summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/s390/Kconfig6
-rw-r--r--arch/s390/Kconfig.debug8
-rw-r--r--arch/s390/Makefile2
-rw-r--r--arch/s390/boot/boot.h18
-rw-r--r--arch/s390/boot/compressed/.gitignore1
-rw-r--r--arch/s390/boot/compressed/Makefile26
-rw-r--r--arch/s390/boot/compressed/decompressor.h4
-rw-r--r--arch/s390/boot/compressed/vmlinux.lds.S9
-rw-r--r--arch/s390/boot/head.S32
-rw-r--r--arch/s390/boot/head_kdump.S8
-rw-r--r--arch/s390/boot/ipl_parm.c49
-rw-r--r--arch/s390/boot/kaslr.c33
-rw-r--r--arch/s390/boot/mem_detect.c13
-rw-r--r--arch/s390/boot/pgm_check_info.c224
-rw-r--r--arch/s390/boot/startup.c70
-rw-r--r--arch/s390/configs/debug_defconfig1
-rw-r--r--arch/s390/crypto/arch_random.c110
-rw-r--r--arch/s390/crypto/prng.c53
-rw-r--r--arch/s390/include/asm/archrandom.h5
-rw-r--r--arch/s390/include/asm/ccwdev.h12
-rw-r--r--arch/s390/include/asm/cio.h2
-rw-r--r--arch/s390/include/asm/delay.h1
-rw-r--r--arch/s390/include/asm/ftrace.h31
-rw-r--r--arch/s390/include/asm/futex.h6
-rw-r--r--arch/s390/include/asm/kasan.h37
-rw-r--r--arch/s390/include/asm/lowcore.h4
-rw-r--r--arch/s390/include/asm/mmu_context.h37
-rw-r--r--arch/s390/include/asm/pgtable.h13
-rw-r--r--arch/s390/include/asm/processor.h13
-rw-r--r--arch/s390/include/asm/ptrace.h1
-rw-r--r--arch/s390/include/asm/sclp.h7
-rw-r--r--arch/s390/include/asm/setup.h6
-rw-r--r--arch/s390/include/asm/thread_info.h2
-rw-r--r--arch/s390/include/asm/timex.h7
-rw-r--r--arch/s390/include/asm/uaccess.h22
-rw-r--r--arch/s390/include/asm/vdso.h25
-rw-r--r--arch/s390/kernel/asm-offsets.c7
-rw-r--r--arch/s390/kernel/base.S22
-rw-r--r--arch/s390/kernel/early.c4
-rw-r--r--arch/s390/kernel/entry.S141
-rw-r--r--arch/s390/kernel/entry.h1
-rw-r--r--arch/s390/kernel/ftrace.c63
-rw-r--r--arch/s390/kernel/head64.S7
-rw-r--r--arch/s390/kernel/mcount.S8
-rw-r--r--arch/s390/kernel/process.c14
-rw-r--r--arch/s390/kernel/setup.c50
-rw-r--r--arch/s390/kernel/smp.c32
-rw-r--r--arch/s390/kernel/time.c44
-rw-r--r--arch/s390/kernel/vdso.c58
-rw-r--r--arch/s390/kernel/vdso64/Makefile5
-rw-r--r--arch/s390/kernel/vdso64/getcpu.S31
-rw-r--r--arch/s390/kernel/vdso64/getcpu.c21
-rw-r--r--arch/s390/kernel/vdso64/vdso.h14
-rw-r--r--arch/s390/kernel/vdso64/vdso64.lds.S1
-rw-r--r--arch/s390/kernel/vdso64/vdso64_generic.c1
-rw-r--r--arch/s390/kernel/vdso64/vdso_user_wrapper.S1
-rw-r--r--arch/s390/kernel/vmlinux.lds.S3
-rw-r--r--arch/s390/lib/delay.c13
-rw-r--r--arch/s390/lib/uaccess.c105
-rw-r--r--arch/s390/mm/dump_pagetables.c2
-rw-r--r--arch/s390/mm/fault.c29
-rw-r--r--arch/s390/mm/init.c12
-rw-r--r--arch/s390/mm/kasan_init.c93
-rw-r--r--arch/s390/mm/pgalloc.c13
-rw-r--r--arch/s390/mm/vmem.c38
-rw-r--r--arch/s390/pci/pci.c4
-rw-r--r--arch/s390/pci/pci_mmio.c104
-rw-r--r--arch/s390/purgatory/head.S9
-rw-r--r--drivers/char/hw_random/s390-trng.c7
-rw-r--r--drivers/s390/block/dasd.c93
-rw-r--r--drivers/s390/block/dasd_eckd.c94
-rw-r--r--drivers/s390/block/dasd_fba.c3
-rw-r--r--drivers/s390/block/dasd_int.h10
-rw-r--r--drivers/s390/char/con3215.c85
-rw-r--r--drivers/s390/char/con3270.c1
-rw-r--r--drivers/s390/char/raw3270.c78
-rw-r--r--drivers/s390/char/raw3270.h1
-rw-r--r--drivers/s390/char/sclp.h10
-rw-r--r--drivers/s390/char/sclp_cmd.c16
-rw-r--r--drivers/s390/char/sclp_early.c59
-rw-r--r--drivers/s390/char/sclp_early_core.c13
-rw-r--r--drivers/s390/char/tape.h1
-rw-r--r--drivers/s390/char/tape_34xx.c1
-rw-r--r--drivers/s390/char/tape_3590.c1
-rw-r--r--drivers/s390/char/tape_core.c50
-rw-r--r--drivers/s390/char/vmur.c24
-rw-r--r--drivers/s390/cio/chsc_sch.c29
-rw-r--r--drivers/s390/cio/cmf.c5
-rw-r--r--drivers/s390/cio/css.c130
-rw-r--r--drivers/s390/cio/css.h10
-rw-r--r--drivers/s390/cio/device.c265
-rw-r--r--drivers/s390/cio/device.h1
-rw-r--r--drivers/s390/cio/device_fsm.c6
-rw-r--r--drivers/s390/cio/eadm_sch.c13
-rw-r--r--drivers/s390/cio/io_sch.h1
-rw-r--r--drivers/s390/crypto/ap_bus.c213
-rw-r--r--drivers/s390/crypto/ap_bus.h12
-rw-r--r--drivers/s390/crypto/pkey_api.c15
-rw-r--r--drivers/s390/crypto/zcrypt_api.c66
-rw-r--r--drivers/s390/crypto/zcrypt_api.h2
-rw-r--r--drivers/s390/scsi/zfcp_ccw.c57
-rw-r--r--drivers/s390/scsi/zfcp_dbf.c25
-rw-r--r--drivers/s390/scsi/zfcp_def.h1
-rw-r--r--drivers/s390/scsi/zfcp_ext.h1
-rw-r--r--init/Kconfig2
-rw-r--r--lib/Kconfig.kasan9
-rwxr-xr-xscripts/recordmcount.pl3
107 files changed, 1268 insertions, 1993 deletions
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 4a2a12be04c9..a60cc523d810 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -53,8 +53,7 @@ config ARCH_SUPPORTS_UPROBES
config KASAN_SHADOW_OFFSET
hex
depends on KASAN
- default 0x18000000000000 if KASAN_S390_4_LEVEL_PAGING
- default 0x30000000000
+ default 0x18000000000000
config S390
def_bool y
@@ -191,7 +190,6 @@ config S390
select PCI_DOMAINS if PCI
select PCI_MSI if PCI
select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
- select SET_FS
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
@@ -714,7 +712,7 @@ if PCI
config PCI_NR_FUNCTIONS
int "Maximum number of PCI functions (1-4096)"
range 1 4096
- default "128"
+ default "512"
help
This allows you to specify the maximum number of PCI functions which
this kernel will support.
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index ab48b694ade8..6bfaceebbbc0 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -5,3 +5,11 @@ config TRACE_IRQFLAGS_SUPPORT
config EARLY_PRINTK
def_bool y
+
+config DEBUG_USER_ASCE
+ bool "Debug User ASCE"
+ help
+ Check on exit to user space that address space control
+ elements are setup correctly.
+
+ If unsure, say N.
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index ba94b03c8b2f..8db267d2a543 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -25,7 +25,7 @@ KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2
KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
-KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float -mbackchain
KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
KBUILD_CFLAGS_DECOMPRESSOR += -ffreestanding
KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member)
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 2ea603f70c3b..8b50967f5804 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -2,20 +2,32 @@
#ifndef BOOT_BOOT_H
#define BOOT_BOOT_H
+#include <linux/types.h>
+
+#define BOOT_STACK_OFFSET 0x8000
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
void startup_kernel(void);
-void detect_memory(void);
+unsigned long detect_memory(void);
+bool is_ipl_block_dump(void);
void store_ipl_parmblock(void);
void setup_boot_command_line(void);
void parse_boot_command_line(void);
-void setup_memory_end(void);
void verify_facilities(void);
void print_missing_facilities(void);
void print_pgm_check_info(void);
unsigned long get_random_base(unsigned long safe_addr);
+void __printf(1, 2) decompressor_printk(const char *fmt, ...);
-extern int kaslr_enabled;
extern const char kernel_version[];
+extern unsigned long memory_limit;
+extern int vmalloc_size_set;
+extern int kaslr_enabled;
unsigned long read_ipl_report(unsigned long safe_offset);
+#endif /* __ASSEMBLY__ */
#endif /* BOOT_BOOT_H */
diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index 765a08f1bd77..01d93832cf4a 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
vmlinux
vmlinux.lds
+vmlinux.syms
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index b235ed95a3d8..de18dab518bb 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -10,21 +10,39 @@ GCOV_PROFILE := n
UBSAN_SANITIZE := n
KASAN_SANITIZE := n
-obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) piggy.o info.o
+obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
+obj-all := $(obj-y) piggy.o syms.o
targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += info.bin $(obj-y)
+targets += info.bin syms.bin vmlinux.syms $(obj-all)
KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
OBJCOPYFLAGS :=
OBJECTS := $(addprefix $(obj)/,$(obj-y))
+OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all))
-LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE
+LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup --build-id=sha1 -T
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS_ALL) FORCE
$(call if_changed,ld)
+LDFLAGS_vmlinux.syms := --oformat $(LD_BFD) -e startup -T
+$(obj)/vmlinux.syms: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE
+ $(call if_changed,ld)
+
+quiet_cmd_dumpsyms = DUMPSYMS $<
+define cmd_dumpsyms
+ $(NM) -n -S --format=bsd "$<" | $(PERL) -ne '/(\w+)\s+(\w+)\s+[tT]\s+(\w+)/ and printf "%x %x %s\0",hex $$1,hex $$2,$$3' > "$@"
+endef
+
+$(obj)/syms.bin: $(obj)/vmlinux.syms FORCE
+ $(call if_changed,dumpsyms)
+
+OBJCOPYFLAGS_syms.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.decompressor.syms
+$(obj)/syms.o: $(obj)/syms.bin FORCE
+ $(call if_changed,objcopy)
+
OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load
$(obj)/info.bin: vmlinux FORCE
$(call if_changed,objcopy)
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
index c15eb7114d83..41f0ad97a4db 100644
--- a/arch/s390/boot/compressed/decompressor.h
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -2,8 +2,10 @@
#ifndef BOOT_COMPRESSED_DECOMPRESSOR_H
#define BOOT_COMPRESSED_DECOMPRESSOR_H
+#include <linux/stddef.h>
+
#ifdef CONFIG_KERNEL_UNCOMPRESSED
-static inline void *decompress_kernel(void) {}
+static inline void *decompress_kernel(void) { return NULL; }
#else
void *decompress_kernel(void);
#endif
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index 9427e2cd0c15..27a09c1c78f6 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -27,6 +27,7 @@ SECTIONS
*(.rodata.*)
_erodata = . ;
}
+ NOTES
.data : {
_data = . ;
*(.data)
@@ -82,6 +83,14 @@ SECTIONS
*(.vmlinux.info)
}
+ .decompressor.syms : {
+ . += 1; /* make sure we have \0 before the first entry */
+ . = ALIGN(2);
+ _decompressor_syms_start = .;
+ *(.decompressor.syms)
+ _decompressor_syms_end = .;
+ }
+
#ifdef CONFIG_KERNEL_UNCOMPRESSED
. = 0x100000;
#else
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index 1a2c2b1ed964..dacb7813f982 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -28,6 +28,7 @@
#include <asm/thread_info.h>
#include <asm/page.h>
#include <asm/ptrace.h>
+#include "boot.h"
#define ARCH_OFFSET 4
@@ -62,8 +63,12 @@ __HEAD
.org __LC_RST_NEW_PSW # 0x1a0
.quad 0,iplstart
+ .org __LC_EXT_NEW_PSW # 0x1b0
+ .quad 0x0002000180000000,0x1b0 # disabled wait
.org __LC_PGM_NEW_PSW # 0x1d0
.quad 0x0000000180000000,startup_pgm_check_handler
+ .org __LC_IO_NEW_PSW # 0x1f0
+ .quad 0x0002000180000000,0x1f0 # disabled wait
.org 0x200
@@ -275,8 +280,8 @@ iplstart:
# or linload or SALIPL
#
.org 0x10000
-ENTRY(startup)
- j .Lep_startup_normal
+SYM_CODE_START(startup)
+ j startup_normal
.org EP_OFFSET
#
# This is a list of s390 kernel entry points. At address 0x1000f the number of
@@ -290,9 +295,9 @@ ENTRY(startup)
# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
#
.org 0x10010
-ENTRY(startup_kdump)
- j .Lep_startup_kdump
-.Lep_startup_normal:
+ j startup_kdump
+SYM_CODE_END(startup)
+SYM_CODE_START_LOCAL(startup_normal)
mvi __LC_AR_MODE_ID,1 # set esame flag
slr %r0,%r0 # set cpuid to zero
lhi %r1,2 # mode 2 = esame (dump)
@@ -303,6 +308,9 @@ ENTRY(startup_kdump)
sam64 # switch to 64 bit addressing mode
basr %r13,0 # get base
.LPG0:
+ mvc __LC_EXT_NEW_PSW(16),.Lext_new_psw-.LPG0(%r13)
+ mvc __LC_PGM_NEW_PSW(16),.Lpgm_new_psw-.LPG0(%r13)
+ mvc __LC_IO_NEW_PSW(16),.Lio_new_psw-.LPG0(%r13)
xc 0x200(256),0x200 # partially clear lowcore
xc 0x300(256),0x300
xc 0xe00(256),0xe00
@@ -315,12 +323,18 @@ ENTRY(startup_kdump)
l %r15,.Lstack-.LPG0(%r13)
brasl %r14,verify_facilities
brasl %r14,startup_kernel
+SYM_CODE_END(startup_normal)
.Lstack:
- .long 0x8000 + (1<<(PAGE_SHIFT+BOOT_STACK_ORDER)) - STACK_FRAME_OVERHEAD
+ .long BOOT_STACK_OFFSET + BOOT_STACK_SIZE - STACK_FRAME_OVERHEAD
.align 8
6: .long 0x7fffffff,0xffffffff
-
+.Lext_new_psw:
+ .quad 0x0002000180000000,0x1b0 # disabled wait
+.Lpgm_new_psw:
+ .quad 0x0000000180000000,startup_pgm_check_handler
+.Lio_new_psw:
+ .quad 0x0002000180000000,0x1f0 # disabled wait
.Lctl: .quad 0x04040000 # cr0: AFP registers & secondary space
.quad 0 # cr1: primary space segment table
.quad .Lduct # cr2: dispatchable unit control table
@@ -359,7 +373,7 @@ ENTRY(startup_kdump)
# It simply saves general/control registers and psw in
# the save area and does disabled wait with a faulty address.
#
-ENTRY(startup_pgm_check_handler)
+SYM_CODE_START_LOCAL(startup_pgm_check_handler)
stmg %r8,%r15,__LC_SAVE_AREA_SYNC
la %r8,4095
stctg %c0,%c15,__LC_CREGS_SAVE_AREA-4095(%r8)
@@ -378,9 +392,9 @@ ENTRY(startup_pgm_check_handler)
la %r8,4095
lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r8)
lpswe __LC_RETURN_PSW # disabled wait
+SYM_CODE_END(startup_pgm_check_handler)
.Ldump_info_stack:
.long 0x5000 + PAGE_SIZE - STACK_FRAME_OVERHEAD
-ENDPROC(startup_pgm_check_handler)
#
# params at 10400 (setup.h)
diff --git a/arch/s390/boot/head_kdump.S b/arch/s390/boot/head_kdump.S
index 174d6959bf5b..f015469e7db9 100644
--- a/arch/s390/boot/head_kdump.S
+++ b/arch/s390/boot/head_kdump.S
@@ -19,8 +19,7 @@
# Note: This code has to be position independent
#
-.align 2
-.Lep_startup_kdump:
+SYM_CODE_START_LOCAL(startup_kdump)
lhi %r1,2 # mode 2 = esame (dump)
sigp %r1,%r0,SIGP_SET_ARCHITECTURE # Switch to esame mode
sam64 # Switch to 64 bit addressing
@@ -87,14 +86,15 @@
startup_kdump_relocated:
basr %r13,0
0: lpswe .Lrestart_psw-0b(%r13) # Start new kernel...
+SYM_CODE_END(startup_kdump)
.align 8
.Lrestart_psw:
.quad 0x0000000080000000,0x0000000000000000 + startup
#else
-.align 2
-.Lep_startup_kdump:
+SYM_CODE_START_LOCAL(startup_kdump)
larl %r13,startup_kdump_crash
lpswe 0(%r13)
+SYM_CODE_END(startup_kdump)
.align 8
startup_kdump_crash:
.quad 0x0002000080000000,0x0000000000000000 + startup_kdump_crash
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index f94b91d72620..d372a45fe10e 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -17,10 +17,10 @@ int __bootdata_preserved(ipl_block_valid);
unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL;
unsigned long __bootdata(vmalloc_size) = VMALLOC_DEFAULT_SIZE;
-unsigned long __bootdata(memory_end);
-int __bootdata(memory_end_set);
int __bootdata(noexec_disabled);
+unsigned long memory_limit;
+int vmalloc_size_set;
int kaslr_enabled;
static inline int __diag308(unsigned long subcode, void *addr)
@@ -57,6 +57,17 @@ void store_ipl_parmblock(void)
ipl_block_valid = 1;
}
+bool is_ipl_block_dump(void)
+{
+ if (ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
+ ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
+ return true;
+ if (ipl_block.pb0_hdr.pbt == IPL_PBT_NVME &&
+ ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP)
+ return true;
+ return false;
+}
+
static size_t scpdata_length(const u8 *buf, size_t count)
{
while (count) {
@@ -237,13 +248,13 @@ void parse_boot_command_line(void)
while (*args) {
args = next_arg(args, &param, &val);
- if (!strcmp(param, "mem") && val) {
- memory_end = round_down(memparse(val, NULL), PAGE_SIZE);
- memory_end_set = 1;
- }
+ if (!strcmp(param, "mem") && val)
+ memory_limit = round_down(memparse(val, NULL), PAGE_SIZE);
- if (!strcmp(param, "vmalloc") && val)
+ if (!strcmp(param, "vmalloc") && val) {
vmalloc_size = round_up(memparse(val, NULL), PAGE_SIZE);
+ vmalloc_size_set = 1;
+ }
if (!strcmp(param, "dfltcc") && val) {
if (!strcmp(val, "off"))
@@ -279,27 +290,3 @@ void parse_boot_command_line(void)
#endif
}
}
-
-static inline bool is_ipl_block_dump(void)
-{
- if (ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
- ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
- return true;
- if (ipl_block.pb0_hdr.pbt == IPL_PBT_NVME &&
- ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP)
- return true;
- return false;
-}
-
-void setup_memory_end(void)
-{
-#ifdef CONFIG_CRASH_DUMP
- if (OLDMEM_BASE) {
- kaslr_enabled = 0;
- } else if (ipl_block_valid && is_ipl_block_dump()) {
- kaslr_enabled = 0;
- if (!sclp_early_get_hsa_size(&memory_end) && memory_end)
- memory_end_set = 1;
- }
-#endif
-}
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
index d844a5ef9089..0dd48fbdbaa4 100644
--- a/arch/s390/boot/kaslr.c
+++ b/arch/s390/boot/kaslr.c
@@ -7,6 +7,7 @@
#include <asm/cpacf.h>
#include <asm/timex.h>
#include <asm/sclp.h>
+#include <asm/kasan.h>
#include "compressed/decompressor.h"
#include "boot.h"
@@ -176,8 +177,14 @@ unsigned long get_random_base(unsigned long safe_addr)
unsigned long kasan_needs;
int i;
- if (memory_end_set)
- memory_limit = min(memory_limit, memory_end);
+ memory_limit = min(memory_limit, ident_map_size);
+
+ /*
+ * Avoid putting kernel in the end of physical memory
+ * which kasan will use for shadow memory and early pgtable
+ * mapping allocations.
+ */
+ memory_limit -= kasan_estimate_memory_needs(memory_limit);
if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
if (safe_addr < INITRD_START + INITRD_SIZE)
@@ -185,28 +192,6 @@ unsigned long get_random_base(unsigned long safe_addr)
}
safe_addr = ALIGN(safe_addr, THREAD_SIZE);
- if ((IS_ENABLED(CONFIG_KASAN))) {
- /*
- * Estimate kasan memory requirements, which it will reserve
- * at the very end of available physical memory. To estimate
- * that, we take into account that kasan would require
- * 1/8 of available physical memory (for shadow memory) +
- * creating page tables for the whole memory + shadow memory
- * region (1 + 1/8). To keep page tables estimates simple take
- * the double of combined ptes size.
- */
- memory_limit = get_mem_detect_end();
- if (memory_end_set && memory_limit > memory_end)
- memory_limit = memory_end;
-
- /* for shadow memory */
- kasan_needs = memory_limit / 8;
- /* for paging structures */
- kasan_needs += (memory_limit + kasan_needs) / PAGE_SIZE /
- _PAGE_ENTRIES * _PAGE_TABLE_SIZE * 2;
- memory_limit -= kasan_needs;
- }
-
kernel_size = vmlinux.image_size + vmlinux.bss_size;
if (safe_addr + kernel_size > memory_limit)
return 0;
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
index 62e7c13ce85c..40168e59abd3 100644
--- a/arch/s390/boot/mem_detect.c
+++ b/arch/s390/boot/mem_detect.c
@@ -8,7 +8,6 @@
#include "compressed/decompressor.h"
#include "boot.h"
-unsigned long __bootdata(max_physmem_end);
struct mem_detect_info __bootdata(mem_detect);
/* up to 256 storage elements, 1020 subincrements each */
@@ -149,27 +148,29 @@ static void search_mem_end(void)
add_mem_detect_block(0, (offset + 1) << 20);
}
-void detect_memory(void)
+unsigned long detect_memory(void)
{
+ unsigned long max_physmem_end;
+
sclp_early_get_memsize(&max_physmem_end);
if (!sclp_early_read_storage_info()) {
mem_detect.info_source = MEM_DETECT_SCLP_STOR_INFO;
- return;
+ return max_physmem_end;
}
if (!diag260()) {
mem_detect.info_source = MEM_DETECT_DIAG260;
- return;
+ return max_physmem_end;
}
if (max_physmem_end) {
add_mem_detect_block(0, max_physmem_end);
mem_detect.info_source = MEM_DETECT_SCLP_READ_INFO;
- return;
+ return max_physmem_end;
}
search_mem_end();
mem_detect.info_source = MEM_DETECT_BIN_SEARCH;
- max_physmem_end = get_mem_detect_end();
+ return get_mem_detect_end();
}
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
index a3c9862bcede..3a46abed2549 100644
--- a/arch/s390/boot/pgm_check_info.c
+++ b/arch/s390/boot/pgm_check_info.c
@@ -1,99 +1,181 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/string.h>
+#include <linux/ctype.h>
+#include <asm/stacktrace.h>
+#include <asm/boot_data.h>
#include <asm/lowcore.h>
#include <asm/setup.h>
#include <asm/sclp.h>
+#include <asm/uv.h>
+#include <stdarg.h>
#include "boot.h"
const char hex_asc[] = "0123456789abcdef";
-#define add_val_as_hex(dst, val) \
- __add_val_as_hex(dst, (const unsigned char *)&val, sizeof(val))
+static char *as_hex(char *dst, unsigned long val, int pad)
+{
+ char *p, *end = p = dst + max(pad, (int)__fls(val | 1) / 4 + 1);
+
+ for (*p-- = 0; p >= dst; val >>= 4)
+ *p-- = hex_asc[val & 0x0f];
+ return end;
+}
-static char *__add_val_as_hex(char *dst, const unsigned char *src, size_t count)
+static char *symstart(char *p)
{
- while (count--)
- dst = hex_byte_pack(dst, *src++);
- return dst;
+ while (*p)
+ p--;
+ return p + 1;
}
-static char *add_str(char *dst, char *src)
+extern char _decompressor_syms_start[], _decompressor_syms_end[];
+static noinline char *findsym(unsigned long ip, unsigned short *off, unsigned short *len)
{
- strcpy(dst, src);
- return dst + strlen(dst);
+ /* symbol entries are in a form "10000 c4 startup\0" */
+ char *a = _decompressor_syms_start;
+ char *b = _decompressor_syms_end;
+ unsigned long start;
+ unsigned long size;
+ char *pivot;
+ char *endp;
+
+ while (a < b) {
+ pivot = symstart(a + (b - a) / 2);
+ start = simple_strtoull(pivot, &endp, 16);
+ size = simple_strtoull(endp + 1, &endp, 16);
+ if (ip < start) {
+ b = pivot;
+ continue;
+ }
+ if (ip > start + size) {
+ a = pivot + strlen(pivot) + 1;
+ continue;
+ }
+ *off = ip - start;
+ *len = size;
+ return endp + 1;
+ }
+ return NULL;
}
-void print_pgm_check_info(void)
+static noinline char *strsym(void *ip)
{
- struct psw_bits *psw = &psw_bits(S390_lowcore.psw_save_area);
- unsigned short ilc = S390_lowcore.pgm_ilc >> 1;
- char buf[256];
- int row, col;
+ static char buf[64];
+ unsigned short off;
+ unsigned short len;
char *p;
- add_str(buf, "Linux version ");
- strlcat(buf, kernel_version, sizeof(buf) - 1);
- strlcat(buf, "\n", sizeof(buf));
- sclp_early_printk(buf);
+ p = findsym((unsigned long)ip, &off, &len);
+ if (p) {
+ strncpy(buf, p, sizeof(buf));
+ /* reserve 15 bytes for offset/len in symbol+0x1234/0x1234 */
+ p = buf + strnlen(buf, sizeof(buf) - 15);
+ strcpy(p, "+0x");
+ p = as_hex(p + 3, off, 0);
+ strcpy(p, "/0x");
+ as_hex(p + 3, len, 0);
+ } else {
+ as_hex(buf, (unsigned long)ip, 16);
+ }
+ return buf;
+}
- p = add_str(buf, "Kernel fault: interruption code ");
- p = add_val_as_hex(buf + strlen(buf), S390_lowcore.pgm_code);
- p = add_str(p, " ilc:");
- *p++ = hex_asc_lo(ilc);
- add_str(p, "\n");
- sclp_early_printk(buf);
+void decompressor_printk(const char *fmt, ...)
