,11 +33,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
return 0;
}
-static struct vm_special_mapping vvar_mapping = {
- .name = "[vvar]",
- .fault = vvar_fault,
-};
-
static struct vm_special_mapping vdso64_mapping = {
.name = "[vdso]",
.mremap = vdso_mremap,
@@ -142,7 +58,7 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
struct vm_area_struct *vma;
int rc;
- BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+ BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES);
if (mmap_write_lock_killable(mm))
return -EINTR;
@@ -157,17 +73,14 @@ static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
rc = vvar_start;
if (IS_ERR_VALUE(vvar_start))
goto out;
- vma = _install_special_mapping(mm, vvar_start, VVAR_NR_PAGES*PAGE_SIZE,
- VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
- VM_PFNMAP,
- &vvar_mapping);
+ vma = vdso_install_vvar_mapping(mm, vvar_start);
rc = PTR_ERR(vma);
if (IS_ERR(vma))
goto out;
- vdso_text_start = vvar_start + VVAR_NR_PAGES * PAGE_SIZE;
+ vdso_text_start = vvar_start + VDSO_NR_PAGES * PAGE_SIZE;
/* VM_MAYWRITE for COW so gdb can set breakpoints */
vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
- VM_READ|VM_EXEC|
+ VM_READ|VM_EXEC|VM_SEALED_SYSMAP|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso_mapping);
if (IS_ERR(vma)) {
@@ -220,7 +133,7 @@ unsigned long vdso_text_size(void)
unsigned long vdso_size(void)
{
- return vdso_text_size() + VVAR_NR_PAGES * PAGE_SIZE;
+ return vdso_text_size() + VDSO_NR_PAGES * PAGE_SIZE;
}
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index 2c5afb88d298..1e4ddd1a683f 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -2,7 +2,7 @@
# List of files in the vdso
# Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
obj-vdso32 = vdso_user_wrapper-32.o note-32.o
# Build rules
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
index 65b9513a5a0e..9630d58c2080 100644
--- a/arch/s390/kernel/vdso32/vdso32.lds.S
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -6,17 +6,16 @@
#include <asm/page.h>
#include <asm/vdso.h>
+#include <vdso/datapage.h>
OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
OUTPUT_ARCH(s390:31-bit)
SECTIONS
{
- PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
-#ifdef CONFIG_TIME_NS
- PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
- . = VDSO_LBASE + SIZEOF_HEADERS;
+ VDSO_VVAR_SYMS
+
+ . = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 37bb4b761229..d8f0df742809 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -2,10 +2,10 @@
# List of files in the vdso
# Include the generic Makefile to check the built vdso.
-include $(srctree)/lib/vdso/Makefile
+include $(srctree)/lib/vdso/Makefile.include
obj-vdso64 = vdso_user_wrapper.o note.o vgetrandom-chacha.o
obj-cvdso64 = vdso64_generic.o getcpu.o vgetrandom.o
-VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK)
+VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE)
CFLAGS_REMOVE_vgetrandom.o = $(VDSO_CFLAGS_REMOVE)
CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE)
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
index 753040a4b5ab..e4f6551ae898 100644
--- a/arch/s390/kernel/vdso64/vdso64.lds.S
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -7,18 +7,16 @@
#include <asm/vdso/vsyscall.h>
#include <asm/page.h>
#include <asm/vdso.h>
+#include <vdso/datapage.h>
OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
OUTPUT_ARCH(s390:64-bit)
SECTIONS
{
- PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
- PROVIDE(_vdso_rng_data = _vdso_data + __VDSO_RND_DATA_OFFSET);
-#ifdef CONFIG_TIME_NS
- PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
-#endif
- . = VDSO_LBASE + SIZEOF_HEADERS;
+ VDSO_VVAR_SYMS
+
+ . = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
diff --git a/arch/s390/kernel/vmcore_info.c b/arch/s390/kernel/vmcore_info.c
index 23f7d7619a99..cc8933e04ff7 100644
--- a/arch/s390/kernel/vmcore_info.c
+++ b/arch/s390/kernel/vmcore_info.c
@@ -1,8 +1,9 @@
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/vmcore_info.h>
-#include <asm/abs_lowcore.h>
#include <linux/mm.h>
+#include <asm/abs_lowcore.h>
+#include <asm/sections.h>
#include <asm/setup.h>
void arch_crash_save_vmcoreinfo(void)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 377b9aaf8c92..ff1ddba96352 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -52,7 +52,6 @@ SECTIONS
SOFTIRQENTRY_TEXT
FTRACE_HOTPATCH_TRAMPOLINES_TEXT
*(.text.*_indirect_*)
- *(.fixup)
*(.gnu.warning)
. = ALIGN(PAGE_SIZE);
_etext = .; /* End of text section */