+{
+ char buf[1024] = { 0 };
+ char *end = buf + sizeof(buf) - 1; /* make sure buf is 0 terminated */
+ unsigned long pad;
+ char *p = buf;
+ va_list args;
- if (kaslr_enabled) {
- p = add_str(buf, "Kernel random base: ");
- p = add_val_as_hex(p, __kaslr_offset);
- add_str(p, "\n");
- sclp_early_printk(buf);
+ va_start(args, fmt);
+ for (; p < end && *fmt; fmt++) {
+ if (*fmt != '%') {
+ *p++ = *fmt;
+ continue;
+ }
+ pad = isdigit(*++fmt) ? simple_strtol(fmt, (char **)&fmt, 10) : 0;
+ switch (*fmt) {
+ case 's':
+ p = buf + strlcat(buf, va_arg(args, char *), sizeof(buf));
+ break;
+ case 'p':
+ if (*++fmt != 'S')
+ goto out;
+ p = buf + strlcat(buf, strsym(va_arg(args, void *)), sizeof(buf));
+ break;
+ case 'l':
+ if (*++fmt != 'x' || end - p <= max(sizeof(long) * 2, pad))
+ goto out;
+ p = as_hex(p, va_arg(args, unsigned long), pad);
+ break;
+ case 'x':
+ if (end - p <= max(sizeof(int) * 2, pad))
+ goto out;
+ p = as_hex(p, va_arg(args, unsigned int), pad);
+ break;
+ default:
+ goto out;
+ }
}
-
- p = add_str(buf, "PSW : ");
- p = add_val_as_hex(p, S390_lowcore.psw_save_area.mask);
- p = add_str(p, " ");
- p = add_val_as_hex(p, S390_lowcore.psw_save_area.addr);
- add_str(p, "\n");
+out:
+ va_end(args);
sclp_early_printk(buf);
+}
- p = add_str(buf, " R:");
- *p++ = hex_asc_lo(psw->per);
- p = add_str(p, " T:");
- *p++ = hex_asc_lo(psw->dat);
- p = add_str(p, " IO:");
- *p++ = hex_asc_lo(psw->io);
- p = add_str(p, " EX:");
- *p++ = hex_asc_lo(psw->ext);
- p = add_str(p, " Key:");
- *p++ = hex_asc_lo(psw->key);
- p = add_str(p, " M:");
- *p++ = hex_asc_lo(psw->mcheck);
- p = add_str(p, " W:");
- *p++ = hex_asc_lo(psw->wait);
- p = add_str(p, " P:");
- *p++ = hex_asc_lo(psw->pstate);
- p = add_str(p, " AS:");
- *p++ = hex_asc_lo(psw->as);
- p = add_str(p, " CC:");
- *p++ = hex_asc_lo(psw->cc);
- p = add_str(p, " PM:");
- *p++ = hex_asc_lo(psw->pm);
- p = add_str(p, " RI:");
- *p++ = hex_asc_lo(psw->ri);
- p = add_str(p, " EA:");
- *p++ = hex_asc_lo(psw->eaba);
- add_str(p, "\n");
- sclp_early_printk(buf);
+static noinline void print_stacktrace(void)
+{
+ struct stack_info boot_stack = { STACK_TYPE_TASK, BOOT_STACK_OFFSET,
+ BOOT_STACK_OFFSET + BOOT_STACK_SIZE };
+ unsigned long sp = S390_lowcore.gpregs_save_area[15];
+ bool first = true;
- for (row = 0; row < 4; row++) {
- p = add_str(buf, row == 0 ? "GPRS:" : " ");
- for (col = 0; col < 4; col++) {
- p = add_str(p, " ");
- p = add_val_as_hex(p, S390_lowcore.gpregs_save_area[row * 4 + col]);
- }
- add_str(p, "\n");
- sclp_early_printk(buf);
+ decompressor_printk("Call Trace:\n");
+ while (!(sp & 0x7) && on_stack(&boot_stack, sp, sizeof(struct stack_frame))) {
+ struct stack_frame *sf = (struct stack_frame *)sp;
+
+ decompressor_printk(first ? "(sp:%016lx [<%016lx>] %pS)\n" :
+ " sp:%016lx [<%016lx>] %pS\n",
+ sp, sf->gprs[8], (void *)sf->gprs[8]);
+ if (sf->back_chain <= sp)
+ break;
+ sp = sf->back_chain;
+ first = false;
}
}
+
+void print_pgm_check_info(void)
+{
+ unsigned long *gpregs = (unsigned long *)S390_lowcore.gpregs_save_area;
+ struct psw_bits *psw = &psw_bits(S390_lowcore.psw_save_area);
+
+ decompressor_printk("Linux version %s\n", kernel_version);
+ if (!is_prot_virt_guest() && early_command_line[0])
+ decompressor_printk("Kernel command line: %s\n", early_command_line);
+ decompressor_printk("Kernel fault: interruption code %04x ilc:%x\n",
+ S390_lowcore.pgm_code, S390_lowcore.pgm_ilc >> 1);
+ if (kaslr_enabled)
+ decompressor_printk("Kernel random base: %lx\n", __kaslr_offset);
+ decompressor_printk("PSW : %016lx %016lx (%pS)\n",
+ S390_lowcore.psw_save_area.mask,
+ S390_lowcore.psw_save_area.addr,
+ (void *)S390_lowcore.psw_save_area.addr);
+ decompressor_printk(
+ " R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n",
+ psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck,
+ psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri,
+ psw->eaba);
+ decompressor_printk("GPRS: %016lx %016lx %016lx %016lx\n",
+ gpregs[0], gpregs[1], gpregs[2], gpregs[3]);
+ decompressor_printk(" %016lx %016lx %016lx %016lx\n",
+ gpregs[4], gpregs[5], gpregs[6], gpregs[7]);
+ decompressor_printk(" %016lx %016lx %016lx %016lx\n",
+ gpregs[8], gpregs[9], gpregs[10], gpregs[11]);
+ decompressor_printk(" %016lx %016lx %016lx %016lx\n",
+ gpregs[12], gpregs[13], gpregs[14], gpregs[15]);
+ print_stacktrace();
+ decompressor_printk("Last Breaking-Event-Address:\n");
+ decompressor_printk(" [<%016lx>] %pS\n", (unsigned long)S390_lowcore.breaking_event_addr,
+ (void *)S390_lowcore.breaking_event_addr);
+}
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index cc96b04cc0ba..05f8eefa3dcf 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -1,7 +1,9 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/string.h>
#include <linux/elf.h>
+#include <asm/boot_data.h>
#include <asm/sections.h>
+#include <asm/cpu_mf.h>
#include <asm/setup.h>
#include <asm/kexec.h>
#include <asm/sclp.h>
@@ -13,6 +15,7 @@
extern char __boot_data_start[], __boot_data_end[];
extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
unsigned long __bootdata_preserved(__kaslr_offset);
+unsigned long __bootdata(ident_map_size);
/*
* Some code and data needs to stay below 2 GB, even when the kernel would be
@@ -58,6 +61,14 @@ void error(char *x)
disabled_wait();
}
+static void setup_lpp(void)
+{
+ S390_lowcore.current_pid = 0;
+ S390_lowcore.lpp = LPP_MAGIC;
+ if (test_facility(40))
+ lpp(&S390_lowcore.lpp);
+}
+
#ifdef CONFIG_KERNEL_UNCOMPRESSED
unsigned long mem_safe_offset(void)
{
@@ -119,6 +130,46 @@ static void handle_relocs(unsigned long offset)
}
/*
+ * Merge information from several sources into a single ident_map_size value.
+ * "ident_map_size" represents the upper limit of physical memory we may ever
+ * reach. It might not be all online memory, but also include standby (offline)
+ * memory. "ident_map_size" could be lower then actual standby or even online
+ * memory present, due to limiting factors. We should never go above this limit.
+ * It is the size of our identity mapping.
+ *
+ * Consider the following factors:
+ * 1. max_physmem_end - end of physical memory online or standby.
+ * Always <= end of the last online memory block (get_mem_detect_end()).
+ * 2. CONFIG_MAX_PHYSMEM_BITS - the maximum size of physical memory the
+ * kernel is able to support.
+ * 3. "mem=" kernel command line option which limits physical memory usage.
+ * 4. OLDMEM_BASE which is a kdump memory limit when the kernel is executed as
+ * crash kernel.
+ * 5. "hsa" size which is a memory limit when the kernel is executed during
+ * zfcp/nvme dump.
+ */
+static void setup_ident_map_size(unsigned long max_physmem_end)
+{
+ unsigned long hsa_size;
+
+ ident_map_size = max_physmem_end;
+ if (memory_limit)
+ ident_map_size = min(ident_map_size, memory_limit);
+ ident_map_size = min(ident_map_size, 1UL << MAX_PHYSMEM_BITS);
+
+#ifdef CONFIG_CRASH_DUMP
+ if (OLDMEM_BASE) {
+ kaslr_enabled = 0;
+ ident_map_size = min(ident_map_size, OLDMEM_SIZE);
+ } else if (ipl_block_valid && is_ipl_block_dump()) {
+ kaslr_enabled = 0;
+ if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size)
+ ident_map_size = min(ident_map_size, hsa_size);
+ }
+#endif
+}
+
+/*
* This function clears the BSS section of the decompressed Linux kernel and NOT the decompressor's.
*/
static void clear_bss_section(void)
@@ -126,12 +177,27 @@ static void clear_bss_section(void)
memset((void *)vmlinux.default_lma + vmlinux.image_size, 0, vmlinux.bss_size);
}
+/*
+ * Set vmalloc area size to an 8th of (potential) physical memory
+ * size, unless size has been set by kernel command line parameter.
+ */
+static void setup_vmalloc_size(void)
+{
+ unsigned long size;
+
+ if (vmalloc_size_set)
+ return;
+ size = round_up(ident_map_size / 8, _SEGMENT_SIZE);
+ vmalloc_size = max(size, vmalloc_size);
+}
+
void startup_kernel(void)
{
unsigned long random_lma;
unsigned long safe_addr;
void *img;
+ setup_lpp();
store_ipl_parmblock();
safe_addr = mem_safe_offset();
safe_addr = read_ipl_report(safe_addr);
@@ -140,8 +206,8 @@ void startup_kernel(void)
sclp_early_read_info();
setup_boot_command_line();
parse_boot_command_line();
- setup_memory_end();
- detect_memory();
+ setup_ident_map_size(detect_memory());
+ setup_vmalloc_size();
random_lma = __kaslr_offset = 0;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index fe6f529ac82c..c52113a238b1 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -826,6 +826,7 @@ CONFIG_FTRACE_SYSCALLS=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_BPF_KPROBE_OVERRIDE=y
CONFIG_HIST_TRIGGERS=y
+CONFIG_DEBUG_USER_ASCE=y
CONFIG_NOTIFIER_ERROR_INJECTION=m
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
diff --git a/arch/s390/crypto/arch_random.c b/arch/s390/crypto/arch_random.c
index dd95cdbd22ce..7b947728d57e 100644
--- a/arch/s390/crypto/arch_random.c
+++ b/arch/s390/crypto/arch_random.c
@@ -2,7 +2,7 @@
/*
* s390 arch random implementation.
*
- * Copyright IBM Corp. 2017, 2018
+ * Copyright IBM Corp. 2017, 2020
* Author(s): Harald Freudenberger
*
* The s390_arch_random_generate() function may be called from random.c
@@ -33,6 +33,7 @@
#include <linux/slab.h>
#include <linux/static_key.h>
#include <linux/workqueue.h>
+#include <linux/moduleparam.h>
#include <asm/cpacf.h>
DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
@@ -99,6 +100,113 @@ static void arch_rng_refill_buffer(struct work_struct *unused)
queue_delayed_work(system_long_wq, &arch_rng_work, delay);
}
+/*
+ * Here follows the implementation of s390_arch_get_random_long().
+ *
+ * The random longs to be pulled by arch_get_random_long() are
+ * prepared in an 4K buffer which is filled from the NIST 800-90
+ * compliant s390 drbg. By default the random long buffer is refilled
+ * 256 times before the drbg itself needs a reseed. The reseed of the
+ * drbg is done with 32 bytes fetched from the high quality (but slow)
+ * trng which is assumed to deliver 100% entropy. So the 32 * 8 = 256
+ * bits of entropy are spread over 256 * 4KB = 1MB serving 131072
+ * arch_get_random_long() invocations before reseeded.
+ *
+ * How often the 4K random long buffer is refilled with the drbg
+ * before the drbg is reseeded can be adjusted. There is a module
+ * parameter 's390_arch_rnd_long_drbg_reseed' accessible via
+ * /sys/module/arch_random/parameters/rndlong_drbg_reseed
+ * or as kernel command line parameter
+ * arch_random.rndlong_drbg_reseed=<value>
+ * This parameter tells how often the drbg fills the 4K buffer before
+ * it is re-seeded by fresh entropy from the trng.
+ * A value of 16 results in reseeding the drbg at every 16 * 4 KB = 64
+ * KB with 32 bytes of fresh entropy pulled from the trng. So a value
+ * of 16 would result in 256 bits entropy per 64 KB.
+ * A value of 256 results in 1MB of drbg output before a reseed of the
+ * drbg is done. So this would spread the 256 bits of entropy among 1MB.
+ * Setting this parameter to 0 forces the reseed to take place every
+ * time the 4K buffer is depleted, so the entropy rises to 256 bits
+ * entropy per 4K or 0.5 bit entropy per arch_get_random_long(). With
+ * setting this parameter to negative values all this effort is
+ * disabled, arch_get_random long() returns false and thus indicating
+ * that the arch_get_random_long() feature is disabled at all.
+ */
+
+static unsigned long rndlong_buf[512];
+static DEFINE_SPINLOCK(rndlong_lock);
+static int rndlong_buf_index;
+
+static int rndlong_drbg_reseed = 256;
+module_param_named(rndlong_drbg_reseed, rndlong_drbg_reseed, int, 0600);
+MODULE_PARM_DESC(rndlong_drbg_reseed, "s390 arch_get_random_long() drbg reseed");
+
+static inline void refill_rndlong_buf(void)
+{
+ static u8 prng_ws[240];
+ static int drbg_counter;
+
+ if (--drbg_counter < 0) {
+ /* need to re-seed the drbg */
+ u8 seed[32];
+
+ /* fetch seed from trng */
+ cpacf_trng(NULL, 0, seed, sizeof(seed));
+ /* seed drbg */
+ memset(prng_ws, 0, sizeof(prng_ws));
+ cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
+ &prng_ws, NULL, 0, seed, sizeof(seed));
+ /* re-init counter for drbg */
+ drbg_counter = rndlong_drbg_reseed;
+ }
+
+ /* fill the arch_get_random_long buffer from drbg */
+ cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, &prng_ws,
+ (u8 *) rndlong_buf, sizeof(rndlong_buf),
+ NULL, 0);
+}
+
+bool s390_arch_get_random_long(unsigned long *v)
+{
+ bool rc = false;
+ unsigned long flags;
+
+ /* arch_get_random_long() disabled ? */
+ if (rndlong_drbg_reseed < 0)
+ return false;
+
+ /* try to lock the random long lock */
+ if (!spin_trylock_irqsave(&rndlong_lock, flags))
+ return false;
+
+ if (--rndlong_buf_index >= 0) {
+ /* deliver next long value from the buffer */
+ *v = rndlong_buf[rndlong_buf_index];
+ rc = true;
+ goto out;
+ }
+
+ /* buffer is depleted and needs refill */
+ if (in_interrupt()) {
+ /* delay refill in interrupt context to next caller */
+ rndlong_buf_index = 0;
+ goto out;
+ }
+
+ /* refill random long buffer */
+ refill_rndlong_buf();
+ rndlong_buf_index = ARRAY_SIZE(rndlong_buf);
+
+ /* and provide one random long */
+ *v = rndlong_buf[--rndlong_buf_index];
+ rc = true;
+
+out:
+ spin_unlock_irqrestore(&rndlong_lock, flags);
+ return rc;
+}
+EXPORT_SYMBOL(s390_arch_get_random_long);
+
static int __init s390_arch_random_init(void)
{
/* all the needed PRNO subfunctions available ? */
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index 5057773f82e9..b2f219ec379c 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -674,20 +674,6 @@ static const struct file_operations prng_tdes_fops = {
.llseek = noop_llseek,
};
-static struct miscdevice prng_sha512_dev = {
- .name = "prandom",
- .minor = MISC_DYNAMIC_MINOR,
- .mode = 0644,
- .fops = &prng_sha512_fops,
-};
-static struct miscdevice prng_tdes_dev = {
- .name = "prandom",
- .minor = MISC_DYNAMIC_MINOR,
- .mode = 0644,
- .fops = &prng_tdes_fops,
-};
-
-
/* chunksize attribute (ro) */
static ssize_t prng_chunksize_show(struct device *dev,
struct device_attribute *attr,
@@ -801,18 +787,30 @@ static struct attribute *prng_sha512_dev_attrs[] = {
&dev_attr_strength.attr,
NULL
};
+ATTRIBUTE_GROUPS(prng_sha512_dev);
+
static struct attribute *prng_tdes_dev_attrs[] = {
&dev_attr_chunksize.attr,
&dev_attr_byte_counter.attr,
&dev_attr_mode.attr,
NULL
};
+ATTRIBUTE_GROUPS(prng_tdes_dev);
-static struct attribute_group prng_sha512_dev_attr_group = {
- .attrs = prng_sha512_dev_attrs
+static struct miscdevice prng_sha512_dev = {
+ .name = "prandom",
+ .minor = MISC_DYNAMIC_MINOR,
+ .mode = 0644,
+ .fops = &prng_sha512_fops,
+ .groups = prng_sha512_dev_groups,
};
-static struct attribute_group prng_tdes_dev_attr_group = {
- .attrs = prng_tdes_dev_attrs
+
+static struct miscdevice prng_tdes_dev = {
+ .name = "prandom",
+ .minor = MISC_DYNAMIC_MINOR,
+ .mode = 0644,
+ .fops = &prng_tdes_fops,
+ .groups = prng_tdes_dev_groups,
};
@@ -867,13 +865,6 @@ static int __init prng_init(void)
prng_sha512_deinstantiate();
goto out;
}
- ret = sysfs_create_group(&prng_sha512_dev.this_device->kobj,
- &prng_sha512_dev_attr_group);
- if (ret) {
- misc_deregister(&prng_sha512_dev);
- prng_sha512_deinstantiate();
- goto out;
- }
} else {
@@ -898,14 +889,6 @@ static int __init prng_init(void)
prng_tdes_deinstantiate();
goto out;
}
- ret = sysfs_create_group(&prng_tdes_dev.this_device->kobj,
- &prng_tdes_dev_attr_group);
- if (ret) {
- misc_deregister(&prng_tdes_dev);
- prng_tdes_deinstantiate();
- goto out;
- }
-
}
out:
@@ -916,13 +899,9 @@ out:
static void __exit prng_exit(void)
{
if (prng_mode == PRNG_MODE_SHA512) {
- sysfs_remove_group(&prng_sha512_dev.this_device->kobj,
- &prng_sha512_dev_attr_group);
misc_deregister(&prng_sha512_dev);
prng_sha512_deinstantiate();
} else {
- sysfs_remove_group(&prng_tdes_dev.this_device->kobj,
- &prng_tdes_dev_attr_group);
misc_deregister(&prng_tdes_dev);
prng_tdes_deinstantiate();
}
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index de61ce562052..5dc712fde3c7 100644
--- a/arch/s390/include/asm/archrandom.h
+++ b/arch/s390/include/asm/archrandom.h
@@ -2,7 +2,7 @@
/*
* Kernel interface for the s390 arch_random_* functions
*
- * Copyright IBM Corp. 2017
+ * Copyright IBM Corp. 2017, 2020
*
* Author: Harald Freudenberger <freude@de.ibm.com>
*
@@ -19,10 +19,13 @@
DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
extern atomic64_t s390_arch_random_counter;
+bool s390_arch_get_random_long(unsigned long *v);
bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
static inline bool __must_check arch_get_random_long(unsigned long *v)
{
+ if (static_branch_likely(&s390_arch_random_available))
+ return s390_arch_get_random_long(v);
return false;
}
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index c0be5fe1ddba..e3e2ab0acf83 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -115,7 +115,7 @@ enum uc_todo {
};
/**
- * struct ccw driver - device driver for channel attached devices
+ * struct ccw_driver - device driver for channel attached devices
* @ids: ids supported by this driver
* @probe: function called on probe
* @remove: function called on remove
@@ -124,11 +124,6 @@ enum uc_todo {
* @notify: notify driver of device state changes
* @path_event: notify driver of channel path events
* @shutdown: called at device shutdown
- * @prepare: prepare for pm state transition
- * @complete: undo work done in @prepare
- * @freeze: callback for freezing during hibernation snapshotting
- * @thaw: undo work done in @freeze
- * @restore: callback for restoring after hibernation
* @uc_handler: callback for unit check handler
* @driver: embedded device driver structure
* @int_class: interruption class to use for accounting interrupts
@@ -142,11 +137,6 @@ struct ccw_driver {
int (*notify) (struct ccw_device *, int);
void (*path_event) (struct ccw_device *, int *);
void (*shutdown) (struct ccw_device *);
- int (*prepare) (struct ccw_device *);
- void (*complete) (struct ccw_device *);
- int (*freeze)(struct ccw_device *);
- int (*thaw) (struct ccw_device *);
- int (*restore)(struct ccw_device *);
enum uc_todo (*uc_handler) (struct ccw_device *, struct irb *);
struct device_driver driver;
enum interruption_class int_class;
diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index 5c58756d6476..23dceb8d0453 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -329,7 +329,7 @@ struct ccw_dev_id {
};
/**
- * ccw_device_id_is_equal() - compare two ccw_dev_ids
+ * ccw_dev_id_is_equal() - compare two ccw_dev_ids
* @dev_id1: a ccw_dev_id
* @dev_id2: another ccw_dev_id
* Returns:
diff --git a/arch/s390/include/asm/delay.h b/arch/s390/include/asm/delay.h
index 898323fd93d2..4a08379cd1eb 100644
--- a/arch/s390/include/asm/delay.h
+++ b/arch/s390/include/asm/delay.h
@@ -13,6 +13,7 @@
#ifndef _S390_DELAY_H
#define _S390_DELAY_H
+void udelay_enable(void);
void __ndelay(unsigned long long nsecs);
void __udelay(unsigned long long usecs);
void udelay_simple(unsigned long long usecs);
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 68d362f8d6c1..695c61989f97 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -2,16 +2,9 @@
#ifndef _ASM_S390_FTRACE_H
#define _ASM_S390_FTRACE_H
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
#define ARCH_SUPPORTS_FTRACE_OPS 1
-
-#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)
#define MCOUNT_INSN_SIZE 6
-#else
-#define MCOUNT_INSN_SIZE 24
-#define MCOUNT_RETURN_FIXUP 18
-#endif
-
-#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
#ifndef __ASSEMBLY__
@@ -22,7 +15,6 @@
#define ftrace_return_address(n) __builtin_return_address(n)
#endif
-void _mcount(void);
void ftrace_caller(void);
extern char ftrace_graph_caller_end;
@@ -30,12 +22,20 @@ extern unsigned long ftrace_plt;
struct dyn_arch_ftrace { };
-#define MCOUNT_ADDR ((unsigned long)_mcount)
+#define MCOUNT_ADDR 0
#define FTRACE_ADDR ((unsigned long)ftrace_caller)
#define KPROBE_ON_FTRACE_NOP 0
#define KPROBE_ON_FTRACE_CALL 1
+struct module;
+struct dyn_ftrace;
+/*
+ * Either -mhotpatch or -mnop-mcount is used - no explicit init is required
+ */
+static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { return 0; }
+#define ftrace_init_nop ftrace_init_nop
+
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
return addr;
@@ -49,28 +49,17 @@ struct ftrace_insn {
static inline void ftrace_generate_nop_insn(struct ftrace_insn *insn)
{
#ifdef CONFIG_FUNCTION_TRACER
-#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)
/* brcl 0,0 */
insn->opc = 0xc004;
insn->disp = 0;
-#else
- /* jg .+24 */
- insn->opc = 0xc0f4;
- insn->disp = MCOUNT_INSN_SIZE / 2;
-#endif
#endif
}
static inline int is_ftrace_nop(struct ftrace_insn *insn)
{
#ifdef CONFIG_FUNCTION_TRACER
-#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)
if (insn->disp == 0)
return 1;
-#else
- if (insn->disp == MCOUNT_INSN_SIZE / 2)
- return 1;
-#endif
#endif
return 0;
}
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 26f9144562c9..c22debfcebf1 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -26,9 +26,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
u32 __user *uaddr)
{
int oldval = 0, newval, ret;
- mm_segment_t old_fs;
- old_fs = enable_sacf_uaccess();
switch (op) {
case FUTEX_OP_SET:
__futex_atomic_op("lr %2,%5\n",
@@ -53,7 +51,6 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
default:
ret = -ENOSYS;
}
- disable_sacf_uaccess(old_fs);
if (!ret)
*oval = oldval;
@@ -64,10 +61,8 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
u32 oldval, u32 newval)
{
- mm_segment_t old_fs;
int ret;
- old_fs = enable_sacf_uaccess();
asm volatile(
" sacf 256\n"
"0: cs %1,%4,0(%5)\n"
@@ -77,7 +72,6 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
: "=d" (ret), "+d" (oldval), "=m" (*uaddr)
: "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr)
: "cc", "memory");
- disable_sacf_uaccess(old_fs);
*uval = oldval;
return ret;
}
diff --git a/arch/s390/include/asm/kasan.h b/arch/s390/include/asm/kasan.h
index e9bf486de136..76f351bd6645 100644
--- a/arch/s390/include/asm/kasan.h
+++ b/arch/s390/include/asm/kasan.h
@@ -2,28 +2,51 @@
#ifndef __ASM_KASAN_H
#define __ASM_KASAN_H
+#include <asm/pgtable.h>
+
#ifdef CONFIG_KASAN
#define KASAN_SHADOW_SCALE_SHIFT 3
-#ifdef CONFIG_KASAN_S390_4_LEVEL_PAGING
#define KASAN_SHADOW_SIZE \
(_AC(1, UL) << (_REGION1_SHIFT - KASAN_SHADOW_SCALE_SHIFT))
-#else
-#define KASAN_SHADOW_SIZE \
- (_AC(1, UL) << (_REGION2_SHIFT - KASAN_SHADOW_SCALE_SHIFT))
-#endif
#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
#define KASAN_SHADOW_START KASAN_SHADOW_OFFSET
#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
extern void kasan_early_init(void);
-extern void kasan_copy_shadow(pgd_t *dst);
+extern void kasan_copy_shadow_mapping(void);
extern void kasan_free_early_identity(void);
extern unsigned long kasan_vmax;
+
+/*
+ * Estimate kasan memory requirements, which it will reserve
+ * at the very end of available physical memory. To estimate
+ * that, we take into account that kasan would require
+ * 1/8 of available physical memory (for shadow memory) +
+ * creating page tables for the whole memory + shadow memory
+ * region (1 + 1/8). To keep page tables estimates simple take
+ * the double of combined ptes size.
+ *
+ * physmem parameter has to be already adjusted if not entire physical memory
+ * would be used (e.g. due to effect of "mem=" option).
+ */
+static inline unsigned long kasan_estimate_memory_needs(unsigned long physmem)
+{
+ unsigned long kasan_needs;
+ unsigned long pages;
+ /* for shadow memory */
+ kasan_needs = round_up(physmem / 8, PAGE_SIZE);
+ /* for paging structures */
+ pages = DIV_ROUND_UP(physmem + kasan_needs, PAGE_SIZE);
+ kasan_needs += DIV_ROUND_UP(pages, _PAGE_ENTRIES) * _PAGE_TABLE_SIZE * 2;
+
+ return kasan_needs;
+}
#else
static inline void kasan_early_init(void) { }
-static inline void kasan_copy_shadow(pgd_t *dst) { }
+static inline void kasan_copy_shadow_mapping(void) { }
static inline void kasan_free_early_identity(void) { }
+static inline unsigned long kasan_estimate_memory_needs(unsigned long physmem) { return 0; }
#endif
#endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 612ed3c6d581..69ce9191eaf1 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -116,7 +116,7 @@ struct lowcore {
/* Address space pointer. */
__u64 kernel_asce; /* 0x0380 */
__u64 user_asce; /* 0x0388 */
- __u64 vdso_asce; /* 0x0390 */
+ __u8 pad_0x0390[0x0398-0x0390]; /* 0x0390 */
/*
* The lpp and current_pid fields form a
@@ -134,7 +134,7 @@ struct lowcore {
__u32 spinlock_index; /* 0x03b0 */
__u32 fpu_flags; /* 0x03b4 */
__u64 percpu_offset; /* 0x03b8 */
- __u64 vdso_per_cpu_data; /* 0x03c0 */
+ __u8 pad_0x03c0[0x03c8-0x03c0]; /* 0x03c0 */
__u64 machine_flags; /* 0x03c8 */
__u64 gmap; /* 0x03d0 */
__u8 pad_0x03d8[0x0400-0x03d8]; /* 0x03d8 */
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index c9f3d8a52756..5dc49c467319 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -71,39 +71,18 @@ static inline int init_new_context(struct task_struct *tsk,
#define destroy_context(mm) do { } while (0)
-static inline void set_user_asce(struct mm_struct *mm)
-{
- S390_lowcore.user_asce = mm->context.asce;
- __ctl_load(S390_lowcore.user_asce, 1, 1);
- clear_cpu_flag(CIF_ASCE_PRIMARY);
-}
-
-static inline void clear_user_asce(void)
-{
- S390_lowcore.user_asce = S390_lowcore.kernel_asce;
- __ctl_load(S390_lowcore.kernel_asce, 1, 1);
- set_cpu_flag(CIF_ASCE_PRIMARY);
-}
-
-mm_segment_t enable_sacf_uaccess(void);
-void disable_sacf_uaccess(mm_segment_t old_fs);
-
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
int cpu = smp_processor_id();
- S390_lowcore.user_asce = next->context.asce;
+ if (next == &init_mm)
+ S390_lowcore.user_asce = s390_invalid_asce;
+ else
+ S390_lowcore.user_asce = next->context.asce;
cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
- /* Clear previous user-ASCE from CR1 and CR7 */
- if (!test_cpu_flag(CIF_ASCE_PRIMARY)) {
- __ctl_load(S390_lowcore.kernel_asce, 1, 1);
- set_cpu_flag(CIF_ASCE_PRIMARY);
- }
- if (test_cpu_flag(CIF_ASCE_SECONDARY)) {
- __ctl_load(S390_lowcore.vdso_asce, 7, 7);
- clear_cpu_flag(CIF_ASCE_SECONDARY);
- }
+ /* Clear previous user-ASCE from CR7 */
+ __ctl_load(s390_invalid_asce, 7, 7);
if (prev != next)
cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
}
@@ -122,7 +101,7 @@ static inline void finish_arch_post_lock_switch(void)
__tlb_flush_mm_lazy(mm);
preempt_enable();
}
- set_fs(current->thread.mm_segment);
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
}
#define enter_lazy_tlb(mm,tsk) do { } while (0)
@@ -133,7 +112,7 @@ static inline void activate_mm(struct mm_struct *prev,
{
switch_mm(prev, next, current);
cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
- set_user_asce(next);
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
}
#endif /* __S390_MMU_CONTEXT_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index b5dbae78969b..794746a32806 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -23,6 +23,7 @@
extern pgd_t swapper_pg_dir[];
extern void paging_init(void);
+extern unsigned long s390_invalid_asce;
enum {
PG_DIRECT_MAP_4K = 0,
@@ -79,15 +80,15 @@ extern unsigned long zero_page_mask;
/*
* The vmalloc and module area will always be on the topmost area of the
- * kernel mapping. We reserve 128GB (64bit) for vmalloc and modules.
- * On 64 bit kernels we have a 2GB area at the top of the vmalloc area where
- * modules will reside. That makes sure that inter module branches always
- * happen without trampolines and in addition the placement within a 2GB frame
- * is branch prediction unit friendly.
+ * kernel mapping. 512GB are reserved for vmalloc by default.
+ * At the top of the vmalloc area a 2GB area is reserved where modules
+ * will reside. That makes sure that inter module branches always
+ * happen without trampolines and in addition the placement within a
+ * 2GB frame is branch prediction unit friendly.
*/
extern unsigned long VMALLOC_START;
extern unsigned long VMALLOC_END;
-#define VMALLOC_DEFAULT_SIZE ((128UL << 30) - MODULES_LEN)
+#define VMALLOC_DEFAULT_SIZE ((512UL << 30) - MODULES_LEN)
extern struct page *vmemmap;
extern unsigned long vmemmap_size;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 962da04234af..6b7269f51f83 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -14,8 +14,6 @@
#include <linux/bits.h>
-#define CIF_ASCE_PRIMARY 0 /* primary asce needs fixup / uaccess */
-#define CIF_ASCE_SECONDARY 1 /* secondary asce needs fixup / uaccess */
#define CIF_NOHZ_DELAY 2 /* delay HZ disable for a tick */
#define CIF_FPU 3 /* restore FPU registers */
#define CIF_IGNORE_IRQ 4 /* ignore interrupt (for udelay) */
@@ -23,8 +21,6 @@
#define CIF_MCCK_GUEST 6 /* machine check happening in guest */
#define CIF_DEDICATED_CPU 7 /* this CPU is dedicated */
-#define _CIF_ASCE_PRIMARY BIT(CIF_ASCE_PRIMARY)
-#define _CIF_ASCE_SECONDARY BIT(CIF_ASCE_SECONDARY)
#define _CIF_NOHZ_DELAY BIT(CIF_NOHZ_DELAY)
#define _CIF_FPU BIT(CIF_FPU)
#define _CIF_IGNORE_IRQ BIT(CIF_IGNORE_IRQ)
@@ -102,8 +98,6 @@ extern void __bpon(void);
#define HAVE_ARCH_PICK_MMAP_LAYOUT
-typedef unsigned int mm_segment_t;
-
/*
* Thread structure
*/
@@ -116,7 +110,6 @@ struct thread_struct {
unsigned long hardirq_timer; /* task cputime in hardirq context */
unsigned long softirq_timer; /* task cputime in softirq context */
unsigned long sys_call_table; /* system call table address */
- mm_segment_t mm_segment;
unsigned long gmap_addr; /* address of last gmap fault. */
unsigned int gmap_write_flag; /* gmap fault write indication */
unsigned int gmap_int_code; /* int code of last gmap fault */
@@ -318,14 +311,10 @@ static __always_inline void __noreturn disabled_wait(void)
}
/*
- * Basic Machine Check/Program Check Handler.
+ * Basic Program Check Handler.
*/
-
extern void s390_base_pgm_handler(void);
-extern void s390_base_ext_handler(void);
-
extern void (*s390_base_pgm_handler_fn)(void);
-extern void (*s390_base_ext_handler_fn)(void);
#define ARCH_LOW_ADDRESS_LIMIT 0x7fffffffUL
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 16b3e4396312..73ca7f7cac33 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -87,6 +87,7 @@ struct pt_regs
unsigned int int_parm;
unsigned long int_parm_long;
unsigned long flags;
+ unsigned long cr1;
};
/*
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index a7bdd128d85b..5763769a39b6 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -12,7 +12,12 @@
#include <asm/cpu.h>
#define SCLP_CHP_INFO_MASK_SIZE 32
-#define SCLP_MAX_CORES 256
+#define EARLY_SCCB_SIZE PAGE_SIZE
+#define SCLP_MAX_CORES 512
+/* 144 + 16 * SCLP_MAX_CORES + 2 * (SCLP_MAX_CORES - 1) */
+#define EXT_SCCB_READ_SCP (3 * PAGE_SIZE)
+/* 24 + 16 * SCLP_MAX_CORES */
+#define EXT_SCCB_READ_CPU (3 * PAGE_SIZE)
struct sclp_chp_info {
u8 recognized[SCLP_CHP_INFO_MASK_SIZE];
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index bdb242a1544e..3e388fa208d4 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -16,8 +16,6 @@
#define EARLY_SCCB_OFFSET 0x11000
#define HEAD_END 0x12000
-#define EARLY_SCCB_SIZE PAGE_SIZE
-
/*
* Machine features detected in early.c
*/
@@ -88,10 +86,8 @@ extern unsigned int zlib_dfltcc_support;
#define ZLIB_DFLTCC_FULL_DEBUG 4
extern int noexec_disabled;
-extern int memory_end_set;
-extern unsigned long memory_end;
+extern unsigned long ident_map_size;
extern unsigned long vmalloc_size;
-extern unsigned long max_physmem_end;
/* The Write Back bit position in the physaddr is given by the SLPC PCI */
extern unsigned long mio_wb_bit_mask;
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 13a04fcf7762..ce788f3e534d 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -18,7 +18,7 @@
#else
#define THREAD_SIZE_ORDER 2
#endif
-#define BOOT_STACK_ORDER 2
+#define BOOT_STACK_SIZE (PAGE_SIZE << 2)
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
#ifndef __ASSEMBLY__
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index 289aaff4d365..c8e244ecdfde 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -49,6 +49,13 @@ static inline void set_clock_comparator(__u64 time)
asm volatile("sckc %0" : : "Q" (time));
}
+static inline void set_tod_programmable_field(u16 val)
+{
+ register unsigned long reg0 asm("0") = val;
+
+ asm volatile("sckpf" : : "d" (reg0));
+}
+
void clock_comparator_work(void);
void __init time_early_init(void);
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index c868e7ee49b3..c6707885e7c2 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -18,23 +18,7 @@
#include <asm/extable.h>
#include <asm/facility.h>
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not. If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define KERNEL_DS (0)
-#define KERNEL_DS_SACF (1)
-#define USER_DS (2)
-#define USER_DS_SACF (3)
-
-#define get_fs() (current->thread.mm_segment)
-#define uaccess_kernel() ((get_fs() & 2) == KERNEL_DS)
-
-void set_fs(mm_segment_t fs);
+void debug_user_asce(void);
static inline int __range_ok(unsigned long addr, unsigned long size)
{
@@ -88,7 +72,7 @@ int __get_user_bad(void) __attribute__((noreturn));
static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
{
- unsigned long spec = 0x010000UL;
+ unsigned long spec = 0x810000UL;
int rc;
switch (size) {
@@ -121,7 +105,7 @@ static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned lon
static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
{
- unsigned long spec = 0x01UL;
+ unsigned long spec = 0x81UL;
int rc;
switch (size) {
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
index 29b44a930e71..f65590889054 100644
--- a/arch/s390/include/asm/vdso.h
+++ b/arch/s390/include/asm/vdso.h
@@ -12,32 +12,9 @@
#ifndef __ASSEMBLY__
-/*
- * Note about the vdso_data and vdso_per_cpu_data structures:
- *
- * NEVER USE THEM IN USERSPACE CODE DIRECTLY. The layout of the
- * structure is supposed to be known only to the function in the vdso
- * itself and may change without notice.
- */
-
-struct vdso_per_cpu_data {
- /*
- * Note: node_id and cpu_nr must be at adjacent memory locations.
- * VDSO userspace must read both values with a single instruction.
- */
- union {
- __u64 getcpu_val;
- struct {
- __u32 node_id;
- __u32 cpu_nr;
- };
- };
-};
-
extern struct vdso_data *vdso_data;
-int vdso_alloc_per_cpu(struct lowcore *lowcore);
-void vdso_free_per_cpu(struct lowcore *lowcore);
+void vdso_getcpu_init(void);
#endif /* __ASSEMBLY__ */
#endif /* __S390_VDSO_H__ */
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 483051e10db3..79724d861dc9 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -13,7 +13,6 @@
#include <linux/purgatory.h>
#include <linux/pgtable.h>
#include <asm/idle.h>
-#include <asm/vdso.h>
#include <asm/gmap.h>
#include <asm/nmi.h>
#include <asm/stacktrace.h>
@@ -48,6 +47,7 @@ int main(void)
OFFSET(__PT_INT_PARM, pt_regs, int_parm);
OFFSET(__PT_INT_PARM_LONG, pt_regs, int_parm_long);
OFFSET(__PT_FLAGS, pt_regs, flags);
+ OFFSET(__PT_CR1, pt_regs, cr1);
DEFINE(__PT_SIZE, sizeof(struct pt_regs));
BLANK();
/* stack_frame offsets */
@@ -59,8 +59,6 @@ int main(void)
OFFSET(__SF_SIE_REASON, stack_frame, empty1[3]);
OFFSET(__SF_SIE_FLAGS, stack_frame, empty1[4]);
BLANK();
- OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val);
- BLANK();
/* idle data offsets */
OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter);
OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit);
@@ -138,12 +136,11 @@ int main(void)
OFFSET(__LC_RESTART_FN, lowcore, restart_fn);
OFFSET(__LC_RESTART_DATA, lowcore, restart_data);
OFFSET(__LC_RESTART_SOURCE, lowcore, restart_source);
+ OFFSET(__LC_KERNEL_ASCE, lowcore, kernel_asce);
OFFSET(__LC_USER_ASCE, lowcore, user_asce);
- OFFSET(__LC_VDSO_ASCE, lowcore, vdso_asce);
OFFSET(__LC_LPP, lowcore, lpp);
OFFSET(__LC_CURRENT_PID, lowcore, current_pid);
OFFSET(__LC_PERCPU_OFFSET, lowcore, percpu_offset);
- OFFSET(__LC_VDSO_PER_CPU, lowcore, vdso_per_cpu_data);
OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags);
OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count);
OFFSET(__LC_GMAP, lowcore, gmap);
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index b79e0fd571f8..d255c69c1779 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -11,32 +11,10 @@
#include <asm/asm-offsets.h>
#include <asm/nospec-insn.h>
#include <asm/ptrace.h>
-#include <asm/sigp.h>
GEN_BR_THUNK %r9
GEN_BR_THUNK %r14
-ENTRY(s390_base_ext_handler)
- stmg %r0,%r15,__LC_SAVE_AREA_ASYNC
- basr %r13,0
-0: aghi %r15,-STACK_FRAME_OVERHEAD
- larl %r1,s390_base_ext_handler_fn
- lg %r9,0(%r1)
- ltgr %r9,%r9
- jz 1f
- BASR_EX %r14,%r9
-1: lmg %r0,%r15,__LC_SAVE_AREA_ASYNC
- ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit
- lpswe __LC_EXT_OLD_PSW
-ENDPROC(s390_base_ext_handler)
-
- .section .bss
- .align 8
- .globl s390_base_ext_handler_fn
-s390_base_ext_handler_fn:
- .quad 0
- .previous
-
ENTRY(s390_base_pgm_handler)
stmg %r0,%r15,__LC_SAVE_AREA_SYNC
basr %r13,0
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 705844f73934..cc89763a4d3c 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -169,12 +169,10 @@ static noinline __init void setup_lowcore_early(void)
{
psw_t psw;
+ psw.addr = (unsigned long)s390_base_pgm_handler;
psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
if (IS_ENABLED(CONFIG_KASAN))
psw.mask |= PSW_MASK_DAT;
- psw.addr = (unsigned long) s390_base_ext_handler;
- S390_lowcore.external_new_psw = psw;
- psw.addr = (unsigned long) s390_base_pgm_handler;
S390_lowcore.program_new_psw = psw;
s390_base_pgm_handler_fn = early_pgm_check_handler;
S390_lowcore.preempt_count = INIT_PREEMPT_COUNT;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 92beb1444644..8bb9ebb71c4b 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -55,7 +55,7 @@ _TIF_WORK = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
_TIF_UPROBE | _TIF_GUARDED_STORAGE | _TIF_PATCH_PENDING)
_TIF_TRACE = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
_TIF_SYSCALL_TRACEPOINT)
-_CIF_WORK = (_CIF_ASCE_PRIMARY | _CIF_ASCE_SECONDARY | _CIF_FPU)
+_CIF_WORK = (_CIF_FPU)
_PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
_LPP_OFFSET = __LC_LPP
@@ -90,6 +90,12 @@ _LPP_OFFSET = __LC_LPP
#endif
.endm
+ .macro DEBUG_USER_ASCE
+#ifdef CONFIG_DEBUG_USER_ASCE
+ brasl %r14,debug_user_asce
+#endif
+ .endm
+
.macro CHECK_VMAP_STACK savearea,oklabel
#ifdef CONFIG_VMAP_STACK
lgr %r14,%r15
@@ -110,9 +116,9 @@ _LPP_OFFSET = __LC_LPP
#endif
.endm
- .macro SWITCH_ASYNC savearea,timer
+ .macro SWITCH_ASYNC savearea,timer,clock
tmhh %r8,0x0001 # interrupting from user ?
- jnz 2f
+ jnz 4f
#if IS_ENABLED(CONFIG_KVM)
lgr %r14,%r9
larl %r13,.Lsie_gmap
@@ -125,10 +131,26 @@ _LPP_OFFSET = __LC_LPP
#endif
0: larl %r13,.Lpsw_idle_exit
cgr %r13,%r9
- jne 1f
+ jne 3f
- mvc __CLOCK_IDLE_EXIT(8,%r2), __LC_INT_CLOCK
- mvc __TIMER_IDLE_EXIT(8,%r2), __LC_ASYNC_ENTER_TIMER
+ larl %r1,smp_cpu_mtid
+ llgf %r1,0(%r1)
+ ltgr %r1,%r1
+ jz 2f # no SMT, skip mt_cycles calculation
+ .insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+80(%r15)
+ larl %r3,mt_cycles
+ ag %r3,__LC_PERCPU_OFFSET
+ la %r4,__SF_EMPTY+16(%r15)
+1: lg %r0,0(%r3)
+ slg %r0,0(%r4)
+ alg %r0,64(%r4)
+ stg %r0,0(%r3)
+ la %r3,8(%r3)
+ la %r4,8(%r4)
+ brct %r1,1b
+
+2: mvc __CLOCK_IDLE_EXIT(8,%r2), \clock
+ mvc __TIMER_IDLE_EXIT(8,%r2), \timer
# account system time going idle
ni __LC_CPU_FLAGS+7,255-_CIF_ENABLED_WAIT
@@ -146,17 +168,17 @@ _LPP_OFFSET = __LC_LPP
mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2)
nihh %r8,0xfcfd # clear wait state and irq bits
-1: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
+3: lg %r14,__LC_ASYNC_STACK # are we already on the target stack?
slgr %r14,%r15
srag %r14,%r14,STACK_SHIFT
- jnz 3f
+ jnz 5f
CHECK_STACK \savearea
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- j 4f
-2: UPDATE_VTIME %r14,%r15,\timer
+ j 6f
+4: UPDATE_VTIME %r14,%r15,\timer
BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
-3: lg %r15,__LC_ASYNC_STACK # load async stack
-4: la %r11,STACK_FRAME_OVERHEAD(%r15)
+5: lg %r15,__LC_ASYNC_STACK # load async stack
+6: la %r11,STACK_FRAME_OVERHEAD(%r15)
.endm
.macro UPDATE_VTIME w1,w2,enter_timer
@@ -327,7 +349,7 @@ ENTRY(sie64a)
BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
.Lsie_skip:
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE # load primary asce
.Lsie_done:
# 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
@@ -380,6 +402,7 @@ ENTRY(system_call)
lg %r12,__LC_CURRENT
lghi %r14,_PIF_SYSCALL
.Lsysc_per:
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
lghi %r13,__TASK_thread
lg %r15,__LC_KERNEL_STACK
la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs
@@ -427,11 +450,9 @@ ENTRY(system_call)
jnz .Lsysc_work
TSTMSK __TI_flags(%r12),_TIF_WORK
jnz .Lsysc_work # check for work
- TSTMSK __LC_CPU_FLAGS,(_CIF_WORK-_CIF_FPU)
- jnz .Lsysc_work
+ DEBUG_USER_ASCE
+ lctlg %c1,%c1,__LC_USER_ASCE
BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
-.Lsysc_restore:
- DISABLE_INTS
TSTMSK __LC_CPU_FLAGS, _CIF_FPU
jz .Lsysc_skip_fpu
brasl %r14,load_fpu_regs
@@ -469,8 +490,6 @@ ENTRY(system_call)
jo .Lsysc_sigpending
TSTMSK __TI_flags(%r12),_TIF_NOTIFY_RESUME
jo .Lsysc_notify_resume
- TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
- jnz .Lsysc_asce
j .Lsysc_return
#
@@ -481,26 +500,6 @@ ENTRY(system_call)
jg schedule
#
-# _CIF_ASCE_PRIMARY and/or _CIF_ASCE_SECONDARY set, load user space asce
-#
-.Lsysc_asce:
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_SECONDARY
- lctlg %c7,%c7,__LC_VDSO_ASCE # load secondary asce
- TSTMSK __LC_CPU_FLAGS,_CIF_ASCE_PRIMARY
- jz .Lsysc_return
-#ifndef CONFIG_HAVE_MARCH_Z10_FEATURES
- tm __LC_STFLE_FAC_LIST+3,0x10 # has MVCOS ?
- jnz .Lsysc_set_fs_fixup
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
- j .Lsysc_return
-.Lsysc_set_fs_fixup:
-#endif
- larl %r14,.Lsysc_return
- jg set_fs_fixup
-
-
-#
# _TIF_SIGPENDING is set, call do_signal
#
.Lsysc_sigpending:
@@ -636,8 +635,11 @@ ENTRY(pgm_check_handler)
0: lg %r12,__LC_CURRENT
lghi %r11,0
lmg %r8,%r9,__LC_PGM_OLD_PSW
- tmhh %r8,0x0001 # test problem state bit
- jnz 3f # -> fault in user space
+ tmhh %r8,0x0001 # coming from user space?
+ jno .Lpgm_skip_asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
+ j 3f
+.Lpgm_skip_asce:
#if IS_ENABLED(CONFIG_KVM)
# cleanup critical section for program checks in sie64a
lgr %r14,%r9
@@ -648,7 +650,7 @@ ENTRY(pgm_check_handler)
jhe 1f
lg %r14,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE # load primary asce
larl %r9,sie_exit # skip forward to sie_exit
lghi %r11,_PIF_GUEST_FAULT
#endif
@@ -709,10 +711,20 @@ ENTRY(pgm_check_handler)
.Lpgm_return:
LOCKDEP_SYS_EXIT
tm __PT_PSW+1(%r11),0x01 # returning to user ?
- jno .Lsysc_restore
+ jno .Lpgm_restore
TSTMSK __PT_FLAGS(%r11),_PIF_SYSCALL
jo .Lsysc_do_syscall
j .Lsysc_tif
+.Lpgm_restore:
+ DISABLE_INTS
+ TSTMSK __LC_CPU_FLAGS, _CIF_FPU
+ jz .Lpgm_skip_fpu
+ brasl %r14,load_fpu_regs
+.Lpgm_skip_fpu:
+ mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
+ stpt __LC_EXIT_TIMER
+ lmg %r0,%r15,__PT_R0(%r11)
+ b __LC_RETURN_LPSWE
#
# PER event in supervisor state, must be kprobes
@@ -745,7 +757,7 @@ ENTRY(io_int_handler)
stmg %r8,%r15,__LC_SAVE_AREA_ASYNC
lg %r12,__LC_CURRENT
lmg %r8,%r9,__LC_IO_OLD_PSW
- SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
+ SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER,__LC_INT_CLOCK
stmg %r0,%r7,__PT_R0(%r11)
# clear user controlled registers to prevent speculative use
xgr %r0,%r0
@@ -759,6 +771,10 @@ ENTRY(io_int_handler)
xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
+ tm __PT_PSW+1(%r11),0x01 # coming from user space?
+ jno .Lio_skip_asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
+.Lio_skip_asce:
mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
TSTMSK __LC_CPU_FLAGS,_CIF_IGNORE_IRQ
@@ -790,6 +806,8 @@ ENTRY(io_int_handler)
mvc __LC_RETURN_PSW(16),__PT_PSW(%r11)
tm __PT_PSW+1(%r11),0x01 # returning to user ?
jno .Lio_exit_kernel
+ DEBUG_USER_ASCE
+ lctlg %c1,%c1,__LC_USER_ASCE
BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP
stpt __LC_EXIT_TIMER
.Lio_exit_kernel:
@@ -855,30 +873,9 @@ ENTRY(io_int_handler)
jo .Lio_guarded_storage
TSTMSK __LC_CPU_FLAGS,_CIF_FPU
jo .Lio_vxrs
- TSTMSK __LC_CPU_FLAGS,(_CIF_ASCE_PRIMARY|_CIF_ASCE_SECONDARY)
- jnz .Lio_asce
j .Lio_return
#
-# _CIF_ASCE_PRIMARY and/or CIF_ASCE_SECONDARY set, load user space asce
-#
-.Lio_asce:
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_SECONDARY
- lctlg %c7,%c7,__LC_VDSO_ASCE # load secondary asce
- TSTMSK __LC_CPU_FLAGS,_CIF_ASCE_PRIMARY
- jz .Lio_return
-#ifndef CONFIG_HAVE_MARCH_Z10_FEATURES
- tm __LC_STFLE_FAC_LIST+3,0x10 # has MVCOS ?
- jnz .Lio_set_fs_fixup
- ni __LC_CPU_FLAGS+7,255-_CIF_ASCE_PRIMARY
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
- j .Lio_return
-.Lio_set_fs_fixup:
-#endif
- larl %r14,.Lio_return
- jg set_fs_fixup
-
-#
# CIF_FPU is set, restore floating-point controls and floating-point registers.
#
.Lio_vxrs:
@@ -945,7 +942,7 @@ ENTRY(ext_int_handler)
stmg %r8,%r15,__LC_SAVE_AREA_ASYNC
lg %r12,__LC_CURRENT
lmg %r8,%r9,__LC_EXT_OLD_PSW
- SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER
+ SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER,__LC_INT_CLOCK
stmg %r0,%r7,__PT_R0(%r11)
# clear user controlled registers to prevent speculative use
xgr %r0,%r0
@@ -959,6 +956,10 @@ ENTRY(ext_int_handler)
xgr %r10,%r10
mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC
stmg %r8,%r9,__PT_PSW(%r11)
+ tm __PT_PSW+1(%r11),0x01 # coming from user space?
+ jno .Lext_skip_asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
+.Lext_skip_asce:
lghi %r1,__LC_EXT_PARAMS2
mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR
mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS
@@ -1167,7 +1168,7 @@ ENTRY(mcck_int_handler)
TSTMSK __LC_MCCK_CODE,MCCK_CODE_PSW_IA_VALID
jno .Lmcck_panic
4: ssm __LC_PGM_NEW_PSW # turn dat on, keep irqs off
- SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER
+ SWITCH_ASYNC __LC_GPREGS_SAVE_AREA+64,__LC_MCCK_ENTER_TIMER,__LC_MCCK_CLOCK
.Lmcck_skip:
lghi %r14,__LC_GPREGS_SAVE_AREA+64
stmg %r0,%r7,__PT_R0(%r11)
@@ -1183,6 +1184,9 @@ ENTRY(mcck_int_handler)
xgr %r10,%r10
mvc __PT_R8(64,%r11),0(%r14)
stmg %r8,%r9,__PT_PSW(%r11)
+ la %r14,4095
+ mvc __PT_CR1(8,%r11),__LC_CREGS_SAVE_AREA-4095+8(%r14)
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11)
xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
lgr %r2,%r11 # pass pointer to pt_regs
@@ -1198,6 +1202,7 @@ ENTRY(mcck_int_handler)
brasl %r14,s390_handle_mcck
TRACE_IRQS_ON
.Lmcck_return:
+ lctlg %c1,%c1,__PT_CR1(%r11)
lmg %r0,%r10,__PT_R0(%r11)
mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW
tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ?
@@ -1274,7 +1279,7 @@ ENDPROC(stack_overflow)
1: BPENTER __SF_SIE_FLAGS(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST)
lg %r9,__SF_SIE_CONTROL(%r15) # get control block pointer
ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE
- lctlg %c1,%c1,__LC_USER_ASCE # load primary asce
+ lctlg %c1,%c1,__LC_KERNEL_ASCE
larl %r9,sie_exit # skip forward to sie_exit
BR_EX %r14,%r11
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index d2ca3fe51f8e..a16c33b32ab0 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -83,7 +83,6 @@ long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user
DECLARE_PER_CPU(u64, mt_cycles[8]);
void gs_load_bc_cb(struct pt_regs *regs);
-void set_fs_fixup(void);
unsigned long stack_alloc(void);
void stack_free(unsigned long stack);
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index b388e87a08bf..ebc1284a618b 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -22,56 +22,26 @@
#include "entry.h"
/*
- * The mcount code looks like this:
- * stg %r14,8(%r15) # offset 0
- * larl %r1,<&counter> # offset 6
- * brasl %r14,_mcount # offset 12
- * lg %r14,8(%r15) # offset 18
- * Total length is 24 bytes. Only the first instruction will be patched
- * by ftrace_make_call / ftrace_make_nop.
- * The enabled ftrace code block looks like this:
+ * To generate function prologue either gcc's hotpatch feature (since gcc 4.8)
+ * or a combination of -pg -mrecord-mcount -mnop-mcount -mfentry flags
+ * (since gcc 9 / clang 10) is used.
+ * In both cases the original and also the disabled function prologue contains
+ * only a single six byte instruction and looks like this:
+ * > brcl 0,0 # offset 0
+ * To enable ftrace the code gets patched like above and afterwards looks
+ * like this:
* > brasl %r0,ftrace_caller # offset 0
- * larl %r1,<&counter> # offset 6
- * brasl %r14,_mcount # offset 12
- * lg %r14,8(%r15) # offset 18
+ *
+ * The instruction will be patched by ftrace_make_call / ftrace_make_nop.
* The ftrace function gets called with a non-standard C function call ABI
* where r0 contains the return address. It is also expected that the called
* function only clobbers r0 and r1, but restores r2-r15.
* For module code we can't directly jump to ftrace caller, but need a
* trampoline (ftrace_plt), which clobbers also r1.
- * The return point of the ftrace function has offset 24, so execution
- * continues behind the mcount block.
- * The disabled ftrace code block looks like this:
- * > jg .+24 # offset 0
- * larl %r1,<&counter> # offset 6
- * brasl %r14,_mcount # offset 12
- * lg %r14,8(%r15) # offset 18
- * The jg instruction branches to offset 24 to skip as many instructions
- * as possible.
- * In case we use gcc's hotpatch feature the original and also the disabled
- * function prologue contains only a single six byte instruction and looks
- * like this:
- * > brcl 0,0 # offset 0
- * To enable ftrace the code gets patched like above and afterwards looks
- * like this:
- * > brasl %r0,ftrace_caller # offset 0
*/
unsigned long ftrace_plt;
-static inline void ftrace_generate_orig_insn(struct ftrace_insn *insn)
-{
-#if defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT)
- /* brcl 0,0 */
- insn->opc = 0xc004;
- insn->disp = 0;
-#else
- /* stg r14,8(r15) */
- insn->opc = 0xe3e0;
- insn->disp = 0xf0080024;
-#endif
-}
-
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
@@ -85,15 +55,10 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
return -EFAULT;
- if (addr == MCOUNT_ADDR) {
- /* Initial code replacement */
- ftrace_generate_orig_insn(&orig);
- ftrace_generate_nop_insn(&new);
- } else {
- /* Replace ftrace call with a nop. */
- ftrace_generate_call_insn(&orig, rec->ip);
- ftrace_generate_nop_insn(&new);
- }
+ /* Replace ftrace call with a nop. */
+ ftrace_generate_call_insn(&orig, rec->ip);
+ ftrace_generate_nop_insn(&new);
+
/* Verify that the to be replaced code matches what we expect. */
if (memcmp(&orig, &old, sizeof(old)))
return -EINVAL;
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 8b88dbbda7df..0c253886da78 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -18,12 +18,7 @@
__HEAD
ENTRY(startup_continue)
- tm __LC_STFLE_FAC_LIST+5,0x80 # LPP available ?
- jz 0f
- xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid
- mvi __LC_LPP,0x80 # and set LPP_MAGIC
- .insn s,0xb2800000,__LC_LPP # load program parameter
-0: larl %r1,tod_clock_base
+ larl %r1,tod_clock_base
mvc 0(16,%r1),__LC_BOOT_CLOCK
larl %r13,.LPG1 # get base
#
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 7458dcfd6464..faf64c2f90f5 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -33,11 +33,6 @@ ENDPROC(ftrace_stub)
#define TRACED_FUNC_FRAME_SIZE STACK_FRAME_OVERHEAD
#endif
-ENTRY(_mcount)
- BR_EX %r14
-ENDPROC(_mcount)
-EXPORT_SYMBOL(_mcount)
-
ENTRY(ftrace_caller)
.globl ftrace_regs_caller
.set ftrace_regs_caller,ftrace_caller
@@ -46,9 +41,6 @@ ENTRY(ftrace_caller)
ipm %r14 # don't put any instructions
sllg %r14,%r14,16 # clobbering CC before this point
lgr %r1,%r15
-#if !(defined(CC_USING_HOTPATCH) || defined(CC_USING_NOP_MCOUNT))
- aghi %r0,MCOUNT_RETURN_FIXUP
-#endif
# allocate stack frame for ftrace_caller to contain traced function
aghi %r15,-TRACED_FUNC_FRAME_SIZE
stg %r1,__SF_BACKCHAIN(%r15)
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index ec801d3bbb37..bc3ca54edfb4 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -94,7 +94,6 @@ int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
/* Save access registers to new thread structure. */
save_access_regs(&p->thread.acrs[0]);
/* start new process with ar4 pointing to the correct address space */
- p->thread.mm_segment = get_fs();
/* Don't copy debug registers */
memset(&p->thread.per_user, 0, sizeof(p->thread.per_user));
memset(&p->thread.per_event, 0, sizeof(p->thread.per_event));
@@ -208,16 +207,3 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
ret = PAGE_ALIGN(mm->brk + brk_rnd());
return (ret > mm->brk) ? ret : mm->brk;
}
-
-void set_fs_fixup(void)
-{
- struct pt_regs *regs = current_pt_regs();
- static bool warned;
-
- set_fs(USER_DS);
- if (warned)
- return;
- WARN(1, "Unbalanced set_fs - int code: 0x%x\n", regs->int_code);
- show_registers(regs);
- warned = true;
-}
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4d843e64496f..1f16a03be995 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -49,6 +49,7 @@
#include <linux/memory.h>
#include <linux/compat.h>
#include <linux/start_kernel.h>
+#include <linux/hugetlb.h>
#include <asm/boot_data.h>
#include <asm/ipl.h>
@@ -94,10 +95,8 @@ char elf_platform[ELF_PLATFORM_SIZE];
unsigned long int_hwcap = 0;
int __bootdata(noexec_disabled);
-int __bootdata(memory_end_set);
-unsigned long __bootdata(memory_end);
+unsigned long __bootdata(ident_map_size);
unsigned long __bootdata(vmalloc_size);
-unsigned long __bootdata(max_physmem_end);
struct mem_detect_info __bootdata(mem_detect);
struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table);
@@ -336,6 +335,7 @@ int __init arch_early_irq_init(void)
if (!stack)
panic("Couldn't allocate async stack");
S390_lowcore.async_stack = stack + STACK_INIT_OFFSET;
+ udelay_enable();
return 0;
}
@@ -556,24 +556,25 @@ static void __init setup_resources(void)
#endif
}
-static void __init setup_memory_end(void)
+static void __init setup_ident_map_size(void)
{
unsigned long vmax, tmp;
/* Choose kernel address space layout: 3 or 4 levels. */
- tmp = (memory_end ?: max_physmem_end) / PAGE_SIZE;
+ tmp = ident_map_size / PAGE_SIZE;
tmp = tmp * (sizeof(struct page) + PAGE_SIZE);
if (tmp + vmalloc_size + MODULES_LEN <= _REGION2_SIZE)
vmax = _REGION2_SIZE; /* 3-level kernel page table */
else
vmax = _REGION1_SIZE; /* 4-level kernel page table */
+ /* module area is at the end of the kernel address space. */
+ MODULES_END = vmax;
if (is_prot_virt_host())
- adjust_to_uv_max(&vmax);
+ adjust_to_uv_max(&MODULES_END);
#ifdef CONFIG_KASAN
- vmax = kasan_vmax;
+ vmax = _REGION1_SIZE;
+ MODULES_END = kasan_vmax;
#endif
- /* module area is at the end of the kernel address space. */
- MODULES_END = vmax;
MODULES_VADDR = MODULES_END - MODULES_LEN;
VMALLOC_END = MODULES_VADDR;
VMALLOC_START = VMALLOC_END - vmalloc_size;
@@ -587,22 +588,22 @@ static void __init setup_memory_end(void)
tmp = min(tmp, 1UL << MAX_PHYSMEM_BITS);
vmemmap = (struct page *) tmp;
- /* Take care that memory_end is set and <= vmemmap */
- memory_end = min(memory_end ?: max_physmem_end, (unsigned long)vmemmap);
+ /* Take care that ident_map_size <= vmemmap */
+ ident_map_size = min(ident_map_size, (unsigned long)vmemmap);
#ifdef CONFIG_KASAN
- memory_end = min(memory_end, KASAN_SHADOW_START);
+ ident_map_size = min(ident_map_size, KASAN_SHADOW_START);
#endif
- vmemmap_size = SECTION_ALIGN_UP(memory_end / PAGE_SIZE) * sizeof(struct page);
+ vmemmap_size = SECTION_ALIGN_UP(ident_map_size / PAGE_SIZE) * sizeof(struct page);
#ifdef CONFIG_KASAN
/* move vmemmap above kasan shadow only if stands in a way */
if (KASAN_SHADOW_END > (unsigned long)vmemmap &&
(unsigned long)vmemmap + vmemmap_size > KASAN_SHADOW_START)
vmemmap = max(vmemmap, (struct page *)KASAN_SHADOW_END);
#endif
- max_pfn = max_low_pfn = PFN_DOWN(memory_end);
- memblock_remove(memory_end, ULONG_MAX);
+ max_pfn = max_low_pfn = PFN_DOWN(ident_map_size);
+ memblock_remove(ident_map_size, ULONG_MAX);
- pr_notice("The maximum memory size is %luMB\n", memory_end >> 20);
+ pr_notice("The maximum memory size is %luMB\n", ident_map_size >> 20);
}
#ifdef CONFIG_CRASH_DUMP
@@ -632,12 +633,11 @@ static struct notifier_block kdump_mem_nb = {
#endif
/*
- * Make sure that the area behind memory_end is protected
+ * Make sure that the area above identity mapping is protected
*/
-static void __init reserve_memory_end(void)
+static void __init reserve_above_ident_map(void)
{
- if (memory_end_set)
- memblock_reserve(memory_end, ULONG_MAX);
+ memblock_reserve(ident_map_size, ULONG_MAX);
}
/*
@@ -674,7 +674,7 @@ static void __init reserve_crashkernel(void)
phys_addr_t low, high;
int rc;
- rc = parse_crashkernel(boot_command_line, memory_end, &crash_size,
+ rc = parse_crashkernel(boot_command_line, ident_map_size, &crash_size,
&crash_base);
crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN);
@@ -1128,7 +1128,7 @@ void __init setup_arch(char **cmdline_p)
setup_control_program_code();
/* Do some memory reservations *before* memory is added to memblock */
- reserve_memory_end();
+ reserve_above_ident_map();
reserve_oldmem();
reserve_kernel();
reserve_initrd();
@@ -1143,10 +1143,12 @@ void __init setup_arch(char **cmdline_p)
remove_oldmem();
setup_uv();
- setup_memory_end();
+ setup_ident_map_size();
setup_memory();
- dma_contiguous_reserve(memory_end);
+ dma_contiguous_reserve(ident_map_size);
vmcp_cma_reserve();
+ if (MACHINE_HAS_EDAT2)
+ hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
check_initrd();
reserve_crashkernel();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 390d97daa2b3..27c763014114 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -47,7 +47,6 @@
#include <asm/vtimer.h>
#include <asm/lowcore.h>
#include <asm/sclp.h>
-#include <asm/vdso.h>
#include <asm/debug.h>
#include <asm/os_info.h>
#include <asm/sigp.h>
@@ -55,6 +54,7 @@
#include <asm/nmi.h>
#include <asm/stacktrace.h>
#include <asm/topology.h>
+#include <asm/vdso.h>
#include "entry.h"
enum {
@@ -217,14 +217,10 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu)
lc->return_mcck_lpswe = gen_lpswe(__LC_RETURN_MCCK_PSW);
if (nmi_alloc_per_cpu(lc))
goto out_async;
- if (vdso_alloc_per_cpu(lc))
- goto out_mcesa;
lowcore_ptr[cpu] = lc;
pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, (u32)(unsigned long) lc);
return 0;
-out_mcesa:
- nmi_free_per_cpu(lc);
out_async:
stack_free(async_stack);
out:
@@ -245,7 +241,6 @@ static void pcpu_free_lowcore(struct pcpu *pcpu)
pcpu_sigp_retry(pcpu, SIGP_SET_PREFIX, 0);
lowcore_ptr[pcpu - pcpu_devices] = NULL;
- vdso_free_per_cpu(pcpu->lowcore);
nmi_free_per_cpu(pcpu->lowcore);
stack_free(async_stack);
if (pcpu == &pcpu_devices[0])
@@ -265,13 +260,13 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
lc->spinlock_index = 0;
lc->percpu_offset = __per_cpu_offset[cpu];
lc->kernel_asce = S390_lowcore.kernel_asce;
- lc->user_asce = S390_lowcore.kernel_asce;
+ lc->user_asce = s390_invalid_asce;
lc->machine_flags = S390_lowcore.machine_flags;
lc->user_timer = lc->system_timer =
lc->steal_timer = lc->avg_steal_timer = 0;
__ctl_store(lc->cregs_save_area, 0, 15);
lc->cregs_save_area[1] = lc->kernel_asce;
- lc->cregs_save_area[7] = lc->vdso_asce;
+ lc->cregs_save_area[7] = lc->user_asce;
save_access_regs((unsigned int *) lc->access_regs_save_area);
memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
sizeof(lc->stfle_fac_list));
@@ -859,13 +854,12 @@ static void smp_init_secondary(void)
S390_lowcore.last_update_clock = get_tod_clock();
restore_access_regs(S390_lowcore.access_regs_save_area);
- set_cpu_flag(CIF_ASCE_PRIMARY);
- set_cpu_flag(CIF_ASCE_SECONDARY);
cpu_init();
rcu_cpu_starting(cpu);
preempt_disable();
init_cpu_timer();
vtime_init();
+ vdso_getcpu_init();
pfault_init();
notify_cpu_starting(cpu);
if (topology_cpu_dedicated(cpu))
@@ -896,24 +890,12 @@ static void __no_sanitize_address smp_start_secondary(void *cpuvoid)
/* Upping and downing of CPUs */
int __cpu_up(unsigned int cpu, struct task_struct *tidle)
{
- struct pcpu *pcpu;
- int base, i, rc;
+ struct pcpu *pcpu = pcpu_devices + cpu;
+ int rc;
- pcpu = pcpu_devices + cpu;
if (pcpu->state != CPU_STATE_CONFIGURED)
return -EIO;
- base = smp_get_base_cpu(cpu);
- for (i = 0; i <= smp_cpu_mtid; i++) {
- if (base + i < nr_cpu_ids)
- if (cpu_online(base + i))
- break;
- }
- /*
- * If this is the first CPU of the core to get online
- * do an initial CPU reset.
- */
- if (i > smp_cpu_mtid &&
- pcpu_sigp_retry(pcpu_devices + base, SIGP_INITIAL_CPU_RESET, 0) !=
+ if (pcpu_sigp_retry(pcpu, SIGP_INITIAL_CPU_RESET, 0) !=
SIGP_CC_ORDER_CODE_ACCEPTED)
return -EIO;
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index 0ac30ee2c633..c59cb44fbb7d 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -927,41 +927,25 @@ static ssize_t online_store(struct device *dev,
*/
static DEVICE_ATTR_RW(online);
-static struct device_attribute *stp_attributes[] = {
- &dev_attr_ctn_id,
- &dev_attr_ctn_type,
- &dev_attr_dst_offset,
- &dev_attr_leap_seconds,
- &dev_attr_online,
- &dev_attr_leap_seconds_scheduled,
- &dev_attr_stratum,
- &dev_attr_time_offset,
- &dev_attr_time_zone_offset,
- &dev_attr_timing_mode,
- &dev_attr_timing_state,
+static struct attribute *stp_dev_attrs[] = {
+ &dev_attr_ctn_id.attr,
+ &dev_attr_ctn_type.attr,
+ &dev_attr_dst_offset.attr,
+ &dev_attr_leap_seconds.attr,
+ &dev_attr_online.attr,
+ &dev_attr_leap_seconds_scheduled.attr,
+ &dev_attr_stratum.attr,
+ &dev_attr_time_offset.attr,
+ &dev_attr_time_zone_offset.attr,
+ &dev_attr_timing_mode.attr,
+ &dev_attr_timing_state.attr,
NULL
};
+ATTRIBUTE_GROUPS(stp_dev);
static int __init stp_init_sysfs(void)
{
- struct device_attribute **attr;
- int rc;
-
- rc = subsys_system_register(&stp_subsys, NULL);
- if (rc)
- goto out;
- for (attr = stp_attributes; *attr; attr++) {
- rc = device_create_file(stp_subsys.dev_root, *attr);
- if (rc)
- goto out_unreg;
- }
- return 0;
-out_unreg:
- for (; attr >= stp_attributes; attr--)
- device_remove_file(stp_subsys.dev_root, *attr);
- bus_unregister(&stp_subsys);
-out:
- return rc;
+ return subsys_system_register(&stp_subsys, stp_dev_groups);
}
device_initcall(stp_init_sysfs);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index f9da5b149141..aef2edff9959 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -29,6 +29,7 @@
#include <asm/sections.h>
#include <asm/vdso.h>
#include <asm/facility.h>
+#include <asm/timex.h>
extern char vdso64_start, vdso64_end;
static void *vdso64_kbase = &vdso64_start;
@@ -99,60 +100,10 @@ static union {
u8 page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
struct vdso_data *vdso_data = (struct vdso_data *)&vdso_data_store.data;
-/*
- * Allocate/free per cpu vdso data.
- */
-#define SEGMENT_ORDER 2
-int vdso_alloc_per_cpu(struct lowcore *lowcore)
+void vdso_getcpu_init(void)
{
- unsigned long segment_table, page_table, page_frame;
- struct vdso_per_cpu_data *vd;
-
- segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
- page_table = get_zeroed_page(GFP_KERNEL);
- page_frame = get_zeroed_page(GFP_KERNEL);
- if (!segment_table || !page_table || !page_frame)
- goto out;
- arch_set_page_dat(virt_to_page(segment_table), SEGMENT_ORDER);
- arch_set_page_dat(virt_to_page(page_table), 0);
-
- /* Initialize per-cpu vdso data page */
- vd = (struct vdso_per_cpu_data *) page_frame;
- vd->cpu_nr = lowcore->cpu_nr;
- vd->node_id = cpu_to_node(vd->cpu_nr);
-
- /* Set up page table for the vdso address space */
- memset64((u64 *)segment_table, _SEGMENT_ENTRY_EMPTY, _CRST_ENTRIES);
- memset64((u64 *)page_table, _PAGE_INVALID, PTRS_PER_PTE);
-
- *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
- *(unsigned long *) page_table = _PAGE_PROTECT + page_frame;
-
- lowcore->vdso_asce = segment_table +
- _ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
- lowcore->vdso_per_cpu_data = page_frame;
-
- return 0;
-
-out:
- free_page(page_frame);
- free_page(page_table);
- free_pages(segment_table, SEGMENT_ORDER);
- return -ENOMEM;
-}
-
-void vdso_free_per_cpu(struct lowcore *lowcore)
-{
- unsigned long segment_table, page_table, page_frame;
-
- segment_table = lowcore->vdso_asce & PAGE_MASK;
- page_table = *(unsigned long *) segment_table;
- page_frame = *(unsigned long *) page_table;
-
- free_page(page_frame);
- free_page(page_table);
- free_pages(segment_table, SEGMENT_ORDER);
+ set_tod_programmable_field(smp_processor_id());
}
/*
@@ -225,6 +176,7 @@ static int __init vdso_init(void)
{
int i;
+ vdso_getcpu_init();
/* Calculate the size of the 64 bit vDSO */
vdso64_pages = ((&vdso64_end - &vdso64_start
+ PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
@@ -240,8 +192,6 @@ static int __init vdso_init(void)
}
vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
vdso64_pagelist[vdso64_pages] = NULL;
- if (vdso_alloc_per_cpu(&S390_lowcore))
- BUG();
get_page(virt_to_page(vdso_data));
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index 13cc5a3f9abf..a6e0fb6b91d6 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -6,8 +6,9 @@ ARCH_REL_TYPE_ABS := R_390_COPY|R_390_GLOB_DAT|R_390_JMP_SLOT|R_390_RELATIVE
ARCH_REL_TYPE_ABS += R_390_GOT|R_390_PLT
include $(srctree)/lib/vdso/Makefile
-obj-vdso64 = vdso_user_wrapper.o note.o getcpu.o
-obj-cvdso64 = vdso64_generic.o
+obj-vdso64 = vdso_user_wrapper.o note.o
+obj-cvdso64 = vdso64_generic.o getcpu.o
+CFLAGS_REMOVE_getcpu.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
CFLAGS_REMOVE_vdso64_generic.o = -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE)
# Build rules
diff --git a/arch/s390/kernel/vdso64/getcpu.S b/arch/s390/kernel/vdso64/getcpu.S
deleted file mode 100644
index 3c04f7328500..000000000000
--- a/arch/s390/kernel/vdso64/getcpu.S
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Userland implementation of getcpu() for 64 bits processes in a
- * s390 kernel for use in the vDSO
- *
- * Copyright IBM Corp. 2016
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <asm/vdso.h>
-#include <asm/asm-offsets.h>
-#include <asm/dwarf.h>
-
- .text
- .align 4
- .globl __kernel_getcpu
- .type __kernel_getcpu,@function
-__kernel_getcpu:
- CFI_STARTPROC
- sacf 256
- lm %r4,%r5,__VDSO_GETCPU_VAL(%r0)
- sacf 0
- ltgr %r2,%r2
- jz 2f
- st %r5,0(%r2)
-2: ltgr %r3,%r3
- jz 3f
- st %r4,0(%r3)
-3: lghi %r2,0
- br %r14
- CFI_ENDPROC
- .size __kernel_getcpu,.-__kernel_getcpu
diff --git a/arch/s390/kernel/vdso64/getcpu.c b/arch/s390/kernel/vdso64/getcpu.c
new file mode 100644
index 000000000000..5b2bc7494d5b
--- /dev/null
+++ b/arch/s390/kernel/vdso64/getcpu.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright IBM Corp. 2020 */
+
+#include <linux/compiler.h>
+#include <linux/getcpu.h>
+#include <asm/timex.h>
+#include "vdso.h"
+
+int __s390_vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+{
+ __u16 todval[8];
+
+ /* CPU number is stored in the programmable field of the TOD clock */
+ get_tod_clock_ext((char *)todval);
+ if (cpu)
+ *cpu = todval[7];
+ /* NUMA node is always zero */
+ if (node)
+ *node = 0;
+ return 0;
+}
diff --git a/arch/s390/kernel/vdso64/vdso.h b/arch/s390/kernel/vdso64/vdso.h
new file mode 100644
index 000000000000..34c7a2312f9d
--- /dev/null
+++ b/arch/s390/kernel/vdso64/vdso.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_S390_KERNEL_VDSO64_VDSO_H
+#define __ARCH_S390_KERNEL_VDSO64_VDSO_H
+
+#include <vdso/datapage.h>
+
+struct getcpu_cache;
+
+int __s390_vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused);
+int __s390_vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
+int __s390_vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
+int __s390_vdso_clock_getres(clockid_t clock, struct __kernel_timespec *ts);
+
+#endif /* __ARCH_S390_KERNEL_VDSO64_VDSO_H */
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
index 7ddb116b5e2e..7bde3909290f 100644
--- a/arch/s390/kernel/vdso64/vdso64.lds.S
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -136,7 +136,6 @@ VERSION
__kernel_clock_gettime;
__kernel_clock_getres;
__kernel_getcpu;
-
local: *;
};
}
diff --git a/arch/s390/kernel/vdso64/vdso64_generic.c b/arch/s390/kernel/vdso64/vdso64_generic.c
index a8cef7e4d137..a9aa75643c08 100644
--- a/arch/s390/kernel/vdso64/vdso64_generic.c
+++ b/arch/s390/kernel/vdso64/vdso64_generic.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include "../../../../lib/vdso/gettimeofday.c"
+#include "vdso.h"
int __s390_vdso_gettimeofday(struct __kernel_old_timeval *tv,
struct timezone *tz)
diff --git a/arch/s390/kernel/vdso64/vdso_user_wrapper.S b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
index a775d7e52872..f773505c7e63 100644
--- a/arch/s390/kernel/vdso64/vdso_user_wrapper.S
+++ b/arch/s390/kernel/vdso64/vdso_user_wrapper.S
@@ -36,3 +36,4 @@ __kernel_\func:
vdso_func gettimeofday
vdso_func clock_getres
vdso_func clock_gettime
+vdso_func getcpu
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 177ccfbda40a..4c0e19145cc6 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -10,7 +10,8 @@
* Put .bss..swapper_pg_dir as the first thing in .bss. This will
* make sure it has 16k alignment.
*/
-#define BSS_FIRST_SECTIONS *(.bss..swapper_pg_dir)
+#define BSS_FIRST_SECTIONS *(.bss..swapper_pg_dir) \
+ *(.bss..invalid_pg_dir)
/* Handle ro_after_init data on our own. */
#define RO_AFTER_INIT_DATA
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 8c0c68e7770e..68d61f2835df 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -13,11 +13,19 @@
#include <linux/export.h>
#include <linux/irqflags.h>
#include <linux/interrupt.h>
+#include <linux/jump_label.h>
#include <linux/irq.h>
#include <asm/vtimer.h>
#include <asm/div64.h>
#include <asm/idle.h>
+static DEFINE_STATIC_KEY_FALSE(udelay_ready);
+
+void __init udelay_enable(void)
+{
+ static_branch_enable(&udelay_ready);
+}
+
void __delay(unsigned long loops)
{
/*
@@ -76,6 +84,11 @@ void __udelay(unsigned long long usecs)
{
unsigned long flags;
+ if (!static_branch_likely(&udelay_ready)) {
+ udelay_simple(usecs);
+ return;
+ }
+
preempt_disable();
local_irq_save(flags);
if (in_irq()) {
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index 0267405ab7c6..e8f642446fed 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -16,6 +16,22 @@
#include <asm/mmu_context.h>
#include <asm/facility.h>
+#ifdef CONFIG_DEBUG_USER_ASCE
+void debug_user_asce(void)
+{
+ unsigned long cr1, cr7;
+
+ __ctl_store(cr1, 1, 1);
+ __ctl_store(cr7, 7, 7);
+ if (cr1 == S390_lowcore.kernel_asce && cr7 == S390_lowcore.user_asce)
+ return;
+ panic("incorrect ASCE on kernel exit\n"
+ "cr1: %016lx cr7: %016lx\n"
+ "kernel: %016llx user: %016llx\n",
+ cr1, cr7, S390_lowcore.kernel_asce, S390_lowcore.user_asce);
+}
+#endif /*CONFIG_DEBUG_USER_ASCE */
+
#ifndef CONFIG_HAVE_MARCH_Z10_FEATURES
static DEFINE_STATIC_KEY_FALSE(have_mvcos);
@@ -40,71 +56,10 @@ static inline int copy_with_mvcos(void)
}
#endif
-void set_fs(mm_segment_t fs)
-{
- current->thread.mm_segment = fs;
- if (fs == USER_DS) {
- __ctl_load(S390_lowcore.user_asce, 1, 1);
- clear_cpu_flag(CIF_ASCE_PRIMARY);
- } else {
- __ctl_load(S390_lowcore.kernel_asce, 1, 1);
- set_cpu_flag(CIF_ASCE_PRIMARY);
- }
- if (fs & 1) {
- if (fs == USER_DS_SACF)
- __ctl_load(S390_lowcore.user_asce, 7, 7);
- else
- __ctl_load(S390_lowcore.kernel_asce, 7, 7);
- set_cpu_flag(CIF_ASCE_SECONDARY);
- }
-}
-EXPORT_SYMBOL(set_fs);
-
-mm_segment_t enable_sacf_uaccess(void)
-{
- mm_segment_t old_fs;
- unsigned long asce, cr;
- unsigned long flags;
-
- old_fs = current->thread.mm_segment;
- if (old_fs & 1)
- return old_fs;
- /* protect against a concurrent page table upgrade */
- local_irq_save(flags);
- current->thread.mm_segment |= 1;
- asce = S390_lowcore.kernel_asce;
- if (likely(old_fs == USER_DS)) {
- __ctl_store(cr, 1, 1);
- if (cr != S390_lowcore.kernel_asce) {
- __ctl_load(S390_lowcore.kernel_asce, 1, 1);
- set_cpu_flag(CIF_ASCE_PRIMARY);
- }
- asce = S390_lowcore.user_asce;
- }
- __ctl_store(cr, 7, 7);
- if (cr != asce) {
- __ctl_load(asce, 7, 7);
- set_cpu_flag(CIF_ASCE_SECONDARY);
- }
- local_irq_restore(flags);
- return old_fs;
-}
-EXPORT_SYMBOL(enable_sacf_uaccess);
-
-void disable_sacf_uaccess(mm_segment_t old_fs)
-{
- current->thread.mm_segment = old_fs;
- if (old_fs == USER_DS && test_facility(27)) {
- __ctl_load(S390_lowcore.user_asce, 1, 1);
- clear_cpu_flag(CIF_ASCE_PRIMARY);
- }
-}
-EXPORT_SYMBOL(disable_sacf_uaccess);
-
static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr,
unsigned long size)
{
- register unsigned long reg0 asm("0") = 0x01UL;
+ register unsigned long reg0 asm("0") = 0x81UL;
unsigned long tmp1, tmp2;
tmp1 = -4096UL;
@@ -135,9 +90,7 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
unsigned long size)
{
unsigned long tmp1, tmp2;
- mm_segment_t old_fs;
- old_fs = enable_sacf_uaccess();
tmp1 = -256UL;
asm volatile(
" sacf 0\n"
@@ -164,7 +117,6 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr,
EX_TABLE(7b,3b) EX_TABLE(8b,3b) EX_TABLE(9b,6b)
: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
: : "cc", "memory");
- disable_sacf_uaccess(old_fs);
return size;
}
@@ -179,7 +131,7 @@ EXPORT_SYMBOL(raw_copy_from_user);
static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
unsigned long size)
{
- register unsigned long reg0 asm("0") = 0x010000UL;
+ register unsigned long reg0 asm("0") = 0x810000UL;
unsigned long tmp1, tmp2;
tmp1 = -4096UL;
@@ -210,9 +162,7 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x,
unsigned long size)
{
unsigned long tmp1, tmp2;
- mm_segment_t old_fs;
- old_fs = enable_sacf_uaccess();
tmp1 = -256UL;
asm volatile(
" sacf 0\n"
@@ -239,7 +189,6 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x,
EX_TABLE(7b,3b) EX_TABLE(8b,3b) EX_TABLE(9b,6b)
: "+a" (size), "+a" (ptr), "+a" (x), "+a" (tmp1), "=a" (tmp2)
: : "cc", "memory");
- disable_sacf_uaccess(old_fs);
return size;
}
@@ -254,7 +203,7 @@ EXPORT_SYMBOL(raw_copy_to_user);
static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from,
unsigned long size)
{
- register unsigned long reg0 asm("0") = 0x010001UL;
+ register unsigned long reg0 asm("0") = 0x810081UL;
unsigned long tmp1, tmp2;
tmp1 = -4096UL;
@@ -277,10 +226,8 @@ static inline unsigned long copy_in_user_mvcos(void __user *to, const void __use
static inline unsigned long copy_in_user_mvc(void __user *to, const void __user *from,
unsigned long size)
{
- mm_segment_t old_fs;
unsigned long tmp1;
- old_fs = enable_sacf_uaccess();
asm volatile(
" sacf 256\n"
" aghi %0,-1\n"
@@ -304,7 +251,6 @@ static inline unsigned long copy_in_user_mvc(void __user *to, const void __user
EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
: "+a" (size), "+a" (to), "+a" (from), "=a" (tmp1)
: : "cc", "memory");
- disable_sacf_uaccess(old_fs);
return size;
}
@@ -318,7 +264,7 @@ EXPORT_SYMBOL(raw_copy_in_user);
static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
{
- register unsigned long reg0 asm("0") = 0x010000UL;
+ register unsigned long reg0 asm("0") = 0x810000UL;
unsigned long tmp1, tmp2;
tmp1 = -4096UL;
@@ -346,10 +292,8 @@ static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size
static inline unsigned long clear_user_xc(void __user *to, unsigned long size)
{
- mm_segment_t old_fs;
unsigned long tmp1, tmp2;
- old_fs = enable_sacf_uaccess();
asm volatile(
" sacf 256\n"
" aghi %0,-1\n"
@@ -378,7 +322,6 @@ static inline unsigned long clear_user_xc(void __user *to, unsigned long size)
EX_TABLE(1b,6b) EX_TABLE(2b,0b) EX_TABLE(4b,0b)
: "+a" (size), "+a" (to), "=a" (tmp1), "=a" (tmp2)
: : "cc", "memory");
- disable_sacf_uaccess(old_fs);
return size;
}
@@ -414,15 +357,9 @@ static inline unsigned long strnlen_user_srst(const char __user *src,
unsigned long __strnlen_user(const char __user *src, unsigned long size)
{
- mm_segment_t old_fs;
- unsigned long len;
-
if (unlikely(!size))
return 0;
- old_fs = enable_sacf_uaccess();
- len = strnlen_user_srst(src, size);
- disable_sacf_uaccess(old_fs);
- return len;
+ return strnlen_user_srst(src, size);
}
EXPORT_SYMBOL(__strnlen_user);
diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
index 8f9ff7e7187d..e40a30647d99 100644
--- a/arch/s390/mm/dump_pagetables.c
+++ b/arch/s390/mm/dump_pagetables.c
@@ -255,7 +255,7 @@ static int pt_dump_init(void)
*/
max_addr = (S390_lowcore.kernel_asce & _REGION_ENTRY_TYPE_MASK) >> 2;
max_addr = 1UL << (max_addr * 11 + 31);
- address_markers[IDENTITY_AFTER_END_NR].start_address = memory_end;
+ address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size;
address_markers[MODULES_NR].start_address = MODULES_VADDR;
address_markers[MODULES_END_NR].start_address = MODULES_END;
address_markers[VMEMMAP_NR].start_address = (unsigned long) vmemmap;
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 996884dcc9fd..b8210103de14 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -53,7 +53,6 @@
enum fault_type {
KERNEL_FAULT,
USER_FAULT,
- VDSO_FAULT,
GMAP_FAULT,
};
@@ -77,22 +76,16 @@ static enum fault_type get_fault_type(struct pt_regs *regs)
trans_exc_code = regs->int_parm_long & 3;
if (likely(trans_exc_code == 0)) {
/* primary space exception */
- if (IS_ENABLED(CONFIG_PGSTE) &&
- test_pt_regs_flag(regs, PIF_GUEST_FAULT))
- return GMAP_FAULT;
- if (current->thread.mm_segment == USER_DS)
+ if (user_mode(regs))
return USER_FAULT;
- return KERNEL_FAULT;
- }
- if (trans_exc_code == 2) {
- /* secondary space exception */
- if (current->thread.mm_segment & 1) {
- if (current->thread.mm_segment == USER_DS_SACF)
- return USER_FAULT;
+ if (!IS_ENABLED(CONFIG_PGSTE))
return KERNEL_FAULT;
- }
- return VDSO_FAULT;
+ if (test_pt_regs_flag(regs, PIF_GUEST_FAULT))
+ return GMAP_FAULT;
+ return KERNEL_FAULT;
}
+ if (trans_exc_code == 2)
+ return USER_FAULT;
if (trans_exc_code == 1) {
/* access register mode, not used in the kernel */
return USER_FAULT;
@@ -188,10 +181,6 @@ static void dump_fault_info(struct pt_regs *regs)
asce = S390_lowcore.user_asce;
pr_cont("user ");
break;
- case VDSO_FAULT:
- asce = S390_lowcore.vdso_asce;
- pr_cont("vdso ");
- break;
case GMAP_FAULT:
asce = ((struct gmap *) S390_lowcore.gmap)->asce;
pr_cont("gmap ");
@@ -414,9 +403,6 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
switch (type) {
case KERNEL_FAULT:
goto out;
- case VDSO_FAULT:
- fault = VM_FAULT_BADMAP;
- goto out;
case USER_FAULT:
case GMAP_FAULT:
if (faulthandler_disabled() || !mm)
@@ -834,7 +820,6 @@ void do_secure_storage_access(struct pt_regs *regs)
if (rc)
BUG();
break;
- case VDSO_FAULT:
case GMAP_FAULT:
default:
do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 77767850d0d0..73a163065b95 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,9 @@
#include <linux/virtio_config.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
+static pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir");
+
+unsigned long s390_invalid_asce;
unsigned long empty_zero_page, zero_page_mask;
EXPORT_SYMBOL(empty_zero_page);
@@ -92,6 +95,9 @@ void __init paging_init(void)
unsigned long pgd_type, asce_bits;
psw_t psw;
+ s390_invalid_asce = (unsigned long)invalid_pg_dir;
+ s390_invalid_asce |= _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
+ crst_table_init((unsigned long *)invalid_pg_dir, _REGION3_ENTRY_EMPTY);
init_mm.pgd = swapper_pg_dir;
if (VMALLOC_END > _REGION2_SIZE) {
asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
@@ -102,14 +108,14 @@ void __init paging_init(void)
}
init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
S390_lowcore.kernel_asce = init_mm.context.asce;
- S390_lowcore.user_asce = S390_lowcore.kernel_asce;
+ S390_lowcore.user_asce = s390_invalid_asce;
crst_table_init((unsigned long *) init_mm.pgd, pgd_type);
vmem_map_init();
- kasan_copy_shadow(init_mm.pgd);
+ kasan_copy_shadow_mapping();
/* enable virtual mapping in kernel mode */
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
- __ctl_load(S390_lowcore.kernel_asce, 7, 7);
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
__ctl_load(S390_lowcore.kernel_asce, 13, 13);
psw.mask = __extract_psw();
psw_bits(psw).dat = 1;
diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c
index 5646b39c728a..db4d303aaaa9 100644
--- a/arch/s390/mm/kasan_init.c
+++ b/arch/s390/mm/kasan_init.c
@@ -87,7 +87,7 @@ enum populate_mode {
POPULATE_ZERO_SHADOW,
POPULATE_SHALLOW
};
-static void __init kasan_early_vmemmap_populate(unsigned long address,
+static void __init kasan_early_pgtable_populate(unsigned long address,
unsigned long end,
enum populate_mode mode)
{
@@ -123,8 +123,7 @@ static void __init kasan_early_vmemmap_populate(unsigned long address,
pgd_populate(&init_mm, pg_dir, p4_dir);
}
- if (IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) &&
- mode == POPULATE_SHALLOW) {
+ if (mode == POPULATE_SHALLOW) {
address = (address + P4D_SIZE) & P4D_MASK;
continue;
}
@@ -143,12 +142,6 @@ static void __init kasan_early_vmemmap_populate(unsigned long address,
p4d_populate(&init_mm, p4_dir, pu_dir);
}
- if (!IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING) &&
- mode == POPULATE_SHALLOW) {
- address = (address + PUD_SIZE) & PUD_MASK;
- continue;
- }
-
pu_dir = pud_offset(p4_dir, address);
if (pud_none(*pu_dir)) {
if (mode == POPULATE_ZERO_SHADOW &&
@@ -281,7 +274,6 @@ void __init kasan_early_init(void)
unsigned long shadow_alloc_size;
unsigned long vmax_unlimited;
unsigned long initrd_end;
- unsigned long asce_type;
unsigned long memsize;
unsigned long pgt_prot = pgprot_val(PAGE_KERNEL_RO);
pte_t pte_z;
@@ -297,32 +289,26 @@ void __init kasan_early_init(void)
memsize = get_mem_detect_end();
if (!memsize)
kasan_early_panic("cannot detect physical memory size\n");
- /* respect mem= cmdline parameter */
- if (memory_end_set && memsize > memory_end)
- memsize = memory_end;
- if (IS_ENABLED(CONFIG_CRASH_DUMP) && OLDMEM_BASE)
- memsize = min(memsize, OLDMEM_SIZE);
- memsize = min(memsize, KASAN_SHADOW_START);
-
- if (IS_ENABLED(CONFIG_KASAN_S390_4_LEVEL_PAGING)) {
- /* 4 level paging */
- BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, P4D_SIZE));
- BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE));
- crst_table_init((unsigned long *)early_pg_dir,
- _REGION2_ENTRY_EMPTY);
- untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION1_SIZE;
- if (has_uv_sec_stor_limit())
- kasan_vmax = min(vmax_unlimited, uv_info.max_sec_stor_addr);
- asce_type = _ASCE_TYPE_REGION2;
- } else {
- /* 3 level paging */
- BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PUD_SIZE));
- BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PUD_SIZE));
- crst_table_init((unsigned long *)early_pg_dir,
- _REGION3_ENTRY_EMPTY);
- untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION2_SIZE;
- asce_type = _ASCE_TYPE_REGION3;
- }
+ /*
+ * Kasan currently supports standby memory but only if it follows
+ * online memory (default allocation), i.e. no memory holes.
+ * - memsize represents end of online memory
+ * - ident_map_size represents online + standby and memory limits
+ * accounted.
+ * Kasan maps "memsize" right away.
+ * [0, memsize] - as identity mapping
+ * [__sha(0), __sha(memsize)] - shadow memory for identity mapping
+ * The rest [memsize, ident_map_size] if memsize < ident_map_size
+ * could be mapped/unmapped dynamically later during memory hotplug.
+ */
+ memsize = min(memsize, ident_map_size);
+
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, P4D_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, P4D_SIZE));
+ crst_table_init((unsigned long *)early_pg_dir, _REGION2_ENTRY_EMPTY);
+ untracked_mem_end = kasan_vmax = vmax_unlimited = _REGION1_SIZE;
+ if (has_uv_sec_stor_limit())
+ kasan_vmax = min(vmax_unlimited, uv_info.max_sec_stor_addr);
/* init kasan zero shadow */
crst_table_init((unsigned long *)kasan_early_shadow_p4d,
@@ -388,27 +374,25 @@ void __init kasan_early_init(void)
* +-----------------+ +- shadow end ---+
*/
/* populate kasan shadow (for identity mapping and zero page mapping) */
- kasan_early_vmemmap_populate(__sha(0), __sha(memsize), POPULATE_MAP);
+ kasan_early_pgtable_populate(__sha(0), __sha(memsize), POPULATE_MAP);
if (IS_ENABLED(CONFIG_MODULES))
untracked_mem_end = kasan_vmax - MODULES_LEN;
if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
untracked_mem_end = kasan_vmax - vmalloc_size - MODULES_LEN;
/* shallowly populate kasan shadow for vmalloc and modules */
- kasan_early_vmemmap_populate(__sha(untracked_mem_end),
- __sha(kasan_vmax), POPULATE_SHALLOW);
+ kasan_early_pgtable_populate(__sha(untracked_mem_end), __sha(kasan_vmax),
+ POPULATE_SHALLOW);
}
/* populate kasan shadow for untracked memory */
- kasan_early_vmemmap_populate(__sha(max_physmem_end),
- __sha(untracked_mem_end),
+ kasan_early_pgtable_populate(__sha(ident_map_size), __sha(untracked_mem_end),
POPULATE_ZERO_SHADOW);
- kasan_early_vmemmap_populate(__sha(kasan_vmax),
- __sha(vmax_unlimited),
+ kasan_early_pgtable_populate(__sha(kasan_vmax), __sha(vmax_unlimited),
POPULATE_ZERO_SHADOW);
/* memory allocated for identity mapping structs will be freed later */
pgalloc_freeable = pgalloc_pos;
/* populate identity mapping */
- kasan_early_vmemmap_populate(0, memsize, POPULATE_ONE2ONE);
- kasan_set_pgd(early_pg_dir, asce_type);
+ kasan_early_pgtable_populate(0, memsize, POPULATE_ONE2ONE);
+ kasan_set_pgd(early_pg_dir, _ASCE_TYPE_REGION2);
kasan_enable_dat();
/* enable kasan */
init_task.kasan_depth = 0;
@@ -416,7 +400,7 @@ void __init kasan_early_init(void)
sclp_early_printk("KernelAddressSanitizer initialized\n");
}
-void __init kasan_copy_shadow(pgd_t *pg_dir)
+void __init kasan_copy_shadow_mapping(void)
{
/*
* At this point we are still running on early pages setup early_pg_dir,
@@ -428,24 +412,13 @@ void __init kasan_copy_shadow(pgd_t *pg_dir)
pgd_t *pg_dir_dst;
p4d_t *p4_dir_src;
p4d_t *p4_dir_dst;
- pud_t *pu_dir_src;
- pud_t *pu_dir_dst;
pg_dir_src = pgd_offset_raw(early_pg_dir, KASAN_SHADOW_START);
- pg_dir_dst = pgd_offset_raw(pg_dir, KASAN_SHADOW_START);
+ pg_dir_dst = pgd_offset_raw(init_mm.pgd, KASAN_SHADOW_START);
p4_dir_src = p4d_offset(pg_dir_src, KASAN_SHADOW_START);
p4_dir_dst = p4d_offset(pg_dir_dst, KASAN_SHADOW_START);
- if (!p4d_folded(*p4_dir_src)) {
- /* 4 level paging */
- memcpy(p4_dir_dst, p4_dir_src,
- (KASAN_SHADOW_SIZE >> P4D_SHIFT) * sizeof(p4d_t));
- return;
- }
- /* 3 level paging */
- pu_dir_src = pud_offset(p4_dir_src, KASAN_SHADOW_START);
- pu_dir_dst = pud_offset(p4_dir_dst, KASAN_SHADOW_START);
- memcpy(pu_dir_dst, pu_dir_src,
- (KASAN_SHADOW_SIZE >> PUD_SHIFT) * sizeof(pud_t));
+ memcpy(p4_dir_dst, p4_dir_src,
+ (KASAN_SHADOW_SIZE >> P4D_SHIFT) * sizeof(p4d_t));
}
void __init kasan_free_early_identity(void)
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 11d2c8395e2a..4e87c819ddea 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -70,19 +70,10 @@ static void __crst_table_upgrade(void *arg)
{
struct mm_struct *mm = arg;
- /* we must change all active ASCEs to avoid the creation of new TLBs */
+ /* change all active ASCEs to avoid the creation of new TLBs */
if (current->active_mm == mm) {
S390_lowcore.user_asce = mm->context.asce;
- if (current->thread.mm_segment == USER_DS) {
- __ctl_load(S390_lowcore.user_asce, 1, 1);
- /* Mark user-ASCE present in CR1 */
- clear_cpu_flag(CIF_ASCE_PRIMARY);
- }
- if (current->thread.mm_segment == USER_DS_SACF) {
- __ctl_load(S390_lowcore.user_asce, 7, 7);
- /* enable_sacf_uaccess does all or nothing */
- WARN_ON(!test_cpu_flag(CIF_ASCE_SECONDARY));
- }
+ __ctl_load(S390_lowcore.user_asce, 7, 7);
}
__tlb_flush_local();
}
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index b239f2ba93b0..01f3a5f58e64 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -76,20 +76,20 @@ static void vmem_pte_free(unsigned long *table)
/*
* The unused vmemmap range, which was not yet memset(PAGE_UNUSED) ranges
- * from unused_pmd_start to next PMD_SIZE boundary.
+ * from unused_sub_pmd_start to next PMD_SIZE boundary.
*/
-static unsigned long unused_pmd_start;
+static unsigned long unused_sub_pmd_start;
-static void vmemmap_flush_unused_pmd(void)
+static void vmemmap_flush_unused_sub_pmd(void)
{
- if (!unused_pmd_start)
+ if (!unused_sub_pmd_start)
return;
- memset(__va(unused_pmd_start), PAGE_UNUSED,
- ALIGN(unused_pmd_start, PMD_SIZE) - unused_pmd_start);
- unused_pmd_start = 0;
+ memset(__va(unused_sub_pmd_start), PAGE_UNUSED,
+ ALIGN(unused_sub_pmd_start, PMD_SIZE) - unused_sub_pmd_start);
+ unused_sub_pmd_start = 0;
}
-static void __vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
+static void vmemmap_mark_sub_pmd_used(unsigned long start, unsigned long end)
{
/*
* As we expect to add in the same granularity as we remove, it's
@@ -106,24 +106,24 @@ static void vmemmap_use_sub_pmd(unsigned long start, unsigned long end)
* We only optimize if the new used range directly follows the
* previously unused range (esp., when populating consecutive sections).
*/
- if (unused_pmd_start == start) {
- unused_pmd_start = end;
- if (likely(IS_ALIGNED(unused_pmd_start, PMD_SIZE)))
- unused_pmd_start = 0;
+ if (unused_sub_pmd_start == start) {
+ unused_sub_pmd_start = end;
+ if (likely(IS_ALIGNED(unused_sub_pmd_start, PMD_SIZE)))
+ unused_sub_pmd_start = 0;
return;
}
- vmemmap_flush_unused_pmd();
- __vmemmap_use_sub_pmd(start, end);
+ vmemmap_flush_unused_sub_pmd();
+ vmemmap_mark_sub_pmd_used(start, end);
}
static void vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
{
void *page = __va(ALIGN_DOWN(start, PMD_SIZE));
- vmemmap_flush_unused_pmd();
+ vmemmap_flush_unused_sub_pmd();
/* Could be our memmap page is filled with PAGE_UNUSED already ... */
- __vmemmap_use_sub_pmd(start, end);
+ vmemmap_mark_sub_pmd_used(start, end);
/* Mark the unused parts of the new memmap page PAGE_UNUSED. */
if (!IS_ALIGNED(start, PMD_SIZE))
@@ -134,7 +134,7 @@ static void vmemmap_use_new_sub_pmd(unsigned long start, unsigned long end)
* unused range in the populated PMD.
*/
if (!IS_ALIGNED(end, PMD_SIZE))
- unused_pmd_start = end;
+ unused_sub_pmd_start = end;
}
/* Returns true if the PMD is completely unused and can be freed. */
@@ -142,7 +142,7 @@ static bool vmemmap_unuse_sub_pmd(unsigned long start, unsigned long end)
{
void *page = __va(ALIGN_DOWN(start, PMD_SIZE));
- vmemmap_flush_unused_pmd();
+ vmemmap_flush_unused_sub_pmd();
memset(__va(start), PAGE_UNUSED, end - start);
return !memchr_inv(page, PAGE_UNUSED, PMD_SIZE);
}
@@ -223,7 +223,7 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr,
if (!add) {
if (pmd_none(*pmd))
continue;
- if (pmd_large(*pmd) && !add) {
+ if (pmd_large(*pmd)) {
if (IS_ALIGNED(addr, PMD_SIZE) &&
IS_ALIGNED(next, PMD_SIZE)) {
if (!direct)
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index 570016ae8bcd..41df8fcfddde 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -851,8 +851,10 @@ static int __init pci_base_init(void)
if (!s390_pci_probe)
return 0;
- if (!test_facility(69) || !test_facility(71))
+ if (!test_facility(69) || !test_facility(71)) {
+ pr_info("PCI is not supported because CPU facilities 69 or 71 are not available\n");
return 0;
+ }
if (test_facility(153) && !s390_pci_no_mio) {
static_branch_enable(&have_mio);
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 401cf670a243..de3bdbed8881 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -93,12 +93,10 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
{
int size, rc = 0;
u8 status = 0;
- mm_segment_t old_fs;
if (!src)
return -EINVAL;
- old_fs = enable_sacf_uaccess();
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) dst,
(u64 __force) src, n,
@@ -113,39 +111,20 @@ static inline int __memcpy_toio_inuser(void __iomem *dst,
dst += size;
n -= size;
}
- disable_sacf_uaccess(old_fs);
if (rc)
zpci_err_mmio(rc, status, (__force u64) dst);
return rc;
}
-static long get_pfn(unsigned long user_addr, unsigned long access,
- unsigned long *pfn)
-{
- struct vm_area_struct *vma;
- long ret;
-
- mmap_read_lock(current->mm);
- ret = -EINVAL;
- vma = find_vma(current->mm, user_addr);
- if (!vma)
- goto out;
- ret = -EACCES;
- if (!(vma->vm_flags & access))
- goto out;
- ret = follow_pfn(vma, user_addr, pfn);
-out:
- mmap_read_unlock(current->mm);
- return ret;
-}
-
SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
const void __user *, user_buffer, size_t, length)
{
u8 local_buf[64];
void __iomem *io_addr;
void *buf;
- unsigned long pfn;
+ struct vm_area_struct *vma;
+ pte_t *ptep;
+ spinlock_t *ptl;
long ret;
if (!zpci_is_enabled())
@@ -158,7 +137,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
* We only support write access to MIO capable devices if we are on
* a MIO enabled system. Otherwise we would have to check for every
* address if it is a special ZPCI_ADDR and would have to do
- * a get_pfn() which we don't need for MIO capable devices. Currently
+ * a pfn lookup which we don't need for MIO capable devices. Currently
* ISM devices are the only devices without MIO support and there is no
* known need for accessing these from userspace.
*/
@@ -176,21 +155,37 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr,
} else
buf = local_buf;
- ret = get_pfn(mmio_addr, VM_WRITE, &pfn);
+ ret = -EFAULT;
+ if (copy_from_user(buf, user_buffer, length))
+ goto out_free;
+
+ mmap_read_lock(current->mm);
+ ret = -EINVAL;
+ vma = find_vma(current->mm, mmio_addr);
+ if (!vma)
+ goto out_unlock_mmap;
+ if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ goto out_unlock_mmap;
+ ret = -EACCES;
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out_unlock_mmap;
+
+ ret = follow_pte_pmd(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
if (ret)
- goto out;
- io_addr = (void __iomem *)((pfn << PAGE_SHIFT) |
+ goto out_unlock_mmap;
+
+ io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) |
(mmio_addr & ~PAGE_MASK));
- ret = -EFAULT;
if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE)
- goto out;
-
- if (copy_from_user(buf, user_buffer, length))
- goto out;
+ goto out_unlock_pt;
ret = zpci_memcpy_toio(io_addr, buf, length);
-out:
+out_unlock_pt:
+ pte_unmap_unlock(ptep, ptl);
+out_unlock_mmap:
+ mmap_read_unlock(current->mm);
+out_free:
if (buf != local_buf)
kfree(buf);
return ret;
@@ -248,9 +243,7 @@ static inline int __memcpy_fromio_inuser(void __user *dst,
{
int size, rc = 0;
u8 status;
- mm_segment_t old_fs;
- old_fs = enable_sacf_uaccess();
while (n > 0) {
size = zpci_get_max_write_size((u64 __force) src,
(u64 __force) dst, n,
@@ -262,7 +255,6 @@ static inline int __memcpy_fromio_inuser(void __user *dst,
dst += size;
n -= size;
}
- disable_sacf_uaccess(old_fs);
if (rc)
zpci_err_mmio(rc, status, (__force u64) dst);
return rc;
@@ -274,7 +266,9 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
u8 local_buf[64];
void __iomem *io_addr;
void *buf;
- unsigned long pfn;
+ struct vm_area_struct *vma;
+ pte_t *ptep;
+ spinlock_t *ptl;
long ret;
if (!zpci_is_enabled())
@@ -287,7 +281,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
* We only support read access to MIO capable devices if we are on
* a MIO enabled system. Otherwise we would have to check for every
* address if it is a special ZPCI_ADDR and would have to do
- * a get_pfn() which we don't need for MIO capable devices. Currently
+ * a pfn lookup which we don't need for MIO capable devices. Currently
* ISM devices are the only devices without MIO support and there is no
* known need for accessing these from userspace.
*/
@@ -306,22 +300,38 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr,
buf = local_buf;
}
- ret = get_pfn(mmio_addr, VM_READ, &pfn);
+ mmap_read_lock(current->mm);
+ ret = -EINVAL;
+ vma = find_vma(current->mm, mmio_addr);
+ if (!vma)
+ goto out_unlock_mmap;
+ if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+ goto out_unlock_mmap;
+ ret = -EACCES;
+ if (!(vma->vm_flags & VM_WRITE))
+ goto out_unlock_mmap;
+
+ ret = follow_pte_pmd(vma->vm_mm, mmio_addr, NULL, &ptep, NULL, &ptl);
if (ret)
- goto out;
- io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK));
+ goto out_unlock_mmap;
+
+ io_addr = (void __iomem *)((pte_pfn(*ptep) << PAGE_SHIFT) |
+ (mmio_addr & ~PAGE_MASK));
if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) {
ret = -EFAULT;
- goto out;
+ goto out_unlock_pt;
}
ret = zpci_memcpy_fromio(buf, io_addr, length);
- if (ret)
- goto out;
- if (copy_to_user(user_buffer, buf, length))
+
+out_unlock_pt:
+ pte_unmap_unlock(ptep, ptl);
+out_unlock_mmap:
+ mmap_read_unlock(current->mm);
+
+ if (!ret && copy_to_user(user_buffer, buf, length))
ret = -EFAULT;
-out:
if (buf != local_buf)
kfree(buf);
return ret;
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
index 5a10ce34b95d..3d1c31e0cf3d 100644
--- a/arch/s390/purgatory/head.S
+++ b/arch/s390/purgatory/head.S
@@ -62,14 +62,15 @@
jh 10b
.endm
-.macro START_NEXT_KERNEL base
+.macro START_NEXT_KERNEL base subcode
lg %r4,kernel_entry-\base(%r13)
lg %r5,load_psw_mask-\base(%r13)
ogr %r4,%r5
stg %r4,0(%r0)
xgr %r0,%r0
- diag %r0,%r0,0x308
+ lghi %r1,\subcode
+ diag %r0,%r1,0x308
.endm
.text
@@ -123,7 +124,7 @@ ENTRY(purgatory_start)
je .start_crash_kernel
/* start normal kernel */
- START_NEXT_KERNEL .base_crash
+ START_NEXT_KERNEL .base_crash 0
.return_old_kernel:
lmg %r6,%r15,gprregs-.base_crash(%r13)
@@ -227,7 +228,7 @@ ENTRY(purgatory_start)
MEMCPY %r9,%r10,%r11
/* start crash kernel */
- START_NEXT_KERNEL .base_dst
+ START_NEXT_KERNEL .base_dst 1
load_psw_mask:
diff --git a/drivers/char/hw_random/s390-trng.c b/drivers/char/hw_random/s390-trng.c
index 413cacbb08e2..7c673afd7241 100644
--- a/drivers/char/hw_random/s390-trng.c
+++ b/drivers/char/hw_random/s390-trng.c
@@ -192,14 +192,15 @@ static int trng_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait)
/*
* hwrng register struct
- * The trng is suppost to have 100% entropy, and thus
- * we register with a very high quality value.
+ * The trng is supposed to have 100% entropy, and thus we register with a very
+ * high quality value. If we ever have a better driver in the future, we should
+ * change this value again when we merge this driver.
*/
static struct hwrng trng_hwrng_dev = {
.name = "s390-trng",
.data_read = trng_hwrng_data_read,
.read = trng_hwrng_read,
- .quality = 999,
+ .quality = 1024,
};
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 217a7b84abdf..fd568248fd26 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -75,7 +75,6 @@ static int dasd_flush_block_queue(struct dasd_block *);
static void dasd_device_tasklet(unsigned long);
static void dasd_block_tasklet(unsigned long);
static void do_kick_device(struct work_struct *);
-static void do_restore_device(struct work_struct *);
static void do_reload_device(struct work_struct *);
static void do_requeue_requests(struct work_struct *);
static void dasd_return_cqr_cb(struct dasd_ccw_req *, void *);
@@ -138,7 +137,6 @@ struct dasd_device *dasd_alloc_device(void)
INIT_LIST_HEAD(&device->ccw_queue);
timer_setup(&device->timer, dasd_device_timeout, 0);
INIT_WORK(&device->kick_work, do_kick_device);
- INIT_WORK(&device->restore_device, do_restore_device);
INIT_WORK(&device->reload_device, do_reload_device);
INIT_WORK(&device->requeue_requests, do_requeue_requests);
device->state = DASD_STATE_NEW;
@@ -621,26 +619,6 @@ void dasd_reload_device(struct dasd_device *device)
EXPORT_SYMBOL(dasd_reload_device);
/*
- * dasd_restore_device will schedule a call do do_restore_device to the kernel
- * event daemon.
- */
-static void do_restore_device(struct work_struct *work)
-{
- struct dasd_device *device = container_of(work, struct dasd_device,
- restore_device);
- device->cdev->drv->restore(device->cdev);
- dasd_put_device(device);
-}
-
-void dasd_restore_device(struct dasd_device *device)
-{
- dasd_get_device(device);
- /* queue call to dasd_restore_device to the kernel event daemon. */
- if (!schedule_work(&device->restore_device))
- dasd_put_device(device);
-}
-
-/*
* Set the target state for a device and starts the state change.
*/
void dasd_set_target_state(struct dasd_device *device, int target)
@@ -1514,7 +1492,6 @@ int dasd_start_IO(struct dasd_ccw_req *cqr)
"start_IO: -EIO device gone, retry");
break;
case -EINVAL:
- /* most likely caused in power management context */
DBF_DEV_EVENT(DBF_WARNING, device, "%s",
"start_IO: -EINVAL device currently "
"not accessible");
@@ -2048,7 +2025,7 @@ static void __dasd_device_check_expire(struct dasd_device *device)
static int __dasd_device_is_unusable(struct dasd_device *device,
struct dasd_ccw_req *cqr)
{
- int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM | DASD_STOPPED_NOSPC);
+ int mask = ~(DASD_STOPPED_DC_WAIT | DASD_STOPPED_NOSPC);
if (test_bit(DASD_FLAG_OFFLINE, &device->flags) &&
!test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
@@ -2112,8 +2089,7 @@ static void __dasd_device_check_path_events(struct dasd_device *device)
if (!dasd_path_get_tbvpm(device))
return;
- if (device->stopped &
- ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM))
+ if (device->stopped & ~(DASD_STOPPED_DC_WAIT))
return;
rc = device->discipline->verify_path(device,
dasd_path_get_tbvpm(device));
@@ -3794,11 +3770,6 @@ int dasd_generic_path_operational(struct dasd_device *device)
"operational\n");
DBF_DEV_EVENT(DBF_WARNING, device, "%s", "path operational");
dasd_device_remove_stop_bits(device, DASD_STOPPED_DC_WAIT);
- if (device->stopped & DASD_UNRESUMED_PM) {
- dasd_device_remove_stop_bits(device, DASD_UNRESUMED_PM);
- dasd_restore_device(device);
- return 1;
- }
dasd_schedule_device_bh(device);
if (device->block) {
dasd_schedule_block_bh(device->block);
@@ -4058,66 +4029,6 @@ void dasd_schedule_requeue(struct dasd_device *device)
}
EXPORT_SYMBOL(dasd_schedule_requeue);
-int dasd_generic_pm_freeze(struct ccw_device *cdev)
-{
- struct dasd_device *device = dasd_device_from_cdev(cdev);
-
- if (IS_ERR(device))
- return PTR_ERR(device);
-
- /* mark device as suspended */
- set_bit(DASD_FLAG_SUSPENDED, &device->flags);
-
- if (device->discipline->freeze)
- device->discipline->freeze(device);
-
- /* disallow new I/O */
- dasd_device_set_stop_bits(device, DASD_STOPPED_PM);
-
- return dasd_generic_requeue_all_requests(device);
-}
-EXPORT_SYMBOL_GPL(dasd_generic_pm_freeze);
-
-int dasd_generic_restore_device(struct ccw_device *cdev)
-{
- struct dasd_device *device = dasd_device_from_cdev(cdev);
- int rc = 0;
-
- if (IS_ERR(device))
- return PTR_ERR(device);
-
- /* allow new IO again */
- dasd_device_remove_stop_bits(device,
- (DASD_STOPPED_PM | DASD_UNRESUMED_PM));
-
- dasd_schedule_device_bh(device);
-
- /*
- * call discipline restore function
- * if device is stopped do nothing e.g. for disconnected devices
- */
- if (device->discipline->restore && !(device->stopped))
- rc = device->discipline->restore(device);
- if (rc || device->stopped)
- /*
- * if the resume failed for the DASD we put it in
- * an UNRESUMED stop state
- */
- device->stopped |= DASD_UNRESUMED_PM;
-
- if (device->block) {
- dasd_schedule_block_bh(device->block);
- if (device->block->request_queue)
- blk_mq_run_hw_queues(device->block->request_queue,
- true);
- }
-
- clear_bit(DASD_FLAG_SUSPENDED, &device->flags);
- dasd_put_device(device);
- return 0;
-}
-EXPORT_SYMBOL_GPL(dasd_generic_restore_device);
-
static struct dasd_ccw_req *dasd_generic_build_rdc(struct dasd_device *device,
int rdc_buffer_size,
int magic)
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index ad44d22e8859..758ee4153ac1 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -5716,95 +5716,6 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
}
}
-static int dasd_eckd_pm_freeze(struct dasd_device *device)
-{
- /*
- * the device should be disconnected from our LCU structure
- * on restore we will reconnect it and reread LCU specific
- * information like PAV support that might have changed
- */
- dasd_alias_remove_device(device);
- dasd_alias_disconnect_device_from_lcu(device);
-
- return 0;
-}
-
-static int dasd_eckd_restore_device(struct dasd_device *device)
-{
- struct dasd_eckd_private *private = device->private;
- struct dasd_eckd_characteristics temp_rdc_data;
- int rc;
- struct dasd_uid temp_uid;
- unsigned long flags;
- unsigned long cqr_flags = 0;
-
- /* Read Configuration Data */
- rc = dasd_eckd_read_conf(device);
- if (rc) {
- DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
- "Read configuration data failed, rc=%d", rc);
- goto out_err;
- }
-
- dasd_eckd_get_uid(device, &temp_uid);
- /* Generate device unique id */
- rc = dasd_eckd_generate_uid(device);
- spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
- if (memcmp(&private->uid, &temp_uid, sizeof(struct dasd_uid)) != 0)
- dev_err(&device->cdev->dev, "The UID of the DASD has "
- "changed\n");
- spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
- if (rc)
- goto out_err;
-
- /* register lcu with alias handling, enable PAV if this is a new lcu */
- rc = dasd_alias_make_device_known_to_lcu(device);
- if (rc)
- goto out_err;
-
- set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr_flags);
- dasd_eckd_validate_server(device, cqr_flags);
-
- /* RE-Read Configuration Data */
- rc = dasd_eckd_read_conf(device);
- if (rc) {
- DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
- "Read configuration data failed, rc=%d", rc);
- goto out_err2;
- }
-
- /* Read Feature Codes */
- dasd_eckd_read_features(device);
-
- /* Read Volume Information */
- dasd_eckd_read_vol_info(device);
-
- /* Read Extent Pool Information */
- dasd_eckd_read_ext_pool_info(device);
-
- /* Read Device Characteristics */
- rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
- &temp_rdc_data, 64);
- if (rc) {
- DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
- "Read device characteristic failed, rc=%d", rc);
- goto out_err2;
- }
- spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
- memcpy(&private->rdc_data, &temp_rdc_data, sizeof(temp_rdc_data));
- spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
-
- /* add device to alias management */
- dasd_alias_add_device(device);
-
- return 0;
-
-out_err2:
- dasd_alias_disconnect_device_from_lcu(device);
-out_err:
- return -1;
-}
-
static int dasd_eckd_reload_device(struct dasd_device *device)
{
struct dasd_eckd_private *private = device->private;
@@ -6668,9 +6579,6 @@ static struct ccw_driver dasd_eckd_driver = {
.notify = dasd_generic_notify,
.path_event = dasd_generic_path_event,
.shutdown = dasd_generic_shutdown,
- .freeze = dasd_generic_pm_freeze,
- .thaw = dasd_generic_restore_device,
- .restore = dasd_generic_restore_device,
.uc_handler = dasd_generic_uc_handler,
.int_class = IRQIO_DAS,
};
@@ -6702,8 +6610,6 @@ static struct dasd_discipline dasd_eckd_discipline = {
.dump_sense_dbf = dasd_eckd_dump_sense_dbf,
.fill_info = dasd_eckd_fill_info,
.ioctl = dasd_eckd_ioctl,
- .freeze = dasd_eckd_pm_freeze,
- .restore = dasd_eckd_restore_device,
.reload = dasd_eckd_reload_device,
.get_uid = dasd_eckd_get_uid,
.kick_validate = dasd_eckd_kick_validate_server,
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index 1a44e321b54e..c027344ee225 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -79,9 +79,6 @@ static struct ccw_driver dasd_fba_driver = {
.set_online = dasd_fba_set_online,
.notify = dasd_generic_notify,
.path_event = dasd_generic_path_event,
- .freeze = dasd_generic_pm_freeze,
- .thaw = dasd_generic_restore_device,
- .restore = dasd_generic_restore_device,
.int_class = IRQIO_DAS,
};
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index fa552f9f1666..7a34161ea5c6 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -355,10 +355,6 @@ struct dasd_discipline {
int (*fill_info) (struct dasd_device *, struct dasd_information2_t *);
int (*ioctl) (struct dasd_block *, unsigned int, void __user *);
- /* suspend/resume functions */
- int (*freeze) (struct dasd_device *);
- int (*restore) (struct dasd_device *);
-
/* reload device after state change */
int (*reload) (struct dasd_device *);
@@ -520,7 +516,6 @@ struct dasd_device {
atomic_t tasklet_scheduled;
struct tasklet_struct tasklet;
struct work_struct kick_work;
- struct work_struct restore_device;
struct work_struct reload_device;
struct work_struct kick_validate;
struct work_struct suc_work;
@@ -592,8 +587,6 @@ struct dasd_queue {
#define DASD_STOPPED_PENDING 4 /* long busy */
#define DASD_STOPPED_DC_WAIT 8 /* disconnected, wait */
#define DASD_STOPPED_SU 16 /* summary unit check handling */
-#define DASD_STOPPED_PM 32 /* pm state transition */
-#define DASD_UNRESUMED_PM 64 /* pm resume failed state */
#define DASD_STOPPED_NOSPC 128 /* no space left */
/* per device flags */
@@ -753,7 +746,6 @@ enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved);
void dasd_enable_device(struct dasd_device *);
void dasd_set_target_state(struct dasd_device *, int);
void dasd_kick_device(struct dasd_device *);
-void dasd_restore_device(struct dasd_device *);
void dasd_reload_device(struct dasd_device *);
void dasd_schedule_requeue(struct dasd_device *);
@@ -785,8 +777,6 @@ int dasd_generic_path_operational(struct dasd_device *);
void dasd_generic_shutdown(struct ccw_device *);
void dasd_generic_handle_state_change(struct dasd_device *);
-int dasd_generic_pm_freeze(struct ccw_device *);
-int dasd_generic_restore_device(struct ccw_device *);
enum uc_todo dasd_generic_uc_handler(struct ccw_device *, struct irb *);
void dasd_generic_path_event(struct ccw_device *, int *);
int dasd_generic_verify_path(struct dasd_device *, __u8);
diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c
index d8acabbb1ed3..1354c42d95aa 100644
--- a/drivers/s390/char/con3215.c
+++ b/drivers/s390/char/con3215.c
@@ -289,16 +289,14 @@ static void raw3215_timeout(struct timer_list *t)
spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
raw->flags &= ~RAW3215_TIMER_RUNS;
- if (!tty_port_suspended(&raw->port)) {
- raw3215_mk_write_req(raw);
- raw3215_start_io(raw);
- if ((raw->queued_read || raw->queued_write) &&
- !(raw->flags & RAW3215_WORKING) &&
- !(raw->flags & RAW3215_TIMER_RUNS)) {
- raw->timer.expires = RAW3215_TIMEOUT + jiffies;
- add_timer(&raw->timer);
- raw->flags |= RAW3215_TIMER_RUNS;
- }
+ raw3215_mk_write_req(raw);
+ raw3215_start_io(raw);
+ if ((raw->queued_read || raw->queued_write) &&
+ !(raw->flags & RAW3215_WORKING) &&
+ !(raw->flags & RAW3215_TIMER_RUNS)) {
+ raw->timer.expires = RAW3215_TIMEOUT + jiffies;
+ add_timer(&raw->timer);
+ raw->flags |= RAW3215_TIMER_RUNS;
}
spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
}
@@ -311,7 +309,7 @@ static void raw3215_timeout(struct timer_list *t)
*/
static inline void raw3215_try_io(struct raw3215_info *raw)
{
- if (!tty_port_initialized(&raw->port) || tty_port_suspended(&raw->port))
+ if (!tty_port_initialized(&raw->port))
return;
if (raw->queued_read != NULL)
raw3215_start_io(raw);
@@ -464,26 +462,6 @@ put_tty:
}
/*
- * Drop the oldest line from the output buffer.
- */
-static void raw3215_drop_line(struct raw3215_info *raw)
-{
- int ix;
- char ch;
-
- BUG_ON(raw->written != 0);
- ix = (raw->head - raw->count) & (RAW3215_BUFFER_SIZE - 1);
- while (raw->count > 0) {
- ch = raw->buffer[ix];
- ix = (ix + 1) & (RAW3215_BUFFER_SIZE - 1);
- raw->count--;
- if (ch == 0x15)
- break;
- }
- raw->head = ix;
-}
-
-/*
* Wait until length bytes are available int the output buffer.
* Has to be called with the s390irq lock held. Can be called
* disabled.
@@ -491,13 +469,6 @@ static void raw3215_drop_line(struct raw3215_info *raw)
static void raw3215_make_room(struct raw3215_info *raw, unsigned int length)
{
while (RAW3215_BUFFER_SIZE - raw->count < length) {
- /* While console is frozen for suspend we have no other
- * choice but to drop message from the buffer to make
- * room for even more messages. */
- if (tty_port_suspended(&raw->port)) {
- raw3215_drop_line(raw);
- continue;
- }
/* there might be a request pending */
raw->flags |= RAW3215_FLUSHING;
raw3215_mk_write_req(raw);
@@ -763,36 +734,6 @@ static int raw3215_set_offline (struct ccw_device *cdev)
return 0;
}
-static int raw3215_pm_stop(struct ccw_device *cdev)
-{
- struct raw3215_info *raw;
- unsigned long flags;
-
- /* Empty the output buffer, then prevent new I/O. */
- raw = dev_get_drvdata(&cdev->dev);
- spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
- raw3215_make_room(raw, RAW3215_BUFFER_SIZE);
- tty_port_set_suspended(&raw->port, 1);
- spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
- return 0;
-}
-
-static int raw3215_pm_start(struct ccw_device *cdev)
-{
- struct raw3215_info *raw;
- unsigned long flags;
-
- /* Allow I/O again and flush output buffer. */
- raw = dev_get_drvdata(&cdev->dev);
- spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
- tty_port_set_suspended(&raw->port, 0);
- raw->flags |= RAW3215_FLUSHING;
- raw3215_try_io(raw);
- raw->flags &= ~RAW3215_FLUSHING;
- spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
- return 0;
-}
-
static struct ccw_device_id raw3215_id[] = {
{ CCW_DEVICE(0x3215, 0) },
{ /* end of list */ },
@@ -808,9 +749,6 @@ static struct ccw_driver raw3215_ccw_driver = {
.remove = &raw3215_remove,
.set_online = &raw3215_set_online,
.set_offline = &raw3215_set_offline,
- .freeze = &raw3215_pm_stop,
- .thaw = &raw3215_pm_start,
- .restore = &raw3215_pm_start,
.int_class = IRQIO_C15,
};
@@ -858,11 +796,6 @@ static void con3215_flush(void)
unsigned long flags;
raw = raw3215[0]; /* console 3215 is the first one */
- if (tty_port_suspended(&raw->port))
- /* The console is still frozen for suspend. */
- if (ccw_device_force_console(raw->cdev))
- /* Forcing didn't work, no panic message .. */
- return;
spin_lock_irqsave(get_ccwdev_lock(raw->cdev), flags);
raw3215_make_room(raw, RAW3215_BUFFER_SIZE);
spin_unlock_irqrestore(get_ccwdev_lock(raw->cdev), flags);
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index e17364e13d2f..e21962c0fd94 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -544,7 +544,6 @@ con3270_flush(void)
cp = condev;
if (!cp->view.dev)
return;
- raw3270_pm_unfreeze(&cp->view);
raw3270_activate_view(&cp->view);
spin_lock_irqsave(&cp->view.lock, flags);
con3270_wait_write(cp);
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index 63a41b168761..646ec796bb83 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -67,7 +67,6 @@ struct raw3270 {
#define RAW3270_FLAGS_14BITADDR 0 /* 14-bit buffer addresses */
#define RAW3270_FLAGS_BUSY 1 /* Device busy, leave it alone */
#define RAW3270_FLAGS_CONSOLE 2 /* Device is the console. */
-#define RAW3270_FLAGS_FROZEN 3 /* set if 3270 is frozen for suspend */
/* Semaphore to protect global data of raw3270 (devices, views, etc). */
static DEFINE_MUTEX(raw3270_mutex);
@@ -260,8 +259,7 @@ raw3270_view_active(struct raw3270_view *view)
{
struct raw3270 *rp = view->dev;
- return rp && rp->view == view &&
- !test_bit(RAW3270_FLAGS_FROZEN, &rp->flags);
+ return rp && rp->view == view;
}
int
@@ -273,8 +271,7 @@ raw3270_start(struct raw3270_view *view, struct raw3270_request *rq)
spin_lock_irqsave(get_ccwdev_lock(view->dev->cdev), flags);
rp = view->dev;
- if (!rp || rp->view != view ||
- test_bit(RAW3270_FLAGS_FROZEN, &rp->flags))
+ if (!rp || rp->view != view)
rc = -EACCES;
else if (!raw3270_state_ready(rp))
rc = -EBUSY;
@@ -291,8 +288,7 @@ raw3270_start_locked(struct raw3270_view *view, struct raw3270_request *rq)
int rc;
rp = view->dev;
- if (!rp || rp->view != view ||
- test_bit(RAW3270_FLAGS_FROZEN, &rp->flags))
+ if (!rp || rp->view != view)
rc = -EACCES;
else if (!raw3270_state_ready(rp))
rc = -EBUSY;
@@ -629,8 +625,7 @@ raw3270_reset(struct raw3270_view *view)
int rc;
rp = view->dev;
- if (!rp || rp->view != view ||
- test_bit(RAW3270_FLAGS_FROZEN, &rp->flags))
+ if (!rp || rp->view != view)
rc = -EACCES;
else if (!raw3270_state_ready(rp))
rc = -EBUSY;
@@ -854,8 +849,6 @@ raw3270_activate_view(struct raw3270_view *view)
rc = 0;
else if (!raw3270_state_ready(rp))
rc = -EBUSY;
- else if (test_bit(RAW3270_FLAGS_FROZEN, &rp->flags))
- rc = -EACCES;
else {
oldview = NULL;
if (rp->view && rp->view->fn->deactivate) {
@@ -903,8 +896,7 @@ raw3270_deactivate_view(struct raw3270_view *view)
list_del_init(&view->list);
list_add_tail(&view->list, &rp->view_list);
/* Try to activate another view. */
- if (raw3270_state_ready(rp) &&
- !test_bit(RAW3270_FLAGS_FROZEN, &rp->flags)) {
+ if (raw3270_state_ready(rp)) {
list_for_each_entry(view, &rp->view_list, list) {
rp->view = view;
if (view->fn->activate(view) == 0)
@@ -999,8 +991,7 @@ raw3270_del_view(struct raw3270_view *view)
rp->view = NULL;
}
list_del_init(&view->list);
- if (!rp->view && raw3270_state_ready(rp) &&
- !test_bit(RAW3270_FLAGS_FROZEN, &rp->flags)) {
+ if (!rp->view && raw3270_state_ready(rp)) {
/* Try to activate another view. */
list_for_each_entry(nv, &rp->view_list, list) {
if (nv->fn->activate(nv) == 0) {
@@ -1215,60 +1206,6 @@ raw3270_set_offline (struct ccw_device *cdev)
return 0;
}
-static int raw3270_pm_stop(struct ccw_device *cdev)
-{
- struct raw3270 *rp;
- struct raw3270_view *view;
- unsigned long flags;
-
- rp = dev_get_drvdata(&cdev->dev);
- if (!rp)
- return 0;
- spin_lock_irqsave(get_ccwdev_lock(rp->cdev), flags);
- if (rp->view && rp->view->fn->deactivate)
- rp->view->fn->deactivate(rp->view);
- if (!test_bit(RAW3270_FLAGS_CONSOLE, &rp->flags)) {
- /*
- * Release tty and fullscreen for all non-console
- * devices.
- */
- list_for_each_entry(view, &rp->view_list, list) {
- if (view->fn->release)
- view->fn->release(view);
- }
- }
- set_bit(RAW3270_FLAGS_FROZEN, &rp->flags);
- spin_unlock_irqrestore(get_ccwdev_lock(rp->cdev), flags);
- return 0;
-}
-
-static int raw3270_pm_start(struct ccw_device *cdev)
-{
- struct raw3270 *rp;
- unsigned long flags;
-
- rp = dev_get_drvdata(&cdev->dev);
- if (!rp)
- return 0;
- spin_lock_irqsave(get_ccwdev_lock(rp->cdev), flags);
- clear_bit(RAW3270_FLAGS_FROZEN, &rp->flags);
- if (rp->view && rp->view->fn->activate)
- rp->view->fn->activate(rp->view);
- spin_unlock_irqrestore(get_ccwdev_lock(rp->cdev), flags);
- return 0;
-}
-
-void raw3270_pm_unfreeze(struct raw3270_view *view)
-{
-#ifdef CONFIG_TN3270_CONSOLE
- struct raw3270 *rp;
-
- rp = view->dev;
- if (rp && test_bit(RAW3270_FLAGS_FROZEN, &rp->flags))
- ccw_device_force_console(rp->cdev);
-#endif
-}
-
static struct ccw_device_id raw3270_id[] = {
{ CCW_DEVICE(0x3270, 0) },
{ CCW_DEVICE(0x3271, 0) },
@@ -1294,9 +1231,6 @@ static struct ccw_driver raw3270_ccw_driver = {
.remove = &raw3270_remove,
.set_online = &raw3270_set_online,
.set_offline = &raw3270_set_offline,
- .freeze = &raw3270_pm_stop,
- .thaw = &raw3270_pm_start,
- .restore = &raw3270_pm_start,
.int_class = IRQIO_C70,
};
diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h
index 8d979e0ee605..c6645167cd2b 100644
--- a/drivers/s390/char/raw3270.h
+++ b/drivers/s390/char/raw3270.h
@@ -199,7 +199,6 @@ struct raw3270_notifier {
int raw3270_register_notifier(struct raw3270_notifier *);
void raw3270_unregister_notifier(struct raw3270_notifier *);
-void raw3270_pm_unfreeze(struct raw3270_view *);
/*
* Little memory allocator for string objects.
diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h
index 69d9cde9ff5a..6de919944a39 100644
--- a/drivers/s390/char/sclp.h
+++ b/drivers/s390/char/sclp.h
@@ -156,7 +156,11 @@ struct read_cpu_info_sccb {
u16 offset_configured;
u16 nr_standby;
u16 offset_standby;
- u8 reserved[4096 - 16];
+ /*
+ * Without ext sccb, struct size is PAGE_SIZE.
+ * With ext sccb, struct size is EXT_SCCB_READ_CPU.
+ */
+ u8 reserved[];
} __attribute__((packed, aligned(PAGE_SIZE)));
struct read_info_sccb {
@@ -199,7 +203,7 @@ struct read_info_sccb {
u8 byte_134; /* 134 */
u8 cpudirq; /* 135 */
u16 cbl; /* 136-137 */
- u8 _pad_138[4096 - 138]; /* 138-4095 */
+ u8 _pad_138[EXT_SCCB_READ_SCP - 138];
} __packed __aligned(PAGE_SIZE);
struct read_storage_sccb {
@@ -328,7 +332,7 @@ unsigned int sclp_early_con_check_vt220(struct init_sccb *sccb);
int sclp_early_set_event_mask(struct init_sccb *sccb,
sccb_mask_t receive_mask,
sccb_mask_t send_mask);
-int sclp_early_get_info(struct read_info_sccb *info);
+struct read_info_sccb * __init sclp_early_get_info(void);
/* useful inlines */
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index f6e97f0830f6..d41bc144c183 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -27,6 +27,7 @@
#include <asm/page.h>
#include <asm/sclp.h>
#include <asm/numa.h>
+#include <asm/facility.h>
#include "sclp.h"
@@ -87,14 +88,17 @@ out:
int _sclp_get_core_info(struct sclp_core_info *info)
{
int rc;
+ int length = test_facility(140) ? EXT_SCCB_READ_CPU : PAGE_SIZE;
struct read_cpu_info_sccb *sccb;
if (!SCLP_HAS_CPU_INFO)
return -EOPNOTSUPP;
- sccb = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
+
+ sccb = (void *)__get_free_pages(GFP_KERNEL | GFP_DMA | __GFP_ZERO, get_order(length));
if (!sccb)
return -ENOMEM;
- sccb->header.length = sizeof(*sccb);
+ sccb->header.length = length;
+ sccb->header.control_mask[2] = 0x80;
rc = sclp_sync_request_timeout(SCLP_CMDW_READ_CPU_INFO, sccb,
SCLP_QUEUE_INTERVAL);
if (rc)
@@ -107,7 +111,7 @@ int _sclp_get_core_info(struct sclp_core_info *info)
}
sclp_fill_core_info(info, sccb);
out:
- free_page((unsigned long) sccb);
+ free_pages((unsigned long) sccb, get_order(length));
return rc;
}
@@ -397,10 +401,10 @@ static void __init add_memory_merged(u16 rn)
goto skip_add;
if (start + size > VMEM_MAX_PHYS)
size = VMEM_MAX_PHYS - start;
- if (memory_end_set && (start >= memory_end))
+ if (start >= ident_map_size)
goto skip_add;
- if (memory_end_set && (start + size > memory_end))
- size = memory_end - start;
+ if (start + size > ident_map_size)
+ size = ident_map_size - start;
block_size = memory_block_size_bytes();
align_to_block_size(&start, &size, block_size);
if (!size)
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index cc5e84b80c69..2f3515fa242a 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -9,9 +9,12 @@
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/errno.h>
+#include <linux/memblock.h>
#include <asm/ctl_reg.h>
#include <asm/sclp.h>
#include <asm/ipl.h>
+#include <asm/setup.h>
+#include <asm/facility.h>
#include "sclp_sdias.h"
#include "sclp.h"
@@ -20,12 +23,14 @@ static struct sclp_ipl_info sclp_ipl_info;
struct sclp_info sclp;
EXPORT_SYMBOL(sclp);
-static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
+static void __init sclp_early_facilities_detect(void)
{
struct sclp_core_entry *cpue;
+ struct read_info_sccb *sccb;
u16 boot_cpu_address, cpu;
- if (sclp_early_get_info(sccb))
+ sccb = sclp_early_get_info();
+ if (!sccb)
return;
sclp.facilities = sccb->facilities;
@@ -107,29 +112,34 @@ void __init sclp_early_get_ipl_info(struct sclp_ipl_info *info)
*info = sclp_ipl_info;
}
-static struct sclp_core_info sclp_early_core_info __initdata;
-static int sclp_early_core_info_valid __initdata;
-
-static void __init sclp_early_init_core_info(struct read_cpu_info_sccb *sccb)
-{
- if (!SCLP_HAS_CPU_INFO)
- return;
- memset(sccb, 0, sizeof(*sccb));
- sccb->header.length = sizeof(*sccb);
- if (sclp_early_cmd(SCLP_CMDW_READ_CPU_INFO, sccb))
- return;
- if (sccb->header.response_code != 0x0010)
- return;
- sclp_fill_core_info(&sclp_early_core_info, sccb);
- sclp_early_core_info_valid = 1;
-}
-
int __init sclp_early_get_core_info(struct sclp_core_info *info)
{
- if (!sclp_early_core_info_valid)
- return -EIO;
- *info = sclp_early_core_info;
- return 0;
+ struct read_cpu_info_sccb *sccb;
+ int length = test_facility(140) ? EXT_SCCB_READ_CPU : PAGE_SIZE;
+ int rc = 0;
+
+ if (!SCLP_HAS_CPU_INFO)
+ return -EOPNOTSUPP;
+
+ sccb = memblock_alloc_low(length, PAGE_SIZE);
+ if (!sccb)
+ return -ENOMEM;
+
+ memset(sccb, 0, length);
+ sccb->header.length = length;
+ sccb->header.control_mask[2] = 0x80;
+ if (sclp_early_cmd(SCLP_CMDW_READ_CPU_INFO, sccb)) {
+ rc = -EIO;
+ goto out;
+ }
+ if (sccb->header.response_code != 0x0010) {
+ rc = -EIO;
+ goto out;
+ }
+ sclp_fill_core_info(info, sccb);
+out:
+ memblock_free_early((unsigned long)sccb, length);
+ return rc;
}
static void __init sclp_early_console_detect(struct init_sccb *sccb)
@@ -148,8 +158,7 @@ void __init sclp_early_detect(void)
{
void *sccb = sclp_early_sccb;
- sclp_early_facilities_detect(sccb);
- sclp_early_init_core_info(sccb);
+ sclp_early_facilities_detect();
/*
* Turn off SCLP event notifications. Also save remote masks in the
diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c
index a960afa974bf..ec9f8ad5341c 100644
--- a/drivers/s390/char/sclp_early_core.c
+++ b/drivers/s390/char/sclp_early_core.c
@@ -11,6 +11,7 @@
#include <asm/irq.h>
#include <asm/sections.h>
#include <asm/mem_detect.h>
+#include <asm/facility.h>
#include "sclp.h"
#include "sclp_rw.h"
@@ -237,13 +238,14 @@ void sclp_early_printk(const char *str)
int __init sclp_early_read_info(void)
{
int i;
+ int length = test_facility(140) ? EXT_SCCB_READ_SCP : PAGE_SIZE;
struct read_info_sccb *sccb = &sclp_info_sccb;
sclp_cmdw_t commands[] = {SCLP_CMDW_READ_SCP_INFO_FORCED,
SCLP_CMDW_READ_SCP_INFO};
for (i = 0; i < ARRAY_SIZE(commands); i++) {
- memset(sccb, 0, sizeof(*sccb));
- sccb->header.length = sizeof(*sccb);
+ memset(sccb, 0, length);
+ sccb->header.length = length;
sccb->header.function_code = 0x80;
sccb->header.control_mask[2] = 0x80;
if (sclp_early_cmd(commands[i], sccb))
@@ -258,13 +260,12 @@ int __init sclp_early_read_info(void)
return -EIO;
}
-int __init sclp_early_get_info(struct read_info_sccb *info)
+struct read_info_sccb * __init sclp_early_get_info(void)
{
if (!sclp_info_sccb_valid)
- return -EIO;
+ return NULL;
- *info = sclp_info_sccb;
- return 0;
+ return &sclp_info_sccb;
}
int __init sclp_early_get_memsize(unsigned long *mem)
diff --git a/drivers/s390/char/tape.h b/drivers/s390/char/tape.h
index e2c60475dfa8..4e5d5efa978f 100644
--- a/drivers/s390/char/tape.h
+++ b/drivers/s390/char/tape.h
@@ -264,7 +264,6 @@ extern void tape_state_set(struct tape_device *, enum tape_state);
extern int tape_generic_online(struct tape_device *, struct tape_discipline *);
extern int tape_generic_offline(struct ccw_device *);
-extern int tape_generic_pm_suspend(struct ccw_device *);
/* Externals from tape_devmap.c */
extern int tape_generic_probe(struct ccw_device *);
diff --git a/drivers/s390/char/tape_34xx.c b/drivers/s390/char/tape_34xx.c
index 6d73ee3f827a..7ada994d4592 100644
--- a/drivers/s390/char/tape_34xx.c
+++ b/drivers/s390/char/tape_34xx.c
@@ -1191,7 +1191,6 @@ static struct ccw_driver tape_34xx_driver = {
.remove = tape_generic_remove,
.set_online = tape_34xx_online,
.set_offline = tape_generic_offline,
- .freeze = tape_generic_pm_suspend,
.int_class = IRQIO_TAP,
};
diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 4554cdf4d6bd..ecf8c5006a0e 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -1651,7 +1651,6 @@ static struct ccw_driver tape_3590_driver = {
.remove = tape_generic_remove,
.set_offline = tape_generic_offline,
.set_online = tape_3590_online,
- .freeze = tape_generic_pm_suspend,
.int_class = IRQIO_TAP,
};
diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c
index 380e6a67719c..a6d2a4792185 100644
--- a/drivers/s390/char/tape_core.c
+++ b/drivers/s390/char/tape_core.c
@@ -428,55 +428,6 @@ tape_cleanup_device(struct tape_device *device)
}
/*
- * Suspend device.
- *
- * Called by the common I/O layer if the drive should be suspended on user
- * request. We refuse to suspend if the device is loaded or in use for the
- * following reason:
- * While the Linux guest is suspended, it might be logged off which causes
- * devices to be detached. Tape devices are automatically rewound and unloaded
- * during DETACH processing (unless the tape device was attached with the
- * NOASSIGN or MULTIUSER option). After rewind/unload, there is no way to
- * resume the original state of the tape device, since we would need to
- * manually re-load the cartridge which was active at suspend time.
- */
-int tape_generic_pm_suspend(struct ccw_device *cdev)
-{
- struct tape_device *device;
-
- device = dev_get_drvdata(&cdev->dev);
- if (!device) {
- return -ENODEV;
- }
-
- DBF_LH(3, "(%08x): tape_generic_pm_suspend(%p)\n",
- device->cdev_id, device);
-
- if (device->medium_state != MS_UNLOADED) {
- pr_err("A cartridge is loaded in tape device %s, "
- "refusing to suspend\n", dev_name(&cdev->dev));
- return -EBUSY;
- }
-
- spin_lock_irq(get_ccwdev_lock(device->cdev));
- switch (device->tape_state) {
- case TS_INIT:
- case TS_NOT_OPER:
- case TS_UNUSED:
- spin_unlock_irq(get_ccwdev_lock(device->cdev));
- break;
- default:
- pr_err("Tape device %s is busy, refusing to "
- "suspend\n", dev_name(&cdev->dev));
- spin_unlock_irq(get_ccwdev_lock(device->cdev));
- return -EBUSY;
- }
-
- DBF_LH(3, "(%08x): Drive suspended.\n", device->cdev_id);
- return 0;
-}
-
-/*
* Set device offline.
*
* Called by the common I/O layer if the drive should set offline on user
@@ -1360,7 +1311,6 @@ EXPORT_SYMBOL(tape_generic_remove);
EXPORT_SYMBOL(tape_generic_probe);
EXPORT_SYMBOL(tape_generic_online);
EXPORT_SYMBOL(tape_generic_offline);
-EXPORT_SYMBOL(tape_generic_pm_suspend);
EXPORT_SYMBOL(tape_put_device);
EXPORT_SYMBOL(tape_get_device);
EXPORT_SYMBOL(tape_state_verbose);
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
index cbde65ab2170..1bbf27b98cf6 100644
--- a/drivers/s390/char/vmur.c
+++ b/drivers/s390/char/vmur.c
@@ -62,7 +62,6 @@ static int ur_probe(struct ccw_device *cdev);
static void ur_remove(struct ccw_device *cdev);
static int ur_set_online(struct ccw_device *cdev);
static int ur_set_offline(struct ccw_device *cdev);
-static int ur_pm_suspend(struct ccw_device *cdev);
static struct ccw_driver ur_driver = {
.driver = {
@@ -74,7 +73,6 @@ static struct ccw_driver ur_driver = {
.remove = ur_remove,
.set_online = ur_set_online,
.set_offline = ur_set_offline,
- .freeze = ur_pm_suspend,
.int_class = IRQIO_VMR,
};
@@ -165,28 +163,6 @@ static void urdev_put(struct urdev *urd)
}
/*
- * State and contents of ur devices can be changed by class D users issuing
- * CP commands such as PURGE or TRANSFER, while the Linux guest is suspended.
- * Also the Linux guest might be logged off, which causes all active spool
- * files to be closed.
- * So we cannot guarantee that spool files are still the same when the Linux
- * guest is resumed. In order to avoid unpredictable results at resume time
- * we simply refuse to suspend if a ur device node is open.
- */
-static int ur_pm_suspend(struct ccw_device *cdev)
-{
- struct urdev *urd = dev_get_drvdata(&cdev->dev);
-
- TRACE("ur_pm_suspend: cdev=%p\n", cdev);
- if (urd->open_flag) {
- pr_err("Unit record device %s is busy, %s refusing to "
- "suspend.\n", dev_name(&cdev->dev), ur_banner);
- return -EBUSY;
- }
- return 0;
-}
-
-/*
* Low-level functions to do I/O to a ur device.
* alloc_chan_prog
* free_chan_prog
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 8f080d3fd380..c42405c620b5 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -120,31 +120,6 @@ static void chsc_subchannel_shutdown(struct subchannel *sch)
cio_disable_subchannel(sch);
}
-static int chsc_subchannel_prepare(struct subchannel *sch)
-{
- int cc;
- struct schib schib;
- /*
- * Don't allow suspend while the subchannel is not idle
- * since we don't have a way to clear the subchannel and
- * cannot disable it with a request running.
- */
- cc = stsch(sch->schid, &schib);
- if (!cc && scsw_stctl(&schib.scsw))
- return -EAGAIN;
- return 0;
-}
-
-static int chsc_subchannel_freeze(struct subchannel *sch)
-{
- return cio_disable_subchannel(sch);
-}
-
-static int chsc_subchannel_restore(struct subchannel *sch)
-{
- return cio_enable_subchannel(sch, (u32)(unsigned long)sch);
-}
-
static struct css_device_id chsc_subchannel_ids[] = {
{ .match_flags = 0x1, .type =SUBCHANNEL_TYPE_CHSC, },
{ /* end of list */ },
@@ -161,10 +136,6 @@ static struct css_driver chsc_subchannel_driver = {
.probe = chsc_subchannel_probe,
.remove = chsc_subchannel_remove,
.shutdown = chsc_subchannel_shutdown,
- .prepare = chsc_subchannel_prepare,
- .freeze = chsc_subchannel_freeze,
- .thaw = chsc_subchannel_restore,
- .restore = chsc_subchannel_restore,
};
static int __init chsc_init_dbfs(void)
diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c
index 72dd2471ec1e..b7b590646d58 100644
--- a/drivers/s390/cio/cmf.c
+++ b/drivers/s390/cio/cmf.c
@@ -1109,11 +1109,6 @@ static ssize_t cmb_enable_store(struct device *dev,
}
DEVICE_ATTR_RW(cmb_enable);
-int ccw_set_cmf(struct ccw_device *cdev, int enable)
-{
- return cmbops->set(cdev, enable ? 2 : 0);
-}
-
/**
* enable_cmf() - switch on the channel measurement for a specific device
* @cdev: The ccw device to be enabled
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index cca1a7c4bb33..94c6470de635 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -18,7 +18,6 @@
#include <linux/errno.h>
#include <linux/list.h>
#include <linux/reboot.h>
-#include <linux/suspend.h>
#include <linux/proc_fs.h>
#include <linux/genalloc.h>
#include <linux/dma-mapping.h>
@@ -1044,59 +1043,6 @@ static struct notifier_block css_reboot_notifier = {
.notifier_call = css_reboot_event,
};
-/*
- * Since the css devices are neither on a bus nor have a class
- * nor have a special device type, we cannot stop/restart channel
- * path measurements via the normal suspend/resume callbacks, but have
- * to use notifiers.
- */
-static int css_power_event(struct notifier_block *this, unsigned long event,
- void *ptr)
-{
- struct channel_subsystem *css;
- int ret;
-
- switch (event) {
- case PM_HIBERNATION_PREPARE:
- case PM_SUSPEND_PREPARE:
- ret = NOTIFY_DONE;
- for_each_css(css) {
- mutex_lock(&css->mutex);
- if (!css->cm_enabled) {
- mutex_unlock(&css->mutex);
- continue;
- }
- ret = __chsc_do_secm(css, 0);
- ret = notifier_from_errno(ret);
- mutex_unlock(&css->mutex);
- }
- break;
- case PM_POST_HIBERNATION:
- case PM_POST_SUSPEND:
- ret = NOTIFY_DONE;
- for_each_css(css) {
- mutex_lock(&css->mutex);
- if (!css->cm_enabled) {
- mutex_unlock(&css->mutex);
- continue;
- }
- ret = __chsc_do_secm(css, 1);
- ret = notifier_from_errno(ret);
- mutex_unlock(&css->mutex);
- }
- /* search for subchannels, which appeared during hibernation */
- css_schedule_reprobe();
- break;
- default:
- ret = NOTIFY_DONE;
- }
- return ret;
-
-}
-static struct notifier_block css_power_notifier = {
- .notifier_call = css_power_event,
-};
-
#define CIO_DMA_GFP (GFP_KERNEL | __GFP_ZERO)
static struct gen_pool *cio_dma_pool;
@@ -1242,12 +1188,9 @@ static int __init css_bus_init(void)
ret = register_reboot_notifier(&css_reboot_notifier);
if (ret)
goto out_unregister;
- ret = register_pm_notifier(&css_power_notifier);
- if (ret)
- goto out_unregister_rn;
ret = cio_dma_pool_init();
if (ret)
- goto out_unregister_pmn;
+ goto out_unregister_rn;
airq_init();
css_init_done = 1;
@@ -1255,8 +1198,6 @@ static int __init css_bus_init(void)
isc_register(IO_SCH_ISC);
return 0;
-out_unregister_pmn:
- unregister_pm_notifier(&css_power_notifier);
out_unregister_rn:
unregister_reboot_notifier(&css_reboot_notifier);
out_unregister:
@@ -1456,74 +1397,6 @@ static int css_uevent(struct device *dev, struct kobj_uevent_env *env)
return ret;
}
-static int css_pm_prepare(struct device *dev)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct css_driver *drv;
-
- if (mutex_is_locked(&sch->reg_mutex))
- return -EAGAIN;
- if (!sch->dev.driver)
- return 0;
- drv = to_cssdriver(sch->dev.driver);
- /* Notify drivers that they may not register children. */
- return drv->prepare ? drv->prepare(sch) : 0;
-}
-
-static void css_pm_complete(struct device *dev)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct css_driver *drv;
-
- if (!sch->dev.driver)
- return;
- drv = to_cssdriver(sch->dev.driver);
- if (drv->complete)
- drv->complete(sch);
-}
-
-static int css_pm_freeze(struct device *dev)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct css_driver *drv;
-
- if (!sch->dev.driver)
- return 0;
- drv = to_cssdriver(sch->dev.driver);
- return drv->freeze ? drv->freeze(sch) : 0;
-}
-
-static int css_pm_thaw(struct device *dev)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct css_driver *drv;
-
- if (!sch->dev.driver)
- return 0;
- drv = to_cssdriver(sch->dev.driver);
- return drv->thaw ? drv->thaw(sch) : 0;
-}
-
-static int css_pm_restore(struct device *dev)
-{
- struct subchannel *sch = to_subchannel(dev);
- struct css_driver *drv;
-
- css_update_ssd_info(sch);
- if (!sch->dev.driver)
- return 0;
- drv = to_cssdriver(sch->dev.driver);
- return drv->restore ? drv->restore(sch) : 0;
-}
-
-static const struct dev_pm_ops css_pm_ops = {
- .prepare = css_pm_prepare,
- .complete = css_pm_complete,
- .freeze = css_pm_freeze,
- .thaw = css_pm_thaw,
- .restore = css_pm_restore,
-};
-
static struct bus_type css_bus_type = {
.name = "css",
.match = css_bus_match,
@@ -1531,7 +1404,6 @@ static struct bus_type css_bus_type = {
.remove = css_remove,
.shutdown = css_shutdown,
.uevent = css_uevent,
- .pm = &css_pm_ops,
};
/**
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 3f322ea0f498..2eddfc47f687 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -72,11 +72,6 @@ struct chp_link;
* @probe: function called on probe
* @remove: function called on remove
* @shutdown: called at device shutdown
- * @prepare: prepare for pm state transition
- * @complete: undo work done in @prepare
- * @freeze: callback for freezing during hibernation snapshotting
- * @thaw: undo work done in @freeze
- * @restore: callback for restoring after hibernation
* @settle: wait for asynchronous work to finish
*/
struct css_driver {
@@ -88,11 +83,6 @@ struct css_driver {
int (*probe)(struct subchannel *);
int (*remove)(struct subchannel *);
void (*shutdown)(struct subchannel *);
- int (*prepare) (struct subchannel *);
- void (*complete) (struct subchannel *);
- int (*freeze)(struct subchannel *);
- int (*thaw) (struct subchannel *);
- int (*restore)(struct subchannel *);
int (*settle)(void);
};
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index b29fe8d50baf..e0005a4fc978 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -149,19 +149,6 @@ static struct css_device_id io_subchannel_ids[] = {
{ /* end of list */ },
};
-static int io_subchannel_prepare(struct subchannel *sch)
-{
- struct ccw_device *cdev;
- /*
- * Don't allow suspend while a ccw device registration
- * is still outstanding.
- */
- cdev = sch_get_cdev(sch);
- if (cdev && !device_is_registered(&cdev->dev))
- return -EAGAIN;
- return 0;
-}
-
static int io_subchannel_settle(void)
{
int ret;
@@ -186,7 +173,6 @@ static struct css_driver io_subchannel_driver = {
.probe = io_subchannel_probe,
.remove = io_subchannel_remove,
.shutdown = io_subchannel_shutdown,
- .prepare = io_subchannel_prepare,
.settle = io_subchannel_settle,
};
@@ -1422,7 +1408,7 @@ static enum io_sch_action sch_get_action(struct subchannel *sch)
}
if (device_is_disconnected(cdev))
return IO_SCH_REPROBE;
- if (cdev->online && !cdev->private->flags.resuming)
+ if (cdev->online)
return IO_SCH_VERIFY;
if (cdev->private->state == DEV_STATE_NOT_OPER)
return IO_SCH_UNREG_ATTACH;
@@ -1514,11 +1500,6 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
break;
case IO_SCH_UNREG_ATTACH:
spin_lock_irqsave(sch->lock, flags);
- if (cdev->private->flags.resuming) {
- /* Device will be handled later. */
- rc = 0;
- goto out_unlock;
- }
sch_set_cdev(sch, NULL);
spin_unlock_irqrestore(sch->lock, flags);
/* Unregister ccw device. */
@@ -1531,7 +1512,7 @@ static int io_subchannel_sch_event(struct subchannel *sch, int process)
switch (action) {
case IO_SCH_ORPH_UNREG:
case IO_SCH_UNREG:
- if (!cdev || !cdev->private->flags.resuming)
+ if (!cdev)
css_sch_device_unregister(sch);
break;
case IO_SCH_ORPH_ATTACH:
@@ -1664,10 +1645,10 @@ void __init ccw_device_destroy_console(struct ccw_device *cdev)
struct io_subchannel_private *io_priv = to_io_private(sch);
set_io_private(sch, NULL);
- put_device(&sch->dev);
- put_device(&cdev->dev);
dma_free_coherent(&sch->dev, sizeof(*io_priv->dma_area),
io_priv->dma_area, io_priv->dma_area_dma);
+ put_device(&sch->dev);
+ put_device(&cdev->dev);
kfree(io_priv);
}
@@ -1690,14 +1671,6 @@ void ccw_device_wait_idle(struct ccw_device *cdev)
udelay_simple(100);
}
}
-
-static int ccw_device_pm_restore(struct device *dev);
-
-int ccw_device_force_console(struct ccw_device *cdev)
-{
- return ccw_device_pm_restore(&cdev->dev);
-}
-EXPORT_SYMBOL_GPL(ccw_device_force_console);
#endif
/**
@@ -1798,235 +1771,6 @@ static void ccw_device_shutdown(struct device *dev)
__disable_cmf(cdev);
}
-static int ccw_device_pm_prepare(struct device *dev)
-{
- struct ccw_device *cdev = to_ccwdev(dev);
-
- if (work_pending(&cdev->private->todo_work))
- return -EAGAIN;
- /* Fail while device is being set online/offline. */
- if (atomic_read(&cdev->private->onoff))
- return -EAGAIN;
-
- if (cdev->online && cdev->drv && cdev->drv->prepare)
- return cdev->drv->prepare(cdev);
-
- return 0;
-}
-
-static void ccw_device_pm_complete(struct device *dev)
-{
- struct ccw_device *cdev = to_ccwdev(dev);
-
- if (cdev->online && cdev->drv && cdev->drv->complete)
- cdev->drv->complete(cdev);
-}
-
-static int ccw_device_pm_freeze(struct device *dev)
-{
- struct ccw_device *cdev = to_ccwdev(dev);
- struct subchannel *sch = to_subchannel(cdev->dev.parent);
- int ret, cm_enabled;
-
- /* Fail suspend while device is in transistional state. */
- if (!dev_fsm_final_state(cdev))
- return -EAGAIN;
- if (!cdev->online)
- return 0;
- if (cdev->drv && cdev->drv->freeze) {
- ret = cdev->drv->freeze(cdev);
- if (ret)
- return ret;
- }
-
- spin_lock_irq(sch->lock);
- cm_enabled = cdev->private->cmb != NULL;
- spin_unlock_irq(sch->lock);
- if (cm_enabled) {
- /* Don't have the css write on memory. */
- ret = ccw_set_cmf(cdev, 0);
- if (ret)
- return ret;
- }
- /* From here on, disallow device driver I/O. */
- spin_lock_irq(sch->lock);
- ret = cio_disable_subchannel(sch);
- spin_unlock_irq(sch->lock);
-
- return ret;
-}
-
-static int ccw_device_pm_thaw(struct device *dev)
-{
- struct ccw_device *cdev = to_ccwdev(dev);
- struct subchannel *sch = to_subchannel(cdev->dev.parent);
- int ret, cm_enabled;
-
- if (!cdev->online)
- return 0;
-
- spin_lock_irq(sch->lock);
- /* Allow device driver I/O again. */
- ret = cio_enable_subchannel(sch, (u32)(addr_t)sch);
- cm_enabled = cdev->private->cmb != NULL;
- spin_unlock_irq(sch->lock);
- if (ret)
- return ret;
-
- if (cm_enabled) {
- ret = ccw_set_cmf(cdev, 1);
- if (ret)
- return ret;
- }
-
- if (cdev->drv && cdev->drv->thaw)
- ret = cdev->drv->thaw(cdev);
-
- return ret;
-}
-
-static void __ccw_device_pm_restore(struct ccw_device *cdev)
-{
- struct subchannel *sch = to_subchannel(cdev->dev.parent);
-
- spin_lock_irq(sch->lock);
- if (cio_is_console(sch->schid)) {
- cio_enable_subchannel(sch, (u32)(addr_t)sch);
- goto out_unlock;
- }
- /*
- * While we were sleeping, devices may have gone or become
- * available again. Kick re-detection.
- */
- cdev->private->flags.resuming = 1;
- cdev->private->path_new_mask = LPM_ANYPATH;
- css_sched_sch_todo(sch, SCH_TODO_EVAL);
- spin_unlock_irq(sch->lock);
- css_wait_for_slow_path();
-
- /* cdev may have been moved to a different subchannel. */
- sch = to_subchannel(cdev->dev.parent);
- spin_lock_irq(sch->lock);
- if (cdev->private->state != DEV_STATE_ONLINE &&
- cdev->private->state != DEV_STATE_OFFLINE)
- goto out_unlock;
-
- ccw_device_recognition(cdev);
- spin_unlock_irq(sch->lock);
- wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev) ||
- cdev->private->state == DEV_STATE_DISCONNECTED);
- spin_lock_irq(sch->lock);
-
-out_unlock:
- cdev->private->flags.resuming = 0;
- spin_unlock_irq(sch->lock);
-}
-
-static int resume_handle_boxed(struct ccw_device *cdev)
-{
- cdev->private->state = DEV_STATE_BOXED;
- if (ccw_device_notify(cdev, CIO_BOXED) == NOTIFY_OK)
- return 0;
- ccw_device_sched_todo(cdev, CDEV_TODO_UNREG);
- return -ENODEV;
-}
-
-static int resume_handle_disc(struct ccw_device *cdev)
-{
- cdev->private->state = DEV_STATE_DISCONNECTED;
- if (ccw_device_notify(cdev, CIO_GONE) == NOTIFY_OK)
- return 0;
- ccw_device_sched_todo(cdev, CDEV_TODO_UNREG);
- return -ENODEV;
-}
-
-static int ccw_device_pm_restore(struct device *dev)
-{
- struct ccw_device *cdev = to_ccwdev(dev);
- struct subchannel *sch;
- int ret = 0;
-
- __ccw_device_pm_restore(cdev);
- sch = to_subchannel(cdev->dev.parent);
- spin_lock_irq(sch->lock);
- if (cio_is_console(sch->schid))
- goto out_restore;
-
- /* check recognition results */
- switch (cdev->private->state) {
- case DEV_STATE_OFFLINE:
- case DEV_STATE_ONLINE:
- cdev->private->flags.donotify = 0;
- break;
- case DEV_STATE_BOXED:
- ret = resume_handle_boxed(cdev);
- if (ret)
- goto out_unlock;
- goto out_restore;
- default:
- ret = resume_handle_disc(cdev);
- if (ret)
- goto out_unlock;
- goto out_restore;
- }
- /* check if the device type has changed */
- if (!ccw_device_test_sense_data(cdev)) {
- ccw_device_update_sense_data(cdev);
- ccw_device_sched_todo(cdev, CDEV_TODO_REBIND);
- ret = -ENODEV;
- goto out_unlock;
- }
- if (!cdev->online)
- goto out_unlock;
-
- if (ccw_device_online(cdev)) {
- ret = resume_handle_disc(cdev);
- if (ret)
- goto out_unlock;
- goto out_restore;
- }
- spin_unlock_irq(sch->lock);
- wait_event(cdev->private->wait_q, dev_fsm_final_state(cdev));
- spin_lock_irq(sch->lock);
-
- if (ccw_device_notify(cdev, CIO_OPER) == NOTIFY_BAD) {
- ccw_device_sched_todo(cdev, CDEV_TODO_UNREG);
- ret = -ENODEV;
- goto out_unlock;
- }
-
- /* reenable cmf, if needed */
- if (cdev->private->cmb) {
- spin_unlock_irq(sch->lock);
- ret = ccw_set_cmf(cdev, 1);
- spin_lock_irq(sch->lock);
- if (ret) {
- CIO_MSG_EVENT(2, "resume: cdev 0.%x.%04x: cmf failed "
- "(rc=%d)\n", cdev->private->dev_id.ssid,
- cdev->private->dev_id.devno, ret);
- ret = 0;
- }
- }
-
-out_restore:
- spin_unlock_irq(sch->lock);
- if (cdev->online && cdev->drv && cdev->drv->restore)
- ret = cdev->drv->restore(cdev);
- return ret;
-
-out_unlock:
- spin_unlock_irq(sch->lock);
- return ret;
-}
-
-static const struct dev_pm_ops ccw_pm_ops = {
- .prepare = ccw_device_pm_prepare,
- .complete = ccw_device_pm_complete,
- .freeze = ccw_device_pm_freeze,
- .thaw = ccw_device_pm_thaw,
- .restore = ccw_device_pm_restore,
-};
-
static struct bus_type ccw_bus_type = {
.name = "ccw",
.match = ccw_bus_match,
@@ -2034,7 +1778,6 @@ static struct bus_type ccw_bus_type = {
.probe = ccw_device_probe,
.remove = ccw_device_remove,
.shutdown = ccw_device_shutdown,
- .pm = &ccw_pm_ops,
};
/**
diff --git a/drivers/s390/cio/device.h b/drivers/s390/cio/device.h
index 853b6a8ca095..24b2fce69590 100644
--- a/drivers/s390/cio/device.h
+++ b/drivers/s390/cio/device.h
@@ -143,6 +143,5 @@ void retry_set_schib(struct ccw_device *cdev);
void cmf_retry_copy_block(struct ccw_device *);
int cmf_reenable(struct ccw_device *);
void cmf_reactivate(void);
-int ccw_set_cmf(struct ccw_device *cdev, int enable);
extern struct device_attribute dev_attr_cmb_enable;
#endif
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 8fc267324ebb..6420b197bb05 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -224,12 +224,6 @@ ccw_device_recog_done(struct ccw_device *cdev, int state)
wake_up(&cdev->private->wait_q);
return;
}
- if (cdev->private->flags.resuming) {
- cdev->private->state = state;
- cdev->private->flags.recog_done = 1;
- wake_up(&cdev->private->wait_q);
- return;
- }
switch (state) {
case DEV_STATE_NOT_OPER:
break;
diff --git a/drivers/s390/cio/eadm_sch.c b/drivers/s390/cio/eadm_sch.c
index 53468ae64b99..c8964e0a23e7 100644
--- a/drivers/s390/cio/eadm_sch.c
+++ b/drivers/s390/cio/eadm_sch.c
@@ -306,16 +306,6 @@ static void eadm_subchannel_shutdown(struct subchannel *sch)
eadm_quiesce(sch);
}
-static int eadm_subchannel_freeze(struct subchannel *sch)
-{
- return cio_disable_subchannel(sch);
-}
-
-static int eadm_subchannel_restore(struct subchannel *sch)
-{
- return cio_enable_subchannel(sch, (u32)(unsigned long)sch);
-}
-
/**
* eadm_subchannel_sch_event - process subchannel event
* @sch: subchannel
@@ -369,9 +359,6 @@ static struct css_driver eadm_subchannel_driver = {
.remove = eadm_subchannel_remove,
.shutdown = eadm_subchannel_shutdown,
.sch_event = eadm_subchannel_sch_event,
- .freeze = eadm_subchannel_freeze,
- .thaw = eadm_subchannel_restore,
- .restore = eadm_subchannel_restore,
};
static int __init eadm_sch_init(void)
diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h
index c03b4a19974e..85a11c1836e5 100644
--- a/drivers/s390/cio/io_sch.h
+++ b/drivers/s390/cio/io_sch.h
@@ -160,7 +160,6 @@ struct ccw_device_private {
unsigned int donotify:1; /* call notify function */
unsigned int recog_done:1; /* dev. recog. complete */
unsigned int fake_irb:2; /* deliver faked irb */
- unsigned int resuming:1; /* recognition while resume */
unsigned int pgroup:1; /* pathgroup is set up */
unsigned int mpath:1; /* multipathing is set up */
unsigned int pgid_unknown:1;/* unknown pgid state */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index ef738b42a092..2758d05a802d 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -1,11 +1,12 @@
// SPDX-License-Identifier: GPL-2.0+
/*
- * Copyright IBM Corp. 2006, 2012
+ * Copyright IBM Corp. 2006, 2020
* Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
* Martin Schwidefsky <schwidefsky@de.ibm.com>
* Ralph Wuerthner <rwuerthn@de.ibm.com>
* Felix Beck <felix.beck@de.ibm.com>
* Holger Dengler <hd@linux.vnet.ibm.com>
+ * Harald Freudenberger <freude@linux.ibm.com>
*
* Adjunct processor bus.
*/
@@ -73,6 +74,12 @@ EXPORT_SYMBOL(ap_perms);
DEFINE_MUTEX(ap_perms_mutex);
EXPORT_SYMBOL(ap_perms_mutex);
+/* # of bus scans since init */
+static atomic64_t ap_scan_bus_count;
+
+/* completion for initial APQN bindings complete */
+static DECLARE_COMPLETION(ap_init_apqn_bindings_complete);
+
static struct ap_config_info *ap_qci_info;
/*
@@ -577,23 +584,125 @@ static int ap_bus_match(struct device *dev, struct device_driver *drv)
*/
static int ap_uevent(struct device *dev, struct kobj_uevent_env *env)
{
+ int rc;
struct ap_device *ap_dev = to_ap_dev(dev);
- int retval = 0;
- if (!ap_dev)
- return -ENODEV;
+ /* Uevents from ap bus core don't need extensions to the env */
+ if (dev == ap_root_device)
+ return 0;
/* Set up DEV_TYPE environment variable. */
- retval = add_uevent_var(env, "DEV_TYPE=%04X", ap_dev->device_type);
- if (retval)
- return retval;
+ rc = add_uevent_var(env, "DEV_TYPE=%04X", ap_dev->device_type);
+ if (rc)
+ return rc;
/* Add MODALIAS= */
- retval = add_uevent_var(env, "MODALIAS=ap:t%02X", ap_dev->device_type);
+ rc = add_uevent_var(env, "MODALIAS=ap:t%02X", ap_dev->device_type);
+ if (rc)
+ return rc;
+
+ return 0;
+}
+
+static void ap_send_init_scan_done_uevent(void)
+{
+ char *envp[] = { "INITSCAN=done", NULL };
- return retval;
+ kobject_uevent_env(&ap_root_device->kobj, KOBJ_CHANGE, envp);
}
+static void ap_send_bindings_complete_uevent(void)
+{
+ char *envp[] = { "BINDINGS=complete", NULL };
+
+ kobject_uevent_env(&ap_root_device->kobj, KOBJ_CHANGE, envp);
+}
+
+/*
+ * calc # of bound APQNs
+ */
+
+struct __ap_calc_ctrs {
+ unsigned int apqns;
+ unsigned int bound;
+};
+
+static int __ap_calc_helper(struct device *dev, void *arg)
+{
+ struct __ap_calc_ctrs *pctrs = (struct __ap_calc_ctrs *) arg;
+
+ if (is_queue_dev(dev)) {
+ pctrs->apqns++;
+ if ((to_ap_dev(dev))->drv)
+ pctrs->bound++;
+ }
+
+ return 0;
+}
+
+static void ap_calc_bound_apqns(unsigned int *apqns, unsigned int *bound)
+{
+ struct __ap_calc_ctrs ctrs;
+
+ memset(&ctrs, 0, sizeof(ctrs));
+ bus_for_each_dev(&ap_bus_type, NULL, (void *) &ctrs, __ap_calc_helper);
+
+ *apqns = ctrs.apqns;
+ *bound = ctrs.bound;
+}
+
+/*
+ * After initial ap bus scan do check if all existing APQNs are
+ * bound to device drivers.
+ */
+static void ap_check_bindings_complete(void)
+{
+ unsigned int apqns, bound;
+
+ if (atomic64_read(&ap_scan_bus_count) >= 1) {
+ ap_calc_bound_apqns(&apqns, &bound);
+ if (bound == apqns) {
+ if (!completion_done(&ap_init_apqn_bindings_complete)) {
+ complete_all(&ap_init_apqn_bindings_complete);
+ AP_DBF(DBF_INFO, "%s complete\n", __func__);
+ }
+ ap_send_bindings_complete_uevent();
+ }
+ }
+}
+
+/*
+ * Interface to wait for the AP bus to have done one initial ap bus
+ * scan and all detected APQNs have been bound to device drivers.
+ * If these both conditions are not fulfilled, this function blocks
+ * on a condition with wait_for_completion_interruptible_timeout().
+ * If these both conditions are fulfilled (before the timeout hits)
+ * the return value is 0. If the timeout (in jiffies) hits instead
+ * -ETIME is returned. On failures negative return values are
+ * returned to the caller.
+ */
+int ap_wait_init_apqn_bindings_complete(unsigned long timeout)
+{
+ long l;
+
+ if (completion_done(&ap_init_apqn_bindings_complete))
+ return 0;
+
+ if (timeout)
+ l = wait_for_completion_interruptible_timeout(
+ &ap_init_apqn_bindings_complete, timeout);
+ else
+ l = wait_for_completion_interruptible(
+ &ap_init_apqn_bindings_complete);
+ if (l < 0)
+ return l == -ERESTARTSYS ? -EINTR : l;
+ else if (l == 0 && timeout)
+ return -ETIME;
+
+ return 0;
+}
+EXPORT_SYMBOL(ap_wait_init_apqn_bindings_complete);
+
static int __ap_queue_devices_with_id_unregister(struct device *dev, void *data)
{
if (is_queue_dev(dev) &&
@@ -602,12 +711,6 @@ static int __ap_queue_devices_with_id_unregister(struct device *dev, void *data)
return 0;
}
-static struct bus_type ap_bus_type = {
- .name = "ap",
- .match = &ap_bus_match,
- .uevent = &ap_uevent,
-};
-
static int __ap_revise_reserved(struct device *dev, void *dummy)
{
int rc, card, queue, devres, drvres;
@@ -719,7 +822,8 @@ static int ap_device_probe(struct device *dev)
hash_del(&to_ap_queue(dev)->hnode);
spin_unlock_bh(&ap_queues_lock);
ap_dev->drv = NULL;
- }
+ } else
+ ap_check_bindings_complete();
out:
if (rc)
@@ -749,6 +853,7 @@ static int ap_device_remove(struct device *dev)
if (is_queue_dev(dev))
hash_del(&to_ap_queue(dev)->hnode);
spin_unlock_bh(&ap_queues_lock);
+ ap_dev->drv = NULL;
put_device(dev);
@@ -1166,21 +1271,55 @@ static ssize_t aqmask_store(struct bus_type *bus, const char *buf,
static BUS_ATTR_RW(aqmask);
-static struct bus_attribute *const ap_bus_attrs[] = {
- &bus_attr_ap_domain,
- &bus_attr_ap_control_domain_mask,
- &bus_attr_ap_usage_domain_mask,
- &bus_attr_ap_adapter_mask,
- &bus_attr_config_time,
- &bus_attr_poll_thread,
- &bus_attr_ap_interrupts,
- &bus_attr_poll_timeout,
- &bus_attr_ap_max_domain_id,
- &bus_attr_ap_max_adapter_id,
- &bus_attr_apmask,
- &bus_attr_aqmask,
+static ssize_t scans_show(struct bus_type *bus, char *buf)
+{
+ return scnprintf(buf, PAGE_SIZE, "%llu\n",
+ atomic64_read(&ap_scan_bus_count));
+}
+
+static BUS_ATTR_RO(scans);
+
+static ssize_t bindings_show(struct bus_type *bus, char *buf)
+{
+ int rc;
+ unsigned int apqns, n;
+
+ ap_calc_bound_apqns(&apqns, &n);
+ if (atomic64_read(&ap_scan_bus_count) >= 1 && n == apqns)
+ rc = scnprintf(buf, PAGE_SIZE, "%u/%u (complete)\n", n, apqns);
+ else
+ rc = scnprintf(buf, PAGE_SIZE, "%u/%u\n", n, apqns);
+
+ return rc;
+}
+
+static BUS_ATTR_RO(bindings);
+
+static struct attribute *ap_bus_attrs[] = {
+ &bus_attr_ap_domain.attr,
+ &bus_attr_ap_control_domain_mask.attr,
+ &bus_attr_ap_usage_domain_mask.attr,
+ &bus_attr_ap_adapter_mask.attr,
+ &bus_attr_config_time.attr,
+ &bus_attr_poll_thread.attr,
+ &bus_attr_ap_interrupts.attr,
+ &bus_attr_poll_timeout.attr,
+ &bus_attr_ap_max_domain_id.attr,
+ &bus_attr_ap_max_adapter_id.attr,
+ &bus_attr_apmask.attr,
+ &bus_attr_aqmask.attr,
+ &bus_attr_scans.attr,
+ &bus_attr_bindings.attr,
NULL,
};
+ATTRIBUTE_GROUPS(ap_bus);
+
+static struct bus_type ap_bus_type = {
+ .name = "ap",
+ .bus_groups = ap_bus_groups,
+ .match = &ap_bus_match,
+ .uevent = &ap_uevent,
+};
/**
* ap_select_domain(): Select an AP domain if possible and we haven't
@@ -1608,6 +1747,12 @@ static void ap_scan_bus(struct work_struct *unused)
ap_domain_index);
}
+ if (atomic64_inc_return(&ap_scan_bus_count) == 1) {
+ AP_DBF(DBF_DEBUG, "%s init scan complete\n", __func__);
+ ap_send_init_scan_done_uevent();
+ ap_check_bindings_complete();
+ }
+
mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ);
}
@@ -1655,7 +1800,7 @@ static void __init ap_perms_init(void)
*/
static int __init ap_module_init(void)
{
- int rc, i;
+ int rc;
rc = ap_debug_init();
if (rc)
@@ -1694,17 +1839,13 @@ static int __init ap_module_init(void)
rc = bus_register(&ap_bus_type);
if (rc)
goto out;
- for (i = 0; ap_bus_attrs[i]; i++) {
- rc = bus_create_file(&ap_bus_type, ap_bus_attrs[i]);
- if (rc)
- goto out_bus;
- }
/* Create /sys/devices/ap. */
ap_root_device = root_device_register("ap");
rc = PTR_ERR_OR_ZERO(ap_root_device);
if (rc)
goto out_bus;
+ ap_root_device->bus = &ap_bus_type;
/* Setup the AP bus rescan timer. */
timer_setup(&ap_config_timer, ap_config_timeout, 0);
@@ -1733,8 +1874,6 @@ out_work:
hrtimer_cancel(&ap_poll_timer);
root_device_unregister(ap_root_device);
out_bus:
- while (i--)
- bus_remove_file(&ap_bus_type, ap_bus_attrs[i]);
bus_unregister(&ap_bus_type);
out:
if (ap_using_interrupts())
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 5029b80132aa..472efd3a755c 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -350,4 +350,16 @@ int ap_parse_mask_str(const char *str,
unsigned long *bitmap, int bits,
struct mutex *lock);
+/*
+ * Interface to wait for the AP bus to have done one initial ap bus
+ * scan and all detected APQNs have been bound to device drivers.
+ * If these both conditions are not fulfilled, this function blocks
+ * on a condition with wait_for_completion_killable_timeout().
+ * If these both conditions are fulfilled (before the timeout hits)
+ * the return value is 0. If the timeout (in jiffies) hits instead
+ * -ETIME is returned. On failures negative return values are
+ * returned to the caller.
+ */
+int ap_wait_init_apqn_bindings_complete(unsigned long timeout);
+
#endif /* _AP_BUS_H_ */
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index dd84995049b9..cf23ce1b1146 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -150,6 +150,8 @@ static int pkey_skey2pkey(const u8 *key, struct pkey_protkey *pkey)
u16 cardnr, domain;
struct keytoken_header *hdr = (struct keytoken_header *)key;
+ zcrypt_wait_api_operational();
+
/*
* The cca_xxx2protkey call may fail when a card has been
* addressed where the master key was changed after last fetch
@@ -197,6 +199,8 @@ static int pkey_clr2ep11key(const u8 *clrkey, size_t clrkeylen,
u16 card, dom;
u32 nr_apqns, *apqns = NULL;
+ zcrypt_wait_api_operational();
+
/* build a list of apqns suitable for ep11 keys with cpacf support */
rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
ZCRYPT_CEX7, EP11_API_V, NULL);
@@ -230,6 +234,8 @@ static int pkey_ep11key2pkey(const u8 *key, struct pkey_protkey *pkey)
u32 nr_apqns, *apqns = NULL;
struct ep11keyblob *kb = (struct ep11keyblob *) key;
+ zcrypt_wait_api_operational();
+
/* build a list of apqns suitable for this key */
rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF,
ZCRYPT_CEX7, EP11_API_V, kb->wkvp);
@@ -436,6 +442,7 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen,
if (rc == 0)
break;
/* PCKMO failed, so try the CCA secure key way */
+ zcrypt_wait_api_operational();
rc = cca_clr2seckey(0xFFFF, 0xFFFF, t->keytype,
ckey.clrkey, tmpbuf);
if (rc == 0)
@@ -625,6 +632,8 @@ static int pkey_clr2seckey2(const struct pkey_apqn *apqns, size_t nr_apqns,
return -EINVAL;
}
+ zcrypt_wait_api_operational();
+
/* simple try all apqns from the list */
for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
card = apqns[i].card;
@@ -801,6 +810,8 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns,
return -EINVAL;
}
+ zcrypt_wait_api_operational();
+
/* simple try all apqns from the list */
for (i = 0, rc = -ENODEV; i < nr_apqns; i++) {
card = apqns[i].card;
@@ -838,6 +849,8 @@ static int pkey_apqns4key(const u8 *key, size_t keylen, u32 flags,
if (keylen < sizeof(struct keytoken_header) || flags == 0)
return -EINVAL;
+ zcrypt_wait_api_operational();
+
if (hdr->type == TOKTYPE_NON_CCA
&& (hdr->version == TOKVER_EP11_AES_WITH_HEADER
|| hdr->version == TOKVER_EP11_ECC_WITH_HEADER)
@@ -941,6 +954,8 @@ static int pkey_apqns4keytype(enum pkey_key_type ktype,
int rc;
u32 _nr_apqns, *_apqns = NULL;
+ zcrypt_wait_api_operational();
+
if (ktype == PKEY_TYPE_CCA_DATA || ktype == PKEY_TYPE_CCA_CIPHER) {
u64 cur_mkvp = 0, old_mkvp = 0;
int minhwtype = ZCRYPT_CEX3C;
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index f60f9fb25214..10206e4498d0 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -1992,6 +1992,72 @@ void zcrypt_rng_device_remove(void)
mutex_unlock(&zcrypt_rng_mutex);
}
+/*
+ * Wait until the zcrypt api is operational.
+ * The AP bus scan and the binding of ap devices to device drivers is
+ * an asynchronous job. This function waits until these initial jobs
+ * are done and so the zcrypt api should be ready to serve crypto
+ * requests - if there are resources available. The function uses an
+ * internal timeout of 60s. The very first caller will either wait for
+ * ap bus bindings complete or the timeout happens. This state will be
+ * remembered for further callers which will only be blocked until a
+ * decision is made (timeout or bindings complete).
+ * On timeout -ETIME is returned, on success the return value is 0.
+ */
+int zcrypt_wait_api_operational(void)
+{
+ static DEFINE_MUTEX(zcrypt_wait_api_lock);
+ static int zcrypt_wait_api_state;
+ int rc;
+
+ rc = mutex_lock_interruptible(&zcrypt_wait_api_lock);
+ if (rc)
+ return rc;
+
+ switch (zcrypt_wait_api_state) {
+ case 0:
+ /* initial state, invoke wait for the ap bus complete */
+ rc = ap_wait_init_apqn_bindings_complete(
+ msecs_to_jiffies(60 * 1000));
+ switch (rc) {
+ case 0:
+ /* ap bus bindings are complete */
+ zcrypt_wait_api_state = 1;
+ break;
+ case -EINTR:
+ /* interrupted, go back to caller */
+ break;
+ case -ETIME:
+ /* timeout */
+ ZCRYPT_DBF(DBF_WARN,
+ "%s ap_wait_init_apqn_bindings_complete() returned with ETIME\n",
+ __func__);
+ zcrypt_wait_api_state = -ETIME;
+ break;
+ default:
+ /* other failure */
+ ZCRYPT_DBF(DBF_DEBUG,
+ "%s ap_wait_init_apqn_bindings_complete() failure rc=%d\n",
+ __func__, rc);
+ break;
+ }
+ break;
+ case 1:
+ /* a previous caller already found ap bus bindings complete */
+ rc = 0;
+ break;
+ default:
+ /* a previous caller had timeout or other failure */
+ rc = zcrypt_wait_api_state;
+ break;
+ }
+
+ mutex_unlock(&zcrypt_wait_api_lock);
+
+ return rc;
+}
+EXPORT_SYMBOL(zcrypt_wait_api_operational);
+
int __init zcrypt_debug_init(void)
{
zcrypt_dbf_info = debug_register("zcrypt", 1, 1,
diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h
index 51c0b8bdef50..16219efb2f61 100644
--- a/drivers/s390/crypto/zcrypt_api.h
+++ b/drivers/s390/crypto/zcrypt_api.h
@@ -162,6 +162,8 @@ void zcrypt_device_status_mask_ext(struct zcrypt_device_status_ext *devstatus);
int zcrypt_device_status_ext(int card, int queue,
struct zcrypt_device_status_ext *devstatus);
+int zcrypt_wait_api_operational(void);
+
static inline unsigned long z_copy_from_user(bool userspace,
void *to,
const void __user *from,
diff --git a/drivers/s390/scsi/zfcp_ccw.c b/drivers/s390/scsi/zfcp_ccw.c
index d9fd0a41da64..bdf2cc1ea713 100644
--- a/drivers/s390/scsi/zfcp_ccw.c
+++ b/drivers/s390/scsi/zfcp_ccw.c
@@ -194,23 +194,21 @@ static int zfcp_ccw_set_online(struct ccw_device *cdev)
}
/**
- * zfcp_ccw_offline_sync - shut down adapter and wait for it to finish
+ * zfcp_ccw_set_offline - set_offline function of zfcp driver
* @cdev: pointer to belonging ccw device
- * @set: Status flags to set.
- * @tag: s390dbf trace record tag
*
* This function gets called by the common i/o layer and sets an adapter
* into state offline.
*/
-static int zfcp_ccw_offline_sync(struct ccw_device *cdev, int set, char *tag)
+static int zfcp_ccw_set_offline(struct ccw_device *cdev)
{
struct zfcp_adapter *adapter = zfcp_ccw_adapter_by_cdev(cdev);
if (!adapter)
return 0;
- zfcp_erp_set_adapter_status(adapter, set);
- zfcp_erp_adapter_shutdown(adapter, 0, tag);
+ zfcp_erp_set_adapter_status(adapter, 0);
+ zfcp_erp_adapter_shutdown(adapter, 0, "ccsoff1");
zfcp_erp_wait(adapter);
zfcp_ccw_adapter_put(adapter);
@@ -218,18 +216,6 @@ static int zfcp_ccw_offline_sync(struct ccw_device *cdev, int set, char *tag)
}
/**
- * zfcp_ccw_set_offline - set_offline function of zfcp driver
- * @cdev: pointer to belonging ccw device
- *
- * This function gets called by the common i/o layer and sets an adapter
- * into state offline.
- */
-static int zfcp_ccw_set_offline(struct ccw_device *cdev)
-{
- return zfcp_ccw_offline_sync(cdev, 0, "ccsoff1");
-}
-
-/**
* zfcp_ccw_notify - ccw notify function
* @cdev: pointer to belonging ccw device
* @event: indicates if adapter was detached or attached
@@ -246,11 +232,6 @@ static int zfcp_ccw_notify(struct ccw_device *cdev, int event)
switch (event) {
case CIO_GONE:
- if (atomic_read(&adapter->status) &
- ZFCP_STATUS_ADAPTER_SUSPENDED) { /* notification ignore */
- zfcp_dbf_hba_basic("ccnigo1", adapter);
- break;
- }
dev_warn(&cdev->dev, "The FCP device has been detached\n");
zfcp_erp_adapter_shutdown(adapter, 0, "ccnoti1");
break;
@@ -260,11 +241,6 @@ static int zfcp_ccw_notify(struct ccw_device *cdev, int event)
zfcp_erp_adapter_shutdown(adapter, 0, "ccnoti2");
break;
case CIO_OPER:
- if (atomic_read(&adapter->status) &
- ZFCP_STATUS_ADAPTER_SUSPENDED) { /* notification ignore */
- zfcp_dbf_hba_basic("ccniop1", adapter);
- break;
- }
dev_info(&cdev->dev, "The FCP device is operational again\n");
zfcp_erp_set_adapter_status(adapter,
ZFCP_STATUS_COMMON_RUNNING);
@@ -300,28 +276,6 @@ static void zfcp_ccw_shutdown(struct ccw_device *cdev)
zfcp_ccw_adapter_put(adapter);
}
-static int zfcp_ccw_suspend(struct ccw_device *cdev)
-{
- zfcp_ccw_offline_sync(cdev, ZFCP_STATUS_ADAPTER_SUSPENDED, "ccsusp1");
- return 0;
-}
-
-static int zfcp_ccw_thaw(struct ccw_device *cdev)
-{
- /* trace records for thaw and final shutdown during suspend
- can only be found in system dump until the end of suspend
- but not after resume because it's based on the memory image
- right after the very first suspend (freeze) callback */
- zfcp_ccw_activate(cdev, 0, "ccthaw1");
- return 0;
-}
-
-static int zfcp_ccw_resume(struct ccw_device *cdev)
-{
- zfcp_ccw_activate(cdev, ZFCP_STATUS_ADAPTER_SUSPENDED, "ccresu1");
- return 0;
-}
-
struct ccw_driver zfcp_ccw_driver = {
.driver = {
.owner = THIS_MODULE,
@@ -334,7 +288,4 @@ struct ccw_driver zfcp_ccw_driver = {
.set_offline = zfcp_ccw_set_offline,
.notify = zfcp_ccw_notify,
.shutdown = zfcp_ccw_shutdown,
- .freeze = zfcp_ccw_suspend,
- .thaw = zfcp_ccw_thaw,
- .restore = zfcp_ccw_resume,
};
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 673e42defb91..ca473b368905 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -263,31 +263,6 @@ void zfcp_dbf_hba_def_err(struct zfcp_adapter *adapter, u64 req_id, u16 scount,
spin_unlock_irqrestore(&dbf->pay_lock, flags);
}
-/**
- * zfcp_dbf_hba_basic - trace event for basic adapter events
- * @tag: identifier for event
- * @adapter: pointer to struct zfcp_adapter
- */
-void zfcp_dbf_hba_basic(char *tag, struct zfcp_adapter *adapter)
-{
- struct zfcp_dbf *dbf = adapter->dbf;
- struct zfcp_dbf_hba *rec = &dbf->hba_buf;
- static int const level = 1;
- unsigned long flags;
-
- if (unlikely(!debug_level_enabled(dbf->hba, level)))
- return;
-
- spin_lock_irqsave(&dbf->hba_lock, flags);
- memset(rec, 0, sizeof(*rec));
-
- memcpy(rec->tag, tag, ZFCP_DBF_TAG_LEN);
- rec->id = ZFCP_DBF_HBA_BASIC;
-
- debug_event(dbf->hba, level, rec, sizeof(*rec));
- spin_unlock_irqrestore(&dbf->hba_lock, flags);
-}
-
static void zfcp_dbf_set_common(struct zfcp_dbf_rec *rec,
struct zfcp_adapter *adapter,
struct zfcp_port *port,
diff --git a/drivers/s390/scsi/zfcp_def.h b/drivers/s390/scsi/zfcp_def.h
index da8a5ceb615c..5069b555c6c1 100644
--- a/drivers/s390/scsi/zfcp_def.h
+++ b/drivers/s390/scsi/zfcp_def.h
@@ -70,7 +70,6 @@
#define ZFCP_STATUS_ADAPTER_SIOSL_ISSUED 0x00000004
#define ZFCP_STATUS_ADAPTER_XCONFIG_OK 0x00000008
#define ZFCP_STATUS_ADAPTER_HOST_CON_INIT 0x00000010
-#define ZFCP_STATUS_ADAPTER_SUSPENDED 0x00000040
#define ZFCP_STATUS_ADAPTER_ERP_PENDING 0x00000100
#define ZFCP_STATUS_ADAPTER_LINK_UNPLUGGED 0x00000200
#define ZFCP_STATUS_ADAPTER_DATA_DIV_ENABLED 0x00000400
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index 3ef5d74331c3..fdac6350c579 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -49,7 +49,6 @@ extern void zfcp_dbf_hba_fsf_fces(char *tag, const struct zfcp_fsf_req *req,
u32 fc_security_new);
extern void zfcp_dbf_hba_bit_err(char *, struct zfcp_fsf_req *);
extern void zfcp_dbf_hba_def_err(struct zfcp_adapter *, u64, u16, void **);
-extern void zfcp_dbf_hba_basic(char *, struct zfcp_adapter *);
extern void zfcp_dbf_san_req(char *, struct zfcp_fsf_req *, u32);
extern void zfcp_dbf_san_res(char *, struct zfcp_fsf_req *);
extern void zfcp_dbf_san_in_els(char *, struct zfcp_fsf_req *);
diff --git a/init/Kconfig b/init/Kconfig
index 0872a5a2e759..b77c60f8b963 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -114,7 +114,7 @@ config INIT_ENV_ARG_LIMIT
config COMPILE_TEST
bool "Compile also drivers which will not load"
- depends on !UML
+ depends on !UML && !S390
default n
help
Some drivers can be compiled on a different platform than they are
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 542a9c18398e..8fb097057fec 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -136,15 +136,6 @@ config KASAN_STACK
default 1 if KASAN_STACK_ENABLE || CC_IS_GCC
default 0
-config KASAN_S390_4_LEVEL_PAGING
- bool "KASan: use 4-level paging"
- depends on S390
- help
- Compiling the kernel with KASan disables automatic 3-level vs
- 4-level paging selection. 3-level paging is used by default (up
- to 3TB of RAM with KASan enabled). This options allows to force
- 4-level paging instead.
-
config KASAN_SW_TAGS_IDENTIFY
bool "Enable memory corruption identification"
depends on KASAN_SW_TAGS
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 3f77a5d695c1..56c801502b9a 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -254,9 +254,6 @@ if ($arch eq "x86_64") {
if ($cc =~ /-DCC_USING_HOTPATCH/) {
$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*brcl\\s*0,[0-9a-f]+ <([^\+]*)>\$";
$mcount_adjust = 0;
- } else {
- $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";
- $mcount_adjust = -14;
}
$alignment = 8;
$type = ".quad";